2589 files changed, 99078 insertions, 16943 deletions

diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index f1c5cc9d17a8..4c3efe434806 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -23,7 +23,7 @@ Description:
 				 [fowner]]
 			lsm:	[[subj_user=] [subj_role=] [subj_type=]
 				 [obj_user=] [obj_role=] [obj_type=]]
-			option:	[[appraise_type=]]
+			option:	[[appraise_type=]] [permit_directio]
 
 		base: 	func:= [BPRM_CHECK][MMAP_CHECK][FILE_CHECK][MODULE_CHECK]
 			mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC]
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index f9fd615427fb..1d27f0a1abd1 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -195,7 +195,7 @@ DVB_DOCUMENTED = \
 #
 
 install_media_images = \
-	$(Q)cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)-cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 26b1e31d5a13..1ec219a14904 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -119,6 +119,20 @@ Example:
 	platform_set_drvdata(), but left the variable "dev" unused,
 	delete it.
 
+If your patch fixes a bug in a specific commit, e.g. you found an issue using
+git-bisect, please use the 'Fixes:' tag with the first 12 characters of the
+SHA-1 ID, and the one line summary.
+Example:
+
+	Fixes: e21d2170f366 ("video: remove unnecessary platform_set_drvdata()")
+
+The following git-config settings can be used to add a pretty format for
+outputting the above style in the git log or git show commands
+
+	[core]
+		abbrev = 12
+	[pretty]
+		fixes = Fixes: %h (\"%s\")
 
 3) Separate your changes.
 
@@ -430,7 +444,7 @@ person it names.  This tag documents that potentially interested parties
 have been included in the discussion
 
 
-14) Using Reported-by:, Tested-by:, Reviewed-by: and Suggested-by:
+14) Using Reported-by:, Tested-by:, Reviewed-by:, Suggested-by: and Fixes:
 
 If this patch fixes a problem reported by somebody else, consider adding a
 Reported-by: tag to credit the reporter for their contribution.  Please
@@ -485,6 +499,12 @@ idea was not posted in a public forum. That said, if we diligently credit our
 idea reporters, they will, hopefully, be inspired to help us again in the
 future.
 
+A Fixes: tag indicates that the patch fixes an issue in a previous commit. It
+is used to make it easy to determine where a bug originated, which can help
+review a bug fix. This tag also assists the stable kernel team in determining
+which stable kernel versions should receive your fix. This is the preferred
+method for indicating a bug fixed by the patch. See #2 above for more details.
+
 
 15) The canonical patch format
 
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index a9691cc48fe3..beb754e87c65 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -111,8 +111,14 @@ Before jumping into the kernel, the following conditions must be met:
 - Caches, MMUs
   The MMU must be off.
   Instruction cache may be on or off.
-  Data cache must be off and invalidated.
-  External caches (if present) must be configured and disabled.
+  The address range corresponding to the loaded kernel image must be
+  cleaned to the PoC. In the presence of a system cache or other
+  coherent masters with caches enabled, this will typically require
+  cache maintenance by VA rather than set/way operations.
+  System caches which respect the architected cache maintenance by VA
+  operations must be configured and may be enabled.
+  System caches which do not respect architected cache maintenance by VA
+  operations (not recommended) must be configured and disabled.
 
 - Architected timers
   CNTFRQ must be programmed with the timer frequency and CNTVOFF must
diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index 5e054bfe4dde..1b84f2b7e65a 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -35,7 +35,11 @@ ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
 
 ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
 
-ffffffbffbc00000	ffffffbffbdfffff	   2MB		earlyprintk device
+ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
+
+ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
+
+ffffffbffbc00000	ffffffbffbdfffff	   2MB		fixed mappings
 
 ffffffbffbe00000	ffffffbffbe0ffff	  64KB		PCI I/O space
 
@@ -60,7 +64,11 @@ fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
 
 fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
 
-fffffdfffbc00000	fffffdfffbdfffff	   2MB		earlyprintk device
+fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
+
+fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
+
+fffffdfffbc00000	fffffdfffbdfffff	   2MB		fixed mappings
 
 fffffdfffbe00000	fffffdfffbe0ffff	  64KB		PCI I/O space
 
diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt
index e742d21dbd96..a69ffe1d54d5 100644
--- a/Documentation/cpu-freq/intel-pstate.txt
+++ b/Documentation/cpu-freq/intel-pstate.txt
@@ -15,10 +15,13 @@ New sysfs files for controlling P state selection have been added to
 /sys/devices/system/cpu/intel_pstate/
 
       max_perf_pct: limits the maximum P state that will be requested by
-      the driver stated as a percentage of the available performance.
+      the driver stated as a percentage of the available performance. The
+      available (P states) performance may be reduced by the no_turbo
+      setting described below.
 
       min_perf_pct: limits the minimum P state that will be  requested by
-      the driver stated as a percentage of the available performance.
+      the driver stated as a percentage of the max (non-turbo)
+      performance level.
 
       no_turbo: limits the driver to selecting P states below the turbo
       frequency range.
diff --git a/Documentation/debugging-via-ohci1394.txt b/Documentation/debugging-via-ohci1394.txt
index fa0151a712f9..5c9a567b3fac 100644
--- a/Documentation/debugging-via-ohci1394.txt
+++ b/Documentation/debugging-via-ohci1394.txt
@@ -25,9 +25,11 @@ using data transfer rates in the order of 10MB/s or more.
 With most FireWire controllers, memory access is limited to the low 4 GB
 of physical address space.  This can be a problem on IA64 machines where
 memory is located mostly above that limit, but it is rarely a problem on
-more common hardware such as x86, x86-64 and PowerPC.  However, at least
-Agere/LSI FW643e and FW643e2 controllers are known to support access to
-physical addresses above 4 GB.
+more common hardware such as x86, x86-64 and PowerPC.
+
+At least LSI FW643e and FW643e2 controllers are known to support access to
+physical addresses above 4 GB, but this feature is currently not enabled by
+Linux.
 
 Together with a early initialization of the OHCI-1394 controller for debugging,
 this facility proved most useful for examining long debugs logs in the printk
@@ -101,8 +103,9 @@ Step-by-step instructions for using firescope with early OHCI initialization:
    compliant, they are based on TI PCILynx chips and require drivers for Win-
    dows operating systems.
 
-   The mentioned kernel log message contains ">4 GB phys DMA" in case of
-   OHCI-1394 controllers which support accesses above this limit.
+   The mentioned kernel log message contains the string "physUB" if the
+   controller implements a writable Physical Upper Bound register.  This is
+   required for physical DMA above 4 GB (but not utilized by Linux yet).
 
 2) Establish a working FireWire cable connection:
 
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 05a27e9442bd..2f5173500bd9 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -309,7 +309,10 @@ ii) Status
     error_if_no_space|queue_if_no_space
 	If the pool runs out of data or metadata space, the pool will
 	either queue or error the IO destined to the data device.  The
-	default is to queue the IO until more space is added.
+	default is to queue the IO until more space is added or the
+	'no_space_timeout' expires.  The 'no_space_timeout' dm-thin-pool
+	module parameter can be used to change this timeout -- it
+	defaults to 60 seconds but may be disabled using a value of 0.
 
 iii) Messages
 
diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt
new file mode 100644
index 000000000000..d790f49066f3
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/coresight.txt
@@ -0,0 +1,204 @@
+* CoreSight Components:
+
+CoreSight components are compliant with the ARM CoreSight architecture
+specification and can be connected in various topologies to suit a particular
+SoCs tracing needs. These trace components can generally be classified as
+sinks, links and sources. Trace data produced by one or more sources flows
+through the intermediate links connecting the source to the currently selected
+sink. Each CoreSight component device should use these properties to describe
+its hardware characteristcs.
+
+* Required properties for all components *except* non-configurable replicators:
+
+	* compatible: These have to be supplemented with "arm,primecell" as
+	  drivers are using the AMBA bus interface.  Possible values include:
+		- "arm,coresight-etb10", "arm,primecell";
+		- "arm,coresight-tpiu", "arm,primecell";
+		- "arm,coresight-tmc", "arm,primecell";
+		- "arm,coresight-funnel", "arm,primecell";
+		- "arm,coresight-etm3x", "arm,primecell";
+
+	* reg: physical base address and length of the register
+	  set(s) of the component.
+
+	* clocks: the clock associated to this component.
+
+	* clock-names: the name of the clock as referenced by the code.
+	  Since we are using the AMBA framework, the name should be
+	  "apb_pclk".
+
+	* port or ports: The representation of the component's port
+	  layout using the generic DT graph presentation found in
+	  "bindings/graph.txt".
+
+* Required properties for devices that don't show up on the AMBA bus, such as
+  non-configurable replicators:
+
+	* compatible: Currently supported value is (note the absence of the
+	  AMBA markee):
+		- "arm,coresight-replicator"
+
+	* id: a unique number that will identify this replicator.
+
+	* port or ports: same as above.
+
+* Optional properties for ETM/PTMs:
+
+	* arm,cp14: must be present if the system accesses ETM/PTM management
+	  registers via co-processor 14.
+
+	* cpu: the cpu phandle this ETM/PTM is affined to. When omitted the
+	  source is considered to belong to CPU0.
+
+* Optional property for TMC:
+
+	* arm,buffer-size: size of contiguous buffer space for TMC ETR
+	 (embedded trace router)
+
+
+Example:
+
+1. Sinks
+	etb@20010000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0x20010000 0 0x1000>;
+
+		coresight-default-sink;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			etb_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port0>;
+			};
+		};
+	};
+
+	tpiu@20030000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0x20030000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator_out_port1>;
+			};
+		};
+	};
+
+2. Links
+	replicator {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+		/* this will show up in debugfs as "0.replicator" */
+		id = <0>;
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator_out_port0: endpoint {
+					remote-endpoint = <&etb_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator_out_port1: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel_out_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@20040000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0x20040000 0 0x1000>;
+
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel_out_port0: endpoint {
+					remote-endpoint =
+							<&replicator_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm1_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&etm0_out_port>;
+				};
+			};
+
+		};
+	};
+
+3. Sources
+	ptm@2201c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201c000 0 0x1000>;
+
+		cpu = <&cpu0>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm0_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port0>;
+			};
+		};
+	};
+
+	ptm@2201d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0x2201d000 0 0x1000>;
+
+		cpu = <&cpu1>;
+		clocks = <&oscclk6a>;
+		clock-names = "apb_pclk";
+		port {
+			ptm1_out_port: endpoint {
+				remote-endpoint = <&funnel_in_port1>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/arm/gic.txt b/Documentation/devicetree/bindings/arm/gic.txt
index bae0d87a38b2..5573c08d3180 100644
--- a/Documentation/devicetree/bindings/arm/gic.txt
+++ b/Documentation/devicetree/bindings/arm/gic.txt
@@ -50,6 +50,11 @@ Optional
   regions, used when the GIC doesn't have banked registers. The offset is
   cpu-offset * cpu-nr.
 
+- arm,routable-irqs : Total number of gic irq inputs which are not directly
+		  connected from the peripherals, but are routed dynamically
+		  by a crossbar/multiplexer preceding the GIC. The GIC irq
+		  input line is assigned dynamically when the corresponding
+		  peripheral's crossbar line is mapped.
 Example:
 
 	intc: interrupt-controller@fff11000 {
@@ -57,6 +62,7 @@ Example:
 		#interrupt-cells = <3>;
 		#address-cells = <1>;
 		interrupt-controller;
+		arm,routable-irqs = <160>;
 		reg = <0xfff11000 0x1000>,
 		      <0xfff10100 0x100>;
 	};
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 3e1e498fea96..a2dbf67c1cb7 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -17,6 +17,9 @@ Required properties:
 	"arm,arm1176-pmu"
 	"arm,arm1136-pmu"
 - interrupts : 1 combined interrupt or 1 per core.
+- cluster : a phandle to the cluster to which it belongs
+	If there are more than one cluster with same CPU type
+	then there should be separate PMU nodes per cluster.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/ata/sata_rcar.txt b/Documentation/devicetree/bindings/ata/sata_rcar.txt
index 1e6111333fa8..7dd32d321a34 100644
--- a/Documentation/devicetree/bindings/ata/sata_rcar.txt
+++ b/Documentation/devicetree/bindings/ata/sata_rcar.txt
@@ -3,7 +3,8 @@
 Required properties:
 - compatible		: should contain one of the following:
 			  - "renesas,sata-r8a7779" for R-Car H1
-			  - "renesas,sata-r8a7790" for R-Car H2
+			  - "renesas,sata-r8a7790-es1" for R-Car H2 ES1
+			  - "renesas,sata-r8a7790" for R-Car H2 other than ES1
 			  - "renesas,sata-r8a7791" for R-Car M2
 - reg			: address and length of the SATA registers;
 - interrupts		: must consist of one interrupt specifier.
diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
index 9fbbdb783a72..68ff2137bae7 100644
--- a/Documentation/devicetree/bindings/dma/ti-edma.txt
+++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
@@ -29,6 +29,6 @@ edma: edma@49000000 {
 	dma-channels = <64>;
 	ti,edma-regions = <4>;
 	ti,edma-slots = <256>;
-	ti,edma-xbar-event-map = <1 12
-				  2 13>;
+	ti,edma-xbar-event-map = /bits/ 16 <1 12
+					    2 13>;
 };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
index 1486497a24c1..8a3c40829899 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
@@ -4,11 +4,13 @@ Specifying interrupt information for devices
 1) Interrupt client nodes
 -------------------------
 
-Nodes that describe devices which generate interrupts must contain an either an
-"interrupts" property or an "interrupts-extended" property. These properties
-contain a list of interrupt specifiers, one per output interrupt. The format of
-the interrupt specifier is determined by the interrupt controller to which the
-interrupts are routed; see section 2 below for details.
+Nodes that describe devices which generate interrupts must contain an
+"interrupts" property, an "interrupts-extended" property, or both. If both are
+present, the latter should take precedence; the former may be provided simply
+for compatibility with software that does not recognize the latter. These
+properties contain a list of interrupt specifiers, one per output interrupt. The
+format of the interrupt specifier is determined by the interrupt controller to
+which the interrupts are routed; see section 2 below for details.
 
   Example:
 	interrupt-parent = <&intc1>;
@@ -28,10 +30,6 @@ should only be used when a device has multiple interrupt parents.
   Example:
 	interrupts-extended = <&intc1 5 1>, <&intc2 1 0>;
 
-A device node may contain either "interrupts" or "interrupts-extended", but not
-both. If both properties are present, then the operating system should log an
-error and use only the data in "interrupts".
-
 2) Interrupt controller nodes
 -----------------------------
 
diff --git a/Documentation/devicetree/bindings/mailbox/mailbox.txt b/Documentation/devicetree/bindings/mailbox/mailbox.txt
new file mode 100644
index 000000000000..1a2cd3d266db
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/mailbox.txt
@@ -0,0 +1,38 @@
+* Generic Mailbox Controller and client driver bindings
+
+Generic binding to provide a way for Mailbox controller drivers to
+assign appropriate mailbox channel to client drivers.
+
+* Mailbox Controller
+
+Required property:
+- #mbox-cells: Must be at least 1. Number of cells in a mailbox
+		specifier.
+
+Example:
+	mailbox: mailbox {
+		...
+		#mbox-cells = <1>;
+	};
+
+
+* Mailbox Client
+
+Required property:
+- mboxes: List of phandle and mailbox channel specifiers.
+
+Optional property:
+- mbox-names: List of identifier strings for each mailbox channel
+		required by the client. The use of this property
+		is discouraged in favor of using index in list of
+		'mboxes' while requesting a mailbox. Instead the
+		platforms may define channel indices, in DT headers,
+		to something legible.
+
+Example:
+	pwr_cntrl: power {
+		...
+		mbox-names = "pwr-ctrl", "rpc";
+		mboxes = <&mailbox 0
+			&mailbox 1>;
+	};
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
new file mode 100644
index 000000000000..98c16672ab5f
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -0,0 +1,49 @@
+* Generic PM domains
+
+System on chip designs are often divided into multiple PM domains that can be
+used for power gating of selected IP blocks for power saving by reduced leakage
+current.
+
+This device tree binding can be used to bind PM domain consumer devices with
+their PM domains provided by PM domain providers. A PM domain provider can be
+represented by any node in the device tree and can provide one or more PM
+domains. A consumer node can refer to the provider by a phandle and a set of
+phandle arguments (so called PM domain specifiers) of length specified by the
+#power-domain-cells property in the PM domain provider node.
+
+==PM domain providers==
+
+Required properties:
+ - #power-domain-cells : Number of cells in a PM domain specifier;
+   Typically 0 for nodes representing a single PM domain and 1 for nodes
+   providing multiple PM domains (e.g. power controllers), but can be any value
+   as specified by device tree binding documentation of particular provider.
+
+Example:
+
+	power: power-controller@12340000 {
+		compatible = "foo,power-controller";
+		reg = <0x12340000 0x1000>;
+		#power-domain-cells = <1>;
+	};
+
+The node above defines a power controller that is a PM domain provider and
+expects one cell as its phandle argument.
+
+==PM domain consumers==
+
+Required properties:
+ - power-domains : A phandle and PM domain specifier as defined by bindings of
+                   the power controller specified by phandle.
+
+Example:
+
+	leaky-device@12350000 {
+		compatible = "foo,i-leak-current";
+		reg = <0x12350000 0x1000>;
+		power-domains = <&power 0>;
+	};
+
+The node above defines a typical PM domain consumer device, which is located
+inside a PM domain with index 0 of a power controller represented by a node
+with the label "power".
diff --git a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
index 46f344965313..4eb7997674a0 100644
--- a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
+++ b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
@@ -1,7 +1,7 @@
 ADI AXI-SPDIF controller
 
 Required properties:
- - compatible : Must be "adi,axi-spdif-1.00.a"
+ - compatible : Must be "adi,axi-spdif-tx-1.00.a"
  - reg : Must contain SPDIF core's registers location and length
  - clocks : Pairs of phandle and specifier referencing the controller's clocks.
    The controller expects two clocks, the clock used for the AXI interface and
diff --git a/Documentation/devicetree/bindings/spi/efm32-spi.txt b/Documentation/devicetree/bindings/spi/efm32-spi.txt
index a590ca51be75..f762e11bfe11 100644
--- a/Documentation/devicetree/bindings/spi/efm32-spi.txt
+++ b/Documentation/devicetree/bindings/spi/efm32-spi.txt
@@ -3,7 +3,7 @@
 Required properties:
 - #address-cells: see spi-bus.txt
 - #size-cells: see spi-bus.txt
-- compatible: should be "efm32,spi"
+- compatible: should be "energymicro,efm32-spi"
 - reg: Offset and length of the register set for the controller
 - interrupts: pair specifying rx and tx irq
 - clocks: phandle to the spi clock
@@ -15,7 +15,7 @@ Example:
 spi1: spi@0x4000c400 { /* USART1 */
 	#address-cells = <1>;
 	#size-cells = <0>;
-	compatible = "efm32,spi";
+	compatible = "energymicro,efm32-spi";
 	reg = <0x4000c400 0x400>;
 	interrupts = <15 16>;
 	clocks = <&cmu 20>;
diff --git a/Documentation/devicetree/bindings/usb/dwc3.txt b/Documentation/devicetree/bindings/usb/dwc3.txt
index e807635f9e1c..471366d6a129 100644
--- a/Documentation/devicetree/bindings/usb/dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/dwc3.txt
@@ -6,11 +6,13 @@ Required properties:
  - compatible: must be "snps,dwc3"
  - reg : Address and length of the register set for the device
  - interrupts: Interrupts used by the dwc3 controller.
+
+Optional properties:
  - usb-phy : array of phandle for the PHY device.  The first element
    in the array is expected to be a handle to the USB2/HS PHY and
    the second element is expected to be a handle to the USB3/SS PHY
-
-Optional properties:
+ - phys: from the *Generic PHY* bindings
+ - phy-names: from the *Generic PHY* bindings
  - tx-fifo-resize: determines if the FIFO *has* to be reallocated.
 
 This is usually a subnode to DWC3 glue to which it is connected.
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index 5752df0e17a2..98424d5363e6 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -6,6 +6,9 @@ Required properties:
     register set for the device.
   - interrupts: one XHCI interrupt should be described here.
 
+Optional properties:
+  - usb3-lpm-capable: determines if platform is USB3 LPM capable
+
 Example:
 	usb@f0931000 {
 		compatible = "xhci-platform";
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index aaaf069306a3..adf5e33e8312 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -26,6 +26,7 @@ Supported adapters:
   * Intel Wellsburg (PCH)
   * Intel Coleto Creek (PCH)
   * Intel Wildcat Point-LP (PCH)
+  * Intel BayTrail (SOC)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index 5602eb71ad5d..e1ae127ed099 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -504,9 +504,12 @@ byte 5:
 * reg_10
 
    bit   7   6   5   4   3   2   1   0
-         0   0   0   0   0   0   0   A
+         0   0   0   0   R   F   T   A
 
          A: 1 = enable absolute tracking
+         T: 1 = enable two finger mode auto correct
+         F: 1 = disable ABS Position Filter
+         R: 1 = enable real hardware resolution
 
 6.2 Native absolute mode 6 byte packet format
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 0091a8215ac1..b61885c35ce1 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -315,7 +315,7 @@ Andrew Morton ã�Œ Linux-kernel メーリングリストã�«ã‚«ãƒ¼ãƒ�ルリリーã
 も��3.x.y カー�ル�存在���場����番��一番大�� 3.x �
 最新�安定版カー�ル��。
 
-3.x.y � "stable" �ーム <stable@kernel.org> �メンテ�れ��り�必
+3.x.y � "stable" �ーム <stable@vger.kernel.org> �メンテ�れ��り�必
 ��応��リリース�れ��。通常�リリース期間� 2週間毎����差�迫�
 ��題���れ�も�少�長��る��も�り��。セキュリティ関連��題
 �場���れ�対�������場�����リリース��れ��。
diff --git a/Documentation/ja_JP/stable_kernel_rules.txt b/Documentation/ja_JP/stable_kernel_rules.txt
index 14265837c4ce..9dbda9b5d21e 100644
--- a/Documentation/ja_JP/stable_kernel_rules.txt
+++ b/Documentation/ja_JP/stable_kernel_rules.txt
@@ -50,16 +50,16 @@ linux-2.6.29/Documentation/stable_kernel_rules.txt
 
 -stable ツリー�パッ�を�付�る手続�-
 
- - 上記��則�従���る�を確���後��stable@kernel.org �パッ�
+ - 上記��則�従���る�を確���後��stable@vger.kernel.org �パッ�
    を�る。
  - �信者�パッ��キュー���付�られ�際�� ACK を��下�れ�場�
    �� NAK を���る。���応�開発者���スケジュール�よ���数
    日��る場���る。
  - も����られ�ら�パッ��他�開発者���関連�るサブシステム�
    メンテナー�よるレビュー���� -stable キュー�追加�れる。
- - パッ�� stable@kernel.org �アドレス�付加�れ��る������れ
+ - パッ�� stable@vger.kernel.org �アドレス�付加�れ��る������れ
    � Linus �ツリー�入る時�自動的� stable �ーム� email �れる。
- - セキュリティパッ����エイリアス (stable@kernel.org) ��られる�
+ - セキュリティパッ����エイリアス (stable@vger.kernel.org) ��られる�
    ������代�り� security@kernel.org �アドレス��られる。
 
 レビューサイクル-
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
new file mode 100644
index 000000000000..ea45dd3901e3
--- /dev/null
+++ b/Documentation/lzo.txt
@@ -0,0 +1,164 @@
+
+LZO stream format as understood by Linux's LZO decompressor
+===========================================================
+
+Introduction
+
+  This is not a specification. No specification seems to be publicly available
+  for the LZO stream format. This document describes what input format the LZO
+  decompressor as implemented in the Linux kernel understands. The file subject
+  of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on
+  the compressor nor on any other implementations though it seems likely that
+  the format matches the standard one. The purpose of this document is to
+  better understand what the code does in order to propose more efficient fixes
+  for future bug reports.
+
+Description
+
+  The stream is composed of a series of instructions, operands, and data. The
+  instructions consist in a few bits representing an opcode, and bits forming
+  the operands for the instruction, whose size and position depend on the
+  opcode and on the number of literals copied by previous instruction. The
+  operands are used to indicate :
+
+    - a distance when copying data from the dictionary (past output buffer)
+    - a length (number of bytes to copy from dictionary)
+    - the number of literals to copy, which is retained in variable "state"
+      as a piece of information for next instructions.
+
+  Optionally depending on the opcode and operands, extra data may follow. These
+  extra data can be a complement for the operand (eg: a length or a distance
+  encoded on larger values), or a literal to be copied to the output buffer.
+
+  The first byte of the block follows a different encoding from other bytes, it
+  seems to be optimized for literal use only, since there is no dictionary yet
+  prior to that byte.
+
+  Lengths are always encoded on a variable size starting with a small number
+  of bits in the operand. If the number of bits isn't enough to represent the
+  length, up to 255 may be added in increments by consuming more bytes with a
+  rate of at most 255 per extra byte (thus the compression ratio cannot exceed
+  around 255:1). The variable length encoding using #bits is always the same :
+
+       length = byte & ((1 << #bits) - 1)
+       if (!length) {
+               length = ((1 << #bits) - 1)
+               length += 255*(number of zero bytes)
+               length += first-non-zero-byte
+       }
+       length += constant (generally 2 or 3)
+
+  For references to the dictionary, distances are relative to the output
+  pointer. Distances are encoded using very few bits belonging to certain
+  ranges, resulting in multiple copy instructions using different encodings.
+  Certain encodings involve one extra byte, others involve two extra bytes
+  forming a little-endian 16-bit quantity (marked LE16 below).
+
+  After any instruction except the large literal copy, 0, 1, 2 or 3 literals
+  are copied before starting the next instruction. The number of literals that
+  were copied may change the meaning and behaviour of the next instruction. In
+  practice, only one instruction needs to know whether 0, less than 4, or more
+  literals were copied. This is the information stored in the <state> variable
+  in this implementation. This number of immediate literals to be copied is
+  generally encoded in the last two bits of the instruction but may also be
+  taken from the last two bits of an extra operand (eg: distance).
+
+  End of stream is declared when a block copy of distance 0 is seen. Only one
+  instruction may encode this distance (0001HLLL), it takes one LE16 operand
+  for the distance, thus requiring 3 bytes.
+
+  IMPORTANT NOTE : in the code some length checks are missing because certain
+  instructions are called under the assumption that a certain number of bytes
+  follow because it has already been garanteed before parsing the instructions.
+  They just have to "refill" this credit if they consume extra bytes. This is
+  an implementation design choice independant on the algorithm or encoding.
+
+Byte sequences
+
+  First byte encoding :
+
+      0..17   : follow regular instruction encoding, see below. It is worth
+                noting that codes 16 and 17 will represent a block copy from
+                the dictionary which is empty, and that they will always be
+                invalid at this place.
+
+      18..21  : copy 0..3 literals
+                state = (byte - 17) = 0..3  [ copy <state> literals ]
+                skip byte
+
+      22..255 : copy literal string
+                length = (byte - 17) = 4..238
+                state = 4 [ don't copy extra literals ]
+                skip byte
+
+  Instruction encoding :
+
+      0 0 0 0 X X X X  (0..15)
+        Depends on the number of literals copied by the last instruction.
+        If last instruction did not copy any literal (state == 0), this
+        encoding will be a copy of 4 or more literal, and must be interpreted
+        like this :
+
+           0 0 0 0 L L L L  (0..15)  : copy long literal string
+           length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte)
+           state = 4  (no extra literals are copied)
+
+        If last instruction used to copy between 1 to 3 literals (encoded in
+        the instruction's opcode or distance), the instruction is a copy of a
+        2-byte block from the dictionary within a 1kB distance. It is worth
+        noting that this instruction provides little savings since it uses 2
+        bytes to encode a copy of 2 other bytes but it encodes the number of
+        following literals for free. It must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 2 bytes from <= 1kB distance
+           length = 2
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 1
+
+        If last instruction used to copy 4 or more literals (as detected by
+        state == 4), the instruction becomes a copy of a 3-byte block from the
+        dictionary from a 2..3kB distance, and must be interpreted like this :
+
+           0 0 0 0 D D S S  (0..15)  : copy 3 bytes from 2..3 kB distance
+           length = 3
+           state = S (copy S literals after this block)
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 2) + D + 2049
+
+      0 0 0 1 H L L L  (16..31)
+           Copy of a block within 16..48kB distance (preferably less than 10B)
+           length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = 16384 + (H << 14) + D
+           state = S (copy S literals after this block)
+           End of stream is reached if distance == 16384
+
+      0 0 1 L L L L L  (32..63)
+           Copy of small block within 16kB distance (preferably less than 34B)
+           length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
+        Always followed by exactly one LE16 :  D D D D D D D D : D D D D D D S S
+           distance = D + 1
+           state = S (copy S literals after this block)
+
+      0 1 L D D D S S  (64..127)
+           Copy 3-4 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 3 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+      1 L L D D D S S  (128..255)
+           Copy 5-8 bytes from block within 2kB distance
+           state = S (copy S literals after this block)
+           length = 5 + L
+         Always followed by exactly one byte : H H H H H H H H
+           distance = (H << 3) + D + 1
+
+Authors
+
+  This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
+  analysis of the decompression code available in Linux 3.16-rc5. The code is
+  tricky, it is possible that this document contains mistakes or that a few
+  corner cases were overlooked. In any case, please report any doubt, fix, or
+  proposed updates to the author(s) so that the document can be updated.
diff --git a/Documentation/mailbox.txt b/Documentation/mailbox.txt
new file mode 100644
index 000000000000..60f43ff629aa
--- /dev/null
+++ b/Documentation/mailbox.txt
@@ -0,0 +1,122 @@
+		The Common Mailbox Framework
+		Jassi Brar <jaswinder.singh@linaro.org>
+
+ This document aims to help developers write client and controller
+drivers for the API. But before we start, let us note that the
+client (especially) and controller drivers are likely going to be
+very platform specific because the remote firmware is likely to be
+proprietary and implement non-standard protocol. So even if two
+platforms employ, say, PL320 controller, the client drivers can't
+be shared across them. Even the PL320 driver might need to accommodate
+some platform specific quirks. So the API is meant mainly to avoid
+similar copies of code written for each platform. Having said that,
+nothing prevents the remote f/w to also be Linux based and use the
+same api there. However none of that helps us locally because we only
+ever deal at client's protocol level.
+ Some of the choices made during implementation are the result of this
+peculiarity of this "common" framework.
+
+
+
+	Part 1 - Controller Driver (See include/linux/mailbox_controller.h)
+
+ Allocate mbox_controller and the array of mbox_chan.
+Populate mbox_chan_ops, except peek_data() all are mandatory.
+The controller driver might know a message has been consumed
+by the remote by getting an IRQ or polling some hardware flag
+or it can never know (the client knows by way of the protocol).
+The method in order of preference is IRQ -> Poll -> None, which
+the controller driver should set via 'txdone_irq' or 'txdone_poll'
+or neither.
+
+
+	Part 2 - Client Driver (See include/linux/mailbox_client.h)
+
+ The client might want to operate in blocking mode (synchronously
+send a message through before returning) or non-blocking/async mode (submit
+a message and a callback function to the API and return immediately).
+
+
+struct demo_client {
+	struct mbox_client cl;
+	struct mbox_chan *mbox;
+	struct completion c;
+	bool async;
+	/* ... */
+};
+
+/*
+ * This is the handler for data received from remote. The behaviour is purely
+ * dependent upon the protocol. This is just an example.
+ */
+static void message_from_remote(struct mbox_client *cl, void *mssg)
+{
+	struct demo_client *dc = container_of(mbox_client,
+						struct demo_client, cl);
+	if (dc->aysnc) {
+		if (is_an_ack(mssg)) {
+			/* An ACK to our last sample sent */
+			return; /* Or do something else here */
+		} else { /* A new message from remote */
+			queue_req(mssg);
+		}
+	} else {
+		/* Remote f/w sends only ACK packets on this channel */
+		return;
+	}
+}
+
+static void sample_sent(struct mbox_client *cl, void *mssg, int r)
+{
+	struct demo_client *dc = container_of(mbox_client,
+						struct demo_client, cl);
+	complete(&dc->c);
+}
+
+static void client_demo(struct platform_device *pdev)
+{
+	struct demo_client *dc_sync, *dc_async;
+	/* The controller already knows async_pkt and sync_pkt */
+	struct async_pkt ap;
+	struct sync_pkt sp;
+
+	dc_sync = kzalloc(sizeof(*dc_sync), GFP_KERNEL);
+	dc_async = kzalloc(sizeof(*dc_async), GFP_KERNEL);
+
+	/* Populate non-blocking mode client */
+	dc_async->cl.dev = &pdev->dev;
+	dc_async->cl.rx_callback = message_from_remote;
+	dc_async->cl.tx_done = sample_sent;
+	dc_async->cl.tx_block = false;
+	dc_async->cl.tx_tout = 0; /* doesn't matter here */
+	dc_async->cl.knows_txdone = false; /* depending upon protocol */
+	dc_async->async = true;
+	init_completion(&dc_async->c);
+
+	/* Populate blocking mode client */
+	dc_sync->cl.dev = &pdev->dev;
+	dc_sync->cl.rx_callback = message_from_remote;
+	dc_sync->cl.tx_done = NULL; /* operate in blocking mode */
+	dc_sync->cl.tx_block = true;
+	dc_sync->cl.tx_tout = 500; /* by half a second */
+	dc_sync->cl.knows_txdone = false; /* depending upon protocol */
+	dc_sync->async = false;
+
+	/* ASync mailbox is listed second in 'mboxes' property */
+	dc_async->mbox = mbox_request_channel(&dc_async->cl, 1);
+	/* Populate data packet */
+	/* ap.xxx = 123; etc */
+	/* Send async message to remote */
+	mbox_send_message(dc_async->mbox, &ap);
+
+	/* Sync mailbox is listed first in 'mboxes' property */
+	dc_sync->mbox = mbox_request_channel(&dc_sync->cl, 0);
+	/* Populate data packet */
+	/* sp.abc = 123; etc */
+	/* Send message to remote in blocking mode */
+	mbox_send_message(dc_sync->mbox, &sp);
+	/* At this point 'sp' has been sent */
+
+	/* Now wait for async chan to be done */
+	wait_for_completion(&dc_async->c);
+}
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
index 69b3cac4749d..5d8675615e59 100644
--- a/Documentation/ramoops.txt
+++ b/Documentation/ramoops.txt
@@ -14,11 +14,19 @@ survive after a restart.
 
 1. Ramoops concepts
 
-Ramoops uses a predefined memory area to store the dump. The start and size of
-the memory area are set using two variables:
+Ramoops uses a predefined memory area to store the dump. The start and size
+and type of the memory area are set using three variables:
   * "mem_address" for the start
   * "mem_size" for the size. The memory size will be rounded down to a
   power of two.
+  * "mem_type" to specifiy if the memory type (default is pgprot_writecombine).
+
+Typically the default value of mem_type=0 should be used as that sets the pstore
+mapping to pgprot_writecombine. Setting mem_type=1 attempts to use
+pgprot_noncached, which only works on some platforms. This is because pstore
+depends on atomic operations. At least on ARM, pgprot_noncached causes the
+memory to be mapped strongly ordered, and atomic operations on strongly ordered
+memory are implementation defined, and won't work on many ARMs such as omaps.
 
 The memory area is divided into "record_size" chunks (also rounded down to
 power of two) and each oops/panic writes a "record_size" chunk of
@@ -55,6 +63,7 @@ Setting the ramoops parameters can be done in 2 different manners:
 static struct ramoops_platform_data ramoops_data = {
         .mem_size               = <...>,
         .mem_address            = <...>,
+        .mem_type               = <...>,
         .record_size            = <...>,
         .dump_oops              = <...>,
         .ecc                    = <...>,
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index b8dd0df76952..0fd40b15e2d5 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV66/AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX,
-    HDAV1.3 (Deluxe), and HDAV1.3 Slim.
+    i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe),
+    Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim.
 
     This module supports autoprobe and multiple cards.
 
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index b0714d8f678a..8dfb6a5f427d 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 
 Procedure for submitting patches to the -stable tree:
 
+ - If the patch covers files in net/ or drivers/net please follow netdev stable
+   submission guidelines as described in
+   Documentation/networking/netdev-FAQ.txt
  - Send the patch, after verifying that it follows the above rules, to
    stable@vger.kernel.org.  You must note the upstream commit ID in the
    changelog of your submission, as well as the kernel version you wish
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index e55124e7c40c..855d9b37bf76 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -317,6 +317,7 @@ for more than this value report a warning.
 This file shows up if CONFIG_DETECT_HUNG_TASK is enabled.
 
 0: means infinite timeout - no checking done.
+Possible values to set are in range {0..LONG_MAX/HZ}.
 
 ==============================================================
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index d614a9b6a280..b602784b289f 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -681,7 +681,8 @@ The batch value of each per cpu pagelist is also updated as a result.  It is
 set to pcp->high/4.  The upper limit of batch is (PAGE_SHIFT * 8)
 
 The initial value is zero.  Kernel does not use this value at boot time to set
-the high water marks for each per cpu page list.
+the high water marks for each per cpu page list.  If the user writes '0' to this
+sysctl, it will revert to this default behavior.
 
 ==============================================================
 
diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt
new file mode 100644
index 000000000000..bba7dbfc49ed
--- /dev/null
+++ b/Documentation/trace/coresight.txt
@@ -0,0 +1,299 @@
+		Coresight - HW Assisted Tracing on ARM
+		======================================
+
+   Author:   Mathieu Poirier <mathieu.poirier@linaro.org>
+   Date:     September 11th, 2014
+
+Introduction
+------------
+
+Coresight is an umbrella of technologies allowing for the debugging of ARM
+based SoC.  It includes solutions for JTAG and HW assisted tracing.  This
+document is concerned with the latter.
+
+HW assisted tracing is becoming increasingly useful when dealing with systems
+that have many SoCs and other components like GPU and DMA engines.  ARM has
+developed a HW assisted tracing solution by means of different components, each
+being added to a design at systhesis time to cater to specific tracing needs.
+Compoments are generally categorised as source, link and sinks and are
+(usually) discovered using the AMBA bus.
+
+"Sources" generate a compressed stream representing the processor instruction
+path based on tracing scenarios as configured by users.  From there the stream
+flows through the coresight system (via ATB bus) using links that are connecting
+the emanating source to a sink(s).  Sinks serve as endpoints to the coresight
+implementation, either storing the compressed stream in a memory buffer or
+creating an interface to the outside world where data can be transferred to a
+host without fear of filling up the onboard coresight memory buffer.
+
+At typical coresight system would look like this:
+
+  *****************************************************************
+ **************************** AMBA AXI  ****************************===||
+  *****************************************************************    ||
+        ^                    ^                            |            ||
+        |                    |                            *            **
+     0000000    :::::     0000000    :::::    :::::    @@@@@@@    ||||||||||||
+     0 CPU 0<-->: C :     0 CPU 0<-->: C :    : C :    @ STM @    || System ||
+  |->0000000    : T :  |->0000000    : T :    : T :<--->@@@@@     || Memory ||
+  |  #######<-->: I :  |  #######<-->: I :    : I :      @@@<-|   ||||||||||||
+  |  # ETM #    :::::  |  # PTM #    :::::    :::::       @   |
+  |   #####      ^ ^   |   #####      ^ !      ^ !        .   |   |||||||||
+  | |->###       | !   | |->###       | !      | !        .   |   || DAP ||
+  | |   #        | !   | |   #        | !      | !        .   |   |||||||||
+  | |   .        | !   | |   .        | !      | !        .   |      |  |
+  | |   .        | !   | |   .        | !      | !        .   |      |  *
+  | |   .        | !   | |   .        | !      | !        .   |      | SWD/
+  | |   .        | !   | |   .        | !      | !        .   |      | JTAG
+  *****************************************************************<-|
+ *************************** AMBA Debug ABP ************************
+  *****************************************************************
+   |    .          !         .          !        !        .    |
+   |    .          *         .          *        *        .    |
+  *****************************************************************
+ ******************** Cross Trigger Matrix (CTM) *******************
+  *****************************************************************
+   |    .     ^              .                            .    |
+   |    *     !              *                            *    |
+  *****************************************************************
+ ****************** AMBA Advanced Trace Bus (ATB) ******************
+  *****************************************************************
+   |          !                        ===============         |
+   |          *                         ===== F =====<---------|
+   |   :::::::::                         ==== U ====
+   |-->:: CTI ::<!!                       === N ===
+   |   :::::::::  !                        == N ==
+   |    ^         *                        == E ==
+   |    !  &&&&&&&&&       IIIIIII         == L ==
+   |------>&& ETB &&<......II     I        =======
+   |    !  &&&&&&&&&       II     I           .
+   |    !                    I     I          .
+   |    !                    I REP I<..........
+   |    !                    I     I
+   |    !!>&&&&&&&&&       II     I           *Source: ARM ltd.
+   |------>& TPIU  &<......II    I            DAP = Debug Access Port
+           &&&&&&&&&       IIIIIII            ETM = Embedded Trace Macrocell
+               ;                              PTM = Program Trace Macrocell
+               ;                              CTI = Cross Trigger Interface
+               *                              ETB = Embedded Trace Buffer
+          To trace port                       TPIU= Trace Port Interface Unit
+                                              SWD = Serial Wire Debug
+
+While on target configuration of the components is done via the ABP bus,
+all trace data are carried out-of-band on the ATB bus.  The CTM provides
+a way to aggregate and distribute signals between CoreSight components.
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform.  This first implementation centers on
+the basic tracing functionality, enabling components such ETM/PTM, funnel,
+replicator, TMC, TPIU and ETB.  Future work will enable more
+intricate IP blocks such as STM and CTI.
+
+
+Acronyms and Classification
+---------------------------
+
+Acronyms:
+
+PTM:     Program Trace Macrocell
+ETM:     Embedded Trace Macrocell
+STM:     System trace Macrocell
+ETB:     Embedded Trace Buffer
+ITM:     Instrumentation Trace Macrocell
+TPIU:    Trace Port Interface Unit
+TMC-ETR: Trace Memory Controller, configured as Embedded Trace Router
+TMC-ETF: Trace Memory Controller, configured as Embedded Trace FIFO
+CTI:     Cross Trigger Interface
+
+Classification:
+
+Source:
+   ETMv3.x ETMv4, PTMv1.0, PTMv1.1, STM, STM500, ITM
+Link:
+   Funnel, replicator (intelligent or not), TMC-ETR
+Sinks:
+   ETBv1.0, ETB1.1, TPIU, TMC-ETF
+Misc:
+   CTI
+
+
+Device Tree Bindings
+----------------------
+
+See Documentation/devicetree/bindings/arm/coresight.txt for details.
+
+As of this writing drivers for ITM, STMs and CTIs are not provided but are
+expected to be added as the solution matures.
+
+
+Framework and implementation
+----------------------------
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform.  Any coresight compliant device can
+register with the framework for as long as they use the right APIs:
+
+struct coresight_device *coresight_register(struct coresight_desc *desc);
+void coresight_unregister(struct coresight_device *csdev);
+
+The registering function is taking a "struct coresight_device *csdev" and
+register the device with the core framework.  The unregister function takes
+a reference to a "strut coresight_device", obtained at registration time.
+
+If everything goes well during the registration process the new devices will
+show up under /sys/bus/coresight/devices, as showns here for a TC2 platform:
+
+root:~# ls /sys/bus/coresight/devices/
+replicator  20030000.tpiu    2201c000.ptm  2203c000.etm  2203e000.etm
+20010000.etb         20040000.funnel  2201d000.ptm  2203d000.etm
+root:~#
+
+The functions take a "struct coresight_device", which looks like this:
+
+struct coresight_desc {
+        enum coresight_dev_type type;
+        struct coresight_dev_subtype subtype;
+        const struct coresight_ops *ops;
+        struct coresight_platform_data *pdata;
+        struct device *dev;
+        const struct attribute_group **groups;
+};
+
+
+The "coresight_dev_type" identifies what the device is, i.e, source link or
+sink while the "coresight_dev_subtype" will characterise that type further.
+
+The "struct coresight_ops" is mandatory and will tell the framework how to
+perform base operations related to the components, each component having
+a different set of requirement.  For that "struct coresight_ops_sink",
+"struct coresight_ops_link" and "struct coresight_ops_source" have been
+provided.
+
+The next field, "struct coresight_platform_data *pdata" is acquired by calling
+"of_get_coresight_platform_data()", as part of the driver's _probe routine and
+"struct device *dev" gets the device reference embedded in the "amba_device":
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ ...
+ ...
+ drvdata->dev = &adev->dev;
+ ...
+}
+
+Specific class of device (source, link, or sink) have generic operations
+that can be performed on them (see "struct coresight_ops").  The
+"**groups" is a list of sysfs entries pertaining to operations
+specific to that component only.  "Implementation defined" customisations are
+expected to be accessed and controlled using those entries.
+
+Last but not least, "struct module *owner" is expected to be set to reflect
+the information carried in "THIS_MODULE".
+
+How to use
+----------
+
+Before trace collection can start, a coresight sink needs to be identify.
+There is no limit on the amount of sinks (nor sources) that can be enabled at
+any given moment.  As a generic operation, all device pertaining to the sink
+class will have an "active" entry in sysfs:
+
+root:/sys/bus/coresight/devices# ls
+replicator  20030000.tpiu    2201c000.ptm  2203c000.etm  2203e000.etm
+20010000.etb         20040000.funnel  2201d000.ptm  2203d000.etm
+root:/sys/bus/coresight/devices# ls 20010000.etb
+enable_sink  status  trigger_cntr
+root:/sys/bus/coresight/devices# echo 1 > 20010000.etb/enable_sink
+root:/sys/bus/coresight/devices# cat 20010000.etb/enable_sink
+1
+root:/sys/bus/coresight/devices#
+
+At boot time the current etm3x driver will configure the first address
+comparator with "_stext" and "_etext", essentially tracing any instruction
+that falls within that range.  As such "enabling" a source will immediately
+trigger a trace capture:
+
+root:/sys/bus/coresight/devices# echo 1 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices# cat 2201c000.ptm/enable_source
+1
+root:/sys/bus/coresight/devices# cat 20010000.etb/status
+Depth:          0x2000
+Status:         0x1
+RAM read ptr:   0x0
+RAM wrt ptr:    0x19d3   <----- The write pointer is moving
+Trigger cnt:    0x0
+Control:        0x1
+Flush status:   0x0
+Flush ctrl:     0x2001
+root:/sys/bus/coresight/devices#
+
+Trace collection is stopped the same way:
+
+root:/sys/bus/coresight/devices# echo 0 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices#
+
+The content of the ETB buffer can be harvested directly from /dev:
+
+root:/sys/bus/coresight/devices# dd if=/dev/20010000.etb \
+of=~/cstrace.bin
+
+64+0 records in
+64+0 records out
+32768 bytes (33 kB) copied, 0.00125258 s, 26.2 MB/s
+root:/sys/bus/coresight/devices#
+
+The file cstrace.bin can be decompressed using "ptm2human", DS-5 or Trace32.
+
+Following is a DS-5 output of an experimental loop that increments a variable up
+to a certain value.  The example is simple and yet provides a glimpse of the
+wealth of possibilities that coresight provides.
+
+Info                                    Tracing enabled
+Instruction     106378866       0x8026B53C      E52DE004        false   PUSH     {lr}
+Instruction     0       0x8026B540      E24DD00C        false   SUB      sp,sp,#0xc
+Instruction     0       0x8026B544      E3A03000        false   MOV      r3,#0
+Instruction     0       0x8026B548      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Timestamp                                       Timestamp: 17106715833
+Instruction     319     0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     9       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     7       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     7       0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     10      0x8026B54C      E59D3004        false   LDR      r3,[sp,#4]
+Instruction     0       0x8026B550      E3530004        false   CMP      r3,#4
+Instruction     0       0x8026B554      E2833001        false   ADD      r3,r3,#1
+Instruction     0       0x8026B558      E58D3004        false   STR      r3,[sp,#4]
+Instruction     0       0x8026B55C      DAFFFFFA        true    BLE      {pc}-0x10 ; 0x8026b54c
+Instruction     6       0x8026B560      EE1D3F30        false   MRC      p15,#0x0,r3,c13,c0,#1
+Instruction     0       0x8026B564      E1A0100D        false   MOV      r1,sp
+Instruction     0       0x8026B568      E3C12D7F        false   BIC      r2,r1,#0x1fc0
+Instruction     0       0x8026B56C      E3C2203F        false   BIC      r2,r2,#0x3f
+Instruction     0       0x8026B570      E59D1004        false   LDR      r1,[sp,#4]
+Instruction     0       0x8026B574      E59F0010        false   LDR      r0,[pc,#16] ; [0x8026B58C] = 0x80550368
+Instruction     0       0x8026B578      E592200C        false   LDR      r2,[r2,#0xc]
+Instruction     0       0x8026B57C      E59221D0        false   LDR      r2,[r2,#0x1d0]
+Instruction     0       0x8026B580      EB07A4CF        true    BL       {pc}+0x1e9344 ; 0x804548c4
+Info                                    Tracing enabled
+Instruction     13570831        0x8026B584      E28DD00C        false   ADD      sp,sp,#0xc
+Instruction     0       0x8026B588      E8BD8000        true    LDM      sp!,{pc}
+Timestamp                                       Timestamp: 17107041535
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 1e6b6531bbcc..d2ba80bb7af5 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -55,6 +55,7 @@ zc3xx		0458:700f	Genius VideoCam Web V2
 sonixj		0458:7025	Genius Eye 311Q
 sn9c20x		0458:7029	Genius Look 320s
 sonixj		0458:702e	Genius Slim 310 NB
+sn9c20x		0458:7045	Genius Look 1320 V2
 sn9c20x		0458:704a	Genius Slim 1320
 sn9c20x		0458:704c	Genius i-Look 1321
 sn9c20x		045e:00f4	LifeCam VX-6000 (SN9C20x + OV9650)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6cd63a9010fb..651caaf3dfa2 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -148,9 +148,9 @@ of banks, as set via the KVM_X86_SETUP_MCE ioctl.
 
 4.4 KVM_CHECK_EXTENSION
 
-Capability: basic
+Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
 Architectures: all
-Type: system ioctl
+Type: system ioctl, vm ioctl
 Parameters: extension identifier (KVM_CAP_*)
 Returns: 0 if unsupported; 1 (or some other positive integer) if supported
 
@@ -160,6 +160,9 @@ receives an integer that describes the extension availability.
 Generally 0 means no and 1 means yes, but some extensions may report
 additional information in the integer return value.
 
+Based on their initialization different VMs may have different capabilities.
+It is thus encouraged to use the vm ioctl to query for capabilities (available
+with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
 
 4.5 KVM_GET_VCPU_MMAP_SIZE
 
@@ -969,18 +972,20 @@ uniprocessor guests).
 
 Possible values are:
 
- - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running
+ - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running [x86, ia64]
  - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
-                                 which has not yet received an INIT signal
+                                 which has not yet received an INIT signal [x86,
+                                 ia64]
  - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
-                                 now ready for a SIPI
+                                 now ready for a SIPI [x86, ia64]
  - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
-                                 is waiting for an interrupt
+                                 is waiting for an interrupt [x86, ia64]
  - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
-                                 accessible via KVM_GET_VCPU_EVENTS)
+                                 accessible via KVM_GET_VCPU_EVENTS) [x86, ia64]
 
-This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
 
 
 4.39 KVM_SET_MP_STATE
@@ -994,8 +999,9 @@ Returns: 0 on success; -1 on error
 Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
 arguments.
 
-This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
 
 
 4.40 KVM_SET_IDENTITY_MAP_ADDR
@@ -2705,6 +2711,21 @@ It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
 external interrupt has just been delivered into the guest. User space
 should put the acknowledged interrupt vector into the 'epr' field.
 
+		/* KVM_EXIT_SYSTEM_EVENT */
+		struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN       1
+#define KVM_SYSTEM_EVENT_RESET          2
+			__u32 type;
+			__u64 flags;
+		} system_event;
+
+If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
+a system-level event using some architecture specific mechanism (hypercall
+or some special instruction). In case of ARM/ARM64, this is triggered using
+HVC instruction based PSCI call from the vcpu. The 'type' field describes
+the system-level event type. The 'flags' field describes architecture
+specific flags for the system-level event.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virtual/kvm/devices/arm-vgic.txt
index 7f4e91b1316b..df8b0c7540b6 100644
--- a/Documentation/virtual/kvm/devices/arm-vgic.txt
+++ b/Documentation/virtual/kvm/devices/arm-vgic.txt
@@ -71,3 +71,13 @@ Groups:
   Errors:
     -ENODEV: Getting or setting this register is not yet supported
     -EBUSY: One or more VCPUs are running
+
+  KVM_DEV_ARM_VGIC_GRP_NR_IRQS
+  Attributes:
+    A value describing the number of interrupts (SGI, PPI and SPI) for
+    this GIC instance, ranging from 64 to 1024, in increments of 32.
+
+  Errors:
+    -EINVAL: Value set is out of the expected range
+    -EBUSY: Value has already be set, or GIC has already been initialized
+            with default values.
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 290894176142..53838d9c6295 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -425,6 +425,20 @@ fault through the slow path.
 Since only 19 bits are used to store generation-number on mmio spte, all
 pages are zapped when there is an overflow.
 
+Unfortunately, a single memory access might access kvm_memslots(kvm) multiple
+times, the last one happening when the generation number is retrieved and
+stored into the MMIO spte.  Thus, the MMIO spte might be created based on
+out-of-date information, but with an up-to-date generation number.
+
+To avoid this, the generation number is incremented again after synchronize_srcu
+returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a
+memslot update, while some SRCU readers might be using the old copy.  We do not
+want to use an MMIO sptes created with an odd generation number, and we can do
+this without losing a bit in the MMIO spte.  The low bit of the generation
+is not stored in MMIO spte, and presumed zero when it is extracted out of the
+spte.  If KVM is unlucky and creates an MMIO spte while the low bit is 1,
+the next access to the spte will always be a cache miss.
+
 
 Further reading
 ===============
diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt
index 550068466605..6ae89a9edf2a 100644
--- a/Documentation/vm/hwpoison.txt
+++ b/Documentation/vm/hwpoison.txt
@@ -84,6 +84,11 @@ PR_MCE_KILL
 		PR_MCE_KILL_EARLY: Early kill
 		PR_MCE_KILL_LATE:  Late kill
 		PR_MCE_KILL_DEFAULT: Use system global default
+	Note that if you want to have a dedicated thread which handles
+	the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should
+	call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise,
+	the SIGBUS is sent to the main thread.
+
 PR_MCE_KILL_GET
 	return current mode
 
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index c584a51add15..afe68ddbe6a4 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
 ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
diff --git a/Documentation/zh_CN/HOWTO b/Documentation/zh_CN/HOWTO
index 6c914aa87e71..54ea24ff63c7 100644
--- a/Documentation/zh_CN/HOWTO
+++ b/Documentation/zh_CN/HOWTO
@@ -237,7 +237,7 @@ kernel.org网站的pub/linux/kernel/v2.6/目录下找到它。它的开��循
 如果没有2.6.x.y版本内核存在，那么最新的2.6.x版本内核就相当于是当�的稳定
 版内核。
 
-2.6.x.y版本由“稳定版��组（邮件地�<stable@kernel.org>）维护，一般隔周�
+2.6.x.y版本由“稳定版��组（邮件地�<stable@vger.kernel.org>）维护，一般隔周�
 布新版本。
 
 内核��中的Documentation/stable_kernel_rules.txt文件具体�述了�被稳定
diff --git a/Documentation/zh_CN/stable_kernel_rules.txt b/Documentation/zh_CN/stable_kernel_rules.txt
index b5b9b0ab02fd..26ea5ed7cd9c 100644
--- a/Documentation/zh_CN/stable_kernel_rules.txt
+++ b/Documentation/zh_CN/stable_kernel_rules.txt
@@ -42,7 +42,7 @@ Documentation/stable_kernel_rules.txt 的中文翻译
 
 �稳定版代�树�交补�的过程：
 
-  - 在确认了补�符�以上的规则�，将补���到stable@kernel.org。
+  - 在确认了补�符�以上的规则�，将补���到stable@vger.kernel.org。
   - 如果补�被接�到队列里，��者会收到一个ACK回�，如果没有被接�，收
     到的是NAK回�。回�需�几天的时间，这�决于开�者的时间安排。
   - 被接�的补�会被加到稳定版本队列里，等待其他开�者的审查。
diff --git a/MAINTAINERS b/MAINTAINERS
index 900d98eec2fc..c701f48b8e00 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -849,6 +849,14 @@ M:	Hubert Feurstein <hubert.feurstein@contec.at>
 S:	Maintained
 F:	arch/arm/mach-ep93xx/micro9.c
 
+ARM/CORESIGHT FRAMEWORK AND DRIVERS
+M:	Mathieu Poirier <mathieu.poirier@linaro.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/coresight/*
+F:	Documentation/trace/coresight.txt
+F:	Documentation/devicetree/bindings/arm/coresight.txt
+
 ARM/CORGI MACHINE SUPPORT
 M:	Richard Purdie <rpurdie@rpsys.net>
 S:	Maintained
@@ -5511,6 +5519,14 @@ S:	Maintained
 F:	drivers/net/macvlan.c
 F:	include/linux/if_macvlan.h
 
+MAILBOX API
+M:	Jassi Brar <jassisinghbrar@gmail.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/mailbox/
+F:	include/linux/mailbox_client.h
+F:	include/linux/mailbox_controller.h
+
 MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7
 M:	Michael Kerrisk <mtk.manpages@gmail.com>
 W:	http://www.kernel.org/doc/man-pages
diff --git a/Makefile b/Makefile
index e5ac8a62e6e5..7aff64ee4fb6 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 3
 PATCHLEVEL = 14
-SUBLEVEL = 0
+SUBLEVEL = 29
 EXTRAVERSION =
-NAME = Shuffling Zombie Juror
+NAME = Remembering Coco
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -639,6 +639,8 @@ KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
 endif
 
+KBUILD_CFLAGS   += $(call cc-option, -fno-var-tracking-assignments)
+
 ifdef CONFIG_DEBUG_INFO
 KBUILD_CFLAGS	+= -g
 KBUILD_AFLAGS	+= -Wa,--gdwarf-2
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index ea16d782af58..398064cef746 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -11,13 +11,16 @@
 
 / {
 	compatible = "snps,nsimosci";
-	clock-frequency = <80000000>;	/* 80 MHZ */
+	clock-frequency = <20000000>;	/* 20 MHZ */
 	#address-cells = <1>;
 	#size-cells = <1>;
 	interrupt-parent = <&intc>;
 
 	chosen {
-		bootargs = "console=tty0 consoleblank=0";
+		/* this is for console on PGU */
+		/* bootargs = "console=tty0 consoleblank=0"; */
+		/* this is for console on serial */
+		bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
 	};
 
 	aliases {
@@ -44,15 +47,14 @@
 		};
 
 		uart0: serial@c0000000 {
-			compatible = "snps,dw-apb-uart";
+			compatible = "ns8250";
 			reg = <0xc0000000 0x2000>;
 			interrupts = <11>;
-			#clock-frequency = <80000000>;
 			clock-frequency = <3686400>;
 			baud = <115200>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			status = "okay";
+			no-loopback-test = <1>;
 		};
 
 		pgu0: pgu@c9000000 {
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 451af30914f6..c01ba35a4eff 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -54,6 +54,7 @@ CONFIG_SERIO_ARC_PS2=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 2fd3162ec4df..c1d3d2da1191 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -55,4 +55,31 @@ extern void read_decode_cache_bcr(void);
 
 #endif	/* !__ASSEMBLY__ */
 
+/* Instruction cache related Auxiliary registers */
+#define ARC_REG_IC_BCR		0x77	/* Build Config reg */
+#define ARC_REG_IC_IVIC		0x10
+#define ARC_REG_IC_CTRL		0x11
+#define ARC_REG_IC_IVIL		0x19
+#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4)
+#define ARC_REG_IC_PTAG		0x1E
+#endif
+
+/* Bit val in IC_CTRL */
+#define IC_CTRL_CACHE_DISABLE   0x1
+
+/* Data cache related Auxiliary registers */
+#define ARC_REG_DC_BCR		0x72	/* Build Config reg */
+#define ARC_REG_DC_IVDC		0x47
+#define ARC_REG_DC_CTRL		0x48
+#define ARC_REG_DC_IVDL		0x4A
+#define ARC_REG_DC_FLSH		0x4B
+#define ARC_REG_DC_FLDL		0x4C
+#if defined(CONFIG_ARC_MMU_V3) || defined (CONFIG_ARC_MMU_V4)
+#define ARC_REG_DC_PTAG		0x5C
+#endif
+
+/* Bit val in DC_CTRL */
+#define DC_CTRL_INV_MODE_FLUSH  0x40
+#define DC_CTRL_FLUSH_STATUS    0x100
+
 #endif /* _ASM_CACHE_H */
diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h
index b65fca7ffeb5..fea931634136 100644
--- a/arch/arc/include/asm/kgdb.h
+++ b/arch/arc/include/asm/kgdb.h
@@ -19,7 +19,7 @@
  * register API yet */
 #undef DBG_MAX_REG_NUM
 
-#define GDB_MAX_REGS		39
+#define GDB_MAX_REGS		87
 
 #define BREAK_INSTR_SIZE	2
 #define CACHE_FLUSH_IS_SAFE	1
@@ -33,23 +33,27 @@ static inline void arch_kgdb_breakpoint(void)
 
 extern void kgdb_trap(struct pt_regs *regs);
 
-enum arc700_linux_regnums {
+/* This is the numbering of registers according to the GDB. See GDB's
+ * arc-tdep.h for details.
+ *
+ * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */
+enum arc_linux_regnums {
 	_R0		= 0,
 	_R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13,
 	_R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24,
 	_R25, _R26,
-	_BTA		= 27,
-	_LP_START	= 28,
-	_LP_END		= 29,
-	_LP_COUNT	= 30,
-	_STATUS32	= 31,
-	_BLINK		= 32,
-	_FP		= 33,
-	__SP		= 34,
-	_EFA		= 35,
-	_RET		= 36,
-	_ORIG_R8	= 37,
-	_STOP_PC	= 38
+	_FP		= 27,
+	__SP		= 28,
+	_R30		= 30,
+	_BLINK		= 31,
+	_LP_COUNT	= 60,
+	_STOP_PC	= 64,
+	_RET		= 64,
+	_LP_START	= 65,
+	_LP_END		= 66,
+	_STATUS32	= 67,
+	_ECR		= 76,
+	_BTA		= 82,
 };
 
 #else
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 2618cc13ba75..76a7739aab1c 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -11,6 +11,7 @@
 #ifndef _UAPI__ASM_ARC_PTRACE_H
 #define _UAPI__ASM_ARC_PTRACE_H
 
+#define PTRACE_GET_THREAD_AREA	25
 
 #ifndef __ASSEMBLY__
 /*
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index b6dc4e21fd32..0b3ef4025d89 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -42,7 +42,7 @@ const struct machine_desc * __init setup_machine_fdt(void *dt)
 	const struct machine_desc *mdesc;
 	unsigned long dt_root;
 	void *clk;
-	unsigned long len;
+	int len;
 
 	if (!early_init_dt_scan(dt))
 		return NULL;
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 47d09d07f093..6e8f83a32522 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -614,11 +614,13 @@ resume_user_mode_begin:
 
 resume_kernel_mode:
 
-#ifdef CONFIG_PREEMPT
-
-	; This is a must for preempt_schedule_irq()
+	; Disable Interrupts from this point on
+	; CONFIG_PREEMPT: This is a must for preempt_schedule_irq()
+	; !CONFIG_PREEMPT: To ensure restore_regs is intr safe
 	IRQ_DISABLE	r9
 
+#ifdef CONFIG_PREEMPT
+
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
 	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 991997269d02..07a58f2d3077 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -12,10 +12,42 @@
  *      to skip certain things during boot on simulator
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/entry.h>
-#include <linux/linkage.h>
 #include <asm/arcregs.h>
+#include <asm/cache.h>
+
+.macro CPU_EARLY_SETUP
+
+	; Setting up Vectror Table (in case exception happens in early boot
+	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
+	; Disable I-cache/D-cache if kernel so configured
+	lr	r5, [ARC_REG_IC_BCR]
+	breq    r5, 0, 1f		; I$ doesn't exist
+	lr	r5, [ARC_REG_IC_CTRL]
+#ifdef CONFIG_ARC_HAS_ICACHE
+	bclr	r5, r5, 0		; 0 - Enable, 1 is Disable
+#else
+	bset	r5, r5, 0		; I$ exists, but is not used
+#endif
+	sr	r5, [ARC_REG_IC_CTRL]
+
+1:
+	lr	r5, [ARC_REG_DC_BCR]
+	breq    r5, 0, 1f		; D$ doesn't exist
+	lr	r5, [ARC_REG_DC_CTRL]
+	bclr	r5, r5, 6		; Invalidate (discard w/o wback)
+#ifdef CONFIG_ARC_HAS_DCACHE
+	bclr	r5, r5, 0		; Enable (+Inv)
+#else
+	bset	r5, r5, 0		; Disable (+Inv)
+#endif
+	sr	r5, [ARC_REG_DC_CTRL]
+
+1:
+.endm
 
 	.cpu A7
 
@@ -24,13 +56,13 @@
 	.globl stext
 stext:
 	;-------------------------------------------------------------------
-	; Don't clobber r0-r4 yet. It might have bootloader provided info
+	; Don't clobber r0-r2 yet. It might have bootloader provided info
 	;-------------------------------------------------------------------
 
-	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+	CPU_EARLY_SETUP
 
 #ifdef CONFIG_SMP
-	; Only Boot (Master) proceeds. Others wait in platform dependent way
+	; Ensure Boot (Master) proceeds. Others wait in platform dependent way
 	;	IDENTITY Reg [ 3  2  1  0 ]
 	;	(cpu-id)             ^^^	=> Zero for UP ARC700
 	;					=> #Core-ID if SMP (Master 0)
@@ -39,7 +71,8 @@ stext:
 	; need to make sure only boot cpu takes this path.
 	GET_CPU_ID  r5
 	cmp	r5, 0
-	jnz	arc_platform_smp_wait_to_boot
+	mov.ne	r0, r5
+	jne	arc_platform_smp_wait_to_boot
 #endif
 	; Clear BSS before updating any globals
 	; XXX: use ZOL here
@@ -89,7 +122,7 @@ stext:
 
 first_lines_of_secondary:
 
-	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+	CPU_EARLY_SETUP
 
 	; setup per-cpu idle task as "current" on this CPU
 	ld	r0, [@secondary_idle_tsk]
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index 5d76706139dd..13b3ffb27a38 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -146,6 +146,10 @@ long arch_ptrace(struct task_struct *child, long request,
 	pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data);
 
 	switch (request) {
+	case PTRACE_GET_THREAD_AREA:
+		ret = put_user(task_thread_info(child)->thr_ptr,
+			       (unsigned long __user *)data);
+		break;
 	default:
 		ret = ptrace_request(child, request, addr, data);
 		break;
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 400c663b21c2..1f676c4794e0 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -73,37 +73,9 @@
 #include <asm/cachectl.h>
 #include <asm/setup.h>
 
-/* Instruction cache related Auxiliary registers */
-#define ARC_REG_IC_BCR		0x77	/* Build Config reg */
-#define ARC_REG_IC_IVIC		0x10
-#define ARC_REG_IC_CTRL		0x11
-#define ARC_REG_IC_IVIL		0x19
-#if (CONFIG_ARC_MMU_VER > 2)
-#define ARC_REG_IC_PTAG		0x1E
-#endif
-
-/* Bit val in IC_CTRL */
-#define IC_CTRL_CACHE_DISABLE   0x1
-
-/* Data cache related Auxiliary registers */
-#define ARC_REG_DC_BCR		0x72	/* Build Config reg */
-#define ARC_REG_DC_IVDC		0x47
-#define ARC_REG_DC_CTRL		0x48
-#define ARC_REG_DC_IVDL		0x4A
-#define ARC_REG_DC_FLSH		0x4B
-#define ARC_REG_DC_FLDL		0x4C
-#if (CONFIG_ARC_MMU_VER > 2)
-#define ARC_REG_DC_PTAG		0x5C
-#endif
-
-/* Bit val in DC_CTRL */
-#define DC_CTRL_INV_MODE_FLUSH  0x40
-#define DC_CTRL_FLUSH_STATUS    0x100
-
-char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len)
+char *arc_cache_mumbojumbo(int c, char *buf, int len)
 {
 	int n = 0;
-	unsigned int c = smp_processor_id();
 
 #define PR_CACHE(p, enb, str)						\
 {									\
@@ -169,72 +141,43 @@ void read_decode_cache_bcr(void)
  */
 void arc_cache_init(void)
 {
-	unsigned int cpu = smp_processor_id();
-	struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
-	struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
-	unsigned int dcache_does_alias, temp;
+	unsigned int __maybe_unused cpu = smp_processor_id();
+	struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc;
 	char str[256];
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
-	if (!ic->ver)
-		goto chk_dc;
-
-#ifdef CONFIG_ARC_HAS_ICACHE
-	/* 1. Confirm some of I-cache params which Linux assumes */
-	if (ic->line_len != L1_CACHE_BYTES)
-		panic("Cache H/W doesn't match kernel Config");
-
-	if (ic->ver != CONFIG_ARC_MMU_VER)
-		panic("Cache ver doesn't match MMU ver\n");
-#endif
-
-	/* Enable/disable I-Cache */
-	temp = read_aux_reg(ARC_REG_IC_CTRL);
-
 #ifdef CONFIG_ARC_HAS_ICACHE
-	temp &= ~IC_CTRL_CACHE_DISABLE;
-#else
-	temp |= IC_CTRL_CACHE_DISABLE;
+	ic = &cpuinfo_arc700[cpu].icache;
+	if (ic->ver) {
+		if (ic->line_len != L1_CACHE_BYTES)
+			panic("ICache line [%d] != kernel Config [%d]",
+			      ic->line_len, L1_CACHE_BYTES);
+
+		if (ic->ver != CONFIG_ARC_MMU_VER)
+			panic("Cache ver [%d] doesn't match MMU ver [%d]\n",
+			      ic->ver, CONFIG_ARC_MMU_VER);
+	}
 #endif
 
-	write_aux_reg(ARC_REG_IC_CTRL, temp);
-
-chk_dc:
-	if (!dc->ver)
-		return;
-
 #ifdef CONFIG_ARC_HAS_DCACHE
-	if (dc->line_len != L1_CACHE_BYTES)
-		panic("Cache H/W doesn't match kernel Config");
+	dc = &cpuinfo_arc700[cpu].dcache;
+	if (dc->ver) {
+		unsigned int dcache_does_alias;
 
-	/* check for D-Cache aliasing */
-	dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE;
+		if (dc->line_len != L1_CACHE_BYTES)
+			panic("DCache line [%d] != kernel Config [%d]",
+			      dc->line_len, L1_CACHE_BYTES);
 
-	if (dcache_does_alias && !cache_is_vipt_aliasing())
-		panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-	else if (!dcache_does_alias && cache_is_vipt_aliasing())
-		panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-#endif
-
-	/* Set the default Invalidate Mode to "simpy discard dirty lines"
-	 *  as this is more frequent then flush before invalidate
-	 * Ofcourse we toggle this default behviour when desired
-	 */
-	temp = read_aux_reg(ARC_REG_DC_CTRL);
-	temp &= ~DC_CTRL_INV_MODE_FLUSH;
+		/* check for D-Cache aliasing */
+		dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE;
 
-#ifdef CONFIG_ARC_HAS_DCACHE
-	/* Enable D-Cache: Clear Bit 0 */
-	write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE);
-#else
-	/* Flush D cache */
-	write_aux_reg(ARC_REG_DC_FLSH, 0x1);
-	/* Disable D cache */
-	write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE);
+		if (dcache_does_alias && !cache_is_vipt_aliasing())
+			panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+		else if (!dcache_does_alias && cache_is_vipt_aliasing())
+			panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+	}
 #endif
-
-	return;
 }
 
 #define OP_INV		0x1
@@ -254,12 +197,16 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
 
 	if (cacheop == OP_INV_IC) {
 		aux_cmd = ARC_REG_IC_IVIL;
+#if (CONFIG_ARC_MMU_VER > 2)
 		aux_tag = ARC_REG_IC_PTAG;
+#endif
 	}
 	else {
 		/* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */
 		aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+#if (CONFIG_ARC_MMU_VER > 2)
 		aux_tag = ARC_REG_DC_PTAG;
+#endif
 	}
 
 	/* Ensure we properly floor/ceil the non-line aligned/sized requests
diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig
index 295cefeb25d3..33058aa40e77 100644
--- a/arch/arc/plat-arcfpga/Kconfig
+++ b/arch/arc/plat-arcfpga/Kconfig
@@ -33,7 +33,6 @@ config ISS_SMP_EXTN
 	bool "ARC SMP Extensions (ISS Models only)"
 	default n
 	depends on SMP
-	select ARC_HAS_COH_RTSC
 	help
 	  SMP Extensions to ARC700, in a "simulation only" Model, supported in
 	  ARC ISS (Instruction Set Simulator).
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 15949459611f..4733d327cfb1 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,6 +6,7 @@ config ARM
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -898,7 +899,7 @@ config ARCH_MULTI_V5
 	bool "ARMv5 based platforms (ARM926T, XSCALE, PJ1, ...)"
 	depends on !ARCH_MULTI_V6_V7
 	select ARCH_MULTI_V4_V5
-	select CPU_ARM926T if (!CPU_ARM946E || CPU_ARM1020 || \
+	select CPU_ARM926T if !(CPU_ARM946E || CPU_ARM1020 || \
 		CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
 		CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_FEROCEON)
 
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 0531da8e5216..6a5a2b481463 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1172,14 +1172,6 @@ config EARLY_PRINTK
 	  kernel low-level debugging functions. Add earlyprintk to your
 	  kernel parameters to enable this console.
 
-config OC_ETM
-	bool "On-chip ETM and ETB"
-	depends on ARM_AMBA
-	help
-	  Enables the on-chip embedded trace macrocell and embedded trace
-	  buffer driver that will allow you to collect traces of the
-	  kernel code.
-
 config ARM_KPROBES_TEST
 	tristate "Kprobes test module"
 	depends on KPROBES && MODULES
@@ -1206,4 +1198,59 @@ config DEBUG_SET_MODULE_RONX
 	  against certain classes of kernel exploits.
 	  If in doubt, say "N".
 
+menuconfig CORESIGHT
+	bool "CoreSight Tracing Support"
+	select ARM_AMBA
+	help
+	  This framework provides a kernel interface for the CoreSight debug
+	  and trace drivers to register themselves with. It's intended to build
+	  a topological view of the CoreSight components based on a DT
+	  specification and configure the right serie of components when a
+	  trace source gets enabled.
+
+if CORESIGHT
+config CORESIGHT_LINKS_AND_SINKS
+	bool "CoreSight Link and Sink drivers"
+	help
+	  This enables support for CoreSight link and sink drivers that are
+	  responsible for transporting and collecting the trace data
+	  respectively.  Link and sinks are dynamically aggregated with a trace
+	  entity at run time to form a complete trace path.
+
+config CORESIGHT_LINK_AND_SINK_TMC
+	bool "Coresight generic TMC driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Trace Memory Controller driver.  Depending
+	  on its configuration the device can act as a link (embedded trace router
+	  - ETR) or sink (embedded trace FIFO).  The driver complies with the
+	  generic implementation of the component without special enhancement or
+	  added features.
+
+config CORESIGHT_SINK_TPIU
+	bool "Coresight generic TPIU driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Trace Port Interface Unit driver, responsible
+	  for bridging the gap between the on-chip coresight components and a trace
+	  port collection engine, typically connected to an external host for use
+	  case capturing more traces than the on-board coresight memory can handle.
+
+config CORESIGHT_SINK_ETBV10
+	bool "Coresight ETBv1.0 driver"
+	depends on CORESIGHT_LINKS_AND_SINKS
+	help
+	  This enables support for the Embedded Trace Buffer version 1.0 driver
+	  that complies with the generic implementation of the component without
+	  special enhancement or added features.
+
+config CORESIGHT_SOURCE_ETM3X
+	bool "CoreSight Embedded Trace Macrocell 3.x driver"
+	select CORESIGHT_LINKS_AND_SINKS
+	help
+	  This driver provides support for processor ETM3.x and PTM1.x modules,
+	  which allows tracing the instructions that a processor is executing
+	  This is primarily useful for instruction level tracing.  Depending
+	  the ETM version data tracing may also be available.
+endif
 endmenu
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 066b03480b63..8017cde13648 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -400,8 +400,7 @@ dtb_check_done:
 		add	sp, sp, r6
 #endif
 
-		tst	r4, #1
-		bleq	cache_clean_flush
+		bl	cache_clean_flush
 
 		adr	r0, BSYM(restart)
 		add	r0, r0, r6
@@ -1050,6 +1049,8 @@ cache_clean_flush:
 		b	call_cache_fn
 
 __armv4_mpu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r2, #1
 		mov	r3, #0
 		mcr	p15, 0, ip, c7, c6, 0	@ invalidate D cache
@@ -1067,6 +1068,8 @@ __armv4_mpu_cache_flush:
 		mov	pc, lr
 		
 __fa526_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r1, #0
 		mcr	p15, 0, r1, c7, c14, 0	@ clean and invalidate D cache
 		mcr	p15, 0, r1, c7, c5, 0	@ flush I cache
@@ -1075,13 +1078,16 @@ __fa526_cache_flush:
 
 __armv6_mmu_cache_flush:
 		mov	r1, #0
-		mcr	p15, 0, r1, c7, c14, 0	@ clean+invalidate D
+		tst	r4, #1
+		mcreq	p15, 0, r1, c7, c14, 0	@ clean+invalidate D
 		mcr	p15, 0, r1, c7, c5, 0	@ invalidate I+BTB
-		mcr	p15, 0, r1, c7, c15, 0	@ clean+invalidate unified
+		mcreq	p15, 0, r1, c7, c15, 0	@ clean+invalidate unified
 		mcr	p15, 0, r1, c7, c10, 4	@ drain WB
 		mov	pc, lr
 
 __armv7_mmu_cache_flush:
+		tst	r4, #1
+		bne	iflush
 		mrc	p15, 0, r10, c0, c1, 5	@ read ID_MMFR1
 		tst	r10, #0xf << 16		@ hierarchical cache (ARMv7)
 		mov	r10, #0
@@ -1142,6 +1148,8 @@ iflush:
 		mov	pc, lr
 
 __armv5tej_mmu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 1:		mrc	p15, 0, r15, c7, c14, 3	@ test,clean,invalidate D cache
 		bne	1b
 		mcr	p15, 0, r0, c7, c5, 0	@ flush I cache
@@ -1149,6 +1157,8 @@ __armv5tej_mmu_cache_flush:
 		mov	pc, lr
 
 __armv4_mmu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r2, #64*1024		@ default: 32K dcache size (*2)
 		mov	r11, #32		@ default: 32 byte line size
 		mrc	p15, 0, r3, c0, c0, 1	@ read cache type
@@ -1182,6 +1192,8 @@ no_cache_id:
 
 __armv3_mmu_cache_flush:
 __armv3_mpu_cache_flush:
+		tst	r4, #1
+		movne	pc, lr
 		mov	r1, #0
 		mcr	p15, 0, r1, c7, c0, 0	@ invalidate whole cache v3
 		mov	pc, lr
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 032030361bef..fdb4f9416353 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -312,7 +312,14 @@ dtb-$(CONFIG_ARCH_U300) += ste-u300.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \
 	vexpress-v2p-ca9.dtb \
 	vexpress-v2p-ca15-tc1.dtb \
-	vexpress-v2p-ca15_a7.dtb
+	vexpress-v2p-ca15_a7.dtb \
+	rtsm_ve-cortex_a9x2.dtb \
+	rtsm_ve-cortex_a9x4.dtb \
+	rtsm_ve-cortex_a15x1.dtb \
+	rtsm_ve-cortex_a15x2.dtb \
+	rtsm_ve-cortex_a15x4.dtb \
+	rtsm_ve-v2p-ca15x1-ca7x1.dtb \
+	rtsm_ve-v2p-ca15x4-ca7x4.dtb
 dtb-$(CONFIG_ARCH_VIRT) += xenvm-4.2.dtb
 dtb-$(CONFIG_ARCH_VT8500) += vt8500-bv07.dtb \
 	wm8505-ref.dtb \
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index e3f27ec31718..2e7d932887b5 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -183,7 +183,7 @@
 &usb {
 	status = "okay";
 
-	control@44e10000 {
+	control@44e10620 {
 		status = "okay";
 	};
 
@@ -204,7 +204,7 @@
 		dr_mode = "host";
 	};
 
-	dma-controller@07402000  {
+	dma-controller@47402000  {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index 7e6c64ed966d..801055a42998 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -325,7 +325,7 @@
 &usb {
 	status = "okay";
 
-	control@44e10000 {
+	control@44e10620 {
 		status = "okay";
 	};
 
@@ -346,7 +346,7 @@
 		dr_mode = "host";
 	};
 
-	dma-controller@07402000  {
+	dma-controller@47402000  {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 486880b74831..dd142bc677ca 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -334,7 +334,7 @@
 &usb {
 	status = "okay";
 
-	control@44e10000 {
+	control@44e10620 {
 		status = "okay";
 	};
 
diff --git a/arch/arm/boot/dts/am335x-igep0033.dtsi b/arch/arm/boot/dts/am335x-igep0033.dtsi
index 7063311a58d9..5942e7dab94f 100644
--- a/arch/arm/boot/dts/am335x-igep0033.dtsi
+++ b/arch/arm/boot/dts/am335x-igep0033.dtsi
@@ -202,7 +202,7 @@
 &usb {
 	status = "okay";
 
-	control@44e10000 {
+	control@44e10620 {
 		status = "okay";
 	};
 
@@ -223,7 +223,7 @@
 		dr_mode = "host";
 	};
 
-	dma-controller@07402000  {
+	dma-controller@47402000  {
 		status = "okay";
 	};
 };
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 6d95d3df33c7..ab01d0f98d1a 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -140,7 +140,7 @@
 			compatible = "ti,edma3";
 			ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2";
 			reg =	<0x49000000 0x10000>,
-				<0x44e10f90 0x10>;
+				<0x44e10f90 0x40>;
 			interrupts = <12 13 14>;
 			#dma-cells = <1>;
 			dma-channels = <64>;
@@ -448,7 +448,7 @@
 			ti,hwmods = "usb_otg_hs";
 			status = "disabled";
 
-			usb_ctrl_mod: control@44e10000 {
+			usb_ctrl_mod: control@44e10620 {
 				compatible = "ti,am335x-usb-ctrl-module";
 				reg = <0x44e10620 0x10
 					0x44e10648 0x4>;
@@ -551,7 +551,7 @@
 					"tx14", "tx15";
 			};
 
-			cppi41dma: dma-controller@07402000 {
+			cppi41dma: dma-controller@47402000 {
 				compatible = "ti,am3359-cppi41";
 				reg =  <0x47400000 0x1000
 					0x47402000 0x1000
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index c6bd4d986c29..8775681df7ed 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -161,9 +161,6 @@
 			ti,hwmods = "mailbox";
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <8>;
-			ti,mbox-names = "wkup_m3";
-			ti,mbox-data = <0 0 0 0>;
-			status = "disabled";
 		};
 
 		timer1: timer@44e31000 {
diff --git a/arch/arm/boot/dts/armada-370-netgear-rn102.dts b/arch/arm/boot/dts/armada-370-netgear-rn102.dts
index 651aeb5ef439..f3188e953de4 100644
--- a/arch/arm/boot/dts/armada-370-netgear-rn102.dts
+++ b/arch/arm/boot/dts/armada-370-netgear-rn102.dts
@@ -144,6 +144,10 @@
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
 
+				/* Use Hardware BCH ECC */
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
+
 				partition@0 {
 					label = "u-boot";
 					reg = <0x0000000 0x180000>;  /* 1.5MB */
diff --git a/arch/arm/boot/dts/armada-370-netgear-rn104.dts b/arch/arm/boot/dts/armada-370-netgear-rn104.dts
index 4e27587667bf..da406c1c726a 100644
--- a/arch/arm/boot/dts/armada-370-netgear-rn104.dts
+++ b/arch/arm/boot/dts/armada-370-netgear-rn104.dts
@@ -146,6 +146,10 @@
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
 
+				/* Use Hardware BCH ECC */
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
+
 				partition@0 {
 					label = "u-boot";
 					reg = <0x0000000 0x180000>;  /* 1.5MB */
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 74b5964430ac..e5d4902c630f 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -226,6 +226,7 @@
 				#size-cells = <0>;
 				compatible = "marvell,orion-mdio";
 				reg = <0x72004 0x4>;
+				clocks = <&gateclk 4>;
 			};
 
 			eth1: ethernet@74000 {
diff --git a/arch/arm/boot/dts/armada-370.dtsi b/arch/arm/boot/dts/armada-370.dtsi
index 0d8530c98cf5..34841fc1a977 100644
--- a/arch/arm/boot/dts/armada-370.dtsi
+++ b/arch/arm/boot/dts/armada-370.dtsi
@@ -106,11 +106,6 @@
 				reg = <0x11100 0x20>;
 			};
 
-			system-controller@18200 {
-				compatible = "marvell,armada-370-xp-system-controller";
-				reg = <0x18200 0x100>;
-			};
-
 			pinctrl {
 				compatible = "marvell,mv88f6710-pinctrl";
 				reg = <0x18000 0x38>;
@@ -167,6 +162,11 @@
 				interrupts = <91>;
 			};
 
+			system-controller@18200 {
+				compatible = "marvell,armada-370-xp-system-controller";
+				reg = <0x18200 0x100>;
+			};
+
 			gateclk: clock-gating-control@18220 {
 				compatible = "marvell,armada-370-gating-clock";
 				reg = <0x18220 0x4>;
diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts
index bcf6d79a57ec..8c2fe44e4dfe 100644
--- a/arch/arm/boot/dts/armada-xp-db.dts
+++ b/arch/arm/boot/dts/armada-xp-db.dts
@@ -40,7 +40,7 @@
 			/* Device Bus parameters are required */
 
 			/* Read parameters */
-			devbus,bus-width    = <8>;
+			devbus,bus-width    = <16>;
 			devbus,turn-off-ps  = <60000>;
 			devbus,badr-skew-ps = <0>;
 			devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index 274e2ad5f51c..df5c34284dbd 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -49,7 +49,7 @@
 			/* Device Bus parameters are required */
 
 			/* Read parameters */
-			devbus,bus-width    = <8>;
+			devbus,bus-width    = <16>;
 			devbus,turn-off-ps  = <60000>;
 			devbus,badr-skew-ps = <0>;
 			devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
index ff049ee862eb..b4aba09de911 100644
--- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
+++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts
@@ -224,6 +224,10 @@
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
 
+				/* Use Hardware BCH ECC */
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
+
 				partition@0 {
 					label = "u-boot";
 					reg = <0x0000000 0x180000>;  /* 1.5MB */
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index 99bcf76e6953..1c6bd83bde5e 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -23,7 +23,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0 0x00000000 0 0xC0000000>; /* 3 GB */
+		reg = <0 0x00000000 0 0x40000000>; /* 1 GB soldered on */
 	};
 
 	soc {
@@ -37,7 +37,7 @@
 			/* Device Bus parameters are required */
 
 			/* Read parameters */
-			devbus,bus-width    = <8>;
+			devbus,bus-width    = <16>;
 			devbus,turn-off-ps  = <60000>;
 			devbus,badr-skew-ps = <0>;
 			devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index fece8665fb63..b8f234bf7de8 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -535,6 +535,7 @@
 				compatible = "atmel,hsmci";
 				reg = <0xfff80000 0x600>;
 				interrupts = <10 IRQ_TYPE_LEVEL_HIGH 0>;
+				pinctrl-names = "default";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
@@ -544,6 +545,7 @@
 				compatible = "atmel,hsmci";
 				reg = <0xfff84000 0x600>;
 				interrupts = <11 IRQ_TYPE_LEVEL_HIGH 0>;
+				pinctrl-names = "default";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				status = "disabled";
diff --git a/arch/arm/boot/dts/clcd-panels.dtsi b/arch/arm/boot/dts/clcd-panels.dtsi
new file mode 100644
index 000000000000..0b0ff6ead4b2
--- /dev/null
+++ b/arch/arm/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+	panels {
+		panel@0 {
+			compatible	= "panel";
+			mode		= "VGA";
+			refresh		= <60>;
+			xres		= <640>;
+			yres		= <480>;
+			pixclock	= <39721>;
+			left_margin	= <40>;
+			right_margin	= <24>;
+			upper_margin	= <32>;
+			lower_margin	= <11>;
+			hsync_len	= <96>;
+			vsync_len	= <2>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+
+		panel@1 {
+			compatible	= "panel";
+			mode		= "XVGA";
+			refresh		= <60>;
+			xres		= <1024>;
+			yres		= <768>;
+			pixclock	= <15748>;
+			left_margin	= <152>;
+			right_margin	= <48>;
+			upper_margin	= <23>;
+			lower_margin	= <3>;
+			hsync_len	= <104>;
+			vsync_len	= <4>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index 5babba0a3a75..9381754b35cc 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -50,13 +50,13 @@
 
 	mcspi1_pins: pinmux_mcspi1_pins {
 		pinctrl-single,pins = <
-			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */
-			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */
-			0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */
-			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */
-			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */
-			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */
-			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */
+			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi1_sclk */
+			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi1_d1 */
+			0x3ac (PIN_INPUT | MUX_MODE0) /* spi1_d0 */
+			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs0 */
+			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs1 */
+			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs2.hdmi1_hpd */
+			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs3.hdmi1_cec */
 		>;
 	};
 
@@ -182,6 +182,7 @@
 					regulator-name = "ldo3";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
 					regulator-boot-on;
 				};
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 1fd75aa4639d..f60aeee2fc9e 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -178,7 +178,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio2: gpio@48055000 {
@@ -189,7 +189,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio3: gpio@48057000 {
@@ -200,7 +200,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio4: gpio@48059000 {
@@ -211,7 +211,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio5: gpio@4805b000 {
@@ -222,7 +222,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio6: gpio@4805d000 {
@@ -233,7 +233,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio7: gpio@48051000 {
@@ -244,7 +244,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio8: gpio@48053000 {
@@ -255,7 +255,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		uart1: serial@4806a000 {
@@ -458,7 +458,7 @@
 		};
 
 		wdt2: wdt@4ae14000 {
-			compatible = "ti,omap4-wdt";
+			compatible = "ti,omap3-wdt";
 			reg = <0x4ae14000 0x80>;
 			interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "wd_timer2";
diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts
index b42e658876e5..457112d659ea 100644
--- a/arch/arm/boot/dts/exynos5250-arndale.dts
+++ b/arch/arm/boot/dts/exynos5250-arndale.dts
@@ -287,6 +287,7 @@
 					regulator-name = "vdd_g3d";
 					regulator-min-microvolt = <1000000>;
 					regulator-max-microvolt = <1000000>;
+					regulator-always-on;
 					regulator-boot-on;
 					op_mode = <1>;
 				};
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 8db792b26f79..15eb8d4e4d3c 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -323,6 +323,13 @@
 			#dma-cells = <1>;
 			#dma-channels = <8>;
 			#dma-requests = <1>;
+			/*
+			 * MDMA1 can support both secure and non-secure
+			 * AXI transactions. When this is enabled in the kernel
+			 * for boards that run in secure mode, we are getting
+			 * imprecise external aborts causing the kernel to oops.
+			 */
+			status = "disabled";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/hi3620.dtsi b/arch/arm/boot/dts/hi3620.dtsi
index ab1116d086be..83a5b8685bd9 100644
--- a/arch/arm/boot/dts/hi3620.dtsi
+++ b/arch/arm/boot/dts/hi3620.dtsi
@@ -73,7 +73,7 @@
 
 		L2: l2-cache {
 			compatible = "arm,pl310-cache";
-			reg = <0xfc10000 0x100000>;
+			reg = <0x100000 0x100000>;
 			interrupts = <0 15 4>;
 			cache-unified;
 			cache-level = <2>;
diff --git a/arch/arm/boot/dts/hip04.dtsi b/arch/arm/boot/dts/hip04.dtsi
new file mode 100644
index 000000000000..238814596a87
--- /dev/null
+++ b/arch/arm/boot/dts/hip04.dtsi
@@ -0,0 +1,984 @@
+/*
+ * Hisilicon Ltd. HiP04 SoC
+ *
+ * Copyright (C) 2013-2014 Hisilicon Ltd.
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ *
+ * Author: Haojian Zhuang <haojian.zhuang@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+	/* memory bus is 64-bit */
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &uart0;
+	};
+
+	bootwrapper {
+		compatible = "hisilicon,hip04-bootwrapper";
+		boot-method = <0x10c00000 0x10000>, <0xe0000100 0x1000>;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+				core2 {
+					cpu = <&CPU2>;
+				};
+				core3 {
+					cpu = <&CPU3>;
+				};
+			};
+			cluster1 {
+				core0 {
+					cpu = <&CPU4>;
+				};
+				core1 {
+					cpu = <&CPU5>;
+				};
+				core2 {
+					cpu = <&CPU6>;
+				};
+				core3 {
+					cpu = <&CPU7>;
+				};
+			};
+			cluster2 {
+				core0 {
+					cpu = <&CPU8>;
+				};
+				core1 {
+					cpu = <&CPU9>;
+				};
+				core2 {
+					cpu = <&CPU10>;
+				};
+				core3 {
+					cpu = <&CPU11>;
+				};
+			};
+			cluster3 {
+				core0 {
+					cpu = <&CPU12>;
+				};
+				core1 {
+					cpu = <&CPU13>;
+				};
+				core2 {
+					cpu = <&CPU14>;
+				};
+				core3 {
+					cpu = <&CPU15>;
+				};
+			};
+		};
+		CPU0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+		CPU1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+		CPU2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+		};
+		CPU3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+		};
+		CPU4: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x100>;
+		};
+		CPU5: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x101>;
+		};
+		CPU6: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x102>;
+		};
+		CPU7: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x103>;
+		};
+		CPU8: cpu@200 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x200>;
+		};
+		CPU9: cpu@201 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x201>;
+		};
+		CPU10: cpu@202 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x202>;
+		};
+		CPU11: cpu@203 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x203>;
+		};
+		CPU12: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x300>;
+		};
+		CPU13: cpu@301 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x301>;
+		};
+		CPU14: cpu@302 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x302>;
+		};
+		CPU15: cpu@303 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0x303>;
+		};
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupt-parent = <&gic>;
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	clk_50m: clk_50m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <50000000>;
+	};
+
+	clk_168m: clk_168m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <168000000>;
+	};
+
+	clk_375m: clk_375m {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <375000000>;
+	};
+
+	soc {
+		/* It's a 32-bit SoC. */
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "simple-bus";
+		interrupt-parent = <&gic>;
+		ranges = <0 0 0xe0000000 0x10000000>;
+
+		gic: interrupt-controller@c01000 {
+			compatible = "hisilicon,hip04-intc";
+			#interrupt-cells = <3>;
+			#address-cells = <0>;
+			interrupt-controller;
+			interrupts = <1 9 0xf04>;
+
+			reg = <0xc01000 0x1000>, <0xc02000 0x1000>,
+			      <0xc04000 0x2000>, <0xc06000 0x2000>;
+		};
+
+		sysctrl: sysctrl {
+			compatible = "hisilicon,sysctrl";
+			reg = <0x3e00000 0x00100000>;
+		};
+
+		fabric: fabric {
+			compatible = "hisilicon,hip04-fabric";
+			reg = <0x302a000 0x1000>;
+		};
+
+		dual_timer0: dual_timer@3000000 {
+			compatible = "arm,sp804", "arm,primecell";
+			reg = <0x3000000 0x1000>;
+			interrupts = <0 224 4>;
+			clocks = <&clk_50m>, <&clk_50m>;
+			clock-names = "apb_pclk";
+		};
+
+		arm-pmu {
+			compatible = "arm,cortex-a15-pmu";
+			interrupts = <0 64 4>,
+				     <0 65 4>,
+				     <0 66 4>,
+				     <0 67 4>,
+				     <0 68 4>,
+				     <0 69 4>,
+				     <0 70 4>,
+				     <0 71 4>,
+				     <0 72 4>,
+				     <0 73 4>,
+				     <0 74 4>,
+				     <0 75 4>,
+				     <0 76 4>,
+				     <0 77 4>,
+				     <0 78 4>,
+				     <0 79 4>;
+		};
+
+		uart0: uart@4007000 {
+			compatible = "snps,dw-apb-uart";
+			reg = <0x4007000 0x1000>;
+			interrupts = <0 381 4>;
+			clocks = <&clk_168m>;
+			clock-names = "uartclk";
+			reg-shift = <2>;
+			status = "disabled";
+		};
+
+		sata0: sata@a000000 {
+			compatible = "hisilicon,hisi-ahci";
+			reg = <0xa000000 0x1000000>;
+			interrupts = <0 372 4>;
+		};
+
+	};
+
+	etb@0,e3c42000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3c42000 0 0x1000>;
+
+		coresight-default-sink;
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb0_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator0_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3c82000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3c82000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb1_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator1_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3cc2000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3cc2000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb2_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator2_out_port0>;
+			};
+		};
+	};
+
+	etb@0,e3d02000 {
+		compatible = "arm,coresight-etb10", "arm,primecell";
+		reg = <0 0xe3d02000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			etb3_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&replicator3_out_port0>;
+			};
+		};
+	};
+
+	tpiu@0,e3c05000 {
+		compatible = "arm,coresight-tpiu", "arm,primecell";
+		reg = <0 0xe3c05000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		port {
+			tpiu_in_port: endpoint@0 {
+				slave-mode;
+				remote-endpoint = <&funnel4_out_port0>;
+			};
+		};
+	};
+
+	replicator0 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator0_out_port0: endpoint {
+					remote-endpoint = <&etb0_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator0_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port0>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator0_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel0_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator1 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator1_out_port0: endpoint {
+					remote-endpoint = <&etb1_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator1_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port1>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator1_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel1_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator2 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator2_out_port0: endpoint {
+					remote-endpoint = <&etb2_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+					replicator2_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port2>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator2_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel2_out_port0>;
+				};
+			};
+		};
+	};
+
+	replicator3 {
+		/* non-configurable replicators don't show up on the
+		 * AMBA bus.  As such no need to add "arm,primecell".
+		 */
+		compatible = "arm,coresight-replicator";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* replicator output ports */
+			port@0 {
+				reg = <0>;
+				replicator3_out_port0: endpoint {
+					remote-endpoint = <&etb3_in_port>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+				replicator3_out_port1: endpoint {
+					remote-endpoint = <&funnel4_in_port3>;
+				};
+			};
+
+			/* replicator input port */
+			port@2 {
+				reg = <0>;
+				replicator3_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&funnel3_out_port0>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c41000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c41000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel0_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator0_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel0_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm0_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel0_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm1_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel0_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm2_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel0_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm3_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c81000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c81000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel1_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator1_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel1_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm4_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel1_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm5_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel1_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm6_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel1_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm7_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3cc1000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3cc1000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel2_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator2_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel2_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm8_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel2_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm9_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel2_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm10_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel2_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm11_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3d01000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3d01000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel3_out_port0: endpoint {
+					remote-endpoint =
+						<&replicator3_in_port0>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel3_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm12_out_port>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel3_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm13_out_port>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel3_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm14_out_port>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel3_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint = <&ptm15_out_port>;
+				};
+			};
+		};
+	};
+
+	funnel@0,e3c04000 {
+		compatible = "arm,coresight-funnel", "arm,primecell";
+		reg = <0 0xe3c04000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			/* funnel output port */
+			port@0 {
+				reg = <0>;
+				funnel4_out_port0: endpoint {
+					remote-endpoint = <&tpiu_in_port>;
+				};
+			};
+
+			/* funnel input ports */
+			port@1 {
+				reg = <0>;
+				funnel4_in_port0: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator0_out_port1>;
+				};
+			};
+
+			port@2 {
+				reg = <1>;
+				funnel4_in_port1: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator1_out_port1>;
+				};
+			};
+
+			port@3 {
+				reg = <2>;
+				funnel4_in_port2: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator2_out_port1>;
+				};
+			};
+
+			port@4 {
+				reg = <3>;
+				funnel4_in_port3: endpoint {
+					slave-mode;
+					remote-endpoint =
+						<&replicator3_out_port1>;
+				};
+			};
+		};
+	};
+
+	ptm@0,e3c7c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7c000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU0>;
+		port {
+			ptm0_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3c7d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7d000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU1>;
+		port {
+			ptm1_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3c7e000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7e000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU2>;
+		port {
+			ptm2_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3c7f000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3c7f000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU3>;
+		port {
+			ptm3_out_port: endpoint {
+				remote-endpoint = <&funnel0_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3cbc000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbc000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU4>;
+		port {
+			ptm4_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3cbd000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbd000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU5>;
+		port {
+			ptm5_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3cbe000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbe000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU6>;
+		port {
+			ptm6_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3cbf000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cbf000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU7>;
+		port {
+			ptm7_out_port: endpoint {
+				remote-endpoint = <&funnel1_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3cfc000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfc000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU8>;
+		port {
+			ptm8_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3cfd000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfd000 0 0x1000>;
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU9>;
+		port {
+			ptm9_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3cfe000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cfe000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU10>;
+		port {
+			ptm10_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3cff000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3cff000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU11>;
+		port {
+			ptm11_out_port: endpoint {
+				remote-endpoint = <&funnel2_in_port3>;
+			};
+		};
+	};
+
+	ptm@0,e3d3c000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3c000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU12>;
+		port {
+			ptm12_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port0>;
+			};
+		};
+	};
+
+	ptm@0,e3d3d000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3d000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU13>;
+		port {
+			ptm13_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port1>;
+			};
+		};
+	};
+
+	ptm@0,e3d3e000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3e000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU14>;
+		port {
+			ptm14_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port2>;
+			};
+		};
+	};
+
+	ptm@0,e3d3f000 {
+		compatible = "arm,coresight-etm3x", "arm,primecell";
+		reg = <0 0xe3d3f000 0 0x1000>;
+
+		clocks = <&clk_375m>;
+		clock-names = "apb_pclk";
+		cpu = <&CPU15>;
+		port {
+			ptm15_out_port: endpoint {
+				remote-endpoint = <&funnel3_in_port3>;
+			};
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 737ed5da8f71..de1611966d8b 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -30,6 +30,7 @@
 		spi2 = &spi3;
 		usb0 = &usbotg;
 		usb1 = &usbhost1;
+		ethernet0 = &fec;
 	};
 
 	cpus {
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 826231eb4446..da2eb7f6a5b2 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -30,6 +30,7 @@
 		spi0 = &cspi1;
 		spi1 = &cspi2;
 		spi2 = &cspi3;
+		ethernet0 = &fec;
 	};
 
 	aitc: aitc-interrupt-controller@e0000000 {
diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi
index 4bcdd3ad15e5..e1b601595a09 100644
--- a/arch/arm/boot/dts/imx51.dtsi
+++ b/arch/arm/boot/dts/imx51.dtsi
@@ -27,6 +27,7 @@
 		spi0 = &ecspi1;
 		spi1 = &ecspi2;
 		spi2 = &cspi;
+		ethernet0 = &fec;
 	};
 
 	tzic: tz-interrupt-controller@e0000000 {
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 4307e80b2d2e..50eda500f39a 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -33,6 +33,7 @@
 		spi0 = &ecspi1;
 		spi1 = &ecspi2;
 		spi2 = &cspi;
+		ethernet0 = &fec;
 	};
 
 	cpus {
@@ -87,7 +88,7 @@
 		ipu: ipu@18000000 {
 			#crtc-cells = <1>;
 			compatible = "fsl,imx53-ipu";
-			reg = <0x18000000 0x080000000>;
+			reg = <0x18000000 0x08000000>;
 			interrupts = <11 10>;
 			clocks = <&clks 59>, <&clks 110>, <&clks 61>;
 			clock-names = "bus", "di0", "di1";
diff --git a/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
index dc86429756d7..4651672bda89 100644
--- a/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
+++ b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
@@ -30,6 +30,16 @@
 		bootargs = "console=ttyS0,115200n8 earlyprintk";
 	};
 
+	mbus {
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+        };
+
 	ocp@f1000000 {
 		pinctrl@10000 {
 			pmx_usb_led: pmx-usb-led {
@@ -73,14 +83,6 @@
 		ehci@50000 {
 			status = "okay";
 		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio-leds {
diff --git a/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
index aa78c2d11fe7..e2cc85cc3b87 100644
--- a/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
+++ b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
@@ -4,6 +4,16 @@
 / {
 	model = "ZyXEL NSA310";
 
+	mbus {
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 
@@ -26,14 +36,6 @@
 			status = "okay";
 			nr-ports = <2>;
 		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio_poweroff {
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index d3f8a6e8ca20..69409f7e05dc 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -275,6 +275,8 @@
 			gpmc,num-waitpins = <4>;
 			ti,hwmods = "gpmc";
 			ti,no-idle-on-init;
+			clocks = <&l3_div_ck>;
+			clock-names = "fck";
 		};
 
 		uart1: serial@4806a000 {
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index a72813a9663e..7a16647c76f4 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -302,6 +302,8 @@
 			gpmc,num-cs = <8>;
 			gpmc,num-waitpins = <4>;
 			ti,hwmods = "gpmc";
+			clocks = <&l3_iclk_div>;
+			clock-names = "fck";
 		};
 
 		i2c1: i2c@48070000 {
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
new file mode 100644
index 000000000000..c9eee916aa7e
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
@@ -0,0 +1,159 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x1CT
+ *
+ * RTSM_VE_Cortex_A15x1.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x1";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x1", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
new file mode 100644
index 000000000000..853a166e3c32
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
@@ -0,0 +1,165 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x2CT
+ *
+ * RTSM_VE_Cortex_A15x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x2";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x2", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
new file mode 100644
index 000000000000..c1947a3a5c88
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
@@ -0,0 +1,177 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ *
+ * RTSM_VE_Cortex_A15x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA15x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
new file mode 100644
index 000000000000..fca6b2f79677
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
@@ -0,0 +1,171 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx2CT
+ *
+ * RTSM_VE_Cortex_A9x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA9x2";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a9x2", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x80000000>;
+	};
+
+	scu@2c000000 {
+		compatible = "arm,cortex-a9-scu";
+		reg = <0x2c000000 0x58>;
+	};
+
+	timer@2c000600 {
+		compatible = "arm,cortex-a9-twd-timer";
+		reg = <0x2c000600 0x20>;
+		interrupts = <1 13 0xf04>;
+	};
+
+	watchdog@2c000620 {
+		compatible = "arm,cortex-a9-twd-wdt";
+		reg = <0x2c000620 0x20>;
+		interrupts = <1 14 0xf04>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x2c001000 0x1000>,
+		      <0x2c000100 0x100>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0x08000000 0x04000000>,
+			 <1 0 0x14000000 0x04000000>,
+			 <2 0 0x18000000 0x04000000>,
+			 <3 0 0x1c000000 0x04000000>,
+			 <4 0 0x0c000000 0x04000000>,
+			 <5 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
new file mode 100644
index 000000000000..fd8a6ed97a04
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
@@ -0,0 +1,183 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx4CT
+ *
+ * RTSM_VE_Cortex_A9x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+	model = "RTSM_VE_CortexA9x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a9x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+		};
+
+		cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <2>;
+		};
+
+		cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <3>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0x80000000>;
+	};
+
+	scu@2c000000 {
+		compatible = "arm,cortex-a9-scu";
+		reg = <0x2c000000 0x58>;
+	};
+
+	timer@2c000600 {
+		compatible = "arm,cortex-a9-twd-timer";
+		reg = <0x2c000600 0x20>;
+		interrupts = <1 13 0xf04>;
+	};
+
+	watchdog@2c000620 {
+		compatible = "arm,cortex-a9-twd-wdt";
+		reg = <0x2c000620 0x20>;
+		interrupts = <1 14 0xf04>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x2c001000 0x1000>,
+		      <0x2c000100 0x100>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0x08000000 0x04000000>,
+			 <1 0 0x14000000 0x04000000>,
+			 <2 0 0x18000000 0x04000000>,
+			 <3 0 0x1c000000 0x04000000>,
+			 <4 0 0x0c000000 0x04000000>,
+			 <5 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
new file mode 100644
index 000000000000..a2d895ee5faa
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
@@ -0,0 +1,231 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * Motherboard component
+ *
+ * VEMotherBoard.lisa
+ */
+
+	motherboard {
+		compatible = "arm,vexpress,v2m-p1", "simple-bus";
+		arm,hbi = <0x190>;
+		arm,vexpress,site = <0>;
+		arm,v2m-memory-map = "rs1";
+		#address-cells = <2>; /* SMB chipselect number and offset */
+		#size-cells = <1>;
+		#interrupt-cells = <1>;
+		ranges;
+
+		flash@0,00000000 {
+			compatible = "arm,vexpress-flash", "cfi-flash";
+			reg = <0 0x00000000 0x04000000>,
+			      <4 0x00000000 0x04000000>;
+			bank-width = <4>;
+		};
+
+		vram@2,00000000 {
+			compatible = "arm,vexpress-vram";
+			reg = <2 0x00000000 0x00800000>;
+		};
+
+		ethernet@2,02000000 {
+			compatible = "smsc,lan91c111";
+			reg = <2 0x02000000 0x10000>;
+			interrupts = <15>;
+		};
+
+		iofpga@3,00000000 {
+			compatible = "arm,amba-bus", "simple-bus";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0 3 0 0x200000>;
+
+			v2m_sysreg: sysreg@010000 {
+				compatible = "arm,vexpress-sysreg";
+				reg = <0x010000 0x1000>;
+				gpio-controller;
+				#gpio-cells = <2>;
+			};
+
+			v2m_sysctl: sysctl@020000 {
+				compatible = "arm,sp810", "arm,primecell";
+				reg = <0x020000 0x1000>;
+				clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>;
+				clock-names = "refclk", "timclk", "apb_pclk";
+				#clock-cells = <1>;
+				clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+			};
+
+			aaci@040000 {
+				compatible = "arm,pl041", "arm,primecell";
+				reg = <0x040000 0x1000>;
+				interrupts = <11>;
+				clocks = <&smbclk>;
+				clock-names = "apb_pclk";
+			};
+
+			mmci@050000 {
+				compatible = "arm,pl180", "arm,primecell";
+				reg = <0x050000 0x1000>;
+				interrupts = <9 10>;
+				cd-gpios = <&v2m_sysreg 0 0>;
+				wp-gpios = <&v2m_sysreg 1 0>;
+				max-frequency = <12000000>;
+				vmmc-supply = <&v2m_fixed_3v3>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "mclk", "apb_pclk";
+			};
+
+			kmi@060000 {
+				compatible = "arm,pl050", "arm,primecell";
+				reg = <0x060000 0x1000>;
+				interrupts = <12>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "KMIREFCLK", "apb_pclk";
+			};
+
+			kmi@070000 {
+				compatible = "arm,pl050", "arm,primecell";
+				reg = <0x070000 0x1000>;
+				interrupts = <13>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "KMIREFCLK", "apb_pclk";
+			};
+
+			v2m_serial0: uart@090000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x090000 0x1000>;
+				interrupts = <5>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial1: uart@0a0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0a0000 0x1000>;
+				interrupts = <6>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial2: uart@0b0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0b0000 0x1000>;
+				interrupts = <7>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			v2m_serial3: uart@0c0000 {
+				compatible = "arm,pl011", "arm,primecell";
+				reg = <0x0c0000 0x1000>;
+				interrupts = <8>;
+				clocks = <&v2m_clk24mhz>, <&smbclk>;
+				clock-names = "uartclk", "apb_pclk";
+			};
+
+			wdt@0f0000 {
+				compatible = "arm,sp805", "arm,primecell";
+				reg = <0x0f0000 0x1000>;
+				interrupts = <0>;
+				clocks = <&v2m_refclk32khz>, <&smbclk>;
+				clock-names = "wdogclk", "apb_pclk";
+			};
+
+			v2m_timer01: timer@110000 {
+				compatible = "arm,sp804", "arm,primecell";
+				reg = <0x110000 0x1000>;
+				interrupts = <2>;
+				clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&smbclk>;
+				clock-names = "timclken1", "timclken2", "apb_pclk";
+			};
+
+			v2m_timer23: timer@120000 {
+				compatible = "arm,sp804", "arm,primecell";
+				reg = <0x120000 0x1000>;
+				interrupts = <3>;
+				clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&smbclk>;
+				clock-names = "timclken1", "timclken2", "apb_pclk";
+			};
+
+			rtc@170000 {
+				compatible = "arm,pl031", "arm,primecell";
+				reg = <0x170000 0x1000>;
+				interrupts = <4>;
+				clocks = <&smbclk>;
+				clock-names = "apb_pclk";
+			};
+
+			clcd@1f0000 {
+				compatible = "arm,pl111", "arm,primecell";
+				reg = <0x1f0000 0x1000>;
+				interrupts = <14>;
+				clocks = <&v2m_oscclk1>, <&smbclk>;
+				clock-names = "v2m:oscclk1", "apb_pclk";
+				mode = "VGA";
+				use_dma = <0>;
+				framebuffer = <0x18000000 0x00180000>;
+			};
+
+			virtio_block@0130000 {
+				compatible = "virtio,mmio";
+				reg = <0x130000 0x200>;
+				interrupts = <42>;
+			};
+
+		};
+
+		v2m_fixed_3v3: fixedregulator@0 {
+			compatible = "regulator-fixed";
+			regulator-name = "3V3";
+			regulator-min-microvolt = <3300000>;
+			regulator-max-microvolt = <3300000>;
+			regulator-always-on;
+		};
+
+		v2m_clk24mhz: clk24mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <24000000>;
+			clock-output-names = "v2m:clk24mhz";
+		};
+
+		v2m_refclk1mhz: refclk1mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <1000000>;
+			clock-output-names = "v2m:refclk1mhz";
+		};
+
+		v2m_refclk32khz: refclk32khz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+			clock-output-names = "v2m:refclk32khz";
+		};
+
+		mcc {
+			compatible = "simple-bus";
+			arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+			v2m_oscclk1: osc@1 {
+				/* CLCD clock */
+				compatible = "arm,vexpress-osc";
+				arm,vexpress-sysreg,func = <1 1>;
+				freq-range = <23750000 63500000>;
+				#clock-cells = <0>;
+				clock-output-names = "v2m:oscclk1";
+			};
+
+			muxfpga@0 {
+				compatible = "arm,vexpress-muxfpga";
+				arm,vexpress-sysreg,func = <7 0>;
+			};
+
+			shutdown@0 {
+				compatible = "arm,vexpress-shutdown";
+				arm,vexpress-sysreg,func = <8 0>;
+			};
+		};
+	};
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
new file mode 100644
index 000000000000..c59f4b5cdf9e
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
@@ -0,0 +1,233 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x1_A7x1.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+	model = "RTSM_VE_CortexA15x1-A7x1";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x1_a7x1", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	clusters {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cluster0: cluster@0 {
+			reg = <0>;
+//			freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+			};
+		};
+
+		cluster1: cluster@1 {
+			reg = <1>;
+//			freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core1: core@0 {
+					reg = <0>;
+				};
+
+			};
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core1>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400", "arm,cci";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+	dcscb@60000000 {
+		compatible = "arm,rtsm,dcscb";
+		reg = <0 0x60000000 0 0x1000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
new file mode 100644
index 000000000000..5f1e727be28c
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
@@ -0,0 +1,317 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x4_A7x4.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+	model = "RTSM_VE_CortexA15x4-A7x4";
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,rtsm_ve,cortex_a15x4_a7x4", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	clusters {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cluster0: cluster@0 {
+			reg = <0>;
+//			freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+				core1: core@1 {
+					reg = <1>;
+				};
+
+				core2: core@2 {
+					reg = <2>;
+				};
+
+				core3: core@3 {
+					reg = <3>;
+				};
+
+			};
+		};
+
+		cluster1: cluster@1 {
+			reg = <1>;
+//			freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core4: core@0 {
+					reg = <0>;
+				};
+
+				core5: core@1 {
+					reg = <1>;
+				};
+
+				core6: core@2 {
+					reg = <2>;
+				};
+				
+				core7: core@3 {
+					reg = <3>;
+				};
+				
+			};
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			cluster = <&cluster0>;
+			core = <&core1>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <2>;
+			cluster = <&cluster0>;
+			core = <&core2>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <3>;
+			cluster = <&cluster0>;
+			core = <&core3>;
+//			clock-frequency = <1000000000>;
+			cci-control-port = <&cci_control1>;
+		};
+
+		cpu4: cpu@4 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x100>;
+			cluster = <&cluster1>;
+			core = <&core4>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+
+		cpu5: cpu@5 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x101>;
+			cluster = <&cluster1>;
+			core = <&core5>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+		
+		cpu6: cpu@6 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x102>;
+			cluster = <&cluster1>;
+			core = <&core6>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+		
+		cpu7: cpu@7 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a7";
+			reg = <0x103>;
+			cluster = <&cluster1>;
+			core = <&core7>;
+//			clock-frequency = <800000000>;
+			cci-control-port = <&cci_control2>;
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>;
+	};
+
+	cci@2c090000 {
+		compatible = "arm,cci-400", "arm,cci";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		reg = <0 0x2c090000 0 0x1000>;
+		ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+		cci_control1: slave-if@4000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x4000 0x1000>;
+		};
+
+		cci_control2: slave-if@5000 {
+			compatible = "arm,cci-400-ctrl-if";
+			interface-type = "ace";
+			reg = <0x5000 0x1000>;
+		};
+	};
+
+	dcscb@60000000 {
+		compatible = "arm,rtsm,dcscb";
+		reg = <0 0x60000000 0 0x1000>;
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x1000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		osc@0 {
+			/* ACLK clock to the AXI master port on the test chip */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 0>;
+			freq-range = <30000000 50000000>;
+			#clock-cells = <0>;
+			clock-output-names = "extsaxiclk";
+		};
+
+		oscclk1: osc@1 {
+			/* Reference clock for the CLCD */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 1>;
+			freq-range = <10000000 80000000>;
+			#clock-cells = <0>;
+			clock-output-names = "clcdclk";
+		};
+
+		smbclk: oscclk2: osc@2 {
+			/* Reference clock for the test chip internal PLLs */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 2>;
+			freq-range = <33000000 100000000>;
+			#clock-cells = <0>;
+			clock-output-names = "tcrefclk";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/s3c6410-mini6410.dts b/arch/arm/boot/dts/s3c6410-mini6410.dts
index 57e00f9bce99..a25debb50401 100644
--- a/arch/arm/boot/dts/s3c6410-mini6410.dts
+++ b/arch/arm/boot/dts/s3c6410-mini6410.dts
@@ -198,10 +198,6 @@
 	status = "okay";
 };
 
-&pwm {
-	status = "okay";
-};
-
 &pinctrl0 {
 	gpio_leds: gpio-leds {
 		samsung,pins = "gpk-4", "gpk-5", "gpk-6", "gpk-7";
diff --git a/arch/arm/boot/dts/s3c64xx.dtsi b/arch/arm/boot/dts/s3c64xx.dtsi
index 4e3be4d3493d..4f1eff3420f6 100644
--- a/arch/arm/boot/dts/s3c64xx.dtsi
+++ b/arch/arm/boot/dts/s3c64xx.dtsi
@@ -168,7 +168,6 @@
 			clocks = <&clocks PCLK_PWM>;
 			samsung,pwm-outputs = <0>, <1>;
 			#pwm-cells = <3>;
-			status = "disabled";
 		};
 
 		pinctrl0: pinctrl@7f008000 {
diff --git a/arch/arm/boot/dts/sama5d3_can.dtsi b/arch/arm/boot/dts/sama5d3_can.dtsi
index a0775851cce5..eaf41451ad0c 100644
--- a/arch/arm/boot/dts/sama5d3_can.dtsi
+++ b/arch/arm/boot/dts/sama5d3_can.dtsi
@@ -40,7 +40,7 @@
 						atmel,clk-output-range = <0 66000000>;
 					};
 
-					can1_clk: can0_clk {
+					can1_clk: can1_clk {
 						#clock-cells = <0>;
 						reg = <41>;
 						atmel,clk-output-range = <0 66000000>;
diff --git a/arch/arm/boot/dts/ste-ccu8540.dts b/arch/arm/boot/dts/ste-ccu8540.dts
index 7f3baf51a3a9..32dd55e5f4e6 100644
--- a/arch/arm/boot/dts/ste-ccu8540.dts
+++ b/arch/arm/boot/dts/ste-ccu8540.dts
@@ -18,6 +18,7 @@
 	compatible = "st-ericsson,ccu8540", "st-ericsson,u8540";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x20000000 0x1f000000>, <0xc0000000 0x3f000000>;
 	};
 
diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi
index ec0698a8354a..9c2ba74a8b60 100644
--- a/arch/arm/boot/dts/tegra124.dtsi
+++ b/arch/arm/boot/dts/tegra124.dtsi
@@ -164,19 +164,6 @@
 		status = "disabled";
 	};
 
-	serial@70006400 {
-		compatible = "nvidia,tegra124-uart", "nvidia,tegra20-uart";
-		reg = <0x70006400 0x40>;
-		reg-shift = <2>;
-		interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&tegra_car TEGRA124_CLK_UARTE>;
-		resets = <&tegra_car 66>;
-		reset-names = "serial";
-		dmas = <&apbdma 20>, <&apbdma 20>;
-		dma-names = "rx", "tx";
-		status = "disabled";
-	};
-
 	pwm@7000a000 {
 		compatible = "nvidia,tegra124-pwm", "nvidia,tegra20-pwm";
 		reg = <0x7000a000 0x100>;
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index ac870fb3fa0d..9584232ee6b6 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -228,6 +228,7 @@
 			};
 
 			clcd@1f0000 {
+				status = "disabled";
 				compatible = "arm,pl111", "arm,primecell";
 				reg = <0x1f0000 0x1000>;
 				interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi
index f1420368355b..6593398c11ae 100644
--- a/arch/arm/boot/dts/vexpress-v2m.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m.dtsi
@@ -227,6 +227,7 @@
 			};
 
 			clcd@1f000 {
+				status = "disabled";
 				compatible = "arm,pl111", "arm,primecell";
 				reg = <0x1f000 0x1000>;
 				interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
index 9420053acc14..7cbe38cecf6c 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xbf000000 0x01000000;
+
 / {
 	model = "V2P-CA15";
 	arm,hbi = <0x237>;
@@ -57,6 +59,8 @@
 		interrupts = <0 85 4>;
 		clocks = <&oscclk5>;
 		clock-names = "pxlclk";
+		mode = "1024x768-16@60";
+		framebuffer = <0 0xbf000000 0 0x01000000>;
 	};
 
 	memory-controller@2b0a0000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 15f98cbcb75a..e56356a249cd 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xff000000 0x01000000;
+
 / {
 	model = "V2P-CA15_CA7";
 	arm,hbi = <0x249>;
@@ -29,29 +31,60 @@
 		i2c1 = &v2m_i2c_pcie;
 	};
 
-	cpus {
+	clusters {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu0: cpu@0 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
+		cluster0: cluster@0 {
 			reg = <0>;
-			cci-control-port = <&cci_control1>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core0: core@0 {
+					reg = <0>;
+				};
+
+				core1: core@1 {
+					reg = <1>;
+				};
+
+			};
 		};
 
-		cpu1: cpu@1 {
-			device_type = "cpu";
-			compatible = "arm,cortex-a15";
+		cluster1: cluster@1 {
 			reg = <1>;
-			cci-control-port = <&cci_control1>;
+			cores {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				core2: core@0 {
+					reg = <0>;
+				};
+
+				core3: core@1 {
+					reg = <1>;
+				};
+
+				core4: core@2 {
+					reg = <2>;
+				};
+			};
 		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
 
 		cpu2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a7";
 			reg = <0x100>;
 			cci-control-port = <&cci_control2>;
+			cluster = <&cluster1>;
+			core = <&core2>;
+			clock-frequency = <800000000>;
 		};
 
 		cpu3: cpu@3 {
@@ -59,6 +92,9 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x101>;
 			cci-control-port = <&cci_control2>;
+			cluster = <&cluster1>;
+			core = <&core3>;
+			clock-frequency = <800000000>;
 		};
 
 		cpu4: cpu@4 {
@@ -66,12 +102,35 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x102>;
 			cci-control-port = <&cci_control2>;
+			cluster = <&cluster1>;
+			core = <&core4>;
+			clock-frequency = <800000000>;
+		};
+
+		cpu0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <0>;
+			cci-control-port = <&cci_control1>;
+			cluster = <&cluster0>;
+			core = <&core0>;
+			clock-frequency = <1000000000>;
+		};
+
+		cpu1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a15";
+			reg = <1>;
+			cci-control-port = <&cci_control1>;
+			cluster = <&cluster0>;
+			core = <&core1>;
+			clock-frequency = <1000000000>;
 		};
 	};
 
 	memory@80000000 {
 		device_type = "memory";
-		reg = <0 0x80000000 0 0x40000000>;
+		reg = <0 0x80000000 0 0x80000000>;
 	};
 
 	wdt@2a490000 {
@@ -86,6 +145,8 @@
 		compatible = "arm,hdlcd";
 		reg = <0 0x2b000000 0 0x1000>;
 		interrupts = <0 85 4>;
+		mode = "1024x768-16@60";
+		framebuffer = <0 0xff000000 0 0x01000000>;
 		clocks = <&oscclk5>;
 		clock-names = "pxlclk";
 	};
@@ -127,6 +188,16 @@
 			interface-type = "ace";
 			reg = <0x5000 0x1000>;
 		};
+
+		pmu@9000 {
+			 compatible = "arm,cci-400-pmu";
+			 reg = <0x9000 0x5000>;
+			 interrupts = <0 101 4>,
+				      <0 102 4>,
+				      <0 103 4>,
+				      <0 104 4>,
+				      <0 105 4>;
+		};
 	};
 
 	memory-controller@7ffd0000 {
@@ -164,12 +235,21 @@
 			     <1 10 0xf08>;
 	};
 
-	pmu {
+	pmu_a15 {
 		compatible = "arm,cortex-a15-pmu";
+		cluster  = <&cluster0>;
 		interrupts = <0 68 4>,
 			     <0 69 4>;
 	};
 
+	pmu_a7 {
+		compatible = "arm,cortex-a7-pmu";
+		cluster  = <&cluster1>;
+		interrupts = <0 128 4>,
+			     <0 129 4>,
+			     <0 130 4>;
+	};
+
 	oscclk6a: oscclk6a {
 		/* Reference 24MHz clock */
 		compatible = "fixed-clock";
@@ -178,6 +258,19 @@
 		clock-output-names = "oscclk6a";
 	};
 
+/* PSCI requires support from firmware and is not present in the normal TC2
+ * distribution, so this node is commented out by default...
+
+	psci {
+		compatible      = "arm,psci";
+		method          = "smc";
+		cpu_suspend     = <0x80100001>;
+		cpu_off         = <0x80100002>;
+		cpu_on          = <0x80100003>;
+		migrate         = <0x80100004>;
+	};
+*/
+
 	dcc {
 		compatible = "arm,vexpress,config-bus";
 		arm,vexpress,config-bridge = <&v2m_sysreg>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
index c544a5504591..cf633ed6a1b4 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/memreserve/ 0xbf000000 0x01000000;
+
 / {
 	model = "V2P-CA5s";
 	arm,hbi = <0x225>;
@@ -59,6 +61,8 @@
 		interrupts = <0 85 4>;
 		clocks = <&oscclk3>;
 		clock-names = "pxlclk";
+		mode = "640x480-16@60";
+		framebuffer = <0xbf000000 0x01000000>;
 	};
 
 	memory-controller@2a150000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
index 62d9b225dcce..f83706bd3f9a 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
@@ -9,6 +9,8 @@
 
 /dts-v1/;
 
+/include/ "clcd-panels.dtsi"
+
 / {
 	model = "V2P-CA9";
 	arm,hbi = <0x191>;
@@ -73,6 +75,8 @@
 		interrupts = <0 44 4>;
 		clocks = <&oscclk1>, <&oscclk2>;
 		clock-names = "clcdclk", "apb_pclk";
+		mode = "XVGA";
+		use_dma = <1>;
 	};
 
 	memory-controller@100e0000 {
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 4bdc41622c36..70b1eff477b3 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+CFLAGS_REMOVE_mcpm_entry.o	= -pg
 AFLAGS_mcpm_head.o		:= -march=armv7-a
 AFLAGS_vlock.o			:= -march=armv7-a
 obj-$(CONFIG_TI_PRIV_EDMA)	+= edma.o
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index 41bca32409fc..5339009b3c0c 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -1423,55 +1423,38 @@ EXPORT_SYMBOL(edma_clear_event);
 
 #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_DMADEVICES)
 
-static int edma_of_read_u32_to_s16_array(const struct device_node *np,
-					 const char *propname, s16 *out_values,
-					 size_t sz)
+static int edma_xbar_event_map(struct device *dev, struct device_node *node,
+			       struct edma_soc_info *pdata, size_t sz)
 {
-	int ret;
-
-	ret = of_property_read_u16_array(np, propname, out_values, sz);
-	if (ret)
-		return ret;
-
-	/* Terminate it */
-	*out_values++ = -1;
-	*out_values++ = -1;
-
-	return 0;
-}
-
-static int edma_xbar_event_map(struct device *dev,
-			       struct device_node *node,
-			       struct edma_soc_info *pdata, int len)
-{
-	int ret, i;
+	const char pname[] = "ti,edma-xbar-event-map";
 	struct resource res;
 	void __iomem *xbar;
-	const s16 (*xbar_chans)[2];
+	s16 (*xbar_chans)[2];
+	size_t nelm = sz / sizeof(s16);
 	u32 shift, offset, mux;
+	int ret, i;
 
-	xbar_chans = devm_kzalloc(dev,
-				  len/sizeof(s16) + 2*sizeof(s16),
-				  GFP_KERNEL);
+	xbar_chans = devm_kzalloc(dev, (nelm + 2) * sizeof(s16), GFP_KERNEL);
 	if (!xbar_chans)
 		return -ENOMEM;
 
 	ret = of_address_to_resource(node, 1, &res);
 	if (ret)
-		return -EIO;
+		return -ENOMEM;
 
 	xbar = devm_ioremap(dev, res.start, resource_size(&res));
 	if (!xbar)
 		return -ENOMEM;
 
-	ret = edma_of_read_u32_to_s16_array(node,
-					    "ti,edma-xbar-event-map",
-					    (s16 *)xbar_chans,
-					    len/sizeof(u32));
+	ret = of_property_read_u16_array(node, pname, (u16 *)xbar_chans, nelm);
 	if (ret)
 		return -EIO;
 
-	for (i = 0; xbar_chans[i][0] != -1; i++) {
+	/* Invalidate last entry for the other user of this mess */
+	nelm >>= 1;
+	xbar_chans[nelm][0] = xbar_chans[nelm][1] = -1;
+
+	for (i = 0; i < nelm; i++) {
 		shift = (xbar_chans[i][1] & 0x03) << 3;
 		offset = xbar_chans[i][1] & 0xfffffffc;
 		mux = readl(xbar + offset);
@@ -1480,8 +1463,7 @@ static int edma_xbar_event_map(struct device *dev,
 		writel(mux, (xbar + offset));
 	}
 
-	pdata->xbar_chans = xbar_chans;
-
+	pdata->xbar_chans = (const s16 (*)[2]) xbar_chans;
 	return 0;
 }
 
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index ee6982976d66..cf4823bc111d 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -235,6 +235,7 @@ CONFIG_SND_SOC_TEGRA_MAX98090=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
 CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_ISP1760_HCD=y
diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c
index 4522366da759..15468fbbdea3 100644
--- a/arch/arm/crypto/aesbs-glue.c
+++ b/arch/arm/crypto/aesbs-glue.c
@@ -137,7 +137,7 @@ static int aesbs_cbc_encrypt(struct blkcipher_desc *desc,
 				dst += AES_BLOCK_SIZE;
 			} while (--blocks);
 		}
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -158,7 +158,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 		bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	while (walk.nbytes) {
 		u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -182,7 +182,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 			dst += AES_BLOCK_SIZE;
 			src += AES_BLOCK_SIZE;
 		} while (--blocks);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -268,7 +268,7 @@ static int aesbs_xts_encrypt(struct blkcipher_desc *desc,
 		bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->enc, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -292,7 +292,7 @@ static int aesbs_xts_decrypt(struct blkcipher_desc *desc,
 		bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 0704e0cf5571..be467f3780dd 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -107,7 +107,6 @@ static inline void arch_counter_set_user_access(void)
 	/* Also disable virtual event stream */
 	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
 			| ARCH_TIMER_USR_VT_ACCESS_EN
-			| ARCH_TIMER_VIRT_EVT_EN
 			| ARCH_TIMER_USR_VCT_ACCESS_EN
 			| ARCH_TIMER_USR_PCT_ACCESS_EN);
 	arch_timer_set_cntkctl(cntkctl);
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 5c2285160575..380ac4f20000 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -30,8 +30,8 @@
  * Endian independent macros for shifting bytes within registers.
  */
 #ifndef __ARMEB__
-#define pull            lsr
-#define push            lsl
+#define lspull          lsr
+#define lspush          lsl
 #define get_byte_0      lsl #0
 #define get_byte_1	lsr #8
 #define get_byte_2	lsr #16
@@ -41,8 +41,8 @@
 #define put_byte_2	lsl #16
 #define put_byte_3	lsl #24
 #else
-#define pull            lsl
-#define push            lsr
+#define lspull          lsl
+#define lspush          lsr
 #define get_byte_0	lsr #24
 #define get_byte_1	lsr #16
 #define get_byte_2	lsr #8
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index acdde76b39bb..43bd224f3beb 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -62,15 +62,18 @@
 #define ARM_CPU_IMP_ARM			0x41
 #define ARM_CPU_IMP_INTEL		0x69
 
-#define ARM_CPU_PART_ARM1136		0xB360
-#define ARM_CPU_PART_ARM1156		0xB560
-#define ARM_CPU_PART_ARM1176		0xB760
-#define ARM_CPU_PART_ARM11MPCORE	0xB020
-#define ARM_CPU_PART_CORTEX_A8		0xC080
-#define ARM_CPU_PART_CORTEX_A9		0xC090
-#define ARM_CPU_PART_CORTEX_A5		0xC050
-#define ARM_CPU_PART_CORTEX_A15		0xC0F0
-#define ARM_CPU_PART_CORTEX_A7		0xC070
+/* ARM implemented processors */
+#define ARM_CPU_PART_ARM1136		0x4100b360
+#define ARM_CPU_PART_ARM1156		0x4100b560
+#define ARM_CPU_PART_ARM1176		0x4100b760
+#define ARM_CPU_PART_ARM11MPCORE	0x4100b020
+#define ARM_CPU_PART_CORTEX_A8		0x4100c080
+#define ARM_CPU_PART_CORTEX_A9		0x4100c090
+#define ARM_CPU_PART_CORTEX_A5		0x4100c050
+#define ARM_CPU_PART_CORTEX_A7		0x4100c070
+#define ARM_CPU_PART_CORTEX_A12		0x4100c0d0
+#define ARM_CPU_PART_CORTEX_A17		0x4100c0e0
+#define ARM_CPU_PART_CORTEX_A15		0x4100c0f0
 
 #define ARM_CPU_XSCALE_ARCH_MASK	0xe000
 #define ARM_CPU_XSCALE_ARCH_V1		0x2000
@@ -169,14 +172,24 @@ static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
 	return (read_cpuid_id() & 0xFF000000) >> 24;
 }
 
-static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
+/*
+ * The CPU part number is meaningless without referring to the CPU
+ * implementer: implementers are free to define their own part numbers
+ * which are permitted to clash with other implementer part numbers.
+ */
+static inline unsigned int __attribute_const__ read_cpuid_part(void)
+{
+	return read_cpuid_id() & 0xff00fff0;
+}
+
+static inline unsigned int __attribute_const__ __deprecated read_cpuid_part_number(void)
 {
 	return read_cpuid_id() & 0xFFF0;
 }
 
 static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void)
 {
-	return read_cpuid_part_number() & ARM_CPU_XSCALE_ARCH_MASK;
+	return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK;
 }
 
 static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index 191ada6e4d2d..662c7bd06108 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -156,7 +156,7 @@
 		/* Select the best insn combination to perform the   */	\
 		/* actual __m * __n / (__p << 64) operation.         */	\
 		if (!__c) {						\
-			asm (	"umull	%Q0, %R0, %1, %Q2\n\t"		\
+			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"		\
 				"mov	%Q0, #0"			\
 				: "=&r" (__res)				\
 				: "r" (__m), "r" (__n)			\
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index f89515adac60..39eb16b0066f 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -52,15 +52,7 @@ extern inline void *return_address(unsigned int level)
 
 #endif
 
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* ifndef __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index e42cf597f6e6..2aff798fbef4 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -3,11 +3,6 @@
 
 #ifdef __KERNEL__
 
-#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP)
-/* ARM doesn't provide unprivileged exclusive memory accessors */
-#include <asm-generic/futex.h>
-#else
-
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
@@ -164,6 +159,5 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-#endif /* !(CPU_USE_DOMAINS && SMP) */
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
deleted file mode 100644
index ad774f37c47c..000000000000
--- a/arch/arm/include/asm/hardware/coresight.h
+++ /dev/null
@@ -1,157 +0,0 @@
-/*
- * linux/arch/arm/include/asm/hardware/coresight.h
- *
- * CoreSight components' registers
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_HARDWARE_CORESIGHT_H
-#define __ASM_HARDWARE_CORESIGHT_H
-
-#define TRACER_ACCESSED_BIT	0
-#define TRACER_RUNNING_BIT	1
-#define TRACER_CYCLE_ACC_BIT	2
-#define TRACER_ACCESSED		BIT(TRACER_ACCESSED_BIT)
-#define TRACER_RUNNING		BIT(TRACER_RUNNING_BIT)
-#define TRACER_CYCLE_ACC	BIT(TRACER_CYCLE_ACC_BIT)
-
-#define TRACER_TIMEOUT 10000
-
-#define etm_writel(t, v, x) \
-	(writel_relaxed((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x)))
-
-/* CoreSight Management Registers */
-#define CSMR_LOCKACCESS 0xfb0
-#define CSMR_LOCKSTATUS 0xfb4
-#define CSMR_AUTHSTATUS 0xfb8
-#define CSMR_DEVID	0xfc8
-#define CSMR_DEVTYPE	0xfcc
-/* CoreSight Component Registers */
-#define CSCR_CLASS	0xff4
-
-#define CS_LAR_KEY	0xc5acce55
-
-/* ETM control register, "ETM Architecture", 3.3.1 */
-#define ETMR_CTRL		0
-#define ETMCTRL_POWERDOWN	1
-#define ETMCTRL_PROGRAM		(1 << 10)
-#define ETMCTRL_PORTSEL		(1 << 11)
-#define ETMCTRL_DO_CONTEXTID	(3 << 14)
-#define ETMCTRL_PORTMASK1	(7 << 4)
-#define ETMCTRL_PORTMASK2	(1 << 21)
-#define ETMCTRL_PORTMASK	(ETMCTRL_PORTMASK1 | ETMCTRL_PORTMASK2)
-#define ETMCTRL_PORTSIZE(x) ((((x) & 7) << 4) | (!!((x) & 8)) << 21)
-#define ETMCTRL_DO_CPRT		(1 << 1)
-#define ETMCTRL_DATAMASK	(3 << 2)
-#define ETMCTRL_DATA_DO_DATA	(1 << 2)
-#define ETMCTRL_DATA_DO_ADDR	(1 << 3)
-#define ETMCTRL_DATA_DO_BOTH	(ETMCTRL_DATA_DO_DATA | ETMCTRL_DATA_DO_ADDR)
-#define ETMCTRL_BRANCH_OUTPUT	(1 << 8)
-#define ETMCTRL_CYCLEACCURATE	(1 << 12)
-
-/* ETM configuration code register */
-#define ETMR_CONFCODE		(0x04)
-
-/* ETM trace start/stop resource control register */
-#define ETMR_TRACESSCTRL	(0x18)
-
-/* ETM trigger event register */
-#define ETMR_TRIGEVT		(0x08)
-
-/* address access type register bits, "ETM architecture",
- * table 3-27 */
-/* - access type */
-#define ETMAAT_IFETCH		0
-#define ETMAAT_IEXEC		1
-#define ETMAAT_IEXECPASS	2
-#define ETMAAT_IEXECFAIL	3
-#define ETMAAT_DLOADSTORE	4
-#define ETMAAT_DLOAD		5
-#define ETMAAT_DSTORE		6
-/* - comparison access size */
-#define ETMAAT_JAVA		(0 << 3)
-#define ETMAAT_THUMB		(1 << 3)
-#define ETMAAT_ARM		(3 << 3)
-/* - data value comparison control */
-#define ETMAAT_NOVALCMP		(0 << 5)
-#define ETMAAT_VALMATCH		(1 << 5)
-#define ETMAAT_VALNOMATCH	(3 << 5)
-/* - exact match */
-#define ETMAAT_EXACTMATCH	(1 << 7)
-/* - context id comparator control */
-#define ETMAAT_IGNCONTEXTID	(0 << 8)
-#define ETMAAT_VALUE1		(1 << 8)
-#define ETMAAT_VALUE2		(2 << 8)
-#define ETMAAT_VALUE3		(3 << 8)
-/* - security level control */
-#define ETMAAT_IGNSECURITY	(0 << 10)
-#define ETMAAT_NSONLY		(1 << 10)
-#define ETMAAT_SONLY		(2 << 10)
-
-#define ETMR_COMP_VAL(x)	(0x40 + (x) * 4)
-#define ETMR_COMP_ACC_TYPE(x)	(0x80 + (x) * 4)
-
-/* ETM status register, "ETM Architecture", 3.3.2 */
-#define ETMR_STATUS		(0x10)
-#define ETMST_OVERFLOW		BIT(0)
-#define ETMST_PROGBIT		BIT(1)
-#define ETMST_STARTSTOP		BIT(2)
-#define ETMST_TRIGGER		BIT(3)
-
-#define etm_progbit(t)		(etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT)
-#define etm_started(t)		(etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP)
-#define etm_triggered(t)	(etm_readl((t), ETMR_STATUS) & ETMST_TRIGGER)
-
-#define ETMR_TRACEENCTRL2	0x1c
-#define ETMR_TRACEENCTRL	0x24
-#define ETMTE_INCLEXCL		BIT(24)
-#define ETMR_TRACEENEVT		0x20
-#define ETMCTRL_OPTS		(ETMCTRL_DO_CPRT | \
-				ETMCTRL_DATA_DO_ADDR | \
-				ETMCTRL_BRANCH_OUTPUT | \
-				ETMCTRL_DO_CONTEXTID)
-
-/* ETM management registers, "ETM Architecture", 3.5.24 */
-#define ETMMR_OSLAR	0x300
-#define ETMMR_OSLSR	0x304
-#define ETMMR_OSSRR	0x308
-#define ETMMR_PDSR	0x314
-
-/* ETB registers, "CoreSight Components TRM", 9.3 */
-#define ETBR_DEPTH		0x04
-#define ETBR_STATUS		0x0c
-#define ETBR_READMEM		0x10
-#define ETBR_READADDR		0x14
-#define ETBR_WRITEADDR		0x18
-#define ETBR_TRIGGERCOUNT	0x1c
-#define ETBR_CTRL		0x20
-#define ETBR_FORMATTERCTRL	0x304
-#define ETBFF_ENFTC		1
-#define ETBFF_ENFCONT		BIT(1)
-#define ETBFF_FONFLIN		BIT(4)
-#define ETBFF_MANUAL_FLUSH	BIT(6)
-#define ETBFF_TRIGIN		BIT(8)
-#define ETBFF_TRIGEVT		BIT(9)
-#define ETBFF_TRIGFL		BIT(10)
-
-#define etb_writel(t, v, x) \
-	(writel_relaxed((v), (t)->etb_regs + (x)))
-#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x)))
-
-#define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etm_unlock(t) \
-	do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
-
-#define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etb_unlock(t) \
-	do { etb_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
-
-#endif /* __ASM_HARDWARE_CORESIGHT_H */
-
diff --git a/arch/arm/include/asm/hardware/cp14.h b/arch/arm/include/asm/hardware/cp14.h
new file mode 100644
index 000000000000..61576dc58ede
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cp14.h
@@ -0,0 +1,542 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_HARDWARE_CP14_H
+#define __ASM_HARDWARE_CP14_H
+
+#include <linux/types.h>
+
+/* Accessors for CP14 registers */
+#define dbg_read(reg)			RCP14_##reg()
+#define dbg_write(val, reg)		WCP14_##reg(val)
+#define etm_read(reg)			RCP14_##reg()
+#define etm_write(val, reg)		WCP14_##reg(val)
+
+/* MRC14 and MCR14 */
+#define MRC14(op1, crn, crm, op2)					\
+({									\
+u32 val;								\
+asm volatile("mrc p14, "#op1", %0, "#crn", "#crm", "#op2 : "=r" (val));	\
+val;									\
+})
+
+#define MCR14(val, op1, crn, crm, op2)					\
+({									\
+asm volatile("mcr p14, "#op1", %0, "#crn", "#crm", "#op2 : : "r" (val));\
+})
+
+/*
+ * Debug Registers
+ *
+ * Available only in DBGv7
+ * DBGECR, DBGDSCCR, DBGDSMCR, DBGDRCR
+ *
+ * Available only in DBGv7.1
+ * DBGBXVRm, DBGOSDLR, DBGDEVID2, DBGDEVID1
+ *
+ * Read only
+ * DBGDIDR, DBGDSCRint, DBGDTRRXint, DBGDRAR, DBGOSLSR, DBGOSSRR, DBGPRSR,
+ * DBGPRSR, DBGDSAR, DBGAUTHSTATUS, DBGDEVID2, DBGDEVID1, DBGDEVID
+ *
+ * Write only
+ * DBGDTRTXint, DBGOSLAR
+ */
+#define RCP14_DBGDIDR()			MRC14(0, c0, c0, 0)
+#define RCP14_DBGDSCRint()		MRC14(0, c0, c1, 0)
+#define RCP14_DBGDTRRXint()		MRC14(0, c0, c5, 0)
+#define RCP14_DBGWFAR()			MRC14(0, c0, c6, 0)
+#define RCP14_DBGVCR()			MRC14(0, c0, c7, 0)
+#define RCP14_DBGECR()			MRC14(0, c0, c9, 0)
+#define RCP14_DBGDSCCR()		MRC14(0, c0, c10, 0)
+#define RCP14_DBGDSMCR()		MRC14(0, c0, c11, 0)
+#define RCP14_DBGDTRRXext()		MRC14(0, c0, c0, 2)
+#define RCP14_DBGDSCRext()		MRC14(0, c0, c2, 2)
+#define RCP14_DBGDTRTXext()		MRC14(0, c0, c3, 2)
+#define RCP14_DBGDRCR()			MRC14(0, c0, c4, 2)
+#define RCP14_DBGBVR0()			MRC14(0, c0, c0, 4)
+#define RCP14_DBGBVR1()			MRC14(0, c0, c1, 4)
+#define RCP14_DBGBVR2()			MRC14(0, c0, c2, 4)
+#define RCP14_DBGBVR3()			MRC14(0, c0, c3, 4)
+#define RCP14_DBGBVR4()			MRC14(0, c0, c4, 4)
+#define RCP14_DBGBVR5()			MRC14(0, c0, c5, 4)
+#define RCP14_DBGBVR6()			MRC14(0, c0, c6, 4)
+#define RCP14_DBGBVR7()			MRC14(0, c0, c7, 4)
+#define RCP14_DBGBVR8()			MRC14(0, c0, c8, 4)
+#define RCP14_DBGBVR9()			MRC14(0, c0, c9, 4)
+#define RCP14_DBGBVR10()		MRC14(0, c0, c10, 4)
+#define RCP14_DBGBVR11()		MRC14(0, c0, c11, 4)
+#define RCP14_DBGBVR12()		MRC14(0, c0, c12, 4)
+#define RCP14_DBGBVR13()		MRC14(0, c0, c13, 4)
+#define RCP14_DBGBVR14()		MRC14(0, c0, c14, 4)
+#define RCP14_DBGBVR15()		MRC14(0, c0, c15, 4)
+#define RCP14_DBGBCR0()			MRC14(0, c0, c0, 5)
+#define RCP14_DBGBCR1()			MRC14(0, c0, c1, 5)
+#define RCP14_DBGBCR2()			MRC14(0, c0, c2, 5)
+#define RCP14_DBGBCR3()			MRC14(0, c0, c3, 5)
+#define RCP14_DBGBCR4()			MRC14(0, c0, c4, 5)
+#define RCP14_DBGBCR5()			MRC14(0, c0, c5, 5)
+#define RCP14_DBGBCR6()			MRC14(0, c0, c6, 5)
+#define RCP14_DBGBCR7()			MRC14(0, c0, c7, 5)
+#define RCP14_DBGBCR8()			MRC14(0, c0, c8, 5)
+#define RCP14_DBGBCR9()			MRC14(0, c0, c9, 5)
+#define RCP14_DBGBCR10()		MRC14(0, c0, c10, 5)
+#define RCP14_DBGBCR11()		MRC14(0, c0, c11, 5)
+#define RCP14_DBGBCR12()		MRC14(0, c0, c12, 5)
+#define RCP14_DBGBCR13()		MRC14(0, c0, c13, 5)
+#define RCP14_DBGBCR14()		MRC14(0, c0, c14, 5)
+#define RCP14_DBGBCR15()		MRC14(0, c0, c15, 5)
+#define RCP14_DBGWVR0()			MRC14(0, c0, c0, 6)
+#define RCP14_DBGWVR1()			MRC14(0, c0, c1, 6)
+#define RCP14_DBGWVR2()			MRC14(0, c0, c2, 6)
+#define RCP14_DBGWVR3()			MRC14(0, c0, c3, 6)
+#define RCP14_DBGWVR4()			MRC14(0, c0, c4, 6)
+#define RCP14_DBGWVR5()			MRC14(0, c0, c5, 6)
+#define RCP14_DBGWVR6()			MRC14(0, c0, c6, 6)
+#define RCP14_DBGWVR7()			MRC14(0, c0, c7, 6)
+#define RCP14_DBGWVR8()			MRC14(0, c0, c8, 6)
+#define RCP14_DBGWVR9()			MRC14(0, c0, c9, 6)
+#define RCP14_DBGWVR10()		MRC14(0, c0, c10, 6)
+#define RCP14_DBGWVR11()		MRC14(0, c0, c11, 6)
+#define RCP14_DBGWVR12()		MRC14(0, c0, c12, 6)
+#define RCP14_DBGWVR13()		MRC14(0, c0, c13, 6)
+#define RCP14_DBGWVR14()		MRC14(0, c0, c14, 6)
+#define RCP14_DBGWVR15()		MRC14(0, c0, c15, 6)
+#define RCP14_DBGWCR0()			MRC14(0, c0, c0, 7)
+#define RCP14_DBGWCR1()			MRC14(0, c0, c1, 7)
+#define RCP14_DBGWCR2()			MRC14(0, c0, c2, 7)
+#define RCP14_DBGWCR3()			MRC14(0, c0, c3, 7)
+#define RCP14_DBGWCR4()			MRC14(0, c0, c4, 7)
+#define RCP14_DBGWCR5()			MRC14(0, c0, c5, 7)
+#define RCP14_DBGWCR6()			MRC14(0, c0, c6, 7)
+#define RCP14_DBGWCR7()			MRC14(0, c0, c7, 7)
+#define RCP14_DBGWCR8()			MRC14(0, c0, c8, 7)
+#define RCP14_DBGWCR9()			MRC14(0, c0, c9, 7)
+#define RCP14_DBGWCR10()		MRC14(0, c0, c10, 7)
+#define RCP14_DBGWCR11()		MRC14(0, c0, c11, 7)
+#define RCP14_DBGWCR12()		MRC14(0, c0, c12, 7)
+#define RCP14_DBGWCR13()		MRC14(0, c0, c13, 7)
+#define RCP14_DBGWCR14()		MRC14(0, c0, c14, 7)
+#define RCP14_DBGWCR15()		MRC14(0, c0, c15, 7)
+#define RCP14_DBGDRAR()			MRC14(0, c1, c0, 0)
+#define RCP14_DBGBXVR0()		MRC14(0, c1, c0, 1)
+#define RCP14_DBGBXVR1()		MRC14(0, c1, c1, 1)
+#define RCP14_DBGBXVR2()		MRC14(0, c1, c2, 1)
+#define RCP14_DBGBXVR3()		MRC14(0, c1, c3, 1)
+#define RCP14_DBGBXVR4()		MRC14(0, c1, c4, 1)
+#define RCP14_DBGBXVR5()		MRC14(0, c1, c5, 1)
+#define RCP14_DBGBXVR6()		MRC14(0, c1, c6, 1)
+#define RCP14_DBGBXVR7()		MRC14(0, c1, c7, 1)
+#define RCP14_DBGBXVR8()		MRC14(0, c1, c8, 1)
+#define RCP14_DBGBXVR9()		MRC14(0, c1, c9, 1)
+#define RCP14_DBGBXVR10()		MRC14(0, c1, c10, 1)
+#define RCP14_DBGBXVR11()		MRC14(0, c1, c11, 1)
+#define RCP14_DBGBXVR12()		MRC14(0, c1, c12, 1)
+#define RCP14_DBGBXVR13()		MRC14(0, c1, c13, 1)
+#define RCP14_DBGBXVR14()		MRC14(0, c1, c14, 1)
+#define RCP14_DBGBXVR15()		MRC14(0, c1, c15, 1)
+#define RCP14_DBGOSLSR()		MRC14(0, c1, c1, 4)
+#define RCP14_DBGOSSRR()		MRC14(0, c1, c2, 4)
+#define RCP14_DBGOSDLR()		MRC14(0, c1, c3, 4)
+#define RCP14_DBGPRCR()			MRC14(0, c1, c4, 4)
+#define RCP14_DBGPRSR()			MRC14(0, c1, c5, 4)
+#define RCP14_DBGDSAR()			MRC14(0, c2, c0, 0)
+#define RCP14_DBGITCTRL()		MRC14(0, c7, c0, 4)
+#define RCP14_DBGCLAIMSET()		MRC14(0, c7, c8, 6)
+#define RCP14_DBGCLAIMCLR()		MRC14(0, c7, c9, 6)
+#define RCP14_DBGAUTHSTATUS()		MRC14(0, c7, c14, 6)
+#define RCP14_DBGDEVID2()		MRC14(0, c7, c0, 7)
+#define RCP14_DBGDEVID1()		MRC14(0, c7, c1, 7)
+#define RCP14_DBGDEVID()		MRC14(0, c7, c2, 7)
+
+#define WCP14_DBGDTRTXint(val)		MCR14(val, 0, c0, c5, 0)
+#define WCP14_DBGWFAR(val)		MCR14(val, 0, c0, c6, 0)
+#define WCP14_DBGVCR(val)		MCR14(val, 0, c0, c7, 0)
+#define WCP14_DBGECR(val)		MCR14(val, 0, c0, c9, 0)
+#define WCP14_DBGDSCCR(val)		MCR14(val, 0, c0, c10, 0)
+#define WCP14_DBGDSMCR(val)		MCR14(val, 0, c0, c11, 0)
+#define WCP14_DBGDTRRXext(val)		MCR14(val, 0, c0, c0, 2)
+#define WCP14_DBGDSCRext(val)		MCR14(val, 0, c0, c2, 2)
+#define WCP14_DBGDTRTXext(val)		MCR14(val, 0, c0, c3, 2)
+#define WCP14_DBGDRCR(val)		MCR14(val, 0, c0, c4, 2)
+#define WCP14_DBGBVR0(val)		MCR14(val, 0, c0, c0, 4)
+#define WCP14_DBGBVR1(val)		MCR14(val, 0, c0, c1, 4)
+#define WCP14_DBGBVR2(val)		MCR14(val, 0, c0, c2, 4)
+#define WCP14_DBGBVR3(val)		MCR14(val, 0, c0, c3, 4)
+#define WCP14_DBGBVR4(val)		MCR14(val, 0, c0, c4, 4)
+#define WCP14_DBGBVR5(val)		MCR14(val, 0, c0, c5, 4)
+#define WCP14_DBGBVR6(val)		MCR14(val, 0, c0, c6, 4)
+#define WCP14_DBGBVR7(val)		MCR14(val, 0, c0, c7, 4)
+#define WCP14_DBGBVR8(val)		MCR14(val, 0, c0, c8, 4)
+#define WCP14_DBGBVR9(val)		MCR14(val, 0, c0, c9, 4)
+#define WCP14_DBGBVR10(val)		MCR14(val, 0, c0, c10, 4)
+#define WCP14_DBGBVR11(val)		MCR14(val, 0, c0, c11, 4)
+#define WCP14_DBGBVR12(val)		MCR14(val, 0, c0, c12, 4)
+#define WCP14_DBGBVR13(val)		MCR14(val, 0, c0, c13, 4)
+#define WCP14_DBGBVR14(val)		MCR14(val, 0, c0, c14, 4)
+#define WCP14_DBGBVR15(val)		MCR14(val, 0, c0, c15, 4)
+#define WCP14_DBGBCR0(val)		MCR14(val, 0, c0, c0, 5)
+#define WCP14_DBGBCR1(val)		MCR14(val, 0, c0, c1, 5)
+#define WCP14_DBGBCR2(val)		MCR14(val, 0, c0, c2, 5)
+#define WCP14_DBGBCR3(val)		MCR14(val, 0, c0, c3, 5)
+#define WCP14_DBGBCR4(val)		MCR14(val, 0, c0, c4, 5)
+#define WCP14_DBGBCR5(val)		MCR14(val, 0, c0, c5, 5)
+#define WCP14_DBGBCR6(val)		MCR14(val, 0, c0, c6, 5)
+#define WCP14_DBGBCR7(val)		MCR14(val, 0, c0, c7, 5)
+#define WCP14_DBGBCR8(val)		MCR14(val, 0, c0, c8, 5)
+#define WCP14_DBGBCR9(val)		MCR14(val, 0, c0, c9, 5)
+#define WCP14_DBGBCR10(val)		MCR14(val, 0, c0, c10, 5)
+#define WCP14_DBGBCR11(val)		MCR14(val, 0, c0, c11, 5)
+#define WCP14_DBGBCR12(val)		MCR14(val, 0, c0, c12, 5)
+#define WCP14_DBGBCR13(val)		MCR14(val, 0, c0, c13, 5)
+#define WCP14_DBGBCR14(val)		MCR14(val, 0, c0, c14, 5)
+#define WCP14_DBGBCR15(val)		MCR14(val, 0, c0, c15, 5)
+#define WCP14_DBGWVR0(val)		MCR14(val, 0, c0, c0, 6)
+#define WCP14_DBGWVR1(val)		MCR14(val, 0, c0, c1, 6)
+#define WCP14_DBGWVR2(val)		MCR14(val, 0, c0, c2, 6)
+#define WCP14_DBGWVR3(val)		MCR14(val, 0, c0, c3, 6)
+#define WCP14_DBGWVR4(val)		MCR14(val, 0, c0, c4, 6)
+#define WCP14_DBGWVR5(val)		MCR14(val, 0, c0, c5, 6)
+#define WCP14_DBGWVR6(val)		MCR14(val, 0, c0, c6, 6)
+#define WCP14_DBGWVR7(val)		MCR14(val, 0, c0, c7, 6)
+#define WCP14_DBGWVR8(val)		MCR14(val, 0, c0, c8, 6)
+#define WCP14_DBGWVR9(val)		MCR14(val, 0, c0, c9, 6)
+#define WCP14_DBGWVR10(val)		MCR14(val, 0, c0, c10, 6)
+#define WCP14_DBGWVR11(val)		MCR14(val, 0, c0, c11, 6)
+#define WCP14_DBGWVR12(val)		MCR14(val, 0, c0, c12, 6)
+#define WCP14_DBGWVR13(val)		MCR14(val, 0, c0, c13, 6)
+#define WCP14_DBGWVR14(val)		MCR14(val, 0, c0, c14, 6)
+#define WCP14_DBGWVR15(val)		MCR14(val, 0, c0, c15, 6)
+#define WCP14_DBGWCR0(val)		MCR14(val, 0, c0, c0, 7)
+#define WCP14_DBGWCR1(val)		MCR14(val, 0, c0, c1, 7)
+#define WCP14_DBGWCR2(val)		MCR14(val, 0, c0, c2, 7)
+#define WCP14_DBGWCR3(val)		MCR14(val, 0, c0, c3, 7)
+#define WCP14_DBGWCR4(val)		MCR14(val, 0, c0, c4, 7)
+#define WCP14_DBGWCR5(val)		MCR14(val, 0, c0, c5, 7)
+#define WCP14_DBGWCR6(val)		MCR14(val, 0, c0, c6, 7)
+#define WCP14_DBGWCR7(val)		MCR14(val, 0, c0, c7, 7)
+#define WCP14_DBGWCR8(val)		MCR14(val, 0, c0, c8, 7)
+#define WCP14_DBGWCR9(val)		MCR14(val, 0, c0, c9, 7)
+#define WCP14_DBGWCR10(val)		MCR14(val, 0, c0, c10, 7)
+#define WCP14_DBGWCR11(val)		MCR14(val, 0, c0, c11, 7)
+#define WCP14_DBGWCR12(val)		MCR14(val, 0, c0, c12, 7)
+#define WCP14_DBGWCR13(val)		MCR14(val, 0, c0, c13, 7)
+#define WCP14_DBGWCR14(val)		MCR14(val, 0, c0, c14, 7)
+#define WCP14_DBGWCR15(val)		MCR14(val, 0, c0, c15, 7)
+#define WCP14_DBGBXVR0(val)		MCR14(val, 0, c1, c0, 1)
+#define WCP14_DBGBXVR1(val)		MCR14(val, 0, c1, c1, 1)
+#define WCP14_DBGBXVR2(val)		MCR14(val, 0, c1, c2, 1)
+#define WCP14_DBGBXVR3(val)		MCR14(val, 0, c1, c3, 1)
+#define WCP14_DBGBXVR4(val)		MCR14(val, 0, c1, c4, 1)
+#define WCP14_DBGBXVR5(val)		MCR14(val, 0, c1, c5, 1)
+#define WCP14_DBGBXVR6(val)		MCR14(val, 0, c1, c6, 1)
+#define WCP14_DBGBXVR7(val)		MCR14(val, 0, c1, c7, 1)
+#define WCP14_DBGBXVR8(val)		MCR14(val, 0, c1, c8, 1)
+#define WCP14_DBGBXVR9(val)		MCR14(val, 0, c1, c9, 1)
+#define WCP14_DBGBXVR10(val)		MCR14(val, 0, c1, c10, 1)
+#define WCP14_DBGBXVR11(val)		MCR14(val, 0, c1, c11, 1)
+#define WCP14_DBGBXVR12(val)		MCR14(val, 0, c1, c12, 1)
+#define WCP14_DBGBXVR13(val)		MCR14(val, 0, c1, c13, 1)
+#define WCP14_DBGBXVR14(val)		MCR14(val, 0, c1, c14, 1)
+#define WCP14_DBGBXVR15(val)		MCR14(val, 0, c1, c15, 1)
+#define WCP14_DBGOSLAR(val)		MCR14(val, 0, c1, c0, 4)
+#define WCP14_DBGOSSRR(val)		MCR14(val, 0, c1, c2, 4)
+#define WCP14_DBGOSDLR(val)		MCR14(val, 0, c1, c3, 4)
+#define WCP14_DBGPRCR(val)		MCR14(val, 0, c1, c4, 4)
+#define WCP14_DBGITCTRL(val)		MCR14(val, 0, c7, c0, 4)
+#define WCP14_DBGCLAIMSET(val)		MCR14(val, 0, c7, c8, 6)
+#define WCP14_DBGCLAIMCLR(val)		MCR14(val, 0, c7, c9, 6)
+
+/*
+ * ETM Registers
+ *
+ * Available only in ETMv3.3, 3.4, 3.5
+ * ETMASICCR, ETMTECR2, ETMFFRR, ETMVDEVR, ETMVDCR1, ETMVDCR2, ETMVDCR3,
+ * ETMDCVRn, ETMDCMRn
+ *
+ * Available only in ETMv3.5 as read only
+ * ETMIDR2
+ *
+ * Available only in ETMv3.5, PFTv1.0, 1.1
+ * ETMTSEVR, ETMVMIDCVR, ETMPDCR
+ *
+ * Read only
+ * ETMCCR, ETMSCR, ETMIDR, ETMCCER, ETMOSLSR
+ * ETMLSR, ETMAUTHSTATUS, ETMDEVID, ETMDEVTYPE, ETMPIDR4, ETMPIDR5, ETMPIDR6,
+ * ETMPIDR7, ETMPIDR0, ETMPIDR1, ETMPIDR2, ETMPIDR2, ETMPIDR3, ETMCIDR0,
+ * ETMCIDR1, ETMCIDR2, ETMCIDR3
+ *
+ * Write only
+ * ETMOSLAR, ETMLAR
+ * Note: ETMCCER[11] controls WO nature of certain regs. Refer ETM arch spec.
+ */
+#define RCP14_ETMCR()			MRC14(1, c0, c0, 0)
+#define RCP14_ETMCCR()			MRC14(1, c0, c1, 0)
+#define RCP14_ETMTRIGGER()		MRC14(1, c0, c2, 0)
+#define RCP14_ETMASICCR()		MRC14(1, c0, c3, 0)
+#define RCP14_ETMSR()			MRC14(1, c0, c4, 0)
+#define RCP14_ETMSCR()			MRC14(1, c0, c5, 0)
+#define RCP14_ETMTSSCR()		MRC14(1, c0, c6, 0)
+#define RCP14_ETMTECR2()		MRC14(1, c0, c7, 0)
+#define RCP14_ETMTEEVR()		MRC14(1, c0, c8, 0)
+#define RCP14_ETMTECR1()		MRC14(1, c0, c9, 0)
+#define RCP14_ETMFFRR()			MRC14(1, c0, c10, 0)
+#define RCP14_ETMFFLR()			MRC14(1, c0, c11, 0)
+#define RCP14_ETMVDEVR()		MRC14(1, c0, c12, 0)
+#define RCP14_ETMVDCR1()		MRC14(1, c0, c13, 0)
+#define RCP14_ETMVDCR2()		MRC14(1, c0, c14, 0)
+#define RCP14_ETMVDCR3()		MRC14(1, c0, c15, 0)
+#define RCP14_ETMACVR0()		MRC14(1, c0, c0, 1)
+#define RCP14_ETMACVR1()		MRC14(1, c0, c1, 1)
+#define RCP14_ETMACVR2()		MRC14(1, c0, c2, 1)
+#define RCP14_ETMACVR3()		MRC14(1, c0, c3, 1)
+#define RCP14_ETMACVR4()		MRC14(1, c0, c4, 1)
+#define RCP14_ETMACVR5()		MRC14(1, c0, c5, 1)
+#define RCP14_ETMACVR6()		MRC14(1, c0, c6, 1)
+#define RCP14_ETMACVR7()		MRC14(1, c0, c7, 1)
+#define RCP14_ETMACVR8()		MRC14(1, c0, c8, 1)
+#define RCP14_ETMACVR9()		MRC14(1, c0, c9, 1)
+#define RCP14_ETMACVR10()		MRC14(1, c0, c10, 1)
+#define RCP14_ETMACVR11()		MRC14(1, c0, c11, 1)
+#define RCP14_ETMACVR12()		MRC14(1, c0, c12, 1)
+#define RCP14_ETMACVR13()		MRC14(1, c0, c13, 1)
+#define RCP14_ETMACVR14()		MRC14(1, c0, c14, 1)
+#define RCP14_ETMACVR15()		MRC14(1, c0, c15, 1)
+#define RCP14_ETMACTR0()		MRC14(1, c0, c0, 2)
+#define RCP14_ETMACTR1()		MRC14(1, c0, c1, 2)
+#define RCP14_ETMACTR2()		MRC14(1, c0, c2, 2)
+#define RCP14_ETMACTR3()		MRC14(1, c0, c3, 2)
+#define RCP14_ETMACTR4()		MRC14(1, c0, c4, 2)
+#define RCP14_ETMACTR5()		MRC14(1, c0, c5, 2)
+#define RCP14_ETMACTR6()		MRC14(1, c0, c6, 2)
+#define RCP14_ETMACTR7()		MRC14(1, c0, c7, 2)
+#define RCP14_ETMACTR8()		MRC14(1, c0, c8, 2)
+#define RCP14_ETMACTR9()		MRC14(1, c0, c9, 2)
+#define RCP14_ETMACTR10()		MRC14(1, c0, c10, 2)
+#define RCP14_ETMACTR11()		MRC14(1, c0, c11, 2)
+#define RCP14_ETMACTR12()		MRC14(1, c0, c12, 2)
+#define RCP14_ETMACTR13()		MRC14(1, c0, c13, 2)
+#define RCP14_ETMACTR14()		MRC14(1, c0, c14, 2)
+#define RCP14_ETMACTR15()		MRC14(1, c0, c15, 2)
+#define RCP14_ETMDCVR0()		MRC14(1, c0, c0, 3)
+#define RCP14_ETMDCVR2()		MRC14(1, c0, c2, 3)
+#define RCP14_ETMDCVR4()		MRC14(1, c0, c4, 3)
+#define RCP14_ETMDCVR6()		MRC14(1, c0, c6, 3)
+#define RCP14_ETMDCVR8()		MRC14(1, c0, c8, 3)
+#define RCP14_ETMDCVR10()		MRC14(1, c0, c10, 3)
+#define RCP14_ETMDCVR12()		MRC14(1, c0, c12, 3)
+#define RCP14_ETMDCVR14()		MRC14(1, c0, c14, 3)
+#define RCP14_ETMDCMR0()		MRC14(1, c0, c0, 4)
+#define RCP14_ETMDCMR2()		MRC14(1, c0, c2, 4)
+#define RCP14_ETMDCMR4()		MRC14(1, c0, c4, 4)
+#define RCP14_ETMDCMR6()		MRC14(1, c0, c6, 4)
+#define RCP14_ETMDCMR8()		MRC14(1, c0, c8, 4)
+#define RCP14_ETMDCMR10()		MRC14(1, c0, c10, 4)
+#define RCP14_ETMDCMR12()		MRC14(1, c0, c12, 4)
+#define RCP14_ETMDCMR14()		MRC14(1, c0, c14, 4)
+#define RCP14_ETMCNTRLDVR0()		MRC14(1, c0, c0, 5)
+#define RCP14_ETMCNTRLDVR1()		MRC14(1, c0, c1, 5)
+#define RCP14_ETMCNTRLDVR2()		MRC14(1, c0, c2, 5)
+#define RCP14_ETMCNTRLDVR3()		MRC14(1, c0, c3, 5)
+#define RCP14_ETMCNTENR0()		MRC14(1, c0, c4, 5)
+#define RCP14_ETMCNTENR1()		MRC14(1, c0, c5, 5)
+#define RCP14_ETMCNTENR2()		MRC14(1, c0, c6, 5)
+#define RCP14_ETMCNTENR3()		MRC14(1, c0, c7, 5)
+#define RCP14_ETMCNTRLDEVR0()		MRC14(1, c0, c8, 5)
+#define RCP14_ETMCNTRLDEVR1()		MRC14(1, c0, c9, 5)
+#define RCP14_ETMCNTRLDEVR2()		MRC14(1, c0, c10, 5)
+#define RCP14_ETMCNTRLDEVR3()		MRC14(1, c0, c11, 5)
+#define RCP14_ETMCNTVR0()		MRC14(1, c0, c12, 5)
+#define RCP14_ETMCNTVR1()		MRC14(1, c0, c13, 5)
+#define RCP14_ETMCNTVR2()		MRC14(1, c0, c14, 5)
+#define RCP14_ETMCNTVR3()		MRC14(1, c0, c15, 5)
+#define RCP14_ETMSQ12EVR()		MRC14(1, c0, c0, 6)
+#define RCP14_ETMSQ21EVR()		MRC14(1, c0, c1, 6)
+#define RCP14_ETMSQ23EVR()		MRC14(1, c0, c2, 6)
+#define RCP14_ETMSQ31EVR()		MRC14(1, c0, c3, 6)
+#define RCP14_ETMSQ32EVR()		MRC14(1, c0, c4, 6)
+#define RCP14_ETMSQ13EVR()		MRC14(1, c0, c5, 6)
+#define RCP14_ETMSQR()			MRC14(1, c0, c7, 6)
+#define RCP14_ETMEXTOUTEVR0()		MRC14(1, c0, c8, 6)
+#define RCP14_ETMEXTOUTEVR1()		MRC14(1, c0, c9, 6)
+#define RCP14_ETMEXTOUTEVR2()		MRC14(1, c0, c10, 6)
+#define RCP14_ETMEXTOUTEVR3()		MRC14(1, c0, c11, 6)
+#define RCP14_ETMCIDCVR0()		MRC14(1, c0, c12, 6)
+#define RCP14_ETMCIDCVR1()		MRC14(1, c0, c13, 6)
+#define RCP14_ETMCIDCVR2()		MRC14(1, c0, c14, 6)
+#define RCP14_ETMCIDCMR()		MRC14(1, c0, c15, 6)
+#define RCP14_ETMIMPSPEC0()		MRC14(1, c0, c0, 7)
+#define RCP14_ETMIMPSPEC1()		MRC14(1, c0, c1, 7)
+#define RCP14_ETMIMPSPEC2()		MRC14(1, c0, c2, 7)
+#define RCP14_ETMIMPSPEC3()		MRC14(1, c0, c3, 7)
+#define RCP14_ETMIMPSPEC4()		MRC14(1, c0, c4, 7)
+#define RCP14_ETMIMPSPEC5()		MRC14(1, c0, c5, 7)
+#define RCP14_ETMIMPSPEC6()		MRC14(1, c0, c6, 7)
+#define RCP14_ETMIMPSPEC7()		MRC14(1, c0, c7, 7)
+#define RCP14_ETMSYNCFR()		MRC14(1, c0, c8, 7)
+#define RCP14_ETMIDR()			MRC14(1, c0, c9, 7)
+#define RCP14_ETMCCER()			MRC14(1, c0, c10, 7)
+#define RCP14_ETMEXTINSELR()		MRC14(1, c0, c11, 7)
+#define RCP14_ETMTESSEICR()		MRC14(1, c0, c12, 7)
+#define RCP14_ETMEIBCR()		MRC14(1, c0, c13, 7)
+#define RCP14_ETMTSEVR()		MRC14(1, c0, c14, 7)
+#define RCP14_ETMAUXCR()		MRC14(1, c0, c15, 7)
+#define RCP14_ETMTRACEIDR()		MRC14(1, c1, c0, 0)
+#define RCP14_ETMIDR2()			MRC14(1, c1, c2, 0)
+#define RCP14_ETMVMIDCVR()		MRC14(1, c1, c0, 1)
+#define RCP14_ETMOSLSR()		MRC14(1, c1, c1, 4)
+/* Not available in PFTv1.1 */
+#define RCP14_ETMOSSRR()		MRC14(1, c1, c2, 4)
+#define RCP14_ETMPDCR()			MRC14(1, c1, c4, 4)
+#define RCP14_ETMPDSR()			MRC14(1, c1, c5, 4)
+#define RCP14_ETMITCTRL()		MRC14(1, c7, c0, 4)
+#define RCP14_ETMCLAIMSET()		MRC14(1, c7, c8, 6)
+#define RCP14_ETMCLAIMCLR()		MRC14(1, c7, c9, 6)
+#define RCP14_ETMLSR()			MRC14(1, c7, c13, 6)
+#define RCP14_ETMAUTHSTATUS()		MRC14(1, c7, c14, 6)
+#define RCP14_ETMDEVID()		MRC14(1, c7, c2, 7)
+#define RCP14_ETMDEVTYPE()		MRC14(1, c7, c3, 7)
+#define RCP14_ETMPIDR4()		MRC14(1, c7, c4, 7)
+#define RCP14_ETMPIDR5()		MRC14(1, c7, c5, 7)
+#define RCP14_ETMPIDR6()		MRC14(1, c7, c6, 7)
+#define RCP14_ETMPIDR7()		MRC14(1, c7, c7, 7)
+#define RCP14_ETMPIDR0()		MRC14(1, c7, c8, 7)
+#define RCP14_ETMPIDR1()		MRC14(1, c7, c9, 7)
+#define RCP14_ETMPIDR2()		MRC14(1, c7, c10, 7)
+#define RCP14_ETMPIDR3()		MRC14(1, c7, c11, 7)
+#define RCP14_ETMCIDR0()		MRC14(1, c7, c12, 7)
+#define RCP14_ETMCIDR1()		MRC14(1, c7, c13, 7)
+#define RCP14_ETMCIDR2()		MRC14(1, c7, c14, 7)
+#define RCP14_ETMCIDR3()		MRC14(1, c7, c15, 7)
+
+#define WCP14_ETMCR(val)		MCR14(val, 1, c0, c0, 0)
+#define WCP14_ETMTRIGGER(val)		MCR14(val, 1, c0, c2, 0)
+#define WCP14_ETMASICCR(val)		MCR14(val, 1, c0, c3, 0)
+#define WCP14_ETMSR(val)		MCR14(val, 1, c0, c4, 0)
+#define WCP14_ETMTSSCR(val)		MCR14(val, 1, c0, c6, 0)
+#define WCP14_ETMTECR2(val)		MCR14(val, 1, c0, c7, 0)
+#define WCP14_ETMTEEVR(val)		MCR14(val, 1, c0, c8, 0)
+#define WCP14_ETMTECR1(val)		MCR14(val, 1, c0, c9, 0)
+#define WCP14_ETMFFRR(val)		MCR14(val, 1, c0, c10, 0)
+#define WCP14_ETMFFLR(val)		MCR14(val, 1, c0, c11, 0)
+#define WCP14_ETMVDEVR(val)		MCR14(val, 1, c0, c12, 0)
+#define WCP14_ETMVDCR1(val)		MCR14(val, 1, c0, c13, 0)
+#define WCP14_ETMVDCR2(val)		MCR14(val, 1, c0, c14, 0)
+#define WCP14_ETMVDCR3(val)		MCR14(val, 1, c0, c15, 0)
+#define WCP14_ETMACVR0(val)		MCR14(val, 1, c0, c0, 1)
+#define WCP14_ETMACVR1(val)		MCR14(val, 1, c0, c1, 1)
+#define WCP14_ETMACVR2(val)		MCR14(val, 1, c0, c2, 1)
+#define WCP14_ETMACVR3(val)		MCR14(val, 1, c0, c3, 1)
+#define WCP14_ETMACVR4(val)		MCR14(val, 1, c0, c4, 1)
+#define WCP14_ETMACVR5(val)		MCR14(val, 1, c0, c5, 1)
+#define WCP14_ETMACVR6(val)		MCR14(val, 1, c0, c6, 1)
+#define WCP14_ETMACVR7(val)		MCR14(val, 1, c0, c7, 1)
+#define WCP14_ETMACVR8(val)		MCR14(val, 1, c0, c8, 1)
+#define WCP14_ETMACVR9(val)		MCR14(val, 1, c0, c9, 1)
+#define WCP14_ETMACVR10(val)		MCR14(val, 1, c0, c10, 1)
+#define WCP14_ETMACVR11(val)		MCR14(val, 1, c0, c11, 1)
+#define WCP14_ETMACVR12(val)		MCR14(val, 1, c0, c12, 1)
+#define WCP14_ETMACVR13(val)		MCR14(val, 1, c0, c13, 1)
+#define WCP14_ETMACVR14(val)		MCR14(val, 1, c0, c14, 1)
+#define WCP14_ETMACVR15(val)		MCR14(val, 1, c0, c15, 1)
+#define WCP14_ETMACTR0(val)		MCR14(val, 1, c0, c0, 2)
+#define WCP14_ETMACTR1(val)		MCR14(val, 1, c0, c1, 2)
+#define WCP14_ETMACTR2(val)		MCR14(val, 1, c0, c2, 2)
+#define WCP14_ETMACTR3(val)		MCR14(val, 1, c0, c3, 2)
+#define WCP14_ETMACTR4(val)		MCR14(val, 1, c0, c4, 2)
+#define WCP14_ETMACTR5(val)		MCR14(val, 1, c0, c5, 2)
+#define WCP14_ETMACTR6(val)		MCR14(val, 1, c0, c6, 2)
+#define WCP14_ETMACTR7(val)		MCR14(val, 1, c0, c7, 2)
+#define WCP14_ETMACTR8(val)		MCR14(val, 1, c0, c8, 2)
+#define WCP14_ETMACTR9(val)		MCR14(val, 1, c0, c9, 2)
+#define WCP14_ETMACTR10(val)		MCR14(val, 1, c0, c10, 2)
+#define WCP14_ETMACTR11(val)		MCR14(val, 1, c0, c11, 2)
+#define WCP14_ETMACTR12(val)		MCR14(val, 1, c0, c12, 2)
+#define WCP14_ETMACTR13(val)		MCR14(val, 1, c0, c13, 2)
+#define WCP14_ETMACTR14(val)		MCR14(val, 1, c0, c14, 2)
+#define WCP14_ETMACTR15(val)		MCR14(val, 1, c0, c15, 2)
+#define WCP14_ETMDCVR0(val)		MCR14(val, 1, c0, c0, 3)
+#define WCP14_ETMDCVR2(val)		MCR14(val, 1, c0, c2, 3)
+#define WCP14_ETMDCVR4(val)		MCR14(val, 1, c0, c4, 3)
+#define WCP14_ETMDCVR6(val)		MCR14(val, 1, c0, c6, 3)
+#define WCP14_ETMDCVR8(val)		MCR14(val, 1, c0, c8, 3)
+#define WCP14_ETMDCVR10(val)		MCR14(val, 1, c0, c10, 3)
+#define WCP14_ETMDCVR12(val)		MCR14(val, 1, c0, c12, 3)
+#define WCP14_ETMDCVR14(val)		MCR14(val, 1, c0, c14, 3)
+#define WCP14_ETMDCMR0(val)		MCR14(val, 1, c0, c0, 4)
+#define WCP14_ETMDCMR2(val)		MCR14(val, 1, c0, c2, 4)
+#define WCP14_ETMDCMR4(val)		MCR14(val, 1, c0, c4, 4)
+#define WCP14_ETMDCMR6(val)		MCR14(val, 1, c0, c6, 4)
+#define WCP14_ETMDCMR8(val)		MCR14(val, 1, c0, c8, 4)
+#define WCP14_ETMDCMR10(val)		MCR14(val, 1, c0, c10, 4)
+#define WCP14_ETMDCMR12(val)		MCR14(val, 1, c0, c12, 4)
+#define WCP14_ETMDCMR14(val)		MCR14(val, 1, c0, c14, 4)
+#define WCP14_ETMCNTRLDVR0(val)		MCR14(val, 1, c0, c0, 5)
+#define WCP14_ETMCNTRLDVR1(val)		MCR14(val, 1, c0, c1, 5)
+#define WCP14_ETMCNTRLDVR2(val)		MCR14(val, 1, c0, c2, 5)
+#define WCP14_ETMCNTRLDVR3(val)		MCR14(val, 1, c0, c3, 5)
+#define WCP14_ETMCNTENR0(val)		MCR14(val, 1, c0, c4, 5)
+#define WCP14_ETMCNTENR1(val)		MCR14(val, 1, c0, c5, 5)
+#define WCP14_ETMCNTENR2(val)		MCR14(val, 1, c0, c6, 5)
+#define WCP14_ETMCNTENR3(val)		MCR14(val, 1, c0, c7, 5)
+#define WCP14_ETMCNTRLDEVR0(val)	MCR14(val, 1, c0, c8, 5)
+#define WCP14_ETMCNTRLDEVR1(val)	MCR14(val, 1, c0, c9, 5)
+#define WCP14_ETMCNTRLDEVR2(val)	MCR14(val, 1, c0, c10, 5)
+#define WCP14_ETMCNTRLDEVR3(val)	MCR14(val, 1, c0, c11, 5)
+#define WCP14_ETMCNTVR0(val)		MCR14(val, 1, c0, c12, 5)
+#define WCP14_ETMCNTVR1(val)		MCR14(val, 1, c0, c13, 5)
+#define WCP14_ETMCNTVR2(val)		MCR14(val, 1, c0, c14, 5)
+#define WCP14_ETMCNTVR3(val)		MCR14(val, 1, c0, c15, 5)
+#define WCP14_ETMSQ12EVR(val)		MCR14(val, 1, c0, c0, 6)
+#define WCP14_ETMSQ21EVR(val)		MCR14(val, 1, c0, c1, 6)
+#define WCP14_ETMSQ23EVR(val)		MCR14(val, 1, c0, c2, 6)
+#define WCP14_ETMSQ31EVR(val)		MCR14(val, 1, c0, c3, 6)
+#define WCP14_ETMSQ32EVR(val)		MCR14(val, 1, c0, c4, 6)
+#define WCP14_ETMSQ13EVR(val)		MCR14(val, 1, c0, c5, 6)
+#define WCP14_ETMSQR(val)		MCR14(val, 1, c0, c7, 6)
+#define WCP14_ETMEXTOUTEVR0(val)	MCR14(val, 1, c0, c8, 6)
+#define WCP14_ETMEXTOUTEVR1(val)	MCR14(val, 1, c0, c9, 6)
+#define WCP14_ETMEXTOUTEVR2(val)	MCR14(val, 1, c0, c10, 6)
+#define WCP14_ETMEXTOUTEVR3(val)	MCR14(val, 1, c0, c11, 6)
+#define WCP14_ETMCIDCVR0(val)		MCR14(val, 1, c0, c12, 6)
+#define WCP14_ETMCIDCVR1(val)		MCR14(val, 1, c0, c13, 6)
+#define WCP14_ETMCIDCVR2(val)		MCR14(val, 1, c0, c14, 6)
+#define WCP14_ETMCIDCMR(val)		MCR14(val, 1, c0, c15, 6)
+#define WCP14_ETMIMPSPEC0(val)		MCR14(val, 1, c0, c0, 7)
+#define WCP14_ETMIMPSPEC1(val)		MCR14(val, 1, c0, c1, 7)
+#define WCP14_ETMIMPSPEC2(val)		MCR14(val, 1, c0, c2, 7)
+#define WCP14_ETMIMPSPEC3(val)		MCR14(val, 1, c0, c3, 7)
+#define WCP14_ETMIMPSPEC4(val)		MCR14(val, 1, c0, c4, 7)
+#define WCP14_ETMIMPSPEC5(val)		MCR14(val, 1, c0, c5, 7)
+#define WCP14_ETMIMPSPEC6(val)		MCR14(val, 1, c0, c6, 7)
+#define WCP14_ETMIMPSPEC7(val)		MCR14(val, 1, c0, c7, 7)
+/* Can be read only in ETMv3.4, ETMv3.5 */
+#define WCP14_ETMSYNCFR(val)		MCR14(val, 1, c0, c8, 7)
+#define WCP14_ETMEXTINSELR(val)		MCR14(val, 1, c0, c11, 7)
+#define WCP14_ETMTESSEICR(val)		MCR14(val, 1, c0, c12, 7)
+#define WCP14_ETMEIBCR(val)		MCR14(val, 1, c0, c13, 7)
+#define WCP14_ETMTSEVR(val)		MCR14(val, 1, c0, c14, 7)
+#define WCP14_ETMAUXCR(val)		MCR14(val, 1, c0, c15, 7)
+#define WCP14_ETMTRACEIDR(val)		MCR14(val, 1, c1, c0, 0)
+#define WCP14_ETMIDR2(val)		MCR14(val, 1, c1, c2, 0)
+#define WCP14_ETMVMIDCVR(val)		MCR14(val, 1, c1, c0, 1)
+#define WCP14_ETMOSLAR(val)		MCR14(val, 1, c1, c0, 4)
+/* Not available in PFTv1.1 */
+#define WCP14_ETMOSSRR(val)		MCR14(val, 1, c1, c2, 4)
+#define WCP14_ETMPDCR(val)		MCR14(val, 1, c1, c4, 4)
+#define WCP14_ETMPDSR(val)		MCR14(val, 1, c1, c5, 4)
+#define WCP14_ETMITCTRL(val)		MCR14(val, 1, c7, c0, 4)
+#define WCP14_ETMCLAIMSET(val)		MCR14(val, 1, c7, c8, 6)
+#define WCP14_ETMCLAIMCLR(val)		MCR14(val, 1, c7, c9, 6)
+/* Writes to this from CP14 interface are ignored */
+#define WCP14_ETMLAR(val)		MCR14(val, 1, c7, c12, 6)
+
+#endif
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 1d3153c7eb41..816db0bf2dd8 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -55,6 +55,7 @@
  * The bits we set in HCR:
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until MMU and caches are on)
  * TSW:		Trap cache operations by set/way
  * TWI:		Trap WFI
  * TWE:		Trap WFE
@@ -68,8 +69,7 @@
  */
 #define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
 			HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
-			HCR_TWE | HCR_SWIO | HCR_TIDCP)
-#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
+			HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP)
 
 /* System Control Register (SCTLR) bits */
 #define SCTLR_TE	(1 << 30)
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 661da11f76f4..3a67bec72d0c 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -48,7 +48,9 @@
 #define c13_TID_URO	26	/* Thread ID, User R/O */
 #define c13_TID_PRIV	27	/* Thread ID, Privileged */
 #define c14_CNTKCTL	28	/* Timer Control Register (PL1) */
-#define NR_CP15_REGS	29	/* Number of regs (incl. invalid) */
+#define c10_AMAIR0	29	/* Auxilary Memory Attribute Indirection Reg0 */
+#define c10_AMAIR1	30	/* Auxilary Memory Attribute Indirection Reg1 */
+#define NR_CP15_REGS	31	/* Number of regs (incl. invalid) */
 
 #define ARM_EXCEPTION_RESET	  0
 #define ARM_EXCEPTION_UNDEFINED   1
@@ -59,6 +61,24 @@
 #define ARM_EXCEPTION_FIQ	  6
 #define ARM_EXCEPTION_HVC	  7
 
+/*
+ * The rr_lo_hi macro swaps a pair of registers depending on
+ * current endianness. It is used in conjunction with ldrd and strd
+ * instructions that load/store a 64-bit value from/to memory to/from
+ * a pair of registers which are used with the mrrc and mcrr instructions.
+ * If used with the ldrd/strd instructions, the a1 parameter is the first
+ * source/destination register and the a2 parameter is the second
+ * source/destination register. Note that the ldrd/strd instructions
+ * already swap the bytes within the words correctly according to the
+ * endianness setting, but the order of the registers need to be effectively
+ * swapped when used with the mrrc/mcrr instructions.
+ */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define rr_lo_hi(a1, a2) a2, a1
+#else
+#define rr_lo_hi(a1, a2) a1, a2
+#endif
+
 #ifndef __ASSEMBLY__
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 0fa90c962ac8..b9db269c6e61 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -149,6 +149,11 @@ static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu)
 
 static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu)
 {
+	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(struct kvm_vcpu *vcpu)
+{
 	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE;
 }
 
@@ -185,9 +190,16 @@ static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
 		default:
 			return be32_to_cpu(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return le16_to_cpu(data & 0xffff);
+		default:
+			return le32_to_cpu(data);
+		}
 	}
-
-	return data;		/* Leave LE untouched */
 }
 
 static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
@@ -203,9 +215,16 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 		default:
 			return cpu_to_be32(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_le16(data & 0xffff);
+		default:
+			return cpu_to_le32(data);
+		}
 	}
-
-	return data;		/* Leave LE untouched */
 }
 
 #endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 098f7dd6d564..46e5d4da1989 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -19,6 +19,8 @@
 #ifndef __ARM_KVM_HOST_H__
 #define __ARM_KVM_HOST_H__
 
+#include <linux/types.h>
+#include <linux/kvm_types.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -36,13 +38,12 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
 
-#define KVM_VCPU_MAX_FEATURES 1
+#define KVM_VCPU_MAX_FEATURES 2
 
 #include <kvm/arm_vgic.h>
 
-struct kvm_vcpu;
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
 
@@ -101,6 +102,12 @@ struct kvm_vcpu_arch {
 	/* The CPU type we expose to the VM */
 	u32 midr;
 
+	/* HYP trapping configuration */
+	u32 hcr;
+
+	/* Interrupt related fields */
+	u32 irq_lines;		/* IRQ and FIQ levels */
+
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
@@ -128,9 +135,6 @@ struct kvm_vcpu_arch {
 	/* IO related fields */
 	struct kvm_decode mmio_decode;
 
-	/* Interrupt related fields */
-	u32 irq_lines;		/* IRQ and FIQ levels */
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
@@ -146,20 +150,17 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-struct kvm_vcpu_init;
 int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			const struct kvm_vcpu_init *init);
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
-struct kvm_one_reg;
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 u64 kvm_call_hyp(void *hypfn, ...);
 void force_vm_exit(const cpumask_t *mask);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-struct kvm;
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
@@ -184,7 +185,6 @@ struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
 
 int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
 unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu);
-struct kvm_one_reg;
 int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 
@@ -222,10 +222,18 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 	return 0;
 }
 
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+	BUG_ON(vgic->type != VGIC_V2);
+}
+
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
-u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
-int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 2d122adcdb22..3f688b458143 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -78,17 +78,6 @@ static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
 	flush_pmd_entry(pte);
 }
 
-static inline bool kvm_is_write_fault(unsigned long hsr)
-{
-	unsigned long hsr_ec = hsr >> HSR_EC_SHIFT;
-	if (hsr_ec == HSR_EC_IABT)
-		return false;
-	else if ((hsr & HSR_ISV) && !(hsr & HSR_WNR))
-		return false;
-	else
-		return true;
-}
-
 static inline void kvm_clean_pgd(pgd_t *pgd)
 {
 	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
@@ -114,11 +103,46 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= L_PMD_S2_RDWR;
 }
 
+/* Open coded p*d_addr_end that can deal with 64bit addresses */
+#define kvm_pgd_addr_end(addr, end)					\
+({	u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;		\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+
+#define kvm_pud_addr_end(addr,end)		(end)
+
+#define kvm_pmd_addr_end(addr, end)					\
+({	u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK;		\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+
+static inline bool kvm_page_empty(void *ptr)
+{
+	struct page *ptr_page = virt_to_page(ptr);
+	return page_count(ptr_page) == 1;
+}
+
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(pudp) (0)
+
+
 struct kvm;
 
-static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
-					      unsigned long size)
+#define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
+	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+					     unsigned long size)
+{
+	if (!vcpu_has_cache_enabled(vcpu))
+		kvm_flush_dcache_to_poc((void *)hva, size);
+	
 	/*
 	 * If we are going to insert an instruction page and the icache is
 	 * either VIPT or PIPT, there is a potential problem where the host
@@ -139,9 +163,10 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
 	}
 }
 
-#define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
 #define kvm_virt_to_phys(x)		virt_to_idmap((unsigned long)(x))
 
+void stage2_flush_vm(struct kvm *kvm);
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/kvm_psci.h b/arch/arm/include/asm/kvm_psci.h
index 9a83d98bf170..6bda945d31fa 100644
--- a/arch/arm/include/asm/kvm_psci.h
+++ b/arch/arm/include/asm/kvm_psci.h
@@ -18,6 +18,10 @@
 #ifndef __ARM_KVM_PSCI_H__
 #define __ARM_KVM_PSCI_H__
 
-bool kvm_psci_call(struct kvm_vcpu *vcpu);
+#define KVM_ARM_PSCI_0_1	1
+#define KVM_ARM_PSCI_0_2	2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
 
 #endif /* __ARM_KVM_PSCI_H__ */
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index dfff709fda3c..219ac88a9542 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -140,6 +140,7 @@
 #define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
 #define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_VECTORS	(_AT(pteval_t, 0x0f) << 2)	/* 1111 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index f24edad26c70..0cd7824ca762 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -62,9 +62,19 @@ struct pmu_hw_events {
 	raw_spinlock_t		pmu_lock;
 };
 
+struct cpupmu_regs {
+	u32 pmc;
+	u32 pmcntenset;
+	u32 pmuseren;
+	u32 pmintenset;
+	u32 pmxevttype[8];
+	u32 pmxevtcnt[8];
+};
+
 struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	active_irqs;
+	cpumask_t	valid_cpus;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 	void		(*enable)(struct perf_event *event);
@@ -81,6 +91,8 @@ struct arm_pmu {
 	int		(*request_irq)(struct arm_pmu *, irq_handler_t handler);
 	void		(*free_irq)(struct arm_pmu *);
 	int		(*map_event)(struct perf_event *event);
+	void		(*save_regs)(struct arm_pmu *, struct cpupmu_regs *);
+	void		(*restore_regs)(struct arm_pmu *, struct cpupmu_regs *);
 	int		num_events;
 	atomic_t	active_events;
 	struct mutex	reserve_mutex;
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index c4ae171850f8..eb628a6679e8 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,6 +16,10 @@
 
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
 #define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL0	0
+#define PSCI_POWER_STATE_AFFINITY_LEVEL1	1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL2	2
+#define PSCI_POWER_STATE_AFFINITY_LEVEL3	3
 
 struct psci_power_state {
 	u16	id;
@@ -42,4 +46,12 @@ static inline void psci_init(void) { }
 static inline bool psci_smp_available(void) { return false; }
 #endif
 
+#ifdef CONFIG_ARM_PSCI
+extern int psci_probe(void);
+#else
+static inline int psci_probe(void)
+{
+	return -ENODEV;
+}
+#endif
 #endif /* __ASM_ARM_PSCI_H */
diff --git a/arch/arm/include/asm/smp_scu.h b/arch/arm/include/asm/smp_scu.h
index 0393fbab8dd5..bfe163c40024 100644
--- a/arch/arm/include/asm/smp_scu.h
+++ b/arch/arm/include/asm/smp_scu.h
@@ -11,7 +11,7 @@
 
 static inline bool scu_a9_has_base(void)
 {
-	return read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9;
+	return read_cpuid_part() == ARM_CPU_PART_CORTEX_A9;
 }
 
 static inline unsigned long scu_a9_get_base(void)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 71a06b293489..3e635eed9c6c 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -43,16 +43,6 @@ struct cpu_context_save {
 	__u32	extra[2];		/* Xscale 'acc' register, etc */
 };
 
-struct arm_restart_block {
-	union {
-		/* For user cache flushing */
-		struct {
-			unsigned long start;
-			unsigned long end;
-		} cache;
-	};
-};
-
 /*
  * low level task data that entry.S needs immediate access to.
  * __switch_to() assumes cpu_context follows immediately after cpu_domain.
@@ -78,7 +68,6 @@ struct thread_info {
 	unsigned long		thumbee_state;	/* ThumbEE Handler Base register */
 #endif
 	struct restart_block	restart_block;
-	struct arm_restart_block	arm_restart_block;
 };
 
 #define INIT_THREAD_INFO(tsk)						\
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 83259b873333..5f833f7adba1 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -1,6 +1,9 @@
 #ifndef __ASMARM_TLS_H
 #define __ASMARM_TLS_H
 
+#include <linux/compiler.h>
+#include <asm/thread_info.h>
+
 #ifdef __ASSEMBLY__
 #include <asm/asm-offsets.h>
 	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
@@ -50,6 +53,49 @@
 #endif
 
 #ifndef __ASSEMBLY__
+
+static inline void set_tls(unsigned long val)
+{
+	struct thread_info *thread;
+
+	thread = current_thread_info();
+
+	thread->tp_value[0] = val;
+
+	/*
+	 * This code runs with preemption enabled and therefore must
+	 * be reentrant with respect to switch_tls.
+	 *
+	 * We need to ensure ordering between the shadow state and the
+	 * hardware state, so that we don't corrupt the hardware state
+	 * with a stale shadow state during context switch.
+	 *
+	 * If we're preempted here, switch_tls will load TPIDRURO from
+	 * thread_info upon resuming execution and the following mcr
+	 * is merely redundant.
+	 */
+	barrier();
+
+	if (!tls_emu) {
+		if (has_tls_reg) {
+			asm("mcr p15, 0, %0, c13, c0, 3"
+			    : : "r" (val));
+		} else {
+#ifdef CONFIG_KUSER_HELPERS
+			/*
+			 * User space must never try to access this
+			 * directly.  Expect your app to break
+			 * eventually if you do so.  The user helper
+			 * at 0xffff0fe0 must be used instead.  (see
+			 * entry-armv.S for details)
+			 */
+			*((unsigned int *)0xffff0ff0) = val;
+#endif
+		}
+
+	}
+}
+
 static inline unsigned long get_tpuser(void)
 {
 	unsigned long reg = 0;
@@ -59,5 +105,23 @@ static inline unsigned long get_tpuser(void)
 
 	return reg;
 }
+
+static inline void set_tpuser(unsigned long val)
+{
+	/* Since TPIDRURW is fully context-switched (unlike TPIDRURO),
+	 * we need not update thread_info.
+	 */
+	if (has_tls_reg && !tls_emu) {
+		asm("mcr p15, 0, %0, c13, c0, 2"
+		    : : "r" (val));
+	}
+}
+
+static inline void flush_tls(void)
+{
+	set_tls(0);
+	set_tpuser(0);
+}
+
 #endif
 #endif	/* __ASMARM_TLS_H */
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84adcd2..611edefaeaf1 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -26,11 +26,14 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
 
 #else
 
 static inline void init_cpu_topology(void) { }
 static inline void store_cpu_topology(unsigned int cpuid) { }
+static inline int cluster_to_logical_mask(unsigned int socket_id,
+	cpumask_t *cluster_mask) { return -EINVAL; }
 
 #endif
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 72abdc541f38..7f3f3cc25d7e 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -171,8 +171,9 @@ extern int __put_user_8(void *, unsigned long long);
 #define __put_user_check(x,p)							\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
+		const typeof(*(p)) __user *__tmp_p = (p);		\
 		register const typeof(*(p)) __r2 asm("r2") = (x);	\
-		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index acabef1a75df..21ca0cebcab0 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -15,7 +15,17 @@
 
 #include <uapi/asm/unistd.h>
 
+/*
+ * This may need to be greater than __NR_last_syscall+1 in order to
+ * account for the padding in the syscall table
+ */
 #define __NR_syscalls  (384)
+
+/*
+ * *NOTE*: This is a ghost syscall private to the kernel.  Only the
+ * __kuser_cmpxchg code in entry-armv.S should be aware of its
+ * existence.  Don't ever use this from user code.
+ */
 #define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
 
 #define __ARCH_WANT_STAT64
@@ -48,6 +58,5 @@
  */
 #define __IGNORE_fadvise64_64
 #define __IGNORE_migrate_pages
-#define __IGNORE_kcmp
 
 #endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index ef0c8785ba16..09ee408c1a67 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -20,10 +20,12 @@
 #define __ARM_KVM_H__
 
 #include <linux/types.h>
+#include <linux/psci.h>
 #include <asm/ptrace.h>
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -83,6 +85,7 @@ struct kvm_regs {
 #define KVM_VGIC_V2_CPU_SIZE		0x2000
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_PSCI_0_2		1 /* CPU uses PSCI v0.2 */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -171,6 +174,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
@@ -201,9 +205,9 @@ struct kvm_arch_memory_slot {
 #define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
 #define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
 
-#define KVM_PSCI_RET_SUCCESS		0
-#define KVM_PSCI_RET_NI			((unsigned long)-1)
-#define KVM_PSCI_RET_INVAL		((unsigned long)-2)
-#define KVM_PSCI_RET_DENIED		((unsigned long)-3)
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
 
 #endif /* __ARM_KVM_H__ */
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index fb5584d0cc05..c3776331f407 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -410,11 +410,6 @@
 #define __NR_sched_getattr		(__NR_SYSCALL_BASE+381)
 
 /*
- * This may need to be greater than __NR_last_syscall+1 in order to
- * account for the padding in the syscall table
- */
-
-/*
  * The following SWIs are ARM private.
  */
 #define __ARM_NR_BASE			(__NR_SYSCALL_BASE+0x0f0000)
@@ -425,12 +420,6 @@
 #define __ARM_NR_set_tls		(__ARM_NR_BASE+5)
 
 /*
- * *NOTE*: This is a ghost syscall private to the kernel.  Only the
- * __kuser_cmpxchg code in entry-armv.S should be aware of its
- * existence.  Don't ever use this from user code.
- */
-
-/*
  * The following syscalls are obsolete and no longer available for EABI.
  */
 #if !defined(__KERNEL__)
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index a30fc9be9e9e..b4ea607ff6de 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -30,7 +30,6 @@ else
 obj-y		+= entry-armv.o
 endif
 
-obj-$(CONFIG_OC_ETM)		+= etm.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index ded041711beb..713e807621d2 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -174,6 +174,7 @@ int main(void)
   DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
   DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
   DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
+  DEFINE(VCPU_HCR,		offsetof(struct kvm_vcpu, arch.hcr));
   DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
   DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
   DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
@@ -181,13 +182,13 @@ int main(void)
   DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
 #ifdef CONFIG_KVM_ARM_VGIC
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_CPU_HCR,		offsetof(struct vgic_cpu, vgic_hcr));
-  DEFINE(VGIC_CPU_VMCR,		offsetof(struct vgic_cpu, vgic_vmcr));
-  DEFINE(VGIC_CPU_MISR,		offsetof(struct vgic_cpu, vgic_misr));
-  DEFINE(VGIC_CPU_EISR,		offsetof(struct vgic_cpu, vgic_eisr));
-  DEFINE(VGIC_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_elrsr));
-  DEFINE(VGIC_CPU_APR,		offsetof(struct vgic_cpu, vgic_apr));
-  DEFINE(VGIC_CPU_LR,		offsetof(struct vgic_cpu, vgic_lr));
+  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
+  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
+  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
+  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
+  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
+  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
+  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
   DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
 #ifdef CONFIG_KVM_ARM_TIMER
   DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
diff --git a/arch/arm/kernel/crash_dump.c b/arch/arm/kernel/crash_dump.c
index 90c50d4b43f7..5d1286d51154 100644
--- a/arch/arm/kernel/crash_dump.c
+++ b/arch/arm/kernel/crash_dump.c
@@ -39,7 +39,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!csize)
 		return 0;
 
-	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+	vaddr = ioremap(__pfn_to_phys(pfn), PAGE_SIZE);
 	if (!vaddr)
 		return -ENOMEM;
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index f751714d52c1..97707977144c 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -212,7 +212,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 
 	if (!mdesc) {
 		const char *prop;
-		long size;
+		int size;
 		unsigned long dt_root;
 
 		early_print("\nError: unrecognized/unsupported "
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 39f89fbd5111..88c6babeb0b5 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -132,6 +132,10 @@
 	orrne	r5, V7M_xPSR_FRAMEPTRALIGN
 	biceq	r5, V7M_xPSR_FRAMEPTRALIGN
 
+	@ ensure bit 0 is cleared in the PC, otherwise behaviour is
+	@ unpredictable
+	bic	r4, #1
+
 	@ write basic exception frame
 	stmdb	r2!, {r1, r3-r5}
 	ldmia	sp, {r1, r3-r5}
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
deleted file mode 100644
index 131a6ab5f355..000000000000
--- a/arch/arm/kernel/etm.c
+++ /dev/null
@@ -1,654 +0,0 @@
-/*
- * linux/arch/arm/kernel/etm.c
- *
- * Driver for ARM's Embedded Trace Macrocell and Embedded Trace Buffer.
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/io.h>
-#include <linux/sysrq.h>
-#include <linux/device.h>
-#include <linux/clk.h>
-#include <linux/amba/bus.h>
-#include <linux/fs.h>
-#include <linux/uaccess.h>
-#include <linux/miscdevice.h>
-#include <linux/vmalloc.h>
-#include <linux/mutex.h>
-#include <linux/module.h>
-#include <asm/hardware/coresight.h>
-#include <asm/sections.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alexander Shishkin");
-
-/*
- * ETM tracer state
- */
-struct tracectx {
-	unsigned int	etb_bufsz;
-	void __iomem	*etb_regs;
-	void __iomem	*etm_regs;
-	unsigned long	flags;
-	int		ncmppairs;
-	int		etm_portsz;
-	struct device	*dev;
-	struct clk	*emu_clk;
-	struct mutex	mutex;
-};
-
-static struct tracectx tracer;
-
-static inline bool trace_isrunning(struct tracectx *t)
-{
-	return !!(t->flags & TRACER_RUNNING);
-}
-
-static int etm_setup_address_range(struct tracectx *t, int n,
-		unsigned long start, unsigned long end, int exclude, int data)
-{
-	u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_NSONLY | \
-		    ETMAAT_NOVALCMP;
-
-	if (n < 1 || n > t->ncmppairs)
-		return -EINVAL;
-
-	/* comparators and ranges are numbered starting with 1 as opposed
-	 * to bits in a word */
-	n--;
-
-	if (data)
-		flags |= ETMAAT_DLOADSTORE;
-	else
-		flags |= ETMAAT_IEXEC;
-
-	/* first comparator for the range */
-	etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2));
-	etm_writel(t, start, ETMR_COMP_VAL(n * 2));
-
-	/* second comparator is right next to it */
-	etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1));
-	etm_writel(t, end, ETMR_COMP_VAL(n * 2 + 1));
-
-	flags = exclude ? ETMTE_INCLEXCL : 0;
-	etm_writel(t, flags | (1 << n), ETMR_TRACEENCTRL);
-
-	return 0;
-}
-
-static int trace_start(struct tracectx *t)
-{
-	u32 v;
-	unsigned long timeout = TRACER_TIMEOUT;
-
-	etb_unlock(t);
-
-	etb_writel(t, 0, ETBR_FORMATTERCTRL);
-	etb_writel(t, 1, ETBR_CTRL);
-
-	etb_lock(t);
-
-	/* configure etm */
-	v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz);
-
-	if (t->flags & TRACER_CYCLE_ACC)
-		v |= ETMCTRL_CYCLEACCURATE;
-
-	etm_unlock(t);
-
-	etm_writel(t, v, ETMR_CTRL);
-
-	while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
-		etm_lock(t);
-		return -EFAULT;
-	}
-
-	etm_setup_address_range(t, 1, (unsigned long)_stext,
-			(unsigned long)_etext, 0, 0);
-	etm_writel(t, 0, ETMR_TRACEENCTRL2);
-	etm_writel(t, 0, ETMR_TRACESSCTRL);
-	etm_writel(t, 0x6f, ETMR_TRACEENEVT);
-
-	v &= ~ETMCTRL_PROGRAM;
-	v |= ETMCTRL_PORTSEL;
-
-	etm_writel(t, v, ETMR_CTRL);
-
-	timeout = TRACER_TIMEOUT;
-	while (etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n");
-		etm_lock(t);
-		return -EFAULT;
-	}
-
-	etm_lock(t);
-
-	t->flags |= TRACER_RUNNING;
-
-	return 0;
-}
-
-static int trace_stop(struct tracectx *t)
-{
-	unsigned long timeout = TRACER_TIMEOUT;
-
-	etm_unlock(t);
-
-	etm_writel(t, 0x440, ETMR_CTRL);
-	while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
-		etm_lock(t);
-		return -EFAULT;
-	}
-
-	etm_lock(t);
-
-	etb_unlock(t);
-	etb_writel(t, ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL);
-
-	timeout = TRACER_TIMEOUT;
-	while (etb_readl(t, ETBR_FORMATTERCTRL) &
-			ETBFF_MANUAL_FLUSH && --timeout)
-		;
-	if (!timeout) {
-		dev_dbg(t->dev, "Waiting for formatter flush to commence "
-				"timed out\n");
-		etb_lock(t);
-		return -EFAULT;
-	}
-
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_lock(t);
-
-	t->flags &= ~TRACER_RUNNING;
-
-	return 0;
-}
-
-static int etb_getdatalen(struct tracectx *t)
-{
-	u32 v;
-	int rp, wp;
-
-	v = etb_readl(t, ETBR_STATUS);
-
-	if (v & 1)
-		return t->etb_bufsz;
-
-	rp = etb_readl(t, ETBR_READADDR);
-	wp = etb_readl(t, ETBR_WRITEADDR);
-
-	if (rp > wp) {
-		etb_writel(t, 0, ETBR_READADDR);
-		etb_writel(t, 0, ETBR_WRITEADDR);
-
-		return 0;
-	}
-
-	return wp - rp;
-}
-
-/* sysrq+v will always stop the running trace and leave it at that */
-static void etm_dump(void)
-{
-	struct tracectx *t = &tracer;
-	u32 first = 0;
-	int length;
-
-	if (!t->etb_regs) {
-		printk(KERN_INFO "No tracing hardware found\n");
-		return;
-	}
-
-	if (trace_isrunning(t))
-		trace_stop(t);
-
-	etb_unlock(t);
-
-	length = etb_getdatalen(t);
-
-	if (length == t->etb_bufsz)
-		first = etb_readl(t, ETBR_WRITEADDR);
-
-	etb_writel(t, first, ETBR_READADDR);
-
-	printk(KERN_INFO "Trace buffer contents length: %d\n", length);
-	printk(KERN_INFO "--- ETB buffer begin ---\n");
-	for (; length; length--)
-		printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM)));
-	printk(KERN_INFO "\n--- ETB buffer end ---\n");
-
-	/* deassert the overflow bit */
-	etb_writel(t, 1, ETBR_CTRL);
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-	etb_writel(t, 0, ETBR_READADDR);
-	etb_writel(t, 0, ETBR_WRITEADDR);
-
-	etb_lock(t);
-}
-
-static void sysrq_etm_dump(int key)
-{
-	dev_dbg(tracer.dev, "Dumping ETB buffer\n");
-	etm_dump();
-}
-
-static struct sysrq_key_op sysrq_etm_op = {
-	.handler = sysrq_etm_dump,
-	.help_msg = "etm-buffer-dump(v)",
-	.action_msg = "etm",
-};
-
-static int etb_open(struct inode *inode, struct file *file)
-{
-	if (!tracer.etb_regs)
-		return -ENODEV;
-
-	file->private_data = &tracer;
-
-	return nonseekable_open(inode, file);
-}
-
-static ssize_t etb_read(struct file *file, char __user *data,
-		size_t len, loff_t *ppos)
-{
-	int total, i;
-	long length;
-	struct tracectx *t = file->private_data;
-	u32 first = 0;
-	u32 *buf;
-
-	mutex_lock(&t->mutex);
-
-	if (trace_isrunning(t)) {
-		length = 0;
-		goto out;
-	}
-
-	etb_unlock(t);
-
-	total = etb_getdatalen(t);
-	if (total == t->etb_bufsz)
-		first = etb_readl(t, ETBR_WRITEADDR);
-
-	etb_writel(t, first, ETBR_READADDR);
-
-	length = min(total * 4, (int)len);
-	buf = vmalloc(length);
-
-	dev_dbg(t->dev, "ETB buffer length: %d\n", total);
-	dev_dbg(t->dev, "ETB status reg: %x\n", etb_readl(t, ETBR_STATUS));
-	for (i = 0; i < length / 4; i++)
-		buf[i] = etb_readl(t, ETBR_READMEM);
-
-	/* the only way to deassert overflow bit in ETB status is this */
-	etb_writel(t, 1, ETBR_CTRL);
-	etb_writel(t, 0, ETBR_CTRL);
-
-	etb_writel(t, 0, ETBR_WRITEADDR);
-	etb_writel(t, 0, ETBR_READADDR);
-	etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-
-	etb_lock(t);
-
-	length -= copy_to_user(data, buf, length);
-	vfree(buf);
-
-out:
-	mutex_unlock(&t->mutex);
-
-	return length;
-}
-
-static int etb_release(struct inode *inode, struct file *file)
-{
-	/* there's nothing to do here, actually */
-	return 0;
-}
-
-static const struct file_operations etb_fops = {
-	.owner = THIS_MODULE,
-	.read = etb_read,
-	.open = etb_open,
-	.release = etb_release,
-	.llseek = no_llseek,
-};
-
-static struct miscdevice etb_miscdev = {
-	.name = "tracebuf",
-	.minor = 0,
-	.fops = &etb_fops,
-};
-
-static int etb_probe(struct amba_device *dev, const struct amba_id *id)
-{
-	struct tracectx *t = &tracer;
-	int ret = 0;
-
-	ret = amba_request_regions(dev, NULL);
-	if (ret)
-		goto out;
-
-	t->etb_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
-	if (!t->etb_regs) {
-		ret = -ENOMEM;
-		goto out_release;
-	}
-
-	amba_set_drvdata(dev, t);
-
-	etb_miscdev.parent = &dev->dev;
-
-	ret = misc_register(&etb_miscdev);
-	if (ret)
-		goto out_unmap;
-
-	t->emu_clk = clk_get(&dev->dev, "emu_src_ck");
-	if (IS_ERR(t->emu_clk)) {
-		dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n");
-		return -EFAULT;
-	}
-
-	clk_enable(t->emu_clk);
-
-	etb_unlock(t);
-	t->etb_bufsz = etb_readl(t, ETBR_DEPTH);
-	dev_dbg(&dev->dev, "Size: %x\n", t->etb_bufsz);
-
-	/* make sure trace capture is disabled */
-	etb_writel(t, 0, ETBR_CTRL);
-	etb_writel(t, 0x1000, ETBR_FORMATTERCTRL);
-	etb_lock(t);
-
-	dev_dbg(&dev->dev, "ETB AMBA driver initialized.\n");
-
-out:
-	return ret;
-
-out_unmap:
-	iounmap(t->etb_regs);
-
-out_release:
-	amba_release_regions(dev);
-
-	return ret;
-}
-
-static int etb_remove(struct amba_device *dev)
-{
-	struct tracectx *t = amba_get_drvdata(dev);
-
-	iounmap(t->etb_regs);
-	t->etb_regs = NULL;
-
-	clk_disable(t->emu_clk);
-	clk_put(t->emu_clk);
-
-	amba_release_regions(dev);
-
-	return 0;
-}
-
-static struct amba_id etb_ids[] = {
-	{
-		.id	= 0x0003b907,
-		.mask	= 0x0007ffff,
-	},
-	{ 0, 0 },
-};
-
-static struct amba_driver etb_driver = {
-	.drv		= {
-		.name	= "etb",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= etb_probe,
-	.remove		= etb_remove,
-	.id_table	= etb_ids,
-};
-
-/* use a sysfs file "trace_running" to start/stop tracing */
-static ssize_t trace_running_show(struct kobject *kobj,
-				  struct kobj_attribute *attr,
-				  char *buf)
-{
-	return sprintf(buf, "%x\n", trace_isrunning(&tracer));
-}
-
-static ssize_t trace_running_store(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   const char *buf, size_t n)
-{
-	unsigned int value;
-	int ret;
-
-	if (sscanf(buf, "%u", &value) != 1)
-		return -EINVAL;
-
-	mutex_lock(&tracer.mutex);
-	ret = value ? trace_start(&tracer) : trace_stop(&tracer);
-	mutex_unlock(&tracer.mutex);
-
-	return ret ? : n;
-}
-
-static struct kobj_attribute trace_running_attr =
-	__ATTR(trace_running, 0644, trace_running_show, trace_running_store);
-
-static ssize_t trace_info_show(struct kobject *kobj,
-				  struct kobj_attribute *attr,
-				  char *buf)
-{
-	u32 etb_wa, etb_ra, etb_st, etb_fc, etm_ctrl, etm_st;
-	int datalen;
-
-	etb_unlock(&tracer);
-	datalen = etb_getdatalen(&tracer);
-	etb_wa = etb_readl(&tracer, ETBR_WRITEADDR);
-	etb_ra = etb_readl(&tracer, ETBR_READADDR);
-	etb_st = etb_readl(&tracer, ETBR_STATUS);
-	etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL);
-	etb_lock(&tracer);
-
-	etm_unlock(&tracer);
-	etm_ctrl = etm_readl(&tracer, ETMR_CTRL);
-	etm_st = etm_readl(&tracer, ETMR_STATUS);
-	etm_lock(&tracer);
-
-	return sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n"
-			"ETBR_WRITEADDR:\t%08x\n"
-			"ETBR_READADDR:\t%08x\n"
-			"ETBR_STATUS:\t%08x\n"
-			"ETBR_FORMATTERCTRL:\t%08x\n"
-			"ETMR_CTRL:\t%08x\n"
-			"ETMR_STATUS:\t%08x\n",
-			datalen,
-			tracer.ncmppairs,
-			etb_wa,
-			etb_ra,
-			etb_st,
-			etb_fc,
-			etm_ctrl,
-			etm_st
-			);
-}
-
-static struct kobj_attribute trace_info_attr =
-	__ATTR(trace_info, 0444, trace_info_show, NULL);
-
-static ssize_t trace_mode_show(struct kobject *kobj,
-				  struct kobj_attribute *attr,
-				  char *buf)
-{
-	return sprintf(buf, "%d %d\n",
-			!!(tracer.flags & TRACER_CYCLE_ACC),
-			tracer.etm_portsz);
-}
-
-static ssize_t trace_mode_store(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   const char *buf, size_t n)
-{
-	unsigned int cycacc, portsz;
-
-	if (sscanf(buf, "%u %u", &cycacc, &portsz) != 2)
-		return -EINVAL;
-
-	mutex_lock(&tracer.mutex);
-	if (cycacc)
-		tracer.flags |= TRACER_CYCLE_ACC;
-	else
-		tracer.flags &= ~TRACER_CYCLE_ACC;
-
-	tracer.etm_portsz = portsz & 0x0f;
-	mutex_unlock(&tracer.mutex);
-
-	return n;
-}
-
-static struct kobj_attribute trace_mode_attr =
-	__ATTR(trace_mode, 0644, trace_mode_show, trace_mode_store);
-
-static int etm_probe(struct amba_device *dev, const struct amba_id *id)
-{
-	struct tracectx *t = &tracer;
-	int ret = 0;
-
-	if (t->etm_regs) {
-		dev_dbg(&dev->dev, "ETM already initialized\n");
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ret = amba_request_regions(dev, NULL);
-	if (ret)
-		goto out;
-
-	t->etm_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
-	if (!t->etm_regs) {
-		ret = -ENOMEM;
-		goto out_release;
-	}
-
-	amba_set_drvdata(dev, t);
-
-	mutex_init(&t->mutex);
-	t->dev = &dev->dev;
-	t->flags = TRACER_CYCLE_ACC;
-	t->etm_portsz = 1;
-
-	etm_unlock(t);
-	(void)etm_readl(t, ETMMR_PDSR);
-	/* dummy first read */
-	(void)etm_readl(&tracer, ETMMR_OSSRR);
-
-	t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf;
-	etm_writel(t, 0x440, ETMR_CTRL);
-	etm_lock(t);
-
-	ret = sysfs_create_file(&dev->dev.kobj,
-			&trace_running_attr.attr);
-	if (ret)
-		goto out_unmap;
-
-	/* failing to create any of these two is not fatal */
-	ret = sysfs_create_file(&dev->dev.kobj, &trace_info_attr.attr);
-	if (ret)
-		dev_dbg(&dev->dev, "Failed to create trace_info in sysfs\n");
-
-	ret = sysfs_create_file(&dev->dev.kobj, &trace_mode_attr.attr);
-	if (ret)
-		dev_dbg(&dev->dev, "Failed to create trace_mode in sysfs\n");
-
-	dev_dbg(t->dev, "ETM AMBA driver initialized.\n");
-
-out:
-	return ret;
-
-out_unmap:
-	iounmap(t->etm_regs);
-
-out_release:
-	amba_release_regions(dev);
-
-	return ret;
-}
-
-static int etm_remove(struct amba_device *dev)
-{
-	struct tracectx *t = amba_get_drvdata(dev);
-
-	iounmap(t->etm_regs);
-	t->etm_regs = NULL;
-
-	amba_release_regions(dev);
-
-	sysfs_remove_file(&dev->dev.kobj, &trace_running_attr.attr);
-	sysfs_remove_file(&dev->dev.kobj, &trace_info_attr.attr);
-	sysfs_remove_file(&dev->dev.kobj, &trace_mode_attr.attr);
-
-	return 0;
-}
-
-static struct amba_id etm_ids[] = {
-	{
-		.id	= 0x0003b921,
-		.mask	= 0x0007ffff,
-	},
-	{ 0, 0 },
-};
-
-static struct amba_driver etm_driver = {
-	.drv		= {
-		.name   = "etm",
-		.owner  = THIS_MODULE,
-	},
-	.probe		= etm_probe,
-	.remove		= etm_remove,
-	.id_table	= etm_ids,
-};
-
-static int __init etm_init(void)
-{
-	int retval;
-
-	retval = amba_driver_register(&etb_driver);
-	if (retval) {
-		printk(KERN_ERR "Failed to register etb\n");
-		return retval;
-	}
-
-	retval = amba_driver_register(&etm_driver);
-	if (retval) {
-		amba_driver_unregister(&etb_driver);
-		printk(KERN_ERR "Failed to probe etm\n");
-		return retval;
-	}
-
-	/* not being able to install this handler is not fatal */
-	(void)register_sysrq_key('v', &sysrq_etm_op);
-
-	return 0;
-}
-
-device_initcall(etm_init);
-
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 3d446605cbf8..c609f6712929 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -29,6 +29,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/smp.h>
 #include <linux/cpu_pm.h>
+#include <linux/coresight.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
@@ -36,7 +37,6 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/kdebug.h>
 #include <asm/traps.h>
-#include <asm/hardware/coresight.h>
 
 /* Breakpoint currently in use for each BRP. */
 static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
@@ -975,7 +975,7 @@ static void reset_ctrl_regs(void *unused)
 	 * Unconditionally clear the OS lock by writing a value
 	 * other than CS_LAR_KEY to the access register.
 	 */
-	ARM_DBG_WRITE(c1, c0, 4, ~CS_LAR_KEY);
+	ARM_DBG_WRITE(c1, c0, 4, ~CORESIGHT_UNLOCK);
 	isb();
 
 	/*
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 9723d17b8f38..1e782bdeee49 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -163,7 +163,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
 		cpumask_copy(d->affinity, affinity);
 
 	return ret;
diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c
index 18a76282970e..380c20fb9c85 100644
--- a/arch/arm/kernel/kprobes-common.c
+++ b/arch/arm/kernel/kprobes-common.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <asm/system_info.h>
+#include <asm/opcodes.h>
 
 #include "kprobes.h"
 
@@ -305,7 +306,8 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 
 	if (handler) {
 		/* We can emulate the instruction in (possibly) modified form */
-		asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist;
+		asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) |
+						   (rn << 16) | reglist);
 		asi->insn_handler = handler;
 		return INSN_GOOD;
 	}
@@ -334,13 +336,14 @@ prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
 #ifdef CONFIG_THUMB2_KERNEL
 	if (thumb) {
 		u16 *thumb_insn = (u16 *)asi->insn;
-		thumb_insn[1] = 0x4770; /* Thumb bx lr */
-		thumb_insn[2] = 0x4770; /* Thumb bx lr */
+		/* Thumb bx lr */
+		thumb_insn[1] = __opcode_to_mem_thumb16(0x4770);
+		thumb_insn[2] = __opcode_to_mem_thumb16(0x4770);
 		return insn;
 	}
-	asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
+	asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */
 #else
-	asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
+	asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */
 #endif
 	/* Make an ARM instruction unconditional */
 	if (insn < 0xe0000000)
@@ -360,12 +363,12 @@ set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
 	if (thumb) {
 		u16 *ip = (u16 *)asi->insn;
 		if (is_wide_instruction(insn))
-			*ip++ = insn >> 16;
-		*ip++ = insn;
+			*ip++ = __opcode_to_mem_thumb16(insn >> 16);
+		*ip++ = __opcode_to_mem_thumb16(insn);
 		return;
 	}
 #endif
-	asi->insn[0] = insn;
+	asi->insn[0] = __opcode_to_mem_arm(insn);
 }
 
 /*
diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c
index 6123daf397a7..241222c66a13 100644
--- a/arch/arm/kernel/kprobes-thumb.c
+++ b/arch/arm/kernel/kprobes-thumb.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
+#include <asm/opcodes.h>
 
 #include "kprobes.h"
 
@@ -163,9 +164,9 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi);
 
 	/* Fixup modified instruction to have halfwords in correct order...*/
-	insn = asi->insn[0];
-	((u16 *)asi->insn)[0] = insn >> 16;
-	((u16 *)asi->insn)[1] = insn & 0xffff;
+	insn = __mem_to_opcode_arm(asi->insn[0]);
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16);
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff);
 
 	return ret;
 }
@@ -1153,7 +1154,7 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 {
 	insn &= ~0x00ff;
 	insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */
-	((u16 *)asi->insn)[0] = insn;
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn);
 	asi->insn_handler = t16_emulate_hiregs;
 	return INSN_GOOD;
 }
@@ -1182,8 +1183,10 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	 * and call it with R9=SP and LR in the register list represented
 	 * by R8.
 	 */
-	((u16 *)asi->insn)[0] = 0xe929;		/* 1st half STMDB R9!,{} */
-	((u16 *)asi->insn)[1] = insn & 0x1ff;	/* 2nd half (register list) */
+	/* 1st half STMDB R9!,{} */
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929);
+	/* 2nd half (register list) */
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
 	asi->insn_handler = t16_emulate_push;
 	return INSN_GOOD;
 }
@@ -1232,8 +1235,10 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	 * and call it with R9=SP and PC in the register list represented
 	 * by R8.
 	 */
-	((u16 *)asi->insn)[0] = 0xe8b9;		/* 1st half LDMIA R9!,{} */
-	((u16 *)asi->insn)[1] = insn & 0x1ff;	/* 2nd half (register list) */
+	/* 1st half LDMIA R9!,{} */
+	((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9);
+	/* 2nd half (register list) */
+	((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
 	asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc
 					 : t16_emulate_pop_nopc;
 	return INSN_GOOD;
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index a7b621ece23d..49a87b6d0bf3 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -26,6 +26,7 @@
 #include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
+#include <asm/opcodes.h>
 #include <asm/cacheflush.h>
 
 #include "kprobes.h"
@@ -62,10 +63,10 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 #ifdef CONFIG_THUMB2_KERNEL
 	thumb = true;
 	addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
-	insn = ((u16 *)addr)[0];
+	insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]);
 	if (is_wide_instruction(insn)) {
-		insn <<= 16;
-		insn |= ((u16 *)addr)[1];
+		u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]);
+		insn = __opcode_thumb32_compose(insn, inst2);
 		decode_insn = thumb32_kprobe_decode_insn;
 	} else
 		decode_insn = thumb16_kprobe_decode_insn;
@@ -73,7 +74,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	thumb = false;
 	if (addr & 0x3)
 		return -EINVAL;
-	insn = *p->addr;
+	insn = __mem_to_opcode_arm(*p->addr);
 	decode_insn = arm_kprobe_decode_insn;
 #endif
 
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index f0d180d8b29f..8cf0996aa1a8 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -184,3 +184,10 @@ void machine_kexec(struct kimage *image)
 
 	soft_restart(reboot_entry_phys);
 }
+
+void arch_crash_save_vmcoreinfo(void)
+{
+#ifdef CONFIG_ARM_LPAE
+	VMCOREINFO_CONFIG(ARM_LPAE);
+#endif
+}
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 789d846a9184..42059a54a9c0 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/cpumask.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -86,6 +87,9 @@ armpmu_map_event(struct perf_event *event,
 		return armpmu_map_cache_event(cache_map, config);
 	case PERF_TYPE_RAW:
 		return armpmu_map_raw_event(raw_event_mask, config);
+	default:
+		if (event->attr.type >= PERF_TYPE_MAX)
+			return armpmu_map_raw_event(raw_event_mask, config);
 	}
 
 	return -ENOENT;
@@ -159,6 +163,8 @@ armpmu_stop(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to update the counter, so ignore
 	 * PERF_EF_UPDATE, see comments in armpmu_start().
@@ -175,6 +181,8 @@ static void armpmu_start(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to reprogram the period, so ignore
 	 * PERF_EF_RELOAD, see the comment below.
@@ -202,6 +210,9 @@ armpmu_del(struct perf_event *event, int flags)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
+
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
 	clear_bit(idx, hw_events->used_mask);
@@ -218,6 +229,10 @@ armpmu_add(struct perf_event *event, int flags)
 	int idx;
 	int err = 0;
 
+	/* An event following a process won't be stopped earlier */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return 0;
+
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
@@ -419,6 +434,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	if (event->cpu != -1 &&
+		!cpumask_test_cpu(event->cpu, &armpmu->valid_cpus))
+		return -ENOENT;
+
 	/* does not support taken branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 20d553c9f5e2..829664913e9b 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -19,6 +19,7 @@
 #define pr_fmt(fmt) "CPU PMU: " fmt
 
 #include <linux/bitmap.h>
+#include <linux/cpu_pm.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
@@ -31,33 +32,36 @@
 #include <asm/pmu.h>
 
 /* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
+static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu);
 
 static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
 static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
 static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
 
+static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs);
+
 /*
  * Despite the names, these two functions are CPU-specific and are used
  * by the OProfile/perf code.
  */
 const char *perf_pmu_name(void)
 {
-	if (!cpu_pmu)
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
+	if (!pmu)
 		return NULL;
 
-	return cpu_pmu->name;
+	return pmu->name;
 }
 EXPORT_SYMBOL_GPL(perf_pmu_name);
 
 int perf_num_counters(void)
 {
-	int max_events = 0;
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
 
-	if (cpu_pmu != NULL)
-		max_events = cpu_pmu->num_events;
+	if (!pmu)
+		return 0;
 
-	return max_events;
+	return pmu->num_events;
 }
 EXPORT_SYMBOL_GPL(perf_num_counters);
 
@@ -75,11 +79,13 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 {
 	int i, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int cpu = -1;
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
 	for (i = 0; i < irqs; ++i) {
-		if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+		cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
+		if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
 			continue;
 		irq = platform_get_irq(pmu_device, i);
 		if (irq >= 0)
@@ -91,6 +97,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 {
 	int i, err, irq, irqs;
 	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int cpu = -1;
 
 	if (!pmu_device)
 		return -ENODEV;
@@ -103,6 +110,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 
 	for (i = 0; i < irqs; ++i) {
 		err = 0;
+		cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
 		irq = platform_get_irq(pmu_device, i);
 		if (irq < 0)
 			continue;
@@ -112,7 +120,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 		 * assume that we're running on a uniprocessor machine and
 		 * continue. Otherwise, continue without this interrupt.
 		 */
-		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+		if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
 			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
 				    irq, i);
 			continue;
@@ -127,7 +135,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 			return err;
 		}
 
-		cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
 	}
 
 	return 0;
@@ -136,7 +144,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	int cpu;
-	for_each_possible_cpu(cpu) {
+	for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) {
 		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
 		events->events = per_cpu(hw_events, cpu);
 		events->used_mask = per_cpu(used_mask, cpu);
@@ -149,7 +157,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 
 	/* Ensure the PMU has sane values out of reset. */
 	if (cpu_pmu->reset)
-		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+		on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1);
 }
 
 /*
@@ -161,21 +169,46 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
 			  void *hcpu)
 {
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu);
+
 	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
 		return NOTIFY_DONE;
 
-	if (cpu_pmu && cpu_pmu->reset)
-		cpu_pmu->reset(cpu_pmu);
+	if (pmu && pmu->reset)
+		pmu->reset(pmu);
 	else
 		return NOTIFY_DONE;
 
 	return NOTIFY_OK;
 }
 
+static int cpu_pmu_pm_notify(struct notifier_block *b,
+				    unsigned long action, void *hcpu)
+{
+	int cpu = smp_processor_id();
+	struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu);
+	struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu);
+
+	if (!pmu)
+		return NOTIFY_DONE;
+
+	if (action == CPU_PM_ENTER && pmu->save_regs) {
+		pmu->save_regs(pmu, pmuregs);
+	} else if (action == CPU_PM_EXIT && pmu->restore_regs) {
+		pmu->restore_regs(pmu, pmuregs);
+	}
+
+	return NOTIFY_OK;
+}
+
 static struct notifier_block cpu_pmu_hotplug_notifier = {
 	.notifier_call = cpu_pmu_notify,
 };
 
+static struct notifier_block cpu_pmu_pm_notifier = {
+	.notifier_call = cpu_pmu_pm_notify,
+};
+
 /*
  * PMU platform driver and devicetree bindings.
  */
@@ -202,51 +235,44 @@ static struct platform_device_id cpu_pmu_plat_device_ids[] = {
 static int probe_current_pmu(struct arm_pmu *pmu)
 {
 	int cpu = get_cpu();
-	unsigned long implementor = read_cpuid_implementor();
-	unsigned long part_number = read_cpuid_part_number();
 	int ret = -ENODEV;
 
 	pr_info("probing PMU on CPU %d\n", cpu);
 
+	switch (read_cpuid_part()) {
 	/* ARM Ltd CPUs. */
-	if (implementor == ARM_CPU_IMP_ARM) {
-		switch (part_number) {
-		case ARM_CPU_PART_ARM1136:
-		case ARM_CPU_PART_ARM1156:
-		case ARM_CPU_PART_ARM1176:
-			ret = armv6pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_ARM11MPCORE:
-			ret = armv6mpcore_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A8:
-			ret = armv7_a8_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A9:
-			ret = armv7_a9_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A5:
-			ret = armv7_a5_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A15:
-			ret = armv7_a15_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A7:
-			ret = armv7_a7_pmu_init(pmu);
-			break;
-		}
-	/* Intel CPUs [xscale]. */
-	} else if (implementor == ARM_CPU_IMP_INTEL) {
-		switch (xscale_cpu_arch_version()) {
-		case ARM_CPU_XSCALE_ARCH_V1:
-			ret = xscale1pmu_init(pmu);
-			break;
-		case ARM_CPU_XSCALE_ARCH_V2:
-			ret = xscale2pmu_init(pmu);
-			break;
+	case ARM_CPU_PART_ARM1136:
+	case ARM_CPU_PART_ARM1156:
+	case ARM_CPU_PART_ARM1176:
+		ret = armv6pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_ARM11MPCORE:
+		ret = armv6mpcore_pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_CORTEX_A8:
+		ret = armv7_a8_pmu_init(pmu);
+		break;
+	case ARM_CPU_PART_CORTEX_A9:
+		ret = armv7_a9_pmu_init(pmu);
+		break;
+
+	default:
+		if (read_cpuid_implementor() == ARM_CPU_IMP_INTEL) {
+			switch (xscale_cpu_arch_version()) {
+			case ARM_CPU_XSCALE_ARCH_V1:
+				ret = xscale1pmu_init(pmu);
+				break;
+			case ARM_CPU_XSCALE_ARCH_V2:
+				ret = xscale2pmu_init(pmu);
+				break;
+			}
 		}
+		break;
 	}
 
+	/* assume PMU support all the CPUs in this case */
+	cpumask_setall(&pmu->valid_cpus);
+
 	put_cpu();
 	return ret;
 }
@@ -254,15 +280,10 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	const int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
 	struct arm_pmu *pmu;
-	int ret = -ENODEV;
-
-	if (cpu_pmu) {
-		pr_info("attempt to register multiple PMU devices!");
-		return -ENOSPC;
-	}
+	int ret = 0;
+	int cpu;
 
 	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
 	if (!pmu) {
@@ -271,8 +292,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 	}
 
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
-		init_fn = of_id->data;
-		ret = init_fn(pmu);
+		smp_call_func_t init_fn = (smp_call_func_t)of_id->data;
+		struct device_node *ncluster;
+		int cluster = -1;
+		cpumask_t sibling_mask;
+
+		ncluster = of_parse_phandle(node, "cluster", 0);
+		if (ncluster) {
+			int len;
+			const u32 *hwid;
+			hwid = of_get_property(ncluster, "reg", &len);
+			if (hwid && len == 4)
+				cluster = be32_to_cpup(hwid);
+		}
+		/* set sibling mask to all cpu mask if socket is not specified */
+		if (cluster == -1 ||
+			cluster_to_logical_mask(cluster, &sibling_mask))
+			cpumask_setall(&sibling_mask);
+
+		smp_call_function_any(&sibling_mask, init_fn, pmu, 1);
+
+		/* now set the valid_cpus after init */
+		cpumask_copy(&pmu->valid_cpus, &sibling_mask);
 	} else {
 		ret = probe_current_pmu(pmu);
 	}
@@ -282,10 +323,12 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	cpu_pmu = pmu;
-	cpu_pmu->plat_device = pdev;
-	cpu_pmu_init(cpu_pmu);
-	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
+	for_each_cpu_mask(cpu, pmu->valid_cpus)
+		per_cpu(cpu_pmu, cpu) = pmu;
+
+	pmu->plat_device = pdev;
+	cpu_pmu_init(pmu);
+	ret = armpmu_register(pmu, -1);
 
 	if (!ret)
 		return 0;
@@ -314,9 +357,17 @@ static int __init register_pmu_driver(void)
 	if (err)
 		return err;
 
+	err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier);
+	if (err) {
+		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+		return err;
+	}
+
 	err = platform_driver_register(&cpu_pmu_driver);
-	if (err)
+	if (err) {
+		cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier);
 		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+	}
 
 	return err;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 039cffb053a7..654db5030c31 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -950,6 +950,51 @@ static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu)
 }
 #endif
 
+static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu,
+					struct cpupmu_regs *regs)
+{
+	unsigned int cnt;
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc));
+	if (!(regs->pmc & ARMV7_PMNC_E))
+		return;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset));
+	asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren));
+	asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset));
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0]));
+	for (cnt = ARMV7_IDX_COUNTER0;
+			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mrc p15, 0, %0, c9, c13, 1"
+					: "=r"(regs->pmxevttype[cnt]));
+		asm volatile("mrc p15, 0, %0, c9, c13, 2"
+					: "=r"(regs->pmxevtcnt[cnt]));
+	}
+	return;
+}
+
+static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu,
+					struct cpupmu_regs *regs)
+{
+	unsigned int cnt;
+	if (!(regs->pmc & ARMV7_PMNC_E))
+		return;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset));
+	asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren));
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset));
+	asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0]));
+	for (cnt = ARMV7_IDX_COUNTER0;
+			cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mcr p15, 0, %0, c9, c13, 1"
+					: : "r"(regs->pmxevttype[cnt]));
+		asm volatile("mcr p15, 0, %0, c9, c13, 2"
+					: : "r"(regs->pmxevtcnt[cnt]));
+	}
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc));
+}
+
 static void armv7pmu_enable_event(struct perf_event *event)
 {
 	unsigned long flags;
@@ -1223,6 +1268,8 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start		= armv7pmu_start;
 	cpu_pmu->stop		= armv7pmu_stop;
 	cpu_pmu->reset		= armv7pmu_reset;
+	cpu_pmu->save_regs	= armv7pmu_save_regs;
+	cpu_pmu->restore_regs	= armv7pmu_restore_regs;
 	cpu_pmu->max_period	= (1LLU << 32) - 1;
 };
 
@@ -1240,7 +1287,7 @@ static u32 armv7_read_num_pmnc_events(void)
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A8";
+	cpu_pmu->name		= "ARMv7_Cortex_A8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1249,7 +1296,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A9";
+	cpu_pmu->name		= "ARMv7_Cortex_A9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1258,7 +1305,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A5";
+	cpu_pmu->name		= "ARMv7_Cortex_A5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1267,7 +1314,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A15";
+	cpu_pmu->name		= "ARMv7_Cortex_A15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1277,7 +1324,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A7";
+	cpu_pmu->name		= "ARMv7_Cortex_A7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 92f7b15dd221..5f6e650ec9ab 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -334,6 +334,8 @@ void flush_thread(void)
 	memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
 	memset(&thread->fpstate, 0, sizeof(union fp_state));
 
+	flush_tls();
+
 	thread_notify(THREAD_NOTIFY_FLUSH, thread);
 }
 
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index 46931880093d..e2c3fa8632e8 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -42,6 +42,7 @@ static u32 psci_function_id[PSCI_FN_MAX];
 #define PSCI_RET_EOPNOTSUPP		-1
 #define PSCI_RET_EINVAL			-2
 #define PSCI_RET_EPERM			-3
+#define PSCI_RET_EALREADYON		-4
 
 static int psci_to_linux_errno(int errno)
 {
@@ -54,6 +55,8 @@ static int psci_to_linux_errno(int errno)
 		return -EINVAL;
 	case PSCI_RET_EPERM:
 		return -EPERM;
+	case PSCI_RET_EALREADYON:
+		return -EAGAIN;
 	};
 
 	return -EINVAL;
@@ -153,7 +156,7 @@ static int psci_migrate(unsigned long cpuid)
 	return psci_to_linux_errno(err);
 }
 
-static const struct of_device_id psci_of_match[] __initconst = {
+static const struct of_device_id psci_of_match[] = {
 	{ .compatible = "arm,psci",	},
 	{},
 };
@@ -208,3 +211,16 @@ out_put_node:
 	of_node_put(np);
 	return;
 }
+
+int psci_probe(void)
+{
+	struct device_node *np;
+	int ret = -ENODEV;
+
+	np = of_find_matching_node(NULL, psci_of_match);
+	if (np)
+		ret = 0;
+
+	of_node_put(np);
+	return ret;
+}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 1e8b030dbefd..a4ef472c0d5e 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -273,6 +273,19 @@ static int cpu_has_aliasing_icache(unsigned int arch)
 	int aliasing_icache;
 	unsigned int id_reg, num_sets, line_size;
 
+#ifdef CONFIG_BIG_LITTLE
+	/*
+	 * We expect a combination of Cortex-A15 and Cortex-A7 cores.
+	 * A7 = VIPT aliasing I-cache
+	 * A15 = PIPT (non-aliasing) I-cache
+	 * To cater for this discrepancy, let's assume aliasing I-cache
+	 * all the time.  This means unneeded extra work on the A15 but
+	 * only ptrace is affected which is not performance critical.
+	 */
+	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0)
+		return 1;
+#endif
+
 	/* PIPT caches never alias. */
 	if (icache_is_pipt())
 		return 0;
@@ -1021,6 +1034,15 @@ static int c_show(struct seq_file *m, void *v)
 		seq_printf(m, "model name\t: %s rev %d (%s)\n",
 			   cpu_name, cpuid & 15, elf_platform);
 
+#if defined(CONFIG_SMP)
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ),
+			   (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100);
+#else
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000/HZ),
+			   (loops_per_jiffy / (5000/HZ)) % 100);
+#endif
 		/* dump out the processor features */
 		seq_puts(m, "Features\t: ");
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b7b4c86e338b..8cd3724714fe 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -388,8 +388,17 @@ asmlinkage void secondary_start_kernel(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	printk(KERN_INFO "SMP: Total of %d processors activated.\n",
-	       num_online_cpus());
+	int cpu;
+	unsigned long bogosum = 0;
+
+	for_each_online_cpu(cpu)
+		bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy;
+
+	printk(KERN_INFO "SMP: Total of %d processors activated "
+	       "(%lu.%02lu BogoMIPS).\n",
+	       num_online_cpus(),
+	       bogosum / (500000/HZ),
+	       (bogosum / (5000/HZ)) % 100);
 
 	hyp_mode_check();
 }
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index af4e8c8a5422..6582c4adc182 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -83,13 +83,16 @@ static int save_trace(struct stackframe *frame, void *d)
 	return trace->nr_entries >= trace->max_entries;
 }
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+/* This must be noinline to so that our skip calculation works correctly */
+static noinline void __save_stack_trace(struct task_struct *tsk,
+	struct stack_trace *trace, unsigned int nosched)
 {
 	struct stack_trace_data data;
 	struct stackframe frame;
 
 	data.trace = trace;
 	data.skip = trace->skip;
+	data.no_sched_functions = nosched;
 
 	if (tsk != current) {
 #ifdef CONFIG_SMP
@@ -102,7 +105,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 			trace->entries[trace->nr_entries++] = ULONG_MAX;
 		return;
 #else
-		data.no_sched_functions = 1;
 		frame.fp = thread_saved_fp(tsk);
 		frame.sp = thread_saved_sp(tsk);
 		frame.lr = 0;		/* recovered from the stack */
@@ -111,11 +113,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	} else {
 		register unsigned long current_sp asm ("sp");
 
-		data.no_sched_functions = 0;
+		/* We don't want this function nor the caller */
+		data.skip += 2;
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_sp;
 		frame.lr = (unsigned long)__builtin_return_address(0);
-		frame.pc = (unsigned long)save_stack_trace_tsk;
+		frame.pc = (unsigned long)__save_stack_trace;
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
@@ -123,9 +126,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	__save_stack_trace(tsk, trace, 1);
+}
+
 void save_stack_trace(struct stack_trace *trace)
 {
-	save_stack_trace_tsk(current, trace);
+	__save_stack_trace(current, trace, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c
index 7b8403b76666..80f0d69205e7 100644
--- a/arch/arm/kernel/thumbee.c
+++ b/arch/arm/kernel/thumbee.c
@@ -45,7 +45,7 @@ static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void
 
 	switch (cmd) {
 	case THREAD_NOTIFY_FLUSH:
-		thread->thumbee_state = 0;
+		teehbr_write(0);
 		break;
 	case THREAD_NOTIFY_SWITCH:
 		current_thread_info()->thumbee_state = teehbr_read();
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 0bc94b1fd1ae..d325410e02c8 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -267,6 +267,33 @@ void store_cpu_topology(unsigned int cpuid)
 }
 
 /*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id:		cluster HW identifier
+ * @cluster_mask:	the cpumask location to be initialized, modified by the
+ *			function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+	int cpu;
+
+	if (!cluster_mask)
+		return -EINVAL;
+
+	for_each_online_cpu(cpu)
+		if (socket_id == topology_physical_package_id(cpu)) {
+			cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+			return 0;
+		}
+
+	return -EINVAL;
+}
+
+/*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
  */
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 172ee18ff124..3f314433d653 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -510,8 +510,6 @@ static int bad_syscall(int n, struct pt_regs *regs)
 	return regs->ARM_r0;
 }
 
-static long do_cache_op_restart(struct restart_block *);
-
 static inline int
 __do_cache_op(unsigned long start, unsigned long end)
 {
@@ -520,24 +518,8 @@ __do_cache_op(unsigned long start, unsigned long end)
 	do {
 		unsigned long chunk = min(PAGE_SIZE, end - start);
 
-		if (signal_pending(current)) {
-			struct thread_info *ti = current_thread_info();
-
-			ti->restart_block = (struct restart_block) {
-				.fn	= do_cache_op_restart,
-			};
-
-			ti->arm_restart_block = (struct arm_restart_block) {
-				{
-					.cache = {
-						.start	= start,
-						.end	= end,
-					},
-				},
-			};
-
-			return -ERESTART_RESTARTBLOCK;
-		}
+		if (fatal_signal_pending(current))
+			return 0;
 
 		ret = flush_cache_user_range(start, start + chunk);
 		if (ret)
@@ -550,15 +532,6 @@ __do_cache_op(unsigned long start, unsigned long end)
 	return 0;
 }
 
-static long do_cache_op_restart(struct restart_block *unused)
-{
-	struct arm_restart_block *restart_block;
-
-	restart_block = &current_thread_info()->arm_restart_block;
-	return __do_cache_op(restart_block->cache.start,
-			     restart_block->cache.end);
-}
-
 static inline int
 do_cache_op(unsigned long start, unsigned long end, int flags)
 {
@@ -578,7 +551,6 @@ do_cache_op(unsigned long start, unsigned long end, int flags)
 #define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE)
 asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 {
-	struct thread_info *thread = current_thread_info();
 	siginfo_t info;
 
 	if ((no >> 16) != (__ARM_NR_BASE>> 16))
@@ -629,21 +601,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 		return regs->ARM_r0;
 
 	case NR(set_tls):
-		thread->tp_value[0] = regs->ARM_r0;
-		if (tls_emu)
-			return 0;
-		if (has_tls_reg) {
-			asm ("mcr p15, 0, %0, c13, c0, 3"
-				: : "r" (regs->ARM_r0));
-		} else {
-			/*
-			 * User space must never try to access this directly.
-			 * Expect your app to break eventually if you do so.
-			 * The user helper at 0xffff0fe0 must be used instead.
-			 * (see entry-armv.S for details)
-			 */
-			*((unsigned int *)0xffff0ff0) = regs->ARM_r0;
-		}
+		set_tls(regs->ARM_r0);
 		return 0;
 
 #ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 789bca9e64a7..f7057ed045b6 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -21,4 +21,5 @@ obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
 obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
 obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index bd18bb8b2770..f48c520c7dde 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -82,12 +82,12 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
 /**
  * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus.
  */
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void)
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
 {
 	return &kvm_arm_running_vcpu;
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
@@ -97,27 +97,16 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
 int kvm_arch_hardware_setup(void)
 {
 	return 0;
 }
 
-void kvm_arch_hardware_unsetup(void)
-{
-}
-
 void kvm_arch_check_processor_compat(void *rtn)
 {
 	*(int *)rtn = 0;
 }
 
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
 
 /**
  * kvm_arch_init_vm - initializes a VM data structure
@@ -155,16 +144,6 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
-			   struct kvm_memory_slot *dont)
-{
-}
-
-int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
-			    unsigned long npages)
-{
-	return 0;
-}
 
 /**
  * kvm_arch_destroy_vm - destroy the VM data structure
@@ -182,9 +161,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 			kvm->vcpus[i] = NULL;
 		}
 	}
+
+	kvm_vgic_destroy(kvm);
 }
 
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r;
 	switch (ext) {
@@ -197,6 +178,8 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ARM_PSCI:
+	case KVM_CAP_ARM_PSCI_0_2:
+	case KVM_CAP_READONLY_MEM:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -224,33 +207,6 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
-{
-}
-
-int kvm_arch_prepare_memory_region(struct kvm *kvm,
-				   struct kvm_memory_slot *memslot,
-				   struct kvm_userspace_memory_region *mem,
-				   enum kvm_mr_change change)
-{
-	return 0;
-}
-
-void kvm_arch_commit_memory_region(struct kvm *kvm,
-				   struct kvm_userspace_memory_region *mem,
-				   const struct kvm_memory_slot *old,
-				   enum kvm_mr_change change)
-{
-}
-
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
-				   struct kvm_memory_slot *slot)
-{
-}
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
@@ -289,6 +245,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
+	kvm_vgic_vcpu_destroy(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
@@ -304,26 +261,15 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	int ret;
-
 	/* Force users to call KVM_ARM_VCPU_INIT */
 	vcpu->arch.target = -1;
 
-	/* Set up VGIC */
-	ret = kvm_vgic_vcpu_init(vcpu);
-	if (ret)
-		return ret;
-
 	/* Set up the timer */
 	kvm_timer_vcpu_init(vcpu);
 
 	return 0;
 }
 
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	vcpu->cpu = cpu;
@@ -464,9 +410,9 @@ static void update_vttbr(struct kvm *kvm)
 
 	/* update vttbr to be used with the new vmid */
 	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
-	kvm->arch.vttbr = pgd_phys & VTTBR_BADDR_MASK;
-	kvm->arch.vttbr |= vmid;
+	kvm->arch.vttbr = pgd_phys | vmid;
 
 	spin_unlock(&kvm_vmid_lock);
 }
@@ -862,7 +808,8 @@ static int hyp_init_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_STARTING:
 	case CPU_STARTING_FROZEN:
-		cpu_init_hyp_mode(NULL);
+		if (__hyp_get_vectors() == hyp_default_vectors)
+			cpu_init_hyp_mode(NULL);
 		break;
 	}
 
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 78c0885d6501..7928dbdf2102 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -23,6 +23,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <trace/events/kvm.h>
@@ -43,6 +44,31 @@ static u32 cache_levels;
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
 #define CSSELR_MAX 12
 
+/*
+ * kvm_vcpu_arch.cp15 holds cp15 registers as an array of u32, but some
+ * of cp15 registers can be viewed either as couple of two u32 registers
+ * or one u64 register. Current u64 register encoding is that least
+ * significant u32 word is followed by most significant u32 word.
+ */
+static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu,
+				       const struct coproc_reg *r,
+				       u64 val)
+{
+	vcpu->arch.cp15[r->reg] = val & 0xffffffff;
+	vcpu->arch.cp15[r->reg + 1] = val >> 32;
+}
+
+static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu,
+				      const struct coproc_reg *r)
+{
+	u64 val;
+
+	val = vcpu->arch.cp15[r->reg + 1];
+	val = val << 32;
+	val = val | vcpu->arch.cp15[r->reg];
+	return val;
+}
+
 int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	kvm_inject_undefined(vcpu);
@@ -205,6 +231,44 @@ done:
 }
 
 /*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct coproc_params *p,
+			  const struct coproc_reg *r)
+{
+	BUG_ON(!p->is_write);
+
+	vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
+	if (p->is_64bit)
+		vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
+
+	return true;
+}
+
+/*
+ * SCTLR accessor. Only called as long as HCR_TVM is set.  If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ *
+ * Used by the cpu-specific code.
+ */
+bool access_sctlr(struct kvm_vcpu *vcpu,
+		  const struct coproc_params *p,
+		  const struct coproc_reg *r)
+{
+	access_vm_reg(vcpu, p, r);
+
+	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
+		vcpu->arch.hcr &= ~HCR_TVM;
+		stage2_flush_vm(vcpu->kvm);
+	}
+
+	return true;
+}
+
+/*
  * We could trap ID_DFR0 and tell the guest we don't support performance
  * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
  * NAKed, so it will read the PMCR anyway.
@@ -261,33 +325,36 @@ static const struct coproc_reg cp15_regs[] = {
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
 			NULL, reset_val, c1_CPACR, 0x00000000 },
 
-	/* TTBR0/TTBR1: swapped by interrupt.S. */
-	{ CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
-	{ CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
-
-	/* TTBCR: swapped by interrupt.S. */
+	/* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */
+	{ CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 },
+	{ CRn(2), CRm( 0), Op1( 0), Op2( 0), is32,
+			access_vm_reg, reset_unknown, c2_TTBR0 },
+	{ CRn(2), CRm( 0), Op1( 0), Op2( 1), is32,
+			access_vm_reg, reset_unknown, c2_TTBR1 },
 	{ CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
-			NULL, reset_val, c2_TTBCR, 0x00000000 },
+			access_vm_reg, reset_val, c2_TTBCR, 0x00000000 },
+	{ CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 },
+
 
 	/* DACR: swapped by interrupt.S. */
 	{ CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c3_DACR },
+			access_vm_reg, reset_unknown, c3_DACR },
 
 	/* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */
 	{ CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c5_DFSR },
+			access_vm_reg, reset_unknown, c5_DFSR },
 	{ CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c5_IFSR },
+			access_vm_reg, reset_unknown, c5_IFSR },
 	{ CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c5_ADFSR },
+			access_vm_reg, reset_unknown, c5_ADFSR },
 	{ CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c5_AIFSR },
+			access_vm_reg, reset_unknown, c5_AIFSR },
 
 	/* DFAR/IFAR: swapped by interrupt.S. */
 	{ CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c6_DFAR },
+			access_vm_reg, reset_unknown, c6_DFAR },
 	{ CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32,
-			NULL, reset_unknown, c6_IFAR },
+			access_vm_reg, reset_unknown, c6_IFAR },
 
 	/* PAR swapped by interrupt.S */
 	{ CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
@@ -324,9 +391,15 @@ static const struct coproc_reg cp15_regs[] = {
 
 	/* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */
 	{ CRn(10), CRm( 2), Op1( 0), Op2( 0), is32,
-			NULL, reset_unknown, c10_PRRR},
+			access_vm_reg, reset_unknown, c10_PRRR},
 	{ CRn(10), CRm( 2), Op1( 0), Op2( 1), is32,
-			NULL, reset_unknown, c10_NMRR},
+			access_vm_reg, reset_unknown, c10_NMRR},
+
+	/* AMAIR0/AMAIR1: swapped by interrupt.S. */
+	{ CRn(10), CRm( 3), Op1( 0), Op2( 0), is32,
+			access_vm_reg, reset_unknown, c10_AMAIR0},
+	{ CRn(10), CRm( 3), Op1( 0), Op2( 1), is32,
+			access_vm_reg, reset_unknown, c10_AMAIR1},
 
 	/* VBAR: swapped by interrupt.S. */
 	{ CRn(12), CRm( 0), Op1( 0), Op2( 0), is32,
@@ -334,7 +407,7 @@ static const struct coproc_reg cp15_regs[] = {
 
 	/* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 1), is32,
-			NULL, reset_val, c13_CID, 0x00000000 },
+			access_vm_reg, reset_val, c13_CID, 0x00000000 },
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 2), is32,
 			NULL, reset_unknown, c13_TID_URW },
 	{ CRn(13), CRm( 0), Op1( 0), Op2( 3), is32,
@@ -443,7 +516,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct coproc_params params;
 
-	params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
+	params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
 	params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf;
 	params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0);
 	params.is_64bit = true;
@@ -451,7 +524,7 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf;
 	params.Op2 = 0;
 	params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
-	params.CRn = 0;
+	params.CRm = 0;
 
 	return emulate_cp15(vcpu, &params);
 }
@@ -634,17 +707,23 @@ static struct coproc_reg invariant_cp15[] = {
 	{ CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR },
 };
 
+/*
+ * Reads a register value from a userspace address to a kernel
+ * variable. Make sure that register size matches sizeof(*__val).
+ */
 static int reg_from_user(void *val, const void __user *uaddr, u64 id)
 {
-	/* This Just Works because we are little endian. */
 	if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0)
 		return -EFAULT;
 	return 0;
 }
 
+/*
+ * Writes a register value to a userspace address from a kernel variable.
+ * Make sure that register size matches sizeof(*__val).
+ */
 static int reg_to_user(void __user *uaddr, const void *val, u64 id)
 {
-	/* This Just Works because we are little endian. */
 	if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0)
 		return -EFAULT;
 	return 0;
@@ -654,6 +733,7 @@ static int get_invariant_cp15(u64 id, void __user *uaddr)
 {
 	struct coproc_params params;
 	const struct coproc_reg *r;
+	int ret;
 
 	if (!index_to_params(id, &params))
 		return -ENOENT;
@@ -662,7 +742,15 @@ static int get_invariant_cp15(u64 id, void __user *uaddr)
 	if (!r)
 		return -ENOENT;
 
-	return reg_to_user(uaddr, &r->val, id);
+	ret = -ENOENT;
+	if (KVM_REG_SIZE(id) == 4) {
+		u32 val = r->val;
+
+		ret = reg_to_user(uaddr, &val, id);
+	} else if (KVM_REG_SIZE(id) == 8) {
+		ret = reg_to_user(uaddr, &r->val, id);
+	}
+	return ret;
 }
 
 static int set_invariant_cp15(u64 id, void __user *uaddr)
@@ -670,7 +758,7 @@ static int set_invariant_cp15(u64 id, void __user *uaddr)
 	struct coproc_params params;
 	const struct coproc_reg *r;
 	int err;
-	u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */
+	u64 val;
 
 	if (!index_to_params(id, &params))
 		return -ENOENT;
@@ -678,7 +766,16 @@ static int set_invariant_cp15(u64 id, void __user *uaddr)
 	if (!r)
 		return -ENOENT;
 
-	err = reg_from_user(&val, uaddr, id);
+	err = -ENOENT;
+	if (KVM_REG_SIZE(id) == 4) {
+		u32 val32;
+
+		err = reg_from_user(&val32, uaddr, id);
+		if (!err)
+			val = val32;
+	} else if (KVM_REG_SIZE(id) == 8) {
+		err = reg_from_user(&val, uaddr, id);
+	}
 	if (err)
 		return err;
 
@@ -694,7 +791,7 @@ static bool is_valid_cache(u32 val)
 	u32 level, ctype;
 
 	if (val >= CSSELR_MAX)
-		return -ENOENT;
+		return false;
 
 	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
         level = (val >> 1);
@@ -956,6 +1053,7 @@ int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	const struct coproc_reg *r;
 	void __user *uaddr = (void __user *)(long)reg->addr;
+	int ret;
 
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
 		return demux_c15_get(reg->id, uaddr);
@@ -967,14 +1065,24 @@ int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (!r)
 		return get_invariant_cp15(reg->id, uaddr);
 
-	/* Note: copies two regs if size is 64 bit. */
-	return reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+	ret = -ENOENT;
+	if (KVM_REG_SIZE(reg->id) == 8) {
+		u64 val;
+
+		val = vcpu_cp15_reg64_get(vcpu, r);
+		ret = reg_to_user(uaddr, &val, reg->id);
+	} else if (KVM_REG_SIZE(reg->id) == 4) {
+		ret = reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+	}
+
+	return ret;
 }
 
 int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	const struct coproc_reg *r;
 	void __user *uaddr = (void __user *)(long)reg->addr;
+	int ret;
 
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
 		return demux_c15_set(reg->id, uaddr);
@@ -986,8 +1094,18 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (!r)
 		return set_invariant_cp15(reg->id, uaddr);
 
-	/* Note: copies two regs if size is 64 bit */
-	return reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+	ret = -ENOENT;
+	if (KVM_REG_SIZE(reg->id) == 8) {
+		u64 val;
+
+		ret = reg_from_user(&val, uaddr, reg->id);
+		if (!ret)
+			vcpu_cp15_reg64_set(vcpu, r, val);
+	} else if (KVM_REG_SIZE(reg->id) == 4) {
+		ret = reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+	}
+
+	return ret;
 }
 
 static unsigned int num_demux_regs(void)
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index 0461d5c8d3de..1a44bbe39643 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -58,8 +58,8 @@ static inline void print_cp_instr(const struct coproc_params *p)
 {
 	/* Look, we even formatted it for you to paste into the table! */
 	if (p->is_64bit) {
-		kvm_pr_unimpl(" { CRm(%2lu), Op1(%2lu), is64, func_%s },\n",
-			      p->CRm, p->Op1, p->is_write ? "write" : "read");
+		kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n",
+			      p->CRn, p->Op1, p->is_write ? "write" : "read");
 	} else {
 		kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32,"
 			      " func_%s },\n",
@@ -135,13 +135,13 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 		return -1;
 	if (i1->CRn != i2->CRn)
 		return i1->CRn - i2->CRn;
-	if (i1->is_64 != i2->is_64)
-		return i2->is_64 - i1->is_64;
 	if (i1->CRm != i2->CRm)
 		return i1->CRm - i2->CRm;
 	if (i1->Op1 != i2->Op1)
 		return i1->Op1 - i2->Op1;
-	return i1->Op2 - i2->Op2;
+	if (i1->Op2 != i2->Op2)
+		return i1->Op2 - i2->Op2;
+	return i2->is_64 - i1->is_64;
 }
 
 
@@ -153,4 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 #define is64		.is_64 = true
 #define is32		.is_64 = false
 
+bool access_sctlr(struct kvm_vcpu *vcpu,
+		  const struct coproc_params *p,
+		  const struct coproc_reg *r);
+
 #endif /* __ARM_KVM_COPROC_LOCAL_H__ */
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index bb0cac1410cc..e6f4ae48bda9 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -34,7 +34,7 @@
 static const struct coproc_reg a15_regs[] = {
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_val, c1_SCTLR, 0x00C50078 },
+			access_sctlr, reset_val, c1_SCTLR, 0x00C50078 },
 };
 
 static struct kvm_coproc_target_table a15_target_table = {
diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c
index 1df767331588..17fc7cd479d3 100644
--- a/arch/arm/kvm/coproc_a7.c
+++ b/arch/arm/kvm/coproc_a7.c
@@ -37,7 +37,7 @@
 static const struct coproc_reg a7_regs[] = {
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
-			NULL, reset_val, c1_SCTLR, 0x00C50878 },
+			access_sctlr, reset_val, c1_SCTLR, 0x00C50878 },
 };
 
 static struct kvm_coproc_target_table a7_target_table = {
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 2786eae10c0d..cc0b78769bd8 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -38,6 +38,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.hcr = HCR_GUEST_MASK;
 	return 0;
 }
 
@@ -123,16 +124,6 @@ static bool is_timer_reg(u64 index)
 	return false;
 }
 
-int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
-{
-	return 0;
-}
-
-u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
-{
-	return 0;
-}
-
 #else
 
 #define NUM_TIMER_REGS 3
@@ -172,7 +163,7 @@ static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
 	if (ret != 0)
-		return ret;
+		return -EFAULT;
 
 	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
 }
@@ -273,13 +264,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 int __attribute_const__ kvm_target_cpu(void)
 {
-	unsigned long implementor = read_cpuid_implementor();
-	unsigned long part_number = read_cpuid_part_number();
-
-	if (implementor != ARM_CPU_IMP_ARM)
-		return -EINVAL;
-
-	switch (part_number) {
+	switch (read_cpuid_part()) {
 	case ARM_CPU_PART_CORTEX_A7:
 		return KVM_ARM_TARGET_CORTEX_A7;
 	case ARM_CPU_PART_CORTEX_A15:
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 0de91fc6de0f..a96a8043277c 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -38,14 +38,18 @@ static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
+	int ret;
+
 	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
 		      kvm_vcpu_hvc_get_imm(vcpu));
 
-	if (kvm_psci_call(vcpu))
+	ret = kvm_psci_call(vcpu);
+	if (ret < 0) {
+		kvm_inject_undefined(vcpu);
 		return 1;
+	}
 
-	kvm_inject_undefined(vcpu);
-	return 1;
+	return ret;
 }
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
@@ -89,6 +93,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	else
 		kvm_vcpu_block(vcpu);
 
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 1;
 }
 
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 1b9844d369cc..768e711c4c1e 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -71,7 +71,7 @@ __do_hyp_init:
 	bne	phase2			@ Yes, second stage init
 
 	@ Set the HTTBR to point to the hypervisor PGD pointer passed
-	mcrr	p15, 4, r2, r3, c2
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
 
 	@ Set the HTCR and VTCR to the same shareability and cacheability
 	@ settings as the non-secure TTBCR and with T0SZ == 0.
@@ -98,6 +98,10 @@ __do_hyp_init:
 	mrc	p15, 0, r0, c10, c2, 1
 	mcr	p15, 4, r0, c10, c2, 1
 
+	@ Invalidate the stale TLBs from Bootloader
+	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
+	dsb	ish
+
 	@ Set the HSCTLR to:
 	@  - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel)
 	@  - Endianness: Kernel config
@@ -137,7 +141,7 @@ phase2:
 	mov	pc, r0
 
 target:	@ We're now in the trampoline code, switch page tables
-	mcrr	p15, 4, r2, r3, c2
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
 	isb
 
 	@ Invalidate the old TLBs
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 0d68d4073068..01dcb0e752d9 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -52,7 +52,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	dsb	ishst
 	add	r0, r0, #KVM_VTTBR
 	ldrd	r2, r3, [r0]
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
 	isb
 	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
 	dsb	ish
@@ -135,7 +135,7 @@ ENTRY(__kvm_vcpu_run)
 	ldr	r1, [vcpu, #VCPU_KVM]
 	add	r1, r1, #KVM_VTTBR
 	ldrd	r2, r3, [r1]
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
 
 	@ We're all done, just restore the GPRs and go to the guest
 	restore_guest_regs
@@ -199,8 +199,13 @@ after_vfp_restore:
 
 	restore_host_regs
 	clrex				@ Clear exclusive monitor
+#ifndef CONFIG_CPU_ENDIAN_BE8
 	mov	r0, r1			@ Return the return code
 	mov	r1, #0			@ Clear upper bits in return value
+#else
+	@ r1 already has return code
+	mov	r0, #0			@ Clear upper bits in return value
+#endif /* CONFIG_CPU_ENDIAN_BE8 */
 	bx	lr			@ return to IOCTL
 
 /********************************************************************
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 6f18695a09cb..98c8c5b9a87f 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -1,4 +1,5 @@
 #include <linux/irqchip/arm-gic.h>
+#include <asm/assembler.h>
 
 #define VCPU_USR_REG(_reg_nr)	(VCPU_USR_REGS + (_reg_nr * 4))
 #define VCPU_USR_SP		(VCPU_USR_REG(13))
@@ -303,13 +304,17 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
 	mrrc	p15, 0, r4, r5, c7	@ PAR
+	mrc	p15, 0, r6, c10, c3, 0	@ AMAIR0
+	mrc	p15, 0, r7, c10, c3, 1	@ AMAIR1
 
 	.if \store_to_vcpu == 0
-	push	{r2,r4-r5}
+	push	{r2,r4-r7}
 	.else
 	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
 	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
 	strd	r4, r5, [r12]
+	str	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+	str	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
 	.endif
 .endm
 
@@ -322,15 +327,19 @@ vcpu	.req	r0		@ vcpu pointer always in r0
  */
 .macro write_cp15_state read_from_vcpu
 	.if \read_from_vcpu == 0
-	pop	{r2,r4-r5}
+	pop	{r2,r4-r7}
 	.else
 	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
 	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
 	ldrd	r4, r5, [r12]
+	ldr	r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+	ldr	r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
 	.endif
 
 	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
 	mcrr	p15, 0, r4, r5, c7	@ PAR
+	mcr	p15, 0, r6, c10, c3, 0	@ AMAIR0
+	mcr	p15, 0, r7, c10, c3, 1	@ AMAIR1
 
 	.if \read_from_vcpu == 0
 	pop	{r2-r12}
@@ -412,15 +421,23 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	ldr	r8, [r2, #GICH_ELRSR0]
 	ldr	r9, [r2, #GICH_ELRSR1]
 	ldr	r10, [r2, #GICH_APR]
-
-	str	r3, [r11, #VGIC_CPU_HCR]
-	str	r4, [r11, #VGIC_CPU_VMCR]
-	str	r5, [r11, #VGIC_CPU_MISR]
-	str	r6, [r11, #VGIC_CPU_EISR]
-	str	r7, [r11, #(VGIC_CPU_EISR + 4)]
-	str	r8, [r11, #VGIC_CPU_ELRSR]
-	str	r9, [r11, #(VGIC_CPU_ELRSR + 4)]
-	str	r10, [r11, #VGIC_CPU_APR]
+ARM_BE8(rev	r3, r3	)
+ARM_BE8(rev	r4, r4	)
+ARM_BE8(rev	r5, r5	)
+ARM_BE8(rev	r6, r6	)
+ARM_BE8(rev	r7, r7	)
+ARM_BE8(rev	r8, r8	)
+ARM_BE8(rev	r9, r9	)
+ARM_BE8(rev	r10, r10	)
+
+	str	r3, [r11, #VGIC_V2_CPU_HCR]
+	str	r4, [r11, #VGIC_V2_CPU_VMCR]
+	str	r5, [r11, #VGIC_V2_CPU_MISR]
+	str	r6, [r11, #VGIC_V2_CPU_EISR]
+	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
+	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
+	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+	str	r10, [r11, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
 	mov	r5, #0
@@ -428,9 +445,10 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	/* Save list registers */
 	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_CPU_LR
+	add	r3, r11, #VGIC_V2_CPU_LR
 	ldr	r4, [r11, #VGIC_CPU_NR_LR]
 1:	ldr	r6, [r2], #4
+ARM_BE8(rev	r6, r6	)
 	str	r6, [r3], #4
 	subs	r4, r4, #1
 	bne	1b
@@ -455,9 +473,12 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	add	r11, vcpu, #VCPU_VGIC_CPU
 
 	/* We only restore a minimal set of registers */
-	ldr	r3, [r11, #VGIC_CPU_HCR]
-	ldr	r4, [r11, #VGIC_CPU_VMCR]
-	ldr	r8, [r11, #VGIC_CPU_APR]
+	ldr	r3, [r11, #VGIC_V2_CPU_HCR]
+	ldr	r4, [r11, #VGIC_V2_CPU_VMCR]
+	ldr	r8, [r11, #VGIC_V2_CPU_APR]
+ARM_BE8(rev	r3, r3	)
+ARM_BE8(rev	r4, r4	)
+ARM_BE8(rev	r8, r8	)
 
 	str	r3, [r2, #GICH_HCR]
 	str	r4, [r2, #GICH_VMCR]
@@ -465,9 +486,10 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	/* Restore list registers */
 	add	r2, r2, #GICH_LR0
-	add	r3, r11, #VGIC_CPU_LR
+	add	r3, r11, #VGIC_V2_CPU_LR
 	ldr	r4, [r11, #VGIC_CPU_NR_LR]
 1:	ldr	r6, [r3], #4
+ARM_BE8(rev	r6, r6  )
 	str	r6, [r2], #4
 	subs	r4, r4, #1
 	bne	1b
@@ -498,7 +520,7 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
 	isb
 
-	mrrc	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
 	ldr	r4, =VCPU_TIMER_CNTV_CVAL
 	add	r5, vcpu, r4
 	strd	r2, r3, [r5]
@@ -538,12 +560,12 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 	ldr	r2, [r4, #KVM_TIMER_CNTVOFF]
 	ldr	r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
-	mcrr	p15, 4, r2, r3, c14	@ CNTVOFF
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c14	@ CNTVOFF
 
 	ldr	r4, =VCPU_TIMER_CNTV_CVAL
 	add	r5, vcpu, r4
 	ldrd	r2, r3, [r5]
-	mcrr	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	mcrr	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
 	isb
 
 	ldr	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
@@ -597,17 +619,14 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 
 /* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
 .macro configure_hyp_role operation
-	mrc	p15, 4, r2, c1, c1, 0	@ HCR
-	bic	r2, r2, #HCR_VIRT_EXCP_MASK
-	ldr	r3, =HCR_GUEST_MASK
 	.if \operation == vmentry
-	orr	r2, r2, r3
+	ldr	r2, [vcpu, #VCPU_HCR]
 	ldr	r3, [vcpu, #VCPU_IRQ_LINES]
 	orr	r2, r2, r3
 	.else
-	bic	r2, r2, r3
+	mov	r2, #0
 	.endif
-	mcr	p15, 4, r2, c1, c1, 0
+	mcr	p15, 4, r2, c1, c1, 0	@ HCR
 .endm
 
 .macro load_vcpu
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 7789857d1470..eea03069161b 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -42,6 +42,8 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
+#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+
 #define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
@@ -88,103 +90,208 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static bool page_empty(void *ptr)
+static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
 {
-	struct page *ptr_page = virt_to_page(ptr);
-	return page_count(ptr_page) == 1;
+	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
+	pgd_clear(pgd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pud_free(NULL, pud_table);
+	put_page(virt_to_page(pgd));
 }
 
 static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
-	if (pud_huge(*pud)) {
-		pud_clear(pud);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	} else {
-		pmd_t *pmd_table = pmd_offset(pud, 0);
-		pud_clear(pud);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-		pmd_free(NULL, pmd_table);
-	}
+	pmd_t *pmd_table = pmd_offset(pud, 0);
+	VM_BUG_ON(pud_huge(*pud));
+	pud_clear(pud);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pmd_free(NULL, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
 static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
-	if (kvm_pmd_huge(*pmd)) {
-		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	} else {
-		pte_t *pte_table = pte_offset_kernel(pmd, 0);
-		pmd_clear(pmd);
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-		pte_free_kernel(NULL, pte_table);
-	}
+	pte_t *pte_table = pte_offset_kernel(pmd, 0);
+	VM_BUG_ON(kvm_pmd_huge(*pmd));
+	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
+	pte_free_kernel(NULL, pte_table);
 	put_page(virt_to_page(pmd));
 }
 
-static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
+static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
+		       phys_addr_t addr, phys_addr_t end)
 {
-	if (pte_present(*pte)) {
-		kvm_set_pte(pte, __pte(0));
-		put_page(virt_to_page(pte));
-		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	}
+	phys_addr_t start_addr = addr;
+	pte_t *pte, *start_pte;
+
+	start_pte = pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			kvm_set_pte(pte, __pte(0));
+			put_page(virt_to_page(pte));
+			kvm_tlb_flush_vmid_ipa(kvm, addr);
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	if (kvm_pte_table_empty(start_pte))
+		clear_pmd_entry(kvm, pmd, start_addr);
+}
+
+static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+		       phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next, start_addr = addr;
+	pmd_t *pmd, *start_pmd;
+
+	start_pmd = pmd = pmd_offset(pud, addr);
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (kvm_pmd_huge(*pmd)) {
+				pmd_clear(pmd);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				put_page(virt_to_page(pmd));
+			} else {
+				unmap_ptes(kvm, pmd, addr, next);
+			}
+		}
+	} while (pmd++, addr = next, addr != end);
+
+	if (kvm_pmd_table_empty(start_pmd))
+		clear_pud_entry(kvm, pud, start_addr);
+}
+
+static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
+		       phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next, start_addr = addr;
+	pud_t *pud, *start_pud;
+
+	start_pud = pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			if (pud_huge(*pud)) {
+				pud_clear(pud);
+				kvm_tlb_flush_vmid_ipa(kvm, addr);
+				put_page(virt_to_page(pud));
+			} else {
+				unmap_pmds(kvm, pud, addr, next);
+			}
+		}
+	} while (pud++, addr = next, addr != end);
+
+	if (kvm_pud_table_empty(start_pud))
+		clear_pgd_entry(kvm, pgd, start_addr);
 }
 
+
 static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
-			unsigned long long start, u64 size)
+			phys_addr_t start, u64 size)
 {
 	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	phys_addr_t addr = start, end = start + size;
+	phys_addr_t next;
+
+	pgd = pgdp + pgd_index(addr);
+	do {
+		next = kvm_pgd_addr_end(addr, end);
+		unmap_puds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+			      phys_addr_t addr, phys_addr_t end)
+{
 	pte_t *pte;
-	unsigned long long addr = start, end = start + size;
-	u64 next;
 
-	while (addr < end) {
-		pgd = pgdp + pgd_index(addr);
-		pud = pud_offset(pgd, addr);
-		if (pud_none(*pud)) {
-			addr = pud_addr_end(addr, end);
-			continue;
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+			kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
 		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
 
-		if (pud_huge(*pud)) {
-			/*
-			 * If we are dealing with a huge pud, just clear it and
-			 * move on.
-			 */
-			clear_pud_entry(kvm, pud, addr);
-			addr = pud_addr_end(addr, end);
-			continue;
-		}
+static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pmd_t *pmd;
+	phys_addr_t next;
 
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			addr = pmd_addr_end(addr, end);
-			continue;
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = kvm_pmd_addr_end(addr, end);
+		if (!pmd_none(*pmd)) {
+			if (kvm_pmd_huge(*pmd)) {
+				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+				kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
+			} else {
+				stage2_flush_ptes(kvm, pmd, addr, next);
+			}
 		}
+	} while (pmd++, addr = next, addr != end);
+}
 
-		if (!kvm_pmd_huge(*pmd)) {
-			pte = pte_offset_kernel(pmd, addr);
-			clear_pte_entry(kvm, pte, addr);
-			next = addr + PAGE_SIZE;
-		}
+static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
+			      phys_addr_t addr, phys_addr_t end)
+{
+	pud_t *pud;
+	phys_addr_t next;
 
-		/*
-		 * If the pmd entry is to be cleared, walk back up the ladder
-		 */
-		if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
-			clear_pmd_entry(kvm, pmd, addr);
-			next = pmd_addr_end(addr, end);
-			if (page_empty(pmd) && !page_empty(pud)) {
-				clear_pud_entry(kvm, pud, addr);
-				next = pud_addr_end(addr, end);
+	pud = pud_offset(pgd, addr);
+	do {
+		next = kvm_pud_addr_end(addr, end);
+		if (!pud_none(*pud)) {
+			if (pud_huge(*pud)) {
+				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+				kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
+			} else {
+				stage2_flush_pmds(kvm, pud, addr, next);
 			}
 		}
+	} while (pud++, addr = next, addr != end);
+}
 
-		addr = next;
-	}
+static void stage2_flush_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+	phys_addr_t next;
+	pgd_t *pgd;
+
+	pgd = kvm->arch.pgd + pgd_index(addr);
+	do {
+		next = kvm_pgd_addr_end(addr, end);
+		stage2_flush_puds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the stage 2 page tables and invalidate any cache lines
+ * backing memory already mapped to the VM.
+ */
+void stage2_flush_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_flush_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
 }
 
 /**
@@ -199,14 +306,14 @@ void free_boot_hyp_pgd(void)
 	if (boot_hyp_pgd) {
 		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		kfree(boot_hyp_pgd);
+		free_pages((unsigned long)boot_hyp_pgd, pgd_order);
 		boot_hyp_pgd = NULL;
 	}
 
 	if (hyp_pgd)
 		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
-	kfree(init_bounce_page);
+	free_page((unsigned long)init_bounce_page);
 	init_bounce_page = NULL;
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
@@ -236,7 +343,7 @@ void free_hyp_pgds(void)
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
 			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 
-		kfree(hyp_pgd);
+		free_pages((unsigned long)hyp_pgd, pgd_order);
 		hyp_pgd = NULL;
 	}
 
@@ -639,21 +746,29 @@ static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
 	return false;
 }
 
+static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
-			  struct kvm_memory_slot *memslot,
+			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  unsigned long fault_status)
 {
 	int ret;
 	bool write_fault, writable, hugetlb = false, force_pte = false;
 	unsigned long mmu_seq;
 	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
-	unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
 	pfn_t pfn;
+	pgprot_t mem_type = PAGE_S2;
 
-	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
+	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
@@ -702,6 +817,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (is_error_pfn(pfn))
 		return -EFAULT;
 
+	if (kvm_is_mmio_pfn(pfn))
+		mem_type = PAGE_S2_DEVICE;
+
 	spin_lock(&kvm->mmu_lock);
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
@@ -709,22 +827,23 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
 
 	if (hugetlb) {
-		pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2);
+		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
 		new_pmd = pmd_mkhuge(new_pmd);
 		if (writable) {
 			kvm_set_s2pmd_writable(&new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_icache_guest_page(kvm, hva & PMD_MASK, PMD_SIZE);
+		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
-		pte_t new_pte = pfn_pte(pfn, PAGE_S2);
+		pte_t new_pte = pfn_pte(pfn, mem_type);
 		if (writable) {
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_icache_guest_page(kvm, hva, PAGE_SIZE);
-		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
+		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
+		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
+				     mem_type == PAGE_S2_DEVICE);
 	}
 
 
@@ -751,7 +870,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	unsigned long fault_status;
 	phys_addr_t fault_ipa;
 	struct kvm_memory_slot *memslot;
-	bool is_iabt;
+	unsigned long hva;
+	bool is_iabt, write_fault, writable;
 	gfn_t gfn;
 	int ret, idx;
 
@@ -762,17 +882,22 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	fault_status = kvm_vcpu_trap_get_fault(vcpu);
+	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
 	if (fault_status != FSC_FAULT && fault_status != FSC_PERM) {
-		kvm_err("Unsupported fault status: EC=%#x DFCS=%#lx\n",
-			kvm_vcpu_trap_get_class(vcpu), fault_status);
+		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
+			kvm_vcpu_trap_get_class(vcpu),
+			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
+			(unsigned long)kvm_vcpu_get_hsr(vcpu));
 		return -EFAULT;
 	}
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	gfn = fault_ipa >> PAGE_SHIFT;
-	if (!kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+	write_fault = kvm_is_write_fault(vcpu);
+	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
 		if (is_iabt) {
 			/* Prefetch Abort on I/O address */
 			kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
@@ -780,13 +905,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			goto out_unlock;
 		}
 
-		if (fault_status != FSC_FAULT) {
-			kvm_err("Unsupported fault status on io memory: %#lx\n",
-				fault_status);
-			ret = -EFAULT;
-			goto out_unlock;
-		}
-
 		/*
 		 * The IPA is reported as [MAX:12], so we need to
 		 * complement it with the bottom 12 bits from the
@@ -798,9 +916,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		goto out_unlock;
 	}
 
-	memslot = gfn_to_memslot(vcpu->kvm, gfn);
-
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
 out_unlock:
@@ -930,7 +1046,7 @@ int kvm_mmu_init(void)
 		size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
 		phys_addr_t phys_base;
 
-		init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
 		if (!init_bounce_page) {
 			kvm_err("Couldn't allocate HYP init bounce page\n");
 			err = -ENOMEM;
@@ -956,8 +1072,9 @@ int kvm_mmu_init(void)
 			 (unsigned long)phys_base);
 	}
 
-	hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
-	boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+
 	if (!hyp_pgd || !boot_hyp_pgd) {
 		kvm_err("Hyp mode PGD not allocated\n");
 		err = -ENOMEM;
@@ -1003,3 +1120,49 @@ out:
 	free_hyp_pgds();
 	return err;
 }
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   enum kvm_mr_change change)
+{
+	gpa_t gpa = old->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = old->npages << PAGE_SHIFT;
+	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+		spin_lock(&kvm->mmu_lock);
+		unmap_stage2_range(kvm, gpa, size);
+		spin_unlock(&kvm->mmu_lock);
+	}
+}
+
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_userspace_memory_region *mem,
+				   enum kvm_mr_change change)
+{
+	return 0;
+}
+
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
+			   struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
+{
+	return 0;
+}
+
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+}
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 448f60e8d23c..09cf37737ee2 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -27,6 +27,36 @@
  * as described in ARM document number ARM DEN 0022A.
  */
 
+#define AFFINITY_MASK(level)	~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
+
+static unsigned long psci_affinity_mask(unsigned long affinity_level)
+{
+	if (affinity_level <= 3)
+		return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
+
+	return 0;
+}
+
+static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * NOTE: For simplicity, we make VCPU suspend emulation to be
+	 * same-as WFI (Wait-for-interrupt) emulation.
+	 *
+	 * This means for KVM the wakeup events are interrupts and
+	 * this is consistent with intended use of StateID as described
+	 * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
+	 *
+	 * Further, we also treat power-down request to be same as
+	 * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
+	 * specification (ARM DEN 0022A). This means all suspend states
+	 * for KVM will preserve the register state.
+	 */
+	kvm_vcpu_block(vcpu);
+
+	return PSCI_RET_SUCCESS;
+}
+
 static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pause = true;
@@ -38,6 +68,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	struct kvm_vcpu *vcpu = NULL, *tmp;
 	wait_queue_head_t *wq;
 	unsigned long cpu_id;
+	unsigned long context_id;
 	unsigned long mpidr;
 	phys_addr_t target_pc;
 	int i;
@@ -58,10 +89,17 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 * Make sure the caller requested a valid CPU and that the CPU is
 	 * turned off.
 	 */
-	if (!vcpu || !vcpu->arch.pause)
-		return KVM_PSCI_RET_INVAL;
+	if (!vcpu)
+		return PSCI_RET_INVALID_PARAMS;
+	if (!vcpu->arch.pause) {
+		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+			return PSCI_RET_ALREADY_ON;
+		else
+			return PSCI_RET_INVALID_PARAMS;
+	}
 
 	target_pc = *vcpu_reg(source_vcpu, 2);
+	context_id = *vcpu_reg(source_vcpu, 3);
 
 	kvm_reset_vcpu(vcpu);
 
@@ -76,26 +114,160 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 		kvm_vcpu_set_be(vcpu);
 
 	*vcpu_pc(vcpu) = target_pc;
+	/*
+	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
+	 * the general puspose registers are undefined upon CPU_ON.
+	 */
+	*vcpu_reg(vcpu, 0) = context_id;
 	vcpu->arch.pause = false;
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
 	wake_up_interruptible(wq);
 
-	return KVM_PSCI_RET_SUCCESS;
+	return PSCI_RET_SUCCESS;
 }
 
-/**
- * kvm_psci_call - handle PSCI call if r0 value is in range
- * @vcpu: Pointer to the VCPU struct
- *
- * Handle PSCI calls from guests through traps from HVC instructions.
- * The calling convention is similar to SMC calls to the secure world where
- * the function number is placed in r0 and this function returns true if the
- * function number specified in r0 is withing the PSCI range, and false
- * otherwise.
- */
-bool kvm_psci_call(struct kvm_vcpu *vcpu)
+static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
+{
+	int i;
+	unsigned long mpidr;
+	unsigned long target_affinity;
+	unsigned long target_affinity_mask;
+	unsigned long lowest_affinity_level;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu *tmp;
+
+	target_affinity = *vcpu_reg(vcpu, 1);
+	lowest_affinity_level = *vcpu_reg(vcpu, 2);
+
+	/* Determine target affinity mask */
+	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
+	if (!target_affinity_mask)
+		return PSCI_RET_INVALID_PARAMS;
+
+	/* Ignore other bits of target affinity */
+	target_affinity &= target_affinity_mask;
+
+	/*
+	 * If one or more VCPU matching target affinity are running
+	 * then ON else OFF
+	 */
+	kvm_for_each_vcpu(i, tmp, kvm) {
+		mpidr = kvm_vcpu_get_mpidr(tmp);
+		if (((mpidr & target_affinity_mask) == target_affinity) &&
+		    !tmp->arch.pause) {
+			return PSCI_0_2_AFFINITY_LEVEL_ON;
+		}
+	}
+
+	return PSCI_0_2_AFFINITY_LEVEL_OFF;
+}
+
+static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
+{
+	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
+	vcpu->run->system_event.type = type;
+	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
+static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN);
+}
+
+static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
+{
+	kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
+}
+
+int kvm_psci_version(struct kvm_vcpu *vcpu)
+{
+	if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+		return KVM_ARM_PSCI_0_2;
+
+	return KVM_ARM_PSCI_0_1;
+}
+
+static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
+{
+	int ret = 1;
+	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long val;
+
+	switch (psci_fn) {
+	case PSCI_0_2_FN_PSCI_VERSION:
+		/*
+		 * Bits[31:16] = Major Version = 0
+		 * Bits[15:0] = Minor Version = 2
+		 */
+		val = 2;
+		break;
+	case PSCI_0_2_FN_CPU_SUSPEND:
+	case PSCI_0_2_FN64_CPU_SUSPEND:
+		val = kvm_psci_vcpu_suspend(vcpu);
+		break;
+	case PSCI_0_2_FN_CPU_OFF:
+		kvm_psci_vcpu_off(vcpu);
+		val = PSCI_RET_SUCCESS;
+		break;
+	case PSCI_0_2_FN_CPU_ON:
+	case PSCI_0_2_FN64_CPU_ON:
+		val = kvm_psci_vcpu_on(vcpu);
+		break;
+	case PSCI_0_2_FN_AFFINITY_INFO:
+	case PSCI_0_2_FN64_AFFINITY_INFO:
+		val = kvm_psci_vcpu_affinity_info(vcpu);
+		break;
+	case PSCI_0_2_FN_MIGRATE:
+	case PSCI_0_2_FN64_MIGRATE:
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
+	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+		/*
+		 * Trusted OS is MP hence does not require migration
+	         * or
+		 * Trusted OS is not present
+		 */
+		val = PSCI_0_2_TOS_MP;
+		break;
+	case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
+	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
+	case PSCI_0_2_FN_SYSTEM_OFF:
+		kvm_psci_system_off(vcpu);
+		/*
+		 * We should'nt be going back to guest VCPU after
+		 * receiving SYSTEM_OFF request.
+		 *
+		 * If user space accidently/deliberately resumes
+		 * guest VCPU after SYSTEM_OFF request then guest
+		 * VCPU should see internal failure from PSCI return
+		 * value. To achieve this, we preload r0 (or x0) with
+		 * PSCI return value INTERNAL_FAILURE.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
+	case PSCI_0_2_FN_SYSTEM_RESET:
+		kvm_psci_system_reset(vcpu);
+		/*
+		 * Same reason as SYSTEM_OFF for preloading r0 (or x0)
+		 * with PSCI return value INTERNAL_FAILURE.
+		 */
+		val = PSCI_RET_INTERNAL_FAILURE;
+		ret = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*vcpu_reg(vcpu, 0) = val;
+	return ret;
+}
+
+static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
 	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
@@ -103,20 +275,45 @@ bool kvm_psci_call(struct kvm_vcpu *vcpu)
 	switch (psci_fn) {
 	case KVM_PSCI_FN_CPU_OFF:
 		kvm_psci_vcpu_off(vcpu);
-		val = KVM_PSCI_RET_SUCCESS;
+		val = PSCI_RET_SUCCESS;
 		break;
 	case KVM_PSCI_FN_CPU_ON:
 		val = kvm_psci_vcpu_on(vcpu);
 		break;
 	case KVM_PSCI_FN_CPU_SUSPEND:
 	case KVM_PSCI_FN_MIGRATE:
-		val = KVM_PSCI_RET_NI;
+		val = PSCI_RET_NOT_SUPPORTED;
 		break;
-
 	default:
-		return false;
+		return -EINVAL;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
-	return true;
+	return 1;
+}
+
+/**
+ * kvm_psci_call - handle PSCI call if r0 value is in range
+ * @vcpu: Pointer to the VCPU struct
+ *
+ * Handle PSCI calls from guests through traps from HVC instructions.
+ * The calling convention is similar to SMC calls to the secure world
+ * where the function number is placed in r0.
+ *
+ * This function returns: > 0 (success), 0 (success but exit to user
+ * space), and < 0 (errors)
+ *
+ * Errors:
+ * -EINVAL: Unrecognized PSCI function
+ */
+int kvm_psci_call(struct kvm_vcpu *vcpu)
+{
+	switch (kvm_psci_version(vcpu)) {
+	case KVM_ARM_PSCI_0_2:
+		return kvm_psci_0_2_call(vcpu);
+	case KVM_ARM_PSCI_0_1:
+		return kvm_psci_0_1_call(vcpu);
+	default:
+		return -EINVAL;
+	};
 }
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 805e3f8fb007..3bc8eb811a73 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -197,24 +197,24 @@
 
 12:	PLD(	pld	[r1, #124]		)
 13:		ldr4w	r1, r4, r5, r6, r7, abort=19f
-		mov	r3, lr, pull #\pull
+		mov	r3, lr, lspull #\pull
 		subs	r2, r2, #32
 		ldr4w	r1, r8, r9, ip, lr, abort=19f
-		orr	r3, r3, r4, push #\push
-		mov	r4, r4, pull #\pull
-		orr	r4, r4, r5, push #\push
-		mov	r5, r5, pull #\pull
-		orr	r5, r5, r6, push #\push
-		mov	r6, r6, pull #\pull
-		orr	r6, r6, r7, push #\push
-		mov	r7, r7, pull #\pull
-		orr	r7, r7, r8, push #\push
-		mov	r8, r8, pull #\pull
-		orr	r8, r8, r9, push #\push
-		mov	r9, r9, pull #\pull
-		orr	r9, r9, ip, push #\push
-		mov	ip, ip, pull #\pull
-		orr	ip, ip, lr, push #\push
+		orr	r3, r3, r4, lspush #\push
+		mov	r4, r4, lspull #\pull
+		orr	r4, r4, r5, lspush #\push
+		mov	r5, r5, lspull #\pull
+		orr	r5, r5, r6, lspush #\push
+		mov	r6, r6, lspull #\pull
+		orr	r6, r6, r7, lspush #\push
+		mov	r7, r7, lspull #\pull
+		orr	r7, r7, r8, lspush #\push
+		mov	r8, r8, lspull #\pull
+		orr	r8, r8, r9, lspush #\push
+		mov	r9, r9, lspull #\pull
+		orr	r9, r9, ip, lspush #\push
+		mov	ip, ip, lspull #\pull
+		orr	ip, ip, lr, lspush #\push
 		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
 		bge	12b
 	PLD(	cmn	r2, #96			)
@@ -225,10 +225,10 @@
 14:		ands	ip, r2, #28
 		beq	16f
 
-15:		mov	r3, lr, pull #\pull
+15:		mov	r3, lr, lspull #\pull
 		ldr1w	r1, lr, abort=21f
 		subs	ip, ip, #4
-		orr	r3, r3, lr, push #\push
+		orr	r3, r3, lr, lspush #\push
 		str1w	r0, r3, abort=21f
 		bgt	15b
 	CALGN(	cmp	r2, #0			)
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index d620a5f22a09..d6e742d24007 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -141,7 +141,7 @@ FN_ENTRY
 		tst	len, #2
 		mov	r5, r4, get_byte_0
 		beq	.Lexit
-		adcs	sum, sum, r4, push #16
+		adcs	sum, sum, r4, lspush #16
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_1
 		strb	r5, [dst], #1
@@ -171,23 +171,23 @@ FN_ENTRY
 		cmp	ip, #2
 		beq	.Lsrc2_aligned
 		bhi	.Lsrc3_aligned
-		mov	r4, r5, pull #8		@ C = 0
+		mov	r4, r5, lspull #8		@ C = 0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
-		mov	r7, r7, pull #8
-		orr	r7, r7, r8, push #24
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
+		mov	r7, r7, lspull #8
+		orr	r7, r7, r8, lspush #24
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #8
+		mov	r4, r8, lspull #8
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -196,50 +196,50 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #8
+		mov	r4, r6, lspull #8
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #24
+		orr	r4, r4, r5, lspush #24
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #8
+		mov	r4, r5, lspull #8
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
 		tst	len, #2
 		beq	.Lexit
-		adcs	sum, sum, r4, push #16
+		adcs	sum, sum, r4, lspush #16
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_1
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_2
 		b	.Lexit
 
-.Lsrc2_aligned:	mov	r4, r5, pull #16
+.Lsrc2_aligned:	mov	r4, r5, lspull #16
 		adds	sum, sum, #0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
-		mov	r7, r7, pull #16
-		orr	r7, r7, r8, push #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
+		mov	r7, r7, lspull #16
+		orr	r7, r7, r8, lspush #16
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #16
+		mov	r4, r8, lspull #16
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -248,20 +248,20 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #16
+		mov	r4, r6, lspull #16
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #16
+		orr	r4, r4, r5, lspush #16
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #16
+		mov	r4, r5, lspull #16
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
@@ -276,24 +276,24 @@ FN_ENTRY
 		load1b	r5
 		b	.Lexit
 
-.Lsrc3_aligned:	mov	r4, r5, pull #24
+.Lsrc3_aligned:	mov	r4, r5, lspull #24
 		adds	sum, sum, #0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
-		mov	r7, r7, pull #24
-		orr	r7, r7, r8, push #8
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
+		mov	r7, r7, lspull #24
+		orr	r7, r7, r8, lspush #8
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #24
+		mov	r4, r8, lspull #24
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -302,20 +302,20 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #24
+		mov	r4, r6, lspull #24
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #8
+		orr	r4, r4, r5, lspush #8
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #24
+		mov	r4, r5, lspull #24
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
@@ -326,7 +326,7 @@ FN_ENTRY
 		load1l	r4
 		mov	r5, r4, get_byte_0
 		strb	r5, [dst], #1
-		adcs	sum, sum, r4, push #24
+		adcs	sum, sum, r4, lspush #24
 		mov	r5, r4, get_byte_1
 		b	.Lexit
 FN_EXIT
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 5fb97e7f9f4b..7a7430950c79 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -47,25 +47,25 @@ ENTRY(__raw_readsl)
 		strb	ip, [r1], #1
 
 4:		subs	r2, r2, #1
-		mov	ip, r3, pull #24
+		mov	ip, r3, lspull #24
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #8
+		orrne	ip, ip, r3, lspush #8
 		strne	ip, [r1], #4
 		bne	4b
 		b	8f
 
 5:		subs	r2, r2, #1
-		mov	ip, r3, pull #16
+		mov	ip, r3, lspull #16
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #16
+		orrne	ip, ip, r3, lspush #16
 		strne	ip, [r1], #4
 		bne	5b
 		b	7f
 
 6:		subs	r2, r2, #1
-		mov	ip, r3, pull #8
+		mov	ip, r3, lspull #8
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #24
+		orrne	ip, ip, r3, lspush #24
 		strne	ip, [r1], #4
 		bne	6b
 
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index 8d3b7813725c..d0d104a0dd11 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -41,26 +41,26 @@ ENTRY(__raw_writesl)
 		blt	5f
 		bgt	6f
 
-4:		mov	ip, r3, pull #16
+4:		mov	ip, r3, lspull #16
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #16
+		orr	ip, ip, r3, lspush #16
 		str	ip, [r0]
 		bne	4b
 		mov	pc, lr
 
-5:		mov	ip, r3, pull #8
+5:		mov	ip, r3, lspull #8
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #24
+		orr	ip, ip, r3, lspush #24
 		str	ip, [r0]
 		bne	5b
 		mov	pc, lr
 
-6:		mov	ip, r3, pull #24
+6:		mov	ip, r3, lspull #24
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #8
+		orr	ip, ip, r3, lspush #8
 		str	ip, [r0]
 		bne	6b
 		mov	pc, lr
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 938fc14f962d..d1fc0c0c342c 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -147,24 +147,24 @@ ENTRY(memmove)
 
 12:	PLD(	pld	[r1, #-128]		)
 13:		ldmdb   r1!, {r7, r8, r9, ip}
-		mov     lr, r3, push #\push
+		mov     lr, r3, lspush #\push
 		subs    r2, r2, #32
 		ldmdb   r1!, {r3, r4, r5, r6}
-		orr     lr, lr, ip, pull #\pull
-		mov     ip, ip, push #\push
-		orr     ip, ip, r9, pull #\pull
-		mov     r9, r9, push #\push
-		orr     r9, r9, r8, pull #\pull
-		mov     r8, r8, push #\push
-		orr     r8, r8, r7, pull #\pull
-		mov     r7, r7, push #\push
-		orr     r7, r7, r6, pull #\pull
-		mov     r6, r6, push #\push
-		orr     r6, r6, r5, pull #\pull
-		mov     r5, r5, push #\push
-		orr     r5, r5, r4, pull #\pull
-		mov     r4, r4, push #\push
-		orr     r4, r4, r3, pull #\pull
+		orr     lr, lr, ip, lspull #\pull
+		mov     ip, ip, lspush #\push
+		orr     ip, ip, r9, lspull #\pull
+		mov     r9, r9, lspush #\push
+		orr     r9, r9, r8, lspull #\pull
+		mov     r8, r8, lspush #\push
+		orr     r8, r8, r7, lspull #\pull
+		mov     r7, r7, lspush #\push
+		orr     r7, r7, r6, lspull #\pull
+		mov     r6, r6, lspush #\push
+		orr     r6, r6, r5, lspull #\pull
+		mov     r5, r5, lspush #\push
+		orr     r5, r5, r4, lspull #\pull
+		mov     r4, r4, lspush #\push
+		orr     r4, r4, r3, lspull #\pull
 		stmdb   r0!, {r4 - r9, ip, lr}
 		bge	12b
 	PLD(	cmn	r2, #96			)
@@ -175,10 +175,10 @@ ENTRY(memmove)
 14:		ands	ip, r2, #28
 		beq	16f
 
-15:		mov     lr, r3, push #\push
+15:		mov     lr, r3, lspush #\push
 		ldr	r3, [r1, #-4]!
 		subs	ip, ip, #4
-		orr	lr, lr, r3, pull #\pull
+		orr	lr, lr, r3, lspull #\pull
 		str	lr, [r0, #-4]!
 		bgt	15b
 	CALGN(	cmp	r2, #0			)
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index 5c908b1cb8ed..e50520904b76 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -117,9 +117,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_1fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_1nowords
-		mov	r3, r7, pull #8
+		mov	r3, r7, lspull #8
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #24
+		orr	r3, r3, r7, lspush #24
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -131,30 +131,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_1rem8lp
 
-.Lc2u_1cpy8lp:	mov	r3, r7, pull #8
+.Lc2u_1cpy8lp:	mov	r3, r7, lspull #8
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #24
-		mov	r4, r4, pull #8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
+		orr	r3, r3, r4, lspush #24
+		mov	r4, r4, lspull #8
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_1cpy8lp
 
 .Lc2u_1rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #24
-		movne	r4, r4, pull #8
-		orrne	r4, r4, r7, push #24
+		orrne	r3, r3, r4, lspush #24
+		movne	r4, r4, lspull #8
+		orrne	r4, r4, r7, lspush #24
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #24
+		orrne	r3, r3, r7, lspush #24
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_1fupi
@@ -172,9 +172,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_2fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_2nowords
-		mov	r3, r7, pull #16
+		mov	r3, r7, lspull #16
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #16
+		orr	r3, r3, r7, lspush #16
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -186,30 +186,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_2rem8lp
 
-.Lc2u_2cpy8lp:	mov	r3, r7, pull #16
+.Lc2u_2cpy8lp:	mov	r3, r7, lspull #16
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #16
-		mov	r4, r4, pull #16
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
+		orr	r3, r3, r4, lspush #16
+		mov	r4, r4, lspull #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_2cpy8lp
 
 .Lc2u_2rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #16
-		movne	r4, r4, pull #16
-		orrne	r4, r4, r7, push #16
+		orrne	r3, r3, r4, lspush #16
+		movne	r4, r4, lspull #16
+		orrne	r4, r4, r7, lspush #16
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #16
+		orrne	r3, r3, r7, lspush #16
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_2fupi
@@ -227,9 +227,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_3fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_3nowords
-		mov	r3, r7, pull #24
+		mov	r3, r7, lspull #24
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #8
+		orr	r3, r3, r7, lspush #8
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -241,30 +241,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_3rem8lp
 
-.Lc2u_3cpy8lp:	mov	r3, r7, pull #24
+.Lc2u_3cpy8lp:	mov	r3, r7, lspull #24
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #8
-		mov	r4, r4, pull #24
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
+		orr	r3, r3, r4, lspush #8
+		mov	r4, r4, lspull #24
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_3cpy8lp
 
 .Lc2u_3rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #8
-		movne	r4, r4, pull #24
-		orrne	r4, r4, r7, push #8
+		orrne	r3, r3, r4, lspush #8
+		movne	r4, r4, lspull #24
+		orrne	r4, r4, r7, lspush #8
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #8
+		orrne	r3, r3, r7, lspush #8
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_3fupi
@@ -382,9 +382,9 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 .Lcfu_1fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_1nowords
-		mov	r3, r7, pull #8
+		mov	r3, r7, lspull #8
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #24
+		orr	r3, r3, r7, lspush #24
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -396,30 +396,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lcfu_1rem8lp
 
-.Lcfu_1cpy8lp:	mov	r3, r7, pull #8
+.Lcfu_1cpy8lp:	mov	r3, r7, lspull #8
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #24
-		mov	r4, r4, pull #8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
+		orr	r3, r3, r4, lspush #24
+		mov	r4, r4, lspull #8
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
 		stmia	r0!, {r3 - r6}
 		bpl	.Lcfu_1cpy8lp
 
 .Lcfu_1rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #24
-		movne	r4, r4, pull #8
-		orrne	r4, r4, r7, push #24
+		orrne	r3, r3, r4, lspush #24
+		movne	r4, r4, lspull #8
+		orrne	r4, r4, r7, lspush #24
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #24
+		orrne	r3, r3, r7, lspush #24
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_1fupi
@@ -437,9 +437,9 @@ USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
 .Lcfu_2fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_2nowords
-		mov	r3, r7, pull #16
+		mov	r3, r7, lspull #16
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #16
+		orr	r3, r3, r7, lspush #16
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -452,30 +452,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		blt	.Lcfu_2rem8lp
 
 
-.Lcfu_2cpy8lp:	mov	r3, r7, pull #16
+.Lcfu_2cpy8lp:	mov	r3, r7, lspull #16
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #16
-		mov	r4, r4, pull #16
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
+		orr	r3, r3, r4, lspush #16
+		mov	r4, r4, lspull #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
 		stmia	r0!, {r3 - r6}
 		bpl	.Lcfu_2cpy8lp
 
 .Lcfu_2rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #16
-		movne	r4, r4, pull #16
-		orrne	r4, r4, r7, push #16
+		orrne	r3, r3, r4, lspush #16
+		movne	r4, r4, lspull #16
+		orrne	r4, r4, r7, lspush #16
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #16
+		orrne	r3, r3, r7, lspush #16
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_2fupi
@@ -493,9 +493,9 @@ USER(	TUSER(	ldrgtb) r3, [r1], #0)			@ May fault
 .Lcfu_3fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_3nowords
-		mov	r3, r7, pull #24
+		mov	r3, r7, lspull #24
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #8
+		orr	r3, r3, r7, lspush #8
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -507,30 +507,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lcfu_3rem8lp
 
-.Lcfu_3cpy8lp:	mov	r3, r7, pull #24
+.Lcfu_3cpy8lp:	mov	r3, r7, lspull #24
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
-		orr	r3, r3, r4, push #8
-		mov	r4, r4, pull #24
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
+		orr	r3, r3, r4, lspush #8
+		mov	r4, r4, lspull #24
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
 		stmia	r0!, {r3 - r6}
 		subs	ip, ip, #16
 		bpl	.Lcfu_3cpy8lp
 
 .Lcfu_3rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #8
-		movne	r4, r4, pull #24
-		orrne	r4, r4, r7, push #8
+		orrne	r3, r3, r4, lspush #8
+		movne	r4, r4, lspull #24
+		orrne	r4, r4, r7, lspush #8
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #8
+		orrne	r3, r3, r7, lspush #8
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_3fupi
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index 034529d801b2..d66f102c352a 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -962,6 +962,7 @@ static int __init at91_clock_reset(void)
 	}
 
 	at91_pmc_write(AT91_PMC_SCDR, scdr);
+	at91_pmc_write(AT91_PMC_PCDR, pcdr);
 	if (cpu_is_sama5d3())
 		at91_pmc_write(AT91_PMC_PCDR1, pcdr1);
 
diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c
index 2ba694f9626b..f8bc3511a8c8 100644
--- a/arch/arm/mach-at91/sysirq_mask.c
+++ b/arch/arm/mach-at91/sysirq_mask.c
@@ -25,24 +25,28 @@
 
 #include "generic.h"
 
-#define AT91_RTC_IDR	0x24	/* Interrupt Disable Register */
-#define AT91_RTC_IMR	0x28	/* Interrupt Mask Register */
+#define AT91_RTC_IDR		0x24	/* Interrupt Disable Register */
+#define AT91_RTC_IMR		0x28	/* Interrupt Mask Register */
+#define AT91_RTC_IRQ_MASK	0x1f	/* Available IRQs mask */
 
 void __init at91_sysirq_mask_rtc(u32 rtc_base)
 {
 	void __iomem *base;
-	u32 mask;
 
 	base = ioremap(rtc_base, 64);
 	if (!base)
 		return;
 
-	mask = readl_relaxed(base + AT91_RTC_IMR);
-	if (mask) {
-		pr_info("AT91: Disabling rtc irq\n");
-		writel_relaxed(mask, base + AT91_RTC_IDR);
-		(void)readl_relaxed(base + AT91_RTC_IMR);	/* flush */
-	}
+	/*
+	 * sam9x5 SoCs have the following errata:
+	 * "RTC: Interrupt Mask Register cannot be used
+	 *  Interrupt Mask Register read always returns 0."
+	 *
+	 * Hence we're not relying on IMR values to disable
+	 * interrupts.
+	 */
+	writel_relaxed(AT91_RTC_IRQ_MASK, base + AT91_RTC_IDR);
+	(void)readl_relaxed(base + AT91_RTC_IMR);	/* flush */
 
 	iounmap(base);
 }
diff --git a/arch/arm/mach-exynos/common.c b/arch/arm/mach-exynos/common.c
index f18be40e5b21..1bf303f8dfe3 100644
--- a/arch/arm/mach-exynos/common.c
+++ b/arch/arm/mach-exynos/common.c
@@ -322,7 +322,7 @@ static int __init exynos_fdt_map_chipid(unsigned long node, const char *uname,
 {
 	struct map_desc iodesc;
 	__be32 *reg;
-	unsigned long len;
+	int len;
 
 	if (!of_flat_dt_is_compatible(node, "samsung,exynos4210-chipid") &&
 		!of_flat_dt_is_compatible(node, "samsung,exynos5440-clock"))
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index c7de89b263dd..f295cbb533bb 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -20,7 +20,7 @@
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
diff --git a/arch/arm/mach-imx/devices/platform-ipu-core.c b/arch/arm/mach-imx/devices/platform-ipu-core.c
index fc4dd7cedc11..6bd7c3f37ac0 100644
--- a/arch/arm/mach-imx/devices/platform-ipu-core.c
+++ b/arch/arm/mach-imx/devices/platform-ipu-core.c
@@ -77,7 +77,7 @@ struct platform_device *__init imx_alloc_mx3_camera(
 
 	pdev = platform_device_alloc("mx3-camera", 0);
 	if (!pdev)
-		goto err;
+		return ERR_PTR(-ENOMEM);
 
 	pdev->dev.dma_mask = kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL);
 	if (!pdev->dev.dma_mask)
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 4e9d58148ca7..c295c10f9217 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -125,6 +125,29 @@ int __init coherency_init(void)
 {
 	struct device_node *np;
 
+	/*
+	 * The coherency fabric is needed:
+	 * - For coherency between processors on Armada XP, so only
+	 *   when SMP is enabled.
+	 * - For coherency between the processor and I/O devices, but
+	 *   this coherency requires many pre-requisites (write
+	 *   allocate cache policy, shareable pages, SMP bit set) that
+	 *   are only meant in SMP situations.
+	 *
+	 * Note that this means that on Armada 370, there is currently
+	 * no way to use hardware I/O coherency, because even when
+	 * CONFIG_SMP is enabled, is_smp() returns false due to the
+	 * Armada 370 being a single-core processor. To lift this
+	 * limitation, we would have to find a way to make the cache
+	 * policy set to write-allocate (on all Armada SoCs), and to
+	 * set the shareable attribute in page tables (on all Armada
+	 * SoCs except the Armada 370). Unfortunately, such decisions
+	 * are taken very early in the kernel boot process, at a point
+	 * where we don't know yet on which SoC we are running.
+	 */
+	if (!is_smp())
+		return 0;
+
 	np = of_find_matching_node(NULL, of_coherency_table);
 	if (np) {
 		struct resource res;
@@ -151,6 +174,9 @@ static int __init coherency_late_init(void)
 {
 	struct device_node *np;
 
+	if (!is_smp())
+		return 0;
+
 	np = of_find_matching_node(NULL, of_coherency_table);
 	if (np) {
 		bus_register_notifier(&platform_bus_type,
diff --git a/arch/arm/mach-mvebu/mvebu-soc-id.c b/arch/arm/mach-mvebu/mvebu-soc-id.c
index f3b325f6cbd4..0e1547a186b0 100644
--- a/arch/arm/mach-mvebu/mvebu-soc-id.c
+++ b/arch/arm/mach-mvebu/mvebu-soc-id.c
@@ -107,7 +107,18 @@ static int __init mvebu_soc_id_init(void)
 	iounmap(pci_base);
 
 res_ioremap:
-	clk_disable_unprepare(clk);
+	/*
+	 * If the PCIe unit is actually enabled and we have PCI
+	 * support in the kernel, we intentionally do not release the
+	 * reference to the clock. We want to keep it running since
+	 * the bootloader does some PCIe link configuration that the
+	 * kernel is for now unable to do, and gating the clock would
+	 * make us loose this precious configuration.
+	 */
+	if (!of_device_is_available(child) || !IS_ENABLED(CONFIG_PCI_MVEBU)) {
+		clk_disable_unprepare(clk);
+		clk_put(clk);
+	}
 
 clk_err:
 	of_node_put(child);
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index fd90cafc2e36..db57072aeed3 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -343,7 +343,7 @@ static struct omap_usb_config h2_usb_config __initdata = {
 	/* usb1 has a Mini-AB port and external isp1301 transceiver */
 	.otg		= 2,
 
-#ifdef	CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.hmc_mode	= 19,	/* 0:host(off) 1:dev|otg 2:disabled */
 	/* .hmc_mode	= 21,*/	/* 0:host(off) 1:dev(loopback) 2:host(loopback) */
 #elif	defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 816ecd13f81e..bfed4f928663 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -366,7 +366,7 @@ static struct omap_usb_config h3_usb_config __initdata = {
 	/* usb1 has a Mini-AB port and external isp1301 transceiver */
 	.otg	    = 2,
 
-#ifdef CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.hmc_mode       = 19,   /* 0:host(off) 1:dev|otg 2:disabled */
 #elif  defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 	/* NONSTANDARD CABLE NEEDED (B-to-Mini-B) */
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index bd5f02e9c354..c49ce83cc1eb 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -312,7 +312,7 @@ static struct omap_usb_config h2_usb_config __initdata = {
 	/* usb1 has a Mini-AB port and external isp1301 transceiver */
 	.otg		= 2,
 
-#ifdef	CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.hmc_mode	= 19,	/* 0:host(off) 1:dev|otg 2:disabled */
 	/* .hmc_mode	= 21,*/	/* 0:host(off) 1:dev(loopback) 2:host(loopback) */
 #elif	defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index d68909b095f1..55b10877f4ff 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -280,7 +280,7 @@ static struct omap_usb_config osk_usb_config __initdata = {
 	 * be used, with a NONSTANDARD gender-bending cable/dongle, as
 	 * a peripheral.
 	 */
-#ifdef	CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
 	.register_dev	= 1,
 	.hmc_mode	= 0,
 #else
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 0af7ca02314d..6c0ab828b751 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -324,13 +324,21 @@ config MACH_TI8148EVM
 	depends on SOC_TI81XX
 	default y
 
-config OMAP3_EMU
-	bool "OMAP3 debugging peripherals"
-	depends on ARCH_OMAP3
-	select ARM_AMBA
-	select OC_ETM
-	help
-	  Say Y here to enable debugging hardware of omap3
+config MACH_OMAP_4430SDP
+	bool "OMAP 4430 SDP board"
+	default y
+	depends on ARCH_OMAP4
+	select OMAP_PACKAGE_CBL
+	select OMAP_PACKAGE_CBS
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+
+config MACH_OMAP4_PANDA
+	bool "OMAP4 Panda Board"
+	default y
+	depends on ARCH_OMAP4
+	select OMAP_PACKAGE_CBL
+	select OMAP_PACKAGE_CBS
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config OMAP3_SDRC_AC_TIMING
 	bool "Enable SDRC AC timing register changes"
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index e6eec6f72fd3..8abb3d806134 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -223,7 +223,6 @@ obj-$(CONFIG_SOC_OMAP5)			+= omap_hwmod_54xx_data.o
 obj-$(CONFIG_SOC_DRA7XX)		+= omap_hwmod_7xx_data.o
 
 # EMU peripherals
-obj-$(CONFIG_OMAP3_EMU)			+= emu.o
 obj-$(CONFIG_HW_PERF_EVENTS)		+= pmu.o
 
 iommu-$(CONFIG_OMAP_IOMMU)		:= omap-iommu.o
diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c
index ac82512b9c8c..b6885e42c0a0 100644
--- a/arch/arm/mach-omap2/board-flash.c
+++ b/arch/arm/mach-omap2/board-flash.c
@@ -142,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs,
 	board_nand_data.nr_parts	= nr_parts;
 	board_nand_data.devsize		= nand_type;
 
-	board_nand_data.ecc_opt = OMAP_ECC_BCH8_CODE_HW;
+	board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_HW;
 	gpmc_nand_init(&board_nand_data, gpmc_t);
 }
 #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 11ed9152e665..793039a9bd26 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -456,7 +456,8 @@ static struct clk_hw_omap dpll4_m5x2_ck_hw = {
 	.clkdm_name	= "dpll4_clkdm",
 };
 
-DEFINE_STRUCT_CLK(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names, dpll4_m5x2_ck_ops);
+DEFINE_STRUCT_CLK_FLAGS(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names,
+			dpll4_m5x2_ck_ops, CLK_SET_RATE_PARENT);
 
 static struct clk dpll4_m5x2_ck_3630 = {
 	.name		= "dpll4_m5x2_ck",
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index 44bb4d544dcf..89cde0786d25 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -314,7 +314,8 @@ void omap3_save_scratchpad_contents(void)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore_3630);
 	else if (omap_rev() != OMAP3430_REV_ES3_0 &&
-					omap_rev() != OMAP3430_REV_ES3_1)
+					omap_rev() != OMAP3430_REV_ES3_1 &&
+					omap_rev() != OMAP3430_REV_ES3_1_2)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore);
 	else
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 01fc710c8181..2498ab025fa2 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -14,6 +14,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
 #include <linux/export.h>
+#include <linux/clockchips.h>
 
 #include <asm/cpuidle.h>
 #include <asm/proc-fns.h>
@@ -83,6 +84,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 {
 	struct idle_statedata *cx = state_ptr + index;
 	u32 mpuss_can_lose_context = 0;
+	int cpu_id = smp_processor_id();
 
 	/*
 	 * CPU0 has to wait and stay ON until CPU1 is OFF state.
@@ -110,6 +112,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) &&
 				 (cx->mpu_logic_state == PWRDM_POWER_OFF);
 
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id);
+
 	/*
 	 * Call idle CPU PM enter notifier chain so that
 	 * VFP and per CPU interrupt context is saved.
@@ -165,6 +169,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	if (dev->cpu == 0 && mpuss_can_lose_context)
 		cpu_cluster_pm_exit();
 
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
+
 fail:
 	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
 	cpu_done[dev->cpu] = false;
@@ -172,6 +178,16 @@ fail:
 	return index;
 }
 
+/*
+ * For each cpu, setup the broadcast timer because local timers
+ * stops for the states above C1.
+ */
+static void omap_setup_broadcast_timer(void *arg)
+{
+	int cpu = smp_processor_id();
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu);
+}
+
 static struct cpuidle_driver omap4_idle_driver = {
 	.name				= "omap4_idle",
 	.owner				= THIS_MODULE,
@@ -189,8 +205,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
 			.exit_latency = 328 + 440,
 			.target_residency = 960,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
-			         CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C2",
 			.desc = "CPUx OFF, MPUSS CSWR",
@@ -199,8 +214,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
 			.exit_latency = 460 + 518,
 			.target_residency = 1100,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
-			         CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C3",
 			.desc = "CPUx OFF, MPUSS OSWR",
@@ -231,5 +245,8 @@ int __init omap4_idle_init(void)
 	if (!cpu_clkdm[0] || !cpu_clkdm[1])
 		return -ENODEV;
 
+	/* Configure the broadcast timer on each cpu */
+	on_each_cpu(omap_setup_broadcast_timer, NULL, 1);
+
 	return cpuidle_register(&omap4_idle_driver, cpu_online_mask);
 }
diff --git a/arch/arm/mach-omap2/emu.c b/arch/arm/mach-omap2/emu.c
deleted file mode 100644
index cbeaca2d7695..000000000000
--- a/arch/arm/mach-omap2/emu.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * emu.c
- *
- * ETM and ETB CoreSight components' resources as found in OMAP3xxx.
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/amba/bus.h>
-#include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-
-#include "soc.h"
-#include "iomap.h"
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alexander Shishkin");
-
-/* Cortex CoreSight components within omap3xxx EMU */
-#define ETM_BASE	(L4_EMU_34XX_PHYS + 0x10000)
-#define DBG_BASE	(L4_EMU_34XX_PHYS + 0x11000)
-#define ETB_BASE	(L4_EMU_34XX_PHYS + 0x1b000)
-#define DAPCTL		(L4_EMU_34XX_PHYS + 0x1d000)
-
-static AMBA_APB_DEVICE(omap3_etb, "etb", 0x000bb907, ETB_BASE, { }, NULL);
-static AMBA_APB_DEVICE(omap3_etm, "etm", 0x102bb921, ETM_BASE, { }, NULL);
-
-static int __init emu_init(void)
-{
-	if (!cpu_is_omap34xx())
-		return -ENODEV;
-
-	amba_device_register(&omap3_etb_device, &iomem_resource);
-	amba_device_register(&omap3_etm_device, &iomem_resource);
-
-	return 0;
-}
-
-omap_subsys_initcall(emu_init);
diff --git a/arch/arm/mach-omap2/irq.c b/arch/arm/mach-omap2/irq.c
index e022a869bff2..6037a9a01ed5 100644
--- a/arch/arm/mach-omap2/irq.c
+++ b/arch/arm/mach-omap2/irq.c
@@ -222,6 +222,7 @@ void __init ti81xx_init_irq(void)
 static inline void omap_intc_handle_irq(void __iomem *base_addr, struct pt_regs *regs)
 {
 	u32 irqnr;
+	int handled_irq = 0;
 
 	do {
 		irqnr = readl_relaxed(base_addr + 0x98);
@@ -249,8 +250,15 @@ out:
 		if (irqnr) {
 			irqnr = irq_find_mapping(domain, irqnr);
 			handle_IRQ(irqnr, regs);
+			handled_irq = 1;
 		}
 	} while (irqnr);
+
+	/* If an irq is masked or deasserted while active, we will
+	 * keep ending up here with no irq handled. So remove it from
+	 * the INTC with an ack.*/
+	if (!handled_irq)
+		omap_ack_irq(NULL);
 }
 
 asmlinkage void __exception_irq_entry omap2_intc_handle_irq(struct pt_regs *regs)
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index 48094b58c88f..b12a4f9fc9d0 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -183,8 +183,10 @@ static int __init _omap_mux_get_by_name(struct omap_mux_partition *partition,
 		m0_entry = mux->muxnames[0];
 
 		/* First check for full name in mode0.muxmode format */
-		if (mode0_len && strncmp(muxname, m0_entry, mode0_len))
-			continue;
+		if (mode0_len)
+			if (strncmp(muxname, m0_entry, mode0_len) ||
+			    (strlen(m0_entry) != mode0_len))
+				continue;
 
 		/* Then check for muxmode only */
 		for (i = 0; i < OMAP_MUX_NR_MODES; i++) {
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 1f33f5db10d5..4551efd28f8d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2185,6 +2185,8 @@ static int _enable(struct omap_hwmod *oh)
 			 oh->mux->pads_dynamic))) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_ENABLED);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	_add_initiator_dep(oh, mpu_oh);
@@ -2291,6 +2293,8 @@ static int _idle(struct omap_hwmod *oh)
 	if (oh->mux && oh->mux->pads_dynamic) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_IDLE);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	oh->_state = _HWMOD_STATE_IDLE;
@@ -2546,11 +2550,12 @@ static int __init _init(struct omap_hwmod *oh, void *data)
 		return -EINVAL;
 	}
 
-	if (np)
+	if (np) {
 		if (of_find_property(np, "ti,no-reset-on-init", NULL))
 			oh->flags |= HWMOD_INIT_NO_RESET;
 		if (of_find_property(np, "ti,no-idle-on-init", NULL))
 			oh->flags |= HWMOD_INIT_NO_IDLE;
+	}
 
 	oh->_state = _HWMOD_STATE_INITIALIZED;
 
@@ -3344,6 +3349,9 @@ int __init omap_hwmod_register_links(struct omap_hwmod_ocp_if **ois)
 	if (!ois)
 		return 0;
 
+	if (ois[0] == NULL) /* Empty list */
+		return 0;
+
 	if (!linkspace) {
 		if (_alloc_linkspace(ois)) {
 			pr_err("omap_hwmod: could not allocate link space\n");
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 4c3b1e6df508..ea4643abbe61 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1968,7 +1968,7 @@ static struct omap_hwmod_irq_info omap3xxx_usb_host_hs_irqs[] = {
 static struct omap_hwmod omap3xxx_usb_host_hs_hwmod = {
 	.name		= "usb_host_hs",
 	.class		= &omap3xxx_usb_host_hs_hwmod_class,
-	.clkdm_name	= "l3_init_clkdm",
+	.clkdm_name	= "usbhost_clkdm",
 	.mpu_irqs	= omap3xxx_usb_host_hs_irqs,
 	.main_clk	= "usbhost_48m_fck",
 	.prcm = {
@@ -2053,7 +2053,7 @@ static struct omap_hwmod_irq_info omap3xxx_usb_tll_hs_irqs[] = {
 static struct omap_hwmod omap3xxx_usb_tll_hs_hwmod = {
 	.name		= "usb_tll_hs",
 	.class		= &omap3xxx_usb_tll_hs_hwmod_class,
-	.clkdm_name	= "l3_init_clkdm",
+	.clkdm_name	= "core_l4_clkdm",
 	.mpu_irqs	= omap3xxx_usb_tll_hs_irqs,
 	.main_clk	= "usbtll_fck",
 	.prcm = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index e297d6231c3a..7babf515465c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -895,7 +895,7 @@ static struct omap_hwmod omap54xx_mcpdm_hwmod = {
 	 * current exception.
 	 */
 
-	.flags		= HWMOD_EXT_OPT_MAIN_CLK,
+	.flags		= HWMOD_EXT_OPT_MAIN_CLK | HWMOD_SWSUP_SIDLE,
 	.main_clk	= "pad_clks_ck",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 810c205d668b..2e35ff99f60e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -35,6 +35,7 @@
 #include "i2c.h"
 #include "mmc.h"
 #include "wd_timer.h"
+#include "soc.h"
 
 /* Base offset for all DRA7XX interrupts external to MPUSS */
 #define DRA7XX_IRQ_GIC_START	32
@@ -2707,7 +2708,6 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
 	&dra7xx_l4_per3__usb_otg_ss1,
 	&dra7xx_l4_per3__usb_otg_ss2,
 	&dra7xx_l4_per3__usb_otg_ss3,
-	&dra7xx_l4_per3__usb_otg_ss4,
 	&dra7xx_l3_main_1__vcp1,
 	&dra7xx_l4_per2__vcp1,
 	&dra7xx_l3_main_1__vcp2,
@@ -2716,8 +2716,26 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
 	NULL,
 };
 
+static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = {
+	&dra7xx_l4_per3__usb_otg_ss4,
+	NULL,
+};
+
+static struct omap_hwmod_ocp_if *dra72x_hwmod_ocp_ifs[] __initdata = {
+	NULL,
+};
+
 int __init dra7xx_hwmod_init(void)
 {
+	int ret;
+
 	omap_hwmod_init();
-	return omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
+	ret = omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
+
+	if (!ret && soc_is_dra74x())
+		return omap_hwmod_register_links(dra74x_hwmod_ocp_ifs);
+	else if (!ret && soc_is_dra72x())
+		return omap_hwmod_register_links(dra72x_hwmod_ocp_ifs);
+
+	return ret;
 }
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 7bdd22afce69..d4d0fce325c7 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -103,7 +103,7 @@ static inline void enable_omap3630_toggle_l2_on_restore(void) { }
 
 #define PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD	(1 << 0)
 
-#if defined(CONFIG_ARCH_OMAP4)
+#if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP4)
 extern u16 pm44xx_errata;
 #define IS_PM44XX_ERRATUM(id)		(pm44xx_errata & (id))
 #else
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index eefb30cfcabd..2b9cff960af2 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -148,26 +148,6 @@ static inline int omap4_init_static_deps(void)
 	struct clockdomain *ducati_clkdm, *l3_2_clkdm;
 	int ret = 0;
 
-	if (omap_rev() == OMAP4430_REV_ES1_0) {
-		WARN(1, "Power Management not supported on OMAP4430 ES1.0\n");
-		return -ENODEV;
-	}
-
-	pr_err("Power Management for TI OMAP4.\n");
-	/*
-	 * OMAP4 chip PM currently works only with certain (newer)
-	 * versions of bootloaders. This is due to missing code in the
-	 * kernel to properly reset and initialize some devices.
-	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
-	 */
-	pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
-
-	ret = pwrdm_for_each(pwrdms_setup, NULL);
-	if (ret) {
-		pr_err("Failed to setup powerdomains\n");
-		return ret;
-	}
-
 	/*
 	 * The dynamic dependency between MPUSS -> MEMIF and
 	 * MPUSS -> L4_PER/L3_* and DUCATI -> L3_* doesn't work as
@@ -231,6 +211,15 @@ int __init omap4_pm_init(void)
 
 	pr_info("Power Management for TI OMAP4+ devices.\n");
 
+	/*
+	 * OMAP4 chip PM currently works only with certain (newer)
+	 * versions of bootloaders. This is due to missing code in the
+	 * kernel to properly reset and initialize some devices.
+	 * http://www.spinics.net/lists/arm-kernel/msg218641.html
+	 */
+	if (cpu_is_omap44xx())
+		pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
+
 	ret = pwrdm_for_each(pwrdms_setup, NULL);
 	if (ret) {
 		pr_err("Failed to setup powerdomains.\n");
diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h
index 076bd90a6ce0..8a9be09d9f38 100644
--- a/arch/arm/mach-omap2/soc.h
+++ b/arch/arm/mach-omap2/soc.h
@@ -245,6 +245,8 @@ IS_AM_SUBCLASS(437x, 0x437)
 #define soc_is_omap54xx()		0
 #define soc_is_omap543x()		0
 #define soc_is_dra7xx()			0
+#define soc_is_dra74x()			0
+#define soc_is_dra72x()			0
 
 #if defined(MULTI_OMAP2)
 # if defined(CONFIG_ARCH_OMAP2)
@@ -393,7 +395,11 @@ IS_OMAP_TYPE(3430, 0x3430)
 
 #if defined(CONFIG_SOC_DRA7XX)
 #undef soc_is_dra7xx
+#undef soc_is_dra74x
+#undef soc_is_dra72x
 #define soc_is_dra7xx()	(of_machine_is_compatible("ti,dra7"))
+#define soc_is_dra74x()	(of_machine_is_compatible("ti,dra74"))
+#define soc_is_dra72x()	(of_machine_is_compatible("ti,dra72"))
 #endif
 
 /* Various silicon revisions for omap2 */
diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h
index f565f9944af2..7548db2bfb8a 100644
--- a/arch/arm/mach-orion5x/common.h
+++ b/arch/arm/mach-orion5x/common.h
@@ -21,7 +21,7 @@ struct mv_sata_platform_data;
 #define ORION_MBUS_DEVBUS_BOOT_ATTR   0x0f
 #define ORION_MBUS_DEVBUS_TARGET(cs)  0x01
 #define ORION_MBUS_DEVBUS_ATTR(cs)    (~(1 << cs))
-#define ORION_MBUS_SRAM_TARGET        0x00
+#define ORION_MBUS_SRAM_TARGET        0x09
 #define ORION_MBUS_SRAM_ATTR          0x00
 
 /*
diff --git a/arch/arm/mach-pxa/include/mach/hx4700.h b/arch/arm/mach-pxa/include/mach/hx4700.h
index 8bc02913517c..0e1bb46264f9 100644
--- a/arch/arm/mach-pxa/include/mach/hx4700.h
+++ b/arch/arm/mach-pxa/include/mach/hx4700.h
@@ -14,6 +14,7 @@
 
 #include <linux/gpio.h>
 #include <linux/mfd/asic3.h>
+#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */
 
 #define HX4700_ASIC3_GPIO_BASE	PXA_NR_BUILTIN_GPIO
 #define HX4700_EGPIO_BASE	(HX4700_ASIC3_GPIO_BASE + ASIC3_NUM_GPIOS)
diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
index 8c1ba4fea384..350579961e78 100644
--- a/arch/arm/mach-tegra/reset-handler.S
+++ b/arch/arm/mach-tegra/reset-handler.S
@@ -51,6 +51,7 @@ ENTRY(tegra_resume)
  THUMB(	it	ne )
 	bne	cpu_resume			@ no
 
+	tegra_get_soc_id TEGRA_APB_MISC_BASE, r6
 	/* Are we on Tegra20? */
 	cmp	r6, #TEGRA20
 	beq	1f				@ Yes
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 4a70be485ff8..556b01d305a8 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -55,6 +55,7 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 
 config ARCH_VEXPRESS_CA9X4
 	bool "Versatile Express Cortex-A9x4 tile"
+	select ARM_ERRATA_643719
 
 config ARCH_VEXPRESS_DCSCB
 	bool "Dual Cluster System Control Block (DCSCB) support"
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 0997e0b7494c..191f2b591adc 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -8,8 +8,15 @@ obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
 CFLAGS_dcscb.o				+= -march=armv7-a
+CFLAGS_REMOVE_dcscb.o			= -pg
 obj-$(CONFIG_ARCH_VEXPRESS_SPC)		+= spc.o
+CFLAGS_REMOVE_spc.o			= -pg
 obj-$(CONFIG_ARCH_VEXPRESS_TC2_PM)	+= tc2_pm.o
 CFLAGS_tc2_pm.o				+= -march=armv7-a
+CFLAGS_REMOVE_tc2_pm.o			= -pg
+ifeq ($(CONFIG_ARCH_VEXPRESS_TC2_PM),y)
+obj-$(CONFIG_ARM_PSCI)			+= tc2_pm_psci.o
+CFLAGS_REMOVE_tc2_pm_psci.o		= -pg
+endif
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
index 14d499688736..b35700f8e01f 100644
--- a/arch/arm/mach-vexpress/dcscb.c
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -23,6 +23,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <asm/cp15.h>
+#include <asm/psci.h>
 
 
 #define RST_HOLD0	0x0
@@ -193,6 +194,12 @@ static int __init dcscb_init(void)
 	unsigned int cfg;
 	int ret;
 
+	ret = psci_probe();
+	if (!ret) {
+		pr_debug("psci found. Aborting native init\n");
+		return -ENODEV;
+	}
+
 	if (!cci_probed())
 		return -ENODEV;
 
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index 993c9ae5dc5e..b4a5f0d8390d 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -53,7 +53,7 @@ static int __init vexpress_dt_find_scu(unsigned long node,
 {
 	if (of_flat_dt_match(node, vexpress_dt_cortex_a9_match)) {
 		phys_addr_t phys_addr;
-		__be32 *reg = of_get_flat_dt_prop(node, "reg", NULL);
+		const __be32 *reg = of_get_flat_dt_prop(node, "reg", NULL);
 
 		if (WARN_ON(!reg))
 			return -EINVAL;
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
index 29e7785a54bc..a32a179080d5 100644
--- a/arch/arm/mach-vexpress/tc2_pm.c
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -27,6 +27,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
 #include <asm/cp15.h>
+#include <asm/psci.h>
 
 #include <linux/arm-cci.h>
 
@@ -329,6 +330,12 @@ static int __init tc2_pm_init(void)
 	u32 a15_cluster_id, a7_cluster_id, sys_info;
 	struct device_node *np;
 
+	ret = psci_probe();
+	if (!ret) {
+		pr_debug("psci found. Aborting native init\n");
+		return -ENODEV;
+	}
+
 	/*
 	 * The power management-related features are hidden behind
 	 * SCC registers. We need to extract runtime information like
diff --git a/arch/arm/mach-vexpress/tc2_pm_psci.c b/arch/arm/mach-vexpress/tc2_pm_psci.c
new file mode 100644
index 000000000000..7cb2148caebc
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_psci.c
@@ -0,0 +1,173 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm_psci.c - TC2 PSCI support
+ *
+ * Created by: Achin Gupta, December 2012
+ * Copyright:  (C) 2012  ARM Limited
+ *
+ * Some portions of this file were originally written by Nicolas Pitre
+ * Copyright:   (C) 2012  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/psci.h>
+#include <asm/atomic.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+#include <mach/motherboard.h>
+
+#include <linux/vexpress.h>
+
+/*
+ * Platform specific state id understood by the firmware and used to
+ * program the power controller
+ */
+#define PSCI_POWER_STATE_ID           0
+
+#define TC2_CLUSTERS			2
+#define TC2_MAX_CPUS_PER_CLUSTER	3
+
+static atomic_t tc2_pm_use_count[TC2_MAX_CPUS_PER_CLUSTER][TC2_CLUSTERS];
+
+static int tc2_pm_psci_power_up(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int mpidr = (cluster << 8) | cpu;
+	int ret = 0;
+
+	BUG_ON(!psci_ops.cpu_on);
+
+	switch (atomic_inc_return(&tc2_pm_use_count[cpu][cluster])) {
+	case 1:
+		/*
+		 * This is a request to power up a cpu that linux thinks has
+		 * been powered down. Retries are needed if the firmware has
+		 * seen the power down request as yet.
+		 */
+		do
+			ret = psci_ops.cpu_on(mpidr,
+					      virt_to_phys(mcpm_entry_point));
+		while (ret == -EAGAIN);
+
+		return ret;
+	case 2:
+		/* This power up request has overtaken a power down request */
+		return ret;
+	default:
+		/* Any other value is a bug */
+		BUG();
+	}
+}
+
+static void tc2_pm_psci_power_down(void)
+{
+	struct psci_power_state power_state;
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	BUG_ON(!psci_ops.cpu_off);
+
+	switch (atomic_dec_return(&tc2_pm_use_count[cpu][cluster])) {
+	case 1:
+		/*
+		 * Overtaken by a power up. Flush caches, exit coherency,
+		 * return & fake a reset
+		 */
+		set_cr(get_cr() & ~CR_C);
+
+		flush_cache_louis();
+
+		asm volatile ("clrex");
+		set_auxcr(get_auxcr() & ~(1 << 6));
+
+		return;
+	case 0:
+		/* A normal request to possibly power down the cluster */
+		power_state.id = PSCI_POWER_STATE_ID;
+		power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+		power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+		psci_ops.cpu_off(power_state);
+
+		/* On success this function never returns */
+	default:
+		/* Any other value is a bug */
+		BUG();
+	}
+}
+
+static void tc2_pm_psci_suspend(u64 unused)
+{
+	struct psci_power_state power_state;
+
+	BUG_ON(!psci_ops.cpu_suspend);
+
+	/* On TC2 always attempt to power down the cluster */
+	power_state.id = PSCI_POWER_STATE_ID;
+	power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+	power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+	psci_ops.cpu_suspend(power_state, virt_to_phys(mcpm_entry_point));
+
+	/* On success this function never returns */
+	BUG();
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+	.power_up      = tc2_pm_psci_power_up,
+	.power_down    = tc2_pm_psci_power_down,
+	.suspend       = tc2_pm_psci_suspend,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);
+
+	atomic_set(&tc2_pm_use_count[cpu][cluster], 1);
+}
+
+static int __init tc2_pm_psci_init(void)
+{
+	int ret;
+
+	ret = psci_probe();
+	if (ret) {
+		pr_debug("psci not found. Aborting psci init\n");
+		return -ENODEV;
+	}
+
+	if (!of_machine_is_compatible("arm,vexpress,v2p-ca15_a7"))
+		return -ENODEV;
+
+	tc2_pm_usage_count_init();
+
+	ret = mcpm_platform_register(&tc2_pm_power_ops);
+	if (!ret)
+		ret = mcpm_sync_init(NULL);
+	if (!ret)
+		pr_info("TC2 power management using PSCI initialized\n");
+	return ret;
+}
+
+early_initcall(tc2_pm_psci_init);
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 4f8b8cb17ff5..ffa9b73b7d34 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -7,6 +7,7 @@
 #include <linux/io.h>
 #include <linux/smp.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
 #include <linux/of_address.h>
 #include <linux/of_fdt.h>
 #include <linux/of_irq.h>
@@ -369,6 +370,31 @@ MACHINE_START(VEXPRESS, "ARM-Versatile Express")
 	.init_machine	= v2m_init,
 MACHINE_END
 
+static void __init v2m_dt_hdlcd_init(void)
+{
+	struct device_node *node;
+	int len, na, ns;
+	const __be32 *prop;
+	phys_addr_t fb_base, fb_size;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,hdlcd");
+	if (!node)
+		return;
+
+	na = of_n_addr_cells(node);
+	ns = of_n_size_cells(node);
+
+	prop = of_get_property(node, "framebuffer", &len);
+	if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+		return;
+
+	fb_base = of_read_number(prop, na);
+	fb_size = of_read_number(prop + na, ns);
+
+	if (WARN_ON(memblock_remove(fb_base, fb_size)))
+		return;
+};
+
 static struct map_desc v2m_rs1_io_desc __initdata = {
 	.virtual	= V2M_PERIPH,
 	.pfn		= __phys_to_pfn(0x1c000000),
@@ -421,6 +447,8 @@ void __init v2m_dt_init_early(void)
 	}
 
 	versatile_sched_clock_init(vexpress_get_24mhz_clock_base(), 24000000);
+
+	v2m_dt_hdlcd_init();
 }
 
 static const struct of_device_id v2m_dt_bus_match[] __initconst = {
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 1f8fed94c2a4..e9c290c21744 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -446,7 +446,6 @@ config CPU_32v5
 
 config CPU_32v6
 	bool
-	select CPU_USE_DOMAINS if CPU_V6 && MMU
 	select TLS_REG_EMUL if !CPU_32v6K && !MMU
 
 config CPU_32v6K
@@ -671,7 +670,7 @@ config ARM_VIRT_EXT
 
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
-	depends on !CPU_USE_DOMAINS && CPU_V7
+	depends on CPU_V7
 	default y if SMP
 	select HAVE_PROC_CPU if PROC_FS
 	help
@@ -799,6 +798,7 @@ config NEED_KUSER_HELPERS
 
 config KUSER_HELPERS
 	bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS
+	depends on MMU
 	default y
 	help
 	  Warning: disabling this option may break user programs.
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 3815a8262af0..8c48c5c22a33 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -17,12 +17,6 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_V6
-	sub	r1, sp, #4			@ Get unused stack location
-	strex	r0, r1, [r1]			@ Clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
-	clrex
-#endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 703375277ba6..4812ad054214 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -13,12 +13,6 @@
  */
 	.align	5
 ENTRY(v7_early_abort)
-	/*
-	 * The effect of data aborts on on the exclusive access monitor are
-	 * UNPREDICTABLE. Do a CLREX to clear the state
-	 */
-	clrex
-
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 924036473b16..d301662b7b32 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -40,6 +40,7 @@
  * This code is not portable to processors with late data abort handling.
  */
 #define CODING_BITS(i)	(i & 0x0e000000)
+#define COND_BITS(i)	(i & 0xf0000000)
 
 #define LDST_I_BIT(i)	(i & (1 << 26))		/* Immediate constant	*/
 #define LDST_P_BIT(i)	(i & (1 << 24))		/* Preindex		*/
@@ -817,6 +818,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		break;
 
 	case 0x04000000:	/* ldr or str immediate */
+		if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */
+			goto bad;
 		offset.un = OFFSET_BITS(instr);
 		handler = do_alignment_ldrstr;
 		break;
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index eb8830a4c5ed..de5ee788d084 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -449,8 +449,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 
 	if (pud_none(*pud_k))
 		goto bad_area;
-	if (!pud_present(*pud))
+	if (!pud_present(*pud)) {
 		set_pud(pud, *pud_k);
+		/*
+		 * There is a small window during free_pgtables() where the
+		 * user *pud entry is 0 but the TLB has not been invalidated
+		 * and we get a level 2 (pmd) translation fault caused by the
+		 * intermediate TLB caching of the old level 1 (pud) entry.
+		 */
+		flush_tlb_kernel_page(addr);
+	}
 
 	pmd = pmd_offset(pud, addr);
 	pmd_k = pmd_offset(pud_k, addr);
@@ -473,8 +481,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 #endif
 	if (pmd_none(pmd_k[index]))
 		goto bad_area;
+	if (!pmd_present(pmd[index]))
+		copy_pmd(pmd, pmd_k);
 
-	copy_pmd(pmd, pmd_k);
 	return 0;
 
 bad_area:
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index 54ee6163c181..66781bf34077 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -56,8 +56,3 @@ int pmd_huge(pmd_t pmd)
 {
 	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
 }
-
-int pmd_huge_support(void)
-{
-	return 1;
-}
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 8e0e52eb76b5..d7a0ee898d24 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -25,6 +25,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 			pr_warning("Failed to allocate identity pmd.\n");
 			return;
 		}
+		/*
+		 * Copy the original PMD to ensure that the PMD entries for
+		 * the kernel image are preserved.
+		 */
+		if (!pud_none(*pud))
+			memcpy(pmd, pmd_offset(pud, 0),
+			       PTRS_PER_PMD * sizeof(pmd_t));
 		pud_populate(&init_mm, pud, pmd);
 		pmd += pmd_index(addr);
 	} else
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index a623cb3ad012..f15c22e8bcd5 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -516,6 +516,16 @@ static void __init build_mem_type_table(void)
 	s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2;
 
 	/*
+	 * We don't use domains on ARMv6 (since this causes problems with
+	 * v6/v7 kernels), so we must use a separate memory type for user
+	 * r/o, kernel r/w to map the vectors page.
+	 */
+#ifndef CONFIG_ARM_LPAE
+	if (cpu_arch == CPU_ARCH_ARMv6)
+		vecs_pgprot |= L_PTE_MT_VECTORS;
+#endif
+
+	/*
 	 * ARMv6 and above have extended page tables.
 	 */
 	if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
@@ -1426,8 +1436,8 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 		return;
 
 	/* remap kernel code and data */
-	map_start = init_mm.start_code;
-	map_end   = init_mm.brk;
+	map_start = init_mm.start_code & PMD_MASK;
+	map_end   = ALIGN(init_mm.brk, PMD_SIZE);
 
 	/* get a handle on things... */
 	pgd0 = pgd_offset_k(0);
@@ -1462,7 +1472,7 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 	}
 
 	/* remap pmds for kernel mapping */
-	phys = __pa(map_start) & PMD_MASK;
+	phys = __pa(map_start);
 	do {
 		*pmdk++ = __pmd(phys | pmdprot);
 		phys += PMD_SIZE;
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index e3c48a3fe063..ee1d80593958 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -112,13 +112,9 @@
  *  100x   1   0   1	r/o	no acc
  *  10x0   1   0   1	r/o	no acc
  *  1011   0   0   1	r/w	no acc
- *  110x   0   1   0	r/w	r/o
- *  11x0   0   1   0	r/w	r/o
- *  1111   0   1   1	r/w	r/w
- *
- * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
  *  110x   1   1   1	r/o	r/o
  *  11x0   1   1   1	r/o	r/o
+ *  1111   0   1   1	r/w	r/w
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -137,7 +133,7 @@
 	.long	PTE_EXT_TEX(2)					@ L_PTE_MT_DEV_NONSHARED
 	.long	0x00						@ unused
 	.long	0x00						@ unused
-	.long	0x00						@ unused
+	.long	PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX	@ L_PTE_MT_VECTORS
 	.endm
 
 	.macro	armv6_set_pte_ext pfx
@@ -158,24 +154,21 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
+
+	@ user read-only -> kernel read-only
+	bicne	r3, r3, #PTE_EXT_AP0
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
-	orr	r3, r3, r2
+	eor	r3, r3, r2
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
 	moveq	r3, #0
-#ifndef CONFIG_CPU_USE_DOMAINS
 	tstne	r1, #L_PTE_NONE
 	movne	r3, #0
-#endif
 
 	str	r3, [r0]
 	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index bdd3be4be77a..1f52915f2b28 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -90,21 +90,14 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
-	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_VALID
-#ifndef CONFIG_CPU_USE_DOMAINS
 	eorne	r1, r1, #L_PTE_NONE
 	tstne	r1, #L_PTE_NONE
-#endif
 	moveq	r3, #0
 
  ARM(	str	r3, [r0, #2048]! )
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 01a719e18bb0..22e3ad63500c 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -64,6 +64,14 @@ ENTRY(cpu_v7_switch_mm)
 	mov	pc, lr
 ENDPROC(cpu_v7_switch_mm)
 
+#ifdef __ARMEB__
+#define rl r3
+#define rh r2
+#else
+#define rl r2
+#define rh r3
+#endif
+
 /*
  * cpu_v7_set_pte_ext(ptep, pte)
  *
@@ -73,13 +81,13 @@ ENDPROC(cpu_v7_switch_mm)
  */
 ENTRY(cpu_v7_set_pte_ext)
 #ifdef CONFIG_MMU
-	tst	r2, #L_PTE_VALID
+	tst	rl, #L_PTE_VALID
 	beq	1f
-	tst	r3, #1 << (57 - 32)		@ L_PTE_NONE
-	bicne	r2, #L_PTE_VALID
+	tst	rh, #1 << (57 - 32)		@ L_PTE_NONE
+	bicne	rl, #L_PTE_VALID
 	bne	1f
-	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
-	orreq	r2, #L_PTE_RDONLY
+	tst	rh, #1 << (55 - 32)		@ L_PTE_DIRTY
+	orreq	rl, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
 	ALT_SMP(W(nop))
 	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 74f6033e76dd..fdedc31e0f40 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -211,7 +211,6 @@ __v7_pj4b_setup:
 /* Auxiliary Debug Modes Control 1 Register */
 #define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */
 #define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */
-#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */
 #define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */
 
 /* Auxiliary Debug Modes Control 2 Register */
@@ -234,7 +233,6 @@ __v7_pj4b_setup:
 	/* Auxiliary Debug Modes Control 1 Register */
 	mrc	p15, 1,	r0, c15, c1, 1
 	orr     r0, r0, #PJ4B_CLEAN_LINE
-	orr     r0, r0, #PJ4B_BCK_OFF_STREX
 	orr     r0, r0, #PJ4B_INTER_PARITY
 	bic	r0, r0, #PJ4B_STATIC_BP
 	mcr	p15, 1,	r0, c15, c1, 1
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index d19b1cfcad91..b34b95f45cb3 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -535,7 +535,7 @@ ENTRY(cpu_xscale_do_suspend)
 	mrc	p15, 0, r5, c15, c1, 0	@ CP access reg
 	mrc	p15, 0, r6, c13, c0, 0	@ PID
 	mrc	p15, 0, r7, c3, c0, 0	@ domain ID
-	mrc	p15, 0, r8, c1, c1, 0	@ auxiliary control reg
+	mrc	p15, 0, r8, c1, c0, 1	@ auxiliary control reg
 	mrc	p15, 0, r9, c1, c0, 0	@ control reg
 	bic	r4, r4, #2		@ clear frequency change bit
 	stmia	r0, {r4 - r9}		@ store cp regs
@@ -552,7 +552,7 @@ ENTRY(cpu_xscale_do_resume)
 	mcr	p15, 0, r6, c13, c0, 0	@ PID
 	mcr	p15, 0, r7, c3, c0, 0	@ domain ID
 	mcr	p15, 0, r1, c2, c0, 0	@ translation table base addr
-	mcr	p15, 0, r8, c1, c1, 0	@ auxiliary control reg
+	mcr	p15, 0, r8, c1, c0, 1	@ auxiliary control reg
 	mov	r0, r9			@ control register
 	b	cpu_resume_mmu
 ENDPROC(cpu_xscale_do_resume)
diff --git a/arch/arm/plat-samsung/s5p-dev-mfc.c b/arch/arm/plat-samsung/s5p-dev-mfc.c
index ad51f85fbd01..a29272818c36 100644
--- a/arch/arm/plat-samsung/s5p-dev-mfc.c
+++ b/arch/arm/plat-samsung/s5p-dev-mfc.c
@@ -125,8 +125,8 @@ device_initcall(s5p_mfc_memory_init);
 int __init s5p_fdt_find_mfc_mem(unsigned long node, const char *uname,
 				int depth, void *data)
 {
-	__be32 *prop;
-	unsigned long len;
+	const __be32 *prop;
+	int len;
 	struct s5p_mfc_dt_meminfo *mfc_mem = data;
 
 	if (!data)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index e44a33805d88..a1842b4da228 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2,13 +2,16 @@ config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_OPP
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
 	select ARM_GIC
+	select ARM_GIC_V3
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
@@ -16,6 +19,8 @@ config ARM64
 	select DCACHE_WORD_ACCESS
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -26,29 +31,40 @@ config ARM64
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_MEMBLOCK
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
+	select OF_RESERVED_MEM
 	select PERF_USE_VMALLOC
 	select POWER_RESET
 	select POWER_SUPPLY
 	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
+	select HAVE_CONTEXT_TRACKING
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -85,7 +101,7 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config ZONE_DMA32
+config ZONE_DMA
 	def_bool y
 
 config ARCH_DMA_ADDR_T_64BIT
@@ -106,6 +122,9 @@ config IOMMU_HELPER
 config KERNEL_MODE_NEON
 	def_bool y
 
+config FIX_EARLYCON_MEM
+	def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -164,6 +183,134 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on SMP
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on SMP
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+	bool "SMT scheduler support"
+	depends on ARM_CPU_TOPOLOGY
+	help
+	  Improves the CPU scheduler's decision making when dealing with
+	  MultiThreading at a cost of slightly increased overhead in some
+	  places. If unsure say N here.
+
+config DISABLE_CPU_SCHED_DOMAIN_BALANCE
+	bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
+	help
+	  Disables scheduler load-balancing at CPU sched domain level.
+
+config SCHED_HMP
+	bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+	depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+	help
+	  Experimental scheduler optimizations for heterogeneous platforms.
+	  Attempts to introspectively select task affinity to optimize power
+	  and performance. Basic support for multiple (>2) cpu types is in place,
+	  but it has only been tested with two types of cpus.
+	  There is currently no support for migration of task groups, hence
+	  !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+	  between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+
+config SCHED_HMP_PRIO_FILTER
+	bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+	depends on SCHED_HMP
+	help
+	  Enables task priority based HMP migration filter. Any task with
+	  a NICE value above the threshold will always be on low-power cpus
+	  with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+	int "NICE priority threshold"
+	default 5
+	depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+	string "HMP scheduler fast CPU mask"
+	depends on SCHED_HMP
+	help
+          Leave empty to use device tree information.
+	  Specify the cpuids of the fast CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+	string "HMP scheduler slow CPU mask"
+	depends on SCHED_HMP
+	help
+	  Leave empty to use device tree information.
+	  Specify the cpuids of the slow CPUs in the system as a list string,
+	  e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+	bool "Allows changing the load tracking scale through sysfs"
+	depends on SCHED_HMP
+	help
+	  When turned on, this option exports the thresholds and load average
+	  period value for the load tracking patches through sysfs.
+	  The values can be modified to change the rate of load accumulation
+	  and the thresholds used for HMP migration.
+	  The load_avg_period_ms is the time in ms to reach a load average of
+	  0.5 for an idle task of 0 load average ratio that start a busy loop.
+	  The up_threshold and down_threshold is the value to go to a faster
+	  CPU or to go back to a slower cpu.
+	  The {up,down}_threshold are devided by 1024 before being compared
+	  to the load average.
+	  For examples, with load_avg_period_ms = 128 and up_threshold = 512,
+	  a running task with a load of 0 will be migrated to a bigger CPU after
+	  128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+	  up_threshold is 0.5.
+	  This patch has the same behavior as changing the Y of the load
+	  average computation to
+	        (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+	  but it remove intermadiate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+	bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+	depends on HMP_VARIABLE_SCALE && CPU_FREQ
+	help
+	  Scales the current load contribution in line with the frequency
+	  of the CPU that the task was executed on.
+	  In this version, we use a simple linear scale derived from the
+	  maximum frequency reported by CPUFreq.
+	  Restricting tracked load to be scaled by the CPU's frequency
+	  represents the consumption of possible compute capacity
+	  (rather than consumption of actual instantaneous capacity as
+	  normal) and allows the HMP migration's simple threshold
+	  migration strategy to interact more predictably with CPUFreq's
+	  asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+	bool "Small task packing for HMP"
+	depends on SCHED_HMP
+	default n
+	help
+	  Allows the HMP Scheduler to pack small tasks into CPUs in the
+	  smallest HMP domain.
+	  Controlled by two sysfs files in sys/kernel/hmp.
+	  packing_enable: 1 to enable, 0 to disable packing. Default 1.
+	  packing_limit: runqueue load ratio where a RQ is considered
+	    to be full. Default is NICE_0_LOAD * 9/8.
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
@@ -332,5 +479,8 @@ source "arch/arm64/Kconfig.debug"
 source "security/Kconfig"
 
 source "crypto/Kconfig"
+if CRYPTO
+source "arch/arm64/crypto/Kconfig"
+endif
 
 source "lib/Kconfig"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 2fceb71ac3b7..8185a913c5ed 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -45,6 +45,7 @@ export	TEXT_OFFSET GZFLAGS
 core-y		+= arch/arm64/kernel/ arch/arm64/mm/
 core-$(CONFIG_KVM) += arch/arm64/kvm/
 core-$(CONFIG_XEN) += arch/arm64/xen/
+core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
 libs-y		:= arch/arm64/lib/ $(libs-y)
 libs-y		+= $(LIBGCC)
 
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index c52bdb051f66..3391691a85f1 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,5 +1,7 @@
-dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb \
+				fvp-base-gicv2-psci.dtb
 dtb-$(CONFIG_ARCH_XGENE) += apm-mustang.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb
 
 targets += dtbs
 targets += $(dtb-y)
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
index 1247ca1200b1..6541962f5d70 100644
--- a/arch/arm64/boot/dts/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -24,3 +24,7 @@
 		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
 	};
 };
+
+&serial0 {
+	status = "ok";
+};
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index d37d7369e260..03431d25123b 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -176,16 +176,174 @@
 				reg-names = "csr-reg";
 				clock-output-names = "eth8clk";
 			};
+
+			sataphy1clk: sataphy1clk@1f21c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f21c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy1clk";
+				status = "disabled";
+				csr-offset = <0x4>;
+				csr-mask = <0x00>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sataphy2clk: sataphy1clk@1f22c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f22c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy2clk";
+				status = "ok";
+				csr-offset = <0x4>;
+				csr-mask = <0x3a>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sataphy3clk: sataphy1clk@1f23c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f23c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sataphy3clk";
+				status = "ok";
+				csr-offset = <0x4>;
+				csr-mask = <0x3a>;
+				enable-offset = <0x0>;
+				enable-mask = <0x06>;
+			};
+
+			sata01clk: sata01clk@1f21c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f21c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sata01clk";
+				csr-offset = <0x4>;
+				csr-mask = <0x05>;
+				enable-offset = <0x0>;
+				enable-mask = <0x39>;
+			};
+
+			sata23clk: sata23clk@1f22c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f22c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sata23clk";
+				csr-offset = <0x4>;
+				csr-mask = <0x05>;
+				enable-offset = <0x0>;
+				enable-mask = <0x39>;
+			};
+
+			sata45clk: sata45clk@1f23c000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f23c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "sata45clk";
+				csr-offset = <0x4>;
+				csr-mask = <0x05>;
+				enable-offset = <0x0>;
+				enable-mask = <0x39>;
+			};
+
+			rtcclk: rtcclk@17000000 {
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x17000000 0x0 0x2000>;
+				reg-names = "csr-reg";
+				csr-offset = <0xc>;
+				csr-mask = <0x2>;
+				enable-offset = <0x10>;
+				enable-mask = <0x2>;
+				clock-output-names = "rtcclk";
+			};
 		};
 
 		serial0: serial@1c020000 {
+			status = "disabled";
 			device_type = "serial";
-			compatible = "ns16550";
+			compatible = "ns16550a";
 			reg = <0 0x1c020000 0x0 0x1000>;
 			reg-shift = <2>;
 			clock-frequency = <10000000>; /* Updated by bootloader */
 			interrupt-parent = <&gic>;
 			interrupts = <0x0 0x4c 0x4>;
 		};
+
+		serial1: serial@1c021000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c021000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4d 0x4>;
+		};
+
+		serial2: serial@1c022000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c022000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4e 0x4>;
+		};
+
+		serial3: serial@1c023000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c023000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4f 0x4>;
+		};
+
+		phy1: phy@1f21a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f21a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy1clk 0>;
+			status = "disabled";
+			apm,tx-boost-gain = <30 30 30 30 30 30>;
+			apm,tx-eye-tuning = <2 10 10 2 10 10>;
+		};
+
+		phy2: phy@1f22a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f22a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy2clk 0>;
+			status = "ok";
+			apm,tx-boost-gain = <30 30 30 30 30 30>;
+			apm,tx-eye-tuning = <1 10 10 2 10 10>;
+		};
+
+		phy3: phy@1f23a000 {
+			compatible = "apm,xgene-phy";
+			reg = <0x0 0x1f23a000 0x0 0x100>;
+			#phy-cells = <1>;
+			clocks = <&sataphy3clk 0>;
+			status = "ok";
+			apm,tx-boost-gain = <31 31 31 31 31 31>;
+			apm,tx-eye-tuning = <2 10 10 2 10 10>;
+		};
 	};
 };
diff --git a/arch/arm64/boot/dts/clcd-panels.dtsi b/arch/arm64/boot/dts/clcd-panels.dtsi
new file mode 100644
index 000000000000..0b0ff6ead4b2
--- /dev/null
+++ b/arch/arm64/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+	panels {
+		panel@0 {
+			compatible	= "panel";
+			mode		= "VGA";
+			refresh		= <60>;
+			xres		= <640>;
+			yres		= <480>;
+			pixclock	= <39721>;
+			left_margin	= <40>;
+			right_margin	= <24>;
+			upper_margin	= <32>;
+			lower_margin	= <11>;
+			hsync_len	= <96>;
+			vsync_len	= <2>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+
+		panel@1 {
+			compatible	= "panel";
+			mode		= "XVGA";
+			refresh		= <60>;
+			xres		= <1024>;
+			yres		= <768>;
+			pixclock	= <15748>;
+			left_margin	= <152>;
+			right_margin	= <48>;
+			upper_margin	= <23>;
+			lower_margin	= <3>;
+			hsync_len	= <104>;
+			vsync_len	= <4>;
+			sync		= <0>;
+			vmode		= "FB_VMODE_NONINTERLACED";
+
+			tim2		= "TIM2_BCD", "TIM2_IPC";
+			cntl		= "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+			caps		= "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+			bpp		= <16>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
new file mode 100644
index 000000000000..a46be6148b3a
--- /dev/null
+++ b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
@@ -0,0 +1,266 @@
+/*
+ * Copyright (c) 2013, ARM Limited. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * Redistributions of source code must retain the above copyright notice, this
+ * list of conditions and the following disclaimer.
+ *
+ * Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * Neither the name of ARM nor the names of its contributors may be used
+ * to endorse or promote products derived from this software without specific
+ * prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/memreserve/ 0x80000000 0x00010000;
+
+/ {
+};
+
+/ {
+	model = "FVP Base";
+	compatible = "arm,vfp-base", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen { };
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+	};
+
+	psci {
+		compatible = "arm,psci";
+		method = "smc";
+		cpu_suspend = <0xc4000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0xc4000003>;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		big0: cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		big1: cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		big2: cpu@2 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		big3: cpu@3 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57", "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little0: cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little1: cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little2: cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x102>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+		little3: cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0x0 0x103>;
+			enable-method = "psci";
+			clock-frequency = <1000000>;
+		};
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&big0>;
+				};
+				core1 {
+					cpu = <&big1>;
+				};
+				core2 {
+					cpu = <&big2>;
+				};
+				core3 {
+					cpu = <&big3>;
+				};
+			};
+			cluster1 {
+				core0 {
+					cpu = <&little0>;
+				};
+				core1 {
+					cpu = <&little1>;
+				};
+				core2 {
+					cpu = <&little2>;
+				};
+				core3 {
+					cpu = <&little3>;
+				};
+			};
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000 0 0x80000000>,
+		      <0x00000008 0x80000000 0 0x80000000>;
+	};
+
+	gic: interrupt-controller@2f000000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x0 0x2f000000 0 0x10000>,
+		      <0x0 0x2c000000 0 0x2000>,
+		      <0x0 0x2c010000 0 0x2000>,
+		      <0x0 0x2c02F000 0 0x2000>;
+		interrupts = <1 9 0xf04>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <1 13 0xff01>,
+			     <1 14 0xff01>,
+			     <1 11 0xff01>,
+			     <1 10 0xff01>;
+		clock-frequency = <100000000>;
+	};
+
+	timer@2a810000 {
+			compatible = "arm,armv7-timer-mem";
+			reg = <0x0 0x2a810000 0x0 0x10000>;
+			clock-frequency = <100000000>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			frame@2a820000 {
+				frame-number = <0>;
+				interrupts = <0 25 4>;
+				reg = <0x0 0x2a820000 0x0 0x10000>;
+			};
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <0 60 4>,
+			     <0 61 4>,
+			     <0 62 4>,
+			     <0 63 4>;
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic 0  0 4>,
+				<0 0  1 &gic 0  1 4>,
+				<0 0  2 &gic 0  2 4>,
+				<0 0  3 &gic 0  3 4>,
+				<0 0  4 &gic 0  4 4>,
+				<0 0  5 &gic 0  5 4>,
+				<0 0  6 &gic 0  6 4>,
+				<0 0  7 &gic 0  7 4>,
+				<0 0  8 &gic 0  8 4>,
+				<0 0  9 &gic 0  9 4>,
+				<0 0 10 &gic 0 10 4>,
+				<0 0 11 &gic 0 11 4>,
+				<0 0 12 &gic 0 12 4>,
+				<0 0 13 &gic 0 13 4>,
+				<0 0 14 &gic 0 14 4>,
+				<0 0 15 &gic 0 15 4>,
+				<0 0 16 &gic 0 16 4>,
+				<0 0 17 &gic 0 17 4>,
+				<0 0 18 &gic 0 18 4>,
+				<0 0 19 &gic 0 19 4>,
+				<0 0 20 &gic 0 20 4>,
+				<0 0 21 &gic 0 21 4>,
+				<0 0 22 &gic 0 22 4>,
+				<0 0 23 &gic 0 23 4>,
+				<0 0 24 &gic 0 24 4>,
+				<0 0 25 &gic 0 25 4>,
+				<0 0 26 &gic 0 26 4>,
+				<0 0 27 &gic 0 27 4>,
+				<0 0 28 &gic 0 28 4>,
+				<0 0 29 &gic 0 29 4>,
+				<0 0 30 &gic 0 30 4>,
+				<0 0 31 &gic 0 31 4>,
+				<0 0 32 &gic 0 32 4>,
+				<0 0 33 &gic 0 33 4>,
+				<0 0 34 &gic 0 34 4>,
+				<0 0 35 &gic 0 35 4>,
+				<0 0 36 &gic 0 36 4>,
+				<0 0 37 &gic 0 37 4>,
+				<0 0 38 &gic 0 38 4>,
+				<0 0 39 &gic 0 39 4>,
+				<0 0 40 &gic 0 40 4>,
+				<0 0 41 &gic 0 41 4>,
+				<0 0 42 &gic 0 42 4>;
+
+		/include/ "rtsm_ve-motherboard.dtsi"
+	};
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm64/boot/dts/juno.dts b/arch/arm64/boot/dts/juno.dts
new file mode 100644
index 000000000000..9785a14ca604
--- /dev/null
+++ b/arch/arm64/boot/dts/juno.dts
@@ -0,0 +1,498 @@
+/*
+ * ARM Ltd. Juno Plaform
+ *
+ * Fast Models FVP v2 support
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "Juno";
+	compatible = "arm,juno", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &soc_uart0;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@100 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x100>;
+			enable-method = "psci";
+		};
+
+		cpu@101 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x101>;
+			enable-method = "psci";
+		};
+
+		cpu@102 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x102>;
+			enable-method = "psci";
+		};
+
+		cpu@103 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53","arm,armv8";
+			reg = <0x0 0x103>;
+			enable-method = "psci";
+		};
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a57","arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x80000000 0x0 0x80000000>,
+		      <0x00000008 0x80000000 0x1 0x80000000>;
+	};
+
+	/* memory@14000000 {
+		device_type = "memory";
+		reg = <0x00000000 0x14000000 0x0 0x02000000>;
+	}; */
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0x0 0x2c010000 0 0x1000>,
+		      <0x0 0x2c02f000 0 0x1000>,
+		      <0x0 0x2c04f000 0 0x2000>,
+		      <0x0 0x2c06f000 0 0x2000>;
+		interrupts = <GIC_PPI 9 0xf04>;
+	};
+
+	msi0: msi@2c1c0000 {
+		compatible = "arm,gic-msi";
+		reg = <0x0 0x2c1c0000 0 0x10000
+		       0x0 0x2c1d0000 0 0x10000
+		       0x0 0x2c1e0000 0 0x10000
+		       0x0 0x2c1f0000 0 0x10000>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 0xff01>,
+			     <GIC_PPI 14 0xff01>,
+			     <GIC_PPI 11 0xff01>,
+			     <GIC_PPI 10 0xff01>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 60 4>,
+			     <GIC_SPI 61 4>,
+			     <GIC_SPI 62 4>,
+			     <GIC_SPI 63 4>;
+	};
+
+	psci {
+		compatible = "arm,psci";
+		method = "smc";
+		cpu_suspend = <0xC4000001>;
+		cpu_off = <0x84000002>;
+		cpu_on = <0xC4000003>;
+		migrate = <0xC4000005>;
+	};
+
+	pci0: pci@30000000 {
+		compatible = "arm,pcie-xr3";
+		device_type = "pci";
+		reg = <0 0x7ff30000 0 0x1000
+		       0 0x7ff20000 0 0x10000
+		       0 0x40000000 0 0x10000000>;
+		bus-range = <0 255>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		ranges = <0x01000000 0x0 0x00000000 0x00 0x5ff00000 0x0 0x00100000
+		          0x02000000 0x0 0x00000000 0x40 0x00000000 0x0 0x80000000
+			  0x42000000 0x0 0x80000000 0x40 0x80000000 0x0 0x80000000>;
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &gic 0 136 4
+			         0 0 0 2 &gic 0 137 4
+				 0 0 0 3 &gic 0 138 4
+				 0 0 0 4 &gic 0 139 4>;
+	};
+
+	scpi: scpi@2b1f0000 {
+		compatible = "arm,scpi-mhu";
+		reg = <0x0 0x2b1f0000 0x0 0x10000>,   /* MHU registers */
+		      <0x0 0x2e000000 0x0 0x10000>;   /* Payload area */
+		interrupts = <0 36 4>,   /* low priority interrupt */
+			     <0 35 4>,   /* high priority interrupt */
+			     <0 37 4>;   /* secure channel interrupt */
+		#clock-cells = <1>;
+		clock-output-names = "a57", "a53", "gpu", "hdlcd0", "hdlcd1";
+	};
+
+	hdlcd0_osc: scpi_osc@3 {
+		compatible = "arm,scpi-osc";
+		#clock-cells = <0>;
+		clocks = <&scpi 3>;
+		frequency-range = <23000000 210000000>;
+		clock-output-names = "pxlclk0";
+	};
+
+	hdlcd1_osc: scpi_osc@4 {
+		compatible = "arm,scpi-osc";
+		#clock-cells = <0>;
+		clocks = <&scpi 4>;
+		frequency-range = <23000000 210000000>;
+		clock-output-names = "pxlclk1";
+	};
+
+	soc_uartclk: refclk72738khz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <7273800>;
+		clock-output-names = "juno:uartclk";
+	};
+
+	soc_refclk24mhz: clk24mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <24000000>;
+		clock-output-names = "juno:clk24mhz";
+	};
+
+	mb_eth25mhz: clk25mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <25000000>;
+		clock-output-names = "ethclk25mhz";
+	};
+
+	soc_usb48mhz: clk48mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <48000000>;
+		clock-output-names = "clk48mhz";
+	};
+
+	soc_smc50mhz: clk50mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <50000000>;
+		clock-output-names = "smc_clk";
+	};
+
+	soc_refclk100mhz: refclk100mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <100000000>;
+		clock-output-names = "apb_pclk";
+	};
+
+	soc_faxiclk: refclk533mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <533000000>;
+		clock-output-names = "faxi_clk";
+	};
+
+	soc_fixed_3v3: fixedregulator@0 {
+		compatible = "regulator-fixed";
+		regulator-name = "3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		regulator-always-on;
+	};
+
+	memory-controller@7ffd0000 {
+		compatible = "arm,pl354", "arm,primecell";
+		reg = <0 0x7ffd0000 0 0x1000>;
+		interrupts = <0 86 4>,
+			     <0 87 4>;
+		clocks = <&soc_smc50mhz>;
+		clock-names = "apb_pclk";
+		chip5-memwidth = <16>;
+	};
+
+	dma0: dma@0x7ff00000 {
+		compatible = "arm,pl330", "arm,primecell";
+		reg = <0x0 0x7ff00000 0 0x1000>;
+		interrupts = <0 95 4>,
+			     <0 88 4>,
+			     <0 89 4>,
+			     <0 90 4>,
+			     <0 91 4>,
+			     <0 108 4>,
+			     <0 109 4>,
+			     <0 110 4>,
+			     <0 111 4>;
+		#dma-cells = <1>;
+		#dma-channels = <8>;
+		#dma-requests = <32>;
+		clocks = <&soc_faxiclk>;
+		clock-names = "apb_pclk";
+	};
+
+	soc_uart0: uart@7ff80000 {
+		compatible = "arm,pl011", "arm,primecell";
+		reg = <0x0 0x7ff80000 0x0 0x1000>;
+		interrupts = <0 83 4>;
+		clocks = <&soc_uartclk>, <&soc_refclk100mhz>;
+		clock-names = "uartclk", "apb_pclk";
+		dmas = <&dma0 1
+			&dma0 2>;
+		dma-names = "rx", "tx";
+	};
+
+	/* this UART is reserved for secure software.
+	soc_uart1: uart@7ff70000 {
+		compatible = "arm,pl011", "arm,primecell";
+		reg = <0x0 0x7ff70000 0x0 0x1000>;
+		interrupts = <0 84 4>;
+		clocks = <&soc_uartclk>, <&soc_refclk100mhz>;
+		clock-names = "uartclk", "apb_pclk";
+	}; */
+
+	ulpi_phy: phy@0 {
+		compatible = "phy-ulpi-generic";
+		reg = <0x0 0x94 0x0 0x4>;
+		phy-id = <0>;
+	};
+
+	ehci@7ffc0000 {
+		compatible = "snps,ehci-h20ahb";
+		/* compatible = "arm,h20ahb-ehci"; */
+		reg = <0x0 0x7ffc0000 0x0 0x10000>;
+		interrupts = <0 117 4>;
+		clocks = <&soc_usb48mhz>;
+		clock-names = "otg";
+		phys = <&ulpi_phy>;
+	};
+
+	ohci@0x7ffb0000 {
+		compatible = "generic-ohci";
+		reg = <0x0 0x7ffb0000 0x0 0x10000>;
+		interrupts = <0 116 4>;
+		clocks = <&soc_usb48mhz>;
+		clock-names = "otg";
+	};
+
+	i2c@0x7ffa0000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "snps,designware-i2c";
+		reg = <0x0 0x7ffa0000 0x0 0x1000>;
+		interrupts = <0 104 4>;
+		clock-frequency = <400000>;
+		i2c-sda-hold-time-ns = <500>;
+		clocks = <&soc_smc50mhz>;
+
+		dvi0: dvi-transmitter@70 {
+			compatible = "nxp,tda998x";
+			reg = <0x70>;
+		};
+
+		dvi1: dvi-transmitter@71 {
+			compatible = "nxp,tda998x";
+			reg = <0x71>;
+		};
+	};
+
+	/* mmci@1c050000 {
+		compatible = "arm,pl180", "arm,primecell";
+		reg = <0x0 0x1c050000 0x0 0x1000>;
+		interrupts = <0 73 4>,
+			     <0 74 4>;
+		max-frequency = <12000000>;
+		vmmc-supply = <&soc_fixed_3v3>;
+		clocks = <&soc_refclk24mhz>, <&soc_refclk100mhz>;
+		clock-names = "mclk", "apb_pclk";
+	}; */
+
+	hdlcd@7ff60000 {
+		compatible = "arm,hdlcd";
+		reg = <0 0x7ff60000 0 0x1000>;
+		interrupts = <0 85 4>;
+		clocks = <&hdlcd0_osc>;
+		clock-names = "pxlclk";
+		i2c-slave = <&dvi0>;
+
+		/* display-timings {
+			native-mode = <&timing0>;
+			timing0: timing@0 {
+				/* 1024 x 768 framebufer, standard VGA timings * /
+				clock-frequency = <65000>;
+				hactive = <1024>;
+				vactive = <768>;
+				hfront-porch = <24>;
+				hback-porch = <160>;
+				hsync-len = <136>;
+				vfront-porch = <3>;
+				vback-porch = <29>;
+				vsync-len = <6>;
+			};
+		}; */
+	};
+
+	hdlcd@7ff50000 {
+		compatible = "arm,hdlcd";
+		reg = <0 0x7ff50000 0 0x1000>;
+		interrupts = <0 93 4>;
+		clocks = <&hdlcd1_osc>;
+		clock-names = "pxlclk";
+		i2c-slave = <&dvi1>;
+
+		display-timings {
+			native-mode = <&timing1>;
+			timing1: timing@1 {
+				/* 1024 x 768 framebufer, standard VGA timings */
+				clock-frequency = <65000>;
+				hactive = <1024>;
+				vactive = <768>;
+				hfront-porch = <24>;
+				hback-porch = <160>;
+				hsync-len = <136>;
+				vfront-porch = <3>;
+				vback-porch = <29>;
+				vsync-len = <6>;
+			};
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 15>;
+		interrupt-map = <0 0  0 &gic 0  68 4>,
+				<0 0  1 &gic 0  69 4>,
+				<0 0  2 &gic 0  70 4>,
+				<0 0  3 &gic 0 160 4>,
+				<0 0  4 &gic 0 161 4>,
+				<0 0  5 &gic 0 162 4>,
+				<0 0  6 &gic 0 163 4>,
+				<0 0  7 &gic 0 164 4>,
+				<0 0  8 &gic 0 165 4>,
+				<0 0  9 &gic 0 166 4>,
+				<0 0 10 &gic 0 167 4>,
+				<0 0 11 &gic 0 168 4>,
+				<0 0 12 &gic 0 169 4>;
+
+		motherboard {
+			model = "V2M-Juno";
+			arm,hbi = <0x252>;
+			arm,vexpress,site = <0>;
+			arm,v2m-memory-map = "rs1";
+			compatible = "arm,vexpress,v2p-p1", "simple-bus";
+			#address-cells = <2>;  /* SMB chipselect number and offset */
+			#size-cells = <1>;
+			#interrupt-cells = <1>;
+			ranges;
+
+			usb@5,00000000 {
+				compatible = "nxp,usb-isp1763";
+				reg = <5 0x00000000 0x20000>;
+				bus-width = <16>;
+				interrupts = <4>;
+			};
+
+			ethernet@2,00000000 {
+				compatible = "smsc,lan9118", "smsc,lan9115";
+				reg = <2 0x00000000 0x10000>;
+				interrupts = <3>;
+				phy-mode = "mii";
+				reg-io-width = <4>;
+				smsc,irq-active-high;
+				smsc,irq-push-pull;
+				clocks = <&mb_eth25mhz>;
+				vdd33a-supply = <&soc_fixed_3v3>; /* change this */
+				vddvario-supply = <&soc_fixed_3v3>; /* and this */
+			};
+
+			iofpga@3,00000000 {
+				compatible = "arm,amba-bus", "simple-bus";
+				#address-cells = <1>;
+				#size-cells = <1>;
+				ranges = <0 3 0 0x200000>;
+
+				kmi@060000 {
+					compatible = "arm,pl050", "arm,primecell";
+					reg = <0x060000 0x1000>;
+					interrupts = <8>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "KMIREFCLK", "apb_pclk";
+				};
+
+				kmi@070000 {
+					compatible = "arm,pl050", "arm,primecell";
+					reg = <0x070000 0x1000>;
+					interrupts = <8>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "KMIREFCLK", "apb_pclk";
+				};
+
+				wdt@0f0000 {
+					compatible = "arm,sp805", "arm,primecell";
+					reg = <0x0f0000 0x10000>;
+					interrupts = <7>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "wdogclk", "apb_pclk";
+				};
+
+				v2m_timer01: timer@110000 {
+					compatible = "arm,sp804", "arm,primecell";
+					reg = <0x110000 0x10000>;
+					interrupts = <9>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "timclken1", "apb_pclk";
+				};
+
+				v2m_timer23: timer@120000 {
+					compatible = "arm,sp804", "arm,primecell";
+					reg = <0x120000 0x10000>;
+					interrupts = <9>;
+					clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+					clock-names = "timclken1", "apb_pclk";
+				};
+
+				rtc@170000 {
+					compatible = "arm,pl031", "arm,primecell";
+					reg = <0x170000 0x10000>;
+					interrupts = <0>;
+					clocks = <&soc_smc50mhz>;
+					clock-names = "apb_pclk";
+				};
+			};
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
index 572005ea2217..f76eb9024a32 100644
--- a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
+++ b/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
@@ -157,3 +157,5 @@
 		/include/ "rtsm_ve-motherboard.dtsi"
 	};
 };
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
index 2f2ecd217363..b683d4703582 100644
--- a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
+++ b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
@@ -182,6 +182,9 @@
 				interrupts = <14>;
 				clocks = <&v2m_oscclk1>, <&v2m_clk24mhz>;
 				clock-names = "clcdclk", "apb_pclk";
+				mode = "XVGA";
+				use_dma = <0>;
+				framebuffer = <0x18000000 0x00180000>;
 			};
 
 			virtio_block@0130000 {
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
new file mode 100644
index 000000000000..5562652c5316
--- /dev/null
+++ b/arch/arm64/crypto/Kconfig
@@ -0,0 +1,53 @@
+
+menuconfig ARM64_CRYPTO
+	bool "ARM64 Accelerated Cryptographic Algorithms"
+	depends on ARM64
+	help
+	  Say Y here to choose from a selection of cryptographic algorithms
+	  implemented using ARM64 specific CPU features or instructions.
+
+if ARM64_CRYPTO
+
+config CRYPTO_SHA1_ARM64_CE
+	tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_SHA2_ARM64_CE
+	tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_GHASH_ARM64_CE
+	tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_HASH
+
+config CRYPTO_AES_ARM64_CE
+	tristate "AES core cipher using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES
+
+config CRYPTO_AES_ARM64_CE_CCM
+	tristate "AES in CCM mode using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES
+	select CRYPTO_AEAD
+
+config CRYPTO_AES_ARM64_CE_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_ABLK_HELPER
+
+config CRYPTO_AES_ARM64_NEON_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_ABLK_HELPER
+
+endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 000000000000..2070a56ecc46
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,38 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
+sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
+sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
+
+obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
+ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
+aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o
+aes-ce-blk-y := aes-glue-ce.o aes-ce.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
+aes-neon-blk-y := aes-glue-neon.o aes-neon.o
+
+AFLAGS_aes-ce.o		:= -DINTERLEAVE=2 -DINTERLEAVE_INLINE
+AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
+
+CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
+
+$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
+	$(call if_changed_dep,cc_o_c)
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
new file mode 100644
index 000000000000..432e4841cd81
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -0,0 +1,222 @@
+/*
+ * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.arch	armv8-a+crypto
+
+	/*
+	 * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+	 *			     u32 *macp, u8 const rk[], u32 rounds);
+	 */
+ENTRY(ce_aes_ccm_auth_data)
+	ldr	w8, [x3]			/* leftover from prev round? */
+	ld1	{v0.2d}, [x0]			/* load mac */
+	cbz	w8, 1f
+	sub	w8, w8, #16
+	eor	v1.16b, v1.16b, v1.16b
+0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
+	subs	w2, w2, #1
+	add	w8, w8, #1
+	ins	v1.b[0], w7
+	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
+	beq	8f				/* out of input? */
+	cbnz	w8, 0b
+	eor	v0.16b, v0.16b, v1.16b
+1:	ld1	{v3.2d}, [x4]			/* load first round key */
+	prfm	pldl1strm, [x1]
+	cmp	w5, #12				/* which key size? */
+	add	x6, x4, #16
+	sub	w7, w5, #2			/* modified # of rounds */
+	bmi	2f
+	bne	5f
+	mov	v5.16b, v3.16b
+	b	4f
+2:	mov	v4.16b, v3.16b
+	ld1	{v5.2d}, [x6], #16		/* load 2nd round key */
+3:	aese	v0.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+4:	ld1	{v3.2d}, [x6], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+5:	ld1	{v4.2d}, [x6], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	ld1	{v5.2d}, [x6], #16		/* load next round key */
+	bpl	3b
+	aese	v0.16b, v4.16b
+	subs	w2, w2, #16			/* last data? */
+	eor	v0.16b, v0.16b, v5.16b		/* final round */
+	bmi	6f
+	ld1	{v1.16b}, [x1], #16		/* load next input block */
+	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
+	bne	1b
+6:	st1	{v0.2d}, [x0]			/* store mac */
+	beq	10f
+	adds	w2, w2, #16
+	beq	10f
+	mov	w8, w2
+7:	ldrb	w7, [x1], #1
+	umov	w6, v0.b[0]
+	eor	w6, w6, w7
+	strb	w6, [x0], #1
+	subs	w2, w2, #1
+	beq	10f
+	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
+	b	7b
+8:	mov	w7, w8
+	add	w8, w8, #16
+9:	ext	v1.16b, v1.16b, v1.16b, #1
+	adds	w7, w7, #1
+	bne	9b
+	eor	v0.16b, v0.16b, v1.16b
+	st1	{v0.2d}, [x0]
+10:	str	w8, [x3]
+	ret
+ENDPROC(ce_aes_ccm_auth_data)
+
+	/*
+	 * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
+	 * 			 u32 rounds);
+	 */
+ENTRY(ce_aes_ccm_final)
+	ld1	{v3.2d}, [x2], #16		/* load first round key */
+	ld1	{v0.2d}, [x0]			/* load mac */
+	cmp	w3, #12				/* which key size? */
+	sub	w3, w3, #2			/* modified # of rounds */
+	ld1	{v1.2d}, [x1]			/* load 1st ctriv */
+	bmi	0f
+	bne	3f
+	mov	v5.16b, v3.16b
+	b	2f
+0:	mov	v4.16b, v3.16b
+1:	ld1	{v5.2d}, [x2], #16		/* load next round key */
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aese	v1.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
+	subs	w3, w3, #3
+	aese	v0.16b, v3.16b
+	aese	v1.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+	bpl	1b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	/* final round key cancels out */
+	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
+	st1	{v0.2d}, [x0]			/* store result */
+	ret
+ENDPROC(ce_aes_ccm_final)
+
+	.macro	aes_ccm_do_crypt,enc
+	ldr	x8, [x6, #8]			/* load lower ctr */
+	ld1	{v0.2d}, [x5]			/* load mac */
+	rev	x8, x8				/* keep swabbed ctr in reg */
+0:	/* outer loop */
+	ld1	{v1.1d}, [x6]			/* load upper ctr */
+	prfm	pldl1strm, [x1]
+	add	x8, x8, #1
+	rev	x9, x8
+	cmp	w4, #12				/* which key size? */
+	sub	w7, w4, #2			/* get modified # of rounds */
+	ins	v1.d[1], x9			/* no carry in lower ctr */
+	ld1	{v3.2d}, [x3]			/* load first round key */
+	add	x10, x3, #16
+	bmi	1f
+	bne	4f
+	mov	v5.16b, v3.16b
+	b	3f
+1:	mov	v4.16b, v3.16b
+	ld1	{v5.2d}, [x10], #16		/* load 2nd round key */
+2:	/* inner loop: 3 rounds, 2x interleaved */
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aese	v1.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aese	v1.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aesmc	v1.16b, v1.16b
+	ld1	{v5.2d}, [x10], #16		/* load next round key */
+	bpl	2b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	subs	w2, w2, #16
+	bmi	6f				/* partial block? */
+	ld1	{v2.16b}, [x1], #16		/* load next input block */
+	.if	\enc == 1
+	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
+	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
+	.else
+	eor	v2.16b, v2.16b, v1.16b		/* xor with crypted ctr */
+	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
+	.endif
+	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
+	st1	{v1.16b}, [x0], #16		/* write output block */
+	bne	0b
+	rev	x8, x8
+	st1	{v0.2d}, [x5]			/* store mac */
+	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
+5:	ret
+
+6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
+	st1	{v0.2d}, [x5]			/* store mac */
+	add	w2, w2, #16			/* process partial tail block */
+7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
+	umov	w6, v1.b[0]			/* get top crypted ctr byte */
+	umov	w7, v0.b[0]			/* get top mac byte */
+	.if	\enc == 1
+	eor	w7, w7, w9
+	eor	w9, w9, w6
+	.else
+	eor	w9, w9, w6
+	eor	w7, w7, w9
+	.endif
+	strb	w9, [x0], #1			/* store out byte */
+	strb	w7, [x5], #1			/* store mac byte */
+	subs	w2, w2, #1
+	beq	5b
+	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
+	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
+	b	7b
+	.endm
+
+	/*
+	 * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 */
+ENTRY(ce_aes_ccm_encrypt)
+	aes_ccm_do_crypt	1
+ENDPROC(ce_aes_ccm_encrypt)
+
+ENTRY(ce_aes_ccm_decrypt)
+	aes_ccm_do_crypt	0
+ENDPROC(ce_aes_ccm_decrypt)
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
new file mode 100644
index 000000000000..9e6cdde9b43d
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -0,0 +1,297 @@
+/*
+ * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/scatterwalk.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+asmlinkage void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+				     u32 *macp, u32 const rk[], u32 rounds);
+
+asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
+				 u32 rounds);
+
+static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
+		      unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm);
+	int ret;
+
+	ret = crypto_aes_expand_key(ctx, in_key, key_len);
+	if (!ret)
+		return 0;
+
+	tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	if ((authsize & 1) || authsize < 4)
+		return -EINVAL;
+	return 0;
+}
+
+static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	__be32 *n = (__be32 *)&maciv[AES_BLOCK_SIZE - 8];
+	u32 l = req->iv[0] + 1;
+
+	/* verify that CCM dimension 'L' is set correctly in the IV */
+	if (l < 2 || l > 8)
+		return -EINVAL;
+
+	/* verify that msglen can in fact be represented in L bytes */
+	if (l < 4 && msglen >> (8 * l))
+		return -EOVERFLOW;
+
+	/*
+	 * Even if the CCM spec allows L values of up to 8, the Linux cryptoapi
+	 * uses a u32 type to represent msglen so the top 4 bytes are always 0.
+	 */
+	n[0] = 0;
+	n[1] = cpu_to_be32(msglen);
+
+	memcpy(maciv, req->iv, AES_BLOCK_SIZE - l);
+
+	/*
+	 * Meaning of byte 0 according to CCM spec (RFC 3610/NIST 800-38C)
+	 * - bits 0..2	: max # of bytes required to represent msglen, minus 1
+	 *                (already set by caller)
+	 * - bits 3..5	: size of auth tag (1 => 4 bytes, 2 => 6 bytes, etc)
+	 * - bit 6	: indicates presence of authenticate-only data
+	 */
+	maciv[0] |= (crypto_aead_authsize(aead) - 2) << 2;
+	if (req->assoclen)
+		maciv[0] |= 0x40;
+
+	memset(&req->iv[AES_BLOCK_SIZE - l], 0, l);
+	return 0;
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct __packed { __be16 l; __be32 h; u16 len; } ltag;
+	struct scatter_walk walk;
+	u32 len = req->assoclen;
+	u32 macp = 0;
+
+	/* prepend the AAD with a length tag */
+	if (len < 0xff00) {
+		ltag.l = cpu_to_be16(len);
+		ltag.len = 2;
+	} else  {
+		ltag.l = cpu_to_be16(0xfffe);
+		put_unaligned_be32(len, &ltag.h);
+		ltag.len = 6;
+	}
+
+	ce_aes_ccm_auth_data(mac, (u8 *)&ltag, ltag.len, &macp, ctx->key_enc,
+			     num_rounds(ctx));
+	scatterwalk_start(&walk, req->assoc);
+
+	do {
+		u32 n = scatterwalk_clamp(&walk, len);
+		u8 *p;
+
+		if (!n) {
+			scatterwalk_start(&walk, sg_next(walk.sg));
+			n = scatterwalk_clamp(&walk, len);
+		}
+		p = scatterwalk_map(&walk);
+		ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc,
+				     num_rounds(ctx));
+		len -= n;
+
+		scatterwalk_unmap(p);
+		scatterwalk_advance(&walk, n);
+		scatterwalk_done(&walk, 0, len);
+	} while (len);
+}
+
+static int ccm_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct blkcipher_desc desc = { .info = req->iv };
+	struct blkcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	kernel_neon_begin_partial(6);
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+					     AES_BLOCK_SIZE);
+
+	while (walk.nbytes) {
+		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+		if (walk.nbytes == len)
+			tail = 0;
+
+		ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   walk.nbytes - tail, ctx->key_enc,
+				   num_rounds(ctx), mac, walk.iv);
+
+		len -= walk.nbytes - tail;
+		err = blkcipher_walk_done(&desc, &walk, tail);
+	}
+	if (!err)
+		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+	kernel_neon_end();
+
+	if (err)
+		return err;
+
+	/* copy authtag to end of dst */
+	scatterwalk_map_and_copy(mac, req->dst, req->cryptlen,
+				 crypto_aead_authsize(aead), 1);
+
+	return 0;
+}
+
+static int ccm_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int authsize = crypto_aead_authsize(aead);
+	struct blkcipher_desc desc = { .info = req->iv };
+	struct blkcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen - authsize;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	kernel_neon_begin_partial(6);
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	blkcipher_walk_init(&walk, req->dst, req->src, len);
+	err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+					     AES_BLOCK_SIZE);
+
+	while (walk.nbytes) {
+		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+		if (walk.nbytes == len)
+			tail = 0;
+
+		ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   walk.nbytes - tail, ctx->key_enc,
+				   num_rounds(ctx), mac, walk.iv);
+
+		len -= walk.nbytes - tail;
+		err = blkcipher_walk_done(&desc, &walk, tail);
+	}
+	if (!err)
+		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+	kernel_neon_end();
+
+	if (err)
+		return err;
+
+	/* compare calculated auth tag with the stored one */
+	scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize,
+				 authsize, 0);
+
+	if (memcmp(mac, buf, authsize))
+		return -EBADMSG;
+	return 0;
+}
+
+static struct crypto_alg ccm_aes_alg = {
+	.cra_name		= "ccm(aes)",
+	.cra_driver_name	= "ccm-aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_AEAD,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_aead_type,
+	.cra_module		= THIS_MODULE,
+	.cra_aead = {
+		.ivsize		= AES_BLOCK_SIZE,
+		.maxauthsize	= AES_BLOCK_SIZE,
+		.setkey		= ccm_setkey,
+		.setauthsize	= ccm_setauthsize,
+		.encrypt	= ccm_encrypt,
+		.decrypt	= ccm_decrypt,
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	if (!(elf_hwcap & HWCAP_AES))
+		return -ENODEV;
+	return crypto_register_alg(&ccm_aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&ccm_aes_alg);
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
+
+MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
new file mode 100644
index 000000000000..2075e1acae6b
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -0,0 +1,155 @@
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+struct aes_block {
+	u8 b[AES_BLOCK_SIZE];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aes_block *out = (struct aes_block *)dst;
+	struct aes_block const *in = (struct aes_block *)src;
+	void *dummy0;
+	int dummy1;
+
+	kernel_neon_begin_partial(4);
+
+	__asm__("	ld1	{v0.16b}, %[in]			;"
+		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	cmp	%w[rounds], #10			;"
+		"	bmi	0f				;"
+		"	bne	3f				;"
+		"	mov	v3.16b, v1.16b			;"
+		"	b	2f				;"
+		"0:	mov	v2.16b, v1.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"1:	aese	v0.16b, v2.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"	aese	v0.16b, v3.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"	subs	%w[rounds], %w[rounds], #3	;"
+		"	aese	v0.16b, v1.16b			;"
+		"	aesmc	v0.16b, v0.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	bpl	1b				;"
+		"	aese	v0.16b, v2.16b			;"
+		"	eor	v0.16b, v0.16b, v3.16b		;"
+		"	st1	{v0.16b}, %[out]		;"
+
+	:	[out]		"=Q"(*out),
+		[key]		"=r"(dummy0),
+		[rounds]	"=r"(dummy1)
+	:	[in]		"Q"(*in),
+				"1"(ctx->key_enc),
+				"2"(num_rounds(ctx) - 2)
+	:	"cc");
+
+	kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aes_block *out = (struct aes_block *)dst;
+	struct aes_block const *in = (struct aes_block *)src;
+	void *dummy0;
+	int dummy1;
+
+	kernel_neon_begin_partial(4);
+
+	__asm__("	ld1	{v0.16b}, %[in]			;"
+		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	cmp	%w[rounds], #10			;"
+		"	bmi	0f				;"
+		"	bne	3f				;"
+		"	mov	v3.16b, v1.16b			;"
+		"	b	2f				;"
+		"0:	mov	v2.16b, v1.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"1:	aesd	v0.16b, v2.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"	aesd	v0.16b, v3.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"	subs	%w[rounds], %w[rounds], #3	;"
+		"	aesd	v0.16b, v1.16b			;"
+		"	aesimc	v0.16b, v0.16b			;"
+		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	bpl	1b				;"
+		"	aesd	v0.16b, v2.16b			;"
+		"	eor	v0.16b, v0.16b, v3.16b		;"
+		"	st1	{v0.16b}, %[out]		;"
+
+	:	[out]		"=Q"(*out),
+		[key]		"=r"(dummy0),
+		[rounds]	"=r"(dummy1)
+	:	[in]		"Q"(*in),
+				"1"(ctx->key_dec),
+				"2"(num_rounds(ctx) - 2)
+	:	"cc");
+
+	kernel_neon_end();
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name		= "aes",
+	.cra_driver_name	= "aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_cipher = {
+		.cia_min_keysize	= AES_MIN_KEY_SIZE,
+		.cia_max_keysize	= AES_MAX_KEY_SIZE,
+		.cia_setkey		= crypto_aes_set_key,
+		.cia_encrypt		= aes_cipher_encrypt,
+		.cia_decrypt		= aes_cipher_decrypt
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
new file mode 100644
index 000000000000..685a18f731eb
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce.S
@@ -0,0 +1,133 @@
+/*
+ * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
+ *                                    Crypto Extensions
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func)		ENTRY(ce_ ## func)
+#define AES_ENDPROC(func)	ENDPROC(ce_ ## func)
+
+	.arch		armv8-a+crypto
+
+	/* preload all round keys */
+	.macro		load_round_keys, rounds, rk
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	ld1		{v17.16b-v18.16b}, [\rk], #32
+1111:	ld1		{v19.16b-v20.16b}, [\rk], #32
+2222:	ld1		{v21.16b-v24.16b}, [\rk], #64
+	ld1		{v25.16b-v28.16b}, [\rk], #64
+	ld1		{v29.16b-v31.16b}, [\rk]
+	.endm
+
+	/* prepare for encryption with key in rk[] */
+	.macro		enc_prepare, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	/* prepare for encryption (again) but with new key in rk[] */
+	.macro		enc_switch_key, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	/* prepare for decryption with key in rk[] */
+	.macro		dec_prepare, rounds, rk, ignore
+	load_round_keys	\rounds, \rk
+	.endm
+
+	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3
+	aes\de		\i0\().16b, \k\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\de		\i3\().16b, \k\().16b
+	.endif
+	.endif
+	aes\mc		\i0\().16b, \i0\().16b
+	.ifnb		\i1
+	aes\mc		\i1\().16b, \i1\().16b
+	.ifnb		\i3
+	aes\mc		\i2\().16b, \i2\().16b
+	aes\mc		\i3\().16b, \i3\().16b
+	.endif
+	.endif
+	.endm
+
+	/* up to 4 interleaved encryption rounds with the same round key */
+	.macro		round_Nx, enc, k, i0, i1, i2, i3
+	.ifc		\enc, e
+	do_enc_Nx	e, mc, \k, \i0, \i1, \i2, \i3
+	.else
+	do_enc_Nx	d, imc, \k, \i0, \i1, \i2, \i3
+	.endif
+	.endm
+
+	/* up to 4 interleaved final rounds */
+	.macro		fin_round_Nx, de, k, k2, i0, i1, i2, i3
+	aes\de		\i0\().16b, \k\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\de		\i3\().16b, \k\().16b
+	.endif
+	.endif
+	eor		\i0\().16b, \i0\().16b, \k2\().16b
+	.ifnb		\i1
+	eor		\i1\().16b, \i1\().16b, \k2\().16b
+	.ifnb		\i3
+	eor		\i2\().16b, \i2\().16b, \k2\().16b
+	eor		\i3\().16b, \i3\().16b, \k2\().16b
+	.endif
+	.endif
+	.endm
+
+	/* up to 4 interleaved blocks */
+	.macro		do_block_Nx, enc, rounds, i0, i1, i2, i3
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	round_Nx	\enc, v17, \i0, \i1, \i2, \i3
+	round_Nx	\enc, v18, \i0, \i1, \i2, \i3
+1111:	round_Nx	\enc, v19, \i0, \i1, \i2, \i3
+	round_Nx	\enc, v20, \i0, \i1, \i2, \i3
+2222:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+	round_Nx	\enc, \key, \i0, \i1, \i2, \i3
+	.endr
+	fin_round_Nx	\enc, v30, v31, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		encrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \in
+	.endm
+
+	.macro		encrypt_block2x, i0, i1, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1
+	.endm
+
+	.macro		encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		decrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \in
+	.endm
+
+	.macro		decrypt_block2x, i0, i1, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1
+	.endm
+
+	.macro		decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+#include "aes-modes.S"
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
new file mode 100644
index 000000000000..60f2f4c12256
--- /dev/null
+++ b/arch/arm64/crypto/aes-glue.c
@@ -0,0 +1,446 @@
+/*
+ * linux/arch/arm64/crypto/aes-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/hwcap.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+#define MODE			"ce"
+#define PRIO			300
+#define aes_ecb_encrypt		ce_aes_ecb_encrypt
+#define aes_ecb_decrypt		ce_aes_ecb_decrypt
+#define aes_cbc_encrypt		ce_aes_cbc_encrypt
+#define aes_cbc_decrypt		ce_aes_cbc_decrypt
+#define aes_ctr_encrypt		ce_aes_ctr_encrypt
+#define aes_xts_encrypt		ce_aes_xts_encrypt
+#define aes_xts_decrypt		ce_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+#else
+#define MODE			"neon"
+#define PRIO			200
+#define aes_ecb_encrypt		neon_aes_ecb_encrypt
+#define aes_ecb_decrypt		neon_aes_ecb_decrypt
+#define aes_cbc_encrypt		neon_aes_cbc_encrypt
+#define aes_cbc_decrypt		neon_aes_cbc_decrypt
+#define aes_ctr_encrypt		neon_aes_ctr_encrypt
+#define aes_xts_encrypt		neon_aes_xts_encrypt
+#define aes_xts_decrypt		neon_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
+MODULE_ALIAS("ecb(aes)");
+MODULE_ALIAS("cbc(aes)");
+MODULE_ALIAS("ctr(aes)");
+MODULE_ALIAS("xts(aes)");
+#endif
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-modes.S */
+asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, int first);
+asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, int first);
+
+asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 iv[], int first);
+asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 iv[], int first);
+
+asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				int rounds, int blocks, u8 ctr[], int first);
+
+asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
+				int rounds, int blocks, u8 const rk2[], u8 iv[],
+				int first);
+asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
+				int rounds, int blocks, u8 const rk2[], u8 iv[],
+				int first);
+
+struct crypto_aes_xts_ctx {
+	struct crypto_aes_ctx key1;
+	struct crypto_aes_ctx __aligned(8) key2;
+};
+
+static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = crypto_aes_expand_key(&ctx->key1, in_key, key_len / 2);
+	if (!ret)
+		ret = crypto_aes_expand_key(&ctx->key2, &in_key[key_len / 2],
+					    key_len / 2);
+	if (!ret)
+		return 0;
+
+	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_dec, rounds, blocks, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+				first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
+				first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key_length / 4;
+	struct blkcipher_walk walk;
+	int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+
+	first = 1;
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+				first);
+		first = 0;
+		nbytes -= blocks * AES_BLOCK_SIZE;
+		if (nbytes && nbytes == walk.nbytes % AES_BLOCK_SIZE)
+			break;
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	if (nbytes) {
+		u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 __aligned(8) tail[AES_BLOCK_SIZE];
+
+		/*
+		 * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
+		 * to tell aes_ctr_encrypt() to only read half a block.
+		 */
+		blocks = (nbytes <= 8) ? -1 : 1;
+
+		aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds,
+				blocks, walk.iv, first);
+		memcpy(tdst, tail, nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key1.key_enc, rounds, blocks,
+				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				(u8 *)ctx->key1.key_dec, rounds, blocks,
+				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static struct crypto_alg aes_algs[] = { {
+	.cra_name		= "__ecb-aes-" MODE,
+	.cra_driver_name	= "__driver-ecb-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= ecb_encrypt,
+		.decrypt	= ecb_decrypt,
+	},
+}, {
+	.cra_name		= "__cbc-aes-" MODE,
+	.cra_driver_name	= "__driver-cbc-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= cbc_encrypt,
+		.decrypt	= cbc_decrypt,
+	},
+}, {
+	.cra_name		= "__ctr-aes-" MODE,
+	.cra_driver_name	= "__driver-ctr-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= crypto_aes_set_key,
+		.encrypt	= ctr_encrypt,
+		.decrypt	= ctr_encrypt,
+	},
+}, {
+	.cra_name		= "__xts-aes-" MODE,
+	.cra_driver_name	= "__driver-xts-aes-" MODE,
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_xts_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= xts_set_key,
+		.encrypt	= xts_encrypt,
+		.decrypt	= xts_decrypt,
+	},
+}, {
+	.cra_name		= "ecb(aes)",
+	.cra_driver_name	= "ecb-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "cbc(aes)",
+	.cra_driver_name	= "cbc-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "ctr(aes)",
+	.cra_driver_name	= "ctr-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "xts(aes)",
+	.cra_driver_name	= "xts-aes-" MODE,
+	.cra_priority		= PRIO,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+} };
+
+static int __init aes_init(void)
+{
+	return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static void __exit aes_exit(void)
+{
+	crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+module_cpu_feature_match(AES, aes_init);
+#else
+module_init(aes_init);
+#endif
+module_exit(aes_exit);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
new file mode 100644
index 000000000000..f6e372c528eb
--- /dev/null
+++ b/arch/arm64/crypto/aes-modes.S
@@ -0,0 +1,532 @@
+/*
+ * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* included by aes-ce.S and aes-neon.S */
+
+	.text
+	.align		4
+
+/*
+ * There are several ways to instantiate this code:
+ * - no interleave, all inline
+ * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2)
+ * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE)
+ * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4)
+ * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE)
+ *
+ * Macros imported by this code:
+ * - enc_prepare	- setup NEON registers for encryption
+ * - dec_prepare	- setup NEON registers for decryption
+ * - enc_switch_key	- change to new key after having prepared for encryption
+ * - encrypt_block	- encrypt a single block
+ * - decrypt block	- decrypt a single block
+ * - encrypt_block2x	- encrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - decrypt_block2x	- decrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - encrypt_block4x	- encrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ * - decrypt_block4x	- decrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ */
+
+#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE)
+#define FRAME_PUSH	stp x29, x30, [sp,#-16]! ; mov x29, sp
+#define FRAME_POP	ldp x29, x30, [sp],#16
+
+#if INTERLEAVE == 2
+
+aes_encrypt_block2x:
+	encrypt_block2x	v0, v1, w3, x2, x6, w7
+	ret
+ENDPROC(aes_encrypt_block2x)
+
+aes_decrypt_block2x:
+	decrypt_block2x	v0, v1, w3, x2, x6, w7
+	ret
+ENDPROC(aes_decrypt_block2x)
+
+#elif INTERLEAVE == 4
+
+aes_encrypt_block4x:
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	ret
+ENDPROC(aes_encrypt_block4x)
+
+aes_decrypt_block4x:
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	ret
+ENDPROC(aes_decrypt_block4x)
+
+#else
+#error INTERLEAVE should equal 2 or 4
+#endif
+
+	.macro		do_encrypt_block2x
+	bl		aes_encrypt_block2x
+	.endm
+
+	.macro		do_decrypt_block2x
+	bl		aes_decrypt_block2x
+	.endm
+
+	.macro		do_encrypt_block4x
+	bl		aes_encrypt_block4x
+	.endm
+
+	.macro		do_decrypt_block4x
+	bl		aes_decrypt_block4x
+	.endm
+
+#else
+#define FRAME_PUSH
+#define FRAME_POP
+
+	.macro		do_encrypt_block2x
+	encrypt_block2x	v0, v1, w3, x2, x6, w7
+	.endm
+
+	.macro		do_decrypt_block2x
+	decrypt_block2x	v0, v1, w3, x2, x6, w7
+	.endm
+
+	.macro		do_encrypt_block4x
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	.endm
+
+	.macro		do_decrypt_block4x
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x6, w7
+	.endm
+
+#endif
+
+	/*
+	 * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, int first)
+	 * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, int first)
+	 */
+
+AES_ENTRY(aes_ecb_encrypt)
+	FRAME_PUSH
+	cbz		w5, .LecbencloopNx
+
+	enc_prepare	w3, x2, x5
+
+.LecbencloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lecbenc1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
+	do_encrypt_block2x
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	do_encrypt_block4x
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LecbencloopNx
+.Lecbenc1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lecbencout
+#endif
+.Lecbencloop:
+	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	encrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbencloop
+.Lecbencout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ecb_encrypt)
+
+
+AES_ENTRY(aes_ecb_decrypt)
+	FRAME_PUSH
+	cbz		w5, .LecbdecloopNx
+
+	dec_prepare	w3, x2, x5
+
+.LecbdecloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lecbdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	do_decrypt_block2x
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	do_decrypt_block4x
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LecbdecloopNx
+.Lecbdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lecbdecout
+#endif
+.Lecbdecloop:
+	ld1		{v0.16b}, [x1], #16		/* get next ct block */
+	decrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbdecloop
+.Lecbdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ecb_decrypt)
+
+
+	/*
+	 * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[], int first)
+	 * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[], int first)
+	 */
+
+AES_ENTRY(aes_cbc_encrypt)
+	cbz		w6, .Lcbcencloop
+
+	ld1		{v0.16b}, [x5]			/* get iv */
+	enc_prepare	w3, x2, x5
+
+.Lcbcencloop:
+	ld1		{v1.16b}, [x1], #16		/* get next pt block */
+	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
+	encrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcencloop
+	ret
+AES_ENDPROC(aes_cbc_encrypt)
+
+
+AES_ENTRY(aes_cbc_decrypt)
+	FRAME_PUSH
+	cbz		w6, .LcbcdecloopNx
+
+	ld1		{v7.16b}, [x5]			/* get iv */
+	dec_prepare	w3, x2, x5
+
+.LcbcdecloopNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lcbcdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	mov		v2.16b, v0.16b
+	mov		v3.16b, v1.16b
+	do_decrypt_block2x
+	eor		v0.16b, v0.16b, v7.16b
+	eor		v1.16b, v1.16b, v2.16b
+	mov		v7.16b, v3.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	mov		v4.16b, v0.16b
+	mov		v5.16b, v1.16b
+	mov		v6.16b, v2.16b
+	do_decrypt_block4x
+	sub		x1, x1, #16
+	eor		v0.16b, v0.16b, v7.16b
+	eor		v1.16b, v1.16b, v4.16b
+	ld1		{v7.16b}, [x1], #16		/* reload 1 ct block */
+	eor		v2.16b, v2.16b, v5.16b
+	eor		v3.16b, v3.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+#endif
+	b		.LcbcdecloopNx
+.Lcbcdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lcbcdecout
+#endif
+.Lcbcdecloop:
+	ld1		{v1.16b}, [x1], #16		/* get next ct block */
+	mov		v0.16b, v1.16b			/* ...and copy to v0 */
+	decrypt_block	v0, w3, x2, x5, w6
+	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
+	mov		v7.16b, v1.16b			/* ct is next iv */
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcdecloop
+.Lcbcdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_cbc_decrypt)
+
+
+	/*
+	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 ctr[], int first)
+	 */
+
+AES_ENTRY(aes_ctr_encrypt)
+	FRAME_PUSH
+	cbnz		w6, .Lctrfirst		/* 1st time around? */
+	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x5, x5
+#if INTERLEAVE >= 2
+	cmn		w5, w4			/* 32 bit overflow? */
+	bcs		.Lctrinc
+	add		x5, x5, #1		/* increment BE ctr */
+	b		.LctrincNx
+#else
+	b		.Lctrinc
+#endif
+.Lctrfirst:
+	enc_prepare	w3, x2, x6
+	ld1		{v4.16b}, [x5]
+	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x5, x5
+#if INTERLEAVE >= 2
+	cmn		w5, w4			/* 32 bit overflow? */
+	bcs		.Lctrloop
+.LctrloopNx:
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lctr1x
+#if INTERLEAVE == 2
+	mov		v0.8b, v4.8b
+	mov		v1.8b, v4.8b
+	rev		x7, x5
+	add		x5, x5, #1
+	ins		v0.d[1], x7
+	rev		x7, x5
+	add		x5, x5, #1
+	ins		v1.d[1], x7
+	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
+	do_encrypt_block2x
+	eor		v0.16b, v0.16b, v2.16b
+	eor		v1.16b, v1.16b, v3.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+#else
+	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
+	dup		v7.4s, w5
+	mov		v0.16b, v4.16b
+	add		v7.4s, v7.4s, v8.4s
+	mov		v1.16b, v4.16b
+	rev32		v8.16b, v7.16b
+	mov		v2.16b, v4.16b
+	mov		v3.16b, v4.16b
+	mov		v1.s[3], v8.s[0]
+	mov		v2.s[3], v8.s[1]
+	mov		v3.s[3], v8.s[2]
+	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
+	do_encrypt_block4x
+	eor		v0.16b, v5.16b, v0.16b
+	ld1		{v5.16b}, [x1], #16		/* get 1 input block  */
+	eor		v1.16b, v6.16b, v1.16b
+	eor		v2.16b, v7.16b, v2.16b
+	eor		v3.16b, v5.16b, v3.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	add		x5, x5, #INTERLEAVE
+#endif
+	cbz		w4, .LctroutNx
+.LctrincNx:
+	rev		x7, x5
+	ins		v4.d[1], x7
+	b		.LctrloopNx
+.LctroutNx:
+	sub		x5, x5, #1
+	rev		x7, x5
+	ins		v4.d[1], x7
+	b		.Lctrout
+.Lctr1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lctrout
+#endif
+.Lctrloop:
+	mov		v0.16b, v4.16b
+	encrypt_block	v0, w3, x2, x6, w7
+	subs		w4, w4, #1
+	bmi		.Lctrhalfblock		/* blocks < 0 means 1/2 block */
+	ld1		{v3.16b}, [x1], #16
+	eor		v3.16b, v0.16b, v3.16b
+	st1		{v3.16b}, [x0], #16
+	beq		.Lctrout
+.Lctrinc:
+	adds		x5, x5, #1		/* increment BE ctr */
+	rev		x7, x5
+	ins		v4.d[1], x7
+	bcc		.Lctrloop		/* no overflow? */
+	umov		x7, v4.d[0]		/* load upper word of ctr  */
+	rev		x7, x7			/* ... to handle the carry */
+	add		x7, x7, #1
+	rev		x7, x7
+	ins		v4.d[0], x7
+	b		.Lctrloop
+.Lctrhalfblock:
+	ld1		{v3.8b}, [x1]
+	eor		v3.8b, v0.8b, v3.8b
+	st1		{v3.8b}, [x0]
+.Lctrout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_ctr_encrypt)
+	.ltorg
+
+
+	/*
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 const rk2[], u8 iv[], int first)
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 const rk2[], u8 iv[], int first)
+	 */
+
+	.macro		next_tweak, out, in, const, tmp
+	sshr		\tmp\().2d,  \in\().2d,   #63
+	and		\tmp\().16b, \tmp\().16b, \const\().16b
+	add		\out\().2d,  \in\().2d,   \in\().2d
+	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+	eor		\out\().16b, \out\().16b, \tmp\().16b
+	.endm
+
+.Lxts_mul_x:
+	.word		1, 0, 0x87, 0
+
+AES_ENTRY(aes_xts_encrypt)
+	FRAME_PUSH
+	cbz		w7, .LxtsencloopNx
+
+	ld1		{v4.16b}, [x6]
+	enc_prepare	w3, x5, x6
+	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
+	enc_switch_key	w3, x2, x6
+	ldr		q7, .Lxts_mul_x
+	b		.LxtsencNx
+
+.LxtsencloopNx:
+	ldr		q7, .Lxts_mul_x
+	next_tweak	v4, v4, v7, v8
+.LxtsencNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lxtsenc1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 pt blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	do_encrypt_block2x
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+	cbz		w4, .LxtsencoutNx
+	next_tweak	v4, v5, v7, v8
+	b		.LxtsencNx
+.LxtsencoutNx:
+	mov		v4.16b, v5.16b
+	b		.Lxtsencout
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v7, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v7, v8
+	eor		v3.16b, v3.16b, v7.16b
+	do_encrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsencout
+	b		.LxtsencloopNx
+#endif
+.Lxtsenc1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lxtsencout
+#endif
+.Lxtsencloop:
+	ld1		{v1.16b}, [x1], #16
+	eor		v0.16b, v1.16b, v4.16b
+	encrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, v4.16b
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	beq		.Lxtsencout
+	next_tweak	v4, v4, v7, v8
+	b		.Lxtsencloop
+.Lxtsencout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_xts_encrypt)
+
+
+AES_ENTRY(aes_xts_decrypt)
+	FRAME_PUSH
+	cbz		w7, .LxtsdecloopNx
+
+	ld1		{v4.16b}, [x6]
+	enc_prepare	w3, x5, x6
+	encrypt_block	v4, w3, x5, x6, w7		/* first tweak */
+	dec_prepare	w3, x2, x6
+	ldr		q7, .Lxts_mul_x
+	b		.LxtsdecNx
+
+.LxtsdecloopNx:
+	ldr		q7, .Lxts_mul_x
+	next_tweak	v4, v4, v7, v8
+.LxtsdecNx:
+#if INTERLEAVE >= 2
+	subs		w4, w4, #INTERLEAVE
+	bmi		.Lxtsdec1x
+#if INTERLEAVE == 2
+	ld1		{v0.16b-v1.16b}, [x1], #32	/* get 2 ct blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	do_decrypt_block2x
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	st1		{v0.16b-v1.16b}, [x0], #32
+	cbz		w4, .LxtsdecoutNx
+	next_tweak	v4, v5, v7, v8
+	b		.LxtsdecNx
+.LxtsdecoutNx:
+	mov		v4.16b, v5.16b
+	b		.Lxtsdecout
+#else
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	next_tweak	v5, v4, v7, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v7, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v7, v8
+	eor		v3.16b, v3.16b, v7.16b
+	do_decrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsdecout
+	b		.LxtsdecloopNx
+#endif
+.Lxtsdec1x:
+	adds		w4, w4, #INTERLEAVE
+	beq		.Lxtsdecout
+#endif
+.Lxtsdecloop:
+	ld1		{v1.16b}, [x1], #16
+	eor		v0.16b, v1.16b, v4.16b
+	decrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, v4.16b
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	beq		.Lxtsdecout
+	next_tweak	v4, v4, v7, v8
+	b		.Lxtsdecloop
+.Lxtsdecout:
+	FRAME_POP
+	ret
+AES_ENDPROC(aes_xts_decrypt)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
new file mode 100644
index 000000000000..b93170e1cc93
--- /dev/null
+++ b/arch/arm64/crypto/aes-neon.S
@@ -0,0 +1,382 @@
+/*
+ * linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func)		ENTRY(neon_ ## func)
+#define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
+
+	/* multiply by polynomial 'x' in GF(2^8) */
+	.macro		mul_by_x, out, in, temp, const
+	sshr		\temp, \in, #7
+	add		\out, \in, \in
+	and		\temp, \temp, \const
+	eor		\out, \out, \temp
+	.endm
+
+	/* preload the entire Sbox */
+	.macro		prepare, sbox, shiftrows, temp
+	adr		\temp, \sbox
+	movi		v12.16b, #0x40
+	ldr		q13, \shiftrows
+	movi		v14.16b, #0x1b
+	ld1		{v16.16b-v19.16b}, [\temp], #64
+	ld1		{v20.16b-v23.16b}, [\temp], #64
+	ld1		{v24.16b-v27.16b}, [\temp], #64
+	ld1		{v28.16b-v31.16b}, [\temp]
+	.endm
+
+	/* do preload for encryption */
+	.macro		enc_prepare, ignore0, ignore1, temp
+	prepare		.LForward_Sbox, .LForward_ShiftRows, \temp
+	.endm
+
+	.macro		enc_switch_key, ignore0, ignore1, temp
+	/* do nothing */
+	.endm
+
+	/* do preload for decryption */
+	.macro		dec_prepare, ignore0, ignore1, temp
+	prepare		.LReverse_Sbox, .LReverse_ShiftRows, \temp
+	.endm
+
+	/* apply SubBytes transformation using the the preloaded Sbox */
+	.macro		sub_bytes, in
+	sub		v9.16b, \in\().16b, v12.16b
+	tbl		\in\().16b, {v16.16b-v19.16b}, \in\().16b
+	sub		v10.16b, v9.16b, v12.16b
+	tbx		\in\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v11.16b, v10.16b, v12.16b
+	tbx		\in\().16b, {v24.16b-v27.16b}, v10.16b
+	tbx		\in\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	/* apply MixColumns transformation */
+	.macro		mix_columns, in
+	mul_by_x	v10.16b, \in\().16b, v9.16b, v14.16b
+	rev32		v8.8h, \in\().8h
+	eor		\in\().16b, v10.16b, \in\().16b
+	shl		v9.4s, v8.4s, #24
+	shl		v11.4s, \in\().4s, #24
+	sri		v9.4s, v8.4s, #8
+	sri		v11.4s, \in\().4s, #8
+	eor		v9.16b, v9.16b, v8.16b
+	eor		v10.16b, v10.16b, v9.16b
+	eor		\in\().16b, v10.16b, v11.16b
+	.endm
+
+	/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+	.macro		inv_mix_columns, in
+	mul_by_x	v11.16b, \in\().16b, v10.16b, v14.16b
+	mul_by_x	v11.16b, v11.16b, v10.16b, v14.16b
+	eor		\in\().16b, \in\().16b, v11.16b
+	rev32		v11.8h, v11.8h
+	eor		\in\().16b, \in\().16b, v11.16b
+	mix_columns	\in
+	.endm
+
+	.macro		do_block, enc, in, rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
+	sub_bytes	\in
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns	\in
+	.else
+	inv_mix_columns	\in
+	.endif
+	b		1111b
+2222:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	.endm
+
+	.macro		encrypt_block, in, rounds, rk, rkp, i
+	do_block	1, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block, in, rounds, rk, rkp, i
+	do_block	0, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	/*
+	 * Interleaved versions: functionally equivalent to the
+	 * ones above, but applied to 2 or 4 AES states in parallel.
+	 */
+
+	.macro		sub_bytes_2x, in0, in1
+	sub		v8.16b, \in0\().16b, v12.16b
+	sub		v9.16b, \in1\().16b, v12.16b
+	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+	sub		v10.16b, v8.16b, v12.16b
+	sub		v11.16b, v9.16b, v12.16b
+	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
+	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v8.16b, v10.16b, v12.16b
+	sub		v9.16b, v11.16b, v12.16b
+	tbx		\in0\().16b, {v24.16b-v27.16b}, v10.16b
+	tbx		\in1\().16b, {v24.16b-v27.16b}, v11.16b
+	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
+	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
+	.endm
+
+	.macro		sub_bytes_4x, in0, in1, in2, in3
+	sub		v8.16b, \in0\().16b, v12.16b
+	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+	sub		v9.16b, \in1\().16b, v12.16b
+	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+	sub		v10.16b, \in2\().16b, v12.16b
+	tbl		\in2\().16b, {v16.16b-v19.16b}, \in2\().16b
+	sub		v11.16b, \in3\().16b, v12.16b
+	tbl		\in3\().16b, {v16.16b-v19.16b}, \in3\().16b
+	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
+	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v8.16b, v8.16b, v12.16b
+	tbx		\in2\().16b, {v20.16b-v23.16b}, v10.16b
+	sub		v9.16b, v9.16b, v12.16b
+	tbx		\in3\().16b, {v20.16b-v23.16b}, v11.16b
+	sub		v10.16b, v10.16b, v12.16b
+	tbx		\in0\().16b, {v24.16b-v27.16b}, v8.16b
+	sub		v11.16b, v11.16b, v12.16b
+	tbx		\in1\().16b, {v24.16b-v27.16b}, v9.16b
+	sub		v8.16b, v8.16b, v12.16b
+	tbx		\in2\().16b, {v24.16b-v27.16b}, v10.16b
+	sub		v9.16b, v9.16b, v12.16b
+	tbx		\in3\().16b, {v24.16b-v27.16b}, v11.16b
+	sub		v10.16b, v10.16b, v12.16b
+	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
+	sub		v11.16b, v11.16b, v12.16b
+	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
+	tbx		\in2\().16b, {v28.16b-v31.16b}, v10.16b
+	tbx		\in3\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	.macro		mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const
+	sshr		\tmp0\().16b, \in0\().16b,  #7
+	add		\out0\().16b, \in0\().16b,  \in0\().16b
+	sshr		\tmp1\().16b, \in1\().16b,  #7
+	and		\tmp0\().16b, \tmp0\().16b, \const\().16b
+	add		\out1\().16b, \in1\().16b,  \in1\().16b
+	and		\tmp1\().16b, \tmp1\().16b, \const\().16b
+	eor		\out0\().16b, \out0\().16b, \tmp0\().16b
+	eor		\out1\().16b, \out1\().16b, \tmp1\().16b
+	.endm
+
+	.macro		mix_columns_2x, in0, in1
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	rev32		v10.8h, \in0\().8h
+	rev32		v11.8h, \in1\().8h
+	eor		\in0\().16b, v8.16b, \in0\().16b
+	eor		\in1\().16b, v9.16b, \in1\().16b
+	shl		v12.4s, v10.4s, #24
+	shl		v13.4s, v11.4s, #24
+	eor		v8.16b, v8.16b, v10.16b
+	sri		v12.4s, v10.4s, #8
+	shl		v10.4s, \in0\().4s, #24
+	eor		v9.16b, v9.16b, v11.16b
+	sri		v13.4s, v11.4s, #8
+	shl		v11.4s, \in1\().4s, #24
+	sri		v10.4s, \in0\().4s, #8
+	eor		\in0\().16b, v8.16b, v12.16b
+	sri		v11.4s, \in1\().4s, #8
+	eor		\in1\().16b, v9.16b, v13.16b
+	eor		\in0\().16b, v10.16b, \in0\().16b
+	eor		\in1\().16b, v11.16b, \in1\().16b
+	.endm
+
+	.macro		inv_mix_cols_2x, in0, in1
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	mul_by_x_2x	v8, v9, v8, v9, v10, v11, v14
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	rev32		v8.8h, v8.8h
+	rev32		v9.8h, v9.8h
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	mix_columns_2x	\in0, \in1
+	.endm
+
+	.macro		inv_mix_cols_4x, in0, in1, in2, in3
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v14
+	mul_by_x_2x	v10, v11, \in2, \in3, v12, v13, v14
+	mul_by_x_2x	v8, v9, v8, v9, v12, v13, v14
+	mul_by_x_2x	v10, v11, v10, v11, v12, v13, v14
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	eor		\in2\().16b, \in2\().16b, v10.16b
+	eor		\in3\().16b, \in3\().16b, v11.16b
+	rev32		v8.8h, v8.8h
+	rev32		v9.8h, v9.8h
+	rev32		v10.8h, v10.8h
+	rev32		v11.8h, v11.8h
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	eor		\in2\().16b, \in2\().16b, v10.16b
+	eor		\in3\().16b, \in3\().16b, v11.16b
+	mix_columns_2x	\in0, \in1
+	mix_columns_2x	\in2, \in3
+	.endm
+
+	.macro		do_block_2x, enc, in0, in1 rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	sub_bytes_2x	\in0, \in1
+	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns_2x	\in0, \in1
+	ldr		q13, .LForward_ShiftRows
+	.else
+	inv_mix_cols_2x	\in0, \in1
+	ldr		q13, .LReverse_ShiftRows
+	.endif
+	movi		v12.16b, #0x40
+	b		1111b
+2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	.endm
+
+	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
+	ld1		{v15.16b}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	sub_bytes_4x	\in0, \in1, \in2, \in3
+	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
+	ld1		{v15.16b}, [\rkp], #16
+	subs		\i, \i, #1
+	beq		2222f
+	.if		\enc == 1
+	mix_columns_2x	\in0, \in1
+	mix_columns_2x	\in2, \in3
+	ldr		q13, .LForward_ShiftRows
+	.else
+	inv_mix_cols_4x	\in0, \in1, \in2, \in3
+	ldr		q13, .LReverse_ShiftRows
+	.endif
+	movi		v12.16b, #0x40
+	b		1111b
+2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	.endm
+
+	.macro		encrypt_block2x, in0, in1, rounds, rk, rkp, i
+	do_block_2x	1, \in0, \in1, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block2x, in0, in1, rounds, rk, rkp, i
+	do_block_2x	0, \in0, \in1, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+#include "aes-modes.S"
+
+	.text
+	.align		4
+.LForward_ShiftRows:
+	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
+	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+
+.LReverse_ShiftRows:
+	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
+	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+
+.LForward_Sbox:
+	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
+	.byte		0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+	.byte		0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+	.byte		0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+	.byte		0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+	.byte		0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+	.byte		0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+	.byte		0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+	.byte		0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+	.byte		0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+	.byte		0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+	.byte		0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+	.byte		0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+	.byte		0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+	.byte		0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+	.byte		0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+	.byte		0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+	.byte		0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+	.byte		0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+	.byte		0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+	.byte		0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+	.byte		0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+	.byte		0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+	.byte		0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+	.byte		0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+	.byte		0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+	.byte		0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+	.byte		0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+	.byte		0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+	.byte		0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+	.byte		0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+	.byte		0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+
+.LReverse_Sbox:
+	.byte		0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+	.byte		0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+	.byte		0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+	.byte		0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+	.byte		0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+	.byte		0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+	.byte		0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+	.byte		0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+	.byte		0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+	.byte		0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+	.byte		0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+	.byte		0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+	.byte		0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+	.byte		0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+	.byte		0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+	.byte		0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+	.byte		0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+	.byte		0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+	.byte		0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+	.byte		0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+	.byte		0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+	.byte		0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+	.byte		0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+	.byte		0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+	.byte		0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+	.byte		0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+	.byte		0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+	.byte		0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+	.byte		0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+	.byte		0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+	.byte		0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+	.byte		0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
new file mode 100644
index 000000000000..dc457015884e
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -0,0 +1,79 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	SHASH	.req	v0
+	SHASH2	.req	v1
+	T1	.req	v2
+	T2	.req	v3
+	MASK	.req	v4
+	XL	.req	v5
+	XM	.req	v6
+	XH	.req	v7
+	IN1	.req	v7
+
+	.text
+	.arch		armv8-a+crypto
+
+	/*
+	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+	 *			   struct ghash_key const *k, const char *head)
+	 */
+ENTRY(pmull_ghash_update)
+	ld1		{SHASH.16b}, [x3]
+	ld1		{XL.16b}, [x1]
+	movi		MASK.16b, #0xe1
+	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	shl		MASK.2d, MASK.2d, #57
+	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
+
+	/* do the head block first, if supplied */
+	cbz		x4, 0f
+	ld1		{T1.2d}, [x4]
+	b		1f
+
+0:	ld1		{T1.2d}, [x2], #16
+	sub		w0, w0, #1
+
+1:	/* multiply XL by SHASH in GF(2^128) */
+CPU_LE(	rev64		T1.16b, T1.16b	)
+
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	eor		T1.16b, T1.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
+
+	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
+	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
+
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, XL.16b, XH.16b
+	eor		XM.16b, XM.16b, T1.16b
+	eor		XM.16b, XM.16b, T2.16b
+	pmull		T2.1q, XL.1d, MASK.1d
+
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	eor		XL.16b, XM.16b, T2.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	pmull		XL.1q, XL.1d, MASK.1d
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
+
+	cbnz		w0, 0b
+
+	st1		{XL.16b}, [x1]
+	ret
+ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
new file mode 100644
index 000000000000..833ec1e3f3e9
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -0,0 +1,156 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+#define GHASH_BLOCK_SIZE	16
+#define GHASH_DIGEST_SIZE	16
+
+struct ghash_key {
+	u64 a;
+	u64 b;
+};
+
+struct ghash_desc_ctx {
+	u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+	u8 buf[GHASH_BLOCK_SIZE];
+	u32 count;
+};
+
+asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+				   struct ghash_key const *k, const char *head);
+
+static int ghash_init(struct shash_desc *desc)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+			unsigned int len)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	ctx->count += len;
+
+	if ((partial + len) >= GHASH_BLOCK_SIZE) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+		int blocks;
+
+		if (partial) {
+			int p = GHASH_BLOCK_SIZE - partial;
+
+			memcpy(ctx->buf + partial, src, p);
+			src += p;
+			len -= p;
+		}
+
+		blocks = len / GHASH_BLOCK_SIZE;
+		len %= GHASH_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(8);
+		pmull_ghash_update(blocks, ctx->digest, src, key,
+				   partial ? ctx->buf : NULL);
+		kernel_neon_end();
+		src += blocks * GHASH_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(ctx->buf + partial, src, len);
+	return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	if (partial) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+
+		kernel_neon_begin_partial(8);
+		pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
+		kernel_neon_end();
+	}
+	put_unaligned_be64(ctx->digest[1], dst);
+	put_unaligned_be64(ctx->digest[0], dst + 8);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+			const u8 *inkey, unsigned int keylen)
+{
+	struct ghash_key *key = crypto_shash_ctx(tfm);
+	u64 a, b;
+
+	if (keylen != GHASH_BLOCK_SIZE) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	/* perform multiplication by 'x' in GF(2^128) */
+	b = get_unaligned_be64(inkey);
+	a = get_unaligned_be64(inkey + 8);
+
+	key->a = (a << 1) | (b >> 63);
+	key->b = (b << 1) | (a >> 63);
+
+	if (b >> 63)
+		key->b ^= 0xc200000000000000UL;
+
+	return 0;
+}
+
+static struct shash_alg ghash_alg = {
+	.digestsize	= GHASH_DIGEST_SIZE,
+	.init		= ghash_init,
+	.update		= ghash_update,
+	.final		= ghash_final,
+	.setkey		= ghash_setkey,
+	.descsize	= sizeof(struct ghash_desc_ctx),
+	.base		= {
+		.cra_name		= "ghash",
+		.cra_driver_name	= "ghash-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= GHASH_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct ghash_key),
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init ghash_ce_mod_init(void)
+{
+	return crypto_register_shash(&ghash_alg);
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+	crypto_unregister_shash(&ghash_alg);
+}
+
+module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
new file mode 100644
index 000000000000..09d57d98609c
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -0,0 +1,153 @@
+/*
+ * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	k0		.req	v0
+	k1		.req	v1
+	k2		.req	v2
+	k3		.req	v3
+
+	t0		.req	v4
+	t1		.req	v5
+
+	dga		.req	q6
+	dgav		.req	v6
+	dgb		.req	s7
+	dgbv		.req	v7
+
+	dg0q		.req	q12
+	dg0s		.req	s12
+	dg0v		.req	v12
+	dg1s		.req	s13
+	dg1v		.req	v13
+	dg2s		.req	s14
+
+	.macro		add_only, op, ev, rc, s0, dg1
+	.ifc		\ev, ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha1h		dg2s, dg0s
+	.ifnb		\dg1
+	sha1\op		dg0q, \dg1, t0.4s
+	.else
+	sha1\op		dg0q, dg1s, t0.4s
+	.endif
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha1h		dg1s, dg0s
+	sha1\op		dg0q, dg2s, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, op, ev, rc, s0, s1, s2, s3, dg1
+	sha1su0		v\s0\().4s, v\s1\().4s, v\s2\().4s
+	add_only	\op, \ev, \rc, \s1, \dg1
+	sha1su1		v\s0\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA1 round constants
+	 */
+	.align		4
+.Lsha1_rcon:
+	.word		0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
+
+	/*
+	 * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+	 * 			  u8 *head, long bytes)
+	 */
+ENTRY(sha1_ce_transform)
+	/* load round constants */
+	adr		x6, .Lsha1_rcon
+	ld1r		{k0.4s}, [x6], #4
+	ld1r		{k1.4s}, [x6], #4
+	ld1r		{k2.4s}, [x6], #4
+	ld1r		{k3.4s}, [x6]
+
+	/* load state */
+	ldr		dga, [x2]
+	ldr		dgb, [x2, #16]
+
+	/* load partial state (if supplied) */
+	cbz		x3, 0f
+	ld1		{v8.4s-v11.4s}, [x3]
+	b		1f
+
+	/* load input */
+0:	ld1		{v8.4s-v11.4s}, [x1], #64
+	sub		w0, w0, #1
+
+1:
+CPU_LE(	rev32		v8.16b, v8.16b		)
+CPU_LE(	rev32		v9.16b, v9.16b		)
+CPU_LE(	rev32		v10.16b, v10.16b	)
+CPU_LE(	rev32		v11.16b, v11.16b	)
+
+2:	add		t0.4s, v8.4s, k0.4s
+	mov		dg0v.16b, dgav.16b
+
+	add_update	c, ev, k0,  8,  9, 10, 11, dgb
+	add_update	c, od, k0,  9, 10, 11,  8
+	add_update	c, ev, k0, 10, 11,  8,  9
+	add_update	c, od, k0, 11,  8,  9, 10
+	add_update	c, ev, k1,  8,  9, 10, 11
+
+	add_update	p, od, k1,  9, 10, 11,  8
+	add_update	p, ev, k1, 10, 11,  8,  9
+	add_update	p, od, k1, 11,  8,  9, 10
+	add_update	p, ev, k1,  8,  9, 10, 11
+	add_update	p, od, k2,  9, 10, 11,  8
+
+	add_update	m, ev, k2, 10, 11,  8,  9
+	add_update	m, od, k2, 11,  8,  9, 10
+	add_update	m, ev, k2,  8,  9, 10, 11
+	add_update	m, od, k2,  9, 10, 11,  8
+	add_update	m, ev, k3, 10, 11,  8,  9
+
+	add_update	p, od, k3, 11,  8,  9, 10
+	add_only	p, ev, k3,  9
+	add_only	p, od, k3, 10
+	add_only	p, ev, k3, 11
+	add_only	p, od
+
+	/* update state */
+	add		dgbv.2s, dgbv.2s, dg1v.2s
+	add		dgav.4s, dgav.4s, dg0v.4s
+
+	cbnz		w0, 0b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if we have no total byte count in x4. In that case, the input
+	 * size was not a round multiple of the block size, and the padding is
+	 * handled by the C code.
+	 */
+	cbz		x4, 3f
+	movi		v9.2d, #0
+	mov		x8, #0x80000000
+	movi		v10.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d8, x8
+	mov		x4, #0
+	mov		v11.d[0], xzr
+	mov		v11.d[1], x7
+	b		2b
+
+	/* store new state */
+3:	str		dga, [x2]
+	str		dgb, [x2, #16]
+	ret
+ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
new file mode 100644
index 000000000000..6fe83f37a750
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -0,0 +1,174 @@
+/*
+ * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+				  u8 *head, long bytes);
+
+static int sha1_init(struct shash_desc *desc)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha1_state){
+		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+	};
+	return 0;
+}
+
+static int sha1_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+
+	sctx->count += len;
+
+	if ((partial + len) >= SHA1_BLOCK_SIZE) {
+		int blocks;
+
+		if (partial) {
+			int p = SHA1_BLOCK_SIZE - partial;
+
+			memcpy(sctx->buffer + partial, data, p);
+			data += p;
+			len -= p;
+		}
+
+		blocks = len / SHA1_BLOCK_SIZE;
+		len %= SHA1_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(16);
+		sha1_ce_transform(blocks, data, sctx->state,
+				  partial ? sctx->buffer : NULL, 0);
+		kernel_neon_end();
+
+		data += blocks * SHA1_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(sctx->buffer + partial, data, len);
+	return 0;
+}
+
+static int sha1_final(struct shash_desc *desc, u8 *out)
+{
+	static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	__be64 bits = cpu_to_be64(sctx->count << 3);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	u32 padlen = SHA1_BLOCK_SIZE
+		     - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
+
+	sha1_update(desc, padding, padlen);
+	sha1_update(desc, (const u8 *)&bits, sizeof(bits));
+
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha1_state){};
+	return 0;
+}
+
+static int sha1_finup(struct shash_desc *desc, const u8 *data,
+		      unsigned int len, u8 *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int blocks;
+	int i;
+
+	if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
+		sha1_update(desc, data, len);
+		return sha1_final(desc, out);
+	}
+
+	/*
+	 * Use a fast path if the input is a multiple of 64 bytes. In
+	 * this case, there is no need to copy data around, and we can
+	 * perform the entire digest calculation in a single invocation
+	 * of sha1_ce_transform()
+	 */
+	blocks = len / SHA1_BLOCK_SIZE;
+
+	kernel_neon_begin_partial(16);
+	sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+	kernel_neon_end();
+
+	for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha1_state){};
+	return 0;
+}
+
+static int sha1_export(struct shash_desc *desc, void *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	struct sha1_state *dst = out;
+
+	*dst = *sctx;
+	return 0;
+}
+
+static int sha1_import(struct shash_desc *desc, const void *in)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	struct sha1_state const *src = in;
+
+	*sctx = *src;
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.init			= sha1_init,
+	.update			= sha1_update,
+	.final			= sha1_final,
+	.finup			= sha1_finup,
+	.export			= sha1_export,
+	.import			= sha1_import,
+	.descsize		= sizeof(struct sha1_state),
+	.digestsize		= SHA1_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha1_state),
+	.base			= {
+		.cra_name		= "sha1",
+		.cra_driver_name	= "sha1-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA1_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+};
+
+static int __init sha1_ce_mod_init(void)
+{
+	return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_ce_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
+module_exit(sha1_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
new file mode 100644
index 000000000000..7f29fc031ea8
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -0,0 +1,156 @@
+/*
+ * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	dga		.req	q20
+	dgav		.req	v20
+	dgb		.req	q21
+	dgbv		.req	v21
+
+	t0		.req	v22
+	t1		.req	v23
+
+	dg0q		.req	q24
+	dg0v		.req	v24
+	dg1q		.req	q25
+	dg1v		.req	v25
+	dg2q		.req	q26
+	dg2v		.req	v26
+
+	.macro		add_only, ev, rc, s0
+	mov		dg2v.16b, dg0v.16b
+	.ifeq		\ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha256h		dg0q, dg1q, t0.4s
+	sha256h2	dg1q, dg2q, t0.4s
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha256h		dg0q, dg1q, t1.4s
+	sha256h2	dg1q, dg2q, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, ev, rc, s0, s1, s2, s3
+	sha256su0	v\s0\().4s, v\s1\().4s
+	add_only	\ev, \rc, \s1
+	sha256su1	v\s0\().4s, v\s2\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA-256 round constants
+	 */
+	.align		4
+.Lsha2_rcon:
+	.word		0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+	.word		0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+	.word		0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+	.word		0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+	.word		0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+	.word		0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+	.word		0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+	.word		0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+	.word		0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+	.word		0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+	.word		0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+	.word		0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+	.word		0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+	.word		0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+	.word		0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+	/*
+	 * void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+	 *                        u8 *head, long bytes)
+	 */
+ENTRY(sha2_ce_transform)
+	/* load round constants */
+	adr		x8, .Lsha2_rcon
+	ld1		{ v0.4s- v3.4s}, [x8], #64
+	ld1		{ v4.4s- v7.4s}, [x8], #64
+	ld1		{ v8.4s-v11.4s}, [x8], #64
+	ld1		{v12.4s-v15.4s}, [x8]
+
+	/* load state */
+	ldp		dga, dgb, [x2]
+
+	/* load partial input (if supplied) */
+	cbz		x3, 0f
+	ld1		{v16.4s-v19.4s}, [x3]
+	b		1f
+
+	/* load input */
+0:	ld1		{v16.4s-v19.4s}, [x1], #64
+	sub		w0, w0, #1
+
+1:
+CPU_LE(	rev32		v16.16b, v16.16b	)
+CPU_LE(	rev32		v17.16b, v17.16b	)
+CPU_LE(	rev32		v18.16b, v18.16b	)
+CPU_LE(	rev32		v19.16b, v19.16b	)
+
+2:	add		t0.4s, v16.4s, v0.4s
+	mov		dg0v.16b, dgav.16b
+	mov		dg1v.16b, dgbv.16b
+
+	add_update	0,  v1, 16, 17, 18, 19
+	add_update	1,  v2, 17, 18, 19, 16
+	add_update	0,  v3, 18, 19, 16, 17
+	add_update	1,  v4, 19, 16, 17, 18
+
+	add_update	0,  v5, 16, 17, 18, 19
+	add_update	1,  v6, 17, 18, 19, 16
+	add_update	0,  v7, 18, 19, 16, 17
+	add_update	1,  v8, 19, 16, 17, 18
+
+	add_update	0,  v9, 16, 17, 18, 19
+	add_update	1, v10, 17, 18, 19, 16
+	add_update	0, v11, 18, 19, 16, 17
+	add_update	1, v12, 19, 16, 17, 18
+
+	add_only	0, v13, 17
+	add_only	1, v14, 18
+	add_only	0, v15, 19
+	add_only	1
+
+	/* update state */
+	add		dgav.4s, dgav.4s, dg0v.4s
+	add		dgbv.4s, dgbv.4s, dg1v.4s
+
+	/* handled all input blocks? */
+	cbnz		w0, 0b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if we have no total byte count in x4. In that case, the input
+	 * size was not a round multiple of the block size, and the padding is
+	 * handled by the C code.
+	 */
+	cbz		x4, 3f
+	movi		v17.2d, #0
+	mov		x8, #0x80000000
+	movi		v18.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d16, x8
+	mov		x4, #0
+	mov		v19.d[0], xzr
+	mov		v19.d[1], x7
+	b		2b
+
+	/* store new state */
+3:	stp		dga, dgb, [x2]
+	ret
+ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
new file mode 100644
index 000000000000..c294e67d3925
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -0,0 +1,255 @@
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage int sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+				 u8 *head, long bytes);
+
+static int sha224_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha256_state){
+		.state = {
+			SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
+			SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
+		}
+	};
+	return 0;
+}
+
+static int sha256_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha256_state){
+		.state = {
+			SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+			SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
+		}
+	};
+	return 0;
+}
+
+static int sha2_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+
+	sctx->count += len;
+
+	if ((partial + len) >= SHA256_BLOCK_SIZE) {
+		int blocks;
+
+		if (partial) {
+			int p = SHA256_BLOCK_SIZE - partial;
+
+			memcpy(sctx->buf + partial, data, p);
+			data += p;
+			len -= p;
+		}
+
+		blocks = len / SHA256_BLOCK_SIZE;
+		len %= SHA256_BLOCK_SIZE;
+
+		kernel_neon_begin_partial(28);
+		sha2_ce_transform(blocks, data, sctx->state,
+				  partial ? sctx->buf : NULL, 0);
+		kernel_neon_end();
+
+		data += blocks * SHA256_BLOCK_SIZE;
+		partial = 0;
+	}
+	if (len)
+		memcpy(sctx->buf + partial, data, len);
+	return 0;
+}
+
+static void sha2_final(struct shash_desc *desc)
+{
+	static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be64 bits = cpu_to_be64(sctx->count << 3);
+	u32 padlen = SHA256_BLOCK_SIZE
+		     - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE);
+
+	sha2_update(desc, padding, padlen);
+	sha2_update(desc, (const u8 *)&bits, sizeof(bits));
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_final(desc);
+
+	for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_final(desc);
+
+	for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static void sha2_finup(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	int blocks;
+
+	if (sctx->count || !len || (len % SHA256_BLOCK_SIZE)) {
+		sha2_update(desc, data, len);
+		sha2_final(desc);
+		return;
+	}
+
+	/*
+	 * Use a fast path if the input is a multiple of 64 bytes. In
+	 * this case, there is no need to copy data around, and we can
+	 * perform the entire digest calculation in a single invocation
+	 * of sha2_ce_transform()
+	 */
+	blocks = len / SHA256_BLOCK_SIZE;
+
+	kernel_neon_begin_partial(28);
+	sha2_ce_transform(blocks, data, sctx->state, NULL, len);
+	kernel_neon_end();
+	data += blocks * SHA256_BLOCK_SIZE;
+}
+
+static int sha224_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_finup(desc, data, len);
+
+	for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha256_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	__be32 *dst = (__be32 *)out;
+	int i;
+
+	sha2_finup(desc, data, len);
+
+	for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], dst++);
+
+	*sctx = (struct sha256_state){};
+	return 0;
+}
+
+static int sha2_export(struct shash_desc *desc, void *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	struct sha256_state *dst = out;
+
+	*dst = *sctx;
+	return 0;
+}
+
+static int sha2_import(struct shash_desc *desc, const void *in)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	struct sha256_state const *src = in;
+
+	*sctx = *src;
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.init			= sha224_init,
+	.update			= sha2_update,
+	.final			= sha224_final,
+	.finup			= sha224_finup,
+	.export			= sha2_export,
+	.import			= sha2_import,
+	.descsize		= sizeof(struct sha256_state),
+	.digestsize		= SHA224_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha256_state),
+	.base			= {
+		.cra_name		= "sha224",
+		.cra_driver_name	= "sha224-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+}, {
+	.init			= sha256_init,
+	.update			= sha2_update,
+	.final			= sha256_final,
+	.finup			= sha256_finup,
+	.export			= sha2_export,
+	.import			= sha2_import,
+	.descsize		= sizeof(struct sha256_state),
+	.digestsize		= SHA256_DIGEST_SIZE,
+	.statesize		= sizeof(struct sha256_state),
+	.base			= {
+		.cra_name		= "sha256",
+		.cra_driver_name	= "sha256-ce",
+		.cra_priority		= 200,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 71c53ecfcc3a..bd36b3013f82 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -10,6 +10,7 @@ generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
 generic-y += emergency-restart.h
+generic-y += early_ioremap.h
 generic-y += errno.h
 generic-y += ftrace.h
 generic-y += hw_irq.h
@@ -35,6 +36,7 @@ generic-y += segment.h
 generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
+generic-y += simd.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 0237f0867e37..9c48d74652cb 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -162,7 +162,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  */
 #define ATOMIC64_INIT(i) { (i) }
 
-#define atomic64_read(v)	(*(volatile long long *)&(v)->counter)
+#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
 #define atomic64_set(v,i)	(((v)->counter) = (i))
 
 static inline void atomic64_add(u64 i, atomic64_t *v)
diff --git a/arch/arm64/include/asm/bL_switcher.h b/arch/arm64/include/asm/bL_switcher.h
new file mode 100644
index 000000000000..2bee500b7f54
--- /dev/null
+++ b/arch/arm64/include/asm/bL_switcher.h
@@ -0,0 +1,54 @@
+/*
+ * Based on the stubs for the ARM implementation which is:
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/notifier.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+static inline int bL_switch_request(unsigned int cpu,
+				    unsigned int new_cluster_id)
+{
+	return -ENOTSUPP;
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE	0
+#define BL_NOTIFY_POST_ENABLE	1
+#define BL_NOTIFY_PRE_DISABLE	2
+#define BL_NOTIFY_POST_DISABLE	3
+
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+
+#endif
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 409ca370cfe2..71a42d6599fb 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -25,11 +25,12 @@
 #define wfi()		asm volatile("wfi" : : : "memory")
 
 #define isb()		asm volatile("isb" : : : "memory")
-#define dsb(opt)	asm volatile("dsb sy" : : : "memory")
+#define dmb(opt)	asm volatile("dmb " #opt : : : "memory")
+#define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
-#define mb()		dsb()
-#define rmb()		asm volatile("dsb ld" : : : "memory")
-#define wmb()		asm volatile("dsb st" : : : "memory")
+#define mb()		dsb(sy)
+#define rmb()		dsb(ld)
+#define wmb()		dsb(st)
 
 #ifndef CONFIG_SMP
 #define smp_mb()	barrier()
@@ -53,9 +54,9 @@ do {									\
 
 #else
 
-#define smp_mb()	asm volatile("dmb ish" : : : "memory")
-#define smp_rmb()	asm volatile("dmb ishld" : : : "memory")
-#define smp_wmb()	asm volatile("dmb ishst" : : : "memory")
+#define smp_mb()	dmb(ish)
+#define smp_rmb()	dmb(ishld)
+#define smp_wmb()	dmb(ishst)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 889324981aa4..f2defe1c380c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -85,6 +85,13 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 }
 
 /*
+ * Cache maintenance functions used by the DMA API. No to be used directly.
+ */
+extern void __dma_map_area(const void *, size_t, int);
+extern void __dma_unmap_area(const void *, size_t, int);
+extern void __dma_flush_range(const void *, const void *);
+
+/*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
  * space" model to handle this.
@@ -116,7 +123,7 @@ extern void flush_dcache_page(struct page *);
 static inline void __flush_icache_all(void)
 {
 	asm("ic	ialluis");
-	dsb();
+	dsb(ish);
 }
 
 #define flush_dcache_mmap_lock(mapping) \
@@ -131,19 +138,10 @@ static inline void __flush_icache_all(void)
 #define flush_icache_page(vma,page)	do { } while (0)
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
  */
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	/*
-	 * set_pte_at() called from vmap_pte_range() does not
-	 * have a DSB after cleaning the cache line.
-	 */
-	dsb();
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 57c0fa7bf711..ddb9d7830558 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -72,7 +72,12 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 }
 
 #define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+({ \
+	__typeof__(*(ptr)) __ret; \
+	__ret = (__typeof__(*(ptr))) \
+		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+	__ret; \
+})
 
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, int size)
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index fda2704b3f9f..56de5aadede2 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -37,8 +37,8 @@ typedef s32		compat_ssize_t;
 typedef s32		compat_time_t;
 typedef s32		compat_clock_t;
 typedef s32		compat_pid_t;
-typedef u32		__compat_uid_t;
-typedef u32		__compat_gid_t;
+typedef u16		__compat_uid_t;
+typedef u16		__compat_gid_t;
 typedef u16		__compat_uid16_t;
 typedef u16		__compat_gid16_t;
 typedef u32		__compat_uid32_t;
@@ -228,7 +228,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
@@ -305,11 +305,6 @@ static inline int is_compat_thread(struct thread_info *thread)
 
 #else /* !CONFIG_COMPAT */
 
-static inline int is_compat_task(void)
-{
-	return 0;
-}
-
 static inline int is_compat_thread(struct thread_info *thread)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
new file mode 100644
index 000000000000..cd4ac0516488
--- /dev/null
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
+ * in the kernel and for user space to keep track of which optional features
+ * are supported by the current system. So let's map feature 'x' to HWCAP_x.
+ * Note that HWCAP_x constants are bit fields so we need to take the log.
+ */
+
+#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
+#define cpu_feature(x)		ilog2(HWCAP_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+	return elf_hwcap & (1UL << num);
+}
+
+#endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index c404fb0df3a6..27f54a7cc81b 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -41,6 +41,7 @@
 
 #define ARM_CPU_PART_AEM_V8	0xD0F0
 #define ARM_CPU_PART_FOUNDATION	0xD000
+#define ARM_CPU_PART_CORTEX_A53	0xD030
 #define ARM_CPU_PART_CORTEX_A57	0xD070
 
 #define APM_CPU_PART_POTENZA	0x0000
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 62314791570c..7fb343779498 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -18,6 +18,15 @@
 
 #ifdef __KERNEL__
 
+/* Low-level stepping controls. */
+#define DBG_MDSCR_SS		(1 << 0)
+#define DBG_SPSR_SS		(1 << 21)
+
+/* MDSCR_EL1 enabling bits */
+#define DBG_MDSCR_KDE		(1 << 13)
+#define DBG_MDSCR_MDE		(1 << 15)
+#define DBG_MDSCR_MASK		~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
+
 #define	DBG_ESR_EVT(x)		(((x) >> 27) & 0x7)
 
 /* AArch64 */
@@ -26,10 +35,52 @@
 #define DBG_ESR_EVT_HWWP	0x2
 #define DBG_ESR_EVT_BRK		0x6
 
-enum debug_el {
-	DBG_ACTIVE_EL0 = 0,
-	DBG_ACTIVE_EL1,
-};
+/*
+ * Break point instruction encoding
+ */
+#define BREAK_INSTR_SIZE		4
+
+/*
+ * ESR values expected for dynamic and compile time BRK instruction
+ */
+#define DBG_ESR_VAL_BRK(x)	(0xf2000000 | ((x) & 0xfffff))
+
+/*
+ * #imm16 values used for BRK instruction generation
+ * Allowed values for kgbd are 0x400 - 0x7ff
+ * 0x400: for dynamic BRK instruction
+ * 0x401: for compile time BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_IMM		0x400
+#define KDBG_COMPILED_DBG_BRK_IMM	0x401
+
+/*
+ * BRK instruction encoding
+ * The #imm16 value should be placed at bits[20:5] within BRK ins
+ */
+#define AARCH64_BREAK_MON	0xd4200000
+
+/*
+ * Extract byte from BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \
+	((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
+
+/*
+ * Extract byte from BRK #imm16
+ */
+#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \
+	(((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
+
+#define KGDB_DYN_DGB_BRK_BYTE(x) \
+	(KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x))
+
+#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DGB_BRK_BYTE(0)
+#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DGB_BRK_BYTE(1)
+#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DGB_BRK_BYTE(2)
+#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DGB_BRK_BYTE(3)
+
+#define CACHE_FLUSH_IS_SAFE		1
 
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4
@@ -43,23 +94,6 @@ enum debug_el {
 #ifndef __ASSEMBLY__
 struct task_struct;
 
-#define local_dbg_save(flags)							\
-	do {									\
-		typecheck(unsigned long, flags);				\
-		asm volatile(							\
-		"mrs	%0, daif			// local_dbg_save\n"	\
-		"msr	daifset, #8"						\
-		: "=r" (flags) : : "memory");					\
-	} while (0)
-
-#define local_dbg_restore(flags)						\
-	do {									\
-		typecheck(unsigned long, flags);				\
-		asm volatile(							\
-		"msr	daif, %0			// local_dbg_restore\n"	\
-		: : "r" (flags) : "memory");					\
-	} while (0)
-
 #define DBG_ARCH_ID_RESERVED	0	/* In case of ptrace ABI updates. */
 
 #define DBG_HOOK_HANDLED	0
@@ -85,6 +119,11 @@ void unregister_break_hook(struct break_hook *hook);
 
 u8 debug_monitors_arch(void);
 
+enum debug_el {
+	DBG_ACTIVE_EL0 = 0,
+	DBG_ACTIVE_EL1,
+};
+
 void enable_debug_monitors(enum debug_el el);
 void disable_debug_monitors(enum debug_el el);
 
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index fd0c0c0e447a..dc82e52acdb3 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -26,10 +26,10 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops coherent_swiotlb_dma_ops;
+extern struct dma_map_ops noncoherent_swiotlb_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
@@ -47,6 +47,11 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return __generic_dma_ops(dev);
 }
 
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	dev->archdata.dma_ops = ops;
+}
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
new file mode 100644
index 000000000000..5f7bfe6df723
--- /dev/null
+++ b/arch/arm64/include/asm/fixmap.h
@@ -0,0 +1,67 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ * Copyright (C) 2013 Mark Salter <msalter@redhat.com>
+ *
+ * Adapted from arch/x86_64 version.
+ *
+ */
+
+#ifndef _ASM_ARM64_FIXMAP_H
+#define _ASM_ARM64_FIXMAP_H
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ *
+ * These 'compile-time allocated' memory buffers are
+ * page-sized. Use set_fixmap(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ */
+enum fixed_addresses {
+	FIX_EARLYCON_MEM_BASE,
+	__end_of_permanent_fixed_addresses,
+
+	/*
+	 * Temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define NR_FIX_BTMAPS		4
+#else
+#define NR_FIX_BTMAPS		64
+#endif
+#define FIX_BTMAPS_SLOTS	7
+#define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+
+#define FIXMAP_PAGE_IO     __pgprot(PROT_DEVICE_nGnRE)
+
+extern void __early_set_fixmap(enum fixed_addresses idx,
+			       phys_addr_t phys, pgprot_t flags);
+
+#define __set_fixmap __early_set_fixmap
+
+#include <asm-generic/fixmap.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_ARM64_FIXMAP_H */
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index c43b4ac13008..50f559f574fe 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -37,8 +37,21 @@ struct fpsimd_state {
 			u32 fpcr;
 		};
 	};
+	/* the id of the last cpu to have restored this state */
+	unsigned int cpu;
 };
 
+/*
+ * Struct for stacking the bottom 'n' FP/SIMD registers.
+ */
+struct fpsimd_partial_state {
+	u32		fpsr;
+	u32		fpcr;
+	u32		num_regs;
+	__uint128_t	vregs[32];
+};
+
+
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /* Masks for extracting the FPSR and FPCR from the FPSCR */
 #define VFP_FPSCR_STAT_MASK	0xf800009f
@@ -58,6 +71,16 @@ extern void fpsimd_load_state(struct fpsimd_state *state);
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
+extern void fpsimd_preserve_current_state(void);
+extern void fpsimd_restore_current_state(void);
+extern void fpsimd_update_current_state(struct fpsimd_state *state);
+
+extern void fpsimd_flush_task_state(struct task_struct *target);
+
+extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state,
+				      u32 num_regs);
+extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state);
+
 #endif
 
 #endif
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index bbec599c96bd..768414d55e64 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -62,3 +62,38 @@
 	ldr	w\tmpnr, [\state, #16 * 2 + 4]
 	msr	fpcr, x\tmpnr
 .endm
+
+.altmacro
+.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2
+	mrs	x\tmpnr1, fpsr
+	str	w\numnr, [\state, #8]
+	mrs	x\tmpnr2, fpcr
+	stp	w\tmpnr1, w\tmpnr2, [\state]
+	adr	x\tmpnr1, 0f
+	add	\state, \state, x\numnr, lsl #4
+	sub	x\tmpnr1, x\tmpnr1, x\numnr, lsl #1
+	br	x\tmpnr1
+	.irp	qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+	.irp	qb, %(qa + 1)
+	stp	q\qa, q\qb, [\state, # -16 * \qa - 16]
+	.endr
+	.endr
+0:
+.endm
+
+.macro fpsimd_restore_partial state, tmpnr1, tmpnr2
+	ldp	w\tmpnr1, w\tmpnr2, [\state]
+	msr	fpsr, x\tmpnr1
+	msr	fpcr, x\tmpnr2
+	adr	x\tmpnr1, 0f
+	ldr	w\tmpnr2, [\state, #8]
+	add	\state, \state, x\tmpnr2, lsl #4
+	sub	x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1
+	br	x\tmpnr1
+	.irp	qa, 30, 28, 26, 24, 22, 20, 18, 16, 14, 12, 10, 8, 6, 4, 2, 0
+	.irp	qb, %(qa + 1)
+	ldp	q\qa, q\qb, [\state, # -16 * \qa - 16]
+	.endr
+	.endr
+0:
+.endm
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
new file mode 100644
index 000000000000..c5534facf941
--- /dev/null
+++ b/arch/arm64/include/asm/ftrace.h
@@ -0,0 +1,59 @@
+/*
+ * arch/arm64/include/asm/ftrace.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_FTRACE_H
+#define __ASM_FTRACE_H
+
+#include <asm/insn.h>
+
+#define MCOUNT_ADDR		((unsigned long)_mcount)
+#define MCOUNT_INSN_SIZE	AARCH64_INSN_SIZE
+
+#ifndef __ASSEMBLY__
+#include <linux/compat.h>
+
+extern void _mcount(unsigned long);
+extern void *return_address(unsigned int);
+
+struct dyn_arch_ftrace {
+	/* No extra data needed for arm64 */
+};
+
+extern unsigned long ftrace_graph_call;
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/*
+	 * addr is the address of the mcount call instruction.
+	 * recordmcount does the necessary offset calculation.
+	 */
+	return addr;
+}
+
+#define ftrace_return_address(n) return_address(n)
+
+/*
+ * Because AArch32 mode does not share the same syscall table with AArch64,
+ * tracing compat syscalls may result in reporting bogus syscalls or even
+ * hang-up, so just do not trace them.
+ * See kernel/trace/trace_syscalls.c
+ *
+ * x86 code says:
+ * If the user realy wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+	return is_compat_task();
+}
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif /* __ASM_FTRACE_H */
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index ae4801d77514..0be67821f9ce 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	5
+#define NR_IPI	6
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index d064047612b1..52b484b6aa1a 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -79,7 +79,6 @@ static inline void decode_ctrl_reg(u32 reg,
  */
 #define ARM_MAX_BRP		16
 #define ARM_MAX_WRP		16
-#define ARM_MAX_HBP_SLOTS	(ARM_MAX_BRP + ARM_MAX_WRP)
 
 /* Virtual debug register bases. */
 #define AARCH64_DBG_REG_BVR	0
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 6cddbb0c9f54..0ad735166d9f 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -30,8 +30,15 @@
 #define COMPAT_HWCAP_IDIVA	(1 << 17)
 #define COMPAT_HWCAP_IDIVT	(1 << 18)
 #define COMPAT_HWCAP_IDIV	(COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_LPAE	(1 << 20)
 #define COMPAT_HWCAP_EVTSTRM	(1 << 21)
 
+#define COMPAT_HWCAP2_AES	(1 << 0)
+#define COMPAT_HWCAP2_PMULL	(1 << 1)
+#define COMPAT_HWCAP2_SHA1	(1 << 2)
+#define COMPAT_HWCAP2_SHA2	(1 << 3)
+#define COMPAT_HWCAP2_CRC32	(1 << 4)
+
 #ifndef __ASSEMBLY__
 /*
  * This yields a mask that user programs can use to figure out what
@@ -41,7 +48,8 @@
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
-extern unsigned int compat_elf_hwcap;
+#define COMPAT_ELF_HWCAP2	(compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
 #endif
 
 extern unsigned long elf_hwcap;
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index c44ad39ed310..62e7b8bcd2dc 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -16,11 +16,14 @@
  */
 #ifndef	__ASM_INSN_H
 #define	__ASM_INSN_H
+
 #include <linux/types.h>
 
 /* A64 instructions are always 32 bits. */
 #define	AARCH64_INSN_SIZE		4
 
+#ifndef __ASSEMBLY__
+
 /*
  * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
  * Section C3.1 "A64 instruction index by encoding":
@@ -105,4 +108,6 @@ int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
+#endif  /* __ASSEMBLY__ */
+
 #endif	/* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 4cc813eddacb..6d5e328575d4 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -27,6 +27,7 @@
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 #include <asm/pgtable.h>
+#include <asm/early_ioremap.h>
 
 #include <xen/xen.h>
 
@@ -229,19 +230,11 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot
 extern void __iounmap(volatile void __iomem *addr);
 extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 
-#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
-
 #define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_nocache(addr, size)	__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define iounmap				__iounmap
 
-#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)
-#define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PTE_PXN | PTE_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
-
 #define ARCH_HAS_IOREMAP_WC
 #include <asm-generic/iomap.h>
 
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index b2fcfbc51ecc..11cc941bd107 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -90,5 +90,28 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
 	return flags & PSR_I_BIT;
 }
 
+/*
+ * save and restore debug state
+ */
+#define local_dbg_save(flags)						\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		asm volatile(						\
+		"mrs    %0, daif		// local_dbg_save\n"	\
+		"msr    daifset, #8"					\
+		: "=r" (flags) : : "memory");				\
+	} while (0)
+
+#define local_dbg_restore(flags)					\
+	do {								\
+		typecheck(unsigned long, flags);			\
+		asm volatile(						\
+		"msr    daif, %0		// local_dbg_restore\n"	\
+		: : "r" (flags) : "memory");				\
+	} while (0)
+
+#define local_dbg_enable()	asm("msr	daifclr, #8" : : : "memory")
+#define local_dbg_disable()	asm("msr	daifset, #8" : : : "memory")
+
 #endif
 #endif
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
new file mode 100644
index 000000000000..3c8aafc1082f
--- /dev/null
+++ b/arch/arm64/include/asm/kgdb.h
@@ -0,0 +1,84 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/include/kgdb.h
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KGDB_H
+#define __ARM_KGDB_H
+
+#include <linux/ptrace.h>
+#include <asm/debug-monitors.h>
+
+#ifndef	__ASSEMBLY__
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	asm ("brk %0" : : "I" (KDBG_COMPILED_DBG_BRK_IMM));
+}
+
+extern void kgdb_handle_bus_error(void);
+extern int kgdb_fault_expected;
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * gdb is expecting the following registers layout.
+ *
+ * General purpose regs:
+ *     r0-r30: 64 bit
+ *     sp,pc : 64 bit
+ *     pstate  : 64 bit
+ *     Total: 34
+ * FPU regs:
+ *     f0-f31: 128 bit
+ *     Total: 32
+ * Extra regs
+ *     fpsr & fpcr: 32 bit
+ *     Total: 2
+ *
+ */
+
+#define _GP_REGS		34
+#define _FP_REGS		32
+#define _EXTRA_REGS		2
+/*
+ * general purpose registers size in bytes.
+ * pstate is only 4 bytes. subtract 4 bytes
+ */
+#define GP_REG_BYTES		(_GP_REGS * 8)
+#define DBG_MAX_REG_NUM		(_GP_REGS + _FP_REGS + _EXTRA_REGS)
+
+/*
+ * Size of I/O buffer for gdb packet.
+ * considering to hold all register contents, size is set
+ */
+
+#define BUFMAX			2048
+
+/*
+ * Number of bytes required for gdb_regs buffer.
+ * _GP_REGS: 8 bytes, _FP_REGS: 16 bytes and _EXTRA_REGS: 4 bytes each
+ * GDB fails to connect for size beyond this with error
+ * "'g' packet reply is too long"
+ */
+
+#define NUMREGBYTES	((_GP_REGS * 8) + (_FP_REGS * 16) + \
+			(_EXTRA_REGS * 4))
+
+#endif /* __ASM_KGDB_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0eb398655378..7fd3e27e3ccc 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -62,6 +62,7 @@
  * RW:		64bit by default, can be overriden for 32bit VMs
  * TAC:		Trap ACTLR
  * TSC:		Trap SMC
+ * TVM:		Trap VM ops (until M+C set in SCTLR_EL1)
  * TSW:		Trap cache operations by set/way
  * TWE:		Trap WFE
  * TWI:		Trap WFI
@@ -74,10 +75,11 @@
  * SWIO:	Turn set/way invalidates into set/way clean+invalidate
  */
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
-			 HCR_BSU_IS | HCR_FB | HCR_TAC | \
-			 HCR_AMO | HCR_IMO | HCR_FMO | \
-			 HCR_SWIO | HCR_TIDCP | HCR_RW)
+			 HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
+			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
+#define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
+
 
 /* Hyp System Control Register (SCTLR_EL2) bits */
 #define SCTLR_EL2_EE	(1 << 25)
@@ -106,7 +108,6 @@
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_PS_MASK	(7 << 16)
-#define VTCR_EL2_PS_40B		(2 << 16)
 #define VTCR_EL2_TG0_MASK	(1 << 14)
 #define VTCR_EL2_TG0_4K		(0 << 14)
 #define VTCR_EL2_TG0_64K	(1 << 14)
@@ -121,6 +122,17 @@
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
 
+/*
+ * We configure the Stage-2 page tables to always restrict the IPA space to be
+ * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
+ * not known to exist and will break with this configuration.
+ *
+ * Note that when using 4K pages, we concatenate two first level page tables
+ * together.
+ *
+ * The magic numbers used for VTTBR_X in this patch can be found in Tables
+ * D4-23 and D4-25 in ARM DDI 0487A.b.
+ */
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
@@ -129,10 +141,9 @@
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS		(VTCR_EL2_PS_40B | VTCR_EL2_TG0_64K | \
-				 VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
-				 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_SL0_LVL1 | \
-				 VTCR_EL2_T0SZ_40B)
+#define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
+				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
 #define VTTBR_X		(38 - VTCR_EL2_T0SZ_40B)
 #else
 /*
@@ -142,15 +153,14 @@
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS		(VTCR_EL2_PS_40B | VTCR_EL2_TG0_4K | \
-				 VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
-				 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_SL0_LVL1 | \
-				 VTCR_EL2_T0SZ_40B)
+#define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
+				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
 #define VTTBR_X		(37 - VTCR_EL2_T0SZ_40B)
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
 #define VTTBR_VMID_SHIFT  (48LLU)
 #define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
 
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index b25763bc0ec4..483842180f8f 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -18,6 +18,8 @@
 #ifndef __ARM_KVM_ASM_H__
 #define __ARM_KVM_ASM_H__
 
+#include <asm/virt.h>
+
 /*
  * 0 is reserved as an invalid value.
  * Order *must* be kept in sync with the hyp switch code.
@@ -43,14 +45,25 @@
 #define	AMAIR_EL1	19	/* Aux Memory Attribute Indirection Register */
 #define	CNTKCTL_EL1	20	/* Timer Control Register (EL1) */
 #define	PAR_EL1		21	/* Physical Address Register */
+#define MDSCR_EL1	22	/* Monitor Debug System Control Register */
+#define DBGBCR0_EL1	23	/* Debug Breakpoint Control Registers (0-15) */
+#define DBGBCR15_EL1	38
+#define DBGBVR0_EL1	39	/* Debug Breakpoint Value Registers (0-15) */
+#define DBGBVR15_EL1	54
+#define DBGWCR0_EL1	55	/* Debug Watchpoint Control Registers (0-15) */
+#define DBGWCR15_EL1	70
+#define DBGWVR0_EL1	71	/* Debug Watchpoint Value Registers (0-15) */
+#define DBGWVR15_EL1	86
+#define MDCCINT_EL1	87	/* Monitor Debug Comms Channel Interrupt Enable Reg */
+
 /* 32bit specific registers. Keep them at the end of the range */
-#define	DACR32_EL2	22	/* Domain Access Control Register */
-#define	IFSR32_EL2	23	/* Instruction Fault Status Register */
-#define	FPEXC32_EL2	24	/* Floating-Point Exception Control Register */
-#define	DBGVCR32_EL2	25	/* Debug Vector Catch Register */
-#define	TEECR32_EL1	26	/* ThumbEE Configuration Register */
-#define	TEEHBR32_EL1	27	/* ThumbEE Handler Base Register */
-#define	NR_SYS_REGS	28
+#define	DACR32_EL2	88	/* Domain Access Control Register */
+#define	IFSR32_EL2	89	/* Instruction Fault Status Register */
+#define	FPEXC32_EL2	90	/* Floating-Point Exception Control Register */
+#define	DBGVCR32_EL2	91	/* Debug Vector Catch Register */
+#define	TEECR32_EL1	92	/* ThumbEE Configuration Register */
+#define	TEEHBR32_EL1	93	/* ThumbEE Handler Base Register */
+#define	NR_SYS_REGS	94
 
 /* 32bit mapping */
 #define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
@@ -79,13 +92,26 @@
 #define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
 #define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
 #define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
-#define c10_AMAIR	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
 #define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
-#define NR_CP15_REGS	(NR_SYS_REGS * 2)
+
+#define cp14_DBGDSCRext	(MDSCR_EL1 * 2)
+#define cp14_DBGBCR0	(DBGBCR0_EL1 * 2)
+#define cp14_DBGBVR0	(DBGBVR0_EL1 * 2)
+#define cp14_DBGBXVR0	(cp14_DBGBVR0 + 1)
+#define cp14_DBGWCR0	(DBGWCR0_EL1 * 2)
+#define cp14_DBGWVR0	(DBGWVR0_EL1 * 2)
+#define cp14_DBGDCCINT	(MDCCINT_EL1 * 2)
+
+#define NR_COPRO_REGS	(NR_SYS_REGS * 2)
 
 #define ARM_EXCEPTION_IRQ	  0
 #define ARM_EXCEPTION_TRAP	  1
 
+#define KVM_ARM64_DEBUG_DIRTY_SHIFT	0
+#define KVM_ARM64_DEBUG_DIRTY		(1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
+
 #ifndef __ASSEMBLY__
 struct kvm;
 struct kvm_vcpu;
@@ -95,13 +121,21 @@ extern char __kvm_hyp_init_end[];
 
 extern char __kvm_hyp_vector[];
 
-extern char __kvm_hyp_code_start[];
-extern char __kvm_hyp_code_end[];
+#define	__kvm_hyp_code_start	__hyp_text_start
+#define	__kvm_hyp_code_end	__hyp_text_end
 
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+extern u64 __vgic_v3_get_ich_vtr_el2(void);
+
+extern char __save_vgic_v2_state[];
+extern char __restore_vgic_v2_state[];
+extern char __save_vgic_v3_state[];
+extern char __restore_vgic_v3_state[];
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
index 9a59301cd014..0b52377a6c11 100644
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -39,7 +39,8 @@ void kvm_register_target_sys_reg_table(unsigned int target,
 				       struct kvm_sys_reg_target_table *table);
 
 int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index dd8ecfc3f995..5674a55b5518 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -174,6 +174,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 
 static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
+	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+{
 	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE;
 }
 
@@ -213,6 +218,17 @@ static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
 		default:
 			return be64_to_cpu(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return le16_to_cpu(data & 0xffff);
+		case 4:
+			return le32_to_cpu(data & 0xffffffff);
+		default:
+			return le64_to_cpu(data);
+		}
 	}
 
 	return data;		/* Leave LE untouched */
@@ -233,6 +249,17 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 		default:
 			return cpu_to_be64(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_le16(data & 0xffff);
+		case 4:
+			return cpu_to_le32(data & 0xffffffff);
+		default:
+			return cpu_to_le64(data);
+		}
 	}
 
 	return data;		/* Leave LE untouched */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 0a1d69751562..bcde41905746 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -22,6 +22,8 @@
 #ifndef __ARM64_KVM_HOST_H__
 #define __ARM64_KVM_HOST_H__
 
+#include <linux/types.h>
+#include <linux/kvm_types.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
@@ -39,10 +41,9 @@
 #include <kvm/arm_vgic.h>
 #include <kvm/arm_arch_timer.h>
 
-#define KVM_VCPU_MAX_FEATURES 2
+#define KVM_VCPU_MAX_FEATURES 3
 
-struct kvm_vcpu;
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(long ext);
 
@@ -86,7 +87,7 @@ struct kvm_cpu_context {
 	struct kvm_regs	gp_regs;
 	union {
 		u64 sys_regs[NR_SYS_REGS];
-		u32 cp15[NR_CP15_REGS];
+		u32 copro[NR_COPRO_REGS];
 	};
 };
 
@@ -101,6 +102,9 @@ struct kvm_vcpu_arch {
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
+	/* Debug state */
+	u64 debug_flags;
+
 	/* Pointer to host CPU context */
 	kvm_cpu_context_t *host_cpu_context;
 
@@ -138,7 +142,20 @@ struct kvm_vcpu_arch {
 
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 #define vcpu_sys_reg(v,r)	((v)->arch.ctxt.sys_regs[(r)])
-#define vcpu_cp15(v,r)		((v)->arch.ctxt.cp15[(r)])
+/*
+ * CP14 and CP15 live in the same array, as they are backed by the
+ * same system registers.
+ */
+#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r)])
+#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r)])
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define vcpu_cp15_64_high(v,r)	vcpu_cp15((v),(r))
+#define vcpu_cp15_64_low(v,r)	vcpu_cp15((v),(r) + 1)
+#else
+#define vcpu_cp15_64_high(v,r)	vcpu_cp15((v),(r) + 1)
+#define vcpu_cp15_64_low(v,r)	vcpu_cp15((v),(r))
+#endif
 
 struct kvm_vm_stat {
 	u32 remote_tlb_flush;
@@ -148,18 +165,15 @@ struct kvm_vcpu_stat {
 	u32 halt_wakeup;
 };
 
-struct kvm_vcpu_init;
 int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			const struct kvm_vcpu_init *init);
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
-struct kvm_one_reg;
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-struct kvm;
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
@@ -177,7 +191,7 @@ static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 }
 
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
 
@@ -200,4 +214,38 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 		     hyp_stack_ptr, vector_ptr);
 }
 
+struct vgic_sr_vectors {
+	void	*save_vgic;
+	void	*restore_vgic;
+};
+
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+	extern struct vgic_sr_vectors __vgic_sr_vectors;
+
+	switch(vgic->type)
+	{
+	case VGIC_V2:
+		__vgic_sr_vectors.save_vgic	= __save_vgic_v2_state;
+		__vgic_sr_vectors.restore_vgic	= __restore_vgic_v2_state;
+		break;
+
+#ifdef CONFIG_ARM_GIC_V3
+	case VGIC_V3:
+		__vgic_sr_vectors.save_vgic	= __save_vgic_v3_state;
+		__vgic_sr_vectors.restore_vgic	= __restore_vgic_v3_state;
+		break;
+#endif
+
+	default:
+		BUG();
+	}
+}
+
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 7f1f9408ff66..a030d163840b 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -59,10 +59,9 @@
 #define KERN_TO_HYP(kva)	((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
 
 /*
- * Align KVM with the kernel's view of physical memory. Should be
- * 40bit IPA, with PGD being 8kB aligned in the 4KB page configuration.
+ * We currently only support a 40bit IPA.
  */
-#define KVM_PHYS_SHIFT	PHYS_MASK_SHIFT
+#define KVM_PHYS_SHIFT	(40)
 #define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
 #define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)
 
@@ -93,20 +92,6 @@ void kvm_clear_hyp_idmap(void);
 #define	kvm_set_pte(ptep, pte)		set_pte(ptep, pte)
 #define	kvm_set_pmd(pmdp, pmd)		set_pmd(pmdp, pmd)
 
-static inline bool kvm_is_write_fault(unsigned long esr)
-{
-	unsigned long esr_ec = esr >> ESR_EL2_EC_SHIFT;
-
-	if (esr_ec == ESR_EL2_EC_IABT)
-		return false;
-
-	if ((esr & ESR_EL2_ISV) && !(esr & ESR_EL2_WNR))
-		return false;
-
-	return true;
-}
-
-static inline void kvm_clean_dcache_area(void *addr, size_t size) {}
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
@@ -122,11 +107,40 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	pmd_val(*pmd) |= PMD_S2_RDWR;
 }
 
+#define kvm_pgd_addr_end(addr, end)	pgd_addr_end(addr, end)
+#define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
+#define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)
+
+static inline bool kvm_page_empty(void *ptr)
+{
+	struct page *ptr_page = virt_to_page(ptr);
+	return page_count(ptr_page) == 1;
+}
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#ifndef CONFIG_ARM64_64K_PAGES
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#else
+#define kvm_pmd_table_empty(pmdp) (0)
+#endif
+#define kvm_pud_table_empty(pudp) (0)
+
+
 struct kvm;
 
-static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
-					      unsigned long size)
+#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
+{
+	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+					     unsigned long size)
 {
+	if (!vcpu_has_cache_enabled(vcpu))
+		kvm_flush_dcache_to_poc((void *)hva, size);
+
 	if (!icache_is_aliasing()) {		/* PIPT */
 		flush_icache_range(hva, hva + size);
 	} else if (!icache_is_aivivt()) {	/* non ASID-tagged VIVT */
@@ -135,8 +149,9 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, hva_t hva,
 	}
 }
 
-#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
 #define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))
 
+void stage2_flush_vm(struct kvm *kvm);
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/kvm_psci.h b/arch/arm64/include/asm/kvm_psci.h
index e301a4816355..bc39e557c56c 100644
--- a/arch/arm64/include/asm/kvm_psci.h
+++ b/arch/arm64/include/asm/kvm_psci.h
@@ -18,6 +18,10 @@
 #ifndef __ARM64_KVM_PSCI_H__
 #define __ARM64_KVM_PSCI_H__
 
-bool kvm_psci_call(struct kvm_vcpu *vcpu);
+#define KVM_ARM_PSCI_0_1	1
+#define KVM_ARM_PSCI_0_2	2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
 
 #endif /* __ARM64_KVM_PSCI_H__ */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 9dc5dc39fded..902eb708804a 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -49,13 +49,15 @@
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
 #define MODULES_END		(PAGE_OFFSET)
 #define MODULES_VADDR		(MODULES_END - SZ_64M)
-#define EARLYCON_IOBASE		(MODULES_VADDR - SZ_4M)
+#define FIXADDR_TOP		(MODULES_VADDR - SZ_2M - PAGE_SIZE)
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
 
 #ifdef CONFIG_COMPAT
 #define TASK_SIZE_32		UL(0x100000000)
 #define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
 #else
 #define TASK_SIZE		TASK_SIZE_64
 #endif /* CONFIG_COMPAT */
@@ -138,6 +140,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define virt_to_pfn(x)      __phys_to_pfn(__virt_to_phys(x))
 
 /*
  *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 2494fc01896a..c2f006c48bdb 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -22,10 +22,16 @@ typedef struct {
 	void *vdso;
 } mm_context_t;
 
+#define INIT_MM_CONTEXT(name) \
+	.context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock),
+
 #define ASID(mm)	((mm)->context.id & 0xffff)
 
 extern void paging_init(void);
 extern void setup_mm_for_reboot(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
+extern void init_mem_pgprot(void);
+/* create an identity mapping for memory (or io if map_io is true) */
+extern void create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io);
 
 #endif
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
index b0cc58a97780..13ce4cc18e26 100644
--- a/arch/arm64/include/asm/neon.h
+++ b/arch/arm64/include/asm/neon.h
@@ -8,7 +8,11 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/types.h>
+
 #define cpu_has_neon()		(1)
 
-void kernel_neon_begin(void);
+#define kernel_neon_begin()	kernel_neon_begin_partial(32)
+
+void kernel_neon_begin_partial(u32 num_regs);
 void kernel_neon_end(void);
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 46bf66628b6a..a6331e6a92b5 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -31,6 +31,15 @@
 /* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
 #define __HAVE_ARCH_GATE_AREA		1
 
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. The idmap only requires a pgd and a next level table to (section) map
+ * the kernel, while the swapper also maps the FDT and requires an additional
+ * table to map an early UART. See __create_page_tables for more information.
+ */
+#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
+#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
+
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_ARM64_64K_PAGES
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index b1d2e26c3c88..f7af66b54cb2 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -100,9 +100,9 @@
 #define PTE_HYP			PTE_USER
 
 /*
- * 40-bit physical address supported.
+ * Highest possible physical address supported.
  */
-#define PHYS_MASK_SHIFT		(40)
+#define PHYS_MASK_SHIFT		(48)
 #define PHYS_MASK		((UL(1) << PHYS_MASK_SHIFT) - 1)
 
 /*
@@ -122,7 +122,6 @@
 #define TCR_SHARED		((UL(3) << 12) | (UL(3) << 28))
 #define TCR_TG0_64K		(UL(1) << 14)
 #define TCR_TG1_64K		(UL(1) << 30)
-#define TCR_IPS_40BIT		(UL(2) << 32)
 #define TCR_ASID16		(UL(1) << 36)
 #define TCR_TBI0		(UL(1) << 37)
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index aa3917c8b623..e28747e15a36 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -52,66 +52,60 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #endif
 #define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
 
-/*
- * The pgprot_* and protection_map entries will be fixed up at runtime to
- * include the cachable and bufferable bits based on memory policy, as well as
- * any architecture dependent bits like global/ASID and SMP shared mapping
- * bits.
- */
-#define _PAGE_DEFAULT		PTE_TYPE_PAGE | PTE_AF
+#ifdef CONFIG_SMP
+#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#else
+#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF)
+#define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF)
+#endif
 
-extern pgprot_t pgprot_default;
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
 
-#define __pgprot_modify(prot,mask,bits) \
-	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+#define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
+#define PROT_SECT_NORMAL_EXEC	(PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
 
-#define _MOD_PROT(p, b)		__pgprot_modify(p, 0, b)
+#define _PAGE_DEFAULT		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
-#define PAGE_NONE		__pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE | PTE_PXN | PTE_UXN)
-#define PAGE_SHARED		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
-#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
-#define PAGE_COPY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_READONLY		_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_KERNEL		_MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 
-#define PAGE_HYP		_MOD_PROT(pgprot_default, PTE_HYP)
+#define PAGE_HYP		__pgprot(_PAGE_DEFAULT | PTE_HYP)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
-#define PAGE_S2			__pgprot_modify(pgprot_default, PTE_S2_MEMATTR_MASK, PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
+#define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN)
 
-#define __PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
-#define __PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
-#define __PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
-#define __PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define __PAGE_COPY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define __PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define __PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-
-#endif /* __ASSEMBLY__ */
-
-#define __P000  __PAGE_NONE
-#define __P001  __PAGE_READONLY
-#define __P010  __PAGE_COPY
-#define __P011  __PAGE_COPY
-#define __P100  __PAGE_READONLY_EXEC
-#define __P101  __PAGE_READONLY_EXEC
-#define __P110  __PAGE_COPY_EXEC
-#define __P111  __PAGE_COPY_EXEC
-
-#define __S000  __PAGE_NONE
-#define __S001  __PAGE_READONLY
-#define __S010  __PAGE_SHARED
-#define __S011  __PAGE_SHARED
-#define __S100  __PAGE_READONLY_EXEC
-#define __S101  __PAGE_READONLY_EXEC
-#define __S110  __PAGE_SHARED_EXEC
-#define __S111  __PAGE_SHARED_EXEC
+#define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
+#define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
+#define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
+#define PAGE_COPY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_COPY_EXEC		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
+
+#define __P000  PAGE_NONE
+#define __P001  PAGE_READONLY
+#define __P010  PAGE_COPY
+#define __P011  PAGE_COPY
+#define __P100  PAGE_READONLY_EXEC
+#define __P101  PAGE_READONLY_EXEC
+#define __P110  PAGE_COPY_EXEC
+#define __P111  PAGE_COPY_EXEC
+
+#define __S000  PAGE_NONE
+#define __S001  PAGE_READONLY
+#define __S010  PAGE_SHARED
+#define __S011  PAGE_SHARED
+#define __S100  PAGE_READONLY_EXEC
+#define __S101  PAGE_READONLY_EXEC
+#define __S110  PAGE_SHARED_EXEC
+#define __S111  PAGE_SHARED_EXEC
 
-#ifndef __ASSEMBLY__
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -145,6 +139,8 @@ extern struct page *empty_zero_page;
 
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -191,6 +187,15 @@ static inline pte_t pte_mkspecial(pte_t pte)
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
+
+	/*
+	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
+	 * or update_mmu_cache() have the necessary barriers.
+	 */
+	if (pte_valid_not_user(pte)) {
+		dsb(ishst);
+		isb();
+	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
@@ -199,7 +204,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
 	if (pte_valid_user(pte)) {
-		if (pte_exec(pte))
+		if (!pte_special(pte) && pte_exec(pte))
 			__sync_icache_dcache(pte, addr);
 		if (pte_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
@@ -227,36 +232,36 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
-/*
- * Software PMD bits for THP
- */
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+	return __pte(pmd_val(pmd));
+}
 
-#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
-#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 57)
+static inline pmd_t pte_pmd(pte_t pte)
+{
+	return __pmd(pte_val(pte));
+}
 
 /*
  * THP definitions.
  */
-#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
-
-#define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#define pmd_trans_splitting(pmd)	pte_special(pmd_pte(pmd))
 #endif
 
-#define PMD_BIT_FUNC(fn,op) \
-static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+#define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
+#define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) &= ~PMD_TYPE_MASK))
 
-PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
-PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
-PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
-PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)		pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
 
@@ -266,31 +271,23 @@ PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
-{
-	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_PXN | PMD_SECT_UXN |
-			      PMD_SECT_RDONLY | PMD_SECT_PROT_NONE |
-			      PMD_SECT_VALID;
-	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
-	return pmd;
-}
-
-#define set_pmd_at(mm, addr, pmdp, pmd)	set_pmd(pmdp, pmd)
+#define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
 
 static inline int has_transparent_hugepage(void)
 {
 	return 1;
 }
 
+#define __pgprot_modify(prot,mask,bits) \
+	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+
 /*
  * Mark the prot value as uncacheable and unbufferable.
  */
 #define pgprot_noncached(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
 #define pgprot_writecombine(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
-#define pgprot_dmacoherent(prot) \
-	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -310,7 +307,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
-	dsb();
+	dsb(ishst);
+	isb();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -340,7 +338,8 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	*pudp = pud;
-	dsb();
+	dsb(ishst);
+	isb();
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -383,12 +382,14 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	return pte;
 }
 
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+	return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
-#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
-
 /*
  * Encode and decode a swap entry:
  *	bits 0-1:	present (must be zero)
@@ -412,7 +413,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
 /*
  * Ensure that there are not more swap files than can be encoded in the kernel
- * the PTEs.
+ * PTEs.
  */
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
 
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 0e7fa4963735..a429b5940be2 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -68,6 +68,7 @@
 
 /* Architecturally defined mapping between AArch32 and AArch64 registers */
 #define compat_usr(x)	regs[(x)]
+#define compat_fp	regs[11]
 #define compat_sp	regs[13]
 #define compat_lr	regs[14]
 #define compat_sp_hyp	regs[15]
@@ -132,7 +133,12 @@ struct pt_regs {
 	(!((regs)->pstate & PSR_F_BIT))
 
 #define user_stack_pointer(regs) \
-	((regs)->sp)
+	(!compat_user_mode(regs)) ? ((regs)->sp) : ((regs)->compat_sp)
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+	return regs->regs[0];
+}
 
 /*
  * Are the current registers suitable for user mode? (used to maintain
@@ -164,7 +170,7 @@ static inline int valid_user_regs(struct user_pt_regs *regs)
 	return 0;
 }
 
-#define instruction_pointer(regs)	(regs)->pc
+#define instruction_pointer(regs)	((unsigned long)(regs)->pc)
 
 #ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index e9c149c042e0..456d67c1f0fa 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -21,6 +21,7 @@ struct sleep_save_sp {
 	phys_addr_t save_ptr_stash_phys;
 };
 
+extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
 extern void cpu_resume(void);
 extern int cpu_suspend(unsigned long);
 
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 70ba9d4ee978..383771eb0b87 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -18,6 +18,7 @@
 
 #include <linux/err.h>
 
+extern const void *sys_call_table[];
 
 static inline int syscall_get_nr(struct task_struct *task,
 				 struct pt_regs *regs)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
new file mode 100644
index 000000000000..5c89df0acbcb
--- /dev/null
+++ b/arch/arm64/include/asm/sysreg.h
@@ -0,0 +1,60 @@
+/*
+ * Macros for accessing system registers with older binutils.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_SYSREG_H
+#define __ASM_SYSREG_H
+
+#define sys_reg(op0, op1, crn, crm, op2) \
+	((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+
+#ifdef __ASSEMBLY__
+
+	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+	.equ	__reg_num_x\num, \num
+	.endr
+	.equ	__reg_num_xzr, 31
+
+	.macro	mrs_s, rt, sreg
+	.inst	0xd5300000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+	.macro	msr_s, sreg, rt
+	.inst	0xd5100000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+#else
+
+asm(
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
+"	.equ	__reg_num_x\\num, \\num\n"
+"	.endr\n"
+"	.equ	__reg_num_xzr, 31\n"
+"\n"
+"	.macro	mrs_s, rt, sreg\n"
+"	.inst	0xd5300000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+"\n"
+"	.macro	msr_s, sreg, rt\n"
+"	.inst	0xd5100000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+);
+
+#endif
+
+#endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 720e70b66ffd..8da65c37193d 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -91,6 +91,9 @@ static inline struct thread_info *current_thread_info(void)
 /*
  * thread information flags:
  *  TIF_SYSCALL_TRACE	- syscall trace active
+ *  TIF_SYSCALL_TRACEPOINT - syscall tracepoint for ftrace
+ *  TIF_SYSCALL_AUDIT	- syscall auditing
+ *  TIF_SECOMP		- syscall secure computing
  *  TIF_SIGPENDING	- signal pending
  *  TIF_NEED_RESCHED	- rescheduling necessary
  *  TIF_NOTIFY_RESUME	- callback before returning to user
@@ -100,7 +103,12 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SIGPENDING		0
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
+#define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
+#define TIF_NOHZ		7
 #define TIF_SYSCALL_TRACE	8
+#define TIF_SYSCALL_AUDIT	9
+#define TIF_SYSCALL_TRACEPOINT	10
+#define TIF_SECCOMP		11
 #define TIF_POLLING_NRFLAG	16
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_FREEZE		19
@@ -112,10 +120,20 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_NOHZ		(1 << TIF_NOHZ)
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_FOREIGN_FPSTATE	(1 << TIF_FOREIGN_FPSTATE)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME)
+				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
+
+#define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
+				 _TIF_NOHZ)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_THREAD_INFO_H */
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 8b482035cfc2..3796ea6bb734 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -72,9 +72,9 @@ extern struct cpu_tlb_fns cpu_tlb;
  */
 static inline void flush_tlb_all(void)
 {
-	dsb();
+	dsb(ishst);
 	asm("tlbi	vmalle1is");
-	dsb();
+	dsb(ish);
 	isb();
 }
 
@@ -82,9 +82,9 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 {
 	unsigned long asid = (unsigned long)ASID(mm) << 48;
 
-	dsb();
+	dsb(ishst);
 	asm("tlbi	aside1is, %0" : : "r" (asid));
-	dsb();
+	dsb(ish);
 }
 
 static inline void flush_tlb_page(struct vm_area_struct *vma,
@@ -93,16 +93,37 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 	unsigned long addr = uaddr >> 12 |
 		((unsigned long)ASID(vma->vm_mm) << 48);
 
-	dsb();
+	dsb(ishst);
 	asm("tlbi	vae1is, %0" : : "r" (addr));
-	dsb();
+	dsb(ish);
 }
 
-/*
- * Convert calls to our calling convention.
- */
-#define flush_tlb_range(vma,start,end)	__cpu_flush_user_tlb_range(start,end,vma)
-#define flush_tlb_kernel_range(s,e)	__cpu_flush_kern_tlb_range(s,e)
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+					unsigned long start, unsigned long end)
+{
+	unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
+	unsigned long addr;
+	start = asid | (start >> 12);
+	end = asid | (end >> 12);
+
+	dsb(ishst);
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+		asm("tlbi vae1is, %0" : : "r"(addr));
+	dsb(ish);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+	start >>= 12;
+	end >>= 12;
+
+	dsb(ishst);
+	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+		asm("tlbi vaae1is, %0" : : "r"(addr));
+	dsb(ish);
+	isb();
+}
 
 /*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
@@ -111,10 +132,10 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep)
 {
 	/*
-	 * set_pte() does not have a DSB, so make sure that the page table
-	 * write is visible.
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
 	 */
-	dsb();
+	dsb(ishst);
 }
 
 #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 000000000000..e0171b393a14
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,70 @@
+#ifndef __ASM_TOPOLOGY_H
+#define __ASM_TOPOLOGY_H
+
+#ifdef CONFIG_SMP
+
+#include <linux/cpumask.h>
+
+struct cpu_topology {
+	int thread_id;
+	int core_id;
+	int cluster_id;
+	cpumask_t thread_sibling;
+	cpumask_t core_sibling;
+};
+
+extern struct cpu_topology cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_id)
+#define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()	(cpu_topology[0].cluster_id != -1)
+#define smt_capable()	(cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+
+#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) {				\
+	.min_interval		= 1,					\
+	.max_interval		= 4,					\
+	.busy_factor		= 64,					\
+	.imbalance_pct		= 125,					\
+	.cache_nice_tries	= 1,					\
+	.busy_idx		= 2,					\
+	.idle_idx		= 1,					\
+	.newidle_idx		= 0,					\
+	.wake_idx		= 0,					\
+	.forkexec_idx		= 0,					\
+									\
+	.flags			= 0*SD_LOAD_BALANCE			\
+				| 1*SD_BALANCE_NEWIDLE			\
+				| 1*SD_BALANCE_EXEC			\
+				| 1*SD_BALANCE_FORK			\
+				| 0*SD_BALANCE_WAKE			\
+				| 1*SD_WAKE_AFFINE			\
+				| 0*SD_SHARE_CPUPOWER			\
+				| 0*SD_SHARE_PKG_RESOURCES		\
+				| 0*SD_SERIALIZE			\
+				,					\
+	.last_balance		 = jiffies,				\
+	.balance_interval	= 1,					\
+}
+#endif
+#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 82ce217e94cf..c335479c2638 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -28,3 +28,5 @@
 #endif
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
+
+#define NR_syscalls (__NR_syscalls)
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index bb8eb8a78e67..faa0e1ce59df 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -404,7 +404,7 @@ __SYSCALL(379, sys_finit_module)
 __SYSCALL(380, sys_sched_setattr)
 __SYSCALL(381, sys_sched_getattr)
 
-#define __NR_compat_syscalls		379
+#define __NR_compat_syscalls		382
 
 /*
  * Compat syscall numbers used by the AArch64 kernel.
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 130e2be952cf..290fb6690b33 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -63,6 +63,10 @@ static inline bool is_hyp_mode_mismatched(void)
 	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
 }
 
+/* The section containing the hypervisor text */
+extern char __hyp_text_start[];
+extern char __hyp_text_end[];
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* ! __ASM__VIRT_H */
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index e4b78bdca19e..942376d37d22 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -9,6 +9,7 @@ header-y += byteorder.h
 header-y += fcntl.h
 header-y += hwcap.h
 header-y += kvm_para.h
+header-y += perf_regs.h
 header-y += param.h
 header-y += ptrace.h
 header-y += setup.h
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index eaf54a30bedc..8e38878c87c6 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -31,11 +31,13 @@
 #define KVM_NR_SPSR	5
 
 #ifndef __ASSEMBLY__
+#include <linux/psci.h>
 #include <asm/types.h>
 #include <asm/ptrace.h>
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -56,8 +58,9 @@ struct kvm_regs {
 #define KVM_ARM_TARGET_FOUNDATION_V8	1
 #define KVM_ARM_TARGET_CORTEX_A57	2
 #define KVM_ARM_TARGET_XGENE_POTENZA	3
+#define KVM_ARM_TARGET_CORTEX_A53	4
 
-#define KVM_ARM_NUM_TARGETS		4
+#define KVM_ARM_NUM_TARGETS		5
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
@@ -77,6 +80,7 @@ struct kvm_regs {
 
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
+#define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -156,6 +160,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
@@ -186,10 +191,10 @@ struct kvm_arch_memory_slot {
 #define KVM_PSCI_FN_CPU_ON		KVM_PSCI_FN(2)
 #define KVM_PSCI_FN_MIGRATE		KVM_PSCI_FN(3)
 
-#define KVM_PSCI_RET_SUCCESS		0
-#define KVM_PSCI_RET_NI			((unsigned long)-1)
-#define KVM_PSCI_RET_INVAL		((unsigned long)-2)
-#define KVM_PSCI_RET_DENIED		((unsigned long)-3)
+#define KVM_PSCI_RET_SUCCESS		PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI			PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL		PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED		PSCI_RET_DENIED
 
 #endif
 
diff --git a/arch/arm64/include/uapi/asm/perf_regs.h b/arch/arm64/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000000..172b8317ee49
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM64_PERF_REGS_H
+#define _ASM_ARM64_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM64_X0,
+	PERF_REG_ARM64_X1,
+	PERF_REG_ARM64_X2,
+	PERF_REG_ARM64_X3,
+	PERF_REG_ARM64_X4,
+	PERF_REG_ARM64_X5,
+	PERF_REG_ARM64_X6,
+	PERF_REG_ARM64_X7,
+	PERF_REG_ARM64_X8,
+	PERF_REG_ARM64_X9,
+	PERF_REG_ARM64_X10,
+	PERF_REG_ARM64_X11,
+	PERF_REG_ARM64_X12,
+	PERF_REG_ARM64_X13,
+	PERF_REG_ARM64_X14,
+	PERF_REG_ARM64_X15,
+	PERF_REG_ARM64_X16,
+	PERF_REG_ARM64_X17,
+	PERF_REG_ARM64_X18,
+	PERF_REG_ARM64_X19,
+	PERF_REG_ARM64_X20,
+	PERF_REG_ARM64_X21,
+	PERF_REG_ARM64_X22,
+	PERF_REG_ARM64_X23,
+	PERF_REG_ARM64_X24,
+	PERF_REG_ARM64_X25,
+	PERF_REG_ARM64_X26,
+	PERF_REG_ARM64_X27,
+	PERF_REG_ARM64_X28,
+	PERF_REG_ARM64_X29,
+	PERF_REG_ARM64_LR,
+	PERF_REG_ARM64_SP,
+	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
+};
+#endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 57c9ffe9a285..376e18e79b9a 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -7,21 +7,29 @@ AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_efi-stub.o 	:= -DTEXT_OFFSET=$(TEXT_OFFSET) \
 			   -I$(src)/../../../scripts/dtc/libfdt
 
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_return_address.o = -pg
+
 # Object file lists.
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o
+			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
+arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
+arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o topology.o
 arm64-obj-$(CONFIG_SMP)			+= smp.o smp_spin_table.o
+arm64-obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
-arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
+arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)	+= sleep.o suspend.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
+arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o
 
 obj-y					+= $(arm64-obj-y) vdso/
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 338b568cd8ae..7f0512feaa13 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -56,3 +56,7 @@ EXPORT_SYMBOL(clear_bit);
 EXPORT_SYMBOL(test_and_clear_bit);
 EXPORT_SYMBOL(change_bit);
 EXPORT_SYMBOL(test_and_change_bit);
+
+#ifdef CONFIG_FUNCTION_TRACER
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 646f888387cd..9a9fce090d58 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -120,6 +120,7 @@ int main(void)
   DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
   DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
   DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
+  DEFINE(VCPU_DEBUG_FLAGS,	offsetof(struct kvm_vcpu, arch.debug_flags));
   DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
   DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
@@ -129,13 +130,24 @@ int main(void)
   DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
   DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_CPU_HCR,		offsetof(struct vgic_cpu, vgic_hcr));
-  DEFINE(VGIC_CPU_VMCR,		offsetof(struct vgic_cpu, vgic_vmcr));
-  DEFINE(VGIC_CPU_MISR,		offsetof(struct vgic_cpu, vgic_misr));
-  DEFINE(VGIC_CPU_EISR,		offsetof(struct vgic_cpu, vgic_eisr));
-  DEFINE(VGIC_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_elrsr));
-  DEFINE(VGIC_CPU_APR,		offsetof(struct vgic_cpu, vgic_apr));
-  DEFINE(VGIC_CPU_LR,		offsetof(struct vgic_cpu, vgic_lr));
+  DEFINE(VGIC_SAVE_FN,		offsetof(struct vgic_sr_vectors, save_vgic));
+  DEFINE(VGIC_RESTORE_FN,	offsetof(struct vgic_sr_vectors, restore_vgic));
+  DEFINE(VGIC_SR_VECTOR_SZ,	sizeof(struct vgic_sr_vectors));
+  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
+  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
+  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
+  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
+  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
+  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
+  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
+  DEFINE(VGIC_V3_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
+  DEFINE(VGIC_V3_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
+  DEFINE(VGIC_V3_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_misr));
+  DEFINE(VGIC_V3_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_eisr));
+  DEFINE(VGIC_V3_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v3.vgic_elrsr));
+  DEFINE(VGIC_V3_CPU_AP0R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap0r));
+  DEFINE(VGIC_V3_CPU_AP1R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap1r));
+  DEFINE(VGIC_V3_CPU_LR,	offsetof(struct vgic_cpu, vgic_v3.vgic_lr));
   DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
   DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
   DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 636ba8b6240b..6c6a2e56a8e3 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -30,15 +30,6 @@
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
 
-/* Low-level stepping controls. */
-#define DBG_MDSCR_SS		(1 << 0)
-#define DBG_SPSR_SS		(1 << 21)
-
-/* MDSCR_EL1 enabling bits */
-#define DBG_MDSCR_KDE		(1 << 13)
-#define DBG_MDSCR_MDE		(1 << 15)
-#define DBG_MDSCR_MASK		~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
-
 /* Determine debug architecture. */
 u8 debug_monitors_arch(void)
 {
@@ -138,6 +129,7 @@ static void clear_os_lock(void *unused)
 {
 	asm volatile("msr oslar_el1, %0" : : "r" (0));
 	isb();
+	local_dbg_enable();
 }
 
 static int os_lock_notify(struct notifier_block *self,
@@ -314,9 +306,6 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 	if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
 		return 0;
 
-	pr_warn("unexpected brk exception at %lx, esr=0x%x\n",
-			(long)instruction_pointer(regs), esr);
-
 	if (!user_mode(regs))
 		return -EFAULT;
 
diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c
index fbb6e1843659..ffbbdde7aba1 100644
--- a/arch/arm64/kernel/early_printk.c
+++ b/arch/arm64/kernel/early_printk.c
@@ -26,6 +26,8 @@
 #include <linux/amba/serial.h>
 #include <linux/serial_reg.h>
 
+#include <asm/fixmap.h>
+
 static void __iomem *early_base;
 static void (*printch)(char ch);
 
@@ -141,8 +143,10 @@ static int __init setup_early_printk(char *buf)
 	}
 	/* no options parsing yet */
 
-	if (paddr)
-		early_base = early_io_map(paddr, EARLYCON_IOBASE);
+	if (paddr) {
+		set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr);
+		early_base = (void __iomem *)fix_to_virt(FIX_EARLYCON_MEM_BASE);
+	}
 
 	printch = match->printch;
 	early_console = &early_console_dev;
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index 6a27cd6dbfa6..d358ccacfc00 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -41,3 +41,27 @@ ENTRY(fpsimd_load_state)
 	fpsimd_restore x0, 8
 	ret
 ENDPROC(fpsimd_load_state)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Save the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_save_partial_state)
+	fpsimd_save_partial x0, 1, 8, 9
+	ret
+ENDPROC(fpsimd_load_partial_state)
+
+/*
+ * Load the bottom n FP registers.
+ *
+ * x0 - pointer to struct fpsimd_partial_state
+ */
+ENTRY(fpsimd_load_partial_state)
+	fpsimd_restore_partial x0, 8, 9
+	ret
+ENDPROC(fpsimd_load_partial_state)
+
+#endif
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
new file mode 100644
index 000000000000..b051871f2965
--- /dev/null
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -0,0 +1,218 @@
+/*
+ * arch/arm64/kernel/entry-ftrace.S
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+/*
+ * Gcc with -pg will put the following code in the beginning of each function:
+ *      mov x0, x30
+ *      bl _mcount
+ *	[function's body ...]
+ * "bl _mcount" may be replaced to "bl ftrace_caller" or NOP if dynamic
+ * ftrace is enabled.
+ *
+ * Please note that x0 as an argument will not be used here because we can
+ * get lr(x30) of instrumented function at any time by winding up call stack
+ * as long as the kernel is compiled without -fomit-frame-pointer.
+ * (or CONFIG_FRAME_POINTER, this is forced on arm64)
+ *
+ * stack layout after mcount_enter in _mcount():
+ *
+ * current sp/fp =>  0:+-----+
+ * in _mcount()        | x29 | -> instrumented function's fp
+ *                     +-----+
+ *                     | x30 | -> _mcount()'s lr (= instrumented function's pc)
+ * old sp       => +16:+-----+
+ * when instrumented   |     |
+ * function calls      | ... |
+ * _mcount()           |     |
+ *                     |     |
+ * instrumented => +xx:+-----+
+ * function's fp       | x29 | -> parent's fp
+ *                     +-----+
+ *                     | x30 | -> instrumented function's lr (= parent's pc)
+ *                     +-----+
+ *                     | ... |
+ */
+
+	.macro mcount_enter
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+	.endm
+
+	.macro mcount_exit
+	ldp	x29, x30, [sp], #16
+	ret
+	.endm
+
+	.macro mcount_adjust_addr rd, rn
+	sub	\rd, \rn, #AARCH64_INSN_SIZE
+	.endm
+
+	/* for instrumented function's parent */
+	.macro mcount_get_parent_fp reg
+	ldr	\reg, [x29]
+	ldr	\reg, [\reg]
+	.endm
+
+	/* for instrumented function */
+	.macro mcount_get_pc0 reg
+	mcount_adjust_addr	\reg, x30
+	.endm
+
+	.macro mcount_get_pc reg
+	ldr	\reg, [x29, #8]
+	mcount_adjust_addr	\reg, \reg
+	.endm
+
+	.macro mcount_get_lr reg
+	ldr	\reg, [x29]
+	ldr	\reg, [\reg, #8]
+	mcount_adjust_addr	\reg, \reg
+	.endm
+
+	.macro mcount_get_lr_addr reg
+	ldr	\reg, [x29]
+	add	\reg, \reg, #8
+	.endm
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+/*
+ * void _mcount(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function makes calls, if enabled, to:
+ *     - tracer function to probe instrumented function's entry,
+ *     - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(_mcount)
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	ldr	x0, =ftrace_trace_stop
+	ldr	x0, [x0]		// if ftrace_trace_stop
+	ret				//   return;
+#endif
+	mcount_enter
+
+	ldr	x0, =ftrace_trace_function
+	ldr	x2, [x0]
+	adr	x0, ftrace_stub
+	cmp	x0, x2			// if (ftrace_trace_function
+	b.eq	skip_ftrace_call	//     != ftrace_stub) {
+
+	mcount_get_pc	x0		//       function's pc
+	mcount_get_lr	x1		//       function's lr (= parent's pc)
+	blr	x2			//   (*ftrace_trace_function)(pc, lr);
+
+#ifndef CONFIG_FUNCTION_GRAPH_TRACER
+skip_ftrace_call:			//   return;
+	mcount_exit			// }
+#else
+	mcount_exit			//   return;
+					// }
+skip_ftrace_call:
+	ldr	x1, =ftrace_graph_return
+	ldr	x2, [x1]		//   if ((ftrace_graph_return
+	cmp	x0, x2			//        != ftrace_stub)
+	b.ne	ftrace_graph_caller
+
+	ldr	x1, =ftrace_graph_entry	//     || (ftrace_graph_entry
+	ldr	x2, [x1]		//        != ftrace_graph_entry_stub))
+	ldr	x0, =ftrace_graph_entry_stub
+	cmp	x0, x2
+	b.ne	ftrace_graph_caller	//     ftrace_graph_caller();
+
+	mcount_exit
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+ENDPROC(_mcount)
+
+#else /* CONFIG_DYNAMIC_FTRACE */
+/*
+ * _mcount() is used to build the kernel with -pg option, but all the branch
+ * instructions to _mcount() are replaced to NOP initially at kernel start up,
+ * and later on, NOP to branch to ftrace_caller() when enabled or branch to
+ * NOP when disabled per-function base.
+ */
+ENTRY(_mcount)
+	ret
+ENDPROC(_mcount)
+
+/*
+ * void ftrace_caller(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function is a counterpart of _mcount() in 'static' ftrace, and
+ * makes calls to:
+ *     - tracer function to probe instrumented function's entry,
+ *     - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(ftrace_caller)
+	mcount_enter
+
+	mcount_get_pc0	x0		//     function's pc
+	mcount_get_lr	x1		//     function's lr
+
+	.global ftrace_call
+ftrace_call:				// tracer(pc, lr);
+	nop				// This will be replaced with "bl xxx"
+					// where xxx can be any kind of tracer.
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.global ftrace_graph_call
+ftrace_graph_call:			// ftrace_graph_caller();
+	nop				// If enabled, this will be replaced
+					// "b ftrace_graph_caller"
+#endif
+
+	mcount_exit
+ENDPROC(ftrace_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(ftrace_stub)
+	ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * void ftrace_graph_caller(void)
+ *
+ * Called from _mcount() or ftrace_caller() when function_graph tracer is
+ * selected.
+ * This function w/ prepare_ftrace_return() fakes link register's value on
+ * the call stack in order to intercept instrumented function's return path
+ * and run return_to_handler() later on its exit.
+ */
+ENTRY(ftrace_graph_caller)
+	mcount_get_lr_addr	  x0	//     pointer to function's saved lr
+	mcount_get_pc		  x1	//     function's pc
+	mcount_get_parent_fp	  x2	//     parent's fp
+	bl	prepare_ftrace_return	// prepare_ftrace_return(&lr, pc, fp)
+
+	mcount_exit
+ENDPROC(ftrace_graph_caller)
+
+/*
+ * void return_to_handler(void)
+ *
+ * Run ftrace_return_to_handler() before going back to parent.
+ * @fp is checked against the value passed by ftrace_graph_caller()
+ * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ */
+ENTRY(return_to_handler)
+	str	x0, [sp, #-16]!
+	mov	x0, x29			//     parent's fp
+	bl	ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
+	mov	x30, x0			// restore the original return address
+	ldr	x0, [sp], #16
+	ret
+END(return_to_handler)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 39ac630d83de..a010e3af4597 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -30,6 +30,32 @@
 #include <asm/unistd32.h>
 
 /*
+ * Context tracking subsystem.  Used to instrument transitions
+ * between user and kernel mode.
+ */
+	.macro ct_user_exit, syscall = 0
+#ifdef CONFIG_CONTEXT_TRACKING
+	bl	context_tracking_user_exit
+	.if \syscall == 1
+	/*
+	 * Save/restore needed during syscalls.  Restore syscall arguments from
+	 * the values already saved on stack during kernel_entry.
+	 */
+	ldp	x0, x1, [sp]
+	ldp	x2, x3, [sp, #S_X2]
+	ldp	x4, x5, [sp, #S_X4]
+	ldp	x6, x7, [sp, #S_X6]
+	.endif
+#endif
+	.endm
+
+	.macro ct_user_enter
+#ifdef CONFIG_CONTEXT_TRACKING
+	bl	context_tracking_user_enter
+#endif
+	.endm
+
+/*
  * Bad Abort numbers
  *-----------------
  */
@@ -88,6 +114,7 @@
 	.macro	kernel_exit, el, ret = 0
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
+	ct_user_enter
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	.endif
 	.if	\ret
@@ -275,7 +302,6 @@ el1_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	mrs	x0, far_el1
-	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
 el1_undef:
@@ -349,7 +375,6 @@ el0_sync:
 	lsr	x24, x25, #ESR_EL1_EC_SHIFT	// exception class
 	cmp	x24, #ESR_EL1_EC_SVC64		// SVC in 64-bit state
 	b.eq	el0_svc
-	adr	lr, ret_from_exception
 	cmp	x24, #ESR_EL1_EC_DABT_EL0	// data abort in EL0
 	b.eq	el0_da
 	cmp	x24, #ESR_EL1_EC_IABT_EL0	// instruction abort in EL0
@@ -378,7 +403,6 @@ el0_sync_compat:
 	lsr	x24, x25, #ESR_EL1_EC_SHIFT	// exception class
 	cmp	x24, #ESR_EL1_EC_SVC32		// SVC in 32-bit state
 	b.eq	el0_svc_compat
-	adr	lr, ret_from_exception
 	cmp	x24, #ESR_EL1_EC_DABT_EL0	// data abort in EL0
 	b.eq	el0_da
 	cmp	x24, #ESR_EL1_EC_IABT_EL0	// instruction abort in EL0
@@ -421,78 +445,94 @@ el0_da:
 	/*
 	 * Data abort handling
 	 */
-	mrs	x0, far_el1
-	bic	x0, x0, #(0xff << 56)
+	mrs	x26, far_el1
 	disable_step x1
 	isb
 	enable_dbg
 	// enable interrupts before calling the main handler
 	enable_irq
+	ct_user_exit
+	bic	x0, x26, #(0xff << 56)
 	mov	x1, x25
 	mov	x2, sp
+	adr	lr, ret_from_exception
 	b	do_mem_abort
 el0_ia:
 	/*
 	 * Instruction abort handling
 	 */
-	mrs	x0, far_el1
+	mrs	x26, far_el1
 	disable_step x1
 	isb
 	enable_dbg
 	// enable interrupts before calling the main handler
 	enable_irq
+	ct_user_exit
+	mov	x0, x26
 	orr	x1, x25, #1 << 24		// use reserved ISS bit for instruction aborts
 	mov	x2, sp
+	adr	lr, ret_from_exception
 	b	do_mem_abort
 el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
+	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
+	adr	lr, ret_from_exception
 	b	do_fpsimd_acc
 el0_fpsimd_exc:
 	/*
 	 * Floating Point or Advanced SIMD exception
 	 */
+	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
+	adr	lr, ret_from_exception
 	b	do_fpsimd_exc
 el0_sp_pc:
 	/*
 	 * Stack or PC alignment exception handling
 	 */
-	mrs	x0, far_el1
+	mrs	x26, far_el1
 	disable_step x1
 	isb
 	enable_dbg
 	// enable interrupts before calling the main handler
 	enable_irq
+	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
+	adr	lr, ret_from_exception
 	b	do_sp_pc_abort
 el0_undef:
 	/*
 	 * Undefined instruction
 	 */
-	mov	x0, sp
 	// enable interrupts before calling the main handler
+	ct_user_exit
 	enable_irq
+	mov	x0, sp
+	adr	lr, ret_from_exception
 	b	do_undefinstr
 el0_dbg:
 	/*
 	 * Debug exception handling
 	 */
 	tbnz	x24, #0, el0_inv		// EL0 only
+	ct_user_exit
 	mrs	x0, far_el1
 	disable_step x1
 	mov	x1, x25
 	mov	x2, sp
 	b	do_debug_exception
 el0_inv:
+	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mrs	x2, esr_el1
+	adr	lr, ret_from_exception
 	b	bad_mode
 ENDPROC(el0_sync)
 
@@ -507,6 +547,7 @@ el0_irq_naked:
 	bl	trace_hardirqs_off
 #endif
 
+	ct_user_exit
 	irq_handler
 	get_thread_info tsk
 
@@ -576,7 +617,7 @@ fast_work_pending:
 	str	x0, [sp, #S_X0]			// returned x0
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
-	/* TIF_SIGPENDING or TIF_NOTIFY_RESUME case */
+	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
 	ldr	x2, [sp, #S_PSTATE]
 	mov	x0, sp				// 'regs'
 	tst	x2, #PSR_MODE_MASK		// user mode regs?
@@ -629,10 +670,12 @@ el0_svc_naked:					// compat entry point
 	isb
 	enable_dbg
 	enable_irq
+	ct_user_exit 1
 
 	get_thread_info tsk
-	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall tracing
-	tbnz	x16, #TIF_SYSCALL_TRACE, __sys_trace // are we tracing syscalls?
+	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
+	tst	x16, #_TIF_SYSCALL_WORK
+	b.ne	__sys_trace
 	adr	lr, ret_fast_syscall		// return address
 	cmp     scno, sc_nr                     // check upper syscall limit
 	b.hs	ni_sys
@@ -648,9 +691,8 @@ ENDPROC(el0_svc)
 	 * switches, and waiting for our parent to respond.
 	 */
 __sys_trace:
-	mov	x1, sp
-	mov	w0, #0				// trace entry
-	bl	syscall_trace
+	mov	x0, sp
+	bl	syscall_trace_enter
 	adr	lr, __sys_trace_return		// return address
 	uxtw	scno, w0			// syscall number (possibly new)
 	mov	x1, sp				// pointer to regs
@@ -665,9 +707,8 @@ __sys_trace:
 
 __sys_trace_return:
 	str	x0, [sp]			// save returned x0
-	mov	x1, sp
-	mov	w0, #1				// trace exit
-	bl	syscall_trace
+	mov	x0, sp
+	bl	syscall_trace_exit
 	b	ret_to_user
 
 /*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 4aef42a04bdc..ad8aebb1cdef 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -35,6 +35,60 @@
 #define FPEXC_IDF	(1 << 7)
 
 /*
+ * In order to reduce the number of times the FPSIMD state is needlessly saved
+ * and restored, we need to keep track of two things:
+ * (a) for each task, we need to remember which CPU was the last one to have
+ *     the task's FPSIMD state loaded into its FPSIMD registers;
+ * (b) for each CPU, we need to remember which task's userland FPSIMD state has
+ *     been loaded into its FPSIMD registers most recently, or whether it has
+ *     been used to perform kernel mode NEON in the meantime.
+ *
+ * For (a), we add a 'cpu' field to struct fpsimd_state, which gets updated to
+ * the id of the current CPU everytime the state is loaded onto a CPU. For (b),
+ * we add the per-cpu variable 'fpsimd_last_state' (below), which contains the
+ * address of the userland FPSIMD state of the task that was loaded onto the CPU
+ * the most recently, or NULL if kernel mode NEON has been performed after that.
+ *
+ * With this in place, we no longer have to restore the next FPSIMD state right
+ * when switching between tasks. Instead, we can defer this check to userland
+ * resume, at which time we verify whether the CPU's fpsimd_last_state and the
+ * task's fpsimd_state.cpu are still mutually in sync. If this is the case, we
+ * can omit the FPSIMD restore.
+ *
+ * As an optimization, we use the thread_info flag TIF_FOREIGN_FPSTATE to
+ * indicate whether or not the userland FPSIMD state of the current task is
+ * present in the registers. The flag is set unless the FPSIMD registers of this
+ * CPU currently contain the most recent userland FPSIMD state of the current
+ * task.
+ *
+ * For a certain task, the sequence may look something like this:
+ * - the task gets scheduled in; if both the task's fpsimd_state.cpu field
+ *   contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
+ *   variable points to the task's fpsimd_state, the TIF_FOREIGN_FPSTATE flag is
+ *   cleared, otherwise it is set;
+ *
+ * - the task returns to userland; if TIF_FOREIGN_FPSTATE is set, the task's
+ *   userland FPSIMD state is copied from memory to the registers, the task's
+ *   fpsimd_state.cpu field is set to the id of the current CPU, the current
+ *   CPU's fpsimd_last_state pointer is set to this task's fpsimd_state and the
+ *   TIF_FOREIGN_FPSTATE flag is cleared;
+ *
+ * - the task executes an ordinary syscall; upon return to userland, the
+ *   TIF_FOREIGN_FPSTATE flag will still be cleared, so no FPSIMD state is
+ *   restored;
+ *
+ * - the task executes a syscall which executes some NEON instructions; this is
+ *   preceded by a call to kernel_neon_begin(), which copies the task's FPSIMD
+ *   register contents to memory, clears the fpsimd_last_state per-cpu variable
+ *   and sets the TIF_FOREIGN_FPSTATE flag;
+ *
+ * - the task gets preempted after kernel_neon_end() is called; as we have not
+ *   returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
+ *   whatever is in the FPSIMD registers is not saved to memory, but discarded.
+ */
+static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state);
+
+/*
  * Trapped FP/ASIMD access.
  */
 void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
@@ -72,43 +126,137 @@ void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 
 void fpsimd_thread_switch(struct task_struct *next)
 {
-	/* check if not kernel threads */
-	if (current->mm)
+	/*
+	 * Save the current FPSIMD state to memory, but only if whatever is in
+	 * the registers is in fact the most recent userland FPSIMD state of
+	 * 'current'.
+	 */
+	if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
 		fpsimd_save_state(&current->thread.fpsimd_state);
-	if (next->mm)
-		fpsimd_load_state(&next->thread.fpsimd_state);
+
+	if (next->mm) {
+		/*
+		 * If we are switching to a task whose most recent userland
+		 * FPSIMD state is already in the registers of *this* cpu,
+		 * we can skip loading the state from memory. Otherwise, set
+		 * the TIF_FOREIGN_FPSTATE flag so the state will be loaded
+		 * upon the next return to userland.
+		 */
+		struct fpsimd_state *st = &next->thread.fpsimd_state;
+
+		if (__this_cpu_read(fpsimd_last_state) == st
+		    && st->cpu == smp_processor_id())
+			clear_ti_thread_flag(task_thread_info(next),
+					     TIF_FOREIGN_FPSTATE);
+		else
+			set_ti_thread_flag(task_thread_info(next),
+					   TIF_FOREIGN_FPSTATE);
+	}
 }
 
 void fpsimd_flush_thread(void)
 {
-	preempt_disable();
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
-	fpsimd_load_state(&current->thread.fpsimd_state);
+	set_thread_flag(TIF_FOREIGN_FPSTATE);
+}
+
+/*
+ * Save the userland FPSIMD state of 'current' to memory, but only if the state
+ * currently held in the registers does in fact belong to 'current'
+ */
+void fpsimd_preserve_current_state(void)
+{
+	preempt_disable();
+	if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
+		fpsimd_save_state(&current->thread.fpsimd_state);
+	preempt_enable();
+}
+
+/*
+ * Load the userland FPSIMD state of 'current' from memory, but only if the
+ * FPSIMD state already held in the registers is /not/ the most recent FPSIMD
+ * state of 'current'
+ */
+void fpsimd_restore_current_state(void)
+{
+	preempt_disable();
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+		fpsimd_load_state(st);
+		this_cpu_write(fpsimd_last_state, st);
+		st->cpu = smp_processor_id();
+	}
+	preempt_enable();
+}
+
+/*
+ * Load an updated userland FPSIMD state for 'current' from memory and set the
+ * flag that indicates that the FPSIMD register contents are the most recent
+ * FPSIMD state of 'current'
+ */
+void fpsimd_update_current_state(struct fpsimd_state *state)
+{
+	preempt_disable();
+	fpsimd_load_state(state);
+	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		struct fpsimd_state *st = &current->thread.fpsimd_state;
+
+		this_cpu_write(fpsimd_last_state, st);
+		st->cpu = smp_processor_id();
+	}
 	preempt_enable();
 }
 
+/*
+ * Invalidate live CPU copies of task t's FPSIMD state
+ */
+void fpsimd_flush_task_state(struct task_struct *t)
+{
+	t->thread.fpsimd_state.cpu = NR_CPUS;
+}
+
 #ifdef CONFIG_KERNEL_MODE_NEON
 
+static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate);
+static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
+
 /*
  * Kernel-side NEON support functions
  */
-void kernel_neon_begin(void)
+void kernel_neon_begin_partial(u32 num_regs)
 {
-	/* Avoid using the NEON in interrupt context */
-	BUG_ON(in_interrupt());
-	preempt_disable();
+	if (in_interrupt()) {
+		struct fpsimd_partial_state *s = this_cpu_ptr(
+			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
 
-	if (current->mm)
-		fpsimd_save_state(&current->thread.fpsimd_state);
+		BUG_ON(num_regs > 32);
+		fpsimd_save_partial_state(s, roundup(num_regs, 2));
+	} else {
+		/*
+		 * Save the userland FPSIMD state if we have one and if we
+		 * haven't done so already. Clear fpsimd_last_state to indicate
+		 * that there is no longer userland FPSIMD state in the
+		 * registers.
+		 */
+		preempt_disable();
+		if (current->mm &&
+		    !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
+			fpsimd_save_state(&current->thread.fpsimd_state);
+		this_cpu_write(fpsimd_last_state, NULL);
+	}
 }
-EXPORT_SYMBOL(kernel_neon_begin);
+EXPORT_SYMBOL(kernel_neon_begin_partial);
 
 void kernel_neon_end(void)
 {
-	if (current->mm)
-		fpsimd_load_state(&current->thread.fpsimd_state);
-
-	preempt_enable();
+	if (in_interrupt()) {
+		struct fpsimd_partial_state *s = this_cpu_ptr(
+			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
+		fpsimd_load_partial_state(s);
+	} else {
+		preempt_enable();
+	}
 }
 EXPORT_SYMBOL(kernel_neon_end);
 
@@ -120,12 +268,12 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
 {
 	switch (cmd) {
 	case CPU_PM_ENTER:
-		if (current->mm)
+		if (current->mm && !test_thread_flag(TIF_FOREIGN_FPSTATE))
 			fpsimd_save_state(&current->thread.fpsimd_state);
 		break;
 	case CPU_PM_EXIT:
 		if (current->mm)
-			fpsimd_load_state(&current->thread.fpsimd_state);
+			set_thread_flag(TIF_FOREIGN_FPSTATE);
 		break;
 	case CPU_PM_ENTER_FAILED:
 	default:
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
new file mode 100644
index 000000000000..649890a3ac4e
--- /dev/null
+++ b/arch/arm64/kernel/ftrace.c
@@ -0,0 +1,177 @@
+/*
+ * arch/arm64/kernel/ftrace.c
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ftrace.h>
+#include <linux/swab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Replace a single instruction, which may be a branch or NOP.
+ * If @validate == true, a replaced instruction is checked against 'old'.
+ */
+static int ftrace_modify_code(unsigned long pc, u32 old, u32 new,
+			      bool validate)
+{
+	u32 replaced;
+
+	/*
+	 * Note:
+	 * Due to modules and __init, code can disappear and change,
+	 * we need to protect against faulting as well as code changing.
+	 * We do this by aarch64_insn_*() which use the probe_kernel_*().
+	 *
+	 * No lock is held here because all the modifications are run
+	 * through stop_machine().
+	 */
+	if (validate) {
+		if (aarch64_insn_read((void *)pc, &replaced))
+			return -EFAULT;
+
+		if (replaced != old)
+			return -EINVAL;
+	}
+	if (aarch64_insn_patch_text_nosync((void *)pc, new))
+		return -EPERM;
+
+	return 0;
+}
+
+/*
+ * Replace tracer function in ftrace_caller()
+ */
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long pc;
+	u32 new;
+
+	pc = (unsigned long)&ftrace_call;
+	new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, true);
+
+	return ftrace_modify_code(pc, 0, new, false);
+}
+
+/*
+ * Turn on the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_nop();
+	new = aarch64_insn_gen_branch_imm(pc, addr, true);
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+/*
+ * Turn off the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	u32 old, new;
+
+	old = aarch64_insn_gen_branch_imm(pc, addr, true);
+	new = aarch64_insn_gen_nop();
+
+	return ftrace_modify_code(pc, old, new, true);
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	*(unsigned long *)data = 0;
+	return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * function_graph tracer expects ftrace_return_to_handler() to be called
+ * on the way back to parent. For this purpose, this function is called
+ * in _mcount() or ftrace_caller() to replace return address (*parent) on
+ * the call stack to return_to_handler.
+ *
+ * Note that @frame_pointer is used only for sanity check later.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+	struct ftrace_graph_ent trace;
+	int err;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * Note:
+	 * No protection against faulting at *parent, which may be seen
+	 * on other archs. It's unlikely on AArch64.
+	 */
+	old = *parent;
+	*parent = return_hooker;
+
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		*parent = old;
+		return;
+	}
+
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+				       frame_pointer);
+	if (err == -EBUSY) {
+		*parent = old;
+		return;
+	}
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Turn on/off the call to ftrace_graph_caller() in ftrace_caller()
+ * depending on @enable.
+ */
+static int ftrace_modify_graph_caller(bool enable)
+{
+	unsigned long pc = (unsigned long)&ftrace_graph_call;
+	u32 branch, nop;
+
+	branch = aarch64_insn_gen_branch_imm(pc,
+			(unsigned long)ftrace_graph_caller, false);
+	nop = aarch64_insn_gen_nop();
+
+	if (enable)
+		return ftrace_modify_code(pc, nop, branch, true);
+	else
+		return ftrace_modify_code(pc, branch, nop, true);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 156f3b4b717a..e28eaef0568f 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -22,10 +22,12 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
+#include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
@@ -34,29 +36,17 @@
 #include <asm/page.h>
 #include <asm/virt.h>
 
-/*
- * swapper_pg_dir is the virtual address of the initial page table. We place
- * the page tables 3 * PAGE_SIZE below KERNEL_RAM_VADDR. The idmap_pg_dir has
- * 2 pages and is placed below swapper_pg_dir.
- */
 #define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
 
 #if (KERNEL_RAM_VADDR & 0xfffff) != 0x80000
 #error KERNEL_RAM_VADDR must start at 0xXXX80000
 #endif
 
-#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
-
-	.globl	swapper_pg_dir
-	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - SWAPPER_DIR_SIZE
-
-	.globl	idmap_pg_dir
-	.equ	idmap_pg_dir, swapper_pg_dir - IDMAP_DIR_SIZE
-
-	.macro	pgtbl, ttb0, ttb1, phys
-	add	\ttb1, \phys, #TEXT_OFFSET - SWAPPER_DIR_SIZE
-	sub	\ttb0, \ttb1, #IDMAP_DIR_SIZE
+	.macro	pgtbl, ttb0, ttb1, virt_to_phys
+	ldr	\ttb1, =swapper_pg_dir
+	ldr	\ttb0, =idmap_pg_dir
+	add	\ttb1, \ttb1, \virt_to_phys
+	add	\ttb0, \ttb0, \virt_to_phys
 	.endm
 
 #ifdef CONFIG_ARM64_64K_PAGES
@@ -295,6 +285,23 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	msr	cnthctl_el2, x0
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 
+#ifdef CONFIG_ARM_GIC_V3
+	/* GICv3 system register access */
+	mrs	x0, id_aa64pfr0_el1
+	ubfx	x0, x0, #24, #4
+	cmp	x0, #1
+	b.ne	3f
+
+	mrs_s	x0, ICC_SRE_EL2
+	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
+	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
+	msr_s	ICC_SRE_EL2, x0
+	isb					// Make sure SRE is now set
+	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
+
+3:
+#endif
+
 	/* Populate ID registers. */
 	mrs	x0, midr_el1
 	mrs	x1, mpidr_el1
@@ -352,8 +359,9 @@ ENDPROC(set_cpu_boot_mode_flag)
  * This is not in .bss, because we set it sufficiently early that the boot-time
  * zeroing of .bss would clobber it.
  */
-	.pushsection	.data
+	.pushsection	.data..cacheline_aligned
 ENTRY(__boot_cpu_mode)
+	.align	L1_CACHE_SHIFT
 	.long	BOOT_CPU_MODE_EL2
 	.long	0
 	.popsection
@@ -410,7 +418,7 @@ ENTRY(secondary_startup)
 	mov	x23, x0				// x23=current cpu_table
 	cbz	x23, __error_p			// invalid processor (x23=0)?
 
-	pgtbl	x25, x26, x24			// x25=TTBR0, x26=TTBR1
+	pgtbl	x25, x26, x28			// x25=TTBR0, x26=TTBR1
 	ldr	x12, [x23, #CPU_INFO_SETUP]
 	add	x12, x12, x28			// __virt_to_phys
 	blr	x12				// initialise processor
@@ -452,8 +460,13 @@ ENDPROC(__enable_mmu)
  *  x27 = *virtual* address to jump to upon completion
  *
  * other registers depend on the function called upon completion
+ *
+ * We align the entire function to the smallest power of two larger than it to
+ * ensure it fits within a single block map entry. Otherwise were PHYS_OFFSET
+ * close to the end of a 512MB or 1GB block we might require an additional
+ * table to map the entire function.
  */
-	.align	6
+	.align	4
 __turn_mmu_on:
 	msr	sctlr_el1, x0
 	isb
@@ -496,26 +509,18 @@ ENDPROC(__calc_phys_offset)
  * Preserves:	tbl, flags
  * Corrupts:	phys, start, end, pstate
  */
-	.macro	create_block_map, tbl, flags, phys, start, end, idmap=0
+	.macro	create_block_map, tbl, flags, phys, start, end
 	lsr	\phys, \phys, #BLOCK_SHIFT
-	.if	\idmap
-	and	\start, \phys, #PTRS_PER_PTE - 1	// table index
-	.else
 	lsr	\start, \start, #BLOCK_SHIFT
 	and	\start, \start, #PTRS_PER_PTE - 1	// table index
-	.endif
 	orr	\phys, \flags, \phys, lsl #BLOCK_SHIFT	// table entry
-	.ifnc	\start,\end
 	lsr	\end, \end, #BLOCK_SHIFT
 	and	\end, \end, #PTRS_PER_PTE - 1		// table end index
-	.endif
 9999:	str	\phys, [\tbl, \start, lsl #3]		// store the entry
-	.ifnc	\start,\end
 	add	\start, \start, #1			// next entry
 	add	\phys, \phys, #BLOCK_SIZE		// next block
 	cmp	\start, \end
 	b.ls	9999b
-	.endif
 	.endm
 
 /*
@@ -524,10 +529,19 @@ ENDPROC(__calc_phys_offset)
  *   - identity mapping to enable the MMU (low address, TTBR0)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
  *     been enabled, including the FDT blob (TTBR1)
- *   - UART mapping if CONFIG_EARLY_PRINTK is enabled (TTBR1)
+ *   - pgd entry for fixed mappings (TTBR1)
  */
 __create_page_tables:
-	pgtbl	x25, x26, x24			// idmap_pg_dir and swapper_pg_dir addresses
+	pgtbl	x25, x26, x28			// idmap_pg_dir and swapper_pg_dir addresses
+	mov	x27, lr
+
+	/*
+	 * Invalidate the idmap and swapper page tables to avoid potential
+	 * dirty cache lines being evicted.
+	 */
+	mov	x0, x25
+	add	x1, x26, #SWAPPER_DIR_SIZE
+	bl	__inval_cache_range
 
 	/*
 	 * Clear the idmap and swapper page tables.
@@ -547,9 +561,13 @@ __create_page_tables:
 	 * Create the identity mapping.
 	 */
 	add	x0, x25, #PAGE_SIZE		// section table address
-	adr	x3, __turn_mmu_on		// virtual/physical address
+	ldr	x3, =KERNEL_START
+	add	x3, x3, x28			// __pa(KERNEL_START)
 	create_pgd_entry x25, x0, x3, x5, x6
-	create_block_map x0, x7, x3, x5, x5, idmap=1
+	ldr	x6, =KERNEL_END
+	mov	x5, x3				// __pa(KERNEL_START)
+	add	x6, x6, x28			// __pa(KERNEL_END)
+	create_block_map x0, x7, x3, x5, x6
 
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
@@ -557,7 +575,7 @@ __create_page_tables:
 	add	x0, x26, #PAGE_SIZE		// section table address
 	mov	x5, #PAGE_OFFSET
 	create_pgd_entry x26, x0, x5, x3, x6
-	ldr	x6, =KERNEL_END - 1
+	ldr	x6, =KERNEL_END
 	mov	x3, x24				// phys offset
 	create_block_map x0, x7, x3, x5, x6
 
@@ -577,15 +595,23 @@ __create_page_tables:
 	sub	x6, x6, #1			// inclusive range
 	create_block_map x0, x7, x3, x5, x6
 1:
-#ifdef CONFIG_EARLY_PRINTK
 	/*
-	 * Create the pgd entry for the UART mapping. The full mapping is done
-	 * later based earlyprintk kernel parameter.
+	 * Create the pgd entry for the fixed mappings.
 	 */
-	ldr	x5, =EARLYCON_IOBASE		// UART virtual address
+	ldr	x5, =FIXADDR_TOP		// Fixed mapping virtual address
 	add	x0, x26, #2 * PAGE_SIZE		// section table address
 	create_pgd_entry x26, x0, x5, x6, x7
-#endif
+
+	/*
+	 * Since the page tables have been populated with non-cacheable
+	 * accesses (MMU disabled), invalidate the idmap and swapper page
+	 * tables again to remove any speculatively loaded cache lines.
+	 */
+	mov	x0, x25
+	add	x1, x26, #SWAPPER_DIR_SIZE
+	bl	__inval_cache_range
+
+	mov	lr, x27
 	ret
 ENDPROC(__create_page_tables)
 	.ltorg
@@ -595,7 +621,7 @@ ENDPROC(__create_page_tables)
 __switch_data:
 	.quad	__mmap_switched
 	.quad	__bss_start			// x6
-	.quad	_end				// x7
+	.quad	__bss_stop			// x7
 	.quad	processor_id			// x4
 	.quad	__fdt_pointer			// x5
 	.quad	memstart_addr			// x6
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index f17f581116fc..a45e2db6e502 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -20,6 +20,7 @@
 
 #define pr_fmt(fmt) "hw-breakpoint: " fmt
 
+#include <linux/compat.h>
 #include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/hw_breakpoint.h>
@@ -27,7 +28,6 @@
 #include <linux/ptrace.h>
 #include <linux/smp.h>
 
-#include <asm/compat.h>
 #include <asm/current.h>
 #include <asm/debug-monitors.h>
 #include <asm/hw_breakpoint.h>
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 0959611d9ff1..a272f335c289 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -19,6 +19,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 92f36835486b..565e26f23f31 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -156,9 +156,10 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 		 * which ends with "dsb; isb" pair guaranteeing global
 		 * visibility.
 		 */
-		atomic_set(&pp->cpu_count, -1);
+		/* Notify other processors with an additional increment. */
+		atomic_inc(&pp->cpu_count);
 	} else {
-		while (atomic_read(&pp->cpu_count) != -1)
+		while (atomic_read(&pp->cpu_count) <= num_online_cpus())
 			cpu_relax();
 		isb();
 	}
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 473e5dbf8f39..dfa6e3e74fdd 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -105,7 +105,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
 		cpumask_copy(d->affinity, affinity);
 
 	return ret;
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
new file mode 100644
index 000000000000..75c9cf1aafee
--- /dev/null
+++ b/arch/arm64/kernel/kgdb.c
@@ -0,0 +1,336 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/kernel/kgdb.c
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/irq.h>
+#include <linux/kdebug.h>
+#include <linux/kgdb.h>
+#include <asm/traps.h>
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+	{ "x0", 8, offsetof(struct pt_regs, regs[0])},
+	{ "x1", 8, offsetof(struct pt_regs, regs[1])},
+	{ "x2", 8, offsetof(struct pt_regs, regs[2])},
+	{ "x3", 8, offsetof(struct pt_regs, regs[3])},
+	{ "x4", 8, offsetof(struct pt_regs, regs[4])},
+	{ "x5", 8, offsetof(struct pt_regs, regs[5])},
+	{ "x6", 8, offsetof(struct pt_regs, regs[6])},
+	{ "x7", 8, offsetof(struct pt_regs, regs[7])},
+	{ "x8", 8, offsetof(struct pt_regs, regs[8])},
+	{ "x9", 8, offsetof(struct pt_regs, regs[9])},
+	{ "x10", 8, offsetof(struct pt_regs, regs[10])},
+	{ "x11", 8, offsetof(struct pt_regs, regs[11])},
+	{ "x12", 8, offsetof(struct pt_regs, regs[12])},
+	{ "x13", 8, offsetof(struct pt_regs, regs[13])},
+	{ "x14", 8, offsetof(struct pt_regs, regs[14])},
+	{ "x15", 8, offsetof(struct pt_regs, regs[15])},
+	{ "x16", 8, offsetof(struct pt_regs, regs[16])},
+	{ "x17", 8, offsetof(struct pt_regs, regs[17])},
+	{ "x18", 8, offsetof(struct pt_regs, regs[18])},
+	{ "x19", 8, offsetof(struct pt_regs, regs[19])},
+	{ "x20", 8, offsetof(struct pt_regs, regs[20])},
+	{ "x21", 8, offsetof(struct pt_regs, regs[21])},
+	{ "x22", 8, offsetof(struct pt_regs, regs[22])},
+	{ "x23", 8, offsetof(struct pt_regs, regs[23])},
+	{ "x24", 8, offsetof(struct pt_regs, regs[24])},
+	{ "x25", 8, offsetof(struct pt_regs, regs[25])},
+	{ "x26", 8, offsetof(struct pt_regs, regs[26])},
+	{ "x27", 8, offsetof(struct pt_regs, regs[27])},
+	{ "x28", 8, offsetof(struct pt_regs, regs[28])},
+	{ "x29", 8, offsetof(struct pt_regs, regs[29])},
+	{ "x30", 8, offsetof(struct pt_regs, regs[30])},
+	{ "sp", 8, offsetof(struct pt_regs, sp)},
+	{ "pc", 8, offsetof(struct pt_regs, pc)},
+	{ "pstate", 8, offsetof(struct pt_regs, pstate)},
+	{ "v0", 16, -1 },
+	{ "v1", 16, -1 },
+	{ "v2", 16, -1 },
+	{ "v3", 16, -1 },
+	{ "v4", 16, -1 },
+	{ "v5", 16, -1 },
+	{ "v6", 16, -1 },
+	{ "v7", 16, -1 },
+	{ "v8", 16, -1 },
+	{ "v9", 16, -1 },
+	{ "v10", 16, -1 },
+	{ "v11", 16, -1 },
+	{ "v12", 16, -1 },
+	{ "v13", 16, -1 },
+	{ "v14", 16, -1 },
+	{ "v15", 16, -1 },
+	{ "v16", 16, -1 },
+	{ "v17", 16, -1 },
+	{ "v18", 16, -1 },
+	{ "v19", 16, -1 },
+	{ "v20", 16, -1 },
+	{ "v21", 16, -1 },
+	{ "v22", 16, -1 },
+	{ "v23", 16, -1 },
+	{ "v24", 16, -1 },
+	{ "v25", 16, -1 },
+	{ "v26", 16, -1 },
+	{ "v27", 16, -1 },
+	{ "v28", 16, -1 },
+	{ "v29", 16, -1 },
+	{ "v30", 16, -1 },
+	{ "v31", 16, -1 },
+	{ "fpsr", 4, -1 },
+	{ "fpcr", 4, -1 },
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return NULL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+		       dbg_reg_def[regno].size);
+	else
+		memset(mem, 0, dbg_reg_def[regno].size);
+	return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+	if (regno >= DBG_MAX_REG_NUM || regno < 0)
+		return -EINVAL;
+
+	if (dbg_reg_def[regno].offset != -1)
+		memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+		       dbg_reg_def[regno].size);
+	return 0;
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+	struct pt_regs *thread_regs;
+
+	/* Initialize to zero */
+	memset((char *)gdb_regs, 0, NUMREGBYTES);
+	thread_regs = task_pt_regs(task);
+	memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+	regs->pc = pc;
+}
+
+static int compiled_break;
+
+static void kgdb_arch_update_addr(struct pt_regs *regs,
+				char *remcom_in_buffer)
+{
+	unsigned long addr;
+	char *ptr;
+
+	ptr = &remcom_in_buffer[1];
+	if (kgdb_hex2long(&ptr, &addr))
+		kgdb_arch_set_pc(regs, addr);
+	else if (compiled_break == 1)
+		kgdb_arch_set_pc(regs, regs->pc + 4);
+
+	compiled_break = 0;
+}
+
+int kgdb_arch_handle_exception(int exception_vector, int signo,
+			       int err_code, char *remcom_in_buffer,
+			       char *remcom_out_buffer,
+			       struct pt_regs *linux_regs)
+{
+	int err;
+
+	switch (remcom_in_buffer[0]) {
+	case 'D':
+	case 'k':
+		/*
+		 * Packet D (Detach), k (kill). No special handling
+		 * is required here. Handle same as c packet.
+		 */
+	case 'c':
+		/*
+		 * Packet c (Continue) to continue executing.
+		 * Set pc to required address.
+		 * Try to read optional parameter and set pc.
+		 * If this was a compiled breakpoint, we need to move
+		 * to the next instruction else we will just breakpoint
+		 * over and over again.
+		 */
+		kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+		atomic_set(&kgdb_cpu_doing_single_step, -1);
+		kgdb_single_step =  0;
+
+		/*
+		 * Received continue command, disable single step
+		 */
+		if (kernel_active_single_step())
+			kernel_disable_single_step();
+
+		err = 0;
+		break;
+	case 's':
+		/*
+		 * Update step address value with address passed
+		 * with step packet.
+		 * On debug exception return PC is copied to ELR
+		 * So just update PC.
+		 * If no step address is passed, resume from the address
+		 * pointed by PC. Do not update PC
+		 */
+		kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+		atomic_set(&kgdb_cpu_doing_single_step, raw_smp_processor_id());
+		kgdb_single_step =  1;
+
+		/*
+		 * Enable single step handling
+		 */
+		if (!kernel_active_single_step())
+			kernel_enable_single_step(linux_regs);
+		err = 0;
+		break;
+	default:
+		err = -1;
+	}
+	return err;
+}
+
+static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	return 0;
+}
+
+static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+	compiled_break = 1;
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+
+	return 0;
+}
+
+static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	return 0;
+}
+
+static struct break_hook kgdb_brkpt_hook = {
+	.esr_mask	= 0xffffffff,
+	.esr_val	= DBG_ESR_VAL_BRK(KGDB_DYN_DGB_BRK_IMM),
+	.fn		= kgdb_brk_fn
+};
+
+static struct break_hook kgdb_compiled_brkpt_hook = {
+	.esr_mask	= 0xffffffff,
+	.esr_val	= DBG_ESR_VAL_BRK(KDBG_COMPILED_DBG_BRK_IMM),
+	.fn		= kgdb_compiled_brk_fn
+};
+
+static struct step_hook kgdb_step_hook = {
+	.fn		= kgdb_step_brk_fn
+};
+
+static void kgdb_call_nmi_hook(void *ignored)
+{
+	kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+}
+
+void kgdb_roundup_cpus(unsigned long flags)
+{
+	local_irq_enable();
+	smp_call_function(kgdb_call_nmi_hook, NULL, 0);
+	local_irq_disable();
+}
+
+static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+{
+	struct pt_regs *regs = args->regs;
+
+	if (kgdb_handle_exception(1, args->signr, cmd, regs))
+		return NOTIFY_DONE;
+	return NOTIFY_STOP;
+}
+
+static int
+kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
+{
+	unsigned long flags;
+	int ret;
+
+	local_irq_save(flags);
+	ret = __kgdb_notify(ptr, cmd);
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static struct notifier_block kgdb_notifier = {
+	.notifier_call	= kgdb_notify,
+	/*
+	 * Want to be lowest priority
+	 */
+	.priority	= -INT_MAX,
+};
+
+/*
+ * kgdb_arch_init - Perform any architecture specific initalization.
+ * This function will handle the initalization of any architecture
+ * specific callbacks.
+ */
+int kgdb_arch_init(void)
+{
+	int ret = register_die_notifier(&kgdb_notifier);
+
+	if (ret != 0)
+		return ret;
+
+	register_break_hook(&kgdb_brkpt_hook);
+	register_break_hook(&kgdb_compiled_brkpt_hook);
+	register_step_hook(&kgdb_step_hook);
+	return 0;
+}
+
+/*
+ * kgdb_arch_exit - Perform any architecture specific uninitalization.
+ * This function will handle the uninitalization of any architecture
+ * specific callbacks, for dynamic registration and unregistration.
+ */
+void kgdb_arch_exit(void)
+{
+	unregister_break_hook(&kgdb_brkpt_hook);
+	unregister_break_hook(&kgdb_compiled_brkpt_hook);
+	unregister_step_hook(&kgdb_step_hook);
+	unregister_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * ARM instructions are always in LE.
+ * Break instruction is encoded in LE format
+ */
+struct kgdb_arch arch_kgdb_ops = {
+	.gdb_bpt_instr = {
+		KGDB_DYN_BRK_INS_BYTE0,
+		KGDB_DYN_BRK_INS_BYTE1,
+		KGDB_DYN_BRK_INS_BYTE2,
+		KGDB_DYN_BRK_INS_BYTE3,
+	}
+};
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 5b1cd792274a..baf5afb7e6a0 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1348,8 +1348,8 @@ early_initcall(init_hw_perf_events);
  * Callchain handling code.
  */
 struct frame_tail {
-	struct frame_tail   __user *fp;
-	unsigned long	    lr;
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
 } __attribute__((packed));
 
 /*
@@ -1386,22 +1386,84 @@ user_backtrace(struct frame_tail __user *tail,
 	return buftail.fp;
 }
 
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+compat_user_backtrace(struct compat_frame_tail __user *tail,
+		      struct perf_callchain_entry *entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	perf_callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
 void perf_callchain_user(struct perf_callchain_entry *entry,
 			 struct pt_regs *regs)
 {
-	struct frame_tail __user *tail;
-
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
 
 	perf_callchain_store(entry, regs->pc);
-	tail = (struct frame_tail __user *)regs->regs[29];
 
-	while (entry->nr < PERF_MAX_STACK_DEPTH &&
-	       tail && !((unsigned long)tail & 0xf))
-		tail = user_backtrace(tail, entry);
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+
+		while (entry->nr < PERF_MAX_STACK_DEPTH &&
+		       tail && !((unsigned long)tail & 0xf))
+			tail = user_backtrace(tail, entry);
+	} else {
+#ifdef CONFIG_COMPAT
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+
+		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+			tail && !((unsigned long)tail & 0x3))
+			tail = compat_user_backtrace(tail, entry);
+#endif
+	}
 }
 
 /*
@@ -1429,6 +1491,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	frame.fp = regs->regs[29];
 	frame.sp = regs->sp;
 	frame.pc = regs->pc;
+
 	walk_stackframe(&frame, callchain_trace, entry);
 }
 
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
new file mode 100644
index 000000000000..422ebd63b619
--- /dev/null
+++ b/arch/arm64/kernel/perf_regs.c
@@ -0,0 +1,46 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+
+#include <asm/compat.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_MAX))
+		return 0;
+
+	/*
+	 * Compat (i.e. 32 bit) mode:
+	 * - PC has been set in the pt_regs struct in kernel_entry,
+	 * - Handle SP and LR here.
+	 */
+	if (compat_user_mode(regs)) {
+		if ((u32)idx == PERF_REG_ARM64_SP)
+			return regs->compat_sp;
+		if ((u32)idx == PERF_REG_ARM64_LR)
+			return regs->compat_lr;
+	}
+
+	return regs->regs[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_ARM64_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	if (is_compat_thread(task_thread_info(task)))
+		return PERF_SAMPLE_REGS_ABI_32;
+	else
+		return PERF_SAMPLE_REGS_ABI_64;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1c0a9be2ffa8..6601cda23170 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -20,6 +20,7 @@
 
 #include <stdarg.h>
 
+#include <linux/compat.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -187,9 +188,27 @@ void exit_thread(void)
 {
 }
 
+static void tls_thread_flush(void)
+{
+	asm ("msr tpidr_el0, xzr");
+
+	if (is_compat_task()) {
+		current->thread.tp_value = 0;
+
+		/*
+		 * We need to ensure ordering between the shadow state and the
+		 * hardware state, so that we don't corrupt the hardware state
+		 * with a stale shadow state during context switch.
+		 */
+		barrier();
+		asm ("msr tpidrro_el0, xzr");
+	}
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
+	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 }
 
@@ -199,7 +218,7 @@ void release_thread(struct task_struct *dead_task)
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	fpsimd_save_state(&current->thread.fpsimd_state);
+	fpsimd_preserve_current_state();
 	*dst = *src;
 	return 0;
 }
@@ -294,7 +313,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	 * Complete any pending TLB or cache maintenance on this CPU in case
 	 * the thread migrates to a different CPU.
 	 */
-	dsb();
+	dsb(ish);
 
 	/* the actual thread switch */
 	last = cpu_switch_to(prev, next);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6a8928bba03c..167c5edecad4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -19,6 +19,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
@@ -41,6 +42,9 @@
 #include <asm/traps.h>
 #include <asm/system_misc.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 /*
  * TODO: does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.
@@ -81,7 +85,8 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 			break;
 		}
 	}
-	for (i = ARM_MAX_BRP; i < ARM_MAX_HBP_SLOTS && !bp; ++i) {
+
+	for (i = 0; i < ARM_MAX_WRP; ++i) {
 		if (current->thread.debug.hbp_watch[i] == bp) {
 			info.si_errno = -((i << 1) + 1);
 			break;
@@ -517,6 +522,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		return ret;
 
 	target->thread.fpsimd_state.user_fpsimd = newstate;
+	fpsimd_flush_task_state(target);
 	return ret;
 }
 
@@ -650,11 +656,16 @@ static int compat_gpr_get(struct task_struct *target,
 			reg = task_pt_regs(target)->regs[idx];
 		}
 
-		ret = copy_to_user(ubuf, &reg, sizeof(reg));
-		if (ret)
-			break;
+		if (kbuf) {
+			memcpy(kbuf, &reg, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_to_user(ubuf, &reg, sizeof(reg));
+			if (ret)
+				break;
 
-		ubuf += sizeof(reg);
+			ubuf += sizeof(reg);
+		}
 	}
 
 	return ret;
@@ -684,11 +695,16 @@ static int compat_gpr_set(struct task_struct *target,
 		unsigned int idx = start + i;
 		compat_ulong_t reg;
 
-		ret = copy_from_user(&reg, ubuf, sizeof(reg));
-		if (ret)
-			return ret;
+		if (kbuf) {
+			memcpy(&reg, kbuf, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_from_user(&reg, ubuf, sizeof(reg));
+			if (ret)
+				return ret;
 
-		ubuf += sizeof(reg);
+			ubuf += sizeof(reg);
+		}
 
 		switch (idx) {
 		case 15:
@@ -764,6 +780,7 @@ static int compat_vfp_set(struct task_struct *target,
 		uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK;
 	}
 
+	fpsimd_flush_task_state(target);
 	return ret;
 }
 
@@ -821,6 +838,7 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 				    compat_ulong_t val)
 {
 	int ret;
+	mm_segment_t old_fs = get_fs();
 
 	if (off & 3 || off >= COMPAT_USER_SZ)
 		return -EIO;
@@ -828,10 +846,13 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 	if (off >= sizeof(compat_elf_gregset_t))
 		return 0;
 
+	set_fs(KERNEL_DS);
 	ret = copy_regset_from_user(tsk, &user_aarch32_view,
 				    REGSET_COMPAT_GPR, off,
 				    sizeof(compat_ulong_t),
 				    &val);
+	set_fs(old_fs);
+
 	return ret;
 }
 
@@ -1058,35 +1079,49 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ptrace_request(child, request, addr, data);
 }
 
-asmlinkage int syscall_trace(int dir, struct pt_regs *regs)
+enum ptrace_syscall_dir {
+	PTRACE_SYSCALL_ENTER = 0,
+	PTRACE_SYSCALL_EXIT,
+};
+
+static void tracehook_report_syscall(struct pt_regs *regs,
+				     enum ptrace_syscall_dir dir)
 {
+	int regno;
 	unsigned long saved_reg;
 
-	if (!test_thread_flag(TIF_SYSCALL_TRACE))
-		return regs->syscallno;
-
-	if (is_compat_task()) {
-		/* AArch32 uses ip (r12) for scratch */
-		saved_reg = regs->regs[12];
-		regs->regs[12] = dir;
-	} else {
-		/*
-		 * Save X7. X7 is used to denote syscall entry/exit:
-		 *   X7 = 0 -> entry, = 1 -> exit
-		 */
-		saved_reg = regs->regs[7];
-		regs->regs[7] = dir;
-	}
+	/*
+	 * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
+	 * used to denote syscall entry/exit:
+	 */
+	regno = (is_compat_task() ? 12 : 7);
+	saved_reg = regs->regs[regno];
+	regs->regs[regno] = dir;
 
-	if (dir)
+	if (dir == PTRACE_SYSCALL_EXIT)
 		tracehook_report_syscall_exit(regs, 0);
 	else if (tracehook_report_syscall_entry(regs))
 		regs->syscallno = ~0UL;
 
-	if (is_compat_task())
-		regs->regs[12] = saved_reg;
-	else
-		regs->regs[7] = saved_reg;
+	regs->regs[regno] = saved_reg;
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_enter(regs, regs->syscallno);
 
 	return regs->syscallno;
 }
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		trace_sys_exit(regs, regs_return_value(regs));
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
+}
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
new file mode 100644
index 000000000000..89102a6ffad5
--- /dev/null
+++ b/arch/arm64/kernel/return_address.c
@@ -0,0 +1,55 @@
+/*
+ * arch/arm64/kernel/return_address.c
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/export.h>
+#include <linux/ftrace.h>
+
+#include <asm/stacktrace.h>
+
+struct return_address_data {
+	unsigned int level;
+	void *addr;
+};
+
+static int save_return_addr(struct stackframe *frame, void *d)
+{
+	struct return_address_data *data = d;
+
+	if (!data->level) {
+		data->addr = (void *)frame->pc;
+		return 1;
+	} else {
+		--data->level;
+		return 0;
+	}
+}
+
+void *return_address(unsigned int level)
+{
+	struct return_address_data data;
+	struct stackframe frame;
+	register unsigned long current_sp asm ("sp");
+
+	data.level = level + 2;
+	data.addr = NULL;
+
+	frame.fp = (unsigned long)__builtin_frame_address(0);
+	frame.sp = current_sp;
+	frame.pc = (unsigned long)return_address; /* dummy */
+
+	walk_stackframe(&frame, save_return_addr, &data);
+
+	if (!data.level)
+		return data.addr;
+	else
+		return NULL;
+}
+EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index c475bde48772..c4ec05d4baab 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -43,6 +43,7 @@
 #include <linux/of_platform.h>
 #include <linux/efi.h>
 
+#include <asm/fixmap.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
@@ -69,8 +70,10 @@ EXPORT_SYMBOL_GPL(elf_hwcap);
 				 COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
 				 COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
 				 COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
-				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
+				 COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\
+				 COMPAT_HWCAP_LPAE)
 unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
 static const char *cpu_name;
@@ -244,6 +247,38 @@ static void __init setup_processor(void)
 	block = (features >> 16) & 0xf;
 	if (block && !(block & 0x8))
 		elf_hwcap |= HWCAP_CRC32;
+
+#ifdef CONFIG_COMPAT
+	/*
+	 * ID_ISAR5_EL1 carries similar information as above, but pertaining to
+	 * the Aarch32 32-bit execution state.
+	 */
+	features = read_cpuid(ID_ISAR5_EL1);
+	block = (features >> 4) & 0xf;
+	if (!(block & 0x8)) {
+		switch (block) {
+		default:
+		case 2:
+			compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
+		case 1:
+			compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
+		case 0:
+			break;
+		}
+	}
+
+	block = (features >> 8) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
+
+	block = (features >> 12) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
+
+	block = (features >> 16) & 0xf;
+	if (block && !(block & 0x8))
+		compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
+#endif
 }
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
@@ -329,6 +364,8 @@ void __init setup_arch(char **cmdline_p)
 
 	*cmdline_p = boot_command_line;
 
+	early_ioremap_init();
+
 	parse_early_param();
 
 	efi_init();
@@ -365,7 +402,7 @@ static int __init arm64_device_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
-arch_initcall(arm64_device_init);
+arch_initcall_sync(arm64_device_init);
 
 static DEFINE_PER_CPU(struct cpu, cpu_data);
 
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 890a591f75dd..bbc1aad21ce6 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/compat.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
@@ -25,7 +26,6 @@
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>
 
-#include <asm/compat.h>
 #include <asm/debug-monitors.h>
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -51,7 +51,7 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 	int err;
 
 	/* dump the hardware registers to the fpsimd_state structure */
-	fpsimd_save_state(fpsimd);
+	fpsimd_preserve_current_state();
 
 	/* copy the FP and status/control registers */
 	err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
@@ -86,11 +86,8 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
 	/* load the hardware registers from the fpsimd_state structure */
-	if (!err) {
-		preempt_disable();
-		fpsimd_load_state(&fpsimd);
-		preempt_enable();
-	}
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
 
 	return err ? -EFAULT : 0;
 }
@@ -100,8 +97,7 @@ static int restore_sigframe(struct pt_regs *regs,
 {
 	sigset_t set;
 	int i, err;
-	struct aux_context __user *aux =
-		(struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+	void *aux = sf->uc.uc_mcontext.__reserved;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0)
@@ -121,8 +117,11 @@ static int restore_sigframe(struct pt_regs *regs,
 
 	err |= !valid_user_regs(&regs->user_regs);
 
-	if (err == 0)
-		err |= restore_fpsimd_context(&aux->fpsimd);
+	if (err == 0) {
+		struct fpsimd_context *fpsimd_ctx =
+			container_of(aux, struct fpsimd_context, head);
+		err |= restore_fpsimd_context(fpsimd_ctx);
+	}
 
 	return err;
 }
@@ -167,8 +166,8 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 			  struct pt_regs *regs, sigset_t *set)
 {
 	int i, err = 0;
-	struct aux_context __user *aux =
-		(struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+	void *aux = sf->uc.uc_mcontext.__reserved;
+	struct _aarch64_ctx *end;
 
 	/* set up the stack frame for unwinding */
 	__put_user_error(regs->regs[29], &sf->fp, err);
@@ -185,12 +184,17 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
-	if (err == 0)
-		err |= preserve_fpsimd_context(&aux->fpsimd);
+	if (err == 0) {
+		struct fpsimd_context *fpsimd_ctx =
+			container_of(aux, struct fpsimd_context, head);
+		err |= preserve_fpsimd_context(fpsimd_ctx);
+		aux += sizeof(*fpsimd_ctx);
+	}
 
 	/* set the "end" magic */
-	__put_user_error(0, &aux->end.magic, err);
-	__put_user_error(0, &aux->end.size, err);
+	end = aux;
+	__put_user_error(0, &end->magic, err);
+	__put_user_error(0, &end->size, err);
 
 	return err;
 }
@@ -416,4 +420,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 	}
+
+	if (thread_flags & _TIF_FOREIGN_FPSTATE)
+		fpsimd_restore_current_state();
+
 }
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index b3fc9f5ec6d3..ac7e237d0bda 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -219,7 +219,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * Note that this also saves V16-31, which aren't visible
 	 * in AArch32.
 	 */
-	fpsimd_save_state(fpsimd);
+	fpsimd_preserve_current_state();
 
 	/* Place structure header on the stack */
 	__put_user_error(magic, &frame->magic, err);
@@ -282,11 +282,8 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
 	 * We don't need to touch the exception register, so
 	 * reload the hardware state.
 	 */
-	if (!err) {
-		preempt_disable();
-		fpsimd_load_state(&fpsimd);
-		preempt_enable();
-	}
+	if (!err)
+		fpsimd_update_current_state(&fpsimd);
 
 	return err ? -EFAULT : 0;
 }
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index b1925729c692..ede186cdd452 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -49,28 +49,39 @@
 	orr	\dst, \dst, \mask		// dst|=(aff3>>rs3)
 	.endm
 /*
- * Save CPU state for a suspend.  This saves callee registers, and allocates
- * space on the kernel stack to save the CPU specific registers + some
- * other data for resume.
+ * Save CPU state for a suspend and execute the suspend finisher.
+ * On success it will return 0 through cpu_resume - ie through a CPU
+ * soft/hard reboot from the reset vector.
+ * On failure it returns the suspend finisher return value or force
+ * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher
+ * is not allowed to return, if it does this must be considered failure).
+ * It saves callee registers, and allocates space on the kernel stack
+ * to save the CPU specific registers + some other data for resume.
  *
  *  x0 = suspend finisher argument
+ *  x1 = suspend finisher function pointer
  */
-ENTRY(__cpu_suspend)
+ENTRY(__cpu_suspend_enter)
 	stp	x29, lr, [sp, #-96]!
 	stp	x19, x20, [sp,#16]
 	stp	x21, x22, [sp,#32]
 	stp	x23, x24, [sp,#48]
 	stp	x25, x26, [sp,#64]
 	stp	x27, x28, [sp,#80]
+	/*
+	 * Stash suspend finisher and its argument in x20 and x19
+	 */
+	mov	x19, x0
+	mov	x20, x1
 	mov	x2, sp
 	sub	sp, sp, #CPU_SUSPEND_SZ	// allocate cpu_suspend_ctx
-	mov	x1, sp
+	mov	x0, sp
 	/*
-	 * x1 now points to struct cpu_suspend_ctx allocated on the stack
+	 * x0 now points to struct cpu_suspend_ctx allocated on the stack
 	 */
-	str	x2, [x1, #CPU_CTX_SP]
-	ldr	x2, =sleep_save_sp
-	ldr	x2, [x2, #SLEEP_SAVE_SP_VIRT]
+	str	x2, [x0, #CPU_CTX_SP]
+	ldr	x1, =sleep_save_sp
+	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
 #ifdef CONFIG_SMP
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
@@ -82,11 +93,21 @@ ENTRY(__cpu_suspend)
 	ldp	w3, w4, [x9, #MPIDR_HASH_SHIFTS]
 	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
-	add	x2, x2, x8, lsl #3
+	add	x1, x1, x8, lsl #3
 #endif
-	bl	__cpu_suspend_finisher
+	bl	__cpu_suspend_save
+	/*
+	 * Grab suspend finisher in x20 and its argument in x19
+	 */
+	mov	x0, x19
+	mov	x1, x20
+	/*
+	 * We are ready for power down, fire off the suspend finisher
+	 * in x1, with argument in x0
+	 */
+	blr	x1
         /*
-	 * Never gets here, unless suspend fails.
+	 * Never gets here, unless suspend finisher fails.
 	 * Successful cpu_suspend should return from cpu_resume, returning
 	 * through this code path is considered an error
 	 * If the return value is set to 0 force x0 = -EOPNOTSUPP
@@ -103,7 +124,7 @@ ENTRY(__cpu_suspend)
 	ldp	x27, x28, [sp, #80]
 	ldp	x29, lr, [sp], #96
 	ret
-ENDPROC(__cpu_suspend)
+ENDPROC(__cpu_suspend_enter)
 	.ltorg
 
 /*
@@ -126,14 +147,12 @@ cpu_resume_after_mmu:
 	ret
 ENDPROC(cpu_resume_after_mmu)
 
-	.data
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
 #ifdef CONFIG_SMP
 	mrs	x1, mpidr_el1
-	adr	x4, mpidr_hash_ptr
-	ldr	x5, [x4]
-	add	x8, x4, x5		// x8 = struct mpidr_hash phys address
+	adrp	x8, mpidr_hash
+	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
         /* retrieve mpidr_hash members to compute the hash */
 	ldr	x2, [x8, #MPIDR_HASH_MASK]
 	ldp	w3, w4, [x8, #MPIDR_HASH_SHIFTS]
@@ -143,14 +162,15 @@ ENTRY(cpu_resume)
 #else
 	mov	x7, xzr
 #endif
-	adr	x0, sleep_save_sp
+	adrp	x0, sleep_save_sp
+	add	x0, x0, #:lo12:sleep_save_sp
 	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	adr	x1, sleep_idmap_phys
+	adrp	x1, sleep_idmap_phys
 	/* load physical address of identity map page table in x1 */
-	ldr	x1, [x1]
+	ldr	x1, [x1, #:lo12:sleep_idmap_phys]
 	mov	sp, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
@@ -159,26 +179,3 @@ ENTRY(cpu_resume)
 	bl	cpu_do_resume		// PC relative jump, MMU off
 	b	cpu_resume_mmu		// Resume MMU, never returns
 ENDPROC(cpu_resume)
-
-	.align 3
-mpidr_hash_ptr:
-	/*
-	 * offset of mpidr_hash symbol from current location
-	 * used to obtain run-time mpidr_hash address with MMU off
-         */
-	.quad	mpidr_hash - .
-/*
- * physical address of identity mapped page tables
- */
-	.type	sleep_idmap_phys, #object
-ENTRY(sleep_idmap_phys)
-	.quad	0
-/*
- * struct sleep_save_sp {
- *	phys_addr_t *save_ptr_stash;
- *	phys_addr_t save_ptr_stash_phys;
- * };
- */
-	.type	sleep_save_sp, #object
-ENTRY(sleep_save_sp)
-	.space	SLEEP_SAVE_SP_SZ	// struct sleep_save_sp
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 7cfb92a4ab66..6819fab9a80b 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -35,6 +35,7 @@
 #include <linux/clockchips.h>
 #include <linux/completion.h>
 #include <linux/of.h>
+#include <linux/irq_work.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
@@ -62,6 +63,7 @@ enum ipi_msg_type {
 	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 	IPI_TIMER,
+	IPI_IRQ_WORK,
 };
 
 /*
@@ -114,6 +116,11 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	return ret;
 }
 
+static void smp_store_cpu_info(unsigned int cpuid)
+{
+	store_cpu_topology(cpuid);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -152,6 +159,8 @@ asmlinkage void secondary_start_kernel(void)
 	 */
 	notify_cpu_starting(cpu);
 
+	smp_store_cpu_info(cpu);
+
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
 	 * the CPU migration code to notice that the CPU is online
@@ -390,6 +399,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	int err;
 	unsigned int cpu, ncores = num_possible_cpus();
 
+	init_cpu_topology();
+
+	smp_store_cpu_info(smp_processor_id());
+
 	/*
 	 * are we trying to boot more cores than exist?
 	 */
@@ -443,6 +456,14 @@ void arch_send_call_function_single_ipi(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	if (smp_cross_call)
+		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+}
+#endif
+
 static const char *ipi_types[NR_IPI] = {
 #define S(x,s)	[x - IPI_RESCHEDULE] = s
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
@@ -450,6 +471,7 @@ static const char *ipi_types[NR_IPI] = {
 	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
 	S(IPI_TIMER, "Timer broadcast interrupts"),
+	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -542,6 +564,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		break;
 #endif
 
+#ifdef CONFIG_IRQ_WORK
+	case IPI_IRQ_WORK:
+		irq_enter();
+		irq_work_run();
+		irq_exit();
+		break;
+#endif
+
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
 		break;
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 44c22805d2e2..0347d38eea29 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -30,7 +30,6 @@ extern void secondary_holding_pen(void);
 volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
-static DEFINE_RAW_SPINLOCK(boot_lock);
 
 /*
  * Write secondary_holding_pen_release in a way that is guaranteed to be
@@ -94,14 +93,6 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 
 static int smp_spin_table_cpu_boot(unsigned int cpu)
 {
-	unsigned long timeout;
-
-	/*
-	 * Set synchronisation state between this boot processor
-	 * and the secondary one
-	 */
-	raw_spin_lock(&boot_lock);
-
 	/*
 	 * Update the pen release flag.
 	 */
@@ -112,34 +103,7 @@ static int smp_spin_table_cpu_boot(unsigned int cpu)
 	 */
 	sev();
 
-	timeout = jiffies + (1 * HZ);
-	while (time_before(jiffies, timeout)) {
-		if (secondary_holding_pen_release == INVALID_HWID)
-			break;
-		udelay(10);
-	}
-
-	/*
-	 * Now the secondary core is starting up let it run its
-	 * calibrations, then wait for it to finish
-	 */
-	raw_spin_unlock(&boot_lock);
-
-	return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
-}
-
-void smp_spin_table_cpu_postboot(void)
-{
-	/*
-	 * Let the primary processor know we're out of the pen.
-	 */
-	write_pen_release(INVALID_HWID);
-
-	/*
-	 * Synchronise with the boot thread.
-	 */
-	raw_spin_lock(&boot_lock);
-	raw_spin_unlock(&boot_lock);
+	return 0;
 }
 
 const struct cpu_operations smp_spin_table_ops = {
@@ -147,5 +111,4 @@ const struct cpu_operations smp_spin_table_ops = {
 	.cpu_init	= smp_spin_table_cpu_init,
 	.cpu_prepare	= smp_spin_table_cpu_prepare,
 	.cpu_boot	= smp_spin_table_cpu_boot,
-	.cpu_postboot	= smp_spin_table_cpu_postboot,
 };
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 38f0558f0c0a..55437ba1f5a4 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -35,7 +35,7 @@
  *	ldp	x29, x30, [sp]
  *	add	sp, sp, #0x10
  */
-int unwind_frame(struct stackframe *frame)
+int notrace unwind_frame(struct stackframe *frame)
 {
 	unsigned long high, low;
 	unsigned long fp = frame->fp;
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 1fa9ce4afd8f..2d6b6065fe7f 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -5,26 +5,24 @@
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
 #include <asm/memory.h>
+#include <asm/mmu_context.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-extern int __cpu_suspend(unsigned long);
+extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long));
 /*
- * This is called by __cpu_suspend() to save the state, and do whatever
+ * This is called by __cpu_suspend_enter() to save the state, and do whatever
  * flushing is required to ensure that when the CPU goes to sleep we have
  * the necessary data available when the caches are not searched.
  *
- * @arg: Argument to pass to suspend operations
- * @ptr: CPU context virtual address
- * @save_ptr: address of the location where the context physical address
- *            must be saved
+ * ptr: CPU context virtual address
+ * save_ptr: address of the location where the context physical address
+ *           must be saved
  */
-int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
-			   phys_addr_t *save_ptr)
+void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr,
+				phys_addr_t *save_ptr)
 {
-	int cpu = smp_processor_id();
-
 	*save_ptr = virt_to_phys(ptr);
 
 	cpu_do_suspend(ptr);
@@ -35,8 +33,6 @@ int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
 	 */
 	__flush_dcache_area(ptr, sizeof(*ptr));
 	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
-
-	return cpu_ops[cpu]->cpu_suspend(arg);
 }
 
 /*
@@ -56,15 +52,15 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 }
 
 /**
- * cpu_suspend
+ * cpu_suspend() - function to enter a low-power state
+ * @arg: argument to pass to CPU suspend operations
  *
- * @arg: argument to pass to the finisher function
+ * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
+ * operations back-end error code otherwise.
  */
 int cpu_suspend(unsigned long arg)
 {
-	struct mm_struct *mm = current->active_mm;
-	int ret, cpu = smp_processor_id();
-	unsigned long flags;
+	int cpu = smp_processor_id();
 
 	/*
 	 * If cpu_ops have not been registered or suspend
@@ -72,6 +68,21 @@ int cpu_suspend(unsigned long arg)
 	 */
 	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
 		return -EOPNOTSUPP;
+	return cpu_ops[cpu]->cpu_suspend(arg);
+}
+
+/*
+ * __cpu_suspend
+ *
+ * arg: argument to pass to the finisher function
+ * fn: finisher function pointer
+ *
+ */
+int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+{
+	struct mm_struct *mm = current->active_mm;
+	int ret;
+	unsigned long flags;
 
 	/*
 	 * From this point debug exceptions are disabled to prevent
@@ -86,16 +97,27 @@ int cpu_suspend(unsigned long arg)
 	 * page tables, so that the thread address space is properly
 	 * set-up on function return.
 	 */
-	ret = __cpu_suspend(arg);
+	ret = __cpu_suspend_enter(arg, fn);
 	if (ret == 0) {
-		cpu_switch_mm(mm->pgd, mm);
+		/*
+		 * We are resuming from reset with TTBR0_EL1 set to the
+		 * idmap to enable the MMU; restore the active_mm mappings in
+		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
+		 * the thread entered __cpu_suspend with TTBR0_EL1 set to
+		 * reserved TTBR0 page tables and should be restored as such.
+		 */
+		if (mm == &init_mm)
+			cpu_set_reserved_ttbr0();
+		else
+			cpu_switch_mm(mm->pgd, mm);
+
 		flush_tlb_all();
 
 		/*
 		 * Restore per-cpu offset before any kernel
 		 * subsystem relying on it has a chance to run.
 		 */
-		set_my_cpu_offset(per_cpu_offset(cpu));
+		set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 
 		/*
 		 * Restore HW breakpoint registers to sane values
@@ -116,10 +138,10 @@ int cpu_suspend(unsigned long arg)
 	return ret;
 }
 
-extern struct sleep_save_sp sleep_save_sp;
-extern phys_addr_t sleep_idmap_phys;
+struct sleep_save_sp sleep_save_sp;
+phys_addr_t sleep_idmap_phys;
 
-static int cpu_suspend_init(void)
+static int __init cpu_suspend_init(void)
 {
 	void *ctx_ptr;
 
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 26e9c4eeaba8..78039927c807 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -79,6 +79,12 @@ long compat_arm_syscall(struct pt_regs *regs)
 
 	case __ARM_NR_compat_set_tls:
 		current->thread.tp_value = regs->regs[0];
+
+		/*
+		 * Protect against register corruption from context switch.
+		 * See comment in tls_thread_flush.
+		 */
+		barrier();
 		asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
 		return 0;
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 000000000000..a7328373e613
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,558 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013,2014 Linaro Limited.
+ *
+ * Based on the arm32 version written by Vincent Guittot in turn based on
+ * arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/topology.h>
+
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+	per_cpu(cpu_scale, cpu) = power;
+}
+
+static int __init get_cpu_for_node(struct device_node *node)
+{
+	struct device_node *cpu_node;
+	int cpu;
+
+	cpu_node = of_parse_phandle(node, "cpu", 0);
+	if (!cpu_node)
+		return -1;
+
+	for_each_possible_cpu(cpu) {
+		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
+			of_node_put(cpu_node);
+			return cpu;
+		}
+	}
+
+	pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+
+	of_node_put(cpu_node);
+	return -1;
+}
+
+static int __init parse_core(struct device_node *core, int cluster_id,
+			     int core_id)
+{
+	char name[10];
+	bool leaf = true;
+	int i = 0;
+	int cpu;
+	struct device_node *t;
+
+	do {
+		snprintf(name, sizeof(name), "thread%d", i);
+		t = of_get_child_by_name(core, name);
+		if (t) {
+			leaf = false;
+			cpu = get_cpu_for_node(t);
+			if (cpu >= 0) {
+				cpu_topology[cpu].cluster_id = cluster_id;
+				cpu_topology[cpu].core_id = core_id;
+				cpu_topology[cpu].thread_id = i;
+			} else {
+				pr_err("%s: Can't get CPU for thread\n",
+				       t->full_name);
+				of_node_put(t);
+				return -EINVAL;
+			}
+			of_node_put(t);
+		}
+		i++;
+	} while (t);
+
+	cpu = get_cpu_for_node(core);
+	if (cpu >= 0) {
+		if (!leaf) {
+			pr_err("%s: Core has both threads and CPU\n",
+			       core->full_name);
+			return -EINVAL;
+		}
+
+		cpu_topology[cpu].cluster_id = cluster_id;
+		cpu_topology[cpu].core_id = core_id;
+	} else if (leaf) {
+		pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init parse_cluster(struct device_node *cluster, int depth)
+{
+	char name[10];
+	bool leaf = true;
+	bool has_cores = false;
+	struct device_node *c;
+	static int cluster_id __initdata;
+	int core_id = 0;
+	int i, ret;
+
+	/*
+	 * First check for child clusters; we currently ignore any
+	 * information about the nesting of clusters and present the
+	 * scheduler with a flat list of them.
+	 */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "cluster%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			leaf = false;
+			ret = parse_cluster(c, depth + 1);
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	/* Now check for cores */
+	i = 0;
+	do {
+		snprintf(name, sizeof(name), "core%d", i);
+		c = of_get_child_by_name(cluster, name);
+		if (c) {
+			has_cores = true;
+
+			if (depth == 0) {
+				pr_err("%s: cpu-map children should be clusters\n",
+				       c->full_name);
+				of_node_put(c);
+				return -EINVAL;
+			}
+
+			if (leaf) {
+				ret = parse_core(c, cluster_id, core_id++);
+			} else {
+				pr_err("%s: Non-leaf cluster with core %s\n",
+				       cluster->full_name, name);
+				ret = -EINVAL;
+			}
+
+			of_node_put(c);
+			if (ret != 0)
+				return ret;
+		}
+		i++;
+	} while (c);
+
+	if (leaf && !has_cores)
+		pr_warn("%s: empty cluster\n", cluster->full_name);
+
+	if (leaf)
+		cluster_id++;
+
+	return 0;
+}
+
+struct cpu_efficiency {
+	const char *compatible;
+	unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+static const struct cpu_efficiency table_efficiency[] = {
+	{ "arm,cortex-a57", 3891 },
+	{ "arm,cortex-a53", 2048 },
+	{ NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu)	__cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to  (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
+static int __init parse_dt_topology(void)
+{
+	struct device_node *cn, *map;
+	int ret = 0;
+	int cpu;
+
+	cn = of_find_node_by_path("/cpus");
+	if (!cn) {
+		pr_err("No CPU information found in DT\n");
+		return 0;
+	}
+
+	/*
+	 * When topology is provided cpu-map is essentially a root
+	 * cluster with restricted subnodes.
+	 */
+	map = of_get_child_by_name(cn, "cpu-map");
+	if (!map)
+		goto out;
+
+	ret = parse_cluster(map, 0);
+	if (ret != 0)
+		goto out_map;
+
+	/*
+	 * Check that all cores are in the topology; the SMP code will
+	 * only mark cores described in the DT as possible.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (cpu_topology[cpu].cluster_id == -1) {
+			pr_err("CPU%d: No topology information specified\n",
+			       cpu);
+			ret = -EINVAL;
+		}
+	}
+
+out_map:
+	of_node_put(map);
+out:
+	of_node_put(cn);
+	return ret;
+}
+
+static void __init parse_dt_cpu_power(void)
+{
+	const struct cpu_efficiency *cpu_eff;
+	struct device_node *cn;
+	unsigned long min_capacity = ULONG_MAX;
+	unsigned long max_capacity = 0;
+	unsigned long capacity = 0;
+	int cpu;
+
+	__cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
+				 GFP_NOWAIT);
+
+	for_each_possible_cpu(cpu) {
+		const u32 *rate;
+		int len;
+
+		/* Too early to use cpu->of_node */
+		cn = of_get_cpu_node(cpu, NULL);
+		if (!cn) {
+			pr_err("Missing device node for CPU %d\n", cpu);
+			continue;
+		}
+
+		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+			if (of_device_is_compatible(cn, cpu_eff->compatible))
+				break;
+
+		if (cpu_eff->compatible == NULL) {
+			pr_warn("%s: Unknown CPU type\n", cn->full_name);
+			continue;
+		}
+
+		rate = of_get_property(cn, "clock-frequency", &len);
+		if (!rate || len != 4) {
+			pr_err("%s: Missing clock-frequency property\n",
+				cn->full_name);
+			continue;
+		}
+
+		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+		/* Save min capacity of the system */
+		if (capacity < min_capacity)
+			min_capacity = capacity;
+
+		/* Save max capacity of the system */
+		if (capacity > max_capacity)
+			max_capacity = capacity;
+
+		cpu_capacity(cpu) = capacity;
+	}
+
+	/* If min and max capacities are equal we bypass the update of the
+	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
+	 * compute a middle_capacity factor that will ensure that the capacity
+	 * of an 'average' CPU of the system will be as close as possible to
+	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * constraint explained near table_efficiency[].
+	 */
+	if (min_capacity == max_capacity)
+		return;
+	else if (4 * max_capacity < (3 * (max_capacity + min_capacity)))
+		middle_capacity = (min_capacity + max_capacity)
+				>> (SCHED_POWER_SHIFT+1);
+	else
+		middle_capacity = ((max_capacity / 3)
+				>> (SCHED_POWER_SHIFT-1)) + 1;
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_topo_data table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+static void update_cpu_power(unsigned int cpu)
+{
+	if (!cpu_capacity(cpu))
+		return;
+
+	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+
+	pr_info("CPU%u: update cpu_power %lu\n",
+		cpu, arch_scale_freq_power(NULL, cpu));
+}
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	if (cpuid_topo->cluster_id == -1) {
+		/*
+		 * DT does not contain topology information for this cpu.
+		 */
+		pr_debug("CPU%u: No topology information configured\n", cpuid);
+		return;
+	}
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+	update_siblings_masks(cpuid);
+	update_cpu_power(cpuid);
+}
+
+#ifdef CONFIG_SCHED_HMP
+
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ *  - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
+
+static const char * const little_cores[] = {
+	"arm,cortex-a53",
+	NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+	const char * const *lc;
+	for (lc = little_cores; *lc; lc++)
+		if (of_device_is_compatible(cn, *lc))
+			return true;
+	return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+					struct cpumask *slow)
+{
+	struct device_node *cn = NULL;
+	int cpu;
+
+	cpumask_clear(fast);
+	cpumask_clear(slow);
+
+	/*
+	 * Use the config options if they are given. This helps testing
+	 * HMP scheduling on systems without a big.LITTLE architecture.
+	 */
+	if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+		if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+			WARN(1, "Failed to parse HMP fast cpu mask!\n");
+		if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+			WARN(1, "Failed to parse HMP slow cpu mask!\n");
+		return;
+	}
+
+	/*
+	 * Else, parse device tree for little cores.
+	 */
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+		const u32 *mpidr;
+		int len;
+
+		mpidr = of_get_property(cn, "reg", &len);
+		if (!mpidr || len != 8) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		cpu = get_logical_index(be32_to_cpup(mpidr+1));
+		if (cpu == -EINVAL) {
+			pr_err("couldn't get logical index for mpidr %x\n",
+							be32_to_cpup(mpidr+1));
+			break;
+		}
+
+		if (is_little_cpu(cn))
+			cpumask_set_cpu(cpu, slow);
+		else
+			cpumask_set_cpu(cpu, fast);
+	}
+
+	if (!cpumask_empty(fast) && !cpumask_empty(slow))
+		return;
+
+	/*
+	 * We didn't find both big and little cores so let's call all cores
+	 * fast as this will keep the system running, with all cores being
+	 * treated equal.
+	 */
+	cpumask_setall(fast);
+	cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+	struct cpumask hmp_fast_cpu_mask;
+	struct hmp_domain *domain;
+
+	arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+	/*
+	 * Initialize hmp_domains
+	 * Must be ordered with respect to compute capacity.
+	 * Fastest domain at head of list.
+	 */
+	if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+		domain = (struct hmp_domain *)
+			kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+		cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+		cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+		list_add(&domain->hmp_domains, hmp_domains_list);
+	}
+	domain = (struct hmp_domain *)
+		kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+	cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+	cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+	list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+static void __init reset_cpu_topology(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+		cpu_topo->thread_id = -1;
+		cpu_topo->core_id = 0;
+		cpu_topo->cluster_id = -1;
+
+		cpumask_clear(&cpu_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
+		cpumask_clear(&cpu_topo->thread_sibling);
+		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+	}
+}
+
+static void __init reset_cpu_power(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		set_power_scale(cpu, SCHED_POWER_SCALE);
+}
+
+void __init init_cpu_topology(void)
+{
+	reset_cpu_topology();
+
+	/*
+	 * Discard anything that was parsed if we hit an error so we
+	 * don't use partial information.
+	 */
+	if (parse_dt_topology())
+		reset_cpu_topology();
+
+	reset_cpu_power();
+	parse_dt_cpu_power();
+}
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index a7149cae1615..7931d6916683 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -156,11 +156,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 				int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
-	unsigned long vdso_base, vdso_mapping_len;
+	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
 	int ret;
 
+	vdso_text_len = vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = (vdso_pages + 1) << PAGE_SHIFT;
+	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
 
 	down_write(&mm->mmap_sem);
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
@@ -170,35 +171,52 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	}
 	mm->context.vdso = (void *)vdso_base;
 
-	ret = install_special_mapping(mm, vdso_base, vdso_mapping_len,
+	ret = install_special_mapping(mm, vdso_base, vdso_text_len,
 				      VM_READ|VM_EXEC|
 				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
 				      vdso_pagelist);
-	if (ret) {
-		mm->context.vdso = NULL;
+	if (ret)
+		goto up_fail;
+
+	vdso_base += vdso_text_len;
+	ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
+				      VM_READ|VM_MAYREAD,
+				      vdso_pagelist + vdso_pages);
+	if (ret)
 		goto up_fail;
-	}
 
-up_fail:
 	up_write(&mm->mmap_sem);
+	return 0;
 
+up_fail:
+	mm->context.vdso = NULL;
+	up_write(&mm->mmap_sem);
 	return ret;
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
+	unsigned long vdso_text;
+
+	if (!vma->vm_mm)
+		return NULL;
+
+	vdso_text = (unsigned long)vma->vm_mm->context.vdso;
+
 	/*
 	 * We can re-use the vdso pointer in mm_context_t for identifying
 	 * the vectors page for compat applications. The vDSO will always
 	 * sit above TASK_UNMAPPED_BASE and so we don't need to worry about
 	 * it conflicting with the vectors base.
 	 */
-	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) {
+	if (vma->vm_start == vdso_text) {
 #ifdef CONFIG_COMPAT
 		if (vma->vm_start == AARCH32_VECTORS_BASE)
 			return "[vectors]";
 #endif
 		return "[vdso]";
+	} else if (vma->vm_start == (vdso_text + (vdso_pages << PAGE_SHIFT))) {
+		return "[vvar]";
 	}
 
 	return NULL;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 6d20b7d162d8..84b942612051 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -47,9 +47,9 @@ $(obj-vdso): %.o: %.S
 	$(call if_changed_dep,vdsoas)
 
 # Actual build commands
-quiet_cmd_vdsold = VDSOL $@
+quiet_cmd_vdsold = VDSOL   $@
       cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
-quiet_cmd_vdsoas = VDSOA $@
+quiet_cmd_vdsoas = VDSOA   $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
 # Install commands for the unstripped file
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 4ba7a55b49c7..51258bc4cb08 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -104,6 +104,13 @@ SECTIONS
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
+
+	. = ALIGN(PAGE_SIZE);
+	idmap_pg_dir = .;
+	. += IDMAP_DIR_SIZE;
+	swapper_pg_dir = .;
+	. += SWAPPER_DIR_SIZE;
+
 	_end = .;
 
 	STABS_DEBUG
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 72a9fd583ad3..32a096174b94 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -20,4 +20,8 @@ kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o
 
 kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o
 kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 08745578d54d..76794692c20b 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -136,13 +136,67 @@ static unsigned long num_core_regs(void)
 }
 
 /**
+ * ARM64 versions of the TIMER registers, always available on arm64
+ */
+
+#define NUM_TIMER_REGS 3
+
+static bool is_timer_reg(u64 index)
+{
+	switch (index) {
+	case KVM_REG_ARM_TIMER_CTL:
+	case KVM_REG_ARM_TIMER_CNT:
+	case KVM_REG_ARM_TIMER_CVAL:
+		return true;
+	}
+	return false;
+}
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+	if (put_user(KVM_REG_ARM_TIMER_CTL, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CNT, uindices))
+		return -EFAULT;
+	uindices++;
+	if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+	int ret;
+
+	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
+	if (ret != 0)
+		return -EFAULT;
+
+	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
+}
+
+static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+	void __user *uaddr = (void __user *)(long)reg->addr;
+	u64 val;
+
+	val = kvm_arm_timer_get_reg(vcpu, reg->id);
+	return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+}
+
+/**
  * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG
  *
  * This is for all registers.
  */
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 {
-	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu);
+	return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
+                + NUM_TIMER_REGS;
 }
 
 /**
@@ -154,6 +208,7 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
 	unsigned int i;
 	const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE;
+	int ret;
 
 	for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) {
 		if (put_user(core_reg | i, uindices))
@@ -161,6 +216,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 		uindices++;
 	}
 
+	ret = copy_timer_indices(vcpu, uindices);
+	if (ret)
+		return ret;
+	uindices += NUM_TIMER_REGS;
+
 	return kvm_arm_copy_sys_reg_indices(vcpu, uindices);
 }
 
@@ -174,6 +234,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return get_core_reg(vcpu, reg);
 
+	if (is_timer_reg(reg->id))
+		return get_timer_reg(vcpu, reg);
+
 	return kvm_arm_sys_reg_get_reg(vcpu, reg);
 }
 
@@ -187,6 +250,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
 		return set_core_reg(vcpu, reg);
 
+	if (is_timer_reg(reg->id))
+		return set_timer_reg(vcpu, reg);
+
 	return kvm_arm_sys_reg_set_reg(vcpu, reg);
 }
 
@@ -214,6 +280,8 @@ int __attribute_const__ kvm_target_cpu(void)
 			return KVM_ARM_TARGET_AEM_V8;
 		case ARM_CPU_PART_FOUNDATION:
 			return KVM_ARM_TARGET_FOUNDATION_V8;
+		case ARM_CPU_PART_CORTEX_A53:
+			return KVM_ARM_TARGET_CORTEX_A53;
 		case ARM_CPU_PART_CORTEX_A57:
 			return KVM_ARM_TARGET_CORTEX_A57;
 		};
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 7bc41eab4c64..34b8bd0711e9 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -30,11 +30,15 @@ typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
 
 static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	if (kvm_psci_call(vcpu))
+	int ret;
+
+	ret = kvm_psci_call(vcpu);
+	if (ret < 0) {
+		kvm_inject_undefined(vcpu);
 		return 1;
+	}
 
-	kvm_inject_undefined(vcpu);
-	return 1;
+	return ret;
 }
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
@@ -62,6 +66,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	else
 		kvm_vcpu_block(vcpu);
 
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 1;
 }
 
@@ -69,9 +75,9 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_EL2_EC_WFI]	= kvm_handle_wfx,
 	[ESR_EL2_EC_CP15_32]	= kvm_handle_cp15_32,
 	[ESR_EL2_EC_CP15_64]	= kvm_handle_cp15_64,
-	[ESR_EL2_EC_CP14_MR]	= kvm_handle_cp14_access,
+	[ESR_EL2_EC_CP14_MR]	= kvm_handle_cp14_32,
 	[ESR_EL2_EC_CP14_LS]	= kvm_handle_cp14_load_store,
-	[ESR_EL2_EC_CP14_64]	= kvm_handle_cp14_access,
+	[ESR_EL2_EC_CP14_64]	= kvm_handle_cp14_64,
 	[ESR_EL2_EC_HVC32]	= handle_hvc,
 	[ESR_EL2_EC_SMC32]	= handle_smc,
 	[ESR_EL2_EC_HVC64]	= handle_hvc,
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 2b0244d65c16..c3191168a994 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -68,12 +68,22 @@ __do_hyp_init:
 	msr	tcr_el2, x4
 
 	ldr	x4, =VTCR_EL2_FLAGS
+	/*
+	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
+	 * VTCR_EL2.
+	 */
+	mrs	x5, ID_AA64MMFR0_EL1
+	bfi	x4, x5, #16, #3
 	msr	vtcr_el2, x4
 
 	mrs	x4, mair_el1
 	msr	mair_el2, x4
 	isb
 
+	/* Invalidate the stale TLBs from Bootloader */
+	tlbi	alle2
+	dsb	sy
+
 	mrs	x4, sctlr_el2
 	and	x4, x4, #SCTLR_EL2_EE	// preserve endianness of EL2
 	ldr	x5, =SCTLR_EL2_FLAGS
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 2c56012cb2d2..b72aa9f9215c 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -16,11 +16,11 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/irqchip/arm-gic.h>
 
 #include <asm/assembler.h>
 #include <asm/memory.h>
 #include <asm/asm-offsets.h>
+#include <asm/debug-monitors.h>
 #include <asm/fpsimdmacros.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
@@ -36,9 +36,6 @@
 	.pushsection	.hyp.text, "ax"
 	.align	PAGE_SHIFT
 
-__kvm_hyp_code_start:
-	.globl __kvm_hyp_code_start
-
 .macro save_common_regs
 	// x2: base address for cpu context
 	// x3: tmp register
@@ -215,6 +212,7 @@ __kvm_hyp_code_start:
 	mrs	x22, 	amair_el1
 	mrs	x23, 	cntkctl_el1
 	mrs	x24,	par_el1
+	mrs	x25,	mdscr_el1
 
 	stp	x4, x5, [x3]
 	stp	x6, x7, [x3, #16]
@@ -226,7 +224,202 @@ __kvm_hyp_code_start:
 	stp	x18, x19, [x3, #112]
 	stp	x20, x21, [x3, #128]
 	stp	x22, x23, [x3, #144]
-	str	x24, [x3, #160]
+	stp	x24, x25, [x3, #160]
+.endm
+
+.macro save_debug
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgbcr15_el1
+	mrs	x19, dbgbcr14_el1
+	mrs	x18, dbgbcr13_el1
+	mrs	x17, dbgbcr12_el1
+	mrs	x16, dbgbcr11_el1
+	mrs	x15, dbgbcr10_el1
+	mrs	x14, dbgbcr9_el1
+	mrs	x13, dbgbcr8_el1
+	mrs	x12, dbgbcr7_el1
+	mrs	x11, dbgbcr6_el1
+	mrs	x10, dbgbcr5_el1
+	mrs	x9, dbgbcr4_el1
+	mrs	x8, dbgbcr3_el1
+	mrs	x7, dbgbcr2_el1
+	mrs	x6, dbgbcr1_el1
+	mrs	x5, dbgbcr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgbvr15_el1
+	mrs	x19, dbgbvr14_el1
+	mrs	x18, dbgbvr13_el1
+	mrs	x17, dbgbvr12_el1
+	mrs	x16, dbgbvr11_el1
+	mrs	x15, dbgbvr10_el1
+	mrs	x14, dbgbvr9_el1
+	mrs	x13, dbgbvr8_el1
+	mrs	x12, dbgbvr7_el1
+	mrs	x11, dbgbvr6_el1
+	mrs	x10, dbgbvr5_el1
+	mrs	x9, dbgbvr4_el1
+	mrs	x8, dbgbvr3_el1
+	mrs	x7, dbgbvr2_el1
+	mrs	x6, dbgbvr1_el1
+	mrs	x5, dbgbvr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgwcr15_el1
+	mrs	x19, dbgwcr14_el1
+	mrs	x18, dbgwcr13_el1
+	mrs	x17, dbgwcr12_el1
+	mrs	x16, dbgwcr11_el1
+	mrs	x15, dbgwcr10_el1
+	mrs	x14, dbgwcr9_el1
+	mrs	x13, dbgwcr8_el1
+	mrs	x12, dbgwcr7_el1
+	mrs	x11, dbgwcr6_el1
+	mrs	x10, dbgwcr5_el1
+	mrs	x9, dbgwcr4_el1
+	mrs	x8, dbgwcr3_el1
+	mrs	x7, dbgwcr2_el1
+	mrs	x6, dbgwcr1_el1
+	mrs	x5, dbgwcr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	mrs	x20, dbgwvr15_el1
+	mrs	x19, dbgwvr14_el1
+	mrs	x18, dbgwvr13_el1
+	mrs	x17, dbgwvr12_el1
+	mrs	x16, dbgwvr11_el1
+	mrs	x15, dbgwvr10_el1
+	mrs	x14, dbgwvr9_el1
+	mrs	x13, dbgwvr8_el1
+	mrs	x12, dbgwvr7_el1
+	mrs	x11, dbgwvr6_el1
+	mrs	x10, dbgwvr5_el1
+	mrs	x9, dbgwvr4_el1
+	mrs	x8, dbgwvr3_el1
+	mrs	x7, dbgwvr2_el1
+	mrs	x6, dbgwvr1_el1
+	mrs	x5, dbgwvr0_el1
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+
+1:
+	str	x20, [x3, #(15 * 8)]
+	str	x19, [x3, #(14 * 8)]
+	str	x18, [x3, #(13 * 8)]
+	str	x17, [x3, #(12 * 8)]
+	str	x16, [x3, #(11 * 8)]
+	str	x15, [x3, #(10 * 8)]
+	str	x14, [x3, #(9 * 8)]
+	str	x13, [x3, #(8 * 8)]
+	str	x12, [x3, #(7 * 8)]
+	str	x11, [x3, #(6 * 8)]
+	str	x10, [x3, #(5 * 8)]
+	str	x9, [x3, #(4 * 8)]
+	str	x8, [x3, #(3 * 8)]
+	str	x7, [x3, #(2 * 8)]
+	str	x6, [x3, #(1 * 8)]
+	str	x5, [x3, #(0 * 8)]
+
+	mrs	x21, mdccint_el1
+	str	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
 .endm
 
 .macro restore_sysregs
@@ -245,7 +438,7 @@ __kvm_hyp_code_start:
 	ldp	x18, x19, [x3, #112]
 	ldp	x20, x21, [x3, #128]
 	ldp	x22, x23, [x3, #144]
-	ldr	x24, [x3, #160]
+	ldp	x24, x25, [x3, #160]
 
 	msr	vmpidr_el2,	x4
 	msr	csselr_el1,	x5
@@ -268,6 +461,198 @@ __kvm_hyp_code_start:
 	msr	amair_el1,	x22
 	msr	cntkctl_el1,	x23
 	msr	par_el1,	x24
+	msr	mdscr_el1,	x25
+.endm
+
+.macro restore_debug
+	// x2: base address for cpu context
+	// x3: tmp register
+
+	mrs	x26, id_aa64dfr0_el1
+	ubfx	x24, x26, #12, #4	// Extract BRPs
+	ubfx	x25, x26, #20, #4	// Extract WRPs
+	mov	w26, #15
+	sub	w24, w26, w24		// How many BPs to skip
+	sub	w25, w26, w25		// How many WPs to skip
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	msr	dbgbcr15_el1, x20
+	msr	dbgbcr14_el1, x19
+	msr	dbgbcr13_el1, x18
+	msr	dbgbcr12_el1, x17
+	msr	dbgbcr11_el1, x16
+	msr	dbgbcr10_el1, x15
+	msr	dbgbcr9_el1, x14
+	msr	dbgbcr8_el1, x13
+	msr	dbgbcr7_el1, x12
+	msr	dbgbcr6_el1, x11
+	msr	dbgbcr5_el1, x10
+	msr	dbgbcr4_el1, x9
+	msr	dbgbcr3_el1, x8
+	msr	dbgbcr2_el1, x7
+	msr	dbgbcr1_el1, x6
+	msr	dbgbcr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x24, lsl #2
+	br	x26
+1:
+	msr	dbgbvr15_el1, x20
+	msr	dbgbvr14_el1, x19
+	msr	dbgbvr13_el1, x18
+	msr	dbgbvr12_el1, x17
+	msr	dbgbvr11_el1, x16
+	msr	dbgbvr10_el1, x15
+	msr	dbgbvr9_el1, x14
+	msr	dbgbvr8_el1, x13
+	msr	dbgbvr7_el1, x12
+	msr	dbgbvr6_el1, x11
+	msr	dbgbvr5_el1, x10
+	msr	dbgbvr4_el1, x9
+	msr	dbgbvr3_el1, x8
+	msr	dbgbvr2_el1, x7
+	msr	dbgbvr1_el1, x6
+	msr	dbgbvr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	msr	dbgwcr15_el1, x20
+	msr	dbgwcr14_el1, x19
+	msr	dbgwcr13_el1, x18
+	msr	dbgwcr12_el1, x17
+	msr	dbgwcr11_el1, x16
+	msr	dbgwcr10_el1, x15
+	msr	dbgwcr9_el1, x14
+	msr	dbgwcr8_el1, x13
+	msr	dbgwcr7_el1, x12
+	msr	dbgwcr6_el1, x11
+	msr	dbgwcr5_el1, x10
+	msr	dbgwcr4_el1, x9
+	msr	dbgwcr3_el1, x8
+	msr	dbgwcr2_el1, x7
+	msr	dbgwcr1_el1, x6
+	msr	dbgwcr0_el1, x5
+
+	add	x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	ldr	x20, [x3, #(15 * 8)]
+	ldr	x19, [x3, #(14 * 8)]
+	ldr	x18, [x3, #(13 * 8)]
+	ldr	x17, [x3, #(12 * 8)]
+	ldr	x16, [x3, #(11 * 8)]
+	ldr	x15, [x3, #(10 * 8)]
+	ldr	x14, [x3, #(9 * 8)]
+	ldr	x13, [x3, #(8 * 8)]
+	ldr	x12, [x3, #(7 * 8)]
+	ldr	x11, [x3, #(6 * 8)]
+	ldr	x10, [x3, #(5 * 8)]
+	ldr	x9, [x3, #(4 * 8)]
+	ldr	x8, [x3, #(3 * 8)]
+	ldr	x7, [x3, #(2 * 8)]
+	ldr	x6, [x3, #(1 * 8)]
+	ldr	x5, [x3, #(0 * 8)]
+
+	adr	x26, 1f
+	add	x26, x26, x25, lsl #2
+	br	x26
+1:
+	msr	dbgwvr15_el1, x20
+	msr	dbgwvr14_el1, x19
+	msr	dbgwvr13_el1, x18
+	msr	dbgwvr12_el1, x17
+	msr	dbgwvr11_el1, x16
+	msr	dbgwvr10_el1, x15
+	msr	dbgwvr9_el1, x14
+	msr	dbgwvr8_el1, x13
+	msr	dbgwvr7_el1, x12
+	msr	dbgwvr6_el1, x11
+	msr	dbgwvr5_el1, x10
+	msr	dbgwvr4_el1, x9
+	msr	dbgwvr3_el1, x8
+	msr	dbgwvr2_el1, x7
+	msr	dbgwvr1_el1, x6
+	msr	dbgwvr0_el1, x5
+
+	ldr	x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+	msr	mdccint_el1, x21
 .endm
 
 .macro skip_32bit_state tmp, target
@@ -282,6 +667,35 @@ __kvm_hyp_code_start:
 	tbz	\tmp, #12, \target
 .endm
 
+.macro skip_debug_state tmp, target
+	ldr	\tmp, [x0, #VCPU_DEBUG_FLAGS]
+	tbz	\tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
+.endm
+
+.macro compute_debug_state target
+	// Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
+	// is set, we do a full save/restore cycle and disable trapping.
+	add	x25, x0, #VCPU_CONTEXT
+
+	// Check the state of MDSCR_EL1
+	ldr	x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)]
+	and	x26, x25, #DBG_MDSCR_KDE
+	and	x25, x25, #DBG_MDSCR_MDE
+	adds	xzr, x25, x26
+	b.eq	9998f		// Nothing to see there
+
+	// If any interesting bits was set, we must set the flag
+	mov	x26, #KVM_ARM64_DEBUG_DIRTY
+	str	x26, [x0, #VCPU_DEBUG_FLAGS]
+	b	9999f		// Don't skip restore
+
+9998:
+	// Otherwise load the flags from memory in case we recently
+	// trapped
+	skip_debug_state x25, \target
+9999:
+.endm
+
 .macro save_guest_32bit_state
 	skip_32bit_state x3, 1f
 
@@ -297,10 +711,13 @@ __kvm_hyp_code_start:
 	mrs	x4, dacr32_el2
 	mrs	x5, ifsr32_el2
 	mrs	x6, fpexc32_el2
-	mrs	x7, dbgvcr32_el2
 	stp	x4, x5, [x3]
-	stp	x6, x7, [x3, #16]
+	str	x6, [x3, #16]
 
+	skip_debug_state x8, 2f
+	mrs	x7, dbgvcr32_el2
+	str	x7, [x3, #24]
+2:
 	skip_tee_state x8, 1f
 
 	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
@@ -323,12 +740,15 @@ __kvm_hyp_code_start:
 
 	add	x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
 	ldp	x4, x5, [x3]
-	ldp	x6, x7, [x3, #16]
+	ldr	x6, [x3, #16]
 	msr	dacr32_el2, x4
 	msr	ifsr32_el2, x5
 	msr	fpexc32_el2, x6
-	msr	dbgvcr32_el2, x7
 
+	skip_debug_state x8, 2f
+	ldr	x7, [x3, #24]
+	msr	dbgvcr32_el2, x7
+2:
 	skip_tee_state x8, 1f
 
 	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
@@ -339,11 +759,8 @@ __kvm_hyp_code_start:
 .endm
 
 .macro activate_traps
-	ldr	x2, [x0, #VCPU_IRQ_LINES]
-	ldr	x1, [x0, #VCPU_HCR_EL2]
-	orr	x2, x2, x1
-	msr	hcr_el2, x2
-
+	ldr     x2, [x0, #VCPU_HCR_EL2]
+	msr     hcr_el2, x2
 	ldr	x2, =(CPTR_EL2_TTA)
 	msr	cptr_el2, x2
 
@@ -353,6 +770,14 @@ __kvm_hyp_code_start:
 	mrs	x2, mdcr_el2
 	and	x2, x2, #MDCR_EL2_HPMN_MASK
 	orr	x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR)
+	orr	x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA)
+
+	// Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap
+	// if not dirty.
+	ldr	x3, [x0, #VCPU_DEBUG_FLAGS]
+	tbnz	x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f
+	orr	x2, x2,  #MDCR_EL2_TDA
+1:
 	msr	mdcr_el2, x2
 .endm
 
@@ -379,100 +804,33 @@ __kvm_hyp_code_start:
 .endm
 
 /*
- * Save the VGIC CPU state into memory
- * x0: Register pointing to VCPU struct
- * Do not corrupt x1!!!
+ * Call into the vgic backend for state saving
  */
 .macro save_vgic_state
-	/* Get VGIC VCTRL base into x2 */
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va	x2
-	ldr	x2, [x2, #KVM_VGIC_VCTRL]
-	kern_hyp_va	x2
-	cbz	x2, 2f		// disabled
-
-	/* Compute the address of struct vgic_cpu */
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	/* Save all interesting registers */
-	ldr	w4, [x2, #GICH_HCR]
-	ldr	w5, [x2, #GICH_VMCR]
-	ldr	w6, [x2, #GICH_MISR]
-	ldr	w7, [x2, #GICH_EISR0]
-	ldr	w8, [x2, #GICH_EISR1]
-	ldr	w9, [x2, #GICH_ELRSR0]
-	ldr	w10, [x2, #GICH_ELRSR1]
-	ldr	w11, [x2, #GICH_APR]
-CPU_BE(	rev	w4,  w4  )
-CPU_BE(	rev	w5,  w5  )
-CPU_BE(	rev	w6,  w6  )
-CPU_BE(	rev	w7,  w7  )
-CPU_BE(	rev	w8,  w8  )
-CPU_BE(	rev	w9,  w9  )
-CPU_BE(	rev	w10, w10 )
-CPU_BE(	rev	w11, w11 )
-
-	str	w4, [x3, #VGIC_CPU_HCR]
-	str	w5, [x3, #VGIC_CPU_VMCR]
-	str	w6, [x3, #VGIC_CPU_MISR]
-	str	w7, [x3, #VGIC_CPU_EISR]
-	str	w8, [x3, #(VGIC_CPU_EISR + 4)]
-	str	w9, [x3, #VGIC_CPU_ELRSR]
-	str	w10, [x3, #(VGIC_CPU_ELRSR + 4)]
-	str	w11, [x3, #VGIC_CPU_APR]
-
-	/* Clear GICH_HCR */
-	str	wzr, [x2, #GICH_HCR]
-
-	/* Save list registers */
-	add	x2, x2, #GICH_LR0
-	ldr	w4, [x3, #VGIC_CPU_NR_LR]
-	add	x3, x3, #VGIC_CPU_LR
-1:	ldr	w5, [x2], #4
-CPU_BE(	rev	w5, w5 )
-	str	w5, [x3], #4
-	sub	w4, w4, #1
-	cbnz	w4, 1b
-2:
+	adr	x24, __vgic_sr_vectors
+	ldr	x24, [x24, VGIC_SAVE_FN]
+	kern_hyp_va	x24
+	blr	x24
+	mrs	x24, hcr_el2
+	mov	x25, #HCR_INT_OVERRIDE
+	neg	x25, x25
+	and	x24, x24, x25
+	msr	hcr_el2, x24
 .endm
 
 /*
- * Restore the VGIC CPU state from memory
- * x0: Register pointing to VCPU struct
+ * Call into the vgic backend for state restoring
  */
 .macro restore_vgic_state
-	/* Get VGIC VCTRL base into x2 */
-	ldr	x2, [x0, #VCPU_KVM]
-	kern_hyp_va	x2
-	ldr	x2, [x2, #KVM_VGIC_VCTRL]
-	kern_hyp_va	x2
-	cbz	x2, 2f		// disabled
-
-	/* Compute the address of struct vgic_cpu */
-	add	x3, x0, #VCPU_VGIC_CPU
-
-	/* We only restore a minimal set of registers */
-	ldr	w4, [x3, #VGIC_CPU_HCR]
-	ldr	w5, [x3, #VGIC_CPU_VMCR]
-	ldr	w6, [x3, #VGIC_CPU_APR]
-CPU_BE(	rev	w4, w4 )
-CPU_BE(	rev	w5, w5 )
-CPU_BE(	rev	w6, w6 )
-
-	str	w4, [x2, #GICH_HCR]
-	str	w5, [x2, #GICH_VMCR]
-	str	w6, [x2, #GICH_APR]
-
-	/* Restore list registers */
-	add	x2, x2, #GICH_LR0
-	ldr	w4, [x3, #VGIC_CPU_NR_LR]
-	add	x3, x3, #VGIC_CPU_LR
-1:	ldr	w5, [x3], #4
-CPU_BE(	rev	w5, w5 )
-	str	w5, [x2], #4
-	sub	w4, w4, #1
-	cbnz	w4, 1b
-2:
+	mrs	x24, hcr_el2
+	ldr	x25, [x0, #VCPU_IRQ_LINES]
+	orr	x24, x24, #HCR_INT_OVERRIDE
+	orr	x24, x24, x25
+	msr	hcr_el2, x24
+	adr	x24, __vgic_sr_vectors
+	ldr	x24, [x24, #VGIC_RESTORE_FN]
+	kern_hyp_va	x24
+	blr	x24
 .endm
 
 .macro save_timer_state
@@ -537,6 +895,14 @@ __restore_sysregs:
 	restore_sysregs
 	ret
 
+__save_debug:
+	save_debug
+	ret
+
+__restore_debug:
+	restore_debug
+	ret
+
 __save_fpsimd:
 	save_fpsimd
 	ret
@@ -568,6 +934,9 @@ ENTRY(__kvm_vcpu_run)
 	bl __save_fpsimd
 	bl __save_sysregs
 
+	compute_debug_state 1f
+	bl	__save_debug
+1:
 	activate_traps
 	activate_vm
 
@@ -579,6 +948,10 @@ ENTRY(__kvm_vcpu_run)
 
 	bl __restore_sysregs
 	bl __restore_fpsimd
+
+	skip_debug_state x3, 1f
+	bl	__restore_debug
+1:
 	restore_guest_32bit_state
 	restore_guest_regs
 
@@ -595,6 +968,10 @@ __kvm_vcpu_return:
 	save_guest_regs
 	bl __save_fpsimd
 	bl __save_sysregs
+
+	skip_debug_state x3, 1f
+	bl	__save_debug
+1:
 	save_guest_32bit_state
 
 	save_timer_state
@@ -609,6 +986,14 @@ __kvm_vcpu_return:
 
 	bl __restore_sysregs
 	bl __restore_fpsimd
+
+	skip_debug_state x3, 1f
+	// Clear the dirty flag for the next run, as all the state has
+	// already been saved. Note that we nuke the whole 64bit word.
+	// If we ever add more flags, we'll have to be more careful...
+	str	xzr, [x0, #VCPU_DEBUG_FLAGS]
+	bl	__restore_debug
+1:
 	restore_host_regs
 
 	mov	x0, x1
@@ -630,9 +1015,15 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	 * whole of Stage-1. Weep...
 	 */
 	tlbi	ipas2e1is, x1
-	dsb	sy
+	/*
+	 * We have to ensure completion of the invalidation at Stage-2,
+	 * since a table walk on another CPU could refill a TLB with a
+	 * complete (S1 + S2) walk based on the old Stage-2 mapping if
+	 * the Stage-1 invalidation happened first.
+	 */
+	dsb	ish
 	tlbi	vmalle1is
-	dsb	sy
+	dsb	ish
 	isb
 
 	msr	vttbr_el2, xzr
@@ -643,10 +1034,16 @@ ENTRY(__kvm_flush_vm_context)
 	dsb	ishst
 	tlbi	alle1is
 	ic	ialluis
-	dsb	sy
+	dsb	ish
 	ret
 ENDPROC(__kvm_flush_vm_context)
 
+	// struct vgic_sr_vectors __vgi_sr_vectors;
+	.align 3
+ENTRY(__vgic_sr_vectors)
+	.skip	VGIC_SR_VECTOR_SZ
+ENDPROC(__vgic_sr_vectors)
+
 __kvm_hyp_panic:
 	// Guess the context by looking at VTTBR:
 	// If zero, then we're already a host.
@@ -824,7 +1221,7 @@ el1_trap:
 	mrs	x2, far_el2
 
 2:	mrs	x0, tpidr_el2
-	str	x1, [x0, #VCPU_ESR_EL2]
+	str	w1, [x0, #VCPU_ESR_EL2]
 	str	x2, [x0, #VCPU_FAR_EL2]
 	str	x3, [x0, #VCPU_HPFAR_EL2]
 
@@ -874,7 +1271,4 @@ ENTRY(__kvm_hyp_vector)
 	ventry	el1_error_invalid		// Error 32-bit EL1
 ENDPROC(__kvm_hyp_vector)
 
-__kvm_hyp_code_end:
-	.globl	__kvm_hyp_code_end
-
 	.popsection
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 02e9d09e1d80..4cc3b719208e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -27,8 +27,10 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/debug-monitors.h>
 #include <trace/events/kvm.h>
 
 #include "sys_regs.h"
@@ -70,13 +72,13 @@ static u32 get_ccsidr(u32 csselr)
 static void do_dc_cisw(u32 val)
 {
 	asm volatile("dc cisw, %x0" : : "r" (val));
-	dsb();
+	dsb(ish);
 }
 
 static void do_dc_csw(u32 val)
 {
 	asm volatile("dc csw, %x0" : : "r" (val));
-	dsb();
+	dsb(ish);
 }
 
 /* See note at ARM ARM B1.14.4 */
@@ -121,17 +123,51 @@ done:
 }
 
 /*
- * We could trap ID_DFR0 and tell the guest we don't support performance
- * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
- * NAKed, so it will read the PMCR anyway.
- *
- * Therefore we tell the guest we have 0 counters.  Unfortunately, we
- * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
- * all PM registers, which doesn't crash the guest kernel at least.
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+			  const struct sys_reg_params *p,
+			  const struct sys_reg_desc *r)
+{
+	unsigned long val;
+
+	BUG_ON(!p->is_write);
+
+	val = *vcpu_reg(vcpu, p->Rt);
+	if (!p->is_aarch32) {
+		vcpu_sys_reg(vcpu, r->reg) = val;
+	} else {
+		if (!p->is_32bit)
+			vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
+		vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
+	}
+
+	return true;
+}
+
+/*
+ * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set.  If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
  */
-static bool pm_fake(struct kvm_vcpu *vcpu,
-		    const struct sys_reg_params *p,
-		    const struct sys_reg_desc *r)
+static bool access_sctlr(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	access_vm_reg(vcpu, p, r);
+
+	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
+		vcpu->arch.hcr_el2 &= ~HCR_TVM;
+		stage2_flush_vm(vcpu->kvm);
+	}
+
+	return true;
+}
+
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
+			const struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
 {
 	if (p->is_write)
 		return ignore_write(vcpu, p);
@@ -139,6 +175,73 @@ static bool pm_fake(struct kvm_vcpu *vcpu,
 		return read_zero(vcpu, p);
 }
 
+static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = (1 << 3);
+		return true;
+	}
+}
+
+static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
+				   const struct sys_reg_params *p,
+				   const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		u32 val;
+		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
+		*vcpu_reg(vcpu, p->Rt) = val;
+		return true;
+	}
+}
+
+/*
+ * We want to avoid world-switching all the DBG registers all the
+ * time:
+ * 
+ * - If we've touched any debug register, it is likely that we're
+ *   going to touch more of them. It then makes sense to disable the
+ *   traps and start doing the save/restore dance
+ * - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
+ *   then mandatory to save/restore the registers, as the guest
+ *   depends on them.
+ * 
+ * For this, we use a DIRTY bit, indicating the guest has modified the
+ * debug registers, used as follow:
+ *
+ * On guest entry:
+ * - If the dirty bit is set (because we're coming back from trapping),
+ *   disable the traps, save host registers, restore guest registers.
+ * - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
+ *   set the dirty bit, disable the traps, save host registers,
+ *   restore guest registers.
+ * - Otherwise, enable the traps
+ *
+ * On guest exit:
+ * - If the dirty bit is set, save guest registers, restore host
+ *   registers and clear the dirty bit. This ensure that the host can
+ *   now use the debug registers.
+ */
+static bool trap_debug_regs(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+	}
+
+	return true;
+}
+
 static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 amair;
@@ -155,9 +258,39 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
 }
 
+/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
+#define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
+	/* DBGBVRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100),	\
+	  trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 },		\
+	/* DBGBCRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101),	\
+	  trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 },		\
+	/* DBGWVRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110),	\
+	  trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 },		\
+	/* DBGWCRn_EL1 */						\
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111),	\
+	  trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
+
 /*
  * Architected system registers.
  * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * We could trap ID_DFR0 and tell the guest we don't support performance
+ * monitoring.  Unfortunately the patch to make the kernel check ID_DFR0 was
+ * NAKed, so it will read the PMCR anyway.
+ *
+ * Therefore we tell the guest we have 0 counters.  Unfortunately, we
+ * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
+ * all PM registers, which doesn't crash the guest kernel at least.
+ *
+ * Debug handling: We do trap most, if not all debug related system
+ * registers. The implementation is good enough to ensure that a guest
+ * can use these with minimal performance degradation. The drawback is
+ * that we don't implement any of the external debug, none of the
+ * OSlock protocol. This should be revisited if we ever encounter a
+ * more demanding guest...
  */
 static const struct sys_reg_desc sys_reg_descs[] = {
 	/* DC ISW */
@@ -170,12 +303,71 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
 	  access_dcsw },
 
+	DBG_BCR_BVR_WCR_WVR_EL1(0),
+	DBG_BCR_BVR_WCR_WVR_EL1(1),
+	/* MDCCINT_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
+	  trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
+	/* MDSCR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
+	  trap_debug_regs, reset_val, MDSCR_EL1, 0 },
+	DBG_BCR_BVR_WCR_WVR_EL1(2),
+	DBG_BCR_BVR_WCR_WVR_EL1(3),
+	DBG_BCR_BVR_WCR_WVR_EL1(4),
+	DBG_BCR_BVR_WCR_WVR_EL1(5),
+	DBG_BCR_BVR_WCR_WVR_EL1(6),
+	DBG_BCR_BVR_WCR_WVR_EL1(7),
+	DBG_BCR_BVR_WCR_WVR_EL1(8),
+	DBG_BCR_BVR_WCR_WVR_EL1(9),
+	DBG_BCR_BVR_WCR_WVR_EL1(10),
+	DBG_BCR_BVR_WCR_WVR_EL1(11),
+	DBG_BCR_BVR_WCR_WVR_EL1(12),
+	DBG_BCR_BVR_WCR_WVR_EL1(13),
+	DBG_BCR_BVR_WCR_WVR_EL1(14),
+	DBG_BCR_BVR_WCR_WVR_EL1(15),
+
+	/* MDRAR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
+	  trap_raz_wi },
+	/* OSLAR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
+	  trap_raz_wi },
+	/* OSLSR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
+	  trap_oslsr_el1 },
+	/* OSDLR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
+	  trap_raz_wi },
+	/* DBGPRCR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
+	  trap_raz_wi },
+	/* DBGCLAIMSET_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
+	  trap_raz_wi },
+	/* DBGCLAIMCLR_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
+	  trap_raz_wi },
+	/* DBGAUTHSTATUS_EL1 */
+	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
+	  trap_dbgauthstatus_el1 },
+
 	/* TEECR32_EL1 */
 	{ Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, TEECR32_EL1, 0 },
 	/* TEEHBR32_EL1 */
 	{ Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, TEEHBR32_EL1, 0 },
+
+	/* MDCCSR_EL1 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
+	  trap_raz_wi },
+	/* DBGDTR_EL0 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
+	  trap_raz_wi },
+	/* DBGDTR[TR]X_EL0 */
+	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
+	  trap_raz_wi },
+
 	/* DBGVCR32_EL2 */
 	{ Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
 	  NULL, reset_val, DBGVCR32_EL2, 0 },
@@ -185,56 +377,56 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_mpidr, MPIDR_EL1 },
 	/* SCTLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  NULL, reset_val, SCTLR_EL1, 0x00C50078 },
+	  access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 },
 	/* CPACR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
 	  NULL, reset_val, CPACR_EL1, 0 },
 	/* TTBR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, TTBR0_EL1 },
+	  access_vm_reg, reset_unknown, TTBR0_EL1 },
 	/* TTBR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
-	  NULL, reset_unknown, TTBR1_EL1 },
+	  access_vm_reg, reset_unknown, TTBR1_EL1 },
 	/* TCR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
-	  NULL, reset_val, TCR_EL1, 0 },
+	  access_vm_reg, reset_val, TCR_EL1, 0 },
 
 	/* AFSR0_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
-	  NULL, reset_unknown, AFSR0_EL1 },
+	  access_vm_reg, reset_unknown, AFSR0_EL1 },
 	/* AFSR1_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
-	  NULL, reset_unknown, AFSR1_EL1 },
+	  access_vm_reg, reset_unknown, AFSR1_EL1 },
 	/* ESR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, ESR_EL1 },
+	  access_vm_reg, reset_unknown, ESR_EL1 },
 	/* FAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
-	  NULL, reset_unknown, FAR_EL1 },
+	  access_vm_reg, reset_unknown, FAR_EL1 },
 	/* PAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
 	  NULL, reset_unknown, PAR_EL1 },
 
 	/* PMINTENSET_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMINTENCLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
-	  pm_fake },
+	  trap_raz_wi },
 
 	/* MAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
-	  NULL, reset_unknown, MAIR_EL1 },
+	  access_vm_reg, reset_unknown, MAIR_EL1 },
 	/* AMAIR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
-	  NULL, reset_amair_el1, AMAIR_EL1 },
+	  access_vm_reg, reset_amair_el1, AMAIR_EL1 },
 
 	/* VBAR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
 	  NULL, reset_val, VBAR_EL1, 0 },
 	/* CONTEXTIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
-	  NULL, reset_val, CONTEXTIDR_EL1, 0 },
+	  access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	/* TPIDR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
 	  NULL, reset_unknown, TPIDR_EL1 },
@@ -249,43 +441,43 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	/* PMCR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCNTENSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCNTENCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMOVSCLR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMSWINC_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMSELR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCEID0_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCEID1_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMCCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMXEVTYPER_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMXEVCNTR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMUSERENR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
-	  pm_fake },
+	  trap_raz_wi },
 	/* PMOVSSET_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
-	  pm_fake },
+	  trap_raz_wi },
 
 	/* TPIDR_EL0 */
 	{ Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
@@ -305,27 +497,205 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  NULL, reset_val, FPEXC32_EL2, 0x70 },
 };
 
-/* Trapped cp15 registers */
+static bool trap_dbgidr(struct kvm_vcpu *vcpu,
+			const struct sys_reg_params *p,
+			const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		return ignore_write(vcpu, p);
+	} else {
+		u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
+		u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
+		u32 el3 = !!((pfr >> 12) & 0xf);
+
+		*vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) |
+					  (((dfr >> 12) & 0xf) << 24) |
+					  (((dfr >> 28) & 0xf) << 20) |
+					  (6 << 16) | (el3 << 14) | (el3 << 12));
+		return true;
+	}
+}
+
+static bool trap_debug32(struct kvm_vcpu *vcpu,
+			 const struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
+{
+	if (p->is_write) {
+		vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+	} else {
+		*vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+	}
+
+	return true;
+}
+
+#define DBG_BCR_BVR_WCR_WVR(n)					\
+	/* DBGBVRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_debug32,	\
+	  NULL, (cp14_DBGBVR0 + (n) * 2) },			\
+	/* DBGBCRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_debug32,	\
+	  NULL, (cp14_DBGBCR0 + (n) * 2) },			\
+	/* DBGWVRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_debug32,	\
+	  NULL, (cp14_DBGWVR0 + (n) * 2) },			\
+	/* DBGWCRn */						\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_debug32,	\
+	  NULL, (cp14_DBGWCR0 + (n) * 2) }
+
+#define DBGBXVR(n)						\
+	{ Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_debug32,	\
+	  NULL, cp14_DBGBXVR0 + n * 2 }
+
+/*
+ * Trapped cp14 registers. We generally ignore most of the external
+ * debug, on the principle that they don't really make sense to a
+ * guest. Revisit this one day, whould this principle change.
+ */
+static const struct sys_reg_desc cp14_regs[] = {
+	/* DBGIDR */
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
+	/* DBGDTRRXext */
+	{ Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
+
+	DBG_BCR_BVR_WCR_WVR(0),
+	/* DBGDSCRint */
+	{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(1),
+	/* DBGDCCINT */
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+	/* DBGDSCRext */
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+	DBG_BCR_BVR_WCR_WVR(2),
+	/* DBGDTR[RT]Xint */
+	{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
+	/* DBGDTR[RT]Xext */
+	{ Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(3),
+	DBG_BCR_BVR_WCR_WVR(4),
+	DBG_BCR_BVR_WCR_WVR(5),
+	/* DBGWFAR */
+	{ Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi },
+	/* DBGOSECCR */
+	{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
+	DBG_BCR_BVR_WCR_WVR(6),
+	/* DBGVCR */
+	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+	DBG_BCR_BVR_WCR_WVR(7),
+	DBG_BCR_BVR_WCR_WVR(8),
+	DBG_BCR_BVR_WCR_WVR(9),
+	DBG_BCR_BVR_WCR_WVR(10),
+	DBG_BCR_BVR_WCR_WVR(11),
+	DBG_BCR_BVR_WCR_WVR(12),
+	DBG_BCR_BVR_WCR_WVR(13),
+	DBG_BCR_BVR_WCR_WVR(14),
+	DBG_BCR_BVR_WCR_WVR(15),
+
+	/* DBGDRAR (32bit) */
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi },
+
+	DBGBXVR(0),
+	/* DBGOSLAR */
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
+	DBGBXVR(1),
+	/* DBGOSLSR */
+	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
+	DBGBXVR(2),
+	DBGBXVR(3),
+	/* DBGOSDLR */
+	{ Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi },
+	DBGBXVR(4),
+	/* DBGPRCR */
+	{ Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi },
+	DBGBXVR(5),
+	DBGBXVR(6),
+	DBGBXVR(7),
+	DBGBXVR(8),
+	DBGBXVR(9),
+	DBGBXVR(10),
+	DBGBXVR(11),
+	DBGBXVR(12),
+	DBGBXVR(13),
+	DBGBXVR(14),
+	DBGBXVR(15),
+
+	/* DBGDSAR (32bit) */
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi },
+
+	/* DBGDEVID2 */
+	{ Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi },
+	/* DBGDEVID1 */
+	{ Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi },
+	/* DBGDEVID */
+	{ Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi },
+	/* DBGCLAIMSET */
+	{ Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi },
+	/* DBGCLAIMCLR */
+	{ Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi },
+	/* DBGAUTHSTATUS */
+	{ Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 },
+};
+
+/* Trapped cp14 64bit registers */
+static const struct sys_reg_desc cp14_64_regs[] = {
+	/* DBGDRAR (64bit) */
+	{ Op1( 0), CRm( 1), .access = trap_raz_wi },
+
+	/* DBGDSAR (64bit) */
+	{ Op1( 0), CRm( 2), .access = trap_raz_wi },
+};
+
+/*
+ * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
+ * depending on the way they are accessed (as a 32bit or a 64bit
+ * register).
+ */
 static const struct sys_reg_desc cp15_regs[] = {
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
+	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
+	{ Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },
+
 	/*
 	 * DC{C,I,CI}SW operations:
 	 */
 	{ Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
 	{ Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), pm_fake },
-	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), pm_fake },
+
+	/* PMU */
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 5), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
+	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
+
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
+	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
+	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
+	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+};
+
+static const struct sys_reg_desc cp15_64_regs[] = {
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
 };
 
 /* Target specific emulation tables */
@@ -385,26 +755,29 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
-int kvm_handle_cp14_access(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	kvm_inject_undefined(vcpu);
-	return 1;
-}
-
-static void emulate_cp15(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *params)
+/*
+ * emulate_cp --  tries to match a sys_reg access in a handling table, and
+ *                call the corresponding trap handler.
+ *
+ * @params: pointer to the descriptor of the access
+ * @table: array of trap descriptors
+ * @num: size of the trap descriptor array
+ *
+ * Return 0 if the access has been handled, and -1 if not.
+ */
+static int emulate_cp(struct kvm_vcpu *vcpu,
+		      const struct sys_reg_params *params,
+		      const struct sys_reg_desc *table,
+		      size_t num)
 {
-	size_t num;
-	const struct sys_reg_desc *table, *r;
+	const struct sys_reg_desc *r;
 
-	table = get_target_table(vcpu->arch.target, false, &num);
+	if (!table)
+		return -1;	/* Not handled */
 
-	/* Search target-specific then generic table. */
 	r = find_reg(params, table, num);
-	if (!r)
-		r = find_reg(params, cp15_regs, ARRAY_SIZE(cp15_regs));
 
-	if (likely(r)) {
+	if (r) {
 		/*
 		 * Not having an accessor means that we have
 		 * configured a trap that we don't know how to
@@ -416,27 +789,58 @@ static void emulate_cp15(struct kvm_vcpu *vcpu,
 		if (likely(r->access(vcpu, params, r))) {
 			/* Skip instruction, since it was emulated */
 			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-			return;
 		}
-		/* If access function fails, it should complain. */
+
+		/* Handled */
+		return 0;
 	}
 
-	kvm_err("Unsupported guest CP15 access at: %08lx\n", *vcpu_pc(vcpu));
+	/* Not handled */
+	return -1;
+}
+
+static void unhandled_cp_access(struct kvm_vcpu *vcpu,
+				struct sys_reg_params *params)
+{
+	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+	int cp;
+
+	switch(hsr_ec) {
+	case ESR_EL2_EC_CP15_32:
+	case ESR_EL2_EC_CP15_64:
+		cp = 15;
+		break;
+	case ESR_EL2_EC_CP14_MR:
+	case ESR_EL2_EC_CP14_64:
+		cp = 14;
+		break;
+	default:
+		WARN_ON((cp = -1));
+	}
+
+	kvm_err("Unsupported guest CP%d access at: %08lx\n",
+		cp, *vcpu_pc(vcpu));
 	print_sys_reg_instr(params);
 	kvm_inject_undefined(vcpu);
 }
 
 /**
- * kvm_handle_cp15_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_desc *global,
+			    size_t nr_global,
+			    const struct sys_reg_desc *target_specific,
+			    size_t nr_specific)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	int Rt2 = (hsr >> 10) & 0xf;
 
+	params.is_aarch32 = true;
+	params.is_32bit = false;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -458,8 +862,14 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		*vcpu_reg(vcpu, params.Rt) = val;
 	}
 
-	emulate_cp15(vcpu, &params);
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
+		goto out;
+	if (!emulate_cp(vcpu, &params, global, nr_global))
+		goto out;
+
+	unhandled_cp_access(vcpu, &params);
 
+out:
 	/* Do the opposite hack for the read side */
 	if (!params.is_write) {
 		u64 val = *vcpu_reg(vcpu, params.Rt);
@@ -475,11 +885,17 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * @vcpu: The VCPU pointer
  * @run:  The kvm_run struct
  */
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
+			    const struct sys_reg_desc *global,
+			    size_t nr_global,
+			    const struct sys_reg_desc *target_specific,
+			    size_t nr_specific)
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = true;
+	params.is_32bit = true;
 	params.CRm = (hsr >> 1) & 0xf;
 	params.Rt  = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
@@ -488,10 +904,51 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	params.Op1 = (hsr >> 14) & 0x7;
 	params.Op2 = (hsr >> 17) & 0x7;
 
-	emulate_cp15(vcpu, &params);
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
+		return 1;
+	if (!emulate_cp(vcpu, &params, global, nr_global))
+		return 1;
+
+	unhandled_cp_access(vcpu, &params);
 	return 1;
 }
 
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	const struct sys_reg_desc *target_specific;
+	size_t num;
+
+	target_specific = get_target_table(vcpu->arch.target, false, &num);
+	return kvm_handle_cp_64(vcpu,
+				cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
+				target_specific, num);
+}
+
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	const struct sys_reg_desc *target_specific;
+	size_t num;
+
+	target_specific = get_target_table(vcpu->arch.target, false, &num);
+	return kvm_handle_cp_32(vcpu,
+				cp15_regs, ARRAY_SIZE(cp15_regs),
+				target_specific, num);
+}
+
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	return kvm_handle_cp_64(vcpu,
+				cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
+				NULL, 0);
+}
+
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	return kvm_handle_cp_32(vcpu,
+				cp14_regs, ARRAY_SIZE(cp14_regs),
+				NULL, 0);
+}
+
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
 			   const struct sys_reg_params *params)
 {
@@ -549,6 +1006,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
 
+	params.is_aarch32 = false;
+	params.is_32bit = false;
 	params.Op0 = (esr >> 20) & 3;
 	params.Op1 = (esr >> 14) & 0x7;
 	params.CRn = (esr >> 10) & 0xf;
@@ -701,17 +1160,15 @@ static struct sys_reg_desc invariant_sys_regs[] = {
 	  NULL, get_ctr_el0 },
 };
 
-static int reg_from_user(void *val, const void __user *uaddr, u64 id)
+static int reg_from_user(u64 *val, const void __user *uaddr, u64 id)
 {
-	/* This Just Works because we are little endian. */
 	if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0)
 		return -EFAULT;
 	return 0;
 }
 
-static int reg_to_user(void __user *uaddr, const void *val, u64 id)
+static int reg_to_user(void __user *uaddr, const u64 *val, u64 id)
 {
-	/* This Just Works because we are little endian. */
 	if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0)
 		return -EFAULT;
 	return 0;
@@ -761,7 +1218,7 @@ static bool is_valid_cache(u32 val)
 	u32 level, ctype;
 
 	if (val >= CSSELR_MAX)
-		return -ENOENT;
+		return false;
 
 	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
 	level = (val >> 1);
@@ -887,7 +1344,7 @@ static unsigned int num_demux_regs(void)
 
 static int write_demux_regids(u64 __user *uindices)
 {
-	u64 val = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX;
+	u64 val = KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX;
 	unsigned int i;
 
 	val |= KVM_REG_ARM_DEMUX_ID_CCSIDR;
@@ -994,14 +1451,32 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 	return write_demux_regids(uindices);
 }
 
+static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n)
+{
+	unsigned int i;
+
+	for (i = 1; i < n; i++) {
+		if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
+			kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 void kvm_sys_reg_table_init(void)
 {
 	unsigned int i;
 	struct sys_reg_desc clidr;
 
 	/* Make sure tables are unique and in order. */
-	for (i = 1; i < ARRAY_SIZE(sys_reg_descs); i++)
-		BUG_ON(cmp_sys_reg(&sys_reg_descs[i-1], &sys_reg_descs[i]) >= 0);
+	BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs)));
+	BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs)));
+	BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs)));
+	BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
+	BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs)));
+	BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)));
 
 	/* We abuse the reset function to overwrite the table itself. */
 	for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index d50d3722998e..d411e251412c 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -30,6 +30,8 @@ struct sys_reg_params {
 	u8	Op2;
 	u8	Rt;
 	bool	is_write;
+	bool	is_aarch32;
+	bool	is_32bit;	/* Only valid if is_aarch32 is true */
 };
 
 struct sys_reg_desc {
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 8fe6f76b0edc..475fd2929310 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -88,6 +88,8 @@ static int __init sys_reg_genericv8_init(void)
 					  &genericv8_target_table);
 	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8,
 					  &genericv8_target_table);
+	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53,
+					  &genericv8_target_table);
 	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57,
 					  &genericv8_target_table);
 	kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA,
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
new file mode 100644
index 000000000000..ae211772f991
--- /dev/null
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -0,0 +1,133 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+ENTRY(__save_vgic_v2_state)
+__save_vgic_v2_state:
+	/* Get VGIC VCTRL base into x2 */
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va	x2
+	ldr	x2, [x2, #KVM_VGIC_VCTRL]
+	kern_hyp_va	x2
+	cbz	x2, 2f		// disabled
+
+	/* Compute the address of struct vgic_cpu */
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	/* Save all interesting registers */
+	ldr	w4, [x2, #GICH_HCR]
+	ldr	w5, [x2, #GICH_VMCR]
+	ldr	w6, [x2, #GICH_MISR]
+	ldr	w7, [x2, #GICH_EISR0]
+	ldr	w8, [x2, #GICH_EISR1]
+	ldr	w9, [x2, #GICH_ELRSR0]
+	ldr	w10, [x2, #GICH_ELRSR1]
+	ldr	w11, [x2, #GICH_APR]
+CPU_BE(	rev	w4,  w4  )
+CPU_BE(	rev	w5,  w5  )
+CPU_BE(	rev	w6,  w6  )
+CPU_BE(	rev	w7,  w7  )
+CPU_BE(	rev	w8,  w8  )
+CPU_BE(	rev	w9,  w9  )
+CPU_BE(	rev	w10, w10 )
+CPU_BE(	rev	w11, w11 )
+
+	str	w4, [x3, #VGIC_V2_CPU_HCR]
+	str	w5, [x3, #VGIC_V2_CPU_VMCR]
+	str	w6, [x3, #VGIC_V2_CPU_MISR]
+	str	w7, [x3, #VGIC_V2_CPU_EISR]
+	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)]
+	str	w9, [x3, #VGIC_V2_CPU_ELRSR]
+	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)]
+	str	w11, [x3, #VGIC_V2_CPU_APR]
+
+	/* Clear GICH_HCR */
+	str	wzr, [x2, #GICH_HCR]
+
+	/* Save list registers */
+	add	x2, x2, #GICH_LR0
+	ldr	w4, [x3, #VGIC_CPU_NR_LR]
+	add	x3, x3, #VGIC_V2_CPU_LR
+1:	ldr	w5, [x2], #4
+CPU_BE(	rev	w5, w5 )
+	str	w5, [x3], #4
+	sub	w4, w4, #1
+	cbnz	w4, 1b
+2:
+	ret
+ENDPROC(__save_vgic_v2_state)
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+ENTRY(__restore_vgic_v2_state)
+__restore_vgic_v2_state:
+	/* Get VGIC VCTRL base into x2 */
+	ldr	x2, [x0, #VCPU_KVM]
+	kern_hyp_va	x2
+	ldr	x2, [x2, #KVM_VGIC_VCTRL]
+	kern_hyp_va	x2
+	cbz	x2, 2f		// disabled
+
+	/* Compute the address of struct vgic_cpu */
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	/* We only restore a minimal set of registers */
+	ldr	w4, [x3, #VGIC_V2_CPU_HCR]
+	ldr	w5, [x3, #VGIC_V2_CPU_VMCR]
+	ldr	w6, [x3, #VGIC_V2_CPU_APR]
+CPU_BE(	rev	w4, w4 )
+CPU_BE(	rev	w5, w5 )
+CPU_BE(	rev	w6, w6 )
+
+	str	w4, [x2, #GICH_HCR]
+	str	w5, [x2, #GICH_VMCR]
+	str	w6, [x2, #GICH_APR]
+
+	/* Restore list registers */
+	add	x2, x2, #GICH_LR0
+	ldr	w4, [x3, #VGIC_CPU_NR_LR]
+	add	x3, x3, #VGIC_V2_CPU_LR
+1:	ldr	w5, [x3], #4
+CPU_BE(	rev	w5, w5 )
+	str	w5, [x2], #4
+	sub	w4, w4, #1
+	cbnz	w4, 1b
+2:
+	ret
+ENDPROC(__restore_vgic_v2_state)
+
+	.popsection
diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S
new file mode 100644
index 000000000000..d16046999e06
--- /dev/null
+++ b/arch/arm64/kvm/vgic-v3-switch.S
@@ -0,0 +1,267 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+
+	.text
+	.pushsection	.hyp.text, "ax"
+
+/*
+ * We store LRs in reverse order to let the CPU deal with streaming
+ * access. Use this macro to make it look saner...
+ */
+#define LR_OFFSET(n)	(VGIC_V3_CPU_LR + (15 - n) * 8)
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+.macro	save_vgic_v3_state
+	// Compute the address of struct vgic_cpu
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	// Make sure stores to the GIC via the memory mapped interface
+	// are now visible to the system register interface
+	dsb	st
+
+	// Save all interesting registers
+	mrs_s	x4, ICH_HCR_EL2
+	mrs_s	x5, ICH_VMCR_EL2
+	mrs_s	x6, ICH_MISR_EL2
+	mrs_s	x7, ICH_EISR_EL2
+	mrs_s	x8, ICH_ELSR_EL2
+
+	str	w4, [x3, #VGIC_V3_CPU_HCR]
+	str	w5, [x3, #VGIC_V3_CPU_VMCR]
+	str	w6, [x3, #VGIC_V3_CPU_MISR]
+	str	w7, [x3, #VGIC_V3_CPU_EISR]
+	str	w8, [x3, #VGIC_V3_CPU_ELRSR]
+
+	msr_s	ICH_HCR_EL2, xzr
+
+	mrs_s	x21, ICH_VTR_EL2
+	mvn	w22, w21
+	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	mrs_s	x20, ICH_LR15_EL2
+	mrs_s	x19, ICH_LR14_EL2
+	mrs_s	x18, ICH_LR13_EL2
+	mrs_s	x17, ICH_LR12_EL2
+	mrs_s	x16, ICH_LR11_EL2
+	mrs_s	x15, ICH_LR10_EL2
+	mrs_s	x14, ICH_LR9_EL2
+	mrs_s	x13, ICH_LR8_EL2
+	mrs_s	x12, ICH_LR7_EL2
+	mrs_s	x11, ICH_LR6_EL2
+	mrs_s	x10, ICH_LR5_EL2
+	mrs_s	x9, ICH_LR4_EL2
+	mrs_s	x8, ICH_LR3_EL2
+	mrs_s	x7, ICH_LR2_EL2
+	mrs_s	x6, ICH_LR1_EL2
+	mrs_s	x5, ICH_LR0_EL2
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	str	x20, [x3, #LR_OFFSET(15)]
+	str	x19, [x3, #LR_OFFSET(14)]
+	str	x18, [x3, #LR_OFFSET(13)]
+	str	x17, [x3, #LR_OFFSET(12)]
+	str	x16, [x3, #LR_OFFSET(11)]
+	str	x15, [x3, #LR_OFFSET(10)]
+	str	x14, [x3, #LR_OFFSET(9)]
+	str	x13, [x3, #LR_OFFSET(8)]
+	str	x12, [x3, #LR_OFFSET(7)]
+	str	x11, [x3, #LR_OFFSET(6)]
+	str	x10, [x3, #LR_OFFSET(5)]
+	str	x9, [x3, #LR_OFFSET(4)]
+	str	x8, [x3, #LR_OFFSET(3)]
+	str	x7, [x3, #LR_OFFSET(2)]
+	str	x6, [x3, #LR_OFFSET(1)]
+	str	x5, [x3, #LR_OFFSET(0)]
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	mrs_s	x20, ICH_AP0R3_EL2
+	str	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+	mrs_s	x19, ICH_AP0R2_EL2
+	str	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+6:	mrs_s	x18, ICH_AP0R1_EL2
+	str	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+5:	mrs_s	x17, ICH_AP0R0_EL2
+	str	w17, [x3, #VGIC_V3_CPU_AP0R]
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	mrs_s	x20, ICH_AP1R3_EL2
+	str	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+	mrs_s	x19, ICH_AP1R2_EL2
+	str	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+6:	mrs_s	x18, ICH_AP1R1_EL2
+	str	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+5:	mrs_s	x17, ICH_AP1R0_EL2
+	str	w17, [x3, #VGIC_V3_CPU_AP1R]
+
+	// Restore SRE_EL1 access and re-enable SRE at EL1.
+	mrs_s	x5, ICC_SRE_EL2
+	orr	x5, x5, #ICC_SRE_EL2_ENABLE
+	msr_s	ICC_SRE_EL2, x5
+	isb
+	mov	x5, #1
+	msr_s	ICC_SRE_EL1, x5
+.endm
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+.macro	restore_vgic_v3_state
+	// Disable SRE_EL1 access. Necessary, otherwise
+	// ICH_VMCR_EL2.VFIQEn becomes one, and FIQ happens...
+	msr_s	ICC_SRE_EL1, xzr
+	isb
+
+	// Compute the address of struct vgic_cpu
+	add	x3, x0, #VCPU_VGIC_CPU
+
+	// Restore all interesting registers
+	ldr	w4, [x3, #VGIC_V3_CPU_HCR]
+	ldr	w5, [x3, #VGIC_V3_CPU_VMCR]
+
+	msr_s	ICH_HCR_EL2, x4
+	msr_s	ICH_VMCR_EL2, x5
+
+	mrs_s	x21, ICH_VTR_EL2
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	ldr	w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+	msr_s	ICH_AP1R3_EL2, x20
+	ldr	w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+	msr_s	ICH_AP1R2_EL2, x19
+6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+	msr_s	ICH_AP1R1_EL2, x18
+5:	ldr	w17, [x3, #VGIC_V3_CPU_AP1R]
+	msr_s	ICH_AP1R0_EL2, x17
+
+	tbnz	w21, #29, 6f	// 6 bits
+	tbz	w21, #30, 5f	// 5 bits
+				// 7 bits
+	ldr	w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+	msr_s	ICH_AP0R3_EL2, x20
+	ldr	w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+	msr_s	ICH_AP0R2_EL2, x19
+6:	ldr	w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+	msr_s	ICH_AP0R1_EL2, x18
+5:	ldr	w17, [x3, #VGIC_V3_CPU_AP0R]
+	msr_s	ICH_AP0R0_EL2, x17
+
+	and	w22, w21, #0xf
+	mvn	w22, w21
+	ubfiz	w23, w22, 2, 4	// w23 = (15 - ListRegs) * 4
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	ldr	x20, [x3, #LR_OFFSET(15)]
+	ldr	x19, [x3, #LR_OFFSET(14)]
+	ldr	x18, [x3, #LR_OFFSET(13)]
+	ldr	x17, [x3, #LR_OFFSET(12)]
+	ldr	x16, [x3, #LR_OFFSET(11)]
+	ldr	x15, [x3, #LR_OFFSET(10)]
+	ldr	x14, [x3, #LR_OFFSET(9)]
+	ldr	x13, [x3, #LR_OFFSET(8)]
+	ldr	x12, [x3, #LR_OFFSET(7)]
+	ldr	x11, [x3, #LR_OFFSET(6)]
+	ldr	x10, [x3, #LR_OFFSET(5)]
+	ldr	x9, [x3, #LR_OFFSET(4)]
+	ldr	x8, [x3, #LR_OFFSET(3)]
+	ldr	x7, [x3, #LR_OFFSET(2)]
+	ldr	x6, [x3, #LR_OFFSET(1)]
+	ldr	x5, [x3, #LR_OFFSET(0)]
+
+	adr	x24, 1f
+	add	x24, x24, x23
+	br	x24
+
+1:
+	msr_s	ICH_LR15_EL2, x20
+	msr_s	ICH_LR14_EL2, x19
+	msr_s	ICH_LR13_EL2, x18
+	msr_s	ICH_LR12_EL2, x17
+	msr_s	ICH_LR11_EL2, x16
+	msr_s	ICH_LR10_EL2, x15
+	msr_s	ICH_LR9_EL2,  x14
+	msr_s	ICH_LR8_EL2,  x13
+	msr_s	ICH_LR7_EL2,  x12
+	msr_s	ICH_LR6_EL2,  x11
+	msr_s	ICH_LR5_EL2,  x10
+	msr_s	ICH_LR4_EL2,   x9
+	msr_s	ICH_LR3_EL2,   x8
+	msr_s	ICH_LR2_EL2,   x7
+	msr_s	ICH_LR1_EL2,   x6
+	msr_s	ICH_LR0_EL2,   x5
+
+	// Ensure that the above will have reached the
+	// (re)distributors. This ensure the guest will read
+	// the correct values from the memory-mapped interface.
+	isb
+	dsb	sy
+
+	// Prevent the guest from touching the GIC system registers
+	mrs_s	x5, ICC_SRE_EL2
+	and	x5, x5, #~ICC_SRE_EL2_ENABLE
+	msr_s	ICC_SRE_EL2, x5
+.endm
+
+ENTRY(__save_vgic_v3_state)
+	save_vgic_v3_state
+	ret
+ENDPROC(__save_vgic_v3_state)
+
+ENTRY(__restore_vgic_v3_state)
+	restore_vgic_v3_state
+	ret
+ENDPROC(__restore_vgic_v3_state)
+
+ENTRY(__vgic_v3_get_ich_vtr_el2)
+	mrs_s	x0, ICH_VTR_EL2
+	ret
+ENDPROC(__vgic_v3_get_ich_vtr_el2)
+
+	.popsection
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 6e0ed93d51fe..c17967fdf5f6 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -46,7 +46,7 @@ USER(9f, strh	wzr, [x0], #2	)
 	sub	x1, x1, #2
 4:	adds	x1, x1, #1
 	b.mi	5f
-	strb	wzr, [x0]
+USER(9f, strb	wzr, [x0]	)
 5:	mov	x0, #0
 	ret
 ENDPROC(__clear_user)
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index b51d36401d83..3ecb56c624d3 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -1,5 +1,5 @@
 obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   cache.o copypage.o flush.o \
 				   ioremap.o mmap.o pgd.o mmu.o \
-				   context.o tlb.o proc.o
+				   context.o proc.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 1ea9f26d1b70..fda756875fa6 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -30,7 +30,7 @@
  *
  *	Corrupted registers: x0-x7, x9-x11
  */
-ENTRY(__flush_dcache_all)
+__flush_dcache_all:
 	dsb	sy				// ensure ordering with previous memory accesses
 	mrs	x0, clidr_el1			// read clidr
 	and	x3, x0, #0x7000000		// extract loc from clidr
@@ -166,3 +166,97 @@ ENTRY(__flush_dcache_area)
 	dsb	sy
 	ret
 ENDPROC(__flush_dcache_area)
+
+/*
+ *	__inval_cache_range(start, end)
+ *	- start   - start address of region
+ *	- end     - end address of region
+ */
+ENTRY(__inval_cache_range)
+	/* FALLTHROUGH */
+
+/*
+ *	__dma_inv_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_inv_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	tst	x1, x3				// end cache line aligned?
+	bic	x1, x1, x3
+	b.eq	1f
+	dc	civac, x1			// clean & invalidate D / U line
+1:	tst	x0, x3				// start cache line aligned?
+	bic	x0, x0, x3
+	b.eq	2f
+	dc	civac, x0			// clean & invalidate D / U line
+	b	3f
+2:	dc	ivac, x0			// invalidate D / U line
+3:	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	2b
+	dsb	sy
+	ret
+ENDPROC(__inval_cache_range)
+ENDPROC(__dma_inv_range)
+
+/*
+ *	__dma_clean_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_clean_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	cvac, x0			// clean D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_clean_range)
+
+/*
+ *	__dma_flush_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(__dma_flush_range)
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	civac, x0			// clean & invalidate D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_flush_range)
+
+/*
+ *	__dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_map_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_FROM_DEVICE
+	b.eq	__dma_inv_range
+	b	__dma_clean_range
+ENDPROC(__dma_map_area)
+
+/*
+ *	__dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_unmap_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_TO_DEVICE
+	b.ne	__dma_inv_range
+	ret
+ENDPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 9aecbace4128..13bbc3be6f5a 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -27,8 +27,10 @@ void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
 	copy_page(kto, kfrom);
 	__flush_dcache_area(kto, PAGE_SIZE);
 }
+EXPORT_SYMBOL_GPL(__cpu_copy_user_page);
 
 void __cpu_clear_user_page(void *kaddr, unsigned long vaddr)
 {
 	clear_page(kaddr);
 }
+EXPORT_SYMBOL_GPL(__cpu_clear_user_page);
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index fbd76785c5db..4164c5ace9f8 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -22,26 +22,37 @@
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
+#include <linux/amba/bus.h>
 
 #include <asm/cacheflush.h>
 
 struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
-					  dma_addr_t *dma_handle, gfp_t flags,
-					  struct dma_attrs *attrs)
+static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
+				 bool coherent)
+{
+	if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+		return pgprot_writecombine(prot);
+	return prot;
+}
+
+static void *__dma_alloc_coherent(struct device *dev, size_t size,
+				  dma_addr_t *dma_handle, gfp_t flags,
+				  struct dma_attrs *attrs)
 {
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
 		return NULL;
 	}
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-		flags |= GFP_DMA32;
+		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA)) {
 		struct page *page;
 
@@ -58,9 +69,9 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
 	}
 }
 
-static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
-					void *vaddr, dma_addr_t dma_handle,
-					struct dma_attrs *attrs)
+static void __dma_free_coherent(struct device *dev, size_t size,
+				void *vaddr, dma_addr_t dma_handle,
+				struct dma_attrs *attrs)
 {
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
@@ -78,9 +89,212 @@ static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
 	}
 }
 
-static struct dma_map_ops arm64_swiotlb_dma_ops = {
-	.alloc = arm64_swiotlb_alloc_coherent,
-	.free = arm64_swiotlb_free_coherent,
+static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
+				     dma_addr_t *dma_handle, gfp_t flags,
+				     struct dma_attrs *attrs)
+{
+	struct page *page, **map;
+	void *ptr, *coherent_ptr;
+	int order, i;
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
+	if (!ptr)
+		goto no_mem;
+	map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
+	if (!map)
+		goto no_map;
+
+	/* remove any dirty cache lines on the kernel alias */
+	__dma_flush_range(ptr, ptr + size);
+
+	/* create a coherent mapping */
+	page = virt_to_page(ptr);
+	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+		map[i] = page + i;
+	coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
+			    __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false));
+	kfree(map);
+	if (!coherent_ptr)
+		goto no_map;
+
+	return coherent_ptr;
+
+no_map:
+	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
+no_mem:
+	*dma_handle = ~0;
+	return NULL;
+}
+
+static void __dma_free_noncoherent(struct device *dev, size_t size,
+				   void *vaddr, dma_addr_t dma_handle,
+				   struct dma_attrs *attrs)
+{
+	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+
+	vunmap(vaddr);
+	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+}
+
+static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	dma_addr_t dev_addr;
+
+	dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+
+	return dev_addr;
+}
+
+
+static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
+				 size_t size, enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+				  int nelems, enum dma_data_direction dir,
+				  struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i, ret;
+
+	ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
+	for_each_sg(sgl, sg, ret, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+
+	return ret;
+}
+
+static void __swiotlb_unmap_sg_attrs(struct device *dev,
+				     struct scatterlist *sgl, int nelems,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+}
+
+static void __swiotlb_sync_single_for_cpu(struct device *dev,
+					  dma_addr_t dev_addr, size_t size,
+					  enum dma_data_direction dir)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+}
+
+static void __swiotlb_sync_single_for_device(struct device *dev,
+					     dma_addr_t dev_addr, size_t size,
+					     enum dma_data_direction dir)
+{
+	swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+}
+
+static void __swiotlb_sync_sg_for_cpu(struct device *dev,
+				      struct scatterlist *sgl, int nelems,
+				      enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
+}
+
+static void __swiotlb_sync_sg_for_device(struct device *dev,
+					 struct scatterlist *sgl, int nelems,
+					 enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+}
+
+/* vma->vm_page_prot must be set appropriately before calling this function */
+static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			     void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+	int ret = -ENXIO;
+	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
+					PAGE_SHIFT;
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+	unsigned long off = vma->vm_pgoff;
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      vma->vm_end - vma->vm_start,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static int __swiotlb_mmap_noncoherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, false);
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+static int __swiotlb_mmap_coherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	/* Just use whatever page_prot attributes were specified */
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+struct dma_map_ops noncoherent_swiotlb_dma_ops = {
+	.alloc = __dma_alloc_noncoherent,
+	.free = __dma_free_noncoherent,
+	.mmap = __swiotlb_mmap_noncoherent,
+	.map_page = __swiotlb_map_page,
+	.unmap_page = __swiotlb_unmap_page,
+	.map_sg = __swiotlb_map_sg_attrs,
+	.unmap_sg = __swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = __swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = __swiotlb_sync_sg_for_device,
+	.dma_supported = swiotlb_dma_supported,
+	.mapping_error = swiotlb_dma_mapping_error,
+};
+EXPORT_SYMBOL(noncoherent_swiotlb_dma_ops);
+
+struct dma_map_ops coherent_swiotlb_dma_ops = {
+	.alloc = __dma_alloc_coherent,
+	.free = __dma_free_coherent,
+	.mmap = __swiotlb_mmap_coherent,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
 	.map_sg = swiotlb_map_sg_attrs,
@@ -92,12 +306,47 @@ static struct dma_map_ops arm64_swiotlb_dma_ops = {
 	.dma_supported = swiotlb_dma_supported,
 	.mapping_error = swiotlb_dma_mapping_error,
 };
+EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
 
-void __init arm64_swiotlb_init(void)
+static int dma_bus_notifier(struct notifier_block *nb,
+			    unsigned long event, void *_dev)
 {
-	dma_ops = &arm64_swiotlb_dma_ops;
-	swiotlb_init(1);
+	struct device *dev = _dev;
+
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+
+	if (of_property_read_bool(dev->of_node, "dma-coherent"))
+		set_dma_ops(dev, &coherent_swiotlb_dma_ops);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block platform_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
+static struct notifier_block amba_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
+extern int swiotlb_late_init_with_default_size(size_t default_size);
+
+static int __init swiotlb_late_init(void)
+{
+	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
+
+	/*
+	 * These must be registered before of_platform_populate().
+	 */
+	bus_register_notifier(&platform_bus_type, &platform_bus_nb);
+	bus_register_notifier(&amba_bustype, &amba_bus_nb);
+
+	dma_ops = &noncoherent_swiotlb_dma_ops;
+
+	return swiotlb_late_init_with_default_size(swiotlb_size);
 }
+arch_initcall(swiotlb_late_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index e4193e3adc7f..0d64089d28b5 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -79,7 +79,8 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 		return;
 
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags)) {
-		__flush_dcache_area(page_address(page), PAGE_SIZE);
+		__flush_dcache_area(page_address(page),
+				PAGE_SIZE << compound_order(page));
 		__flush_icache_all();
 	} else if (icache_is_aivivt()) {
 		__flush_icache_all();
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 5e9aec358306..023747bf4dd7 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -51,12 +51,11 @@ int pmd_huge(pmd_t pmd)
 
 int pud_huge(pud_t pud)
 {
+#ifndef __PAGETABLE_PMD_FOLDED
 	return !(pud_val(pud) & PUD_TABLE_BIT);
-}
-
-int pmd_huge_support(void)
-{
-	return 1;
+#else
+	return 0;
+#endif
 }
 
 static __init int setup_hugepagesz(char *opt)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d0b4c2efda90..cc3339d0a276 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 
 #include <asm/sections.h>
@@ -59,22 +60,22 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif
 
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
-
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma32 = min;
+	unsigned long max_dma = min;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
-#ifdef CONFIG_ZONE_DMA32
 	/* 4GB maximum for 32-bit only capable devices */
-	max_dma32 = max(min, min(max, MAX_DMA32_PFN));
-	zone_size[ZONE_DMA32] = max_dma32 - min;
-#endif
-	zone_size[ZONE_NORMAL] = max - max_dma32;
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		unsigned long max_dma_phys =
+			(unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
+		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+		zone_size[ZONE_DMA] = max_dma - min;
+	}
+	zone_size[ZONE_NORMAL] = max - max_dma;
 
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -84,15 +85,15 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 		if (start >= max)
 			continue;
-#ifdef CONFIG_ZONE_DMA32
-		if (start < max_dma32) {
-			unsigned long dma_end = min(end, max_dma32);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) {
+			unsigned long dma_end = min(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
-#endif
-		if (end > max_dma32) {
+
+		if (end > max_dma) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma32);
+			unsigned long normal_start = max(start, max_dma);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -127,20 +128,16 @@ void __init arm64_memblock_init(void)
 {
 	u64 *reserve_map, base, size;
 
-	/* Register the kernel text, kernel data and initrd with memblock */
+	/*
+	 * Register the kernel text, kernel data, initrd, and initial
+	 * pagetables with memblock.
+	 */
 	memblock_reserve(__pa(_text), _end - _text);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start)
 		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
 #endif
 
-	/*
-	 * Reserve the page tables.  These are already in use,
-	 * and can only be in node 0.
-	 */
-	memblock_reserve(__pa(swapper_pg_dir), SWAPPER_DIR_SIZE);
-	memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE);
-
 	/* Reserve the dtb region */
 	memblock_reserve(virt_to_phys(initial_boot_params),
 			 be32_to_cpu(initial_boot_params->totalsize));
@@ -160,6 +157,7 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(base, size);
 	}
 
+	early_init_fdt_scan_reserved_mem();
 	dma_contiguous_reserve(0);
 
 	memblock_allow_resize();
@@ -261,8 +259,6 @@ static void __init free_unused_memmap(void)
  */
 void __init mem_init(void)
 {
-	arm64_swiotlb_init();
-
 	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index 2bb1d586664c..7ec328392ae0 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -25,6 +25,10 @@
 #include <linux/vmalloc.h>
 #include <linux/io.h>
 
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
 static void __iomem *__ioremap_caller(phys_addr_t phys_addr, size_t size,
 				      pgprot_t prot, void *caller)
 {
@@ -98,3 +102,84 @@ void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_cache);
+
+#ifndef CONFIG_ARM64_64K_PAGES
+static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
+#endif
+
+static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	pgd = pgd_offset_k(addr);
+	BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));
+
+	pud = pud_offset(pgd, addr);
+	BUG_ON(pud_none(*pud) || pud_bad(*pud));
+
+	return pmd_offset(pud, addr);
+}
+
+static inline pte_t * __init early_ioremap_pte(unsigned long addr)
+{
+	pmd_t *pmd = early_ioremap_pmd(addr);
+
+	BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd));
+
+	return pte_offset_kernel(pmd, addr);
+}
+
+void __init early_ioremap_init(void)
+{
+	pmd_t *pmd;
+
+	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
+#ifndef CONFIG_ARM64_64K_PAGES
+	/* need to populate pmd for 4k pagesize only */
+	pmd_populate_kernel(&init_mm, pmd, bm_pte);
+#endif
+	/*
+	 * The boot-ioremap range spans multiple pmds, for which
+	 * we are not prepared:
+	 */
+	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+
+	if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
+		WARN_ON(1);
+		pr_warn("pmd %p != %p\n",
+			pmd, early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END)));
+		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+			fix_to_virt(FIX_BTMAP_BEGIN));
+		pr_warn("fix_to_virt(FIX_BTMAP_END):   %08lx\n",
+			fix_to_virt(FIX_BTMAP_END));
+
+		pr_warn("FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
+		pr_warn("FIX_BTMAP_BEGIN:     %d\n",
+			FIX_BTMAP_BEGIN);
+	}
+
+	early_ioremap_setup();
+}
+
+void __init __early_set_fixmap(enum fixed_addresses idx,
+			       phys_addr_t phys, pgprot_t flags)
+{
+	unsigned long addr = __fix_to_virt(idx);
+	pte_t *pte;
+
+	if (idx >= __end_of_fixed_addresses) {
+		BUG();
+		return;
+	}
+
+	pte = early_ioremap_pte(addr);
+
+	if (pgprot_val(flags))
+		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
+	else {
+		pte_clear(&init_mm, addr, pte);
+		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
+	}
+}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f8dc7e8fce6f..a2155ca6921c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -43,11 +43,6 @@
 struct page *empty_zero_page;
 EXPORT_SYMBOL(empty_zero_page);
 
-pgprot_t pgprot_default;
-EXPORT_SYMBOL(pgprot_default);
-
-static pmdval_t prot_sect_kernel;
-
 struct cachepolicy {
 	const char	policy[16];
 	u64		mair;
@@ -122,33 +117,6 @@ static int __init early_cachepolicy(char *p)
 }
 early_param("cachepolicy", early_cachepolicy);
 
-/*
- * Adjust the PMD section entries according to the CPU in use.
- */
-static void __init init_mem_pgprot(void)
-{
-	pteval_t default_pgprot;
-	int i;
-
-	default_pgprot = PTE_ATTRINDX(MT_NORMAL);
-	prot_sect_kernel = PMD_TYPE_SECT | PMD_SECT_AF | PMD_ATTRINDX(MT_NORMAL);
-
-#ifdef CONFIG_SMP
-	/*
-	 * Mark memory with the "shared" attribute for SMP systems
-	 */
-	default_pgprot |= PTE_SHARED;
-	prot_sect_kernel |= PMD_SECT_S;
-#endif
-
-	for (i = 0; i < 16; i++) {
-		unsigned long v = pgprot_val(protection_map[i]);
-		protection_map[i] = __pgprot(v | default_pgprot);
-	}
-
-	pgprot_default = __pgprot(PTE_TYPE_PAGE | PTE_AF | default_pgprot);
-}
-
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
@@ -168,7 +136,8 @@ static void __init *early_alloc(unsigned long sz)
 }
 
 static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
-				  unsigned long end, unsigned long pfn)
+				  unsigned long end, unsigned long pfn,
+				  pgprot_t prot)
 {
 	pte_t *pte;
 
@@ -180,16 +149,28 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+		set_pte(pte, pfn_pte(pfn, prot));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
-				  unsigned long end, phys_addr_t phys)
+				  unsigned long end, phys_addr_t phys,
+				  int map_io)
 {
 	pmd_t *pmd;
 	unsigned long next;
+	pmdval_t prot_sect;
+	pgprot_t prot_pte;
+
+	if (map_io) {
+		prot_sect = PMD_TYPE_SECT | PMD_SECT_AF |
+			    PMD_ATTRINDX(MT_DEVICE_nGnRE);
+		prot_pte = __pgprot(PROT_DEVICE_nGnRE);
+	} else {
+		prot_sect = PROT_SECT_NORMAL_EXEC;
+		prot_pte = PAGE_KERNEL_EXEC;
+	}
 
 	/*
 	 * Check for initial section mappings in the pgd/pud and remove them.
@@ -205,7 +186,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0) {
 			pmd_t old_pmd =*pmd;
-			set_pmd(pmd, __pmd(phys | prot_sect_kernel));
+			set_pmd(pmd, __pmd(phys | prot_sect));
 			/*
 			 * Check for previous table entries created during
 			 * boot (__create_page_tables) and flush them.
@@ -213,21 +194,23 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 			if (!pmd_none(old_pmd))
 				flush_tlb_all();
 		} else {
-			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys));
+			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
+				       prot_pte);
 		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
 }
 
 static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
-				  unsigned long end, unsigned long phys)
+				  unsigned long end, unsigned long phys,
+				  int map_io)
 {
 	pud_t *pud = pud_offset(pgd, addr);
 	unsigned long next;
 
 	do {
 		next = pud_addr_end(addr, end);
-		alloc_init_pmd(pud, addr, next, phys);
+		alloc_init_pmd(pud, addr, next, phys, map_io);
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
 }
@@ -236,70 +219,43 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
  * Create the page directory entries and any necessary page tables for the
  * mapping specified by 'md'.
  */
-static void __init create_mapping(phys_addr_t phys, unsigned long virt,
-				  phys_addr_t size)
+static void __init __create_mapping(pgd_t *pgd, phys_addr_t phys,
+				    unsigned long virt, phys_addr_t size,
+				    int map_io)
 {
 	unsigned long addr, length, end, next;
-	pgd_t *pgd;
-
-	if (virt < VMALLOC_START) {
-		pr_warning("BUG: not creating mapping for 0x%016llx at 0x%016lx - outside kernel range\n",
-			   phys, virt);
-		return;
-	}
 
 	addr = virt & PAGE_MASK;
 	length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
 
-	pgd = pgd_offset_k(addr);
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys);
+		alloc_init_pud(pgd, addr, next, phys, map_io);
 		phys += next - addr;
 	} while (pgd++, addr = next, addr != end);
 }
 
-#ifdef CONFIG_EARLY_PRINTK
-/*
- * Create an early I/O mapping using the pgd/pmd entries already populated
- * in head.S as this function is called too early to allocated any memory. The
- * mapping size is 2MB with 4KB pages or 64KB or 64KB pages.
- */
-void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
+static void __init create_mapping(phys_addr_t phys, unsigned long virt,
+				  phys_addr_t size)
 {
-	unsigned long size, mask;
-	bool page64k = IS_ENABLED(CONFIG_ARM64_64K_PAGES);
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	/*
-	 * No early pte entries with !ARM64_64K_PAGES configuration, so using
-	 * sections (pmd).
-	 */
-	size = page64k ? PAGE_SIZE : SECTION_SIZE;
-	mask = ~(size - 1);
-
-	pgd = pgd_offset_k(virt);
-	pud = pud_offset(pgd, virt);
-	if (pud_none(*pud))
-		return NULL;
-	pmd = pmd_offset(pud, virt);
-
-	if (page64k) {
-		if (pmd_none(*pmd))
-			return NULL;
-		pte = pte_offset_kernel(pmd, virt);
-		set_pte(pte, __pte((phys & mask) | PROT_DEVICE_nGnRE));
-	} else {
-		set_pmd(pmd, __pmd((phys & mask) | PROT_SECT_DEVICE_nGnRE));
+	if (virt < VMALLOC_START) {
+		pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
+			&phys, virt);
+		return;
 	}
+	__create_mapping(pgd_offset_k(virt & PAGE_MASK), phys, virt, size, 0);
+}
 
-	return (void __iomem *)((virt & mask) + (phys & ~mask));
+void __init create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io)
+{
+	if ((addr >> PGDIR_SHIFT) >= ARRAY_SIZE(idmap_pg_dir)) {
+		pr_warn("BUG: not creating id mapping for %pa\n", &addr);
+		return;
+	}
+	__create_mapping(&idmap_pg_dir[pgd_index(addr)],
+			 addr, addr, size, map_io);
 }
-#endif
 
 static void __init map_mem(void)
 {
@@ -357,7 +313,6 @@ void __init paging_init(void)
 {
 	void *zero_page;
 
-	init_mem_pgprot();
 	map_mem();
 
 	/*
@@ -416,6 +371,9 @@ int kern_addr_valid(unsigned long addr)
 	if (pmd_none(*pmd))
 		return 0;
 
+	if (pmd_sect(*pmd))
+		return pfn_valid(pmd_pfn(*pmd));
+
 	pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte))
 		return 0;
@@ -456,7 +414,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 			if (!p)
 				return -ENOMEM;
 
-			set_pmd(pmd, __pmd(__pa(p) | prot_sect_kernel));
+			set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL));
 		} else
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
 	} while (addr = next, addr != end);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 1333e6f9a8e5..e085ee6ef4e2 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -173,12 +173,6 @@ ENDPROC(cpu_do_switch_mm)
  *	value of the SCTLR_EL1 register.
  */
 ENTRY(__cpu_setup)
-	/*
-	 * Preserve the link register across the function call.
-	 */
-	mov	x28, lr
-	bl	__flush_dcache_all
-	mov	lr, x28
 	ic	iallu				// I+BTB cache invalidate
 	tlbi	vmalle1is			// invalidate I + D TLBs
 	dsb	sy
@@ -215,8 +209,14 @@ ENTRY(__cpu_setup)
 	 * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
 	 * both user and kernel.
 	 */
-	ldr	x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \
+	ldr	x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | \
 		      TCR_ASID16 | TCR_TBI0 | (1 << 31)
+	/*
+	 * Read the PARange bits from ID_AA64MMFR0_EL1 and set the IPS bits in
+	 * TCR_EL1.
+	 */
+	mrs	x9, ID_AA64MMFR0_EL1
+	bfi	x10, x9, #32, #3
 #ifdef CONFIG_ARM64_64K_PAGES
 	orr	x10, x10, TCR_TG0_64K
 	orr	x10, x10, TCR_TG1_64K
diff --git a/arch/arm64/mm/tlb.S b/arch/arm64/mm/tlb.S
deleted file mode 100644
index 19da91e0cd27..000000000000
--- a/arch/arm64/mm/tlb.S
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * Based on arch/arm/mm/tlb.S
- *
- * Copyright (C) 1997-2002 Russell King
- * Copyright (C) 2012 ARM Ltd.
- * Written by Catalin Marinas <catalin.marinas@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/asm-offsets.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-#include "proc-macros.S"
-
-/*
- *	__cpu_flush_user_tlb_range(start, end, vma)
- *
- *	Invalidate a range of TLB entries in the specified address space.
- *
- *	- start - start address (may not be aligned)
- *	- end   - end address (exclusive, may not be aligned)
- *	- vma   - vma_struct describing address range
- */
-ENTRY(__cpu_flush_user_tlb_range)
-	vma_vm_mm x3, x2			// get vma->vm_mm
-	mmid	w3, x3				// get vm_mm->context.id
-	dsb	sy
-	lsr	x0, x0, #12			// align address
-	lsr	x1, x1, #12
-	bfi	x0, x3, #48, #16		// start VA and ASID
-	bfi	x1, x3, #48, #16		// end VA and ASID
-1:	tlbi	vae1is, x0			// TLB invalidate by address and ASID
-	add	x0, x0, #1
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
-	ret
-ENDPROC(__cpu_flush_user_tlb_range)
-
-/*
- *	__cpu_flush_kern_tlb_range(start,end)
- *
- *	Invalidate a range of kernel TLB entries.
- *
- *	- start - start address (may not be aligned)
- *	- end   - end address (exclusive, may not be aligned)
- */
-ENTRY(__cpu_flush_kern_tlb_range)
-	dsb	sy
-	lsr	x0, x0, #12			// align address
-	lsr	x1, x1, #12
-1:	tlbi	vaae1is, x0			// TLB invalidate by address
-	add	x0, x0, #1
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
-	isb
-	ret
-ENDPROC(__cpu_flush_kern_tlb_range)
diff --git a/arch/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h
index 8a029505d7b7..2f1c3c2657ad 100644
--- a/arch/blackfin/include/asm/ftrace.h
+++ b/arch/blackfin/include/asm/ftrace.h
@@ -66,16 +66,7 @@ extern inline void *return_address(unsigned int level)
 
 #endif /* CONFIG_FRAME_POINTER */
 
-#define HAVE_ARCH_CALLER_ADDR
-
-/* inline function or macro may lead to unexpected result */
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index db95f570705f..4729752b7256 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -234,9 +234,6 @@ struct kvm_vm_data {
 #define KVM_REQ_PTC_G		32
 #define KVM_REQ_RESUME		33
 
-struct kvm;
-struct kvm_vcpu;
-
 struct kvm_mmio_req {
 	uint64_t addr;          /*  physical address		*/
 	uint64_t size;          /*  size in bytes		*/
@@ -595,6 +592,18 @@ void kvm_sal_emul(struct kvm_vcpu *vcpu);
 struct kvm *kvm_arch_alloc_vm(void);
 void kvm_arch_free_vm(struct kvm *kvm);
 
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm,
+		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_commit_memory_region(struct kvm *kvm,
+		struct kvm_userspace_memory_region *mem,
+		const struct kvm_memory_slot *old,
+		enum kvm_mr_change change) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+
 #endif /* __ASSEMBLY__*/
 
 #endif
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index 990b86420cc6..3d50ea955c4c 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -25,6 +25,7 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select KVM_APIC_ARCHITECTURE
 	select KVM_MMIO
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 53f44bee9ebb..c9aa236dc29b 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -125,7 +125,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler)
 
 static  DEFINE_SPINLOCK(vp_lock);
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	long  status;
 	long  tmp_base;
@@ -160,7 +160,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
 
 	long status;
@@ -190,7 +190,7 @@ void kvm_arch_check_processor_compat(void *rtn)
 	*(int *)rtn = 0;
 }
 
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 
 	int r;
@@ -1363,10 +1363,6 @@ static void kvm_release_vm_pages(struct kvm *kvm)
 	}
 }
 
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
-
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvm_iommu_unmap_guest(kvm);
@@ -1375,10 +1371,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_release_vm_pages(kvm);
 }
 
-void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
-{
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	if (cpu != vcpu->cpu) {
@@ -1467,7 +1459,6 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	kfree(vcpu->arch.apic);
 }
 
-
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -1550,21 +1541,12 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
-			   struct kvm_memory_slot *dont)
-{
-}
-
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    unsigned long npages)
 {
 	return 0;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
-{
-}
-
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		struct kvm_memory_slot *memslot,
 		struct kvm_userspace_memory_region *mem,
@@ -1596,14 +1578,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	return 0;
 }
 
-void kvm_arch_commit_memory_region(struct kvm *kvm,
-		struct kvm_userspace_memory_region *mem,
-		const struct kvm_memory_slot *old,
-		enum kvm_mr_change change)
-{
-	return;
-}
-
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
 	kvm_flush_remote_tlbs(kvm);
@@ -1852,10 +1826,6 @@ int kvm_arch_hardware_setup(void)
 	return 0;
 }
 
-void kvm_arch_hardware_unsetup(void)
-{
-}
-
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
 {
 	return __apic_accept_irq(vcpu, irq->vector);
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 68232db98baa..76069c18ee42 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -114,11 +114,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 0;
-}
-
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
 {
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index dbdd2231c75d..b2e322939256 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -17,6 +17,7 @@ config M68K
 	select FPU if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
+	select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
 	select MODULES_USE_ELF_RELA
diff --git a/arch/m68k/mm/hwtest.c b/arch/m68k/mm/hwtest.c
index 2c7dde3c6430..2a5259fd23eb 100644
--- a/arch/m68k/mm/hwtest.c
+++ b/arch/m68k/mm/hwtest.c
@@ -28,9 +28,11 @@
 int hwreg_present( volatile void *regp )
 {
     int	ret = 0;
+    unsigned long flags;
     long	save_sp, save_vbr;
     long	tmp_vectors[3];
 
+    local_irq_save(flags);
     __asm__ __volatile__
 	(	"movec	%/vbr,%2\n\t"
 		"movel	#Lberr1,%4@(8)\n\t"
@@ -46,6 +48,7 @@ int hwreg_present( volatile void *regp )
 		: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
 		: "a" (regp), "a" (tmp_vectors)
                 );
+    local_irq_restore(flags);
 
     return( ret );
 }
@@ -58,9 +61,11 @@ EXPORT_SYMBOL(hwreg_present);
 int hwreg_write( volatile void *regp, unsigned short val )
 {
 	int		ret;
+	unsigned long flags;
 	long	save_sp, save_vbr;
 	long	tmp_vectors[3];
 
+	local_irq_save(flags);
 	__asm__ __volatile__
 	(	"movec	%/vbr,%2\n\t"
 		"movel	#Lberr2,%4@(8)\n\t"
@@ -78,6 +83,7 @@ int hwreg_write( volatile void *regp, unsigned short val )
 		: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
 		: "a" (regp), "a" (tmp_vectors), "g" (val)
 	);
+	local_irq_restore(flags);
 
 	return( ret );
 }
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index 5d6b4b407dda..2d6f0de77325 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -15,6 +15,7 @@ static inline void wr_fence(void)
 	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_FENCE;
 	barrier();
 	*flushptr = 0;
+	barrier();
 }
 
 #else /* CONFIG_METAG_META21 */
@@ -35,6 +36,7 @@ static inline void wr_fence(void)
 	*flushptr = 0;
 	*flushptr = 0;
 	*flushptr = 0;
+	barrier();
 }
 
 #endif /* !CONFIG_METAG_META21 */
@@ -68,6 +70,7 @@ static inline void fence(void)
 	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_ATOMIC_UNLOCK;
 	barrier();
 	*flushptr = 0;
+	barrier();
 }
 #define smp_mb()        fence()
 #define smp_rmb()       fence()
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index f16477d1f571..a8a37477c66e 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -22,6 +22,8 @@
 /* Add an extra page of padding at the top of the stack for the guard page. */
 #define STACK_TOP	(TASK_SIZE - PAGE_SIZE)
 #define STACK_TOP_MAX	STACK_TOP
+/* Maximum virtual space for stack */
+#define STACK_SIZE_MAX	(CONFIG_MAX_STACK_SIZE_MB*1024*1024)
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index 042431509b56..3c52fa6d0f8e 100644
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -110,11 +110,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index abdfb10e7eca..c76630603058 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -43,13 +43,13 @@
 #include <asm/pci-bridge.h>
 
 #ifdef CONFIG_EARLY_PRINTK
-static char *stdout;
+static const char *stdout;
 
 static int __init early_init_dt_scan_chosen_serial(unsigned long node,
 				const char *uname, int depth, void *data)
 {
-	unsigned long l;
-	char *p;
+	int l;
+	const char *p;
 
 	pr_debug("%s: depth: %d, uname: %s\n", __func__, depth, uname);
 
@@ -80,7 +80,7 @@ static int __init early_init_dt_scan_chosen_serial(unsigned long node,
 				(strncmp(p, "xlnx,opb-uartlite", 17) == 0) ||
 				(strncmp(p, "xlnx,axi-uartlite", 17) == 0) ||
 				(strncmp(p, "xlnx,mdm", 8) == 0)) {
-			unsigned int *addrp;
+			const unsigned int *addrp;
 
 			*(u32 *)data = UARTLITE;
 
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index c00c4ddf4514..5244cecf1e45 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 
 #include <asm/addrspace.h>
 
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index c2bb4f896ce7..3aa5b46b2d40 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -635,7 +635,7 @@ static void octeon_irq_cpu_offline_ciu(struct irq_data *data)
 		cpumask_clear(&new_affinity);
 		cpumask_set_cpu(cpumask_first(cpu_online_mask), &new_affinity);
 	}
-	__irq_set_affinity_locked(data, &new_affinity);
+	irq_set_affinity_locked(data, &new_affinity, false);
 }
 
 static int octeon_irq_ciu_set_affinity(struct irq_data *data,
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 331b837cec57..270cb3c6c498 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -458,6 +458,18 @@ static void octeon_halt(void)
 	octeon_kill_core(NULL);
 }
 
+static char __read_mostly octeon_system_type[80];
+
+static int __init init_octeon_system_type(void)
+{
+	snprintf(octeon_system_type, sizeof(octeon_system_type), "%s (%s)",
+		cvmx_board_type_to_string(octeon_bootinfo->board_type),
+		octeon_model_get_string(read_c0_prid()));
+
+	return 0;
+}
+early_initcall(init_octeon_system_type);
+
 /**
  * Return a string representing the system type
  *
@@ -465,11 +477,7 @@ static void octeon_halt(void)
  */
 const char *octeon_board_type_string(void)
 {
-	static char name[80];
-	sprintf(name, "%s (%s)",
-		cvmx_board_type_to_string(octeon_bootinfo->board_type),
-		octeon_model_get_string(read_c0_prid()));
-	return name;
+	return octeon_system_type;
 }
 
 const char *get_system_type(void)
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index 992aaba603b5..b463f2aa5a61 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -24,7 +24,7 @@ do {							\
 	asm volatile (					\
 		"1: " load " %[tmp_dst], 0(%[tmp_src])\n"	\
 		"   li %[tmp_err], 0\n"			\
-		"2:\n"					\
+		"2: .insn\n"				\
 							\
 		".section .fixup, \"ax\"\n"		\
 		"3: li %[tmp_err], 1\n"			\
@@ -46,7 +46,7 @@ do {						\
 	asm volatile (				\
 		"1: " store " %[tmp_src], 0(%[tmp_dst])\n"\
 		"   li %[tmp_err], 0\n"		\
-		"2:\n"				\
+		"2: .insn\n"			\
 						\
 		".section .fixup, \"ax\"\n"	\
 		"3: li %[tmp_err], 1\n"		\
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index a995fce87791..ad91e1a3bb2c 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -64,11 +64,6 @@
 #define CAUSEB_DC       27
 #define CAUSEF_DC       (_ULCAST_(1)   << 27)
 
-struct kvm;
-struct kvm_run;
-struct kvm_vcpu;
-struct kvm_interrupt;
-
 extern atomic_t kvm_mips_instance;
 extern pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn);
 extern void (*kvm_mips_release_pfn_clean) (pfn_t pfn);
@@ -645,5 +640,16 @@ extern void mips32_SyncICache(unsigned long addr, unsigned long size);
 extern int kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
 extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
 
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm,
+		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+		struct kvm_memory_slot *slot) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
 #endif /* __MIPS_KVM_HOST_H__ */
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 7bba9da110af..6d019ca1bead 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -23,7 +23,7 @@
 struct pt_regs {
 #ifdef CONFIG_32BIT
 	/* Pad bytes for argument save space on the stack. */
-	unsigned long pad0[6];
+	unsigned long pad0[8];
 #endif
 
 	/* Saved main processor registers. */
diff --git a/arch/mips/include/asm/reg.h b/arch/mips/include/asm/reg.h
index 910e71a12466..b8343ccbc989 100644
--- a/arch/mips/include/asm/reg.h
+++ b/arch/mips/include/asm/reg.h
@@ -12,116 +12,194 @@
 #ifndef __ASM_MIPS_REG_H
 #define __ASM_MIPS_REG_H
 
-
-#if defined(CONFIG_32BIT) || defined(WANT_COMPAT_REG_H)
-
-#define EF_R0			6
-#define EF_R1			7
-#define EF_R2			8
-#define EF_R3			9
-#define EF_R4			10
-#define EF_R5			11
-#define EF_R6			12
-#define EF_R7			13
-#define EF_R8			14
-#define EF_R9			15
-#define EF_R10			16
-#define EF_R11			17
-#define EF_R12			18
-#define EF_R13			19
-#define EF_R14			20
-#define EF_R15			21
-#define EF_R16			22
-#define EF_R17			23
-#define EF_R18			24
-#define EF_R19			25
-#define EF_R20			26
-#define EF_R21			27
-#define EF_R22			28
-#define EF_R23			29
-#define EF_R24			30
-#define EF_R25			31
+#define MIPS32_EF_R0		6
+#define MIPS32_EF_R1		7
+#define MIPS32_EF_R2		8
+#define MIPS32_EF_R3		9
+#define MIPS32_EF_R4		10
+#define MIPS32_EF_R5		11
+#define MIPS32_EF_R6		12
+#define MIPS32_EF_R7		13
+#define MIPS32_EF_R8		14
+#define MIPS32_EF_R9		15
+#define MIPS32_EF_R10		16
+#define MIPS32_EF_R11		17
+#define MIPS32_EF_R12		18
+#define MIPS32_EF_R13		19
+#define MIPS32_EF_R14		20
+#define MIPS32_EF_R15		21
+#define MIPS32_EF_R16		22
+#define MIPS32_EF_R17		23
+#define MIPS32_EF_R18		24
+#define MIPS32_EF_R19		25
+#define MIPS32_EF_R20		26
+#define MIPS32_EF_R21		27
+#define MIPS32_EF_R22		28
+#define MIPS32_EF_R23		29
+#define MIPS32_EF_R24		30
+#define MIPS32_EF_R25		31
 
 /*
  * k0/k1 unsaved
  */
-#define EF_R26			32
-#define EF_R27			33
+#define MIPS32_EF_R26		32
+#define MIPS32_EF_R27		33
 
-#define EF_R28			34
-#define EF_R29			35
-#define EF_R30			36
-#define EF_R31			37
+#define MIPS32_EF_R28		34
+#define MIPS32_EF_R29		35
+#define MIPS32_EF_R30		36
+#define MIPS32_EF_R31		37
 
 /*
  * Saved special registers
  */
-#define EF_LO			38
-#define EF_HI			39
-
-#define EF_CP0_EPC		40
-#define EF_CP0_BADVADDR		41
-#define EF_CP0_STATUS		42
-#define EF_CP0_CAUSE		43
-#define EF_UNUSED0		44
-
-#define EF_SIZE			180
-
-#endif
-
-#if defined(CONFIG_64BIT) && !defined(WANT_COMPAT_REG_H)
-
-#define EF_R0			 0
-#define EF_R1			 1
-#define EF_R2			 2
-#define EF_R3			 3
-#define EF_R4			 4
-#define EF_R5			 5
-#define EF_R6			 6
-#define EF_R7			 7
-#define EF_R8			 8
-#define EF_R9			 9
-#define EF_R10			10
-#define EF_R11			11
-#define EF_R12			12
-#define EF_R13			13
-#define EF_R14			14
-#define EF_R15			15
-#define EF_R16			16
-#define EF_R17			17
-#define EF_R18			18
-#define EF_R19			19
-#define EF_R20			20
-#define EF_R21			21
-#define EF_R22			22
-#define EF_R23			23
-#define EF_R24			24
-#define EF_R25			25
+#define MIPS32_EF_LO		38
+#define MIPS32_EF_HI		39
+
+#define MIPS32_EF_CP0_EPC	40
+#define MIPS32_EF_CP0_BADVADDR	41
+#define MIPS32_EF_CP0_STATUS	42
+#define MIPS32_EF_CP0_CAUSE	43
+#define MIPS32_EF_UNUSED0	44
+
+#define MIPS32_EF_SIZE		180
+
+#define MIPS64_EF_R0		0
+#define MIPS64_EF_R1		1
+#define MIPS64_EF_R2		2
+#define MIPS64_EF_R3		3
+#define MIPS64_EF_R4		4
+#define MIPS64_EF_R5		5
+#define MIPS64_EF_R6		6
+#define MIPS64_EF_R7		7
+#define MIPS64_EF_R8		8
+#define MIPS64_EF_R9		9
+#define MIPS64_EF_R10		10
+#define MIPS64_EF_R11		11
+#define MIPS64_EF_R12		12
+#define MIPS64_EF_R13		13
+#define MIPS64_EF_R14		14
+#define MIPS64_EF_R15		15
+#define MIPS64_EF_R16		16
+#define MIPS64_EF_R17		17
+#define MIPS64_EF_R18		18
+#define MIPS64_EF_R19		19
+#define MIPS64_EF_R20		20
+#define MIPS64_EF_R21		21
+#define MIPS64_EF_R22		22
+#define MIPS64_EF_R23		23
+#define MIPS64_EF_R24		24
+#define MIPS64_EF_R25		25
 
 /*
  * k0/k1 unsaved
  */
-#define EF_R26			26
-#define EF_R27			27
+#define MIPS64_EF_R26		26
+#define MIPS64_EF_R27		27
 
 
-#define EF_R28			28
-#define EF_R29			29
-#define EF_R30			30
-#define EF_R31			31
+#define MIPS64_EF_R28		28
+#define MIPS64_EF_R29		29
+#define MIPS64_EF_R30		30
+#define MIPS64_EF_R31		31
 
 /*
  * Saved special registers
  */
-#define EF_LO			32
-#define EF_HI			33
-
-#define EF_CP0_EPC		34
-#define EF_CP0_BADVADDR		35
-#define EF_CP0_STATUS		36
-#define EF_CP0_CAUSE		37
-
-#define EF_SIZE			304	/* size in bytes */
+#define MIPS64_EF_LO		32
+#define MIPS64_EF_HI		33
+
+#define MIPS64_EF_CP0_EPC	34
+#define MIPS64_EF_CP0_BADVADDR	35
+#define MIPS64_EF_CP0_STATUS	36
+#define MIPS64_EF_CP0_CAUSE	37
+
+#define MIPS64_EF_SIZE		304	/* size in bytes */
+
+#if defined(CONFIG_32BIT)
+
+#define EF_R0			MIPS32_EF_R0
+#define EF_R1			MIPS32_EF_R1
+#define EF_R2			MIPS32_EF_R2
+#define EF_R3			MIPS32_EF_R3
+#define EF_R4			MIPS32_EF_R4
+#define EF_R5			MIPS32_EF_R5
+#define EF_R6			MIPS32_EF_R6
+#define EF_R7			MIPS32_EF_R7
+#define EF_R8			MIPS32_EF_R8
+#define EF_R9			MIPS32_EF_R9
+#define EF_R10			MIPS32_EF_R10
+#define EF_R11			MIPS32_EF_R11
+#define EF_R12			MIPS32_EF_R12
+#define EF_R13			MIPS32_EF_R13
+#define EF_R14			MIPS32_EF_R14
+#define EF_R15			MIPS32_EF_R15
+#define EF_R16			MIPS32_EF_R16
+#define EF_R17			MIPS32_EF_R17
+#define EF_R18			MIPS32_EF_R18
+#define EF_R19			MIPS32_EF_R19
+#define EF_R20			MIPS32_EF_R20
+#define EF_R21			MIPS32_EF_R21
+#define EF_R22			MIPS32_EF_R22
+#define EF_R23			MIPS32_EF_R23
+#define EF_R24			MIPS32_EF_R24
+#define EF_R25			MIPS32_EF_R25
+#define EF_R26			MIPS32_EF_R26
+#define EF_R27			MIPS32_EF_R27
+#define EF_R28			MIPS32_EF_R28
+#define EF_R29			MIPS32_EF_R29
+#define EF_R30			MIPS32_EF_R30
+#define EF_R31			MIPS32_EF_R31
+#define EF_LO			MIPS32_EF_LO
+#define EF_HI			MIPS32_EF_HI
+#define EF_CP0_EPC		MIPS32_EF_CP0_EPC
+#define EF_CP0_BADVADDR		MIPS32_EF_CP0_BADVADDR
+#define EF_CP0_STATUS		MIPS32_EF_CP0_STATUS
+#define EF_CP0_CAUSE		MIPS32_EF_CP0_CAUSE
+#define EF_UNUSED0		MIPS32_EF_UNUSED0
+#define EF_SIZE			MIPS32_EF_SIZE
+
+#elif defined(CONFIG_64BIT)
+
+#define EF_R0			MIPS64_EF_R0
+#define EF_R1			MIPS64_EF_R1
+#define EF_R2			MIPS64_EF_R2
+#define EF_R3			MIPS64_EF_R3
+#define EF_R4			MIPS64_EF_R4
+#define EF_R5			MIPS64_EF_R5
+#define EF_R6			MIPS64_EF_R6
+#define EF_R7			MIPS64_EF_R7
+#define EF_R8			MIPS64_EF_R8
+#define EF_R9			MIPS64_EF_R9
+#define EF_R10			MIPS64_EF_R10
+#define EF_R11			MIPS64_EF_R11
+#define EF_R12			MIPS64_EF_R12
+#define EF_R13			MIPS64_EF_R13
+#define EF_R14			MIPS64_EF_R14
+#define EF_R15			MIPS64_EF_R15
+#define EF_R16			MIPS64_EF_R16
+#define EF_R17			MIPS64_EF_R17
+#define EF_R18			MIPS64_EF_R18
+#define EF_R19			MIPS64_EF_R19
+#define EF_R20			MIPS64_EF_R20
+#define EF_R21			MIPS64_EF_R21
+#define EF_R22			MIPS64_EF_R22
+#define EF_R23			MIPS64_EF_R23
+#define EF_R24			MIPS64_EF_R24
+#define EF_R25			MIPS64_EF_R25
+#define EF_R26			MIPS64_EF_R26
+#define EF_R27			MIPS64_EF_R27
+#define EF_R28			MIPS64_EF_R28
+#define EF_R29			MIPS64_EF_R29
+#define EF_R30			MIPS64_EF_R30
+#define EF_R31			MIPS64_EF_R31
+#define EF_LO			MIPS64_EF_LO
+#define EF_HI			MIPS64_EF_HI
+#define EF_CP0_EPC		MIPS64_EF_CP0_EPC
+#define EF_CP0_BADVADDR		MIPS64_EF_CP0_BADVADDR
+#define EF_CP0_STATUS		MIPS64_EF_CP0_STATUS
+#define EF_CP0_CAUSE		MIPS64_EF_CP0_CAUSE
+#define EF_SIZE			MIPS64_EF_SIZE
 
 #endif /* CONFIG_64BIT */
 
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 24846f9053fe..e80ae50cae80 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -136,7 +136,8 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 
 #define _TIF_WORK_SYSCALL_ENTRY	(_TIF_NOHZ | _TIF_SYSCALL_TRACE |	\
-				 _TIF_SYSCALL_AUDIT | _TIF_SYSCALL_TRACEPOINT)
+				 _TIF_SYSCALL_AUDIT | \
+				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
 
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT	(_TIF_NOHZ | _TIF_SYSCALL_TRACE |	\
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 7faf5f2bee25..71df942fb77c 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -72,12 +72,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 
 #include <asm/processor.h>
 
-/*
- * When this file is selected, we are definitely running a 64bit kernel.
- * So using the right regs define in asm/reg.h
- */
-#define WANT_COMPAT_REG_H
-
 /* These MUST be defined before elf.h gets included */
 extern void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs);
 #define ELF_CORE_COPY_REGS(_dest, _regs) elf32_core_copy_regs(_dest, _regs);
@@ -149,21 +143,21 @@ void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs)
 {
 	int i;
 
-	for (i = 0; i < EF_R0; i++)
+	for (i = 0; i < MIPS32_EF_R0; i++)
 		grp[i] = 0;
-	grp[EF_R0] = 0;
+	grp[MIPS32_EF_R0] = 0;
 	for (i = 1; i <= 31; i++)
-		grp[EF_R0 + i] = (elf_greg_t) regs->regs[i];
-	grp[EF_R26] = 0;
-	grp[EF_R27] = 0;
-	grp[EF_LO] = (elf_greg_t) regs->lo;
-	grp[EF_HI] = (elf_greg_t) regs->hi;
-	grp[EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
-	grp[EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
-	grp[EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
-	grp[EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
-#ifdef EF_UNUSED0
-	grp[EF_UNUSED0] = 0;
+		grp[MIPS32_EF_R0 + i] = (elf_greg_t) regs->regs[i];
+	grp[MIPS32_EF_R26] = 0;
+	grp[MIPS32_EF_R27] = 0;
+	grp[MIPS32_EF_LO] = (elf_greg_t) regs->lo;
+	grp[MIPS32_EF_HI] = (elf_greg_t) regs->hi;
+	grp[MIPS32_EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
+	grp[MIPS32_EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
+	grp[MIPS32_EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
+	grp[MIPS32_EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
+#ifdef MIPS32_EF_UNUSED0
+	grp[MIPS32_EF_UNUSED0] = 0;
 #endif
 }
 
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 5b5ddb231f26..78f18436cdf2 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -255,11 +255,13 @@ static void __init gic_setup_intr(unsigned int intr, unsigned int cpu,
 
 	/* Setup Intr to Pin mapping */
 	if (pin & GIC_MAP_TO_NMI_MSK) {
+		int i;
+
 		GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin);
 		/* FIXME: hack to route NMI to all cpu's */
-		for (cpu = 0; cpu < NR_CPUS; cpu += 32) {
+		for (i = 0; i < NR_CPUS; i += 32) {
 			GICWRITE(GIC_REG_ADDR(SHARED,
-					  GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)),
+					  GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)),
 				 0xffffffff);
 		}
 	} else {
diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c
index fab40f7d2e03..ac9facc08694 100644
--- a/arch/mips/kernel/irq-msc01.c
+++ b/arch/mips/kernel/irq-msc01.c
@@ -131,7 +131,7 @@ void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqma
 
 	board_bind_eic_interrupt = &msc_bind_eic_interrupt;
 
-	for (; nirq >= 0; nirq--, imp++) {
+	for (; nirq > 0; nirq--, imp++) {
 		int n = imp->im_irq;
 
 		switch (imp->im_type) {
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 539b6294b613..8f89ff4ed524 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -123,7 +123,11 @@ NESTED(_mcount, PT_SIZE, ra)
 	 nop
 #endif
 	b	ftrace_stub
+#ifdef CONFIG_32BIT
+	 addiu sp, sp, 8
+#else
 	 nop
+#endif
 
 static_trace:
 	MCOUNT_SAVE_REGS
@@ -133,6 +137,9 @@ static_trace:
 	 move	a1, AT		/* arg2: parent's return address */
 
 	MCOUNT_RESTORE_REGS
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
 	.globl ftrace_stub
 ftrace_stub:
 	RETURN_BACK
@@ -177,6 +184,11 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra)
 	jal	prepare_ftrace_return
 	 nop
 	MCOUNT_RESTORE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
+#endif
 	RETURN_BACK
 	END(ftrace_graph_caller)
 
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 7da9b76db4d9..60f48febe762 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -170,6 +170,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 		__get_user(fregs[i], i + (__u64 __user *) data);
 
 	__get_user(child->thread.fpu.fcr31, data + 64);
+	child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
 
 	/* FIR may not be written.  */
 
@@ -265,36 +266,160 @@ int ptrace_set_watch_regs(struct task_struct *child,
 
 /* regset get/set implementations */
 
-static int gpr_get(struct task_struct *target,
-		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
+static int gpr32_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
 {
 	struct pt_regs *regs = task_pt_regs(target);
+	u32 uregs[ELF_NGREG] = {};
+	unsigned i;
 
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   regs, 0, sizeof(*regs));
+	for (i = MIPS32_EF_R1; i <= MIPS32_EF_R31; i++) {
+		/* k0/k1 are copied as zero. */
+		if (i == MIPS32_EF_R26 || i == MIPS32_EF_R27)
+			continue;
+
+		uregs[i] = regs->regs[i - MIPS32_EF_R0];
+	}
+
+	uregs[MIPS32_EF_LO] = regs->lo;
+	uregs[MIPS32_EF_HI] = regs->hi;
+	uregs[MIPS32_EF_CP0_EPC] = regs->cp0_epc;
+	uregs[MIPS32_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
+	uregs[MIPS32_EF_CP0_STATUS] = regs->cp0_status;
+	uregs[MIPS32_EF_CP0_CAUSE] = regs->cp0_cause;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				   sizeof(uregs));
 }
 
-static int gpr_set(struct task_struct *target,
-		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
+static int gpr32_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
 {
-	struct pt_regs newregs;
-	int ret;
+	struct pt_regs *regs = task_pt_regs(target);
+	u32 uregs[ELF_NGREG];
+	unsigned start, num_regs, i;
+	int err;
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &newregs,
-				 0, sizeof(newregs));
-	if (ret)
-		return ret;
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
 
-	*task_pt_regs(target) = newregs;
+	if (start + num_regs > ELF_NGREG)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				 sizeof(uregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++) {
+		/*
+		 * Cast all values to signed here so that if this is a 64-bit
+		 * kernel, the supplied 32-bit values will be sign extended.
+		 */
+		switch (i) {
+		case MIPS32_EF_R1 ... MIPS32_EF_R25:
+			/* k0/k1 are ignored. */
+		case MIPS32_EF_R28 ... MIPS32_EF_R31:
+			regs->regs[i - MIPS32_EF_R0] = (s32)uregs[i];
+			break;
+		case MIPS32_EF_LO:
+			regs->lo = (s32)uregs[i];
+			break;
+		case MIPS32_EF_HI:
+			regs->hi = (s32)uregs[i];
+			break;
+		case MIPS32_EF_CP0_EPC:
+			regs->cp0_epc = (s32)uregs[i];
+			break;
+		}
+	}
 
 	return 0;
 }
 
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
+static int gpr64_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	struct pt_regs *regs = task_pt_regs(target);
+	u64 uregs[ELF_NGREG] = {};
+	unsigned i;
+
+	for (i = MIPS64_EF_R1; i <= MIPS64_EF_R31; i++) {
+		/* k0/k1 are copied as zero. */
+		if (i == MIPS64_EF_R26 || i == MIPS64_EF_R27)
+			continue;
+
+		uregs[i] = regs->regs[i - MIPS64_EF_R0];
+	}
+
+	uregs[MIPS64_EF_LO] = regs->lo;
+	uregs[MIPS64_EF_HI] = regs->hi;
+	uregs[MIPS64_EF_CP0_EPC] = regs->cp0_epc;
+	uregs[MIPS64_EF_CP0_BADVADDR] = regs->cp0_badvaddr;
+	uregs[MIPS64_EF_CP0_STATUS] = regs->cp0_status;
+	uregs[MIPS64_EF_CP0_CAUSE] = regs->cp0_cause;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				   sizeof(uregs));
+}
+
+static int gpr64_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	struct pt_regs *regs = task_pt_regs(target);
+	u64 uregs[ELF_NGREG];
+	unsigned start, num_regs, i;
+	int err;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > ELF_NGREG)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0,
+				 sizeof(uregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++) {
+		switch (i) {
+		case MIPS64_EF_R1 ... MIPS64_EF_R25:
+			/* k0/k1 are ignored. */
+		case MIPS64_EF_R28 ... MIPS64_EF_R31:
+			regs->regs[i - MIPS64_EF_R0] = uregs[i];
+			break;
+		case MIPS64_EF_LO:
+			regs->lo = uregs[i];
+			break;
+		case MIPS64_EF_HI:
+			regs->hi = uregs[i];
+			break;
+		case MIPS64_EF_CP0_EPC:
+			regs->cp0_epc = uregs[i];
+			break;
+		}
+	}
+
+	return 0;
+}
+
+#endif /* CONFIG_64BIT */
+
 static int fpr_get(struct task_struct *target,
 		   const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
@@ -322,14 +447,16 @@ enum mips_regset {
 	REGSET_FPR,
 };
 
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
 static const struct user_regset mips_regsets[] = {
 	[REGSET_GPR] = {
 		.core_note_type	= NT_PRSTATUS,
 		.n		= ELF_NGREG,
 		.size		= sizeof(unsigned int),
 		.align		= sizeof(unsigned int),
-		.get		= gpr_get,
-		.set		= gpr_set,
+		.get		= gpr32_get,
+		.set		= gpr32_set,
 	},
 	[REGSET_FPR] = {
 		.core_note_type	= NT_PRFPREG,
@@ -349,14 +476,18 @@ static const struct user_regset_view user_mips_view = {
 	.n		= ARRAY_SIZE(mips_regsets),
 };
 
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
 static const struct user_regset mips64_regsets[] = {
 	[REGSET_GPR] = {
 		.core_note_type	= NT_PRSTATUS,
 		.n		= ELF_NGREG,
 		.size		= sizeof(unsigned long),
 		.align		= sizeof(unsigned long),
-		.get		= gpr_get,
-		.set		= gpr_set,
+		.get		= gpr64_get,
+		.set		= gpr64_set,
 	},
 	[REGSET_FPR] = {
 		.core_note_type	= NT_PRFPREG,
@@ -369,25 +500,26 @@ static const struct user_regset mips64_regsets[] = {
 };
 
 static const struct user_regset_view user_mips64_view = {
-	.name		= "mips",
+	.name		= "mips64",
 	.e_machine	= ELF_ARCH,
 	.ei_osabi	= ELF_OSABI,
 	.regsets	= mips64_regsets,
-	.n		= ARRAY_SIZE(mips_regsets),
+	.n		= ARRAY_SIZE(mips64_regsets),
 };
 
+#endif /* CONFIG_64BIT */
+
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
 #ifdef CONFIG_32BIT
 	return &user_mips_view;
-#endif
-
+#else
 #ifdef CONFIG_MIPS32_O32
-		if (test_thread_flag(TIF_32BIT_REGS))
-			return &user_mips_view;
+	if (test_tsk_thread_flag(task, TIF_32BIT_REGS))
+		return &user_mips_view;
 #endif
-
 	return &user_mips64_view;
+#endif
 }
 
 long arch_ptrace(struct task_struct *child, long request,
@@ -593,7 +725,7 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 #endif
 		case FPC_CSR:
-			child->thread.fpu.fcr31 = data;
+			child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
 			break;
 		case DSP_BASE ... DSP_BASE + 5: {
 			dspreg_t *dregs;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index e0b499694d18..81e6ae0220bc 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1429,7 +1429,7 @@ asmlinkage void cache_parity_error(void)
 	       reg_val & (1<<30) ? "secondary" : "primary",
 	       reg_val & (1<<31) ? "data" : "insn");
 	if (cpu_has_mips_r2 &&
-	    ((current_cpu_data.processor_id && 0xff0000) == PRID_COMP_MIPS)) {
+	    ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) {
 		pr_err("Error bits: %s%s%s%s%s%s%s%s\n",
 			reg_val & (1<<29) ? "ED " : "",
 			reg_val & (1<<28) ? "ET " : "",
@@ -1469,7 +1469,7 @@ asmlinkage void do_ftlb(void)
 
 	/* For the moment, report the problem and hang. */
 	if (cpu_has_mips_r2 &&
-	    ((current_cpu_data.processor_id && 0xff0000) == PRID_COMP_MIPS)) {
+	    ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS)) {
 		pr_err("FTLB error exception, cp0_ecc=0x%08x:\n",
 		       read_c0_ecc());
 		pr_err("cp0_errorepc == %0*lx\n", field, read_c0_errorepc());
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index c369a5d35527..b897dde93e7a 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -605,7 +605,6 @@ static void emulate_load_store_insn(struct pt_regs *regs,
 	case sdc1_op:
 		die_if_kernel("Unaligned FP access in kernel code", regs);
 		BUG_ON(!used_math());
-		BUG_ON(!is_fpu_owner());
 
 		lose_fpu(1);	/* Save FPU state for the emulator. */
 		res = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index da5186fbd77a..3e0ff8d0fbf9 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -149,9 +149,7 @@ void kvm_mips_free_vcpus(struct kvm *kvm)
 		if (kvm->arch.guest_pmap[i] != KVM_INVALID_PAGE)
 			kvm_mips_release_pfn_clean(kvm->arch.guest_pmap[i]);
 	}
-
-	if (kvm->arch.guest_pmap)
-		kfree(kvm->arch.guest_pmap);
+	kfree(kvm->arch.guest_pmap);
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		kvm_arch_vcpu_free(vcpu);
@@ -304,7 +302,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (cpu_has_veic || cpu_has_vint) {
 		size = 0x200 + VECTORSPACING * 64;
 	} else {
-		size = 0x200;
+		size = 0x4000;
 	}
 
 	/* Save Linux EBASE */
@@ -389,12 +387,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 
 	kvm_mips_dump_stats(vcpu);
 
-	if (vcpu->arch.guest_ebase)
-		kfree(vcpu->arch.guest_ebase);
-
-	if (vcpu->arch.kseg0_commpage)
-		kfree(vcpu->arch.kseg0_commpage);
-
+	kfree(vcpu->arch.guest_ebase);
+	kfree(vcpu->arch.kseg0_commpage);
+	kfree(vcpu);
 }
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c
index 4b6274b47f33..e75ef8219caf 100644
--- a/arch/mips/kvm/kvm_mips_emul.c
+++ b/arch/mips/kvm/kvm_mips_emul.c
@@ -1571,17 +1571,17 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 			arch->gprs[rt] = kvm_read_c0_guest_userlocal(cop0);
 #else
 			/* UserLocal not implemented */
-			er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
+			er = EMULATE_FAIL;
 #endif
 			break;
 
 		default:
-			printk("RDHWR not supported\n");
+			kvm_debug("RDHWR %#x not supported @ %p\n", rd, opc);
 			er = EMULATE_FAIL;
 			break;
 		}
 	} else {
-		printk("Emulate RI not supported @ %p: %#x\n", opc, inst);
+		kvm_debug("Emulate RI not supported @ %p: %#x\n", opc, inst);
 		er = EMULATE_FAIL;
 	}
 
@@ -1590,6 +1590,7 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 	 */
 	if (er == EMULATE_FAIL) {
 		vcpu->arch.pc = curr_pc;
+		er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
 	}
 	return er;
 }
diff --git a/arch/mips/lantiq/dts/easy50712.dts b/arch/mips/lantiq/dts/easy50712.dts
index fac1f5b178eb..143b8a37b5e4 100644
--- a/arch/mips/lantiq/dts/easy50712.dts
+++ b/arch/mips/lantiq/dts/easy50712.dts
@@ -8,6 +8,7 @@
 	};
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index 9e4484ccbb03..9005a8d60969 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -11,7 +11,8 @@ obj-$(CONFIG_PCI) += pci.o
 # Serial port support
 #
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-obj-$(CONFIG_SERIAL_8250) += serial.o
+loongson-serial-$(CONFIG_SERIAL_8250) := serial.o
+obj-y += $(loongson-serial-m) $(loongson-serial-y)
 obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
 obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
 
diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c
index aed32b88576c..7d8c9cce3009 100644
--- a/arch/mips/loongson/lemote-2f/clock.c
+++ b/arch/mips/loongson/lemote-2f/clock.c
@@ -91,6 +91,7 @@ EXPORT_SYMBOL(clk_put);
 
 int clk_set_rate(struct clk *clk, unsigned long rate)
 {
+	unsigned int rate_khz = rate / 1000;
 	int ret = 0;
 	int regval;
 	int i;
@@ -111,10 +112,10 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 		if (loongson2_clockmod_table[i].frequency ==
 		    CPUFREQ_ENTRY_INVALID)
 			continue;
-		if (rate == loongson2_clockmod_table[i].frequency)
+		if (rate_khz == loongson2_clockmod_table[i].frequency)
 			break;
 	}
-	if (rate != loongson2_clockmod_table[i].frequency)
+	if (rate_khz != loongson2_clockmod_table[i].frequency)
 		return -ENOTSUPP;
 
 	clk->rate = rate;
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index 77e0ae036e7c..4ec8ee10d371 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -84,11 +84,6 @@ int pud_huge(pud_t pud)
 	return (pud_val(pud) & _PAGE_HUGE) != 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 6b59617760c1..4be046bfc673 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -74,6 +74,7 @@
  */
 unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL_GPL(empty_zero_page);
+EXPORT_SYMBOL(zero_page_mask);
 
 /*
  * Not static inline because used by IP27 special magic initialization code
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index b234b1b5ccad..dd012c599ad1 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1057,6 +1057,7 @@ static void build_update_entries(u32 **p, unsigned int tmp, unsigned int ptep)
 struct mips_huge_tlb_info {
 	int huge_pte;
 	int restore_scratch;
+	bool need_reload_pte;
 };
 
 static struct mips_huge_tlb_info
@@ -1071,6 +1072,7 @@ build_fast_tlb_refill_handler (u32 **p, struct uasm_label **l,
 
 	rv.huge_pte = scratch;
 	rv.restore_scratch = 0;
+	rv.need_reload_pte = false;
 
 	if (check_for_high_segbits) {
 		UASM_i_MFC0(p, tmp, C0_BADVADDR);
@@ -1259,6 +1261,7 @@ static void build_r4000_tlb_refill_handler(void)
 	} else {
 		htlb_info.huge_pte = K0;
 		htlb_info.restore_scratch = 0;
+		htlb_info.need_reload_pte = true;
 		vmalloc_mode = refill_noscratch;
 		/*
 		 * create the plain linear handler
@@ -1295,6 +1298,8 @@ static void build_r4000_tlb_refill_handler(void)
 	}
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	uasm_l_tlb_huge_update(&l, p);
+	if (htlb_info.need_reload_pte)
+		UASM_i_LW(&p, htlb_info.huge_pte, 0, K1);
 	build_huge_update_entries(&p, htlb_info.huge_pte, K1);
 	build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random,
 				   htlb_info.restore_scratch);
diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c
index 6854ed5097d2..83a1dfd8f0e3 100644
--- a/arch/mips/oprofile/backtrace.c
+++ b/arch/mips/oprofile/backtrace.c
@@ -92,7 +92,7 @@ static inline int unwind_user_frame(struct stackframe *old_frame,
 				/* This marks the end of the previous function,
 				   which means we overran. */
 				break;
-			stack_size = (unsigned) stack_adjustment;
+			stack_size = (unsigned long) stack_adjustment;
 		} else if (is_ra_save_ins(&ip)) {
 			int ra_slot = ip.i_format.simmediate;
 			if (ra_slot < 0)
diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S
index 7e0277a1048f..32a7c828f073 100644
--- a/arch/mips/power/hibernate.S
+++ b/arch/mips/power/hibernate.S
@@ -43,6 +43,7 @@ LEAF(swsusp_arch_resume)
 	bne t1, t3, 1b
 	PTR_L t0, PBE_NEXT(t0)
 	bnez t0, 0b
+	jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */
 	PTR_LA t0, saved_regs
 	PTR_L ra, PT_R31(t0)
 	PTR_L sp, PT_R29(t0)
diff --git a/arch/mips/ralink/dts/mt7620a_eval.dts b/arch/mips/ralink/dts/mt7620a_eval.dts
index 35eb874ab7f1..709f58132f5c 100644
--- a/arch/mips/ralink/dts/mt7620a_eval.dts
+++ b/arch/mips/ralink/dts/mt7620a_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink MT7620A evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt2880_eval.dts b/arch/mips/ralink/dts/rt2880_eval.dts
index 322d7002595b..0a685db093d4 100644
--- a/arch/mips/ralink/dts/rt2880_eval.dts
+++ b/arch/mips/ralink/dts/rt2880_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT2880 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x8000000 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/ralink/dts/rt3052_eval.dts
index 0ac73ea28198..ec9e9a035541 100644
--- a/arch/mips/ralink/dts/rt3052_eval.dts
+++ b/arch/mips/ralink/dts/rt3052_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT3052 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt3883_eval.dts b/arch/mips/ralink/dts/rt3883_eval.dts
index 2fa6b330bf4f..e8df21a5d10d 100644
--- a/arch/mips/ralink/dts/rt3883_eval.dts
+++ b/arch/mips/ralink/dts/rt3883_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT3883 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index bb2a8ec440e7..a8f4a70c0742 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -22,6 +22,7 @@ config PARISC
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
 	select SYSCTL_ARCH_UNALIGN_ALLOW
+	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_MOD_ARCH_SPECIFIC
 	select VIRT_TO_BUS
 	select MODULES_USE_ELF_RELA
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 7187664034c3..5db8882f732c 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -48,7 +48,12 @@ cflags-y	:= -pipe
 
 # These flags should be implied by an hppa-linux configuration, but they
 # are not in gcc 3.2.
-cflags-y	+= -mno-space-regs -mfast-indirect-calls
+cflags-y	+= -mno-space-regs
+
+# -mfast-indirect-calls is only relevant for 32-bit kernels.
+ifndef CONFIG_64BIT
+cflags-y	+= -mfast-indirect-calls
+endif
 
 # Currently we save and restore fpregs on all kernel entry/interruption paths.
 # If that gets optimized, we might need to disable the use of fpregs in the
diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h
index 72c0fafaa039..544ed8ef87eb 100644
--- a/arch/parisc/include/asm/ftrace.h
+++ b/arch/parisc/include/asm/ftrace.h
@@ -24,15 +24,7 @@ extern void return_to_handler(void);
 
 extern unsigned long return_address(unsigned int);
 
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 return_address(1)
-#define CALLER_ADDR2 return_address(2)
-#define CALLER_ADDR3 return_address(3)
-#define CALLER_ADDR4 return_address(4)
-#define CALLER_ADDR5 return_address(5)
-#define CALLER_ADDR6 return_address(6)
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 198a86feb574..d951c9681ab3 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -55,6 +55,11 @@
 #define STACK_TOP	TASK_SIZE
 #define STACK_TOP_MAX	DEFAULT_TASK_SIZE
 
+/* Allow bigger stacks for 64-bit processes */
+#define STACK_SIZE_MAX	(USER_WIDE_MODE					\
+			 ? (1 << 30)	/* 1 GB */			\
+			 : (CONFIG_MAX_STACK_SIZE_MB*1024*1024))
+
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/parisc/include/asm/shmparam.h b/arch/parisc/include/asm/shmparam.h
index 628ddc22faa8..afe1300ab667 100644
--- a/arch/parisc/include/asm/shmparam.h
+++ b/arch/parisc/include/asm/shmparam.h
@@ -1,8 +1,7 @@
 #ifndef _ASMPARISC_SHMPARAM_H
 #define _ASMPARISC_SHMPARAM_H
 
-#define __ARCH_FORCE_SHMLBA 	1
-
-#define SHMLBA 0x00400000   /* attach addr needs to be 4 Mb aligned */
+#define SHMLBA	   PAGE_SIZE	/* attach addr a multiple of this */
+#define SHM_COLOUR 0x00400000	/* shared mappings colouring */
 
 #endif /* _ASMPARISC_SHMPARAM_H */
diff --git a/arch/parisc/include/uapi/asm/resource.h b/arch/parisc/include/uapi/asm/resource.h
index 8b06343b62ed..090483c47dbb 100644
--- a/arch/parisc/include/uapi/asm/resource.h
+++ b/arch/parisc/include/uapi/asm/resource.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_PARISC_RESOURCE_H
 #define _ASM_PARISC_RESOURCE_H
 
-#define _STK_LIM_MAX	10 * _STK_LIM
 #include <asm-generic/resource.h>
 
 #endif
diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h
index 0a3eada1863b..f395cde7b593 100644
--- a/arch/parisc/include/uapi/asm/shmbuf.h
+++ b/arch/parisc/include/uapi/asm/shmbuf.h
@@ -36,23 +36,16 @@ struct shmid64_ds {
 	unsigned int		__unused2;
 };
 
-#ifdef CONFIG_64BIT
-/* The 'unsigned int' (formerly 'unsigned long') data types below will
- * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on
- * a wide kernel, but if some of these values are meant to contain pointers
- * they may need to be 'long long' instead. -PB XXX FIXME
- */
-#endif
 struct shminfo64 {
-	unsigned int	shmmax;
-	unsigned int	shmmin;
-	unsigned int	shmmni;
-	unsigned int	shmseg;
-	unsigned int	shmall;
-	unsigned int	__unused1;
-	unsigned int	__unused2;
-	unsigned int	__unused3;
-	unsigned int	__unused4;
+	unsigned long	shmmax;
+	unsigned long	shmmin;
+	unsigned long	shmmni;
+	unsigned long	shmseg;
+	unsigned long	shmall;
+	unsigned long	__unused1;
+	unsigned long	__unused2;
+	unsigned long	__unused3;
+	unsigned long	__unused4;
 };
 
 #endif /* _PARISC_SHMBUF_H */
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index a2fa297196bc..f5645d6a89f2 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -69,8 +69,6 @@
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-#define SA_RESTORER	0x04000000 /* obsolete -- ignored */
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index a6ffc775a9f8..f6448c7c62b5 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -323,7 +323,8 @@ void flush_dcache_page(struct page *page)
 		 * specifically accesses it, of course) */
 
 		flush_tlb_page(mpnt, addr);
-		if (old_addr == 0 || (old_addr & (SHMLBA - 1)) != (addr & (SHMLBA - 1))) {
+		if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
+				      != (addr & (SHM_COLOUR - 1))) {
 			__flush_cache_page(mpnt, addr, page_to_phys(page));
 			if (old_addr)
 				printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? (char *)mpnt->vm_file->f_path.dentry->d_name.name : "(null)");
diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c
index 608716f8496b..af3bc359dc70 100644
--- a/arch/parisc/kernel/hardware.c
+++ b/arch/parisc/kernel/hardware.c
@@ -1210,7 +1210,8 @@ static struct hp_hardware hp_hardware_list[] = {
 	{HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"}, 
 	{HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"}, 
 	{HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"}, 
-	{HPHW_FIO, 0x076, 0x000AD, 0x00, "Crestone Peak RS-232"},
+	{HPHW_FIO, 0x076, 0x000AD, 0x0, "Crestone Peak Core RS-232"},
+	{HPHW_FIO, 0x077, 0x000AD, 0x0, "Crestone Peak Fast? Core RS-232"},
 	{HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"}, 
 	{HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"}, 
 	{HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"}, 
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index b7cadc4a06cd..e1ffea2f9a0b 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -45,7 +45,7 @@
 
 static int get_offset(unsigned int last_mmap)
 {
-	return (last_mmap & (SHMLBA-1)) >> PAGE_SHIFT;
+	return (last_mmap & (SHM_COLOUR-1)) >> PAGE_SHIFT;
 }
 
 static unsigned long shared_align_offset(unsigned int last_mmap,
@@ -57,8 +57,8 @@ static unsigned long shared_align_offset(unsigned int last_mmap,
 static inline unsigned long COLOR_ALIGN(unsigned long addr,
 			 unsigned int last_mmap, unsigned long pgoff)
 {
-	unsigned long base = (addr+SHMLBA-1) & ~(SHMLBA-1);
-	unsigned long off  = (SHMLBA-1) &
+	unsigned long base = (addr+SHM_COLOUR-1) & ~(SHM_COLOUR-1);
+	unsigned long off  = (SHM_COLOUR-1) &
 		(shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT);
 
 	return base + off;
@@ -72,10 +72,10 @@ static unsigned long mmap_upper_limit(void)
 {
 	unsigned long stack_base;
 
-	/* Limit stack size to 1GB - see setup_arg_pages() in fs/exec.c */
+	/* Limit stack size - see setup_arg_pages() in fs/exec.c */
 	stack_base = rlimit_max(RLIMIT_STACK);
-	if (stack_base > (1 << 30))
-		stack_base = 1 << 30;
+	if (stack_base > STACK_SIZE_MAX)
+		stack_base = STACK_SIZE_MAX;
 
 	return PAGE_ALIGN(STACK_TOP - stack_base);
 }
@@ -101,7 +101,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (flags & MAP_FIXED) {
 		if ((flags & MAP_SHARED) && last_mmap &&
 		    (addr - shared_align_offset(last_mmap, pgoff))
-				& (SHMLBA - 1))
+				& (SHM_COLOUR - 1))
 			return -EINVAL;
 		goto found_addr;
 	}
@@ -122,7 +122,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.length = len;
 	info.low_limit = mm->mmap_legacy_base;
 	info.high_limit = mmap_upper_limit();
-	info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0;
 	info.align_offset = shared_align_offset(last_mmap, pgoff);
 	addr = vm_unmapped_area(&info);
 
@@ -161,7 +161,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (flags & MAP_FIXED) {
 		if ((flags & MAP_SHARED) && last_mmap &&
 		    (addr - shared_align_offset(last_mmap, pgoff))
-			& (SHMLBA - 1))
+			& (SHM_COLOUR - 1))
 			return -EINVAL;
 		goto found_addr;
 	}
@@ -182,7 +182,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
-	info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0;
 	info.align_offset = shared_align_offset(last_mmap, pgoff);
 	addr = vm_unmapped_area(&info);
 	if (!(addr & ~PAGE_MASK))
diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c
index bb9f3b64de55..ec741fe02ab6 100644
--- a/arch/parisc/kernel/sys_parisc32.c
+++ b/arch/parisc/kernel/sys_parisc32.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2000-2001 Hewlett Packard Company
  * Copyright (C) 2000 John Marvin
  * Copyright (C) 2001 Matthew Wilcox
+ * Copyright (C) 2014 Helge Deller <deller@gmx.de>
  *
  * These routines maintain argument size conversion between 32bit and 64bit
  * environment. Based heavily on sys_ia32.c and sys_sparc32.c.
@@ -57,3 +58,12 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23,
     	current->comm, current->pid, r20);
     return -ENOSYS;
 }
+
+asmlinkage long sys32_fanotify_mark(compat_int_t fanotify_fd, compat_uint_t flags,
+	compat_uint_t mask0, compat_uint_t mask1, compat_int_t dfd,
+	const char  __user * pathname)
+{
+	return sys_fanotify_mark(fanotify_fd, flags,
+			((__u64)mask1 << 32) | mask0,
+			 dfd, pathname);
+}
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index a63bb179f79a..7ef22e3387e0 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -74,7 +74,7 @@ ENTRY(linux_gateway_page)
 	/* ADDRESS 0xb0 to 0xb8, lws uses two insns for entry */
 	/* Light-weight-syscall entry must always be located at 0xb0 */
 	/* WARNING: Keep this number updated with table size changes */
-#define __NR_lws_entries (2)
+#define __NR_lws_entries (3)
 
 lws_entry:
 	gate	lws_start, %r0		/* increase privilege */
@@ -502,7 +502,7 @@ lws_exit:
 
 	
 	/***************************************************
-		Implementing CAS as an atomic operation:
+		Implementing 32bit CAS as an atomic operation:
 
 		%r26 - Address to examine
 		%r25 - Old value to check (old)
@@ -589,10 +589,13 @@ cas_nocontend:
 # endif
 /* ENABLE_LWS_DEBUG */
 
+	rsm	PSW_SM_I, %r0				/* Disable interrupts */
+	/* COW breaks can cause contention on UP systems */
 	LDCW	0(%sr2,%r20), %r28			/* Try to acquire the lock */
 	cmpb,<>,n	%r0, %r28, cas_action		/* Did we get it? */
 cas_wouldblock:
 	ldo	2(%r0), %r28				/* 2nd case */
+	ssm	PSW_SM_I, %r0
 	b	lws_exit				/* Contended... */
 	ldo	-EAGAIN(%r0), %r21			/* Spin in userspace */
 
@@ -619,15 +622,17 @@ cas_action:
 	stw	%r1, 4(%sr2,%r20)
 #endif
 	/* The load and store could fail */
-1:	ldw	0(%sr3,%r26), %r28
+1:	ldw,ma	0(%sr3,%r26), %r28
 	sub,<>	%r28, %r25, %r0
-2:	stw	%r24, 0(%sr3,%r26)
+2:	stw,ma	%r24, 0(%sr3,%r26)
 	/* Free lock */
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
 #endif
+	/* Enable interrupts */
+	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
 	b	lws_exit
 	copy	%r0, %r21
@@ -639,6 +644,7 @@ cas_action:
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
 #endif
+	ssm	PSW_SM_I, %r0
 	b	lws_exit
 	ldo	-EFAULT(%r0),%r21	/* set errno */
 	nop
@@ -653,6 +659,230 @@ cas_action:
 	ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page)
 
 
+	/***************************************************
+		New CAS implementation which uses pointers and variable size
+		information. The value pointed by old and new MUST NOT change
+		while performing CAS. The lock only protect the value at %r26.
+
+		%r26 - Address to examine
+		%r25 - Pointer to the value to check (old)
+		%r24 - Pointer to the value to set (new)
+		%r23 - Size of the variable (0/1/2/3 for 8/16/32/64 bit)
+		%r28 - Return non-zero on failure
+		%r21 - Kernel error code
+
+		%r21 has the following meanings:
+
+		EAGAIN - CAS is busy, ldcw failed, try again.
+		EFAULT - Read or write failed.
+
+		Scratch: r20, r22, r28, r29, r1, fr4 (32bit for 64bit CAS only)
+
+	****************************************************/
+
+	/* ELF32 Process entry path */
+lws_compare_and_swap_2:
+#ifdef CONFIG_64BIT
+	/* Clip the input registers */
+	depdi	0, 31, 32, %r26
+	depdi	0, 31, 32, %r25
+	depdi	0, 31, 32, %r24
+	depdi	0, 31, 32, %r23
+#endif
+
+	/* Check the validity of the size pointer */
+	subi,>>= 4, %r23, %r0
+	b,n	lws_exit_nosys
+
+	/* Jump to the functions which will load the old and new values into
+	   registers depending on the their size */
+	shlw	%r23, 2, %r29
+	blr	%r29, %r0
+	nop
+
+	/* 8bit load */
+4:	ldb	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+5:	ldb	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 16bit load */
+6:	ldh	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+7:	ldh	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 32bit load */
+8:	ldw	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+9:	ldw	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 64bit load */
+#ifdef CONFIG_64BIT
+10:	ldd	0(%sr3,%r25), %r25
+11:	ldd	0(%sr3,%r24), %r24
+#else
+	/* Load new value into r22/r23 - high/low */
+10:	ldw	0(%sr3,%r25), %r22
+11:	ldw	4(%sr3,%r25), %r23
+	/* Load new value into fr4 for atomic store later */
+12:	flddx	0(%sr3,%r24), %fr4
+#endif
+
+cas2_lock_start:
+	/* Load start of lock table */
+	ldil	L%lws_lock_start, %r20
+	ldo	R%lws_lock_start(%r20), %r28
+
+	/* Extract four bits from r26 and hash lock (Bits 4-7) */
+	extru  %r26, 27, 4, %r20
+
+	/* Find lock to use, the hash is either one of 0 to
+	   15, multiplied by 16 (keep it 16-byte aligned)
+	   and add to the lock table offset. */
+	shlw	%r20, 4, %r20
+	add	%r20, %r28, %r20
+
+	rsm	PSW_SM_I, %r0			/* Disable interrupts */
+	/* COW breaks can cause contention on UP systems */
+	LDCW	0(%sr2,%r20), %r28		/* Try to acquire the lock */
+	cmpb,<>,n	%r0, %r28, cas2_action	/* Did we get it? */
+cas2_wouldblock:
+	ldo	2(%r0), %r28			/* 2nd case */
+	ssm	PSW_SM_I, %r0
+	b	lws_exit			/* Contended... */
+	ldo	-EAGAIN(%r0), %r21		/* Spin in userspace */
+
+	/*
+		prev = *addr;
+		if ( prev == old )
+		  *addr = new;
+		return prev;
+	*/
+
+	/* NOTES:
+		This all works becuse intr_do_signal
+		and schedule both check the return iasq
+		and see that we are on the kernel page
+		so this process is never scheduled off
+		or is ever sent any signal of any sort,
+		thus it is wholly atomic from usrspaces
+		perspective
+	*/
+cas2_action:
+	/* Jump to the correct function */
+	blr	%r29, %r0
+	/* Set %r28 as non-zero for now */
+	ldo	1(%r0),%r28
+
+	/* 8bit CAS */
+13:	ldb,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+14:	stb,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 16bit CAS */
+15:	ldh,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+16:	sth,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 32bit CAS */
+17:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+18:	stw,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 64bit CAS */
+#ifdef CONFIG_64BIT
+19:	ldd,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+20:	std,ma	%r24, 0(%sr3,%r26)
+	copy	%r0, %r28
+#else
+	/* Compare first word */
+19:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r22, %r0
+	b,n	cas2_end
+	/* Compare second word */
+20:	ldw,ma	4(%sr3,%r26), %r29
+	sub,=	%r29, %r23, %r0
+	b,n	cas2_end
+	/* Perform the store */
+21:	fstdx	%fr4, 0(%sr3,%r26)
+	copy	%r0, %r28
+#endif
+
+cas2_end:
+	/* Free lock */
+	stw,ma	%r20, 0(%sr2,%r20)
+	/* Enable interrupts */
+	ssm	PSW_SM_I, %r0
+	/* Return to userspace, set no error */
+	b	lws_exit
+	copy	%r0, %r21
+
+22:
+	/* Error occurred on load or store */
+	/* Free lock */
+	stw	%r20, 0(%sr2,%r20)
+	ssm	PSW_SM_I, %r0
+	ldo	1(%r0),%r28
+	b	lws_exit
+	ldo	-EFAULT(%r0),%r21	/* set errno */
+	nop
+	nop
+	nop
+
+	/* Exception table entries, for the load and store, return EFAULT.
+	   Each of the entries must be relocated. */
+	ASM_EXCEPTIONTABLE_ENTRY(4b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(5b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(6b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(7b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(8b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(9b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(10b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(11b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(13b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(14b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(15b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(16b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(17b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(18b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(19b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(20b-linux_gateway_page, 22b-linux_gateway_page)
+#ifndef CONFIG_64BIT
+	ASM_EXCEPTIONTABLE_ENTRY(12b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(21b-linux_gateway_page, 22b-linux_gateway_page)
+#endif
+
 	/* Make sure nothing else is placed on this page */
 	.align PAGE_SIZE
 END(linux_gateway_page)
@@ -669,8 +899,9 @@ ENTRY(end_linux_gateway_page)
 	/* Light-weight-syscall table */
 	/* Start of lws table. */
 ENTRY(lws_table)
-	LWS_ENTRY(compare_and_swap32)	/* 0 - ELF32 Atomic compare and swap */
-	LWS_ENTRY(compare_and_swap64)	/* 1 - ELF64 Atomic compare and swap */
+	LWS_ENTRY(compare_and_swap32)		/* 0 - ELF32 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap64)		/* 1 - ELF64 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap_2)		/* 2 - ELF32 Atomic 64bit CAS */
 END(lws_table)
 	/* End of lws table */
 
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 80e5dd248934..fc77d53e2ca5 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -286,11 +286,11 @@
 	ENTRY_COMP(msgsnd)
 	ENTRY_COMP(msgrcv)
 	ENTRY_SAME(msgget)		/* 190 */
-	ENTRY_SAME(msgctl)
-	ENTRY_SAME(shmat)
+	ENTRY_COMP(msgctl)
+	ENTRY_COMP(shmat)
 	ENTRY_SAME(shmdt)
 	ENTRY_SAME(shmget)
-	ENTRY_SAME(shmctl)		/* 195 */
+	ENTRY_COMP(shmctl)		/* 195 */
 	ENTRY_SAME(ni_syscall)		/* streams1 */
 	ENTRY_SAME(ni_syscall)		/* streams2 */
 	ENTRY_SAME(lstat64)
@@ -323,7 +323,7 @@
 	ENTRY_SAME(epoll_ctl)		/* 225 */
 	ENTRY_SAME(epoll_wait)
  	ENTRY_SAME(remap_file_pages)
-	ENTRY_SAME(semtimedop)
+	ENTRY_COMP(semtimedop)
 	ENTRY_COMP(mq_open)
 	ENTRY_SAME(mq_unlink)		/* 230 */
 	ENTRY_COMP(mq_timedsend)
@@ -392,7 +392,7 @@
 	ENTRY_COMP(vmsplice)
 	ENTRY_COMP(move_pages)		/* 295 */
 	ENTRY_SAME(getcpu)
-	ENTRY_SAME(epoll_pwait)
+	ENTRY_COMP(epoll_pwait)
 	ENTRY_COMP(statfs64)
 	ENTRY_COMP(fstatfs64)
 	ENTRY_COMP(kexec_load)		/* 300 */
@@ -418,7 +418,7 @@
 	ENTRY_SAME(accept4)		/* 320 */
 	ENTRY_SAME(prlimit64)
 	ENTRY_SAME(fanotify_init)
-	ENTRY_COMP(fanotify_mark)
+	ENTRY_DIFF(fanotify_mark)
 	ENTRY_COMP(clock_adjtime)
 	ENTRY_SAME(name_to_handle_at)	/* 325 */
 	ENTRY_COMP(open_by_handle_at)
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 1cd1d0c83b6d..47ee620d15d2 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/console.h>
 #include <linux/bug.h>
+#include <linux/ratelimit.h>
 
 #include <asm/assembly.h>
 #include <asm/uaccess.h>
@@ -42,9 +43,6 @@
 
 #include "../math-emu/math-emu.h"	/* for handle_fpe() */
 
-#define PRINT_USER_FAULTS /* (turn this on if you want user faults to be */
-			  /*  dumped to the console via printk)          */
-
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
 DEFINE_SPINLOCK(pa_dbit_lock);
 #endif
@@ -160,6 +158,17 @@ void show_regs(struct pt_regs *regs)
 	}
 }
 
+static DEFINE_RATELIMIT_STATE(_hppa_rs,
+	DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
+
+#define parisc_printk_ratelimited(critical, regs, fmt, ...)	{	      \
+	if ((critical || show_unhandled_signals) && __ratelimit(&_hppa_rs)) { \
+		printk(fmt, ##__VA_ARGS__);				      \
+		show_regs(regs);					      \
+	}								      \
+}
+
+
 static void do_show_stack(struct unwind_frame_info *info)
 {
 	int i = 1;
@@ -229,12 +238,10 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err)
 		if (err == 0)
 			return; /* STFU */
 
-		printk(KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n",
+		parisc_printk_ratelimited(1, regs,
+			KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n",
 			current->comm, task_pid_nr(current), str, err, regs->iaoq[0]);
-#ifdef PRINT_USER_FAULTS
-		/* XXX for debugging only */
-		show_regs(regs);
-#endif
+
 		return;
 	}
 
@@ -321,14 +328,11 @@ static void handle_break(struct pt_regs *regs)
 			(tt == BUG_TRAP_TYPE_NONE) ? 9 : 0);
 	}
 
-#ifdef PRINT_USER_FAULTS
-	if (unlikely(iir != GDB_BREAK_INSN)) {
-		printk(KERN_DEBUG "break %d,%d: pid=%d command='%s'\n",
+	if (unlikely(iir != GDB_BREAK_INSN))
+		parisc_printk_ratelimited(0, regs,
+			KERN_DEBUG "break %d,%d: pid=%d command='%s'\n",
 			iir & 31, (iir>>13) & ((1<<13)-1),
 			task_pid_nr(current), current->comm);
-		show_regs(regs);
-	}
-#endif
 
 	/* send standard GDB signal */
 	handle_gdb_break(regs, TRAP_BRKPT);
@@ -758,11 +762,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 
 	default:
 		if (user_mode(regs)) {
-#ifdef PRINT_USER_FAULTS
-			printk(KERN_DEBUG "\nhandle_interruption() pid=%d command='%s'\n",
-			    task_pid_nr(current), current->comm);
-			show_regs(regs);
-#endif
+			parisc_printk_ratelimited(0, regs, KERN_DEBUG
+				"handle_interruption() pid=%d command='%s'\n",
+				task_pid_nr(current), current->comm);
 			/* SIGBUS, for lack of a better one. */
 			si.si_signo = SIGBUS;
 			si.si_code = BUS_OBJERR;
@@ -779,16 +781,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 
 	if (user_mode(regs)) {
 	    if ((fault_space >> SPACEID_SHIFT) != (regs->sr[7] >> SPACEID_SHIFT)) {
-#ifdef PRINT_USER_FAULTS
-		if (fault_space == 0)
-			printk(KERN_DEBUG "User Fault on Kernel Space ");
-		else
-			printk(KERN_DEBUG "User Fault (long pointer) (fault %d) ",
-			       code);
-		printk(KERN_CONT "pid=%d command='%s'\n",
-		       task_pid_nr(current), current->comm);
-		show_regs(regs);
-#endif
+		parisc_printk_ratelimited(0, regs, KERN_DEBUG
+				"User fault %d on space 0x%08lx, pid=%d command='%s'\n",
+				code, fault_space,
+				task_pid_nr(current), current->comm);
 		si.si_signo = SIGSEGV;
 		si.si_errno = 0;
 		si.si_code = SEGV_MAPERR;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 9d08c71a967e..d72197f0ddb8 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -19,10 +19,6 @@
 #include <asm/uaccess.h>
 #include <asm/traps.h>
 
-#define PRINT_USER_FAULTS /* (turn this on if you want user faults to be */
-			 /*  dumped to the console via printk)          */
-
-
 /* Various important other fields */
 #define bit22set(x)		(x & 0x00000200)
 #define bits23_25set(x)		(x & 0x000001c0)
@@ -34,6 +30,8 @@
 
 DEFINE_PER_CPU(struct exception_data, exception_data);
 
+int show_unhandled_signals = 1;
+
 /*
  * parisc_acctyp(unsigned int inst) --
  *    Given a PA-RISC memory access instruction, determine if the
@@ -173,6 +171,32 @@ int fixup_exception(struct pt_regs *regs)
 	return 0;
 }
 
+/*
+ * Print out info about fatal segfaults, if the show_unhandled_signals
+ * sysctl is set:
+ */
+static inline void
+show_signal_msg(struct pt_regs *regs, unsigned long code,
+		unsigned long address, struct task_struct *tsk,
+		struct vm_area_struct *vma)
+{
+	if (!unhandled_signal(tsk, SIGSEGV))
+		return;
+
+	if (!printk_ratelimit())
+		return;
+
+	pr_warn("\n");
+	pr_warn("do_page_fault() command='%s' type=%lu address=0x%08lx",
+	    tsk->comm, code, address);
+	print_vma_addr(KERN_CONT " in ", regs->iaoq[0]);
+	if (vma)
+		pr_warn(" vm_start = 0x%08lx, vm_end = 0x%08lx\n",
+				vma->vm_start, vma->vm_end);
+
+	show_regs(regs);
+}
+
 void do_page_fault(struct pt_regs *regs, unsigned long code,
 			      unsigned long address)
 {
@@ -270,16 +294,8 @@ bad_area:
 	if (user_mode(regs)) {
 		struct siginfo si;
 
-#ifdef PRINT_USER_FAULTS
-		printk(KERN_DEBUG "\n");
-		printk(KERN_DEBUG "do_page_fault() pid=%d command='%s' type=%lu address=0x%08lx\n",
-		    task_pid_nr(tsk), tsk->comm, code, address);
-		if (vma) {
-			printk(KERN_DEBUG "vm_start = 0x%08lx, vm_end = 0x%08lx\n",
-					vma->vm_start, vma->vm_end);
-		}
-		show_regs(regs);
-#endif
+		show_signal_msg(regs, code, address, tsk, vma);
+
 		switch (code) {
 		case 15:	/* Data TLB miss fault/Data page fault */
 			/* send SIGSEGV when outside of vma */
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 957bf344c0f5..ee3c6608126a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -141,6 +141,7 @@ config PPC
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
 	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
@@ -410,7 +411,7 @@ config KEXEC
 config CRASH_DUMP
 	bool "Build a kdump crash kernel"
 	depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
-	select RELOCATABLE if PPC64 || 44x || FSL_BOOKE
+	select RELOCATABLE if (PPC64 && !COMPILE_TEST) || 44x || FSL_BOOKE
 	help
 	  Build a kernel suitable for use as a kdump capture kernel.
 	  The same kernel binary can be used as production kernel and dump
@@ -1000,6 +1001,7 @@ endmenu
 if PPC64
 config RELOCATABLE
 	bool "Build a relocatable kernel"
+	depends on !COMPILE_TEST
 	select NONSTATIC_KERNEL
 	help
 	  This builds a kernel image that is capable of running anywhere
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 0f4344e6fbca..8289e2b241a2 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -149,7 +149,9 @@ endif
 
 CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell)
 
-KBUILD_CPPFLAGS	+= -Iarch/$(ARCH)
+asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
+
+KBUILD_CPPFLAGS	+= -Iarch/$(ARCH) $(asinstr)
 KBUILD_AFLAGS	+= -Iarch/$(ARCH)
 KBUILD_CFLAGS	+= -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index a613d2c82fd9..b142b8e0ed9e 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -8,7 +8,11 @@
 #include <linux/sched.h>
 
 #define COMPAT_USER_HZ		100
+#ifdef __BIG_ENDIAN__
 #define COMPAT_UTS_MACHINE	"ppc\0\0"
+#else
+#define COMPAT_UTS_MACHINE	"ppcle\0\0"
+#endif
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1eaea2dea174..7b3907aad2a9 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -53,7 +53,6 @@
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 
-struct kvm;
 extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 extern int kvm_unmap_hva_range(struct kvm *kvm,
 			       unsigned long start, unsigned long end);
@@ -78,10 +77,6 @@ extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 /* Physical Address Mask - allowed range of real mode RAM access */
 #define KVM_PAM			0x0fffffffffffffffULL
 
-struct kvm;
-struct kvm_run;
-struct kvm_vcpu;
-
 struct lppaca;
 struct slb_shadow;
 struct dtl_entry;
@@ -676,4 +671,12 @@ struct kvm_vcpu_arch {
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
 
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_exit(void) {}
+
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index ad3025d0880b..f20786825b8f 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -57,10 +57,10 @@ struct machdep_calls {
 	void            (*hpte_removebolted)(unsigned long ea,
 					     int psize, int ssize);
 	void		(*flush_hash_range)(unsigned long number, int local);
-	void		(*hugepage_invalidate)(struct mm_struct *mm,
+	void		(*hugepage_invalidate)(unsigned long vsid,
+					       unsigned long addr,
 					       unsigned char *hpte_slot_array,
-					       unsigned long addr, int psize);
-
+					       int psize, int ssize);
 	/* special for kexec, to be called in real mode, linear mapping is
 	 * destroyed as well */
 	void		(*hpte_clear_all)(void);
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 3fd2f1b6f906..cefc7b4f4fb1 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -60,8 +60,7 @@ struct power_pmu {
 #define PPMU_SIAR_VALID		0x00000010 /* Processor has SIAR Valid bit */
 #define PPMU_HAS_SSLOT		0x00000020 /* Has sampled slot in MMCRA */
 #define PPMU_HAS_SIER		0x00000040 /* Has SIER */
-#define PPMU_BHRB		0x00000080 /* has BHRB feature enabled */
-#define PPMU_EBB		0x00000100 /* supports event based branch */
+#define PPMU_ARCH_207S		0x00000080 /* PMC is architecture v2.07S */
 
 /*
  * Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index eb9261024f51..7b3d54fae46f 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -413,7 +413,7 @@ static inline char *get_hpte_slot_array(pmd_t *pmdp)
 }
 
 extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
-				   pmd_t *pmdp);
+				   pmd_t *pmdp, unsigned long old_pmd);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);
 extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot);
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 6586a40a46ce..cded7c1278ef 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -318,11 +318,16 @@ n:
 	addi	reg,reg,(name - 0b)@l;
 
 #ifdef __powerpc64__
+#ifdef HAVE_AS_ATHIGH
+#define __AS_ATHIGH high
+#else
+#define __AS_ATHIGH h
+#endif
 #define LOAD_REG_IMMEDIATE(reg,expr)		\
 	lis     reg,(expr)@highest;		\
 	ori     reg,reg,(expr)@higher;	\
 	rldicr  reg,reg,32,31;		\
-	oris    reg,reg,(expr)@h;		\
+	oris    reg,reg,(expr)@__AS_ATHIGH;	\
 	ori     reg,reg,(expr)@l;
 
 #define LOAD_REG_ADDR(reg,name)			\
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index d836d945068d..9ecede1e124c 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -46,11 +46,31 @@
  * in order to deal with 64K made of 4K HW pages. Thus we override the
  * generic accessors and iterators here
  */
-#define __real_pte(e,p) 	((real_pte_t) { \
-			(e), (pte_val(e) & _PAGE_COMBO) ? \
-				(pte_val(*((p) + PTRS_PER_PTE))) : 0 })
-#define __rpte_to_hidx(r,index)	((pte_val((r).pte) & _PAGE_COMBO) ? \
-        (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+{
+	real_pte_t rpte;
+
+	rpte.pte = pte;
+	rpte.hidx = 0;
+	if (pte_val(pte) & _PAGE_COMBO) {
+		/*
+		 * Make sure we order the hidx load against the _PAGE_COMBO
+		 * check. The store side ordering is done in __hash_page_4K
+		 */
+		smp_rmb();
+		rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE));
+	}
+	return rpte;
+}
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	if ((pte_val(rpte.pte) & _PAGE_COMBO))
+		return (rpte.hidx >> (index<<2)) & 0xf;
+	return (pte_val(rpte.pte) >> 12) & 0xf;
+}
+
 #define __rpte_to_pte(r)	((r).pte)
 #define __rpte_sub_valid(rpte, index) \
 	(pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index)))
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 279b80f3bb29..c0c61fa9cd9e 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -47,6 +47,12 @@
 				 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER	12
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STACK_FRAME_MIN_SIZE	32
+#else
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
+#endif
+
 /* Size of dummy stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	128
 #define __SIGNAL_FRAMESIZE32	64
@@ -60,6 +66,7 @@
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x72656773)
 #define STACK_INT_FRAME_SIZE	(sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD)
 #define STACK_FRAME_MARKER	2
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
 
 /* Size of stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	64
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 90c06ec6eff5..ce17815b8b55 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -213,6 +213,7 @@
 #define SPRN_ACOP	0x1F	/* Available Coprocessor Register */
 #define SPRN_TFIAR	0x81	/* Transaction Failure Inst Addr   */
 #define SPRN_TEXASR	0x82	/* Transaction EXception & Summary */
+#define   TEXASR_FS	__MASK(63-36)	/* Transaction Failure Summary */
 #define SPRN_TEXASRU	0x83	/* ''	   ''	   ''	 Upper 32  */
 #define SPRN_TFHAR	0x80	/* Transaction Failure Handler Addr */
 #define SPRN_CTRLF	0x088
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 35aa339410bd..4dbe072eecbe 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -61,6 +61,7 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+	smp_mb();
 	return !arch_spin_value_unlocked(*lock);
 }
 
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 0e83e7d8c73f..b5fad8afe837 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -84,6 +84,8 @@ static inline void clear_task_ebb(struct task_struct *t)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
     /* EBB perf events are not inherited, so clear all EBB state. */
+    t->thread.ebbrr = 0;
+    t->thread.ebbhr = 0;
     t->thread.bescr = 0;
     t->thread.mmcr2 = 0;
     t->thread.mmcr0 = 0;
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 3ddf70276706..0616916b446a 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -190,7 +190,7 @@ SYSCALL_SPU(getcwd)
 SYSCALL_SPU(capget)
 SYSCALL_SPU(capset)
 COMPAT_SYS(sigaltstack)
-COMPAT_SYS_SPU(sendfile)
+SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 PPC_SYS(vfork)
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 5b7657959faa..de2c0e4ee1aa 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -41,5 +41,6 @@
 #define PPC_FEATURE2_EBB		0x10000000
 #define PPC_FEATURE2_ISEL		0x08000000
 #define PPC_FEATURE2_TAR		0x04000000
+#define PPC_FEATURE2_VEC_CRYPTO		0x02000000
 
 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 6c8dd5da4de5..7ac1eab3ff8a 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -109,7 +109,8 @@ extern void __restore_cpu_e6500(void);
 				 PPC_FEATURE_PSERIES_PERFMON_COMPAT)
 #define COMMON_USER2_POWER8	(PPC_FEATURE2_ARCH_2_07 | \
 				 PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
-				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR)
+				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+				 PPC_FEATURE2_VEC_CRYPTO)
 #define COMMON_USER_PA6T	(COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
 				 PPC_FEATURE_TRUE_LE | \
 				 PPC_FEATURE_HAS_ALTIVEC_COMP)
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index 7898be90f2dc..d64e92b22dd8 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -36,7 +36,7 @@ static int __init early_init_dt_scan_epapr(unsigned long node,
 					   int depth, void *data)
 {
 	const u32 *insts;
-	unsigned long len;
+	int len;
 	int i;
 
 	insts = of_get_flat_dt_prop(node, "hcall-instructions", &len);
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 2230fd0ca3e4..7213d930918d 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -55,9 +55,9 @@ int crash_mem_ranges;
 int __init early_init_dt_scan_fw_dump(unsigned long node,
 			const char *uname, int depth, void *data)
 {
-	__be32 *sections;
+	const __be32 *sections;
 	int i, num_sections;
-	unsigned long size;
+	int size;
 	const int *token;
 
 	if (depth != 1 || strcmp(uname, "rtas") != 0)
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 40bd7bd4e19a..8a8b722870a1 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -48,6 +48,9 @@ static struct of_device_id legacy_serial_parents[] __initdata = {
 static unsigned int legacy_serial_count;
 static int legacy_serial_console = -1;
 
+static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
+	UPF_SHARE_IRQ | UPF_FIXED_PORT;
+
 static unsigned int tsi_serial_in(struct uart_port *p, int offset)
 {
 	unsigned int tmp;
@@ -153,8 +156,6 @@ static int __init add_legacy_soc_port(struct device_node *np,
 {
 	u64 addr;
 	const __be32 *addrp;
-	upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ
-		| UPF_FIXED_PORT;
 	struct device_node *tsi = of_get_parent(np);
 
 	/* We only support ports that have a clock frequency properly
@@ -185,9 +186,11 @@ static int __init add_legacy_soc_port(struct device_node *np,
 	 * IO port value. It will be fixed up later along with the irq
 	 */
 	if (tsi && !strcmp(tsi->type, "tsi-bridge"))
-		return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0);
+		return add_legacy_port(np, -1, UPIO_TSI, addr, addr,
+				       NO_IRQ, legacy_port_flags, 0);
 	else
-		return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0);
+		return add_legacy_port(np, -1, UPIO_MEM, addr, addr,
+				       NO_IRQ, legacy_port_flags, 0);
 }
 
 static int __init add_legacy_isa_port(struct device_node *np,
@@ -233,7 +236,7 @@ static int __init add_legacy_isa_port(struct device_node *np,
 
 	/* Add port, irq will be dealt with later */
 	return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]),
-			       taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0);
+			       taddr, NO_IRQ, legacy_port_flags, 0);
 
 }
 
@@ -306,7 +309,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
 	 * IO port value. It will be fixed up later along with the irq
 	 */
 	return add_legacy_port(np, index, iotype, base, addr, NO_IRQ,
-			       UPF_BOOT_AUTOCONF, np != pci_dev);
+			       legacy_port_flags, np != pci_dev);
 }
 #endif
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 59d229a2a3e0..879b3aacac32 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -237,7 +237,7 @@ static void wake_offline_cpus(void)
 		if (!cpu_online(cpu)) {
 			printk(KERN_INFO "kexec: Waking offline cpu %d.\n",
 			       cpu);
-			cpu_up(cpu);
+			WARN_ON(cpu_up(cpu));
 		}
 	}
 }
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 27c93f41166f..fc0927a162ff 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -78,7 +78,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
@@ -109,7 +109,7 @@ static long mce_handle_common_ierror(uint64_t srr1)
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
 			handled = 1;
 		}
 		break;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index af064d28b365..31d021506d21 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -610,6 +610,31 @@ out_and_saveregs:
 	tm_save_sprs(thr);
 }
 
+extern void __tm_recheckpoint(struct thread_struct *thread,
+			      unsigned long orig_msr);
+
+void tm_recheckpoint(struct thread_struct *thread,
+		     unsigned long orig_msr)
+{
+	unsigned long flags;
+
+	/* We really can't be interrupted here as the TEXASR registers can't
+	 * change and later in the trecheckpoint code, we have a userspace R1.
+	 * So let's hard disable over this region.
+	 */
+	local_irq_save(flags);
+	hard_irq_disable();
+
+	/* The TM SPRs are restored here, so that TEXASR.FS can be set
+	 * before the trecheckpoint and no explosion occurs.
+	 */
+	tm_restore_sprs(thread);
+
+	__tm_recheckpoint(thread, orig_msr);
+
+	local_irq_restore(flags);
+}
+
 static inline void tm_recheckpoint_new_task(struct task_struct *new)
 {
 	unsigned long msr;
@@ -628,13 +653,10 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
 	if (!new->thread.regs)
 		return;
 
-	/* The TM SPRs are restored here, so that TEXASR.FS can be set
-	 * before the trecheckpoint and no explosion occurs.
-	 */
-	tm_restore_sprs(&new->thread);
-
-	if (!MSR_TM_ACTIVE(new->thread.regs->msr))
+	if (!MSR_TM_ACTIVE(new->thread.regs->msr)){
+		tm_restore_sprs(&new->thread);
 		return;
+	}
 	msr = new->thread.tm_orig_msr;
 	/* Recheckpoint to restore original checkpointed register state. */
 	TM_DEBUG("*** tm_recheckpoint of pid %d "
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f58c0d3aaeb4..8dd5a093195b 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -162,7 +162,7 @@ static struct ibm_pa_feature {
 	{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
 };
 
-static void __init scan_features(unsigned long node, unsigned char *ftrs,
+static void __init scan_features(unsigned long node, const unsigned char *ftrs,
 				 unsigned long tablelen,
 				 struct ibm_pa_feature *fp,
 				 unsigned long ft_size)
@@ -201,8 +201,8 @@ static void __init scan_features(unsigned long node, unsigned char *ftrs,
 
 static void __init check_cpu_pa_features(unsigned long node)
 {
-	unsigned char *pa_ftrs;
-	unsigned long tablelen;
+	const unsigned char *pa_ftrs;
+	int tablelen;
 
 	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
 	if (pa_ftrs == NULL)
@@ -215,7 +215,7 @@ static void __init check_cpu_pa_features(unsigned long node)
 #ifdef CONFIG_PPC_STD_MMU_64
 static void __init check_cpu_slb_size(unsigned long node)
 {
-	__be32 *slb_size_ptr;
+	const __be32 *slb_size_ptr;
 
 	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
 	if (slb_size_ptr != NULL) {
@@ -256,7 +256,7 @@ static struct feature_property {
 static inline void identical_pvr_fixup(unsigned long node)
 {
 	unsigned int pvr;
-	char *model = of_get_flat_dt_prop(node, "model", NULL);
+	const char *model = of_get_flat_dt_prop(node, "model", NULL);
 
 	/*
 	 * Since 440GR(x)/440EP(x) processors have the same pvr,
@@ -294,11 +294,11 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
 	const __be32 *prop;
 	const __be32 *intserv;
 	int i, nthreads;
-	unsigned long len;
+	int len;
 	int found = -1;
 	int found_thread = 0;
 
@@ -391,7 +391,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
 					 int depth, void *data)
 {
-	unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
+	const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
 
 	/* Use common scan routine to determine if this is the chosen node */
 	if (early_init_dt_scan_chosen(node, uname, depth, data) == 0)
@@ -442,8 +442,9 @@ int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
  */
 static int __init early_init_dt_scan_drconf_memory(unsigned long node)
 {
-	__be32 *dm, *ls, *usm;
-	unsigned long l, n, flags;
+	const __be32 *dm, *ls, *usm;
+	int l;
+	unsigned long n, flags;
 	u64 base, size, memblock_size;
 	unsigned int is_kexec_kdump = 0, rngs;
 
@@ -563,7 +564,8 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 
 static void __init early_reserve_mem_dt(void)
 {
-	unsigned long i, len, dt_root;
+	unsigned long i, dt_root;
+	int len;
 	const __be32 *prop;
 
 	dt_root = of_get_flat_dt_root();
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 4cf674d7d5ae..8c923bac430f 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1135,7 +1135,7 @@ void __init rtas_initialize(void)
 int __init early_init_dt_scan_rtas(unsigned long node,
 		const char *uname, int depth, void *data)
 {
-	u32 *basep, *entryp, *sizep;
+	const u32 *basep, *entryp, *sizep;
 
 	if (depth != 1 || strcmp(uname, "rtas") != 0)
 		return 0;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index bc76cc6b419c..04aa4d3c7c05 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -456,9 +456,17 @@ void __init smp_setup_cpu_maps(void)
 		}
 
 		for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
+			bool avail;
+
 			DBG("    thread %d -> cpu %d (hard id %d)\n",
 			    j, cpu, be32_to_cpu(intserv[j]));
-			set_cpu_present(cpu, true);
+
+			avail = of_device_is_available(dn);
+			if (!avail)
+				avail = !of_property_match_string(dn,
+						"enable-method", "spin-table");
+
+			set_cpu_present(cpu, avail);
 			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
 			cpu++;
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index a67e00aa3caa..4e47db686b5d 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -881,6 +881,8 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	 * transactional versions should be loaded.
 	 */
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 	/* Get the top half of the MSR */
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 8d253c29649b..d501dc4dc3e6 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -527,6 +527,8 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 	}
 #endif
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index b3dab20acf34..f8b994abb57f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -511,7 +511,7 @@ void timer_interrupt(struct pt_regs * regs)
 	may_hard_irq_enable();
 
 
-#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
 #endif
@@ -805,9 +805,6 @@ static void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	/* Don't adjust the decrementer if some irq work is pending */
-	if (test_irq_work_pending())
-		return 0;
 	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
 	set_dec(evt);
 
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index ef47bcbd4352..03567c05950a 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -307,7 +307,7 @@ dont_backup_fp:
 	 *	Call with IRQs off, stacks get all out of sync for
 	 *	some periods in here!
 	 */
-_GLOBAL(tm_recheckpoint)
+_GLOBAL(__tm_recheckpoint)
 	mfcr	r5
 	mflr	r0
 	stw	r5, 8(r1)
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 75702e207b29..f7089fcfaa5d 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -69,8 +69,12 @@ static void udbg_uart_putc(char c)
 
 static int udbg_uart_getc_poll(void)
 {
-	if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR))
+	if (!udbg_uart_in)
+		return -1;
+
+	if (!(udbg_uart_in(UART_LSR) & LSR_DR))
 		return udbg_uart_in(UART_RBR);
+
 	return -1;
 }
 
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
index 47afd08c90f7..fe7e97a1aad9 100644
--- a/arch/powerpc/kernel/vdso32/getcpu.S
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -30,8 +30,8 @@
 V_FUNCTION_BEGIN(__kernel_getcpu)
   .cfi_startproc
 	mfspr	r5,SPRN_USPRG3
-	cmpdi	cr0,r3,0
-	cmpdi	cr1,r4,0
+	cmpwi	cr0,r3,0
+	cmpwi	cr1,r4,0
 	clrlwi  r6,r5,16
 	rlwinm  r7,r5,16,31-15,31-0
 	beq	cr0,1f
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 141b2027189a..ab7881c83da6 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -173,6 +173,7 @@ config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && E500
 	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	help
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 17fc9496b6ac..7a25d9218a05 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -86,7 +86,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	/* CPU points to the first thread of the core */
 	if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
-#ifdef CONFIG_KVM_XICS
+#ifdef CONFIG_PPC_ICP_NATIVE
 		int real_cpu = cpu + vcpu->arch.ptid;
 		if (paca[real_cpu].kvm_hstate.xics_phys)
 			xics_wake_cpu(real_cpu);
@@ -1360,9 +1360,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (cpu != smp_processor_id()) {
-#ifdef CONFIG_KVM_XICS
 		xics_wake_cpu(cpu);
-#endif
 		if (vcpu->arch.ptid)
 			++vc->n_woken;
 	}
diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c
index efbd9962a209..bb164860f832 100644
--- a/arch/powerpc/kvm/mpic.c
+++ b/arch/powerpc/kvm/mpic.c
@@ -1823,8 +1823,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return 0;
 }
 
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
-			  struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
 	int r = -EINVAL;
@@ -1836,7 +1835,6 @@ int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
 		e->irqchip.pin = ue->u.irqchip.pin;
 		if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS)
 			goto out;
-		rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
 		break;
 	case KVM_IRQ_ROUTING_MSI:
 		e->set = kvm_set_msi;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3cf541a53e2a..2b009227b93b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -243,24 +243,16 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvmppc_emulate_mmio);
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
 int kvm_arch_hardware_setup(void)
 {
 	return 0;
 }
 
-void kvm_arch_hardware_unsetup(void)
-{
-}
-
 void kvm_arch_check_processor_compat(void *rtn)
 {
 	*(int *)rtn = kvmppc_core_check_processor_compat();
@@ -321,11 +313,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	module_put(kvm->arch.kvm_ops->owner);
 }
 
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
-
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r;
 	/* FIXME!!
@@ -458,10 +446,6 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 	return kvmppc_core_create_memslot(kvm, slot, npages);
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
-{
-}
-
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
 				   struct kvm_userspace_memory_region *mem,
@@ -478,10 +462,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	kvmppc_core_commit_memory_region(kvm, mem, old);
 }
 
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
@@ -1157,8 +1137,3 @@ int kvm_arch_init(void *opaque)
 {
 	return 0;
 }
-
-void kvm_arch_exit(void)
-{
-
-}
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 0c9c8d7d0734..170a0346f756 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -70,12 +70,16 @@ void __rw_yield(arch_rwlock_t *rw)
 
 void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
+	smp_mb();
+
 	while (lock->slock) {
 		HMT_low();
 		if (SHARED_PROCESSOR)
 			__spin_yield(lock);
 	}
 	HMT_medium();
+
+	smp_mb();
 }
 
 EXPORT_SYMBOL(arch_spin_unlock_wait);
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index c0511c27a733..412dd46dd0b7 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1470,7 +1470,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				regs->gpr[rd] = byterev_4(val);
 			goto ldst_done;
 
-#ifdef CONFIG_PPC_CPU
+#ifdef CONFIG_PPC_FPU
 		case 535:	/* lfsx */
 		case 567:	/* lfsux */
 			if (!(regs->msr & MSR_FP))
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3ea26c25590b..838de8e17dc5 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -418,18 +418,18 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	local_irq_restore(flags);
 }
 
-static void native_hugepage_invalidate(struct mm_struct *mm,
+static void native_hugepage_invalidate(unsigned long vsid,
+				       unsigned long addr,
 				       unsigned char *hpte_slot_array,
-				       unsigned long addr, int psize)
+				       int psize, int ssize)
 {
-	int ssize = 0, i;
-	int lock_tlbie;
+	int i;
 	struct hash_pte *hptep;
 	int actual_psize = MMU_PAGE_16M;
 	unsigned int max_hpte_count, valid;
 	unsigned long flags, s_addr = addr;
 	unsigned long hpte_v, want_v, shift;
-	unsigned long hidx, vpn = 0, vsid, hash, slot;
+	unsigned long hidx, vpn = 0, hash, slot;
 
 	shift = mmu_psize_defs[psize].shift;
 	max_hpte_count = 1U << (PMD_SHIFT - shift);
@@ -443,15 +443,6 @@ static void native_hugepage_invalidate(struct mm_struct *mm,
 
 		/* get the vpn */
 		addr = s_addr + (i * (1ul << shift));
-		if (!is_kernel_addr(addr)) {
-			ssize = user_segment_size(addr);
-			vsid = get_vsid(mm->context.id, addr, ssize);
-			WARN_ON(vsid == 0);
-		} else {
-			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
-			ssize = mmu_kernel_ssize;
-		}
-
 		vpn = hpt_vpn(addr, vsid, ssize);
 		hash = hpt_hash(vpn, shift, ssize);
 		if (hidx & _PTEIDX_SECONDARY)
@@ -471,22 +462,13 @@ static void native_hugepage_invalidate(struct mm_struct *mm,
 		else
 			/* Invalidate the hpte. NOTE: this also unlocks it */
 			hptep->v = 0;
+		/*
+		 * We need to do tlb invalidate for all the address, tlbie
+		 * instruction compares entry_VA in tlb with the VA specified
+		 * here
+		 */
+		tlbie(vpn, psize, actual_psize, ssize, 0);
 	}
-	/*
-	 * Since this is a hugepage, we just need a single tlbie.
-	 * use the last vpn.
-	 */
-	lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
-	if (lock_tlbie)
-		raw_spin_lock(&native_tlbie_lock);
-
-	asm volatile("ptesync":::"memory");
-	__tlbie(vpn, psize, actual_psize, ssize);
-	asm volatile("eieio; tlbsync; ptesync":::"memory");
-
-	if (lock_tlbie)
-		raw_spin_unlock(&native_tlbie_lock);
-
 	local_irq_restore(flags);
 }
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d766d6ee33fe..ff27d169fa80 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -265,9 +265,9 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 					 const char *uname, int depth,
 					 void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *prop;
-	unsigned long size = 0;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int size = 0;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -320,9 +320,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *prop;
-	unsigned long size = 0;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int size = 0;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -402,9 +402,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 					const char *uname, int depth,
 					void *data) {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be64 *addr_prop;
-	__be32 *page_count_prop;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be64 *addr_prop;
+	const __be32 *page_count_prop;
 	unsigned int expected_pages;
 	long unsigned int phys_addr;
 	long unsigned int block_size;
@@ -546,8 +546,8 @@ static int __init htab_dt_scan_pftsize(unsigned long node,
 				       const char *uname, int depth,
 				       void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *prop;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -960,6 +960,22 @@ void hash_failure_debug(unsigned long ea, unsigned long access,
 		trap, vsid, ssize, psize, lpsize, pte);
 }
 
+static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
+			     int psize, bool user_region)
+{
+	if (user_region) {
+		if (psize != get_paca_psize(ea)) {
+			get_paca()->context = mm->context;
+			slb_flush_and_rebolt();
+		}
+	} else if (get_paca()->vmalloc_sllp !=
+		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
+		get_paca()->vmalloc_sllp =
+			mmu_psize_defs[mmu_vmalloc_psize].sllp;
+		slb_vmalloc_update();
+	}
+}
+
 /* Result code is:
  *  0 - handled
  *  1 - normal page fault
@@ -1081,6 +1097,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			WARN_ON(1);
 		}
 #endif
+		check_paca_psize(ea, mm, psize, user_region);
+
 		goto bail;
 	}
 
@@ -1121,17 +1139,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 #endif
 		}
 	}
-	if (user_region) {
-		if (psize != get_paca_psize(ea)) {
-			get_paca()->context = mm->context;
-			slb_flush_and_rebolt();
-		}
-	} else if (get_paca()->vmalloc_sllp !=
-		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
-		get_paca()->vmalloc_sllp =
-			mmu_psize_defs[mmu_vmalloc_psize].sllp;
-		slb_vmalloc_update();
-	}
+
+	check_paca_psize(ea, mm, psize, user_region);
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 826893fcb3a7..5f5e6328c21c 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -18,6 +18,57 @@
 #include <linux/mm.h>
 #include <asm/machdep.h>
 
+static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
+				pmd_t *pmdp, unsigned int psize, int ssize)
+{
+	int i, max_hpte_count, valid;
+	unsigned long s_addr;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, shift, vpn, hash, slot;
+
+	s_addr = addr & HPAGE_PMD_MASK;
+	hpte_slot_array = get_hpte_slot_array(pmdp);
+	/*
+	 * IF we try to do a HUGE PTE update after a withdraw is done.
+	 * we will find the below NULL. This happens when we do
+	 * split_huge_page_pmd
+	 */
+	if (!hpte_slot_array)
+		return;
+
+	if (ppc_md.hugepage_invalidate)
+		return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+						  psize, ssize);
+	/*
+	 * No bluk hpte removal support, invalidate each entry
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = HPAGE_PMD_SIZE >> shift;
+	for (i = 0; i < max_hpte_count; i++) {
+		/*
+		 * 8 bits per each hpte entries
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+		ppc_md.hpte_invalidate(slot, vpn, psize,
+				       MMU_PAGE_16M, ssize, 0);
+	}
+}
+
+
 int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		    pmd_t *pmdp, unsigned long trap, int local, int ssize,
 		    unsigned int psize)
@@ -33,7 +84,9 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * atomically mark the linux large page PMD busy and dirty
 	 */
 	do {
-		old_pmd = pmd_val(*pmdp);
+		pmd_t pmd = ACCESS_ONCE(*pmdp);
+
+		old_pmd = pmd_val(pmd);
 		/* If PMD busy, retry the access */
 		if (unlikely(old_pmd & _PAGE_BUSY))
 			return 0;
@@ -85,6 +138,15 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	vpn = hpt_vpn(ea, vsid, ssize);
 	hash = hpt_hash(vpn, shift, ssize);
 	hpte_slot_array = get_hpte_slot_array(pmdp);
+	if (psize == MMU_PAGE_4K) {
+		/*
+		 * invalidate the old hpte entry if we have that mapped via 64K
+		 * base page size. This is because demote_segment won't flush
+		 * hash page table entries.
+		 */
+		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+			invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize);
+	}
 
 	valid = hpte_valid(hpte_slot_array, index);
 	if (valid) {
@@ -107,11 +169,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 			 * safely update this here.
 			 */
 			valid = 0;
-			new_pmd &= ~_PAGE_HPTEFLAGS;
 			hpte_slot_array[index] = 0;
-		} else
-			/* clear the busy bits and set the hash pte bits */
-			new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+		}
 	}
 
 	if (!valid) {
@@ -119,11 +178,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 
 		/* insert new entry */
 		pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
-repeat:
-		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-
-		/* clear the busy bits and set the hash pte bits */
-		new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+		new_pmd |= _PAGE_HASHPTE;
 
 		/* Add in WIMG bits */
 		rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
@@ -132,6 +187,8 @@ repeat:
 		 * enable the memory coherence always
 		 */
 		rflags |= HPTE_R_M;
+repeat:
+		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 
 		/* Insert into the hash table, primary slot */
 		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
@@ -172,8 +229,17 @@ repeat:
 		mark_hpte_slot_valid(hpte_slot_array, index, slot);
 	}
 	/*
-	 * No need to use ldarx/stdcx here
+	 * Mark the pte with _PAGE_COMBO, if we are trying to hash it with
+	 * base page size 4k.
+	 */
+	if (psize == MMU_PAGE_4K)
+		new_pmd |= _PAGE_COMBO;
+	/*
+	 * The hpte valid is stored in the pgtable whose address is in the
+	 * second half of the PMD. Order this against clearing of the busy bit in
+	 * huge pmd.
 	 */
+	smp_wmb();
 	*pmdp = __pmd(new_pmd & ~_PAGE_BUSY);
 	return 0;
 }
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index eb923654ba80..7e70ae968e5f 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd)
 	 */
 	return ((pgd_val(pgd) & 0x3) != 0x0);
 }
-
-int pmd_huge_support(void)
-{
-	return 1;
-}
 #else
 int pmd_huge(pmd_t pmd)
 {
@@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd)
 {
 	return 0;
 }
-
-int pmd_huge_support(void)
-{
-	return 0;
-}
 #endif
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 30a42e24bf14..a5fff173be4f 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -610,8 +610,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 		unmap_cpu_from_node(lcpu);
-		break;
 		ret = NOTIFY_OK;
+		break;
 #endif
 	}
 	return ret;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 62bf5e8e78da..c64da56d7582 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -538,7 +538,7 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 	*pmdp = __pmd((old & ~clr) | set);
 #endif
 	if (old & _PAGE_HASHPTE)
-		hpte_do_hugepage_flush(mm, addr, pmdp);
+		hpte_do_hugepage_flush(mm, addr, pmdp, old);
 	return old;
 }
 
@@ -645,7 +645,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma,
 	if (!(old & _PAGE_SPLITTING)) {
 		/* We need to flush the hpte */
 		if (old & _PAGE_HASHPTE)
-			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
+			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old);
 	}
 }
 
@@ -718,7 +718,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
  * neesd to be flushed.
  */
 void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
-			    pmd_t *pmdp)
+			    pmd_t *pmdp, unsigned long old_pmd)
 {
 	int ssize, i;
 	unsigned long s_addr;
@@ -740,12 +740,29 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 	if (!hpte_slot_array)
 		return;
 
-	/* get the base page size */
+	/* get the base page size,vsid and segment size */
+#ifdef CONFIG_DEBUG_VM
 	psize = get_slice_psize(mm, s_addr);
+	BUG_ON(psize == MMU_PAGE_16M);
+#endif
+	if (old_pmd & _PAGE_COMBO)
+		psize = MMU_PAGE_4K;
+	else
+		psize = MMU_PAGE_64K;
+
+	if (!is_kernel_addr(s_addr)) {
+		ssize = user_segment_size(s_addr);
+		vsid = get_vsid(mm->context.id, s_addr, ssize);
+		WARN_ON(vsid == 0);
+	} else {
+		vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize);
+		ssize = mmu_kernel_ssize;
+	}
 
 	if (ppc_md.hugepage_invalidate)
-		return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
-						  s_addr, psize);
+		return ppc_md.hugepage_invalidate(vsid, s_addr,
+						  hpte_slot_array,
+						  psize, ssize);
 	/*
 	 * No bluk hpte removal support, invalidate each entry
 	 */
@@ -763,15 +780,6 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 
 		/* get the vpn */
 		addr = s_addr + (i * (1ul << shift));
-		if (!is_kernel_addr(addr)) {
-			ssize = user_segment_size(addr);
-			vsid = get_vsid(mm->context.id, addr, ssize);
-			WARN_ON(vsid == 0);
-		} else {
-			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
-			ssize = mmu_kernel_ssize;
-		}
-
 		vpn = hpt_vpn(addr, vsid, ssize);
 		hash = hpt_hash(vpn, shift, ssize);
 		if (hidx & _PTEIDX_SECONDARY)
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index c99f6510a0b2..9adda5790463 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -216,7 +216,7 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 		if (!(pte & _PAGE_HASHPTE))
 			continue;
 		if (unlikely(hugepage_shift && pmd_trans_huge(*(pmd_t *)pte)))
-			hpte_do_hugepage_flush(mm, start, (pmd_t *)pte);
+			hpte_do_hugepage_flush(mm, start, (pmd_t *)ptep, pte);
 		else
 			hpte_need_flush(mm, start, ptep, pte, 0);
 	}
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e780748b..2396dda282cd 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -35,7 +35,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 		return 0;		/* must be 16-byte aligned */
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return 0;
-	if (sp >= prev_sp + STACK_FRAME_OVERHEAD)
+	if (sp >= prev_sp + STACK_FRAME_MIN_SIZE)
 		return 1;
 	/*
 	 * sp could decrease when we jump off an interrupt stack
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 67cf22083f4c..38265dc85318 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -483,7 +483,7 @@ static bool is_ebb_event(struct perf_event *event)
 	 * check that the PMU supports EBB, meaning those that don't can still
 	 * use bit 63 of the event code for something else if they wish.
 	 */
-	return (ppmu->flags & PPMU_EBB) &&
+	return (ppmu->flags & PPMU_ARCH_207S) &&
 	       ((event->attr.config >> PERF_EVENT_CONFIG_EBB_SHIFT) & 1);
 }
 
@@ -851,7 +851,22 @@ static void power_pmu_read(struct perf_event *event)
 	} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
 
 	local64_add(delta, &event->count);
-	local64_sub(delta, &event->hw.period_left);
+
+	/*
+	 * A number of places program the PMC with (0x80000000 - period_left).
+	 * We never want period_left to be less than 1 because we will program
+	 * the PMC with a value >= 0x800000000 and an edge detected PMC will
+	 * roll around to 0 before taking an exception. We have seen this
+	 * on POWER8.
+	 *
+	 * To fix this, clamp the minimum value of period_left to 1.
+	 */
+	do {
+		prev = local64_read(&event->hw.period_left);
+		val = prev - delta;
+		if (val < 1)
+			val = 1;
+	} while (local64_cmpxchg(&event->hw.period_left, prev, val) != prev);
 }
 
 /*
@@ -1152,6 +1167,9 @@ static void power_pmu_enable(struct pmu *pmu)
 
 	write_mmcr0(cpuhw, mmcr0);
 
+	if (ppmu->flags & PPMU_ARCH_207S)
+		mtspr(SPRN_MMCR2, 0);
+
 	/*
 	 * Enable instruction sampling if necessary
 	 */
@@ -1548,7 +1566,7 @@ static int power_pmu_event_init(struct perf_event *event)
 
 	if (has_branch_stack(event)) {
 	        /* PMU has BHRB enabled */
-		if (!(ppmu->flags & PPMU_BHRB))
+		if (!(ppmu->flags & PPMU_ARCH_207S))
 			return -EOPNOTSUPP;
 	}
 
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 96cee20dcd34..4a06530cbb71 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -751,7 +751,7 @@ static struct power_pmu power8_pmu = {
 	.get_constraint		= power8_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
 	.disable_pmc		= power8_disable_pmc,
-	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
+	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
 	.cache_events		= &power8_cache_events,
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 18c104820198..6e19b0ad5d26 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -199,8 +199,8 @@ static void __init efika_setup_arch(void)
 
 static int __init efika_probe(void)
 {
-	char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
-					  "model", NULL);
+	const char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
+						"model", NULL);
 
 	if (model == NULL)
 		return 0;
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index c665d7de6c99..7044fd36197b 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -574,8 +574,8 @@ chrp_init2(void)
 
 static int __init chrp_probe(void)
 {
- 	char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
- 					  "device_type", NULL);
+	const char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
+						"device_type", NULL);
  	if (dtype == NULL)
  		return 0;
  	if (strcmp(dtype, "chrp"))
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 253fefe3d1a0..5b51079f3e3b 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -549,7 +549,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
 		bus = eeh_pe_bus_get(pe);
-		if (pci_is_root_bus(bus))
+		if (pci_is_root_bus(bus) ||
+		    pci_is_root_bus(bus->parent))
 			ret = ioda_eeh_root_reset(hose, option);
 		else
 			ret = ioda_eeh_bridge_reset(hose, bus->self, option);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 65499adaecff..3bf1eb433112 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -50,7 +50,7 @@ int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
 {
 	const void *basep, *entryp;
-	unsigned long basesz, entrysz;
+	int basesz, entrysz, runtimesz;
 
 	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
 		return 0;
@@ -64,10 +64,10 @@ int __init early_init_dt_scan_opal(unsigned long node,
 	opal.base = of_read_number(basep, basesz/4);
 	opal.entry = of_read_number(entryp, entrysz/4);
 
-	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%ld)\n",
+	pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%d)\n",
 		 opal.base, basep, basesz);
-	pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n",
-		 opal.entry, entryp, entrysz);
+	pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n",
+		 opal.size, sizep, runtimesz);
 
 	powerpc_firmware_features |= FW_FEATURE_OPAL;
 	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
@@ -84,6 +84,68 @@ int __init early_init_dt_scan_opal(unsigned long node,
 	return 1;
 }
 
+<<<<<<< HEAD
+=======
+int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
+				   const char *uname, int depth, void *data)
+{
+	int i, psize, size;
+	const __be32 *prop;
+
+	if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
+		return 0;
+
+	prop = of_get_flat_dt_prop(node, "mcheck-recoverable-ranges", &psize);
+
+	if (!prop)
+		return 1;
+
+	pr_debug("Found machine check recoverable ranges.\n");
+
+	/*
+	 * Calculate number of available entries.
+	 *
+	 * Each recoverable address range entry is (start address, len,
+	 * recovery address), 2 cells each for start and recovery address,
+	 * 1 cell for len, totalling 5 cells per entry.
+	 */
+	mc_recoverable_range_len = psize / (sizeof(*prop) * 5);
+
+	/* Sanity check */
+	if (!mc_recoverable_range_len)
+		return 1;
+
+	/* Size required to hold all the entries. */
+	size = mc_recoverable_range_len *
+			sizeof(struct mcheck_recoverable_range);
+
+	/*
+	 * Allocate a buffer to hold the MC recoverable ranges. We would be
+	 * accessing them in real mode, hence it needs to be within
+	 * RMO region.
+	 */
+	mc_recoverable_range =__va(memblock_alloc_base(size, __alignof__(u64),
+							ppc64_rma_size));
+	memset(mc_recoverable_range, 0, size);
+
+	for (i = 0; i < mc_recoverable_range_len; i++) {
+		mc_recoverable_range[i].start_addr =
+					of_read_number(prop + (i * 5) + 0, 2);
+		mc_recoverable_range[i].end_addr =
+					mc_recoverable_range[i].start_addr +
+					of_read_number(prop + (i * 5) + 2, 1);
+		mc_recoverable_range[i].recover_addr =
+					of_read_number(prop + (i * 5) + 3, 2);
+
+		pr_debug("Machine check recoverable range: %llx..%llx: %llx\n",
+				mc_recoverable_range[i].start_addr,
+				mc_recoverable_range[i].end_addr,
+				mc_recoverable_range[i].recover_addr);
+	}
+	return 1;
+}
+
+>>>>>>> 9d0c4dfedd96... of/fdt: update of_get_flat_dt_prop in prep for libfdt
 static int __init opal_register_exception_handlers(void)
 {
 #ifdef __BIG_ENDIAN__
@@ -269,7 +331,7 @@ int opal_get_chars(uint32_t vtermno, char *buf, int count)
 	if ((be64_to_cpu(evt) & OPAL_EVENT_CONSOLE_INPUT) == 0)
 		return 0;
 	len = cpu_to_be64(count);
-	rc = opal_console_read(vtermno, &len, buf);	
+	rc = opal_console_read(vtermno, &len, buf);
 	if (rc == OPAL_SUCCESS)
 		return be64_to_cpu(len);
 	return 0;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3b2b4fb3585b..d558b8595e6f 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -491,6 +491,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
 		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
 	}
+	*pdev->dev.dma_mask = dma_mask;
 	return 0;
 }
 
@@ -901,7 +902,6 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				  unsigned int is_64, struct msi_msg *msg)
 {
 	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
-	struct pci_dn *pdn = pci_get_pdn(dev);
 	struct irq_data *idata;
 	struct irq_chip *ichip;
 	unsigned int xive_num = hwirq - phb->msi_base;
@@ -917,7 +917,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 		return -ENXIO;
 
 	/* Force 32-bit MSI on some broken devices */
-	if (pdn && pdn->force_32bit_msi)
+	if (dev->no_64bit_msi)
 		is_64 = 0;
 
 	/* Assign XIVE to PE */
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 8518817dcdfd..52c1162bcee3 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -1,3 +1,4 @@
+
 /*
  * Support PCI/PCIe on PowerNV platforms
  *
@@ -50,9 +51,8 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
 
-	if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
+	if (pdev->no_64bit_msi && !phb->msi32_support)
 		return -ENODEV;
 
 	return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a8fe5aa3d34f..3b46eed1dcf6 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -380,7 +380,7 @@ static int dlpar_online_cpu(struct device_node *dn)
 			BUG_ON(get_cpu_current_state(cpu)
 					!= CPU_STATE_OFFLINE);
 			cpu_maps_update_done();
-			rc = cpu_up(cpu);
+			rc = device_online(get_cpu_device(cpu));
 			if (rc)
 				goto out;
 			cpu_maps_update_begin();
@@ -463,7 +463,7 @@ static int dlpar_offline_cpu(struct device_node *dn)
 			if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
 				set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
 				cpu_maps_update_done();
-				rc = cpu_down(cpu);
+				rc = device_offline(get_cpu_device(cpu));
 				if (rc)
 					goto out;
 				cpu_maps_update_begin();
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 8a8f0472d98f..83da53fde6b5 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -464,6 +464,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state)
 			} else {
 				result = EEH_STATE_NOT_SUPPORT;
 			}
+			break;
 		default:
 			result = EEH_STATE_NOT_SUPPORT;
 		}
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 0ea99e3d4815..2d6fe89ff89d 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -88,13 +88,14 @@ void set_default_offline_state(int cpu)
 
 static void rtas_stop_self(void)
 {
-	struct rtas_args args = {
-		.token = cpu_to_be32(rtas_stop_self_token),
+	static struct rtas_args args = {
 		.nargs = 0,
 		.nret = 1,
 		.rets = &args.args[0],
 	};
 
+	args.token = cpu_to_be32(rtas_stop_self_token);
+
 	local_irq_disable();
 
 	BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9590dbb756f2..b9a82042760f 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -160,7 +160,7 @@ static int pseries_remove_memory(struct device_node *np)
 static inline int pseries_remove_memblock(unsigned long base,
 					  unsigned int memblock_size)
 {
-	return -EOPNOTSUPP;
+	return 0;
 }
 static inline int pseries_remove_memory(struct device_node *np)
 {
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 33b552ffbe57..de1ec54a2a57 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -329,16 +329,16 @@ struct direct_window {
 
 /* Dynamic DMA Window support */
 struct ddw_query_response {
-	__be32 windows_available;
-	__be32 largest_available_block;
-	__be32 page_size;
-	__be32 migration_capable;
+	u32 windows_available;
+	u32 largest_available_block;
+	u32 page_size;
+	u32 migration_capable;
 };
 
 struct ddw_create_response {
-	__be32 liobn;
-	__be32 addr_hi;
-	__be32 addr_lo;
+	u32 liobn;
+	u32 addr_hi;
+	u32 addr_lo;
 };
 
 static LIST_HEAD(direct_window_list);
@@ -721,20 +721,22 @@ static int __init disable_ddw_setup(char *str)
 
 early_param("disable_ddw", disable_ddw_setup);
 
-static void remove_ddw(struct device_node *np)
+static void remove_ddw(struct device_node *np, bool remove_prop)
 {
 	struct dynamic_dma_window_prop *dwp;
 	struct property *win64;
-	const u32 *ddw_avail;
+	u32 ddw_avail[3];
 	u64 liobn;
-	int len, ret;
+	int ret = 0;
+
+	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
+					 &ddw_avail[0], 3);
 
-	ddw_avail = of_get_property(np, "ibm,ddw-applicable", &len);
 	win64 = of_find_property(np, DIRECT64_PROPNAME, NULL);
 	if (!win64)
 		return;
 
-	if (!ddw_avail || len < 3 * sizeof(u32) || win64->length < sizeof(*dwp))
+	if (ret || win64->length < sizeof(*dwp))
 		goto delprop;
 
 	dwp = win64->value;
@@ -761,7 +763,8 @@ static void remove_ddw(struct device_node *np)
 			np->full_name, ret, ddw_avail[2], liobn);
 
 delprop:
-	ret = of_remove_property(np, win64);
+	if (remove_prop)
+		ret = of_remove_property(np, win64);
 	if (ret)
 		pr_warning("%s: failed to remove direct window property: %d\n",
 			np->full_name, ret);
@@ -805,7 +808,7 @@ static int find_existing_ddw_windows(void)
 		window = kzalloc(sizeof(*window), GFP_KERNEL);
 		if (!window || len < sizeof(struct dynamic_dma_window_prop)) {
 			kfree(window);
-			remove_ddw(pdn);
+			remove_ddw(pdn, true);
 			continue;
 		}
 
@@ -871,8 +874,9 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
-		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, cfg_addr,
-				BUID_HI(buid), BUID_LO(buid), page_shift, window_shift);
+		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create,
+				cfg_addr, BUID_HI(buid), BUID_LO(buid),
+				page_shift, window_shift);
 	} while (rtas_busy_delay(ret));
 	dev_info(&dev->dev,
 		"ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d "
@@ -909,7 +913,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	int page_shift;
 	u64 dma_addr, max_addr;
 	struct device_node *dn;
-	const u32 *uninitialized_var(ddw_avail);
+	u32 ddw_avail[3];
 	struct direct_window *window;
 	struct property *win64;
 	struct dynamic_dma_window_prop *ddwprop;
@@ -941,8 +945,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * for the given node in that order.
 	 * the property is actually in the parent, not the PE
 	 */
-	ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len);
-	if (!ddw_avail || len < 3 * sizeof(u32))
+	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+					 &ddw_avail[0], 3);
+	if (ret)
 		goto out_failed;
 
        /*
@@ -965,11 +970,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		dev_dbg(&dev->dev, "no free dynamic windows");
 		goto out_failed;
 	}
-	if (be32_to_cpu(query.page_size) & 4) {
+	if (query.page_size & 4) {
 		page_shift = 24; /* 16MB */
-	} else if (be32_to_cpu(query.page_size) & 2) {
+	} else if (query.page_size & 2) {
 		page_shift = 16; /* 64kB */
-	} else if (be32_to_cpu(query.page_size) & 1) {
+	} else if (query.page_size & 1) {
 		page_shift = 12; /* 4kB */
 	} else {
 		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
@@ -979,7 +984,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
 	max_addr = memory_hotplug_max();
-	if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) {
+	if (query.largest_available_block < (max_addr >> page_shift)) {
 		dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
 			  1ULL << page_shift);
@@ -1005,8 +1010,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (ret != 0)
 		goto out_free_prop;
 
-	ddwprop->liobn = create.liobn;
-	ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2));
+	ddwprop->liobn = cpu_to_be32(create.liobn);
+	ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) |
+			create.addr_lo);
 	ddwprop->tce_shift = cpu_to_be32(page_shift);
 	ddwprop->window_shift = cpu_to_be32(len);
 
@@ -1038,14 +1044,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	list_add(&window->list, &direct_window_list);
 	spin_unlock(&direct_window_list_lock);
 
-	dma_addr = of_read_number(&create.addr_hi, 2);
+	dma_addr = be64_to_cpu(ddwprop->dma_base);
 	goto out_unlock;
 
 out_free_window:
 	kfree(window);
 
 out_clear_window:
-	remove_ddw(pdn);
+	remove_ddw(pdn, true);
 
 out_free_prop:
 	kfree(win64->name);
@@ -1255,7 +1261,14 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 
 	switch (action) {
 	case OF_RECONFIG_DETACH_NODE:
-		remove_ddw(np);
+		/*
+		 * Removing the property will invoke the reconfig
+		 * notifier again, which causes dead-lock on the
+		 * read-write semaphore of the notifier chain. So
+		 * we have to remove the property when releasing
+		 * the device node.
+		 */
+		remove_ddw(np, false);
 		if (pci && pci->iommu_table)
 			iommu_free_table(pci->iommu_table, np->full_name);
 
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index b02af9ef3ff6..ccf6f162f69c 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -430,16 +430,17 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
 		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
 }
 
-static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
-				       unsigned char *hpte_slot_array,
-				       unsigned long addr, int psize)
+static void pSeries_lpar_hugepage_invalidate(unsigned long vsid,
+					     unsigned long addr,
+					     unsigned char *hpte_slot_array,
+					     int psize, int ssize)
 {
-	int ssize = 0, i, index = 0;
+	int i, index = 0;
 	unsigned long s_addr = addr;
 	unsigned int max_hpte_count, valid;
 	unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
 	unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
-	unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
+	unsigned long shift, hidx, vpn = 0, hash, slot;
 
 	shift = mmu_psize_defs[psize].shift;
 	max_hpte_count = 1U << (PMD_SHIFT - shift);
@@ -452,15 +453,6 @@ static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
 
 		/* get the vpn */
 		addr = s_addr + (i * (1ul << shift));
-		if (!is_kernel_addr(addr)) {
-			ssize = user_segment_size(addr);
-			vsid = get_vsid(mm->context.id, addr, ssize);
-			WARN_ON(vsid == 0);
-		} else {
-			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
-			ssize = mmu_kernel_ssize;
-		}
-
 		vpn = hpt_vpn(addr, vsid, ssize);
 		hash = hpt_hash(vpn, shift, ssize);
 		if (hidx & _PTEIDX_SECONDARY)
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 0c882e83c4ce..6849d85ea0d5 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -428,7 +428,7 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 	 */
 again:
 	if (type == PCI_CAP_ID_MSI) {
-		if (pdn->force_32bit_msi) {
+		if (pdev->no_64bit_msi) {
 			rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec);
 			if (rc < 0) {
 				/*
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index efe61374f6ea..e68922b0d4f5 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -118,10 +118,10 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		}
 	}
 
-	/* Unregister the bridge device from sysfs and remove the PCI bus */
-	device_unregister(b->bridge);
+	/* Remove the PCI bus and unregister the bridge device from sysfs */
 	phb->bus = NULL;
 	pci_remove_bus(b);
+	device_unregister(b->bridge);
 
 	/* Now release the IO resource */
 	if (res->flags & IORESOURCE_IO)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 972df0ffd4dc..0b84df948ed6 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -671,7 +671,7 @@ static int __init pseries_probe_fw_features(unsigned long node,
 					    void *data)
 {
 	const char *prop;
-	unsigned long len;
+	int len;
 	static int hypertas_found;
 	static int vec5_found;
 
@@ -704,7 +704,7 @@ static int __init pseries_probe_fw_features(unsigned long node,
 static int __init pSeries_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
- 	char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
+	const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
 
  	if (dtype == NULL)
  		return 0;
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index b07909850f77..bc5fbc201bcb 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -288,10 +288,10 @@ static inline void disable_surveillance(void)
 	args.token = rtas_token("set-indicator");
 	if (args.token == RTAS_UNKNOWN_SERVICE)
 		return;
-	args.nargs = 3;
-	args.nret = 1;
+	args.nargs = cpu_to_be32(3);
+	args.nret = cpu_to_be32(1);
 	args.rets = &args.args[3];
-	args.args[0] = SURVEILLANCE_TOKEN;
+	args.args[0] = cpu_to_be32(SURVEILLANCE_TOKEN);
 	args.args[1] = 0;
 	args.args[2] = 0;
 	enter_rtas(__pa(&args));
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 65a07750f4f9..a0a3bed6e4dc 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -93,6 +93,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
@@ -117,6 +118,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index cf3c0089bef2..23223cd63e54 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -820,6 +820,9 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 		else
 			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
 		spin_unlock(&ctrblk_lock);
+	} else {
+		if (!nbytes)
+			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
 	}
 	/*
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 0a5aac8a9412..7acb77f7ef1a 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -429,6 +429,9 @@ static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
 		else
 			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
 		spin_unlock(&ctrblk_lock);
+	} else {
+		if (!nbytes)
+			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
 	}
 	/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
 	if (nbytes) {
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index fa9aaf7144b7..1d4706114a45 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,23 +15,29 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <asm/barrier.h>
 #include <asm/cmpxchg.h>
 
 #define ATOMIC_INIT(i)  { (i) }
 
+#define __ATOMIC_NO_BARRIER	"\n"
+
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 
 #define __ATOMIC_OR	"lao"
 #define __ATOMIC_AND	"lan"
 #define __ATOMIC_ADD	"laa"
+#define __ATOMIC_BARRIER "bcr	14,0\n"
 
-#define __ATOMIC_LOOP(ptr, op_val, op_string)				\
+#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
 ({									\
 	int old_val;							\
 									\
 	typecheck(atomic_t *, ptr);					\
 	asm volatile(							\
+		__barrier						\
 		op_string "	%0,%2,%1\n"				\
+		__barrier						\
 		: "=d" (old_val), "+Q" ((ptr)->counter)			\
 		: "d" (op_val)						\
 		: "cc", "memory");					\
@@ -43,8 +49,9 @@
 #define __ATOMIC_OR	"or"
 #define __ATOMIC_AND	"nr"
 #define __ATOMIC_ADD	"ar"
+#define __ATOMIC_BARRIER "\n"
 
-#define __ATOMIC_LOOP(ptr, op_val, op_string)				\
+#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
 ({									\
 	int old_val, new_val;						\
 									\
@@ -82,7 +89,7 @@ static inline void atomic_set(atomic_t *v, int i)
 
 static inline int atomic_add_return(int i, atomic_t *v)
 {
-	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD) + i;
+	return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i;
 }
 
 static inline void atomic_add(int i, atomic_t *v)
@@ -94,12 +101,10 @@ static inline void atomic_add(int i, atomic_t *v)
 			: "+Q" (v->counter)
 			: "i" (i)
 			: "cc", "memory");
-	} else {
-		atomic_add_return(i, v);
+		return;
 	}
-#else
-	atomic_add_return(i, v);
 #endif
+	__ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_NO_BARRIER);
 }
 
 #define atomic_add_negative(_i, _v)	(atomic_add_return(_i, _v) < 0)
@@ -115,12 +120,12 @@ static inline void atomic_add(int i, atomic_t *v)
 
 static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 {
-	__ATOMIC_LOOP(v, ~mask, __ATOMIC_AND);
+	__ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER);
 }
 
 static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
 {
-	__ATOMIC_LOOP(v, mask, __ATOMIC_OR);
+	__ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER);
 }
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
@@ -157,19 +162,24 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #ifdef CONFIG_64BIT
 
+#define __ATOMIC64_NO_BARRIER	"\n"
+
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 
 #define __ATOMIC64_OR	"laog"
 #define __ATOMIC64_AND	"lang"
 #define __ATOMIC64_ADD	"laag"
+#define __ATOMIC64_BARRIER "bcr	14,0\n"
 
-#define __ATOMIC64_LOOP(ptr, op_val, op_string)				\
+#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
 ({									\
 	long long old_val;						\
 									\
 	typecheck(atomic64_t *, ptr);					\
 	asm volatile(							\
+		__barrier						\
 		op_string "	%0,%2,%1\n"				\
+		__barrier						\
 		: "=d" (old_val), "+Q" ((ptr)->counter)			\
 		: "d" (op_val)						\
 		: "cc", "memory");					\
@@ -181,8 +191,9 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define __ATOMIC64_OR	"ogr"
 #define __ATOMIC64_AND	"ngr"
 #define __ATOMIC64_ADD	"agr"
+#define __ATOMIC64_BARRIER "\n"
 
-#define __ATOMIC64_LOOP(ptr, op_val, op_string)				\
+#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
 ({									\
 	long long old_val, new_val;					\
 									\
@@ -220,17 +231,32 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 
 static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
-	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD) + i;
+	return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i;
+}
+
+static inline void atomic64_add(long long i, atomic64_t *v)
+{
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
+		asm volatile(
+			"agsi	%0,%1\n"
+			: "+Q" (v->counter)
+			: "i" (i)
+			: "cc", "memory");
+		return;
+	}
+#endif
+	__ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER);
 }
 
 static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v)
 {
-	__ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND);
+	__ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER);
 }
 
 static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v)
 {
-	__ATOMIC64_LOOP(v, mask, __ATOMIC64_OR);
+	__ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER);
 }
 
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
@@ -334,25 +360,13 @@ static inline void atomic64_clear_mask(unsigned long long mask, atomic64_t *v)
 	} while (atomic64_cmpxchg(v, old, new) != old);
 }
 
-#endif /* CONFIG_64BIT */
-
 static inline void atomic64_add(long long i, atomic64_t *v)
 {
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
-	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
-		asm volatile(
-			"agsi	%0,%1\n"
-			: "+Q" (v->counter)
-			: "i" (i)
-			: "cc", "memory");
-	} else {
-		atomic64_add_return(i, v);
-	}
-#else
 	atomic64_add_return(i, v);
-#endif
 }
 
+#endif /* CONFIG_64BIT */
+
 static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
 {
 	long long c, old;
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 6e6ad0680829..4e206123b439 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -47,14 +47,18 @@
 
 #include <linux/typecheck.h>
 #include <linux/compiler.h>
+#include <asm/barrier.h>
+
+#define __BITOPS_NO_BARRIER	"\n"
 
 #ifndef CONFIG_64BIT
 
 #define __BITOPS_OR		"or"
 #define __BITOPS_AND		"nr"
 #define __BITOPS_XOR		"xr"
+#define __BITOPS_BARRIER	"\n"
 
-#define __BITOPS_LOOP(__addr, __val, __op_string)		\
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier)	\
 ({								\
 	unsigned long __old, __new;				\
 								\
@@ -67,7 +71,7 @@
 		"	jl	0b"				\
 		: "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\
 		: "d" (__val)					\
-		: "cc");					\
+		: "cc", "memory");				\
 	__old;							\
 })
 
@@ -78,17 +82,20 @@
 #define __BITOPS_OR		"laog"
 #define __BITOPS_AND		"lang"
 #define __BITOPS_XOR		"laxg"
+#define __BITOPS_BARRIER	"bcr	14,0\n"
 
-#define __BITOPS_LOOP(__addr, __val, __op_string)		\
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier)	\
 ({								\
 	unsigned long __old;					\
 								\
 	typecheck(unsigned long *, (__addr));			\
 	asm volatile(						\
+		__barrier					\
 		__op_string "	%0,%2,%1\n"			\
+		__barrier					\
 		: "=d" (__old),	"+Q" (*(__addr))		\
 		: "d" (__val)					\
-		: "cc");					\
+		: "cc", "memory");				\
 	__old;							\
 })
 
@@ -97,8 +104,9 @@
 #define __BITOPS_OR		"ogr"
 #define __BITOPS_AND		"ngr"
 #define __BITOPS_XOR		"xgr"
+#define __BITOPS_BARRIER	"\n"
 
-#define __BITOPS_LOOP(__addr, __val, __op_string)		\
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier)	\
 ({								\
 	unsigned long __old, __new;				\
 								\
@@ -111,7 +119,7 @@
 		"	jl	0b"				\
 		: "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\
 		: "d" (__val)					\
-		: "cc");					\
+		: "cc", "memory");				\
 	__old;							\
 })
 
@@ -149,12 +157,12 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
 			"oi	%0,%b1\n"
 			: "+Q" (*caddr)
 			: "i" (1 << (nr & 7))
-			: "cc");
+			: "cc", "memory");
 		return;
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__BITOPS_LOOP(addr, mask, __BITOPS_OR);
+	__BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_NO_BARRIER);
 }
 
 static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -170,12 +178,12 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
 			"ni	%0,%b1\n"
 			: "+Q" (*caddr)
 			: "i" (~(1 << (nr & 7)))
-			: "cc");
+			: "cc", "memory");
 		return;
 	}
 #endif
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	__BITOPS_LOOP(addr, mask, __BITOPS_AND);
+	__BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_NO_BARRIER);
 }
 
 static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -191,12 +199,12 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
 			"xi	%0,%b1\n"
 			: "+Q" (*caddr)
 			: "i" (1 << (nr & 7))
-			: "cc");
+			: "cc", "memory");
 		return;
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__BITOPS_LOOP(addr, mask, __BITOPS_XOR);
+	__BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_NO_BARRIER);
 }
 
 static inline int
@@ -206,8 +214,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __BITOPS_LOOP(addr, mask, __BITOPS_OR);
-	barrier();
+	old = __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_BARRIER);
 	return (old & mask) != 0;
 }
 
@@ -218,8 +225,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	old = __BITOPS_LOOP(addr, mask, __BITOPS_AND);
-	barrier();
+	old = __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_BARRIER);
 	return (old & ~mask) != 0;
 }
 
@@ -230,8 +236,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR);
-	barrier();
+	old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_BARRIER);
 	return (old & mask) != 0;
 }
 
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index f201af8be580..31b5ca8f8c3d 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -219,7 +219,7 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *);
 #define to_ccwdev(n) container_of(n, struct ccw_device, dev)
 #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
 
-extern struct ccw_device *ccw_device_probe_console(void);
+extern struct ccw_device *ccw_device_probe_console(struct ccw_driver *);
 extern void ccw_device_wait_idle(struct ccw_device *);
 extern int ccw_device_force_console(struct ccw_device *);
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index eef3dd3fd9a9..892d9571fbf4 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -13,8 +13,11 @@
 
 #ifndef ASM_KVM_HOST_H
 #define ASM_KVM_HOST_H
+
+#include <linux/types.h>
 #include <linux/hrtimer.h>
 #include <linux/interrupt.h>
+#include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 #include <asm/debug.h>
 #include <asm/cpu.h>
@@ -289,4 +292,18 @@ static inline bool kvm_is_error_hva(unsigned long addr)
 
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 extern char sie_exit;
+
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_check_processor_compat(void *rtn) {}
+static inline void kvm_arch_exit(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm,
+		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+		struct kvm_memory_slot *slot) {}
+
 #endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index bbf8141408cd..2bed4f02a558 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -142,9 +142,9 @@ struct _lowcore {
 	__u8	pad_0x02fc[0x0300-0x02fc];	/* 0x02fc */
 
 	/* Interrupt response block */
-	__u8	irb[64];			/* 0x0300 */
+	__u8	irb[96];			/* 0x0300 */
 
-	__u8	pad_0x0340[0x0e00-0x0340];	/* 0x0340 */
+	__u8	pad_0x0360[0x0e00-0x0360];	/* 0x0360 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
@@ -288,12 +288,13 @@ struct _lowcore {
 	__u8	pad_0x03a0[0x0400-0x03a0];	/* 0x03a0 */
 
 	/* Interrupt response block. */
-	__u8	irb[64];			/* 0x0400 */
+	__u8	irb[96];			/* 0x0400 */
+	__u8	pad_0x0460[0x0480-0x0460];	/* 0x0460 */
 
 	/* Per cpu primary space access list */
-	__u32	paste[16];			/* 0x0440 */
+	__u32	paste[16];			/* 0x0480 */
 
-	__u8	pad_0x0480[0x0e00-0x0480];	/* 0x0480 */
+	__u8	pad_0x04c0[0x0e00-0x04c0];	/* 0x04c0 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index db02052bd137..5426c9eb5114 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -245,7 +245,7 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index f6be6087a0e9..184d305af3e7 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -64,7 +64,7 @@ void update_cr_regs(struct task_struct *task)
 		if (task->thread.per_flags & PER_FLAG_NO_TE)
 			cr_new &= ~(1UL << 55);
 		if (cr_new != cr)
-			__ctl_load(cr, 0, 0);
+			__ctl_load(cr_new, 0, 0);
 		/* Set or clear transaction execution TDC bits 62 and 63. */
 		__ctl_store(cr, 2, 2);
 		cr_new = cr & ~3UL;
@@ -323,9 +323,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 			unsigned long mask = PSW_MASK_USER;
 
 			mask |= is_ri_task(child) ? PSW_MASK_RI : 0;
-			if ((data & ~mask) != PSW_USER_BITS)
+			if ((data ^ PSW_USER_BITS) & ~mask)
+				/* Invalid psw mask. */
+				return -EINVAL;
+			if ((data & PSW_MASK_ASC) == PSW_ASC_HOME)
+				/* Invalid address-space-control bits */
 				return -EINVAL;
 			if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))
+				/* Invalid addressing mode bits */
 				return -EINVAL;
 		}
 		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
@@ -661,9 +666,12 @@ static int __poke_user_compat(struct task_struct *child,
 
 			mask |= is_ri_task(child) ? PSW32_MASK_RI : 0;
 			/* Build a 64 bit psw mask from 31 bit mask. */
-			if ((tmp & ~mask) != PSW32_USER_BITS)
+			if ((tmp ^ PSW32_USER_BITS) & ~mask)
 				/* Invalid psw mask. */
 				return -EINVAL;
+			if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME)
+				/* Invalid address-space-control bits */
+				return -EINVAL;
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 				(regs->psw.mask & PSW_MASK_BA) |
 				(__u64)(tmp & mask) << 32;
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index dd95f1631621..a80190be6e83 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -226,7 +226,7 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtom_clock_sec =
 		tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtom_clock_nsec = tk->xtime_nsec +
-		+ (tk->wall_to_monotonic.tv_nsec << tk->shift);
+		+ ((u64) tk->wall_to_monotonic.tv_nsec << tk->shift);
 	nsecps = (u64) NSEC_PER_SEC << tk->shift;
 	while (vdso_data->wtom_clock_nsec >= nsecps) {
 		vdso_data->wtom_clock_nsec -= nsecps;
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
deleted file mode 100644
index 70b46eacf8e1..000000000000
--- a/arch/s390/kvm/Kconfig
+++ /dev/null
@@ -1,52 +0,0 @@
-#
-# KVM configuration
-#
-source "virt/kvm/Kconfig"
-
-menuconfig VIRTUALIZATION
-	def_bool y
-	prompt "KVM"
-	---help---
-	  Say Y here to get to see options for using your Linux host to run other
-	  operating systems inside virtual machines (guests).
-	  This option alone does not add any kernel code.
-
-	  If you say N, all options in this submenu will be skipped and disabled.
-
-if VIRTUALIZATION
-
-config KVM
-	def_tristate y
-	prompt "Kernel-based Virtual Machine (KVM) support"
-	depends on HAVE_KVM
-	select PREEMPT_NOTIFIERS
-	select ANON_INODES
-	select HAVE_KVM_CPU_RELAX_INTERCEPT
-	select HAVE_KVM_EVENTFD
-	---help---
-	  Support hosting paravirtualized guest machines using the SIE
-	  virtualization capability on the mainframe. This should work
-	  on any 64bit machine.
-
-	  This module provides access to the hardware capabilities through
-	  a character device node named /dev/kvm.
-
-	  To compile this as a module, choose M here: the module
-	  will be called kvm.
-
-	  If unsure, say N.
-
-config KVM_S390_UCONTROL
-	bool "Userspace controlled virtual machines"
-	depends on KVM
-	---help---
-	  Allow CAP_SYS_ADMIN users to create KVM virtual machines that are
-	  controlled by userspace.
-
-	  If unsure, say N.
-
-# OK, it's a little counter-intuitive to do this, but it puts it neatly under
-# the virtualization menu.
-source drivers/vhost/Kconfig
-
-endif # VIRTUALIZATION
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
deleted file mode 100644
index 5f79d2d79ca7..000000000000
--- a/arch/s390/kvm/interrupt.c
+++ /dev/null
@@ -1,843 +0,0 @@
-/*
- * handling kvm guest interrupts
- *
- * Copyright IBM Corp. 2008
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
- *    Author(s): Carsten Otte <cotte@de.ibm.com>
- */
-
-#include <linux/interrupt.h>
-#include <linux/kvm_host.h>
-#include <linux/hrtimer.h>
-#include <linux/signal.h>
-#include <linux/slab.h>
-#include <asm/asm-offsets.h>
-#include <asm/uaccess.h>
-#include "kvm-s390.h"
-#include "gaccess.h"
-#include "trace-s390.h"
-
-#define IOINT_SCHID_MASK 0x0000ffff
-#define IOINT_SSID_MASK 0x00030000
-#define IOINT_CSSID_MASK 0x03fc0000
-#define IOINT_AI_MASK 0x04000000
-
-static int is_ioint(u64 type)
-{
-	return ((type & 0xfffe0000u) != 0xfffe0000u);
-}
-
-static int psw_extint_disabled(struct kvm_vcpu *vcpu)
-{
-	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
-}
-
-static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
-{
-	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
-}
-
-static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
-{
-	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
-}
-
-static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
-{
-	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
-	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO) ||
-	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT))
-		return 0;
-	return 1;
-}
-
-static u64 int_word_to_isc_bits(u32 int_word)
-{
-	u8 isc = (int_word & 0x38000000) >> 27;
-
-	return (0x80 >> isc) << 24;
-}
-
-static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
-				      struct kvm_s390_interrupt_info *inti)
-{
-	switch (inti->type) {
-	case KVM_S390_INT_EXTERNAL_CALL:
-		if (psw_extint_disabled(vcpu))
-			return 0;
-		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
-			return 1;
-	case KVM_S390_INT_EMERGENCY:
-		if (psw_extint_disabled(vcpu))
-			return 0;
-		if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
-			return 1;
-		return 0;
-	case KVM_S390_INT_SERVICE:
-		if (psw_extint_disabled(vcpu))
-			return 0;
-		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
-			return 1;
-		return 0;
-	case KVM_S390_INT_VIRTIO:
-		if (psw_extint_disabled(vcpu))
-			return 0;
-		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
-			return 1;
-		return 0;
-	case KVM_S390_PROGRAM_INT:
-	case KVM_S390_SIGP_STOP:
-	case KVM_S390_SIGP_SET_PREFIX:
-	case KVM_S390_RESTART:
-		return 1;
-	case KVM_S390_MCHK:
-		if (psw_mchk_disabled(vcpu))
-			return 0;
-		if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14)
-			return 1;
-		return 0;
-	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		if (psw_ioint_disabled(vcpu))
-			return 0;
-		if (vcpu->arch.sie_block->gcr[6] &
-		    int_word_to_isc_bits(inti->io.io_int_word))
-			return 1;
-		return 0;
-	default:
-		printk(KERN_WARNING "illegal interrupt type %llx\n",
-		       inti->type);
-		BUG();
-	}
-	return 0;
-}
-
-static void __set_cpu_idle(struct kvm_vcpu *vcpu)
-{
-	BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
-	atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
-	set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
-}
-
-static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
-{
-	BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
-	atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
-	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
-}
-
-static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
-{
-	atomic_clear_mask(CPUSTAT_ECALL_PEND |
-		CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
-		&vcpu->arch.sie_block->cpuflags);
-	vcpu->arch.sie_block->lctl = 0x0000;
-	vcpu->arch.sie_block->ictl &= ~ICTL_LPSW;
-}
-
-static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
-{
-	atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
-}
-
-static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
-				      struct kvm_s390_interrupt_info *inti)
-{
-	switch (inti->type) {
-	case KVM_S390_INT_EXTERNAL_CALL:
-	case KVM_S390_INT_EMERGENCY:
-	case KVM_S390_INT_SERVICE:
-	case KVM_S390_INT_VIRTIO:
-		if (psw_extint_disabled(vcpu))
-			__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
-		else
-			vcpu->arch.sie_block->lctl |= LCTL_CR0;
-		break;
-	case KVM_S390_SIGP_STOP:
-		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
-		break;
-	case KVM_S390_MCHK:
-		if (psw_mchk_disabled(vcpu))
-			vcpu->arch.sie_block->ictl |= ICTL_LPSW;
-		else
-			vcpu->arch.sie_block->lctl |= LCTL_CR14;
-		break;
-	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		if (psw_ioint_disabled(vcpu))
-			__set_cpuflag(vcpu, CPUSTAT_IO_INT);
-		else
-			vcpu->arch.sie_block->lctl |= LCTL_CR6;
-		break;
-	default:
-		BUG();
-	}
-}
-
-static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
-				   struct kvm_s390_interrupt_info *inti)
-{
-	const unsigned short table[] = { 2, 4, 4, 6 };
-	int rc = 0;
-
-	switch (inti->type) {
-	case KVM_S390_INT_EMERGENCY:
-		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
-		vcpu->stat.deliver_emergency_signal++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 inti->emerg.code, 0);
-		rc  = put_guest(vcpu, 0x1201, (u16 __user *)__LC_EXT_INT_CODE);
-		rc |= put_guest(vcpu, inti->emerg.code,
-				(u16 __user *)__LC_EXT_CPU_ADDR);
-		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      __LC_EXT_NEW_PSW, sizeof(psw_t));
-		break;
-	case KVM_S390_INT_EXTERNAL_CALL:
-		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
-		vcpu->stat.deliver_external_call++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 inti->extcall.code, 0);
-		rc  = put_guest(vcpu, 0x1202, (u16 __user *)__LC_EXT_INT_CODE);
-		rc |= put_guest(vcpu, inti->extcall.code,
-				(u16 __user *)__LC_EXT_CPU_ADDR);
-		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      __LC_EXT_NEW_PSW, sizeof(psw_t));
-		break;
-	case KVM_S390_INT_SERVICE:
-		VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
-			   inti->ext.ext_params);
-		vcpu->stat.deliver_service_signal++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 inti->ext.ext_params, 0);
-		rc  = put_guest(vcpu, 0x2401, (u16 __user *)__LC_EXT_INT_CODE);
-		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      __LC_EXT_NEW_PSW, sizeof(psw_t));
-		rc |= put_guest(vcpu, inti->ext.ext_params,
-				(u32 __user *)__LC_EXT_PARAMS);
-		break;
-	case KVM_S390_INT_VIRTIO:
-		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
-			   inti->ext.ext_params, inti->ext.ext_params2);
-		vcpu->stat.deliver_virtio_interrupt++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 inti->ext.ext_params,
-						 inti->ext.ext_params2);
-		rc  = put_guest(vcpu, 0x2603, (u16 __user *)__LC_EXT_INT_CODE);
-		rc |= put_guest(vcpu, 0x0d00, (u16 __user *)__LC_EXT_CPU_ADDR);
-		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      __LC_EXT_NEW_PSW, sizeof(psw_t));
-		rc |= put_guest(vcpu, inti->ext.ext_params,
-				(u32 __user *)__LC_EXT_PARAMS);
-		rc |= put_guest(vcpu, inti->ext.ext_params2,
-				(u64 __user *)__LC_EXT_PARAMS2);
-		break;
-	case KVM_S390_SIGP_STOP:
-		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
-		vcpu->stat.deliver_stop_signal++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 0, 0);
-		__set_intercept_indicator(vcpu, inti);
-		break;
-
-	case KVM_S390_SIGP_SET_PREFIX:
-		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
-			   inti->prefix.address);
-		vcpu->stat.deliver_prefix_signal++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 inti->prefix.address, 0);
-		kvm_s390_set_prefix(vcpu, inti->prefix.address);
-		break;
-
-	case KVM_S390_RESTART:
-		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
-		vcpu->stat.deliver_restart_signal++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 0, 0);
-		rc  = copy_to_guest(vcpu,
-				    offsetof(struct _lowcore, restart_old_psw),
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      offsetof(struct _lowcore, restart_psw),
-				      sizeof(psw_t));
-		atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
-		break;
-	case KVM_S390_PROGRAM_INT:
-		VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
-			   inti->pgm.code,
-			   table[vcpu->arch.sie_block->ipa >> 14]);
-		vcpu->stat.deliver_program_int++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 inti->pgm.code, 0);
-		rc  = put_guest(vcpu, inti->pgm.code, (u16 __user *)__LC_PGM_INT_CODE);
-		rc |= put_guest(vcpu, table[vcpu->arch.sie_block->ipa >> 14],
-				(u16 __user *)__LC_PGM_ILC);
-		rc |= copy_to_guest(vcpu, __LC_PGM_OLD_PSW,
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      __LC_PGM_NEW_PSW, sizeof(psw_t));
-		break;
-
-	case KVM_S390_MCHK:
-		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
-			   inti->mchk.mcic);
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 inti->mchk.cr14,
-						 inti->mchk.mcic);
-		rc  = kvm_s390_vcpu_store_status(vcpu,
-						 KVM_S390_STORE_STATUS_PREFIXED);
-		rc |= put_guest(vcpu, inti->mchk.mcic, (u64 __user *) __LC_MCCK_CODE);
-		rc |= copy_to_guest(vcpu, __LC_MCK_OLD_PSW,
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      __LC_MCK_NEW_PSW, sizeof(psw_t));
-		break;
-
-	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-	{
-		__u32 param0 = ((__u32)inti->io.subchannel_id << 16) |
-			inti->io.subchannel_nr;
-		__u64 param1 = ((__u64)inti->io.io_int_parm << 32) |
-			inti->io.io_int_word;
-		VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
-		vcpu->stat.deliver_io_int++;
-		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
-						 param0, param1);
-		rc  = put_guest(vcpu, inti->io.subchannel_id,
-				(u16 __user *) __LC_SUBCHANNEL_ID);
-		rc |= put_guest(vcpu, inti->io.subchannel_nr,
-				(u16 __user *) __LC_SUBCHANNEL_NR);
-		rc |= put_guest(vcpu, inti->io.io_int_parm,
-				(u32 __user *) __LC_IO_INT_PARM);
-		rc |= put_guest(vcpu, inti->io.io_int_word,
-				(u32 __user *) __LC_IO_INT_WORD);
-		rc |= copy_to_guest(vcpu, __LC_IO_OLD_PSW,
-				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-				      __LC_IO_NEW_PSW, sizeof(psw_t));
-		break;
-	}
-	default:
-		BUG();
-	}
-	if (rc) {
-		printk("kvm: The guest lowcore is not mapped during interrupt "
-		       "delivery, killing userspace\n");
-		do_exit(SIGKILL);
-	}
-}
-
-static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
-{
-	int rc;
-
-	if (psw_extint_disabled(vcpu))
-		return 0;
-	if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
-		return 0;
-	rc  = put_guest(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE);
-	rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
-			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
-	rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
-			      __LC_EXT_NEW_PSW, sizeof(psw_t));
-	if (rc) {
-		printk("kvm: The guest lowcore is not mapped during interrupt "
-			"delivery, killing userspace\n");
-		do_exit(SIGKILL);
-	}
-	return 1;
-}
-
-static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
-{
-	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
-	struct kvm_s390_interrupt_info  *inti;
-	int rc = 0;
-
-	if (atomic_read(&li->active)) {
-		spin_lock_bh(&li->lock);
-		list_for_each_entry(inti, &li->list, list)
-			if (__interrupt_is_deliverable(vcpu, inti)) {
-				rc = 1;
-				break;
-			}
-		spin_unlock_bh(&li->lock);
-	}
-
-	if ((!rc) && atomic_read(&fi->active)) {
-		spin_lock(&fi->lock);
-		list_for_each_entry(inti, &fi->list, list)
-			if (__interrupt_is_deliverable(vcpu, inti)) {
-				rc = 1;
-				break;
-			}
-		spin_unlock(&fi->lock);
-	}
-
-	if ((!rc) && (vcpu->arch.sie_block->ckc <
-		get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) {
-		if ((!psw_extint_disabled(vcpu)) &&
-			(vcpu->arch.sie_block->gcr[0] & 0x800ul))
-			rc = 1;
-	}
-
-	return rc;
-}
-
-int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
-int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
-{
-	u64 now, sltime;
-	DECLARE_WAITQUEUE(wait, current);
-
-	vcpu->stat.exit_wait_state++;
-	if (kvm_cpu_has_interrupt(vcpu))
-		return 0;
-
-	__set_cpu_idle(vcpu);
-	spin_lock_bh(&vcpu->arch.local_int.lock);
-	vcpu->arch.local_int.timer_due = 0;
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
-
-	if (psw_interrupts_disabled(vcpu)) {
-		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
-		__unset_cpu_idle(vcpu);
-		return -EOPNOTSUPP; /* disabled wait */
-	}
-
-	if (psw_extint_disabled(vcpu) ||
-	    (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) {
-		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
-		goto no_timer;
-	}
-
-	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
-	if (vcpu->arch.sie_block->ckc < now) {
-		__unset_cpu_idle(vcpu);
-		return 0;
-	}
-
-	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-
-	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
-	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
-no_timer:
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-	spin_lock(&vcpu->arch.local_int.float_int->lock);
-	spin_lock_bh(&vcpu->arch.local_int.lock);
-	add_wait_queue(&vcpu->wq, &wait);
-	while (list_empty(&vcpu->arch.local_int.list) &&
-		list_empty(&vcpu->arch.local_int.float_int->list) &&
-		(!vcpu->arch.local_int.timer_due) &&
-		!signal_pending(current)) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		spin_unlock_bh(&vcpu->arch.local_int.lock);
-		spin_unlock(&vcpu->arch.local_int.float_int->lock);
-		schedule();
-		spin_lock(&vcpu->arch.local_int.float_int->lock);
-		spin_lock_bh(&vcpu->arch.local_int.lock);
-	}
-	__unset_cpu_idle(vcpu);
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&vcpu->wq, &wait);
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
-	spin_unlock(&vcpu->arch.local_int.float_int->lock);
-	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-
-	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
-	return 0;
-}
-
-void kvm_s390_tasklet(unsigned long parm)
-{
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm;
-
-	spin_lock(&vcpu->arch.local_int.lock);
-	vcpu->arch.local_int.timer_due = 1;
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
-	spin_unlock(&vcpu->arch.local_int.lock);
-}
-
-/*
- * low level hrtimer wake routine. Because this runs in hardirq context
- * we schedule a tasklet to do the real work.
- */
-enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
-{
-	struct kvm_vcpu *vcpu;
-
-	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
-	tasklet_schedule(&vcpu->arch.tasklet);
-
-	return HRTIMER_NORESTART;
-}
-
-void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
-{
-	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
-	struct kvm_s390_interrupt_info  *n, *inti = NULL;
-	int deliver;
-
-	__reset_intercept_indicators(vcpu);
-	if (atomic_read(&li->active)) {
-		do {
-			deliver = 0;
-			spin_lock_bh(&li->lock);
-			list_for_each_entry_safe(inti, n, &li->list, list) {
-				if (__interrupt_is_deliverable(vcpu, inti)) {
-					list_del(&inti->list);
-					deliver = 1;
-					break;
-				}
-				__set_intercept_indicator(vcpu, inti);
-			}
-			if (list_empty(&li->list))
-				atomic_set(&li->active, 0);
-			spin_unlock_bh(&li->lock);
-			if (deliver) {
-				__do_deliver_interrupt(vcpu, inti);
-				kfree(inti);
-			}
-		} while (deliver);
-	}
-
-	if ((vcpu->arch.sie_block->ckc <
-		get_tod_clock_fast() + vcpu->arch.sie_block->epoch))
-		__try_deliver_ckc_interrupt(vcpu);
-
-	if (atomic_read(&fi->active)) {
-		do {
-			deliver = 0;
-			spin_lock(&fi->lock);
-			list_for_each_entry_safe(inti, n, &fi->list, list) {
-				if (__interrupt_is_deliverable(vcpu, inti)) {
-					list_del(&inti->list);
-					deliver = 1;
-					break;
-				}
-				__set_intercept_indicator(vcpu, inti);
-			}
-			if (list_empty(&fi->list))
-				atomic_set(&fi->active, 0);
-			spin_unlock(&fi->lock);
-			if (deliver) {
-				__do_deliver_interrupt(vcpu, inti);
-				kfree(inti);
-			}
-		} while (deliver);
-	}
-}
-
-void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
-{
-	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
-	struct kvm_s390_interrupt_info  *n, *inti = NULL;
-	int deliver;
-
-	__reset_intercept_indicators(vcpu);
-	if (atomic_read(&li->active)) {
-		do {
-			deliver = 0;
-			spin_lock_bh(&li->lock);
-			list_for_each_entry_safe(inti, n, &li->list, list) {
-				if ((inti->type == KVM_S390_MCHK) &&
-				    __interrupt_is_deliverable(vcpu, inti)) {
-					list_del(&inti->list);
-					deliver = 1;
-					break;
-				}
-				__set_intercept_indicator(vcpu, inti);
-			}
-			if (list_empty(&li->list))
-				atomic_set(&li->active, 0);
-			spin_unlock_bh(&li->lock);
-			if (deliver) {
-				__do_deliver_interrupt(vcpu, inti);
-				kfree(inti);
-			}
-		} while (deliver);
-	}
-
-	if (atomic_read(&fi->active)) {
-		do {
-			deliver = 0;
-			spin_lock(&fi->lock);
-			list_for_each_entry_safe(inti, n, &fi->list, list) {
-				if ((inti->type == KVM_S390_MCHK) &&
-				    __interrupt_is_deliverable(vcpu, inti)) {
-					list_del(&inti->list);
-					deliver = 1;
-					break;
-				}
-				__set_intercept_indicator(vcpu, inti);
-			}
-			if (list_empty(&fi->list))
-				atomic_set(&fi->active, 0);
-			spin_unlock(&fi->lock);
-			if (deliver) {
-				__do_deliver_interrupt(vcpu, inti);
-				kfree(inti);
-			}
-		} while (deliver);
-	}
-}
-
-int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
-{
-	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	struct kvm_s390_interrupt_info *inti;
-
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
-	if (!inti)
-		return -ENOMEM;
-
-	inti->type = KVM_S390_PROGRAM_INT;
-	inti->pgm.code = code;
-
-	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1);
-	spin_lock_bh(&li->lock);
-	list_add(&inti->list, &li->list);
-	atomic_set(&li->active, 1);
-	BUG_ON(waitqueue_active(li->wq));
-	spin_unlock_bh(&li->lock);
-	return 0;
-}
-
-struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
-						    u64 cr6, u64 schid)
-{
-	struct kvm_s390_float_interrupt *fi;
-	struct kvm_s390_interrupt_info *inti, *iter;
-
-	if ((!schid && !cr6) || (schid && cr6))
-		return NULL;
-	mutex_lock(&kvm->lock);
-	fi = &kvm->arch.float_int;
-	spin_lock(&fi->lock);
-	inti = NULL;
-	list_for_each_entry(iter, &fi->list, list) {
-		if (!is_ioint(iter->type))
-			continue;
-		if (cr6 &&
-		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
-			continue;
-		if (schid) {
-			if (((schid & 0x00000000ffff0000) >> 16) !=
-			    iter->io.subchannel_id)
-				continue;
-			if ((schid & 0x000000000000ffff) !=
-			    iter->io.subchannel_nr)
-				continue;
-		}
-		inti = iter;
-		break;
-	}
-	if (inti)
-		list_del_init(&inti->list);
-	if (list_empty(&fi->list))
-		atomic_set(&fi->active, 0);
-	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
-	return inti;
-}
-
-int kvm_s390_inject_vm(struct kvm *kvm,
-		       struct kvm_s390_interrupt *s390int)
-{
-	struct kvm_s390_local_interrupt *li;
-	struct kvm_s390_float_interrupt *fi;
-	struct kvm_s390_interrupt_info *inti, *iter;
-	int sigcpu;
-
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
-	if (!inti)
-		return -ENOMEM;
-
-	switch (s390int->type) {
-	case KVM_S390_INT_VIRTIO:
-		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
-			 s390int->parm, s390int->parm64);
-		inti->type = s390int->type;
-		inti->ext.ext_params = s390int->parm;
-		inti->ext.ext_params2 = s390int->parm64;
-		break;
-	case KVM_S390_INT_SERVICE:
-		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
-		inti->type = s390int->type;
-		inti->ext.ext_params = s390int->parm;
-		break;
-	case KVM_S390_PROGRAM_INT:
-	case KVM_S390_SIGP_STOP:
-	case KVM_S390_INT_EXTERNAL_CALL:
-	case KVM_S390_INT_EMERGENCY:
-		kfree(inti);
-		return -EINVAL;
-	case KVM_S390_MCHK:
-		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
-			 s390int->parm64);
-		inti->type = s390int->type;
-		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
-		inti->mchk.mcic = s390int->parm64;
-		break;
-	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		if (s390int->type & IOINT_AI_MASK)
-			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
-		else
-			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
-				 s390int->type & IOINT_CSSID_MASK,
-				 s390int->type & IOINT_SSID_MASK,
-				 s390int->type & IOINT_SCHID_MASK);
-		inti->type = s390int->type;
-		inti->io.subchannel_id = s390int->parm >> 16;
-		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
-		inti->io.io_int_parm = s390int->parm64 >> 32;
-		inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull;
-		break;
-	default:
-		kfree(inti);
-		return -EINVAL;
-	}
-	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
-				 2);
-
-	mutex_lock(&kvm->lock);
-	fi = &kvm->arch.float_int;
-	spin_lock(&fi->lock);
-	if (!is_ioint(inti->type))
-		list_add_tail(&inti->list, &fi->list);
-	else {
-		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
-
-		/* Keep I/O interrupts sorted in isc order. */
-		list_for_each_entry(iter, &fi->list, list) {
-			if (!is_ioint(iter->type))
-				continue;
-			if (int_word_to_isc_bits(iter->io.io_int_word)
-			    <= isc_bits)
-				continue;
-			break;
-		}
-		list_add_tail(&inti->list, &iter->list);
-	}
-	atomic_set(&fi->active, 1);
-	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
-	if (sigcpu == KVM_MAX_VCPUS) {
-		do {
-			sigcpu = fi->next_rr_cpu++;
-			if (sigcpu == KVM_MAX_VCPUS)
-				sigcpu = fi->next_rr_cpu = 0;
-		} while (fi->local_int[sigcpu] == NULL);
-	}
-	li = fi->local_int[sigcpu];
-	spin_lock_bh(&li->lock);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(li->wq))
-		wake_up_interruptible(li->wq);
-	spin_unlock_bh(&li->lock);
-	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
-	return 0;
-}
-
-int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
-			 struct kvm_s390_interrupt *s390int)
-{
-	struct kvm_s390_local_interrupt *li;
-	struct kvm_s390_interrupt_info *inti;
-
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
-	if (!inti)
-		return -ENOMEM;
-
-	switch (s390int->type) {
-	case KVM_S390_PROGRAM_INT:
-		if (s390int->parm & 0xffff0000) {
-			kfree(inti);
-			return -EINVAL;
-		}
-		inti->type = s390int->type;
-		inti->pgm.code = s390int->parm;
-		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
-			   s390int->parm);
-		break;
-	case KVM_S390_SIGP_SET_PREFIX:
-		inti->prefix.address = s390int->parm;
-		inti->type = s390int->type;
-		VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
-			   s390int->parm);
-		break;
-	case KVM_S390_SIGP_STOP:
-	case KVM_S390_RESTART:
-		VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
-		inti->type = s390int->type;
-		break;
-	case KVM_S390_INT_EXTERNAL_CALL:
-		if (s390int->parm & 0xffff0000) {
-			kfree(inti);
-			return -EINVAL;
-		}
-		VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
-			   s390int->parm);
-		inti->type = s390int->type;
-		inti->extcall.code = s390int->parm;
-		break;
-	case KVM_S390_INT_EMERGENCY:
-		if (s390int->parm & 0xffff0000) {
-			kfree(inti);
-			return -EINVAL;
-		}
-		VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", s390int->parm);
-		inti->type = s390int->type;
-		inti->emerg.code = s390int->parm;
-		break;
-	case KVM_S390_MCHK:
-		VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
-			   s390int->parm64);
-		inti->type = s390int->type;
-		inti->mchk.mcic = s390int->parm64;
-		break;
-	case KVM_S390_INT_VIRTIO:
-	case KVM_S390_INT_SERVICE:
-	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-	default:
-		kfree(inti);
-		return -EINVAL;
-	}
-	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, s390int->type, s390int->parm,
-				   s390int->parm64, 2);
-
-	mutex_lock(&vcpu->kvm->lock);
-	li = &vcpu->arch.local_int;
-	spin_lock_bh(&li->lock);
-	if (inti->type == KVM_S390_PROGRAM_INT)
-		list_add(&inti->list, &li->list);
-	else
-		list_add_tail(&inti->list, &li->list);
-	atomic_set(&li->active, 1);
-	if (inti->type == KVM_S390_SIGP_STOP)
-		li->action_bits |= ACTION_STOP_ON_STOP;
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
-	spin_unlock_bh(&li->lock);
-	mutex_unlock(&vcpu->kvm->lock);
-	return 0;
-}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e0676f390d57..429ca0851bfd 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -95,16 +95,12 @@ static inline int test_vfacility(unsigned long nr)
 }
 
 /* Section: not file related */
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	/* every s390 is virtualization enabled ;-) */
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
 static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);
 
 int kvm_arch_hardware_setup(void)
@@ -119,19 +115,11 @@ void kvm_arch_hardware_unsetup(void)
 	gmap_unregister_ipte_notifier(&gmap_notifier);
 }
 
-void kvm_arch_check_processor_compat(void *rtn)
-{
-}
-
 int kvm_arch_init(void *opaque)
 {
 	return 0;
 }
 
-void kvm_arch_exit(void)
-{
-}
-
 /* Section: device related */
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg)
@@ -141,7 +129,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r;
 
@@ -304,10 +292,6 @@ static void kvm_free_vcpus(struct kvm *kvm)
 	mutex_unlock(&kvm->lock);
 }
 
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
-
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvm_free_vcpus(kvm);
@@ -336,11 +320,6 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
-	/* Nothing todo */
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	save_fp_ctl(&vcpu->arch.host_fpregs.fpc);
@@ -753,7 +732,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 
 	if (rc == 0) {
 		if (kvm_is_ucontrol(vcpu->kvm))
-			rc = -EOPNOTSUPP;
+			/* Don't exit for host interrupts. */
+			rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
 		else
 			rc = kvm_handle_sie_intercept(vcpu);
 	}
@@ -1100,21 +1080,12 @@ int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
-			   struct kvm_memory_slot *dont)
-{
-}
-
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    unsigned long npages)
 {
 	return 0;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
-{
-}
-
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
@@ -1160,15 +1131,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	return;
 }
 
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
-				   struct kvm_memory_slot *slot)
-{
-}
-
 static int __init kvm_s390_init(void)
 {
 	int ret;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d261c62e40a6..248445f92604 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -223,11 +223,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmdp, int write)
 {
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ad446b0c55b6..1b30d5488f82 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -43,6 +43,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
 
 unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
+EXPORT_SYMBOL(zero_page_mask);
 
 static void __init setup_zero_pages(void)
 {
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 3584ed9b20a1..e309c5c41158 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -810,11 +810,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pte_t *ptep;
 
 	down_read(&mm->mmap_sem);
+retry:
 	ptep = get_locked_pte(current->mm, addr, &ptl);
 	if (unlikely(!ptep)) {
 		up_read(&mm->mmap_sem);
 		return -EFAULT;
 	}
+	if (!(pte_val(*ptep) & _PAGE_INVALID) &&
+	     (pte_val(*ptep) & _PAGE_PROTECT)) {
+			pte_unmap_unlock(*ptep, ptl);
+			if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) {
+				up_read(&mm->mmap_sem);
+				return -EFAULT;
+			}
+			goto retry;
+		}
 
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 708d60e40066..8e08c6712eb8 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -276,7 +276,6 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter)
 	case BPF_S_LD_W_IND:
 	case BPF_S_LD_H_IND:
 	case BPF_S_LD_B_IND:
-	case BPF_S_LDX_B_MSH:
 	case BPF_S_LD_IMM:
 	case BPF_S_LD_MEM:
 	case BPF_S_MISC_TXA:
@@ -812,7 +811,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int bpfsize,
 		return NULL;
 	memset(header, 0, sz);
 	header->pages = sz / PAGE_SIZE;
-	hole = sz - (bpfsize + sizeof(*header));
+	hole = min(sz - (bpfsize + sizeof(*header)), PAGE_SIZE - sizeof(*header));
 	/* Insert random number of illegal instructions before BPF code
 	 * and make sure the first instruction starts at an even address.
 	 */
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index 13e9966464c2..e79fb6ebaa42 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -40,15 +40,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 /* arch/sh/kernel/return_address.c */
 extern void *return_address(unsigned int);
 
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
index ff1465c0519c..5acf89c1afc5 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
@@ -118,7 +118,7 @@ static struct plat_sci_port scif0_platform_data = {
 };
 
 static struct resource scif0_resources[] = {
-	DEFINE_RES_MEM(0xfffffe80, 0x100),
+	DEFINE_RES_MEM(0xfffffe80, 0x10),
 	DEFINE_RES_IRQ(evt2irq(0x4e0)),
 };
 
@@ -143,7 +143,7 @@ static struct plat_sci_port scif1_platform_data = {
 };
 
 static struct resource scif1_resources[] = {
-	DEFINE_RES_MEM(0xa4000150, 0x100),
+	DEFINE_RES_MEM(0xa4000150, 0x10),
 	DEFINE_RES_IRQ(evt2irq(0x900)),
 };
 
@@ -169,7 +169,7 @@ static struct plat_sci_port scif2_platform_data = {
 };
 
 static struct resource scif2_resources[] = {
-	DEFINE_RES_MEM(0xa4000140, 0x100),
+	DEFINE_RES_MEM(0xa4000140, 0x10),
 	DEFINE_RES_IRQ(evt2irq(0x880)),
 };
 
diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c
index b959f5592604..8dfe645bcc4b 100644
--- a/arch/sh/kernel/dumpstack.c
+++ b/arch/sh/kernel/dumpstack.c
@@ -115,7 +115,7 @@ static int print_trace_stack(void *data, char *name)
  */
 static void print_trace_address(void *data, unsigned long addr, int reliable)
 {
-	printk(data);
+	printk("%s", (char *)data);
 	printk_address(addr, reliable);
 }
 
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 0d676a41081e..d7762349ea48 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -83,11 +83,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 0;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 7d8b7e94b93b..a38513c33a62 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -67,6 +67,7 @@ config SPARC64
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_KMEMLEAK
+	select SPARSE_IRQ
 	select RTC_DRV_CMOS
 	select RTC_DRV_BQ4802
 	select RTC_DRV_SUN4V
@@ -77,6 +78,7 @@ config SPARC64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select HAVE_C_RECORDMCOUNT
 	select NO_BOOTMEM
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 905832aa9e9e..a0ed182ae73c 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -21,7 +21,7 @@
 
 extern int __atomic_add_return(int, atomic_t *);
 extern int atomic_cmpxchg(atomic_t *, int, int);
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+extern int atomic_xchg(atomic_t *, int);
 extern int __atomic_add_unless(atomic_t *, int, int);
 extern void atomic_set(atomic_t *, int);
 
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 1fae1a02e3c2..ae0f9a7a314d 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -11,22 +11,14 @@
 #ifndef __ARCH_SPARC_CMPXCHG__
 #define __ARCH_SPARC_CMPXCHG__
 
-static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
-{
-	__asm__ __volatile__("swap [%2], %0"
-			     : "=&r" (val)
-			     : "0" (val), "r" (m)
-			     : "memory");
-	return val;
-}
-
+extern unsigned long __xchg_u32(volatile u32 *m, u32 new);
 extern void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
 	switch (size) {
 	case 4:
-		return xchg_u32(ptr, x);
+		return __xchg_u32(ptr, x);
 	}
 	__xchg_called_with_bad_pointer();
 	return x;
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index ca121f0fa3ec..17be9d618335 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2944,6 +2944,16 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 					  unsigned long reg_val);
 #endif
 
+#define	HV_FAST_T5_GET_PERFREG		0x1a8
+#define	HV_FAST_T5_SET_PERFREG		0x1a9
+
+#ifndef	__ASSEMBLY__
+unsigned long sun4v_t5_get_perfreg(unsigned long reg_num,
+				   unsigned long *reg_val);
+unsigned long sun4v_t5_set_perfreg(unsigned long reg_num,
+				   unsigned long reg_val);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2975,6 +2985,7 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 #define HV_GRP_VF_CPU			0x0205
 #define HV_GRP_KT_CPU			0x0209
 #define HV_GRP_VT_CPU			0x020c
+#define HV_GRP_T5_CPU			0x0211
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index abf6afe82ca8..3deb07ff1e00 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -37,7 +37,7 @@
  *
  * ino_bucket->irq allocation is made during {sun4v_,}build_irq().
  */
-#define NR_IRQS    255
+#define NR_IRQS		(2048)
 
 extern void irq_install_pre_handler(int irq,
 				    void (*func)(unsigned int, void *, void *),
@@ -57,11 +57,8 @@ extern unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p,
 				    unsigned long iclr_base);
 extern void sun4u_destroy_msi(unsigned int irq);
 
-extern unsigned char irq_alloc(unsigned int dev_handle,
-				    unsigned int dev_ino);
-#ifdef CONFIG_PCI_MSI
-extern void irq_free(unsigned int irq);
-#endif
+unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino);
+void irq_free(unsigned int irq);
 
 extern void __init init_IRQ(void);
 extern void fixup_irqs(void);
diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h
index bdb524a7b814..8732ed391aff 100644
--- a/arch/sparc/include/asm/ldc.h
+++ b/arch/sparc/include/asm/ldc.h
@@ -53,13 +53,14 @@ struct ldc_channel;
 /* Allocate state for a channel.  */
 extern struct ldc_channel *ldc_alloc(unsigned long id,
 				     const struct ldc_channel_config *cfgp,
-				     void *event_arg);
+				     void *event_arg,
+				     const char *name);
 
 /* Shut down and free state for a channel.  */
 extern void ldc_free(struct ldc_channel *lp);
 
 /* Register TX and RX queues of the link with the hypervisor.  */
-extern int ldc_bind(struct ldc_channel *lp, const char *name);
+extern int ldc_bind(struct ldc_channel *lp);
 
 /* For non-RAW protocols we need to complete a handshake before
  * communication can proceed.  ldc_connect() does that, if the
diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h
index a12dbe3b7762..e48fdf4e16ff 100644
--- a/arch/sparc/include/asm/oplib_64.h
+++ b/arch/sparc/include/asm/oplib_64.h
@@ -62,7 +62,8 @@ struct linux_mem_p1275 {
 /* You must call prom_init() before using any of the library services,
  * preferably as early as possible.  Pass it the romvec pointer.
  */
-extern void prom_init(void *cif_handler, void *cif_stack);
+extern void prom_init(void *cif_handler);
+extern void prom_init_report(void);
 
 /* Boot argument acquisition, returns the boot command line string. */
 extern char *prom_getbootargs(void);
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index aac53fcea807..b18e602fcac4 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -57,18 +57,21 @@ extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct pag
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long iopte; } iopte_t;
 typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pud; } pud_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
 
 #define pte_val(x)	((x).pte)
 #define iopte_val(x)	((x).iopte)
 #define pmd_val(x)      ((x).pmd)
+#define pud_val(x)      ((x).pud)
 #define pgd_val(x)	((x).pgd)
 #define pgprot_val(x)	((x).pgprot)
 
 #define __pte(x)	((pte_t) { (x) } )
 #define __iopte(x)	((iopte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
+#define __pud(x)        ((pud_t) { (x) } )
 #define __pgd(x)	((pgd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
@@ -77,18 +80,21 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 typedef unsigned long pte_t;
 typedef unsigned long iopte_t;
 typedef unsigned long pmd_t;
+typedef unsigned long pud_t;
 typedef unsigned long pgd_t;
 typedef unsigned long pgprot_t;
 
 #define pte_val(x)	(x)
 #define iopte_val(x)	(x)
 #define pmd_val(x)      (x)
+#define pud_val(x)      (x)
 #define pgd_val(x)	(x)
 #define pgprot_val(x)	(x)
 
 #define __pte(x)	(x)
 #define __iopte(x)	(x)
 #define __pmd(x)        (x)
+#define __pud(x)        (x)
 #define __pgd(x)	(x)
 #define __pgprot(x)	(x)
 
@@ -96,21 +102,14 @@ typedef unsigned long pgprot_t;
 
 typedef pte_t *pgtable_t;
 
-/* These two values define the virtual address space range in which we
- * must forbid 64-bit user processes from making mappings.  It used to
- * represent precisely the virtual address space hole present in most
- * early sparc64 chips including UltraSPARC-I.  But now it also is
- * further constrained by the limits of our page tables, which is
- * 43-bits of virtual address.
- */
-#define SPARC64_VA_HOLE_TOP	_AC(0xfffffc0000000000,UL)
-#define SPARC64_VA_HOLE_BOTTOM	_AC(0x0000040000000000,UL)
+extern unsigned long sparc64_va_hole_top;
+extern unsigned long sparc64_va_hole_bottom;
 
 /* The next two defines specify the actual exclusion region we
  * enforce, wherein we use a 4GB red zone on each side of the VA hole.
  */
-#define VA_EXCLUDE_START (SPARC64_VA_HOLE_BOTTOM - (1UL << 32UL))
-#define VA_EXCLUDE_END   (SPARC64_VA_HOLE_TOP + (1UL << 32UL))
+#define VA_EXCLUDE_START (sparc64_va_hole_bottom - (1UL << 32UL))
+#define VA_EXCLUDE_END   (sparc64_va_hole_top + (1UL << 32UL))
 
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_32BIT) ? \
 				 _AC(0x0000000070000000,UL) : \
@@ -118,20 +117,16 @@ typedef pte_t *pgtable_t;
 
 #include <asm-generic/memory_model.h>
 
-#define PAGE_OFFSET_BY_BITS(X)	(-(_AC(1,UL) << (X)))
 extern unsigned long PAGE_OFFSET;
 
 #endif /* !(__ASSEMBLY__) */
 
-/* The maximum number of physical memory address bits we support, this
- * is used to size various tables used to manage kernel TLB misses and
- * also the sparsemem code.
+/* The maximum number of physical memory address bits we support.  The
+ * largest value we can support is whatever "KPGD_SHIFT + KPTE_BITS"
+ * evaluates to.
  */
-#define MAX_PHYS_ADDRESS_BITS	47
+#define MAX_PHYS_ADDRESS_BITS	53
 
-/* These two shift counts are used when indexing sparc64_valid_addr_bitmap
- * and kpte_linear_bitmap.
- */
 #define ILOG2_4MB		22
 #define ILOG2_256MB		28
 
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index bcfe063bce23..2c8d41fb13a4 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -15,6 +15,13 @@
 
 extern struct kmem_cache *pgtable_cache;
 
+static inline void __pgd_populate(pgd_t *pgd, pud_t *pud)
+{
+	pgd_set(pgd, pud);
+}
+
+#define pgd_populate(MM, PGD, PUD)	__pgd_populate(PGD, PUD)
+
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
@@ -25,7 +32,23 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	kmem_cache_free(pgtable_cache, pgd);
 }
 
-#define pud_populate(MM, PUD, PMD)	pud_set(PUD, PMD)
+static inline void __pud_populate(pud_t *pud, pmd_t *pmd)
+{
+	pud_set(pud, pmd);
+}
+
+#define pud_populate(MM, PUD, PMD)	__pud_populate(PUD, PMD)
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return kmem_cache_alloc(pgtable_cache,
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	kmem_cache_free(pgtable_cache, pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -91,4 +114,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pte_t *pte,
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
 	pgtable_free_tlb(tlb, pmd, false)
 
+#define __pud_free_tlb(tlb, pud, addr)		      \
+	pgtable_free_tlb(tlb, pud, false)
+
 #endif /* _SPARC64_PGALLOC_H */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 0f9e94537eee..e8dfabf156c7 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -20,11 +20,10 @@
 #include <asm/page.h>
 #include <asm/processor.h>
 
-#include <asm-generic/pgtable-nopud.h>
-
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
  * The page copy blockops can use 0x6000000 to 0x8000000.
- * The TSB is mapped in the 0x8000000 to 0xa000000 range.
+ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
+ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range.
  * The PROM resides in an area spanning 0xf0000000 to 0x100000000.
  * The vmalloc area spans 0x100000000 to 0x200000000.
  * Since modules need to be in the lowest 32-bits of the address space,
@@ -33,17 +32,15 @@
  * 0x400000000.
  */
 #define	TLBTEMP_BASE		_AC(0x0000000006000000,UL)
-#define	TSBMAP_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_8K_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_4M_BASE		_AC(0x0000000008400000,UL)
 #define MODULES_VADDR		_AC(0x0000000010000000,UL)
 #define MODULES_LEN		_AC(0x00000000e0000000,UL)
 #define MODULES_END		_AC(0x00000000f0000000,UL)
 #define LOW_OBP_ADDRESS		_AC(0x00000000f0000000,UL)
 #define HI_OBP_ADDRESS		_AC(0x0000000100000000,UL)
 #define VMALLOC_START		_AC(0x0000000100000000,UL)
-#define VMALLOC_END		_AC(0x0000010000000000,UL)
-#define VMEMMAP_BASE		_AC(0x0000010000000000,UL)
-
-#define vmemmap			((struct page *)VMEMMAP_BASE)
+#define VMEMMAP_BASE		VMALLOC_END
 
 /* PMD_SHIFT determines the size of the area a second-level page
  * table can map
@@ -53,13 +50,25 @@
 #define PMD_MASK	(~(PMD_SIZE-1))
 #define PMD_BITS	(PAGE_SHIFT - 3)
 
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + (PAGE_SHIFT-3) + PMD_BITS)
+/* PUD_SHIFT determines the size of the area a third-level page
+ * table can map
+ */
+#define PUD_SHIFT	(PMD_SHIFT + PMD_BITS)
+#define PUD_SIZE	(_AC(1,UL) << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+#define PUD_BITS	(PAGE_SHIFT - 3)
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT	(PUD_SHIFT + PUD_BITS)
 #define PGDIR_SIZE	(_AC(1,UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 #define PGDIR_BITS	(PAGE_SHIFT - 3)
 
-#if (PGDIR_SHIFT + PGDIR_BITS) != 43
+#if (MAX_PHYS_ADDRESS_BITS > PGDIR_SHIFT + PGDIR_BITS)
+#error MAX_PHYS_ADDRESS_BITS exceeds what kernel page tables can support
+#endif
+
+#if (PGDIR_SHIFT + PGDIR_BITS) != 53
 #error Page table parameters do not cover virtual address space properly.
 #endif
 
@@ -69,19 +78,32 @@
 
 #ifndef __ASSEMBLY__
 
+extern unsigned long VMALLOC_END;
+
+#define vmemmap			((struct page *)VMEMMAP_BASE)
+
 #include <linux/sched.h>
 
+bool kern_addr_valid(unsigned long addr);
+
 /* Entries per page directory level. */
 #define PTRS_PER_PTE	(1UL << (PAGE_SHIFT-3))
 #define PTRS_PER_PMD	(1UL << PMD_BITS)
+#define PTRS_PER_PUD	(1UL << PUD_BITS)
 #define PTRS_PER_PGD	(1UL << PGDIR_BITS)
 
 /* Kernel has a separate 44bit address space. */
 #define FIRST_USER_ADDRESS	0
 
-#define pte_ERROR(e)	__builtin_trap()
-#define pmd_ERROR(e)	__builtin_trap()
-#define pgd_ERROR(e)	__builtin_trap()
+#define pmd_ERROR(e)							\
+	pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n",		\
+	       __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0))
+#define pud_ERROR(e)							\
+	pr_err("%s:%d: bad pud %p(%016lx) seen at (%pS)\n",		\
+	       __FILE__, __LINE__, &(e), pud_val(e), __builtin_return_address(0))
+#define pgd_ERROR(e)							\
+	pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n",		\
+	       __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0))
 
 #endif /* !(__ASSEMBLY__) */
 
@@ -90,6 +112,7 @@
 #define _PAGE_R	  	  _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/
 #define _PAGE_SPECIAL     _AC(0x0200000000000000,UL) /* Special page         */
 #define _PAGE_PMD_HUGE    _AC(0x0100000000000000,UL) /* Huge page            */
+#define _PAGE_PUD_HUGE    _PAGE_PMD_HUGE
 
 /* Advertise support for _PAGE_SPECIAL */
 #define __HAVE_ARCH_PTE_SPECIAL
@@ -258,8 +281,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
 {
 	unsigned long mask, tmp;
 
-	/* SUN4U: 0x600307ffffffecb8 (negated == 0x9ffcf80000001347)
-	 * SUN4V: 0x30ffffffffffee17 (negated == 0xcf000000000011e8)
+	/* SUN4U: 0x630107ffffffec38 (negated == 0x9cfef800000013c7)
+	 * SUN4V: 0x33ffffffffffee07 (negated == 0xcc000000000011f8)
 	 *
 	 * Even if we use negation tricks the result is still a 6
 	 * instruction sequence, so don't try to play fancy and just
@@ -289,10 +312,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
 	"	.previous\n"
 	: "=r" (mask), "=r" (tmp)
 	: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
-	       _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U |
+	       _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
 	  "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
-	       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V |
+	       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
 
 	return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -633,29 +656,29 @@ static inline unsigned long pmd_large(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return (pte_val(pte) & _PAGE_PMD_HUGE) && pte_present(pte);
+	return pte_val(pte) & _PAGE_PMD_HUGE;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_young(pmd_t pmd)
+static inline unsigned long pmd_pfn(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_young(pte);
+	return pte_pfn(pte);
 }
 
-static inline unsigned long pmd_write(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_write(pte);
+	return pte_young(pte);
 }
 
-static inline unsigned long pmd_pfn(pmd_t pmd)
+static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_pfn(pte);
+	return pte_write(pte);
 }
 
 static inline unsigned long pmd_trans_huge(pmd_t pmd)
@@ -719,20 +742,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
-	unsigned long mask;
-
-	if (tlb_type == hypervisor)
-		mask = _PAGE_PRESENT_4V;
-	else
-		mask = _PAGE_PRESENT_4U;
-
-	pmd_val(pmd) &= ~mask;
-
-	return pmd;
-}
-
 static inline pmd_t pmd_mksplitting(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
@@ -757,6 +766,22 @@ static inline int pmd_present(pmd_t pmd)
 
 #define pmd_none(pmd)			(!pmd_val(pmd))
 
+/* pmd_bad() is only called on non-trans-huge PMDs.  Our encoding is
+ * very simple, it's just the physical address.  PTE tables are of
+ * size PAGE_SIZE so make sure the sub-PAGE_SIZE bits are clear and
+ * the top bits outside of the range of any physical address size we
+ * support are clear as well.  We also validate the physical itself.
+ */
+#define pmd_bad(pmd)			(pmd_val(pmd) & ~PAGE_MASK)
+
+#define pud_none(pud)			(!pud_val(pud))
+
+#define pud_bad(pud)			(pud_val(pud) & ~PAGE_MASK)
+
+#define pgd_none(pgd)			(!pgd_val(pgd))
+
+#define pgd_bad(pgd)			(pgd_val(pgd) & ~PAGE_MASK)
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t pmd);
@@ -790,16 +815,34 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 #define pud_page_vaddr(pud)		\
 	((unsigned long) __va(pud_val(pud)))
 #define pud_page(pud) 			virt_to_page((void *)pud_page_vaddr(pud))
-#define pmd_bad(pmd)			(0)
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
-#define pud_none(pud)			(!pud_val(pud))
-#define pud_bad(pud)			(0)
 #define pud_present(pud)		(pud_val(pud) != 0U)
 #define pud_clear(pudp)			(pud_val(*(pudp)) = 0UL)
+#define pgd_page_vaddr(pgd)		\
+	((unsigned long) __va(pgd_val(pgd)))
+#define pgd_present(pgd)		(pgd_val(pgd) != 0U)
+#define pgd_clear(pgdp)			(pgd_val(*(pgd)) = 0UL)
+
+static inline unsigned long pud_large(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+
+	return pte_val(pte) & _PAGE_PMD_HUGE;
+}
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+
+	return pte_pfn(pte);
+}
 
 /* Same in both SUN4V and SUN4U.  */
 #define pte_none(pte) 			(!pte_val(pte))
 
+#define pgd_set(pgdp, pudp)	\
+	(pgd_val(*(pgdp)) = (__pa((unsigned long) (pudp))))
+
 /* to find an entry in a page-table-directory. */
 #define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
 #define pgd_offset(mm, address)	((mm)->pgd + pgd_index(address))
@@ -807,6 +850,11 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
+/* Find an entry in the third-level page table.. */
+#define pud_index(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+#define pud_offset(pgdp, address)	\
+	((pud_t *) pgd_page_vaddr(*(pgdp)) + pud_index(address))
+
 /* Find an entry in the second-level page table.. */
 #define pmd_offset(pudp, address)	\
 	((pmd_t *) pud_page_vaddr(*(pudp)) + \
@@ -879,7 +927,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 #endif
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD];
 
 extern void paging_init(void);
 extern unsigned long find_ecache_flush_span(unsigned long size);
@@ -893,6 +940,10 @@ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 				 pmd_t *pmd);
 
+#define __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				       pgtable_t pgtable);
@@ -919,18 +970,6 @@ extern unsigned long pte_file(pte_t);
 extern pte_t pgoff_to_pte(unsigned long);
 #define PTE_FILE_MAX_BITS	(64UL - PAGE_SHIFT - 1UL)
 
-extern unsigned long sparc64_valid_addr_bitmap[];
-
-/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-static inline bool kern_addr_valid(unsigned long addr)
-{
-	unsigned long paddr = __pa(addr);
-
-	if ((paddr >> 41UL) != 0UL)
-		return false;
-	return test_bit(paddr >> 22, sparc64_valid_addr_bitmap);
-}
-
 extern int page_in_phys_avail(unsigned long paddr);
 
 /*
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index 5e35e0517318..acd614668ec1 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -24,6 +24,10 @@ static inline int con_is_present(void)
 }
 #endif
 
+#ifdef CONFIG_SPARC64
+extern void __init start_early_boot(void);
+#endif
+
 extern void sun_do_break(void);
 extern int stop_a_enabled;
 extern int scons_pwroff;
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 6b67e50fb9b4..69424d48cbb7 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -45,6 +45,8 @@
 #define SUN4V_CHIP_NIAGARA3	0x03
 #define SUN4V_CHIP_NIAGARA4	0x04
 #define SUN4V_CHIP_NIAGARA5	0x05
+#define SUN4V_CHIP_SPARC_M6	0x06
+#define SUN4V_CHIP_SPARC_M7	0x07
 #define SUN4V_CHIP_SPARC64X	0x8a
 #define SUN4V_CHIP_UNKNOWN	0xff
 
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index a5f01ac6d0f1..cc6275c931a5 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -63,7 +63,8 @@ struct thread_info {
 	struct pt_regs		*kern_una_regs;
 	unsigned int		kern_una_insn;
 
-	unsigned long		fpregs[0] __attribute__ ((aligned(64)));
+	unsigned long		fpregs[(7 * 256) / sizeof(unsigned long)]
+		__attribute__ ((aligned(64)));
 };
 
 #endif /* !(__ASSEMBLY__) */
@@ -102,6 +103,7 @@ struct thread_info {
 #define FAULT_CODE_ITLB		0x04	/* Miss happened in I-TLB	   */
 #define FAULT_CODE_WINFIXUP	0x08	/* Miss happened during spill/fill */
 #define FAULT_CODE_BLKCOMMIT	0x10	/* Use blk-commit ASI in copy_page */
+#define	FAULT_CODE_BAD_RA	0x20	/* Bad RA for sun4v		   */
 
 #if PAGE_SHIFT == 13
 #define THREAD_SIZE (2*PAGE_SIZE)
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 3c3c89f52643..7f9bab26a499 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -34,6 +34,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 {
 }
 
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
 #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
 extern void flush_tlb_pending(void);
@@ -48,11 +50,6 @@ extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
 
-#define flush_tlb_kernel_range(start,end) \
-do {	flush_tsb_kernel_range(start,end); \
-	__flush_tlb_kernel_range(start,end); \
-} while (0)
-
 static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
 {
 	__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
@@ -63,11 +60,6 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
-#define flush_tlb_kernel_range(start, end) \
-do {	flush_tsb_kernel_range(start,end); \
-	smp_flush_tlb_kernel_range(start, end); \
-} while (0)
-
 #define global_flush_tlb_page(mm, vaddr) \
 	smp_flush_tlb_page(mm, vaddr)
 
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 2230f80d9fe3..ecb49cfa3be9 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -133,9 +133,24 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	sub	TSB, 0x8, TSB;   \
 	TSB_STORE(TSB, TAG);
 
-	/* Do a kernel page table walk.  Leaves physical PTE pointer in
-	 * REG1.  Jumps to FAIL_LABEL on early page table walk termination.
-	 * VADDR will not be clobbered, but REG2 will.
+	/* Do a kernel page table walk.  Leaves valid PTE value in
+	 * REG1.  Jumps to FAIL_LABEL on early page table walk
+	 * termination.  VADDR will not be clobbered, but REG2 will.
+	 *
+	 * There are two masks we must apply to propagate bits from
+	 * the virtual address into the PTE physical address field
+	 * when dealing with huge pages.  This is because the page
+	 * table boundaries do not match the huge page size(s) the
+	 * hardware supports.
+	 *
+	 * In these cases we propagate the bits that are below the
+	 * page table level where we saw the huge page mapping, but
+	 * are still within the relevant physical bits for the huge
+	 * page size in question.  So for PMD mappings (which fall on
+	 * bit 23, for 8MB per PMD) we must propagate bit 22 for a
+	 * 4MB huge page.  For huge PUDs (which fall on bit 33, for
+	 * 8GB per PUD), we have to accomodate 256MB and 2GB huge
+	 * pages.  So for those we propagate bits 32 to 28.
 	 */
 #define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL)	\
 	sethi		%hi(swapper_pg_dir), REG1; \
@@ -145,15 +160,40 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	ldx		[REG1 + REG2], REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
-	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
+	 sllx		VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
 	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
-	 sllx		VADDR, 64 - PMD_SHIFT, REG2; \
+	sethi		%uhi(_PAGE_PUD_HUGE), REG2; \
+	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		REG2, 32, REG2; \
+	andcc		REG1, REG2, %g0; \
+	sethi		%hi(0xf8000000), REG2; \
+	bne,pt		%xcc, 697f; \
+	 sllx		REG2, 1, REG2; \
+	sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
-	add		REG1, REG2, REG1;
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	sethi		%uhi(_PAGE_PMD_HUGE), REG2; \
+	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		REG2, 32, REG2; \
+	andcc		REG1, REG2, %g0; \
+	be,pn		%xcc, 698f; \
+	 sethi		%hi(0x400000), REG2; \
+697:	brgez,pn	REG1, FAIL_LABEL; \
+	 andn		REG1, REG2, REG1; \
+	and		VADDR, REG2, REG2; \
+	ba,pt		%xcc, 699f; \
+	 or		REG1, REG2, REG1; \
+698:	sllx		VADDR, 64 - PMD_SHIFT, REG2; \
+	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
+	andn		REG2, 0x7, REG2; \
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	brgez,pn	REG1, FAIL_LABEL; \
+	 nop; \
+699:
 
 	/* PMD has been loaded into REG1, interpret the value, seeing
 	 * if it is a HUGE PMD or a normal one.  If it is not valid
@@ -171,7 +211,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andcc		REG1, REG2, %g0;		\
 	be,pt		%xcc, 700f;			\
 	 sethi		%hi(4 * 1024 * 1024), REG2;	\
-	andn		REG1, REG2, REG1;		\
+	brgez,pn	REG1, FAIL_LABEL;		\
+	 andn		REG1, REG2, REG1;		\
 	and		VADDR, REG2, REG2;		\
 	brlz,pt		REG1, PTE_LABEL;		\
 	 or		REG1, REG2, REG1;		\
@@ -197,6 +238,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	ldxa		[PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \
+	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
+	andn		REG2, 0x7, REG2; \
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	brz,pn		REG1, FAIL_LABEL; \
 	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
@@ -245,8 +291,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	(KERNEL_TSB_SIZE_BYTES / 16)
 #define KERNEL_TSB4M_NENTRIES	4096
 
-#define KTSB_PHYS_SHIFT		15
-
 	/* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL
 	 * on TSB hit.  REG1, REG2, REG3, and REG4 are used as temporaries
 	 * and the found TTE will be left in REG1.  REG3 and REG4 must
@@ -255,17 +299,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * VADDR and TAG will be preserved and not clobbered by this macro.
 	 */
 #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-661:	sethi		%hi(swapper_tsb), REG1;			\
-	or		REG1, %lo(swapper_tsb), REG1; \
+661:	sethi		%uhi(swapper_tsb), REG1; \
+	sethi		%hi(swapper_tsb), REG2; \
+	or		REG1, %ulo(swapper_tsb), REG1; \
+	or		REG2, %lo(swapper_tsb), REG2; \
 	.section	.swapper_tsb_phys_patch, "ax"; \
 	.word		661b; \
 	.previous; \
-661:	nop; \
-	.section	.tsb_ldquad_phys_patch, "ax"; \
-	.word		661b; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	.previous; \
+	sllx		REG1, 32, REG1; \
+	or		REG1, REG2, REG1; \
 	srlx		VADDR, PAGE_SHIFT, REG2; \
 	and		REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
@@ -280,17 +322,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * we can make use of that for the index computation.
 	 */
 #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-661:	sethi		%hi(swapper_4m_tsb), REG1;	     \
-	or		REG1, %lo(swapper_4m_tsb), REG1; \
+661:	sethi		%uhi(swapper_4m_tsb), REG1; \
+	sethi		%hi(swapper_4m_tsb), REG2; \
+	or		REG1, %ulo(swapper_4m_tsb), REG1; \
+	or		REG2, %lo(swapper_4m_tsb), REG2; \
 	.section	.swapper_4m_tsb_phys_patch, "ax"; \
 	.word		661b; \
 	.previous; \
-661:	nop; \
-	.section	.tsb_ldquad_phys_patch, "ax"; \
-	.word		661b; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	.previous; \
+	sllx		REG1, 32, REG1; \
+	or		REG1, REG2, REG1; \
 	and		TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 432afa838861..55841c184e6d 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -118,12 +118,18 @@ struct vio_disk_attr_info {
 	u8			vdisk_type;
 #define VD_DISK_TYPE_SLICE	0x01 /* Slice in block device	*/
 #define VD_DISK_TYPE_DISK	0x02 /* Entire block device	*/
-	u16			resv1;
+	u8			vdisk_mtype;		/* v1.1 */
+#define VD_MEDIA_TYPE_FIXED	0x01 /* Fixed device */
+#define VD_MEDIA_TYPE_CD	0x02 /* CD Device    */
+#define VD_MEDIA_TYPE_DVD	0x03 /* DVD Device   */
+	u8			resv1;
 	u32			vdisk_block_size;
 	u64			operations;
-	u64			vdisk_size;
+	u64			vdisk_size;		/* v1.1 */
 	u64			max_xfer_size;
-	u64			resv2[2];
+	u32			phys_block_size;	/* v1.2 */
+	u32			resv2;
+	u64			resv3[1];
 };
 
 struct vio_disk_desc {
@@ -259,7 +265,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr,
 				  unsigned int ring_size)
 {
 	return (dr->pending -
-		((dr->prod - dr->cons) & (ring_size - 1)));
+		((dr->prod - dr->cons) & (ring_size - 1)) - 1);
 }
 
 #define VIO_MAX_TYPE_LEN	32
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 39ca301920db..11fdf0ef50bb 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -39,6 +39,14 @@
 297:	wr		%o5, FPRS_FEF, %fprs;		\
 298:
 
+#define VISEntryHalfFast(fail_label)			\
+	rd		%fprs, %o5;			\
+	andcc		%o5, FPRS_FEF, %g0;		\
+	be,pt		%icc, 297f;			\
+	 nop;						\
+	ba,a,pt		%xcc, fail_label;		\
+297:	wr		%o5, FPRS_FEF, %fprs;
+
 #define VISExitHalf					\
 	wr		%o5, 0, %fprs;
 
diff --git a/arch/sparc/include/uapi/asm/swab.h b/arch/sparc/include/uapi/asm/swab.h
index a34ad079487e..4c7c12d69bea 100644
--- a/arch/sparc/include/uapi/asm/swab.h
+++ b/arch/sparc/include/uapi/asm/swab.h
@@ -9,9 +9,9 @@ static inline __u16 __arch_swab16p(const __u16 *addr)
 {
 	__u16 ret;
 
-	__asm__ __volatile__ ("lduha [%1] %2, %0"
+	__asm__ __volatile__ ("lduha [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab16p __arch_swab16p
@@ -20,9 +20,9 @@ static inline __u32 __arch_swab32p(const __u32 *addr)
 {
 	__u32 ret;
 
-	__asm__ __volatile__ ("lduwa [%1] %2, %0"
+	__asm__ __volatile__ ("lduwa [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab32p __arch_swab32p
@@ -31,9 +31,9 @@ static inline __u64 __arch_swab64p(const __u64 *addr)
 {
 	__u64 ret;
 
-	__asm__ __volatile__ ("ldxa [%1] %2, %0"
+	__asm__ __volatile__ ("ldxa [%2] %3, %0"
 			      : "=r" (ret)
-			      : "r" (addr), "i" (ASI_PL));
+			      : "m" (*addr), "r" (addr), "i" (ASI_PL));
 	return ret;
 }
 #define __arch_swab64p __arch_swab64p
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 5c5125895db8..52e10defedc4 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -493,6 +493,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara5";
 		break;
 
+	case SUN4V_CHIP_SPARC_M6:
+		sparc_cpu_type = "SPARC-M6";
+		sparc_fpu_type = "SPARC-M6 integrated FPU";
+		sparc_pmu_type = "sparc-m6";
+		break;
+
+	case SUN4V_CHIP_SPARC_M7:
+		sparc_cpu_type = "SPARC-M7";
+		sparc_fpu_type = "SPARC-M7 integrated FPU";
+		sparc_pmu_type = "sparc-m7";
+		break;
+
 	case SUN4V_CHIP_SPARC64X:
 		sparc_cpu_type = "SPARC64-X";
 		sparc_fpu_type = "SPARC64-X integrated FPU";
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index de1c844dfabc..e69ec0e3f155 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -326,6 +326,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA3:
 	case SUN4V_CHIP_NIAGARA4:
 	case SUN4V_CHIP_NIAGARA5:
+	case SUN4V_CHIP_SPARC_M6:
+	case SUN4V_CHIP_SPARC_M7:
 	case SUN4V_CHIP_SPARC64X:
 		rover_inc_table = niagara_iterate_method;
 		break;
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index dff60abbea01..f87a55d77094 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1200,14 +1200,14 @@ static int ds_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	ds_cfg.tx_irq = vdev->tx_irq;
 	ds_cfg.rx_irq = vdev->rx_irq;
 
-	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp);
+	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp, "DS");
 	if (IS_ERR(lp)) {
 		err = PTR_ERR(lp);
 		goto out_free_ds_states;
 	}
 	dp->lp = lp;
 
-	err = ldc_bind(lp, "DS");
+	err = ldc_bind(lp);
 	if (err)
 		goto out_free_ldc;
 
diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S
index b2c2c5be281c..d668ca149e64 100644
--- a/arch/sparc/kernel/dtlb_prot.S
+++ b/arch/sparc/kernel/dtlb_prot.S
@@ -24,11 +24,11 @@
 	mov		TLB_TAG_ACCESS, %g4		! For reload of vaddr
 
 /* PROT ** ICACHE line 2: More real fault processing */
+	ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
 	bgu,pn		%xcc, winfix_trampoline		! Yes, perform winfixup
-	 ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
-	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
 	 mov		FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
-	nop
+	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
+	 nop
 	nop
 	nop
 	nop
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 140966fbd303..c88ffb9ee482 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -66,13 +66,10 @@ struct pause_patch_entry {
 extern struct pause_patch_entry __pause_3insn_patch,
 	__pause_3insn_patch_end;
 
-extern void __init per_cpu_patch(void);
 extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
 				    struct sun4v_1insn_patch_entry *);
 extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
 				    struct sun4v_2insn_patch_entry *);
-extern void __init sun4v_patch(void);
-extern void __init boot_cpu_id_too_large(int cpu);
 extern unsigned int dcache_parity_tl1_occurred;
 extern unsigned int icache_parity_tl1_occurred;
 
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 26b706a1867d..3d61fcae7ee3 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -282,8 +282,8 @@ sun4v_chip_type:
 	stx	%l2, [%l4 + 0x0]
 	ldx	[%sp + 2047 + 128 + 0x50], %l3	! physaddr low
 	/* 4MB align */
-	srlx	%l3, 22, %l3
-	sllx	%l3, 22, %l3
+	srlx	%l3, ILOG2_4MB, %l3
+	sllx	%l3, ILOG2_4MB, %l3
 	stx	%l3, [%l4 + 0x8]
 
 	/* Leave service as-is, "call-method" */
@@ -427,6 +427,12 @@ sun4v_chip_type:
 	cmp	%g2, '5'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA5, %g4
+	cmp	%g2, '6'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M6, %g4
+	cmp	%g2, '7'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M7, %g4
 	ba,pt	%xcc, 49f
 	 nop
 
@@ -585,6 +591,12 @@ niagara_tlb_fixup:
 	cmp	%g1, SUN4V_CHIP_NIAGARA5
 	be,pt	%xcc, niagara4_patch
 	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M6
+	be,pt	%xcc, niagara4_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M7
+	be,pt	%xcc, niagara4_patch
+	 nop
 
 	call	generic_patch_copyops
 	 nop
@@ -660,14 +672,12 @@ tlb_fixup_done:
 	sethi	%hi(init_thread_union), %g6
 	or	%g6, %lo(init_thread_union), %g6
 	ldx	[%g6 + TI_TASK], %g4
-	mov	%sp, %l6
 
 	wr	%g0, ASI_P, %asi
 	mov	1, %g1
 	sllx	%g1, THREAD_SHIFT, %g1
 	sub	%g1, (STACKFRAME_SZ + STACK_BIAS), %g1
 	add	%g6, %g1, %sp
-	mov	0, %fp
 
 	/* Set per-cpu pointer initially to zero, this makes
 	 * the boot-cpu use the in-kernel-image per-cpu areas
@@ -694,44 +704,14 @@ tlb_fixup_done:
 	 nop
 #endif
 
-	mov	%l6, %o1			! OpenPROM stack
 	call	prom_init
 	 mov	%l7, %o0			! OpenPROM cif handler
 
-	/* Initialize current_thread_info()->cpu as early as possible.
-	 * In order to do that accurately we have to patch up the get_cpuid()
-	 * assembler sequences.  And that, in turn, requires that we know
-	 * if we are on a Starfire box or not.  While we're here, patch up
-	 * the sun4v sequences as well.
+	/* To create a one-register-window buffer between the kernel's
+	 * initial stack and the last stack frame we use from the firmware,
+	 * do the rest of the boot from a C helper function.
 	 */
-	call	check_if_starfire
-	 nop
-	call	per_cpu_patch
-	 nop
-	call	sun4v_patch
-	 nop
-
-#ifdef CONFIG_SMP
-	call	hard_smp_processor_id
-	 nop
-	cmp	%o0, NR_CPUS
-	blu,pt	%xcc, 1f
-	 nop
-	call	boot_cpu_id_too_large
-	 nop
-	/* Not reached... */
-
-1:
-#else
-	mov	0, %o0
-#endif
-	sth	%o0, [%g6 + TI_CPU]
-
-	call	prom_init_report
-	 nop
-
-	/* Off we go.... */
-	call	start_kernel
+	call	start_early_boot
 	 nop
 	/* Not reached... */
 
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index c0a2de0fd624..5c55145bfbf0 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -46,6 +46,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_VF_CPU,				},
 	{ .group = HV_GRP_KT_CPU,				},
 	{ .group = HV_GRP_VT_CPU,				},
+	{ .group = HV_GRP_T5_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
 };
 
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index f3ab509b76a8..caedf8320416 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -821,3 +821,19 @@ ENTRY(sun4v_vt_set_perfreg)
 	retl
 	 nop
 ENDPROC(sun4v_vt_set_perfreg)
+
+ENTRY(sun4v_t5_get_perfreg)
+	mov	%o1, %o4
+	mov	HV_FAST_T5_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+ENDPROC(sun4v_t5_get_perfreg)
+
+ENTRY(sun4v_t5_set_perfreg)
+	mov	HV_FAST_T5_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_t5_set_perfreg)
diff --git a/arch/sparc/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S
index b7ddcdd1dea9..cdbfec299f2f 100644
--- a/arch/sparc/kernel/hvtramp.S
+++ b/arch/sparc/kernel/hvtramp.S
@@ -109,7 +109,6 @@ hv_cpu_startup:
 	sllx		%g5, THREAD_SHIFT, %g5
 	sub		%g5, (STACKFRAME_SZ + STACK_BIAS), %g5
 	add		%g6, %g5, %sp
-	mov		0, %fp
 
 	call		init_irqwork_curcpu
 	 nop
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index e7e215dfa866..c2d81ad62e78 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -278,7 +278,8 @@ static void *sbus_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	if ((va = __get_free_pages(GFP_KERNEL|__GFP_COMP, order)) == 0)
+	va = __get_free_pages(gfp, order);
+	if (va == 0)
 		goto err_nopages;
 
 	if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL)
@@ -443,7 +444,7 @@ static void *pci32_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	va = (void *) __get_free_pages(GFP_KERNEL, order);
+	va = (void *) __get_free_pages(gfp, order);
 	if (va == NULL) {
 		printk("pci_alloc_consistent: no %ld pages\n", len_total>>PAGE_SHIFT);
 		goto err_nopages;
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 666193f4e8bb..4033c23bdfa6 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -47,8 +47,6 @@
 #include "cpumap.h"
 #include "kstack.h"
 
-#define NUM_IVECS	(IMAP_INR + 1)
-
 struct ino_bucket *ivector_table;
 unsigned long ivector_table_pa;
 
@@ -107,55 +105,196 @@ static void bucket_set_irq(unsigned long bucket_pa, unsigned int irq)
 
 #define irq_work_pa(__cpu)	&(trap_block[(__cpu)].irq_worklist_pa)
 
-static struct {
-	unsigned int dev_handle;
-	unsigned int dev_ino;
-	unsigned int in_use;
-} irq_table[NR_IRQS];
-static DEFINE_SPINLOCK(irq_alloc_lock);
+static unsigned long hvirq_major __initdata;
+static int __init early_hvirq_major(char *p)
+{
+	int rc = kstrtoul(p, 10, &hvirq_major);
+
+	return rc;
+}
+early_param("hvirq", early_hvirq_major);
+
+static int hv_irq_version;
+
+/* Major version 2.0 of HV_GRP_INTR added support for the VIRQ cookie
+ * based interfaces, but:
+ *
+ * 1) Several OSs, Solaris and Linux included, use them even when only
+ *    negotiating version 1.0 (or failing to negotiate at all).  So the
+ *    hypervisor has a workaround that provides the VIRQ interfaces even
+ *    when only verion 1.0 of the API is in use.
+ *
+ * 2) Second, and more importantly, with major version 2.0 these VIRQ
+ *    interfaces only were actually hooked up for LDC interrupts, even
+ *    though the Hypervisor specification clearly stated:
+ *
+ *	The new interrupt API functions will be available to a guest
+ *	when it negotiates version 2.0 in the interrupt API group 0x2. When
+ *	a guest negotiates version 2.0, all interrupt sources will only
+ *	support using the cookie interface, and any attempt to use the
+ *	version 1.0 interrupt APIs numbered 0xa0 to 0xa6 will result in the
+ *	ENOTSUPPORTED error being returned.
+ *
+ *   with an emphasis on "all interrupt sources".
+ *
+ * To correct this, major version 3.0 was created which does actually
+ * support VIRQs for all interrupt sources (not just LDC devices).  So
+ * if we want to move completely over the cookie based VIRQs we must
+ * negotiate major version 3.0 or later of HV_GRP_INTR.
+ */
+static bool sun4v_cookie_only_virqs(void)
+{
+	if (hv_irq_version >= 3)
+		return true;
+	return false;
+}
 
-unsigned char irq_alloc(unsigned int dev_handle, unsigned int dev_ino)
+static void __init irq_init_hv(void)
 {
-	unsigned long flags;
-	unsigned char ent;
+	unsigned long hv_error, major, minor = 0;
+
+	if (tlb_type != hypervisor)
+		return;
 
-	BUILD_BUG_ON(NR_IRQS >= 256);
+	if (hvirq_major)
+		major = hvirq_major;
+	else
+		major = 3;
 
-	spin_lock_irqsave(&irq_alloc_lock, flags);
+	hv_error = sun4v_hvapi_register(HV_GRP_INTR, major, &minor);
+	if (!hv_error)
+		hv_irq_version = major;
+	else
+		hv_irq_version = 1;
 
-	for (ent = 1; ent < NR_IRQS; ent++) {
-		if (!irq_table[ent].in_use)
+	pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n",
+		hv_irq_version,
+		sun4v_cookie_only_virqs() ? "enabled" : "disabled");
+}
+
+/* This function is for the timer interrupt.*/
+int __init arch_probe_nr_irqs(void)
+{
+	return 1;
+}
+
+#define DEFAULT_NUM_IVECS	(0xfffU)
+static unsigned int nr_ivec = DEFAULT_NUM_IVECS;
+#define NUM_IVECS (nr_ivec)
+
+static unsigned int __init size_nr_ivec(void)
+{
+	if (tlb_type == hypervisor) {
+		switch (sun4v_chip_type) {
+		/* Athena's devhandle|devino is large.*/
+		case SUN4V_CHIP_SPARC64X:
+			nr_ivec = 0xffff;
 			break;
+		}
 	}
-	if (ent >= NR_IRQS) {
-		printk(KERN_ERR "IRQ: Out of virtual IRQs.\n");
-		ent = 0;
-	} else {
-		irq_table[ent].dev_handle = dev_handle;
-		irq_table[ent].dev_ino = dev_ino;
-		irq_table[ent].in_use = 1;
-	}
+	return nr_ivec;
+}
+
+struct irq_handler_data {
+	union {
+		struct {
+			unsigned int dev_handle;
+			unsigned int dev_ino;
+		};
+		unsigned long sysino;
+	};
+	struct ino_bucket bucket;
+	unsigned long	iclr;
+	unsigned long	imap;
+};
+
+static inline unsigned int irq_data_to_handle(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
+
+	return ihd->dev_handle;
+}
+
+static inline unsigned int irq_data_to_ino(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
 
-	spin_unlock_irqrestore(&irq_alloc_lock, flags);
+	return ihd->dev_ino;
+}
+
+static inline unsigned long irq_data_to_sysino(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
 
-	return ent;
+	return ihd->sysino;
 }
 
-#ifdef CONFIG_PCI_MSI
 void irq_free(unsigned int irq)
 {
-	unsigned long flags;
+	void *data = irq_get_handler_data(irq);
 
-	if (irq >= NR_IRQS)
-		return;
+	kfree(data);
+	irq_set_handler_data(irq, NULL);
+	irq_free_descs(irq, 1);
+}
 
-	spin_lock_irqsave(&irq_alloc_lock, flags);
+unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino)
+{
+	int irq;
 
-	irq_table[irq].in_use = 0;
+	irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL);
+	if (irq <= 0)
+		goto out;
 
-	spin_unlock_irqrestore(&irq_alloc_lock, flags);
+	return irq;
+out:
+	return 0;
+}
+
+static unsigned int cookie_exists(u32 devhandle, unsigned int devino)
+{
+	unsigned long hv_err, cookie;
+	struct ino_bucket *bucket;
+	unsigned int irq = 0U;
+
+	hv_err = sun4v_vintr_get_cookie(devhandle, devino, &cookie);
+	if (hv_err) {
+		pr_err("HV get cookie failed hv_err = %ld\n", hv_err);
+		goto out;
+	}
+
+	if (cookie & ((1UL << 63UL))) {
+		cookie = ~cookie;
+		bucket = (struct ino_bucket *) __va(cookie);
+		irq = bucket->__irq;
+	}
+out:
+	return irq;
+}
+
+static unsigned int sysino_exists(u32 devhandle, unsigned int devino)
+{
+	unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino);
+	struct ino_bucket *bucket;
+	unsigned int irq;
+
+	bucket = &ivector_table[sysino];
+	irq = bucket_get_irq(__pa(bucket));
+
+	return irq;
+}
+
+void ack_bad_irq(unsigned int irq)
+{
+	pr_crit("BAD IRQ ack %d\n", irq);
+}
+
+void irq_install_pre_handler(int irq,
+			     void (*func)(unsigned int, void *, void *),
+			     void *arg1, void *arg2)
+{
+	pr_warn("IRQ pre handler NOT supported.\n");
 }
-#endif
 
 /*
  * /proc/interrupts printing:
@@ -206,15 +345,6 @@ static unsigned int sun4u_compute_tid(unsigned long imap, unsigned long cpuid)
 	return tid;
 }
 
-struct irq_handler_data {
-	unsigned long	iclr;
-	unsigned long	imap;
-
-	void		(*pre_handler)(unsigned int, void *, void *);
-	void		*arg1;
-	void		*arg2;
-};
-
 #ifdef CONFIG_SMP
 static int irq_choose_cpu(unsigned int irq, const struct cpumask *affinity)
 {
@@ -316,8 +446,8 @@ static void sun4u_irq_eoi(struct irq_data *data)
 
 static void sun4v_irq_enable(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
 	unsigned long cpuid = irq_choose_cpu(data->irq, data->affinity);
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_settarget(ino, cpuid);
@@ -337,8 +467,8 @@ static void sun4v_irq_enable(struct irq_data *data)
 static int sun4v_set_affinity(struct irq_data *data,
 			       const struct cpumask *mask, bool force)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
 	unsigned long cpuid = irq_choose_cpu(data->irq, mask);
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_settarget(ino, cpuid);
@@ -351,7 +481,7 @@ static int sun4v_set_affinity(struct irq_data *data,
 
 static void sun4v_irq_disable(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_setenabled(ino, HV_INTR_DISABLED);
@@ -362,7 +492,7 @@ static void sun4v_irq_disable(struct irq_data *data)
 
 static void sun4v_irq_eoi(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE);
@@ -373,14 +503,13 @@ static void sun4v_irq_eoi(struct irq_data *data)
 
 static void sun4v_virq_enable(struct irq_data *data)
 {
-	unsigned long cpuid, dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
+	unsigned long cpuid;
 	int err;
 
 	cpuid = irq_choose_cpu(data->irq, data->affinity);
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
@@ -403,14 +532,13 @@ static void sun4v_virq_enable(struct irq_data *data)
 static int sun4v_virt_set_affinity(struct irq_data *data,
 				    const struct cpumask *mask, bool force)
 {
-	unsigned long cpuid, dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
+	unsigned long cpuid;
 	int err;
 
 	cpuid = irq_choose_cpu(data->irq, mask);
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
@@ -422,11 +550,10 @@ static int sun4v_virt_set_affinity(struct irq_data *data,
 
 static void sun4v_virq_disable(struct irq_data *data)
 {
-	unsigned long dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
 	int err;
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
 
 	err = sun4v_vintr_set_valid(dev_handle, dev_ino,
 				    HV_INTR_DISABLED);
@@ -438,12 +565,10 @@ static void sun4v_virq_disable(struct irq_data *data)
 
 static void sun4v_virq_eoi(struct irq_data *data)
 {
-	unsigned long dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
 	int err;
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_state(dev_handle, dev_ino,
 				    HV_INTR_STATE_IDLE);
 	if (err != HV_EOK)
@@ -479,31 +604,10 @@ static struct irq_chip sun4v_virq = {
 	.flags			= IRQCHIP_EOI_IF_HANDLED,
 };
 
-static void pre_flow_handler(struct irq_data *d)
-{
-	struct irq_handler_data *handler_data = irq_data_get_irq_handler_data(d);
-	unsigned int ino = irq_table[d->irq].dev_ino;
-
-	handler_data->pre_handler(ino, handler_data->arg1, handler_data->arg2);
-}
-
-void irq_install_pre_handler(int irq,
-			     void (*func)(unsigned int, void *, void *),
-			     void *arg1, void *arg2)
-{
-	struct irq_handler_data *handler_data = irq_get_handler_data(irq);
-
-	handler_data->pre_handler = func;
-	handler_data->arg1 = arg1;
-	handler_data->arg2 = arg2;
-
-	__irq_set_preflow_handler(irq, pre_flow_handler);
-}
-
 unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap)
 {
-	struct ino_bucket *bucket;
 	struct irq_handler_data *handler_data;
+	struct ino_bucket *bucket;
 	unsigned int irq;
 	int ino;
 
@@ -537,119 +641,166 @@ out:
 	return irq;
 }
 
-static unsigned int sun4v_build_common(unsigned long sysino,
-				       struct irq_chip *chip)
+static unsigned int sun4v_build_common(u32 devhandle, unsigned int devino,
+		void (*handler_data_init)(struct irq_handler_data *data,
+		u32 devhandle, unsigned int devino),
+		struct irq_chip *chip)
 {
-	struct ino_bucket *bucket;
-	struct irq_handler_data *handler_data;
+	struct irq_handler_data *data;
 	unsigned int irq;
 
-	BUG_ON(tlb_type != hypervisor);
+	irq = irq_alloc(devhandle, devino);
+	if (!irq)
+		goto out;
 
-	bucket = &ivector_table[sysino];
-	irq = bucket_get_irq(__pa(bucket));
-	if (!irq) {
-		irq = irq_alloc(0, sysino);
-		bucket_set_irq(__pa(bucket), irq);
-		irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq,
-					      "IVEC");
+	data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
+	if (unlikely(!data)) {
+		pr_err("IRQ handler data allocation failed.\n");
+		irq_free(irq);
+		irq = 0;
+		goto out;
 	}
 
-	handler_data = irq_get_handler_data(irq);
-	if (unlikely(handler_data))
-		goto out;
+	irq_set_handler_data(irq, data);
+	handler_data_init(data, devhandle, devino);
+	irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, "IVEC");
+	data->imap = ~0UL;
+	data->iclr = ~0UL;
+out:
+	return irq;
+}
 
-	handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
-	if (unlikely(!handler_data)) {
-		prom_printf("IRQ: kzalloc(irq_handler_data) failed.\n");
-		prom_halt();
-	}
-	irq_set_handler_data(irq, handler_data);
+static unsigned long cookie_assign(unsigned int irq, u32 devhandle,
+		unsigned int devino)
+{
+	struct irq_handler_data *ihd = irq_get_handler_data(irq);
+	unsigned long hv_error, cookie;
 
-	/* Catch accidental accesses to these things.  IMAP/ICLR handling
-	 * is done by hypervisor calls on sun4v platforms, not by direct
-	 * register accesses.
+	/* handler_irq needs to find the irq. cookie is seen signed in
+	 * sun4v_dev_mondo and treated as a non ivector_table delivery.
 	 */
-	handler_data->imap = ~0UL;
-	handler_data->iclr = ~0UL;
+	ihd->bucket.__irq = irq;
+	cookie = ~__pa(&ihd->bucket);
 
-out:
-	return irq;
+	hv_error = sun4v_vintr_set_cookie(devhandle, devino, cookie);
+	if (hv_error)
+		pr_err("HV vintr set cookie failed = %ld\n", hv_error);
+
+	return hv_error;
 }
 
-unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino)
+static void cookie_handler_data(struct irq_handler_data *data,
+				u32 devhandle, unsigned int devino)
 {
-	unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino);
+	data->dev_handle = devhandle;
+	data->dev_ino = devino;
+}
 
-	return sun4v_build_common(sysino, &sun4v_irq);
+static unsigned int cookie_build_irq(u32 devhandle, unsigned int devino,
+				     struct irq_chip *chip)
+{
+	unsigned long hv_error;
+	unsigned int irq;
+
+	irq = sun4v_build_common(devhandle, devino, cookie_handler_data, chip);
+
+	hv_error = cookie_assign(irq, devhandle, devino);
+	if (hv_error) {
+		irq_free(irq);
+		irq = 0;
+	}
+
+	return irq;
 }
 
-unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
+static unsigned int sun4v_build_cookie(u32 devhandle, unsigned int devino)
 {
-	struct irq_handler_data *handler_data;
-	unsigned long hv_err, cookie;
-	struct ino_bucket *bucket;
 	unsigned int irq;
 
-	bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC);
-	if (unlikely(!bucket))
-		return 0;
+	irq = cookie_exists(devhandle, devino);
+	if (irq)
+		goto out;
 
-	/* The only reference we store to the IRQ bucket is
-	 * by physical address which kmemleak can't see, tell
-	 * it that this object explicitly is not a leak and
-	 * should be scanned.
-	 */
-	kmemleak_not_leak(bucket);
+	irq = cookie_build_irq(devhandle, devino, &sun4v_virq);
 
-	__flush_dcache_range((unsigned long) bucket,
-			     ((unsigned long) bucket +
-			      sizeof(struct ino_bucket)));
+out:
+	return irq;
+}
 
-	irq = irq_alloc(devhandle, devino);
+static void sysino_set_bucket(unsigned int irq)
+{
+	struct irq_handler_data *ihd = irq_get_handler_data(irq);
+	struct ino_bucket *bucket;
+	unsigned long sysino;
+
+	sysino = sun4v_devino_to_sysino(ihd->dev_handle, ihd->dev_ino);
+	BUG_ON(sysino >= nr_ivec);
+	bucket = &ivector_table[sysino];
 	bucket_set_irq(__pa(bucket), irq);
+}
 
-	irq_set_chip_and_handler_name(irq, &sun4v_virq, handle_fasteoi_irq,
-				      "IVEC");
+static void sysino_handler_data(struct irq_handler_data *data,
+				u32 devhandle, unsigned int devino)
+{
+	unsigned long sysino;
 
-	handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
-	if (unlikely(!handler_data))
-		return 0;
+	sysino = sun4v_devino_to_sysino(devhandle, devino);
+	data->sysino = sysino;
+}
 
-	/* In order to make the LDC channel startup sequence easier,
-	 * especially wrt. locking, we do not let request_irq() enable
-	 * the interrupt.
-	 */
-	irq_set_status_flags(irq, IRQ_NOAUTOEN);
-	irq_set_handler_data(irq, handler_data);
+static unsigned int sysino_build_irq(u32 devhandle, unsigned int devino,
+				     struct irq_chip *chip)
+{
+	unsigned int irq;
 
-	/* Catch accidental accesses to these things.  IMAP/ICLR handling
-	 * is done by hypervisor calls on sun4v platforms, not by direct
-	 * register accesses.
-	 */
-	handler_data->imap = ~0UL;
-	handler_data->iclr = ~0UL;
+	irq = sun4v_build_common(devhandle, devino, sysino_handler_data, chip);
+	if (!irq)
+		goto out;
 
-	cookie = ~__pa(bucket);
-	hv_err = sun4v_vintr_set_cookie(devhandle, devino, cookie);
-	if (hv_err) {
-		prom_printf("IRQ: Fatal, cannot set cookie for [%x:%x] "
-			    "err=%lu\n", devhandle, devino, hv_err);
-		prom_halt();
-	}
+	sysino_set_bucket(irq);
+out:
+	return irq;
+}
 
+static int sun4v_build_sysino(u32 devhandle, unsigned int devino)
+{
+	int irq;
+
+	irq = sysino_exists(devhandle, devino);
+	if (irq)
+		goto out;
+
+	irq = sysino_build_irq(devhandle, devino, &sun4v_irq);
+out:
 	return irq;
 }
 
-void ack_bad_irq(unsigned int irq)
+unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino)
 {
-	unsigned int ino = irq_table[irq].dev_ino;
+	unsigned int irq;
 
-	if (!ino)
-		ino = 0xdeadbeef;
+	if (sun4v_cookie_only_virqs())
+		irq = sun4v_build_cookie(devhandle, devino);
+	else
+		irq = sun4v_build_sysino(devhandle, devino);
 
-	printk(KERN_CRIT "Unexpected IRQ from ino[%x] irq[%u]\n",
-	       ino, irq);
+	return irq;
+}
+
+unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
+{
+	int irq;
+
+	irq = cookie_build_irq(devhandle, devino, &sun4v_virq);
+	if (!irq)
+		goto out;
+
+	/* This is borrowed from the original function.
+	 */
+	irq_set_status_flags(irq, IRQ_NOAUTOEN);
+
+out:
+	return irq;
 }
 
 void *hardirq_stack[NR_CPUS];
@@ -720,9 +871,12 @@ void fixup_irqs(void)
 
 	for (irq = 0; irq < NR_IRQS; irq++) {
 		struct irq_desc *desc = irq_to_desc(irq);
-		struct irq_data *data = irq_desc_get_irq_data(desc);
+		struct irq_data *data;
 		unsigned long flags;
 
+		if (!desc)
+			continue;
+		data = irq_desc_get_irq_data(desc);
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		if (desc->action && !irqd_is_per_cpu(data)) {
 			if (data->chip->irq_set_affinity)
@@ -922,16 +1076,22 @@ static struct irqaction timer_irq_action = {
 	.name = "timer",
 };
 
-/* Only invoked on boot processor. */
-void __init init_IRQ(void)
+static void __init irq_ivector_init(void)
 {
-	unsigned long size;
+	unsigned long size, order;
+	unsigned int ivecs;
 
-	map_prom_timers();
-	kill_prom_timer();
+	/* If we are doing cookie only VIRQs then we do not need the ivector
+	 * table to process interrupts.
+	 */
+	if (sun4v_cookie_only_virqs())
+		return;
 
-	size = sizeof(struct ino_bucket) * NUM_IVECS;
-	ivector_table = kzalloc(size, GFP_KERNEL);
+	ivecs = size_nr_ivec();
+	size = sizeof(struct ino_bucket) * ivecs;
+	order = get_order(size);
+	ivector_table = (struct ino_bucket *)
+		__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!ivector_table) {
 		prom_printf("Fatal error, cannot allocate ivector_table\n");
 		prom_halt();
@@ -940,6 +1100,15 @@ void __init init_IRQ(void)
 			     ((unsigned long) ivector_table) + size);
 
 	ivector_table_pa = __pa(ivector_table);
+}
+
+/* Only invoked on boot processor.*/
+void __init init_IRQ(void)
+{
+	irq_init_hv();
+	irq_ivector_init();
+	map_prom_timers();
+	kill_prom_timer();
 
 	if (tlb_type == hypervisor)
 		sun4v_init_mondo_queues();
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 542e96ac4d39..ef0d8e9e1210 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -47,14 +47,6 @@ kvmap_itlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
 
 	TSB_LOCK_TAG(%g1, %g2, %g7)
-
-	/* Load and check PTE.  */
-	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
-	mov		1, %g7
-	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
-	brgez,a,pn	%g5, kvmap_itlb_longpath
-	 TSB_STORE(%g1, %g7)
-
 	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
@@ -118,6 +110,12 @@ kvmap_dtlb_obp:
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop
 
+kvmap_linear_early:
+	sethi		%hi(kern_linear_pte_xor), %g7
+	ldx		[%g7 + %lo(kern_linear_pte_xor)], %g2
+	ba,pt		%xcc, kvmap_dtlb_tsb4m_load
+	 xor		%g2, %g4, %g5
+
 	.align		32
 kvmap_dtlb_tsb4m_load:
 	TSB_LOCK_TAG(%g1, %g2, %g7)
@@ -146,105 +144,17 @@ kvmap_dtlb_4v:
 	/* Correct TAG_TARGET is already in %g6, check 4mb TSB.  */
 	KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
 #endif
-	/* TSB entry address left in %g1, lookup linear PTE.
-	 * Must preserve %g1 and %g6 (TAG).
-	 */
-kvmap_dtlb_tsb4m_miss:
-	/* Clear the PAGE_OFFSET top virtual bits, shift
-	 * down to get PFN, and make sure PFN is in range.
-	 */
-661:	sllx		%g4, 0, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	/* Check to see if we know about valid memory at the 4MB
-	 * chunk this physical address will reside within.
+	/* Linear mapping TSB lookup failed.  Fallthrough to kernel
+	 * page table based lookup.
 	 */
-661:	srlx		%g5, MAX_PHYS_ADDRESS_BITS, %g2
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	brnz,pn		%g2, kvmap_dtlb_longpath
-	 nop
-
-	/* This unconditional branch and delay-slot nop gets patched
-	 * by the sethi sequence once the bitmap is properly setup.
-	 */
-	.globl		valid_addr_bitmap_insn
-valid_addr_bitmap_insn:
-	ba,pt		%xcc, 2f
-	 nop
-	.subsection	2
-	.globl		valid_addr_bitmap_patch
-valid_addr_bitmap_patch:
-	sethi		%hi(sparc64_valid_addr_bitmap), %g7
-	or		%g7, %lo(sparc64_valid_addr_bitmap), %g7
-	.previous
-
-661:	srlx		%g5, ILOG2_4MB, %g2
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	srlx		%g2, 6, %g5
-	and		%g2, 63, %g2
-	sllx		%g5, 3, %g5
-	ldx		[%g7 + %g5], %g5
-	mov		1, %g7
-	sllx		%g7, %g2, %g7
-	andcc		%g5, %g7, %g0
-	be,pn		%xcc, kvmap_dtlb_longpath
-
-2:	 sethi		%hi(kpte_linear_bitmap), %g2
-
-	/* Get the 256MB physical address index. */
-661:	sllx		%g4, 0, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	or		%g2, %lo(kpte_linear_bitmap), %g2
-
-661:	srlx		%g5, ILOG2_256MB, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	and		%g5, (32 - 1), %g7
-
-	/* Divide by 32 to get the offset into the bitmask.  */
-	srlx		%g5, 5, %g5
-	add		%g7, %g7, %g7
-	sllx		%g5, 3, %g5
-
-	/* kern_linear_pte_xor[(mask >> shift) & 3)] */
-	ldx		[%g2 + %g5], %g2
-	srlx		%g2, %g7, %g7
-	sethi		%hi(kern_linear_pte_xor), %g5
-	and		%g7, 3, %g7
-	or		%g5, %lo(kern_linear_pte_xor), %g5
-	sllx		%g7, 3, %g7
-	ldx		[%g5 + %g7], %g2
-
 	.globl		kvmap_linear_patch
 kvmap_linear_patch:
-	ba,pt		%xcc, kvmap_dtlb_tsb4m_load
-	 xor		%g2, %g4, %g5
+	ba,a,pt		%xcc, kvmap_linear_early
 
 kvmap_dtlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
 
 	TSB_LOCK_TAG(%g1, %g2, %g7)
-
-	/* Load and check PTE.  */
-	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
-	mov		1, %g7
-	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
-	brgez,a,pn	%g5, kvmap_dtlb_longpath
-	 TSB_STORE(%g1, %g7)
-
 	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
@@ -276,13 +186,8 @@ kvmap_dtlb_load:
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 kvmap_vmemmap:
-	sub		%g4, %g5, %g5
-	srlx		%g5, 22, %g5
-	sethi		%hi(vmemmap_table), %g1
-	sllx		%g5, 3, %g5
-	or		%g1, %lo(vmemmap_table), %g1
-	ba,pt		%xcc, kvmap_dtlb_load
-	 ldx		[%g1 + %g5], %g5
+	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
+	ba,a,pt		%xcc, kvmap_dtlb_load
 #endif
 
 kvmap_dtlb_nonlinear:
@@ -294,8 +199,8 @@ kvmap_dtlb_nonlinear:
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	/* Do not use the TSB for vmemmap.  */
-	mov		(VMEMMAP_BASE >> 40), %g5
-	sllx		%g5, 40, %g5
+	sethi		%hi(VMEMMAP_BASE), %g5
+	ldx		[%g5 + %lo(VMEMMAP_BASE)], %g5
 	cmp		%g4,%g5
 	bgeu,pn		%xcc, kvmap_vmemmap
 	 nop
@@ -307,8 +212,8 @@ kvmap_dtlb_tsbmiss:
 	sethi		%hi(MODULES_VADDR), %g5
 	cmp		%g4, %g5
 	blu,pn		%xcc, kvmap_dtlb_longpath
-	 mov		(VMALLOC_END >> 40), %g5
-	sllx		%g5, 40, %g5
+	 sethi		%hi(VMALLOC_END), %g5
+	ldx		[%g5 + %lo(VMALLOC_END)], %g5
 	cmp		%g4, %g5
 	bgeu,pn		%xcc, kvmap_dtlb_longpath
 	 nop
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index e01d75d40329..27bb55485472 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1078,7 +1078,8 @@ static void ldc_iommu_release(struct ldc_channel *lp)
 
 struct ldc_channel *ldc_alloc(unsigned long id,
 			      const struct ldc_channel_config *cfgp,
-			      void *event_arg)
+			      void *event_arg,
+			      const char *name)
 {
 	struct ldc_channel *lp;
 	const struct ldc_mode_ops *mops;
@@ -1093,6 +1094,8 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 	err = -EINVAL;
 	if (!cfgp)
 		goto out_err;
+	if (!name)
+		goto out_err;
 
 	switch (cfgp->mode) {
 	case LDC_MODE_RAW:
@@ -1185,6 +1188,21 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 
 	INIT_HLIST_HEAD(&lp->mh_list);
 
+	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
+	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
+
+	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
+			  lp->rx_irq_name, lp);
+	if (err)
+		goto out_free_txq;
+
+	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
+			  lp->tx_irq_name, lp);
+	if (err) {
+		free_irq(lp->cfg.rx_irq, lp);
+		goto out_free_txq;
+	}
+
 	return lp;
 
 out_free_txq:
@@ -1237,31 +1255,14 @@ EXPORT_SYMBOL(ldc_free);
  * state.  This does not initiate a handshake, ldc_connect() does
  * that.
  */
-int ldc_bind(struct ldc_channel *lp, const char *name)
+int ldc_bind(struct ldc_channel *lp)
 {
 	unsigned long hv_err, flags;
 	int err = -EINVAL;
 
-	if (!name ||
-	    (lp->state != LDC_STATE_INIT))
+	if (lp->state != LDC_STATE_INIT)
 		return -EINVAL;
 
-	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
-	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
-
-	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
-			  lp->rx_irq_name, lp);
-	if (err)
-		return err;
-
-	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
-			  lp->tx_irq_name, lp);
-	if (err) {
-		free_irq(lp->cfg.rx_irq, lp);
-		return err;
-	}
-
-
 	spin_lock_irqsave(&lp->lock, flags);
 
 	enable_irq(lp->cfg.rx_irq);
@@ -1336,7 +1337,7 @@ int ldc_connect(struct ldc_channel *lp)
 	if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) ||
 	    !(lp->flags & LDC_FLAG_REGISTERED_QUEUES) ||
 	    lp->hs_state != LDC_HS_OPEN)
-		err = -EINVAL;
+		err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL);
 	else
 		err = start_handshake(lp);
 
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 6479256fd5a4..fce8ab17bcbb 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -141,7 +141,6 @@ static inline unsigned int get_nmi_count(int cpu)
 
 static __init void nmi_cpu_busy(void *data)
 {
-	local_irq_enable_in_hardirq();
 	while (endflag == 0)
 		mb();
 }
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 8f76f23dac38..f9c6813c132d 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -581,7 +581,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 {
 	unsigned long csr_reg, csr, csr_error_bits;
 	irqreturn_t ret = IRQ_NONE;
-	u16 stat;
+	u32 stat;
 
 	csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL;
 	csr = upa_readq(csr_reg);
@@ -617,7 +617,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 			       pbm->name);
 		ret = IRQ_HANDLED;
 	}
-	pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat);
+	pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat);
 	if (stat & (PCI_STATUS_PARITY |
 		    PCI_STATUS_SIG_TARGET_ABORT |
 		    PCI_STATUS_REC_TARGET_ABORT |
@@ -625,7 +625,7 @@ static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
 		    PCI_STATUS_SIG_SYSTEM_ERROR)) {
 		printk("%s: PCI bus error, PCI_STATUS[%04x]\n",
 		       pbm->name, stat);
-		pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff);
+		pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff);
 		ret = IRQ_HANDLED;
 	}
 	return ret;
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 269af58497aa..7e967c8018c8 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -191,12 +191,41 @@ static const struct pcr_ops n4_pcr_ops = {
 	.pcr_nmi_disable	= PCR_N4_PICNPT,
 };
 
+static u64 n5_pcr_read(unsigned long reg_num)
+{
+	unsigned long val;
+
+	(void) sun4v_t5_get_perfreg(reg_num, &val);
+
+	return val;
+}
+
+static void n5_pcr_write(unsigned long reg_num, u64 val)
+{
+	(void) sun4v_t5_set_perfreg(reg_num, val);
+}
+
+static const struct pcr_ops n5_pcr_ops = {
+	.read_pcr		= n5_pcr_read,
+	.write_pcr		= n5_pcr_write,
+	.read_pic		= n4_pic_read,
+	.write_pic		= n4_pic_write,
+	.nmi_picl_value		= n4_picl_value,
+	.pcr_nmi_enable		= (PCR_N4_PICNPT | PCR_N4_STRACE |
+				   PCR_N4_UTRACE | PCR_N4_TOE |
+				   (26 << PCR_N4_SL_SHIFT)),
+	.pcr_nmi_disable	= PCR_N4_PICNPT,
+};
+
+
 static unsigned long perf_hsvc_group;
 static unsigned long perf_hsvc_major;
 static unsigned long perf_hsvc_minor;
 
 static int __init register_perf_hsvc(void)
 {
+	unsigned long hverror;
+
 	if (tlb_type == hypervisor) {
 		switch (sun4v_chip_type) {
 		case SUN4V_CHIP_NIAGARA1:
@@ -215,6 +244,10 @@ static int __init register_perf_hsvc(void)
 			perf_hsvc_group = HV_GRP_VT_CPU;
 			break;
 
+		case SUN4V_CHIP_NIAGARA5:
+			perf_hsvc_group = HV_GRP_T5_CPU;
+			break;
+
 		default:
 			return -ENODEV;
 		}
@@ -222,10 +255,12 @@ static int __init register_perf_hsvc(void)
 
 		perf_hsvc_major = 1;
 		perf_hsvc_minor = 0;
-		if (sun4v_hvapi_register(perf_hsvc_group,
-					 perf_hsvc_major,
-					 &perf_hsvc_minor)) {
-			printk("perfmon: Could not register hvapi.\n");
+		hverror = sun4v_hvapi_register(perf_hsvc_group,
+					       perf_hsvc_major,
+					       &perf_hsvc_minor);
+		if (hverror) {
+			pr_err("perfmon: Could not register hvapi(0x%lx).\n",
+			       hverror);
 			return -ENODEV;
 		}
 	}
@@ -254,6 +289,10 @@ static int __init setup_sun4v_pcr_ops(void)
 		pcr_ops = &n4_pcr_ops;
 		break;
 
+	case SUN4V_CHIP_NIAGARA5:
+		pcr_ops = &n5_pcr_ops;
+		break;
+
 	default:
 		ret = -ENODEV;
 		break;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b5c38faa4ead..617b9fe33771 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1662,7 +1662,8 @@ static bool __init supported_pmu(void)
 		sparc_pmu = &niagara2_pmu;
 		return true;
 	}
-	if (!strcmp(sparc_pmu_type, "niagara4")) {
+	if (!strcmp(sparc_pmu_type, "niagara4") ||
+	    !strcmp(sparc_pmu_type, "niagara5")) {
 		sparc_pmu = &niagara4_pmu;
 		return true;
 	}
@@ -1671,9 +1672,12 @@ static bool __init supported_pmu(void)
 
 int __init init_hw_perf_events(void)
 {
+	int err;
+
 	pr_info("Performance events: ");
 
-	if (!supported_pmu()) {
+	err = pcr_arch_init();
+	if (err || !supported_pmu()) {
 		pr_cont("No support for PMU type '%s'\n", sparc_pmu_type);
 		return 0;
 	}
@@ -1685,7 +1689,7 @@ int __init init_hw_perf_events(void)
 
 	return 0;
 }
-early_initcall(init_hw_perf_events);
+pure_initcall(init_hw_perf_events);
 
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			   struct pt_regs *regs)
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d7b4967f8fa6..c6f7113b6e2f 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -306,6 +306,9 @@ static void __global_pmu_self(int this_cpu)
 	struct global_pmu_snapshot *pp;
 	int i, num;
 
+	if (!pcr_ops)
+		return;
+
 	pp = &global_cpu_snapshot[this_cpu].pmu;
 
 	num = 1;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3fdb455e3318..61a519808cb7 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -30,6 +30,7 @@
 #include <linux/cpu.h>
 #include <linux/initrd.h>
 #include <linux/module.h>
+#include <linux/start_kernel.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -174,7 +175,7 @@ char reboot_command[COMMAND_LINE_SIZE];
 
 static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 };
 
-void __init per_cpu_patch(void)
+static void __init per_cpu_patch(void)
 {
 	struct cpuid_patch_entry *p;
 	unsigned long ver;
@@ -266,7 +267,7 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
 	}
 }
 
-void __init sun4v_patch(void)
+static void __init sun4v_patch(void)
 {
 	extern void sun4v_hvapi_init(void);
 
@@ -335,14 +336,25 @@ static void __init pause_patch(void)
 	}
 }
 
-#ifdef CONFIG_SMP
-void __init boot_cpu_id_too_large(int cpu)
+void __init start_early_boot(void)
 {
-	prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n",
-		    cpu, NR_CPUS);
-	prom_halt();
+	int cpu;
+
+	check_if_starfire();
+	per_cpu_patch();
+	sun4v_patch();
+
+	cpu = hard_smp_processor_id();
+	if (cpu >= NR_CPUS) {
+		prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n",
+			    cpu, NR_CPUS);
+		prom_halt();
+	}
+	current_thread_info()->cpu = cpu;
+
+	prom_init_report();
+	start_kernel();
 }
-#endif
 
 /* On Ultra, we support all of the v8 capabilities. */
 unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |
@@ -500,12 +512,16 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_BLKINIT;
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_N2;
 	}
@@ -533,6 +549,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
 					AV_SPARC_ASI_BLK_INIT |
@@ -540,6 +558,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
 					AV_SPARC_FMAF);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b085311dcd0e..9af0a5dbb36d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -151,7 +151,7 @@ void cpu_panic(void)
 #define NUM_ROUNDS	64	/* magic value */
 #define NUM_ITERS	5	/* likewise */
 
-static DEFINE_SPINLOCK(itc_sync_lock);
+static DEFINE_RAW_SPINLOCK(itc_sync_lock);
 static unsigned long go[SLAVE + 1];
 
 #define DEBUG_TICK_SYNC	0
@@ -259,7 +259,7 @@ static void smp_synchronize_one_tick(int cpu)
 	go[MASTER] = 0;
 	membar_safe("#StoreLoad");
 
-	spin_lock_irqsave(&itc_sync_lock, flags);
+	raw_spin_lock_irqsave(&itc_sync_lock, flags);
 	{
 		for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) {
 			while (!go[MASTER])
@@ -270,7 +270,7 @@ static void smp_synchronize_one_tick(int cpu)
 			membar_safe("#StoreLoad");
 		}
 	}
-	spin_unlock_irqrestore(&itc_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&itc_sync_lock, flags);
 }
 
 #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
@@ -823,13 +823,17 @@ void arch_send_call_function_single_ipi(int cpu)
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	irq_enter();
 	generic_smp_call_function_interrupt();
+	irq_exit();
 }
 
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
+	irq_enter();
 	generic_smp_call_function_single_interrupt();
+	irq_exit();
 }
 
 static void tsb_sync(void *info)
@@ -1395,7 +1399,6 @@ void __cpu_die(unsigned int cpu)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	pcr_arch_init();
 }
 
 void smp_send_reschedule(int cpu)
@@ -1480,6 +1483,13 @@ static void __init pcpu_populate_pte(unsigned long addr)
 	pud_t *pud;
 	pmd_t *pmd;
 
+	if (pgd_none(*pgd)) {
+		pud_t *new;
+
+		new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+		pgd_populate(&init_mm, pgd, new);
+	}
+
 	pud = pud_offset(pgd, addr);
 	if (pud_none(*pud)) {
 		pmd_t *new;
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index e0c09bf85610..6179e19bc9b9 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -195,6 +195,11 @@ sun4v_tsb_miss_common:
 	 ldx	[%g2 + TRAP_PER_CPU_PGD_PADDR], %g7
 
 sun4v_itlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1
+
 	sethi	%hi(sun4v_err_itlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_itlb_vaddr)]
 	sethi	%hi(sun4v_err_itlb_ctx), %g1
@@ -206,15 +211,10 @@ sun4v_itlb_error:
 	sethi	%hi(sun4v_err_itlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_itlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_itlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
@@ -222,6 +222,11 @@ sun4v_itlb_error:
 	/* NOTREACHED */
 
 sun4v_dtlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1
+
 	sethi	%hi(sun4v_err_dtlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)]
 	sethi	%hi(sun4v_err_dtlb_ctx), %g1
@@ -233,21 +238,23 @@ sun4v_dtlb_error:
 	sethi	%hi(sun4v_err_dtlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_dtlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_dtlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
 
 	/* NOTREACHED */
 
+sun4v_bad_ra:
+	or	%g0, %g4, %g5
+	ba,pt	%xcc, sparc64_realfault_common
+	 or	%g1, %g0, %g4
+
+	/* NOTREACHED */
+
 	/* Instruction Access Exception, tl0. */
 sun4v_iacc:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g2
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index f7c72b6efc27..d066eb18650c 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -44,7 +44,7 @@ SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1)
 SIGN1(sys32_io_submit, compat_sys_io_submit, %o1)
 SIGN1(sys32_mq_open, compat_sys_mq_open, %o1)
 SIGN1(sys32_select, compat_sys_select, %o0)
-SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5)
+SIGN1(sys32_futex, compat_sys_futex, %o1)
 SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
 SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
 SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index 737f8cbc7d56..88ede1d53b4c 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -109,10 +109,13 @@ startup_continue:
 	brnz,pn		%g1, 1b
 	 nop
 
-	sethi		%hi(p1275buf), %g2
-	or		%g2, %lo(p1275buf), %g2
-	ldx		[%g2 + 0x10], %l2
-	add		%l2, -(192 + 128), %sp
+	/* Get onto temporary stack which will be in the locked
+	 * kernel image.
+	 */
+	sethi		%hi(tramp_stack), %g1
+	or		%g1, %lo(tramp_stack), %g1
+	add		%g1, TRAMP_STACK_SIZE, %g1
+	sub		%g1, STACKFRAME_SZ + STACK_BIAS + 256, %sp
 	flushw
 
 	/* Setup the loop variables:
@@ -394,7 +397,6 @@ after_lock_tlb:
 	sllx		%g5, THREAD_SHIFT, %g5
 	sub		%g5, (STACKFRAME_SZ + STACK_BIAS), %g5
 	add		%g6, %g5, %sp
-	mov		0, %fp
 
 	rdpr		%pstate, %o1
 	or		%o1, PSTATE_IE, %o1
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4ced92f05358..25d0c7ece9cc 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2102,6 +2102,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_nonresum_oflow_cnt);
 }
 
+static void sun4v_tlb_error(struct pt_regs *regs)
+{
+	die_if_kernel("TLB/TSB error", regs);
+}
+
 unsigned long sun4v_err_itlb_vaddr;
 unsigned long sun4v_err_itlb_ctx;
 unsigned long sun4v_err_itlb_pte;
@@ -2109,8 +2114,7 @@ unsigned long sun4v_err_itlb_error;
 
 void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2123,7 +2127,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx,
 	       sun4v_err_itlb_pte, sun4v_err_itlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 unsigned long sun4v_err_dtlb_vaddr;
@@ -2133,8 +2137,7 @@ unsigned long sun4v_err_dtlb_error;
 
 void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2147,7 +2150,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx,
 	       sun4v_err_dtlb_pte, sun4v_err_dtlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 void hypervisor_tlbop_error(unsigned long err, unsigned long op)
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 14158d40ba76..be98685c14c6 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -162,10 +162,10 @@ tsb_miss_page_table_walk_sun4v_fastpath:
 	nop
 	.previous
 
-	rdpr	%tl, %g3
-	cmp	%g3, 1
+	rdpr	%tl, %g7
+	cmp	%g7, 1
 	bne,pn	%xcc, winfix_trampoline
-	 nop
+	 mov	%g3, %g4
 	ba,pt	%xcc, etrap
 	 rd	%pc, %g7
 	call	hugetlb_setup
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 3c1a7cb31579..35ab8b60d256 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -166,17 +166,23 @@ static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs)
 unsigned long compute_effective_address(struct pt_regs *regs,
 					unsigned int insn, unsigned int rd)
 {
+	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
 	unsigned int rs1 = (insn >> 14) & 0x1f;
 	unsigned int rs2 = insn & 0x1f;
-	int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+	unsigned long addr;
 
 	if (insn & 0x2000) {
 		maybe_flush_windows(rs1, 0, rd, from_kernel);
-		return (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
+		addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
 	} else {
 		maybe_flush_windows(rs1, rs2, rd, from_kernel);
-		return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
+		addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
 	}
+
+	if (!from_kernel && test_thread_flag(TIF_32BIT))
+		addr &= 0xffffffff;
+
+	return addr;
 }
 
 /* This is just to make gcc think die_if_kernel does return... */
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index f8e7dd53e1c7..9c5fbd0b8a04 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -714,7 +714,7 @@ int vio_ldc_alloc(struct vio_driver_state *vio,
 	cfg.tx_irq = vio->vdev->tx_irq;
 	cfg.rx_irq = vio->vdev->rx_irq;
 
-	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg);
+	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg, vio->name);
 	if (IS_ERR(lp))
 		return PTR_ERR(lp);
 
@@ -746,7 +746,7 @@ void vio_port_up(struct vio_driver_state *vio)
 
 	err = 0;
 	if (state == LDC_STATE_INIT) {
-		err = ldc_bind(vio->lp, vio->name);
+		err = ldc_bind(vio->lp);
 		if (err)
 			printk(KERN_WARNING "%s: Port %lu bind failed, "
 			       "err=%d\n",
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 932ff90fd760..09243057cb0b 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -35,8 +35,9 @@ jiffies = jiffies_64;
 
 SECTIONS
 {
-	/* swapper_low_pmd_dir is sparc64 only */
-	swapper_low_pmd_dir = 0x0000000000402000;
+#ifdef CONFIG_SPARC64
+	swapper_pg_dir = 0x0000000000402000;
+#endif
 	. = INITIAL_ADDRESS;
 	.text TEXTSTART :
 	{
@@ -122,11 +123,6 @@ SECTIONS
 		*(.swapper_4m_tsb_phys_patch)
 		__swapper_4m_tsb_phys_patch_end = .;
 	}
-	.page_offset_shift_patch : {
-		__page_offset_shift_patch = .;
-		*(.page_offset_shift_patch)
-		__page_offset_shift_patch_end = .;
-	}
 	.popc_3insn_patch : {
 		__popc_3insn_patch = .;
 		*(.popc_3insn_patch)
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 2c20ad63ddbf..30eee6e8a81b 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -236,6 +236,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 */
 	VISEntryHalf
 
+	membar		#Sync
 	alignaddr	%o1, %g0, %g0
 
 	add		%o1, (64 - 1), %o4
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 9cf2ee01cee3..140527a20e7d 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -41,6 +41,10 @@
 #endif
 #endif
 
+#if !defined(EX_LD) && !defined(EX_ST)
+#define NON_USER_COPY
+#endif
+
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
@@ -197,9 +201,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 mov		EX_RETVAL(%o3), %o0
 
 .Llarge_src_unaligned:
+#ifdef NON_USER_COPY
+	VISEntryHalfFast(.Lmedium_vis_entry_fail)
+#else
+	VISEntryHalf
+#endif
 	andn		%o2, 0x3f, %o4
 	sub		%o2, %o4, %o2
-	VISEntryHalf
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
 	EX_LD(LOAD(ldd, %g1 + 0x00, %f0))
@@ -240,6 +248,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 	ba,a,pt		%icc, .Lmedium_unaligned
 
+#ifdef NON_USER_COPY
+.Lmedium_vis_entry_fail:
+	 or		%o0, %o1, %g2
+#endif
 .Lmedium:
 	LOAD(prefetch, %o1 + 0x40, #n_reads_strong)
 	andcc		%g2, 0x7, %g0
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 1d32b54089aa..8f2f94d53434 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -40,6 +40,19 @@ int __atomic_add_return(int i, atomic_t *v)
 }
 EXPORT_SYMBOL(__atomic_add_return);
 
+int atomic_xchg(atomic_t *v, int new)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(ATOMIC_HASH(v), flags);
+	ret = v->counter;
+	v->counter = new;
+	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
+	return ret;
+}
+EXPORT_SYMBOL(atomic_xchg);
+
 int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -132,3 +145,17 @@ unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new)
 	return (unsigned long)prev;
 }
 EXPORT_SYMBOL(__cmpxchg_u32);
+
+unsigned long __xchg_u32(volatile u32 *ptr, u32 new)
+{
+	unsigned long flags;
+	u32 prev;
+
+	spin_lock_irqsave(ATOMIC_HASH(ptr), flags);
+	prev = *ptr;
+	*ptr = new;
+	spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);
+
+	return (unsigned long)prev;
+}
+EXPORT_SYMBOL(__xchg_u32);
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index 99c017be8719..f75e6906df14 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -3,8 +3,9 @@
  * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
  * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
  *
- * Returns 0, if ok, and number of bytes not yet set if exception
- * occurs and we were called as clear_user.
+ * Calls to memset returns initial %o0. Calls to bzero returns 0, if ok, and
+ * number of bytes not yet set if exception occurs and we were called as
+ * clear_user.
  */
 
 #include <asm/ptrace.h>
@@ -65,6 +66,8 @@ __bzero_begin:
 	.globl	__memset_start, __memset_end
 __memset_start:
 memset:
+	mov	%o0, %g1
+	mov	1, %g4
 	and	%o1, 0xff, %g3
 	sll	%g3, 8, %g2
 	or	%g3, %g2, %g3
@@ -89,6 +92,7 @@ memset:
 	 sub	%o0, %o2, %o0
 
 __bzero:
+	clr	%g4
 	mov	%g0, %g3
 1:
 	cmp	%o1, 7
@@ -151,8 +155,8 @@ __bzero:
 	bne,a	8f
 	 EX(stb	%g3, [%o0], and %o1, 1)
 8:
-	retl
-	 clr	%o0
+	b	0f
+	 nop
 7:
 	be	13b
 	 orcc	%o1, 0, %g0
@@ -164,6 +168,12 @@ __bzero:
 	bne	8b
 	 EX(stb	%g3, [%o0 - 1], add %o1, 1)
 0:
+	andcc	%g4, 1, %g0
+	be	5f
+	 nop
+	retl
+	 mov	%g1, %o0
+5:
 	retl
 	 clr	%o0
 __memset_end:
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index aa4d55b0bdf0..5ce8f2f64604 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -499,7 +499,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs)
 		case 0: fsr = *pfsr;
 			if (IR == -1) IR = 2;
 			/* fcc is always fcc0 */
-			fsr &= ~0xc00; fsr |= (IR << 10); break;
+			fsr &= ~0xc00; fsr |= (IR << 10);
 			*pfsr = fsr;
 			break;
 		case 1: rd->s = IR; break;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 69bb818fdd79..45a413e4380a 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -96,38 +96,51 @@ static unsigned int get_user_insn(unsigned long tpc)
 	pte_t *ptep, pte;
 	unsigned long pa;
 	u32 insn = 0;
-	unsigned long pstate;
 
-	if (pgd_none(*pgdp))
-		goto outret;
+	if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp)))
+		goto out;
 	pudp = pud_offset(pgdp, tpc);
-	if (pud_none(*pudp))
-		goto outret;
-	pmdp = pmd_offset(pudp, tpc);
-	if (pmd_none(*pmdp))
-		goto outret;
+	if (pud_none(*pudp) || unlikely(pud_bad(*pudp)))
+		goto out;
 
 	/* This disables preemption for us as well. */
-	__asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
-	__asm__ __volatile__("wrpr %0, %1, %%pstate"
-				: : "r" (pstate), "i" (PSTATE_IE));
-	ptep = pte_offset_map(pmdp, tpc);
-	pte = *ptep;
-	if (!pte_present(pte))
-		goto out;
+	local_irq_disable();
+
+	pmdp = pmd_offset(pudp, tpc);
+	if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
+		goto out_irq_enable;
 
-	pa  = (pte_pfn(pte) << PAGE_SHIFT);
-	pa += (tpc & ~PAGE_MASK);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (pmd_trans_huge(*pmdp)) {
+		if (pmd_trans_splitting(*pmdp))
+			goto out_irq_enable;
 
-	/* Use phys bypass so we don't pollute dtlb/dcache. */
-	__asm__ __volatile__("lduwa [%1] %2, %0"
-			     : "=r" (insn)
-			     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+		pa  = pmd_pfn(*pmdp) << PAGE_SHIFT;
+		pa += tpc & ~HPAGE_MASK;
 
+		/* Use phys bypass so we don't pollute dtlb/dcache. */
+		__asm__ __volatile__("lduwa [%1] %2, %0"
+				     : "=r" (insn)
+				     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+	} else
+#endif
+	{
+		ptep = pte_offset_map(pmdp, tpc);
+		pte = *ptep;
+		if (pte_present(pte)) {
+			pa  = (pte_pfn(pte) << PAGE_SHIFT);
+			pa += (tpc & ~PAGE_MASK);
+
+			/* Use phys bypass so we don't pollute dtlb/dcache. */
+			__asm__ __volatile__("lduwa [%1] %2, %0"
+					     : "=r" (insn)
+					     : "r" (pa), "i" (ASI_PHYS_USE_EC));
+		}
+		pte_unmap(ptep);
+	}
+out_irq_enable:
+	local_irq_enable();
 out:
-	pte_unmap(ptep);
-	__asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
-outret:
 	return insn;
 }
 
@@ -153,7 +166,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 }
 
 static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
-			     unsigned int insn, int fault_code)
+			     unsigned long fault_addr, unsigned int insn,
+			     int fault_code)
 {
 	unsigned long addr;
 	siginfo_t info;
@@ -161,10 +175,18 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 	info.si_code = code;
 	info.si_signo = sig;
 	info.si_errno = 0;
-	if (fault_code & FAULT_CODE_ITLB)
+	if (fault_code & FAULT_CODE_ITLB) {
 		addr = regs->tpc;
-	else
-		addr = compute_effective_address(regs, insn, 0);
+	} else {
+		/* If we were able to probe the faulting instruction, use it
+		 * to compute a precise fault address.  Otherwise use the fault
+		 * time provided address which may only have page granularity.
+		 */
+		if (insn)
+			addr = compute_effective_address(regs, insn, 0);
+		else
+			addr = fault_addr;
+	}
 	info.si_addr = (void __user *) addr;
 	info.si_trapno = 0;
 
@@ -239,7 +261,7 @@ static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code,
 		/* The si_code was set to make clear whether
 		 * this was a SEGV_MAPERR or SEGV_ACCERR fault.
 		 */
-		do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code);
+		do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code);
 		return;
 	}
 
@@ -259,18 +281,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
 	show_regs(regs);
 }
 
-static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
-							 unsigned long addr)
-{
-	static int times;
-
-	if (times++ < 10)
-		printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
-		       "reports 64-bit fault address [%lx]\n",
-		       current->comm, current->pid, addr);
-	show_regs(regs);
-}
-
 asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -300,10 +310,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 				goto intr_or_no_mm;
 			}
 		}
-		if (unlikely((address >> 32) != 0)) {
-			bogus_32bit_fault_address(regs, address);
+		if (unlikely((address >> 32) != 0))
 			goto intr_or_no_mm;
-		}
 	}
 
 	if (regs->tstate & TSTATE_PRIV) {
@@ -340,6 +348,9 @@ retry:
 		down_read(&mm->mmap_sem);
 	}
 
+	if (fault_code & FAULT_CODE_BAD_RA)
+		goto do_sigbus;
+
 	vma = find_vma(mm, address);
 	if (!vma)
 		goto bad_area;
@@ -525,7 +536,7 @@ do_sigbus:
 	 * Send a sigbus, regardless of whether we were in kernel
 	 * or user mode.
 	 */
-	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code);
+	do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code);
 
 	/* Kernel mode? Handle exceptions or die */
 	if (regs->tstate & TSTATE_PRIV)
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index c4d3da68b800..ae6ce383d4df 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -73,7 +73,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
 	struct page *head, *page, *tail;
 	int refs;
 
-	if (!pmd_large(pmd))
+	if (!(pmd_val(pmd) & _PAGE_VALID))
 		return 0;
 
 	if (write && !pmd_write(pmd))
@@ -160,6 +160,36 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next, flags;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+
+	local_irq_save(flags);
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			break;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			break;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_restore(flags);
+
+	return nr;
+}
+
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages)
 {
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 9bd9ce80bf77..d329537739c6 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -231,11 +231,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int pmd_huge_support(void)
-{
-	return 0;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index eafbc65c9c47..34506f292533 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -73,7 +73,6 @@ unsigned long kern_linear_pte_xor[4] __read_mostly;
  * 'cpu' properties, but we need to have this table setup before the
  * MDESC is initialized.
  */
-unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
 
 #ifndef CONFIG_DEBUG_PAGEALLOC
 /* A special kernel TSB for 4MB, 256MB, 2GB and 16GB linear mappings.
@@ -82,10 +81,11 @@ unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
  */
 extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES];
 #endif
+extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
 
 static unsigned long cpu_pgsz_mask;
 
-#define MAX_BANKS	32
+#define MAX_BANKS	1024
 
 static struct linux_prom64_registers pavail[MAX_BANKS];
 static int pavail_ents;
@@ -163,10 +163,6 @@ static void __init read_obp_memory(const char *property,
 	     cmp_p64, NULL);
 }
 
-unsigned long sparc64_valid_addr_bitmap[VALID_ADDR_BITMAP_BYTES /
-					sizeof(unsigned long)];
-EXPORT_SYMBOL(sparc64_valid_addr_bitmap);
-
 /* Kernel physical address base and size in bytes.  */
 unsigned long kern_base __read_mostly;
 unsigned long kern_size __read_mostly;
@@ -350,6 +346,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 
 	mm = vma->vm_mm;
 
+	/* Don't insert a non-valid PTE into the TSB, we'll deadlock.  */
+	if (!pte_accessible(mm, pte))
+		return;
+
 	spin_lock_irqsave(&mm->context.lock, flags);
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -588,7 +588,7 @@ static void __init remap_kernel(void)
 	int i, tlb_ent = sparc64_highest_locked_tlbent();
 
 	tte_vaddr = (unsigned long) KERNBASE;
-	phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+	phys_page = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
 	tte_data = kern_large_tte(phys_page);
 
 	kern_locked_tte_data = tte_data;
@@ -834,7 +834,10 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	return -1;
+	/* The following condition has been observed on LDOM guests.*/
+	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
+		" rule. Some physical memory will be owned by node 0.");
+	return 0;
 }
 
 static u64 memblock_nid_range(u64 start, u64 end, int *nid)
@@ -1356,9 +1359,144 @@ static unsigned long __init bootmem_init(unsigned long phys_base)
 static struct linux_prom64_registers pall[MAX_BANKS] __initdata;
 static int pall_ents __initdata;
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
+static unsigned long max_phys_bits = 40;
+
+bool kern_addr_valid(unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if ((long)addr < 0L) {
+		unsigned long pa = __pa(addr);
+
+		if ((addr >> max_phys_bits) != 0UL)
+			return false;
+
+		return pfn_valid(pa >> PAGE_SHIFT);
+	}
+
+	if (addr >= (unsigned long) KERNBASE &&
+	    addr < (unsigned long)&_end)
+		return true;
+
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		return 0;
+
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud))
+		return 0;
+
+	if (pud_large(*pud))
+		return pfn_valid(pud_pfn(*pud));
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return 0;
+
+	if (pmd_large(*pmd))
+		return pfn_valid(pmd_pfn(*pmd));
+
+	pte = pte_offset_kernel(pmd, addr);
+	if (pte_none(*pte))
+		return 0;
+
+	return pfn_valid(pte_pfn(*pte));
+}
+EXPORT_SYMBOL(kern_addr_valid);
+
+static unsigned long __ref kernel_map_hugepud(unsigned long vstart,
+					      unsigned long vend,
+					      pud_t *pud)
+{
+	const unsigned long mask16gb = (1UL << 34) - 1UL;
+	u64 pte_val = vstart;
+
+	/* Each PUD is 8GB */
+	if ((vstart & mask16gb) ||
+	    (vend - vstart <= mask16gb)) {
+		pte_val ^= kern_linear_pte_xor[2];
+		pud_val(*pud) = pte_val | _PAGE_PUD_HUGE;
+
+		return vstart + PUD_SIZE;
+	}
+
+	pte_val ^= kern_linear_pte_xor[3];
+	pte_val |= _PAGE_PUD_HUGE;
+
+	vend = vstart + mask16gb + 1UL;
+	while (vstart < vend) {
+		pud_val(*pud) = pte_val;
+
+		pte_val += PUD_SIZE;
+		vstart += PUD_SIZE;
+		pud++;
+	}
+	return vstart;
+}
+
+static bool kernel_can_map_hugepud(unsigned long vstart, unsigned long vend,
+				   bool guard)
+{
+	if (guard && !(vstart & ~PUD_MASK) && (vend - vstart) >= PUD_SIZE)
+		return true;
+
+	return false;
+}
+
+static unsigned long __ref kernel_map_hugepmd(unsigned long vstart,
+					      unsigned long vend,
+					      pmd_t *pmd)
+{
+	const unsigned long mask256mb = (1UL << 28) - 1UL;
+	const unsigned long mask2gb = (1UL << 31) - 1UL;
+	u64 pte_val = vstart;
+
+	/* Each PMD is 8MB */
+	if ((vstart & mask256mb) ||
+	    (vend - vstart <= mask256mb)) {
+		pte_val ^= kern_linear_pte_xor[0];
+		pmd_val(*pmd) = pte_val | _PAGE_PMD_HUGE;
+
+		return vstart + PMD_SIZE;
+	}
+
+	if ((vstart & mask2gb) ||
+	    (vend - vstart <= mask2gb)) {
+		pte_val ^= kern_linear_pte_xor[1];
+		pte_val |= _PAGE_PMD_HUGE;
+		vend = vstart + mask256mb + 1UL;
+	} else {
+		pte_val ^= kern_linear_pte_xor[2];
+		pte_val |= _PAGE_PMD_HUGE;
+		vend = vstart + mask2gb + 1UL;
+	}
+
+	while (vstart < vend) {
+		pmd_val(*pmd) = pte_val;
+
+		pte_val += PMD_SIZE;
+		vstart += PMD_SIZE;
+		pmd++;
+	}
+
+	return vstart;
+}
+
+static bool kernel_can_map_hugepmd(unsigned long vstart, unsigned long vend,
+				   bool guard)
+{
+	if (guard && !(vstart & ~PMD_MASK) && (vend - vstart) >= PMD_SIZE)
+		return true;
+
+	return false;
+}
+
 static unsigned long __ref kernel_map_range(unsigned long pstart,
-					    unsigned long pend, pgprot_t prot)
+					    unsigned long pend, pgprot_t prot,
+					    bool use_huge)
 {
 	unsigned long vstart = PAGE_OFFSET + pstart;
 	unsigned long vend = PAGE_OFFSET + pend;
@@ -1377,19 +1515,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 		pmd_t *pmd;
 		pte_t *pte;
 
+		if (pgd_none(*pgd)) {
+			pud_t *new;
+
+			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+			alloc_bytes += PAGE_SIZE;
+			pgd_populate(&init_mm, pgd, new);
+		}
 		pud = pud_offset(pgd, vstart);
 		if (pud_none(*pud)) {
 			pmd_t *new;
 
+			if (kernel_can_map_hugepud(vstart, vend, use_huge)) {
+				vstart = kernel_map_hugepud(vstart, vend, pud);
+				continue;
+			}
 			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
 			alloc_bytes += PAGE_SIZE;
 			pud_populate(&init_mm, pud, new);
 		}
 
 		pmd = pmd_offset(pud, vstart);
-		if (!pmd_present(*pmd)) {
+		if (pmd_none(*pmd)) {
 			pte_t *new;
 
+			if (kernel_can_map_hugepmd(vstart, vend, use_huge)) {
+				vstart = kernel_map_hugepmd(vstart, vend, pmd);
+				continue;
+			}
 			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
 			alloc_bytes += PAGE_SIZE;
 			pmd_populate_kernel(&init_mm, pmd, new);
@@ -1412,100 +1565,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 	return alloc_bytes;
 }
 
-extern unsigned int kvmap_linear_patch[1];
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
-static void __init kpte_set_val(unsigned long index, unsigned long val)
-{
-	unsigned long *ptr = kpte_linear_bitmap;
-
-	val <<= ((index % (BITS_PER_LONG / 2)) * 2);
-	ptr += (index / (BITS_PER_LONG / 2));
-
-	*ptr |= val;
-}
-
-static const unsigned long kpte_shift_min = 28; /* 256MB */
-static const unsigned long kpte_shift_max = 34; /* 16GB */
-static const unsigned long kpte_shift_incr = 3;
-
-static unsigned long kpte_mark_using_shift(unsigned long start, unsigned long end,
-					   unsigned long shift)
+static void __init flush_all_kernel_tsbs(void)
 {
-	unsigned long size = (1UL << shift);
-	unsigned long mask = (size - 1UL);
-	unsigned long remains = end - start;
-	unsigned long val;
-
-	if (remains < size || (start & mask))
-		return start;
-
-	/* VAL maps:
-	 *
-	 *	shift 28 --> kern_linear_pte_xor index 1
-	 *	shift 31 --> kern_linear_pte_xor index 2
-	 *	shift 34 --> kern_linear_pte_xor index 3
-	 */
-	val = ((shift - kpte_shift_min) / kpte_shift_incr) + 1;
-
-	remains &= ~mask;
-	if (shift != kpte_shift_max)
-		remains = size;
-
-	while (remains) {
-		unsigned long index = start >> kpte_shift_min;
+	int i;
 
-		kpte_set_val(index, val);
+	for (i = 0; i < KERNEL_TSB_NENTRIES; i++) {
+		struct tsb *ent = &swapper_tsb[i];
 
-		start += 1UL << kpte_shift_min;
-		remains -= 1UL << kpte_shift_min;
+		ent->tag = (1UL << TSB_TAG_INVALID_BIT);
 	}
+#ifndef CONFIG_DEBUG_PAGEALLOC
+	for (i = 0; i < KERNEL_TSB4M_NENTRIES; i++) {
+		struct tsb *ent = &swapper_4m_tsb[i];
 
-	return start;
-}
-
-static void __init mark_kpte_bitmap(unsigned long start, unsigned long end)
-{
-	unsigned long smallest_size, smallest_mask;
-	unsigned long s;
-
-	smallest_size = (1UL << kpte_shift_min);
-	smallest_mask = (smallest_size - 1UL);
-
-	while (start < end) {
-		unsigned long orig_start = start;
-
-		for (s = kpte_shift_max; s >= kpte_shift_min; s -= kpte_shift_incr) {
-			start = kpte_mark_using_shift(start, end, s);
-
-			if (start != orig_start)
-				break;
-		}
-
-		if (start == orig_start)
-			start = (start + smallest_size) & ~smallest_mask;
+		ent->tag = (1UL << TSB_TAG_INVALID_BIT);
 	}
+#endif
 }
 
-static void __init init_kpte_bitmap(void)
-{
-	unsigned long i;
-
-	for (i = 0; i < pall_ents; i++) {
-		unsigned long phys_start, phys_end;
-
-		phys_start = pall[i].phys_addr;
-		phys_end = phys_start + pall[i].reg_size;
-
-		mark_kpte_bitmap(phys_start, phys_end);
-	}
-}
+extern unsigned int kvmap_linear_patch[1];
 
 static void __init kernel_physical_mapping_init(void)
 {
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	unsigned long i, mem_alloced = 0UL;
+	bool use_huge = true;
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	use_huge = false;
+#endif
 	for (i = 0; i < pall_ents; i++) {
 		unsigned long phys_start, phys_end;
 
@@ -1513,7 +1600,7 @@ static void __init kernel_physical_mapping_init(void)
 		phys_end = phys_start + pall[i].reg_size;
 
 		mem_alloced += kernel_map_range(phys_start, phys_end,
-						PAGE_KERNEL);
+						PAGE_KERNEL, use_huge);
 	}
 
 	printk("Allocated %ld bytes for kernel page tables.\n",
@@ -1522,8 +1609,9 @@ static void __init kernel_physical_mapping_init(void)
 	kvmap_linear_patch[0] = 0x01000000; /* nop */
 	flushi(&kvmap_linear_patch[0]);
 
+	flush_all_kernel_tsbs();
+
 	__flush_tlb_all();
-#endif
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -1533,7 +1621,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	unsigned long phys_end = phys_start + (numpages * PAGE_SIZE);
 
 	kernel_map_range(phys_start, phys_end,
-			 (enable ? PAGE_KERNEL : __pgprot(0)));
+			 (enable ? PAGE_KERNEL : __pgprot(0)), false);
 
 	flush_tsb_kernel_range(PAGE_OFFSET + phys_start,
 			       PAGE_OFFSET + phys_end);
@@ -1561,76 +1649,56 @@ unsigned long __init find_ecache_flush_span(unsigned long size)
 unsigned long PAGE_OFFSET;
 EXPORT_SYMBOL(PAGE_OFFSET);
 
-static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits)
-{
-	unsigned long final_shift;
-	unsigned int val = *insn;
-	unsigned int cnt;
-
-	/* We are patching in ilog2(max_supported_phys_address), and
-	 * we are doing so in a manner similar to a relocation addend.
-	 * That is, we are adding the shift value to whatever value
-	 * is in the shift instruction count field already.
-	 */
-	cnt = (val & 0x3f);
-	val &= ~0x3f;
-
-	/* If we are trying to shift >= 64 bits, clear the destination
-	 * register.  This can happen when phys_bits ends up being equal
-	 * to MAX_PHYS_ADDRESS_BITS.
-	 */
-	final_shift = (cnt + (64 - phys_bits));
-	if (final_shift >= 64) {
-		unsigned int rd = (val >> 25) & 0x1f;
-
-		val = 0x80100000 | (rd << 25);
-	} else {
-		val |= final_shift;
-	}
-	*insn = val;
-
-	__asm__ __volatile__("flush	%0"
-			     : /* no outputs */
-			     : "r" (insn));
-}
-
-static void __init page_offset_shift_patch(unsigned long phys_bits)
-{
-	extern unsigned int __page_offset_shift_patch;
-	extern unsigned int __page_offset_shift_patch_end;
-	unsigned int *p;
-
-	p = &__page_offset_shift_patch;
-	while (p < &__page_offset_shift_patch_end) {
-		unsigned int *insn = (unsigned int *)(unsigned long)*p;
+unsigned long VMALLOC_END   = 0x0000010000000000UL;
+EXPORT_SYMBOL(VMALLOC_END);
 
-		page_offset_shift_patch_one(insn, phys_bits);
-
-		p++;
-	}
-}
+unsigned long sparc64_va_hole_top =    0xfffff80000000000UL;
+unsigned long sparc64_va_hole_bottom = 0x0000080000000000UL;
 
 static void __init setup_page_offset(void)
 {
-	unsigned long max_phys_bits = 40;
-
 	if (tlb_type == cheetah || tlb_type == cheetah_plus) {
+		/* Cheetah/Panther support a full 64-bit virtual
+		 * address, so we can use all that our page tables
+		 * support.
+		 */
+		sparc64_va_hole_top =    0xfff0000000000000UL;
+		sparc64_va_hole_bottom = 0x0010000000000000UL;
+
 		max_phys_bits = 42;
 	} else if (tlb_type == hypervisor) {
 		switch (sun4v_chip_type) {
 		case SUN4V_CHIP_NIAGARA1:
 		case SUN4V_CHIP_NIAGARA2:
+			/* T1 and T2 support 48-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xffff800000000000UL;
+			sparc64_va_hole_bottom = 0x0000800000000000UL;
+
 			max_phys_bits = 39;
 			break;
 		case SUN4V_CHIP_NIAGARA3:
+			/* T3 supports 48-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xffff800000000000UL;
+			sparc64_va_hole_bottom = 0x0000800000000000UL;
+
 			max_phys_bits = 43;
 			break;
 		case SUN4V_CHIP_NIAGARA4:
 		case SUN4V_CHIP_NIAGARA5:
 		case SUN4V_CHIP_SPARC64X:
-		default:
+		case SUN4V_CHIP_SPARC_M6:
+			/* T4 and later support 52-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xfff8000000000000UL;
+			sparc64_va_hole_bottom = 0x0008000000000000UL;
 			max_phys_bits = 47;
 			break;
+		case SUN4V_CHIP_SPARC_M7:
+		default:
+			/* M7 and later support 52-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xfff8000000000000UL;
+			sparc64_va_hole_bottom = 0x0008000000000000UL;
+			max_phys_bits = 49;
+			break;
 		}
 	}
 
@@ -1640,12 +1708,16 @@ static void __init setup_page_offset(void)
 		prom_halt();
 	}
 
-	PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits);
+	PAGE_OFFSET = sparc64_va_hole_top;
+	VMALLOC_END = ((sparc64_va_hole_bottom >> 1) +
+		       (sparc64_va_hole_bottom >> 2));
 
-	pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n",
+	pr_info("MM: PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n",
 		PAGE_OFFSET, max_phys_bits);
-
-	page_offset_shift_patch(max_phys_bits);
+	pr_info("MM: VMALLOC [0x%016lx --> 0x%016lx]\n",
+		VMALLOC_START, VMALLOC_END);
+	pr_info("MM: VMEMMAP [0x%016lx --> 0x%016lx]\n",
+		VMEMMAP_BASE, VMEMMAP_BASE << 1);
 }
 
 static void __init tsb_phys_patch(void)
@@ -1690,21 +1762,42 @@ static void __init tsb_phys_patch(void)
 #define NUM_KTSB_DESCR	1
 #endif
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
-extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
+
+/* The swapper TSBs are loaded with a base sequence of:
+ *
+ *	sethi	%uhi(SYMBOL), REG1
+ *	sethi	%hi(SYMBOL), REG2
+ *	or	REG1, %ulo(SYMBOL), REG1
+ *	or	REG2, %lo(SYMBOL), REG2
+ *	sllx	REG1, 32, REG1
+ *	or	REG1, REG2, REG1
+ *
+ * When we use physical addressing for the TSB accesses, we patch the
+ * first four instructions in the above sequence.
+ */
 
 static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
 {
-	pa >>= KTSB_PHYS_SHIFT;
+	unsigned long high_bits, low_bits;
+
+	high_bits = (pa >> 32) & 0xffffffff;
+	low_bits = (pa >> 0) & 0xffffffff;
 
 	while (start < end) {
 		unsigned int *ia = (unsigned int *)(unsigned long)*start;
 
-		ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+		ia[0] = (ia[0] & ~0x3fffff) | (high_bits >> 10);
 		__asm__ __volatile__("flush	%0" : : "r" (ia));
 
-		ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+		ia[1] = (ia[1] & ~0x3fffff) | (low_bits >> 10);
 		__asm__ __volatile__("flush	%0" : : "r" (ia + 1));
 
+		ia[2] = (ia[2] & ~0x1fff) | (high_bits & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 2));
+
+		ia[3] = (ia[3] & ~0x1fff) | (low_bits & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 3));
+
 		start++;
 	}
 }
@@ -1843,7 +1936,6 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 /* paging_init() sets up the page tables */
 
 static unsigned long last_valid_pfn;
-pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 static void sun4u_pgprot_init(void);
 static void sun4v_pgprot_init(void);
@@ -1881,7 +1973,7 @@ void __init paging_init(void)
 
 	BUILD_BUG_ON(NR_CPUS > 4096);
 
-	kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
+	kern_base = (prom_boot_mapping_phys_low >> ILOG2_4MB) << ILOG2_4MB;
 	kern_size = (unsigned long)&_end - (unsigned long)KERNBASE;
 
 	/* Invalidate both kernel TSBs.  */
@@ -1937,7 +2029,7 @@ void __init paging_init(void)
 	shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE);
 
 	real_end = (unsigned long)_end;
-	num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << 22);
+	num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << ILOG2_4MB);
 	printk("Kernel: Using %d locked TLB entries for main kernel image.\n",
 	       num_kernel_image_mappings);
 
@@ -1946,16 +2038,10 @@ void __init paging_init(void)
 	 */
 	init_mm.pgd += ((shift) / (sizeof(pgd_t)));
 	
-	memset(swapper_low_pmd_dir, 0, sizeof(swapper_low_pmd_dir));
+	memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir));
 
-	/* Now can init the kernel/bad page tables. */
-	pud_set(pud_offset(&swapper_pg_dir[0], 0),
-		swapper_low_pmd_dir + (shift / sizeof(pgd_t)));
-	
 	inherit_prom_mappings();
 	
-	init_kpte_bitmap();
-
 	/* Ok, we can use our TLB miss and window trap handlers safely.  */
 	setup_tba();
 
@@ -2062,70 +2148,6 @@ int page_in_phys_avail(unsigned long paddr)
 	return 0;
 }
 
-static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata;
-static int pavail_rescan_ents __initdata;
-
-/* Certain OBP calls, such as fetching "available" properties, can
- * claim physical memory.  So, along with initializing the valid
- * address bitmap, what we do here is refetch the physical available
- * memory list again, and make sure it provides at least as much
- * memory as 'pavail' does.
- */
-static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap)
-{
-	int i;
-
-	read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents);
-
-	for (i = 0; i < pavail_ents; i++) {
-		unsigned long old_start, old_end;
-
-		old_start = pavail[i].phys_addr;
-		old_end = old_start + pavail[i].reg_size;
-		while (old_start < old_end) {
-			int n;
-
-			for (n = 0; n < pavail_rescan_ents; n++) {
-				unsigned long new_start, new_end;
-
-				new_start = pavail_rescan[n].phys_addr;
-				new_end = new_start +
-					pavail_rescan[n].reg_size;
-
-				if (new_start <= old_start &&
-				    new_end >= (old_start + PAGE_SIZE)) {
-					set_bit(old_start >> 22, bitmap);
-					goto do_next_page;
-				}
-			}
-
-			prom_printf("mem_init: Lost memory in pavail\n");
-			prom_printf("mem_init: OLD start[%lx] size[%lx]\n",
-				    pavail[i].phys_addr,
-				    pavail[i].reg_size);
-			prom_printf("mem_init: NEW start[%lx] size[%lx]\n",
-				    pavail_rescan[i].phys_addr,
-				    pavail_rescan[i].reg_size);
-			prom_printf("mem_init: Cannot continue, aborting.\n");
-			prom_halt();
-
-		do_next_page:
-			old_start += PAGE_SIZE;
-		}
-	}
-}
-
-static void __init patch_tlb_miss_handler_bitmap(void)
-{
-	extern unsigned int valid_addr_bitmap_insn[];
-	extern unsigned int valid_addr_bitmap_patch[];
-
-	valid_addr_bitmap_insn[1] = valid_addr_bitmap_patch[1];
-	mb();
-	valid_addr_bitmap_insn[0] = valid_addr_bitmap_patch[0];
-	flushi(&valid_addr_bitmap_insn[0]);
-}
-
 static void __init register_page_bootmem_info(void)
 {
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -2138,18 +2160,6 @@ static void __init register_page_bootmem_info(void)
 }
 void __init mem_init(void)
 {
-	unsigned long addr, last;
-
-	addr = PAGE_OFFSET + kern_base;
-	last = PAGE_ALIGN(kern_size) + addr;
-	while (addr < last) {
-		set_bit(__pa(addr) >> 22, sparc64_valid_addr_bitmap);
-		addr += PAGE_SIZE;
-	}
-
-	setup_valid_addr_bitmap_from_pavail(sparc64_valid_addr_bitmap);
-	patch_tlb_miss_handler_bitmap();
-
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
 	register_page_bootmem_info();
@@ -2239,18 +2249,9 @@ unsigned long _PAGE_CACHE __read_mostly;
 EXPORT_SYMBOL(_PAGE_CACHE);
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-unsigned long vmemmap_table[VMEMMAP_SIZE];
-
-static long __meminitdata addr_start, addr_end;
-static int __meminitdata node_start;
-
 int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 			       int node)
 {
-	unsigned long phys_start = (vstart - VMEMMAP_BASE);
-	unsigned long phys_end = (vend - VMEMMAP_BASE);
-	unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK;
-	unsigned long end = VMEMMAP_ALIGN(phys_end);
 	unsigned long pte_base;
 
 	pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U |
@@ -2261,47 +2262,52 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 			    _PAGE_CP_4V | _PAGE_CV_4V |
 			    _PAGE_P_4V | _PAGE_W_4V);
 
-	for (; addr < end; addr += VMEMMAP_CHUNK) {
-		unsigned long *vmem_pp =
-			vmemmap_table + (addr >> VMEMMAP_CHUNK_SHIFT);
-		void *block;
+	pte_base |= _PAGE_PMD_HUGE;
 
-		if (!(*vmem_pp & _PAGE_VALID)) {
-			block = vmemmap_alloc_block(1UL << 22, node);
-			if (!block)
+	vstart = vstart & PMD_MASK;
+	vend = ALIGN(vend, PMD_SIZE);
+	for (; vstart < vend; vstart += PMD_SIZE) {
+		pgd_t *pgd = pgd_offset_k(vstart);
+		unsigned long pte;
+		pud_t *pud;
+		pmd_t *pmd;
+
+		if (pgd_none(*pgd)) {
+			pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
+
+			if (!new)
 				return -ENOMEM;
+			pgd_populate(&init_mm, pgd, new);
+		}
 
-			*vmem_pp = pte_base | __pa(block);
+		pud = pud_offset(pgd, vstart);
+		if (pud_none(*pud)) {
+			pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
 
-			/* check to see if we have contiguous blocks */
-			if (addr_end != addr || node_start != node) {
-				if (addr_start)
-					printk(KERN_DEBUG " [%lx-%lx] on node %d\n",
-					       addr_start, addr_end-1, node_start);
-				addr_start = addr;
-				node_start = node;
-			}
-			addr_end = addr + VMEMMAP_CHUNK;
+			if (!new)
+				return -ENOMEM;
+			pud_populate(&init_mm, pud, new);
 		}
-	}
-	return 0;
-}
 
-void __meminit vmemmap_populate_print_last(void)
-{
-	if (addr_start) {
-		printk(KERN_DEBUG " [%lx-%lx] on node %d\n",
-		       addr_start, addr_end-1, node_start);
-		addr_start = 0;
-		addr_end = 0;
-		node_start = 0;
+		pmd = pmd_offset(pud, vstart);
+
+		pte = pmd_val(*pmd);
+		if (!(pte & _PAGE_VALID)) {
+			void *block = vmemmap_alloc_block(PMD_SIZE, node);
+
+			if (!block)
+				return -ENOMEM;
+
+			pmd_val(*pmd) = pte_base | __pa(block);
+		}
 	}
+
+	return 0;
 }
 
 void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
-
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 static void prot_init_common(unsigned long page_none,
@@ -2614,6 +2620,10 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	pte = pmd_val(entry);
 
+	/* Don't insert a non-valid PMD into the TSB, we'll deadlock.  */
+	if (!(pte & _PAGE_VALID))
+		return;
+
 	/* We are fabricating 8MB pages using 4MB real hw pages.  */
 	pte |= (addr & (1UL << REAL_HPAGE_SHIFT));
 
@@ -2694,3 +2704,26 @@ void hugetlb_setup(struct pt_regs *regs)
 	}
 }
 #endif
+
+#ifdef CONFIG_SMP
+#define do_flush_tlb_kernel_range	smp_flush_tlb_kernel_range
+#else
+#define do_flush_tlb_kernel_range	__flush_tlb_kernel_range
+#endif
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) {
+		if (start < LOW_OBP_ADDRESS) {
+			flush_tsb_kernel_range(start, LOW_OBP_ADDRESS);
+			do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS);
+		}
+		if (end > HI_OBP_ADDRESS) {
+			flush_tsb_kernel_range(HI_OBP_ADDRESS, end);
+			do_flush_tlb_kernel_range(HI_OBP_ADDRESS, end);
+		}
+	} else {
+		flush_tsb_kernel_range(start, end);
+		do_flush_tlb_kernel_range(start, end);
+	}
+}
diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h
index 5d3782deb403..ac491193cb54 100644
--- a/arch/sparc/mm/init_64.h
+++ b/arch/sparc/mm/init_64.h
@@ -8,15 +8,8 @@
  */
 
 #define MAX_PHYS_ADDRESS	(1UL << MAX_PHYS_ADDRESS_BITS)
-#define KPTE_BITMAP_CHUNK_SZ		(256UL * 1024UL * 1024UL)
-#define KPTE_BITMAP_BYTES	\
-	((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 4)
-#define VALID_ADDR_BITMAP_CHUNK_SZ	(4UL * 1024UL * 1024UL)
-#define VALID_ADDR_BITMAP_BYTES	\
-	((MAX_PHYS_ADDRESS / VALID_ADDR_BITMAP_CHUNK_SZ) / 8)
 
 extern unsigned long kern_linear_pte_xor[4];
-extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
 extern unsigned int sparc64_highest_unlocked_tlb_ent;
 extern unsigned long sparc64_kern_pri_context;
 extern unsigned long sparc64_kern_pri_nuc_bits;
@@ -38,15 +31,4 @@ extern unsigned long kern_locked_tte_data;
 
 extern void prom_world(int enter);
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#define VMEMMAP_CHUNK_SHIFT	22
-#define VMEMMAP_CHUNK		(1UL << VMEMMAP_CHUNK_SHIFT)
-#define VMEMMAP_CHUNK_MASK	~(VMEMMAP_CHUNK - 1UL)
-#define VMEMMAP_ALIGN(x)	(((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK)
-
-#define VMEMMAP_SIZE	((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \
-			  sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT)
-extern unsigned long vmemmap_table[VMEMMAP_SIZE];
-#endif
-
 #endif /* _SPARC64_MM_INIT_H */
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index b12cb5e72812..b89aba217e3b 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -134,7 +134,7 @@ no_cache_flush:
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
-			       pmd_t pmd, bool exec)
+			       pmd_t pmd)
 {
 	unsigned long end;
 	pte_t *pte;
@@ -142,8 +142,11 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 	pte = pte_offset_map(&pmd, vaddr);
 	end = vaddr + HPAGE_SIZE;
 	while (vaddr < end) {
-		if (pte_val(*pte) & _PAGE_VALID)
+		if (pte_val(*pte) & _PAGE_VALID) {
+			bool exec = pte_exec(*pte);
+
 			tlb_batch_add_one(mm, vaddr, exec);
+		}
 		pte++;
 		vaddr += PAGE_SIZE;
 	}
@@ -177,19 +180,30 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 
 	if (!pmd_none(orig)) {
-		pte_t orig_pte = __pte(pmd_val(orig));
-		bool exec = pte_exec(orig_pte);
-
 		addr &= HPAGE_MASK;
 		if (pmd_trans_huge(orig)) {
+			pte_t orig_pte = __pte(pmd_val(orig));
+			bool exec = pte_exec(orig_pte);
+
 			tlb_batch_add_one(mm, addr, exec);
 			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec);
 		} else {
-			tlb_batch_pmd_scan(mm, addr, orig, exec);
+			tlb_batch_pmd_scan(mm, addr, orig);
 		}
 	}
 }
 
+void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pmd_t *pmdp)
+{
+	pmd_t entry = *pmdp;
+
+	pmd_val(entry) &= ~_PAGE_VALID;
+
+	set_pmd_at(vma->vm_mm, address, pmdp, entry);
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				pgtable_t pgtable)
 {
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index f5d506fdddad..fe19b81acc09 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -133,7 +133,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 	mm->context.tsb_block[tsb_idx].tsb_nentries =
 		tsb_bytes / sizeof(struct tsb);
 
-	base = TSBMAP_BASE;
+	switch (tsb_idx) {
+	case MM_TSB_BASE:
+		base = TSBMAP_8K_BASE;
+		break;
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	case MM_TSB_HUGE:
+		base = TSBMAP_4M_BASE;
+		break;
+#endif
+	default:
+		BUG();
+	}
+
 	tte = pgprot_val(PAGE_KERNEL_LOCKED);
 	tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb);
 	BUG_ON(tsb_paddr & (tsb_bytes - 1UL));
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 01fe9946d388..44d258da0a1b 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define BNE		(F2(0, 2) | CONDNE)
 
 #ifdef CONFIG_SPARC64
-#define BNE_PTR		(F2(0, 1) | CONDNE | (2 << 20))
+#define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
 #else
-#define BNE_PTR		BNE
+#define BE_PTR		BE
 #endif
 
 #define SETHI(K, REG)	\
@@ -600,7 +600,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ANC_IFINDEX:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load32(r_A, struct net_device, ifindex, r_A);
 				break;
@@ -613,7 +613,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ANC_HATYPE:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load16(r_A, struct net_device, type, r_A);
 				break;
diff --git a/arch/sparc/power/hibernate_asm.S b/arch/sparc/power/hibernate_asm.S
index 79942166df84..d7d9017dcb15 100644
--- a/arch/sparc/power/hibernate_asm.S
+++ b/arch/sparc/power/hibernate_asm.S
@@ -54,8 +54,8 @@ ENTRY(swsusp_arch_resume)
 	 nop
 
 	/* Write PAGE_OFFSET to %g7 */
-	sethi	%uhi(PAGE_OFFSET), %g7
-	sllx	%g7, 32, %g7
+	sethi	%hi(PAGE_OFFSET), %g7
+	ldx	[%g7 + %lo(PAGE_OFFSET)], %g7
 
 	setuw	(PAGE_SIZE-8), %g3
 
diff --git a/arch/sparc/prom/bootstr_64.c b/arch/sparc/prom/bootstr_64.c
index ab9ccc63b388..7149e77714a4 100644
--- a/arch/sparc/prom/bootstr_64.c
+++ b/arch/sparc/prom/bootstr_64.c
@@ -14,7 +14,10 @@
  *          the .bss section or it will break things.
  */
 
-#define BARG_LEN  256
+/* We limit BARG_LEN to 1024 because this is the size of the
+ * 'barg_out' command line buffer in the SILO bootloader.
+ */
+#define BARG_LEN 1024
 struct {
 	int bootstr_len;
 	int bootstr_valid;
diff --git a/arch/sparc/prom/cif.S b/arch/sparc/prom/cif.S
index 9c86b4b7d429..8050f381f518 100644
--- a/arch/sparc/prom/cif.S
+++ b/arch/sparc/prom/cif.S
@@ -11,11 +11,10 @@
 	.text
 	.globl	prom_cif_direct
 prom_cif_direct:
+	save	%sp, -192, %sp
 	sethi	%hi(p1275buf), %o1
 	or	%o1, %lo(p1275buf), %o1
-	ldx	[%o1 + 0x0010], %o2	! prom_cif_stack
-	save	%o2, -192, %sp
-	ldx	[%i1 + 0x0008], %l2	! prom_cif_handler
+	ldx	[%o1 + 0x0008], %l2	! prom_cif_handler
 	mov	%g4, %l0
 	mov	%g5, %l1
 	mov	%g6, %l3
diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c
index d95db755828f..110b0d78b864 100644
--- a/arch/sparc/prom/init_64.c
+++ b/arch/sparc/prom/init_64.c
@@ -26,13 +26,13 @@ phandle prom_chosen_node;
  * It gets passed the pointer to the PROM vector.
  */
 
-extern void prom_cif_init(void *, void *);
+extern void prom_cif_init(void *);
 
-void __init prom_init(void *cif_handler, void *cif_stack)
+void __init prom_init(void *cif_handler)
 {
 	phandle node;
 
-	prom_cif_init(cif_handler, cif_stack);
+	prom_cif_init(cif_handler);
 
 	prom_chosen_node = prom_finddevice(prom_chosen_path);
 	if (!prom_chosen_node || (s32)prom_chosen_node == -1)
diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c
index e58b81726319..545d8bb79b65 100644
--- a/arch/sparc/prom/p1275.c
+++ b/arch/sparc/prom/p1275.c
@@ -9,6 +9,7 @@
 #include <linux/smp.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
+#include <linux/irqflags.h>
 
 #include <asm/openprom.h>
 #include <asm/oplib.h>
@@ -19,7 +20,6 @@
 struct {
 	long prom_callback;			/* 0x00 */
 	void (*prom_cif_handler)(long *);	/* 0x08 */
-	unsigned long prom_cif_stack;		/* 0x10 */
 } p1275buf;
 
 extern void prom_world(int);
@@ -36,8 +36,8 @@ void p1275_cmd_direct(unsigned long *args)
 {
 	unsigned long flags;
 
-	raw_local_save_flags(flags);
-	raw_local_irq_restore((unsigned long)PIL_NMI);
+	local_save_flags(flags);
+	local_irq_restore((unsigned long)PIL_NMI);
 	raw_spin_lock(&prom_entry_lock);
 
 	prom_world(1);
@@ -45,11 +45,10 @@ void p1275_cmd_direct(unsigned long *args)
 	prom_world(0);
 
 	raw_spin_unlock(&prom_entry_lock);
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 }
 
 void prom_cif_init(void *cif_handler, void *cif_stack)
 {
 	p1275buf.prom_cif_handler = (void (*)(long *))cif_handler;
-	p1275buf.prom_cif_stack = (unsigned long)cif_stack;
 }
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 0cb3bbaa580c..e514899e1100 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -166,11 +166,6 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
 }
 
-int pmd_huge_support(void)
-{
-	return 1;
-}
-
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 3716e6952554..e8ab93c3e638 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q)
 
 	while(1){
 		struct ubd *dev = q->queuedata;
-		if(dev->end_sg == 0){
+		if(dev->request == NULL){
 			struct request *req = blk_fetch_request(q);
 			if(req == NULL)
 				return;
@@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 			}
 			prepare_flush_request(req, io_req);
-			submit_request(io_req, dev);
+			if (submit_request(io_req, dev) == false)
+				return;
 		}
 
 		while(dev->start_sg < dev->end_sg){
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index fb5e4c658f7a..ef470a7a3d0f 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -14,6 +14,8 @@
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
@@ -73,7 +75,7 @@ do { \
 		else \
 			mm->mmap = NULL; \
 		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		mm->mmap_cache = NULL; \
+		vmacache_invalidate(mm); \
 		mm->map_count--; \
 		remove_vma(high_vma); \
 	} \
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
index de7dc5fdd58b..24e836023e6c 100644
--- a/arch/unicore32/mm/alignment.c
+++ b/arch/unicore32/mm/alignment.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
+#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/unaligned.h>
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0af5250d914f..98aa930230ec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -127,6 +127,7 @@ config X86
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
 	select HAVE_CC_STACKPROTECTOR
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -965,10 +966,27 @@ config VM86
 	default y
 	depends on X86_32
 	---help---
-	  This option is required by programs like DOSEMU to run 16-bit legacy
-	  code on X86 processors. It also may be needed by software like
-	  XFree86 to initialize some video cards via BIOS. Disabling this
-	  option saves about 6k.
+	  This option is required by programs like DOSEMU to run
+	  16-bit real mode legacy code on x86 processors. It also may
+	  be needed by software like XFree86 to initialize some video
+	  cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+	bool "Enable support for 16-bit segments" if EXPERT
+	default y
+	---help---
+	  This option is required by programs like Wine to run 16-bit
+	  protected mode legacy code on x86 processors.  Disabling
+	  this option saves about 300 bytes on i386, or around 6K text
+	  plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+	def_bool y
+	depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+	def_bool y
+	depends on X86_16BIT && X86_64
 
 config TOSHIBA
 	tristate "Toshiba Laptop support"
@@ -1579,6 +1597,7 @@ config EFI
 config EFI_STUB
        bool "EFI stub support"
        depends on EFI
+       select RELOCATABLE
        ---help---
           This kernel feature allows a bzImage to be loaded directly
 	  by EFI firmware without the use of a bootloader.
@@ -1909,6 +1928,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y
 	depends on X86_64 || X86_PAE
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	def_bool y
+	depends on X86_64 && HUGETLB_PAGE && MIGRATION
+
 menu "Power management and ACPI options"
 
 config ARCH_HIBERNATION_HEADER
@@ -2413,12 +2436,9 @@ config X86_DMA_REMAP
 	depends on STA2X11
 
 config IOSF_MBI
-	bool
+	tristate
+	default m
 	depends on PCI
-	---help---
-	  To be selected by modules requiring access to the Intel OnChip System
-	  Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms
-	  enumerable by PCI.
 
 source "net/Kconfig"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index eeda43abed6e..0dd99ea1caf1 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -79,6 +79,7 @@ else
         UTS_MACHINE := x86_64
         CHECKFLAGS += -D__x86_64__ -m64
 
+        biarch := -m64
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
@@ -152,6 +153,7 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
 
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 0fcd9133790c..b5bb49866bcc 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -75,8 +75,10 @@ suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
+RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
+	     perl $(srctree)/arch/x86/tools/calc_run_size.pl)
 quiet_cmd_mkpiggy = MKPIGGY $@
-      cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
+      cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
 
 targets += piggy.S
 $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 4dbf967da50d..6cfcf2a2eb93 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -183,12 +183,27 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 static bool mem_avoid_overlap(struct mem_vector *img)
 {
 	int i;
+	struct setup_data *ptr;
 
 	for (i = 0; i < MEM_AVOID_MAX; i++) {
 		if (mem_overlaps(img, &mem_avoid[i]))
 			return true;
 	}
 
+	/* Avoid all entries in the setup_data linked list. */
+	ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data;
+	while (ptr) {
+		struct mem_vector avoid;
+
+		avoid.start = (u64)ptr;
+		avoid.size = sizeof(*ptr) + ptr->len;
+
+		if (mem_overlaps(img, &avoid))
+			return true;
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
+
 	return false;
 }
 
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index feca05fa4536..832a6590e9b3 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -425,6 +425,9 @@ void setup_graphics(struct boot_params *boot_params)
  * Because the x86 boot code expects to be passed a boot_params we
  * need to create one ourselves (usually the bootloader would create
  * one for us).
+ *
+ * The caller is responsible for filling out ->code32_start in the
+ * returned boot_params.
  */
 struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 {
@@ -483,8 +486,6 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 	hdr->vid_mode = 0xffff;
 	hdr->boot_flag = 0xAA55;
 
-	hdr->code32_start = (__u64)(unsigned long)image->image_base;
-
 	hdr->type_of_loader = 0x21;
 
 	/* Convert unicode cmdline to ascii */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 9116aac232c7..c5b56ed10aff 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -50,6 +50,13 @@ ENTRY(efi_pe_entry)
 	pushl	%eax
 	pushl	%esi
 	pushl	%ecx
+
+	call	reloc
+reloc:
+	popl	%ecx
+	subl	reloc, %ecx
+	movl	%ecx, BP_code32_start(%eax)
+
 	sub	$0x4, %esp
 
 ENTRY(efi_stub_entry)
@@ -63,12 +70,7 @@ ENTRY(efi_stub_entry)
 	hlt
 	jmp	1b
 2:
-	call	3f
-3:
-	popl	%eax
-	subl	$3b, %eax
-	subl	BP_pref_address(%esi), %eax
-	add	BP_code32_start(%esi), %eax
+	movl	BP_code32_start(%esi), %eax
 	leal	preferred_addr(%eax), %eax
 	jmp	*%eax
 
@@ -184,7 +186,8 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
 				/* push arguments for decompress_kernel: */
-	pushl	$z_output_len	/* decompressed length */
+	pushl	$z_run_size	/* size of kernel with .bss and .brk */
+	pushl	$z_output_len	/* decompressed length, end of relocs */
 	leal	z_extract_offset_negative(%ebx), %ebp
 	pushl	%ebp		/* output address */
 	pushl	$z_input_len	/* input_len */
@@ -194,7 +197,7 @@ relocated:
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
 	call	decompress_kernel /* returns kernel location in %eax */
-	addl	$24, %esp
+	addl	$28, %esp
 
 /*
  * Jump to the decompressed kernel.
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index c5c1ae0997e7..34bbc0911b7c 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -217,6 +217,8 @@ ENTRY(efi_pe_entry)
 	cmpq	$0,%rax
 	je	1f
 	mov	%rax, %rdx
+	leaq	startup_32(%rip), %rax
+	movl	%eax, BP_code32_start(%rdx)
 	popq	%rsi
 	popq	%rdi
 
@@ -230,12 +232,7 @@ ENTRY(efi_stub_entry)
 	hlt
 	jmp	1b
 2:
-	call	3f
-3:
-	popq	%rax
-	subq	$3b, %rax
-	subq	BP_pref_address(%rsi), %rax
-	add	BP_code32_start(%esi), %eax
+	movl	BP_code32_start(%esi), %eax
 	leaq	preferred_addr(%rax), %rax
 	jmp	*%rax
 
@@ -337,13 +334,16 @@ relocated:
  * Do the decompression, and jump to the new kernel..
  */
 	pushq	%rsi			/* Save the real mode argument */
+	movq	$z_run_size, %r9	/* size of kernel with .bss and .brk */
+	pushq	%r9
 	movq	%rsi, %rdi		/* real mode address */
 	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
 	leaq	input_data(%rip), %rdx  /* input_data */
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
-	movq	$z_output_len, %r9	/* decompressed length */
+	movq	$z_output_len, %r9	/* decompressed length, end of relocs */
 	call	decompress_kernel	/* returns kernel location in %rax */
+	popq	%r9
 	popq	%rsi
 
 /*
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 196eaf373a06..eb25ca1eb6da 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -393,7 +393,8 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
-				  unsigned long output_len)
+				  unsigned long output_len,
+				  unsigned long run_size)
 {
 	real_mode = rmode;
 
@@ -416,8 +417,14 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
-	output = choose_kernel_location(input_data, input_len,
-					output, output_len);
+	/*
+	 * The memory hole needed for the kernel is the larger of either
+	 * the entire decompressed kernel plus relocation table, or the
+	 * entire decompressed kernel plus .bss and .brk sections.
+	 */
+	output = choose_kernel_location(input_data, input_len, output,
+					output_len > run_size ? output_len
+							      : run_size);
 
 	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index b669ab65bf6c..d8222f213182 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -36,11 +36,13 @@ int main(int argc, char *argv[])
 	uint32_t olen;
 	long ilen;
 	unsigned long offs;
+	unsigned long run_size;
 	FILE *f = NULL;
 	int retval = 1;
 
-	if (argc < 2) {
-		fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
+	if (argc < 3) {
+		fprintf(stderr, "Usage: %s compressed_file run_size\n",
+				argv[0]);
 		goto bail;
 	}
 
@@ -74,6 +76,7 @@ int main(int argc, char *argv[])
 	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
 	offs += 64*1024 + 128;	/* Add 64K + 128 bytes slack */
 	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+	run_size = atoi(argv[2]);
 
 	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
 	printf(".globl z_input_len\n");
@@ -85,6 +88,8 @@ int main(int argc, char *argv[])
 	/* z_extract_offset_negative allows simplification of head_32.S */
 	printf(".globl z_extract_offset_negative\n");
 	printf("z_extract_offset_negative = -0x%lx\n", offs);
+	printf(".globl z_run_size\n");
+	printf("z_run_size = %lu\n", run_size);
 
 	printf(".globl input_data, input_data_end\n");
 	printf("input_data:\n");
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index ec3b8ba68096..04da6c2194ba 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -91,10 +91,9 @@ bs_die:
 
 	.section ".bsdata", "a"
 bugger_off_msg:
-	.ascii	"Direct floppy boot is not supported. "
-	.ascii	"Use a boot loader program instead.\r\n"
+	.ascii	"Use a boot loader.\r\n"
 	.ascii	"\n"
-	.ascii	"Remove disk and press any key to reboot ...\r\n"
+	.ascii	"Remove disk and press any key to reboot...\r\n"
 	.byte	0
 
 #ifdef CONFIG_EFI_STUB
@@ -108,7 +107,7 @@ coff_header:
 #else
 	.word	0x8664				# x86-64
 #endif
-	.word	3				# nr_sections
+	.word	4				# nr_sections
 	.long	0 				# TimeDateStamp
 	.long	0				# PointerToSymbolTable
 	.long	1				# NumberOfSymbols
@@ -250,6 +249,25 @@ section_table:
 	.word	0				# NumberOfLineNumbers
 	.long	0x60500020			# Characteristics (section flags)
 
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".bss"
+	.byte	0
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0xc8000080			# Characteristics (section flags)
+
 #endif /* CONFIG_EFI_STUB */
 
 	# Kernel attributes; used by setup.  This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 8e15b22391fc..3dafaeb9f549 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -142,7 +142,7 @@ static void usage(void)
 
 #ifdef CONFIG_EFI_STUB
 
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
 {
 	unsigned int pe_header;
 	unsigned short num_sections;
@@ -163,10 +163,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 			put_unaligned_le32(size, section + 0x8);
 
 			/* section header vma field */
-			put_unaligned_le32(offset, section + 0xc);
+			put_unaligned_le32(vma, section + 0xc);
 
 			/* section header 'size of initialised data' field */
-			put_unaligned_le32(size, section + 0x10);
+			put_unaligned_le32(datasz, section + 0x10);
 
 			/* section header 'file offset' field */
 			put_unaligned_le32(offset, section + 0x14);
@@ -178,6 +178,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 	}
 }
 
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+	update_pecoff_section_header_fields(section_name, offset, size, size, offset);
+}
+
 static void update_pecoff_setup_and_reloc(unsigned int size)
 {
 	u32 setup_offset = 0x200;
@@ -202,9 +207,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 
 	pe_header = get_unaligned_le32(&buf[0x3c]);
 
-	/* Size of image */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
 	/*
 	 * Size of code: Subtract the size of the first sector (512 bytes)
 	 * which includes the header.
@@ -219,6 +221,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 	update_pecoff_section_header(".text", text_start, text_sz);
 }
 
+static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz)
+{
+	unsigned int pe_header;
+	unsigned int bss_sz = init_sz - file_sz;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/* Size of uninitialized data */
+	put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]);
+
+	/* Size of image */
+	put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
+
+	update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0);
+}
+
 #endif /* CONFIG_EFI_STUB */
 
 
@@ -270,6 +288,9 @@ int main(int argc, char ** argv)
 	int fd;
 	void *kernel;
 	u32 crc = 0xffffffffUL;
+#ifdef CONFIG_EFI_STUB
+	unsigned int init_sz;
+#endif
 
 	/* Defaults for old kernel */
 #ifdef CONFIG_X86_32
@@ -343,7 +364,9 @@ int main(int argc, char ** argv)
 	put_unaligned_le32(sys_size, &buf[0x1f4]);
 
 #ifdef CONFIG_EFI_STUB
-	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+	update_pecoff_text(setup_sectors * 512, i + (sys_size * 16));
+	init_sz = get_unaligned_le32(&buf[0x260]);
+	update_pecoff_bss(i + (sys_size * 16), init_sz);
 
 #ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
 	efi_stub_entry -= 0x200;
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 586f41aac361..185fad49d86f 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -24,10 +24,6 @@
 .align 16
 .Lbswap_mask:
 	.octa 0x000102030405060708090a0b0c0d0e0f
-.Lpoly:
-	.octa 0xc2000000000000000000000000000001
-.Ltwo_one:
-	.octa 0x00000001000000000000000000000001
 
 #define DATA	%xmm0
 #define SHASH	%xmm1
@@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update)
 .Lupdate_just_ret:
 	ret
 ENDPROC(clmul_ghash_update)
-
-/*
- * void clmul_ghash_setkey(be128 *shash, const u8 *key);
- *
- * Calculate hash_key << 1 mod poly
- */
-ENTRY(clmul_ghash_setkey)
-	movaps .Lbswap_mask, BSWAP
-	movups (%rsi), %xmm0
-	PSHUFB_XMM BSWAP %xmm0
-	movaps %xmm0, %xmm1
-	psllq $1, %xmm0
-	psrlq $63, %xmm1
-	movaps %xmm1, %xmm2
-	pslldq $8, %xmm1
-	psrldq $8, %xmm2
-	por %xmm1, %xmm0
-	# reduction
-	pshufd $0b00100100, %xmm2, %xmm1
-	pcmpeqd .Ltwo_one, %xmm1
-	pand .Lpoly, %xmm1
-	pxor %xmm1, %xmm0
-	movups %xmm0, (%rdi)
-	ret
-ENDPROC(clmul_ghash_setkey)
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 6759dd1135be..d785cf2c529c 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -30,8 +30,6 @@ void clmul_ghash_mul(char *dst, const be128 *shash);
 void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
 			const be128 *shash);
 
-void clmul_ghash_setkey(be128 *shash, const u8 *key);
-
 struct ghash_async_ctx {
 	struct cryptd_ahash *cryptd_tfm;
 };
@@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
 	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	be128 *x = (be128 *)key;
+	u64 a, b;
 
 	if (keylen != GHASH_BLOCK_SIZE) {
 		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	clmul_ghash_setkey(&ctx->shash, key);
+	/* perform multiplication by 'x' in GF(2^128) */
+	a = be64_to_cpu(x->a);
+	b = be64_to_cpu(x->b);
+
+	ctx->shash.a = (__be64)((b << 1) | (a >> 63));
+	ctx->shash.b = (__be64)((a << 1) | (b >> 63));
+
+	if (a >> 63)
+		ctx->shash.b ^= cpu_to_be64(0xc2);
 
 	return 0;
 }
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index f30cd10293f0..8626b03e83b7 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -141,7 +141,7 @@ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out)
 
 	/* save number of bits */
 	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3) | sctx->count[0] >> 61;
+	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
 
 	/* Pad out to 112 mod 128 and append length */
 	index = sctx->count[0] & 0x7f;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 4299eb05023c..92a2e9333620 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target)
 1:	movl	(%rbp),%ebp
 	_ASM_EXTABLE(1b,ia32_badarg)
 	ASM_CLAC
+
+	/*
+	 * Sysenter doesn't filter flags, so we need to clear NT
+	 * ourselves.  To save a few cycles, we can check whether
+	 * NT was set instead of doing an unconditional popfq.
+	 */
+	testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp)
+	jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
 	orl     $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	testl   $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	CFI_REMEMBER_STATE
@@ -184,6 +194,8 @@ sysexit_from_sys_call:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS_SYSEXIT32
 
+	CFI_RESTORE_STATE
+
 #ifdef CONFIG_AUDITSYSCALL
 	.macro auditsys_entry_common
 	movl %esi,%r9d			/* 6th arg: 4th syscall arg */
@@ -226,7 +238,6 @@ sysexit_from_sys_call:
 	.endm
 
 sysenter_auditsys:
-	CFI_RESTORE_STATE
 	auditsys_entry_common
 	movl %ebp,%r9d			/* reload 6th syscall arg */
 	jmp sysenter_dispatch
@@ -235,6 +246,11 @@ sysexit_audit:
 	auditsys_exit sysexit_from_sys_call
 #endif
 
+sysenter_fix_flags:
+	pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+	popfq_cfi
+	jmp sysenter_flags_fixed
+
 sysenter_tracesys:
 #ifdef CONFIG_AUDITSYSCALL
 	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e099f9502ace..1717156f4dd1 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -203,6 +203,7 @@
 #define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
 #define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+#define X86_FEATURE_VMMCALL	(8*32+15) /* Prefer vmmcall to vmcall */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
@@ -217,9 +218,13 @@
 #define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_MPX		(9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	(9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_RDSEED	(9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		(9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	(9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512PF	(9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	(9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	(9*32+28) /* AVX-512 Conflict Detection */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index acd86c850414..f949715e3957 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -130,7 +130,8 @@ extern void efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
-extern void efi_setup_page_tables(void);
+extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
 extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_mkexec(void);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9c999c1674fa..01f15b227d7e 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -155,8 +155,9 @@ do {						\
 #define elf_check_arch(x)			\
 	((x)->e_machine == EM_X86_64)
 
-#define compat_elf_check_arch(x)		\
-	(elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+#define compat_elf_check_arch(x)					\
+	(elf_check_arch_ia32(x) ||					\
+	 (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
 
 #if __USER32_DS != __USER_DS
 # error "The following code assumes __USER32_DS == __USER_DS"
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
new file mode 100644
index 000000000000..99efebb2f69d
--- /dev/null
+++ b/arch/x86/include/asm/espfix.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 7252cd339175..6762a55b798a 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -123,14 +123,14 @@ enum fixed_addresses {
 	__end_of_permanent_fixed_addresses,
 
 	/*
-	 * 256 temporary boot-time mappings, used by early_ioremap(),
+	 * 512 temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.
 	 *
-	 * If necessary we round it up to the next 256 pages boundary so
+	 * If necessary we round it up to the next 512 pages boundary so
 	 * that we can have a single pgd entry and a single pte table:
 	 */
 #define NR_FIX_BTMAPS		64
-#define FIX_BTMAPS_SLOTS	4
+#define FIX_BTMAPS_SLOTS	8
 #define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
 	FIX_BTMAP_END =
 	 (__end_of_permanent_fixed_addresses ^
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index a8091216963b..68c05398bba9 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
+	ptep_clear_flush(vma, addr, ptep);
 }
 
 static inline int huge_pte_none(pte_t pte)
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 8e71c7941767..57995f0596a6 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -50,6 +50,32 @@
 #define BT_MBI_PCIE_READ	0x00
 #define BT_MBI_PCIE_WRITE	0x01
 
+/* Quark available units */
+#define QRK_MBI_UNIT_HBA	0x00
+#define QRK_MBI_UNIT_HB	0x03
+#define QRK_MBI_UNIT_RMU	0x04
+#define QRK_MBI_UNIT_MM	0x05
+#define QRK_MBI_UNIT_MMESRAM	0x05
+#define QRK_MBI_UNIT_SOC	0x31
+
+/* Quark read/write opcodes */
+#define QRK_MBI_HBA_READ	0x10
+#define QRK_MBI_HBA_WRITE	0x11
+#define QRK_MBI_HB_READ	0x10
+#define QRK_MBI_HB_WRITE	0x11
+#define QRK_MBI_RMU_READ	0x10
+#define QRK_MBI_RMU_WRITE	0x11
+#define QRK_MBI_MM_READ	0x10
+#define QRK_MBI_MM_WRITE	0x11
+#define QRK_MBI_MMESRAM_READ	0x12
+#define QRK_MBI_MMESRAM_WRITE	0x13
+#define QRK_MBI_SOC_READ	0x06
+#define QRK_MBI_SOC_WRITE	0x07
+
+#if IS_ENABLED(CONFIG_IOSF_MBI)
+
+bool iosf_mbi_available(void);
+
 /**
  * iosf_mbi_read() - MailBox Interface read command
  * @port:	port indicating subunit being accessed
@@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr);
  */
 int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask);
 
+#else /* CONFIG_IOSF_MBI is not enabled */
+static inline
+bool iosf_mbi_available(void)
+{
+	return false;
+}
+
+static inline
+int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
+{
+	WARN(1, "IOSF_MBI driver not available");
+	return -EPERM;
+}
+
+static inline
+int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr)
+{
+	WARN(1, "IOSF_MBI driver not available");
+	return -EPERM;
+}
+
+static inline
+int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)
+{
+	WARN(1, "IOSF_MBI driver not available");
+	return -EPERM;
+}
+#endif /* CONFIG_IOSF_MBI */
+
 #endif /* IOSF_MBI_SYMS_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf88e624..0a8b519226b8 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
 
 #define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
 
-#define INTERRUPT_RETURN	iretq
+#define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
 	sysretq;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fdf83afbb7d9..829e3088b5a0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -103,10 +103,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 
 #define ASYNC_PF_PER_VCPU 64
 
-struct kvm_vcpu;
-struct kvm;
-struct kvm_async_pf;
-
 enum kvm_reg {
 	VCPU_REGS_RAX = 0,
 	VCPU_REGS_RCX = 1,
@@ -462,7 +458,7 @@ struct kvm_vcpu_arch {
 	bool nmi_injected;    /* Trying to inject an NMI this entry */
 
 	struct mtrr_state_type mtrr_state;
-	u32 pat;
+	u64 pat;
 
 	int switch_db_regs;
 	unsigned long db[KVM_NR_DB_REGS];
@@ -480,6 +476,7 @@ struct kvm_vcpu_arch {
 	u64 mmio_gva;
 	unsigned access;
 	gfn_t mmio_gfn;
+	u64 mmio_gen;
 
 	struct kvm_pmu pmu;
 
@@ -662,8 +659,8 @@ struct msr_data {
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
-	int (*hardware_enable)(void *dummy);
-	void (*hardware_disable)(void *dummy);
+	int (*hardware_enable)(void);
+	void (*hardware_disable)(void);
 	void (*check_processor_compatibility)(void *rtn);
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
@@ -983,6 +980,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
 }
 
+static inline u64 get_canonical(u64 la)
+{
+	return ((int64_t)la << 16) >> 16;
+}
+
+static inline bool is_noncanonical_address(u64 la)
+{
+#ifdef CONFIG_X86_64
+	return get_canonical(la) != la;
+#else
+	return false;
+#endif
+}
+
 #define TSS_IOPB_BASE_OFFSET 0x66
 #define TSS_BASE_SIZE 0x68
 #define TSS_IOPB_SIZE (65536 / 8)
@@ -1041,7 +1052,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
 
 void kvm_define_shared_msr(unsigned index, u32 msr);
-void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
 bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c7678e43465b..e62cf897f781 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_KVM_PARA_H
 
 #include <asm/processor.h>
+#include <asm/alternative.h>
 #include <uapi/asm/kvm_para.h>
 
 extern void kvmclock_init(void);
@@ -16,10 +17,15 @@ static inline bool kvm_check_and_clear_guest_paused(void)
 }
 #endif /* CONFIG_KVM_GUEST */
 
-/* This instruction is vmcall.  On non-VT architectures, it will generate a
- * trap that we will then rewrite to the appropriate instruction.
+#ifdef CONFIG_DEBUG_RODATA
+#define KVM_HYPERCALL \
+        ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
+#else
+/* On AMD processors, vmcall will generate a trap that we will
+ * then rewrite to the appropriate instruction.
  */
 #define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
+#endif
 
 /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
  * instruction.  The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index f48b17df4224..3a52ee0e726d 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -20,7 +20,6 @@
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define STACKFAULT_STACK 0
 #define DOUBLEFAULT_STACK 1
 #define NMI_STACK 0
 #define DEBUG_STACK 0
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8de6d9cf3b95..d54d1eebeffe 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,12 +14,11 @@
 #define IRQ_STACK_ORDER 2
 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 2
+#define DEBUG_STACK 3
+#define MCE_STACK 4
+#define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
 
 #define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e22c1dbf7feb..d869931bde62 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
 extern pmd_t level2_ident_pgt[512];
+extern pte_t level1_fixmap_pgt[512];
 extern pgd_t init_level4_pgt[];
 
 #define swapper_pg_dir init_level4_pgt
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index c883bf726398..7166e25ecb57 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 1aa9ccd43223..94e40f1efdfd 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -385,6 +385,8 @@ extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags);
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+			       unsigned numpages);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index c8b051933b1b..b39e194f6c8d 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -5,6 +5,18 @@
 #include <asm/percpu.h>
 #include <linux/thread_info.h>
 
+#ifdef CONFIG_X86_32
+/*
+ * i386's current_thread_info() depends on ESP and for interrupt/exception
+ * stacks this doesn't yield the actual task thread_info.
+ *
+ * We hard rely on the fact that all the TIF_NEED_RESCHED bits are
+ * the same, therefore use the slightly more expensive version below.
+ */
+#undef tif_need_resched
+#define tif_need_resched() test_tsk_thread_flag(current, TIF_NEED_RESCHED)
+#endif
+
 DECLARE_PER_CPU(int, __preempt_count);
 
 /*
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 14fd6fd75a19..6205f0c434db 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -231,6 +231,22 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 
 #define ARCH_HAS_USER_SINGLE_STEP_INFO
 
+/*
+ * When hitting ptrace_stop(), we cannot return using SYSRET because
+ * that does not restore the full CPU state, only a minimal set.  The
+ * ptracer can change arbitrary register values, which is usually okay
+ * because the usual ptrace stops run off the signal delivery path which
+ * forces IRET; however, ptrace_event() stops happen in arbitrary places
+ * in the kernel and don't force IRET path.
+ *
+ * So force IRET path after a ptrace stop.
+ */
+#define arch_ptrace_stop_needed(code, info)				\
+({									\
+	set_thread_flag(TIF_NOTIFY_RESUME);				\
+	false;								\
+})
+
 struct user_desc;
 extern int do_get_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index d62c9f809bc5..75b14ca135be 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -65,6 +65,8 @@ static inline void x86_ce4100_early_setup(void) { }
 
 #ifndef _SETUP
 
+#include <asm/espfix.h>
+
 /*
  * This is set up by the setup-routine at boot-time
  */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e1940c06ed02..e870ea9232c3 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -144,7 +144,7 @@ struct thread_info {
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
 	(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME |	\
-	 _TIF_USER_RETURN_NOTIFY)
+	 _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 58d66fe06b61..b409b17efb48 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -39,6 +39,7 @@ asmlinkage void simd_coprocessor_error(void);
 
 #ifdef CONFIG_TRACING
 asmlinkage void trace_page_fault(void);
+#define trace_stack_segment stack_segment
 #define trace_divide_error divide_error
 #define trace_bounds bounds
 #define trace_invalid_op invalid_op
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 2a46ca720afc..2874be9aef0a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void)
 		native_read_tscp(&p);
 	} else {
 		/* Load per CPU data from GDT */
-		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+		asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 	}
 
 	return p;
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 554738963b28..6c1d7411eb00 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -6,11 +6,14 @@
 
 #define XSTATE_CPUID		0x0000000d
 
-#define XSTATE_FP	0x1
-#define XSTATE_SSE	0x2
-#define XSTATE_YMM	0x4
-#define XSTATE_BNDREGS	0x8
-#define XSTATE_BNDCSR	0x10
+#define XSTATE_FP		0x1
+#define XSTATE_SSE		0x2
+#define XSTATE_YMM		0x4
+#define XSTATE_BNDREGS		0x8
+#define XSTATE_BNDCSR		0x10
+#define XSTATE_OPMASK		0x20
+#define XSTATE_ZMM_Hi256	0x40
+#define XSTATE_Hi16_ZMM		0x80
 
 #define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
 
@@ -23,7 +26,8 @@
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
 /* Supported features which support lazy state saving */
-#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
+#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
+			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
 
 /* Supported features which require eager state saving */
 #define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index 46727eb37bfe..6e1aaf73852a 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -28,6 +28,13 @@ struct user_desc {
 	unsigned int  seg_not_present:1;
 	unsigned int  useable:1;
 #ifdef __x86_64__
+	/*
+	 * Because this bit is not present in 32-bit user code, user
+	 * programs can pass uninitialized values here.  Therefore, in
+	 * any context in which a user_desc comes from a 32-bit program,
+	 * the kernel must act as though lm == 0, regardless of the
+	 * actual value.
+	 */
 	unsigned int  lm:1;
 #endif
 };
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 0e79420376eb..990a2fe1588d 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -67,6 +67,7 @@
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_INVEPT              50
 #define EXIT_REASON_PREEMPTION_TIMER    52
+#define EXIT_REASON_INVVPID             53
 #define EXIT_REASON_WBINVD              54
 #define EXIT_REASON_XSETBV              55
 #define EXIT_REASON_APIC_WRITE          56
@@ -114,6 +115,7 @@
 	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
 	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
 	{ EXIT_REASON_INVD,                  "INVD" }, \
+	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }
 
 #endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cb648c84b327..56bac868cb91 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 7f26c9a70a9e..523f147b2470 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1290,7 +1290,7 @@ void setup_local_APIC(void)
 	unsigned int value, queued;
 	int i, j, acked = 0;
 	unsigned long long tsc = 0, ntsc;
-	long long max_loops = cpu_khz;
+	long long max_loops = cpu_khz ? cpu_khz : 1000000;
 
 	if (cpu_has_tsc)
 		rdtscll(tsc);
@@ -1387,7 +1387,7 @@ void setup_local_APIC(void)
 			break;
 		}
 		if (queued) {
-			if (cpu_has_tsc) {
+			if (cpu_has_tsc && cpu_khz) {
 				rdtscll(ntsc);
 				max_loops = (cpu_khz << 10) - (ntsc - tsc);
 			} else
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c67ffa686064..c005fdd52529 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -508,6 +508,13 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	}
 #endif
 
+	/*
+	 * This is only needed to tell the kernel whether to use VMCALL
+	 * and VMMCALL.  VMMCALL is never executed except under virt, so
+	 * we can set it unconditionally.
+	 */
+	set_cpu_cap(c, X86_FEATURE_VMMCALL);
+
 	/* F16h erratum 793, CVE-2013-6885 */
 	if (c->x86 == 0x16 && c->x86_model <= 0xf) {
 		u64 val;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8e28bf2fc3ef..e6bddd5b9da3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
 static int __init x86_xsave_setup(char *s)
 {
+	if (strlen(s))
+		return 0;
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 	setup_clear_cpu_cap(X86_FEATURE_AVX);
@@ -1141,7 +1143,7 @@ void syscall_init(void)
 	/* Flags to clear on syscall */
 	wrmsrl(MSR_SYSCALL_MASK,
 	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
-	       X86_EFLAGS_IOPL|X86_EFLAGS_AC);
+	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 5cd9bfabd645..66746a880dec 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -153,6 +153,21 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
 		}
 	}
+
+	/*
+	 * Intel Quark Core DevMan_001.pdf section 6.4.11
+	 * "The operating system also is required to invalidate (i.e., flush)
+	 *  the TLB when any changes are made to any of the page table entries.
+	 *  The operating system must reload CR3 to cause the TLB to be flushed"
+	 *
+	 * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
+	 * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+	 * to be modified
+	 */
+	if (c->x86 == 5 && c->x86_model == 9) {
+		pr_info("Disabling PGE capability bit\n");
+		setup_clear_cpu_cap(X86_FEATURE_PGE);
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -368,6 +383,13 @@ static void init_intel(struct cpuinfo_x86 *c)
 	detect_extended_topology(c);
 
 	l2 = init_intel_cacheinfo(c);
+
+	/* Detect legacy cache sizes if init_intel_cacheinfo did not */
+	if (l2 == 0) {
+		cpu_detect_cache_sizes(c);
+		l2 = c->x86_cache_size;
+	}
+
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
 		/* Check for version and the number of counters */
@@ -482,6 +504,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 	 */
 	if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
 		size = 256;
+
+	/*
+	 * Intel Quark SoC X1000 contains a 4-way set associative
+	 * 16K cache with a 16 byte cache line and 256 lines per tag
+	 */
+	if ((c->x86 == 5) && (c->x86_model == 9))
+		size = 16;
 	return size;
 }
 #endif
@@ -709,7 +738,8 @@ static const struct cpu_dev intel_cpu_dev = {
 			  [3] = "OverDrive PODP5V83",
 			  [4] = "Pentium MMX",
 			  [7] = "Mobile Pentium 75 - 200",
-			  [8] = "Mobile Pentium MMX"
+			  [8] = "Mobile Pentium MMX",
+			  [9] = "Quark SoC X1000",
 		  }
 		},
 		{ .family = 6, .model_names =
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 617a9e284245..b63773ba1646 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size)
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
  */
-static void apply_ucode_in_initrd(void *ucode, size_t size)
+static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
 {
 	struct equiv_cpu_entry *eq;
 	size_t *cont_sz;
 	u32 *header;
 	u8  *data, **cont;
+	u8 (*patch)[PATCH_MAX_SIZE];
 	u16 eq_id = 0;
 	int offset, left;
 	u32 rev, eax, ebx, ecx, edx;
@@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
 	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
 	cont_sz = (size_t *)__pa_nodebug(&container_size);
 	cont	= (u8 **)__pa_nodebug(&container);
+	patch	= (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
 #else
 	new_rev = &ucode_new_rev;
 	cont_sz = &container_size;
 	cont	= &container;
+	patch	= &amd_ucode_patch;
 #endif
 
 	data   = ucode;
@@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
 				rev = mc->hdr.patch_id;
 				*new_rev = rev;
 
-				/* save ucode patch */
-				memcpy(amd_ucode_patch, mc,
-				       min_t(u32, header[1], PATCH_MAX_SIZE));
+				if (save_patch)
+					memcpy(patch, mc,
+					       min_t(u32, header[1], PATCH_MAX_SIZE));
 			}
 		}
 
@@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void)
 	*data = cp.data;
 	*size = cp.size;
 
-	apply_ucode_in_initrd(cp.data, cp.size);
+	apply_ucode_in_initrd(cp.data, cp.size, true);
 }
 
 #ifdef CONFIG_X86_32
@@ -263,7 +266,7 @@ void load_ucode_amd_ap(void)
 	size_t *usize;
 	void **ucode;
 
-	mc = (struct microcode_amd *)__pa(amd_ucode_patch);
+	mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
 	if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
 		__apply_microcode_amd(mc);
 		return;
@@ -275,7 +278,7 @@ void load_ucode_amd_ap(void)
 	if (!*ucode || !*usize)
 		return;
 
-	apply_ucode_in_initrd(*ucode, *usize);
+	apply_ucode_in_initrd(*ucode, *usize, false);
 }
 
 static void __init collect_cpu_sig_on_bsp(void *arg)
@@ -339,7 +342,7 @@ void load_ucode_amd_ap(void)
 		 * AP has a different equivalence ID than BSP, looks like
 		 * mixed-steppings silicon so go through the ucode blob anew.
 		 */
-		apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size);
+		apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false);
 	}
 }
 #endif
@@ -347,7 +350,9 @@ void load_ucode_amd_ap(void)
 int __init save_microcode_in_initrd_amd(void)
 {
 	unsigned long cont;
+	int retval = 0;
 	enum ucode_state ret;
+	u8 *cont_va;
 	u32 eax;
 
 	if (!container)
@@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void)
 
 #ifdef CONFIG_X86_32
 	get_bsp_sig();
-	cont = (unsigned long)container;
+	cont	= (unsigned long)container;
+	cont_va = __va(container);
 #else
 	/*
 	 * We need the physical address of the container for both bitness since
 	 * boot_params.hdr.ramdisk_image is a physical address.
 	 */
-	cont = __pa(container);
+	cont    = __pa(container);
+	cont_va = container;
 #endif
 
 	/*
@@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void)
 	if (relocated_ramdisk)
 		container = (u8 *)(__va(relocated_ramdisk) +
 			     (cont - boot_params.hdr.ramdisk_image));
+	else
+		container = cont_va;
 
 	if (ucode_new_rev)
 		pr_info("microcode: updated early to new patch_level=0x%08x\n",
@@ -382,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void)
 
 	ret = load_microcode_amd(eax, container, container_size);
 	if (ret != UCODE_OK)
-		return -EINVAL;
+		retval = -EINVAL;
 
 	/*
 	 * This will be freed any msec now, stash patches for the current
@@ -391,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void)
 	container = NULL;
 	container_size = 0;
 
-	return 0;
+	return retval;
 }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 9f7ca266864a..832d05a914ba 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -26,6 +26,7 @@
 #include <asm/irq_regs.h>
 #include <asm/i8259.h>
 #include <asm/apic.h>
+#include <asm/timer.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -105,6 +106,11 @@ static void __init ms_hyperv_init_platform(void)
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+
+#ifdef CONFIG_X86_IO_APIC
+	no_timer_check = 1;
+#endif
+
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 79f9f848bee4..fb345c43815f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
+		/* Check if the extra msrs can be safely accessed*/
+		if (!er->extra_msr_access)
+			return -ENXIO;
 
 		reg->idx = er->idx;
 		reg->config = event->attr.config1;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 4972c244d0bc..7876c346ed1a 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -293,14 +293,16 @@ struct extra_reg {
 	u64			config_mask;
 	u64			valid_mask;
 	int			idx;  /* per_xxx->regs[] reg index */
+	bool			extra_msr_access;
 };
 
 #define EVENT_EXTRA_REG(e, ms, m, vm, i) {	\
-	.event = (e),		\
-	.msr = (ms),		\
-	.config_mask = (m),	\
-	.valid_mask = (vm),	\
-	.idx = EXTRA_REG_##i,	\
+	.event = (e),			\
+	.msr = (ms),			\
+	.config_mask = (m),		\
+	.valid_mask = (vm),		\
+	.idx = EXTRA_REG_##i,		\
+	.extra_msr_access = true,	\
 	}
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index aa333d966886..d4c0a0e46040 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1383,6 +1383,15 @@ again:
 	intel_pmu_lbr_read();
 
 	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
@@ -2174,6 +2183,41 @@ static void intel_snb_check_microcode(void)
 	}
 }
 
+/*
+ * Under certain circumstances, access certain MSR may cause #GP.
+ * The function tests if the input MSR can be safely accessed.
+ */
+static bool check_msr(unsigned long msr, u64 mask)
+{
+	u64 val_old, val_new, val_tmp;
+
+	/*
+	 * Read the current value, change it and read it back to see if it
+	 * matches, this is needed to detect certain hardware emulators
+	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
+	 */
+	if (rdmsrl_safe(msr, &val_old))
+		return false;
+
+	/*
+	 * Only change the bits which can be updated by wrmsrl.
+	 */
+	val_tmp = val_old ^ mask;
+	if (wrmsrl_safe(msr, val_tmp) ||
+	    rdmsrl_safe(msr, &val_new))
+		return false;
+
+	if (val_new != val_tmp)
+		return false;
+
+	/* Here it's sure that the MSR can be safely accessed.
+	 * Restore the old value and return.
+	 */
+	wrmsrl(msr, val_old);
+
+	return true;
+}
+
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
@@ -2263,7 +2307,8 @@ __init int intel_pmu_init(void)
 	union cpuid10_ebx ebx;
 	struct event_constraint *c;
 	unsigned int unused;
-	int version;
+	struct extra_reg *er;
+	int version, i;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
 		switch (boot_cpu_data.x86) {
@@ -2466,6 +2511,9 @@ __init int intel_pmu_init(void)
 	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		/* dTLB-load-misses on IVB is different than SNB */
+		hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
 		       sizeof(hw_cache_extra_regs));
 
@@ -2566,6 +2614,34 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/*
+	 * Access LBR MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support LBR MSR
+	 * Check all LBT MSR here.
+	 * Disable LBR access if any LBR MSRs can not be accessed.
+	 */
+	if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+		x86_pmu.lbr_nr = 0;
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
+		      check_msr(x86_pmu.lbr_to + i, 0xffffUL)))
+			x86_pmu.lbr_nr = 0;
+	}
+
+	/*
+	 * Access extra MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support offcore event
+	 * Check all extra_regs here.
+	 */
+	if (x86_pmu.extra_regs) {
+		for (er = x86_pmu.extra_regs; er->msr; er++) {
+			er->extra_msr_access = check_msr(er->msr, 0x1ffUL);
+			/* Disable LBR select mapping */
+			if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access)
+				x86_pmu.lbr_sel_map = NULL;
+		}
+	}
+
 	/* Support full width counters using alternative MSR range */
 	if (x86_pmu.intel_cap.full_width_write) {
 		x86_pmu.max_period = x86_pmu.cntval_mask;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 5ad35ad94d0f..95700e52061d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -511,6 +511,7 @@ static int rapl_cpu_prepare(int cpu)
 	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
 	int phys_id = topology_physical_package_id(cpu);
 	u64 ms;
+	u64 msr_rapl_power_unit_bits;
 
 	if (pmu)
 		return 0;
@@ -518,6 +519,9 @@ static int rapl_cpu_prepare(int cpu)
 	if (phys_id < 0)
 		return -1;
 
+	if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+		return -1;
+
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 	if (!pmu)
 		return -1;
@@ -531,8 +535,7 @@ static int rapl_cpu_prepare(int cpu)
 	 *
 	 * we cache in local PMU instance
 	 */
-	rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
-	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+	pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 	pmu->pmu = &rapl_pmu_class;
 
 	/*
@@ -649,7 +652,9 @@ static int __init rapl_pmu_init(void)
 	get_online_cpus();
 
 	for_each_online_cpu(cpu) {
-		rapl_cpu_prepare(cpu);
+		ret = rapl_cpu_prepare(cpu);
+		if (ret)
+			goto out;
 		rapl_cpu_init(cpu);
 	}
 
@@ -672,6 +677,7 @@ static int __init rapl_pmu_init(void)
 		hweight32(rapl_cntr_mask),
 		ktime_to_ms(pmu->timer_interval));
 
+out:
 	put_online_cpus();
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 047f540cf3f7..2f9858894d5a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2886,6 +2886,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
 }
 
+/*
+ * Using uncore_pmu_event_init pmu event_init callback
+ * as a detection point for uncore events.
+ */
+static int uncore_pmu_event_init(struct perf_event *event);
+
+static bool is_uncore_event(struct perf_event *event)
+{
+	return event->pmu->event_init == uncore_pmu_event_init;
+}
+
 static int
 uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
@@ -2900,13 +2911,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b
 		return -EINVAL;
 
 	n = box->n_events;
-	box->event_list[n] = leader;
-	n++;
+
+	if (is_uncore_event(leader)) {
+		box->event_list[n] = leader;
+		n++;
+	}
+
 	if (!dogrp)
 		return n;
 
 	list_for_each_entry(event, &leader->sibling_list, group_entry) {
-		if (event->state <= PERF_EVENT_STATE_OFF)
+		if (!is_uncore_event(event) ||
+		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 
 		if (n >= max_count)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207dab92..66e274a3d968 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = {
 		[ DEBUG_STACK-1			]	= "#DB",
 		[ NMI_STACK-1			]	= "NMI",
 		[ DOUBLEFAULT_STACK-1		]	= "#DF",
-		[ STACKFAULT_STACK-1		]	= "#SS",
 		[ MCE_STACK-1			]	= "#MC",
 #if DEBUG_STKSZ > EXCEPTION_STKSZ
 		[ N_EXCEPTION_STACKS ...
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bc4a088f9023..6d7d5a1260a6 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func)
 	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
 	/*
- 	 * Revision 13 of all triggering devices id in this quirk have
-	 * a problem draining interrupts when irq remapping is enabled,
-	 * and should be flagged as broken.  Additionally revisions 0x12
-	 * and 0x22 of device id 0x3405 has this problem.
+	 * Revision <= 13 of all triggering devices id in this quirk
+	 * have a problem draining interrupts when irq remapping is
+	 * enabled, and should be flagged as broken. Additionally
+	 * revision 0x22 of device id 0x3405 has this problem.
 	 */
-	if (revision == 0x13)
+	if (revision <= 0x13)
 		set_irq_remapping_broken();
-	else if ((device == 0x3405) &&
-	    ((revision == 0x12) ||
-	     (revision == 0x22)))
+	else if (device == 0x3405 && revision == 0x22)
 		set_irq_remapping_broken();
-
 }
 
 /*
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index a2a4f4697889..c5a9cb94dee6 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -431,8 +431,9 @@ sysenter_past_esp:
 	jnz sysenter_audit
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
+	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
+sysenter_after_call:
 	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
@@ -513,6 +514,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -527,6 +529,7 @@ syscall_exit:
 restore_all:
 	TRACE_IRQS_IRET
 restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
 	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
 	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
 	# are returning to the kernel.
@@ -537,6 +540,7 @@ restore_all_notrace:
 	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
+#endif
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
 irq_return:
@@ -549,13 +553,9 @@ ENTRY(iret_exc)
 .previous
 	_ASM_EXTABLE(irq_return,iret_exc)
 
+#ifdef CONFIG_X86_ESPFIX32
 	CFI_RESTORE_STATE
 ldt_ss:
-	larl PT_OLDSS(%esp), %eax
-	jnz restore_nocheck
-	testl $0x00400000, %eax		# returning to 32bit stack?
-	jnz restore_nocheck		# allright, normal return
-
 #ifdef CONFIG_PARAVIRT
 	/*
 	 * The kernel can't run on a non-flat stack if paravirt mode
@@ -597,6 +597,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -687,8 +688,13 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp resume_userspace
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl $-ENOSYS,%eax
+	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
 /*
@@ -704,6 +710,7 @@ END(syscall_badsys)
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
  */
+#ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
 	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -713,8 +720,10 @@ END(syscall_badsys)
 	pushl_cfi %eax
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
+#endif
 .endm
 .macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
 	movl %ss, %eax
 	/* see if on espfix stack */
 	cmpw $__ESPFIX_SS, %ax
@@ -725,6 +734,7 @@ END(syscall_badsys)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1355,11 +1365,13 @@ END(debug)
 ENTRY(nmi)
 	RING0_INT_FRAME
 	ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
 	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
 	popl_cfi %eax
 	je nmi_espfix_stack
+#endif
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
 	pushl_cfi %eax
@@ -1399,6 +1411,7 @@ nmi_debug_stack_check:
 	FIX_STACK 24, nmi_stack_correct, 1
 	jmp nmi_stack_correct
 
+#ifdef CONFIG_X86_ESPFIX32
 nmi_espfix_stack:
 	/* We have a RING0_INT_FRAME here.
 	 *
@@ -1420,6 +1433,7 @@ nmi_espfix_stack:
 	lss 12+4(%esp), %esp		# back to espfix stack
 	CFI_ADJUST_CFA_OFFSET -24
 	jmp irq_return
+#endif
 	CFI_ENDPROC
 END(nmi)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1e96c3628bf2..02553d6d183d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -58,6 +58,7 @@
 #include <asm/asm.h>
 #include <asm/context_tracking.h>
 #include <asm/smap.h>
+#include <asm/pgtable_types.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -1041,32 +1042,52 @@ restore_args:
 
 irq_return:
 	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return, bad_iret)
 
-#ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
-	iretq
-	_ASM_EXTABLE(native_iret, bad_iret)
+	/*
+	 * Are we returning to a stack segment from the LDT?  Note: in
+	 * 64-bit mode SS:RSP on the exception stack is always valid.
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	testb $4,(SS-RIP)(%rsp)
+	jnz native_irq_return_ldt
 #endif
 
-	.section .fixup,"ax"
-bad_iret:
+.global native_irq_return_iret
+native_irq_return_iret:
 	/*
-	 * The iret traps when the %cs or %ss being restored is bogus.
-	 * We've lost the original trap vector and error code.
-	 * #GPF is the most likely one to get for an invalid selector.
-	 * So pretend we completed the iret and took the #GPF in user mode.
-	 *
-	 * We are now running with the kernel GS after exception recovery.
-	 * But error_entry expects us to have user GS to match the user %cs,
-	 * so swap back.
+	 * This may fault.  Non-paranoid faults on return to userspace are
+	 * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
+	 * Double-faults due to espfix64 are handled in do_double_fault.
+	 * Other faults here are fatal.
 	 */
-	pushq $0
+	iretq
 
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+	pushq_cfi %rax
+	pushq_cfi %rdi
 	SWAPGS
-	jmp general_protection
-
-	.previous
+	movq PER_CPU_VAR(espfix_waddr),%rdi
+	movq %rax,(0*8)(%rdi)	/* RAX */
+	movq (2*8)(%rsp),%rax	/* RIP */
+	movq %rax,(1*8)(%rdi)
+	movq (3*8)(%rsp),%rax	/* CS */
+	movq %rax,(2*8)(%rdi)
+	movq (4*8)(%rsp),%rax	/* RFLAGS */
+	movq %rax,(3*8)(%rdi)
+	movq (6*8)(%rsp),%rax	/* SS */
+	movq %rax,(5*8)(%rdi)
+	movq (5*8)(%rsp),%rax	/* RSP */
+	movq %rax,(4*8)(%rdi)
+	andl $0xffff0000,%eax
+	popq_cfi %rdi
+	orq PER_CPU_VAR(espfix_stack),%rax
+	SWAPGS
+	movq %rax,%rsp
+	popq_cfi %rax
+	jmp native_irq_return_iret
+#endif
 
 	/* edi: workmask, edx: work */
 retint_careful:
@@ -1110,9 +1131,9 @@ ENTRY(retint_kernel)
 	call preempt_schedule_irq
 	jmp exit_intr
 #endif
-
 	CFI_ENDPROC
 END(common_interrupt)
+
 /*
  * End of kprobes section
  */
@@ -1484,7 +1505,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 
 paranoidzeroentry_ist debug do_debug DEBUG_STACK
 paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
-paranoiderrorentry stack_segment do_stack_segment
+errorentry stack_segment do_stack_segment
 #ifdef CONFIG_XEN
 zeroentry xen_debug do_debug
 zeroentry xen_int3 do_int3
@@ -1594,16 +1615,15 @@ error_sti:
 
 /*
  * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. The exception handlers after iret run with
- * kernel gs again, so don't set the user space flag. B stepping K8s
- * sometimes report an truncated RIP for IRET exceptions returning to
- * compat mode. Check for these here too.
+ * usergs. Handle them here.  B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return(%rip),%rcx
+	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
-	je error_swapgs
+	je error_bad_iret
 	movl %ecx,%eax	/* zero extend */
 	cmpq %rax,RIP+8(%rsp)
 	je bstep_iret
@@ -1614,7 +1634,15 @@ error_kernelspace:
 bstep_iret:
 	/* Fix truncated RIP */
 	movq %rcx,RIP+8(%rsp)
-	jmp error_swapgs
+	/* fall through */
+
+error_bad_iret:
+	SWAPGS
+	mov %rsp,%rdi
+	call fixup_bad_iret
+	mov %rax,%rsp
+	decl %ebx	/* Return to usergs */
+	jmp error_sti
 	CFI_ENDPROC
 END(error_entry)
 
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 000000000000..94d857fb1033
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ *   This program is free software; you can redistribute it and/or modify it
+ *   under the terms and conditions of the GNU General Public License,
+ *   version 2, as published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope it will be useful, but WITHOUT
+ *   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *   more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer.  This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart.  When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace.  The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables.  The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE	(8*8UL)
+#define ESPFIX_STACKS_PER_PAGE	(PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE	(1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS		(ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES  DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+	__aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+	unsigned long page, slot;
+	unsigned long addr;
+
+	page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+	slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+	addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+	addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+	addr += ESPFIX_BASE_ADDR;
+	return addr;
+}
+
+#define PTE_STRIDE        (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT	  ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+	unsigned long rand;
+
+	/*
+	 * This is run before the entropy pools are initialized,
+	 * but this is hopefully better than nothing.
+	 */
+	if (!arch_get_random_long(&rand)) {
+		/* The constant is an arbitrary large prime */
+		rdtscll(rand);
+		rand *= 0xc345c6b72fd16123UL;
+	}
+
+	slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+	page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+		& (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+	pgd_t *pgd_p;
+	pteval_t ptemask;
+
+	ptemask = __supported_pte_mask;
+
+	/* Install the espfix pud into the kernel page directory */
+	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+	/* Randomize the locations */
+	init_espfix_random();
+
+	/* The rest is the same as for any other processor */
+	init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+	unsigned int cpu, page;
+	unsigned long addr;
+	pud_t pud, *pud_p;
+	pmd_t pmd, *pmd_p;
+	pte_t pte, *pte_p;
+	int n;
+	void *stack_page;
+	pteval_t ptemask;
+
+	/* We only have to do this once... */
+	if (likely(this_cpu_read(espfix_stack)))
+		return;		/* Already initialized */
+
+	cpu = smp_processor_id();
+	addr = espfix_base_addr(cpu);
+	page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+	/* Did another CPU already set this up? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (likely(stack_page))
+		goto done;
+
+	mutex_lock(&espfix_init_mutex);
+
+	/* Did we race on the lock? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (stack_page)
+		goto unlock_done;
+
+	ptemask = __supported_pte_mask;
+
+	pud_p = &espfix_pud_page[pud_index(addr)];
+	pud = *pud_p;
+	if (!pud_present(pud)) {
+		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+			set_pud(&pud_p[n], pud);
+	}
+
+	pmd_p = pmd_offset(&pud, addr);
+	pmd = *pmd_p;
+	if (!pmd_present(pmd)) {
+		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+			set_pmd(&pmd_p[n], pmd);
+	}
+
+	pte_p = pte_offset_kernel(&pmd, addr);
+	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+		set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+	/* Job is done for this CPU and any CPU which shares this page */
+	ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+	mutex_unlock(&espfix_init_mutex);
+done:
+	this_cpu_write(espfix_stack, addr);
+	this_cpu_write(espfix_waddr, (unsigned long)stack_page
+		       + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index e6253195a301..1ffc32dbe450 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -659,8 +659,8 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
 		ret = -EPERM;
 		goto out;
 	}
-	run_sync();
  out:
+	run_sync();
 	return ret;
 
  fail_update:
diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c
index c3aae6672843..2e97b3cfa6c7 100644
--- a/arch/x86/kernel/iosf_mbi.c
+++ b/arch/x86/kernel/iosf_mbi.c
@@ -25,6 +25,10 @@
 
 #include <asm/iosf_mbi.h>
 
+#define PCI_DEVICE_ID_BAYTRAIL		0x0F00
+#define PCI_DEVICE_ID_BRASWELL		0x2280
+#define PCI_DEVICE_ID_QUARK_X1000	0x0958
+
 static DEFINE_SPINLOCK(iosf_mbi_lock);
 
 static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset)
@@ -177,6 +181,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)
 }
 EXPORT_SYMBOL(iosf_mbi_modify);
 
+bool iosf_mbi_available(void)
+{
+	/* Mbi isn't hot-pluggable. No remove routine is provided */
+	return mbi_pdev;
+}
+EXPORT_SYMBOL(iosf_mbi_available);
+
 static int iosf_mbi_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *unused)
 {
@@ -193,7 +204,9 @@ static int iosf_mbi_probe(struct pci_dev *pdev,
 }
 
 static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) },
 	{ 0, },
 };
 MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 713f1b3bad52..0b1e1d5dbc5b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -280,7 +280,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
-	pv_info.paravirt_enabled = 1;
+
+	/*
+	 * KVM isn't paravirt in the sense of paravirt_enabled.  A KVM
+	 * guest kernel works like a bare metal kernel with additional
+	 * features, and paravirt_enabled is about features that are
+	 * missing.
+	 */
+	pv_info.paravirt_enabled = 0;
 
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index e6041094ff26..c8e98cdc84c2 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -263,7 +263,6 @@ void __init kvmclock_init(void)
 #endif
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
-	pv_info.paravirt_enabled = 1;
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ebc987398923..c37886d759cc 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,11 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
+	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34f93eb..a1da6737ba5b 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
 DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, iret);
 		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9c0280f93d05..e2d26ce9b854 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -286,24 +286,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
-	/*
-	 * Reload esp0, LDT and the page table pointer:
-	 */
+	/* Reload esp0 and ss1. */
 	load_sp0(tss, next);
 
-	/*
-	 * Switch DS and ES.
-	 * This won't pick up thread selector changes, but I guess that is ok.
-	 */
-	savesegment(es, prev->es);
-	if (unlikely(next->es | prev->es))
-		loadsegment(es, next->es);
-
-	savesegment(ds, prev->ds);
-	if (unlikely(next->ds | prev->ds))
-		loadsegment(ds, next->ds);
-
-
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
 	 *
@@ -312,41 +297,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	savesegment(fs, fsindex);
 	savesegment(gs, gsindex);
 
+	/*
+	 * Load TLS before restoring any segments so that segment loads
+	 * reference the correct GDT entries.
+	 */
 	load_TLS(next, cpu);
 
 	/*
-	 * Leave lazy mode, flushing any hypercalls made here.
-	 * This must be done before restoring TLS segments so
-	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
-	 * to date.
+	 * Leave lazy mode, flushing any hypercalls made here.  This
+	 * must be done after loading TLS entries in the GDT but before
+	 * loading segments that might reference them, and and it must
+	 * be done before math_state_restore, so the TS bit is up to
+	 * date.
 	 */
 	arch_end_context_switch(next_p);
 
+	/* Switch DS and ES.
+	 *
+	 * Reading them only returns the selectors, but writing them (if
+	 * nonzero) loads the full descriptor from the GDT or LDT.  The
+	 * LDT for next is loaded in switch_mm, and the GDT is loaded
+	 * above.
+	 *
+	 * We therefore need to write new values to the segment
+	 * registers on every context switch unless both the new and old
+	 * values are zero.
+	 *
+	 * Note that we don't need to do anything for CS and SS, as
+	 * those are saved and restored as part of pt_regs.
+	 */
+	savesegment(es, prev->es);
+	if (unlikely(next->es | prev->es))
+		loadsegment(es, next->es);
+
+	savesegment(ds, prev->ds);
+	if (unlikely(next->ds | prev->ds))
+		loadsegment(ds, next->ds);
+
 	/*
 	 * Switch FS and GS.
 	 *
-	 * Segment register != 0 always requires a reload.  Also
-	 * reload when it has changed.  When prev process used 64bit
-	 * base always reload to avoid an information leak.
+	 * These are even more complicated than FS and GS: they have
+	 * 64-bit bases are that controlled by arch_prctl.  Those bases
+	 * only differ from the values in the GDT or LDT if the selector
+	 * is 0.
+	 *
+	 * Loading the segment register resets the hidden base part of
+	 * the register to 0 or the value from the GDT / LDT.  If the
+	 * next base address zero, writing 0 to the segment register is
+	 * much faster than using wrmsr to explicitly zero the base.
+	 *
+	 * The thread_struct.fs and thread_struct.gs values are 0
+	 * if the fs and gs bases respectively are not overridden
+	 * from the values implied by fsindex and gsindex.  They
+	 * are nonzero, and store the nonzero base addresses, if
+	 * the bases are overridden.
+	 *
+	 * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
+	 * be impossible.
+	 *
+	 * Therefore we need to reload the segment registers if either
+	 * the old or new selector is nonzero, and we need to override
+	 * the base address if next thread expects it to be overridden.
+	 *
+	 * This code is unnecessarily slow in the case where the old and
+	 * new indexes are zero and the new base is nonzero -- it will
+	 * unnecessarily write 0 to the selector before writing the new
+	 * base address.
+	 *
+	 * Note: This all depends on arch_prctl being the only way that
+	 * user code can override the segment base.  Once wrfsbase and
+	 * wrgsbase are enabled, most of this code will need to change.
 	 */
 	if (unlikely(fsindex | next->fsindex | prev->fs)) {
 		loadsegment(fs, next->fsindex);
+
 		/*
-		 * Check if the user used a selector != 0; if yes
-		 *  clear 64bit base, since overloaded base is always
-		 *  mapped to the Null selector
+		 * If user code wrote a nonzero value to FS, then it also
+		 * cleared the overridden base address.
+		 *
+		 * XXX: if user code wrote 0 to FS and cleared the base
+		 * address itself, we won't notice and we'll incorrectly
+		 * restore the prior base address next time we reschdule
+		 * the process.
 		 */
 		if (fsindex)
 			prev->fs = 0;
 	}
-	/* when next process has a 64bit base use it */
 	if (next->fs)
 		wrmsrl(MSR_FS_BASE, next->fs);
 	prev->fsindex = fsindex;
 
 	if (unlikely(gsindex | next->gsindex | prev->gs)) {
 		load_gs_index(next->gsindex);
+
+		/* This works (and fails) the same way as fsindex above. */
 		if (gsindex)
 			prev->gs = 0;
 	}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 7461f50d5bb1..0686fe313b3b 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1441,15 +1441,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 	force_sig_info(SIGTRAP, &info, tsk);
 }
 
-
-#ifdef CONFIG_X86_32
-# define IS_IA32	1
-#elif defined CONFIG_IA32_EMULATION
-# define IS_IA32	is_compat_task()
-#else
-# define IS_IA32	0
-#endif
-
 /*
  * We must return the syscall number to actually look up in the table.
  * This can be -1L to skip running any syscall at all.
@@ -1487,7 +1478,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->orig_ax);
 
-	if (IS_IA32)
+	if (is_ia32_task())
 		audit_syscall_entry(AUDIT_ARCH_I386,
 				    regs->orig_ax,
 				    regs->bx, regs->cx,
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819bb6a8..80eab01c1a68 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail)
 
 void arch_remove_reservations(struct resource *avail)
 {
-	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	/*
+	 * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+	 * the low 1MB unconditionally, as this area is needed for some ISA
+	 * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+	 */
 	if (avail->flags & IORESOURCE_MEM) {
-		if (avail->start < BIOS_END)
-			avail->start = BIOS_END;
 		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
 
 		remove_e820_regions(avail);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 9e5de6813e1f..b88fc86309bc 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		 * handler too.
 		 */
 		regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
+		/*
+		 * Ensure the signal handler starts with the new fpu state.
+		 */
+		if (used_math())
+			drop_init_fpu(current);
 	}
 	signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a32da804252e..682876533ed9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -243,6 +243,13 @@ static void notrace start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
+	 * Enable the espfix hack for this CPU
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap();
+#endif
+
+	/*
 	 * We need to hold vector_lock so there the set of online cpus
 	 * does not change while we are assigning vectors to cpus.  Holding
 	 * this lock ensures we don't half assign or remove an irq from a cpu.
@@ -1280,6 +1287,9 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, cpu_sibling_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
+		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(cpu_sibling_mask(cpu));
 	cpumask_clear(cpu_core_mask(cpu));
 	c->phys_proc_id = 0;
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index f7fec09e3e3a..4e942f31b1a7 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -27,6 +27,37 @@ static int get_free_idx(void)
 	return -ESRCH;
 }
 
+static bool tls_desc_okay(const struct user_desc *info)
+{
+	if (LDT_empty(info))
+		return true;
+
+	/*
+	 * espfix is required for 16-bit data segments, but espfix
+	 * only works for LDT segments.
+	 */
+	if (!info->seg_32bit)
+		return false;
+
+	/* Only allow data segments in the TLS array. */
+	if (info->contents > 1)
+		return false;
+
+	/*
+	 * Non-present segments with DPL 3 present an interesting attack
+	 * surface.  The kernel should handle such segments correctly,
+	 * but TLS is very difficult to protect in a sandbox, so prevent
+	 * such segments from being created.
+	 *
+	 * If userspace needs to remove a TLS entry, it can still delete
+	 * it outright.
+	 */
+	if (info->seg_not_present)
+		return false;
+
+	return true;
+}
+
 static void set_tls_desc(struct task_struct *p, int idx,
 			 const struct user_desc *info, int n)
 {
@@ -66,6 +97,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
 	if (copy_from_user(&info, u_info, sizeof(info)))
 		return -EFAULT;
 
+	if (!tls_desc_okay(&info))
+		return -EINVAL;
+
 	if (idx == -1)
 		idx = info.entry_number;
 
@@ -192,6 +226,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 {
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
+	int i;
 
 	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +240,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 	else
 		info = infobuf;
 
+	for (i = 0; i < count / sizeof(struct user_desc); i++)
+		if (!tls_desc_okay(info + i))
+			return -EINVAL;
+
 	set_tls_desc(target,
 		     GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
 		     info, count / sizeof(struct user_desc));
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 57409f6b8c62..f9d976e0ae67 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -218,32 +218,40 @@ DO_ERROR_INFO(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op,		     ILL
 DO_ERROR     (X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",	coprocessor_segment_overrun			  )
 DO_ERROR     (X86_TRAP_TS,     SIGSEGV, "invalid TSS",			invalid_TSS					  )
 DO_ERROR     (X86_TRAP_NP,     SIGBUS,  "segment not present",		segment_not_present				  )
-#ifdef CONFIG_X86_32
 DO_ERROR     (X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment					  )
-#endif
 DO_ERROR_INFO(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check,	     BUS_ADRALN, 0	  )
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
-	enum ctx_state prev_state;
-
-	prev_state = exception_enter();
-	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-		       X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
-		preempt_conditional_sti(regs);
-		do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-		preempt_conditional_cli(regs);
-	}
-	exception_exit(prev_state);
-}
-
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 {
 	static const char str[] = "double fault";
 	struct task_struct *tsk = current;
 
+#ifdef CONFIG_X86_ESPFIX64
+	extern unsigned char native_irq_return_iret[];
+
+	/*
+	 * If IRET takes a non-IST fault on the espfix64 stack, then we
+	 * end up promoting it to a doublefault.  In that case, modify
+	 * the stack to make it look like we just entered the #GP
+	 * handler from user space, similar to bad_iret.
+	 */
+	if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+		regs->cs == __KERNEL_CS &&
+		regs->ip == (unsigned long)native_irq_return_iret)
+	{
+		struct pt_regs *normal_regs = task_pt_regs(current);
+
+		/* Fake a #GP(0) from userspace. */
+		memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+		normal_regs->orig_ax = 0;  /* Missing (lost) #GP error code */
+		regs->ip = (unsigned long)general_protection;
+		regs->sp = (unsigned long)&normal_regs->orig_ax;
+		return;
+	}
+#endif
+
 	exception_enter();
 	/* Return not checked because double check cannot be ignored */
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -376,6 +384,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 		*regs = *eregs;
 	return regs;
 }
+
+struct bad_iret_stack {
+	void *error_entry_ret;
+	struct pt_regs regs;
+};
+
+asmlinkage __visible
+struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+{
+	/*
+	 * This is called from entry_64.S early in handling a fault
+	 * caused by a bad iret to user mode.  To handle the fault
+	 * correctly, we want move our stack frame to task_pt_regs
+	 * and we want to pretend that the exception came from the
+	 * iret target.
+	 */
+	struct bad_iret_stack *new_stack =
+		container_of(task_pt_regs(current),
+			     struct bad_iret_stack, regs);
+
+	/* Copy the IRET target to the new stack. */
+	memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
+
+	/* Copy the remainder of the stack from the current stack. */
+	memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
+
+	BUG_ON(!user_mode_vm(&new_stack->regs));
+	return new_stack;
+}
 #endif
 
 /*
@@ -748,7 +785,7 @@ void __init trap_init(void)
 	set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun);
 	set_intr_gate(X86_TRAP_TS, invalid_TSS);
 	set_intr_gate(X86_TRAP_NP, segment_not_present);
-	set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+	set_intr_gate(X86_TRAP_SS, stack_segment);
 	set_intr_gate(X86_TRAP_GP, general_protection);
 	set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug);
 	set_intr_gate(X86_TRAP_MF, coprocessor_error);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cfbe99f88830..de0290605903 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -921,9 +921,9 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
-	}
 
-	set_cyc2ns_scale(tsc_khz, freq->cpu);
+		set_cyc2ns_scale(tsc_khz, freq->cpu);
+	}
 
 	return 0;
 }
@@ -1173,14 +1173,17 @@ void __init tsc_init(void)
 
 	x86_init.timers.tsc_pre_init();
 
-	if (!cpu_has_tsc)
+	if (!cpu_has_tsc) {
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
+	}
 
 	tsc_khz = x86_platform.calibrate_tsc();
 	cpu_khz = tsc_khz;
 
 	if (!tsc_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
 	}
 
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1f96f9347ed9..09ce23ae370c 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 	if (!show_unhandled_signals)
 		return;
 
-	pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
-			      level, current->comm, task_pid_nr(current),
-			      message, regs->ip, regs->cs,
-			      regs->sp, regs->ax, regs->si, regs->di);
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+			   level, current->comm, task_pid_nr(current),
+			   message, regs->ip, regs->cs,
+			   regs->sp, regs->ax, regs->si, regs->di);
 }
 
 static int addr_to_vsyscall_nr(unsigned long addr)
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a4b451c6addf..dd50e26c58f6 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
 		return -1;
 
-	drop_init_fpu(tsk);	/* trigger finit */
-
 	return 0;
 }
 
@@ -399,8 +397,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 			set_used_math();
 		}
 
-		if (use_eager_fpu())
+		if (use_eager_fpu()) {
+			preempt_disable();
 			math_state_restore();
+			preempt_enable();
+		}
 
 		return err;
 	} else {
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 287e4c85fff9..f9d16ff56c6b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,6 +27,7 @@ config KVM
 	select MMU_NOTIFIER
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 07ffca0a89e9..38d3751472e4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -498,11 +498,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
 	masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc);
 }
 
-static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
-{
-	register_address_increment(ctxt, &ctxt->_eip, rel);
-}
-
 static u32 desc_limit_scaled(struct desc_struct *desc)
 {
 	u32 limit = get_desc_limit(desc);
@@ -576,6 +571,38 @@ static int emulate_nm(struct x86_emulate_ctxt *ctxt)
 	return emulate_exception(ctxt, NM_VECTOR, 0, false);
 }
 
+static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
+			       int cs_l)
+{
+	switch (ctxt->op_bytes) {
+	case 2:
+		ctxt->_eip = (u16)dst;
+		break;
+	case 4:
+		ctxt->_eip = (u32)dst;
+		break;
+	case 8:
+		if ((cs_l && is_noncanonical_address(dst)) ||
+		    (!cs_l && (dst & ~(u32)-1)))
+			return emulate_gp(ctxt, 0);
+		ctxt->_eip = dst;
+		break;
+	default:
+		WARN(1, "unsupported eip assignment size\n");
+	}
+	return X86EMUL_CONTINUE;
+}
+
+static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
+{
+	return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64);
+}
+
+static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
+{
+	return assign_eip_near(ctxt, ctxt->_eip + rel);
+}
+
 static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg)
 {
 	u16 selector;
@@ -1958,13 +1985,15 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt)
 	case 2: /* call near abs */ {
 		long int old_eip;
 		old_eip = ctxt->_eip;
-		ctxt->_eip = ctxt->src.val;
+		rc = assign_eip_near(ctxt, ctxt->src.val);
+		if (rc != X86EMUL_CONTINUE)
+			break;
 		ctxt->src.val = old_eip;
 		rc = em_push(ctxt);
 		break;
 	}
 	case 4: /* jmp abs */
-		ctxt->_eip = ctxt->src.val;
+		rc = assign_eip_near(ctxt, ctxt->src.val);
 		break;
 	case 5: /* jmp far */
 		rc = em_jmp_far(ctxt);
@@ -1996,16 +2025,21 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
 
 static int em_ret(struct x86_emulate_ctxt *ctxt)
 {
-	ctxt->dst.type = OP_REG;
-	ctxt->dst.addr.reg = &ctxt->_eip;
-	ctxt->dst.bytes = ctxt->op_bytes;
-	return em_pop(ctxt);
+	int rc;
+	unsigned long eip;
+
+	rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	return assign_eip_near(ctxt, eip);
 }
 
 static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long cs;
+	int cpl = ctxt->ops->cpl(ctxt);
 
 	rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2015,6 +2049,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
+	/* Outer-privilege level return is not implemented */
+	if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
+		return X86EMUL_UNHANDLEABLE;
 	rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
 	return rc;
 }
@@ -2273,7 +2310,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 {
 	const struct x86_emulate_ops *ops = ctxt->ops;
 	struct desc_struct cs, ss;
-	u64 msr_data;
+	u64 msr_data, rcx, rdx;
 	int usermode;
 	u16 cs_sel = 0, ss_sel = 0;
 
@@ -2289,6 +2326,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 	else
 		usermode = X86EMUL_MODE_PROT32;
 
+	rcx = reg_read(ctxt, VCPU_REGS_RCX);
+	rdx = reg_read(ctxt, VCPU_REGS_RDX);
+
 	cs.dpl = 3;
 	ss.dpl = 3;
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
@@ -2306,6 +2346,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 		ss_sel = cs_sel + 8;
 		cs.d = 0;
 		cs.l = 1;
+		if (is_noncanonical_address(rcx) ||
+		    is_noncanonical_address(rdx))
+			return emulate_gp(ctxt, 0);
 		break;
 	}
 	cs_sel |= SELECTOR_RPL_MASK;
@@ -2314,8 +2357,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 	ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
 	ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
 
-	ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX);
-	*reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX);
+	ctxt->_eip = rdx;
+	*reg_write(ctxt, VCPU_REGS_RSP) = rcx;
 
 	return X86EMUL_CONTINUE;
 }
@@ -2854,10 +2897,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt)
 
 static int em_call(struct x86_emulate_ctxt *ctxt)
 {
+	int rc;
 	long rel = ctxt->src.val;
 
 	ctxt->src.val = (unsigned long)ctxt->_eip;
-	jmp_rel(ctxt, rel);
+	rc = jmp_rel(ctxt, rel);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
 	return em_push(ctxt);
 }
 
@@ -2889,11 +2935,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
 static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
+	unsigned long eip;
 
-	ctxt->dst.type = OP_REG;
-	ctxt->dst.addr.reg = &ctxt->_eip;
-	ctxt->dst.bytes = ctxt->op_bytes;
-	rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
+	rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+	rc = assign_eip_near(ctxt, eip);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rsp_increment(ctxt, ctxt->src.val);
@@ -3223,20 +3270,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt)
 
 static int em_loop(struct x86_emulate_ctxt *ctxt)
 {
+	int rc = X86EMUL_CONTINUE;
+
 	register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1);
 	if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) &&
 	    (ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags)))
-		jmp_rel(ctxt, ctxt->src.val);
+		rc = jmp_rel(ctxt, ctxt->src.val);
 
-	return X86EMUL_CONTINUE;
+	return rc;
 }
 
 static int em_jcxz(struct x86_emulate_ctxt *ctxt)
 {
+	int rc = X86EMUL_CONTINUE;
+
 	if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0)
-		jmp_rel(ctxt, ctxt->src.val);
+		rc = jmp_rel(ctxt, ctxt->src.val);
 
-	return X86EMUL_CONTINUE;
+	return rc;
 }
 
 static int em_in(struct x86_emulate_ctxt *ctxt)
@@ -4633,7 +4684,7 @@ special_insn:
 		break;
 	case 0x70 ... 0x7f: /* jcc (short) */
 		if (test_cc(ctxt->b, ctxt->eflags))
-			jmp_rel(ctxt, ctxt->src.val);
+			rc = jmp_rel(ctxt, ctxt->src.val);
 		break;
 	case 0x8d: /* lea r16/r32, m */
 		ctxt->dst.val = ctxt->src.addr.mem.ea;
@@ -4662,7 +4713,7 @@ special_insn:
 		break;
 	case 0xe9: /* jmp rel */
 	case 0xeb: /* jmp rel short */
-		jmp_rel(ctxt, ctxt->src.val);
+		rc = jmp_rel(ctxt, ctxt->src.val);
 		ctxt->dst.type = OP_NONE; /* Disable writeback. */
 		break;
 	case 0xf4:              /* hlt */
@@ -4782,7 +4833,7 @@ twobyte_insn:
 		break;
 	case 0x80 ... 0x8f: /* jnz rel, etc*/
 		if (test_cc(ctxt->b, ctxt->eflags))
-			jmp_rel(ctxt, ctxt->src.val);
+			rc = jmp_rel(ctxt, ctxt->src.val);
 		break;
 	case 0x90 ... 0x9f:     /* setcc r/m8 */
 		ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 518d86471b76..298781d4cfb4 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -262,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 		return;
 
 	timer = &pit->pit_state.timer;
+	mutex_lock(&pit->pit_state.lock);
 	if (hrtimer_cancel(timer))
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+	mutex_unlock(&pit->pit_state.lock);
 }
 
 static void destroy_pit_timer(struct kvm_pit *pit)
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 484bc874688b..3ec38cb56bd5 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 
 	vector = kvm_cpu_get_extint(v);
 
-	if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+	if (vector != -1)
 		return vector;			/* PIC */
 
 	return kvm_get_apic_interrupt(v);	/* APIC */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9736529ade08..453e5fbbb7ae 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -352,31 +352,90 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 
 static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 {
-	apic->irr_pending = false;
+	struct kvm_vcpu *vcpu;
+
+	vcpu = apic->vcpu;
+
 	apic_clear_vector(vec, apic->regs + APIC_IRR);
-	if (apic_search_irr(apic) != -1)
-		apic->irr_pending = true;
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		/* try to update RVI */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	else {
+		vec = apic_search_irr(apic);
+		apic->irr_pending = (vec != -1);
+	}
 }
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
-	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+
+	if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * With APIC virtualization enabled, all caching is disabled
+	 * because the processor can modify ISR under the hood.  Instead
+	 * just set SVI.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
+	else {
 		++apic->isr_count;
-	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+		BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+		/*
+		 * ISR (in service register) bit is set when injecting an interrupt.
+		 * The highest vector is injected. Thus the latest bit set matches
+		 * the highest bit in ISR.
+		 */
+		apic->highest_isr_cache = vec;
+	}
+}
+
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+	int result;
+
 	/*
-	 * ISR (in service register) bit is set when injecting an interrupt.
-	 * The highest vector is injected. Thus the latest bit set matches
-	 * the highest bit in ISR.
+	 * Note that isr_count is always 1, and highest_isr_cache
+	 * is always -1, with APIC virtualization enabled.
 	 */
-	apic->highest_isr_cache = vec;
+	if (!apic->isr_count)
+		return -1;
+	if (likely(apic->highest_isr_cache != -1))
+		return apic->highest_isr_cache;
+
+	result = find_highest_vector(apic->regs + APIC_ISR);
+	ASSERT(result == -1 || result >= 16);
+
+	return result;
 }
 
 static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 {
-	if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * We do get here for APIC virtualization enabled if the guest
+	 * uses the Hyper-V APIC enlightenment.  In this case we may need
+	 * to trigger a new interrupt delivery by writing the SVI field;
+	 * on the other hand isr_count and highest_isr_cache are unused
+	 * and must be left alone.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+					       apic_find_highest_isr(apic));
+	else {
 		--apic->isr_count;
-	BUG_ON(apic->isr_count < 0);
-	apic->highest_isr_cache = -1;
+		BUG_ON(apic->isr_count < 0);
+		apic->highest_isr_cache = -1;
+	}
 }
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
@@ -456,22 +515,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
 }
 
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
-	int result;
-
-	/* Note that isr_count is always 1 with vid enabled */
-	if (!apic->isr_count)
-		return -1;
-	if (likely(apic->highest_isr_cache != -1))
-		return apic->highest_isr_cache;
-
-	result = find_highest_vector(apic->regs + APIC_ISR);
-	ASSERT(result == -1 || result >= 16);
-
-	return result;
-}
-
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -1608,6 +1651,13 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	if (vector == -1)
 		return -1;
 
+	/*
+	 * We get here even with APIC virtualization enabled, if doing
+	 * nested virtualization and L1 runs with the "acknowledge interrupt
+	 * on exit" mode.  Then we cannot inject the interrupt via RVI,
+	 * because the process would deliver it through the IDT.
+	 */
+
 	apic_set_isr(vector, apic);
 	apic_update_ppr(apic);
 	apic_clear_irr(vector, apic);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9b531351a587..32e5329ab0b6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -198,16 +198,20 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
 /*
- * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number,
- * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation
- * number.
+ * the low bit of the generation number is always presumed to be zero.
+ * This disables mmio caching during memslot updates.  The concept is
+ * similar to a seqcount but instead of retrying the access we just punt
+ * and ignore the cache.
+ *
+ * spte bits 3-11 are used as bits 1-9 of the generation number,
+ * the bits 52-61 are used as bits 10-19 of the generation number.
  */
-#define MMIO_SPTE_GEN_LOW_SHIFT		3
+#define MMIO_SPTE_GEN_LOW_SHIFT		2
 #define MMIO_SPTE_GEN_HIGH_SHIFT	52
 
-#define MMIO_GEN_SHIFT			19
-#define MMIO_GEN_LOW_SHIFT		9
-#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 1)
+#define MMIO_GEN_SHIFT			20
+#define MMIO_GEN_LOW_SHIFT		10
+#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 2)
 #define MMIO_GEN_MASK			((1 << MMIO_GEN_SHIFT) - 1)
 #define MMIO_MAX_GEN			((1 << MMIO_GEN_SHIFT) - 1)
 
@@ -235,12 +239,7 @@ static unsigned int get_mmio_spte_generation(u64 spte)
 
 static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
 {
-	/*
-	 * Init kvm generation close to MMIO_MAX_GEN to easily test the
-	 * code of handling generation number wrap-around.
-	 */
-	return (kvm_memslots(kvm)->generation +
-		      MMIO_MAX_GEN - 150) & MMIO_GEN_MASK;
+	return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
 }
 
 static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
@@ -3157,7 +3156,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 		return;
 
-	vcpu_clear_mmio_info(vcpu, ~0ul);
+	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 	if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3329,7 +3328,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	arch.direct_map = vcpu->arch.mmu.direct_map;
 	arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
+	return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
 }
 
 static bool can_do_async_pf(struct kvm_vcpu *vcpu)
@@ -4379,8 +4378,8 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	 * The very rare case: if the generation-number is round,
 	 * zap all shadow pages.
 	 */
-	if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
-		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
+	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
+		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2de1bc09a8d4..78cfcb348f8a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -606,7 +606,7 @@ static int has_svm(void)
 	return 1;
 }
 
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
 {
 	/* Make sure we clean up behind us */
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -617,7 +617,7 @@ static void svm_hardware_disable(void *garbage)
 	amd_pmu_disable_virt();
 }
 
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
 {
 
 	struct svm_cpu_data *sd;
@@ -3213,7 +3213,7 @@ static int wrmsr_interception(struct vcpu_svm *svm)
 	msr.host_initiated = false;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-	if (svm_set_msr(&svm->vcpu, &msr)) {
+	if (kvm_set_msr(&svm->vcpu, &msr)) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(&svm->vcpu, 0);
 	} else {
@@ -3495,9 +3495,9 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 
 	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || !svm_exit_handlers[exit_code]) {
-		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
-		kvm_run->hw.hardware_exit_reason = exit_code;
-		return 0;
+		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code);
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
 	}
 
 	return svm_exit_handlers[exit_code](svm);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 392752834751..9ffaf739a86b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2582,12 +2582,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	default:
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
+			u64 old_msr_data = msr->data;
 			msr->data = data;
 			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
 				preempt_disable();
-				kvm_set_shared_msr(msr->index, msr->data,
-						   msr->mask);
+				ret = kvm_set_shared_msr(msr->index, msr->data,
+							 msr->mask);
 				preempt_enable();
+				if (ret)
+					msr->data = old_msr_data;
 			}
 			break;
 		}
@@ -2655,7 +2658,7 @@ static void kvm_cpu_vmxon(u64 addr)
 			: "memory", "cc");
 }
 
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2719,7 +2722,7 @@ static void kvm_cpu_vmxoff(void)
 	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
 }
 
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
 {
 	if (vmm_exclusive) {
 		vmclear_local_loaded_vmcss();
@@ -5169,7 +5172,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu)
 	msr.data = data;
 	msr.index = ecx;
 	msr.host_initiated = false;
-	if (vmx_set_msr(vcpu, &msr) != 0) {
+	if (kvm_set_msr(vcpu, &msr) != 0) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -6441,6 +6444,12 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int handle_invvpid(struct kvm_vcpu *vcpu)
+{
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -6486,6 +6495,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_MWAIT_INSTRUCTION]	      = handle_invalid_op,
 	[EXIT_REASON_MONITOR_INSTRUCTION]     = handle_invalid_op,
 	[EXIT_REASON_INVEPT]                  = handle_invept,
+	[EXIT_REASON_INVVPID]                 = handle_invvpid,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -6719,7 +6729,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
 	case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
 	case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
-	case EXIT_REASON_INVEPT:
+	case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID:
 		/*
 		 * VMX instructions trap unconditionally. This allows L1 to
 		 * emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6884,10 +6894,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	    && kvm_vmx_exit_handlers[exit_reason])
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
 	else {
-		vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
-		vcpu->run->hw.hardware_exit_reason = exit_reason;
+		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
 	}
-	return 0;
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b8578432d5b..f127b83b5e0c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -225,24 +225,29 @@ static void kvm_shared_msr_cpu_online(void)
 		shared_msr_update(i, shared_msrs_global.msrs[i]);
 }
 
-void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 {
 	unsigned int cpu = smp_processor_id();
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	int err;
 
 	if (((value ^ smsr->values[slot].curr) & mask) == 0)
-		return;
+		return 0;
 	smsr->values[slot].curr = value;
-	wrmsrl(shared_msrs_global.msrs[slot], value);
+	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
+	if (err)
+		return 1;
+
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
 		smsr->registered = true;
 	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -946,7 +951,6 @@ void kvm_enable_efer_bits(u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
-
 /*
  * Writes msr value into into the appropriate "register".
  * Returns 0 on success, non-0 otherwise.
@@ -954,8 +958,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
  */
 int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 {
+	switch (msr->index) {
+	case MSR_FS_BASE:
+	case MSR_GS_BASE:
+	case MSR_KERNEL_GS_BASE:
+	case MSR_CSTAR:
+	case MSR_LSTAR:
+		if (is_noncanonical_address(msr->data))
+			return 1;
+		break;
+	case MSR_IA32_SYSENTER_EIP:
+	case MSR_IA32_SYSENTER_ESP:
+		/*
+		 * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if
+		 * non-canonical address is written on Intel but not on
+		 * AMD (which ignores the top 32-bits, because it does
+		 * not implement 64-bit SYSENTER).
+		 *
+		 * 64-bit code should hence be able to write a non-canonical
+		 * value on AMD.  Making the address canonical ensures that
+		 * vmentry does not fail on Intel after writing a non-canonical
+		 * value, and that something deterministic happens if the guest
+		 * invokes 64-bit SYSENTER.
+		 */
+		msr->data = get_canonical(msr->data);
+	}
 	return kvm_x86_ops->set_msr(vcpu, msr);
 }
+EXPORT_SYMBOL_GPL(kvm_set_msr);
 
 /*
  * Adapt set_msr() to msr_io()'s calling convention
@@ -1109,7 +1139,6 @@ static inline u64 get_kernel_ns(void)
 {
 	struct timespec ts;
 
-	WARN_ON(preemptible());
 	ktime_get_ts(&ts);
 	monotonic_to_bootbased(&ts);
 	return timespec_to_ns(&ts);
@@ -1867,7 +1896,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
 			break;
 		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
-		if (kvm_write_guest(kvm, data,
+		if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
 			&tsc_ref, sizeof(tsc_ref)))
 			return 1;
 		mark_page_dirty(kvm, gfn);
@@ -2578,7 +2607,7 @@ out:
 	return r;
 }
 
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r;
 
@@ -4882,7 +4911,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 
 	++vcpu->stat.insn_emulation_fail;
 	trace_kvm_emulate_insn_failed(vcpu);
-	if (!is_guest_mode(vcpu)) {
+	if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
@@ -6780,7 +6809,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
 	kvm_rip_write(vcpu, 0);
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
@@ -6791,7 +6820,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	bool stable, backwards_tsc = false;
 
 	kvm_shared_msr_cpu_online();
-	ret = kvm_x86_ops->hardware_enable(garbage);
+	ret = kvm_x86_ops->hardware_enable();
 	if (ret != 0)
 		return ret;
 
@@ -6871,10 +6900,10 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
-	kvm_x86_ops->hardware_disable(garbage);
-	drop_user_return_notifiers(garbage);
+	kvm_x86_ops->hardware_disable();
+	drop_user_return_notifiers();
 }
 
 int kvm_arch_hardware_setup(void)
@@ -6991,6 +7020,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	if (type)
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 8da5823bcde6..21ea4fc91b5b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -78,15 +78,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
 	vcpu->arch.mmio_gva = gva & PAGE_MASK;
 	vcpu->arch.access = access;
 	vcpu->arch.mmio_gfn = gfn;
+	vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+}
+
+static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
 }
 
 /*
- * Clear the mmio cache info for the given gva,
- * specially, if gva is ~0ul, we clear all mmio cache info.
+ * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
+ * clear all mmio cache info.
  */
+#define MMIO_GVA_ANY (~(gva_t)0)
+
 static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
+	if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
 		return;
 
 	vcpu->arch.mmio_gva = 0;
@@ -94,7 +102,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
 
 static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 {
-	if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK))
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
+	      vcpu->arch.mmio_gva == (gva & PAGE_MASK))
 		return true;
 
 	return false;
@@ -102,7 +111,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
 
 static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
-	if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
+	if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
+	      vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
 		return true;
 
 	return false;
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
index 3056702e81fb..060cc4415bd9 100644
--- a/arch/x86/lib/hash.c
+++ b/arch/x86/lib/hash.c
@@ -39,7 +39,11 @@
 
 static inline u32 crc32_u32(u32 crc, u32 val)
 {
+#ifdef CONFIG_AS_CRC32
 	asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val));
+#else
+	asm (".byte 0xf2, 0x0f, 0x38, 0xf1, 0xc1" : "+a" (crc) : "c" (val));
+#endif
 	return crc;
 }
 
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a33081..3620928631ce 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,11 +30,13 @@ struct pg_state {
 	unsigned long start_address;
 	unsigned long current_address;
 	const struct addr_marker *marker;
+	unsigned long lines;
 };
 
 struct addr_marker {
 	unsigned long start_address;
 	const char *name;
+	unsigned long max_lines;
 };
 
 /* indices for address_markers; keep sync'd w/ address_markers below */
@@ -45,6 +47,7 @@ enum address_markers_idx {
 	LOW_KERNEL_NR,
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
+	ESPFIX_START_NR,
 	HIGH_KERNEL_NR,
 	MODULES_VADDR_NR,
 	MODULES_END_NR,
@@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,		"Low Kernel Mapping" },
 	{ VMALLOC_START,        "vmalloc() Area" },
 	{ VMEMMAP_START,        "Vmemmap" },
+	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
 	{ __START_KERNEL_map,   "High Kernel Mapping" },
 	{ MODULES_VADDR,        "Modules" },
 	{ MODULES_END,          "End Modules" },
@@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		      pgprot_t new_prot, int level)
 {
 	pgprotval_t prot, cur;
-	static const char units[] = "KMGTPE";
+	static const char units[] = "BKMGTPE";
 
 	/*
 	 * If we have a "break" in the series, we need to flush the state that
@@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		st->current_prot = new_prot;
 		st->level = level;
 		st->marker = address_markers;
+		st->lines = 0;
 		seq_printf(m, "---[ %s ]---\n", st->marker->name);
 	} else if (prot != cur || level != st->level ||
 		   st->current_address >= st->marker[1].start_address) {
@@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		/*
 		 * Now print the actual finished series
 		 */
-		seq_printf(m, "0x%0*lx-0x%0*lx   ",
-			   width, st->start_address,
-			   width, st->current_address);
-
-		delta = (st->current_address - st->start_address) >> 10;
-		while (!(delta & 1023) && unit[1]) {
-			delta >>= 10;
-			unit++;
+		if (!st->marker->max_lines ||
+		    st->lines < st->marker->max_lines) {
+			seq_printf(m, "0x%0*lx-0x%0*lx   ",
+				   width, st->start_address,
+				   width, st->current_address);
+
+			delta = (st->current_address - st->start_address) >> 10;
+			while (!(delta & 1023) && unit[1]) {
+				delta >>= 10;
+				unit++;
+			}
+			seq_printf(m, "%9lu%c ", delta, *unit);
+			printk_prot(m, st->current_prot, st->level);
 		}
-		seq_printf(m, "%9lu%c ", delta, *unit);
-		printk_prot(m, st->current_prot, st->level);
+		st->lines++;
 
 		/*
 		 * We print markers for special areas of address space,
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8c9f647ff9e1..8b977ebf9388 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 {
 	return NULL;
 }
-
-int pmd_huge_support(void)
-{
-	return 0;
-}
 #else
 
 struct page *
@@ -80,11 +75,6 @@ int pud_huge(pud_t pud)
 {
 	return !!(pud_val(pud) & _PAGE_PSE);
 }
-
-int pmd_huge_support(void)
-{
-	return 1;
-}
 #endif
 
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index f35c66c5959a..2308a401a1c5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1110,7 +1110,7 @@ void mark_rodata_ro(void)
 	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
 	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
 	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
-	unsigned long all_end = PFN_ALIGN(&_end);
+	unsigned long all_end;
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
@@ -1121,7 +1121,16 @@ void mark_rodata_ro(void)
 	/*
 	 * The rodata/data/bss/brk section (but not the kernel text!)
 	 * should also be not-executable.
+	 *
+	 * We align all_end to PMD_SIZE because the existing mapping
+	 * is a full PMD. If we would align _brk_end to PAGE_SIZE we
+	 * split the PMD and the reminder between _brk_end and the end
+	 * of the PMD will remain mapped executable.
+	 *
+	 * Any PMD which was setup after the one which covers _brk_end
+	 * has been zapped already via cleanup_highmem().
 	 */
+	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
 	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
 
 	rodata_test();
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 799580cabc78..94bd24771812 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 	return err;
 }
 
+static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
+			       void *arg)
+{
+	unsigned long i;
+
+	for (i = 0; i < nr_pages; ++i)
+		if (pfn_valid(start_pfn + i) &&
+		    !PageReserved(pfn_to_page(start_pfn + i)))
+			return 1;
+
+	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
+
+	return 0;
+}
+
 /*
  * Remap an arbitrary physical address space into the kernel virtual
  * address space. Needed when the kernel wants to access high addresses
@@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
+	pfn      = phys_addr >> PAGE_SHIFT;
 	last_pfn = last_addr >> PAGE_SHIFT;
-	for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) {
-		int is_ram = page_is_ram(pfn);
-
-		if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn)))
-			return NULL;
-		WARN_ON_ONCE(is_ram);
-	}
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+				  __ioremap_check_ram) == 1)
+		return NULL;
 
 	/*
 	 * Mappings have to be page-aligned
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index b3b19f46c016..fed892de9baf 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -405,7 +405,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
 	psize = page_level_size(level);
 	pmask = page_level_mask(level);
 	offset = virt_addr & ~pmask;
-	phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+	phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
 	return (phys_addr | offset);
 }
 EXPORT_SYMBOL_GPL(slow_virt_to_phys);
@@ -692,6 +692,18 @@ static bool try_to_free_pmd_page(pmd_t *pmd)
 	return true;
 }
 
+static bool try_to_free_pud_page(pud_t *pud)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		if (!pud_none(pud[i]))
+			return false;
+
+	free_page((unsigned long)pud);
+	return true;
+}
+
 static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
 {
 	pte_t *pte = pte_offset_kernel(pmd, start);
@@ -805,6 +817,16 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 	 */
 }
 
+static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
+{
+	pgd_t *pgd_entry = root + pgd_index(addr);
+
+	unmap_pud_range(pgd_entry, addr, end);
+
+	if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
+		pgd_clear(pgd_entry);
+}
+
 static int alloc_pte_page(pmd_t *pmd)
 {
 	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -999,9 +1021,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 {
 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
-	bool allocd_pgd = false;
-	pgd_t *pgd_entry;
 	pud_t *pud = NULL;	/* shut up gcc */
+	pgd_t *pgd_entry;
 	int ret;
 
 	pgd_entry = cpa->pgd + pgd_index(addr);
@@ -1015,7 +1036,6 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 			return -1;
 
 		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
-		allocd_pgd = true;
 	}
 
 	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
@@ -1023,19 +1043,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 
 	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
 	if (ret < 0) {
-		unmap_pud_range(pgd_entry, addr,
+		unmap_pgd_range(cpa->pgd, addr,
 				addr + (cpa->numpages << PAGE_SHIFT));
-
-		if (allocd_pgd) {
-			/*
-			 * If I allocated this PUD page, I can just as well
-			 * free it in this error path.
-			 */
-			pgd_clear(pgd_entry);
-			free_page((unsigned long)pud);
-		}
 		return ret;
 	}
+
 	cpa->numpages = ret;
 	return 0;
 }
@@ -1861,6 +1873,12 @@ out:
 	return retval;
 }
 
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+			       unsigned numpages)
+{
+	unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index c96314abd144..0004ac72dbdd 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 int ptep_clear_flush_young(struct vm_area_struct *vma,
 			   unsigned long address, pte_t *ptep)
 {
-	int young;
-
-	young = ptep_test_and_clear_young(vma, address, ptep);
-	if (young)
-		flush_tlb_page(vma, address);
-
-	return young;
+	/*
+	 * On x86 CPUs, clearing the accessed bit without a TLB flush
+	 * doesn't cause data corruption. [ It could cause incorrect
+	 * page aging and the (mistaken) reclaim of hot pages, but the
+	 * chance of that should be relatively low. ]
+	 *
+	 * So as a performance optimization don't flush the TLB when
+	 * clearing the accessed bit, it will eventually be flushed by
+	 * a context switch or a VM operation anyway. [ In the rare
+	 * event of it not getting flushed for a long time the delay
+	 * shouldn't really matter because there's no real memory
+	 * pressure for swapout to react to. ]
+	 */
+	return ptep_test_and_clear_young(vma, address, ptep);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4ed75dd81d05..af2d4317b218 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -171,7 +171,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
 	memset(header, 0xcc, sz); /* fill whole space with int3 instructions */
 
 	header->pages = sz / PAGE_SIZE;
-	hole = sz - (proglen + sizeof(*header));
+	hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header));
 
 	/* insert a random number of int3 instructions before BPF code */
 	*image_ptr = &header->image[prandom_u32() % hole];
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index db6b1ab43255..96a159afe3c6 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res,
 			return start;
 		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
+	} else if (res->flags & IORESOURCE_MEM) {
+		/* The low 1MB range is reserved for ISA cards */
+		if (start < BIOS_END)
+			start = BIOS_END;
 	}
 	return start;
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 8aee671ad05f..313468fe2555 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -928,14 +928,36 @@ static void __init efi_map_regions_fixed(void)
 
 }
 
+static void *realloc_pages(void *old_memmap, int old_shift)
+{
+	void *ret;
+
+	ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
+	if (!ret)
+		goto out;
+
+	/*
+	 * A first-time allocation doesn't have anything to copy.
+	 */
+	if (!old_memmap)
+		return ret;
+
+	memcpy(ret, old_memmap, PAGE_SIZE << old_shift);
+
+out:
+	free_pages((unsigned long)old_memmap, old_shift);
+	return ret;
+}
+
 /*
- * Map efi memory ranges for runtime serivce and update new_memmap with virtual
- * addresses.
+ * Map the efi memory ranges of the runtime services and update new_mmap with
+ * virtual addresses.
  */
-static void * __init efi_map_regions(int *count)
+static void * __init efi_map_regions(int *count, int *pg_shift)
 {
+	void *p, *new_memmap = NULL;
+	unsigned long left = 0;
 	efi_memory_desc_t *md;
-	void *p, *tmp, *new_memmap = NULL;
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
@@ -950,20 +972,23 @@ static void * __init efi_map_regions(int *count)
 		efi_map_region(md);
 		get_systab_virt_addr(md);
 
-		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
-			       GFP_KERNEL);
-		if (!tmp)
-			goto out;
-		new_memmap = tmp;
+		if (left < memmap.desc_size) {
+			new_memmap = realloc_pages(new_memmap, *pg_shift);
+			if (!new_memmap)
+				return NULL;
+
+			left += PAGE_SIZE << *pg_shift;
+			(*pg_shift)++;
+		}
+
 		memcpy(new_memmap + (*count * memmap.desc_size), md,
 		       memmap.desc_size);
+
+		left -= memmap.desc_size;
 		(*count)++;
 	}
 
 	return new_memmap;
-out:
-	kfree(new_memmap);
-	return NULL;
 }
 
 /*
@@ -989,9 +1014,9 @@ out:
  */
 void __init efi_enter_virtual_mode(void)
 {
-	efi_status_t status;
+	int err, count = 0, pg_shift = 0;
 	void *new_memmap = NULL;
-	int err, count = 0;
+	efi_status_t status;
 
 	efi.systab = NULL;
 
@@ -1008,20 +1033,24 @@ void __init efi_enter_virtual_mode(void)
 		efi_map_regions_fixed();
 	} else {
 		efi_merge_regions();
-		new_memmap = efi_map_regions(&count);
+		new_memmap = efi_map_regions(&count, &pg_shift);
 		if (!new_memmap) {
 			pr_err("Error reallocating memory, EFI runtime non-functional!\n");
 			return;
 		}
-	}
 
-	err = save_runtime_map();
-	if (err)
-		pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+		err = save_runtime_map();
+		if (err)
+			pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+	}
 
 	BUG_ON(!efi.systab);
 
-	efi_setup_page_tables();
+	if (!efi_setup) {
+		if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift))
+			return;
+	}
+
 	efi_sync_low_kernel_mappings();
 
 	if (!efi_setup) {
@@ -1061,7 +1090,35 @@ void __init efi_enter_virtual_mode(void)
 
 	efi_runtime_mkexec();
 
-	kfree(new_memmap);
+
+	/*
+	 * We mapped the descriptor array into the EFI pagetable above but we're
+	 * not unmapping it here. Here's why:
+	 *
+	 * We're copying select PGDs from the kernel page table to the EFI page
+	 * table and when we do so and make changes to those PGDs like unmapping
+	 * stuff from them, those changes appear in the kernel page table and we
+	 * go boom.
+	 *
+	 * From setup_real_mode():
+	 *
+	 * ...
+	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
+	 *
+	 * In this particular case, our allocation is in PGD 0 of the EFI page
+	 * table but we've copied that PGD from PGD[272] of the EFI page table:
+	 *
+	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
+	 *
+	 * where the direct memory mapping in kernel space is.
+	 *
+	 * new_memmap's VA comes from that direct mapping and thus clearing it,
+	 * it would get cleared in the kernel page table too.
+	 *
+	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
+	 */
+	if (!efi_setup)
+		free_pages((unsigned long)new_memmap, pg_shift);
 
 	/* clean DUMMY object */
 	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 0b74cdf7f816..9ee3491e31fb 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -40,7 +40,12 @@
 static unsigned long efi_rt_eflags;
 
 void efi_sync_low_kernel_mappings(void) {}
-void efi_setup_page_tables(void) {}
+void __init efi_dump_pagetable(void) {}
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	return 0;
+}
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {}
 
 void __init efi_map_region(efi_memory_desc_t *md)
 {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 0c2a234fef1e..666b74a09092 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -137,12 +137,38 @@ void efi_sync_low_kernel_mappings(void)
 		sizeof(pgd_t) * num_pgds);
 }
 
-void efi_setup_page_tables(void)
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
+	pgd_t *pgd;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return 0;
+
 	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+	pgd = __va(efi_scratch.efi_pgt);
 
-	if (!efi_enabled(EFI_OLD_MEMMAP))
-		efi_scratch.use_pgd = true;
+	/*
+	 * It can happen that the physical address of new_memmap lands in memory
+	 * which is not mapped in the EFI page table. Therefore we need to go
+	 * and ident-map those pages containing the map before calling
+	 * phys_efi_set_virtual_address_map().
+	 */
+	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
+		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
+		return 1;
+	}
+
+	efi_scratch.use_pgd = true;
+
+
+	return 0;
+}
+
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
 }
 
 static void __init __map_region(efi_memory_desc_t *md, u64 va)
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index a12bddc7ccea..7f517ca19d32 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -212,10 +212,10 @@
 203	common	sched_setaffinity	sys_sched_setaffinity
 204	common	sched_getaffinity	sys_sched_getaffinity
 205	64	set_thread_area
-206	common	io_setup		sys_io_setup
+206	64	io_setup		sys_io_setup
 207	common	io_destroy		sys_io_destroy
 208	common	io_getevents		sys_io_getevents
-209	common	io_submit		sys_io_submit
+209	64	io_submit		sys_io_submit
 210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
 212	common	lookup_dcookie		sys_lookup_dcookie
@@ -358,3 +358,5 @@
 540	x32	process_vm_writev	compat_sys_process_vm_writev
 541	x32	setsockopt		compat_sys_setsockopt
 542	x32	getsockopt		compat_sys_getsockopt
+543	x32	io_setup		compat_sys_io_setup
+544	x32	io_submit		compat_sys_io_submit
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
new file mode 100644
index 000000000000..23210baade2d
--- /dev/null
+++ b/arch/x86/tools/calc_run_size.pl
@@ -0,0 +1,39 @@
+#!/usr/bin/perl
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | perl calc_run_size.pl
+use strict;
+
+my $mem_size = 0;
+my $file_offset = 0;
+
+my $sections=" *[0-9]+ \.(?:bss|brk) +";
+while (<>) {
+	if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
+		my $size = hex($1);
+		my $offset = hex($2);
+		$mem_size += $size;
+		if ($file_offset == 0) {
+			$file_offset = $offset;
+		} elsif ($file_offset != $offset) {
+			# BFD linker shows the same file offset in ELF.
+			# Gold linker shows them as consecutive.
+			next if ($file_offset + $mem_size == $offset + $size);
+
+			printf STDERR "file_offset: 0x%lx\n", $file_offset;
+			printf STDERR "mem_size: 0x%lx\n", $mem_size;
+			printf STDERR "offset: 0x%lx\n", $offset;
+			printf STDERR "size: 0x%lx\n", $size;
+
+			die ".bss and .brk are non-contiguous\n";
+		}
+	}
+}
+
+if ($file_offset == 0) {
+	die "Never found .bss or .brk file offset\n";
+}
+printf("%d\n", $mem_size + $file_offset);
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 431e87544411..ab6ba35a9357 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -117,30 +117,45 @@ subsys_initcall(init_vdso);
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 	unsigned long addr, end;
 	unsigned offset;
-	end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+	/*
+	 * Round up the start address.  It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
 	if (end >= TASK_SIZE_MAX)
 		end = TASK_SIZE_MAX;
 	end -= len;
-	/* This loses some more bits than a modulo, but is cheaper */
-	offset = get_random_int() & (PTRS_PER_PTE - 1);
-	addr = start + (offset << PAGE_SHIFT);
-	if (addr >= end)
-		addr = end;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
 
 	/*
-	 * page-align it here so that get_unmapped_area doesn't
-	 * align it wrongfully again to the next page. addr can come in 4K
-	 * unaligned here as a result of stack start randomization.
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
 	 */
-	addr = PAGE_ALIGN(addr);
 	addr = align_vdso_addr(addr);
 
 	return addr;
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index c98583588580..5b406fc45674 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -134,6 +134,7 @@ static int __init xlated_setup_gnttab_pages(void)
 {
 	struct page **pages;
 	xen_pfn_t *pfns;
+	void *vaddr;
 	int rc;
 	unsigned int i;
 	unsigned long nr_grant_frames = gnttab_max_grant_frames();
@@ -159,21 +160,20 @@ static int __init xlated_setup_gnttab_pages(void)
 	for (i = 0; i < nr_grant_frames; i++)
 		pfns[i] = page_to_pfn(pages[i]);
 
-	rc = arch_gnttab_map_shared(pfns, nr_grant_frames, nr_grant_frames,
-				    &xen_auto_xlat_grant_frames.vaddr);
-
-	if (rc) {
+	vaddr = vmap(pages, nr_grant_frames, 0, PAGE_KERNEL);
+	if (!vaddr) {
 		pr_warn("%s Couldn't map %ld pfns rc:%d\n", __func__,
 			nr_grant_frames, rc);
 		free_xenballooned_pages(nr_grant_frames, pages);
 		kfree(pages);
 		kfree(pfns);
-		return rc;
+		return -ENOMEM;
 	}
 	kfree(pages);
 
 	xen_auto_xlat_grant_frames.pfn = pfns;
 	xen_auto_xlat_grant_frames.count = nr_grant_frames;
+	xen_auto_xlat_grant_frames.vaddr = vaddr;
 
 	return 0;
 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 2423ef04ffea..c83da6fb2dee 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
  *
  * We can construct this by grafting the Xen provided pagetable into
  * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
- * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt.  This
- * means that only the kernel has a physical mapping to start with -
- * but that's enough to get __va working.  We need to fill in the rest
- * of the physical mapping once some sort of allocator has been set
- * up.
- * NOTE: for PVH, the page tables are native.
+ * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
+ * kernel has a physical mapping to start with - but that's enough to
+ * get __va working.  We need to fill in the rest of the physical
+ * mapping once some sort of allocator has been set up.  NOTE: for
+ * PVH, the page tables are native.
  */
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
@@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		/* L3_i[0] -> level2_ident_pgt */
 		convert_pfn_mfn(level3_ident_pgt);
 		/* L3_k[510] -> level2_kernel_pgt
-		 * L3_i[511] -> level2_fixmap_pgt */
+		 * L3_k[511] -> level2_fixmap_pgt */
 		convert_pfn_mfn(level3_kernel_pgt);
+
+		/* L3_k[511][506] -> level1_fixmap_pgt */
+		convert_pfn_mfn(level2_fixmap_pgt);
 	}
 	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
@@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
 	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][511] have entries that point to the same
+	 * Both L4[272][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you
 	 * are OK - which is what cleanup_highmap does) */
 	copy_page(level2_ident_pgt, l2);
-	/* Graft it onto L4[511][511] */
+	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
-	/* Get [511][510] and graft that in level2_fixmap_pgt */
-	l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
-	l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
-	copy_page(level2_fixmap_pgt, l2);
-	/* Note that we don't do anything with level1_fixmap_pgt which
-	 * we don't need. */
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		/* Make pagetable pieces RO */
 		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
@@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
 
 		/* Pin down new L4 */
 		pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 0982233b9b84..a6a72ce8630f 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -574,13 +574,7 @@ void xen_enable_syscall(void)
 	}
 #endif /* CONFIG_X86_64 */
 }
-void xen_enable_nmi(void)
-{
-#ifdef CONFIG_X86_64
-	if (register_callback(CALLBACKTYPE_nmi, (char *)nmi))
-		BUG();
-#endif
-}
+
 void __init xen_pvmmu_arch_setup(void)
 {
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
@@ -595,7 +589,6 @@ void __init xen_pvmmu_arch_setup(void)
 
 	xen_enable_sysenter();
 	xen_enable_syscall();
-	xen_enable_nmi();
 }
 
 /* This function is not called for HVM domains */
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 581521c843a5..c570feab9fa2 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -274,7 +274,7 @@ void __init xen_init_spinlocks(void)
 		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
 		return;
 	}
-
+	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
 }
@@ -290,6 +290,9 @@ static __init int xen_init_spinlocks_jump(void)
 	if (!xen_pvspin)
 		return 0;
 
+	if (!xen_domain())
+		return 0;
+
 	static_key_slow_inc(&paravirt_ticketlocks_enabled);
 	return 0;
 }
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 7b78f88c1707..5718b0b58b60 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -444,7 +444,7 @@ void xen_setup_timer(int cpu)
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
 				      IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER|
-				      IRQF_FORCE_RESUME,
+				      IRQF_FORCE_RESUME|IRQF_EARLY_RESUME,
 				      name, NULL);
 	(void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX);
 
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 216446295ada..51230ba97bef 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -67,7 +67,12 @@
 #define VMALLOC_START		0xC0000000
 #define VMALLOC_END		0xC7FEFFFF
 #define TLBTEMP_BASE_1		0xC7FF0000
-#define TLBTEMP_BASE_2		0xC7FF8000
+#define TLBTEMP_BASE_2		(TLBTEMP_BASE_1 + DCACHE_WAY_SIZE)
+#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE
+#define TLBTEMP_SIZE		(2 * DCACHE_WAY_SIZE)
+#else
+#define TLBTEMP_SIZE		ICACHE_WAY_SIZE
+#endif
 
 /*
  * For the Xtensa architecture, the PTE layout is as follows:
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index fd686dc45d1a..c7211e7e182d 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -52,7 +52,12 @@
  */
 	.macro	get_fs	ad, sp
 	GET_CURRENT(\ad,\sp)
+#if THREAD_CURRENT_DS > 1020
+	addi	\ad, \ad, TASK_THREAD
+	l32i	\ad, \ad, THREAD_CURRENT_DS - TASK_THREAD
+#else
 	l32i	\ad, \ad, THREAD_CURRENT_DS
+#endif
 	.endm
 
 /*
diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h
index b4cb1100c0fb..a47909f0c34b 100644
--- a/arch/xtensa/include/uapi/asm/ioctls.h
+++ b/arch/xtensa/include/uapi/asm/ioctls.h
@@ -28,17 +28,17 @@
 #define TCSETSW		0x5403
 #define TCSETSF		0x5404
 
-#define TCGETA		_IOR('t', 23, struct termio)
-#define TCSETA		_IOW('t', 24, struct termio)
-#define TCSETAW		_IOW('t', 25, struct termio)
-#define TCSETAF		_IOW('t', 28, struct termio)
+#define TCGETA		0x80127417	/* _IOR('t', 23, struct termio) */
+#define TCSETA		0x40127418	/* _IOW('t', 24, struct termio) */
+#define TCSETAW		0x40127419	/* _IOW('t', 25, struct termio) */
+#define TCSETAF		0x4012741C	/* _IOW('t', 28, struct termio) */
 
 #define TCSBRK		_IO('t', 29)
 #define TCXONC		_IO('t', 30)
 #define TCFLSH		_IO('t', 31)
 
-#define TIOCSWINSZ	_IOW('t', 103, struct winsize)
-#define TIOCGWINSZ	_IOR('t', 104, struct winsize)
+#define TIOCSWINSZ	0x40087467	/* _IOW('t', 103, struct winsize) */
+#define TIOCGWINSZ	0x80087468	/* _IOR('t', 104, struct winsize) */
 #define	TIOCSTART	_IO('t', 110)		/* start output, like ^Q */
 #define	TIOCSTOP	_IO('t', 111)		/* stop output, like ^S */
 #define TIOCOUTQ        _IOR('t', 115, int)     /* output queue size */
@@ -88,7 +88,6 @@
 #define TIOCSETD	_IOW('T', 35, int)
 #define TIOCGETD	_IOR('T', 36, int)
 #define TCSBRKP		_IOW('T', 37, int)   /* Needed for POSIX tcsendbreak()*/
-#define TIOCTTYGSTRUCT	_IOR('T', 38, struct tty_struct) /* For debugging only*/
 #define TIOCSBRK	_IO('T', 39) 	     /* BSD compatibility */
 #define TIOCCBRK	_IO('T', 40)	     /* BSD compatibility */
 #define TIOCGSID	_IOR('T', 41, pid_t) /* Return the session ID of FD*/
@@ -114,8 +113,10 @@
 #define TIOCSERGETLSR   _IOR('T', 89, unsigned int) /* Get line status reg. */
   /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
 # define TIOCSER_TEMT    0x01		     /* Transmitter physically empty */
-#define TIOCSERGETMULTI _IOR('T', 90, struct serial_multiport_struct) /* Get multiport config  */
-#define TIOCSERSETMULTI _IOW('T', 91, struct serial_multiport_struct) /* Set multiport config */
+#define TIOCSERGETMULTI 0x80a8545a /* Get multiport config  */
+			/* _IOR('T', 90, struct serial_multiport_struct) */
+#define TIOCSERSETMULTI 0x40a8545b /* Set multiport config */
+			/* _IOW('T', 91, struct serial_multiport_struct) */
 
 #define TIOCMIWAIT	_IO('T', 92) /* wait for a change on serial input line(s) */
 #define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index b9395529f02d..50084f7c01c8 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -384,7 +384,8 @@ __SYSCALL(174, sys_chroot, 1)
 #define __NR_pivot_root 			175
 __SYSCALL(175, sys_pivot_root, 2)
 #define __NR_umount 				176
-__SYSCALL(176, sys_umount, 2)
+__SYSCALL(176, sys_oldumount, 1)
+#define __ARCH_WANT_SYS_OLDUMOUNT
 #define __NR_swapoff 				177
 __SYSCALL(177, sys_swapoff, 1)
 #define __NR_sync 				178
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index ef7f4990722b..a06b7efaae82 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1001,9 +1001,8 @@ ENTRY(fast_syscall_xtensa)
 	movi	a7, 4			# sizeof(unsigned int)
 	access_ok a3, a7, a0, a2, .Leac	# a0: scratch reg, a2: sp
 
-	addi	a6, a6, -1		# assuming SYS_XTENSA_ATOMIC_SET = 1
-	_bgeui	a6, SYS_XTENSA_COUNT - 1, .Lill
-	_bnei	a6, SYS_XTENSA_ATOMIC_CMP_SWP - 1, .Lnswp
+	_bgeui	a6, SYS_XTENSA_COUNT, .Lill
+	_bnei	a6, SYS_XTENSA_ATOMIC_CMP_SWP, .Lnswp
 
 	/* Fall through for ATOMIC_CMP_SWP. */
 
@@ -1015,27 +1014,26 @@ TRY	s32i	a5, a3, 0		# different, modify value
 	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, 1			# and return 1
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 1:	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, 0			# return 0 (note that we cannot set
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 .Lnswp:	/* Atomic set, add, and exg_add. */
 
 TRY	l32i	a7, a3, 0		# orig
+	addi	a6, a6, -SYS_XTENSA_ATOMIC_SET
 	add	a0, a4, a7		# + arg
 	moveqz	a0, a4, a6		# set
+	addi	a6, a6, SYS_XTENSA_ATOMIC_SET
 TRY	s32i	a0, a3, 0		# write new value
 
 	mov	a0, a2
 	mov	a2, a7
 	l32i	a7, a0, PT_AREG7	# restore a7
 	l32i	a0, a0, PT_AREG0	# restore a0
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 CATCH
@@ -1044,7 +1042,7 @@ CATCH
 	movi	a2, -EFAULT
 	rfe
 
-.Lill:	l32i	a7, a2, PT_AREG0	# restore a7
+.Lill:	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, -EINVAL
 	rfe
@@ -1565,7 +1563,7 @@ ENTRY(fast_second_level_miss)
 	rsr	a0, excvaddr
 	bltu	a0, a3, 2f
 
-	addi	a1, a0, -(2 << (DCACHE_ALIAS_ORDER + PAGE_SHIFT))
+	addi	a1, a0, -TLBTEMP_SIZE
 	bgeu	a1, a3, 2f
 
 	/* Check if we have to restore an ITLB mapping. */
@@ -1820,7 +1818,6 @@ ENTRY(_switch_to)
 
 	entry	a1, 16
 
-	mov	a10, a2			# preserve 'prev' (a2)
 	mov	a11, a3			# and 'next' (a3)
 
 	l32i	a4, a2, TASK_THREAD_INFO
@@ -1828,8 +1825,14 @@ ENTRY(_switch_to)
 
 	save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
-	s32i	a0, a10, THREAD_RA	# save return address
-	s32i	a1, a10, THREAD_SP	# save stack pointer
+#if THREAD_RA > 1020 || THREAD_SP > 1020
+	addi	a10, a2, TASK_THREAD
+	s32i	a0, a10, THREAD_RA - TASK_THREAD	# save return address
+	s32i	a1, a10, THREAD_SP - TASK_THREAD	# save stack pointer
+#else
+	s32i	a0, a2, THREAD_RA	# save return address
+	s32i	a1, a2, THREAD_SP	# save stack pointer
+#endif
 
 	/* Disable ints while we manipulate the stack pointer. */
 
@@ -1870,7 +1873,6 @@ ENTRY(_switch_to)
 	load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
 	wsr	a14, ps
-	mov	a2, a10			# return 'prev'
 	rsync
 
 	retw
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 2d9cc6dbfd78..e8b76b8e4b29 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -49,9 +49,8 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag)
 
 	/* We currently don't support coherent memory outside KSEG */
 
-	if (ret < XCHAL_KSEG_CACHED_VADDR
-	    || ret >= XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE)
-		BUG();
+	BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
+	       ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
 
 	if (ret != 0) {
@@ -68,10 +67,11 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_coherent(struct device *hwdev, size_t size,
 			 void *vaddr, dma_addr_t dma_handle)
 {
-	long addr=(long)vaddr+XCHAL_KSEG_CACHED_VADDR-XCHAL_KSEG_BYPASS_VADDR;
+	unsigned long addr = (unsigned long)vaddr +
+		XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
 
-	if (addr < 0 || addr >= XCHAL_KSEG_SIZE)
-		BUG();
+	BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR ||
+	       addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
 	free_pages(addr, get_order(size));
 }
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 84fe931bb60e..555f75cff7d3 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -221,7 +221,7 @@ static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
 		int depth, void *data)
 {
 	const __be32 *ranges;
-	unsigned long len;
+	int len;
 
 	if (depth > 1)
 		return 0;
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index f9e1ec346e35..8453e6e39895 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -376,38 +376,42 @@ _DoubleExceptionVector_WindowOverflow:
 	beqz	a2, 1f		# if at start of vector, don't restore
 
 	addi	a0, a0, -128
-	bbsi	a0, 8, 1f	# don't restore except for overflow 8 and 12
-	bbsi	a0, 7, 2f
+	bbsi.l	a0, 8, 1f	# don't restore except for overflow 8 and 12
+
+	/*
+	 * This fixup handler is for the extremely unlikely case where the
+	 * overflow handler's reference thru a0 gets a hardware TLB refill
+	 * that bumps out the (distinct, aliasing) TLB entry that mapped its
+	 * prior references thru a9/a13, and where our reference now thru
+	 * a9/a13 gets a 2nd-level miss exception (not hardware TLB refill).
+	 */
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	bbsi.l	a0, 7, 2f
 
 	/*
 	 * Restore a0 as saved by _WindowOverflow8().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a9, and where our reference now thru a9
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a9, -16
-	wsr	a2, depc	# replace the saved a0
-	j	1f
+	l32e	a0, a9, -16
+	wsr	a0, depc	# replace the saved a0
+	j	3f
 
 2:
 	/*
 	 * Restore a0 as saved by _WindowOverflow12().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a13, and where our reference now thru a13
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a13, -16
-	wsr	a2, depc	# replace the saved a0
+	l32e	a0, a13, -16
+	wsr	a0, depc	# replace the saved a0
+3:
+	xsr	a3, excsave1
+	movi	a0, 0
+	s32i	a0, a3, EXC_TABLE_FIXUP
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
 1:
 	/*
 	 * Restore WindowBase while leaving all address registers restored.
@@ -449,6 +453,7 @@ _DoubleExceptionVector_WindowOverflow:
 
 	s32i	a0, a2, PT_DEPC
 
+_DoubleExceptionVector_handle_exception:
 	addx4	a0, a0, a3
 	l32i	a0, a0, EXC_TABLE_FAST_USER
 	xsr	a3, excsave1
@@ -464,11 +469,120 @@ _DoubleExceptionVector_WindowOverflow:
 	rotw	-3
 	j	1b
 
-	.end literal_prefix
 
 ENDPROC(_DoubleExceptionVector)
 
 /*
+ * Fixup handler for TLB miss in double exception handler for window owerflow.
+ * We get here with windowbase set to the window that was being spilled and
+ * a0 trashed. a0 bit 7 determines if this is a call8 (bit clear) or call12
+ * (bit set) window.
+ *
+ * We do the following here:
+ * - go to the original window retaining a0 value;
+ * - set up exception stack to return back to appropriate a0 restore code
+ *   (we'll need to rotate window back and there's no place to save this
+ *    information, use different return address for that);
+ * - handle the exception;
+ * - go to the window that was being spilled;
+ * - set up window_overflow_restore_a0_fixup as a fixup routine;
+ * - reload a0;
+ * - restore the original window;
+ * - reset the default fixup routine;
+ * - return to user. By the time we get to this fixup handler all information
+ *   about the conditions of the original double exception that happened in
+ *   the window overflow handler is lost, so we just return to userspace to
+ *   retry overflow from start.
+ *
+ * a0: value of depc, original value in depc
+ * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
+ * a3: exctable, original value in excsave1
+ */
+
+ENTRY(window_overflow_restore_a0_fixup)
+
+	rsr	a0, ps
+	extui	a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
+	rsr	a2, windowbase
+	sub	a0, a2, a0
+	extui	a0, a0, 0, 3
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	_beqi	a0, 1, .Lhandle_1
+	_beqi	a0, 3, .Lhandle_3
+
+	.macro	overflow_fixup_handle_exception_pane n
+
+	rsr	a0, depc
+	rotw	-\n
+
+	xsr	a3, excsave1
+	wsr	a2, depc
+	l32i	a2, a3, EXC_TABLE_KSTK
+	s32i	a0, a2, PT_AREG0
+
+	movi	a0, .Lrestore_\n
+	s32i	a0, a2, PT_DEPC
+	rsr	a0, exccause
+	j	_DoubleExceptionVector_handle_exception
+
+	.endm
+
+	overflow_fixup_handle_exception_pane 2
+.Lhandle_1:
+	overflow_fixup_handle_exception_pane 1
+.Lhandle_3:
+	overflow_fixup_handle_exception_pane 3
+
+	.macro	overflow_fixup_restore_a0_pane n
+
+	rotw	\n
+	/* Need to preserve a0 value here to be able to handle exception
+	 * that may occur on a0 reload from stack. It may occur because
+	 * TLB miss handler may not be atomic and pointer to page table
+	 * may be lost before we get here. There are no free registers,
+	 * so we need to use EXC_TABLE_DOUBLE_SAVE area.
+	 */
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	bbsi.l	a0, 7, 1f
+	l32e	a0, a9, -16
+	j	2f
+1:
+	l32e	a0, a13, -16
+2:
+	rotw	-\n
+
+	.endm
+
+.Lrestore_2:
+	overflow_fixup_restore_a0_pane 2
+
+.Lset_default_fixup:
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, 0
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	rfe
+
+.Lrestore_1:
+	overflow_fixup_restore_a0_pane 1
+	j	.Lset_default_fixup
+.Lrestore_3:
+	overflow_fixup_restore_a0_pane 3
+	j	.Lset_default_fixup
+
+ENDPROC(window_overflow_restore_a0_fixup)
+
+	.end literal_prefix
+/*
  * Debug interrupt vector
  *
  * There is not much space here, so simply jump to another handler.
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index ee32c0085dff..d16db6df86f8 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -269,13 +269,13 @@ SECTIONS
 		  .UserExceptionVector.literal)
   SECTION_VECTOR (_DoubleExceptionVector_literal,
 		  .DoubleExceptionVector.literal,
-		  DOUBLEEXC_VECTOR_VADDR - 16,
+		  DOUBLEEXC_VECTOR_VADDR - 40,
 		  SIZEOF(.UserExceptionVector.text),
 		  .UserExceptionVector.text)
   SECTION_VECTOR (_DoubleExceptionVector_text,
 		  .DoubleExceptionVector.text,
 		  DOUBLEEXC_VECTOR_VADDR,
-		  32,
+		  40,
 		  .DoubleExceptionVector.literal)
 
   . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4e491d9b5292..d8f80e733cf8 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -80,7 +80,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	blkg->q = q;
 	INIT_LIST_HEAD(&blkg->q_node);
 	blkg->blkcg = blkcg;
-	blkg->refcnt = 1;
+	atomic_set(&blkg->refcnt, 1);
 
 	/* root blkg uses @q->root_rl, init rl only for !root blkgs */
 	if (blkcg != &blkcg_root) {
@@ -399,11 +399,8 @@ void __blkg_release_rcu(struct rcu_head *rcu_head)
 
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
-	if (blkg->parent) {
-		spin_lock_irq(blkg->q->queue_lock);
+	if (blkg->parent)
 		blkg_put(blkg->parent);
-		spin_unlock_irq(blkg->q->queue_lock);
-	}
 
 	blkg_free(blkg);
 }
@@ -862,6 +859,13 @@ void blkcg_drain_queue(struct request_queue *q)
 {
 	lockdep_assert_held(q->queue_lock);
 
+	/*
+	 * @q could be exiting and already have destroyed all blkgs as
+	 * indicated by NULL root_blkg.  If so, don't confuse policies.
+	 */
+	if (!q->root_blkg)
+		return;
+
 	blk_throtl_drain(q);
 }
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 86154eab9523..c135f5660702 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
 #include <linux/blkdev.h>
+#include <linux/atomic.h>
 
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
@@ -104,7 +105,7 @@ struct blkcg_gq {
 	struct request_list		rl;
 
 	/* reference count */
-	int				refcnt;
+	atomic_t			refcnt;
 
 	/* is this blkg online? protected by both blkcg and q locks */
 	bool				online;
@@ -253,13 +254,12 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
  * blkg_get - get a blkg reference
  * @blkg: blkg to get
  *
- * The caller should be holding queue_lock and an existing reference.
+ * The caller should be holding an existing reference.
  */
 static inline void blkg_get(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(!blkg->refcnt);
-	blkg->refcnt++;
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	atomic_inc(&blkg->refcnt);
 }
 
 void __blkg_release_rcu(struct rcu_head *rcu);
@@ -267,14 +267,11 @@ void __blkg_release_rcu(struct rcu_head *rcu);
 /**
  * blkg_put - put a blkg reference
  * @blkg: blkg to put
- *
- * The caller should be holding queue_lock.
  */
 static inline void blkg_put(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(blkg->refcnt <= 0);
-	if (!--blkg->refcnt)
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	if (atomic_dec_and_test(&blkg->refcnt))
 		call_rcu(&blkg->rcu_head, __blkg_release_rcu);
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index bfe16d5af9f9..e45b321cf6a0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2353,7 +2353,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req);
+	trace_block_rq_complete(req->q, req, nr_bytes);
 
 	/*
 	 * For fs requests, rq is just carrier of independent bio's
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index f8721278601c..78d38352bf8d 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -95,7 +95,7 @@ unsigned int *blk_mq_make_queue_map(struct blk_mq_reg *reg)
 	unsigned int *map;
 
 	/* If cpus are offline, map them to first hctx */
-	map = kzalloc_node(sizeof(*map) * num_possible_cpus(), GFP_KERNEL,
+	map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
 				reg->numa_node);
 	if (!map)
 		return NULL;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5d21239bc859..95138e9d0ad5 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -553,7 +553,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		bottom = max(b->physical_block_size, b->io_min) + alignment;
 
 		/* Verify that top and bottom intervals line up */
-		if (max(top, bottom) & (min(top, bottom) - 1)) {
+		if (max(top, bottom) % min(top, bottom)) {
 			t->misaligned = 1;
 			ret = -1;
 		}
@@ -598,7 +598,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm(t->alignment_offset, alignment)
-		& (max(t->physical_block_size, t->io_min) - 1);
+		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 3f33d8672268..a185b86741e5 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag)
 EXPORT_SYMBOL(blk_queue_find_tag);
 
 /**
- * __blk_free_tags - release a given set of tag maintenance info
+ * blk_free_tags - release a given set of tag maintenance info
  * @bqt:	the tag map to free
  *
- * Tries to free the specified @bqt.  Returns true if it was
- * actually freed and false if there are still references using it
+ * Drop the reference count on @bqt and frees it when the last reference
+ * is dropped.
  */
-static int __blk_free_tags(struct blk_queue_tag *bqt)
+void blk_free_tags(struct blk_queue_tag *bqt)
 {
-	int retval;
-
-	retval = atomic_dec_and_test(&bqt->refcnt);
-	if (retval) {
+	if (atomic_dec_and_test(&bqt->refcnt)) {
 		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
 							bqt->max_depth);
 
@@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt)
 
 		kfree(bqt);
 	}
-
-	return retval;
 }
+EXPORT_SYMBOL(blk_free_tags);
 
 /**
  * __blk_queue_free_tags - release tag maintenance info
@@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q)
 	if (!bqt)
 		return;
 
-	__blk_free_tags(bqt);
+	blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
 	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
 }
 
 /**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt:	the tag map to free
- *
- * For externally managed @bqt frees the map.  Callers of this
- * function must guarantee to have released all the queues that
- * might have been using this tag map.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
-	if (unlikely(!__blk_free_tags(bqt)))
-		BUG();
-}
-EXPORT_SYMBOL(blk_free_tags);
-
-/**
  * blk_queue_free_tags - release tag maintenance info
  * @q:  the request queue for the device
  *
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 744833b630c6..91c25f261c91 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1275,12 +1275,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 static void
 cfq_update_group_weight(struct cfq_group *cfqg)
 {
-	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
-
 	if (cfqg->new_weight) {
 		cfqg->weight = cfqg->new_weight;
 		cfqg->new_weight = 0;
 	}
+}
+
+static void
+cfq_update_group_leaf_weight(struct cfq_group *cfqg)
+{
+	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
 	if (cfqg->new_leaf_weight) {
 		cfqg->leaf_weight = cfqg->new_leaf_weight;
@@ -1299,7 +1303,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	/* add to the service tree */
 	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
-	cfq_update_group_weight(cfqg);
+	cfq_update_group_leaf_weight(cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/*
@@ -1323,6 +1327,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	 */
 	while ((parent = cfqg_parent(pos))) {
 		if (propagate) {
+			cfq_update_group_weight(pos);
 			propagate = !parent->nr_active++;
 			parent->children_weight += pos->weight;
 		}
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index fbd5a67cb773..a0926a6094b2 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -690,6 +690,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKROSET:
 	case BLKDISCARD:
 	case BLKSECDISCARD:
+	case BLKZEROOUT:
 	/*
 	 * the ones below are implemented in blkdev_locked_ioctl,
 	 * but we call blkdev_ioctl, which gets the lock for us
diff --git a/block/genhd.c b/block/genhd.c
index 791f41943132..a8d586a729bb 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -28,10 +28,10 @@ struct kobject *block_depr;
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
 
-/* For extended devt allocation.  ext_devt_mutex prevents look up
+/* For extended devt allocation.  ext_devt_lock prevents look up
  * results from going away underneath its user.
  */
-static DEFINE_MUTEX(ext_devt_mutex);
+static DEFINE_SPINLOCK(ext_devt_lock);
 static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
@@ -420,9 +420,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	}
 
 	/* allocate ext devt */
-	mutex_lock(&ext_devt_mutex);
-	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL);
-	mutex_unlock(&ext_devt_mutex);
+	idr_preload(GFP_KERNEL);
+
+	spin_lock(&ext_devt_lock);
+	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
+	spin_unlock(&ext_devt_lock);
+
+	idr_preload_end();
 	if (idx < 0)
 		return idx == -ENOSPC ? -EBUSY : idx;
 
@@ -441,15 +445,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
  */
 void blk_free_devt(dev_t devt)
 {
-	might_sleep();
-
 	if (devt == MKDEV(0, 0))
 		return;
 
 	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 }
 
@@ -665,7 +667,6 @@ void del_gendisk(struct gendisk *disk)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
-	blk_free_devt(disk_to_dev(disk)->devt);
 }
 EXPORT_SYMBOL(del_gendisk);
 
@@ -690,13 +691,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	} else {
 		struct hd_struct *part;
 
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
 		if (part && get_disk(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 
 	return disk;
@@ -1069,9 +1070,16 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 	struct disk_part_tbl *old_ptbl = disk->part_tbl;
 	struct disk_part_tbl *new_ptbl;
 	int len = old_ptbl ? old_ptbl->len : 0;
-	int target = partno + 1;
+	int i, target;
 	size_t size;
-	int i;
+
+	/*
+	 * check for int overflow, since we can get here from blkpg_ioctl()
+	 * with a user passed 'partno'.
+	 */
+	target = partno + 1;
+	if (target < 0)
+		return -EINVAL;
 
 	/* disk_max_parts() is zero during initialization, ignore if so */
 	if (disk_max_parts(disk) && target > disk_max_parts(disk))
@@ -1098,6 +1106,7 @@ static void disk_release(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	blk_free_devt(dev->devt);
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 789cdea05893..0d9e5f97f0a8 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -211,6 +211,7 @@ static const struct attribute_group *part_attr_groups[] = {
 static void part_release(struct device *dev)
 {
 	struct hd_struct *p = dev_to_part(dev);
+	blk_free_devt(dev->devt);
 	free_part_stats(p);
 	free_part_info(p);
 	kfree(p);
@@ -253,7 +254,6 @@ void delete_partition(struct gendisk *disk, int partno)
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
-	blk_free_devt(part_devt(part));
 
 	hd_struct_put(part);
 }
diff --git a/block/partitions/aix.c b/block/partitions/aix.c
index 43be471d9b1d..0931f5136ab2 100644
--- a/block/partitions/aix.c
+++ b/block/partitions/aix.c
@@ -253,7 +253,7 @@ int aix_partition(struct parsed_partitions *state)
 				continue;
 			}
 			lv_ix = be16_to_cpu(p->lv_ix) - 1;
-			if (lv_ix > state->limit) {
+			if (lv_ix >= state->limit) {
 				cur_lv_ix = -1;
 				continue;
 			}
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 26487972ac54..4044cf789c7a 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -489,7 +489,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
 		err = DRIVER_ERROR << 24;
-		goto out;
+		goto error;
 	}
 
 	memset(sense, 0, sizeof(sense));
@@ -499,7 +499,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	blk_execute_rq(q, disk, rq, 0);
 
-out:
 	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
 		if (rq->sense_len && rq->sense) {
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 966f893711b3..1de4beeb25f8 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/rwsem.h>
+#include <linux/security.h>
 
 struct alg_type_list {
 	const struct af_alg_type *type;
@@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 
 	sock_init_data(newsock, sk2);
 	sock_graft(sk2, newsock);
+	security_sk_clone(sk, sk2);
 
 	err = type->accept(ask->private, sk2);
 	if (err) {
@@ -447,6 +449,9 @@ void af_alg_complete(struct crypto_async_request *req, int err)
 {
 	struct af_alg_completion *completion = req->data;
 
+	if (err == -EINPROGRESS)
+		return;
+
 	completion->err = err;
 	complete(&completion->completion);
 }
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index a19c027b29bd..83187f497c7c 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -49,7 +49,7 @@ struct skcipher_ctx {
 	struct ablkcipher_request req;
 };
 
-#define MAX_SGL_ENTS ((PAGE_SIZE - sizeof(struct skcipher_sg_list)) / \
+#define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
 		      sizeof(struct scatterlist) - 1)
 
 static inline int skcipher_sndbuf(struct sock *sk)
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 3c562f5a60bb..e1bce26cd4f9 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -78,8 +78,6 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 		tx = dma->device_prep_dma_xor(chan, dma_dest, src_list,
 					      xor_src_cnt, unmap->len,
 					      dma_flags);
-		src_list[0] = tmp;
-
 
 		if (unlikely(!tx))
 			async_tx_quiesce(&submit->depend_tx);
@@ -92,6 +90,7 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 						      xor_src_cnt, unmap->len,
 						      dma_flags);
 		}
+		src_list[0] = tmp;
 
 		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index a79e7e9ab86e..0122bec38564 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -70,14 +70,12 @@ static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static inline unsigned int blkcipher_done_slow(struct crypto_blkcipher *tfm,
-					       struct blkcipher_walk *walk,
+static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
 					       unsigned int bsize)
 {
 	u8 *addr;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 
-	addr = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	addr = blkcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize, 1);
 	return bsize;
@@ -105,7 +103,6 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk,
 int blkcipher_walk_done(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk, int err)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
 	unsigned int nbytes = 0;
 
 	if (likely(err >= 0)) {
@@ -117,7 +114,7 @@ int blkcipher_walk_done(struct blkcipher_desc *desc,
 			err = -EINVAL;
 			goto err;
 		} else
-			n = blkcipher_done_slow(tfm, walk, n);
+			n = blkcipher_done_slow(walk, n);
 
 		nbytes = walk->total - n;
 		err = 0;
@@ -136,7 +133,7 @@ err:
 	}
 
 	if (walk->iv != desc->info)
-		memcpy(desc->info, walk->iv, crypto_blkcipher_ivsize(tfm));
+		memcpy(desc->info, walk->iv, walk->ivsize);
 	if (walk->buffer != walk->page)
 		kfree(walk->buffer);
 	if (walk->page)
@@ -226,22 +223,20 @@ static inline int blkcipher_next_fast(struct blkcipher_desc *desc,
 static int blkcipher_walk_next(struct blkcipher_desc *desc,
 			       struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 	unsigned int bsize;
 	unsigned int n;
 	int err;
 
 	n = walk->total;
-	if (unlikely(n < crypto_blkcipher_blocksize(tfm))) {
+	if (unlikely(n < walk->cipher_blocksize)) {
 		desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
 		return blkcipher_walk_done(desc, walk, -EINVAL);
 	}
 
 	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
 			 BLKCIPHER_WALK_DIFF);
-	if (!scatterwalk_aligned(&walk->in, alignmask) ||
-	    !scatterwalk_aligned(&walk->out, alignmask)) {
+	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
+	    !scatterwalk_aligned(&walk->out, walk->alignmask)) {
 		walk->flags |= BLKCIPHER_WALK_COPY;
 		if (!walk->page) {
 			walk->page = (void *)__get_free_page(GFP_ATOMIC);
@@ -250,12 +245,12 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		}
 	}
 
-	bsize = min(walk->blocksize, n);
+	bsize = min(walk->walk_blocksize, n);
 	n = scatterwalk_clamp(&walk->in, n);
 	n = scatterwalk_clamp(&walk->out, n);
 
 	if (unlikely(n < bsize)) {
-		err = blkcipher_next_slow(desc, walk, bsize, alignmask);
+		err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
 		goto set_phys_lowmem;
 	}
 
@@ -277,28 +272,26 @@ set_phys_lowmem:
 	return err;
 }
 
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk,
-				    struct crypto_blkcipher *tfm,
-				    unsigned int alignmask)
+static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
 {
-	unsigned bs = walk->blocksize;
-	unsigned int ivsize = crypto_blkcipher_ivsize(tfm);
-	unsigned aligned_bs = ALIGN(bs, alignmask + 1);
-	unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
-			    (alignmask + 1);
+	unsigned bs = walk->walk_blocksize;
+	unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
+	unsigned int size = aligned_bs * 2 +
+			    walk->ivsize + max(aligned_bs, walk->ivsize) -
+			    (walk->alignmask + 1);
 	u8 *iv;
 
-	size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
+	size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
 	walk->buffer = kmalloc(size, GFP_ATOMIC);
 	if (!walk->buffer)
 		return -ENOMEM;
 
-	iv = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = blkcipher_get_spot(iv, ivsize);
+	iv = blkcipher_get_spot(iv, walk->ivsize);
 
-	walk->iv = memcpy(iv, walk->iv, ivsize);
+	walk->iv = memcpy(iv, walk->iv, walk->ivsize);
 	return 0;
 }
 
@@ -306,7 +299,10 @@ int blkcipher_walk_virt(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
@@ -315,7 +311,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags |= BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
@@ -323,9 +322,6 @@ EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
 static int blkcipher_walk_first(struct blkcipher_desc *desc,
 				struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
-
 	if (WARN_ON_ONCE(in_irq()))
 		return -EDEADLK;
 
@@ -335,8 +331,8 @@ static int blkcipher_walk_first(struct blkcipher_desc *desc,
 
 	walk->buffer = NULL;
 	walk->iv = desc->info;
-	if (unlikely(((unsigned long)walk->iv & alignmask))) {
-		int err = blkcipher_copy_iv(walk, tfm, alignmask);
+	if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
+		int err = blkcipher_copy_iv(walk);
 		if (err)
 			return err;
 	}
@@ -353,11 +349,28 @@ int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      unsigned int blocksize)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = blocksize;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
 
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize)
+{
+	walk->flags &= ~BLKCIPHER_WALK_PHYS;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_aead_blocksize(tfm);
+	walk->ivsize = crypto_aead_ivsize(tfm);
+	walk->alignmask = crypto_aead_alignmask(tfm);
+	return blkcipher_walk_first(desc, walk);
+}
+EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
+
 static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
 			    unsigned int keylen)
 {
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 1512e41cd93d..43665d0d0905 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -466,7 +466,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	type -= CRYPTO_MSG_BASE;
 	link = &crypto_dispatch[type];
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) &&
diff --git a/crypto/crypto_wq.c b/crypto/crypto_wq.c
index adad92a44ba2..2f1b8d12952a 100644
--- a/crypto/crypto_wq.c
+++ b/crypto/crypto_wq.c
@@ -33,7 +33,7 @@ static void __exit crypto_wq_exit(void)
 	destroy_workqueue(kcrypto_wq);
 }
 
-module_init(crypto_wq_init);
+subsys_initcall(crypto_wq_init);
 module_exit(crypto_wq_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/Kconfig b/drivers/Kconfig
index b3138fbb46a4..c1e4021f4362 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -170,4 +170,6 @@ source "drivers/phy/Kconfig"
 
 source "drivers/powercap/Kconfig"
 
+source "drivers/gator/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 8e3b8b06c0b2..5bf13fd5ad65 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -155,3 +155,6 @@ obj-$(CONFIG_IPACK_BUS)		+= ipack/
 obj-$(CONFIG_NTB)		+= ntb/
 obj-$(CONFIG_FMC)		+= fmc/
 obj-$(CONFIG_POWERCAP)		+= powercap/
+
+obj-$(CONFIG_GATOR)		+= gator/
+obj-$(CONFIG_CORESIGHT)		+= coresight/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 4770de5707b9..561bf25ac9f9 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -56,6 +56,23 @@ config ACPI_PROCFS
 
 	  Say N to delete /proc/acpi/ files that have moved to /sys/
 
+config ACPI_PROCFS_POWER
+	bool "Deprecated power /proc/acpi directories"
+	depends on PROC_FS
+	help
+	  For backwards compatibility, this option allows
+          deprecated power /proc/acpi/ directories to exist, even when
+          they have been replaced by functions in /sys.
+          The deprecated directories (and their replacements) include:
+	  /proc/acpi/battery/* (/sys/class/power_supply/*)
+	  /proc/acpi/ac_adapter/* (sys/class/power_supply/*)
+	  This option has no effect on /proc/acpi/ directories
+	  and functions, which do not yet exist in /sys
+	  This option, together with the proc directories, will be
+	  deleted in 2.6.39.
+
+	  Say N to delete power /proc/acpi/ directories that have moved to /sys/
+
 config ACPI_EC_DEBUGFS
 	tristate "EC read/write access through /sys/kernel/debug/ec"
 	default n
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 0331f91d56e6..bce34afadcd0 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -47,6 +47,7 @@ acpi-y				+= sysfs.o
 acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
+acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
 ifdef CONFIG_ACPI_VIDEO
 acpi-y				+= video_detect.o
 endif
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 6f190bc2b8b7..0bebc6905383 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -30,6 +30,10 @@
 #include <linux/types.h>
 #include <linux/dmi.h>
 #include <linux/delay.h>
+#ifdef CONFIG_ACPI_PROCFS_POWER
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#endif
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/acpi.h>
@@ -51,26 +55,74 @@ MODULE_AUTHOR("Paul Diefenbaugh");
 MODULE_DESCRIPTION("ACPI AC Adapter Driver");
 MODULE_LICENSE("GPL");
 
+
+static int acpi_ac_add(struct acpi_device *device);
+static int acpi_ac_remove(struct acpi_device *device);
+static void acpi_ac_notify(struct acpi_device *device, u32 event);
+
+static const struct acpi_device_id ac_device_ids[] = {
+	{"ACPI0003", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, ac_device_ids);
+
+#ifdef CONFIG_PM_SLEEP
+static int acpi_ac_resume(struct device *dev);
+#endif
+static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume);
+
+#ifdef CONFIG_ACPI_PROCFS_POWER
+extern struct proc_dir_entry *acpi_lock_ac_dir(void);
+extern void *acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir);
+static int acpi_ac_open_fs(struct inode *inode, struct file *file);
+#endif
+
+
 static int ac_sleep_before_get_state_ms;
 
+static struct acpi_driver acpi_ac_driver = {
+	.name = "ac",
+	.class = ACPI_AC_CLASS,
+	.ids = ac_device_ids,
+	.flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS,
+	.ops = {
+		.add = acpi_ac_add,
+		.remove = acpi_ac_remove,
+		.notify = acpi_ac_notify,
+		},
+	.drv.pm = &acpi_ac_pm,
+};
+
 struct acpi_ac {
 	struct power_supply charger;
-	struct platform_device *pdev;
+	struct acpi_device * device;
 	unsigned long long state;
 };
 
 #define to_acpi_ac(x) container_of(x, struct acpi_ac, charger)
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+static const struct file_operations acpi_ac_fops = {
+	.owner = THIS_MODULE,
+	.open = acpi_ac_open_fs,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
 /* --------------------------------------------------------------------------
                                AC Adapter Management
    -------------------------------------------------------------------------- */
 
 static int acpi_ac_get_state(struct acpi_ac *ac)
 {
-	acpi_status status;
-	acpi_handle handle = ACPI_HANDLE(&ac->pdev->dev);
+	acpi_status status = AE_OK;
 
-	status = acpi_evaluate_integer(handle, "_PSR", NULL,
+	if (!ac)
+		return -EINVAL;
+
+	status = acpi_evaluate_integer(ac->device->handle, "_PSR", NULL,
 				       &ac->state);
 	if (ACPI_FAILURE(status)) {
 		ACPI_EXCEPTION((AE_INFO, status,
@@ -111,14 +163,90 @@ static enum power_supply_property ac_props[] = {
 	POWER_SUPPLY_PROP_ONLINE,
 };
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+/* --------------------------------------------------------------------------
+                              FS Interface (/proc)
+   -------------------------------------------------------------------------- */
+
+static struct proc_dir_entry *acpi_ac_dir;
+
+static int acpi_ac_seq_show(struct seq_file *seq, void *offset)
+{
+	struct acpi_ac *ac = seq->private;
+
+
+	if (!ac)
+		return 0;
+
+	if (acpi_ac_get_state(ac)) {
+		seq_puts(seq, "ERROR: Unable to read AC Adapter state\n");
+		return 0;
+	}
+
+	seq_puts(seq, "state:                   ");
+	switch (ac->state) {
+	case ACPI_AC_STATUS_OFFLINE:
+		seq_puts(seq, "off-line\n");
+		break;
+	case ACPI_AC_STATUS_ONLINE:
+		seq_puts(seq, "on-line\n");
+		break;
+	default:
+		seq_puts(seq, "unknown\n");
+		break;
+	}
+
+	return 0;
+}
+
+static int acpi_ac_open_fs(struct inode *inode, struct file *file)
+{
+	return single_open(file, acpi_ac_seq_show, PDE_DATA(inode));
+}
+
+static int acpi_ac_add_fs(struct acpi_ac *ac)
+{
+	struct proc_dir_entry *entry = NULL;
+
+	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for AC is loaded,"
+			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	if (!acpi_device_dir(ac->device)) {
+		acpi_device_dir(ac->device) =
+			proc_mkdir(acpi_device_bid(ac->device), acpi_ac_dir);
+		if (!acpi_device_dir(ac->device))
+			return -ENODEV;
+	}
+
+	/* 'state' [R] */
+	entry = proc_create_data(ACPI_AC_FILE_STATE,
+				 S_IRUGO, acpi_device_dir(ac->device),
+				 &acpi_ac_fops, ac);
+	if (!entry)
+		return -ENODEV;
+	return 0;
+}
+
+static int acpi_ac_remove_fs(struct acpi_ac *ac)
+{
+
+	if (acpi_device_dir(ac->device)) {
+		remove_proc_entry(ACPI_AC_FILE_STATE,
+				  acpi_device_dir(ac->device));
+		remove_proc_entry(acpi_device_bid(ac->device), acpi_ac_dir);
+		acpi_device_dir(ac->device) = NULL;
+	}
+
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                                    Driver Model
    -------------------------------------------------------------------------- */
 
-static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data)
+static void acpi_ac_notify(struct acpi_device *device, u32 event)
 {
-	struct acpi_ac *ac = data;
-	struct acpi_device *adev;
+	struct acpi_ac *ac = acpi_driver_data(device);
 
 	if (!ac)
 		return;
@@ -141,11 +269,10 @@ static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data)
 			msleep(ac_sleep_before_get_state_ms);
 
 		acpi_ac_get_state(ac);
-		adev = ACPI_COMPANION(&ac->pdev->dev);
-		acpi_bus_generate_netlink_event(adev->pnp.device_class,
-						dev_name(&ac->pdev->dev),
-						event, (u32) ac->state);
-		acpi_notifier_call_chain(adev, event, (u32) ac->state);
+		acpi_bus_generate_netlink_event(device->pnp.device_class,
+						  dev_name(&device->dev), event,
+						  (u32) ac->state);
+		acpi_notifier_call_chain(device, event, (u32) ac->state);
 		kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE);
 	}
 
@@ -170,54 +297,53 @@ static struct dmi_system_id ac_dmi_table[] = {
 	{},
 };
 
-static int acpi_ac_probe(struct platform_device *pdev)
+static int acpi_ac_add(struct acpi_device *device)
 {
 	int result = 0;
 	struct acpi_ac *ac = NULL;
-	struct acpi_device *adev;
 
-	if (!pdev)
-		return -EINVAL;
 
-	adev = ACPI_COMPANION(&pdev->dev);
-	if (!adev)
-		return -ENODEV;
+	if (!device)
+		return -EINVAL;
 
 	ac = kzalloc(sizeof(struct acpi_ac), GFP_KERNEL);
 	if (!ac)
 		return -ENOMEM;
 
-	strcpy(acpi_device_name(adev), ACPI_AC_DEVICE_NAME);
-	strcpy(acpi_device_class(adev), ACPI_AC_CLASS);
-	ac->pdev = pdev;
-	platform_set_drvdata(pdev, ac);
+	ac->device = device;
+	strcpy(acpi_device_name(device), ACPI_AC_DEVICE_NAME);
+	strcpy(acpi_device_class(device), ACPI_AC_CLASS);
+	device->driver_data = ac;
 
 	result = acpi_ac_get_state(ac);
 	if (result)
 		goto end;
 
-	ac->charger.name = acpi_device_bid(adev);
+	ac->charger.name = acpi_device_bid(device);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	result = acpi_ac_add_fs(ac);
+	if (result)
+		goto end;
+#endif
 	ac->charger.type = POWER_SUPPLY_TYPE_MAINS;
 	ac->charger.properties = ac_props;
 	ac->charger.num_properties = ARRAY_SIZE(ac_props);
 	ac->charger.get_property = get_ac_property;
-	result = power_supply_register(&pdev->dev, &ac->charger);
+	result = power_supply_register(&ac->device->dev, &ac->charger);
 	if (result)
 		goto end;
 
-	result = acpi_install_notify_handler(ACPI_HANDLE(&pdev->dev),
-			ACPI_ALL_NOTIFY, acpi_ac_notify_handler, ac);
-	if (result) {
-		power_supply_unregister(&ac->charger);
-		goto end;
-	}
 	printk(KERN_INFO PREFIX "%s [%s] (%s)\n",
-	       acpi_device_name(adev), acpi_device_bid(adev),
+	       acpi_device_name(device), acpi_device_bid(device),
 	       ac->state ? "on-line" : "off-line");
 
 end:
-	if (result)
+	if (result) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_ac_remove_fs(ac);
+#endif
 		kfree(ac);
+	}
 
 	dmi_check_system(ac_dmi_table);
 	return result;
@@ -232,7 +358,7 @@ static int acpi_ac_resume(struct device *dev)
 	if (!dev)
 		return -EINVAL;
 
-	ac = platform_get_drvdata(to_platform_device(dev));
+	ac = acpi_driver_data(to_acpi_device(dev));
 	if (!ac)
 		return -EINVAL;
 
@@ -246,44 +372,29 @@ static int acpi_ac_resume(struct device *dev)
 #else
 #define acpi_ac_resume NULL
 #endif
-static SIMPLE_DEV_PM_OPS(acpi_ac_pm_ops, NULL, acpi_ac_resume);
 
-static int acpi_ac_remove(struct platform_device *pdev)
+static int acpi_ac_remove(struct acpi_device *device)
 {
-	struct acpi_ac *ac;
+	struct acpi_ac *ac = NULL;
+
 
-	if (!pdev)
+	if (!device || !acpi_driver_data(device))
 		return -EINVAL;
 
-	acpi_remove_notify_handler(ACPI_HANDLE(&pdev->dev),
-			ACPI_ALL_NOTIFY, acpi_ac_notify_handler);
+	ac = acpi_driver_data(device);
 
-	ac = platform_get_drvdata(pdev);
 	if (ac->charger.dev)
 		power_supply_unregister(&ac->charger);
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_ac_remove_fs(ac);
+#endif
+
 	kfree(ac);
 
 	return 0;
 }
 
-static const struct acpi_device_id acpi_ac_match[] = {
-	{ "ACPI0003", 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(acpi, acpi_ac_match);
-
-static struct platform_driver acpi_ac_driver = {
-	.probe          = acpi_ac_probe,
-	.remove         = acpi_ac_remove,
-	.driver         = {
-		.name   = "acpi-ac",
-		.owner  = THIS_MODULE,
-		.pm     = &acpi_ac_pm_ops,
-		.acpi_match_table = ACPI_PTR(acpi_ac_match),
-	},
-};
-
 static int __init acpi_ac_init(void)
 {
 	int result;
@@ -291,16 +402,30 @@ static int __init acpi_ac_init(void)
 	if (acpi_disabled)
 		return -ENODEV;
 
-	result = platform_driver_register(&acpi_ac_driver);
-	if (result < 0)
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_ac_dir = acpi_lock_ac_dir();
+	if (!acpi_ac_dir)
 		return -ENODEV;
+#endif
+
+
+	result = acpi_bus_register_driver(&acpi_ac_driver);
+	if (result < 0) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_unlock_ac_dir(acpi_ac_dir);
+#endif
+		return -ENODEV;
+	}
 
 	return 0;
 }
 
 static void __exit acpi_ac_exit(void)
 {
-	platform_driver_unregister(&acpi_ac_driver);
+	acpi_bus_unregister_driver(&acpi_ac_driver);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_unlock_ac_dir(acpi_ac_dir);
+#endif
 }
 module_init(acpi_ac_init);
 module_exit(acpi_ac_exit);
diff --git a/drivers/acpi/acpi_cmos_rtc.c b/drivers/acpi/acpi_cmos_rtc.c
index 84190ed89c04..aff69d9bfcbf 100644
--- a/drivers/acpi/acpi_cmos_rtc.c
+++ b/drivers/acpi/acpi_cmos_rtc.c
@@ -35,7 +35,7 @@ acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address,
 		      void *handler_context, void *region_context)
 {
 	int i;
-	u8 *value = (u8 *)&value64;
+	u8 *value = (u8 *)value64;
 
 	if (address > 0xff || !value64)
 		return AE_BAD_PARAMETER;
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index dbfe49e5fd63..1d4950388fa1 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -29,7 +29,6 @@ ACPI_MODULE_NAME("platform");
 static const struct acpi_device_id acpi_platform_device_ids[] = {
 
 	{ "PNP0D40" },
-	{ "ACPI0003" },
 	{ "VPC2004" },
 	{ "BCM4752" },
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index c29c2c3ec0ad..52c81c49cc7d 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -170,6 +170,9 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	acpi_status status;
 	int ret;
 
+	if (pr->apic_id == -1)
+		return -ENODEV;
+
 	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
 	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT))
 		return -ENODEV;
@@ -260,10 +263,8 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	}
 
 	apic_id = acpi_get_apicid(pr->handle, device_declaration, pr->acpi_id);
-	if (apic_id < 0) {
+	if (apic_id < 0)
 		acpi_handle_debug(pr->handle, "failed to get CPU APIC ID.\n");
-		return -ENODEV;
-	}
 	pr->apic_id = apic_id;
 
 	cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id);
@@ -404,7 +405,6 @@ static int acpi_processor_add(struct acpi_device *device,
 		goto err;
 
 	pr->dev = dev;
-	dev->offline = pr->flags.need_hotplug_init;
 
 	/* Trigger the processor driver's .probe() if present. */
 	if (device_attach(dev) >= 0)
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 4ed1aa384df2..514f34033f96 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -132,9 +132,9 @@ u8 ACPI_INIT_GLOBAL(acpi_gbl_do_not_use_xsdt, FALSE);
  * address. Although ACPICA adheres to the ACPI specification which
  * requires the use of the corresponding 64-bit address if it is non-zero,
  * some machines have been found to have a corrupted non-zero 64-bit
- * address. Default is FALSE, do not favor the 32-bit addresses.
+ * address. Default is TRUE, favor the 32-bit addresses.
  */
-u8 ACPI_INIT_GLOBAL(acpi_gbl_use32_bit_fadt_addresses, FALSE);
+u8 ACPI_INIT_GLOBAL(acpi_gbl_use32_bit_fadt_addresses, TRUE);
 
 /*
  * Optionally truncate I/O addresses to 16 bits. Provides compatibility
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index d95ca5449ace..e6ab104afe42 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -254,6 +254,7 @@ struct acpi_create_field_info {
 	u32 field_bit_position;
 	u32 field_bit_length;
 	u16 resource_length;
+	u16 pin_number_index;
 	u8 field_flags;
 	u8 attribute;
 	u8 field_type;
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index cc7ab6dd724e..a47cc78ffd4f 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -263,6 +263,7 @@ struct acpi_object_region_field {
 	ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u16 resource_length;
 	union acpi_operand_object *region_obj;	/* Containing op_region object */
 	u8 *resource_buffer;	/* resource_template for serial regions/fields */
+	u16 pin_number_index;	/* Index relative to previous Connection/Template */
 };
 
 struct acpi_object_bank_field {
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index e7a57c554e84..9af55bd6c4d7 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -360,6 +360,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 			 */
 			info->resource_buffer = NULL;
 			info->connection_node = NULL;
+			info->pin_number_index = 0;
 
 			/*
 			 * A Connection() is either an actual resource descriptor (buffer)
@@ -437,6 +438,7 @@ acpi_ds_get_field_names(struct acpi_create_field_info *info,
 			}
 
 			info->field_bit_position += info->field_bit_length;
+			info->pin_number_index++;	/* Index relative to previous Connection() */
 			break;
 
 		default:
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 144cbb9b73bc..cd4b231ae760 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -142,6 +142,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 	union acpi_operand_object *region_obj2;
 	void *region_context = NULL;
 	struct acpi_connection_info *context;
+	acpi_physical_address address;
 
 	ACPI_FUNCTION_TRACE(ev_address_space_dispatch);
 
@@ -231,25 +232,23 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 	/* We have everything we need, we can invoke the address space handler */
 
 	handler = handler_desc->address_space.handler;
-
-	ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
-			  "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
-			  &region_obj->region.handler->address_space, handler,
-			  ACPI_FORMAT_NATIVE_UINT(region_obj->region.address +
-						  region_offset),
-			  acpi_ut_get_region_name(region_obj->region.
-						  space_id)));
+	address = (region_obj->region.address + region_offset);
 
 	/*
 	 * Special handling for generic_serial_bus and general_purpose_io:
 	 * There are three extra parameters that must be passed to the
 	 * handler via the context:
-	 *   1) Connection buffer, a resource template from Connection() op.
-	 *   2) Length of the above buffer.
-	 *   3) Actual access length from the access_as() op.
+	 *   1) Connection buffer, a resource template from Connection() op
+	 *   2) Length of the above buffer
+	 *   3) Actual access length from the access_as() op
+	 *
+	 * In addition, for general_purpose_io, the Address and bit_width fields
+	 * are defined as follows:
+	 *   1) Address is the pin number index of the field (bit offset from
+	 *      the previous Connection)
+	 *   2) bit_width is the actual bit length of the field (number of pins)
 	 */
-	if (((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) ||
-	     (region_obj->region.space_id == ACPI_ADR_SPACE_GPIO)) &&
+	if ((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) &&
 	    context && field_obj) {
 
 		/* Get the Connection (resource_template) buffer */
@@ -258,6 +257,24 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 		context->length = field_obj->field.resource_length;
 		context->access_length = field_obj->field.access_length;
 	}
+	if ((region_obj->region.space_id == ACPI_ADR_SPACE_GPIO) &&
+	    context && field_obj) {
+
+		/* Get the Connection (resource_template) buffer */
+
+		context->connection = field_obj->field.resource_buffer;
+		context->length = field_obj->field.resource_length;
+		context->access_length = field_obj->field.access_length;
+		address = field_obj->field.pin_number_index;
+		bit_width = field_obj->field.bit_length;
+	}
+
+	ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
+			  "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
+			  &region_obj->region.handler->address_space, handler,
+			  ACPI_FORMAT_NATIVE_UINT(address),
+			  acpi_ut_get_region_name(region_obj->region.
+						  space_id)));
 
 	if (!(handler_desc->address_space.handler_flags &
 	      ACPI_ADDR_HANDLER_DEFAULT_INSTALLED)) {
@@ -271,9 +288,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 
 	/* Call the handler */
 
-	status = handler(function,
-			 (region_obj->region.address + region_offset),
-			 bit_width, value, context,
+	status = handler(function, address, bit_width, value, context,
 			 region_obj2->extra.region_context);
 
 	if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index cfd875243421..d36894a228b1 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -178,6 +178,37 @@ acpi_ex_read_data_from_field(struct acpi_walk_state *walk_state,
 		buffer = &buffer_desc->integer.value;
 	}
 
+	if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) &&
+	    (obj_desc->field.region_obj->region.space_id ==
+	     ACPI_ADR_SPACE_GPIO)) {
+		/*
+		 * For GPIO (general_purpose_io), the Address will be the bit offset
+		 * from the previous Connection() operator, making it effectively a
+		 * pin number index. The bit_length is the length of the field, which
+		 * is thus the number of pins.
+		 */
+		ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+				  "GPIO FieldRead [FROM]:  Pin %u Bits %u\n",
+				  obj_desc->field.pin_number_index,
+				  obj_desc->field.bit_length));
+
+		/* Lock entire transaction if requested */
+
+		acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags);
+
+		/* Perform the write */
+
+		status = acpi_ex_access_region(obj_desc, 0,
+					       (u64 *)buffer, ACPI_READ);
+		acpi_ex_release_global_lock(obj_desc->common_field.field_flags);
+		if (ACPI_FAILURE(status)) {
+			acpi_ut_remove_reference(buffer_desc);
+		} else {
+			*ret_buffer_desc = buffer_desc;
+		}
+		return_ACPI_STATUS(status);
+	}
+
 	ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
 			  "FieldRead [TO]:   Obj %p, Type %X, Buf %p, ByteLen %X\n",
 			  obj_desc, obj_desc->common.type, buffer,
@@ -325,6 +356,42 @@ acpi_ex_write_data_to_field(union acpi_operand_object *source_desc,
 
 		*result_desc = buffer_desc;
 		return_ACPI_STATUS(status);
+	} else if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) &&
+		   (obj_desc->field.region_obj->region.space_id ==
+		    ACPI_ADR_SPACE_GPIO)) {
+		/*
+		 * For GPIO (general_purpose_io), we will bypass the entire field
+		 * mechanism and handoff the bit address and bit width directly to
+		 * the handler. The Address will be the bit offset
+		 * from the previous Connection() operator, making it effectively a
+		 * pin number index. The bit_length is the length of the field, which
+		 * is thus the number of pins.
+		 */
+		if (source_desc->common.type != ACPI_TYPE_INTEGER) {
+			return_ACPI_STATUS(AE_AML_OPERAND_TYPE);
+		}
+
+		ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+				  "GPIO FieldWrite [FROM]: (%s:%X), Val %.8X  [TO]:  Pin %u Bits %u\n",
+				  acpi_ut_get_type_name(source_desc->common.
+							type),
+				  source_desc->common.type,
+				  (u32)source_desc->integer.value,
+				  obj_desc->field.pin_number_index,
+				  obj_desc->field.bit_length));
+
+		buffer = &source_desc->integer.value;
+
+		/* Lock entire transaction if requested */
+
+		acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags);
+
+		/* Perform the write */
+
+		status = acpi_ex_access_region(obj_desc, 0,
+					       (u64 *)buffer, ACPI_WRITE);
+		acpi_ex_release_global_lock(obj_desc->common_field.field_flags);
+		return_ACPI_STATUS(status);
 	}
 
 	/* Get a pointer to the data to be written */
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 5a588611ab48..8c88cfdec441 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -484,6 +484,8 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info)
 			obj_desc->field.resource_length = info->resource_length;
 		}
 
+		obj_desc->field.pin_number_index = info->pin_number_index;
+
 		/* Allow full data read from EC address space */
 
 		if ((obj_desc->field.region_obj->region.space_id ==
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index a05afff50eb9..b6f6863c07f9 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -207,13 +207,30 @@ acpi_ns_simple_repair(struct acpi_evaluate_info *info,
 	 * this predefined name. Either one return value is expected, or none,
 	 * for both methods and other objects.
 	 *
-	 * Exit now if there is no return object. Warning if one was expected.
+	 * Try to fix if there was no return object. Warning if failed to fix.
 	 */
 	if (!return_object) {
 		if (expected_btypes && (!(expected_btypes & ACPI_RTYPE_NONE))) {
-			ACPI_WARN_PREDEFINED((AE_INFO, info->full_pathname,
-					      ACPI_WARN_ALWAYS,
-					      "Missing expected return value"));
+			if (package_index != ACPI_NOT_PACKAGE_ELEMENT) {
+				ACPI_WARN_PREDEFINED((AE_INFO,
+						      info->full_pathname,
+						      ACPI_WARN_ALWAYS,
+						      "Found unexpected NULL package element"));
+
+				status =
+				    acpi_ns_repair_null_element(info,
+								expected_btypes,
+								package_index,
+								return_object_ptr);
+				if (ACPI_SUCCESS(status)) {
+					return (AE_OK);	/* Repair was successful */
+				}
+			} else {
+				ACPI_WARN_PREDEFINED((AE_INFO,
+						      info->full_pathname,
+						      ACPI_WARN_ALWAYS,
+						      "Missing expected return value"));
+			}
 
 			return (AE_AML_NO_RETURN_VALUE);
 		}
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 6412d3c301cb..1bc879ec83d4 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -461,6 +461,7 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 	u32 table_count;
 	struct acpi_table_header *table;
 	acpi_physical_address address;
+	acpi_physical_address rsdt_address;
 	u32 length;
 	u8 *table_entry;
 	acpi_status status;
@@ -488,11 +489,14 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 		 * as per the ACPI specification.
 		 */
 		address = (acpi_physical_address) rsdp->xsdt_physical_address;
+		rsdt_address =
+		    (acpi_physical_address) rsdp->rsdt_physical_address;
 		table_entry_size = ACPI_XSDT_ENTRY_SIZE;
 	} else {
 		/* Root table is an RSDT (32-bit physical addresses) */
 
 		address = (acpi_physical_address) rsdp->rsdt_physical_address;
+		rsdt_address = address;
 		table_entry_size = ACPI_RSDT_ENTRY_SIZE;
 	}
 
@@ -515,8 +519,7 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 
 			/* Fall back to the RSDT */
 
-			address =
-			    (acpi_physical_address) rsdp->rsdt_physical_address;
+			address = rsdt_address;
 			table_entry_size = ACPI_RSDT_ENTRY_SIZE;
 		}
 	}
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index edff4e653d9a..c66bca17e736 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -1001,5 +1001,11 @@ acpi_ut_copy_iobject_to_iobject(union acpi_operand_object *source_desc,
 		status = acpi_ut_copy_simple_object(source_desc, *dest_desc);
 	}
 
+	/* Delete the allocated object if copy failed */
+
+	if (ACPI_FAILURE(status)) {
+		acpi_ut_remove_reference(*dest_desc);
+	}
+
 	return_ACPI_STATUS(status);
 }
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 45c0eb26b33d..cd2047af96db 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -353,7 +353,7 @@ void acpi_ut_print_string(char *string, u16 max_length)
 	}
 
 	acpi_os_printf("\"");
-	for (i = 0; string[i] && (i < max_length); i++) {
+	for (i = 0; (i < max_length) && string[i]; i++) {
 
 		/* Escape sequences */
 
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 797a6938d051..0f004159a317 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -34,8 +34,15 @@
 #include <linux/dmi.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/delay.h>
 #include <asm/unaligned.h>
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <asm/uaccess.h>
+#endif
+
 #include <linux/acpi.h>
 #include <linux/power_supply.h>
 
@@ -66,6 +73,19 @@ static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+extern struct proc_dir_entry *acpi_lock_battery_dir(void);
+extern void *acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir);
+
+enum acpi_battery_files {
+	info_tag = 0,
+	state_tag,
+	alarm_tag,
+	ACPI_BATTERY_NUMFILES,
+};
+
+#endif
+
 static const struct acpi_device_id battery_device_ids[] = {
 	{"PNP0C0A", 0},
 	{"", 0},
@@ -301,6 +321,14 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+inline char *acpi_battery_units(struct acpi_battery *battery)
+{
+	return (battery->power_unit == ACPI_BATTERY_POWER_UNIT_MA) ?
+		"mA" : "mW";
+}
+#endif
+
 /* --------------------------------------------------------------------------
                                Battery Management
    -------------------------------------------------------------------------- */
@@ -719,6 +747,279 @@ static void acpi_battery_refresh(struct acpi_battery *battery)
 }
 
 /* --------------------------------------------------------------------------
+                              FS Interface (/proc)
+   -------------------------------------------------------------------------- */
+
+#ifdef CONFIG_ACPI_PROCFS_POWER
+static struct proc_dir_entry *acpi_battery_dir;
+
+static int acpi_battery_print_info(struct seq_file *seq, int result)
+{
+	struct acpi_battery *battery = seq->private;
+
+	if (result)
+		goto end;
+
+	seq_printf(seq, "present:                 %s\n",
+		   acpi_battery_present(battery) ? "yes" : "no");
+	if (!acpi_battery_present(battery))
+		goto end;
+	if (battery->design_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "design capacity:         unknown\n");
+	else
+		seq_printf(seq, "design capacity:         %d %sh\n",
+			   battery->design_capacity,
+			   acpi_battery_units(battery));
+
+	if (battery->full_charge_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "last full capacity:      unknown\n");
+	else
+		seq_printf(seq, "last full capacity:      %d %sh\n",
+			   battery->full_charge_capacity,
+			   acpi_battery_units(battery));
+
+	seq_printf(seq, "battery technology:      %srechargeable\n",
+		   (!battery->technology)?"non-":"");
+
+	if (battery->design_voltage == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "design voltage:          unknown\n");
+	else
+		seq_printf(seq, "design voltage:          %d mV\n",
+			   battery->design_voltage);
+	seq_printf(seq, "design capacity warning: %d %sh\n",
+		   battery->design_capacity_warning,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "design capacity low:     %d %sh\n",
+		   battery->design_capacity_low,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "cycle count:		  %i\n", battery->cycle_count);
+	seq_printf(seq, "capacity granularity 1:  %d %sh\n",
+		   battery->capacity_granularity_1,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "capacity granularity 2:  %d %sh\n",
+		   battery->capacity_granularity_2,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "model number:            %s\n", battery->model_number);
+	seq_printf(seq, "serial number:           %s\n", battery->serial_number);
+	seq_printf(seq, "battery type:            %s\n", battery->type);
+	seq_printf(seq, "OEM info:                %s\n", battery->oem_info);
+      end:
+	if (result)
+		seq_printf(seq, "ERROR: Unable to read battery info\n");
+	return result;
+}
+
+static int acpi_battery_print_state(struct seq_file *seq, int result)
+{
+	struct acpi_battery *battery = seq->private;
+
+	if (result)
+		goto end;
+
+	seq_printf(seq, "present:                 %s\n",
+		   acpi_battery_present(battery) ? "yes" : "no");
+	if (!acpi_battery_present(battery))
+		goto end;
+
+	seq_printf(seq, "capacity state:          %s\n",
+			(battery->state & 0x04) ? "critical" : "ok");
+	if ((battery->state & 0x01) && (battery->state & 0x02))
+		seq_printf(seq,
+			   "charging state:          charging/discharging\n");
+	else if (battery->state & 0x01)
+		seq_printf(seq, "charging state:          discharging\n");
+	else if (battery->state & 0x02)
+		seq_printf(seq, "charging state:          charging\n");
+	else
+		seq_printf(seq, "charging state:          charged\n");
+
+	if (battery->rate_now == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "present rate:            unknown\n");
+	else
+		seq_printf(seq, "present rate:            %d %s\n",
+			   battery->rate_now, acpi_battery_units(battery));
+
+	if (battery->capacity_now == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "remaining capacity:      unknown\n");
+	else
+		seq_printf(seq, "remaining capacity:      %d %sh\n",
+			   battery->capacity_now, acpi_battery_units(battery));
+	if (battery->voltage_now == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "present voltage:         unknown\n");
+	else
+		seq_printf(seq, "present voltage:         %d mV\n",
+			   battery->voltage_now);
+      end:
+	if (result)
+		seq_printf(seq, "ERROR: Unable to read battery state\n");
+
+	return result;
+}
+
+static int acpi_battery_print_alarm(struct seq_file *seq, int result)
+{
+	struct acpi_battery *battery = seq->private;
+
+	if (result)
+		goto end;
+
+	if (!acpi_battery_present(battery)) {
+		seq_printf(seq, "present:                 no\n");
+		goto end;
+	}
+	seq_printf(seq, "alarm:                   ");
+	if (!battery->alarm)
+		seq_printf(seq, "unsupported\n");
+	else
+		seq_printf(seq, "%u %sh\n", battery->alarm,
+				acpi_battery_units(battery));
+      end:
+	if (result)
+		seq_printf(seq, "ERROR: Unable to read battery alarm\n");
+	return result;
+}
+
+static ssize_t acpi_battery_write_alarm(struct file *file,
+					const char __user * buffer,
+					size_t count, loff_t * ppos)
+{
+	int result = 0;
+	char alarm_string[12] = { '\0' };
+	struct seq_file *m = file->private_data;
+	struct acpi_battery *battery = m->private;
+
+	if (!battery || (count > sizeof(alarm_string) - 1))
+		return -EINVAL;
+	if (!acpi_battery_present(battery)) {
+		result = -ENODEV;
+		goto end;
+	}
+	if (copy_from_user(alarm_string, buffer, count)) {
+		result = -EFAULT;
+		goto end;
+	}
+	alarm_string[count] = '\0';
+	battery->alarm = simple_strtol(alarm_string, NULL, 0);
+	result = acpi_battery_set_alarm(battery);
+      end:
+	if (!result)
+		return count;
+	return result;
+}
+
+typedef int(*print_func)(struct seq_file *seq, int result);
+
+static print_func acpi_print_funcs[ACPI_BATTERY_NUMFILES] = {
+	acpi_battery_print_info,
+	acpi_battery_print_state,
+	acpi_battery_print_alarm,
+};
+
+static int acpi_battery_read(int fid, struct seq_file *seq)
+{
+	struct acpi_battery *battery = seq->private;
+	int result = acpi_battery_update(battery);
+	return acpi_print_funcs[fid](seq, result);
+}
+
+#define DECLARE_FILE_FUNCTIONS(_name) \
+static int acpi_battery_read_##_name(struct seq_file *seq, void *offset) \
+{ \
+	return acpi_battery_read(_name##_tag, seq); \
+} \
+static int acpi_battery_##_name##_open_fs(struct inode *inode, struct file *file) \
+{ \
+	return single_open(file, acpi_battery_read_##_name, PDE_DATA(inode)); \
+}
+
+DECLARE_FILE_FUNCTIONS(info);
+DECLARE_FILE_FUNCTIONS(state);
+DECLARE_FILE_FUNCTIONS(alarm);
+
+#undef DECLARE_FILE_FUNCTIONS
+
+#define FILE_DESCRIPTION_RO(_name) \
+	{ \
+	.name = __stringify(_name), \
+	.mode = S_IRUGO, \
+	.ops = { \
+		.open = acpi_battery_##_name##_open_fs, \
+		.read = seq_read, \
+		.llseek = seq_lseek, \
+		.release = single_release, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
+#define FILE_DESCRIPTION_RW(_name) \
+	{ \
+	.name = __stringify(_name), \
+	.mode = S_IFREG | S_IRUGO | S_IWUSR, \
+	.ops = { \
+		.open = acpi_battery_##_name##_open_fs, \
+		.read = seq_read, \
+		.llseek = seq_lseek, \
+		.write = acpi_battery_write_##_name, \
+		.release = single_release, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
+static const struct battery_file {
+	struct file_operations ops;
+	umode_t mode;
+	const char *name;
+} acpi_battery_file[] = {
+	FILE_DESCRIPTION_RO(info),
+	FILE_DESCRIPTION_RO(state),
+	FILE_DESCRIPTION_RW(alarm),
+};
+
+#undef FILE_DESCRIPTION_RO
+#undef FILE_DESCRIPTION_RW
+
+static int acpi_battery_add_fs(struct acpi_device *device)
+{
+	struct proc_dir_entry *entry = NULL;
+	int i;
+
+	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded,"
+			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	if (!acpi_device_dir(device)) {
+		acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device),
+						     acpi_battery_dir);
+		if (!acpi_device_dir(device))
+			return -ENODEV;
+	}
+
+	for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i) {
+		entry = proc_create_data(acpi_battery_file[i].name,
+					 acpi_battery_file[i].mode,
+					 acpi_device_dir(device),
+					 &acpi_battery_file[i].ops,
+					 acpi_driver_data(device));
+		if (!entry)
+			return -ENODEV;
+	}
+	return 0;
+}
+
+static void acpi_battery_remove_fs(struct acpi_device *device)
+{
+	int i;
+	if (!acpi_device_dir(device))
+		return;
+	for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i)
+		remove_proc_entry(acpi_battery_file[i].name,
+				  acpi_device_dir(device));
+
+	remove_proc_entry(acpi_device_bid(device), acpi_battery_dir);
+	acpi_device_dir(device) = NULL;
+}
+
+#endif
+
+/* --------------------------------------------------------------------------
                                  Driver Interface
    -------------------------------------------------------------------------- */
 
@@ -770,6 +1071,28 @@ static struct dmi_system_id bat_dmi_table[] = {
 	{},
 };
 
+/*
+ * Some machines'(E,G Lenovo Z480) ECs are not stable
+ * during boot up and this causes battery driver fails to be
+ * probed due to failure of getting battery information
+ * from EC sometimes. After several retries, the operation
+ * may work. So add retry code here and 20ms sleep between
+ * every retries.
+ */
+static int acpi_battery_update_retry(struct acpi_battery *battery)
+{
+	int retry, ret;
+
+	for (retry = 5; retry; retry--) {
+		ret = acpi_battery_update(battery);
+		if (!ret)
+			break;
+
+		msleep(20);
+	}
+	return ret;
+}
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -788,10 +1111,21 @@ static int acpi_battery_add(struct acpi_device *device)
 	mutex_init(&battery->sysfs_lock);
 	if (acpi_has_method(battery->device->handle, "_BIX"))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
-	result = acpi_battery_update(battery);
+
+	result = acpi_battery_update_retry(battery);
 	if (result)
 		goto fail;
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	result = acpi_battery_add_fs(device);
+#endif
+	if (result) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_battery_remove_fs(device);
+#endif
+		goto fail;
+	}
+
 	printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n",
 		ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device),
 		device->status.battery_present ? "present" : "absent");
@@ -817,6 +1151,9 @@ static int acpi_battery_remove(struct acpi_device *device)
 		return -EINVAL;
 	battery = acpi_driver_data(device);
 	unregister_pm_notifier(&battery->pm_nb);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_battery_remove_fs(device);
+#endif
 	sysfs_remove_battery(battery);
 	mutex_destroy(&battery->lock);
 	mutex_destroy(&battery->sysfs_lock);
@@ -867,7 +1204,19 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 
 	if (dmi_check_system(bat_dmi_table))
 		battery_bix_broken_package = 1;
-	acpi_bus_register_driver(&acpi_battery_driver);
+
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_battery_dir = acpi_lock_battery_dir();
+	if (!acpi_battery_dir)
+		return;
+#endif
+	if (acpi_bus_register_driver(&acpi_battery_driver) < 0) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_unlock_battery_dir(acpi_battery_dir);
+#endif
+		return;
+	}
+	return;
 }
 
 static int __init acpi_battery_init(void)
@@ -879,6 +1228,9 @@ static int __init acpi_battery_init(void)
 static void __exit acpi_battery_exit(void)
 {
 	acpi_bus_unregister_driver(&acpi_battery_driver);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_unlock_battery_dir(acpi_battery_dir);
+#endif
 }
 
 module_init(acpi_battery_init);
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index afec4526c48a..3d8413d02a97 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -314,6 +314,14 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		     DMI_MATCH(DMI_PRODUCT_VERSION, "2349D15"),
 		},
 	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Dell Inspiron 7737",
+	.matches = {
+		    DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		    DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7737"),
+		},
+	},
 
 	/*
 	 * BIOS invocation of _OSI(Linux) is almost always a BIOS bug.
@@ -374,6 +382,19 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		     DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T500"),
 		},
 	},
+	/*
+	 * Without this this EEEpc exports a non working WMI interface, with
+	 * this it exports a working "good old" eeepc_laptop interface, fixing
+	 * both brightness control, and rfkill not working.
+	 */
+	{
+	.callback = dmi_enable_osi_linux,
+	.ident = "Asus EEE PC 1015PX",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "1015PX"),
+		},
+	},
 	{}
 };
 
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index fcb59c21c68d..b48aefab57e8 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -52,6 +52,12 @@ struct proc_dir_entry *acpi_root_dir;
 EXPORT_SYMBOL(acpi_root_dir);
 
 #ifdef CONFIG_X86
+#ifdef CONFIG_ACPI_CUSTOM_DSDT
+static inline int set_copy_dsdt(const struct dmi_system_id *id)
+{
+	return 0;
+}
+#else
 static int set_copy_dsdt(const struct dmi_system_id *id)
 {
 	printk(KERN_NOTICE "%s detected - "
@@ -59,6 +65,7 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
 	acpi_gbl_copy_dsdt_locally = 1;
 	return 0;
 }
+#endif
 
 static struct dmi_system_id dsdt_dmi_table[] __initdata = {
 	/*
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 714e957a871a..db35594d4df7 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -302,6 +302,10 @@ static void acpi_button_notify(struct acpi_device *device, u32 event)
 			input_sync(input);
 
 			pm_wakeup_event(&device->dev, 0);
+			acpi_bus_generate_netlink_event(
+					device->pnp.device_class,
+					dev_name(&device->dev),
+					event, ++button->pushed);
 		}
 		break;
 	default:
diff --git a/drivers/acpi/cm_sbs.c b/drivers/acpi/cm_sbs.c
new file mode 100644
index 000000000000..6c9ee68e46fb
--- /dev/null
+++ b/drivers/acpi/cm_sbs.c
@@ -0,0 +1,105 @@
+/*
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or (at
+ *  your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/types.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+
+#define PREFIX "ACPI: "
+
+ACPI_MODULE_NAME("cm_sbs");
+#define ACPI_AC_CLASS		"ac_adapter"
+#define ACPI_BATTERY_CLASS	"battery"
+#define _COMPONENT		ACPI_SBS_COMPONENT
+static struct proc_dir_entry *acpi_ac_dir;
+static struct proc_dir_entry *acpi_battery_dir;
+
+static DEFINE_MUTEX(cm_sbs_mutex);
+
+static int lock_ac_dir_cnt;
+static int lock_battery_dir_cnt;
+
+struct proc_dir_entry *acpi_lock_ac_dir(void)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (!acpi_ac_dir)
+		acpi_ac_dir = proc_mkdir(ACPI_AC_CLASS, acpi_root_dir);
+	if (acpi_ac_dir) {
+		lock_ac_dir_cnt++;
+	} else {
+		printk(KERN_ERR PREFIX
+				  "Cannot create %s\n", ACPI_AC_CLASS);
+	}
+	mutex_unlock(&cm_sbs_mutex);
+	return acpi_ac_dir;
+}
+EXPORT_SYMBOL(acpi_lock_ac_dir);
+
+void acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir_param)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (acpi_ac_dir_param)
+		lock_ac_dir_cnt--;
+	if (lock_ac_dir_cnt == 0 && acpi_ac_dir_param && acpi_ac_dir) {
+		remove_proc_entry(ACPI_AC_CLASS, acpi_root_dir);
+		acpi_ac_dir = NULL;
+	}
+	mutex_unlock(&cm_sbs_mutex);
+}
+EXPORT_SYMBOL(acpi_unlock_ac_dir);
+
+struct proc_dir_entry *acpi_lock_battery_dir(void)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (!acpi_battery_dir) {
+		acpi_battery_dir =
+		    proc_mkdir(ACPI_BATTERY_CLASS, acpi_root_dir);
+	}
+	if (acpi_battery_dir) {
+		lock_battery_dir_cnt++;
+	} else {
+		printk(KERN_ERR PREFIX
+				  "Cannot create %s\n", ACPI_BATTERY_CLASS);
+	}
+	mutex_unlock(&cm_sbs_mutex);
+	return acpi_battery_dir;
+}
+EXPORT_SYMBOL(acpi_lock_battery_dir);
+
+void acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir_param)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (acpi_battery_dir_param)
+		lock_battery_dir_cnt--;
+	if (lock_battery_dir_cnt == 0 && acpi_battery_dir_param
+	    && acpi_battery_dir) {
+		remove_proc_entry(ACPI_BATTERY_CLASS, acpi_root_dir);
+		acpi_battery_dir = NULL;
+	}
+	mutex_unlock(&cm_sbs_mutex);
+	return;
+}
+EXPORT_SYMBOL(acpi_unlock_battery_dir);
diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index 368f9ddb8480..e4a6f78f3bbc 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -96,6 +96,13 @@ static void container_device_detach(struct acpi_device *adev)
 		device_unregister(dev);
 }
 
+static void container_device_online(struct acpi_device *adev)
+{
+	struct device *dev = acpi_driver_data(adev);
+
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
 static struct acpi_scan_handler container_handler = {
 	.ids = container_device_ids,
 	.attach = container_device_attach,
@@ -103,6 +110,7 @@ static struct acpi_scan_handler container_handler = {
 	.hotplug = {
 		.enabled = true,
 		.demand_offline = true,
+		.notify_online = container_device_online,
 	},
 };
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index c14a00d3dca6..22621c7b1867 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -257,7 +257,7 @@ int acpi_bus_init_power(struct acpi_device *device)
 
 	device->power.state = ACPI_STATE_UNKNOWN;
 	if (!acpi_device_is_present(device))
-		return 0;
+		return -ENXIO;
 
 	result = acpi_device_get_power(device, &state);
 	if (result)
@@ -987,6 +987,8 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 		acpi_dev_pm_full_power(adev);
 		__acpi_device_run_wake(adev, false);
 	}
+
+	dev->pm_domain->detach = acpi_dev_pm_detach;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index d7d32c28829b..49d89909b4ed 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -78,6 +78,9 @@ enum {
 	EC_FLAGS_BLOCKED,		/* Transactions are blocked */
 };
 
+#define ACPI_EC_COMMAND_POLL		0x01 /* Available for command byte */
+#define ACPI_EC_COMMAND_COMPLETE	0x02 /* Completed last byte */
+
 /* ec.c is compiled in acpi namespace so this shows up as acpi.ec_delay param */
 static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY;
 module_param(ec_delay, uint, 0644);
@@ -109,7 +112,7 @@ struct transaction {
 	u8 ri;
 	u8 wlen;
 	u8 rlen;
-	bool done;
+	u8 flags;
 };
 
 struct acpi_ec *boot_ec, *first_ec;
@@ -150,69 +153,83 @@ static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data)
 	outb(data, ec->data_addr);
 }
 
-static int ec_transaction_done(struct acpi_ec *ec)
+static int ec_transaction_completed(struct acpi_ec *ec)
 {
 	unsigned long flags;
 	int ret = 0;
 	spin_lock_irqsave(&ec->lock, flags);
-	if (!ec->curr || ec->curr->done)
+	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE))
 		ret = 1;
 	spin_unlock_irqrestore(&ec->lock, flags);
 	return ret;
 }
 
-static void start_transaction(struct acpi_ec *ec)
+static bool advance_transaction(struct acpi_ec *ec)
 {
-	ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0;
-	ec->curr->done = false;
-	acpi_ec_write_cmd(ec, ec->curr->command);
-}
-
-static void advance_transaction(struct acpi_ec *ec, u8 status)
-{
-	unsigned long flags;
 	struct transaction *t;
+	u8 status;
+	bool wakeup = false;
 
-	spin_lock_irqsave(&ec->lock, flags);
+	pr_debug("===== %s =====\n", in_interrupt() ? "IRQ" : "TASK");
+	status = acpi_ec_read_status(ec);
 	t = ec->curr;
 	if (!t)
-		goto unlock;
-	if (t->wlen > t->wi) {
-		if ((status & ACPI_EC_FLAG_IBF) == 0)
-			acpi_ec_write_data(ec,
-				t->wdata[t->wi++]);
-		else
-			goto err;
-	} else if (t->rlen > t->ri) {
-		if ((status & ACPI_EC_FLAG_OBF) == 1) {
-			t->rdata[t->ri++] = acpi_ec_read_data(ec);
-			if (t->rlen == t->ri)
-				t->done = true;
+		goto err;
+	if (t->flags & ACPI_EC_COMMAND_POLL) {
+		if (t->wlen > t->wi) {
+			if ((status & ACPI_EC_FLAG_IBF) == 0)
+				acpi_ec_write_data(ec, t->wdata[t->wi++]);
+			else
+				goto err;
+		} else if (t->rlen > t->ri) {
+			if ((status & ACPI_EC_FLAG_OBF) == 1) {
+				t->rdata[t->ri++] = acpi_ec_read_data(ec);
+				if (t->rlen == t->ri) {
+					t->flags |= ACPI_EC_COMMAND_COMPLETE;
+					wakeup = true;
+				}
+			} else
+				goto err;
+		} else if (t->wlen == t->wi &&
+			   (status & ACPI_EC_FLAG_IBF) == 0) {
+			t->flags |= ACPI_EC_COMMAND_COMPLETE;
+			wakeup = true;
+		}
+		return wakeup;
+	} else {
+		if ((status & ACPI_EC_FLAG_IBF) == 0) {
+			acpi_ec_write_cmd(ec, t->command);
+			t->flags |= ACPI_EC_COMMAND_POLL;
 		} else
 			goto err;
-	} else if (t->wlen == t->wi &&
-		   (status & ACPI_EC_FLAG_IBF) == 0)
-		t->done = true;
-	goto unlock;
+		return wakeup;
+	}
 err:
 	/*
 	 * If SCI bit is set, then don't think it's a false IRQ
 	 * otherwise will take a not handled IRQ as a false one.
 	 */
-	if (in_interrupt() && !(status & ACPI_EC_FLAG_SCI))
-		++t->irq_count;
+	if (!(status & ACPI_EC_FLAG_SCI)) {
+		if (in_interrupt() && t)
+			++t->irq_count;
+	}
+	return wakeup;
+}
 
-unlock:
-	spin_unlock_irqrestore(&ec->lock, flags);
+static void start_transaction(struct acpi_ec *ec)
+{
+	ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0;
+	ec->curr->flags = 0;
+	(void)advance_transaction(ec);
 }
 
-static int acpi_ec_sync_query(struct acpi_ec *ec);
+static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data);
 
 static int ec_check_sci_sync(struct acpi_ec *ec, u8 state)
 {
 	if (state & ACPI_EC_FLAG_SCI) {
 		if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags))
-			return acpi_ec_sync_query(ec);
+			return acpi_ec_sync_query(ec, NULL);
 	}
 	return 0;
 }
@@ -228,15 +245,17 @@ static int ec_poll(struct acpi_ec *ec)
 			/* don't sleep with disabled interrupts */
 			if (EC_FLAGS_MSI || irqs_disabled()) {
 				udelay(ACPI_EC_MSI_UDELAY);
-				if (ec_transaction_done(ec))
+				if (ec_transaction_completed(ec))
 					return 0;
 			} else {
 				if (wait_event_timeout(ec->wait,
-						ec_transaction_done(ec),
+						ec_transaction_completed(ec),
 						msecs_to_jiffies(1)))
 					return 0;
 			}
-			advance_transaction(ec, acpi_ec_read_status(ec));
+			spin_lock_irqsave(&ec->lock, flags);
+			(void)advance_transaction(ec);
+			spin_unlock_irqrestore(&ec->lock, flags);
 		} while (time_before(jiffies, delay));
 		pr_debug("controller reset, restart transaction\n");
 		spin_lock_irqsave(&ec->lock, flags);
@@ -268,23 +287,6 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	return ret;
 }
 
-static int ec_check_ibf0(struct acpi_ec *ec)
-{
-	u8 status = acpi_ec_read_status(ec);
-	return (status & ACPI_EC_FLAG_IBF) == 0;
-}
-
-static int ec_wait_ibf0(struct acpi_ec *ec)
-{
-	unsigned long delay = jiffies + msecs_to_jiffies(ec_delay);
-	/* interrupt wait manually if GPE mode is not active */
-	while (time_before(jiffies, delay))
-		if (wait_event_timeout(ec->wait, ec_check_ibf0(ec),
-					msecs_to_jiffies(1)))
-			return 0;
-	return -ETIME;
-}
-
 static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 {
 	int status;
@@ -305,12 +307,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 			goto unlock;
 		}
 	}
-	if (ec_wait_ibf0(ec)) {
-		pr_err("input buffer is not empty, "
-				"aborting transaction\n");
-		status = -ETIME;
-		goto end;
-	}
 	pr_debug("transaction start (cmd=0x%02x, addr=0x%02x)\n",
 			t->command, t->wdata ? t->wdata[0] : 0);
 	/* disable GPE during transaction if storm is detected */
@@ -334,7 +330,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 		set_bit(EC_FLAGS_GPE_STORM, &ec->flags);
 	}
 	pr_debug("transaction end\n");
-end:
 	if (ec->global_lock)
 		acpi_release_global_lock(glk);
 unlock:
@@ -443,10 +438,8 @@ acpi_handle ec_get_handle(void)
 
 EXPORT_SYMBOL(ec_get_handle);
 
-static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data);
-
 /*
- * Clears stale _Q events that might have accumulated in the EC.
+ * Process _Q events that might have accumulated in the EC.
  * Run with locked ec mutex.
  */
 static void acpi_ec_clear(struct acpi_ec *ec)
@@ -455,7 +448,7 @@ static void acpi_ec_clear(struct acpi_ec *ec)
 	u8 value = 0;
 
 	for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) {
-		status = acpi_ec_query_unlocked(ec, &value);
+		status = acpi_ec_sync_query(ec, &value);
 		if (status || !value)
 			break;
 	}
@@ -582,13 +575,18 @@ static void acpi_ec_run(void *cxt)
 	kfree(handler);
 }
 
-static int acpi_ec_sync_query(struct acpi_ec *ec)
+static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data)
 {
 	u8 value = 0;
 	int status;
 	struct acpi_ec_query_handler *handler, *copy;
-	if ((status = acpi_ec_query_unlocked(ec, &value)))
+
+	status = acpi_ec_query_unlocked(ec, &value);
+	if (data)
+		*data = value;
+	if (status)
 		return status;
+
 	list_for_each_entry(handler, &ec->list, node) {
 		if (value == handler->query_bit) {
 			/* have custom handler for this bit */
@@ -612,7 +610,7 @@ static void acpi_ec_gpe_query(void *ec_cxt)
 	if (!ec)
 		return;
 	mutex_lock(&ec->mutex);
-	acpi_ec_sync_query(ec);
+	acpi_ec_sync_query(ec, NULL);
 	mutex_unlock(&ec->mutex);
 }
 
@@ -631,17 +629,14 @@ static int ec_check_sci(struct acpi_ec *ec, u8 state)
 static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
 	u32 gpe_number, void *data)
 {
+	unsigned long flags;
 	struct acpi_ec *ec = data;
-	u8 status = acpi_ec_read_status(ec);
 
-	pr_debug("~~~> interrupt, status:0x%02x\n", status);
-
-	advance_transaction(ec, status);
-	if (ec_transaction_done(ec) &&
-	    (acpi_ec_read_status(ec) & ACPI_EC_FLAG_IBF) == 0) {
+	spin_lock_irqsave(&ec->lock, flags);
+	if (advance_transaction(ec))
 		wake_up(&ec->wait);
-		ec_check_sci(ec, acpi_ec_read_status(ec));
-	}
+	spin_unlock_irqrestore(&ec->lock, flags);
+	ec_check_sci(ec, acpi_ec_read_status(ec));
 	return ACPI_INTERRUPT_HANDLED | ACPI_REENABLE_GPE;
 }
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 3dca36d4ad26..17f9ec501972 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -1071,9 +1071,9 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 
 	if (pr->id == 0 && cpuidle_get_driver() == &acpi_idle_driver) {
 
-		cpuidle_pause_and_lock();
 		/* Protect against cpu-hotplug */
 		get_online_cpus();
+		cpuidle_pause_and_lock();
 
 		/* Disable all cpuidle devices */
 		for_each_online_cpu(cpu) {
@@ -1100,8 +1100,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr)
 				cpuidle_enable_device(dev);
 			}
 		}
-		put_online_cpus();
 		cpuidle_resume_and_unlock();
+		put_online_cpus();
 	}
 
 	return 0;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 0bdacc5e26a3..2ba8f02ced36 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -77,7 +77,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_MEMORY24:
 		memory24 = &ares->data.memory24;
-		if (!memory24->address_length)
+		if (!memory24->minimum && !memory24->address_length)
 			return false;
 		acpi_dev_get_memresource(res, memory24->minimum,
 					 memory24->address_length,
@@ -85,7 +85,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
 		break;
 	case ACPI_RESOURCE_TYPE_MEMORY32:
 		memory32 = &ares->data.memory32;
-		if (!memory32->address_length)
+		if (!memory32->minimum && !memory32->address_length)
 			return false;
 		acpi_dev_get_memresource(res, memory32->minimum,
 					 memory32->address_length,
@@ -93,7 +93,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
 		fixed_memory32 = &ares->data.fixed_memory32;
-		if (!fixed_memory32->address_length)
+		if (!fixed_memory32->address && !fixed_memory32->address_length)
 			return false;
 		acpi_dev_get_memresource(res, fixed_memory32->address,
 					 fixed_memory32->address_length,
@@ -150,7 +150,7 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res)
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_IO:
 		io = &ares->data.io;
-		if (!io->address_length)
+		if (!io->minimum && !io->address_length)
 			return false;
 		acpi_dev_get_ioresource(res, io->minimum,
 					io->address_length,
@@ -158,7 +158,7 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res)
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_IO:
 		fixed_io = &ares->data.fixed_io;
-		if (!fixed_io->address_length)
+		if (!fixed_io->address && !fixed_io->address_length)
 			return false;
 		acpi_dev_get_ioresource(res, fixed_io->address,
 					fixed_io->address_length,
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 57b053f424d1..666beea3bf1c 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -106,7 +106,7 @@ static int create_modalias(struct acpi_device *acpi_dev, char *modalias,
 	list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
 		count = snprintf(&modalias[len], size, "%s:", id->id);
 		if (count < 0)
-			return EINVAL;
+			return -EINVAL;
 		if (count >= size)
 			return -ENOMEM;
 		len += count;
@@ -329,7 +329,8 @@ static int acpi_scan_hot_remove(struct acpi_device *device)
 	unsigned long long sta;
 	acpi_status status;
 
-	if (device->handler->hotplug.demand_offline && !acpi_force_hot_remove) {
+	if (device->handler && device->handler->hotplug.demand_offline
+	    && !acpi_force_hot_remove) {
 		if (!acpi_scan_is_offline(device, true))
 			return -EBUSY;
 	} else {
@@ -660,8 +661,14 @@ static ssize_t
 acpi_device_sun_show(struct device *dev, struct device_attribute *attr,
 		     char *buf) {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	acpi_status status;
+	unsigned long long sun;
+
+	status = acpi_evaluate_integer(acpi_dev->handle, "_SUN", NULL, &sun);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
 
-	return sprintf(buf, "%lu\n", acpi_dev->pnp.sun);
+	return sprintf(buf, "%llu\n", sun);
 }
 static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL);
 
@@ -683,7 +690,6 @@ static int acpi_device_setup_files(struct acpi_device *dev)
 {
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
 	acpi_status status;
-	unsigned long long sun;
 	int result = 0;
 
 	/*
@@ -724,14 +730,10 @@ static int acpi_device_setup_files(struct acpi_device *dev)
 	if (dev->pnp.unique_id)
 		result = device_create_file(&dev->dev, &dev_attr_uid);
 
-	status = acpi_evaluate_integer(dev->handle, "_SUN", NULL, &sun);
-	if (ACPI_SUCCESS(status)) {
-		dev->pnp.sun = (unsigned long)sun;
+	if (acpi_has_method(dev->handle, "_SUN")) {
 		result = device_create_file(&dev->dev, &dev_attr_sun);
 		if (result)
 			goto end;
-	} else {
-		dev->pnp.sun = (unsigned long)-1;
 	}
 
 	if (acpi_has_method(dev->handle, "_STA")) {
@@ -863,7 +865,7 @@ static void acpi_free_power_resources_lists(struct acpi_device *device)
 	if (device->wakeup.flags.valid)
 		acpi_power_resources_list_free(&device->wakeup.resources);
 
-	if (!device->flags.power_manageable)
+	if (!device->power.flags.power_resources)
 		return;
 
 	for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) {
@@ -915,12 +917,17 @@ static void acpi_device_notify(acpi_handle handle, u32 event, void *data)
 	device->driver->ops.notify(device, event);
 }
 
-static acpi_status acpi_device_notify_fixed(void *data)
+static void acpi_device_notify_fixed(void *data)
 {
 	struct acpi_device *device = data;
 
 	/* Fixed hardware devices have no handles */
 	acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device);
+}
+
+static acpi_status acpi_device_fixed_event(void *data)
+{
+	acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data);
 	return AE_OK;
 }
 
@@ -931,12 +938,12 @@ static int acpi_device_install_notify_handler(struct acpi_device *device)
 	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
 		status =
 		    acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						     acpi_device_notify_fixed,
+						     acpi_device_fixed_event,
 						     device);
 	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
 		status =
 		    acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						     acpi_device_notify_fixed,
+						     acpi_device_fixed_event,
 						     device);
 	else
 		status = acpi_install_notify_handler(device->handle,
@@ -953,10 +960,10 @@ static void acpi_device_remove_notify_handler(struct acpi_device *device)
 {
 	if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
 		acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
-						acpi_device_notify_fixed);
+						acpi_device_fixed_event);
 	else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
 		acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
-						acpi_device_notify_fixed);
+						acpi_device_fixed_event);
 	else
 		acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
 					   acpi_device_notify);
@@ -1547,10 +1554,8 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 			device->power.flags.power_resources)
 		device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1;
 
-	if (acpi_bus_init_power(device)) {
-		acpi_free_power_resources_lists(device);
+	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
-	}
 }
 
 static void acpi_bus_get_flags(struct acpi_device *device)
@@ -2036,13 +2041,18 @@ static void acpi_bus_attach(struct acpi_device *device)
 	/* Skip devices that are not present. */
 	if (!acpi_device_is_present(device)) {
 		device->flags.visited = false;
+		device->flags.power_manageable = 0;
 		return;
 	}
 	if (device->handler)
 		goto ok;
 
 	if (!device->flags.initialized) {
-		acpi_bus_update_power(device, NULL);
+		device->flags.power_manageable =
+			device->power.states[ACPI_STATE_D0].flags.valid;
+		if (acpi_bus_init_power(device))
+			device->flags.power_manageable = 0;
+
 		device->flags.initialized = true;
 	}
 	device->flags.visited = false;
@@ -2061,6 +2071,9 @@ static void acpi_bus_attach(struct acpi_device *device)
  ok:
 	list_for_each_entry(child, &device->children, node)
 		acpi_bus_attach(child);
+
+	if (device->handler && device->handler->hotplug.notify_online)
+		device->handler->hotplug.notify_online(device);
 }
 
 /**
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 85e3b612bdc0..81a756c765dc 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/hardirq.h>
 #include <linux/acpi.h>
+#include <linux/dynamic_debug.h>
 
 #include "internal.h"
 
@@ -464,6 +465,24 @@ acpi_evaluate_hotplug_ost(acpi_handle handle, u32 source_event,
 EXPORT_SYMBOL(acpi_evaluate_hotplug_ost);
 
 /**
+ * acpi_handle_path: Return the object path of handle
+ *
+ * Caller must free the returned buffer
+ */
+static char *acpi_handle_path(acpi_handle handle)
+{
+	struct acpi_buffer buffer = {
+		.length = ACPI_ALLOCATE_BUFFER,
+		.pointer = NULL
+	};
+
+	if (in_interrupt() ||
+	    acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer) != AE_OK)
+		return NULL;
+	return buffer.pointer;
+}
+
+/**
  * acpi_handle_printk: Print message with ACPI prefix and object path
  *
  * This function is called through acpi_handle_<level> macros and prints
@@ -476,29 +495,50 @@ acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	struct acpi_buffer buffer = {
-		.length = ACPI_ALLOCATE_BUFFER,
-		.pointer = NULL
-	};
 	const char *path;
 
 	va_start(args, fmt);
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	if (in_interrupt() ||
-	    acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer) != AE_OK)
-		path = "<n/a>";
-	else
-		path = buffer.pointer;
-
-	printk("%sACPI: %s: %pV", level, path, &vaf);
+	path = acpi_handle_path(handle);
+	printk("%sACPI: %s: %pV", level, path ? path : "<n/a>" , &vaf);
 
 	va_end(args);
-	kfree(buffer.pointer);
+	kfree(path);
 }
 EXPORT_SYMBOL(acpi_handle_printk);
 
+#if defined(CONFIG_DYNAMIC_DEBUG)
+/**
+ * __acpi_handle_debug: pr_debug with ACPI prefix and object path
+ *
+ * This function is called through acpi_handle_debug macro and debug
+ * prints a message with ACPI prefix and object path. This function
+ * acquires the global namespace mutex to obtain an object path.  In
+ * interrupt context, it shows the object path as <n/a>.
+ */
+void
+__acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle,
+		    const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	const char *path;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	path = acpi_handle_path(handle);
+	__dynamic_pr_debug(descriptor, "ACPI: %s: %pV", path ? path : "<n/a>", &vaf);
+
+	va_end(args);
+	kfree(path);
+}
+EXPORT_SYMBOL(__acpi_handle_debug);
+#endif
+
 /**
  * acpi_has_method: Check whether @handle has a method named @name
  * @handle: ACPI device handle
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index b6ba88ed31ae..bb0b90461a6b 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -459,10 +459,10 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	},
 	{
 	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad T430s",
+	 .ident = "ThinkPad T430 and T430s",
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430"),
 		},
 	},
 	{
@@ -474,7 +474,7 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		},
 	},
 	{
-	.callback = video_set_use_native_backlight,
+	 .callback = video_set_use_native_backlight,
 	.ident = "ThinkPad X1 Carbon",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -494,7 +494,7 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	 .ident = "Dell Inspiron 7520",
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "Inspiron 7520"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"),
 		},
 	},
 	{
@@ -507,6 +507,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	},
 	{
 	 .callback = video_set_use_native_backlight,
+	 .ident = "Acer Aspire 5742G",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5742G"),
+		},
+	},
+	{
+	 .callback = video_set_use_native_backlight,
 	 .ident = "Acer Aspire V5-431",
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 9e6029105607..0b3ce7bce836 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -327,7 +327,7 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
 
 		amba_put_disable_pclk(dev);
 
-		if (cid == AMBA_CID)
+		if (cid == AMBA_CID || cid == CORESIGHT_CID)
 			dev->periphid = pid;
 
 		if (!dev->periphid)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index c81d809c111b..cc5f102bebf3 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -61,6 +61,7 @@ enum board_ids {
 	/* board IDs by feature in alphabetical order */
 	board_ahci,
 	board_ahci_ign_iferr,
+	board_ahci_nomsi,
 	board_ahci_noncq,
 	board_ahci_nosntf,
 	board_ahci_yes_fbs,
@@ -122,6 +123,13 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	[board_ahci_nomsi] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_MSI),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_noncq] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_NCQ),
 		.flags		= AHCI_FLAG_COMMON,
@@ -306,6 +314,22 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x9c85), board_ahci }, /* Wildcat Point-LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */
+	{ PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */
+	{ PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
+	{ PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
+	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -443,16 +467,23 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172),
+	  .driver_data = board_ahci_yes_fbs },			/* 88se9182 */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9182),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 on some Gigabyte */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0),
+	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a3),
 	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230),
 	  .driver_data = board_ahci_yes_fbs },
+	{ PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642),
+	  .driver_data = board_ahci_yes_fbs },
 
 	/* Promise */
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
+	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
 	/* Asmedia */
 	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
@@ -461,10 +492,11 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci },	/* ASM1062 */
 
 	/*
-	 * Samsung SSDs found on some macbooks.  NCQ times out.
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=60731
+	 * Samsung SSDs found on some macbooks.  NCQ times out if MSI is
+	 * enabled.  https://bugzilla.kernel.org/show_bug.cgi?id=60731
 	 */
-	{ PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq },
+	{ PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi },
+	{ PCI_VDEVICE(SAMSUNG, 0xa800), board_ahci_nomsi },
 
 	/* Enmotus */
 	{ PCI_DEVICE(0x1c44, 0x8000), board_ahci },
@@ -1163,7 +1195,7 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host)
 #endif
 
 static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports,
-			 struct ahci_host_priv *hpriv)
+				struct ahci_host_priv *hpriv)
 {
 	int rc, nvec;
 
@@ -1189,6 +1221,13 @@ static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports,
 	else if (rc > 0)
 		goto single_msi;
 
+	/* fallback to single MSI mode if the controller enforced MRSM mode */
+	if (readl(hpriv->mmio + HOST_CTL) & HOST_MRSM) {
+		pci_disable_msi(pdev);
+		printk(KERN_INFO "ahci: MRSM is on, fallback to single MSI\n");
+		goto single_msi;
+	}
+
 	return nvec;
 
 single_msi:
@@ -1233,18 +1272,18 @@ int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis)
 		return rc;
 
 	for (i = 0; i < host->n_ports; i++) {
-		const char* desc;
 		struct ahci_port_priv *pp = host->ports[i]->private_data;
 
-		/* pp is NULL for dummy ports */
-		if (pp)
-			desc = pp->irq_desc;
-		else
-			desc = dev_driver_string(host->dev);
+		/* Do not receive interrupts sent by dummy ports */
+		if (!pp) {
+			disable_irq(irq + i);
+			continue;
+		}
 
-		rc = devm_request_threaded_irq(host->dev,
-			irq + i, ahci_hw_interrupt, ahci_thread_fn, IRQF_SHARED,
-			desc, host->ports[i]);
+		rc = devm_request_threaded_irq(host->dev, irq + i,
+					       ahci_hw_interrupt,
+					       ahci_thread_fn, IRQF_SHARED,
+					       pp->irq_desc, host->ports[i]);
 		if (rc)
 			goto out_free_irqs;
 	}
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 2289efdf8203..ad36faf31dbd 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -91,6 +91,7 @@ enum {
 	/* HOST_CTL bits */
 	HOST_RESET		= (1 << 0),  /* reset controller; self-clear */
 	HOST_IRQ_EN		= (1 << 1),  /* global IRQ enable */
+	HOST_MRSM		= (1 << 2),  /* MSI Revert to Single Message */
 	HOST_AHCI_EN		= (1 << 31), /* AHCI enabled */
 
 	/* HOST_CAP bits */
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 6334c8d7c3f1..39f76b987c75 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -340,6 +340,14 @@ static const struct pci_device_id piix_pci_tbl[] = {
 	{ 0x8086, 0x0F21, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_byt },
 	/* SATA Controller IDE (Coleto Creek) */
 	{ 0x8086, 0x23a6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c88, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c89, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c80, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
+	/* SATA Controller IDE (9 Series) */
+	{ 0x8086, 0x8c81, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
 
 	{ }	/* terminate list */
 };
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 8cb2522d592a..538574f98e22 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4226,6 +4226,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	/* devices that don't properly handle queued TRIM commands */
 	{ "Micron_M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
 	{ "Crucial_CT???M500SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Micron_M550*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Crucial_CT*M550SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
 
 	/*
 	 * Some WD SATA-I drives spin up and down erratically when the link
@@ -4785,6 +4787,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
  *	ata_qc_new - Request an available ATA command, for queueing
  *	@ap: target port
  *
+ *	Some ATA host controllers may implement a queue depth which is less
+ *	than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
+ *	the hardware limitation.
+ *
  *	LOCKING:
  *	None.
  */
@@ -4792,21 +4798,27 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 {
 	struct ata_queued_cmd *qc = NULL;
-	unsigned int i;
+	unsigned int max_queue = ap->host->n_tags;
+	unsigned int i, tag;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	/* the last tag is reserved for internal command. */
-	for (i = 0; i < ATA_MAX_QUEUE - 1; i++)
-		if (!test_and_set_bit(i, &ap->qc_allocated)) {
-			qc = __ata_qc_from_tag(ap, i);
+	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
+		tag = tag < max_queue ? tag : 0;
+
+		/* the last tag is reserved for internal command. */
+		if (tag == ATA_TAG_INTERNAL)
+			continue;
+
+		if (!test_and_set_bit(tag, &ap->qc_allocated)) {
+			qc = __ata_qc_from_tag(ap, tag);
+			qc->tag = tag;
+			ap->last_tag = tag;
 			break;
 		}
-
-	if (qc)
-		qc->tag = i;
+	}
 
 	return qc;
 }
@@ -6096,6 +6108,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 {
 	spin_lock_init(&host->lock);
 	mutex_init(&host->eh_mutex);
+	host->n_tags = ATA_MAX_QUEUE - 1;
 	host->dev = dev;
 	host->ops = ops;
 }
@@ -6177,6 +6190,8 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 {
 	int i, rc;
 
+	host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1);
+
 	/* host must have been started */
 	if (!(host->flags & ATA_HOST_STARTED)) {
 		dev_err(host->dev, "BUG: trying to register unstarted host\n");
@@ -6322,6 +6337,8 @@ int ata_host_activate(struct ata_host *host, int irq,
 static void ata_port_detach(struct ata_port *ap)
 {
 	unsigned long flags;
+	struct ata_link *link;
+	struct ata_device *dev;
 
 	if (!ap->ops->error_handler)
 		goto skip_eh;
@@ -6341,6 +6358,13 @@ static void ata_port_detach(struct ata_port *ap)
 	cancel_delayed_work_sync(&ap->hotplug_task);
 
  skip_eh:
+	/* clean up zpodd on port removal */
+	ata_for_each_link(link, ap, HOST_FIRST) {
+		ata_for_each_dev(dev, link, ALL) {
+			if (zpodd_dev_enabled(dev))
+				zpodd_exit(dev);
+		}
+	}
 	if (ap->pmp_link) {
 		int i;
 		for (i = 0; i < SATA_PMP_MAX_PORTS; i++)
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index b603720b877d..37acda6fa7e4 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2008,13 +2008,15 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask,
 
 	DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
 
-	/* software reset.  causes dev0 to be selected */
-	iowrite8(ap->ctl, ioaddr->ctl_addr);
-	udelay(20);	/* FIXME: flush */
-	iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
-	udelay(20);	/* FIXME: flush */
-	iowrite8(ap->ctl, ioaddr->ctl_addr);
-	ap->last_ctl = ap->ctl;
+	if (ap->ioaddr.ctl_addr) {
+		/* software reset.  causes dev0 to be selected */
+		iowrite8(ap->ctl, ioaddr->ctl_addr);
+		udelay(20);	/* FIXME: flush */
+		iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
+		udelay(20);	/* FIXME: flush */
+		iowrite8(ap->ctl, ioaddr->ctl_addr);
+		ap->last_ctl = ap->ctl;
+	}
 
 	/* wait the port to become ready */
 	return ata_sff_wait_after_reset(&ap->link, devmask, deadline);
@@ -2215,10 +2217,6 @@ void ata_sff_error_handler(struct ata_port *ap)
 
 	spin_unlock_irqrestore(ap->lock, flags);
 
-	/* ignore ata_sff_softreset if ctl isn't accessible */
-	if (softreset == ata_sff_softreset && !ap->ioaddr.ctl_addr)
-		softreset = NULL;
-
 	/* ignore built-in hardresets if SCR access is not available */
 	if ((hardreset == sata_std_hardreset ||
 	     hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link))
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
index d63ee8f41a4f..e3a49df958a3 100644
--- a/drivers/ata/pata_at91.c
+++ b/drivers/ata/pata_at91.c
@@ -408,12 +408,13 @@ static int pata_at91_probe(struct platform_device *pdev)
 
 	host->private_data = info;
 
-	return ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
-			gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
-			irq_flags, &pata_at91_sht);
+	ret = ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
+				gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
+				irq_flags, &pata_at91_sht);
+	if (ret)
+		goto err_put;
 
-	if (!ret)
-		return 0;
+	return 0;
 
 err_put:
 	clk_put(info->mck);
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index f35f15f4d83e..f7badaa39eb6 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -586,7 +586,7 @@ static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask,
  *	Note: Original code is ata_bus_softreset().
  */
 
-static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
+static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
                                       unsigned long deadline)
 {
 	struct ata_ioports *ioaddr = &ap->ioaddr;
@@ -600,9 +600,7 @@ static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
 	udelay(20);
 	out_be32(ioaddr->ctl_addr, ap->ctl);
 
-	scc_wait_after_reset(&ap->link, devmask, deadline);
-
-	return 0;
+	return scc_wait_after_reset(&ap->link, devmask, deadline);
 }
 
 /**
@@ -619,7 +617,8 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes,
 {
 	struct ata_port *ap = link->ap;
 	unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS;
-	unsigned int devmask = 0, err_mask;
+	unsigned int devmask = 0;
+	int rc;
 	u8 err;
 
 	DPRINTK("ENTER\n");
@@ -635,9 +634,9 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes,
 
 	/* issue bus reset */
 	DPRINTK("about to softreset, devmask=%x\n", devmask);
-	err_mask = scc_bus_softreset(ap, devmask, deadline);
-	if (err_mask) {
-		ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", err_mask);
+	rc = scc_bus_softreset(ap, devmask, deadline);
+	if (rc) {
+		ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc);
 		return -EIO;
 	}
 
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index 96c6a79ef606..79dedbae282c 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -252,12 +252,18 @@ static void serverworks_set_dmamode(struct ata_port *ap, struct ata_device *adev
 	pci_write_config_byte(pdev, 0x54, ultra_cfg);
 }
 
-static struct scsi_host_template serverworks_sht = {
+static struct scsi_host_template serverworks_osb4_sht = {
+	ATA_BMDMA_SHT(DRV_NAME),
+	.sg_tablesize	= LIBATA_DUMB_MAX_PRD,
+};
+
+static struct scsi_host_template serverworks_csb_sht = {
 	ATA_BMDMA_SHT(DRV_NAME),
 };
 
 static struct ata_port_operations serverworks_osb4_port_ops = {
 	.inherits	= &ata_bmdma_port_ops,
+	.qc_prep	= ata_bmdma_dumb_qc_prep,
 	.cable_detect	= serverworks_cable_detect,
 	.mode_filter	= serverworks_osb4_filter,
 	.set_piomode	= serverworks_set_piomode,
@@ -266,6 +272,7 @@ static struct ata_port_operations serverworks_osb4_port_ops = {
 
 static struct ata_port_operations serverworks_csb_port_ops = {
 	.inherits	= &serverworks_osb4_port_ops,
+	.qc_prep	= ata_bmdma_qc_prep,
 	.mode_filter	= serverworks_csb_filter,
 };
 
@@ -405,6 +412,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 		}
 	};
 	const struct ata_port_info *ppi[] = { &info[id->driver_data], NULL };
+	struct scsi_host_template *sht = &serverworks_csb_sht;
 	int rc;
 
 	rc = pcim_enable_device(pdev);
@@ -418,6 +426,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 		/* Select non UDMA capable OSB4 if we can't do fixups */
 		if (rc < 0)
 			ppi[0] = &info[1];
+		sht = &serverworks_osb4_sht;
 	}
 	/* setup CSB5/CSB6 : South Bridge and IDE option RAID */
 	else if ((pdev->device == PCI_DEVICE_ID_SERVERWORKS_CSB5IDE) ||
@@ -434,7 +443,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 			ppi[1] = &ata_dummy_port_info;
 	}
 
-	return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0);
+	return ata_pci_bmdma_init_one(pdev, ppi, sht, NULL, 0);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index fb0b40a191c2..ee2780dd90a8 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1503,7 +1503,7 @@ static int sata_fsl_probe(struct platform_device *ofdev)
 	host_priv->csr_base = csr_base;
 
 	irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
-	if (irq < 0) {
+	if (!irq) {
 		dev_err(&ofdev->dev, "invalid irq from platform\n");
 		goto error_exit_with_cleanup;
 	}
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 2b25bd83fc9d..c1ea780fca07 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -146,6 +146,7 @@
 enum sata_rcar_type {
 	RCAR_GEN1_SATA,
 	RCAR_GEN2_SATA,
+	RCAR_R8A7790_ES1_SATA,
 };
 
 struct sata_rcar_priv {
@@ -763,6 +764,9 @@ static void sata_rcar_setup_port(struct ata_host *host)
 	ap->udma_mask	= ATA_UDMA6;
 	ap->flags	|= ATA_FLAG_SATA;
 
+	if (priv->type == RCAR_R8A7790_ES1_SATA)
+		ap->flags	|= ATA_FLAG_NO_DIPM;
+
 	ioaddr->cmd_addr = base + SDATA_REG;
 	ioaddr->ctl_addr = base + SSDEVCON_REG;
 	ioaddr->scr_addr = base + SCRSSTS_REG;
@@ -792,6 +796,7 @@ static void sata_rcar_init_controller(struct ata_host *host)
 		sata_rcar_gen1_phy_init(priv);
 		break;
 	case RCAR_GEN2_SATA:
+	case RCAR_R8A7790_ES1_SATA:
 		sata_rcar_gen2_phy_init(priv);
 		break;
 	default:
@@ -838,6 +843,10 @@ static struct of_device_id sata_rcar_match[] = {
 		.data = (void *)RCAR_GEN2_SATA
 	},
 	{
+		.compatible = "renesas,sata-r8a7790-es1",
+		.data = (void *)RCAR_R8A7790_ES1_SATA
+	},
+	{
 		.compatible = "renesas,sata-r8a7791",
 		.data = (void *)RCAR_GEN2_SATA
 	},
@@ -849,6 +858,7 @@ static const struct platform_device_id sata_rcar_id_table[] = {
 	{ "sata_rcar", RCAR_GEN1_SATA }, /* Deprecated by "sata-r8a7779" */
 	{ "sata-r8a7779", RCAR_GEN1_SATA },
 	{ "sata-r8a7790", RCAR_GEN2_SATA },
+	{ "sata-r8a7790-es1", RCAR_R8A7790_ES1_SATA },
 	{ "sata-r8a7791", RCAR_GEN2_SATA },
 	{ },
 };
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index ec36e7772e57..3f0d3732df7f 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -185,6 +185,14 @@ config GENERIC_CPU_DEVICES
 	bool
 	default n
 
+config HAVE_CPU_AUTOPROBE
+	def_bool ARCH_HAS_CPU_AUTOPROBE
+
+config GENERIC_CPU_AUTOPROBE
+	bool
+	depends on !ARCH_HAS_CPU_AUTOPROBE
+	select HAVE_CPU_AUTOPROBE
+
 config SOC_BUS
 	bool
 
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 59dc8086e4fa..45d0fa78981c 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -254,13 +254,15 @@ static ssize_t store_drivers_probe(struct bus_type *bus,
 				   const char *buf, size_t count)
 {
 	struct device *dev;
+	int err = -EINVAL;
 
 	dev = bus_find_device_by_name(bus, NULL, buf);
 	if (!dev)
 		return -ENODEV;
-	if (bus_rescan_devices_helper(dev, NULL) != 0)
-		return -EINVAL;
-	return count;
+	if (bus_rescan_devices_helper(dev, NULL) == 0)
+		err = count;
+	put_device(dev);
+	return err;
 }
 
 static struct device *next_device(struct klist_iter *i)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2b567177ef78..6a8955e78610 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -741,12 +741,12 @@ class_dir_create_and_add(struct class *class, struct kobject *parent_kobj)
 	return &dir->kobj;
 }
 
+static DEFINE_MUTEX(gdp_mutex);
 
 static struct kobject *get_device_parent(struct device *dev,
 					 struct device *parent)
 {
 	if (dev->class) {
-		static DEFINE_MUTEX(gdp_mutex);
 		struct kobject *kobj = NULL;
 		struct kobject *parent_kobj;
 		struct kobject *k;
@@ -810,7 +810,9 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 	    glue_dir->kset != &dev->class->p->glue_dirs)
 		return;
 
+	mutex_lock(&gdp_mutex);
 	kobject_put(glue_dir);
+	mutex_unlock(&gdp_mutex);
 }
 
 static void cleanup_device_parent(struct device *dev)
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index f48370dfc908..8a38bf8c792f 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -15,6 +15,7 @@
 #include <linux/percpu.h>
 #include <linux/acpi.h>
 #include <linux/of.h>
+#include <linux/cpufeature.h>
 
 #include "base.h"
 
@@ -286,6 +287,45 @@ static void cpu_device_release(struct device *dev)
 	 */
 }
 
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+static ssize_t print_cpu_modalias(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	ssize_t n;
+	u32 i;
+
+	n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:",
+		    CPU_FEATURE_TYPEVAL);
+
+	for (i = 0; i < MAX_CPU_FEATURES; i++)
+		if (cpu_have_feature(i)) {
+			if (PAGE_SIZE < n + sizeof(",XXXX\n")) {
+				WARN(1, "CPU features overflow page\n");
+				break;
+			}
+			n += sprintf(&buf[n], ",%04X", i);
+		}
+	buf[n++] = '\n';
+	return n;
+}
+#else
+#define print_cpu_modalias	arch_print_cpu_modalias
+#endif
+
+static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf) {
+		print_cpu_modalias(NULL, NULL, buf);
+		add_uevent_var(env, "MODALIAS=%s", buf);
+		kfree(buf);
+	}
+	return 0;
+}
+#endif
+
 /*
  * register_cpu - Setup a sysfs device for a CPU.
  * @cpu - cpu->hotpluggable field set to 1 will generate a control file in
@@ -306,8 +346,8 @@ int register_cpu(struct cpu *cpu, int num)
 	cpu->dev.offline_disabled = !cpu->hotpluggable;
 	cpu->dev.offline = !cpu_online(num);
 	cpu->dev.of_node = of_get_cpu_node(num, NULL);
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-	cpu->dev.bus->uevent = arch_cpu_uevent;
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+	cpu->dev.bus->uevent = cpu_uevent;
 #endif
 	cpu->dev.groups = common_cpu_attr_groups;
 	if (cpu->hotpluggable)
@@ -330,8 +370,8 @@ struct device *get_cpu_device(unsigned cpu)
 }
 EXPORT_SYMBOL_GPL(get_cpu_device);
 
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-static DEVICE_ATTR(modalias, 0444, arch_print_cpu_modalias, NULL);
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
 #endif
 
 static struct attribute *cpu_root_attrs[] = {
@@ -344,7 +384,7 @@ static struct attribute *cpu_root_attrs[] = {
 	&cpu_attrs[2].attr.attr,
 	&dev_attr_kernel_max.attr,
 	&dev_attr_offline.attr,
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 	&dev_attr_modalias.attr,
 #endif
 	NULL
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 06051767393f..8a8d611f2021 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -52,6 +52,7 @@ static DEFINE_MUTEX(deferred_probe_mutex);
 static LIST_HEAD(deferred_probe_pending_list);
 static LIST_HEAD(deferred_probe_active_list);
 static struct workqueue_struct *deferred_wq;
+static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
 
 /**
  * deferred_probe_work_func() - Retry probing devices in the active list.
@@ -135,6 +136,17 @@ static bool driver_deferred_probe_enable = false;
  * This functions moves all devices from the pending list to the active
  * list and schedules the deferred probe workqueue to process them.  It
  * should be called anytime a driver is successfully bound to a device.
+ *
+ * Note, there is a race condition in multi-threaded probe. In the case where
+ * more than one device is probing at the same time, it is possible for one
+ * probe to complete successfully while another is about to defer. If the second
+ * depends on the first, then it will get put on the pending list after the
+ * trigger event has already occured and will be stuck there.
+ *
+ * The atomic 'deferred_trigger_count' is used to determine if a successful
+ * trigger has occurred in the midst of probing a driver. If the trigger count
+ * changes in the midst of a probe, then deferred processing should be triggered
+ * again.
  */
 static void driver_deferred_probe_trigger(void)
 {
@@ -147,6 +159,7 @@ static void driver_deferred_probe_trigger(void)
 	 * into the active list so they can be retried by the workqueue
 	 */
 	mutex_lock(&deferred_probe_mutex);
+	atomic_inc(&deferred_trigger_count);
 	list_splice_tail_init(&deferred_probe_pending_list,
 			      &deferred_probe_active_list);
 	mutex_unlock(&deferred_probe_mutex);
@@ -265,6 +278,7 @@ static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
 static int really_probe(struct device *dev, struct device_driver *drv)
 {
 	int ret = 0;
+	int local_trigger_count = atomic_read(&deferred_trigger_count);
 
 	atomic_inc(&probe_count);
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
@@ -310,6 +324,9 @@ probe_failed:
 		/* Driver requested deferred probing */
 		dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
 		driver_deferred_probe_add(dev);
+		/* Did a trigger occur while probing? Need to re-trigger if yes */
+		if (local_trigger_count != atomic_read(&deferred_trigger_count))
+			driver_deferred_probe_trigger();
 	} else if (ret != -ENODEV && ret != -ENXIO) {
 		/* driver matched but the probe failed */
 		printk(KERN_WARNING
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 165c2c299e57..d3bffa478eca 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -155,13 +155,23 @@ static int __init cma_activate_area(struct cma *cma)
 		base_pfn = pfn;
 		for (j = pageblock_nr_pages; j; --j, pfn++) {
 			WARN_ON_ONCE(!pfn_valid(pfn));
+			/*
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
+			 */
 			if (page_zone(pfn_to_page(pfn)) != zone)
-				return -EINVAL;
+				goto err;
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
 
 	return 0;
+
+err:
+	kfree(cma->bitmap);
+	return -EINVAL;
 }
 
 static struct cma cma_areas[MAX_CMA_AREAS];
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index c30df50e4440..2495ee577a64 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1081,6 +1081,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 	if (!firmware_p)
 		return -EINVAL;
 
+	if (!name || name[0] == '\0')
+		return -EINVAL;
+
 	ret = _request_firmware_prepare(&fw, name, device);
 	if (ret <= 0) /* error or already assigned */
 		goto out;
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index bc78848dd59a..9dbf4ef2b2a3 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -13,6 +13,7 @@
 #include <linux/string.h>
 #include <linux/platform_device.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
@@ -87,7 +88,16 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 		return -ENXIO;
 	return dev->archdata.irqs[num];
 #else
-	struct resource *r = platform_get_resource(dev, IORESOURCE_IRQ, num);
+	struct resource *r;
+	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) {
+		int ret;
+
+		ret = of_irq_get(dev->dev.of_node, num);
+		if (ret >= 0 || ret == -EPROBE_DEFER)
+			return ret;
+	}
+
+	r = platform_get_resource(dev, IORESOURCE_IRQ, num);
 
 	return r ? r->start : -ENXIO;
 #endif
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index bfb8955c406c..35081d42661e 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -9,6 +9,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
@@ -2177,3 +2178,291 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+/*
+ * Device Tree based PM domain providers.
+ *
+ * The code below implements generic device tree based PM domain providers that
+ * bind device tree nodes with generic PM domains registered in the system.
+ *
+ * Any driver that registers generic PM domains and needs to support binding of
+ * devices to these domains is supposed to register a PM domain provider, which
+ * maps a PM domain specifier retrieved from the device tree to a PM domain.
+ *
+ * Two simple mapping functions have been provided for convenience:
+ *  - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
+ *  - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by
+ *    index.
+ */
+
+/**
+ * struct of_genpd_provider - PM domain provider registration structure
+ * @link: Entry in global list of PM domain providers
+ * @node: Pointer to device tree node of PM domain provider
+ * @xlate: Provider-specific xlate callback mapping a set of specifier cells
+ *         into a PM domain.
+ * @data: context pointer to be passed into @xlate callback
+ */
+struct of_genpd_provider {
+	struct list_head link;
+	struct device_node *node;
+	genpd_xlate_t xlate;
+	void *data;
+};
+
+/* List of registered PM domain providers. */
+static LIST_HEAD(of_genpd_providers);
+/* Mutex to protect the list above. */
+static DEFINE_MUTEX(of_genpd_mutex);
+
+/**
+ * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct generic_pm_domain
+ *
+ * This is a generic xlate function that can be used to model PM domains that
+ * have their own device tree nodes. The private data of xlate function needs
+ * to be a valid pointer to struct generic_pm_domain.
+ */
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	if (genpdspec->args_count != 0)
+		return ERR_PTR(-EINVAL);
+	return data;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple);
+
+/**
+ * __of_genpd_xlate_onecell() - Xlate function using a single index.
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct genpd_onecell_data
+ *
+ * This is a generic xlate function that can be used to model simple PM domain
+ * controllers that have one device tree node and provide multiple PM domains.
+ * A single cell is used as an index into an array of PM domains specified in
+ * the genpd_onecell_data struct when registering the provider.
+ */
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	struct genpd_onecell_data *genpd_data = data;
+	unsigned int idx = genpdspec->args[0];
+
+	if (genpdspec->args_count != 1)
+		return ERR_PTR(-EINVAL);
+
+	if (idx >= genpd_data->num_domains) {
+		pr_err("%s: invalid domain index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!genpd_data->domains[idx])
+		return ERR_PTR(-ENOENT);
+
+	return genpd_data->domains[idx];
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell);
+
+/**
+ * __of_genpd_add_provider() - Register a PM domain provider for a node
+ * @np: Device node pointer associated with the PM domain provider.
+ * @xlate: Callback for decoding PM domain from phandle arguments.
+ * @data: Context pointer for @xlate callback.
+ */
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data)
+{
+	struct of_genpd_provider *cp;
+
+	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+	if (!cp)
+		return -ENOMEM;
+
+	cp->node = of_node_get(np);
+	cp->data = data;
+	cp->xlate = xlate;
+
+	mutex_lock(&of_genpd_mutex);
+	list_add(&cp->link, &of_genpd_providers);
+	mutex_unlock(&of_genpd_mutex);
+	pr_debug("Added domain provider from %s\n", np->full_name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
+
+/**
+ * of_genpd_del_provider() - Remove a previously registered PM domain provider
+ * @np: Device node pointer associated with the PM domain provider
+ */
+void of_genpd_del_provider(struct device_node *np)
+{
+	struct of_genpd_provider *cp;
+
+	mutex_lock(&of_genpd_mutex);
+	list_for_each_entry(cp, &of_genpd_providers, link) {
+		if (cp->node == np) {
+			list_del(&cp->link);
+			of_node_put(cp->node);
+			kfree(cp);
+			break;
+		}
+	}
+	mutex_unlock(&of_genpd_mutex);
+}
+EXPORT_SYMBOL_GPL(of_genpd_del_provider);
+
+/**
+ * of_genpd_get_from_provider() - Look-up PM domain
+ * @genpdspec: OF phandle args to use for look-up
+ *
+ * Looks for a PM domain provider under the node specified by @genpdspec and if
+ * found, uses xlate function of the provider to map phandle args to a PM
+ * domain.
+ *
+ * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
+ * on failure.
+ */
+static struct generic_pm_domain *of_genpd_get_from_provider(
+					struct of_phandle_args *genpdspec)
+{
+	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
+	struct of_genpd_provider *provider;
+
+	mutex_lock(&of_genpd_mutex);
+
+	/* Check if we have such a provider in our array */
+	list_for_each_entry(provider, &of_genpd_providers, link) {
+		if (provider->node == genpdspec->np)
+			genpd = provider->xlate(genpdspec, provider->data);
+		if (!IS_ERR(genpd))
+			break;
+	}
+
+	mutex_unlock(&of_genpd_mutex);
+
+	return genpd;
+}
+
+/**
+ * genpd_dev_pm_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Currently not used
+ *
+ * Try to locate a corresponding generic PM domain, which the device was
+ * attached to previously. If such is found, the device is detached from it.
+ */
+static void genpd_dev_pm_detach(struct device *dev, bool power_off)
+{
+	struct generic_pm_domain *pd = NULL, *gpd;
+	int ret = 0;
+
+	if (!dev->pm_domain)
+		return;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (&gpd->domain == dev->pm_domain) {
+			pd = gpd;
+			break;
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	if (!pd)
+		return;
+
+	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_remove_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to remove from PM domain %s: %d",
+			pd->name, ret);
+		return;
+	}
+
+	/* Check if PM domain can be powered off after removing this device. */
+	genpd_queue_power_off_work(pd);
+}
+
+/**
+ * genpd_dev_pm_attach - Attach a device to its PM domain using DT.
+ * @dev: Device to attach.
+ *
+ * Parse device's OF node to find a PM domain specifier. If such is found,
+ * attaches the device to retrieved pm_domain ops.
+ *
+ * Both generic and legacy Samsung-specific DT bindings are supported to keep
+ * backwards compatibility with existing DTBs.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int genpd_dev_pm_attach(struct device *dev)
+{
+	struct of_phandle_args pd_args;
+	struct generic_pm_domain *pd;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	if (dev->pm_domain)
+		return -EEXIST;
+
+	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
+					"#power-domain-cells", 0, &pd_args);
+	if (ret < 0) {
+		if (ret != -ENOENT)
+			return ret;
+
+		/*
+		 * Try legacy Samsung-specific bindings
+		 * (for backwards compatibility of DT ABI)
+		 */
+		pd_args.args_count = 0;
+		pd_args.np = of_parse_phandle(dev->of_node,
+						"samsung,power-domain", 0);
+		if (!pd_args.np)
+			return -ENOENT;
+	}
+
+	pd = of_genpd_get_from_provider(&pd_args);
+	if (IS_ERR(pd)) {
+		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
+			__func__, PTR_ERR(pd));
+		of_node_put(dev->of_node);
+		return PTR_ERR(pd);
+	}
+
+	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_add_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to add to PM domain %s: %d",
+			pd->name, ret);
+		of_node_put(dev->of_node);
+		return ret;
+	}
+
+	dev->pm_domain->detach = genpd_dev_pm_detach;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+#endif
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index fa4187418440..08d99ef60b70 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -735,11 +735,9 @@ int of_init_opp_table(struct device *dev)
 		unsigned long freq = be32_to_cpup(val++) * 1000;
 		unsigned long volt = be32_to_cpup(val++);
 
-		if (dev_pm_opp_add(dev, freq, volt)) {
+		if (dev_pm_opp_add(dev, freq, volt))
 			dev_warn(dev, "%s: Failed to add OPP %ld\n",
 				 __func__, freq);
-			continue;
-		}
 		nr -= 2;
 	}
 
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index d4dd77134814..154e7a8c0a04 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -701,7 +701,7 @@ int regcache_sync_block(struct regmap *map, void *block,
 			unsigned int block_base, unsigned int start,
 			unsigned int end)
 {
-	if (regmap_can_raw_write(map))
+	if (regmap_can_raw_write(map) && !map->use_single_rw)
 		return regcache_sync_block_raw(map, block, cache_present,
 					       block_base, start, end);
 	else
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index c5471cd6ebb7..d39fd610aa3b 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -473,6 +473,7 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
 {
 	struct rb_node *next;
 	struct regmap_range_node *range_node;
+	const char *devname = "dummy";
 
 	/* If we don't have the debugfs root yet, postpone init */
 	if (!regmap_debugfs_root) {
@@ -491,12 +492,15 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
 	INIT_LIST_HEAD(&map->debugfs_off_cache);
 	mutex_init(&map->cache_lock);
 
+	if (map->dev)
+		devname = dev_name(map->dev);
+
 	if (name) {
 		map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
-					      dev_name(map->dev), name);
+					      devname, name);
 		name = map->debugfs_name;
 	} else {
-		name = dev_name(map->dev);
+		name = devname;
 	}
 
 	map->debugfs = debugfs_create_dir(name, regmap_debugfs_root);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 6a19515f8a45..2f9a3d8ecbbf 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -105,7 +105,7 @@ bool regmap_readable(struct regmap *map, unsigned int reg)
 
 bool regmap_volatile(struct regmap *map, unsigned int reg)
 {
-	if (!regmap_readable(map, reg))
+	if (!map->format.format_write && !regmap_readable(map, reg))
 		return false;
 
 	if (map->volatile_reg)
@@ -1308,7 +1308,7 @@ int _regmap_write(struct regmap *map, unsigned int reg,
 	}
 
 #ifdef LOG_DEVICE
-	if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+	if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
 		dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
@@ -1557,6 +1557,11 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 	} else {
 		void *wval;
 
+		if (!val_count) {
+			ret = -EINVAL;
+			goto out;
+		}
+
 		wval = kmemdup(val, val_count * val_bytes, GFP_KERNEL);
 		if (!wval) {
 			ret = -ENOMEM;
@@ -1739,7 +1744,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg,
 	ret = map->reg_read(context, reg, val);
 	if (ret == 0) {
 #ifdef LOG_DEVICE
-		if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+		if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
 			dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 94ffee378f10..37a5661ca5f9 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -40,8 +40,7 @@
 static ssize_t show_##name(struct device *dev,			\
 		struct device_attribute *attr, char *buf)	\
 {								\
-	unsigned int cpu = dev->id;				\
-	return sprintf(buf, "%d\n", topology_##name(cpu));	\
+	return sprintf(buf, "%d\n", topology_##name(dev->id));	\
 }
 
 #if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c
index 89c497c630b4..04a14e0f8878 100644
--- a/drivers/block/drbd/drbd_interval.c
+++ b/drivers/block/drbd/drbd_interval.c
@@ -79,6 +79,7 @@ bool
 drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 {
 	struct rb_node **new = &root->rb_node, *parent = NULL;
+	sector_t this_end = this->sector + (this->size >> 9);
 
 	BUG_ON(!IS_ALIGNED(this->size, 512));
 
@@ -87,6 +88,8 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 			rb_entry(*new, struct drbd_interval, rb);
 
 		parent = *new;
+		if (here->end < this_end)
+			here->end = this_end;
 		if (this->sector < here->sector)
 			new = &(*new)->rb_left;
 		else if (this->sector > here->sector)
@@ -99,6 +102,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 			return false;
 	}
 
+	this->end = this_end;
 	rb_link_node(&this->rb, parent, new);
 	rb_insert_augmented(&this->rb, root, &augment_callbacks);
 	return true;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index c706d50a8b06..8c16c2f97026 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -525,6 +525,12 @@ void conn_try_outdate_peer_async(struct drbd_tconn *tconn)
 	struct task_struct *opa;
 
 	kref_get(&tconn->kref);
+	/* We may just have force_sig()'ed this thread
+	 * to get it out of some blocking network function.
+	 * Clear signals; otherwise kthread_run(), which internally uses
+	 * wait_on_completion_killable(), will mistake our pending signal
+	 * for a new fatal signal and fail. */
+	flush_signals(current);
 	opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h");
 	if (IS_ERR(opa)) {
 		conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n");
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 2023043ce7c0..dab515cd77bf 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3053,7 +3053,10 @@ static int raw_cmd_copyout(int cmd, void __user *param,
 	int ret;
 
 	while (ptr) {
-		ret = copy_to_user(param, ptr, sizeof(*ptr));
+		struct floppy_raw_cmd cmd = *ptr;
+		cmd.next = NULL;
+		cmd.kernel_data = NULL;
+		ret = copy_to_user(param, &cmd, sizeof(cmd));
 		if (ret)
 			return -EFAULT;
 		param += sizeof(struct floppy_raw_cmd);
@@ -3107,10 +3110,11 @@ loop:
 		return -ENOMEM;
 	*rcmd = ptr;
 	ret = copy_from_user(ptr, param, sizeof(*ptr));
-	if (ret)
-		return -EFAULT;
 	ptr->next = NULL;
 	ptr->buffer_length = 0;
+	ptr->kernel_data = NULL;
+	if (ret)
+		return -EFAULT;
 	param += sizeof(struct floppy_raw_cmd);
 	if (ptr->cmd_count > 33)
 			/* the command may now also take up the space
@@ -3126,7 +3130,6 @@ loop:
 	for (i = 0; i < 16; i++)
 		ptr->reply[i] = 0;
 	ptr->resultcode = 0;
-	ptr->kernel_data = NULL;
 
 	if (ptr->flags & (FD_RAW_READ | FD_RAW_WRITE)) {
 		if (ptr->length <= 0)
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index d777bb7cea93..4e763b0dbbfc 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -252,38 +252,45 @@ static void mtip_async_complete(struct mtip_port *port,
 				void *data,
 				int status)
 {
-	struct mtip_cmd *command;
+	struct mtip_cmd *cmd;
 	struct driver_data *dd = data;
-	int cb_status = status ? -EIO : 0;
+	int unaligned, cb_status = status ? -EIO : 0;
+	void (*func)(void *, int);
 
 	if (unlikely(!dd) || unlikely(!port))
 		return;
 
-	command = &port->commands[tag];
+	cmd = &port->commands[tag];
 
 	if (unlikely(status == PORT_IRQ_TF_ERR)) {
 		dev_warn(&port->dd->pdev->dev,
 			"Command tag %d failed due to TFE\n", tag);
 	}
 
+	/* Clear the active flag */
+	atomic_set(&port->commands[tag].active, 0);
+
 	/* Upper layer callback */
-	if (likely(command->async_callback))
-		command->async_callback(command->async_data, cb_status);
+	func = cmd->async_callback;
+	if (likely(func && cmpxchg(&cmd->async_callback, func, 0) == func)) {
 
-	command->async_callback = NULL;
-	command->comp_func = NULL;
+		/* Unmap the DMA scatter list entries */
+		dma_unmap_sg(&dd->pdev->dev,
+			cmd->sg,
+			cmd->scatter_ents,
+			cmd->direction);
 
-	/* Unmap the DMA scatter list entries */
-	dma_unmap_sg(&dd->pdev->dev,
-		command->sg,
-		command->scatter_ents,
-		command->direction);
+		func(cmd->async_data, cb_status);
+		unaligned = cmd->unaligned;
 
-	/* Clear the allocated and active bits for the command */
-	atomic_set(&port->commands[tag].active, 0);
-	release_slot(port, tag);
+		/* Clear the allocated bit for the command */
+		release_slot(port, tag);
 
-	up(&port->cmd_slot);
+		if (unlikely(unaligned))
+			up(&port->cmd_slot_unal);
+		else
+			up(&port->cmd_slot);
+	}
 }
 
 /*
@@ -660,11 +667,12 @@ static void mtip_timeout_function(unsigned long int data)
 {
 	struct mtip_port *port = (struct mtip_port *) data;
 	struct host_to_dev_fis *fis;
-	struct mtip_cmd *command;
-	int tag, cmdto_cnt = 0;
+	struct mtip_cmd *cmd;
+	int unaligned, tag, cmdto_cnt = 0;
 	unsigned int bit, group;
 	unsigned int num_command_slots;
 	unsigned long to, tagaccum[SLOTBITS_IN_LONGS];
+	void (*func)(void *, int);
 
 	if (unlikely(!port))
 		return;
@@ -694,8 +702,8 @@ static void mtip_timeout_function(unsigned long int data)
 			group = tag >> 5;
 			bit = tag & 0x1F;
 
-			command = &port->commands[tag];
-			fis = (struct host_to_dev_fis *) command->command;
+			cmd = &port->commands[tag];
+			fis = (struct host_to_dev_fis *) cmd->command;
 
 			set_bit(tag, tagaccum);
 			cmdto_cnt++;
@@ -709,27 +717,30 @@ static void mtip_timeout_function(unsigned long int data)
 			 */
 			writel(1 << bit, port->completed[group]);
 
-			/* Call the async completion callback. */
-			if (likely(command->async_callback))
-				command->async_callback(command->async_data,
-							 -EIO);
-			command->async_callback = NULL;
-			command->comp_func = NULL;
+			/* Clear the active flag for the command */
+			atomic_set(&port->commands[tag].active, 0);
 
-			/* Unmap the DMA scatter list entries */
-			dma_unmap_sg(&port->dd->pdev->dev,
-					command->sg,
-					command->scatter_ents,
-					command->direction);
+			func = cmd->async_callback;
+			if (func &&
+			    cmpxchg(&cmd->async_callback, func, 0) == func) {
 
-			/*
-			 * Clear the allocated bit and active tag for the
-			 * command.
-			 */
-			atomic_set(&port->commands[tag].active, 0);
-			release_slot(port, tag);
+				/* Unmap the DMA scatter list entries */
+				dma_unmap_sg(&port->dd->pdev->dev,
+						cmd->sg,
+						cmd->scatter_ents,
+						cmd->direction);
 
-			up(&port->cmd_slot);
+				func(cmd->async_data, -EIO);
+				unaligned = cmd->unaligned;
+
+				/* Clear the allocated bit for the command. */
+				release_slot(port, tag);
+
+				if (unaligned)
+					up(&port->cmd_slot_unal);
+				else
+					up(&port->cmd_slot);
+			}
 		}
 	}
 
@@ -1518,6 +1529,37 @@ static inline void ata_swap_string(u16 *buf, unsigned int len)
 		be16_to_cpus(&buf[i]);
 }
 
+static void mtip_set_timeout(struct driver_data *dd,
+					struct host_to_dev_fis *fis,
+					unsigned int *timeout, u8 erasemode)
+{
+	switch (fis->command) {
+	case ATA_CMD_DOWNLOAD_MICRO:
+		*timeout = 120000; /* 2 minutes */
+		break;
+	case ATA_CMD_SEC_ERASE_UNIT:
+	case 0xFC:
+		if (erasemode)
+			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
+		else
+			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
+		break;
+	case ATA_CMD_STANDBYNOW1:
+		*timeout = 120000;  /* 2 minutes */
+		break;
+	case 0xF7:
+	case 0xFA:
+		*timeout = 60000;  /* 60 seconds */
+		break;
+	case ATA_CMD_SMART:
+		*timeout = 15000;  /* 15 seconds */
+		break;
+	default:
+		*timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
+		break;
+	}
+}
+
 /*
  * Request the device identity information.
  *
@@ -1633,6 +1675,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	int rv;
 	struct host_to_dev_fis	fis;
 	unsigned long start;
+	unsigned int timeout;
 
 	/* Build the FIS. */
 	memset(&fis, 0, sizeof(struct host_to_dev_fis));
@@ -1640,6 +1683,8 @@ static int mtip_standby_immediate(struct mtip_port *port)
 	fis.opts	= 1 << 7;
 	fis.command	= ATA_CMD_STANDBYNOW1;
 
+	mtip_set_timeout(port->dd, &fis, &timeout, 0);
+
 	start = jiffies;
 	rv = mtip_exec_internal_command(port,
 					&fis,
@@ -1648,7 +1693,7 @@ static int mtip_standby_immediate(struct mtip_port *port)
 					0,
 					0,
 					GFP_ATOMIC,
-					15000);
+					timeout);
 	dbg_printk(MTIP_DRV_NAME "Time taken to complete standby cmd: %d ms\n",
 			jiffies_to_msecs(jiffies - start));
 	if (rv)
@@ -2191,36 +2236,6 @@ static unsigned int implicit_sector(unsigned char command,
 	}
 	return rv;
 }
-static void mtip_set_timeout(struct driver_data *dd,
-					struct host_to_dev_fis *fis,
-					unsigned int *timeout, u8 erasemode)
-{
-	switch (fis->command) {
-	case ATA_CMD_DOWNLOAD_MICRO:
-		*timeout = 120000; /* 2 minutes */
-		break;
-	case ATA_CMD_SEC_ERASE_UNIT:
-	case 0xFC:
-		if (erasemode)
-			*timeout = ((*(dd->port->identify + 90) * 2) * 60000);
-		else
-			*timeout = ((*(dd->port->identify + 89) * 2) * 60000);
-		break;
-	case ATA_CMD_STANDBYNOW1:
-		*timeout = 120000;  /* 2 minutes */
-		break;
-	case 0xF7:
-	case 0xFA:
-		*timeout = 60000;  /* 60 seconds */
-		break;
-	case ATA_CMD_SMART:
-		*timeout = 15000;  /* 15 seconds */
-		break;
-	default:
-		*timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
-		break;
-	}
-}
 
 /*
  * Executes a taskfile
@@ -4213,6 +4228,7 @@ skip_create_disk:
 	blk_queue_max_hw_sectors(dd->queue, 0xffff);
 	blk_queue_max_segment_size(dd->queue, 0x400000);
 	blk_queue_io_min(dd->queue, 4096);
+	blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask);
 
 	/*
 	 * write back cache is not supported in the device. FUA depends on
@@ -4467,6 +4483,57 @@ static DEFINE_HANDLER(5);
 static DEFINE_HANDLER(6);
 static DEFINE_HANDLER(7);
 
+static void mtip_disable_link_opts(struct driver_data *dd, struct pci_dev *pdev)
+{
+	int pos;
+	unsigned short pcie_dev_ctrl;
+
+	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+	if (pos) {
+		pci_read_config_word(pdev,
+			pos + PCI_EXP_DEVCTL,
+			&pcie_dev_ctrl);
+		if (pcie_dev_ctrl & (1 << 11) ||
+		    pcie_dev_ctrl & (1 << 4)) {
+			dev_info(&dd->pdev->dev,
+				"Disabling ERO/No-Snoop on bridge device %04x:%04x\n",
+					pdev->vendor, pdev->device);
+			pcie_dev_ctrl &= ~(PCI_EXP_DEVCTL_NOSNOOP_EN |
+						PCI_EXP_DEVCTL_RELAX_EN);
+			pci_write_config_word(pdev,
+				pos + PCI_EXP_DEVCTL,
+				pcie_dev_ctrl);
+		}
+	}
+}
+
+static void mtip_fix_ero_nosnoop(struct driver_data *dd, struct pci_dev *pdev)
+{
+	/*
+	 * This workaround is specific to AMD/ATI chipset with a PCI upstream
+	 * device with device id 0x5aXX
+	 */
+	if (pdev->bus && pdev->bus->self) {
+		if (pdev->bus->self->vendor == PCI_VENDOR_ID_ATI &&
+		    ((pdev->bus->self->device & 0xff00) == 0x5a00)) {
+			mtip_disable_link_opts(dd, pdev->bus->self);
+		} else {
+			/* Check further up the topology */
+			struct pci_dev *parent_dev = pdev->bus->self;
+			if (parent_dev->bus &&
+				parent_dev->bus->parent &&
+				parent_dev->bus->parent->self &&
+				parent_dev->bus->parent->self->vendor ==
+					 PCI_VENDOR_ID_ATI &&
+				(parent_dev->bus->parent->self->device &
+					0xff00) == 0x5a00) {
+				mtip_disable_link_opts(dd,
+					parent_dev->bus->parent->self);
+			}
+		}
+	}
+}
+
 /*
  * Called for each supported PCI device detected.
  *
@@ -4618,6 +4685,8 @@ static int mtip_pci_probe(struct pci_dev *pdev,
 		goto block_initialize_err;
 	}
 
+	mtip_fix_ero_nosnoop(dd, pdev);
+
 	/* Initialize the block layer. */
 	rv = mtip_block_initialize(dd);
 	if (rv < 0) {
@@ -4921,13 +4990,13 @@ static int __init mtip_init(void)
  */
 static void __exit mtip_exit(void)
 {
-	debugfs_remove_recursive(dfs_parent);
-
 	/* Release the allocated major block device number. */
 	unregister_blkdev(mtip_major, MTIP_DRV_NAME);
 
 	/* Unregister the PCI driver. */
 	pci_unregister_driver(&mtip_pci_driver);
+
+	debugfs_remove_recursive(dfs_parent);
 }
 
 MODULE_AUTHOR("Micron Technology, Inc");
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 54174cb32feb..ffb955e7ccb9 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -92,7 +92,7 @@
 
 /* Driver name and version strings */
 #define MTIP_DRV_NAME		"mtip32xx"
-#define MTIP_DRV_VERSION	"1.3.0"
+#define MTIP_DRV_VERSION	"1.3.1"
 
 /* Maximum number of minor device numbers per device. */
 #define MTIP_MAX_MINORS		16
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 34898d53395b..255ca232ecc7 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1366,6 +1366,14 @@ static bool obj_request_exists_test(struct rbd_obj_request *obj_request)
 	return test_bit(OBJ_REQ_EXISTS, &obj_request->flags) != 0;
 }
 
+static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
+{
+	struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+
+	return obj_request->img_offset <
+	    round_up(rbd_dev->parent_overlap, rbd_obj_bytes(&rbd_dev->header));
+}
+
 static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
 {
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
@@ -1382,6 +1390,13 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request)
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
+static void rbd_img_request_get(struct rbd_img_request *img_request)
+{
+	dout("%s: img %p (was %d)\n", __func__, img_request,
+	     atomic_read(&img_request->kref.refcount));
+	kref_get(&img_request->kref);
+}
+
 static bool img_request_child_test(struct rbd_img_request *img_request);
 static void rbd_parent_request_destroy(struct kref *kref);
 static void rbd_img_request_destroy(struct kref *kref);
@@ -2128,6 +2143,7 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request)
 	img_request->next_completion = which;
 out:
 	spin_unlock_irq(&img_request->completion_lock);
+	rbd_img_request_put(img_request);
 
 	if (!more)
 		rbd_img_request_complete(img_request);
@@ -2225,6 +2241,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 			goto out_partial;
 		obj_request->osd_req = osd_req;
 		obj_request->callback = rbd_img_obj_callback;
+		rbd_img_request_get(img_request);
 
 		osd_req_op_extent_init(osd_req, 0, opcode, offset, length,
 						0, 0);
@@ -2253,7 +2270,7 @@ out_partial:
 	rbd_obj_request_put(obj_request);
 out_unwind:
 	for_each_obj_request_safe(img_request, obj_request, next_obj_request)
-		rbd_obj_request_put(obj_request);
+		rbd_img_obj_request_del(img_request, obj_request);
 
 	return -ENOMEM;
 }
@@ -2647,7 +2664,7 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
 	 */
 	if (!img_request_write_test(img_request) ||
 		!img_request_layered_test(img_request) ||
-		rbd_dev->parent_overlap <= obj_request->img_offset ||
+		!obj_request_overlaps_parent(obj_request) ||
 		((known = obj_request_known_test(obj_request)) &&
 			obj_request_exists_test(obj_request))) {
 
@@ -3200,7 +3217,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
 	page_count = (u32) calc_pages_for(offset, length);
 	pages = ceph_alloc_page_vector(page_count, GFP_KERNEL);
 	if (IS_ERR(pages))
-		ret = PTR_ERR(pages);
+		return PTR_ERR(pages);
 
 	ret = -ENOMEM;
 	obj_request = rbd_obj_request_create(object_name, offset, length,
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5814deb6963d..0ebadf93b6c5 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
 #include <linux/genhd.h>
+#include <linux/cdrom.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -22,8 +23,8 @@
 
 #define DRV_MODULE_NAME		"sunvdc"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"1.0"
-#define DRV_MODULE_RELDATE	"June 25, 2007"
+#define DRV_MODULE_VERSION	"1.1"
+#define DRV_MODULE_RELDATE	"February 13, 2013"
 
 static char version[] =
 	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
@@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_MODULE_VERSION);
 
-#define VDC_TX_RING_SIZE	256
+#define VDC_TX_RING_SIZE	512
 
 #define WAITING_FOR_LINK_UP	0x01
 #define WAITING_FOR_TX_SPACE	0x02
@@ -65,11 +66,9 @@ struct vdc_port {
 	u64			operations;
 	u32			vdisk_size;
 	u8			vdisk_type;
+	u8			vdisk_mtype;
 
 	char			disk_name[32];
-
-	struct vio_disk_geom	geom;
-	struct vio_disk_vtoc	label;
 };
 
 static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
@@ -79,9 +78,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
 
 /* Ordered from largest major to lowest */
 static struct vio_version vdc_versions[] = {
+	{ .major = 1, .minor = 1 },
 	{ .major = 1, .minor = 0 },
 };
 
+static inline int vdc_version_supported(struct vdc_port *port,
+					u16 major, u16 minor)
+{
+	return port->vio.ver.major == major && port->vio.ver.minor >= minor;
+}
+
 #define VDCBLK_NAME	"vdisk"
 static int vdc_major;
 #define PARTITION_SHIFT	3
@@ -94,18 +100,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr)
 static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	struct vdc_port *port = disk->private_data;
+	sector_t nsect = get_capacity(disk);
+	sector_t cylinders = nsect;
 
-	geo->heads = (u8) port->geom.num_hd;
-	geo->sectors = (u8) port->geom.num_sec;
-	geo->cylinders = port->geom.num_cyl;
+	geo->heads = 0xff;
+	geo->sectors = 0x3f;
+	sector_div(cylinders, geo->heads * geo->sectors);
+	geo->cylinders = cylinders;
+	if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect)
+		geo->cylinders = 0xffff;
 
 	return 0;
 }
 
+/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev
+ * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
+ * Needed to be able to install inside an ldom from an iso image.
+ */
+static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+		     unsigned command, unsigned long argument)
+{
+	int i;
+	struct gendisk *disk;
+
+	switch (command) {
+	case CDROMMULTISESSION:
+		pr_debug(PFX "Multisession CDs not supported\n");
+		for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+			if (put_user(0, (char __user *)(argument + i)))
+				return -EFAULT;
+		return 0;
+
+	case CDROM_GET_CAPABILITY:
+		disk = bdev->bd_disk;
+
+		if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+			return 0;
+		return -EINVAL;
+
+	default:
+		pr_debug(PFX "ioctl %08x not supported\n", command);
+		return -EINVAL;
+	}
+}
+
 static const struct block_device_operations vdc_fops = {
 	.owner		= THIS_MODULE,
 	.getgeo		= vdc_getgeo,
+	.ioctl		= vdc_ioctl,
 };
 
 static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
@@ -165,9 +207,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 	struct vio_disk_attr_info *pkt = arg;
 
 	viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] "
-	       "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
+	       "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
 	       pkt->tag.stype, pkt->operations,
-	       pkt->vdisk_size, pkt->vdisk_type,
+	       pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype,
 	       pkt->xfer_mode, pkt->vdisk_block_size,
 	       pkt->max_xfer_size);
 
@@ -192,8 +234,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 		}
 
 		port->operations = pkt->operations;
-		port->vdisk_size = pkt->vdisk_size;
 		port->vdisk_type = pkt->vdisk_type;
+		if (vdc_version_supported(port, 1, 1)) {
+			port->vdisk_size = pkt->vdisk_size;
+			port->vdisk_mtype = pkt->vdisk_mtype;
+		}
 		if (pkt->max_xfer_size < port->max_xfer_size)
 			port->max_xfer_size = pkt->max_xfer_size;
 		port->vdisk_block_size = pkt->vdisk_block_size;
@@ -236,7 +281,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 
 	__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
 
-	if (blk_queue_stopped(port->disk->queue))
+	/* restart blk queue when ring is half emptied */
+	if (blk_queue_stopped(port->disk->queue) &&
+	    vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50)
 		blk_start_queue(port->disk->queue);
 }
 
@@ -388,12 +435,6 @@ static int __send_request(struct request *req)
 	for (i = 0; i < nsg; i++)
 		len += sg[i].length;
 
-	if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
-		blk_stop_queue(port->disk->queue);
-		err = -ENOMEM;
-		goto out;
-	}
-
 	desc = vio_dring_cur(dr);
 
 	err = ldc_map_sg(port->vio.lp, sg, nsg,
@@ -433,21 +474,32 @@ static int __send_request(struct request *req)
 		port->req_id++;
 		dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
 	}
-out:
 
 	return err;
 }
 
-static void do_vdc_request(struct request_queue *q)
+static void do_vdc_request(struct request_queue *rq)
 {
-	while (1) {
-		struct request *req = blk_fetch_request(q);
+	struct request *req;
 
-		if (!req)
-			break;
+	while ((req = blk_peek_request(rq)) != NULL) {
+		struct vdc_port *port;
+		struct vio_dring_state *dr;
 
-		if (__send_request(req) < 0)
-			__blk_end_request_all(req, -EIO);
+		port = req->rq_disk->private_data;
+		dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+		if (unlikely(vdc_tx_dring_avail(dr) < 1))
+			goto wait;
+
+		blk_start_request(req);
+
+		if (__send_request(req) < 0) {
+			blk_requeue_request(rq, req);
+wait:
+			/* Avoid pointless unplugs. */
+			blk_stop_queue(rq);
+			break;
+		}
 	}
 }
 
@@ -656,25 +708,27 @@ static int probe_disk(struct vdc_port *port)
 	if (comp.err)
 		return comp.err;
 
-	err = generic_request(port, VD_OP_GET_VTOC,
-			      &port->label, sizeof(port->label));
-	if (err < 0) {
-		printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err);
-		return err;
-	}
-
-	err = generic_request(port, VD_OP_GET_DISKGEOM,
-			      &port->geom, sizeof(port->geom));
-	if (err < 0) {
-		printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
-		       "error %d\n", err);
-		return err;
+	if (vdc_version_supported(port, 1, 1)) {
+		/* vdisk_size should be set during the handshake, if it wasn't
+		 * then the underlying disk is reserved by another system
+		 */
+		if (port->vdisk_size == -1)
+			return -ENODEV;
+	} else {
+		struct vio_disk_geom geom;
+
+		err = generic_request(port, VD_OP_GET_DISKGEOM,
+				      &geom, sizeof(geom));
+		if (err < 0) {
+			printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+			       "error %d\n", err);
+			return err;
+		}
+		port->vdisk_size = ((u64)geom.num_cyl *
+				    (u64)geom.num_hd *
+				    (u64)geom.num_sec);
 	}
 
-	port->vdisk_size = ((u64)port->geom.num_cyl *
-			    (u64)port->geom.num_hd *
-			    (u64)port->geom.num_sec);
-
 	q = blk_init_queue(do_vdc_request, &port->vio.lock);
 	if (!q) {
 		printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
@@ -691,6 +745,10 @@ static int probe_disk(struct vdc_port *port)
 
 	port->disk = g;
 
+	/* Each segment in a request is up to an aligned page in size. */
+	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
+	blk_queue_max_segment_size(q, PAGE_SIZE);
+
 	blk_queue_max_segments(q, port->ring_cookies);
 	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
@@ -704,9 +762,32 @@ static int probe_disk(struct vdc_port *port)
 
 	set_capacity(g, port->vdisk_size);
 
-	printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+	if (vdc_version_supported(port, 1, 1)) {
+		switch (port->vdisk_mtype) {
+		case VD_MEDIA_TYPE_CD:
+			pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_DVD:
+			pr_info(PFX "Virtual DVD %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_FIXED:
+			pr_info(PFX "Virtual Hard disk %s\n", port->disk_name);
+			break;
+		}
+	}
+
+	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
-	       port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
+	       port->vio.ver.major, port->vio.ver.minor);
 
 	add_disk(g);
 
@@ -765,6 +846,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	else
 		snprintf(port->disk_name, sizeof(port->disk_name),
 			 VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26));
+	port->vdisk_size = -1;
 
 	err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
 			      vdc_versions, ARRAY_SIZE(vdc_versions),
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index b1cb3f4c4db4..6c911c86fb5a 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -144,11 +144,11 @@ static void virtblk_done(struct virtqueue *vq)
 		if (unlikely(virtqueue_is_broken(vq)))
 			break;
 	} while (!virtqueue_enable_cb(vq));
-	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 
 	/* In case queue is stopped waiting for more buffers. */
 	if (req_done)
 		blk_mq_start_stopped_hw_queues(vblk->disk->queue);
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 }
 
 static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
@@ -200,8 +200,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 	spin_lock_irqsave(&vblk->vq_lock, flags);
 	if (__virtblk_add_req(vblk->vq, vbr, vbr->sg, num) < 0) {
 		virtqueue_kick(vblk->vq);
-		spin_unlock_irqrestore(&vblk->vq_lock, flags);
 		blk_mq_stop_hw_queue(hctx);
+		spin_unlock_irqrestore(&vblk->vq_lock, flags);
 		return BLK_MQ_RQ_QUEUE_BUSY;
 	}
 
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 64c60edcdfbc..63fc7f06a014 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -763,6 +763,7 @@ again:
 			BUG_ON(new_map_idx >= segs_to_map);
 			if (unlikely(map[new_map_idx].status != 0)) {
 				pr_debug(DRV_PFX "invalid buffer -- could not remap it\n");
+				put_free_pages(blkif, &pages[seg_idx]->page, 1);
 				pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE;
 				ret |= 1;
 				goto next;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 51c557cfd92b..d8ddb8e2adc1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -447,7 +447,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	}
 
 	if (page_zero_filled(uncmem)) {
-		kunmap_atomic(user_mem);
+		if (user_mem)
+			kunmap_atomic(user_mem);
 		/* Free memory associated with this sector now. */
 		write_lock(&zram->meta->tb_lock);
 		zram_free_page(zram, index);
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index 106d1d8e16ad..b11949c5b029 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -82,6 +82,7 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x04CA, 0x3004) },
 	{ USB_DEVICE(0x04CA, 0x3005) },
 	{ USB_DEVICE(0x04CA, 0x3006) },
+	{ USB_DEVICE(0x04CA, 0x3007) },
 	{ USB_DEVICE(0x04CA, 0x3008) },
 	{ USB_DEVICE(0x04CA, 0x300b) },
 	{ USB_DEVICE(0x13d3, 0x3362) },
@@ -127,6 +128,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h
index 7399303d7d99..9e81a3d01d2b 100644
--- a/drivers/bluetooth/btmrvl_drv.h
+++ b/drivers/bluetooth/btmrvl_drv.h
@@ -66,6 +66,7 @@ struct btmrvl_adapter {
 	u8 hs_state;
 	u8 wakeup_tries;
 	wait_queue_head_t cmd_wait_q;
+	wait_queue_head_t event_hs_wait_q;
 	u8 cmd_complete;
 	bool is_suspended;
 };
diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c
index 1e0320af00c6..49d20989b45a 100644
--- a/drivers/bluetooth/btmrvl_main.c
+++ b/drivers/bluetooth/btmrvl_main.c
@@ -112,6 +112,7 @@ int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb)
 			adapter->hs_state = HS_ACTIVATED;
 			if (adapter->psmode)
 				adapter->ps_state = PS_SLEEP;
+			wake_up_interruptible(&adapter->event_hs_wait_q);
 			BT_DBG("HS ACTIVATED!");
 		} else {
 			BT_DBG("HS Enable failed");
@@ -251,11 +252,31 @@ EXPORT_SYMBOL_GPL(btmrvl_enable_ps);
 
 int btmrvl_enable_hs(struct btmrvl_private *priv)
 {
+	struct btmrvl_adapter *adapter = priv->adapter;
 	int ret;
 
 	ret = btmrvl_send_sync_cmd(priv, BT_CMD_HOST_SLEEP_ENABLE, NULL, 0);
-	if (ret)
+	if (ret) {
 		BT_ERR("Host sleep enable command failed\n");
+		return ret;
+	}
+
+	ret = wait_event_interruptible_timeout(adapter->event_hs_wait_q,
+					       adapter->hs_state,
+			msecs_to_jiffies(WAIT_UNTIL_HS_STATE_CHANGED));
+	if (ret < 0) {
+		BT_ERR("event_hs_wait_q terminated (%d): %d,%d,%d",
+		       ret, adapter->hs_state, adapter->ps_state,
+		       adapter->wakeup_tries);
+	} else if (!ret) {
+		BT_ERR("hs_enable timeout: %d,%d,%d", adapter->hs_state,
+		       adapter->ps_state, adapter->wakeup_tries);
+		ret = -ETIMEDOUT;
+	} else {
+		BT_DBG("host sleep enabled: %d,%d,%d", adapter->hs_state,
+		       adapter->ps_state, adapter->wakeup_tries);
+		ret = 0;
+	}
 
 	return ret;
 }
@@ -341,6 +362,7 @@ static void btmrvl_init_adapter(struct btmrvl_private *priv)
 	priv->adapter->ps_state = PS_AWAKE;
 
 	init_waitqueue_head(&priv->adapter->cmd_wait_q);
+	init_waitqueue_head(&priv->adapter->event_hs_wait_q);
 }
 
 static void btmrvl_free_adapter(struct btmrvl_private *priv)
@@ -648,6 +670,7 @@ int btmrvl_remove_card(struct btmrvl_private *priv)
 	hdev = priv->btmrvl_dev.hcidev;
 
 	wake_up_interruptible(&priv->adapter->cmd_wait_q);
+	wake_up_interruptible(&priv->adapter->event_hs_wait_q);
 
 	kthread_stop(priv->main_thread.task);
 
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index baeaaed299e4..e00c3f84a4cf 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -149,6 +149,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
@@ -308,6 +309,9 @@ static void btusb_intr_complete(struct urb *urb)
 			BT_ERR("%s corrupted event packet", hdev->name);
 			hdev->stat.err_rx++;
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_INTR_RUNNING, &data->flags))
@@ -396,6 +400,9 @@ static void btusb_bulk_complete(struct urb *urb)
 			BT_ERR("%s corrupted ACL packet", hdev->name);
 			hdev->stat.err_rx++;
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_BULK_RUNNING, &data->flags))
@@ -490,6 +497,9 @@ static void btusb_isoc_complete(struct urb *urb)
 				hdev->stat.err_rx++;
 			}
 		}
+	} else if (urb->status == -ENOENT) {
+		/* Avoid suspend failed when usb_kill_urb */
+		return;
 	}
 
 	if (!test_bit(BTUSB_ISOC_RUNNING, &data->flags))
@@ -1478,10 +1488,8 @@ static int btusb_probe(struct usb_interface *intf,
 	if (id->driver_info & BTUSB_BCM92035)
 		hdev->setup = btusb_setup_bcm92035;
 
-	if (id->driver_info & BTUSB_INTEL) {
-		usb_enable_autosuspend(data->udev);
+	if (id->driver_info & BTUSB_INTEL)
 		hdev->setup = btusb_setup_intel;
-	}
 
 	/* Interface numbers are hardcoded in the specification */
 	data->isoc = usb_ifnum_to_if(data->udev, 1);
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index f6f497450560..56519927479f 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -237,7 +237,7 @@ static void h5_pkt_cull(struct h5 *h5)
 			break;
 
 		to_remove--;
-		seq = (seq - 1) % 8;
+		seq = (seq - 1) & 0x07;
 	}
 
 	if (seq != h5->rx_ack)
@@ -406,6 +406,7 @@ static int h5_rx_3wire_hdr(struct hci_uart *hu, unsigned char c)
 	    H5_HDR_PKT_TYPE(hdr) != HCI_3WIRE_LINK_PKT) {
 		BT_ERR("Non-link packet received in non-active state");
 		h5_reset_rx(h5);
+		return 0;
 	}
 
 	h5->rx_func = h5_rx_payload;
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 6e06f6f69152..77af52f0e3b1 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -118,10 +118,6 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 
 int hci_uart_tx_wakeup(struct hci_uart *hu)
 {
-	struct tty_struct *tty = hu->tty;
-	struct hci_dev *hdev = hu->hdev;
-	struct sk_buff *skb;
-
 	if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) {
 		set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
 		return 0;
@@ -129,6 +125,22 @@ int hci_uart_tx_wakeup(struct hci_uart *hu)
 
 	BT_DBG("");
 
+	schedule_work(&hu->write_work);
+
+	return 0;
+}
+
+static void hci_uart_write_work(struct work_struct *work)
+{
+	struct hci_uart *hu = container_of(work, struct hci_uart, write_work);
+	struct tty_struct *tty = hu->tty;
+	struct hci_dev *hdev = hu->hdev;
+	struct sk_buff *skb;
+
+	/* REVISIT: should we cope with bad skbs or ->write() returning
+	 * and error value ?
+	 */
+
 restart:
 	clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
 
@@ -153,7 +165,6 @@ restart:
 		goto restart;
 
 	clear_bit(HCI_UART_SENDING, &hu->tx_state);
-	return 0;
 }
 
 static void hci_uart_init_work(struct work_struct *work)
@@ -281,6 +292,7 @@ static int hci_uart_tty_open(struct tty_struct *tty)
 	tty->receive_room = 65536;
 
 	INIT_WORK(&hu->init_ready, hci_uart_init_work);
+	INIT_WORK(&hu->write_work, hci_uart_write_work);
 
 	spin_lock_init(&hu->rx_lock);
 
@@ -318,6 +330,8 @@ static void hci_uart_tty_close(struct tty_struct *tty)
 	if (hdev)
 		hci_uart_close(hdev);
 
+	cancel_work_sync(&hu->write_work);
+
 	if (test_and_clear_bit(HCI_UART_PROTO_SET, &hu->flags)) {
 		if (hdev) {
 			if (test_bit(HCI_UART_REGISTERED, &hu->flags))
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index fffa61ff5cb1..12df101ca942 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -68,6 +68,7 @@ struct hci_uart {
 	unsigned long		hdev_flags;
 
 	struct work_struct	init_ready;
+	struct work_struct	write_work;
 
 	struct hci_uart_proto	*proto;
 	void			*priv;
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 962fd35cbd8d..bc8e1af279c0 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -26,6 +26,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/irq_regs.h>
+#include <asm/psci.h>
 #include <asm/pmu.h>
 #include <asm/smp_plat.h>
 
@@ -544,6 +545,7 @@ static int cci_pmu_init(struct arm_pmu *cci_pmu, struct platform_device *pdev)
 
 	cci_pmu->plat_device = pdev;
 	cci_pmu->num_events = pmu_get_max_counters();
+	cpumask_setall(&cci_pmu->valid_cpus);
 
 	return armpmu_register(cci_pmu, -1);
 }
@@ -969,6 +971,11 @@ static int cci_probe(void)
 	const char *match_str;
 	bool is_ace;
 
+	if (psci_probe() == 0) {
+		pr_debug("psci found. Aborting cci probe\n");
+		return -ENODEV;
+	}
+
 	np = of_find_matching_node(NULL, arm_cci_matches);
 	if (!np)
 		return -ENODEV;
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 725c46162bbd..372ae72cce34 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -222,12 +222,6 @@ static int mvebu_mbus_window_conflicts(struct mvebu_mbus_state *mbus,
 		 */
 		if ((u64)base < wend && end > wbase)
 			return 0;
-
-		/*
-		 * Check if target/attribute conflicts
-		 */
-		if (target == wtarget && attr == wattr)
-			return 0;
 	}
 
 	return 1;
diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c
index 974321a2508d..14790304b84b 100644
--- a/drivers/char/applicom.c
+++ b/drivers/char/applicom.c
@@ -345,7 +345,6 @@ out:
 			free_irq(apbs[i].irq, &dummy);
 		iounmap(apbs[i].RamIO);
 	}
-	pci_disable_device(dev);
 	return ret;
 }
 
diff --git a/drivers/char/hw_random/pseries-rng.c b/drivers/char/hw_random/pseries-rng.c
index ab7ffdec0ec3..f38f2c13e79c 100644
--- a/drivers/char/hw_random/pseries-rng.c
+++ b/drivers/char/hw_random/pseries-rng.c
@@ -25,18 +25,21 @@
 #include <asm/vio.h>
 
 
-static int pseries_rng_data_read(struct hwrng *rng, u32 *data)
+static int pseries_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
 {
+	u64 buffer[PLPAR_HCALL_BUFSIZE];
+	size_t size = max < 8 ? max : 8;
 	int rc;
 
-	rc = plpar_hcall(H_RANDOM, (unsigned long *)data);
+	rc = plpar_hcall(H_RANDOM, (unsigned long *)buffer);
 	if (rc != H_SUCCESS) {
 		pr_err_ratelimited("H_RANDOM call failed %d\n", rc);
 		return -EIO;
 	}
+	memcpy(data, buffer, size);
 
 	/* The hypervisor interface returns 64 bits */
-	return 8;
+	return size;
 }
 
 /**
@@ -55,7 +58,7 @@ static unsigned long pseries_rng_get_desired_dma(struct vio_dev *vdev)
 
 static struct hwrng pseries_rng = {
 	.name		= KBUILD_MODNAME,
-	.data_read	= pseries_rng_data_read,
+	.read		= pseries_rng_read,
 };
 
 static int __init pseries_rng_probe(struct vio_dev *dev,
diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c
index d915707d2ba1..93dcad0c1cbe 100644
--- a/drivers/char/i8k.c
+++ b/drivers/char/i8k.c
@@ -138,7 +138,9 @@ static int i8k_smm(struct smm_regs *regs)
 	if (!alloc_cpumask_var(&old_mask, GFP_KERNEL))
 		return -ENOMEM;
 	cpumask_copy(old_mask, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(0));
+	rc = set_cpus_allowed_ptr(current, cpumask_of(0));
+	if (rc)
+		goto out;
 	if (smp_processor_id() != 0) {
 		rc = -EBUSY;
 		goto out;
diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c
index f5e4cd7617f6..61e71616689b 100644
--- a/drivers/char/ipmi/ipmi_bt_sm.c
+++ b/drivers/char/ipmi/ipmi_bt_sm.c
@@ -352,7 +352,7 @@ static inline void write_all_bytes(struct si_sm_data *bt)
 
 static inline int read_all_bytes(struct si_sm_data *bt)
 {
-	unsigned char i;
+	unsigned int i;
 
 	/*
 	 * length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.
diff --git a/drivers/char/ipmi/ipmi_kcs_sm.c b/drivers/char/ipmi/ipmi_kcs_sm.c
index 6a4bdc18955a..8c25f596808a 100644
--- a/drivers/char/ipmi/ipmi_kcs_sm.c
+++ b/drivers/char/ipmi/ipmi_kcs_sm.c
@@ -251,8 +251,9 @@ static inline int check_obf(struct si_sm_data *kcs, unsigned char status,
 	if (!GET_STATUS_OBF(status)) {
 		kcs->obf_timeout -= time;
 		if (kcs->obf_timeout < 0) {
-		    start_error_recovery(kcs, "OBF not ready in time");
-		    return 1;
+			kcs->obf_timeout = OBF_RETRY_TIMEOUT;
+			start_error_recovery(kcs, "OBF not ready in time");
+			return 1;
 		}
 		return 0;
 	}
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 03f41896d090..8b4fa2c4e661 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -249,6 +249,9 @@ struct smi_info {
 	/* The timer for this si. */
 	struct timer_list   si_timer;
 
+	/* This flag is set, if the timer is running (timer_pending() isn't enough) */
+	bool		    timer_running;
+
 	/* The time (in jiffies) the last timeout occurred at. */
 	unsigned long       last_timeout_jiffies;
 
@@ -435,6 +438,13 @@ static void start_clear_flags(struct smi_info *smi_info)
 	smi_info->si_state = SI_CLEARING_FLAGS;
 }
 
+static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
+{
+	smi_info->last_timeout_jiffies = jiffies;
+	mod_timer(&smi_info->si_timer, new_val);
+	smi_info->timer_running = true;
+}
+
 /*
  * When we have a situtaion where we run out of memory and cannot
  * allocate messages, we just leave them in the BMC and run the system
@@ -447,8 +457,7 @@ static inline void disable_si_irq(struct smi_info *smi_info)
 		start_disable_irq(smi_info);
 		smi_info->interrupt_disabled = 1;
 		if (!atomic_read(&smi_info->stop_operation))
-			mod_timer(&smi_info->si_timer,
-				  jiffies + SI_TIMEOUT_JIFFIES);
+			smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
 	}
 }
 
@@ -908,15 +917,7 @@ static void sender(void                *send_info,
 		list_add_tail(&msg->link, &smi_info->xmit_msgs);
 
 	if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL) {
-		/*
-		 * last_timeout_jiffies is updated here to avoid
-		 * smi_timeout() handler passing very large time_diff
-		 * value to smi_event_handler() that causes
-		 * the send command to abort.
-		 */
-		smi_info->last_timeout_jiffies = jiffies;
-
-		mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
+		smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
 
 		if (smi_info->thread)
 			wake_up_process(smi_info->thread);
@@ -1005,6 +1006,17 @@ static int ipmi_thread(void *data)
 
 		spin_lock_irqsave(&(smi_info->si_lock), flags);
 		smi_result = smi_event_handler(smi_info, 0);
+
+		/*
+		 * If the driver is doing something, there is a possible
+		 * race with the timer.  If the timer handler see idle,
+		 * and the thread here sees something else, the timer
+		 * handler won't restart the timer even though it is
+		 * required.  So start it here if necessary.
+		 */
+		if (smi_result != SI_SM_IDLE && !smi_info->timer_running)
+			smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
+
 		spin_unlock_irqrestore(&(smi_info->si_lock), flags);
 		busy_wait = ipmi_thread_busy_wait(smi_result, smi_info,
 						  &busy_until);
@@ -1074,10 +1086,6 @@ static void smi_timeout(unsigned long data)
 		     * SI_USEC_PER_JIFFY);
 	smi_result = smi_event_handler(smi_info, time_diff);
 
-	spin_unlock_irqrestore(&(smi_info->si_lock), flags);
-
-	smi_info->last_timeout_jiffies = jiffies_now;
-
 	if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
 		/* Running with interrupts, only do long timeouts. */
 		timeout = jiffies + SI_TIMEOUT_JIFFIES;
@@ -1099,7 +1107,10 @@ static void smi_timeout(unsigned long data)
 
  do_mod_timer:
 	if (smi_result != SI_SM_IDLE)
-		mod_timer(&(smi_info->si_timer), timeout);
+		smi_mod_timer(smi_info, timeout);
+	else
+		smi_info->timer_running = false;
+	spin_unlock_irqrestore(&(smi_info->si_lock), flags);
 }
 
 static irqreturn_t si_irq_handler(int irq, void *data)
@@ -1147,8 +1158,7 @@ static int smi_start_processing(void       *send_info,
 
 	/* Set up the timer that drives the interface. */
 	setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi);
-	new_smi->last_timeout_jiffies = jiffies;
-	mod_timer(&new_smi->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
+	smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);
 
 	/*
 	 * Check if the user forcefully enabled the daemon.
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 429b75bb60e8..8a64dbeae7b1 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1063,8 +1063,8 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	 * pool while mixing, and hash one final time.
 	 */
 	sha_transform(hash.w, extract, workspace);
-	memset(extract, 0, sizeof(extract));
-	memset(workspace, 0, sizeof(workspace));
+	memzero_explicit(extract, sizeof(extract));
+	memzero_explicit(workspace, sizeof(workspace));
 
 	/*
 	 * In case the hash function has some recognizable output
@@ -1076,7 +1076,7 @@ static void extract_buf(struct entropy_store *r, __u8 *out)
 	hash.w[2] ^= rol32(hash.w[2], 16);
 
 	memcpy(out, &hash, EXTRACT_SIZE);
-	memset(&hash, 0, sizeof(hash));
+	memzero_explicit(&hash, sizeof(hash));
 }
 
 static ssize_t extract_entropy(struct entropy_store *r, void *buf,
@@ -1124,7 +1124,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 	}
 
 	/* Wipe data just returned from memory */
-	memset(tmp, 0, sizeof(tmp));
+	memzero_explicit(tmp, sizeof(tmp));
 
 	return ret;
 }
@@ -1162,7 +1162,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
 	}
 
 	/* Wipe data just returned from memory */
-	memset(tmp, 0, sizeof(tmp));
+	memzero_explicit(tmp, sizeof(tmp));
 
 	return ret;
 }
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 62e10fd1e1cb..6af17002a115 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -491,11 +491,10 @@ static int tpm_startup(struct tpm_chip *chip, __be16 startup_type)
 int tpm_get_timeouts(struct tpm_chip *chip)
 {
 	struct tpm_cmd_t tpm_cmd;
-	struct timeout_t *timeout_cap;
+	unsigned long new_timeout[4];
+	unsigned long old_timeout[4];
 	struct duration_t *duration_cap;
 	ssize_t rc;
-	u32 timeout;
-	unsigned int scale = 1;
 
 	tpm_cmd.header.in = tpm_getcap_header;
 	tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
@@ -529,25 +528,46 @@ int tpm_get_timeouts(struct tpm_chip *chip)
 	    != sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32))
 		return -EINVAL;
 
-	timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout;
-	/* Don't overwrite default if value is 0 */
-	timeout = be32_to_cpu(timeout_cap->a);
-	if (timeout && timeout < 1000) {
-		/* timeouts in msec rather usec */
-		scale = 1000;
-		chip->vendor.timeout_adjusted = true;
+	old_timeout[0] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.a);
+	old_timeout[1] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.b);
+	old_timeout[2] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.c);
+	old_timeout[3] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.d);
+	memcpy(new_timeout, old_timeout, sizeof(new_timeout));
+
+	/*
+	 * Provide ability for vendor overrides of timeout values in case
+	 * of misreporting.
+	 */
+	if (chip->ops->update_timeouts != NULL)
+		chip->vendor.timeout_adjusted =
+			chip->ops->update_timeouts(chip, new_timeout);
+
+	if (!chip->vendor.timeout_adjusted) {
+		/* Don't overwrite default if value is 0 */
+		if (new_timeout[0] != 0 && new_timeout[0] < 1000) {
+			int i;
+
+			/* timeouts in msec rather usec */
+			for (i = 0; i != ARRAY_SIZE(new_timeout); i++)
+				new_timeout[i] *= 1000;
+			chip->vendor.timeout_adjusted = true;
+		}
+	}
+
+	/* Report adjusted timeouts */
+	if (chip->vendor.timeout_adjusted) {
+		dev_info(chip->dev,
+			 HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n",
+			 old_timeout[0], new_timeout[0],
+			 old_timeout[1], new_timeout[1],
+			 old_timeout[2], new_timeout[2],
+			 old_timeout[3], new_timeout[3]);
 	}
-	if (timeout)
-		chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale);
-	timeout = be32_to_cpu(timeout_cap->b);
-	if (timeout)
-		chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale);
-	timeout = be32_to_cpu(timeout_cap->c);
-	if (timeout)
-		chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale);
-	timeout = be32_to_cpu(timeout_cap->d);
-	if (timeout)
-		chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale);
+
+	chip->vendor.timeout_a = usecs_to_jiffies(new_timeout[0]);
+	chip->vendor.timeout_b = usecs_to_jiffies(new_timeout[1]);
+	chip->vendor.timeout_c = usecs_to_jiffies(new_timeout[2]);
+	chip->vendor.timeout_d = usecs_to_jiffies(new_timeout[3]);
 
 duration:
 	tpm_cmd.header.in = tpm_getcap_header;
@@ -991,13 +1011,13 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 	int err, total = 0, retries = 5;
 	u8 *dest = out;
 
+	if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
+		return -EINVAL;
+
 	chip = tpm_chip_find_get(chip_num);
 	if (chip == NULL)
 		return -ENODEV;
 
-	if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
-		return -EINVAL;
-
 	do {
 		tpm_cmd.header.in = tpm_getrandom_header;
 		tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes);
@@ -1016,6 +1036,7 @@ int tpm_get_random(u32 chip_num, u8 *out, size_t max)
 		num_bytes -= recd;
 	} while (retries-- && total < max);
 
+	tpm_chip_put(chip);
 	return total ? total : -EIO;
 }
 EXPORT_SYMBOL_GPL(tpm_get_random);
@@ -1095,7 +1116,7 @@ struct tpm_chip *tpm_register_hardware(struct device *dev,
 		goto del_misc;
 
 	if (tpm_add_ppi(&dev->kobj))
-		goto del_misc;
+		goto del_sysfs;
 
 	chip->bios_dir = tpm_bios_log_setup(chip->devname);
 
@@ -1106,6 +1127,8 @@ struct tpm_chip *tpm_register_hardware(struct device *dev,
 
 	return chip;
 
+del_sysfs:
+	tpm_sysfs_del_device(chip);
 del_misc:
 	tpm_dev_del_device(chip);
 put_device:
diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 5b0dd8ef74c0..be9af2e6ca5a 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -715,6 +715,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	}
 
 	tpm_get_timeouts(chip);
+	tpm_do_selftest(chip);
 
 	dev_info(chip->dev, "TPM I2C Initialized\n");
 	return 0;
diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index b3ea223585bd..61dcc8011ec7 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -328,13 +328,11 @@ int tpm_add_ppi(struct kobject *parent)
 	/* Cache TPM ACPI handle and version string */
 	acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
 			    ppi_callback, NULL, NULL, &tpm_ppi_handle);
-	if (tpm_ppi_handle == NULL)
-		return -ENODEV;
-
-	return sysfs_create_group(parent, &ppi_attr_grp);
+	return tpm_ppi_handle ? sysfs_create_group(parent, &ppi_attr_grp) : 0;
 }
 
 void tpm_remove_ppi(struct kobject *parent)
 {
-	sysfs_remove_group(parent, &ppi_attr_grp);
+	if (tpm_ppi_handle)
+		sysfs_remove_group(parent, &ppi_attr_grp);
 }
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index a9ed2270c25d..2c46734b266d 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -373,6 +373,36 @@ out_err:
 	return rc;
 }
 
+struct tis_vendor_timeout_override {
+	u32 did_vid;
+	unsigned long timeout_us[4];
+};
+
+static const struct tis_vendor_timeout_override vendor_timeout_overrides[] = {
+	/* Atmel 3204 */
+	{ 0x32041114, { (TIS_SHORT_TIMEOUT*1000), (TIS_LONG_TIMEOUT*1000),
+			(TIS_SHORT_TIMEOUT*1000), (TIS_SHORT_TIMEOUT*1000) } },
+};
+
+static bool tpm_tis_update_timeouts(struct tpm_chip *chip,
+				    unsigned long *timeout_cap)
+{
+	int i;
+	u32 did_vid;
+
+	did_vid = ioread32(chip->vendor.iobase + TPM_DID_VID(0));
+
+	for (i = 0; i != ARRAY_SIZE(vendor_timeout_overrides); i++) {
+		if (vendor_timeout_overrides[i].did_vid != did_vid)
+			continue;
+		memcpy(timeout_cap, vendor_timeout_overrides[i].timeout_us,
+		       sizeof(vendor_timeout_overrides[i].timeout_us));
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Early probing for iTPM with STS_DATA_EXPECT flaw.
  * Try sending command without itpm flag set and if that
@@ -437,6 +467,7 @@ static const struct tpm_class_ops tpm_tis = {
 	.recv = tpm_tis_recv,
 	.send = tpm_tis_send,
 	.cancel = tpm_tis_ready,
+	.update_timeouts = tpm_tis_update_timeouts,
 	.req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
 	.req_canceled = tpm_tis_req_canceled,
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 5543b7df8e16..d95f120af5c5 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -24,7 +24,7 @@
  * Traits of this clock:
  * prepare - clk_prepare only ensures that parents are prepared
  * enable - clk_enable only ensures that parents are enabled
- * rate - rate is adjustable.  clk->rate = parent->rate / divisor
+ * rate - rate is adjustable.  clk->rate = DIV_ROUND_UP(parent->rate / divisor)
  * parent - fixed parent.  No clk_set_parent support
  */
 
@@ -43,6 +43,17 @@ static unsigned int _get_table_maxdiv(const struct clk_div_table *table)
 	return maxdiv;
 }
 
+static unsigned int _get_table_mindiv(const struct clk_div_table *table)
+{
+	unsigned int mindiv = UINT_MAX;
+	const struct clk_div_table *clkt;
+
+	for (clkt = table; clkt->div; clkt++)
+		if (clkt->div < mindiv)
+			mindiv = clkt->div;
+	return mindiv;
+}
+
 static unsigned int _get_maxdiv(struct clk_divider *divider)
 {
 	if (divider->flags & CLK_DIVIDER_ONE_BASED)
@@ -115,7 +126,7 @@ static unsigned long clk_divider_recalc_rate(struct clk_hw *hw,
 		return parent_rate;
 	}
 
-	return parent_rate / div;
+	return DIV_ROUND_UP(parent_rate, div);
 }
 
 /*
@@ -144,6 +155,91 @@ static bool _is_valid_div(struct clk_divider *divider, unsigned int div)
 	return true;
 }
 
+static int _round_up_table(const struct clk_div_table *table, int div)
+{
+	const struct clk_div_table *clkt;
+	int up = INT_MAX;
+
+	for (clkt = table; clkt->div; clkt++) {
+		if (clkt->div == div)
+			return clkt->div;
+		else if (clkt->div < div)
+			continue;
+
+		if ((clkt->div - div) < (up - div))
+			up = clkt->div;
+	}
+
+	return up;
+}
+
+static int _round_down_table(const struct clk_div_table *table, int div)
+{
+	const struct clk_div_table *clkt;
+	int down = _get_table_mindiv(table);
+
+	for (clkt = table; clkt->div; clkt++) {
+		if (clkt->div == div)
+			return clkt->div;
+		else if (clkt->div > div)
+			continue;
+
+		if ((div - clkt->div) < (div - down))
+			down = clkt->div;
+	}
+
+	return down;
+}
+
+static int _div_round_up(struct clk_divider *divider,
+		unsigned long parent_rate, unsigned long rate)
+{
+	int div = DIV_ROUND_UP(parent_rate, rate);
+
+	if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+		div = __roundup_pow_of_two(div);
+	if (divider->table)
+		div = _round_up_table(divider->table, div);
+
+	return div;
+}
+
+static int _div_round_closest(struct clk_divider *divider,
+		unsigned long parent_rate, unsigned long rate)
+{
+	int up, down, div;
+
+	up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate);
+
+	if (divider->flags & CLK_DIVIDER_POWER_OF_TWO) {
+		up = __roundup_pow_of_two(div);
+		down = __rounddown_pow_of_two(div);
+	} else if (divider->table) {
+		up = _round_up_table(divider->table, div);
+		down = _round_down_table(divider->table, div);
+	}
+
+	return (up - div) <= (div - down) ? up : down;
+}
+
+static int _div_round(struct clk_divider *divider, unsigned long parent_rate,
+		unsigned long rate)
+{
+	if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST)
+		return _div_round_closest(divider, parent_rate, rate);
+
+	return _div_round_up(divider, parent_rate, rate);
+}
+
+static bool _is_best_div(struct clk_divider *divider,
+		unsigned long rate, unsigned long now, unsigned long best)
+{
+	if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST)
+		return abs(rate - now) < abs(rate - best);
+
+	return now <= rate && now > best;
+}
+
 static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 		unsigned long *best_parent_rate)
 {
@@ -159,7 +255,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 
 	if (!(__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT)) {
 		parent_rate = *best_parent_rate;
-		bestdiv = DIV_ROUND_UP(parent_rate, rate);
+		bestdiv = _div_round(divider, parent_rate, rate);
 		bestdiv = bestdiv == 0 ? 1 : bestdiv;
 		bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv;
 		return bestdiv;
@@ -185,8 +281,8 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 		}
 		parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
 				MULT_ROUND_UP(rate, i));
-		now = parent_rate / i;
-		if (now <= rate && now > best) {
+		now = DIV_ROUND_UP(parent_rate, i);
+		if (_is_best_div(divider, rate, now, best)) {
 			bestdiv = i;
 			best = now;
 			*best_parent_rate = parent_rate;
@@ -207,7 +303,7 @@ static long clk_divider_round_rate(struct clk_hw *hw, unsigned long rate,
 	int div;
 	div = clk_divider_bestdiv(hw, rate, prate);
 
-	return *prate / div;
+	return DIV_ROUND_UP(*prate, div);
 }
 
 static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -218,7 +314,11 @@ static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned long flags = 0;
 	u32 val;
 
-	div = parent_rate / rate;
+	div = DIV_ROUND_UP(parent_rate, rate);
+
+	if (!_is_valid_div(divider, div))
+		return -EINVAL;
+
 	value = _get_val(divider, div);
 
 	if (value > div_mask(divider))
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index 00a3abe103a5..611b936ecffe 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -130,7 +130,7 @@ static struct device_node *s2mps11_clk_parse_dt(struct platform_device *pdev)
 	int i;
 
 	if (!iodev->dev->of_node)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	clk_np = of_find_node_by_name(iodev->dev->of_node, "clocks");
 	if (!clk_np) {
@@ -190,16 +190,13 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 			goto err_reg;
 		}
 
-		s2mps11_clk->lookup = devm_kzalloc(&pdev->dev,
-					sizeof(struct clk_lookup), GFP_KERNEL);
+		s2mps11_clk->lookup = clkdev_alloc(s2mps11_clk->clk,
+					s2mps11_name(s2mps11_clk), NULL);
 		if (!s2mps11_clk->lookup) {
 			ret = -ENOMEM;
 			goto err_lup;
 		}
 
-		s2mps11_clk->lookup->con_id = s2mps11_name(s2mps11_clk);
-		s2mps11_clk->lookup->clk = s2mps11_clk->clk;
-
 		clkdev_add(s2mps11_clk->lookup);
 	}
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index c42e608af6bb..f9c4632d4dd3 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -1487,6 +1487,7 @@ static struct clk *clk_propagate_rate_change(struct clk *clk, unsigned long even
 static void clk_change_rate(struct clk *clk)
 {
 	struct clk *child;
+	struct hlist_node *tmp;
 	unsigned long old_rate;
 	unsigned long best_parent_rate = 0;
 	bool skip_set_rate = false;
@@ -1525,7 +1526,11 @@ static void clk_change_rate(struct clk *clk)
 	if (clk->notifier_count && old_rate != clk->rate)
 		__clk_notify(clk, POST_RATE_CHANGE, old_rate, clk->rate);
 
-	hlist_for_each_entry(child, &clk->children, child_node) {
+	/*
+	 * Use safe iteration, as change_rate can actually swap parents
+	 * for certain clock types.
+	 */
+	hlist_for_each_entry_safe(child, tmp, &clk->children, child_node) {
 		/* Skip children who will be reparented to another clock */
 		if (child->new_parent && child->new_parent != clk)
 			continue;
@@ -1977,9 +1982,28 @@ struct clk *__clk_register(struct device *dev, struct clk_hw *hw)
 }
 EXPORT_SYMBOL_GPL(__clk_register);
 
-static int _clk_register(struct device *dev, struct clk_hw *hw, struct clk *clk)
+/**
+ * clk_register - allocate a new clock, register it and return an opaque cookie
+ * @dev: device that is registering this clock
+ * @hw: link to hardware-specific clock data
+ *
+ * clk_register is the primary interface for populating the clock tree with new
+ * clock nodes.  It returns a pointer to the newly allocated struct clk which
+ * cannot be dereferenced by driver code but may be used in conjuction with the
+ * rest of the clock API.  In the event of an error clk_register will return an
+ * error code; drivers must test for an error code after calling clk_register.
+ */
+struct clk *clk_register(struct device *dev, struct clk_hw *hw)
 {
 	int i, ret;
+	struct clk *clk;
+
+	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
+	if (!clk) {
+		pr_err("%s: could not allocate clk\n", __func__);
+		ret = -ENOMEM;
+		goto fail_out;
+	}
 
 	clk->name = kstrdup(hw->init->name, GFP_KERNEL);
 	if (!clk->name) {
@@ -2019,7 +2043,7 @@ static int _clk_register(struct device *dev, struct clk_hw *hw, struct clk *clk)
 
 	ret = __clk_init(dev, clk);
 	if (!ret)
-		return 0;
+		return clk;
 
 fail_parent_names_copy:
 	while (--i >= 0)
@@ -2028,36 +2052,6 @@ fail_parent_names_copy:
 fail_parent_names:
 	kfree(clk->name);
 fail_name:
-	return ret;
-}
-
-/**
- * clk_register - allocate a new clock, register it and return an opaque cookie
- * @dev: device that is registering this clock
- * @hw: link to hardware-specific clock data
- *
- * clk_register is the primary interface for populating the clock tree with new
- * clock nodes.  It returns a pointer to the newly allocated struct clk which
- * cannot be dereferenced by driver code but may be used in conjuction with the
- * rest of the clock API.  In the event of an error clk_register will return an
- * error code; drivers must test for an error code after calling clk_register.
- */
-struct clk *clk_register(struct device *dev, struct clk_hw *hw)
-{
-	int ret;
-	struct clk *clk;
-
-	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
-	if (!clk) {
-		pr_err("%s: could not allocate clk\n", __func__);
-		ret = -ENOMEM;
-		goto fail_out;
-	}
-
-	ret = _clk_register(dev, hw, clk);
-	if (!ret)
-		return clk;
-
 	kfree(clk);
 fail_out:
 	return ERR_PTR(ret);
@@ -2144,9 +2138,10 @@ void clk_unregister(struct clk *clk)
 
 	if (!hlist_empty(&clk->children)) {
 		struct clk *child;
+		struct hlist_node *t;
 
 		/* Reparent all children to the orphan list. */
-		hlist_for_each_entry(child, &clk->children, child_node)
+		hlist_for_each_entry_safe(child, t, &clk->children, child_node)
 			clk_set_parent(child, NULL);
 	}
 
@@ -2166,7 +2161,7 @@ EXPORT_SYMBOL_GPL(clk_unregister);
 
 static void devm_clk_release(struct device *dev, void *res)
 {
-	clk_unregister(res);
+	clk_unregister(*(struct clk **)res);
 }
 
 /**
@@ -2181,18 +2176,18 @@ static void devm_clk_release(struct device *dev, void *res)
 struct clk *devm_clk_register(struct device *dev, struct clk_hw *hw)
 {
 	struct clk *clk;
-	int ret;
+	struct clk **clkp;
 
-	clk = devres_alloc(devm_clk_release, sizeof(*clk), GFP_KERNEL);
-	if (!clk)
+	clkp = devres_alloc(devm_clk_release, sizeof(*clkp), GFP_KERNEL);
+	if (!clkp)
 		return ERR_PTR(-ENOMEM);
 
-	ret = _clk_register(dev, hw, clk);
-	if (!ret) {
-		devres_add(dev, clk);
+	clk = clk_register(dev, hw);
+	if (!IS_ERR(clk)) {
+		*clkp = clk;
+		devres_add(dev, clkp);
 	} else {
-		devres_free(clk);
-		clk = ERR_PTR(ret);
+		devres_free(clkp);
 	}
 
 	return clk;
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index 00f878a04d3f..0996a3a39855 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -55,7 +55,7 @@ static int clk_rcg2_is_enabled(struct clk_hw *hw)
 	if (ret)
 		return ret;
 
-	return (cmd & CMD_ROOT_OFF) != 0;
+	return (cmd & CMD_ROOT_OFF) == 0;
 }
 
 static u8 clk_rcg2_get_parent(struct clk_hw *hw)
diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c
index f9b59c7e48e9..f3c95d648a53 100644
--- a/drivers/clk/qcom/mmcc-msm8960.c
+++ b/drivers/clk/qcom/mmcc-msm8960.c
@@ -37,6 +37,8 @@
 #define P_PLL2	2
 #define P_PLL3	3
 
+#define F_MN(f, s, _m, _n) { .freq = f, .src = s, .m = _m, .n = _n }
+
 static u8 mmcc_pxo_pll8_pll2_map[] = {
 	[P_PXO]		= 0,
 	[P_PLL8]	= 2,
@@ -58,8 +60,8 @@ static u8 mmcc_pxo_pll8_pll2_pll3_map[] = {
 
 static const char *mmcc_pxo_pll8_pll2_pll3[] = {
 	"pxo",
-	"pll2",
 	"pll8_vote",
+	"pll2",
 	"pll3",
 };
 
@@ -709,18 +711,18 @@ static struct clk_branch csiphy2_timer_clk = {
 };
 
 static struct freq_tbl clk_tbl_gfx2d[] = {
-	{  27000000, P_PXO,  1,  0 },
-	{  48000000, P_PLL8, 1,  8 },
-	{  54857000, P_PLL8, 1,  7 },
-	{  64000000, P_PLL8, 1,  6 },
-	{  76800000, P_PLL8, 1,  5 },
-	{  96000000, P_PLL8, 1,  4 },
-	{ 128000000, P_PLL8, 1,  3 },
-	{ 145455000, P_PLL2, 2, 11 },
-	{ 160000000, P_PLL2, 1,  5 },
-	{ 177778000, P_PLL2, 2,  9 },
-	{ 200000000, P_PLL2, 1,  4 },
-	{ 228571000, P_PLL2, 2,  7 },
+	F_MN( 27000000, P_PXO,  1,  0),
+	F_MN( 48000000, P_PLL8, 1,  8),
+	F_MN( 54857000, P_PLL8, 1,  7),
+	F_MN( 64000000, P_PLL8, 1,  6),
+	F_MN( 76800000, P_PLL8, 1,  5),
+	F_MN( 96000000, P_PLL8, 1,  4),
+	F_MN(128000000, P_PLL8, 1,  3),
+	F_MN(145455000, P_PLL2, 2, 11),
+	F_MN(160000000, P_PLL2, 1,  5),
+	F_MN(177778000, P_PLL2, 2,  9),
+	F_MN(200000000, P_PLL2, 1,  4),
+	F_MN(228571000, P_PLL2, 2,  7),
 	{ }
 };
 
@@ -841,22 +843,22 @@ static struct clk_branch gfx2d1_clk = {
 };
 
 static struct freq_tbl clk_tbl_gfx3d[] = {
-	{  27000000, P_PXO,  1,  0 },
-	{  48000000, P_PLL8, 1,  8 },
-	{  54857000, P_PLL8, 1,  7 },
-	{  64000000, P_PLL8, 1,  6 },
-	{  76800000, P_PLL8, 1,  5 },
-	{  96000000, P_PLL8, 1,  4 },
-	{ 128000000, P_PLL8, 1,  3 },
-	{ 145455000, P_PLL2, 2, 11 },
-	{ 160000000, P_PLL2, 1,  5 },
-	{ 177778000, P_PLL2, 2,  9 },
-	{ 200000000, P_PLL2, 1,  4 },
-	{ 228571000, P_PLL2, 2,  7 },
-	{ 266667000, P_PLL2, 1,  3 },
-	{ 300000000, P_PLL3, 1,  4 },
-	{ 320000000, P_PLL2, 2,  5 },
-	{ 400000000, P_PLL2, 1,  2 },
+	F_MN( 27000000, P_PXO,  1,  0),
+	F_MN( 48000000, P_PLL8, 1,  8),
+	F_MN( 54857000, P_PLL8, 1,  7),
+	F_MN( 64000000, P_PLL8, 1,  6),
+	F_MN( 76800000, P_PLL8, 1,  5),
+	F_MN( 96000000, P_PLL8, 1,  4),
+	F_MN(128000000, P_PLL8, 1,  3),
+	F_MN(145455000, P_PLL2, 2, 11),
+	F_MN(160000000, P_PLL2, 1,  5),
+	F_MN(177778000, P_PLL2, 2,  9),
+	F_MN(200000000, P_PLL2, 1,  4),
+	F_MN(228571000, P_PLL2, 2,  7),
+	F_MN(266667000, P_PLL2, 1,  3),
+	F_MN(300000000, P_PLL3, 1,  4),
+	F_MN(320000000, P_PLL2, 2,  5),
+	F_MN(400000000, P_PLL2, 1,  2),
 	{ }
 };
 
@@ -896,7 +898,7 @@ static struct clk_dyn_rcg gfx3d_src = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gfx3d_src",
 			.parent_names = mmcc_pxo_pll8_pll2_pll3,
-			.num_parents = 3,
+			.num_parents = 4,
 			.ops = &clk_dyn_rcg_ops,
 		},
 	},
@@ -994,7 +996,7 @@ static struct clk_rcg jpegd_src = {
 	.ns_reg = 0x00ac,
 	.p = {
 		.pre_div_shift = 12,
-		.pre_div_width = 2,
+		.pre_div_width = 4,
 	},
 	.s = {
 		.src_sel_shift = 0,
@@ -1114,7 +1116,7 @@ static struct clk_branch mdp_lut_clk = {
 		.enable_reg = 0x016c,
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
-			.parent_names = (const char *[]){ "mdp_clk" },
+			.parent_names = (const char *[]){ "mdp_src" },
 			.num_parents = 1,
 			.name = "mdp_lut_clk",
 			.ops = &clk_branch_ops,
@@ -1208,7 +1210,7 @@ static struct clk_branch rot_clk = {
 
 static u8 mmcc_pxo_hdmi_map[] = {
 	[P_PXO]		= 0,
-	[P_HDMI_PLL]	= 2,
+	[P_HDMI_PLL]	= 3,
 };
 
 static const char *mmcc_pxo_hdmi[] = {
@@ -1341,15 +1343,15 @@ static struct clk_branch hdmi_app_clk = {
 };
 
 static struct freq_tbl clk_tbl_vcodec[] = {
-	{  27000000, P_PXO,  1,  0 },
-	{  32000000, P_PLL8, 1, 12 },
-	{  48000000, P_PLL8, 1,  8 },
-	{  54860000, P_PLL8, 1,  7 },
-	{  96000000, P_PLL8, 1,  4 },
-	{ 133330000, P_PLL2, 1,  6 },
-	{ 200000000, P_PLL2, 1,  4 },
-	{ 228570000, P_PLL2, 2,  7 },
-	{ 266670000, P_PLL2, 1,  3 },
+	F_MN( 27000000, P_PXO,  1,  0),
+	F_MN( 32000000, P_PLL8, 1, 12),
+	F_MN( 48000000, P_PLL8, 1,  8),
+	F_MN( 54860000, P_PLL8, 1,  7),
+	F_MN( 96000000, P_PLL8, 1,  4),
+	F_MN(133330000, P_PLL2, 1,  6),
+	F_MN(200000000, P_PLL2, 1,  4),
+	F_MN(228570000, P_PLL2, 2,  7),
+	F_MN(266670000, P_PLL2, 1,  3),
 	{ }
 };
 
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index c95774514b81..6a0ae77d1939 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -169,6 +169,7 @@ static struct clk_pll mmpll0 = {
 	.config_reg = 0x0014,
 	.mode_reg = 0x0000,
 	.status_reg = 0x001c,
+	.status_bit = 17,
         .clkr.hw.init = &(struct clk_init_data){
                 .name = "mmpll0",
                 .parent_names = (const char *[]){ "xo" },
@@ -192,9 +193,10 @@ static struct clk_pll mmpll1 = {
 	.l_reg = 0x0044,
 	.m_reg = 0x0048,
 	.n_reg = 0x004c,
-	.config_reg = 0x0054,
+	.config_reg = 0x0050,
 	.mode_reg = 0x0040,
 	.status_reg = 0x005c,
+	.status_bit = 17,
         .clkr.hw.init = &(struct clk_init_data){
                 .name = "mmpll1",
                 .parent_names = (const char *[]){ "xo" },
@@ -218,7 +220,7 @@ static struct clk_pll mmpll2 = {
 	.l_reg = 0x4104,
 	.m_reg = 0x4108,
 	.n_reg = 0x410c,
-	.config_reg = 0x4114,
+	.config_reg = 0x4110,
 	.mode_reg = 0x4100,
 	.status_reg = 0x411c,
         .clkr.hw.init = &(struct clk_init_data){
@@ -233,9 +235,10 @@ static struct clk_pll mmpll3 = {
 	.l_reg = 0x0084,
 	.m_reg = 0x0088,
 	.n_reg = 0x008c,
-	.config_reg = 0x0094,
+	.config_reg = 0x0090,
 	.mode_reg = 0x0080,
 	.status_reg = 0x009c,
+	.status_bit = 17,
         .clkr.hw.init = &(struct clk_init_data){
                 .name = "mmpll3",
                 .parent_names = (const char *[]){ "xo" },
@@ -2318,7 +2321,7 @@ static const struct pll_config mmpll1_config = {
 	.vco_val = 0x0,
 	.vco_mask = 0x3 << 20,
 	.pre_div_val = 0x0,
-	.pre_div_mask = 0x3 << 12,
+	.pre_div_mask = 0x7 << 12,
 	.post_div_val = 0x0,
 	.post_div_mask = 0x3 << 8,
 	.mn_ena_mask = BIT(24),
@@ -2332,7 +2335,7 @@ static struct pll_config mmpll3_config = {
 	.vco_val = 0x0,
 	.vco_mask = 0x3 << 20,
 	.pre_div_val = 0x0,
-	.pre_div_mask = 0x3 << 12,
+	.pre_div_mask = 0x7 << 12,
 	.post_div_val = 0x0,
 	.post_div_mask = 0x3 << 8,
 	.mn_ena_mask = BIT(24),
diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c
index c2d204315546..125eba86c844 100644
--- a/drivers/clk/spear/spear3xx_clock.c
+++ b/drivers/clk/spear/spear3xx_clock.c
@@ -211,7 +211,7 @@ static inline void spear310_clk_init(void) { }
 /* array of all spear 320 clock lookups */
 #ifdef CONFIG_MACH_SPEAR320
 
-#define SPEAR320_CONTROL_REG		(soc_config_base + 0x0000)
+#define SPEAR320_CONTROL_REG		(soc_config_base + 0x0010)
 #define SPEAR320_EXT_CTRL_REG		(soc_config_base + 0x0018)
 
 	#define SPEAR320_UARTX_PCLK_MASK		0x1
diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index 0d20241e0770..e1769addf435 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -1718,7 +1718,7 @@ struct clk *tegra_clk_register_plle_tegra114(const char *name,
 					"pll_re_vco");
 	} else {
 		val_aux &= ~(PLLE_AUX_PLLRE_SEL | PLLE_AUX_PLLP_SEL);
-		pll_writel(val, pll_params->aux_reg, pll);
+		pll_writel(val_aux, pll_params->aux_reg, pll);
 	}
 
 	clk = _tegra_clk_register_pll(pll, name, parent_name, flags,
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index 166e02f16c8a..cc37c342c4cb 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -764,7 +764,6 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_sdmmc2_8] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true },
 	[tegra_clk_i2s1] = { .dt_id = TEGRA124_CLK_I2S1, .present = true },
 	[tegra_clk_i2c1] = { .dt_id = TEGRA124_CLK_I2C1, .present = true },
-	[tegra_clk_ndflash] = { .dt_id = TEGRA124_CLK_NDFLASH, .present = true },
 	[tegra_clk_sdmmc1_8] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true },
 	[tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true },
 	[tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true },
@@ -809,7 +808,6 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_trace] = { .dt_id = TEGRA124_CLK_TRACE, .present = true },
 	[tegra_clk_soc_therm] = { .dt_id = TEGRA124_CLK_SOC_THERM, .present = true },
 	[tegra_clk_dtv] = { .dt_id = TEGRA124_CLK_DTV, .present = true },
-	[tegra_clk_ndspeed] = { .dt_id = TEGRA124_CLK_NDSPEED, .present = true },
 	[tegra_clk_i2cslow] = { .dt_id = TEGRA124_CLK_I2CSLOW, .present = true },
 	[tegra_clk_dsib] = { .dt_id = TEGRA124_CLK_DSIB, .present = true },
 	[tegra_clk_tsec] = { .dt_id = TEGRA124_CLK_TSEC, .present = true },
@@ -952,7 +950,6 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_clk_out_3_mux] = { .dt_id = TEGRA124_CLK_CLK_OUT_3_MUX, .present = true },
 	[tegra_clk_dsia_mux] = { .dt_id = TEGRA124_CLK_DSIA_MUX, .present = true },
 	[tegra_clk_dsib_mux] = { .dt_id = TEGRA124_CLK_DSIB_MUX, .present = true },
-	[tegra_clk_uarte] = { .dt_id = TEGRA124_CLK_UARTE, .present = true },
 };
 
 static struct tegra_devclk devclks[] __initdata = {
diff --git a/drivers/clk/ti/clk-44xx.c b/drivers/clk/ti/clk-44xx.c
index ae00218b5da3..02517a8206bd 100644
--- a/drivers/clk/ti/clk-44xx.c
+++ b/drivers/clk/ti/clk-44xx.c
@@ -222,7 +222,6 @@ static struct ti_dt_clk omap44xx_clks[] = {
 	DT_CLK(NULL, "auxclk5_src_ck", "auxclk5_src_ck"),
 	DT_CLK(NULL, "auxclk5_ck", "auxclk5_ck"),
 	DT_CLK(NULL, "auxclkreq5_ck", "auxclkreq5_ck"),
-	DT_CLK("50000000.gpmc", "fck", "dummy_ck"),
 	DT_CLK("omap_i2c.1", "ick", "dummy_ck"),
 	DT_CLK("omap_i2c.2", "ick", "dummy_ck"),
 	DT_CLK("omap_i2c.3", "ick", "dummy_ck"),
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index 0ef9f581286b..08f3d1b915b3 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -182,7 +182,6 @@ static struct ti_dt_clk omap54xx_clks[] = {
 	DT_CLK(NULL, "auxclk3_src_ck", "auxclk3_src_ck"),
 	DT_CLK(NULL, "auxclk3_ck", "auxclk3_ck"),
 	DT_CLK(NULL, "auxclkreq3_ck", "auxclkreq3_ck"),
-	DT_CLK(NULL, "gpmc_ck", "dummy_ck"),
 	DT_CLK("omap_i2c.1", "ick", "dummy_ck"),
 	DT_CLK("omap_i2c.2", "ick", "dummy_ck"),
 	DT_CLK("omap_i2c.3", "ick", "dummy_ck"),
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index 9977653f2d63..f7e40734c819 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -262,7 +262,6 @@ static struct ti_dt_clk dra7xx_clks[] = {
 	DT_CLK(NULL, "vip1_gclk_mux", "vip1_gclk_mux"),
 	DT_CLK(NULL, "vip2_gclk_mux", "vip2_gclk_mux"),
 	DT_CLK(NULL, "vip3_gclk_mux", "vip3_gclk_mux"),
-	DT_CLK(NULL, "gpmc_ck", "dummy_ck"),
 	DT_CLK("omap_i2c.1", "ick", "dummy_ck"),
 	DT_CLK("omap_i2c.2", "ick", "dummy_ck"),
 	DT_CLK("omap_i2c.3", "ick", "dummy_ck"),
diff --git a/drivers/clk/versatile/clk-vexpress-osc.c b/drivers/clk/versatile/clk-vexpress-osc.c
index 2dc8b41a339d..a535c7bf8574 100644
--- a/drivers/clk/versatile/clk-vexpress-osc.c
+++ b/drivers/clk/versatile/clk-vexpress-osc.c
@@ -102,7 +102,7 @@ void __init vexpress_osc_of_setup(struct device_node *node)
 
 	osc = kzalloc(sizeof(*osc), GFP_KERNEL);
 	if (!osc)
-		goto error;
+		return;
 
 	osc->func = vexpress_config_func_get_by_node(node);
 	if (!osc->func) {
diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index 0fc31d029e52..351c56431cc8 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -250,7 +250,8 @@ static void __init global_timer_of_register(struct device_node *np)
 	 * fire when the timer value is greater than or equal to. In previous
 	 * revisions the comparators fired when the timer value was equal to.
 	 */
-	if ((read_cpuid_id() & 0xf0000f) < 0x200000) {
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9
+	    && (read_cpuid_id() & 0xf0000f) < 0x200000) {
 		pr_warn("global-timer: non support for this cpu version.\n");
 		return;
 	}
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 48f76bc05da0..e252939b9ee1 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -418,8 +418,6 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 	evt->set_mode = exynos4_tick_set_mode;
 	evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	evt->rating = 450;
-	clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
-					0xf, 0x7fffffff);
 
 	exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
 
@@ -432,9 +430,12 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
 				evt->irq);
 			return -EIO;
 		}
+		irq_force_affinity(mct_irqs[MCT_L0_IRQ + cpu], cpumask_of(cpu));
 	} else {
 		enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
 	}
+	clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
+					0xf, 0x7fffffff);
 
 	return 0;
 }
@@ -452,7 +453,6 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
 					   unsigned long action, void *hcpu)
 {
 	struct mct_clock_event_device *mevt;
-	unsigned int cpu;
 
 	/*
 	 * Grab cpu pointer in each case to avoid spurious
@@ -463,12 +463,6 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
 		mevt = this_cpu_ptr(&percpu_mct_tick);
 		exynos4_local_timer_setup(&mevt->evt);
 		break;
-	case CPU_ONLINE:
-		cpu = (unsigned long)hcpu;
-		if (mct_int_type == MCT_INT_SPI)
-			irq_set_affinity(mct_irqs[MCT_L0_IRQ + cpu],
-						cpumask_of(cpu));
-		break;
 	case CPU_DYING:
 		mevt = this_cpu_ptr(&percpu_mct_tick);
 		exynos4_local_timer_stop(&mevt->evt);
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index bf497afba9ad..7d19f86012f2 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -182,6 +182,12 @@ static void __init sun4i_timer_init(struct device_node *node)
 	/* Make sure timer is stopped before playing with interrupts */
 	sun4i_clkevt_time_stop(0);
 
+	sun4i_clockevent.cpumask = cpu_possible_mask;
+	sun4i_clockevent.irq = irq;
+
+	clockevents_config_and_register(&sun4i_clockevent, rate,
+					TIMER_SYNC_TICKS, 0xffffffff);
+
 	ret = setup_irq(irq, &sun4i_timer_irq);
 	if (ret)
 		pr_warn("failed to setup irq %d\n", irq);
@@ -189,12 +195,6 @@ static void __init sun4i_timer_init(struct device_node *node)
 	/* Enable timer0 interrupt */
 	val = readl(timer_base + TIMER_IRQ_EN_REG);
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
-
-	sun4i_clockevent.cpumask = cpu_possible_mask;
-	sun4i_clockevent.irq = irq;
-
-	clockevents_config_and_register(&sun4i_clockevent, rate,
-					TIMER_SYNC_TICKS, 0xffffffff);
 }
 CLOCKSOURCE_OF_DECLARE(sun4i, "allwinner,sun4i-timer",
 		       sun4i_timer_init);
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 18c5b9b16645..3165811e2407 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -369,7 +369,7 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg,
 		return;
 
 	/* Can only change if privileged. */
-	if (!capable(CAP_NET_ADMIN)) {
+	if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) {
 		err = EPERM;
 		goto out;
 	}
diff --git a/drivers/coresight/Makefile b/drivers/coresight/Makefile
new file mode 100644
index 000000000000..4b4bec890ef5
--- /dev/null
+++ b/drivers/coresight/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for CoreSight drivers.
+#
+obj-$(CONFIG_CORESIGHT) += coresight.o
+obj-$(CONFIG_OF) += of_coresight.o
+obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o
+obj-$(CONFIG_CORESIGHT_SINK_TPIU) += coresight-tpiu.o
+obj-$(CONFIG_CORESIGHT_SINK_ETBV10) += coresight-etb10.o
+obj-$(CONFIG_CORESIGHT_LINKS_AND_SINKS) += coresight-funnel.o \
+					   coresight-replicator.o
+obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o
diff --git a/drivers/coresight/coresight-etb10.c b/drivers/coresight/coresight-etb10.c
new file mode 100644
index 000000000000..c922d4aded8a
--- /dev/null
+++ b/drivers/coresight/coresight-etb10.c
@@ -0,0 +1,537 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/seq_file.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define ETB_RAM_DEPTH_REG	0x004
+#define ETB_STATUS_REG		0x00c
+#define ETB_RAM_READ_DATA_REG	0x010
+#define ETB_RAM_READ_POINTER	0x014
+#define ETB_RAM_WRITE_POINTER	0x018
+#define ETB_TRG			0x01c
+#define ETB_CTL_REG		0x020
+#define ETB_RWD_REG		0x024
+#define ETB_FFSR		0x300
+#define ETB_FFCR		0x304
+#define ETB_ITMISCOP0		0xee0
+#define ETB_ITTRFLINACK		0xee4
+#define ETB_ITTRFLIN		0xee8
+#define ETB_ITATBDATA0		0xeeC
+#define ETB_ITATBCTR2		0xef0
+#define ETB_ITATBCTR1		0xef4
+#define ETB_ITATBCTR0		0xef8
+
+/* register description */
+/* STS - 0x00C */
+#define ETB_STATUS_RAM_FULL	BIT(0)
+/* CTL - 0x020 */
+#define ETB_CTL_CAPT_EN		BIT(0)
+/* FFCR - 0x304 */
+#define ETB_FFCR_EN_FTC		BIT(0)
+#define ETB_FFCR_FON_MAN	BIT(6)
+#define ETB_FFCR_STOP_FI	BIT(12)
+#define ETB_FFCR_STOP_TRIGGER	BIT(13)
+
+#define ETB_FFCR_BIT		6
+#define ETB_FFSR_BIT		1
+#define ETB_FRAME_SIZE_WORDS	4
+
+/**
+ * struct etb_drvdata - specifics associated to an ETB component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @miscdev:	specifics to handle "/dev/xyz.etb" entry.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @in_use:	synchronise user space access to etb buffer.
+ * @buf:	area of memory where ETB buffer content gets sent.
+ * @buffer_depth: size of @buf.
+ * @enable:	this ETB is being used.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct etb_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct miscdevice	miscdev;
+	struct clk		*clk;
+	spinlock_t		spinlock;
+	atomic_t		in_use;
+	u8			*buf;
+	u32			buffer_depth;
+	bool			enable;
+	u32			trigger_cntr;
+};
+
+static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata)
+{
+	int ret;
+	u32 depth = 0;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	/* RO registers don't need locking */
+	depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+
+	clk_disable_unprepare(drvdata->clk);
+	return depth;
+}
+
+static void etb_enable_hw(struct etb_drvdata *drvdata)
+{
+	int i;
+	u32 depth;
+
+	CS_UNLOCK(drvdata->base);
+
+	depth = drvdata->buffer_depth;
+	/* reset write RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+	/* clear entire RAM buffer */
+	for (i = 0; i < depth; i++)
+		writel_relaxed(0x0, drvdata->base + ETB_RWD_REG);
+
+	/* reset write RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+	/* reset read RAM pointer address */
+	writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + ETB_TRG);
+	writel_relaxed(ETB_FFCR_EN_FTC | ETB_FFCR_STOP_TRIGGER,
+		       drvdata->base + ETB_FFCR);
+	/* ETB trace capture enable */
+	writel_relaxed(ETB_CTL_CAPT_EN, drvdata->base + ETB_CTL_REG);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int etb_enable(struct coresight_device *csdev)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+	unsigned long flags;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	etb_enable_hw(drvdata);
+	drvdata->enable = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "ETB enabled\n");
+	return 0;
+}
+
+static void etb_disable_hw(struct etb_drvdata *drvdata)
+{
+	u32 ffcr;
+
+	CS_UNLOCK(drvdata->base);
+
+	ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+	/* stop formatter when a stop has completed */
+	ffcr |= ETB_FFCR_STOP_FI;
+	writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+	/* manually generate a flush of the system */
+	ffcr |= ETB_FFCR_FON_MAN;
+	writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+
+	if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			ETB_FFCR);
+	}
+
+	/* disable trace capture */
+	writel_relaxed(0x0, drvdata->base + ETB_CTL_REG);
+
+	if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			ETB_FFCR);
+	}
+
+	CS_LOCK(drvdata->base);
+}
+
+static void etb_dump_hw(struct etb_drvdata *drvdata)
+{
+	int i;
+	u8 *buf_ptr;
+	u32 read_data, depth;
+	u32 read_ptr, write_ptr;
+	u32 frame_off, frame_endoff;
+
+	CS_UNLOCK(drvdata->base);
+
+	read_ptr = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+	write_ptr = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+
+	frame_off = write_ptr % ETB_FRAME_SIZE_WORDS;
+	frame_endoff = ETB_FRAME_SIZE_WORDS - frame_off;
+	if (frame_off) {
+		dev_err(drvdata->dev,
+			"write_ptr: %lu not aligned to formatter frame size\n",
+			(unsigned long)write_ptr);
+		dev_err(drvdata->dev, "frameoff: %lu, frame_endoff: %lu\n",
+			(unsigned long)frame_off, (unsigned long)frame_endoff);
+		write_ptr += frame_endoff;
+	}
+
+	if ((readl_relaxed(drvdata->base + ETB_STATUS_REG)
+		      & ETB_STATUS_RAM_FULL) == 0)
+		writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+	else
+		writel_relaxed(write_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+	depth = drvdata->buffer_depth;
+	buf_ptr = drvdata->buf;
+	for (i = 0; i < depth; i++) {
+		read_data = readl_relaxed(drvdata->base +
+					  ETB_RAM_READ_DATA_REG);
+		*buf_ptr++ = read_data >> 0;
+		*buf_ptr++ = read_data >> 8;
+		*buf_ptr++ = read_data >> 16;
+		*buf_ptr++ = read_data >> 24;
+	}
+
+	if (frame_off) {
+		buf_ptr -= (frame_endoff * 4);
+		for (i = 0; i < frame_endoff; i++) {
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+			*buf_ptr++ = 0x0;
+		}
+	}
+
+	writel_relaxed(read_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void etb_disable(struct coresight_device *csdev)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	etb_disable_hw(drvdata);
+	etb_dump_hw(drvdata);
+	drvdata->enable = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "ETB disabled\n");
+}
+
+static const struct coresight_ops_sink etb_sink_ops = {
+	.enable		= etb_enable,
+	.disable	= etb_disable,
+};
+
+static const struct coresight_ops etb_cs_ops = {
+	.sink_ops	= &etb_sink_ops,
+};
+
+static void etb_dump(struct etb_drvdata *drvdata)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->enable) {
+		etb_disable_hw(drvdata);
+		etb_dump_hw(drvdata);
+		etb_enable_hw(drvdata);
+	}
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "ETB dumped\n");
+}
+
+static int etb_open(struct inode *inode, struct file *file)
+{
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+
+	if (atomic_cmpxchg(&drvdata->in_use, 0, 1))
+		return -EBUSY;
+
+	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	return 0;
+}
+
+static ssize_t etb_read(struct file *file, char __user *data,
+				size_t len, loff_t *ppos)
+{
+	u32 depth;
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+
+	etb_dump(drvdata);
+
+	depth = drvdata->buffer_depth;
+	if (*ppos + len > depth * 4)
+		len = depth * 4 - *ppos;
+
+	if (copy_to_user(data, drvdata->buf + *ppos, len)) {
+		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		return -EFAULT;
+	}
+
+	*ppos += len;
+
+	dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n",
+		__func__, len, (int) (depth * 4 - *ppos));
+	return len;
+}
+
+static int etb_release(struct inode *inode, struct file *file)
+{
+	struct etb_drvdata *drvdata = container_of(file->private_data,
+						   struct etb_drvdata, miscdev);
+	atomic_set(&drvdata->in_use, 0);
+
+	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	return 0;
+}
+
+static const struct file_operations etb_fops = {
+	.owner		= THIS_MODULE,
+	.open		= etb_open,
+	.read		= etb_read,
+	.release	= etb_release,
+	.llseek		= no_llseek,
+};
+
+static ssize_t status_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags;
+	u32 etb_rdr, etb_sr, etb_rrp, etb_rwp;
+	u32 etb_trg, etb_cr, etb_ffsr, etb_ffcr;
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		goto out;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	etb_rdr = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+	etb_sr = readl_relaxed(drvdata->base + ETB_STATUS_REG);
+	etb_rrp = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+	etb_rwp = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+	etb_trg = readl_relaxed(drvdata->base + ETB_TRG);
+	etb_cr = readl_relaxed(drvdata->base + ETB_CTL_REG);
+	etb_ffsr = readl_relaxed(drvdata->base + ETB_FFSR);
+	etb_ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf,
+		       "Depth:\t\t0x%x\n"
+		       "Status:\t\t0x%x\n"
+		       "RAM read ptr:\t0x%x\n"
+		       "RAM wrt ptr:\t0x%x\n"
+		       "Trigger cnt:\t0x%x\n"
+		       "Control:\t0x%x\n"
+		       "Flush status:\t0x%x\n"
+		       "Flush ctrl:\t0x%x\n",
+		       etb_rdr, etb_sr, etb_rrp, etb_rwp,
+		       etb_trg, etb_cr, etb_ffsr, etb_ffcr);
+out:
+	return -EINVAL;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t trigger_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->trigger_cntr;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_cntr = val;
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	&dev_attr_status.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static int etb_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct etb_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	drvdata->buffer_depth =  etb_get_buffer_depth(drvdata);
+	clk_disable_unprepare(drvdata->clk);
+
+	if (drvdata->buffer_depth < 0)
+		return -EINVAL;
+
+	drvdata->buf = devm_kzalloc(dev,
+				    drvdata->buffer_depth * 4, GFP_KERNEL);
+	if (!drvdata->buf)
+		return -ENOMEM;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_SINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+	desc->ops = &etb_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_etb_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+	drvdata->miscdev.fops = &etb_fops;
+	ret = misc_register(&drvdata->miscdev);
+	if (ret)
+		goto err_misc_register;
+
+	dev_info(dev, "ETB initialized\n");
+	return 0;
+
+err_misc_register:
+	coresight_unregister(drvdata->csdev);
+	return ret;
+}
+
+static int etb_remove(struct amba_device *adev)
+{
+	struct etb_drvdata *drvdata = amba_get_drvdata(adev);
+
+	misc_deregister(&drvdata->miscdev);
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id etb_ids[] = {
+	{
+		.id	= 0x0003b907,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver etb_driver = {
+	.drv = {
+		.name	= "coresight-etb10",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= etb_probe,
+	.remove		= etb_remove,
+	.id_table	= etb_ids,
+};
+
+static int __init etb_init(void)
+{
+	return amba_driver_register(&etb_driver);
+}
+module_init(etb_init);
+
+static void __exit etb_exit(void)
+{
+	amba_driver_unregister(&etb_driver);
+}
+module_exit(etb_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Embedded Trace Buffer driver");
diff --git a/drivers/coresight/coresight-etm-cp14.c b/drivers/coresight/coresight-etm-cp14.c
new file mode 100644
index 000000000000..12a220682117
--- /dev/null
+++ b/drivers/coresight/coresight-etm-cp14.c
@@ -0,0 +1,591 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <asm/hardware/cp14.h>
+
+#include "coresight-etm.h"
+
+int etm_readl_cp14(u32 reg, unsigned int *val)
+{
+	switch (reg) {
+	case ETMCR:
+		*val = etm_read(ETMCR);
+		return 0;
+	case ETMCCR:
+		*val = etm_read(ETMCCR);
+		return 0;
+	case ETMTRIGGER:
+		*val = etm_read(ETMTRIGGER);
+		return 0;
+	case ETMSR:
+		*val = etm_read(ETMSR);
+		return 0;
+	case ETMSCR:
+		*val = etm_read(ETMSCR);
+		return 0;
+	case ETMTSSCR:
+		*val = etm_read(ETMTSSCR);
+		return 0;
+	case ETMTEEVR:
+		*val = etm_read(ETMTEEVR);
+		return 0;
+	case ETMTECR1:
+		*val = etm_read(ETMTECR1);
+		return 0;
+	case ETMFFLR:
+		*val = etm_read(ETMFFLR);
+		return 0;
+	case ETMACVRn(0):
+		*val = etm_read(ETMACVR0);
+		return 0;
+	case ETMACVRn(1):
+		*val = etm_read(ETMACVR1);
+		return 0;
+	case ETMACVRn(2):
+		*val = etm_read(ETMACVR2);
+		return 0;
+	case ETMACVRn(3):
+		*val = etm_read(ETMACVR3);
+		return 0;
+	case ETMACVRn(4):
+		*val = etm_read(ETMACVR4);
+		return 0;
+	case ETMACVRn(5):
+		*val = etm_read(ETMACVR5);
+		return 0;
+	case ETMACVRn(6):
+		*val = etm_read(ETMACVR6);
+		return 0;
+	case ETMACVRn(7):
+		*val = etm_read(ETMACVR7);
+		return 0;
+	case ETMACVRn(8):
+		*val = etm_read(ETMACVR8);
+		return 0;
+	case ETMACVRn(9):
+		*val = etm_read(ETMACVR9);
+		return 0;
+	case ETMACVRn(10):
+		*val = etm_read(ETMACVR10);
+		return 0;
+	case ETMACVRn(11):
+		*val = etm_read(ETMACVR11);
+		return 0;
+	case ETMACVRn(12):
+		*val = etm_read(ETMACVR12);
+		return 0;
+	case ETMACVRn(13):
+		*val = etm_read(ETMACVR13);
+		return 0;
+	case ETMACVRn(14):
+		*val = etm_read(ETMACVR14);
+		return 0;
+	case ETMACVRn(15):
+		*val = etm_read(ETMACVR15);
+		return 0;
+	case ETMACTRn(0):
+		*val = etm_read(ETMACTR0);
+		return 0;
+	case ETMACTRn(1):
+		*val = etm_read(ETMACTR1);
+		return 0;
+	case ETMACTRn(2):
+		*val = etm_read(ETMACTR2);
+		return 0;
+	case ETMACTRn(3):
+		*val = etm_read(ETMACTR3);
+		return 0;
+	case ETMACTRn(4):
+		*val = etm_read(ETMACTR4);
+		return 0;
+	case ETMACTRn(5):
+		*val = etm_read(ETMACTR5);
+		return 0;
+	case ETMACTRn(6):
+		*val = etm_read(ETMACTR6);
+		return 0;
+	case ETMACTRn(7):
+		*val = etm_read(ETMACTR7);
+		return 0;
+	case ETMACTRn(8):
+		*val = etm_read(ETMACTR8);
+		return 0;
+	case ETMACTRn(9):
+		*val = etm_read(ETMACTR9);
+		return 0;
+	case ETMACTRn(10):
+		*val = etm_read(ETMACTR10);
+		return 0;
+	case ETMACTRn(11):
+		*val = etm_read(ETMACTR11);
+		return 0;
+	case ETMACTRn(12):
+		*val = etm_read(ETMACTR12);
+		return 0;
+	case ETMACTRn(13):
+		*val = etm_read(ETMACTR13);
+		return 0;
+	case ETMACTRn(14):
+		*val = etm_read(ETMACTR14);
+		return 0;
+	case ETMACTRn(15):
+		*val = etm_read(ETMACTR15);
+		return 0;
+	case ETMCNTRLDVRn(0):
+		*val = etm_read(ETMCNTRLDVR0);
+		return 0;
+	case ETMCNTRLDVRn(1):
+		*val = etm_read(ETMCNTRLDVR1);
+		return 0;
+	case ETMCNTRLDVRn(2):
+		*val = etm_read(ETMCNTRLDVR2);
+		return 0;
+	case ETMCNTRLDVRn(3):
+		*val = etm_read(ETMCNTRLDVR3);
+		return 0;
+	case ETMCNTENRn(0):
+		*val = etm_read(ETMCNTENR0);
+		return 0;
+	case ETMCNTENRn(1):
+		*val = etm_read(ETMCNTENR1);
+		return 0;
+	case ETMCNTENRn(2):
+		*val = etm_read(ETMCNTENR2);
+		return 0;
+	case ETMCNTENRn(3):
+		*val = etm_read(ETMCNTENR3);
+		return 0;
+	case ETMCNTRLDEVRn(0):
+		*val = etm_read(ETMCNTRLDEVR0);
+		return 0;
+	case ETMCNTRLDEVRn(1):
+		*val = etm_read(ETMCNTRLDEVR1);
+		return 0;
+	case ETMCNTRLDEVRn(2):
+		*val = etm_read(ETMCNTRLDEVR2);
+		return 0;
+	case ETMCNTRLDEVRn(3):
+		*val = etm_read(ETMCNTRLDEVR3);
+		return 0;
+	case ETMCNTVRn(0):
+		*val = etm_read(ETMCNTVR0);
+		return 0;
+	case ETMCNTVRn(1):
+		*val = etm_read(ETMCNTVR1);
+		return 0;
+	case ETMCNTVRn(2):
+		*val = etm_read(ETMCNTVR2);
+		return 0;
+	case ETMCNTVRn(3):
+		*val = etm_read(ETMCNTVR3);
+		return 0;
+	case ETMSQ12EVR:
+		*val = etm_read(ETMSQ12EVR);
+		return 0;
+	case ETMSQ21EVR:
+		*val = etm_read(ETMSQ21EVR);
+		return 0;
+	case ETMSQ23EVR:
+		*val = etm_read(ETMSQ23EVR);
+		return 0;
+	case ETMSQ31EVR:
+		*val = etm_read(ETMSQ31EVR);
+		return 0;
+	case ETMSQ32EVR:
+		*val = etm_read(ETMSQ32EVR);
+		return 0;
+	case ETMSQ13EVR:
+		*val = etm_read(ETMSQ13EVR);
+		return 0;
+	case ETMSQR:
+		*val = etm_read(ETMSQR);
+		return 0;
+	case ETMEXTOUTEVRn(0):
+		*val = etm_read(ETMEXTOUTEVR0);
+		return 0;
+	case ETMEXTOUTEVRn(1):
+		*val = etm_read(ETMEXTOUTEVR1);
+		return 0;
+	case ETMEXTOUTEVRn(2):
+		*val = etm_read(ETMEXTOUTEVR2);
+		return 0;
+	case ETMEXTOUTEVRn(3):
+		*val = etm_read(ETMEXTOUTEVR3);
+		return 0;
+	case ETMCIDCVRn(0):
+		*val = etm_read(ETMCIDCVR0);
+		return 0;
+	case ETMCIDCVRn(1):
+		*val = etm_read(ETMCIDCVR1);
+		return 0;
+	case ETMCIDCVRn(2):
+		*val = etm_read(ETMCIDCVR2);
+		return 0;
+	case ETMCIDCMR:
+		*val = etm_read(ETMCIDCMR);
+		return 0;
+	case ETMIMPSPEC0:
+		*val = etm_read(ETMIMPSPEC0);
+		return 0;
+	case ETMIMPSPEC1:
+		*val = etm_read(ETMIMPSPEC1);
+		return 0;
+	case ETMIMPSPEC2:
+		*val = etm_read(ETMIMPSPEC2);
+		return 0;
+	case ETMIMPSPEC3:
+		*val = etm_read(ETMIMPSPEC3);
+		return 0;
+	case ETMIMPSPEC4:
+		*val = etm_read(ETMIMPSPEC4);
+		return 0;
+	case ETMIMPSPEC5:
+		*val = etm_read(ETMIMPSPEC5);
+		return 0;
+	case ETMIMPSPEC6:
+		*val = etm_read(ETMIMPSPEC6);
+		return 0;
+	case ETMIMPSPEC7:
+		*val = etm_read(ETMIMPSPEC7);
+		return 0;
+	case ETMSYNCFR:
+		*val = etm_read(ETMSYNCFR);
+		return 0;
+	case ETMIDR:
+		*val = etm_read(ETMIDR);
+		return 0;
+	case ETMCCER:
+		*val = etm_read(ETMCCER);
+		return 0;
+	case ETMEXTINSELR:
+		*val = etm_read(ETMEXTINSELR);
+		return 0;
+	case ETMTESSEICR:
+		*val = etm_read(ETMTESSEICR);
+		return 0;
+	case ETMEIBCR:
+		*val = etm_read(ETMEIBCR);
+		return 0;
+	case ETMTSEVR:
+		*val = etm_read(ETMTSEVR);
+		return 0;
+	case ETMAUXCR:
+		*val = etm_read(ETMAUXCR);
+		return 0;
+	case ETMTRACEIDR:
+		*val = etm_read(ETMTRACEIDR);
+		return 0;
+	case ETMVMIDCVR:
+		*val = etm_read(ETMVMIDCVR);
+		return 0;
+	case ETMOSLSR:
+		*val = etm_read(ETMOSLSR);
+		return 0;
+	case ETMOSSRR:
+		*val = etm_read(ETMOSSRR);
+		return 0;
+	case ETMPDCR:
+		*val = etm_read(ETMPDCR);
+		return 0;
+	case ETMPDSR:
+		*val = etm_read(ETMPDSR);
+		return 0;
+	default:
+		*val = 0;
+		return -EINVAL;
+	}
+}
+
+int etm_writel_cp14(u32 reg, u32 val)
+{
+	switch (reg) {
+	case ETMCR:
+		etm_write(val, ETMCR);
+		break;
+	case ETMTRIGGER:
+		etm_write(val, ETMTRIGGER);
+		break;
+	case ETMSR:
+		etm_write(val, ETMSR);
+		break;
+	case ETMTSSCR:
+		etm_write(val, ETMTSSCR);
+		break;
+	case ETMTEEVR:
+		etm_write(val, ETMTEEVR);
+		break;
+	case ETMTECR1:
+		etm_write(val, ETMTECR1);
+		break;
+	case ETMFFLR:
+		etm_write(val, ETMFFLR);
+		break;
+	case ETMACVRn(0):
+		etm_write(val, ETMACVR0);
+		break;
+	case ETMACVRn(1):
+		etm_write(val, ETMACVR1);
+		break;
+	case ETMACVRn(2):
+		etm_write(val, ETMACVR2);
+		break;
+	case ETMACVRn(3):
+		etm_write(val, ETMACVR3);
+		break;
+	case ETMACVRn(4):
+		etm_write(val, ETMACVR4);
+		break;
+	case ETMACVRn(5):
+		etm_write(val, ETMACVR5);
+		break;
+	case ETMACVRn(6):
+		etm_write(val, ETMACVR6);
+		break;
+	case ETMACVRn(7):
+		etm_write(val, ETMACVR7);
+		break;
+	case ETMACVRn(8):
+		etm_write(val, ETMACVR8);
+		break;
+	case ETMACVRn(9):
+		etm_write(val, ETMACVR9);
+		break;
+	case ETMACVRn(10):
+		etm_write(val, ETMACVR10);
+		break;
+	case ETMACVRn(11):
+		etm_write(val, ETMACVR11);
+		break;
+	case ETMACVRn(12):
+		etm_write(val, ETMACVR12);
+		break;
+	case ETMACVRn(13):
+		etm_write(val, ETMACVR13);
+		break;
+	case ETMACVRn(14):
+		etm_write(val, ETMACVR14);
+		break;
+	case ETMACVRn(15):
+		etm_write(val, ETMACVR15);
+		break;
+	case ETMACTRn(0):
+		etm_write(val, ETMACTR0);
+		break;
+	case ETMACTRn(1):
+		etm_write(val, ETMACTR1);
+		break;
+	case ETMACTRn(2):
+		etm_write(val, ETMACTR2);
+		break;
+	case ETMACTRn(3):
+		etm_write(val, ETMACTR3);
+		break;
+	case ETMACTRn(4):
+		etm_write(val, ETMACTR4);
+		break;
+	case ETMACTRn(5):
+		etm_write(val, ETMACTR5);
+		break;
+	case ETMACTRn(6):
+		etm_write(val, ETMACTR6);
+		break;
+	case ETMACTRn(7):
+		etm_write(val, ETMACTR7);
+		break;
+	case ETMACTRn(8):
+		etm_write(val, ETMACTR8);
+		break;
+	case ETMACTRn(9):
+		etm_write(val, ETMACTR9);
+		break;
+	case ETMACTRn(10):
+		etm_write(val, ETMACTR10);
+		break;
+	case ETMACTRn(11):
+		etm_write(val, ETMACTR11);
+		break;
+	case ETMACTRn(12):
+		etm_write(val, ETMACTR12);
+		break;
+	case ETMACTRn(13):
+		etm_write(val, ETMACTR13);
+		break;
+	case ETMACTRn(14):
+		etm_write(val, ETMACTR14);
+		break;
+	case ETMACTRn(15):
+		etm_write(val, ETMACTR15);
+		break;
+	case ETMCNTRLDVRn(0):
+		etm_write(val, ETMCNTRLDVR0);
+		break;
+	case ETMCNTRLDVRn(1):
+		etm_write(val, ETMCNTRLDVR1);
+		break;
+	case ETMCNTRLDVRn(2):
+		etm_write(val, ETMCNTRLDVR2);
+		break;
+	case ETMCNTRLDVRn(3):
+		etm_write(val, ETMCNTRLDVR3);
+		break;
+	case ETMCNTENRn(0):
+		etm_write(val, ETMCNTENR0);
+		break;
+	case ETMCNTENRn(1):
+		etm_write(val, ETMCNTENR1);
+		break;
+	case ETMCNTENRn(2):
+		etm_write(val, ETMCNTENR2);
+		break;
+	case ETMCNTENRn(3):
+		etm_write(val, ETMCNTENR3);
+		break;
+	case ETMCNTRLDEVRn(0):
+		etm_write(val, ETMCNTRLDEVR0);
+		break;
+	case ETMCNTRLDEVRn(1):
+		etm_write(val, ETMCNTRLDEVR1);
+		break;
+	case ETMCNTRLDEVRn(2):
+		etm_write(val, ETMCNTRLDEVR2);
+		break;
+	case ETMCNTRLDEVRn(3):
+		etm_write(val, ETMCNTRLDEVR3);
+		break;
+	case ETMCNTVRn(0):
+		etm_write(val, ETMCNTVR0);
+		break;
+	case ETMCNTVRn(1):
+		etm_write(val, ETMCNTVR1);
+		break;
+	case ETMCNTVRn(2):
+		etm_write(val, ETMCNTVR2);
+		break;
+	case ETMCNTVRn(3):
+		etm_write(val, ETMCNTVR3);
+		break;
+	case ETMSQ12EVR:
+		etm_write(val, ETMSQ12EVR);
+		break;
+	case ETMSQ21EVR:
+		etm_write(val, ETMSQ21EVR);
+		break;
+	case ETMSQ23EVR:
+		etm_write(val, ETMSQ23EVR);
+		break;
+	case ETMSQ31EVR:
+		etm_write(val, ETMSQ31EVR);
+		break;
+	case ETMSQ32EVR:
+		etm_write(val, ETMSQ32EVR);
+		break;
+	case ETMSQ13EVR:
+		etm_write(val, ETMSQ13EVR);
+		break;
+	case ETMSQR:
+		etm_write(val, ETMSQR);
+		break;
+	case ETMEXTOUTEVRn(0):
+		etm_write(val, ETMEXTOUTEVR0);
+		break;
+	case ETMEXTOUTEVRn(1):
+		etm_write(val, ETMEXTOUTEVR1);
+		break;
+	case ETMEXTOUTEVRn(2):
+		etm_write(val, ETMEXTOUTEVR2);
+		break;
+	case ETMEXTOUTEVRn(3):
+		etm_write(val, ETMEXTOUTEVR3);
+		break;
+	case ETMCIDCVRn(0):
+		etm_write(val, ETMCIDCVR0);
+		break;
+	case ETMCIDCVRn(1):
+		etm_write(val, ETMCIDCVR1);
+		break;
+	case ETMCIDCVRn(2):
+		etm_write(val, ETMCIDCVR2);
+		break;
+	case ETMCIDCMR:
+		etm_write(val, ETMCIDCMR);
+		break;
+	case ETMIMPSPEC0:
+		etm_write(val, ETMIMPSPEC0);
+		break;
+	case ETMIMPSPEC1:
+		etm_write(val, ETMIMPSPEC1);
+		break;
+	case ETMIMPSPEC2:
+		etm_write(val, ETMIMPSPEC2);
+		break;
+	case ETMIMPSPEC3:
+		etm_write(val, ETMIMPSPEC3);
+		break;
+	case ETMIMPSPEC4:
+		etm_write(val, ETMIMPSPEC4);
+		break;
+	case ETMIMPSPEC5:
+		etm_write(val, ETMIMPSPEC5);
+		break;
+	case ETMIMPSPEC6:
+		etm_write(val, ETMIMPSPEC6);
+		break;
+	case ETMIMPSPEC7:
+		etm_write(val, ETMIMPSPEC7);
+		break;
+	case ETMSYNCFR:
+		etm_write(val, ETMSYNCFR);
+		break;
+	case ETMEXTINSELR:
+		etm_write(val, ETMEXTINSELR);
+		break;
+	case ETMTESSEICR:
+		etm_write(val, ETMTESSEICR);
+		break;
+	case ETMEIBCR:
+		etm_write(val, ETMEIBCR);
+		break;
+	case ETMTSEVR:
+		etm_write(val, ETMTSEVR);
+		break;
+	case ETMAUXCR:
+		etm_write(val, ETMAUXCR);
+		break;
+	case ETMTRACEIDR:
+		etm_write(val, ETMTRACEIDR);
+		break;
+	case ETMVMIDCVR:
+		etm_write(val, ETMVMIDCVR);
+		break;
+	case ETMOSLAR:
+		etm_write(val, ETMOSLAR);
+		break;
+	case ETMOSSRR:
+		etm_write(val, ETMOSSRR);
+		break;
+	case ETMPDCR:
+		etm_write(val, ETMPDCR);
+		break;
+	case ETMPDSR:
+		etm_write(val, ETMPDSR);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/coresight/coresight-etm.h b/drivers/coresight/coresight-etm.h
new file mode 100644
index 000000000000..501c5fac8a45
--- /dev/null
+++ b/drivers/coresight/coresight-etm.h
@@ -0,0 +1,251 @@
+/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_CORESIGHT_ETM_H
+#define _CORESIGHT_CORESIGHT_ETM_H
+
+#include <linux/spinlock.h>
+#include "coresight-priv.h"
+
+/*
+ * Device registers:
+ * 0x000 - 0x2FC: Trace         registers
+ * 0x300 - 0x314: Management    registers
+ * 0x318 - 0xEFC: Trace         registers
+ *
+ * Coresight registers
+ * 0xF00 - 0xF9C: Management    registers
+ * 0xFA0 - 0xFA4: Management    registers in PFTv1.0
+ *                Trace         registers in PFTv1.1
+ * 0xFA8 - 0xFFC: Management    registers
+ */
+
+/* Trace registers (0x000-0x2FC) */
+#define ETMCR			0x000
+#define ETMCCR			0x004
+#define ETMTRIGGER		0x008
+#define ETMSR			0x010
+#define ETMSCR			0x014
+#define ETMTSSCR		0x018
+#define ETMTECR2		0x01c
+#define ETMTEEVR		0x020
+#define ETMTECR1		0x024
+#define ETMFFLR			0x02c
+#define ETMACVRn(n)		(0x040 + (n * 4))
+#define ETMACTRn(n)		(0x080 + (n * 4))
+#define ETMCNTRLDVRn(n)		(0x140 + (n * 4))
+#define ETMCNTENRn(n)		(0x150 + (n * 4))
+#define ETMCNTRLDEVRn(n)	(0x160 + (n * 4))
+#define ETMCNTVRn(n)		(0x170 + (n * 4))
+#define ETMSQ12EVR		0x180
+#define ETMSQ21EVR		0x184
+#define ETMSQ23EVR		0x188
+#define ETMSQ31EVR		0x18c
+#define ETMSQ32EVR		0x190
+#define ETMSQ13EVR		0x194
+#define ETMSQR			0x19c
+#define ETMEXTOUTEVRn(n)	(0x1a0 + (n * 4))
+#define ETMCIDCVRn(n)		(0x1b0 + (n * 4))
+#define ETMCIDCMR		0x1bc
+#define ETMIMPSPEC0		0x1c0
+#define ETMIMPSPEC1		0x1c4
+#define ETMIMPSPEC2		0x1c8
+#define ETMIMPSPEC3		0x1cc
+#define ETMIMPSPEC4		0x1d0
+#define ETMIMPSPEC5		0x1d4
+#define ETMIMPSPEC6		0x1d8
+#define ETMIMPSPEC7		0x1dc
+#define ETMSYNCFR		0x1e0
+#define ETMIDR			0x1e4
+#define ETMCCER			0x1e8
+#define ETMEXTINSELR		0x1ec
+#define ETMTESSEICR		0x1f0
+#define ETMEIBCR		0x1f4
+#define ETMTSEVR		0x1f8
+#define ETMAUXCR		0x1fc
+#define ETMTRACEIDR		0x200
+#define ETMVMIDCVR		0x240
+/* Management registers (0x300-0x314) */
+#define ETMOSLAR		0x300
+#define ETMOSLSR		0x304
+#define ETMOSSRR		0x308
+#define ETMPDCR			0x310
+#define ETMPDSR			0x314
+#define ETM_MAX_ADDR_CMP	16
+#define ETM_MAX_CNTR		4
+#define ETM_MAX_CTXID_CMP	3
+
+/* Register definition */
+/* ETMCR - 0x00 */
+#define ETMCR_PWD_DWN		BIT(0)
+#define ETMCR_STALL_MODE	BIT(7)
+#define ETMCR_ETM_PRG		BIT(10)
+#define ETMCR_ETM_EN		BIT(11)
+#define ETMCR_CYC_ACC		BIT(12)
+#define ETMCR_CTXID_SIZE	(BIT(14)|BIT(15))
+#define ETMCR_TIMESTAMP_EN	BIT(28)
+/* ETMCCR - 0x04 */
+#define ETMCCR_FIFOFULL		BIT(23)
+/* ETMPDCR - 0x310 */
+#define ETMPDCR_PWD_UP		BIT(3)
+/* ETMTECR1 - 0x024 */
+#define ETMTECR1_ADDR_COMP_1	BIT(0)
+#define ETMTECR1_INC_EXC	BIT(24)
+#define ETMTECR1_START_STOP	BIT(25)
+/* ETMCCER - 0x1E8 */
+#define ETMCCER_TIMESTAMP	BIT(22)
+
+#define ETM_MODE_EXCLUDE	BIT(0)
+#define ETM_MODE_CYCACC		BIT(1)
+#define ETM_MODE_STALL		BIT(2)
+#define ETM_MODE_TIMESTAMP	BIT(3)
+#define ETM_MODE_CTXID		BIT(4)
+#define ETM_MODE_ALL		0x1f
+
+#define ETM_SQR_MASK		0x3
+#define ETM_TRACEID_MASK	0x3f
+#define ETM_EVENT_MASK		0x1ffff
+#define ETM_SYNC_MASK		0xfff
+#define ETM_ALL_MASK		0xffffffff
+
+#define ETMSR_PROG_BIT		1
+#define ETM_SEQ_STATE_MAX_VAL	(0x2)
+#define PORT_SIZE_MASK		(GENMASK(21, 21) | GENMASK(6, 4))
+
+#define ETM_HARD_WIRE_RES_A	/* Hard wired, always true */	\
+				((0x0f << 0)	|		\
+				/* Resource index A */		\
+				(0x06 << 4))
+
+#define ETM_ADD_COMP_0		/* Single addr comparator 1 */	\
+				((0x00 << 7)	|		\
+				/* Resource index B */		\
+				(0x00 << 11))
+
+#define ETM_EVENT_NOT_A		BIT(14) /* NOT(A) */
+
+#define ETM_DEFAULT_EVENT_VAL	(ETM_HARD_WIRE_RES_A	|	\
+				 ETM_ADD_COMP_0		|	\
+				 ETM_EVENT_NOT_A)
+/**
+ * struct etm_drvdata - specifics associated to an ETM component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @cpu:	the cpu this component is affined to.
+ * @port_size:	port size as reported by ETMCR bit 4-6 and 21.
+ * @arch:	ETM/PTM version number.
+ * @use_cpu14:	true if management registers need to be accessed via CP14.
+ * @enable:	is this ETM/PTM currently tracing.
+ * @sticky_enable: true if ETM base configuration has been done.
+ * @boot_enable:true if we should start tracing at boot time.
+ * @os_unlock:	true if access to management registers is allowed.
+ * @nr_addr_cmp:Number of pairs of address comparators as found in ETMCCR.
+ * @nr_cntr:	Number of counters as found in ETMCCR bit 13-15.
+ * @nr_ext_inp:	Number of external input as found in ETMCCR bit 17-19.
+ * @nr_ext_out:	Number of external output as found in ETMCCR bit 20-22.
+ * @nr_ctxid_cmp: Number of contextID comparators as found in ETMCCR bit 24-25.
+ * @etmccr:	value of register ETMCCR.
+ * @etmccer:	value of register ETMCCER.
+ * @traceid:	value of the current ID for this component.
+ * @mode:	controls various modes supported by this ETM/PTM.
+ * @ctrl:	used in conjunction with @mode.
+ * @trigger_event: setting for register ETMTRIGGER.
+ * @startstop_ctrl: setting for register ETMTSSCR.
+ * @enable_event: setting for register ETMTEEVR.
+ * @enable_ctrl1: setting for register ETMTECR1.
+ * @fifofull_level: setting for register ETMFFLR.
+ * @addr_idx:	index for the address comparator selection.
+ * @addr_val:	value for address comparator register.
+ * @addr_acctype: access type for address comparator register.
+ * @addr_type:	current status of the comparator register.
+ * @cntr_idx:	index for the counter register selection.
+ * @cntr_rld_val: reload value of a counter register.
+ * @cntr_event:	control for counter enable register.
+ * @cntr_rld_event: value for counter reload event register.
+ * @cntr_val:	counter value register.
+ * @seq_12_event: event causing the transition from 1 to 2.
+ * @seq_21_event: event causing the transition from 2 to 1.
+ * @seq_23_event: event causing the transition from 2 to 3.
+ * @seq_31_event: event causing the transition from 3 to 1.
+ * @seq_32_event: event causing the transition from 3 to 2.
+ * @seq_13_event: event causing the transition from 1 to 3.
+ * @seq_curr_state: current value of the sequencer register.
+ * @ctxid_idx: index for the context ID registers.
+ * @ctxid_val: value for the context ID to trigger on.
+ * @ctxid_mask: mask applicable to all the context IDs.
+ * @sync_freq:	Synchronisation frequency.
+ * @timestamp_event: Defines an event that requests the insertion
+		     of a timestamp into the trace stream.
+ */
+struct etm_drvdata {
+	void __iomem			*base;
+	struct device			*dev;
+	struct coresight_device		*csdev;
+	struct clk			*clk;
+	spinlock_t			spinlock;
+	int				cpu;
+	int				port_size;
+	u8				arch;
+	bool				use_cp14;
+	bool				enable;
+	bool				sticky_enable;
+	bool				boot_enable;
+	bool				os_unlock;
+	u8				nr_addr_cmp;
+	u8				nr_cntr;
+	u8				nr_ext_inp;
+	u8				nr_ext_out;
+	u8				nr_ctxid_cmp;
+	u32				etmccr;
+	u32				etmccer;
+	u32				traceid;
+	u32				mode;
+	u32				ctrl;
+	u32				trigger_event;
+	u32				startstop_ctrl;
+	u32				enable_event;
+	u32				enable_ctrl1;
+	u32				fifofull_level;
+	u8				addr_idx;
+	u32				addr_val[ETM_MAX_ADDR_CMP];
+	u32				addr_acctype[ETM_MAX_ADDR_CMP];
+	u32				addr_type[ETM_MAX_ADDR_CMP];
+	u8				cntr_idx;
+	u32				cntr_rld_val[ETM_MAX_CNTR];
+	u32				cntr_event[ETM_MAX_CNTR];
+	u32				cntr_rld_event[ETM_MAX_CNTR];
+	u32				cntr_val[ETM_MAX_CNTR];
+	u32				seq_12_event;
+	u32				seq_21_event;
+	u32				seq_23_event;
+	u32				seq_31_event;
+	u32				seq_32_event;
+	u32				seq_13_event;
+	u32				seq_curr_state;
+	u8				ctxid_idx;
+	u32				ctxid_val[ETM_MAX_CTXID_CMP];
+	u32				ctxid_mask;
+	u32				sync_freq;
+	u32				timestamp_event;
+};
+
+enum etm_addr_type {
+	ETM_ADDR_TYPE_NONE,
+	ETM_ADDR_TYPE_SINGLE,
+	ETM_ADDR_TYPE_RANGE,
+	ETM_ADDR_TYPE_START,
+	ETM_ADDR_TYPE_STOP,
+};
+#endif
diff --git a/drivers/coresight/coresight-etm3x.c b/drivers/coresight/coresight-etm3x.c
new file mode 100644
index 000000000000..d9e3ed6aa857
--- /dev/null
+++ b/drivers/coresight/coresight-etm3x.c
@@ -0,0 +1,1928 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/stat.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+
+#include "coresight-etm.h"
+
+#ifdef CONFIG_CORESIGHT_SOURCE_ETM_DEFAULT_ENABLE
+static int boot_enable = 1;
+#else
+static int boot_enable;
+#endif
+module_param_named(
+	boot_enable, boot_enable, int, S_IRUGO
+);
+
+/* The number of ETM/PTM currently registered */
+static int etm_count;
+static struct etm_drvdata *etmdrvdata[NR_CPUS];
+
+static inline void etm_writel(struct etm_drvdata *drvdata,
+			      u32 val, u32 off)
+{
+	if (drvdata->use_cp14) {
+		if (etm_writel_cp14(off, val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		writel_relaxed(val, drvdata->base + off);
+	}
+}
+
+static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off)
+{
+	u32 val;
+
+	if (drvdata->use_cp14) {
+		if (etm_readl_cp14(off, &val)) {
+			dev_err(drvdata->dev,
+				"invalid CP14 access to ETM reg: %#x", off);
+		}
+	} else {
+		val = readl_relaxed(drvdata->base + off);
+	}
+
+	return val;
+}
+
+/*
+ * Memory mapped writes to clear os lock are not supported on some processors
+ * and OS lock must be unlocked before any memory mapped access on such
+ * processors, otherwise memory mapped reads/writes will be invalid.
+ */
+static void etm_os_unlock(void *info)
+{
+	struct etm_drvdata *drvdata = (struct etm_drvdata *)info;
+	/* Writing any value to ETMOSLAR unlocks the trace registers */
+	etm_writel(drvdata, 0x0, ETMOSLAR);
+	isb();
+}
+
+static void etm_set_pwrdwn(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	/* Ensure pending cp14 accesses complete before setting pwrdwn */
+	mb();
+	isb();
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr |= ETMCR_PWD_DWN;
+	etm_writel(drvdata, etmcr, ETMCR);
+}
+
+static void etm_clr_pwrdwn(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= ~ETMCR_PWD_DWN;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/* Ensure pwrup completes before subsequent cp14 accesses */
+	mb();
+	isb();
+}
+
+static void etm_set_pwrup(struct etm_drvdata *drvdata)
+{
+	u32 etmpdcr;
+
+	etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+	etmpdcr |= ETMPDCR_PWD_UP;
+	writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+	/* Ensure pwrup completes before subsequent cp14 accesses */
+	mb();
+	isb();
+}
+
+static void etm_clr_pwrup(struct etm_drvdata *drvdata)
+{
+	u32 etmpdcr;
+
+	/* Ensure pending cp14 accesses complete before clearing pwrup */
+	mb();
+	isb();
+	etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+	etmpdcr &= ~ETMPDCR_PWD_UP;
+	writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+}
+
+/**
+ * coresight_timeout_etm - loop until a bit has changed to a specific state.
+ * @drvdata: etm's private data structure.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Basically the same as @coresight_timeout except for the register access
+ * method where we have to account for CP14 configurations.
+
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+static int coresight_timeout_etm(struct etm_drvdata *drvdata, u32 offset,
+				  int position, int value)
+{
+	int i;
+	u32 val;
+
+	for (i = TIMEOUT_US; i > 0; i--) {
+		val = etm_readl(drvdata, offset);
+		/* Waiting on the bit to go from 0 to 1 */
+		if (value) {
+			if (val & BIT(position))
+				return 0;
+		/* Waiting on the bit to go from 1 to 0 */
+		} else {
+			if (!(val & BIT(position)))
+				return 0;
+		}
+
+		/*
+		 * Delay is arbitrary - the specification doesn't say how long
+		 * we are expected to wait.  Extra check required to make sure
+		 * we don't wait needlessly on the last iteration.
+		 */
+		if (i - 1)
+			udelay(1);
+	}
+
+	return -EAGAIN;
+}
+
+
+static void etm_set_prog(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr |= ETMCR_ETM_PRG;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/*
+	 * Recommended by spec for cp14 accesses to ensure etmcr write is
+	 * complete before polling etmsr
+	 */
+	isb();
+	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n", ETMSR);
+	}
+}
+
+static void etm_clr_prog(struct etm_drvdata *drvdata)
+{
+	u32 etmcr;
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= ~ETMCR_ETM_PRG;
+	etm_writel(drvdata, etmcr, ETMCR);
+	/*
+	 * Recommended by spec for cp14 accesses to ensure etmcr write is
+	 * complete before polling etmsr
+	 */
+	isb();
+	if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n", ETMSR);
+	}
+}
+
+static void etm_set_default(struct etm_drvdata *drvdata)
+{
+	int i;
+
+	drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->enable_event = ETM_HARD_WIRE_RES_A;
+
+	drvdata->seq_12_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_21_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_23_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_31_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_32_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->seq_13_event = ETM_DEFAULT_EVENT_VAL;
+	drvdata->timestamp_event = ETM_DEFAULT_EVENT_VAL;
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		drvdata->cntr_rld_val[i] = 0x0;
+		drvdata->cntr_event[i] = ETM_DEFAULT_EVENT_VAL;
+		drvdata->cntr_rld_event[i] = ETM_DEFAULT_EVENT_VAL;
+		drvdata->cntr_val[i] = 0x0;
+	}
+
+	drvdata->seq_curr_state = 0x0;
+	drvdata->ctxid_idx = 0x0;
+	for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+		drvdata->ctxid_val[i] = 0x0;
+	drvdata->ctxid_mask = 0x0;
+}
+
+static void etm_enable_hw(void *info)
+{
+	int i;
+	u32 etmcr;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+
+	/* Turn engine on */
+	etm_clr_pwrdwn(drvdata);
+	/* Apply power to trace registers */
+	etm_set_pwrup(drvdata);
+	/* Make sure all registers are accessible */
+	etm_os_unlock(drvdata);
+
+	etm_set_prog(drvdata);
+
+	etmcr = etm_readl(drvdata, ETMCR);
+	etmcr &= (ETMCR_PWD_DWN | ETMCR_ETM_PRG);
+	etmcr |= drvdata->port_size;
+	etm_writel(drvdata, drvdata->ctrl | etmcr, ETMCR);
+	etm_writel(drvdata, drvdata->trigger_event, ETMTRIGGER);
+	etm_writel(drvdata, drvdata->startstop_ctrl, ETMTSSCR);
+	etm_writel(drvdata, drvdata->enable_event, ETMTEEVR);
+	etm_writel(drvdata, drvdata->enable_ctrl1, ETMTECR1);
+	etm_writel(drvdata, drvdata->fifofull_level, ETMFFLR);
+	for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+		etm_writel(drvdata, drvdata->addr_val[i], ETMACVRn(i));
+		etm_writel(drvdata, drvdata->addr_acctype[i], ETMACTRn(i));
+	}
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		etm_writel(drvdata, drvdata->cntr_rld_val[i], ETMCNTRLDVRn(i));
+		etm_writel(drvdata, drvdata->cntr_event[i], ETMCNTENRn(i));
+		etm_writel(drvdata, drvdata->cntr_rld_event[i],
+			   ETMCNTRLDEVRn(i));
+		etm_writel(drvdata, drvdata->cntr_val[i], ETMCNTVRn(i));
+	}
+	etm_writel(drvdata, drvdata->seq_12_event, ETMSQ12EVR);
+	etm_writel(drvdata, drvdata->seq_21_event, ETMSQ21EVR);
+	etm_writel(drvdata, drvdata->seq_23_event, ETMSQ23EVR);
+	etm_writel(drvdata, drvdata->seq_31_event, ETMSQ31EVR);
+	etm_writel(drvdata, drvdata->seq_32_event, ETMSQ32EVR);
+	etm_writel(drvdata, drvdata->seq_13_event, ETMSQ13EVR);
+	etm_writel(drvdata, drvdata->seq_curr_state, ETMSQR);
+	for (i = 0; i < drvdata->nr_ext_out; i++)
+		etm_writel(drvdata, ETM_DEFAULT_EVENT_VAL, ETMEXTOUTEVRn(i));
+	for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+		etm_writel(drvdata, drvdata->ctxid_val[i], ETMCIDCVRn(i));
+	etm_writel(drvdata, drvdata->ctxid_mask, ETMCIDCMR);
+	etm_writel(drvdata, drvdata->sync_freq, ETMSYNCFR);
+	/* No external input selected */
+	etm_writel(drvdata, 0x0, ETMEXTINSELR);
+	etm_writel(drvdata, drvdata->timestamp_event, ETMTSEVR);
+	/* No auxiliary control selected */
+	etm_writel(drvdata, 0x0, ETMAUXCR);
+	etm_writel(drvdata, drvdata->traceid, ETMTRACEIDR);
+	/* No VMID comparator value selected */
+	etm_writel(drvdata, 0x0, ETMVMIDCVR);
+
+	/* Ensures trace output is enabled from this ETM */
+	etm_writel(drvdata, drvdata->ctrl | ETMCR_ETM_EN | etmcr, ETMCR);
+
+	etm_clr_prog(drvdata);
+	CS_LOCK(drvdata->base);
+
+	dev_dbg(drvdata->dev, "cpu: %d enable smp call done\n", drvdata->cpu);
+}
+
+static int etm_trace_id_simple(struct etm_drvdata *drvdata)
+{
+	if (!drvdata->enable)
+		return drvdata->traceid;
+
+	return (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+}
+
+static int etm_trace_id(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	unsigned long flags;
+	int trace_id = -1;
+
+	if (!drvdata->enable)
+		return drvdata->traceid;
+
+	if (clk_prepare_enable(drvdata->clk))
+		goto out;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return trace_id;
+}
+
+static int etm_enable(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		goto err_clk;
+
+	spin_lock(&drvdata->spinlock);
+
+	/*
+	 * Configure the ETM only if the CPU is online.  If it isn't online
+	 * hw configuration will take place when 'CPU_STARTING' is received
+	 * in @etm_cpu_callback.
+	 */
+	if (cpu_online(drvdata->cpu)) {
+		ret = smp_call_function_single(drvdata->cpu,
+					       etm_enable_hw, drvdata, 1);
+		if (ret)
+			goto err;
+	}
+
+	drvdata->enable = true;
+	drvdata->sticky_enable = true;
+
+	spin_unlock(&drvdata->spinlock);
+
+	dev_info(drvdata->dev, "ETM tracing enabled\n");
+	return 0;
+err:
+	spin_unlock(&drvdata->spinlock);
+	clk_disable_unprepare(drvdata->clk);
+err_clk:
+	return ret;
+}
+
+static void etm_disable_hw(void *info)
+{
+	int i;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+	etm_set_prog(drvdata);
+
+	/* Program trace enable to low by using always false event */
+	etm_writel(drvdata, ETM_HARD_WIRE_RES_A | ETM_EVENT_NOT_A, ETMTEEVR);
+
+	/* Read back sequencer and counters for post trace analysis */
+	drvdata->seq_curr_state = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+
+	for (i = 0; i < drvdata->nr_cntr; i++)
+		drvdata->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i));
+
+	etm_set_pwrdwn(drvdata);
+	CS_LOCK(drvdata->base);
+
+	dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu);
+}
+
+static void etm_disable(struct coresight_device *csdev)
+{
+	struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	/*
+	 * Taking hotplug lock here protects from clocks getting disabled
+	 * with tracing being left on (crash scenario) if user disable occurs
+	 * after cpu online mask indicates the cpu is offline but before the
+	 * DYING hotplug callback is serviced by the ETM driver.
+	 */
+	get_online_cpus();
+	spin_lock(&drvdata->spinlock);
+
+	/*
+	 * Executing etm_disable_hw on the cpu whose ETM is being disabled
+	 * ensures that register writes occur when cpu is powered.
+	 */
+	smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1);
+	drvdata->enable = false;
+
+	spin_unlock(&drvdata->spinlock);
+	put_online_cpus();
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "ETM tracing disabled\n");
+}
+
+static const struct coresight_ops_source etm_source_ops = {
+	.trace_id	= etm_trace_id,
+	.enable		= etm_enable,
+	.disable	= etm_disable,
+};
+
+static const struct coresight_ops etm_cs_ops = {
+	.source_ops	= &etm_source_ops,
+};
+
+static ssize_t nr_addr_cmp_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_addr_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_addr_cmp);
+
+static ssize_t nr_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_cntr;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_cntr);
+
+static ssize_t nr_ctxid_cmp_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->nr_ctxid_cmp;
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_ctxid_cmp);
+
+static ssize_t etmsr_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags, val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	val = etm_readl(drvdata, ETMSR);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(etmsr);
+
+static ssize_t reset_store(struct device *dev,
+			   struct device_attribute *attr,
+			   const char *buf, size_t size)
+{
+	int i, ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		spin_lock(&drvdata->spinlock);
+		drvdata->mode = ETM_MODE_EXCLUDE;
+		drvdata->ctrl = 0x0;
+		drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+		drvdata->startstop_ctrl = 0x0;
+		drvdata->addr_idx = 0x0;
+		for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+			drvdata->addr_val[i] = 0x0;
+			drvdata->addr_acctype[i] = 0x0;
+			drvdata->addr_type[i] = ETM_ADDR_TYPE_NONE;
+		}
+		drvdata->cntr_idx = 0x0;
+
+		etm_set_default(drvdata);
+		spin_unlock(&drvdata->spinlock);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_WO(reset);
+
+static ssize_t mode_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->mode;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t mode_store(struct device *dev,
+			  struct device_attribute *attr,
+			  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->mode = val & ETM_MODE_ALL;
+
+	if (drvdata->mode & ETM_MODE_EXCLUDE)
+		drvdata->enable_ctrl1 |= ETMTECR1_INC_EXC;
+	else
+		drvdata->enable_ctrl1 &= ~ETMTECR1_INC_EXC;
+
+	if (drvdata->mode & ETM_MODE_CYCACC)
+		drvdata->ctrl |= ETMCR_CYC_ACC;
+	else
+		drvdata->ctrl &= ~ETMCR_CYC_ACC;
+
+	if (drvdata->mode & ETM_MODE_STALL) {
+		if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
+			dev_warn(drvdata->dev, "stall mode not supported\n");
+			return -EINVAL;
+		}
+		drvdata->ctrl |= ETMCR_STALL_MODE;
+	 } else
+		drvdata->ctrl &= ~ETMCR_STALL_MODE;
+
+	if (drvdata->mode & ETM_MODE_TIMESTAMP) {
+		if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
+			dev_warn(drvdata->dev, "timestamp not supported\n");
+			return -EINVAL;
+		}
+		drvdata->ctrl |= ETMCR_TIMESTAMP_EN;
+	} else
+		drvdata->ctrl &= ~ETMCR_TIMESTAMP_EN;
+
+	if (drvdata->mode & ETM_MODE_CTXID)
+		drvdata->ctrl |= ETMCR_CTXID_SIZE;
+	else
+		drvdata->ctrl &= ~ETMCR_CTXID_SIZE;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(mode);
+
+static ssize_t trigger_event_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->trigger_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_event_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_event);
+
+static ssize_t enable_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->enable_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t enable_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->enable_event = val & ETM_EVENT_MASK;
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_event);
+
+static ssize_t fifofull_level_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->fifofull_level;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t fifofull_level_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->fifofull_level = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(fifofull_level);
+
+static ssize_t addr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->addr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_addr_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->addr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_idx);
+
+static ssize_t addr_single_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_single_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EINVAL;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_SINGLE;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_single);
+
+static ssize_t addr_range_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val1 = drvdata->addr_val[idx];
+	val2 = drvdata->addr_val[idx + 1];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx %#lx\n", val1, val2);
+}
+
+static ssize_t addr_range_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	u8 idx;
+	unsigned long val1, val2;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+		return -EINVAL;
+	/* Lower address comparator cannot have a higher address value */
+	if (val1 > val2)
+		return -EINVAL;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (idx % 2 != 0) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+	if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+	      (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+	       drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val1;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_RANGE;
+	drvdata->addr_val[idx + 1] = val2;
+	drvdata->addr_type[idx + 1] = ETM_ADDR_TYPE_RANGE;
+	drvdata->enable_ctrl1 |= (1 << (idx/2));
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_range);
+
+static ssize_t addr_start_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_start_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_START;
+	drvdata->startstop_ctrl |= (1 << idx);
+	drvdata->enable_ctrl1 |= BIT(25);
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_start);
+
+static ssize_t addr_stop_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	u8 idx;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	val = drvdata->addr_val[idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_stop_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	u8 idx;
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	idx = drvdata->addr_idx;
+	if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+	      drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EPERM;
+	}
+
+	drvdata->addr_val[idx] = val;
+	drvdata->addr_type[idx] = ETM_ADDR_TYPE_STOP;
+	drvdata->startstop_ctrl |= (1 << (idx + 16));
+	drvdata->enable_ctrl1 |= ETMTECR1_START_STOP;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_stop);
+
+static ssize_t addr_acctype_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->addr_acctype[drvdata->addr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_acctype_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->addr_acctype[drvdata->addr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(addr_acctype);
+
+static ssize_t cntr_idx_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->cntr_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_idx_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_cntr)
+		return -EINVAL;
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_idx);
+
+static ssize_t cntr_rld_val_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_rld_val[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_val_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_rld_val[drvdata->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_val);
+
+static ssize_t cntr_event_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_event[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_event_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_event);
+
+static ssize_t cntr_rld_event_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->cntr_rld_event[drvdata->cntr_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_event_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_rld_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_event);
+
+static ssize_t cntr_val_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int i, ret = 0;
+	u32 val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		spin_lock(&drvdata->spinlock);
+		for (i = 0; i < drvdata->nr_cntr; i++)
+			ret += sprintf(buf, "counter %d: %x\n",
+				       i, drvdata->cntr_val[i]);
+		spin_unlock(&drvdata->spinlock);
+		return ret;
+	}
+
+	for (i = 0; i < drvdata->nr_cntr; i++) {
+		val = etm_readl(drvdata, ETMCNTVRn(i));
+		ret += sprintf(buf, "counter %d: %x\n", i, val);
+	}
+
+	return ret;
+}
+
+static ssize_t cntr_val_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->cntr_val[drvdata->cntr_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(cntr_val);
+
+static ssize_t seq_12_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_12_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_12_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_12_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_12_event);
+
+static ssize_t seq_21_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_21_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_21_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_21_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_21_event);
+
+static ssize_t seq_23_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_23_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_23_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_23_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_23_event);
+
+static ssize_t seq_31_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_31_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_31_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_31_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_31_event);
+
+static ssize_t seq_32_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_32_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_32_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_32_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_32_event);
+
+static ssize_t seq_13_event_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->seq_13_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_13_event_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->seq_13_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(seq_13_event);
+
+static ssize_t seq_curr_state_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long val, flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		val = drvdata->seq_curr_state;
+		goto out;
+	}
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_curr_state_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val > ETM_SEQ_STATE_MAX_VAL)
+		return -EINVAL;
+
+	drvdata->seq_curr_state = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(seq_curr_state);
+
+static ssize_t ctxid_idx_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->ctxid_idx;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_idx_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	if (val >= drvdata->nr_ctxid_cmp)
+		return -EINVAL;
+
+	/*
+	 * Use spinlock to ensure index doesn't change while it gets
+	 * dereferenced multiple times within a spinlock block elsewhere.
+	 */
+	spin_lock(&drvdata->spinlock);
+	drvdata->ctxid_idx = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_idx);
+
+static ssize_t ctxid_val_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	spin_lock(&drvdata->spinlock);
+	val = drvdata->ctxid_val[drvdata->ctxid_idx];
+	spin_unlock(&drvdata->spinlock);
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_val_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	spin_lock(&drvdata->spinlock);
+	drvdata->ctxid_val[drvdata->ctxid_idx] = val;
+	spin_unlock(&drvdata->spinlock);
+
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_val);
+
+static ssize_t ctxid_mask_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->ctxid_mask;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_mask_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->ctxid_mask = val;
+	return size;
+}
+static DEVICE_ATTR_RW(ctxid_mask);
+
+static ssize_t sync_freq_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->sync_freq;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t sync_freq_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->sync_freq = val & ETM_SYNC_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(sync_freq);
+
+static ssize_t timestamp_event_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->timestamp_event;
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t timestamp_event_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->timestamp_event = val & ETM_EVENT_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(timestamp_event);
+
+static ssize_t status_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+
+	CS_UNLOCK(drvdata->base);
+	ret = sprintf(buf,
+		      "ETMCCR: 0x%08x\n"
+		      "ETMCCER: 0x%08x\n"
+		      "ETMSCR: 0x%08x\n"
+		      "ETMIDR: 0x%08x\n"
+		      "ETMCR: 0x%08x\n"
+		      "ETMTRACEIDR: 0x%08x\n"
+		      "Enable event: 0x%08x\n"
+		      "Enable start/stop: 0x%08x\n"
+		      "Enable control: CR1 0x%08x CR2 0x%08x\n"
+		      "CPU affinity: %d\n",
+		      drvdata->etmccr, drvdata->etmccer,
+		      etm_readl(drvdata, ETMSCR), etm_readl(drvdata, ETMIDR),
+		      etm_readl(drvdata, ETMCR), etm_trace_id_simple(drvdata),
+		      etm_readl(drvdata, ETMTEEVR),
+		      etm_readl(drvdata, ETMTSSCR),
+		      etm_readl(drvdata, ETMTECR1),
+		      etm_readl(drvdata, ETMTECR2),
+		      drvdata->cpu);
+	CS_LOCK(drvdata->base);
+
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+
+	return ret;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t traceid_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	int ret;
+	unsigned long val, flags;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	if (!drvdata->enable) {
+		val = drvdata->traceid;
+		goto out;
+	}
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	CS_UNLOCK(drvdata->base);
+
+	val = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+
+	CS_LOCK(drvdata->base);
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	clk_disable_unprepare(drvdata->clk);
+out:
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t traceid_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->traceid = val & ETM_TRACEID_MASK;
+	return size;
+}
+static DEVICE_ATTR_RW(traceid);
+
+static struct attribute *coresight_etm_attrs[] = {
+	&dev_attr_nr_addr_cmp.attr,
+	&dev_attr_nr_cntr.attr,
+	&dev_attr_nr_ctxid_cmp.attr,
+	&dev_attr_etmsr.attr,
+	&dev_attr_reset.attr,
+	&dev_attr_mode.attr,
+	&dev_attr_trigger_event.attr,
+	&dev_attr_enable_event.attr,
+	&dev_attr_fifofull_level.attr,
+	&dev_attr_addr_idx.attr,
+	&dev_attr_addr_single.attr,
+	&dev_attr_addr_range.attr,
+	&dev_attr_addr_start.attr,
+	&dev_attr_addr_stop.attr,
+	&dev_attr_addr_acctype.attr,
+	&dev_attr_cntr_idx.attr,
+	&dev_attr_cntr_rld_val.attr,
+	&dev_attr_cntr_event.attr,
+	&dev_attr_cntr_rld_event.attr,
+	&dev_attr_cntr_val.attr,
+	&dev_attr_seq_12_event.attr,
+	&dev_attr_seq_21_event.attr,
+	&dev_attr_seq_23_event.attr,
+	&dev_attr_seq_31_event.attr,
+	&dev_attr_seq_32_event.attr,
+	&dev_attr_seq_13_event.attr,
+	&dev_attr_seq_curr_state.attr,
+	&dev_attr_ctxid_idx.attr,
+	&dev_attr_ctxid_val.attr,
+	&dev_attr_ctxid_mask.attr,
+	&dev_attr_sync_freq.attr,
+	&dev_attr_timestamp_event.attr,
+	&dev_attr_status.attr,
+	&dev_attr_traceid.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etm);
+
+static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action,
+			    void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+
+	if (!etmdrvdata[cpu])
+		goto out;
+
+	switch (action & (~CPU_TASKS_FROZEN)) {
+	case CPU_STARTING:
+		spin_lock(&etmdrvdata[cpu]->spinlock);
+		if (!etmdrvdata[cpu]->os_unlock) {
+			etm_os_unlock(etmdrvdata[cpu]);
+			etmdrvdata[cpu]->os_unlock = true;
+		}
+
+		if (etmdrvdata[cpu]->enable)
+			etm_enable_hw(etmdrvdata[cpu]);
+		spin_unlock(&etmdrvdata[cpu]->spinlock);
+		break;
+
+	case CPU_ONLINE:
+		if (etmdrvdata[cpu]->boot_enable &&
+		    !etmdrvdata[cpu]->sticky_enable)
+			coresight_enable(etmdrvdata[cpu]->csdev);
+		break;
+
+	case CPU_DYING:
+		spin_lock(&etmdrvdata[cpu]->spinlock);
+		if (etmdrvdata[cpu]->enable)
+			etm_disable_hw(etmdrvdata[cpu]);
+		spin_unlock(&etmdrvdata[cpu]->spinlock);
+		break;
+	}
+out:
+	return NOTIFY_OK;
+}
+
+static struct notifier_block etm_cpu_notifier = {
+	.notifier_call = etm_cpu_callback,
+};
+
+static bool etm_arch_supported(u8 arch)
+{
+	switch (arch) {
+	case ETM_ARCH_V3_3:
+		break;
+	case ETM_ARCH_V3_5:
+		break;
+	case PFT_ARCH_V1_0:
+		break;
+	case PFT_ARCH_V1_1:
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
+static void etm_init_arch_data(void *info)
+{
+	u32 etmidr;
+	u32 etmccr;
+	struct etm_drvdata *drvdata = info;
+
+	CS_UNLOCK(drvdata->base);
+
+	/* First dummy read */
+	(void)etm_readl(drvdata, ETMPDSR);
+	/* Provide power to ETM: ETMPDCR[3] == 1 */
+	etm_set_pwrup(drvdata);
+	/*
+	 * Clear power down bit since when this bit is set writes to
+	 * certain registers might be ignored.
+	 */
+	etm_clr_pwrdwn(drvdata);
+	/*
+	 * Set prog bit. It will be set from reset but this is included to
+	 * ensure it is set
+	 */
+	etm_set_prog(drvdata);
+
+	/* Find all capabilities */
+	etmidr = etm_readl(drvdata, ETMIDR);
+	drvdata->arch = BMVAL(etmidr, 4, 11);
+	drvdata->port_size = etm_readl(drvdata, ETMCR) & PORT_SIZE_MASK;
+
+	drvdata->etmccer = etm_readl(drvdata, ETMCCER);
+	etmccr = etm_readl(drvdata, ETMCCR);
+	drvdata->etmccr = etmccr;
+	drvdata->nr_addr_cmp = BMVAL(etmccr, 0, 3) * 2;
+	drvdata->nr_cntr = BMVAL(etmccr, 13, 15);
+	drvdata->nr_ext_inp = BMVAL(etmccr, 17, 19);
+	drvdata->nr_ext_out = BMVAL(etmccr, 20, 22);
+	drvdata->nr_ctxid_cmp = BMVAL(etmccr, 24, 25);
+
+	etm_set_pwrdwn(drvdata);
+	etm_clr_pwrup(drvdata);
+	CS_LOCK(drvdata->base);
+}
+
+static void etm_init_default_data(struct etm_drvdata *drvdata)
+{
+	static int etm3x_traceid;
+
+	u32 flags = (1 << 0 | /* instruction execute*/
+		     3 << 3 | /* ARM instruction */
+		     0 << 5 | /* No data value comparison */
+		     0 << 7 | /* No exact mach */
+		     0 << 8 | /* Ignore context ID */
+		     0 << 10); /* Security ignored */
+
+	/*
+	 * Initial configuration only - guarantees sources handled by
+	 * this driver have a unique ID at startup time but not between
+	 * all other types of sources.  For that we lean on the core
+	 * framework.
+	 */
+	drvdata->traceid = etm3x_traceid++;
+	drvdata->ctrl = (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN);
+	drvdata->enable_ctrl1 = ETMTECR1_ADDR_COMP_1;
+	if (drvdata->nr_addr_cmp >= 2) {
+		drvdata->addr_val[0] = (u32) _stext;
+		drvdata->addr_val[1] = (u32) _etext;
+		drvdata->addr_acctype[0] = flags;
+		drvdata->addr_acctype[1] = flags;
+		drvdata->addr_type[0] = ETM_ADDR_TYPE_RANGE;
+		drvdata->addr_type[1] = ETM_ADDR_TYPE_RANGE;
+	}
+
+	etm_set_default(drvdata);
+}
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct etm_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+
+		adev->dev.platform_data = pdata;
+		drvdata->use_cp14 = of_property_read_bool(np, "arm,cp14");
+	}
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	drvdata->cpu = pdata ? pdata->cpu : 0;
+
+	get_online_cpus();
+	etmdrvdata[drvdata->cpu] = drvdata;
+
+	if (!smp_call_function_single(drvdata->cpu, etm_os_unlock, drvdata, 1))
+		drvdata->os_unlock = true;
+
+	if (smp_call_function_single(drvdata->cpu,
+				     etm_init_arch_data,  drvdata, 1))
+		dev_err(dev, "ETM arch init failed\n");
+
+	if (!etm_count++)
+		register_hotcpu_notifier(&etm_cpu_notifier);
+
+	put_online_cpus();
+
+	if (etm_arch_supported(drvdata->arch) == false) {
+		ret = -EINVAL;
+		goto err_arch_supported;
+	}
+	etm_init_default_data(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	desc->type = CORESIGHT_DEV_TYPE_SOURCE;
+	desc->subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC;
+	desc->ops = &etm_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_etm_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto err_arch_supported;
+	}
+
+	dev_info(dev, "ETM initialized\n");
+
+	if (boot_enable) {
+		coresight_enable(drvdata->csdev);
+		drvdata->boot_enable = true;
+	}
+
+	return 0;
+
+err_arch_supported:
+	clk_disable_unprepare(drvdata->clk);
+	if (--etm_count == 0)
+		unregister_hotcpu_notifier(&etm_cpu_notifier);
+	return ret;
+}
+
+static int etm_remove(struct amba_device *adev)
+{
+	struct etm_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	if (--etm_count == 0)
+		unregister_hotcpu_notifier(&etm_cpu_notifier);
+
+	return 0;
+}
+
+static struct amba_id etm_ids[] = {
+	{	/* ETM 3.3 */
+		.id	= 0x0003b921,
+		.mask	= 0x0003ffff,
+	},
+	{	/* ETM 3.5 */
+		.id	= 0x0003b956,
+		.mask	= 0x0003ffff,
+	},
+	{	/* PTM 1.0 */
+		.id	= 0x0003b950,
+		.mask	= 0x0003ffff,
+	},
+	{	/* PTM 1.1 */
+		.id	= 0x0003b95f,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver etm_driver = {
+	.drv = {
+		.name	= "coresight-etm3x",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= etm_probe,
+	.remove		= etm_remove,
+	.id_table	= etm_ids,
+};
+
+int __init etm_init(void)
+{
+	return amba_driver_register(&etm_driver);
+}
+module_init(etm_init);
+
+void __exit etm_exit(void)
+{
+	amba_driver_unregister(&etm_driver);
+}
+module_exit(etm_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Program Flow Trace driver");
diff --git a/drivers/coresight/coresight-funnel.c b/drivers/coresight/coresight-funnel.c
new file mode 100644
index 000000000000..2108edffe1f4
--- /dev/null
+++ b/drivers/coresight/coresight-funnel.c
@@ -0,0 +1,268 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define FUNNEL_FUNCTL		0x000
+#define FUNNEL_PRICTL		0x004
+
+#define FUNNEL_HOLDTIME_MASK	0xf00
+#define FUNNEL_HOLDTIME_SHFT	0x8
+#define FUNNEL_HOLDTIME		(0x7 << FUNNEL_HOLDTIME_SHFT)
+
+/**
+ * struct funnel_drvdata - specifics associated to a funnel component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ * @priority:	port selection order.
+ */
+struct funnel_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct clk		*clk;
+	unsigned long		priority;
+};
+
+static void funnel_enable_hw(struct funnel_drvdata *drvdata, int port)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	functl &= ~FUNNEL_HOLDTIME_MASK;
+	functl |= FUNNEL_HOLDTIME;
+	functl |= (1 << port);
+	writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+	writel_relaxed(drvdata->priority, drvdata->base + FUNNEL_PRICTL);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int funnel_enable(struct coresight_device *csdev, int inport,
+			 int outport)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	funnel_enable_hw(drvdata, inport);
+
+	dev_info(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
+	return 0;
+}
+
+static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	functl &= ~(1 << inport);
+	writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void funnel_disable(struct coresight_device *csdev, int inport,
+			   int outport)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	funnel_disable_hw(drvdata, inport);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
+}
+
+static const struct coresight_ops_link funnel_link_ops = {
+	.enable		= funnel_enable,
+	.disable	= funnel_disable,
+};
+
+static const struct coresight_ops funnel_cs_ops = {
+	.link_ops	= &funnel_link_ops,
+};
+
+static ssize_t priority_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->priority;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t priority_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->priority = val;
+	return size;
+}
+static DEVICE_ATTR_RW(priority);
+
+static u32 get_funnel_ctrl_hw(struct funnel_drvdata *drvdata)
+{
+	u32 functl;
+
+	CS_UNLOCK(drvdata->base);
+	functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+	CS_LOCK(drvdata->base);
+
+	return functl;
+}
+
+static ssize_t funnel_ctrl_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	int ret;
+	u32 val;
+	struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	val = get_funnel_ctrl_hw(drvdata);
+	clk_disable_unprepare(drvdata->clk);
+
+	return sprintf(buf, "%#x\n", val);
+}
+static DEVICE_ATTR_RO(funnel_ctrl);
+
+static struct attribute *coresight_funnel_attrs[] = {
+	&dev_attr_funnel_ctrl.attr,
+	&dev_attr_priority.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_funnel);
+
+static int funnel_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct funnel_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	drvdata->clk = adev->pclk;
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_LINK;
+	desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG;
+	desc->ops = &funnel_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->groups = coresight_funnel_groups;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "FUNNEL initialized\n");
+	return 0;
+}
+
+static int funnel_remove(struct amba_device *adev)
+{
+	struct funnel_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id funnel_ids[] = {
+	{
+		.id     = 0x0003b908,
+		.mask   = 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver funnel_driver = {
+	.drv = {
+		.name	= "coresight-funnel",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= funnel_probe,
+	.remove		= funnel_remove,
+	.id_table	= funnel_ids,
+};
+
+static int __init funnel_init(void)
+{
+	return amba_driver_register(&funnel_driver);
+}
+module_init(funnel_init);
+
+static void __exit funnel_exit(void)
+{
+	amba_driver_unregister(&funnel_driver);
+}
+module_exit(funnel_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Funnel driver");
diff --git a/drivers/coresight/coresight-priv.h b/drivers/coresight/coresight-priv.h
new file mode 100644
index 000000000000..7b3372fca4f6
--- /dev/null
+++ b/drivers/coresight/coresight-priv.h
@@ -0,0 +1,63 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_PRIV_H
+#define _CORESIGHT_PRIV_H
+
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/coresight.h>
+
+/*
+ * Coresight management registers (0xf00-0xfcc)
+ * 0xfa0 - 0xfa4: Management	registers in PFTv1.0
+ *		  Trace		registers in PFTv1.1
+ */
+#define CORESIGHT_ITCTRL	0xf00
+#define CORESIGHT_CLAIMSET	0xfa0
+#define CORESIGHT_CLAIMCLR	0xfa4
+#define CORESIGHT_LAR		0xfb0
+#define CORESIGHT_LSR		0xfb4
+#define CORESIGHT_AUTHSTATUS	0xfb8
+#define CORESIGHT_DEVID		0xfc8
+#define CORESIGHT_DEVTYPE	0xfcc
+
+#define TIMEOUT_US		100
+#define BMVAL(val, lsb, msb)	((val & GENMASK(msb, lsb)) >> lsb)
+
+static inline void CS_LOCK(void __iomem *addr)
+{
+	do {
+		/* Wait for things to settle */
+		mb();
+		writel_relaxed(0x0, addr + CORESIGHT_LAR);
+	} while (0);
+}
+
+static inline void CS_UNLOCK(void __iomem *addr)
+{
+	do {
+		writel_relaxed(CORESIGHT_UNLOCK, addr + CORESIGHT_LAR);
+		/* Make sure everyone has seen this */
+		mb();
+	} while (0);
+}
+
+#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
+extern int etm_readl_cp14(u32 off, unsigned int *val);
+extern int etm_writel_cp14(u32 off, u32 val);
+#else
+static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; }
+static inline int etm_writel_cp14(u32 val, u32 off) { return 0; }
+#endif
+
+#endif
diff --git a/drivers/coresight/coresight-replicator.c b/drivers/coresight/coresight-replicator.c
new file mode 100644
index 000000000000..a2dfcf903551
--- /dev/null
+++ b/drivers/coresight/coresight-replicator.c
@@ -0,0 +1,137 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+
+#include "coresight-priv.h"
+
+/**
+ * struct replicator_drvdata - specifics associated to a replicator component
+ * @dev:	the device entity associated with this component
+ * @csdev:	component vitals needed by the framework
+ */
+struct replicator_drvdata {
+	struct device		*dev;
+	struct coresight_device	*csdev;
+};
+
+static int replicator_enable(struct coresight_device *csdev, int inport,
+			     int outport)
+{
+	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	dev_info(drvdata->dev, "REPLICATOR enabled\n");
+	return 0;
+}
+
+static void replicator_disable(struct coresight_device *csdev, int inport,
+			       int outport)
+{
+	struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	dev_info(drvdata->dev, "REPLICATOR disabled\n");
+}
+
+static const struct coresight_ops_link replicator_link_ops = {
+	.enable		= replicator_enable,
+	.disable	= replicator_disable,
+};
+
+static const struct coresight_ops replicator_cs_ops = {
+	.link_ops	= &replicator_link_ops,
+};
+
+static int replicator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct replicator_drvdata *drvdata;
+	struct coresight_desc *desc;
+	struct device_node *np = pdev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		pdev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &pdev->dev;
+	platform_set_drvdata(pdev, drvdata);
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_LINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
+	desc->ops = &replicator_cs_ops;
+	desc->pdata = pdev->dev.platform_data;
+	desc->dev = &pdev->dev;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "REPLICATOR initialized\n");
+	return 0;
+}
+
+static int replicator_remove(struct platform_device *pdev)
+{
+	struct replicator_drvdata *drvdata = platform_get_drvdata(pdev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct of_device_id replicator_match[] = {
+	{.compatible = "arm,coresight-replicator"},
+	{}
+};
+
+static struct platform_driver replicator_driver = {
+	.probe          = replicator_probe,
+	.remove         = replicator_remove,
+	.driver         = {
+		.name   = "coresight-replicator",
+		.of_match_table = replicator_match,
+	},
+};
+
+static int __init replicator_init(void)
+{
+	return platform_driver_register(&replicator_driver);
+}
+module_init(replicator_init);
+
+static void __exit replicator_exit(void)
+{
+	platform_driver_unregister(&replicator_driver);
+}
+module_exit(replicator_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Replicator driver");
diff --git a/drivers/coresight/coresight-tmc.c b/drivers/coresight/coresight-tmc.c
new file mode 100644
index 000000000000..ce2c293f1707
--- /dev/null
+++ b/drivers/coresight/coresight-tmc.c
@@ -0,0 +1,776 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TMC_RSZ			0x004
+#define TMC_STS			0x00c
+#define TMC_RRD			0x010
+#define TMC_RRP			0x014
+#define TMC_RWP			0x018
+#define TMC_TRG			0x01c
+#define TMC_CTL			0x020
+#define TMC_RWD			0x024
+#define TMC_MODE		0x028
+#define TMC_LBUFLEVEL		0x02c
+#define TMC_CBUFLEVEL		0x030
+#define TMC_BUFWM		0x034
+#define TMC_RRPHI		0x038
+#define TMC_RWPHI		0x03c
+#define TMC_AXICTL		0x110
+#define TMC_DBALO		0x118
+#define TMC_DBAHI		0x11c
+#define TMC_FFSR		0x300
+#define TMC_FFCR		0x304
+#define TMC_PSCR		0x308
+#define TMC_ITMISCOP0		0xee0
+#define TMC_ITTRFLIN		0xee8
+#define TMC_ITATBDATA0		0xeec
+#define TMC_ITATBCTR2		0xef0
+#define TMC_ITATBCTR1		0xef4
+#define TMC_ITATBCTR0		0xef8
+
+/* register description */
+/* TMC_CTL - 0x020 */
+#define TMC_CTL_CAPT_EN		BIT(0)
+/* TMC_STS - 0x00C */
+#define TMC_STS_TRIGGERED	BIT(1)
+/* TMC_AXICTL - 0x110 */
+#define TMC_AXICTL_PROT_CTL_B0	BIT(0)
+#define TMC_AXICTL_PROT_CTL_B1	BIT(1)
+#define TMC_AXICTL_SCT_GAT_MODE	BIT(7)
+#define TMC_AXICTL_WR_BURST_LEN 0xF00
+/* TMC_FFCR - 0x304 */
+#define TMC_FFCR_EN_FMT		BIT(0)
+#define TMC_FFCR_EN_TI		BIT(1)
+#define TMC_FFCR_FON_FLIN	BIT(4)
+#define TMC_FFCR_FON_TRIG_EVT	BIT(5)
+#define TMC_FFCR_FLUSHMAN	BIT(6)
+#define TMC_FFCR_TRIGON_TRIGIN	BIT(8)
+#define TMC_FFCR_STOP_ON_FLUSH	BIT(12)
+
+#define TMC_STS_TRIGGERED_BIT	2
+#define TMC_FFCR_FLUSHMAN_BIT	6
+
+enum tmc_config_type {
+	TMC_CONFIG_TYPE_ETB,
+	TMC_CONFIG_TYPE_ETR,
+	TMC_CONFIG_TYPE_ETF,
+};
+
+enum tmc_mode {
+	TMC_MODE_CIRCULAR_BUFFER,
+	TMC_MODE_SOFTWARE_FIFO,
+	TMC_MODE_HARDWARE_FIFO,
+};
+
+enum tmc_mem_intf_width {
+	TMC_MEM_INTF_WIDTH_32BITS	= 0x2,
+	TMC_MEM_INTF_WIDTH_64BITS	= 0x3,
+	TMC_MEM_INTF_WIDTH_128BITS	= 0x4,
+	TMC_MEM_INTF_WIDTH_256BITS	= 0x5,
+};
+
+/**
+ * struct tmc_drvdata - specifics associated to an TMC component
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @miscdev:	specifics to handle "/dev/xyz.tmc" entry.
+ * @clk:	the clock this component is associated to.
+ * @spinlock:	only one at a time pls.
+ * @read_count:	manages preparation of buffer for reading.
+ * @buf:	area of memory where trace data get sent.
+ * @paddr:	DMA start location in RAM.
+ * @vaddr:	virtual representation of @paddr.
+ * @size:	@buf size.
+ * @enable:	this TMC is being used.
+ * @config_type: TMC variant, must be of type @tmc_config_type.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct tmc_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct miscdevice	miscdev;
+	struct clk		*clk;
+	spinlock_t		spinlock;
+	int			read_count;
+	bool			reading;
+	char			*buf;
+	dma_addr_t		paddr;
+	void __iomem		*vaddr;
+	u32			size;
+	bool			enable;
+	enum tmc_config_type	config_type;
+	u32			trigger_cntr;
+};
+
+static void tmc_wait_for_ready(struct tmc_drvdata *drvdata)
+{
+	/* Ensure formatter, unformatter and hardware fifo are empty */
+	if (coresight_timeout(drvdata->base,
+			      TMC_STS, TMC_STS_TRIGGERED_BIT, 1)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			TMC_STS);
+	}
+}
+
+static void tmc_flush_and_stop(struct tmc_drvdata *drvdata)
+{
+	u32 ffcr;
+
+	ffcr = readl_relaxed(drvdata->base + TMC_FFCR);
+	ffcr |= TMC_FFCR_STOP_ON_FLUSH;
+	writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+	ffcr |= TMC_FFCR_FLUSHMAN;
+	writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+	/* Ensure flush completes */
+	if (coresight_timeout(drvdata->base,
+			      TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) {
+		dev_err(drvdata->dev,
+			"timeout observed when probing at offset %#x\n",
+			TMC_FFCR);
+	}
+
+	tmc_wait_for_ready(drvdata);
+}
+
+static void tmc_enable_hw(struct tmc_drvdata *drvdata)
+{
+	writel_relaxed(TMC_CTL_CAPT_EN, drvdata->base + TMC_CTL);
+}
+
+static void tmc_disable_hw(struct tmc_drvdata *drvdata)
+{
+	writel_relaxed(0x0, drvdata->base + TMC_CTL);
+}
+
+static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata)
+{
+	/* Zero out the memory to help with debug */
+	memset(drvdata->buf, 0, drvdata->size);
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+		       TMC_FFCR_TRIGON_TRIGIN,
+		       drvdata->base + TMC_FFCR);
+
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
+{
+	u32 axictl;
+
+	/* Zero out the memory to help with debug */
+	memset(drvdata->vaddr, 0, drvdata->size);
+
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(drvdata->size / 4, drvdata->base + TMC_RSZ);
+	writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+
+	axictl = readl_relaxed(drvdata->base + TMC_AXICTL);
+	axictl |= TMC_AXICTL_WR_BURST_LEN;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+	axictl &= ~TMC_AXICTL_SCT_GAT_MODE;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+	axictl = (axictl &
+		  ~(TMC_AXICTL_PROT_CTL_B0 | TMC_AXICTL_PROT_CTL_B1)) |
+		  TMC_AXICTL_PROT_CTL_B1;
+	writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+
+	writel_relaxed(drvdata->paddr, drvdata->base + TMC_DBALO);
+	writel_relaxed(0x0, drvdata->base + TMC_DBAHI);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+		       TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+		       TMC_FFCR_TRIGON_TRIGIN,
+		       drvdata->base + TMC_FFCR);
+	writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_enable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	writel_relaxed(TMC_MODE_HARDWARE_FIFO, drvdata->base + TMC_MODE);
+	writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI,
+		       drvdata->base + TMC_FFCR);
+	writel_relaxed(0x0, drvdata->base + TMC_BUFWM);
+	tmc_enable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static int tmc_enable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+	int ret;
+	unsigned long flags;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->reading) {
+		spin_unlock_irqrestore(&drvdata->spinlock, flags);
+		clk_disable_unprepare(drvdata->clk);
+		return -EBUSY;
+	}
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_enable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_enable_hw(drvdata);
+	} else {
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_enable_hw(drvdata);
+		else
+			tmc_etf_enable_hw(drvdata);
+	}
+	drvdata->enable = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC enabled\n");
+	return 0;
+}
+
+static int tmc_enable_sink(struct coresight_device *csdev)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return tmc_enable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static int tmc_enable_link(struct coresight_device *csdev, int inport,
+			   int outport)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	return tmc_enable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata)
+{
+	enum tmc_mem_intf_width memwidth;
+	u8 memwords;
+	char *bufp;
+	u32 read_data;
+	int i;
+
+	memwidth = BMVAL(readl_relaxed(drvdata->base + CORESIGHT_DEVID), 8, 10);
+	if (memwidth == TMC_MEM_INTF_WIDTH_32BITS)
+		memwords = 1;
+	else if (memwidth == TMC_MEM_INTF_WIDTH_64BITS)
+		memwords = 2;
+	else if (memwidth == TMC_MEM_INTF_WIDTH_128BITS)
+		memwords = 4;
+	else
+		memwords = 8;
+
+	bufp = drvdata->buf;
+	while (1) {
+		for (i = 0; i < memwords; i++) {
+			read_data = readl_relaxed(drvdata->base + TMC_RRD);
+			if (read_data == 0xFFFFFFFF)
+				return;
+			memcpy(bufp, &read_data, 4);
+			bufp += 4;
+		}
+	}
+}
+
+static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_etb_dump_hw(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata)
+{
+	u32 rwp, val;
+
+	rwp = readl_relaxed(drvdata->base + TMC_RWP);
+	val = readl_relaxed(drvdata->base + TMC_STS);
+
+	/* How much memory do we still have */
+	if (val & BIT(0))
+		drvdata->buf = drvdata->vaddr + rwp - drvdata->paddr;
+	else
+		drvdata->buf = drvdata->vaddr;
+}
+
+static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_etr_dump_hw(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	tmc_flush_and_stop(drvdata);
+	tmc_disable_hw(drvdata);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tmc_disable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (drvdata->reading)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_disable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_disable_hw(drvdata);
+	} else {
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_disable_hw(drvdata);
+		else
+			tmc_etf_disable_hw(drvdata);
+	}
+out:
+	drvdata->enable = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "TMC disabled\n");
+}
+
+static void tmc_disable_sink(struct coresight_device *csdev)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tmc_disable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static void tmc_disable_link(struct coresight_device *csdev, int inport,
+			     int outport)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tmc_disable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static const struct coresight_ops_sink tmc_sink_ops = {
+	.enable		= tmc_enable_sink,
+	.disable	= tmc_disable_sink,
+};
+
+static const struct coresight_ops_link tmc_link_ops = {
+	.enable		= tmc_enable_link,
+	.disable	= tmc_disable_link,
+};
+
+static const struct coresight_ops tmc_etb_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etr_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etf_cs_ops = {
+	.sink_ops	= &tmc_sink_ops,
+	.link_ops	= &tmc_link_ops,
+};
+
+static int tmc_read_prepare(struct tmc_drvdata *drvdata)
+{
+	int ret;
+	unsigned long flags;
+	enum tmc_mode mode;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (!drvdata->enable)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_disable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_disable_hw(drvdata);
+	} else {
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode == TMC_MODE_CIRCULAR_BUFFER) {
+			tmc_etb_disable_hw(drvdata);
+		} else {
+			ret = -ENODEV;
+			goto err;
+		}
+	}
+out:
+	drvdata->reading = true;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC read start\n");
+	return 0;
+err:
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+	return ret;
+}
+
+static void tmc_read_unprepare(struct tmc_drvdata *drvdata)
+{
+	unsigned long flags;
+	enum tmc_mode mode;
+
+	spin_lock_irqsave(&drvdata->spinlock, flags);
+	if (!drvdata->enable)
+		goto out;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		tmc_etb_enable_hw(drvdata);
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		tmc_etr_enable_hw(drvdata);
+	} else {
+		mode = readl_relaxed(drvdata->base + TMC_MODE);
+		if (mode == TMC_MODE_CIRCULAR_BUFFER)
+			tmc_etb_enable_hw(drvdata);
+	}
+out:
+	drvdata->reading = false;
+	spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+	dev_info(drvdata->dev, "TMC read end\n");
+}
+
+static int tmc_open(struct inode *inode, struct file *file)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+	int ret = 0;
+
+	if (drvdata->read_count++)
+		goto out;
+
+	ret = tmc_read_prepare(drvdata);
+	if (ret)
+		return ret;
+out:
+	nonseekable_open(inode, file);
+
+	dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+	return 0;
+}
+
+static ssize_t tmc_read(struct file *file, char __user *data, size_t len,
+			loff_t *ppos)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+	char *bufp = drvdata->buf + *ppos;
+
+	if (*ppos + len > drvdata->size)
+		len = drvdata->size - *ppos;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		if (bufp == (char *)(drvdata->vaddr + drvdata->size))
+			bufp = drvdata->vaddr;
+		else if (bufp > (char *)(drvdata->vaddr + drvdata->size))
+			bufp -= drvdata->size;
+		if ((bufp + len) > (char *)(drvdata->vaddr + drvdata->size))
+			len = (char *)(drvdata->vaddr + drvdata->size) - bufp;
+	}
+
+	if (copy_to_user(data, bufp, len)) {
+		dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+		return -EFAULT;
+	}
+
+	*ppos += len;
+
+	dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n",
+		__func__, len, (int) (drvdata->size - *ppos));
+	return len;
+}
+
+static int tmc_release(struct inode *inode, struct file *file)
+{
+	struct tmc_drvdata *drvdata = container_of(file->private_data,
+						   struct tmc_drvdata, miscdev);
+
+	if (--drvdata->read_count) {
+		if (drvdata->read_count < 0) {
+			dev_err(drvdata->dev, "mismatched close\n");
+			drvdata->read_count = 0;
+		}
+		goto out;
+	}
+
+	tmc_read_unprepare(drvdata);
+out:
+	dev_dbg(drvdata->dev, "%s: released\n", __func__);
+	return 0;
+}
+
+static const struct file_operations tmc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= tmc_open,
+	.read		= tmc_read,
+	.release	= tmc_release,
+	.llseek		= no_llseek,
+};
+
+static ssize_t trigger_cntr_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+	unsigned long val = drvdata->trigger_cntr;
+
+	return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return ret;
+
+	drvdata->trigger_cntr = val;
+	return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static struct attribute *coresight_etr_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etr);
+
+static struct attribute *coresight_etf_attrs[] = {
+	&dev_attr_trigger_cntr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etf);
+
+static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret = 0;
+	u32 devid;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct tmc_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	spin_lock_init(&drvdata->spinlock);
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID);
+	drvdata->config_type = BMVAL(devid, 6, 7);
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		if (np)
+			ret = of_property_read_u32(np,
+						   "arm,buffer-size",
+						   &drvdata->size);
+		if (ret)
+			drvdata->size = SZ_1M;
+	} else {
+		drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4;
+	}
+
+	clk_disable_unprepare(drvdata->clk);
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		drvdata->vaddr = dma_alloc_coherent(dev, drvdata->size,
+						&drvdata->paddr, GFP_KERNEL);
+		if (!drvdata->vaddr)
+			return -ENOMEM;
+
+		memset(drvdata->vaddr, 0, drvdata->size);
+		drvdata->buf = drvdata->vaddr;
+	} else {
+		drvdata->buf = devm_kzalloc(dev, drvdata->size, GFP_KERNEL);
+		if (!drvdata->buf)
+			return -ENOMEM;
+	}
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto err_devm_kzalloc;
+	}
+
+	desc->pdata = pdata;
+	desc->dev = dev;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+		desc->type = CORESIGHT_DEV_TYPE_SINK;
+		desc->ops = &tmc_etb_cs_ops;
+		desc->groups = coresight_etb_groups;
+	} else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+		desc->type = CORESIGHT_DEV_TYPE_SINK;
+		desc->ops = &tmc_etr_cs_ops;
+		desc->groups = coresight_etr_groups;
+	} else {
+		desc->type = CORESIGHT_DEV_TYPE_LINKSINK;
+		desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
+		desc->ops = &tmc_etf_cs_ops;
+		desc->groups = coresight_etf_groups;
+	}
+
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto err_devm_kzalloc;
+	}
+
+	drvdata->miscdev.name = pdata->name;
+	drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+	drvdata->miscdev.fops = &tmc_fops;
+	ret = misc_register(&drvdata->miscdev);
+	if (ret)
+		goto err_misc_register;
+
+	dev_info(dev, "TMC initialized\n");
+	return 0;
+
+err_misc_register:
+	coresight_unregister(drvdata->csdev);
+err_devm_kzalloc:
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+		dma_free_coherent(dev, drvdata->size,
+				&drvdata->paddr, GFP_KERNEL);
+	return ret;
+}
+
+static int tmc_remove(struct amba_device *adev)
+{
+	struct tmc_drvdata *drvdata = amba_get_drvdata(adev);
+
+	misc_deregister(&drvdata->miscdev);
+	coresight_unregister(drvdata->csdev);
+	if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+		dma_free_coherent(drvdata->dev, drvdata->size,
+				  &drvdata->paddr, GFP_KERNEL);
+
+	return 0;
+}
+
+static struct amba_id tmc_ids[] = {
+	{
+		.id     = 0x0003b961,
+		.mask   = 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver tmc_driver = {
+	.drv = {
+		.name   = "coresight-tmc",
+		.owner  = THIS_MODULE,
+	},
+	.probe		= tmc_probe,
+	.remove		= tmc_remove,
+	.id_table	= tmc_ids,
+};
+
+static int __init tmc_init(void)
+{
+	return amba_driver_register(&tmc_driver);
+}
+module_init(tmc_init);
+
+static void __exit tmc_exit(void)
+{
+	amba_driver_unregister(&tmc_driver);
+}
+module_exit(tmc_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Memory Controller driver");
diff --git a/drivers/coresight/coresight-tpiu.c b/drivers/coresight/coresight-tpiu.c
new file mode 100644
index 000000000000..ae101082791a
--- /dev/null
+++ b/drivers/coresight/coresight-tpiu.c
@@ -0,0 +1,217 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TPIU_SUPP_PORTSZ	0x000
+#define TPIU_CURR_PORTSZ	0x004
+#define TPIU_SUPP_TRIGMODES	0x100
+#define TPIU_TRIG_CNTRVAL	0x104
+#define TPIU_TRIG_MULT		0x108
+#define TPIU_SUPP_TESTPATM	0x200
+#define TPIU_CURR_TESTPATM	0x204
+#define TPIU_TEST_PATREPCNTR	0x208
+#define TPIU_FFSR		0x300
+#define TPIU_FFCR		0x304
+#define TPIU_FSYNC_CNTR		0x308
+#define TPIU_EXTCTL_INPORT	0x400
+#define TPIU_EXTCTL_OUTPORT	0x404
+#define TPIU_ITTRFLINACK	0xee4
+#define TPIU_ITTRFLIN		0xee8
+#define TPIU_ITATBDATA0		0xeec
+#define TPIU_ITATBCTR2		0xef0
+#define TPIU_ITATBCTR1		0xef4
+#define TPIU_ITATBCTR0		0xef8
+
+/** register definition **/
+/* FFCR - 0x304 */
+#define FFCR_FON_MAN		BIT(6)
+
+/**
+ * @base:	memory mapped base address for this component.
+ * @dev:	the device entity associated to this component.
+ * @csdev:	component vitals needed by the framework.
+ * @clk:	the clock this component is associated to.
+ */
+struct tpiu_drvdata {
+	void __iomem		*base;
+	struct device		*dev;
+	struct coresight_device	*csdev;
+	struct clk		*clk;
+};
+
+static void tpiu_enable_hw(struct tpiu_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	/* TODO: fill this up */
+
+	CS_LOCK(drvdata->base);
+}
+
+static int tpiu_enable(struct coresight_device *csdev)
+{
+	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+	int ret;
+
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	tpiu_enable_hw(drvdata);
+
+	dev_info(drvdata->dev, "TPIU enabled\n");
+	return 0;
+}
+
+static void tpiu_disable_hw(struct tpiu_drvdata *drvdata)
+{
+	CS_UNLOCK(drvdata->base);
+
+	/* Clear formatter controle reg. */
+	writel_relaxed(0x0, drvdata->base + TPIU_FFCR);
+	/* Generate manual flush */
+	writel_relaxed(FFCR_FON_MAN, drvdata->base + TPIU_FFCR);
+
+	CS_LOCK(drvdata->base);
+}
+
+static void tpiu_disable(struct coresight_device *csdev)
+{
+	struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+	tpiu_disable_hw(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	dev_info(drvdata->dev, "TPIU disabled\n");
+}
+
+static const struct coresight_ops_sink tpiu_sink_ops = {
+	.enable		= tpiu_enable,
+	.disable	= tpiu_disable,
+};
+
+static const struct coresight_ops tpiu_cs_ops = {
+	.sink_ops	= &tpiu_sink_ops,
+};
+
+static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
+{
+	int ret;
+	void __iomem *base;
+	struct device *dev = &adev->dev;
+	struct coresight_platform_data *pdata = NULL;
+	struct tpiu_drvdata *drvdata;
+	struct resource *res = &adev->res;
+	struct coresight_desc *desc;
+	struct device_node *np = adev->dev.of_node;
+
+	if (np) {
+		pdata = of_get_coresight_platform_data(dev, np);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+		adev->dev.platform_data = pdata;
+	}
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->dev = &adev->dev;
+	dev_set_drvdata(dev, drvdata);
+
+	/* Validity for the resource is already checked by the AMBA core */
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drvdata->base = base;
+
+	drvdata->clk = adev->pclk;
+	ret = clk_prepare_enable(drvdata->clk);
+	if (ret)
+		return ret;
+
+	/* Disable tpiu to support older devices */
+	tpiu_disable_hw(drvdata);
+
+	clk_disable_unprepare(drvdata->clk);
+
+	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->type = CORESIGHT_DEV_TYPE_SINK;
+	desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT;
+	desc->ops = &tpiu_cs_ops;
+	desc->pdata = pdata;
+	desc->dev = dev;
+	drvdata->csdev = coresight_register(desc);
+	if (IS_ERR(drvdata->csdev))
+		return PTR_ERR(drvdata->csdev);
+
+	dev_info(dev, "TPIU initialized\n");
+	return 0;
+}
+
+static int tpiu_remove(struct amba_device *adev)
+{
+	struct tpiu_drvdata *drvdata = amba_get_drvdata(adev);
+
+	coresight_unregister(drvdata->csdev);
+	return 0;
+}
+
+static struct amba_id tpiu_ids[] = {
+	{
+		.id	= 0x0003b912,
+		.mask	= 0x0003ffff,
+	},
+	{ 0, 0},
+};
+
+static struct amba_driver tpiu_driver = {
+	.drv = {
+		.name	= "coresight-tpiu",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= tpiu_probe,
+	.remove		= tpiu_remove,
+	.id_table	= tpiu_ids,
+};
+
+static int __init tpiu_init(void)
+{
+	return amba_driver_register(&tpiu_driver);
+}
+module_init(tpiu_init);
+
+static void __exit tpiu_exit(void)
+{
+	amba_driver_unregister(&tpiu_driver);
+}
+module_exit(tpiu_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Port Interface Unit driver");
diff --git a/drivers/coresight/coresight.c b/drivers/coresight/coresight.c
new file mode 100644
index 000000000000..6e0181f84425
--- /dev/null
+++ b/drivers/coresight/coresight.c
@@ -0,0 +1,717 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/of_platform.h>
+#include <linux/delay.h>
+
+#include "coresight-priv.h"
+
+static DEFINE_MUTEX(coresight_mutex);
+
+static int coresight_id_match(struct device *dev, void *data)
+{
+	int trace_id, i_trace_id;
+	struct coresight_device *csdev, *i_csdev;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/*
+	 * No need to care about oneself and components that are not
+	 * sources or not enabled
+	 */
+	if (i_csdev == csdev || !i_csdev->enable ||
+	    i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE)
+		return 0;
+
+	/* Get the source ID for both compoment */
+	trace_id = source_ops(csdev)->trace_id(csdev);
+	i_trace_id = source_ops(i_csdev)->trace_id(i_csdev);
+
+	/* All you need is one */
+	if (trace_id == i_trace_id)
+		return 1;
+
+	return 0;
+}
+
+static int coresight_source_is_unique(struct coresight_device *csdev)
+{
+	int trace_id = source_ops(csdev)->trace_id(csdev);
+
+	/* this shouldn't happen */
+	if (trace_id < 0)
+		return 0;
+
+	return !bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_id_match);
+}
+
+static int coresight_find_link_inport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *parent;
+	struct coresight_connection *conn;
+
+	parent = container_of(csdev->path_link.next,
+			      struct coresight_device, path_link);
+
+	for (i = 0; i < parent->nr_outport; i++) {
+		conn = &parent->conns[i];
+		if (conn->child_dev == csdev)
+			return conn->child_port;
+	}
+
+	dev_err(&csdev->dev, "couldn't find inport, parent: %s, child: %s\n",
+		dev_name(&parent->dev), dev_name(&csdev->dev));
+
+	return 0;
+}
+
+static int coresight_find_link_outport(struct coresight_device *csdev)
+{
+	int i;
+	struct coresight_device *child;
+	struct coresight_connection *conn;
+
+	child = container_of(csdev->path_link.prev,
+			     struct coresight_device, path_link);
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		if (conn->child_dev == child)
+			return conn->outport;
+	}
+
+	dev_err(&csdev->dev, "couldn't find outport, parent: %s, child: %s\n",
+		dev_name(&csdev->dev), dev_name(&child->dev));
+
+	return 0;
+}
+
+static int coresight_enable_sink(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!csdev->enable) {
+		if (sink_ops(csdev)->enable) {
+			ret = sink_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_sink(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (sink_ops(csdev)->disable) {
+			sink_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_link(struct coresight_device *csdev)
+{
+	int ret;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+		refport = inport;
+	else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+		refport = outport;
+	else
+		refport = 0;
+
+	if (atomic_inc_return(&csdev->refcnt[refport]) == 1) {
+		if (link_ops(csdev)->enable) {
+			ret = link_ops(csdev)->enable(csdev, inport, outport);
+			if (ret)
+				return ret;
+		}
+	}
+
+	csdev->enable = true;
+
+	return 0;
+}
+
+static void coresight_disable_link(struct coresight_device *csdev)
+{
+	int i, nr_conns;
+	int link_subtype;
+	int refport, inport, outport;
+
+	inport = coresight_find_link_inport(csdev);
+	outport = coresight_find_link_outport(csdev);
+	link_subtype = csdev->subtype.link_subtype;
+
+	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
+		refport = inport;
+		nr_conns = csdev->nr_inport;
+	} else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) {
+		refport = outport;
+		nr_conns = csdev->nr_outport;
+	} else {
+		refport = 0;
+		nr_conns = 1;
+	}
+
+	if (atomic_dec_return(&csdev->refcnt[refport]) == 0) {
+		if (link_ops(csdev)->disable)
+			link_ops(csdev)->disable(csdev, inport, outport);
+	}
+
+	for (i = 0; i < nr_conns; i++)
+		if (atomic_read(&csdev->refcnt[i]) != 0)
+			return;
+
+	csdev->enable = false;
+}
+
+static int coresight_enable_source(struct coresight_device *csdev)
+{
+	int ret;
+
+	if (!coresight_source_is_unique(csdev)) {
+		dev_warn(&csdev->dev, "traceID %d not unique\n",
+			 source_ops(csdev)->trace_id(csdev));
+		return -EINVAL;
+	}
+
+	if (!csdev->enable) {
+		if (source_ops(csdev)->enable) {
+			ret = source_ops(csdev)->enable(csdev);
+			if (ret)
+				return ret;
+		}
+		csdev->enable = true;
+	}
+
+	atomic_inc(csdev->refcnt);
+
+	return 0;
+}
+
+static void coresight_disable_source(struct coresight_device *csdev)
+{
+	if (atomic_dec_return(csdev->refcnt) == 0) {
+		if (source_ops(csdev)->disable) {
+			source_ops(csdev)->disable(csdev);
+			csdev->enable = false;
+		}
+	}
+}
+
+static int coresight_enable_path(struct list_head *path)
+{
+	int ret = 0;
+	struct coresight_device *cd;
+
+	list_for_each_entry(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			ret = coresight_enable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * Don't enable the source just yet - this needs to
+			 * happen at the very end when all links and sink
+			 * along the path have been configured properly.
+			 */
+			;
+		} else {
+			ret = coresight_enable_link(cd);
+		}
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	list_for_each_entry_continue_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return ret;
+}
+
+static int coresight_disable_path(struct list_head *path)
+{
+	struct coresight_device *cd;
+
+	list_for_each_entry_reverse(cd, path, path_link) {
+		if (cd == list_first_entry(path, struct coresight_device,
+					   path_link)) {
+			coresight_disable_sink(cd);
+		} else if (list_is_last(&cd->path_link, path)) {
+			/*
+			 * The source has already been stopped, no need
+			 * to do it again here.
+			 */
+			;
+		} else {
+			coresight_disable_link(cd);
+		}
+	}
+
+	return 0;
+}
+
+static int coresight_build_paths(struct coresight_device *csdev,
+				 struct list_head *path,
+				 bool enable)
+{
+	int i, ret = -EINVAL;
+	struct coresight_connection *conn;
+
+	list_add(&csdev->path_link, path);
+
+	if (csdev->type == CORESIGHT_DEV_TYPE_SINK && csdev->activated) {
+		if (enable)
+			ret = coresight_enable_path(path);
+		else
+			ret = coresight_disable_path(path);
+	} else {
+		for (i = 0; i < csdev->nr_outport; i++) {
+			conn = &csdev->conns[i];
+			if (coresight_build_paths(conn->child_dev,
+						    path, enable) == 0)
+				ret = 0;
+		}
+	}
+
+	if (list_first_entry(path, struct coresight_device, path_link) != csdev)
+		dev_err(&csdev->dev, "wrong device in %s\n", __func__);
+
+	list_del(&csdev->path_link);
+
+	return ret;
+}
+
+int coresight_enable(struct coresight_device *csdev)
+{
+	int ret = 0;
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		ret = -EINVAL;
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (csdev->enable)
+		goto out;
+
+	if (coresight_build_paths(csdev, &path, true)) {
+		dev_err(&csdev->dev, "building path(s) failed\n");
+		goto out;
+	}
+
+	if (coresight_enable_source(csdev))
+		dev_err(&csdev->dev, "source enable failed\n");
+out:
+	mutex_unlock(&coresight_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(coresight_enable);
+
+void coresight_disable(struct coresight_device *csdev)
+{
+	LIST_HEAD(path);
+
+	mutex_lock(&coresight_mutex);
+	if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+		dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+		goto out;
+	}
+	if (!csdev->enable)
+		goto out;
+
+	coresight_disable_source(csdev);
+	if (coresight_build_paths(csdev, &path, false))
+		dev_err(&csdev->dev, "releasing path(s) failed\n");
+
+out:
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_disable);
+
+static ssize_t enable_sink_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->activated);
+}
+
+static ssize_t enable_sink_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t size)
+{
+	int ret;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val)
+		csdev->activated = true;
+	else
+		csdev->activated = false;
+
+	return size;
+
+}
+static DEVICE_ATTR_RW(enable_sink);
+
+static ssize_t enable_source_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->enable);
+}
+
+static ssize_t enable_source_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t size)
+{
+	int ret = 0;
+	unsigned long val;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (val) {
+		ret = coresight_enable(csdev);
+		if (ret)
+			return ret;
+	} else {
+		coresight_disable(csdev);
+	}
+
+	return size;
+}
+static DEVICE_ATTR_RW(enable_source);
+
+static struct attribute *coresight_sink_attrs[] = {
+	&dev_attr_enable_sink.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_sink);
+
+static struct attribute *coresight_source_attrs[] = {
+	&dev_attr_enable_source.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(coresight_source);
+
+static struct device_type coresight_dev_type[] = {
+	{
+		.name = "none",
+	},
+	{
+		.name = "sink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "link",
+	},
+	{
+		.name = "linksink",
+		.groups = coresight_sink_groups,
+	},
+	{
+		.name = "source",
+		.groups = coresight_source_groups,
+	},
+};
+
+static void coresight_device_release(struct device *dev)
+{
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	kfree(csdev);
+}
+
+static int coresight_orphan_match(struct device *dev, void *data)
+{
+	int i;
+	bool still_orphan = false;
+	struct coresight_device *csdev, *i_csdev;
+	struct coresight_connection *conn;
+
+	csdev = data;
+	i_csdev = to_coresight_device(dev);
+
+	/* No need to check oneself */
+	if (csdev == i_csdev)
+		return 0;
+
+	/* Move on to another component if no connection is orphan */
+	if (!i_csdev->orphan)
+		return 0;
+	/*
+	 * Circle throuch all the connection of that component.  If we find
+	 * an orphan connection whose name matches @csdev, link it.
+	 */
+	for (i = 0; i < i_csdev->nr_outport; i++)	{
+		conn = &i_csdev->conns[i];
+
+		/* We have found at least one orphan connection */
+		if (conn->child_dev == NULL) {
+			/* Does it match this newly added device? */
+			if (!strcmp(dev_name(&csdev->dev), conn->child_name))
+				conn->child_dev = csdev;
+		} else {
+			/* Too bad, this component still has an orphan */
+			still_orphan = true;
+		}
+	}
+
+	i_csdev->orphan = still_orphan;
+
+	/*
+	 * Returning '0' ensures that all known component on the
+	 * bus will be checked.
+	 */
+	return 0;
+}
+
+static void coresight_fixup_orphan_conns(struct coresight_device *csdev)
+{
+	/*
+	 * No need to check for a return value as orphan connection(s)
+	 * are hooked-up with each newly added component.
+	 */
+	bus_for_each_dev(&coresight_bustype, NULL,
+				 csdev, coresight_orphan_match);
+}
+
+
+static int coresight_name_match(struct device *dev, void *data)
+{
+	char *to_match;
+	struct coresight_device *i_csdev;
+
+	to_match = data;
+	i_csdev = to_coresight_device(dev);
+
+	if (!strcmp(to_match, dev_name(&i_csdev->dev)))
+		return 1;
+
+	return 0;
+}
+
+static void coresight_fixup_device_conns(struct coresight_device *csdev)
+{
+	int i;
+	struct device *dev = NULL;
+	struct coresight_connection *conn;
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conn = &csdev->conns[i];
+		dev = bus_find_device(&coresight_bustype, NULL,
+				      (void *)conn->child_name,
+				      coresight_name_match);
+
+		if (dev) {
+			conn->child_dev = to_coresight_device(dev);
+		} else {
+			csdev->orphan = true;
+			conn->child_dev = NULL;
+		}
+	}
+}
+
+/**
+ * coresight_timeout - loop until a bit has changed to a specific state.
+ * @addr: base address of the area of interest.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+int coresight_timeout(void __iomem *addr, u32 offset, int position, int value)
+{
+	int i;
+	u32 val;
+
+	for (i = TIMEOUT_US; i > 0; i--) {
+		val = __raw_readl(addr + offset);
+		/* waiting on the bit to go from 0 to 1 */
+		if (value) {
+			if (val & BIT(position))
+				return 0;
+		/* waiting on the bit to go from 1 to 0 */
+		} else {
+			if (!(val & BIT(position)))
+				return 0;
+		}
+
+		/*
+		 * Delay is arbitrary - the specification doesn't say how long
+		 * we are expected to wait.  Extra check required to make sure
+		 * we don't wait needlessly on the last iteration.
+		 */
+		if (i - 1)
+			udelay(1);
+	}
+
+	return -EAGAIN;
+}
+
+struct bus_type coresight_bustype = {
+	.name	= "coresight",
+};
+
+static int __init coresight_init(void)
+{
+	return bus_register(&coresight_bustype);
+}
+postcore_initcall(coresight_init);
+
+struct coresight_device *coresight_register(struct coresight_desc *desc)
+{
+	int i;
+	int ret;
+	int link_subtype;
+	int nr_refcnts = 1;
+	atomic_t *refcnts = NULL;
+	struct coresight_device *csdev;
+	struct coresight_connection *conns;
+
+	csdev = kzalloc(sizeof(*csdev), GFP_KERNEL);
+	if (!csdev) {
+		ret = -ENOMEM;
+		goto err_kzalloc_csdev;
+	}
+
+	if (desc->type == CORESIGHT_DEV_TYPE_LINK ||
+	    desc->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+		link_subtype = desc->subtype.link_subtype;
+
+		if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+			nr_refcnts = desc->pdata->nr_inport;
+		else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+			nr_refcnts = desc->pdata->nr_outport;
+	}
+
+	refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL);
+	if (!refcnts) {
+		ret = -ENOMEM;
+		goto err_kzalloc_refcnts;
+	}
+
+	csdev->refcnt = refcnts;
+
+	csdev->nr_inport = desc->pdata->nr_inport;
+	csdev->nr_outport = desc->pdata->nr_outport;
+	conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL);
+	if (!conns) {
+		ret = -ENOMEM;
+		goto err_kzalloc_conns;
+	}
+
+	for (i = 0; i < csdev->nr_outport; i++) {
+		conns[i].outport = desc->pdata->outports[i];
+		conns[i].child_name = desc->pdata->child_names[i];
+		conns[i].child_port = desc->pdata->child_ports[i];
+	}
+
+	csdev->conns = conns;
+
+	csdev->type = desc->type;
+	csdev->subtype = desc->subtype;
+	csdev->ops = desc->ops;
+	csdev->orphan = false;
+
+	csdev->dev.type = &coresight_dev_type[desc->type];
+	csdev->dev.groups = desc->groups;
+	csdev->dev.parent = desc->dev;
+	csdev->dev.release = coresight_device_release;
+	csdev->dev.bus = &coresight_bustype;
+	dev_set_name(&csdev->dev, "%s", desc->pdata->name);
+
+	ret = device_register(&csdev->dev);
+	if (ret)
+		goto err_device_register;
+
+	mutex_lock(&coresight_mutex);
+
+	coresight_fixup_device_conns(csdev);
+	coresight_fixup_orphan_conns(csdev);
+
+	mutex_unlock(&coresight_mutex);
+
+	return csdev;
+
+err_device_register:
+	kfree(conns);
+err_kzalloc_conns:
+	kfree(refcnts);
+err_kzalloc_refcnts:
+	kfree(csdev);
+err_kzalloc_csdev:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(coresight_register);
+
+void coresight_unregister(struct coresight_device *csdev)
+{
+	mutex_lock(&coresight_mutex);
+
+	kfree(csdev->conns);
+	device_unregister(&csdev->dev);
+
+	mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_unregister);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/coresight/of_coresight.c b/drivers/coresight/of_coresight.c
new file mode 100644
index 000000000000..5030c0734508
--- /dev/null
+++ b/drivers/coresight/of_coresight.c
@@ -0,0 +1,204 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+#include <linux/coresight.h>
+#include <asm/smp_plat.h>
+
+
+static int of_dev_node_match(struct device *dev, void *data)
+{
+	return dev->of_node == data;
+}
+
+static struct device *
+of_coresight_get_endpoint_device(struct device_node *endpoint)
+{
+	struct device *dev = NULL;
+
+	/*
+	 * If we have a non-configuable replicator, it will be found on the
+	 * platform bus.
+	 */
+	dev = bus_find_device(&platform_bus_type, NULL,
+			      endpoint, of_dev_node_match);
+	if (dev)
+		return dev;
+
+	/*
+	 * We have a configurable component - circle through the AMBA bus
+	 * looking for the device that matches the endpoint node.
+	 */
+	return bus_find_device(&amba_bustype, NULL,
+			       endpoint, of_dev_node_match);
+}
+
+static struct device_node *of_get_coresight_endpoint(
+		const struct device_node *parent, struct device_node *prev)
+{
+	struct device_node *node = of_graph_get_next_endpoint(parent, prev);
+
+	of_node_put(prev);
+	return node;
+}
+
+static void of_coresight_get_ports(struct device_node *node,
+				   int *nr_inport, int *nr_outport)
+{
+	struct device_node *ep = NULL;
+	int in = 0, out = 0;
+
+	do {
+		ep = of_get_coresight_endpoint(node, ep);
+		if (!ep)
+			break;
+
+		if (of_property_read_bool(ep, "slave-mode"))
+			in++;
+		else
+			out++;
+
+	} while (ep);
+
+	*nr_inport = in;
+	*nr_outport = out;
+}
+
+static int of_coresight_alloc_memory(struct device *dev,
+			struct coresight_platform_data *pdata)
+{
+	/* List of output port on this component */
+	pdata->outports = devm_kzalloc(dev, pdata->nr_outport *
+				       sizeof(*pdata->outports),
+				       GFP_KERNEL);
+	if (!pdata->outports)
+		return -ENOMEM;
+
+	/* Children connected to this component via @outport */
+	 pdata->child_names = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_names),
+					  GFP_KERNEL);
+	if (!pdata->child_names)
+		return -ENOMEM;
+
+	/* Port number on the child this component is connected to */
+	pdata->child_ports = devm_kzalloc(dev, pdata->nr_outport *
+					  sizeof(*pdata->child_ports),
+					  GFP_KERNEL);
+	if (!pdata->child_ports)
+		return -ENOMEM;
+
+	return 0;
+}
+
+struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node)
+{
+	int i = 0, ret = 0;
+	struct coresight_platform_data *pdata;
+	struct of_endpoint endpoint, rendpoint;
+	struct device *rdev;
+	struct device_node *cpu;
+	struct device_node *ep = NULL;
+	struct device_node *rparent = NULL;
+	struct device_node *rport = NULL;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	/* Use device name as debugfs handle */
+	pdata->name = dev_name(dev);
+
+	/* Get the number of input and output port for this component */
+	of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
+
+	if (pdata->nr_outport) {
+		ret = of_coresight_alloc_memory(dev, pdata);
+		if (ret)
+			return ERR_PTR(ret);
+
+		/* Iterate through each port to discover topology */
+		do {
+			/* Get a handle on a port */
+			ep = of_get_coresight_endpoint(node, ep);
+			if (!ep)
+				break;
+
+			/*
+			 * No need to deal with input ports, processing for as
+			 * processing for output ports will deal with them.
+			 */
+			if (of_find_property(ep, "slave-mode", NULL))
+				continue;
+
+			/* Get a handle on the local endpoint */
+			ret = of_graph_parse_endpoint(ep, &endpoint);
+
+			if (ret)
+				continue;
+
+			/* The local out port number */
+			pdata->outports[i] = endpoint.id;
+
+			/*
+			 * Get a handle on the remote port and parent
+			 * attached to it.
+			 */
+			rparent = of_graph_get_remote_port_parent(ep);
+			rport = of_graph_get_remote_port(ep);
+
+			if (!rparent || !rport)
+				continue;
+
+			if (of_graph_parse_endpoint(rport, &rendpoint))
+				continue;
+
+			rdev = of_coresight_get_endpoint_device(rparent);
+			if (!dev)
+				continue;
+
+			pdata->child_names[i] = dev_name(rdev);
+			pdata->child_ports[i] = rendpoint.id;
+
+			i++;
+		} while (ep);
+	}
+
+	/* Affinity defaults to CPU0 */
+	pdata->cpu = 0;
+	cpu = of_parse_phandle(node, "cpu", 0);
+	if (cpu) {
+		const u32 *mpidr;
+		int len, index;
+
+		mpidr = of_get_property(cpu, "reg", &len);
+		if (mpidr && len == 4) {
+			index = get_logical_index(be32_to_cpup(mpidr));
+			if (index != -EINVAL)
+				pdata->cpu = index;
+		}
+	}
+
+	return pdata;
+}
+EXPORT_SYMBOL_GPL(of_get_coresight_platform_data);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 31297499a60a..56f9cdb8d097 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -4,7 +4,8 @@
 
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
+	depends on (BIG_LITTLE && ARM_CPU_TOPOLOGY) || (ARM64 && SMP)
+	depends on HAVE_CLK
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 74945652dd7a..dac58f67307a 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -47,7 +47,7 @@ obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
 # LITTLE drivers, so that it is probed last.
 obj-$(CONFIG_ARM_DT_BL_CPUFREQ)		+= arm_big_little_dt.o
 
-obj-$(CONFIG_ARCH_DAVINCI_DA850)	+= davinci-cpufreq.o
+obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
 obj-$(CONFIG_UX500_SOC_DB8500)		+= dbx500-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS_CPUFREQ)	+= exynos-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS4210_CPUFREQ)	+= exynos4210-cpufreq.o
diff --git a/drivers/cpufreq/at32ap-cpufreq.c b/drivers/cpufreq/at32ap-cpufreq.c
index a1c79f549edb..7b612c8bb09e 100644
--- a/drivers/cpufreq/at32ap-cpufreq.c
+++ b/drivers/cpufreq/at32ap-cpufreq.c
@@ -52,7 +52,7 @@ static int at32_set_target(struct cpufreq_policy *policy, unsigned int index)
 static int at32_cpufreq_driver_init(struct cpufreq_policy *policy)
 {
 	unsigned int frequency, rate, min_freq;
-	static struct clk *cpuclk;
+	struct clk *cpuclk;
 	int retval, steps, i;
 
 	if (policy->cpu != 0)
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 0c12ffc0ebcb..51322856f908 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -131,7 +131,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	cpu_reg = devm_regulator_get_optional(cpu_dev, "cpu0");
+	cpu_reg = regulator_get_optional(cpu_dev, "cpu0");
 	if (IS_ERR(cpu_reg)) {
 		/*
 		 * If cpu0 regulator supply node is present, but regulator is
@@ -146,23 +146,23 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 			PTR_ERR(cpu_reg));
 	}
 
-	cpu_clk = devm_clk_get(cpu_dev, NULL);
+	cpu_clk = clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
 		ret = PTR_ERR(cpu_clk);
 		pr_err("failed to get cpu0 clock: %d\n", ret);
-		goto out_put_node;
+		goto out_put_reg;
 	}
 
 	ret = of_init_opp_table(cpu_dev);
 	if (ret) {
 		pr_err("failed to init OPP table: %d\n", ret);
-		goto out_put_node;
+		goto out_put_clk;
 	}
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		pr_err("failed to init cpufreq table: %d\n", ret);
-		goto out_put_node;
+		goto out_put_clk;
 	}
 
 	of_property_read_u32(np, "voltage-tolerance", &voltage_tolerance);
@@ -217,6 +217,12 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 
 out_free_table:
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
+out_put_clk:
+	if (!IS_ERR(cpu_clk))
+		clk_put(cpu_clk);
+out_put_reg:
+	if (!IS_ERR(cpu_reg))
+		regulator_put(cpu_reg);
 out_put_node:
 	of_node_put(np);
 	return ret;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 199b52b7c3e1..4854f81d038b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -460,7 +460,18 @@ show_one(cpuinfo_max_freq, cpuinfo.max_freq);
 show_one(cpuinfo_transition_latency, cpuinfo.transition_latency);
 show_one(scaling_min_freq, min);
 show_one(scaling_max_freq, max);
-show_one(scaling_cur_freq, cur);
+
+static ssize_t show_scaling_cur_freq(
+	struct cpufreq_policy *policy, char *buf)
+{
+	ssize_t ret;
+
+	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get)
+		ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu));
+	else
+		ret = sprintf(buf, "%u\n", policy->cur);
+	return ret;
+}
 
 static int cpufreq_set_policy(struct cpufreq_policy *policy,
 				struct cpufreq_policy *new_policy);
@@ -854,11 +865,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 		if (ret)
 			goto err_out_kobj_put;
 	}
-	if (has_target()) {
-		ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
-		if (ret)
-			goto err_out_kobj_put;
-	}
+
+	ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
+	if (ret)
+		goto err_out_kobj_put;
+
 	if (cpufreq_driver->bios_limit) {
 		ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
 		if (ret)
@@ -1089,10 +1100,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 	 * the creation of a brand new one. So we need to perform this update
 	 * by invoking update_policy_cpu().
 	 */
-	if (frozen && cpu != policy->cpu)
+	if (frozen && cpu != policy->cpu) {
 		update_policy_cpu(policy, cpu);
-	else
+		WARN_ON(kobject_move(&policy->kobj, &dev->kobj));
+	} else {
 		policy->cpu = cpu;
+	}
 
 	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
@@ -1223,6 +1236,8 @@ err_get_freq:
 		per_cpu(cpufreq_cpu_data, j) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	up_write(&policy->rwsem);
+
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 err_set_policy_cpu:
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index ba43991ba98a..e1c6433b16e0 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -366,6 +366,11 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		break;
 
 	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&dbs_data->mutex);
+		if (!cpu_cdbs->cur_policy) {
+			mutex_unlock(&dbs_data->mutex);
+			break;
+		}
 		mutex_lock(&cpu_cdbs->timer_mutex);
 		if (policy->max < cpu_cdbs->cur_policy->cur)
 			__cpufreq_driver_target(cpu_cdbs->cur_policy,
@@ -375,6 +380,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 					policy->min, CPUFREQ_RELATION_L);
 		dbs_check_cpu(dbs_data, cpu);
 		mutex_unlock(&cpu_cdbs->timer_mutex);
+		mutex_unlock(&dbs_data->mutex);
 		break;
 	}
 	return 0;
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index bf8902a0866d..b464f29d8d54 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -19,7 +19,7 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
 #include <linux/platform_device.h>
 
 #define HB_CPUFREQ_CHANGE_NOTE	0x80000001
diff --git a/drivers/cpufreq/integrator-cpufreq.c b/drivers/cpufreq/integrator-cpufreq.c
index 0e27844e8c2d..8089dd2cd9d8 100644
--- a/drivers/cpufreq/integrator-cpufreq.c
+++ b/drivers/cpufreq/integrator-cpufreq.c
@@ -213,9 +213,9 @@ static int __init integrator_cpufreq_probe(struct platform_device *pdev)
 	return cpufreq_register_driver(&integrator_driver);
 }
 
-static void __exit integrator_cpufreq_remove(struct platform_device *pdev)
+static int __exit integrator_cpufreq_remove(struct platform_device *pdev)
 {
-	cpufreq_unregister_driver(&integrator_driver);
+	return cpufreq_unregister_driver(&integrator_driver);
 }
 
 static const struct of_device_id integrator_cpufreq_match[] = {
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2cd36b9297f3..533a509439ca 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -37,12 +37,13 @@
 #define BYT_RATIOS		0x66a
 #define BYT_VIDS		0x66b
 #define BYT_TURBO_RATIOS	0x66c
+#define BYT_TURBO_VIDS		0x66d
 
 
-#define FRAC_BITS 6
+#define FRAC_BITS 8
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
-#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS)
+
 
 static inline int32_t mul_fp(int32_t x, int32_t y)
 {
@@ -54,24 +55,37 @@ static inline int32_t div_fp(int32_t x, int32_t y)
 	return div_s64((int64_t)x << FRAC_BITS, (int64_t)y);
 }
 
+static inline int ceiling_fp(int32_t x)
+{
+	int mask, ret;
+
+	ret = fp_toint(x);
+	mask = (1 << FRAC_BITS) - 1;
+	if (x & mask)
+		ret += 1;
+	return ret;
+}
+
 struct sample {
 	int32_t core_pct_busy;
 	u64 aperf;
 	u64 mperf;
-	unsigned long long tsc;
 	int freq;
+	ktime_t time;
 };
 
 struct pstate_data {
 	int	current_pstate;
 	int	min_pstate;
 	int	max_pstate;
+	int	scaling;
 	int	turbo_pstate;
 };
 
 struct vid_data {
-	int32_t min;
-	int32_t max;
+	int min;
+	int max;
+	int turbo;
 	int32_t ratio;
 };
 
@@ -96,11 +110,10 @@ struct cpudata {
 	struct vid_data vid;
 	struct _pid pid;
 
+	ktime_t last_sample_time;
 	u64	prev_aperf;
 	u64	prev_mperf;
-	unsigned long long prev_tsc;
-	int	sample_ptr;
-	struct sample samples[SAMPLE_COUNT];
+	struct sample sample;
 };
 
 static struct cpudata **all_cpu_data;
@@ -117,6 +130,7 @@ struct pstate_funcs {
 	int (*get_max)(void);
 	int (*get_min)(void);
 	int (*get_turbo)(void);
+	int (*get_scaling)(void);
 	void (*set)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
 };
@@ -131,6 +145,7 @@ static struct pstate_funcs pstate_funcs;
 
 struct perf_limits {
 	int no_turbo;
+	int turbo_disabled;
 	int max_perf_pct;
 	int min_perf_pct;
 	int32_t max_perf;
@@ -199,7 +214,7 @@ static signed int pid_calc(struct _pid *pid, int32_t busy)
 	pid->last_err = fp_error;
 
 	result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
-
+	result = result + (1 << (FRAC_BITS-1));
 	return (signed int)fp_toint(result);
 }
 
@@ -290,7 +305,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 	limits.no_turbo = clamp_t(int, input, 0 , 1);
-
+	if (limits.turbo_disabled) {
+		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
+		limits.no_turbo = limits.turbo_disabled;
+	}
 	return count;
 }
 
@@ -360,21 +378,21 @@ static int byt_get_min_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_RATIOS, value);
-	return (value >> 8) & 0xFF;
+	return (value >> 8) & 0x7F;
 }
 
 static int byt_get_max_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_RATIOS, value);
-	return (value >> 16) & 0xFF;
+	return (value >> 16) & 0x7F;
 }
 
 static int byt_get_turbo_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_TURBO_RATIOS, value);
-	return value & 0x3F;
+	return value & 0x7F;
 }
 
 static void byt_set_pstate(struct cpudata *cpudata, int pstate)
@@ -384,7 +402,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	u32 vid;
 
 	val = pstate << 8;
-	if (limits.no_turbo)
+	if (limits.no_turbo && !limits.turbo_disabled)
 		val |= (u64)1 << 32;
 
 	vid_fp = cpudata->vid.min + mul_fp(
@@ -392,17 +410,37 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 		cpudata->vid.ratio);
 
 	vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max);
-	vid = fp_toint(vid_fp);
+	vid = ceiling_fp(vid_fp);
+
+	if (pstate > cpudata->pstate.max_pstate)
+		vid = cpudata->vid.turbo;
 
 	val |= vid;
 
 	wrmsrl(MSR_IA32_PERF_CTL, val);
 }
 
+#define BYT_BCLK_FREQS 5
+static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800};
+
+static int byt_get_scaling(void)
+{
+	u64 value;
+	int i;
+
+	rdmsrl(MSR_FSB_FREQ, value);
+	i = value & 0x3;
+
+	BUG_ON(i > BYT_BCLK_FREQS);
+
+	return byt_freq_table[i] * 100;
+}
+
 static void byt_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
 
+
 	rdmsrl(BYT_VIDS, value);
 	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
 	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
@@ -410,6 +448,9 @@ static void byt_get_vid(struct cpudata *cpudata)
 		cpudata->vid.max - cpudata->vid.min,
 		int_tofp(cpudata->pstate.max_pstate -
 			cpudata->pstate.min_pstate));
+
+	rdmsrl(BYT_TURBO_VIDS, value);
+	cpudata->vid.turbo = value & 0x7f;
 }
 
 
@@ -439,12 +480,17 @@ static int core_get_turbo_pstate(void)
 	return ret;
 }
 
+static inline int core_get_scaling(void)
+{
+	return 100000;
+}
+
 static void core_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 
 	val = pstate << 8;
-	if (limits.no_turbo)
+	if (limits.no_turbo && !limits.turbo_disabled)
 		val |= (u64)1 << 32;
 
 	wrmsrl(MSR_IA32_PERF_CTL, val);
@@ -463,6 +509,7 @@ static struct cpu_defaults core_params = {
 		.get_max = core_get_max_pstate,
 		.get_min = core_get_min_pstate,
 		.get_turbo = core_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
 	},
 };
@@ -481,6 +528,7 @@ static struct cpu_defaults byt_params = {
 		.get_min = byt_get_min_pstate,
 		.get_turbo = byt_get_turbo_pstate,
 		.set = byt_set_pstate,
+		.get_scaling = byt_get_scaling,
 		.get_vid = byt_get_vid,
 	},
 };
@@ -514,7 +562,7 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
-	trace_cpu_frequency(pstate * 100000, cpu->cpu);
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 
 	cpu->pstate.current_pstate = pstate;
 
@@ -543,62 +591,54 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
 	cpu->pstate.max_pstate = pstate_funcs.get_max();
 	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
+	cpu->pstate.scaling = pstate_funcs.get_scaling();
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
-
-	/*
-	 * goto max pstate so we don't slow up boot if we are built-in if we are
-	 * a module we will take care of it during normal operation
-	 */
-	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
 }
 
 static inline void intel_pstate_calc_busy(struct cpudata *cpu,
 					struct sample *sample)
 {
-	int32_t core_pct;
-	int32_t c0_pct;
+	int64_t core_pct;
+	int32_t rem;
 
-	core_pct = div_fp(int_tofp((sample->aperf)),
-			int_tofp((sample->mperf)));
-	core_pct = mul_fp(core_pct, int_tofp(100));
-	FP_ROUNDUP(core_pct);
+	core_pct = int_tofp(sample->aperf) * int_tofp(100);
+	core_pct = div_u64_rem(core_pct, int_tofp(sample->mperf), &rem);
 
-	c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc));
+	if ((rem << 1) >= int_tofp(sample->mperf))
+		core_pct += 1;
 
 	sample->freq = fp_toint(
-		mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
+		mul_fp(int_tofp(
+			cpu->pstate.max_pstate * cpu->pstate.scaling / 100),
+			core_pct));
 
-	sample->core_pct_busy = mul_fp(core_pct, c0_pct);
+	sample->core_pct_busy = (int32_t)core_pct;
 }
 
 static inline void intel_pstate_sample(struct cpudata *cpu)
 {
 	u64 aperf, mperf;
-	unsigned long long tsc;
 
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
-	tsc = native_read_tsc();
 
 	aperf = aperf >> FRAC_BITS;
 	mperf = mperf >> FRAC_BITS;
-	tsc = tsc >> FRAC_BITS;
 
-	cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
-	cpu->samples[cpu->sample_ptr].aperf = aperf;
-	cpu->samples[cpu->sample_ptr].mperf = mperf;
-	cpu->samples[cpu->sample_ptr].tsc = tsc;
-	cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
-	cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
-	cpu->samples[cpu->sample_ptr].tsc -= cpu->prev_tsc;
+	cpu->last_sample_time = cpu->sample.time;
+	cpu->sample.time = ktime_get();
+	cpu->sample.aperf = aperf;
+	cpu->sample.mperf = mperf;
+	cpu->sample.aperf -= cpu->prev_aperf;
+	cpu->sample.mperf -= cpu->prev_mperf;
 
-	intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
+	intel_pstate_calc_busy(cpu, &cpu->sample);
 
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
-	cpu->prev_tsc = tsc;
 }
 
 static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
@@ -612,13 +652,25 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 
 static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
-	int32_t core_busy, max_pstate, current_pstate;
+	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
+	u32 duration_us;
+	u32 sample_time;
 
-	core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
+	core_busy = cpu->sample.core_pct_busy;
 	max_pstate = int_tofp(cpu->pstate.max_pstate);
 	current_pstate = int_tofp(cpu->pstate.current_pstate);
 	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
-	return FP_ROUNDUP(core_busy);
+
+	sample_time = (pid_params.sample_rate_ms  * USEC_PER_MSEC);
+	duration_us = (u32) ktime_us_delta(cpu->sample.time,
+					cpu->last_sample_time);
+	if (duration_us > sample_time * 3) {
+		sample_ratio = div_fp(int_tofp(sample_time),
+				int_tofp(duration_us));
+		core_busy = mul_fp(core_busy, sample_ratio);
+	}
+
+	return core_busy;
 }
 
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
@@ -648,7 +700,7 @@ static void intel_pstate_timer_func(unsigned long __data)
 
 	intel_pstate_sample(cpu);
 
-	sample = &cpu->samples[cpu->sample_ptr];
+	sample = &cpu->sample;
 
 	intel_pstate_adjust_busy_pstate(cpu);
 
@@ -672,10 +724,14 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x37, byt_params),
 	ICPU(0x3a, core_params),
 	ICPU(0x3c, core_params),
+	ICPU(0x3d, core_params),
 	ICPU(0x3e, core_params),
 	ICPU(0x3f, core_params),
 	ICPU(0x45, core_params),
 	ICPU(0x46, core_params),
+	ICPU(0x4c, byt_params),
+	ICPU(0x4f, core_params),
+	ICPU(0x56, core_params),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -696,14 +752,8 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	cpu = all_cpu_data[cpunum];
 
-	intel_pstate_get_cpu_pstates(cpu);
-	if (!cpu->pstate.current_pstate) {
-		all_cpu_data[cpunum] = NULL;
-		kfree(cpu);
-		return -ENODATA;
-	}
-
 	cpu->cpu = cpunum;
+	intel_pstate_get_cpu_pstates(cpu);
 
 	init_timer_deferrable(&cpu->timer);
 	cpu->timer.function = intel_pstate_timer_func;
@@ -712,7 +762,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu->timer.expires = jiffies + HZ/100;
 	intel_pstate_busy_pid_reset(cpu);
 	intel_pstate_sample(cpu);
-	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
 
 	add_timer_on(&cpu->timer, cpunum);
 
@@ -729,7 +778,7 @@ static unsigned int intel_pstate_get(unsigned int cpu_num)
 	cpu = all_cpu_data[cpu_num];
 	if (!cpu)
 		return 0;
-	sample = &cpu->samples[cpu->sample_ptr];
+	sample = &cpu->sample;
 	return sample->freq;
 }
 
@@ -745,9 +794,10 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits.min_perf_pct = 100;
 		limits.min_perf = int_tofp(1);
+		limits.max_policy_pct = 100;
 		limits.max_perf_pct = 100;
 		limits.max_perf = int_tofp(1);
-		limits.no_turbo = 0;
+		limits.no_turbo = limits.turbo_disabled;
 		return 0;
 	}
 	limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
@@ -787,6 +837,7 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
 	int rc;
+	u64 misc_en;
 
 	rc = intel_pstate_init_cpu(policy->cpu);
 	if (rc)
@@ -794,18 +845,24 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	if (!limits.no_turbo &&
-		limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
+	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
+	if (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
+		cpu->pstate.max_pstate == cpu->pstate.turbo_pstate) {
+		limits.turbo_disabled = 1;
+		limits.no_turbo = 1;
+	}
+	if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
-	policy->min = cpu->pstate.min_pstate * 100000;
-	policy->max = cpu->pstate.turbo_pstate * 100000;
+	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
+	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 
 	/* cpuinfo and default policy values */
-	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
-	policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000;
+	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
+	policy->cpuinfo.max_freq =
+		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
@@ -863,6 +920,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 	pstate_funcs.get_max   = funcs->get_max;
 	pstate_funcs.get_min   = funcs->get_min;
 	pstate_funcs.get_turbo = funcs->get_turbo;
+	pstate_funcs.get_scaling = funcs->get_scaling;
 	pstate_funcs.set       = funcs->set;
 	pstate_funcs.get_vid   = funcs->get_vid;
 }
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index b6581abc9207..7231967f51b4 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -62,14 +62,14 @@ static int loongson2_cpufreq_target(struct cpufreq_policy *policy,
 	set_cpus_allowed_ptr(current, &cpus_allowed);
 
 	/* setting the cpu frequency */
-	clk_set_rate(policy->clk, freq);
+	clk_set_rate(policy->clk, freq * 1000);
 
 	return 0;
 }
 
 static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	static struct clk *cpuclk;
+	struct clk *cpuclk;
 	int i;
 	unsigned long rate;
 	int ret;
@@ -92,7 +92,7 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	     i++)
 		loongson2_clockmod_table[i].frequency = (rate * i) / 8;
 
-	ret = clk_set_rate(cpuclk, rate);
+	ret = clk_set_rate(cpuclk, rate * 1000);
 	if (ret) {
 		clk_put(cpuclk);
 		return ret;
diff --git a/drivers/cpufreq/unicore2-cpufreq.c b/drivers/cpufreq/unicore2-cpufreq.c
index 36cc330b8747..99d280d6f370 100644
--- a/drivers/cpufreq/unicore2-cpufreq.c
+++ b/drivers/cpufreq/unicore2-cpufreq.c
@@ -45,7 +45,7 @@ static int ucv2_target(struct cpufreq_policy *policy,
 	freqs.new = target_freq;
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	ret = clk_set_rate(policy->mclk, target_freq * 1000);
+	ret = clk_set_rate(policy->clk, target_freq * 1000);
 	cpufreq_notify_post_transition(policy, &freqs, ret);
 
 	return ret;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 0378328f47a7..d97a03dbf42c 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -835,8 +835,9 @@ static int ahash_update_ctx(struct ahash_request *req)
 					   edesc->sec4_sg + sec4_sg_src_index,
 					   chained);
 			if (*next_buflen) {
-				sg_copy_part(next_buf, req->src, to_hash -
-					     *buflen, req->nbytes);
+				scatterwalk_map_and_copy(next_buf, req->src,
+							 to_hash - *buflen,
+							 *next_buflen, 0);
 				state->current_buf = !state->current_buf;
 			}
 		} else {
@@ -869,7 +870,8 @@ static int ahash_update_ctx(struct ahash_request *req)
 			kfree(edesc);
 		}
 	} else if (*next_buflen) {
-		sg_copy(buf + *buflen, req->src, req->nbytes);
+		scatterwalk_map_and_copy(buf + *buflen, req->src, 0,
+					 req->nbytes, 0);
 		*buflen = *next_buflen;
 		*next_buflen = last_buflen;
 	}
@@ -1216,8 +1218,9 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		src_map_to_sec4_sg(jrdev, req->src, src_nents,
 				   edesc->sec4_sg + 1, chained);
 		if (*next_buflen) {
-			sg_copy_part(next_buf, req->src, to_hash - *buflen,
-				    req->nbytes);
+			scatterwalk_map_and_copy(next_buf, req->src,
+						 to_hash - *buflen,
+						 *next_buflen, 0);
 			state->current_buf = !state->current_buf;
 		}
 
@@ -1248,7 +1251,8 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 			kfree(edesc);
 		}
 	} else if (*next_buflen) {
-		sg_copy(buf + *buflen, req->src, req->nbytes);
+		scatterwalk_map_and_copy(buf + *buflen, req->src, 0,
+					 req->nbytes, 0);
 		*buflen = *next_buflen;
 		*next_buflen = 0;
 	}
@@ -1348,9 +1352,9 @@ static int ahash_update_first(struct ahash_request *req)
 	struct device *jrdev = ctx->jrdev;
 	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
 		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
-	u8 *next_buf = state->buf_0 + state->current_buf *
-		       CAAM_MAX_HASH_BLOCK_SIZE;
-	int *next_buflen = &state->buflen_0 + state->current_buf;
+	u8 *next_buf = state->current_buf ? state->buf_1 : state->buf_0;
+	int *next_buflen = state->current_buf ?
+		&state->buflen_1 : &state->buflen_0;
 	int to_hash;
 	u32 *sh_desc = ctx->sh_desc_update_first, *desc;
 	dma_addr_t ptr = ctx->sh_desc_update_first_dma;
@@ -1405,7 +1409,8 @@ static int ahash_update_first(struct ahash_request *req)
 		}
 
 		if (*next_buflen)
-			sg_copy_part(next_buf, req->src, to_hash, req->nbytes);
+			scatterwalk_map_and_copy(next_buf, req->src, to_hash,
+						 *next_buflen, 0);
 
 		sh_len = desc_len(sh_desc);
 		desc = edesc->hw_desc;
@@ -1438,7 +1443,8 @@ static int ahash_update_first(struct ahash_request *req)
 		state->update = ahash_update_no_ctx;
 		state->finup = ahash_finup_no_ctx;
 		state->final = ahash_final_no_ctx;
-		sg_copy(next_buf, req->src, req->nbytes);
+		scatterwalk_map_and_copy(next_buf, req->src, 0,
+					 req->nbytes, 0);
 	}
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "next buf@"__stringify(__LINE__)": ",
diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c
index 9f25f5296029..0eabd81e1a90 100644
--- a/drivers/crypto/caam/error.c
+++ b/drivers/crypto/caam/error.c
@@ -16,9 +16,13 @@
 	char *tmp;						\
 								\
 	tmp = kmalloc(sizeof(format) + max_alloc, GFP_ATOMIC);	\
-	sprintf(tmp, format, param);				\
-	strcat(str, tmp);					\
-	kfree(tmp);						\
+	if (likely(tmp)) {					\
+		sprintf(tmp, format, param);			\
+		strcat(str, tmp);				\
+		kfree(tmp);					\
+	} else {						\
+		strcat(str, "kmalloc failure in SPRINTFCAT");	\
+	}							\
 }
 
 static void report_jump_idx(u32 status, char *outstr)
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index 1d80bd3636c5..b512a4ba7569 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -453,8 +453,8 @@ static int caam_jr_probe(struct platform_device *pdev)
 	int error;
 
 	jrdev = &pdev->dev;
-	jrpriv = kmalloc(sizeof(struct caam_drv_private_jr),
-			 GFP_KERNEL);
+	jrpriv = devm_kmalloc(jrdev, sizeof(struct caam_drv_private_jr),
+			      GFP_KERNEL);
 	if (!jrpriv)
 		return -ENOMEM;
 
@@ -487,10 +487,8 @@ static int caam_jr_probe(struct platform_device *pdev)
 
 	/* Now do the platform independent part */
 	error = caam_jr_init(jrdev); /* now turn on hardware */
-	if (error) {
-		kfree(jrpriv);
+	if (error)
 		return error;
-	}
 
 	jrpriv->dev = jrdev;
 	spin_lock(&driver_data.jr_alloc_lock);
diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c
index ea2e406610eb..b872eed2957b 100644
--- a/drivers/crypto/caam/key_gen.c
+++ b/drivers/crypto/caam/key_gen.c
@@ -51,23 +51,29 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len,
 	u32 *desc;
 	struct split_key_result result;
 	dma_addr_t dma_addr_in, dma_addr_out;
-	int ret = 0;
+	int ret = -ENOMEM;
 
 	desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
 	if (!desc) {
 		dev_err(jrdev, "unable to allocate key input memory\n");
-		return -ENOMEM;
+		return ret;
 	}
 
-	init_job_desc(desc, 0);
-
 	dma_addr_in = dma_map_single(jrdev, (void *)key_in, keylen,
 				     DMA_TO_DEVICE);
 	if (dma_mapping_error(jrdev, dma_addr_in)) {
 		dev_err(jrdev, "unable to map key input memory\n");
-		kfree(desc);
-		return -ENOMEM;
+		goto out_free;
 	}
+
+	dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len,
+				      DMA_FROM_DEVICE);
+	if (dma_mapping_error(jrdev, dma_addr_out)) {
+		dev_err(jrdev, "unable to map key output memory\n");
+		goto out_unmap_in;
+	}
+
+	init_job_desc(desc, 0);
 	append_key(desc, dma_addr_in, keylen, CLASS_2 | KEY_DEST_CLASS_REG);
 
 	/* Sets MDHA up into an HMAC-INIT */
@@ -84,13 +90,6 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len,
 	 * FIFO_STORE with the explicit split-key content store
 	 * (0x26 output type)
 	 */
-	dma_addr_out = dma_map_single(jrdev, key_out, split_key_pad_len,
-				      DMA_FROM_DEVICE);
-	if (dma_mapping_error(jrdev, dma_addr_out)) {
-		dev_err(jrdev, "unable to map key output memory\n");
-		kfree(desc);
-		return -ENOMEM;
-	}
 	append_fifo_store(desc, dma_addr_out, split_key_len,
 			  LDST_CLASS_2_CCB | FIFOST_TYPE_SPLIT_KEK);
 
@@ -118,10 +117,10 @@ int gen_split_key(struct device *jrdev, u8 *key_out, int split_key_len,
 
 	dma_unmap_single(jrdev, dma_addr_out, split_key_pad_len,
 			 DMA_FROM_DEVICE);
+out_unmap_in:
 	dma_unmap_single(jrdev, dma_addr_in, keylen, DMA_TO_DEVICE);
-
+out_free:
 	kfree(desc);
-
 	return ret;
 }
 EXPORT_SYMBOL(gen_split_key);
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
index b12ff85f4241..ce28a563effc 100644
--- a/drivers/crypto/caam/sg_sw_sec4.h
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -116,57 +116,3 @@ static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg,
 	}
 	return nents;
 }
-
-/* Map SG page in kernel virtual address space and copy */
-static inline void sg_map_copy(u8 *dest, struct scatterlist *sg,
-			       int len, int offset)
-{
-	u8 *mapped_addr;
-
-	/*
-	 * Page here can be user-space pinned using get_user_pages
-	 * Same must be kmapped before use and kunmapped subsequently
-	 */
-	mapped_addr = kmap_atomic(sg_page(sg));
-	memcpy(dest, mapped_addr + offset, len);
-	kunmap_atomic(mapped_addr);
-}
-
-/* Copy from len bytes of sg to dest, starting from beginning */
-static inline void sg_copy(u8 *dest, struct scatterlist *sg, unsigned int len)
-{
-	struct scatterlist *current_sg = sg;
-	int cpy_index = 0, next_cpy_index = current_sg->length;
-
-	while (next_cpy_index < len) {
-		sg_map_copy(dest + cpy_index, current_sg, current_sg->length,
-			    current_sg->offset);
-		current_sg = scatterwalk_sg_next(current_sg);
-		cpy_index = next_cpy_index;
-		next_cpy_index += current_sg->length;
-	}
-	if (cpy_index < len)
-		sg_map_copy(dest + cpy_index, current_sg, len-cpy_index,
-			    current_sg->offset);
-}
-
-/* Copy sg data, from to_skip to end, to dest */
-static inline void sg_copy_part(u8 *dest, struct scatterlist *sg,
-				      int to_skip, unsigned int end)
-{
-	struct scatterlist *current_sg = sg;
-	int sg_index, cpy_index, offset;
-
-	sg_index = current_sg->length;
-	while (sg_index <= to_skip) {
-		current_sg = scatterwalk_sg_next(current_sg);
-		sg_index += current_sg->length;
-	}
-	cpy_index = sg_index - to_skip;
-	offset = current_sg->offset + current_sg->length - cpy_index;
-	sg_map_copy(dest, current_sg, cpy_index, offset);
-	if (end - sg_index) {
-		current_sg = scatterwalk_sg_next(current_sg);
-		sg_copy(dest + cpy_index, current_sg, end - sg_index);
-	}
-}
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index a999f537228f..92105f3dc8e0 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -190,7 +190,7 @@ static void add_session_id(struct cryp_ctx *ctx)
 static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 {
 	struct cryp_ctx *ctx;
-	int i;
+	int count;
 	struct cryp_device_data *device_data;
 
 	if (param == NULL) {
@@ -215,12 +215,11 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	if (cryp_pending_irq_src(device_data,
 				 CRYP_IRQ_SRC_OUTPUT_FIFO)) {
 		if (ctx->outlen / ctx->blocksize > 0) {
-			for (i = 0; i < ctx->blocksize / 4; i++) {
-				*(ctx->outdata) = readl_relaxed(
-						&device_data->base->dout);
-				ctx->outdata += 4;
-				ctx->outlen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			readsl(&device_data->base->dout, ctx->outdata, count);
+			ctx->outdata += count;
+			ctx->outlen -= count;
 
 			if (ctx->outlen == 0) {
 				cryp_disable_irq_src(device_data,
@@ -230,12 +229,12 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	} else if (cryp_pending_irq_src(device_data,
 					CRYP_IRQ_SRC_INPUT_FIFO)) {
 		if (ctx->datalen / ctx->blocksize > 0) {
-			for (i = 0 ; i < ctx->blocksize / 4; i++) {
-				writel_relaxed(ctx->indata,
-						&device_data->base->din);
-				ctx->indata += 4;
-				ctx->datalen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			writesl(&device_data->base->din, ctx->indata, count);
+
+			ctx->indata += count;
+			ctx->datalen -= count;
 
 			if (ctx->datalen == 0)
 				cryp_disable_irq_src(device_data,
diff --git a/drivers/dma/TODO b/drivers/dma/TODO
index 734ed0206cd5..b8045cd42ee1 100644
--- a/drivers/dma/TODO
+++ b/drivers/dma/TODO
@@ -7,7 +7,6 @@ TODO for slave dma
 	- imx-dma
 	- imx-sdma
 	- mxs-dma.c
-	- dw_dmac
 	- intel_mid_dma
 4. Check other subsystems for dma drivers and merge/move to dmaengine
 5. Remove dma_slave_config's dma direction.
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index ed610b497518..a4068e2d2b5d 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1014,6 +1014,7 @@ static void dmaengine_unmap(struct kref *kref)
 		dma_unmap_page(dev, unmap->addr[i], unmap->len,
 			       DMA_BIDIRECTIONAL);
 	}
+	cnt = unmap->map_cnt;
 	mempool_free(unmap, __get_unmap_pool(cnt)->pool);
 }
 
@@ -1079,6 +1080,7 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 	memset(unmap, 0, sizeof(*unmap));
 	kref_init(&unmap->kref);
 	unmap->dev = dev;
+	unmap->map_cnt = nr;
 
 	return unmap;
 }
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 13ac3f240e79..b0972b3869c7 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -279,6 +279,15 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 	channel_set_bit(dw, CH_EN, dwc->mask);
 }
 
+static void dwc_dostart_first_queued(struct dw_dma_chan *dwc)
+{
+	if (list_empty(&dwc->queue))
+		return;
+
+	list_move(dwc->queue.next, &dwc->active_list);
+	dwc_dostart(dwc, dwc_first_active(dwc));
+}
+
 /*----------------------------------------------------------------------*/
 
 static void
@@ -335,10 +344,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 * the completed ones.
 	 */
 	list_splice_init(&dwc->active_list, &list);
-	if (!list_empty(&dwc->queue)) {
-		list_move(dwc->queue.next, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	}
+	dwc_dostart_first_queued(dwc);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -467,10 +473,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	/* Try to continue after resetting the channel... */
 	dwc_chan_disable(dw, dwc);
 
-	if (!list_empty(&dwc->queue)) {
-		list_move(dwc->queue.next, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	}
+	dwc_dostart_first_queued(dwc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
@@ -677,17 +680,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	 * possible, perhaps even appending to those already submitted
 	 * for DMA. But this is hard to do in a race-free manner.
 	 */
-	if (list_empty(&dwc->active_list)) {
-		dev_vdbg(chan2dev(tx->chan), "%s: started %u\n", __func__,
-				desc->txd.cookie);
-		list_add_tail(&desc->desc_node, &dwc->active_list);
-		dwc_dostart(dwc, dwc_first_active(dwc));
-	} else {
-		dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__,
-				desc->txd.cookie);
 
-		list_add_tail(&desc->desc_node, &dwc->queue);
-	}
+	dev_vdbg(chan2dev(tx->chan), "%s: queued %u\n", __func__, desc->txd.cookie);
+	list_add_tail(&desc->desc_node, &dwc->queue);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -1092,9 +1087,12 @@ dwc_tx_status(struct dma_chan *chan,
 static void dwc_issue_pending(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
 
-	if (!list_empty(&dwc->queue))
-		dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+	spin_lock_irqsave(&dwc->lock, flags);
+	if (list_empty(&dwc->active_list))
+		dwc_dostart_first_queued(dwc);
+	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
 static int dwc_alloc_chan_resources(struct dma_chan *chan)
@@ -1545,11 +1543,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	/* Disable BLOCK interrupts as well */
 	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 
-	err = devm_request_irq(chip->dev, chip->irq, dw_dma_interrupt,
-			       IRQF_SHARED, "dw_dmac", dw);
-	if (err)
-		return err;
-
 	/* Create a pool of consistent memory blocks for hardware descriptors */
 	dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev,
 					 sizeof(struct dw_desc), 4, 0);
@@ -1560,6 +1553,11 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
 
+	err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
+			  "dw_dmac", dw);
+	if (err)
+		return err;
+
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < nr_channels; i++) {
 		struct dw_dma_chan	*dwc = &dw->chan[i];
@@ -1664,6 +1662,7 @@ int dw_dma_remove(struct dw_dma_chip *chip)
 	dw_dma_off(dw);
 	dma_async_device_unregister(&dw->dma);
 
+	free_irq(chip->irq, dw);
 	tasklet_kill(&dw->tasklet);
 
 	list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels,
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index cd8da451d199..bf5ad0f5a77a 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -182,11 +182,13 @@ static void edma_execute(struct edma_chan *echan)
 				  echan->ecc->dummy_slot);
 	}
 
-	edma_resume(echan->ch_num);
-
 	if (edesc->processed <= MAX_NR_SG) {
 		dev_dbg(dev, "first transfer starting %d\n", echan->ch_num);
 		edma_start(echan->ch_num);
+	} else {
+		dev_dbg(dev, "chan: %d: completed %d elements, resuming\n",
+			echan->ch_num, edesc->processed);
+		edma_resume(echan->ch_num);
 	}
 
 	/*
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 766b68ed505c..394cbc5c93e3 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -191,12 +191,10 @@ static void mv_set_mode(struct mv_xor_chan *chan,
 
 static void mv_chan_activate(struct mv_xor_chan *chan)
 {
-	u32 activation;
-
 	dev_dbg(mv_chan_to_devp(chan), " activate chan.\n");
-	activation = readl_relaxed(XOR_ACTIVATION(chan));
-	activation |= 0x1;
-	writel_relaxed(activation, XOR_ACTIVATION(chan));
+
+	/* writel ensures all descriptors are flushed before activation */
+	writel(BIT(0), XOR_ACTIVATION(chan));
 }
 
 static char mv_chan_is_busy(struct mv_xor_chan *chan)
diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c
index df6575f1430d..682288ced4ac 100644
--- a/drivers/edac/cpc925_edac.c
+++ b/drivers/edac/cpc925_edac.c
@@ -562,7 +562,7 @@ static void cpc925_mc_check(struct mem_ctl_info *mci)
 
 	if (apiexcp & UECC_EXCP_DETECTED) {
 		cpc925_mc_printk(mci, KERN_INFO, "DRAM UECC Fault\n");
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 				     pfn, offset, 0,
 				     csrow, -1, -1,
 				     mci->ctl_name, "");
diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c
index 3cda79bc8b00..ece3aef16bb1 100644
--- a/drivers/edac/e7xxx_edac.c
+++ b/drivers/edac/e7xxx_edac.c
@@ -226,7 +226,7 @@ static void process_ce(struct mem_ctl_info *mci, struct e7xxx_error_info *info)
 static void process_ce_no_info(struct mem_ctl_info *mci)
 {
 	edac_dbg(3, "\n");
-	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
 			     "e7xxx CE log register overflow", "");
 }
 
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index fa1326e5a4b0..ad76f10865c6 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -242,11 +242,11 @@ static void i3200_process_error_info(struct mem_ctl_info *mci,
 					     -1, -1,
 					     "i3000 UE", "");
 		} else if (log & I3200_ECCERRLOG_CE) {
-			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 					     0, 0, eccerrlog_syndrome(log),
 					     eccerrlog_row(channel, log),
 					     -1, -1,
-					     "i3000 UE", "");
+					     "i3000 CE", "");
 		}
 	}
 }
diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c
index 3382f6344e42..4382343a7c60 100644
--- a/drivers/edac/i82860_edac.c
+++ b/drivers/edac/i82860_edac.c
@@ -124,7 +124,7 @@ static int i82860_process_error_info(struct mem_ctl_info *mci,
 				     dimm->location[0], dimm->location[1], -1,
 				     "i82860 UE", "");
 	else
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     info->eap, 0, info->derrsyn,
 				     dimm->location[0], dimm->location[1], -1,
 				     "i82860 CE", "");
diff --git a/drivers/extcon/extcon-max14577.c b/drivers/extcon/extcon-max14577.c
index 3846941801b8..5c948c9625d2 100644
--- a/drivers/extcon/extcon-max14577.c
+++ b/drivers/extcon/extcon-max14577.c
@@ -650,7 +650,7 @@ static int max14577_muic_probe(struct platform_device *pdev)
 		unsigned int virq = 0;
 
 		virq = regmap_irq_get_virq(max14577->irq_data, muic_irq->irq);
-		if (!virq)
+		if (virq <= 0)
 			return -EINVAL;
 		muic_irq->virq = virq;
 
@@ -710,13 +710,8 @@ static int max14577_muic_probe(struct platform_device *pdev)
 	 * driver should notify cable state to upper layer.
 	 */
 	INIT_DELAYED_WORK(&info->wq_detcable, max14577_muic_detect_cable_wq);
-	ret = queue_delayed_work(system_power_efficient_wq, &info->wq_detcable,
+	queue_delayed_work(system_power_efficient_wq, &info->wq_detcable,
 			delay_jiffies);
-	if (ret < 0) {
-		dev_err(&pdev->dev,
-			"failed to schedule delayed work for cable detect\n");
-		goto err_extcon;
-	}
 
 	return ret;
 
diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index da268fbc901b..4657a91acf56 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -1193,7 +1193,7 @@ static int max77693_muic_probe(struct platform_device *pdev)
 
 
 	/* Initialize MUIC register by using platform data or default data */
-	if (pdata->muic_data) {
+	if (pdata && pdata->muic_data) {
 		init_data = pdata->muic_data->init_data;
 		num_init_data = pdata->muic_data->num_init_data;
 	} else {
@@ -1226,7 +1226,7 @@ static int max77693_muic_probe(struct platform_device *pdev)
 				= init_data[i].data;
 	}
 
-	if (pdata->muic_data) {
+	if (pdata && pdata->muic_data) {
 		struct max77693_muic_platform_data *muic_pdata
 						   = pdata->muic_data;
 
diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c
index 6a00464658c5..5e1b88cecb76 100644
--- a/drivers/extcon/extcon-max8997.c
+++ b/drivers/extcon/extcon-max8997.c
@@ -715,7 +715,7 @@ static int max8997_muic_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 
-	if (pdata->muic_pdata) {
+	if (pdata && pdata->muic_pdata) {
 		struct max8997_muic_platform_data *muic_pdata
 			= pdata->muic_pdata;
 
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index d7d5c8af92b9..6d4456898007 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -1637,8 +1637,7 @@ static int dispatch_ioctl(struct client *client,
 	    _IOC_SIZE(cmd) > sizeof(buffer))
 		return -ENOTTY;
 
-	if (_IOC_DIR(cmd) == _IOC_READ)
-		memset(&buffer, 0, _IOC_SIZE(cmd));
+	memset(&buffer, 0, sizeof(buffer));
 
 	if (_IOC_DIR(cmd) & _IOC_WRITE)
 		if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd)))
diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h
index c98764aeeec6..f477308b6e9c 100644
--- a/drivers/firewire/core.h
+++ b/drivers/firewire/core.h
@@ -237,8 +237,8 @@ static inline bool is_next_generation(int new_generation, int old_generation)
 
 #define LOCAL_BUS 0xffc0
 
-/* arbitrarily chosen maximum range for physical DMA: 128 TB */
-#define FW_MAX_PHYSICAL_RANGE		(128ULL << 40)
+/* OHCI-1394's default upper bound for physical DMA: 4 GB */
+#define FW_MAX_PHYSICAL_RANGE		(1ULL << 32)
 
 void fw_core_handle_request(struct fw_card *card, struct fw_packet *request);
 void fw_core_handle_response(struct fw_card *card, struct fw_packet *packet);
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 8db663219560..586f2f7f6993 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -3716,7 +3716,7 @@ static int pci_probe(struct pci_dev *dev,
 		    version >> 16, version & 0xff, ohci->card.index,
 		    ohci->n_ir, ohci->n_it, ohci->quirks,
 		    reg_read(ohci, OHCI1394_PhyUpperBound) ?
-			", >4 GB phys DMA" : "");
+			", physUB" : "");
 
 	return 0;
 
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 4b9dc836dcf9..e992abc5ef26 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -40,7 +40,7 @@ struct pstore_read_data {
 static inline u64 generic_id(unsigned long timestamp,
 			     unsigned int part, int count)
 {
-	return (timestamp * 100 + part) * 1000 + count;
+	return ((u64) timestamp * 100 + part) * 1000 + count;
 }
 
 static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index f0a43646a2f3..5abe943e3404 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -481,7 +481,7 @@ EXPORT_SYMBOL_GPL(efivar_entry_remove);
  */
 static void efivar_entry_list_del_unlock(struct efivar_entry *entry)
 {
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	list_del(&entry->list);
 	spin_unlock_irq(&__efivars->lock);
@@ -507,7 +507,7 @@ int __efivar_entry_delete(struct efivar_entry *entry)
 	const struct efivar_operations *ops = __efivars->ops;
 	efi_status_t status;
 
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	status = ops->set_variable(entry->var.VariableName,
 				   &entry->var.VendorGuid,
@@ -667,7 +667,7 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 	int strsize1, strsize2;
 	bool found = false;
 
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	list_for_each_entry_safe(entry, n, head, list) {
 		strsize1 = ucs2_strsize(name, 1024);
@@ -739,7 +739,7 @@ int __efivar_entry_get(struct efivar_entry *entry, u32 *attributes,
 	const struct efivar_operations *ops = __efivars->ops;
 	efi_status_t status;
 
-	WARN_ON(!spin_is_locked(&__efivars->lock));
+	lockdep_assert_held(&__efivars->lock);
 
 	status = ops->get_variable(entry->var.VariableName,
 				   &entry->var.VendorGuid,
diff --git a/drivers/gator/Kconfig b/drivers/gator/Kconfig
new file mode 100644
index 000000000000..a9503a9a4e9f
--- /dev/null
+++ b/drivers/gator/Kconfig
@@ -0,0 +1,38 @@
+config GATOR
+	tristate "Gator module for ARM's Streamline Performance Analyzer"
+	default m if (ARM || ARM64)
+	depends on PROFILING
+	depends on HIGH_RES_TIMERS
+	depends on PERF_EVENTS
+	depends on HW_PERF_EVENTS || !(ARM || ARM64)
+	select TRACING
+	help
+	  Gator module for ARM's Streamline Performance Analyzer
+
+config GATOR_WITH_MALI_SUPPORT
+	bool
+
+choice
+	prompt "Enable Mali GPU support in Gator"
+	depends on GATOR
+	optional
+	help
+	  Enable Mali GPU support in Gator
+
+config GATOR_MALI_4XXMP
+	bool "Mali-400MP or Mali-450MP"
+	select GATOR_WITH_MALI_SUPPORT
+
+config GATOR_MALI_MIDGARD
+	bool "Mali-T60x, Mali-T62x, Mali-T72x or Mali-T76x"
+	select GATOR_WITH_MALI_SUPPORT
+
+endchoice
+
+config GATOR_MALI_PATH
+	string "Path to Mali driver"
+	depends on GATOR_WITH_MALI_SUPPORT
+	default "drivers/gpu/arm/mali400mp"
+	help
+	  The gator code adds this to its include path so it can get the Mali
+	  trace headers with: #include "linux/mali_linux_trace.h"
diff --git a/drivers/gator/LICENSE b/drivers/gator/LICENSE
new file mode 100644
index 000000000000..d159169d1050
--- /dev/null
+++ b/drivers/gator/LICENSE
@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/drivers/gator/Makefile b/drivers/gator/Makefile
new file mode 100644
index 000000000000..28d2070b11d5
--- /dev/null
+++ b/drivers/gator/Makefile
@@ -0,0 +1,79 @@
+ifneq ($(KERNELRELEASE),)
+
+# Uncomment the following line to enable kernel stack unwinding within gator, or update gator_backtrace.c
+# EXTRA_CFLAGS +=	-DGATOR_KERNEL_STACK_UNWINDING
+
+CONFIG_GATOR ?= m
+obj-$(CONFIG_GATOR) := gator.o
+
+gator-y :=	gator_main.o \
+		gator_events_block.o \
+		gator_events_irq.o \
+		gator_events_meminfo.o \
+		gator_events_mmapped.o \
+		gator_events_net.o \
+		gator_events_perf_pmu.o \
+		gator_events_sched.o \
+
+# Convert the old GATOR_WITH_MALI_SUPPORT to the new kernel flags
+ifneq ($(GATOR_WITH_MALI_SUPPORT),)
+  CONFIG_GATOR_WITH_MALI_SUPPORT := y
+  ifeq ($(GATOR_WITH_MALI_SUPPORT),MALI_MIDGARD)
+    CONFIG_GATOR_MALI_4XXMP := n
+    CONFIG_GATOR_MALI_MIDGARD := y
+  else
+    CONFIG_GATOR_MALI_4XXMP := y
+    CONFIG_GATOR_MALI_MIDGARD := n
+  endif
+  EXTRA_CFLAGS += -DMALI_SUPPORT=$(GATOR_WITH_MALI_SUPPORT)
+  ifneq ($(GATOR_MALI_INTERFACE_STYLE),)
+    EXTRA_CFLAGS += -DGATOR_MALI_INTERFACE_STYLE=$(GATOR_MALI_INTERFACE_STYLE)
+  endif
+endif
+
+ifeq ($(CONFIG_GATOR_WITH_MALI_SUPPORT),y)
+  ifeq ($(CONFIG_GATOR_MALI_MIDGARD),y)
+    gator-y +=	gator_events_mali_midgard.o \
+		gator_events_mali_midgard_hw.o
+    include $(src)/mali_midgard.mk
+  else
+    gator-y +=	gator_events_mali_4xx.o
+  endif
+  gator-y +=	gator_events_mali_common.o
+
+  ifneq ($(CONFIG_GATOR_MALI_PATH),)
+    ccflags-y += -I$(CONFIG_GATOR_MALI_PATH)
+  endif
+  ccflags-$(CONFIG_GATOR_MALI_4XXMP) += -DMALI_SUPPORT=MALI_4xx
+  ccflags-$(CONFIG_GATOR_MALI_MIDGARD) += -DMALI_SUPPORT=MALI_MIDGARD
+endif
+
+# GATOR_TEST controls whether to include (=1) or exclude (=0) test code.
+GATOR_TEST ?= 0
+EXTRA_CFLAGS +=	-DGATOR_TEST=$(GATOR_TEST)
+
+# Should the original or new block_rq_complete API be used?
+OLD_BLOCK_RQ_COMPLETE := $(shell grep -A3 block_rq_complete $(srctree)/include/trace/events/block.h | grep nr_bytes -q; echo $$?)
+EXTRA_CFLAGS += -DOLD_BLOCK_RQ_COMPLETE=$(OLD_BLOCK_RQ_COMPLETE)
+
+gator-$(CONFIG_ARM) +=	gator_events_armv6.o \
+			gator_events_armv7.o \
+			gator_events_l2c-310.o \
+			gator_events_scorpion.o
+
+gator-$(CONFIG_ARM64) +=
+
+else
+
+all:
+	@echo
+	@echo "usage:"
+	@echo "      make -C <kernel_build_dir> M=\`pwd\` ARCH=arm CROSS_COMPILE=<...> modules"
+	@echo
+	$(error)
+
+clean:
+	rm -f *.o .*.cmd modules.order Module.symvers gator.ko gator.mod.c
+	rm -rf .tmp_versions
+
+endif
diff --git a/drivers/gator/gator.h b/drivers/gator/gator.h
new file mode 100644
index 000000000000..5cc73a388c4f
--- /dev/null
+++ b/drivers/gator/gator.h
@@ -0,0 +1,152 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef GATOR_H_
+#define GATOR_H_
+
+#include <linux/version.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+
+#define GATOR_PERF_SUPPORT      (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 0, 0))
+#define GATOR_PERF_PMU_SUPPORT  (GATOR_PERF_SUPPORT && defined(CONFIG_PERF_EVENTS) && (!(defined(__arm__) || defined(__aarch64__)) || defined(CONFIG_HW_PERF_EVENTS)))
+#define GATOR_NO_PERF_SUPPORT   (!(GATOR_PERF_SUPPORT))
+#define GATOR_CPU_FREQ_SUPPORT  ((LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)) && defined(CONFIG_CPU_FREQ))
+#define GATOR_IKS_SUPPORT       defined(CONFIG_BL_SWITCHER)
+
+/* cpu ids */
+#define ARM1136     0xb36
+#define ARM1156     0xb56
+#define ARM1176     0xb76
+#define ARM11MPCORE 0xb02
+#define CORTEX_A5   0xc05
+#define CORTEX_A7   0xc07
+#define CORTEX_A8   0xc08
+#define CORTEX_A9   0xc09
+#define CORTEX_A15  0xc0f
+#define CORTEX_A17  0xc0e
+#define SCORPION    0x00f
+#define SCORPIONMP  0x02d
+#define KRAITSIM    0x049
+#define KRAIT       0x04d
+#define KRAIT_S4_PRO 0x06f
+#define CORTEX_A53  0xd03
+#define CORTEX_A57  0xd07
+#define AARCH64     0xd0f
+#define OTHER       0xfff
+
+/* gpu enums */
+#define MALI_4xx     1
+#define MALI_MIDGARD 2
+
+#define MAXSIZE_CORE_NAME 32
+
+struct gator_cpu {
+	const int cpuid;
+	/* Human readable name */
+	const char core_name[MAXSIZE_CORE_NAME];
+	/* gatorfs event and Perf PMU name */
+	const char *const pmnc_name;
+	/* compatible from Documentation/devicetree/bindings/arm/cpus.txt */
+	const char *const dt_name;
+	const int pmnc_counters;
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid);
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name);
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+struct dentry *gatorfs_mkdir(struct super_block *sb, struct dentry *root,
+			     char const *name);
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+			 char const *name, unsigned long *val);
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+			    char const *name, unsigned long *val);
+
+/******************************************************************************
+ * Tracepoints
+ ******************************************************************************/
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 32)
+#	error Kernels prior to 2.6.32 not supported
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		static void probe_##probe_name(PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		register_trace_##probe_name(probe_##probe_name)
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		unregister_trace_##probe_name(probe_##probe_name)
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		static void probe_##probe_name(void *data, PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		register_trace_##probe_name(probe_##probe_name, NULL)
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		unregister_trace_##probe_name(probe_##probe_name, NULL)
+#else
+#	define GATOR_DEFINE_PROBE(probe_name, proto) \
+		extern struct tracepoint *gator_tracepoint_##probe_name; \
+		static void probe_##probe_name(void *data, PARAMS(proto))
+#	define GATOR_REGISTER_TRACE(probe_name) \
+		((gator_tracepoint_##probe_name == NULL) || tracepoint_probe_register(gator_tracepoint_##probe_name, probe_##probe_name, NULL))
+#	define GATOR_UNREGISTER_TRACE(probe_name) \
+		tracepoint_probe_unregister(gator_tracepoint_##probe_name, probe_##probe_name, NULL)
+#endif
+
+/******************************************************************************
+ * Events
+ ******************************************************************************/
+struct gator_interface {
+	/* Complementary function to init */
+	void (*shutdown)(void);
+	int (*create_files)(struct super_block *sb, struct dentry *root);
+	int (*start)(void);
+	/* Complementary function to start */
+	void (*stop)(void);
+	int (*online)(int **buffer, bool migrate);
+	int (*offline)(int **buffer, bool migrate);
+	/* called in process context but may not be running on core 'cpu' */
+	void (*online_dispatch)(int cpu, bool migrate);
+	/* called in process context but may not be running on core 'cpu' */
+	void (*offline_dispatch)(int cpu, bool migrate);
+	int (*read)(int **buffer, bool sched_switch);
+	int (*read64)(long long **buffer);
+	int (*read_proc)(long long **buffer, struct task_struct *);
+	struct list_head list;
+};
+
+int gator_events_install(struct gator_interface *interface);
+int gator_events_get_key(void);
+u32 gator_cpuid(void);
+
+void gator_backtrace_handler(struct pt_regs *const regs);
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid);
+
+#if !GATOR_IKS_SUPPORT
+
+#define get_physical_cpu() smp_processor_id()
+#define lcpu_to_pcpu(lcpu) lcpu
+#define pcpu_to_lcpu(pcpu) pcpu
+
+#else
+
+#define get_physical_cpu() lcpu_to_pcpu(get_logical_cpu())
+int lcpu_to_pcpu(const int lcpu);
+int pcpu_to_lcpu(const int pcpu);
+
+#endif
+
+#define get_logical_cpu() smp_processor_id()
+#define on_primary_core() (get_logical_cpu() == 0)
+
+#endif /* GATOR_H_ */
diff --git a/drivers/gator/gator_annotate.c b/drivers/gator/gator_annotate.c
new file mode 100644
index 000000000000..ff9a3cef7b2e
--- /dev/null
+++ b/drivers/gator/gator_annotate.c
@@ -0,0 +1,189 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <asm/current.h>
+#include <linux/spinlock.h>
+
+static DEFINE_SPINLOCK(annotate_lock);
+static bool collect_annotations;
+
+static int annotate_copy(struct file *file, char const __user *buf, size_t count)
+{
+	int cpu = 0;
+	int write = per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF];
+
+	if (file == NULL) {
+		/* copy from kernel */
+		memcpy(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count);
+	} else {
+		/* copy from user space */
+		if (copy_from_user(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count) != 0)
+			return -1;
+	}
+	per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF] = (write + count) & gator_buffer_mask[ANNOTATE_BUF];
+
+	return 0;
+}
+
+static ssize_t annotate_write(struct file *file, char const __user *buf, size_t count_orig, loff_t *offset)
+{
+	int pid, cpu, header_size, available, contiguous, length1, length2, size, count = count_orig & 0x7fffffff;
+	bool interrupt_context;
+
+	if (*offset)
+		return -EINVAL;
+
+	interrupt_context = in_interrupt();
+	/* Annotations are not supported in interrupt context, but may work
+	 * if you comment out the the next four lines of code. By doing so,
+	 * annotations in interrupt context can result in deadlocks and lost
+	 * data.
+	 */
+	if (interrupt_context) {
+		pr_warning("gator: Annotations are not supported in interrupt context. Edit gator_annotate.c in the gator driver to enable annotations in interrupt context.\n");
+		return -EINVAL;
+	}
+
+ retry:
+	/* synchronize between cores and with collect_annotations */
+	spin_lock(&annotate_lock);
+
+	if (!collect_annotations) {
+		/* Not collecting annotations, tell the caller everything was written */
+		size = count_orig;
+		goto annotate_write_out;
+	}
+
+	/* Annotation only uses a single per-cpu buffer as the data must be in order to the engine */
+	cpu = 0;
+
+	if (current == NULL)
+		pid = 0;
+	else
+		pid = current->pid;
+
+	/* determine total size of the payload */
+	header_size = MAXSIZE_PACK32 * 3 + MAXSIZE_PACK64;
+	available = buffer_bytes_available(cpu, ANNOTATE_BUF) - header_size;
+	size = count < available ? count : available;
+
+	if (size <= 0) {
+		/* Buffer is full, wait until space is available */
+		spin_unlock(&annotate_lock);
+
+		/* Drop the annotation as blocking is not allowed in interrupt context */
+		if (interrupt_context)
+			return -EINVAL;
+
+		wait_event_interruptible(gator_annotate_wait, buffer_bytes_available(cpu, ANNOTATE_BUF) > header_size || !collect_annotations);
+
+		/* Check to see if a signal is pending */
+		if (signal_pending(current))
+			return -EINTR;
+
+		goto retry;
+	}
+
+	/* synchronize shared variables annotateBuf and annotatePos */
+	if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF]) {
+		u64 time = gator_get_time();
+
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+		gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, time);
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, size);
+
+		/* determine the sizes to capture, length1 + length2 will equal size */
+		contiguous = contiguous_space_available(cpu, ANNOTATE_BUF);
+		if (size < contiguous) {
+			length1 = size;
+			length2 = 0;
+		} else {
+			length1 = contiguous;
+			length2 = size - contiguous;
+		}
+
+		if (annotate_copy(file, buf, length1) != 0) {
+			size = -EINVAL;
+			goto annotate_write_out;
+		}
+
+		if (length2 > 0 && annotate_copy(file, &buf[length1], length2) != 0) {
+			size = -EINVAL;
+			goto annotate_write_out;
+		}
+
+		/* Check and commit; commit is set to occur once buffer is 3/4 full */
+		buffer_check(cpu, ANNOTATE_BUF, time);
+	}
+
+annotate_write_out:
+	spin_unlock(&annotate_lock);
+
+	/* return the number of bytes written */
+	return size;
+}
+
+#include "gator_annotate_kernel.c"
+
+static int annotate_release(struct inode *inode, struct file *file)
+{
+	int cpu = 0;
+
+	/* synchronize between cores */
+	spin_lock(&annotate_lock);
+
+	if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF] && buffer_check_space(cpu, ANNOTATE_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+		uint32_t pid = current->pid;
+
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+		/* time */
+		gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, 0);
+		/* size */
+		gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, 0);
+	}
+
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, ANNOTATE_BUF, gator_get_time());
+
+	spin_unlock(&annotate_lock);
+
+	return 0;
+}
+
+static const struct file_operations annotate_fops = {
+	.write = annotate_write,
+	.release = annotate_release
+};
+
+static int gator_annotate_create_files(struct super_block *sb, struct dentry *root)
+{
+	return gatorfs_create_file_perm(sb, root, "annotate", &annotate_fops, 0666);
+}
+
+static int gator_annotate_start(void)
+{
+	collect_annotations = true;
+	return 0;
+}
+
+static void gator_annotate_stop(void)
+{
+	/* the spinlock here will ensure that when this function exits, we are not in the middle of an annotation */
+	spin_lock(&annotate_lock);
+	collect_annotations = false;
+	wake_up(&gator_annotate_wait);
+	spin_unlock(&annotate_lock);
+}
diff --git a/drivers/gator/gator_annotate_kernel.c b/drivers/gator/gator_annotate_kernel.c
new file mode 100644
index 000000000000..69471f99e5fb
--- /dev/null
+++ b/drivers/gator/gator_annotate_kernel.c
@@ -0,0 +1,200 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define ESCAPE_CODE 0x1c
+#define STRING_ANNOTATION 0x06
+#define NAME_CHANNEL_ANNOTATION 0x07
+#define NAME_GROUP_ANNOTATION 0x08
+#define VISUAL_ANNOTATION 0x04
+#define MARKER_ANNOTATION 0x05
+
+static void kannotate_write(const char *ptr, unsigned int size)
+{
+	int retval;
+	int pos = 0;
+	loff_t offset = 0;
+
+	while (pos < size) {
+		retval = annotate_write(NULL, &ptr[pos], size - pos, &offset);
+		if (retval < 0) {
+			pr_warning("gator: kannotate_write failed with return value %d\n", retval);
+			return;
+		}
+		pos += retval;
+	}
+}
+
+static void marshal_u16(char *buf, u16 val)
+{
+	buf[0] = val & 0xff;
+	buf[1] = (val >> 8) & 0xff;
+}
+
+static void marshal_u32(char *buf, u32 val)
+{
+	buf[0] = val & 0xff;
+	buf[1] = (val >> 8) & 0xff;
+	buf[2] = (val >> 16) & 0xff;
+	buf[3] = (val >> 24) & 0xff;
+}
+
+void gator_annotate_channel(int channel, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_channel);
+
+void gator_annotate(const char *str)
+{
+	gator_annotate_channel(0, str);
+}
+EXPORT_SYMBOL(gator_annotate);
+
+void gator_annotate_channel_color(int channel, int color, const char *str)
+{
+	const u16 str_size = (strlen(str) + 4) & 0xffff;
+	char header[12];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, str_size);
+	marshal_u32(header + 8, color);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_channel_color);
+
+void gator_annotate_color(int color, const char *str)
+{
+	gator_annotate_channel_color(0, color, str);
+}
+EXPORT_SYMBOL(gator_annotate_color);
+
+void gator_annotate_channel_end(int channel)
+{
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = STRING_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u16(header + 6, 0);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_channel_end);
+
+void gator_annotate_end(void)
+{
+	gator_annotate_channel_end(0);
+}
+EXPORT_SYMBOL(gator_annotate_end);
+
+void gator_annotate_name_channel(int channel, int group, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[12];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = NAME_CHANNEL_ANNOTATION;
+	marshal_u32(header + 2, channel);
+	marshal_u32(header + 6, group);
+	marshal_u16(header + 10, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_channel);
+
+void gator_annotate_name_group(int group, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = NAME_GROUP_ANNOTATION;
+	marshal_u32(header + 2, group);
+	marshal_u16(header + 6, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_group);
+
+void gator_annotate_visual(const char *data, unsigned int length, const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[4];
+	char header_length[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = VISUAL_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	marshal_u32(header_length, length);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+	kannotate_write(header_length, sizeof(header_length));
+	kannotate_write(data, length);
+}
+EXPORT_SYMBOL(gator_annotate_visual);
+
+void gator_annotate_marker(void)
+{
+	char header[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, 0);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker);
+
+void gator_annotate_marker_str(const char *str)
+{
+	const u16 str_size = strlen(str) & 0xffff;
+	char header[4];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_marker_str);
+
+void gator_annotate_marker_color(int color)
+{
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, 4);
+	marshal_u32(header + 4, color);
+	kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker_color);
+
+void gator_annotate_marker_color_str(int color, const char *str)
+{
+	const u16 str_size = (strlen(str) + 4) & 0xffff;
+	char header[8];
+
+	header[0] = ESCAPE_CODE;
+	header[1] = MARKER_ANNOTATION;
+	marshal_u16(header + 2, str_size);
+	marshal_u32(header + 4, color);
+	kannotate_write(header, sizeof(header));
+	kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_marker_color_str);
diff --git a/drivers/gator/gator_backtrace.c b/drivers/gator/gator_backtrace.c
new file mode 100644
index 000000000000..76c941d009a9
--- /dev/null
+++ b/drivers/gator/gator_backtrace.c
@@ -0,0 +1,208 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * EABI backtrace stores {fp,lr} on the stack.
+ */
+struct stack_frame_eabi {
+	union {
+		struct {
+			unsigned long fp;
+			/* May be the fp in the case of a leaf function or clang */
+			unsigned long lr;
+			/* If lr is really the fp, lr2 is the corresponding lr */
+			unsigned long lr2;
+		};
+		/* Used to read 32 bit fp/lr from a 64 bit kernel */
+		struct {
+			u32 fp_32;
+			/* same as lr above */
+			u32 lr_32;
+			/* same as lr2 above */
+			u32 lr2_32;
+		};
+	};
+};
+
+static void gator_add_trace(int cpu, unsigned long address)
+{
+	off_t offset = 0;
+	unsigned long cookie = get_address_cookie(cpu, current, address & ~1, &offset);
+
+	if (cookie == NO_COOKIE || cookie == UNRESOLVED_COOKIE)
+		offset = address;
+
+	marshal_backtrace(offset & ~1, cookie, 0);
+}
+
+static void arm_backtrace_eabi(int cpu, struct pt_regs *const regs, unsigned int depth)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	struct stack_frame_eabi *curr;
+	struct stack_frame_eabi bufcurr;
+#if defined(__arm__)
+	const bool is_compat = false;
+	unsigned long fp = regs->ARM_fp;
+	unsigned long sp = regs->ARM_sp;
+	unsigned long lr = regs->ARM_lr;
+	const int gcc_frame_offset = sizeof(unsigned long);
+#else
+	/* Is userspace aarch32 (32 bit) */
+	const bool is_compat = compat_user_mode(regs);
+	unsigned long fp = (is_compat ? regs->regs[11] : regs->regs[29]);
+	unsigned long sp = (is_compat ? regs->compat_sp : regs->sp);
+	unsigned long lr = (is_compat ? regs->compat_lr : regs->regs[30]);
+	const int gcc_frame_offset = (is_compat ? sizeof(u32) : 0);
+#endif
+	/* clang frame offset is always zero */
+	int is_user_mode = user_mode(regs);
+
+	/* pc (current function) has already been added */
+
+	if (!is_user_mode)
+		return;
+
+	/* Add the lr (parent function), entry preamble may not have
+	 * executed
+	 */
+	gator_add_trace(cpu, lr);
+
+	/* check fp is valid */
+	if (fp == 0 || fp < sp)
+		return;
+
+	/* Get the current stack frame */
+	curr = (struct stack_frame_eabi *)(fp - gcc_frame_offset);
+	if ((unsigned long)curr & 3)
+		return;
+
+	while (depth-- && curr) {
+		if (!access_ok(VERIFY_READ, curr, sizeof(struct stack_frame_eabi)) ||
+				__copy_from_user_inatomic(&bufcurr, curr, sizeof(struct stack_frame_eabi))) {
+			return;
+		}
+
+		fp = (is_compat ? bufcurr.fp_32 : bufcurr.fp);
+		lr = (is_compat ? bufcurr.lr_32 : bufcurr.lr);
+
+#define calc_next(reg) ((reg) - gcc_frame_offset)
+		/* Returns true if reg is a valid fp */
+#define validate_next(reg, curr) \
+		((reg) != 0 && (calc_next(reg) & 3) == 0 && (unsigned long)(curr) < calc_next(reg))
+
+		/* Try lr from the stack as the fp because gcc leaf functions do
+		 * not push lr. If gcc_frame_offset is non-zero, the lr will also
+		 * be the clang fp. This assumes code is at a lower address than
+		 * the stack
+		 */
+		if (validate_next(lr, curr)) {
+			fp = lr;
+			lr = (is_compat ? bufcurr.lr2_32 : bufcurr.lr2);
+		}
+
+		gator_add_trace(cpu, lr);
+
+		if (!validate_next(fp, curr))
+			return;
+
+		/* Move to the next stack frame */
+		curr = (struct stack_frame_eabi *)calc_next(fp);
+	}
+#endif
+}
+
+#if defined(__arm__) || defined(__aarch64__)
+static int report_trace(struct stackframe *frame, void *d)
+{
+	unsigned int *depth = d, cookie = NO_COOKIE;
+	unsigned long addr = frame->pc;
+
+	if (*depth) {
+#if defined(MODULE)
+		unsigned int cpu = get_physical_cpu();
+		struct module *mod = __module_address(addr);
+
+		if (mod) {
+			cookie = get_cookie(cpu, current, mod->name, false);
+			addr = addr - (unsigned long)mod->module_core;
+		}
+#endif
+		marshal_backtrace(addr & ~1, cookie, 1);
+		(*depth)--;
+	}
+
+	return *depth == 0;
+}
+#endif
+
+/* Uncomment the following line to enable kernel stack unwinding within gator, note it can also be defined from the Makefile */
+/* #define GATOR_KERNEL_STACK_UNWINDING */
+
+#if (defined(__arm__) || defined(__aarch64__)) && !defined(GATOR_KERNEL_STACK_UNWINDING)
+/* Disabled by default */
+MODULE_PARM_DESC(kernel_stack_unwinding, "Allow kernel stack unwinding.");
+static bool kernel_stack_unwinding;
+module_param(kernel_stack_unwinding, bool, 0644);
+#endif
+
+static void kernel_backtrace(int cpu, struct pt_regs *const regs)
+{
+#if defined(__arm__) || defined(__aarch64__)
+#ifdef GATOR_KERNEL_STACK_UNWINDING
+	int depth = gator_backtrace_depth;
+#else
+	int depth = (kernel_stack_unwinding ? gator_backtrace_depth : 1);
+#endif
+	struct stackframe frame;
+
+	if (depth == 0)
+		depth = 1;
+#if defined(__arm__)
+	frame.fp = regs->ARM_fp;
+	frame.sp = regs->ARM_sp;
+	frame.lr = regs->ARM_lr;
+	frame.pc = regs->ARM_pc;
+#else
+	frame.fp = regs->regs[29];
+	frame.sp = regs->sp;
+	frame.pc = regs->pc;
+#endif
+	walk_stackframe(&frame, report_trace, &depth);
+#else
+	marshal_backtrace(PC_REG & ~1, NO_COOKIE, 1);
+#endif
+}
+
+static void gator_add_sample(int cpu, struct pt_regs *const regs, u64 time)
+{
+	bool in_kernel;
+	unsigned long exec_cookie;
+
+	if (!regs)
+		return;
+
+	in_kernel = !user_mode(regs);
+	exec_cookie = get_exec_cookie(cpu, current);
+
+	if (!marshal_backtrace_header(exec_cookie, current->tgid, current->pid, time))
+		return;
+
+	if (in_kernel) {
+		kernel_backtrace(cpu, regs);
+	} else {
+		/* Cookie+PC */
+		gator_add_trace(cpu, PC_REG);
+
+		/* Backtrace */
+		if (gator_backtrace_depth)
+			arm_backtrace_eabi(cpu, regs, gator_backtrace_depth);
+	}
+
+	marshal_backtrace_footer(time);
+}
diff --git a/drivers/gator/gator_buffer.c b/drivers/gator/gator_buffer.c
new file mode 100644
index 000000000000..910d5aa15066
--- /dev/null
+++ b/drivers/gator/gator_buffer.c
@@ -0,0 +1,171 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void marshal_frame(int cpu, int buftype)
+{
+	int frame;
+	bool write_cpu;
+
+	if (!per_cpu(gator_buffer, cpu)[buftype])
+		return;
+
+	switch (buftype) {
+	case SUMMARY_BUF:
+		write_cpu = false;
+		frame = FRAME_SUMMARY;
+		break;
+	case BACKTRACE_BUF:
+		write_cpu = true;
+		frame = FRAME_BACKTRACE;
+		break;
+	case NAME_BUF:
+		write_cpu = true;
+		frame = FRAME_NAME;
+		break;
+	case COUNTER_BUF:
+		write_cpu = false;
+		frame = FRAME_COUNTER;
+		break;
+	case BLOCK_COUNTER_BUF:
+		write_cpu = true;
+		frame = FRAME_BLOCK_COUNTER;
+		break;
+	case ANNOTATE_BUF:
+		write_cpu = false;
+		frame = FRAME_ANNOTATE;
+		break;
+	case SCHED_TRACE_BUF:
+		write_cpu = true;
+		frame = FRAME_SCHED_TRACE;
+		break;
+	case IDLE_BUF:
+		write_cpu = false;
+		frame = FRAME_IDLE;
+		break;
+	case ACTIVITY_BUF:
+		write_cpu = false;
+		frame = FRAME_ACTIVITY;
+		break;
+	default:
+		write_cpu = false;
+		frame = -1;
+		break;
+	}
+
+	/* add response type */
+	if (gator_response_type > 0)
+		gator_buffer_write_packed_int(cpu, buftype, gator_response_type);
+
+	/* leave space for 4-byte unpacked length */
+	per_cpu(gator_buffer_write, cpu)[buftype] = (per_cpu(gator_buffer_write, cpu)[buftype] + sizeof(s32)) & gator_buffer_mask[buftype];
+
+	/* add frame type and core number */
+	gator_buffer_write_packed_int(cpu, buftype, frame);
+	if (write_cpu)
+		gator_buffer_write_packed_int(cpu, buftype, cpu);
+}
+
+static int buffer_bytes_available(int cpu, int buftype)
+{
+	int remaining, filled;
+
+	filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_read, cpu)[buftype];
+	if (filled < 0)
+		filled += gator_buffer_size[buftype];
+
+	remaining = gator_buffer_size[buftype] - filled;
+
+	if (per_cpu(buffer_space_available, cpu)[buftype])
+		/* Give some extra room; also allows space to insert the overflow error packet */
+		remaining -= 200;
+	else
+		/* Hysteresis, prevents multiple overflow messages */
+		remaining -= 2000;
+
+	return remaining;
+}
+
+static bool buffer_check_space(int cpu, int buftype, int bytes)
+{
+	int remaining = buffer_bytes_available(cpu, buftype);
+
+	if (remaining < bytes)
+		per_cpu(buffer_space_available, cpu)[buftype] = false;
+	else
+		per_cpu(buffer_space_available, cpu)[buftype] = true;
+
+	return per_cpu(buffer_space_available, cpu)[buftype];
+}
+
+static int contiguous_space_available(int cpu, int buftype)
+{
+	int remaining = buffer_bytes_available(cpu, buftype);
+	int contiguous = gator_buffer_size[buftype] - per_cpu(gator_buffer_write, cpu)[buftype];
+
+	if (remaining < contiguous)
+		return remaining;
+	return contiguous;
+}
+
+static void gator_commit_buffer(int cpu, int buftype, u64 time)
+{
+	int type_length, commit, length, byte;
+	unsigned long flags;
+
+	if (!per_cpu(gator_buffer, cpu)[buftype])
+		return;
+
+	/* post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload */
+	local_irq_save(flags);
+	type_length = gator_response_type ? 1 : 0;
+	commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+	length = per_cpu(gator_buffer_write, cpu)[buftype] - commit;
+	if (length < 0)
+		length += gator_buffer_size[buftype];
+	length = length - type_length - sizeof(s32);
+
+	if (length <= FRAME_HEADER_SIZE) {
+		/* Nothing to write, only the frame header is present */
+		local_irq_restore(flags);
+		return;
+	}
+
+	for (byte = 0; byte < sizeof(s32); byte++)
+		per_cpu(gator_buffer, cpu)[buftype][(commit + type_length + byte) & gator_buffer_mask[buftype]] = (length >> byte * 8) & 0xFF;
+
+	per_cpu(gator_buffer_commit, cpu)[buftype] = per_cpu(gator_buffer_write, cpu)[buftype];
+
+	if (gator_live_rate > 0) {
+		while (time > per_cpu(gator_buffer_commit_time, cpu))
+			per_cpu(gator_buffer_commit_time, cpu) += gator_live_rate;
+	}
+
+	marshal_frame(cpu, buftype);
+	local_irq_restore(flags);
+
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	if (per_cpu(in_scheduler_context, cpu)) {
+#ifndef CONFIG_PREEMPT_RT_FULL
+		/* mod_timer can not be used in interrupt context in RT-Preempt full */
+		mod_timer(&gator_buffer_wake_up_timer, jiffies + 1);
+#endif
+	} else {
+		up(&gator_buffer_wake_sem);
+	}
+}
+
+static void buffer_check(int cpu, int buftype, u64 time)
+{
+	int filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_commit, cpu)[buftype];
+
+	if (filled < 0)
+		filled += gator_buffer_size[buftype];
+	if (filled >= ((gator_buffer_size[buftype] * 3) / 4))
+		gator_commit_buffer(cpu, buftype, time);
+}
diff --git a/drivers/gator/gator_buffer_write.c b/drivers/gator/gator_buffer_write.c
new file mode 100644
index 000000000000..654ec606cfad
--- /dev/null
+++ b/drivers/gator/gator_buffer_write.c
@@ -0,0 +1,83 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void gator_buffer_write_packed_int(int cpu, int buftype, int x)
+{
+	uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+	uint32_t mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+	int packedBytes = 0;
+	int more = true;
+
+	while (more) {
+		/* low order 7 bits of x */
+		char b = x & 0x7f;
+
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+			more = false;
+		else
+			b |= 0x80;
+
+		buffer[(write + packedBytes) & mask] = b;
+		packedBytes++;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_packed_int64(int cpu, int buftype, long long x)
+{
+	uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+	uint32_t mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+	int packedBytes = 0;
+	int more = true;
+
+	while (more) {
+		/* low order 7 bits of x */
+		char b = x & 0x7f;
+
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+			more = false;
+		else
+			b |= 0x80;
+
+		buffer[(write + packedBytes) & mask] = b;
+		packedBytes++;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_bytes(int cpu, int buftype, const char *x, int len)
+{
+	int i;
+	u32 write = per_cpu(gator_buffer_write, cpu)[buftype];
+	u32 mask = gator_buffer_mask[buftype];
+	char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+
+	for (i = 0; i < len; i++) {
+		buffer[write] = x[i];
+		write = (write + 1) & mask;
+	}
+
+	per_cpu(gator_buffer_write, cpu)[buftype] = write;
+}
+
+static void gator_buffer_write_string(int cpu, int buftype, const char *x)
+{
+	int len = strlen(x);
+
+	gator_buffer_write_packed_int(cpu, buftype, len);
+	gator_buffer_write_bytes(cpu, buftype, x, len);
+}
diff --git a/drivers/gator/gator_cookies.c b/drivers/gator/gator_cookies.c
new file mode 100644
index 000000000000..c43cce815226
--- /dev/null
+++ b/drivers/gator/gator_cookies.c
@@ -0,0 +1,446 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/* must be power of 2 */
+#define COOKIEMAP_ENTRIES	1024
+/* must be a power of 2 - 512/4 = 128 entries */
+#define TRANSLATE_BUFFER_SIZE 512
+#define TRANSLATE_TEXT_SIZE		256
+#define MAX_COLLISIONS		2
+
+static uint32_t *gator_crc32_table;
+static unsigned int translate_buffer_mask;
+
+struct cookie_args {
+	struct task_struct *task;
+	const char *text;
+};
+
+static DEFINE_PER_CPU(char *, translate_text);
+static DEFINE_PER_CPU(uint32_t, cookie_next_key);
+static DEFINE_PER_CPU(uint64_t *, cookie_keys);
+static DEFINE_PER_CPU(uint32_t *, cookie_values);
+static DEFINE_PER_CPU(int, translate_buffer_read);
+static DEFINE_PER_CPU(int, translate_buffer_write);
+static DEFINE_PER_CPU(struct cookie_args *, translate_buffer);
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq);
+static void wq_cookie_handler(struct work_struct *unused);
+static DECLARE_WORK(cookie_work, wq_cookie_handler);
+static struct timer_list app_process_wake_up_timer;
+static void app_process_wake_up_handler(unsigned long unused_data);
+
+static uint32_t cookiemap_code(uint64_t value64)
+{
+	uint32_t value = (uint32_t)((value64 >> 32) + value64);
+	uint32_t cookiecode = (value >> 24) & 0xff;
+
+	cookiecode = cookiecode * 31 + ((value >> 16) & 0xff);
+	cookiecode = cookiecode * 31 + ((value >> 8) & 0xff);
+	cookiecode = cookiecode * 31 + ((value >> 0) & 0xff);
+	cookiecode &= (COOKIEMAP_ENTRIES - 1);
+	return cookiecode * MAX_COLLISIONS;
+}
+
+static uint32_t gator_chksum_crc32(const char *data)
+{
+	register unsigned long crc;
+	const unsigned char *block = data;
+	int i, length = strlen(data);
+
+	crc = 0xFFFFFFFF;
+	for (i = 0; i < length; i++)
+		crc = ((crc >> 8) & 0x00FFFFFF) ^ gator_crc32_table[(crc ^ *block++) & 0xFF];
+
+	return (crc ^ 0xFFFFFFFF);
+}
+
+/*
+ * Exists
+ *  Pre:  [0][1][v][3]..[n-1]
+ *  Post: [v][0][1][3]..[n-1]
+ */
+static uint32_t cookiemap_exists(uint64_t key)
+{
+	unsigned long x, flags, retval = 0;
+	int cpu = get_physical_cpu();
+	uint32_t cookiecode = cookiemap_code(key);
+	uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+	uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+
+	/* Can be called from interrupt handler or from work queue */
+	local_irq_save(flags);
+	for (x = 0; x < MAX_COLLISIONS; x++) {
+		if (keys[x] == key) {
+			uint32_t value = values[x];
+
+			for (; x > 0; x--) {
+				keys[x] = keys[x - 1];
+				values[x] = values[x - 1];
+			}
+			keys[0] = key;
+			values[0] = value;
+			retval = value;
+			break;
+		}
+	}
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+/*
+ * Add
+ *  Pre:  [0][1][2][3]..[n-1]
+ *  Post: [v][0][1][2]..[n-2]
+ */
+static void cookiemap_add(uint64_t key, uint32_t value)
+{
+	int cpu = get_physical_cpu();
+	int cookiecode = cookiemap_code(key);
+	uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+	uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+	int x;
+
+	for (x = MAX_COLLISIONS - 1; x > 0; x--) {
+		keys[x] = keys[x - 1];
+		values[x] = values[x - 1];
+	}
+	keys[0] = key;
+	values[0] = value;
+}
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+static void translate_buffer_write_args(int cpu, struct task_struct *task, const char *text)
+{
+	unsigned long flags;
+	int write;
+	int next_write;
+	struct cookie_args *args;
+
+	local_irq_save(flags);
+
+	write = per_cpu(translate_buffer_write, cpu);
+	next_write = (write + 1) & translate_buffer_mask;
+
+	/* At least one entry must always remain available as when read == write, the queue is empty not full */
+	if (next_write != per_cpu(translate_buffer_read, cpu)) {
+		args = &per_cpu(translate_buffer, cpu)[write];
+		args->task = task;
+		args->text = text;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+		get_task_struct(task);
+#endif
+		per_cpu(translate_buffer_write, cpu) = next_write;
+	}
+
+	local_irq_restore(flags);
+}
+#endif
+
+static void translate_buffer_read_args(int cpu, struct cookie_args *args)
+{
+	unsigned long flags;
+	int read;
+
+	local_irq_save(flags);
+
+	read = per_cpu(translate_buffer_read, cpu);
+	*args = per_cpu(translate_buffer, cpu)[read];
+	per_cpu(translate_buffer_read, cpu) = (read + 1) & translate_buffer_mask;
+
+	local_irq_restore(flags);
+}
+
+static void wq_cookie_handler(struct work_struct *unused)
+{
+	struct cookie_args args;
+	int cpu = get_physical_cpu(), cookie;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started != 0) {
+		while (per_cpu(translate_buffer_read, cpu) != per_cpu(translate_buffer_write, cpu)) {
+			translate_buffer_read_args(cpu, &args);
+			cookie = get_cookie(cpu, args.task, args.text, true);
+			marshal_link(cookie, args.task->tgid, args.task->pid);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+			put_task_struct(args.task);
+#endif
+		}
+	}
+
+	mutex_unlock(&start_mutex);
+}
+
+static void app_process_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&cookie_work);
+}
+
+/* Retrieve full name from proc/pid/cmdline for java processes on Android */
+static int translate_app_process(const char **text, int cpu, struct task_struct *task, bool from_wq)
+{
+	void *maddr;
+	unsigned int len;
+	unsigned long addr;
+	struct mm_struct *mm;
+	struct page *page = NULL;
+	struct vm_area_struct *page_vma;
+	int bytes, offset, retval = 0;
+	char *buf = per_cpu(translate_text, cpu);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+	/* Push work into a work queue if in atomic context as the kernel
+	 * functions below might sleep. Rely on the in_interrupt variable
+	 * rather than in_irq() or in_interrupt() kernel functions, as the
+	 * value of these functions seems inconsistent during a context
+	 * switch between android/linux versions
+	 */
+	if (!from_wq) {
+		/* Check if already in buffer */
+		int pos = per_cpu(translate_buffer_read, cpu);
+
+		while (pos != per_cpu(translate_buffer_write, cpu)) {
+			if (per_cpu(translate_buffer, cpu)[pos].task == task)
+				goto out;
+			pos = (pos + 1) & translate_buffer_mask;
+		}
+
+		translate_buffer_write_args(cpu, task, *text);
+
+		/* Not safe to call in RT-Preempt full in schedule switch context */
+		mod_timer(&app_process_wake_up_timer, jiffies + 1);
+		goto out;
+	}
+#endif
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+	if (!mm->arg_end)
+		goto outmm;
+	addr = mm->arg_start;
+	len = mm->arg_end - mm->arg_start;
+
+	if (len > TRANSLATE_TEXT_SIZE)
+		len = TRANSLATE_TEXT_SIZE;
+
+	down_read(&mm->mmap_sem);
+	while (len) {
+		if (get_user_pages(task, mm, addr, 1, 0, 1, &page, &page_vma) <= 0)
+			goto outsem;
+
+		maddr = kmap(page);
+		offset = addr & (PAGE_SIZE - 1);
+		bytes = len;
+		if (bytes > PAGE_SIZE - offset)
+			bytes = PAGE_SIZE - offset;
+
+		copy_from_user_page(page_vma, page, addr, buf, maddr + offset, bytes);
+
+		/* release page allocated by get_user_pages() */
+		kunmap(page);
+		page_cache_release(page);
+
+		len -= bytes;
+		buf += bytes;
+		addr += bytes;
+
+		*text = per_cpu(translate_text, cpu);
+		retval = 1;
+	}
+
+	/* On app_process startup, /proc/pid/cmdline is initially "zygote" then "<pre-initialized>" but changes after an initial startup period */
+	if (strcmp(*text, "zygote") == 0 || strcmp(*text, "<pre-initialized>") == 0)
+		retval = 0;
+
+outsem:
+	up_read(&mm->mmap_sem);
+outmm:
+	mmput(mm);
+out:
+	return retval;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq)
+{
+	unsigned long flags, cookie;
+	uint64_t key;
+
+	key = gator_chksum_crc32(text);
+	key = (key << 32) | (uint32_t)task->tgid;
+
+	cookie = cookiemap_exists(key);
+	if (cookie)
+		return cookie;
+
+	/* On 64-bit android app_process can be app_process32 or app_process64 */
+	if (strncmp(text, APP_PROCESS, sizeof(APP_PROCESS) - 1) == 0) {
+		if (!translate_app_process(&text, cpu, task, from_wq))
+			return UNRESOLVED_COOKIE;
+	}
+
+	/* Can be called from interrupt handler or from work queue or from scheduler trace */
+	local_irq_save(flags);
+
+	cookie = UNRESOLVED_COOKIE;
+	if (marshal_cookie_header(text)) {
+		cookie = per_cpu(cookie_next_key, cpu) += nr_cpu_ids;
+		cookiemap_add(key, cookie);
+		marshal_cookie(cookie, text);
+	}
+
+	local_irq_restore(flags);
+
+	return cookie;
+}
+
+static int get_exec_cookie(int cpu, struct task_struct *task)
+{
+	struct mm_struct *mm = task->mm;
+	const char *text;
+
+	/* kernel threads have no address space */
+	if (!mm)
+		return NO_COOKIE;
+
+	if (task && task->mm && task->mm->exe_file) {
+		text = task->mm->exe_file->f_path.dentry->d_name.name;
+		return get_cookie(cpu, task, text, false);
+	}
+
+	return UNRESOLVED_COOKIE;
+}
+
+static unsigned long get_address_cookie(int cpu, struct task_struct *task, unsigned long addr, off_t *offset)
+{
+	unsigned long cookie = NO_COOKIE;
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	const char *text;
+
+	if (!mm)
+		return cookie;
+
+	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+		if (addr < vma->vm_start || addr >= vma->vm_end)
+			continue;
+
+		if (vma->vm_file) {
+			text = vma->vm_file->f_path.dentry->d_name.name;
+			cookie = get_cookie(cpu, task, text, false);
+			*offset = (vma->vm_pgoff << PAGE_SHIFT) + addr - vma->vm_start;
+		} else {
+			/* must be an anonymous map */
+			*offset = addr;
+		}
+
+		break;
+	}
+
+	if (!vma)
+		cookie = UNRESOLVED_COOKIE;
+
+	return cookie;
+}
+
+static int cookies_initialize(void)
+{
+	uint32_t crc, poly;
+	int i, j, cpu, size, err = 0;
+
+	translate_buffer_mask = TRANSLATE_BUFFER_SIZE / sizeof(per_cpu(translate_buffer, 0)[0]) - 1;
+
+	for_each_present_cpu(cpu) {
+		per_cpu(cookie_next_key, cpu) = nr_cpu_ids + cpu;
+
+		size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint64_t);
+		per_cpu(cookie_keys, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(cookie_keys, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+		memset(per_cpu(cookie_keys, cpu), 0, size);
+
+		size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint32_t);
+		per_cpu(cookie_values, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(cookie_values, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+		memset(per_cpu(cookie_values, cpu), 0, size);
+
+		per_cpu(translate_buffer, cpu) = kmalloc(TRANSLATE_BUFFER_SIZE, GFP_KERNEL);
+		if (!per_cpu(translate_buffer, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+
+		per_cpu(translate_buffer_write, cpu) = 0;
+		per_cpu(translate_buffer_read, cpu) = 0;
+
+		per_cpu(translate_text, cpu) = kmalloc(TRANSLATE_TEXT_SIZE, GFP_KERNEL);
+		if (!per_cpu(translate_text, cpu)) {
+			err = -ENOMEM;
+			goto cookie_setup_error;
+		}
+	}
+
+	/* build CRC32 table */
+	poly = 0x04c11db7;
+	gator_crc32_table = kmalloc(256 * sizeof(*gator_crc32_table), GFP_KERNEL);
+	if (!gator_crc32_table) {
+		err = -ENOMEM;
+		goto cookie_setup_error;
+	}
+	for (i = 0; i < 256; i++) {
+		crc = i;
+		for (j = 8; j > 0; j--) {
+			if (crc & 1)
+				crc = (crc >> 1) ^ poly;
+			else
+				crc >>= 1;
+		}
+		gator_crc32_table[i] = crc;
+	}
+
+	setup_timer(&app_process_wake_up_timer, app_process_wake_up_handler, 0);
+
+cookie_setup_error:
+	return err;
+}
+
+static void cookies_release(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		kfree(per_cpu(cookie_keys, cpu));
+		per_cpu(cookie_keys, cpu) = NULL;
+
+		kfree(per_cpu(cookie_values, cpu));
+		per_cpu(cookie_values, cpu) = NULL;
+
+		kfree(per_cpu(translate_buffer, cpu));
+		per_cpu(translate_buffer, cpu) = NULL;
+		per_cpu(translate_buffer_read, cpu) = 0;
+		per_cpu(translate_buffer_write, cpu) = 0;
+
+		kfree(per_cpu(translate_text, cpu));
+		per_cpu(translate_text, cpu) = NULL;
+	}
+
+	del_timer_sync(&app_process_wake_up_timer);
+	kfree(gator_crc32_table);
+	gator_crc32_table = NULL;
+}
diff --git a/drivers/gator/gator_events_armv6.c b/drivers/gator/gator_events_armv6.c
new file mode 100644
index 000000000000..a157a0013302
--- /dev/null
+++ b/drivers/gator/gator_events_armv6.c
@@ -0,0 +1,234 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+
+/*
+ * Per-CPU PMCR
+ */
+#define PMCR_E			(1 << 0)	/* Enable */
+#define PMCR_P			(1 << 1)	/* Count reset */
+#define PMCR_C			(1 << 2)	/* Cycle counter reset */
+#define PMCR_OFL_PMN0	(1 << 8)	/* Count reg 0 overflow */
+#define PMCR_OFL_PMN1	(1 << 9)	/* Count reg 1 overflow */
+#define PMCR_OFL_CCNT	(1 << 10)	/* Cycle counter overflow */
+
+#define PMN0 0
+#define PMN1 1
+#define CCNT 2
+#define CNTMAX	(CCNT+1)
+
+static int pmnc_counters;
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+static inline void armv6_pmnc_write(u32 val)
+{
+	/* upper 4bits and 7, 11 are write-as-0 */
+	val &= 0x0ffff77f;
+	asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r" (val));
+}
+
+static inline u32 armv6_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r" (val));
+	return val;
+}
+
+static void armv6_pmnc_reset_counter(unsigned int cnt)
+{
+	u32 val = 0;
+
+	switch (cnt) {
+	case CCNT:
+		asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r" (val));
+		break;
+	case PMN0:
+		asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r" (val));
+		break;
+	case PMN1:
+		asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r" (val));
+		break;
+	}
+}
+
+int gator_events_armv6_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	pmnc_counters = 3;
+
+	for (i = PMN0; i <= CCNT; i++) {
+		char buf[40];
+
+		if (i == CCNT)
+			snprintf(buf, sizeof(buf), "ARM_%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "ARM_%s_cnt%d", pmnc_name, i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i != CCNT)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_armv6_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+	u32 pmnc;
+
+	if (armv6_pmnc_read() & PMCR_E)
+		armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+
+	/* initialize PMNC, reset overflow, D bit, C bit and P bit. */
+	armv6_pmnc_write(PMCR_OFL_PMN0 | PMCR_OFL_PMN1 | PMCR_OFL_CCNT |
+			 PMCR_C | PMCR_P);
+
+	/* configure control register */
+	for (pmnc = 0, cnt = PMN0; cnt <= CCNT; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters) */
+		if (cnt == PMN0)
+			pmnc |= event << 20;
+		else if (cnt == PMN1)
+			pmnc |= event << 12;
+
+		/* Reset counter */
+		armv6_pmnc_reset_counter(cnt);
+	}
+	armv6_pmnc_write(pmnc | PMCR_E);
+
+	/* return zero values, no need to read as the counters were just reset */
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_armv6_offline(int **buffer, bool migrate)
+{
+	unsigned int cnt;
+
+	armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+	for (cnt = PMN0; cnt <= CCNT; cnt++)
+		armv6_pmnc_reset_counter(cnt);
+
+	return 0;
+}
+
+static void gator_events_armv6_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_armv6_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(armv6_pmnc_read() & PMCR_E))
+		return 0;
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			u32 value = 0;
+
+			switch (cnt) {
+			case CCNT:
+				asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r" (value));
+				break;
+			case PMN0:
+				asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r" (value));
+				break;
+			case PMN1:
+				asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r" (value));
+				break;
+			}
+			armv6_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_armv6_interface = {
+	.create_files = gator_events_armv6_create_files,
+	.stop = gator_events_armv6_stop,
+	.online = gator_events_armv6_online,
+	.offline = gator_events_armv6_offline,
+	.read = gator_events_armv6_read,
+};
+
+int gator_events_armv6_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case ARM1136:
+	case ARM1156:
+	case ARM1176:
+		pmnc_name = "ARM11";
+		break;
+	case ARM11MPCORE:
+		pmnc_name = "ARM11MPCore";
+		break;
+	default:
+		return -1;
+	}
+
+	for (cnt = PMN0; cnt <= CCNT; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_armv6_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_armv7.c b/drivers/gator/gator_events_armv7.c
new file mode 100644
index 000000000000..09c94220114c
--- /dev/null
+++ b/drivers/gator/gator_events_armv7.c
@@ -0,0 +1,314 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*  Disabling interrupts
+ *    Many of the functions below disable interrupts via local_irq_save(). This disabling of interrupts is done to prevent any race conditions
+ *    between multiple entities (e.g. hrtimer interrupts and event based interrupts) calling the same functions. As accessing the pmu involves
+ *    several steps (disable, select, read, enable), these steps must be performed atomically. Normal synchronization routines cannot be used
+ *    as these functions are being called from interrupt context.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E		(1 << 0)	/* Enable all counters */
+#define PMNC_P		(1 << 1)	/* Reset all counters */
+#define PMNC_C		(1 << 2)	/* Cycle counter reset */
+#define	PMNC_MASK	0x3f	/* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG	(1 << 31)
+
+#define CCNT		0
+#define CNT0		1
+#define CNTMAX		(6+1)
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+inline void armv7_pmnc_write(u32 val)
+{
+	val &= PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	return val;
+}
+
+inline u32 armv7_ccnt_read(u32 reset_value)
+{
+	unsigned long flags;
+	u32 newval = -reset_value;
+	u32 den = CCNT_REG;
+	u32 val;
+
+	local_irq_save(flags);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den));	/* disable */
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));	/* read */
+	asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (newval));	/* new value */
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den));	/* enable */
+	local_irq_restore(flags);
+
+	return val;
+}
+
+inline u32 armv7_cntn_read(unsigned int cnt, u32 reset_value)
+{
+	unsigned long flags;
+	u32 newval = -reset_value;
+	u32 sel = (cnt - CNT0);
+	u32 den = 1 << sel;
+	u32 oldval;
+
+	local_irq_save(flags);
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den));	/* disable */
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (sel));	/* select */
+	asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (oldval));	/* read */
+	asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (newval));	/* new value */
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den));	/* enable */
+	local_irq_restore(flags);
+
+	return oldval;
+}
+
+static inline void armv7_pmnc_disable_interrupt(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : (1 << 31);
+
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_reset_interrupt(void)
+{
+	/* Get and reset overflow status flags */
+	u32 flags;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (flags));
+	flags &= 0x8000003f;
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (flags));
+	return flags;
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+	return cnt;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int cnt)
+{
+	u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+	return cnt;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int cnt)
+{
+	u32 val = (cnt - CNT0);
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+	return cnt;
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+	if (armv7_pmnc_select_counter(cnt) == cnt)
+		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+}
+
+static int gator_events_armv7_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < pmnc_counters; i++) {
+		char buf[40];
+
+		if (i == 0)
+			snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i > 0)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_armv7_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+	if (armv7_pmnc_read() & PMNC_E)
+		armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+	/* Initialize & Reset PMNC: C bit and P bit */
+	armv7_pmnc_write(PMNC_P | PMNC_C);
+
+	/* Reset overflow flags */
+	armv7_pmnc_reset_interrupt();
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		/* Disable counter */
+		armv7_pmnc_disable_counter(cnt);
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters), we don't need to set the event if it's a cycle count */
+		if (cnt != CCNT)
+			armv7_pmnc_write_evtsel(cnt, event);
+
+		armv7_pmnc_disable_interrupt(cnt);
+
+		/* Reset counter */
+		cnt ? armv7_cntn_read(cnt, 0) : armv7_ccnt_read(0);
+
+		/* Enable counter */
+		armv7_pmnc_enable_counter(cnt);
+	}
+
+	/* enable */
+	armv7_pmnc_write(armv7_pmnc_read() | PMNC_E);
+
+	/* return zero values, no need to read as the counters were just reset */
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_armv7_offline(int **buffer, bool migrate)
+{
+	/* disable all counters, including PMCCNTR; overflow IRQs will not be signaled */
+	armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+	return 0;
+}
+
+static void gator_events_armv7_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_armv7_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(armv7_pmnc_read() & PMNC_E))
+		return 0;
+
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			int value;
+
+			if (cnt == CCNT)
+				value = armv7_ccnt_read(0);
+			else
+				value = armv7_cntn_read(cnt, 0);
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_armv7_interface = {
+	.create_files = gator_events_armv7_create_files,
+	.stop = gator_events_armv7_stop,
+	.online = gator_events_armv7_online,
+	.offline = gator_events_armv7_offline,
+	.read = gator_events_armv7_read,
+};
+
+int gator_events_armv7_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case CORTEX_A5:
+		pmnc_name = "ARMv7_Cortex_A5";
+		pmnc_counters = 2;
+		break;
+	case CORTEX_A7:
+		pmnc_name = "ARMv7_Cortex_A7";
+		pmnc_counters = 4;
+		break;
+	case CORTEX_A8:
+		pmnc_name = "ARMv7_Cortex_A8";
+		pmnc_counters = 4;
+		break;
+	case CORTEX_A9:
+		pmnc_name = "ARMv7_Cortex_A9";
+		pmnc_counters = 6;
+		break;
+	case CORTEX_A15:
+		pmnc_name = "ARMv7_Cortex_A15";
+		pmnc_counters = 6;
+		break;
+	/* ARM Cortex A17 is not supported by version of Linux before 3.0 */
+	default:
+		return -1;
+	}
+
+	pmnc_counters++;	/* CNT[n] + CCNT */
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_armv7_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_block.c b/drivers/gator/gator_events_block.c
new file mode 100644
index 000000000000..a352a54afa02
--- /dev/null
+++ b/drivers/gator/gator_events_block.c
@@ -0,0 +1,160 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/block.h>
+
+#define BLOCK_RQ_WR		0
+#define BLOCK_RQ_RD		1
+
+#define BLOCK_TOTAL		(BLOCK_RQ_RD+1)
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+#define EVENTWRITE REQ_RW
+#else
+#define EVENTWRITE REQ_WRITE
+#endif
+
+static ulong block_rq_wr_enabled;
+static ulong block_rq_rd_enabled;
+static ulong block_rq_wr_key;
+static ulong block_rq_rd_key;
+static atomic_t blockCnt[BLOCK_TOTAL];
+static int blockGet[BLOCK_TOTAL * 4];
+
+/* Tracepoint changed in 3.15 backported to older kernels. The Makefile tries to autodetect the correct value, but if it fails change the #if below */
+#if OLD_BLOCK_RQ_COMPLETE
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq))
+#else
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq, unsigned int nr_bytes))
+#endif
+{
+	int write;
+	unsigned int size;
+
+	if (!rq)
+		return;
+
+	write = rq->cmd_flags & EVENTWRITE;
+#if OLD_BLOCK_RQ_COMPLETE
+	size = rq->resid_len;
+#else
+	size = nr_bytes;
+#endif
+
+	if (!size)
+		return;
+
+	if (write) {
+		if (block_rq_wr_enabled)
+			atomic_add(size, &blockCnt[BLOCK_RQ_WR]);
+	} else {
+		if (block_rq_rd_enabled)
+			atomic_add(size, &blockCnt[BLOCK_RQ_RD]);
+	}
+}
+
+static int gator_events_block_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* block_complete_wr */
+	dir = gatorfs_mkdir(sb, root, "Linux_block_rq_wr");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &block_rq_wr_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_wr_key);
+
+	/* block_complete_rd */
+	dir = gatorfs_mkdir(sb, root, "Linux_block_rq_rd");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &block_rq_rd_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_rd_key);
+
+	return 0;
+}
+
+static int gator_events_block_start(void)
+{
+	/* register tracepoints */
+	if (block_rq_wr_enabled || block_rq_rd_enabled)
+		if (GATOR_REGISTER_TRACE(block_rq_complete))
+			goto fail_block_rq_exit;
+	pr_debug("gator: registered block event tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_block_rq_exit:
+	pr_err("gator: block event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_block_stop(void)
+{
+	if (block_rq_wr_enabled || block_rq_rd_enabled)
+		GATOR_UNREGISTER_TRACE(block_rq_complete);
+	pr_debug("gator: unregistered block event tracepoints\n");
+
+	block_rq_wr_enabled = 0;
+	block_rq_rd_enabled = 0;
+}
+
+static int gator_events_block_read(int **buffer, bool sched_switch)
+{
+	int len, value, data = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	len = 0;
+	if (block_rq_wr_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_WR])) > 0) {
+		atomic_sub(value, &blockCnt[BLOCK_RQ_WR]);
+		blockGet[len++] = block_rq_wr_key;
+		/* Indicates to Streamline that value bytes were written now, not since the last message */
+		blockGet[len++] = 0;
+		blockGet[len++] = block_rq_wr_key;
+		blockGet[len++] = value;
+		data += value;
+	}
+	if (block_rq_rd_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_RD])) > 0) {
+		atomic_sub(value, &blockCnt[BLOCK_RQ_RD]);
+		blockGet[len++] = block_rq_rd_key;
+		/* Indicates to Streamline that value bytes were read now, not since the last message */
+		blockGet[len++] = 0;
+		blockGet[len++] = block_rq_rd_key;
+		blockGet[len++] = value;
+		data += value;
+	}
+
+	if (buffer)
+		*buffer = blockGet;
+
+	return len;
+}
+
+static struct gator_interface gator_events_block_interface = {
+	.create_files = gator_events_block_create_files,
+	.start = gator_events_block_start,
+	.stop = gator_events_block_stop,
+	.read = gator_events_block_read,
+};
+
+int gator_events_block_init(void)
+{
+	block_rq_wr_enabled = 0;
+	block_rq_rd_enabled = 0;
+
+	block_rq_wr_key = gator_events_get_key();
+	block_rq_rd_key = gator_events_get_key();
+
+	return gator_events_install(&gator_events_block_interface);
+}
diff --git a/drivers/gator/gator_events_irq.c b/drivers/gator/gator_events_irq.c
new file mode 100644
index 000000000000..5221aac581b3
--- /dev/null
+++ b/drivers/gator/gator_events_irq.c
@@ -0,0 +1,163 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/irq.h>
+
+#define HARDIRQ		0
+#define SOFTIRQ		1
+#define TOTALIRQ	(SOFTIRQ+1)
+
+static ulong hardirq_enabled;
+static ulong softirq_enabled;
+static ulong hardirq_key;
+static ulong softirq_key;
+static DEFINE_PER_CPU(atomic_t[TOTALIRQ], irqCnt);
+static DEFINE_PER_CPU(int[TOTALIRQ * 2], irqGet);
+
+GATOR_DEFINE_PROBE(irq_handler_exit,
+		   TP_PROTO(int irq, struct irqaction *action, int ret))
+{
+	atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[HARDIRQ]);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 37)
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(struct softirq_action *h, struct softirq_action *vec))
+#else
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(unsigned int vec_nr))
+#endif
+{
+	atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[SOFTIRQ]);
+}
+
+static int gator_events_irq_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* irq */
+	dir = gatorfs_mkdir(sb, root, "Linux_irq_irq");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &hardirq_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &hardirq_key);
+
+	/* soft irq */
+	dir = gatorfs_mkdir(sb, root, "Linux_irq_softirq");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &softirq_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &softirq_key);
+
+	return 0;
+}
+
+static int gator_events_irq_online(int **buffer, bool migrate)
+{
+	int len = 0, cpu = get_physical_cpu();
+
+	/* synchronization with the irq_exit functions is not necessary as the values are being reset */
+	if (hardirq_enabled) {
+		atomic_set(&per_cpu(irqCnt, cpu)[HARDIRQ], 0);
+		per_cpu(irqGet, cpu)[len++] = hardirq_key;
+		per_cpu(irqGet, cpu)[len++] = 0;
+	}
+
+	if (softirq_enabled) {
+		atomic_set(&per_cpu(irqCnt, cpu)[SOFTIRQ], 0);
+		per_cpu(irqGet, cpu)[len++] = softirq_key;
+		per_cpu(irqGet, cpu)[len++] = 0;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(irqGet, cpu);
+
+	return len;
+}
+
+static int gator_events_irq_start(void)
+{
+	/* register tracepoints */
+	if (hardirq_enabled)
+		if (GATOR_REGISTER_TRACE(irq_handler_exit))
+			goto fail_hardirq_exit;
+	if (softirq_enabled)
+		if (GATOR_REGISTER_TRACE(softirq_exit))
+			goto fail_softirq_exit;
+	pr_debug("gator: registered irq tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_softirq_exit:
+	if (hardirq_enabled)
+		GATOR_UNREGISTER_TRACE(irq_handler_exit);
+fail_hardirq_exit:
+	pr_err("gator: irq tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_irq_stop(void)
+{
+	if (hardirq_enabled)
+		GATOR_UNREGISTER_TRACE(irq_handler_exit);
+	if (softirq_enabled)
+		GATOR_UNREGISTER_TRACE(softirq_exit);
+	pr_debug("gator: unregistered irq tracepoints\n");
+
+	hardirq_enabled = 0;
+	softirq_enabled = 0;
+}
+
+static int gator_events_irq_read(int **buffer, bool sched_switch)
+{
+	int len, value;
+	int cpu = get_physical_cpu();
+
+	len = 0;
+	if (hardirq_enabled) {
+		value = atomic_read(&per_cpu(irqCnt, cpu)[HARDIRQ]);
+		atomic_sub(value, &per_cpu(irqCnt, cpu)[HARDIRQ]);
+
+		per_cpu(irqGet, cpu)[len++] = hardirq_key;
+		per_cpu(irqGet, cpu)[len++] = value;
+	}
+
+	if (softirq_enabled) {
+		value = atomic_read(&per_cpu(irqCnt, cpu)[SOFTIRQ]);
+		atomic_sub(value, &per_cpu(irqCnt, cpu)[SOFTIRQ]);
+
+		per_cpu(irqGet, cpu)[len++] = softirq_key;
+		per_cpu(irqGet, cpu)[len++] = value;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(irqGet, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_irq_interface = {
+	.create_files = gator_events_irq_create_files,
+	.online = gator_events_irq_online,
+	.start = gator_events_irq_start,
+	.stop = gator_events_irq_stop,
+	.read = gator_events_irq_read,
+};
+
+int gator_events_irq_init(void)
+{
+	hardirq_key = gator_events_get_key();
+	softirq_key = gator_events_get_key();
+
+	hardirq_enabled = 0;
+	softirq_enabled = 0;
+
+	return gator_events_install(&gator_events_irq_interface);
+}
diff --git a/drivers/gator/gator_events_l2c-310.c b/drivers/gator/gator_events_l2c-310.c
new file mode 100644
index 000000000000..73aaac32327e
--- /dev/null
+++ b/drivers/gator/gator_events_l2c-310.c
@@ -0,0 +1,208 @@
+/**
+ * l2c310 (L2 Cache Controller) event counters for gator
+ *
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#if defined(CONFIG_OF)
+#include <linux/of.h>
+#include <linux/of_address.h>
+#endif
+#include <asm/hardware/cache-l2x0.h>
+
+#include "gator.h"
+
+#define L2C310_COUNTERS_NUM 2
+
+static struct {
+	unsigned long enabled;
+	unsigned long event;
+	unsigned long key;
+} l2c310_counters[L2C310_COUNTERS_NUM];
+
+static int l2c310_buffer[L2C310_COUNTERS_NUM * 2];
+
+static void __iomem *l2c310_base;
+
+static void gator_events_l2c310_reset_counters(void)
+{
+	u32 val = readl(l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+	val |= ((1 << L2C310_COUNTERS_NUM) - 1) << 1;
+
+	writel(val, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_create_files(struct super_block *sb,
+					    struct dentry *root)
+{
+	int i;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		char buf[16];
+		struct dentry *dir;
+
+		snprintf(buf, sizeof(buf), "L2C-310_cnt%d", i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (WARN_ON(!dir))
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled",
+				     &l2c310_counters[i].enabled);
+		gatorfs_create_ulong(sb, dir, "event",
+				     &l2c310_counters[i].event);
+		gatorfs_create_ro_ulong(sb, dir, "key",
+					&l2c310_counters[i].key);
+	}
+
+	return 0;
+}
+
+static int gator_events_l2c310_start(void)
+{
+	static const unsigned long l2x0_event_cntx_cfg[L2C310_COUNTERS_NUM] = {
+		L2X0_EVENT_CNT0_CFG,
+		L2X0_EVENT_CNT1_CFG,
+	};
+	int i;
+
+	/* Counter event sources */
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++)
+		writel((l2c310_counters[i].event & 0xf) << 2,
+		       l2c310_base + l2x0_event_cntx_cfg[i]);
+
+	gator_events_l2c310_reset_counters();
+
+	/* Event counter enable */
+	writel(1, l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+	return 0;
+}
+
+static void gator_events_l2c310_stop(void)
+{
+	/* Event counter disable */
+	writel(0, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_read(int **buffer, bool sched_switch)
+{
+	static const unsigned long l2x0_event_cntx_val[L2C310_COUNTERS_NUM] = {
+		L2X0_EVENT_CNT0_VAL,
+		L2X0_EVENT_CNT1_VAL,
+	};
+	int i;
+	int len = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		if (l2c310_counters[i].enabled) {
+			l2c310_buffer[len++] = l2c310_counters[i].key;
+			l2c310_buffer[len++] = readl(l2c310_base +
+						     l2x0_event_cntx_val[i]);
+		}
+	}
+
+	/* l2c310 counters are saturating, not wrapping in case of overflow */
+	gator_events_l2c310_reset_counters();
+
+	if (buffer)
+		*buffer = l2c310_buffer;
+
+	return len;
+}
+
+static struct gator_interface gator_events_l2c310_interface = {
+	.create_files = gator_events_l2c310_create_files,
+	.start = gator_events_l2c310_start,
+	.stop = gator_events_l2c310_stop,
+	.read = gator_events_l2c310_read,
+};
+
+#define L2C310_ADDR_PROBE (~0)
+
+MODULE_PARM_DESC(l2c310_addr, "L2C310 physical base address (0 to disable)");
+static unsigned long l2c310_addr = L2C310_ADDR_PROBE;
+module_param(l2c310_addr, ulong, 0444);
+
+static void __iomem *gator_events_l2c310_probe(void)
+{
+	phys_addr_t variants[] = {
+#if defined(CONFIG_ARCH_EXYNOS4) || defined(CONFIG_ARCH_S5PV310)
+		0x10502000,
+#endif
+#if defined(CONFIG_ARCH_OMAP4)
+		0x48242000,
+#endif
+#if defined(CONFIG_ARCH_TEGRA)
+		0x50043000,
+#endif
+#if defined(CONFIG_ARCH_U8500)
+		0xa0412000,
+#endif
+#if defined(CONFIG_ARCH_VEXPRESS)
+		0x1e00a000, /* A9x4 core tile (HBI-0191) */
+		0x2c0f0000, /* New memory map tiles */
+#endif
+	};
+	int i;
+	void __iomem *base;
+#if defined(CONFIG_OF)
+	struct device_node *node = of_find_all_nodes(NULL);
+
+	if (node) {
+		of_node_put(node);
+
+		node = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
+		base = of_iomap(node, 0);
+		of_node_put(node);
+
+		return base;
+	}
+#endif
+
+	for (i = 0; i < ARRAY_SIZE(variants); i++) {
+		base = ioremap(variants[i], SZ_4K);
+		if (base) {
+			u32 cache_id = readl(base + L2X0_CACHE_ID);
+
+			if ((cache_id & 0xff0003c0) == 0x410000c0)
+				return base;
+
+			iounmap(base);
+		}
+	}
+
+	return NULL;
+}
+
+int gator_events_l2c310_init(void)
+{
+	int i;
+
+	if (gator_cpuid() != CORTEX_A5 && gator_cpuid() != CORTEX_A9)
+		return -1;
+
+	if (l2c310_addr == L2C310_ADDR_PROBE)
+		l2c310_base = gator_events_l2c310_probe();
+	else if (l2c310_addr)
+		l2c310_base = ioremap(l2c310_addr, SZ_4K);
+
+	if (!l2c310_base)
+		return -1;
+
+	for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+		l2c310_counters[i].enabled = 0;
+		l2c310_counters[i].key = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_l2c310_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.c b/drivers/gator/gator_events_mali_4xx.c
new file mode 100644
index 000000000000..9cf43fe2c29b
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.c
@@ -0,0 +1,622 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#include "linux/mali_linux_trace.h"
+
+#include "gator_events_mali_common.h"
+#include "gator_events_mali_4xx.h"
+
+/*
+* There have been four different variants of the comms between gator and Mali depending on driver version:
+* # | DDK vsn range             | Support                                                             | Notes
+*
+* 1 | (obsolete)                | No software counter support                                         | Obsolete patches
+* 2 | (obsolete)                | Tracepoint called for each separate s/w counter value as it appears | Obsolete patches
+* 3 | r3p0-04rel0 - r3p2-01rel2 | Single tracepoint for all s/w counters in a bundle.                 |
+* 4 | r3p2-01rel3 - date        | As above but with extensions for MP devices (Mali-450)              | At least r4p0-00rel1
+*/
+
+#if !defined(GATOR_MALI_INTERFACE_STYLE)
+#define GATOR_MALI_INTERFACE_STYLE (4)
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE == 1
+#error GATOR_MALI_INTERFACE_STYLE 1 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE == 2
+#error GATOR_MALI_INTERFACE_STYLE 2 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE >= 3
+/* Valid GATOR_MALI_INTERFACE_STYLE */
+#else
+#error Unknown GATOR_MALI_INTERFACE_STYLE option.
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE < 4
+#include "mali/mali_mjollnir_profiling_gator_api.h"
+#else
+#include "mali/mali_utgard_profiling_gator_api.h"
+#endif
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_4xx)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_4xx
+#endif
+
+static const char mali_name[] = "4xx";
+
+/* gatorfs variables for counter enable state,
+ * the event the counter should count and the
+ * 'key' (a unique id set by gatord and returned
+ * by gator.ko)
+ */
+static unsigned long counter_enabled[NUMBER_OF_EVENTS];
+static unsigned long counter_event[NUMBER_OF_EVENTS];
+static unsigned long counter_key[NUMBER_OF_EVENTS];
+
+/* The data we have recorded */
+static u32 counter_data[NUMBER_OF_EVENTS];
+/* The address to sample (or 0 if samples are sent to us) */
+static u32 *counter_address[NUMBER_OF_EVENTS];
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+static int counter_prev[NUMBER_OF_EVENTS];
+static bool prev_set[NUMBER_OF_EVENTS];
+
+/* Note whether tracepoints have been registered */
+static int trace_registered;
+
+/*
+ * These numbers define the actual numbers of each block type that exist in the system. Initially
+ * these are set to the maxima defined above; if the driver is capable of being queried (newer
+ * drivers only) then the values may be revised.
+ */
+static unsigned int n_vp_cores = MAX_NUM_VP_CORES;
+static unsigned int n_l2_cores = MAX_NUM_L2_CACHE_CORES;
+static unsigned int n_fp_cores = MAX_NUM_FP_CORES;
+
+extern struct mali_counter mali_activity[2];
+static const char *const mali_activity_names[] = {
+	"fragment",
+	"vertex",
+};
+
+/**
+ * Returns non-zero if the given counter ID is an activity counter.
+ */
+static inline int is_activity_counter(unsigned int event_id)
+{
+	return (event_id >= FIRST_ACTIVITY_EVENT &&
+		event_id <= LAST_ACTIVITY_EVENT);
+}
+
+/**
+ * Returns non-zero if the given counter ID is a hardware counter.
+ */
+static inline int is_hw_counter(unsigned int event_id)
+{
+	return (event_id >= FIRST_HW_COUNTER && event_id <= LAST_HW_COUNTER);
+}
+
+/* Probe for hardware counter events */
+GATOR_DEFINE_PROBE(mali_hw_counter, TP_PROTO(unsigned int event_id, unsigned int value))
+{
+	if (is_hw_counter(event_id))
+		counter_data[event_id] = value;
+}
+
+GATOR_DEFINE_PROBE(mali_sw_counters, TP_PROTO(pid_t pid, pid_t tid, void *surface_id, unsigned int *counters))
+{
+	u32 i;
+
+	/* Copy over the values for those counters which are enabled. */
+	for (i = FIRST_SW_COUNTER; i <= LAST_SW_COUNTER; i++) {
+		if (counter_enabled[i])
+			counter_data[i] = (u32)(counters[i - FIRST_SW_COUNTER]);
+	}
+}
+
+/**
+ * Create a single filesystem entry for a specified event.
+ * @param sb the superblock
+ * @param root Filesystem root
+ * @param name The name of the entry to create
+ * @param event The ID of the event
+ * @param create_event_item boolean indicating whether to create an 'event' filesystem entry. True to create.
+ *
+ * @return 0 if ok, non-zero if the create failed.
+ */
+static int create_fs_entry(struct super_block *sb, struct dentry *root, const char *name, int event, int create_event_item)
+{
+	struct dentry *dir;
+
+	dir = gatorfs_mkdir(sb, root, name);
+
+	if (!dir)
+		return -1;
+
+	if (create_event_item)
+		gatorfs_create_ulong(sb, dir, "event", &counter_event[event]);
+
+	gatorfs_create_ulong(sb, dir, "enabled", &counter_enabled[event]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &counter_key[event]);
+
+	return 0;
+}
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+/*
+ * Read the version info structure if available
+ */
+static void initialise_version_info(void)
+{
+	void (*mali_profiling_get_mali_version_symbol)(struct _mali_profiling_mali_version *values);
+
+	mali_profiling_get_mali_version_symbol = symbol_get(_mali_profiling_get_mali_version);
+
+	if (mali_profiling_get_mali_version_symbol) {
+		struct _mali_profiling_mali_version version_info;
+
+		pr_debug("gator: mali online _mali_profiling_get_mali_version symbol @ %p\n",
+				mali_profiling_get_mali_version_symbol);
+
+		/*
+		 * Revise the number of each different core type using information derived from the DDK.
+		 */
+		mali_profiling_get_mali_version_symbol(&version_info);
+
+		n_fp_cores = version_info.num_of_fp_cores;
+		n_vp_cores = version_info.num_of_vp_cores;
+		n_l2_cores = version_info.num_of_l2_cores;
+
+		/* Release the function - we're done with it. */
+		symbol_put(_mali_profiling_get_mali_version);
+	} else {
+		pr_err("gator: mali online _mali_profiling_get_mali_version symbol not found\n");
+		pr_err("gator:  check your Mali DDK version versus the GATOR_MALI_INTERFACE_STYLE setting\n");
+	}
+}
+#endif
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	int event;
+
+	char buf[40];
+	int core_id;
+	int counter_number;
+
+	pr_debug("gator: Initialising counters with style = %d\n", GATOR_MALI_INTERFACE_STYLE);
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+	/*
+	 * Initialise first: this sets up the number of cores available (on compatible DDK versions).
+	 * Ideally this would not need guarding but other parts of the code depend on the interface style being set
+	 * correctly; if it is not then the system can enter an inconsistent state.
+	 */
+	initialise_version_info();
+#endif
+
+	mali_activity[0].cores = n_fp_cores;
+	mali_activity[1].cores = n_vp_cores;
+	for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+		if (gator_mali_create_file_system(mali_name, mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+			return -1;
+	}
+
+	/* Vertex processor counters */
+	for (core_id = 0; core_id < n_vp_cores; core_id++) {
+		int activity_counter_id = ACTIVITY_VP_0;
+
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_active", mali_name, core_id);
+		if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+			return -1;
+
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_VP_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* Fragment processors' counters */
+	for (core_id = 0; core_id < n_fp_cores; core_id++) {
+		int activity_counter_id = ACTIVITY_FP_0 + core_id;
+
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_active", mali_name, core_id);
+		if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+			return -1;
+
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_FP_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* L2 Cache counters */
+	for (core_id = 0; core_id < n_l2_cores; core_id++) {
+		for (counter_number = 0; counter_number < 2; counter_number++) {
+			int counter_id = COUNTER_L2_0_C0 + (2 * core_id) + counter_number;
+
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_L2_%d_cnt%d", mali_name, core_id, counter_number);
+			if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+				return -1;
+		}
+	}
+
+	/* Now set up the software counter entries */
+	for (event = FIRST_SW_COUNTER; event <= LAST_SW_COUNTER; event++) {
+		snprintf(buf, sizeof(buf), "ARM_Mali-%s_SW_%d", mali_name, event - FIRST_SW_COUNTER);
+
+		if (create_fs_entry(sb, root, buf, event, 0) != 0)
+			return -1;
+	}
+
+	/* Now set up the special counter entries */
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Filmstrip_cnt0", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_FILMSTRIP, 1) != 0)
+		return -1;
+
+#ifdef DVFS_REPORTED_BY_DDK
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Frequency", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_FREQUENCY, 1) != 0)
+		return -1;
+
+	snprintf(buf, sizeof(buf), "ARM_Mali-%s_Voltage", mali_name);
+	if (create_fs_entry(sb, root, buf, COUNTER_VOLTAGE, 1) != 0)
+		return -1;
+#endif
+
+	return 0;
+}
+
+/*
+ * Local store for the get_counters entry point into the DDK.
+ * This is stored here since it is used very regularly.
+ */
+static void (*mali_get_counters)(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+static u32 (*mali_get_l2_counters)(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * Examine list of counters between two index limits and determine if any one is enabled.
+ * Returns 1 if any counter is enabled, 0 if none is.
+ */
+static int is_any_counter_enabled(unsigned int first_counter, unsigned int last_counter)
+{
+	unsigned int i;
+
+	for (i = first_counter; i <= last_counter; i++) {
+		if (counter_enabled[i])
+			return 1;	/* At least one counter is enabled */
+	}
+
+	return 0;		/* No s/w counters enabled */
+}
+
+static void init_counters(unsigned int from_counter, unsigned int to_counter)
+{
+	unsigned int counter_id;
+
+	/* If a Mali driver is present and exporting the appropriate symbol
+	 * then we can request the HW counters (of which there are only 2)
+	 * be configured to count the desired events
+	 */
+	mali_profiling_set_event_type *mali_set_hw_event;
+
+	mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+	if (mali_set_hw_event) {
+		pr_debug("gator: mali online _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+
+		for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+			if (counter_enabled[counter_id])
+				mali_set_hw_event(counter_id, counter_event[counter_id]);
+			else
+				mali_set_hw_event(counter_id, 0xFFFFFFFF);
+		}
+
+		symbol_put(_mali_profiling_set_event);
+	} else {
+		pr_err("gator: mali online _mali_profiling_set_event symbol not found\n");
+	}
+}
+
+static void mali_counter_initialize(void)
+{
+	int i;
+
+	mali_profiling_control_type *mali_control;
+
+	init_counters(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores) - 1);
+	init_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1);
+	init_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1);
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		/* The event attribute in the XML file keeps the actual frame rate. */
+		unsigned int rate = counter_event[COUNTER_FILMSTRIP] & 0xff;
+		unsigned int resize_factor = (counter_event[COUNTER_FILMSTRIP] >> 8) & 0xff;
+
+		pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+		mali_control(SW_COUNTER_ENABLE, (is_any_counter_enabled(FIRST_SW_COUNTER, LAST_SW_COUNTER) ? 1 : 0));
+		mali_control(FBDUMP_CONTROL_ENABLE, (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0));
+		mali_control(FBDUMP_CONTROL_RATE, rate);
+		mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+		pr_debug("gator: sent mali_control enabled=%d, rate=%d\n", (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0), rate);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+	}
+
+	mali_get_counters = symbol_get(_mali_profiling_get_counters);
+	if (mali_get_counters)
+		pr_debug("gator: mali online _mali_profiling_get_counters symbol @ %p\n", mali_get_counters);
+	else
+		pr_debug("gator WARNING: mali _mali_profiling_get_counters symbol not defined\n");
+
+	mali_get_l2_counters = symbol_get(_mali_profiling_get_l2_counters);
+	if (mali_get_l2_counters)
+		pr_debug("gator: mali online _mali_profiling_get_l2_counters symbol @ %p\n", mali_get_l2_counters);
+	else
+		pr_debug("gator WARNING: mali _mali_profiling_get_l2_counters symbol not defined\n");
+
+	if (!mali_get_counters && !mali_get_l2_counters) {
+		pr_debug("gator: WARNING: no L2 counters available\n");
+		n_l2_cores = 0;
+	}
+
+	/* Clear counters in the start */
+	for (i = 0; i < NUMBER_OF_EVENTS; i++) {
+		counter_data[i] = 0;
+		prev_set[i] = false;
+	}
+}
+
+static void mali_counter_deinitialize(void)
+{
+	mali_profiling_set_event_type *mali_set_hw_event;
+	mali_profiling_control_type *mali_control;
+
+	mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+	if (mali_set_hw_event) {
+		int i;
+
+		pr_debug("gator: mali offline _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+		for (i = FIRST_HW_COUNTER; i <= LAST_HW_COUNTER; i++)
+			mali_set_hw_event(i, 0xFFFFFFFF);
+
+		symbol_put(_mali_profiling_set_event);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_set_event symbol not found\n");
+	}
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+
+	if (mali_control) {
+		pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+		/* Reset the DDK state - disable counter collection */
+		mali_control(SW_COUNTER_ENABLE, 0);
+
+		mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+	}
+
+	if (mali_get_counters)
+		symbol_put(_mali_profiling_get_counters);
+
+	if (mali_get_l2_counters)
+		symbol_put(_mali_profiling_get_l2_counters);
+}
+
+static int start(void)
+{
+	/* register tracepoints */
+	if (GATOR_REGISTER_TRACE(mali_hw_counter)) {
+		pr_err("gator: mali_hw_counter tracepoint failed to activate\n");
+		return -1;
+	}
+
+	/* For Mali drivers with built-in support. */
+	if (GATOR_REGISTER_TRACE(mali_sw_counters)) {
+		pr_err("gator: mali_sw_counters tracepoint failed to activate\n");
+		return -1;
+	}
+
+	trace_registered = 1;
+
+	mali_counter_initialize();
+	return 0;
+}
+
+static void stop(void)
+{
+	unsigned int cnt;
+
+	pr_debug("gator: mali stop\n");
+
+	if (trace_registered) {
+		GATOR_UNREGISTER_TRACE(mali_hw_counter);
+
+		/* For Mali drivers with built-in support. */
+		GATOR_UNREGISTER_TRACE(mali_sw_counters);
+
+		pr_debug("gator: mali timeline tracepoint deactivated\n");
+
+		trace_registered = 0;
+	}
+
+	for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+		counter_enabled[cnt] = 0;
+		counter_event[cnt] = 0;
+		counter_address[cnt] = NULL;
+	}
+
+	mali_counter_deinitialize();
+}
+
+static void dump_counters(unsigned int from_counter, unsigned int to_counter, unsigned int *len)
+{
+	unsigned int counter_id;
+
+	for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+		if (counter_enabled[counter_id]) {
+			counter_dump[(*len)++] = counter_key[counter_id];
+			counter_dump[(*len)++] = counter_data[counter_id];
+
+			counter_data[counter_id] = 0;
+		}
+	}
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int len = 0;
+
+	if (!on_primary_core())
+		return 0;
+
+	/* Read the L2 C0 and C1 here. */
+	if (n_l2_cores > 0 && is_any_counter_enabled(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores))) {
+		unsigned int unavailable_l2_caches = 0;
+		struct _mali_profiling_l2_counter_values cache_values;
+		unsigned int cache_id;
+		struct _mali_profiling_core_counters *per_core;
+
+		/* Poke the driver to get the counter values - older style; only one L2 cache */
+		if (mali_get_l2_counters) {
+			unavailable_l2_caches = mali_get_l2_counters(&cache_values);
+		} else if (mali_get_counters) {
+			per_core = &cache_values.cores[0];
+			mali_get_counters(&per_core->source0, &per_core->value0, &per_core->source1, &per_core->value1);
+		} else {
+			/* This should never happen, as n_l2_caches is only set > 0 if one of the above functions is found. */
+		}
+
+		/* Fill in the two cache counter values for each cache block. */
+		for (cache_id = 0; cache_id < n_l2_cores; cache_id++) {
+			unsigned int counter_id_0 = COUNTER_L2_0_C0 + (2 * cache_id);
+			unsigned int counter_id_1 = counter_id_0 + 1;
+
+			if ((1 << cache_id) & unavailable_l2_caches)
+				continue; /* This cache is unavailable (powered-off, possibly). */
+
+			per_core = &cache_values.cores[cache_id];
+
+			if (counter_enabled[counter_id_0] && prev_set[counter_id_0]) {
+				/* Calculate and save src0's counter val0 */
+				counter_dump[len++] = counter_key[counter_id_0];
+				counter_dump[len++] = per_core->value0 - counter_prev[counter_id_0];
+			}
+
+			if (counter_enabled[counter_id_1] && prev_set[counter_id_1]) {
+				/* Calculate and save src1's counter val1 */
+				counter_dump[len++] = counter_key[counter_id_1];
+				counter_dump[len++] = per_core->value1 - counter_prev[counter_id_1];
+			}
+
+			/* Save the previous values for the counters. */
+			counter_prev[counter_id_0] = per_core->value0;
+			prev_set[counter_id_0] = true;
+			counter_prev[counter_id_1] = per_core->value1;
+			prev_set[counter_id_1] = true;
+		}
+	}
+
+	/* Process other (non-timeline) counters. */
+	dump_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1, &len);
+	dump_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1, &len);
+
+	dump_counters(FIRST_SW_COUNTER, LAST_SW_COUNTER, &len);
+
+#ifdef DVFS_REPORTED_BY_DDK
+	{
+		int cnt;
+		/*
+		 * Add in the voltage and frequency counters if enabled. Note
+		 * that, since these are actually passed as events, the counter
+		 * value should not be cleared.
+		 */
+		cnt = COUNTER_FREQUENCY;
+		if (counter_enabled[cnt]) {
+			counter_dump[len++] = counter_key[cnt];
+			counter_dump[len++] = counter_data[cnt];
+		}
+
+		cnt = COUNTER_VOLTAGE;
+		if (counter_enabled[cnt]) {
+			counter_dump[len++] = counter_key[cnt];
+			counter_dump[len++] = counter_data[cnt];
+		}
+	}
+#endif
+
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mali_interface = {
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read,
+};
+
+extern void gator_events_mali_log_dvfs_event(unsigned int frequency_mhz, unsigned int voltage_mv)
+{
+#ifdef DVFS_REPORTED_BY_DDK
+	counter_data[COUNTER_FREQUENCY] = frequency_mhz;
+	counter_data[COUNTER_VOLTAGE] = voltage_mv;
+#endif
+}
+
+int gator_events_mali_init(void)
+{
+	unsigned int cnt;
+
+	pr_debug("gator: mali init\n");
+
+	gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+
+	for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+		counter_enabled[cnt] = 0;
+		counter_event[cnt] = 0;
+		counter_key[cnt] = gator_events_get_key();
+		counter_address[cnt] = NULL;
+		counter_data[cnt] = 0;
+	}
+
+	trace_registered = 0;
+
+	return gator_events_install(&gator_events_mali_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.h b/drivers/gator/gator_events_mali_4xx.h
new file mode 100644
index 000000000000..976ca8c4cfa1
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * Header contains common definitions for the Mali-4xx processors.
+ */
+#if !defined(GATOR_EVENTS_MALI_4xx_H)
+#define GATOR_EVENTS_MALI_4xx_H
+
+extern void gator_events_mali_log_dvfs_event(unsigned int d0, unsigned int d1);
+
+#endif /* GATOR_EVENTS_MALI_4xx_H */
diff --git a/drivers/gator/gator_events_mali_common.c b/drivers/gator/gator_events_mali_common.c
new file mode 100644
index 000000000000..1af87d649afe
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.c
@@ -0,0 +1,72 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include "gator_events_mali_common.h"
+
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event)
+{
+	int err;
+	char buf[255];
+	struct dentry *dir;
+
+	/* If the counter name is empty ignore it */
+	if (strlen(event_name) != 0) {
+		/* Set up the filesystem entry for this event. */
+		if (mali_name == NULL)
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s", event_name);
+		else
+			snprintf(buf, sizeof(buf), "ARM_Mali-%s_%s", mali_name, event_name);
+
+		dir = gatorfs_mkdir(sb, root, buf);
+
+		if (dir == NULL) {
+			pr_debug("gator: %s: error creating file system for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+
+		err = gatorfs_create_ulong(sb, dir, "enabled", &counter->enabled);
+		if (err != 0) {
+			pr_debug("gator: %s: error calling gatorfs_create_ulong for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+		err = gatorfs_create_ro_ulong(sb, dir, "key", &counter->key);
+		if (err != 0) {
+			pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+			return -1;
+		}
+		if (counter->cores != -1) {
+			err = gatorfs_create_ro_ulong(sb, dir, "cores", &counter->cores);
+			if (err != 0) {
+				pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+				return -1;
+			}
+		}
+		if (event != NULL) {
+			err = gatorfs_create_ulong(sb, dir, "event", event);
+			if (err != 0) {
+				pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+				return -1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters)
+{
+	unsigned int cnt;
+
+	for (cnt = 0; cnt < n_counters; cnt++) {
+		struct mali_counter *counter = &counters[cnt];
+
+		counter->key = gator_events_get_key();
+		counter->enabled = 0;
+		counter->cores = -1;
+	}
+}
diff --git a/drivers/gator/gator_events_mali_common.h b/drivers/gator/gator_events_mali_common.h
new file mode 100644
index 000000000000..e7082e62fe88
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.h
@@ -0,0 +1,77 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if !defined(GATOR_EVENTS_MALI_COMMON_H)
+#define GATOR_EVENTS_MALI_COMMON_H
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Ensure that MALI_SUPPORT has been defined to something. */
+#ifndef MALI_SUPPORT
+#error MALI_SUPPORT not defined!
+#endif
+
+/* Values for the supported activity event types */
+#define ACTIVITY_START  (1)
+#define ACTIVITY_STOP   (2)
+
+/*
+ * Runtime state information for a counter.
+ */
+struct mali_counter {
+	/* 'key' (a unique id set by gatord and returned by gator.ko) */
+	unsigned long key;
+	/* counter enable state */
+	unsigned long enabled;
+	/* for activity counters, the number of cores, otherwise -1 */
+	unsigned long cores;
+};
+
+/*
+ * Mali-4xx
+ */
+typedef int mali_profiling_set_event_type(unsigned int, int);
+typedef void mali_profiling_control_type(unsigned int, unsigned int);
+
+/*
+ * Driver entry points for functions called directly by gator.
+ */
+extern int _mali_profiling_set_event(unsigned int, int);
+extern void _mali_profiling_control(unsigned int, unsigned int);
+extern void _mali_profiling_get_counters(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+
+/**
+ * Creates a filesystem entry under /dev/gator relating to the specified event name and key, and
+ * associate the key/enable values with this entry point.
+ *
+ * @param event_name The name of the event.
+ * @param sb Linux super block
+ * @param root Directory under which the entry will be created.
+ * @param counter_key Ptr to location which will be associated with the counter key.
+ * @param counter_enabled Ptr to location which will be associated with the counter enable state.
+ *
+ * @return 0 if entry point was created, non-zero if not.
+ */
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event);
+
+/**
+ * Initializes the counter array.
+ *
+ * @param keys The array of counters
+ * @param n_counters The number of entries in each of the arrays.
+ */
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters);
+
+#endif /* GATOR_EVENTS_MALI_COMMON_H  */
diff --git a/drivers/gator/gator_events_mali_midgard.c b/drivers/gator/gator_events_mali_midgard.c
new file mode 100644
index 000000000000..0aec906d7ae5
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard.c
@@ -0,0 +1,562 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_MIDGARD)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_MIDGARD
+#endif
+
+static const char mali_name[] = "Midgard";
+
+/* Counters for Mali-Midgard:
+ *
+ *  - Timeline events
+ *    They are tracepoints, but instead of reporting a number they report a START/STOP event.
+ *    They are reported in Streamline as number of microseconds while that particular counter was active.
+ *
+ *  - SW counters
+ *    They are tracepoints reporting a particular number.
+ *    They are accumulated in sw_counter_data array until they are passed to Streamline, then they are zeroed.
+ *
+ *  - Accumulators
+ *    They are the same as software counters but their value is not zeroed.
+ */
+
+/* Timeline (start/stop) activity */
+static const char *const timeline_event_names[] = {
+	"PM_SHADER_0",
+	"PM_SHADER_1",
+	"PM_SHADER_2",
+	"PM_SHADER_3",
+	"PM_SHADER_4",
+	"PM_SHADER_5",
+	"PM_SHADER_6",
+	"PM_SHADER_7",
+	"PM_TILER_0",
+	"PM_L2_0",
+	"PM_L2_1",
+	"MMU_AS_0",
+	"MMU_AS_1",
+	"MMU_AS_2",
+	"MMU_AS_3"
+};
+
+enum {
+	PM_SHADER_0 = 0,
+	PM_SHADER_1,
+	PM_SHADER_2,
+	PM_SHADER_3,
+	PM_SHADER_4,
+	PM_SHADER_5,
+	PM_SHADER_6,
+	PM_SHADER_7,
+	PM_TILER_0,
+	PM_L2_0,
+	PM_L2_1,
+	MMU_AS_0,
+	MMU_AS_1,
+	MMU_AS_2,
+	MMU_AS_3
+};
+/* The number of shader blocks in the enum above */
+#define NUM_PM_SHADER (8)
+
+/* Software Counters */
+static const char *const software_counter_names[] = {
+	"MMU_PAGE_FAULT_0",
+	"MMU_PAGE_FAULT_1",
+	"MMU_PAGE_FAULT_2",
+	"MMU_PAGE_FAULT_3"
+};
+
+enum {
+	MMU_PAGE_FAULT_0 = 0,
+	MMU_PAGE_FAULT_1,
+	MMU_PAGE_FAULT_2,
+	MMU_PAGE_FAULT_3
+};
+
+/* Software Counters */
+static const char *const accumulators_names[] = {
+	"TOTAL_ALLOC_PAGES"
+};
+
+enum {
+	TOTAL_ALLOC_PAGES = 0
+};
+
+#define FIRST_TIMELINE_EVENT (0)
+#define NUMBER_OF_TIMELINE_EVENTS (sizeof(timeline_event_names) / sizeof(timeline_event_names[0]))
+#define FIRST_SOFTWARE_COUNTER (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS)
+#define NUMBER_OF_SOFTWARE_COUNTERS (sizeof(software_counter_names) / sizeof(software_counter_names[0]))
+#define FIRST_ACCUMULATOR (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS)
+#define NUMBER_OF_ACCUMULATORS (sizeof(accumulators_names) / sizeof(accumulators_names[0]))
+#define FILMSTRIP (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS)
+#define NUMBER_OF_EVENTS (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS + 1)
+
+/*
+ * gatorfs variables for counter enable state
+ */
+static struct mali_counter counters[NUMBER_OF_EVENTS];
+static unsigned long filmstrip_event;
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+
+/*
+ * Array holding counter start times (in ns) for each counter. A zero
+ * here indicates that the activity monitored by this counter is not
+ * running.
+ */
+static struct timespec timeline_event_starttime[NUMBER_OF_TIMELINE_EVENTS];
+
+/* The data we have recorded */
+static unsigned int timeline_data[NUMBER_OF_TIMELINE_EVENTS];
+static unsigned int sw_counter_data[NUMBER_OF_SOFTWARE_COUNTERS];
+static unsigned int accumulators_data[NUMBER_OF_ACCUMULATORS];
+
+/* Hold the previous timestamp, used to calculate the sample interval. */
+static struct timespec prev_timestamp;
+
+/**
+ * Returns the timespan (in microseconds) between the two specified timestamps.
+ *
+ * @param start Ptr to the start timestamp
+ * @param end Ptr to the end timestamp
+ *
+ * @return Number of microseconds between the two timestamps (can be negative if start follows end).
+ */
+static inline long get_duration_us(const struct timespec *start, const struct timespec *end)
+{
+	long event_duration_us = (end->tv_nsec - start->tv_nsec) / 1000;
+
+	event_duration_us += (end->tv_sec - start->tv_sec) * 1000000;
+
+	return event_duration_us;
+}
+
+static void record_timeline_event(unsigned int timeline_index, unsigned int type)
+{
+	struct timespec event_timestamp;
+	struct timespec *event_start = &timeline_event_starttime[timeline_index];
+
+	switch (type) {
+	case ACTIVITY_START:
+		/* Get the event time... */
+		getnstimeofday(&event_timestamp);
+
+		/* Remember the start time if the activity is not already started */
+		if (event_start->tv_sec == 0)
+			*event_start = event_timestamp;	/* Structure copy */
+		break;
+
+	case ACTIVITY_STOP:
+		/* if the counter was started... */
+		if (event_start->tv_sec != 0) {
+			/* Get the event time... */
+			getnstimeofday(&event_timestamp);
+
+			/* Accumulate the duration in us */
+			timeline_data[timeline_index] += get_duration_us(event_start, &event_timestamp);
+
+			/* Reset the start time to indicate the activity is stopped. */
+			event_start->tv_sec = 0;
+		}
+		break;
+
+	default:
+		/* Other activity events are ignored. */
+		break;
+	}
+}
+
+/*
+ * Documentation about the following tracepoints is in mali_linux_trace.h
+ */
+
+GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long long value))
+{
+#define SHADER_PRESENT_LO       0x100	/* (RO) Shader core present bitmap, low word */
+#define TILER_PRESENT_LO        0x110	/* (RO) Tiler core present bitmap, low word */
+#define L2_PRESENT_LO           0x120	/* (RO) Level 2 cache present bitmap, low word */
+#define BIT_AT(value, pos) ((value >> pos) & 1)
+
+	static unsigned long long previous_shader_bitmask;
+	static unsigned long long previous_tiler_bitmask;
+	static unsigned long long previous_l2_bitmask;
+
+	switch (event_id) {
+	case SHADER_PRESENT_LO:
+		{
+			unsigned long long changed_bitmask = previous_shader_bitmask ^ value;
+			int pos;
+
+			for (pos = 0; pos < NUM_PM_SHADER; ++pos) {
+				if (BIT_AT(changed_bitmask, pos))
+					record_timeline_event(PM_SHADER_0 + pos, BIT_AT(value, pos) ? ACTIVITY_START : ACTIVITY_STOP);
+			}
+
+			previous_shader_bitmask = value;
+			break;
+		}
+
+	case TILER_PRESENT_LO:
+		{
+			unsigned long long changed = previous_tiler_bitmask ^ value;
+
+			if (BIT_AT(changed, 0))
+				record_timeline_event(PM_TILER_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+
+			previous_tiler_bitmask = value;
+			break;
+		}
+
+	case L2_PRESENT_LO:
+		{
+			unsigned long long changed = previous_l2_bitmask ^ value;
+
+			if (BIT_AT(changed, 0))
+				record_timeline_event(PM_L2_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+			if (BIT_AT(changed, 4))
+				record_timeline_event(PM_L2_1, BIT_AT(value, 4) ? ACTIVITY_START : ACTIVITY_STOP);
+
+			previous_l2_bitmask = value;
+			break;
+		}
+
+	default:
+		/* No other blocks are supported at present */
+		break;
+	}
+
+#undef SHADER_PRESENT_LO
+#undef TILER_PRESENT_LO
+#undef L2_PRESENT_LO
+#undef BIT_AT
+}
+
+GATOR_DEFINE_PROBE(mali_page_fault_insert_pages, TP_PROTO(int event_id, unsigned long value))
+{
+	/* We add to the previous since we may receive many tracepoints in one sample period */
+	sw_counter_data[MMU_PAGE_FAULT_0 + event_id] += value;
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_in_use, TP_PROTO(int event_id))
+{
+	record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_START);
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_released, TP_PROTO(int event_id))
+{
+	record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_STOP);
+}
+
+GATOR_DEFINE_PROBE(mali_total_alloc_pages_change, TP_PROTO(long long int event_id))
+{
+	accumulators_data[TOTAL_ALLOC_PAGES] = event_id;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	int event;
+	/*
+	 * Create the filesystem for all events
+	 */
+	int counter_index = 0;
+	mali_profiling_control_type *mali_control;
+
+	for (event = FIRST_TIMELINE_EVENT; event < FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS; event++) {
+		if (gator_mali_create_file_system(mali_name, timeline_event_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+	counter_index = 0;
+	for (event = FIRST_SOFTWARE_COUNTER; event < FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS; event++) {
+		if (gator_mali_create_file_system(mali_name, software_counter_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+	counter_index = 0;
+	for (event = FIRST_ACCUMULATOR; event < FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS; event++) {
+		if (gator_mali_create_file_system(mali_name, accumulators_names[counter_index], sb, root, &counters[event], NULL) != 0)
+			return -1;
+		counter_index++;
+	}
+
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		if (gator_mali_create_file_system(mali_name, "Filmstrip_cnt0", sb, root, &counters[FILMSTRIP], &filmstrip_event) != 0)
+			return -1;
+		symbol_put(_mali_profiling_control);
+	}
+
+	return 0;
+}
+
+static int register_tracepoints(void)
+{
+	if (GATOR_REGISTER_TRACE(mali_pm_status)) {
+		pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_page_fault_insert_pages)) {
+		pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_mmu_as_in_use)) {
+		pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_mmu_as_released)) {
+		pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint failed to activate\n");
+		return 0;
+	}
+
+	if (GATOR_REGISTER_TRACE(mali_total_alloc_pages_change)) {
+		pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint failed to activate\n");
+		return 0;
+	}
+
+	pr_debug("gator: Mali-Midgard: start\n");
+	pr_debug("gator: Mali-Midgard: mali_pm_status probe is at %p\n", &probe_mali_pm_status);
+	pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages probe is at %p\n", &probe_mali_page_fault_insert_pages);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use probe is at %p\n", &probe_mali_mmu_as_in_use);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_released probe is at %p\n", &probe_mali_mmu_as_released);
+	pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change probe is at %p\n", &probe_mali_total_alloc_pages_change);
+
+	return 1;
+}
+
+static int start(void)
+{
+	unsigned int cnt;
+	mali_profiling_control_type *mali_control;
+
+	/* Clean all data for the next capture */
+	for (cnt = 0; cnt < NUMBER_OF_TIMELINE_EVENTS; cnt++) {
+		timeline_event_starttime[cnt].tv_sec = timeline_event_starttime[cnt].tv_nsec = 0;
+		timeline_data[cnt] = 0;
+	}
+
+	for (cnt = 0; cnt < NUMBER_OF_SOFTWARE_COUNTERS; cnt++)
+		sw_counter_data[cnt] = 0;
+
+	for (cnt = 0; cnt < NUMBER_OF_ACCUMULATORS; cnt++)
+		accumulators_data[cnt] = 0;
+
+	/* Register tracepoints */
+	if (register_tracepoints() == 0)
+		return -1;
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		/* The event attribute in the XML file keeps the actual frame rate. */
+		unsigned int enabled = counters[FILMSTRIP].enabled ? 1 : 0;
+		unsigned int rate = filmstrip_event & 0xff;
+		unsigned int resize_factor = (filmstrip_event >> 8) & 0xff;
+
+		pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+		mali_control(FBDUMP_CONTROL_ENABLE, enabled);
+		mali_control(FBDUMP_CONTROL_RATE, rate);
+		mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+		pr_debug("gator: sent mali_control enabled=%d, rate=%d, resize_factor=%d\n", enabled, rate, resize_factor);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+	}
+
+	/*
+	 * Set the first timestamp for calculating the sample interval. The first interval could be quite long,
+	 * since it will be the time between 'start' and the first 'read'.
+	 * This means that timeline values will be divided by a big number for the first sample.
+	 */
+	getnstimeofday(&prev_timestamp);
+
+	return 0;
+}
+
+static void stop(void)
+{
+	mali_profiling_control_type *mali_control;
+
+	pr_debug("gator: Mali-Midgard: stop\n");
+
+	/*
+	 * It is safe to unregister traces even if they were not successfully
+	 * registered, so no need to check.
+	 */
+	GATOR_UNREGISTER_TRACE(mali_pm_status);
+	pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_page_fault_insert_pages);
+	pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_mmu_as_in_use);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_mmu_as_released);
+	pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint deactivated\n");
+
+	GATOR_UNREGISTER_TRACE(mali_total_alloc_pages_change);
+	pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint deactivated\n");
+
+	/* Generic control interface for Mali DDK. */
+	mali_control = symbol_get(_mali_profiling_control);
+	if (mali_control) {
+		pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+		mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+		symbol_put(_mali_profiling_control);
+	} else {
+		pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+	}
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int cnt;
+	int len = 0;
+	long sample_interval_us = 0;
+	struct timespec read_timestamp;
+
+	if (!on_primary_core())
+		return 0;
+
+	/* Get the start of this sample period. */
+	getnstimeofday(&read_timestamp);
+
+	/*
+	 * Calculate the sample interval if the previous sample time is valid.
+	 * We use tv_sec since it will not be 0.
+	 */
+	if (prev_timestamp.tv_sec != 0)
+		sample_interval_us = get_duration_us(&prev_timestamp, &read_timestamp);
+
+	/* Structure copy. Update the previous timestamp. */
+	prev_timestamp = read_timestamp;
+
+	/*
+	 * Report the timeline counters (ACTIVITY_START/STOP)
+	 */
+	for (cnt = FIRST_TIMELINE_EVENT; cnt < (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS); cnt++) {
+		struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_TIMELINE_EVENT;
+			unsigned int value;
+
+			/* If the activity is still running, reset its start time to the
+			 * start of this sample period to correct the count. Add the
+			 * time up to the end of the sample onto the count.
+			 */
+			if (timeline_event_starttime[index].tv_sec != 0) {
+				const long event_duration = get_duration_us(&timeline_event_starttime[index], &read_timestamp);
+
+				timeline_data[index] += event_duration;
+				timeline_event_starttime[index] = read_timestamp;	/* Activity is still running. */
+			}
+
+			if (sample_interval_us != 0) {
+				/* Convert the counter to a percent-of-sample value */
+				value = (timeline_data[index] * 100) / sample_interval_us;
+			} else {
+				pr_debug("gator: Mali-Midgard: setting value to zero\n");
+				value = 0;
+			}
+
+			/* Clear the counter value ready for the next sample. */
+			timeline_data[index] = 0;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = value;
+		}
+	}
+
+	/* Report the software counters */
+	for (cnt = FIRST_SOFTWARE_COUNTER; cnt < (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS); cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_SOFTWARE_COUNTER;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = sw_counter_data[index];
+			/* Set the value to zero for the next time */
+			sw_counter_data[index] = 0;
+		}
+	}
+
+	/* Report the accumulators */
+	for (cnt = FIRST_ACCUMULATOR; cnt < (FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS); cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			const int index = cnt - FIRST_ACCUMULATOR;
+
+			counter_dump[len++] = counter->key;
+			counter_dump[len++] = accumulators_data[index];
+			/* Do not zero the accumulator */
+		}
+	}
+
+	/* Update the buffer */
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read
+};
+
+extern int gator_events_mali_midgard_init(void)
+{
+	pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+	gator_mali_initialise_counters(counters, NUMBER_OF_EVENTS);
+
+	return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw.c b/drivers/gator/gator_events_mali_midgard_hw.c
new file mode 100644
index 000000000000..c8065da56815
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw.c
@@ -0,0 +1,977 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Mali Midgard DDK includes */
+#if defined(MALI_SIMPLE_API)
+/* Header with wrapper functions to kbase structures and functions */
+#include "mali/mali_kbase_gator_api.h"
+#elif defined(MALI_DIR_MIDGARD)
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard */
+#include "mali_linux_trace.h"
+#include "mali_kbase.h"
+#include "mali_kbase_mem_linux.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx */
+#include "linux/mali_linux_trace.h"
+#include "kbase/src/common/mali_kbase.h"
+#include "kbase/src/linux/mali_kbase_mem_linux.h"
+#endif
+
+/* If API version is not specified then assume API version 1. */
+#ifndef MALI_DDK_GATOR_API_VERSION
+#define MALI_DDK_GATOR_API_VERSION 1
+#endif
+
+#if (MALI_DDK_GATOR_API_VERSION != 1) && (MALI_DDK_GATOR_API_VERSION != 2) && (MALI_DDK_GATOR_API_VERSION != 3)
+#error MALI_DDK_GATOR_API_VERSION is invalid (must be 1 for r1/r2 DDK, or 2 for r3/r4 DDK, or 3 for r5 and later DDK).
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Mali-Midgard
+ */
+#if MALI_DDK_GATOR_API_VERSION == 3
+static uint32_t (*kbase_gator_instr_hwcnt_dump_irq_symbol)(struct kbase_gator_hwcnt_handles *);
+static uint32_t (*kbase_gator_instr_hwcnt_dump_complete_symbol)(struct kbase_gator_hwcnt_handles *, uint32_t *const);
+static struct kbase_gator_hwcnt_handles *(*kbase_gator_hwcnt_init_symbol)(struct kbase_gator_hwcnt_info *);
+static void (*kbase_gator_hwcnt_term_symbol)(struct kbase_gator_hwcnt_info *, struct kbase_gator_hwcnt_handles *);
+
+#else
+static struct kbase_device *(*kbase_find_device_symbol)(int);
+static struct kbase_context *(*kbase_create_context_symbol)(struct kbase_device *);
+static void (*kbase_destroy_context_symbol)(struct kbase_context *);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32);
+static void (*kbase_va_free_symbol)(struct kbase_context *, void *);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32, struct kbase_hwc_dma_mapping *);
+static void (*kbase_va_free_symbol)(struct kbase_context *, struct kbase_hwc_dma_mapping *);
+#endif
+
+static mali_error (*kbase_instr_hwcnt_enable_symbol)(struct kbase_context *, struct kbase_uk_hwcnt_setup *);
+static mali_error (*kbase_instr_hwcnt_disable_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_clear_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_dump_irq_symbol)(struct kbase_context *);
+static mali_bool (*kbase_instr_hwcnt_dump_complete_symbol)(struct kbase_context *, mali_bool *);
+
+static long shader_present_low;
+#endif
+
+/** The interval between reads, in ns.
+ *
+ * Earlier we introduced a 'hold off for 1ms after last read' to
+ * resolve MIDBASE-2178 and MALINE-724. However, the 1ms hold off is
+ * too long if no context switches occur as there is a race between
+ * this value and the tick of the read clock in gator which is also
+ * 1ms. If we 'miss' the current read, the counter values are
+ * effectively 'spread' over 2ms and the values seen are half what
+ * they should be (since Streamline averages over sample time). In the
+ * presence of context switches this spread can vary and markedly
+ * affect the counters. Currently there is no 'proper' solution to
+ * this, but empirically we have found that reducing the minimum read
+ * interval to 950us causes the counts to be much more stable.
+ */
+static const int READ_INTERVAL_NSEC = 950000;
+
+#if GATOR_TEST
+#include "gator_events_mali_midgard_hw_test.c"
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION != 3
+/* Blocks for HW counters */
+enum {
+	JM_BLOCK = 0,
+	TILER_BLOCK,
+	SHADER_BLOCK,
+	MMU_BLOCK
+};
+#endif
+
+static const char *mali_name;
+
+/* Counters for Mali-Midgard:
+ *
+ *    For HW counters we need strings to create /dev/gator/events files.
+ *    Enums are not needed because the position of the HW name in the array is the same
+ *    of the corresponding value in the received block of memory.
+ *    HW counters are requested by calculating a bitmask, passed then to the driver.
+ *    Every millisecond a HW counters dump is requested, and if the previous has been completed they are read.
+ */
+
+/* Hardware Counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+
+static const char *const *hardware_counter_names;
+static int number_of_hardware_counters;
+
+#else
+
+static const char *const hardware_counter_names[] = {
+	/* Job Manager */
+	"",
+	"",
+	"",
+	"",
+	"MESSAGES_SENT",
+	"MESSAGES_RECEIVED",
+	"GPU_ACTIVE",		/* 6 */
+	"IRQ_ACTIVE",
+	"JS0_JOBS",
+	"JS0_TASKS",
+	"JS0_ACTIVE",
+	"",
+	"JS0_WAIT_READ",
+	"JS0_WAIT_ISSUE",
+	"JS0_WAIT_DEPEND",
+	"JS0_WAIT_FINISH",
+	"JS1_JOBS",
+	"JS1_TASKS",
+	"JS1_ACTIVE",
+	"",
+	"JS1_WAIT_READ",
+	"JS1_WAIT_ISSUE",
+	"JS1_WAIT_DEPEND",
+	"JS1_WAIT_FINISH",
+	"JS2_JOBS",
+	"JS2_TASKS",
+	"JS2_ACTIVE",
+	"",
+	"JS2_WAIT_READ",
+	"JS2_WAIT_ISSUE",
+	"JS2_WAIT_DEPEND",
+	"JS2_WAIT_FINISH",
+	"JS3_JOBS",
+	"JS3_TASKS",
+	"JS3_ACTIVE",
+	"",
+	"JS3_WAIT_READ",
+	"JS3_WAIT_ISSUE",
+	"JS3_WAIT_DEPEND",
+	"JS3_WAIT_FINISH",
+	"JS4_JOBS",
+	"JS4_TASKS",
+	"JS4_ACTIVE",
+	"",
+	"JS4_WAIT_READ",
+	"JS4_WAIT_ISSUE",
+	"JS4_WAIT_DEPEND",
+	"JS4_WAIT_FINISH",
+	"JS5_JOBS",
+	"JS5_TASKS",
+	"JS5_ACTIVE",
+	"",
+	"JS5_WAIT_READ",
+	"JS5_WAIT_ISSUE",
+	"JS5_WAIT_DEPEND",
+	"JS5_WAIT_FINISH",
+	"JS6_JOBS",
+	"JS6_TASKS",
+	"JS6_ACTIVE",
+	"",
+	"JS6_WAIT_READ",
+	"JS6_WAIT_ISSUE",
+	"JS6_WAIT_DEPEND",
+	"JS6_WAIT_FINISH",
+
+	/*Tiler */
+	"",
+	"",
+	"",
+	"JOBS_PROCESSED",
+	"TRIANGLES",
+	"QUADS",
+	"POLYGONS",
+	"POINTS",
+	"LINES",
+	"VCACHE_HIT",
+	"VCACHE_MISS",
+	"FRONT_FACING",
+	"BACK_FACING",
+	"PRIM_VISIBLE",
+	"PRIM_CULLED",
+	"PRIM_CLIPPED",
+	"LEVEL0",
+	"LEVEL1",
+	"LEVEL2",
+	"LEVEL3",
+	"LEVEL4",
+	"LEVEL5",
+	"LEVEL6",
+	"LEVEL7",
+	"COMMAND_1",
+	"COMMAND_2",
+	"COMMAND_3",
+	"COMMAND_4",
+	"COMMAND_4_7",
+	"COMMAND_8_15",
+	"COMMAND_16_63",
+	"COMMAND_64",
+	"COMPRESS_IN",
+	"COMPRESS_OUT",
+	"COMPRESS_FLUSH",
+	"TIMESTAMPS",
+	"PCACHE_HIT",
+	"PCACHE_MISS",
+	"PCACHE_LINE",
+	"PCACHE_STALL",
+	"WRBUF_HIT",
+	"WRBUF_MISS",
+	"WRBUF_LINE",
+	"WRBUF_PARTIAL",
+	"WRBUF_STALL",
+	"ACTIVE",
+	"LOADING_DESC",
+	"INDEX_WAIT",
+	"INDEX_RANGE_WAIT",
+	"VERTEX_WAIT",
+	"PCACHE_WAIT",
+	"WRBUF_WAIT",
+	"BUS_READ",
+	"BUS_WRITE",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"UTLB_STALL",
+	"UTLB_REPLAY_MISS",
+	"UTLB_REPLAY_FULL",
+	"UTLB_NEW_MISS",
+	"UTLB_HIT",
+
+	/* Shader Core */
+	"",
+	"",
+	"",
+	"SHADER_CORE_ACTIVE",
+	"FRAG_ACTIVE",
+	"FRAG_PRIMATIVES",
+	"FRAG_PRIMATIVES_DROPPED",
+	"FRAG_CYCLE_DESC",
+	"FRAG_CYCLES_PLR",
+	"FRAG_CYCLES_VERT",
+	"FRAG_CYCLES_TRISETUP",
+	"FRAG_CYCLES_RAST",
+	"FRAG_THREADS",
+	"FRAG_DUMMY_THREADS",
+	"FRAG_QUADS_RAST",
+	"FRAG_QUADS_EZS_TEST",
+	"FRAG_QUADS_EZS_KILLED",
+	"FRAG_QUADS_LZS_TEST",
+	"FRAG_QUADS_LZS_KILLED",
+	"FRAG_CYCLE_NO_TILE",
+	"FRAG_NUM_TILES",
+	"FRAG_TRANS_ELIM",
+	"COMPUTE_ACTIVE",
+	"COMPUTE_TASKS",
+	"COMPUTE_THREADS",
+	"COMPUTE_CYCLES_DESC",
+	"TRIPIPE_ACTIVE",
+	"ARITH_WORDS",
+	"ARITH_CYCLES_REG",
+	"ARITH_CYCLES_L0",
+	"ARITH_FRAG_DEPEND",
+	"LS_WORDS",
+	"LS_ISSUES",
+	"LS_RESTARTS",
+	"LS_REISSUES_MISS",
+	"LS_REISSUES_VD",
+	"LS_REISSUE_ATTRIB_MISS",
+	"LS_NO_WB",
+	"TEX_WORDS",
+	"TEX_BUBBLES",
+	"TEX_WORDS_L0",
+	"TEX_WORDS_DESC",
+	"TEX_THREADS",
+	"TEX_RECIRC_FMISS",
+	"TEX_RECIRC_DESC",
+	"TEX_RECIRC_MULTI",
+	"TEX_RECIRC_PMISS",
+	"TEX_RECIRC_CONF",
+	"LSC_READ_HITS",
+	"LSC_READ_MISSES",
+	"LSC_WRITE_HITS",
+	"LSC_WRITE_MISSES",
+	"LSC_ATOMIC_HITS",
+	"LSC_ATOMIC_MISSES",
+	"LSC_LINE_FETCHES",
+	"LSC_DIRTY_LINE",
+	"LSC_SNOOPS",
+	"AXI_TLB_STALL",
+	"AXI_TLB_MIESS",
+	"AXI_TLB_TRANSACTION",
+	"LS_TLB_MISS",
+	"LS_TLB_HIT",
+	"AXI_BEATS_READ",
+	"AXI_BEATS_WRITTEN",
+
+	/*L2 and MMU */
+	"",
+	"",
+	"",
+	"",
+	"MMU_HIT",
+	"MMU_NEW_MISS",
+	"MMU_REPLAY_FULL",
+	"MMU_REPLAY_MISS",
+	"MMU_TABLE_WALK",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"UTLB_HIT",
+	"UTLB_NEW_MISS",
+	"UTLB_REPLAY_FULL",
+	"UTLB_REPLAY_MISS",
+	"UTLB_STALL",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"",
+	"L2_WRITE_BEATS",
+	"L2_READ_BEATS",
+	"L2_ANY_LOOKUP",
+	"L2_READ_LOOKUP",
+	"L2_SREAD_LOOKUP",
+	"L2_READ_REPLAY",
+	"L2_READ_SNOOP",
+	"L2_READ_HIT",
+	"L2_CLEAN_MISS",
+	"L2_WRITE_LOOKUP",
+	"L2_SWRITE_LOOKUP",
+	"L2_WRITE_REPLAY",
+	"L2_WRITE_SNOOP",
+	"L2_WRITE_HIT",
+	"L2_EXT_READ_FULL",
+	"L2_EXT_READ_HALF",
+	"L2_EXT_WRITE_FULL",
+	"L2_EXT_WRITE_HALF",
+	"L2_EXT_READ",
+	"L2_EXT_READ_LINE",
+	"L2_EXT_WRITE",
+	"L2_EXT_WRITE_LINE",
+	"L2_EXT_WRITE_SMALL",
+	"L2_EXT_BARRIER",
+	"L2_EXT_AR_STALL",
+	"L2_EXT_R_BUF_FULL",
+	"L2_EXT_RD_BUF_FULL",
+	"L2_EXT_R_RAW",
+	"L2_EXT_W_STALL",
+	"L2_EXT_W_BUF_FULL",
+	"L2_EXT_R_W_HAZARD",
+	"L2_TAG_HAZARD",
+	"L2_SNOOP_FULL",
+	"L2_REPLAY_FULL"
+};
+
+static const int number_of_hardware_counters = ARRAY_SIZE(hardware_counter_names);
+
+#endif
+
+#define GET_HW_BLOCK(c) (((c) >> 6) & 0x3)
+#define GET_COUNTER_OFFSET(c) ((c) & 0x3f)
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+/* Opaque handles for kbase_context and kbase_hwc_dma_mapping */
+static struct kbase_gator_hwcnt_handles *handles;
+
+/* Information about hardware counters */
+static struct kbase_gator_hwcnt_info *in_out_info;
+
+#else
+/* Memory to dump hardware counters into */
+static void *kernel_dump_buffer;
+
+#if MALI_DDK_GATOR_API_VERSION == 2
+/* DMA state used to manage lifetime of the buffer */
+struct kbase_hwc_dma_mapping kernel_dump_buffer_handle;
+#endif
+
+/* kbase context and device */
+static struct kbase_context *kbcontext;
+static struct kbase_device *kbdevice;
+
+/*
+ * The following function has no external prototype in older DDK
+ * revisions. When the DDK is updated then this should be removed.
+ */
+struct kbase_device *kbase_find_device(int minor);
+#endif
+
+static volatile bool kbase_device_busy;
+static unsigned int num_hardware_counters_enabled;
+
+/* gatorfs variables for counter enable state */
+static struct mali_counter *counters;
+
+/* An array used to return the data we recorded as key,value pairs */
+static int *counter_dump;
+
+extern struct mali_counter mali_activity[3];
+
+static const char *const mali_activity_names[] = {
+	"fragment",
+	"vertex",
+	"opencl",
+};
+
+#define SYMBOL_GET(FUNCTION, ERROR_COUNT) \
+	do { \
+		if (FUNCTION ## _symbol) { \
+			pr_err("gator: mali " #FUNCTION " symbol was already registered\n"); \
+			(ERROR_COUNT)++; \
+		} else { \
+			FUNCTION ## _symbol = symbol_get(FUNCTION); \
+			if (!FUNCTION ## _symbol) { \
+				pr_err("gator: mali online " #FUNCTION " symbol not found\n"); \
+				(ERROR_COUNT)++; \
+			} \
+		} \
+	} while (0)
+
+#define SYMBOL_CLEANUP(FUNCTION) \
+	do { \
+		if (FUNCTION ## _symbol) { \
+			symbol_put(FUNCTION); \
+			FUNCTION ## _symbol = NULL; \
+		} \
+	} while (0)
+
+/**
+ * Execute symbol_get for all the Mali symbols and check for success.
+ * @return the number of symbols not loaded.
+ */
+static int init_symbols(void)
+{
+	int error_count = 0;
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_instr_hwcnt_dump_irq, error_count);
+	SYMBOL_GET(kbase_gator_instr_hwcnt_dump_complete, error_count);
+	SYMBOL_GET(kbase_gator_hwcnt_init, error_count);
+	SYMBOL_GET(kbase_gator_hwcnt_term, error_count);
+#else
+	SYMBOL_GET(kbase_find_device, error_count);
+	SYMBOL_GET(kbase_create_context, error_count);
+	SYMBOL_GET(kbase_va_alloc, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_enable, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_clear, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_dump_irq, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_dump_complete, error_count);
+	SYMBOL_GET(kbase_instr_hwcnt_disable, error_count);
+	SYMBOL_GET(kbase_va_free, error_count);
+	SYMBOL_GET(kbase_destroy_context, error_count);
+#endif
+
+	return error_count;
+}
+
+/**
+ * Execute symbol_put for all the registered Mali symbols.
+ */
+static void clean_symbols(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_irq);
+	SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_complete);
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_init);
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_term);
+#else
+	SYMBOL_CLEANUP(kbase_find_device);
+	SYMBOL_CLEANUP(kbase_create_context);
+	SYMBOL_CLEANUP(kbase_va_alloc);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_enable);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_clear);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_irq);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_complete);
+	SYMBOL_CLEANUP(kbase_instr_hwcnt_disable);
+	SYMBOL_CLEANUP(kbase_va_free);
+	SYMBOL_CLEANUP(kbase_destroy_context);
+#endif
+}
+
+/**
+ * Determines whether a read should take place
+ * @param current_time The current time, obtained from getnstimeofday()
+ * @param prev_time_s The number of seconds at the previous read attempt.
+ * @param next_read_time_ns The time (in ns) when the next read should be allowed.
+ *
+ * Note that this function has been separated out here to allow it to be tested.
+ */
+static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time_s, s32 *next_read_time_ns)
+{
+	/* If the current ns count rolls over a second, roll the next read time too. */
+	if (current_time->tv_sec != *prev_time_s)
+		*next_read_time_ns = *next_read_time_ns - NSEC_PER_SEC;
+
+	/* Abort the read if the next read time has not arrived. */
+	if (current_time->tv_nsec < *next_read_time_ns)
+		return 0;
+
+	/* Set the next read some fixed time after this one, and update the read timestamp. */
+	*next_read_time_ns = current_time->tv_nsec + READ_INTERVAL_NSEC;
+
+	*prev_time_s = current_time->tv_sec;
+	return 1;
+}
+
+static int start(void)
+{
+#if MALI_DDK_GATOR_API_VERSION != 3
+	struct kbase_uk_hwcnt_setup setup;
+	unsigned long long shadersPresent = 0;
+	u16 bitmask[] = { 0, 0, 0, 0 };
+	mali_error err;
+#endif
+	int cnt;
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	/* Setup HW counters */
+	num_hardware_counters_enabled = 0;
+
+	/* Declare and initialise kbase_gator_hwcnt_info structure */
+	in_out_info = kmalloc(sizeof(*in_out_info), GFP_KERNEL);
+	for (cnt = 0; cnt < ARRAY_SIZE(in_out_info->bitmask); cnt++)
+		in_out_info->bitmask[cnt] = 0;
+
+	/* Calculate enable bitmasks based on counters_enabled array */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+		if (counters[cnt].enabled) {
+			int block = GET_HW_BLOCK(cnt);
+			int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+			in_out_info->bitmask[block] |= (1 << enable_bit);
+			pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+			num_hardware_counters_enabled++;
+		}
+	}
+
+	/* Create a kbase context for HW counters */
+	if (num_hardware_counters_enabled > 0) {
+		if (init_symbols() > 0) {
+			clean_symbols();
+			/* No Mali driver code entrypoints found - not a fault. */
+			return 0;
+		}
+
+		handles = kbase_gator_hwcnt_init_symbol(in_out_info);
+
+		if (handles == NULL)
+			goto out;
+
+		kbase_device_busy = false;
+	}
+
+	return 0;
+#else
+	/* Setup HW counters */
+	num_hardware_counters_enabled = 0;
+
+	/* Calculate enable bitmasks based on counters_enabled array */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+		const struct mali_counter *counter = &counters[cnt];
+
+		if (counter->enabled) {
+			int block = GET_HW_BLOCK(cnt);
+			int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+			bitmask[block] |= (1 << enable_bit);
+			pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+			num_hardware_counters_enabled++;
+		}
+	}
+
+	/* Create a kbase context for HW counters */
+	if (num_hardware_counters_enabled > 0) {
+		if (init_symbols() > 0) {
+			clean_symbols();
+			/* No Mali driver code entrypoints found - not a fault. */
+			return 0;
+		}
+
+		kbdevice = kbase_find_device_symbol(-1);
+
+		/* If we already got a context, fail */
+		if (kbcontext) {
+			pr_debug("gator: Mali-Midgard: error context already present\n");
+			goto out;
+		}
+
+		/* kbcontext will only be valid after all the Mali symbols are loaded successfully */
+		kbcontext = kbase_create_context_symbol(kbdevice);
+		if (!kbcontext) {
+			pr_debug("gator: Mali-Midgard: error creating kbase context\n");
+			goto out;
+		}
+
+		/* See if we can get the number of shader cores */
+		shadersPresent = kbdevice->shader_present_bitmap;
+		shader_present_low = (unsigned long)shadersPresent;
+
+		/*
+		 * The amount of memory needed to store the dump (bytes)
+		 * DUMP_SIZE = number of core groups
+		 *             * number of blocks (always 8 for midgard)
+		 *             * number of counters per block (always 64 for midgard)
+		 *             * number of bytes per counter (always 4 in midgard)
+		 * For a Mali-Midgard with a single core group = 1 * 8 * 64 * 4 = 2048
+		 * For a Mali-Midgard with a dual core group   = 2 * 8 * 64 * 4 = 4096
+		 */
+#if MALI_DDK_GATOR_API_VERSION == 1
+		kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+		kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096, &kernel_dump_buffer_handle);
+#endif
+		if (!kernel_dump_buffer) {
+			pr_debug("gator: Mali-Midgard: error trying to allocate va\n");
+			goto destroy_context;
+		}
+
+		setup.dump_buffer = (uintptr_t)kernel_dump_buffer;
+		setup.jm_bm = bitmask[JM_BLOCK];
+		setup.tiler_bm = bitmask[TILER_BLOCK];
+		setup.shader_bm = bitmask[SHADER_BLOCK];
+		setup.mmu_l2_bm = bitmask[MMU_BLOCK];
+		/* These counters do not exist on Mali-T60x */
+		setup.l3_cache_bm = 0;
+
+		/* Use kbase API to enable hardware counters and provide dump buffer */
+		err = kbase_instr_hwcnt_enable_symbol(kbcontext, &setup);
+		if (err != MALI_ERROR_NONE) {
+			pr_debug("gator: Mali-Midgard: can't setup hardware counters\n");
+			goto free_buffer;
+		}
+		pr_debug("gator: Mali-Midgard: hardware counters enabled\n");
+		kbase_instr_hwcnt_clear_symbol(kbcontext);
+		pr_debug("gator: Mali-Midgard: hardware counters cleared\n");
+
+		kbase_device_busy = false;
+	}
+
+	return 0;
+
+free_buffer:
+#if MALI_DDK_GATOR_API_VERSION == 1
+	kbase_va_free_symbol(kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+	kbase_va_free_symbol(kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+destroy_context:
+	kbase_destroy_context_symbol(kbcontext);
+#endif
+
+out:
+	clean_symbols();
+	return -1;
+}
+
+static void stop(void)
+{
+	unsigned int cnt;
+#if MALI_DDK_GATOR_API_VERSION == 3
+	struct kbase_gator_hwcnt_handles *temp_hand;
+#else
+	struct kbase_context *temp_kbcontext;
+#endif
+
+	pr_debug("gator: Mali-Midgard: stop\n");
+
+	/* Set all counters as disabled */
+	for (cnt = 0; cnt < number_of_hardware_counters; cnt++)
+		counters[cnt].enabled = 0;
+
+	/* Destroy the context for HW counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+	if (num_hardware_counters_enabled > 0 && handles != NULL) {
+		/*
+		 * Set the global variable to NULL before destroying it, because
+		 * other function will check this before using it.
+		 */
+		temp_hand = handles;
+		handles = NULL;
+
+		kbase_gator_hwcnt_term_symbol(in_out_info, temp_hand);
+
+		kfree(in_out_info);
+
+#else
+	if (num_hardware_counters_enabled > 0 && kbcontext != NULL) {
+		/*
+		 * Set the global variable to NULL before destroying it, because
+		 * other function will check this before using it.
+		 */
+		temp_kbcontext = kbcontext;
+		kbcontext = NULL;
+
+		kbase_instr_hwcnt_disable_symbol(temp_kbcontext);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+		kbase_va_free_symbol(temp_kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+		kbase_va_free_symbol(temp_kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+		kbase_destroy_context_symbol(temp_kbcontext);
+#endif
+
+		pr_debug("gator: Mali-Midgard: hardware counters stopped\n");
+
+		clean_symbols();
+	}
+}
+
+static int read_counter(const int cnt, const int len, const struct mali_counter *counter)
+{
+	const int block = GET_HW_BLOCK(cnt);
+	const int counter_offset = GET_COUNTER_OFFSET(cnt);
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	const char *block_base_address = (char *)in_out_info->kernel_dump_buffer;
+	int i;
+	int shader_core_count = 0;
+	u32 value = 0;
+
+	for (i = 0; i < in_out_info->nr_hwc_blocks; i++) {
+		if (block == in_out_info->hwc_layout[i]) {
+			value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+			if (block == SHADER_BLOCK)
+				++shader_core_count;
+		}
+	}
+
+	if (shader_core_count > 1)
+		value /= shader_core_count;
+#else
+	const char *block_base_address = (char *)kernel_dump_buffer + vithar_blocks[block];
+
+	/* If counter belongs to shader block need to take into account all cores */
+	if (block == SHADER_BLOCK) {
+		int i = 0;
+		int shader_core_count = 0;
+
+		value = 0;
+
+		for (i = 0; i < 4; i++) {
+			if ((shader_present_low >> i) & 1) {
+				value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+				shader_core_count++;
+			}
+		}
+
+		for (i = 0; i < 4; i++) {
+			if ((shader_present_low >> (i+4)) & 1) {
+				value += *((u32 *)(block_base_address + (0x100 * i) + 0x800) + counter_offset);
+				shader_core_count++;
+			}
+		}
+
+		/* Need to total by number of cores to produce an average */
+		if (shader_core_count != 0)
+			value /= shader_core_count;
+	} else {
+		value = *((u32 *)block_base_address + counter_offset);
+	}
+#endif
+
+	counter_dump[len + 0] = counter->key;
+	counter_dump[len + 1] = value;
+
+	return 2;
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+	int cnt;
+	int len = 0;
+	uint32_t success;
+
+	struct timespec current_time;
+	static u32 prev_time_s;
+	static s32 next_read_time_ns;
+
+	if (!on_primary_core() || sched_switch)
+		return 0;
+
+	getnstimeofday(&current_time);
+
+	/*
+	 * Discard reads unless a respectable time has passed. This
+	 * reduces the load on the GPU without sacrificing accuracy on
+	 * the Streamline display.
+	 */
+	if (!is_read_scheduled(&current_time, &prev_time_s, &next_read_time_ns))
+		return 0;
+
+	/*
+	 * Report the HW counters
+	 * Only process hardware counters if at least one of the hardware counters is enabled.
+	 */
+	if (num_hardware_counters_enabled > 0) {
+#if MALI_DDK_GATOR_API_VERSION != 3
+		const unsigned int vithar_blocks[] = {
+			0x700,	/* VITHAR_JOB_MANAGER,     Block 0 */
+			0x400,	/* VITHAR_TILER,           Block 1 */
+			0x000,	/* VITHAR_SHADER_CORE,     Block 2 */
+			0x500	/* VITHAR_MEMORY_SYSTEM,   Block 3 */
+		};
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+		if (!handles)
+			return -1;
+
+		/* Mali symbols can be called safely since a kbcontext is valid */
+		if (kbase_gator_instr_hwcnt_dump_complete_symbol(handles, &success) == MALI_TRUE) {
+#else
+		if (!kbcontext)
+			return -1;
+
+		/* Mali symbols can be called safely since a kbcontext is valid */
+		if (kbase_instr_hwcnt_dump_complete_symbol(kbcontext, &success) == MALI_TRUE) {
+#endif
+			kbase_device_busy = false;
+
+			if (success == MALI_TRUE) {
+				/* Cycle through hardware counters and accumulate totals */
+				for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+					const struct mali_counter *counter = &counters[cnt];
+
+					if (counter->enabled)
+						len += read_counter(cnt, len, counter);
+				}
+			}
+		}
+
+		if (!kbase_device_busy) {
+			kbase_device_busy = true;
+#if MALI_DDK_GATOR_API_VERSION == 3
+			kbase_gator_instr_hwcnt_dump_irq_symbol(handles);
+#else
+			kbase_instr_hwcnt_dump_irq_symbol(kbcontext);
+#endif
+		}
+	}
+
+	/* Update the buffer */
+	if (buffer)
+		*buffer = counter_dump;
+
+	return len;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+	unsigned int event;
+	/*
+	 * Create the filesystem for all events
+	 */
+	for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+		if (gator_mali_create_file_system("Midgard", mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+			return -1;
+	}
+
+	for (event = 0; event < number_of_hardware_counters; event++) {
+		if (gator_mali_create_file_system(mali_name, hardware_counter_names[event], sb, root, &counters[event], NULL) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static void shutdown(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	void (*kbase_gator_hwcnt_term_names_symbol)(void) = NULL;
+	int error_count = 0;
+#endif
+
+	kfree(counters);
+	kfree(counter_dump);
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_hwcnt_term_names, error_count);
+
+	number_of_hardware_counters = -1;
+	hardware_counter_names = NULL;
+	if (kbase_gator_hwcnt_term_names_symbol != NULL) {
+		kbase_gator_hwcnt_term_names_symbol();
+		pr_err("Released symbols\n");
+	}
+
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_term_names);
+#endif
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+	.shutdown = shutdown,
+	.create_files = create_files,
+	.start = start,
+	.stop = stop,
+	.read = read
+};
+
+int gator_events_mali_midgard_hw_init(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+	const char *const *(*kbase_gator_hwcnt_init_names_symbol)(uint32_t *) = NULL;
+	int error_count = 0;
+#endif
+
+	pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+#if GATOR_TEST
+	test_all_is_read_scheduled();
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+	SYMBOL_GET(kbase_gator_hwcnt_init_names, error_count);
+	if (error_count > 0) {
+		SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+		return 1;
+	}
+
+	number_of_hardware_counters = -1;
+	hardware_counter_names = kbase_gator_hwcnt_init_names_symbol(&number_of_hardware_counters);
+
+	SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+
+	if ((hardware_counter_names == NULL) || (number_of_hardware_counters <= 0)) {
+		pr_err("gator: Error reading hardware counters names: got %d names\n", number_of_hardware_counters);
+		return -1;
+	}
+#else
+	mali_name = "Midgard";
+#endif
+
+	counters = kmalloc(sizeof(*counters)*number_of_hardware_counters, GFP_KERNEL);
+	counter_dump = kmalloc(sizeof(*counter_dump)*number_of_hardware_counters*2, GFP_KERNEL);
+
+	gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+	gator_mali_initialise_counters(counters, number_of_hardware_counters);
+
+	return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw_test.c b/drivers/gator/gator_events_mali_midgard_hw_test.c
new file mode 100644
index 000000000000..31a91e1c72b2
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw_test.c
@@ -0,0 +1,55 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/**
+ * Test functions for mali_t600_hw code.
+ */
+
+static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time_s, s32 *next_read_time_ns);
+
+static int test_is_read_scheduled(u32 s, u32 ns, u32 prev_s, s32 next_ns, int expected_result, s32 expected_next_ns)
+{
+	struct timespec current_time;
+	u32 prev_time_s = prev_s;
+	s32 next_read_time_ns = next_ns;
+
+	current_time.tv_sec = s;
+	current_time.tv_nsec = ns;
+
+	if (is_read_scheduled(&current_time, &prev_time_s, &next_read_time_ns) != expected_result) {
+		pr_err("Failed do_read(%u, %u, %u, %d): expected %d\n", s, ns, prev_s, next_ns, expected_result);
+		return 0;
+	}
+
+	if (next_read_time_ns != expected_next_ns) {
+		pr_err("Failed: next_read_ns expected=%d, actual=%d\n", expected_next_ns, next_read_time_ns);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void test_all_is_read_scheduled(void)
+{
+	const int HIGHEST_NS = 999999999;
+	int n_tests_passed = 0;
+
+	pr_err("gator: running tests on %s\n", __FILE__);
+
+	n_tests_passed += test_is_read_scheduled(0, 0, 0, 0, 1, READ_INTERVAL_NSEC);	/* Null time */
+	n_tests_passed += test_is_read_scheduled(100, 1000, 0, 0, 1, READ_INTERVAL_NSEC + 1000);	/* Initial values */
+
+	n_tests_passed += test_is_read_scheduled(100, HIGHEST_NS, 100, HIGHEST_NS + 500, 0, HIGHEST_NS + 500);
+	n_tests_passed += test_is_read_scheduled(101, 0001, 100, HIGHEST_NS + 500, 0, HIGHEST_NS + 500 - NSEC_PER_SEC);
+	n_tests_passed += test_is_read_scheduled(101, 600, 100, HIGHEST_NS + 500 - NSEC_PER_SEC, 1, 600 + READ_INTERVAL_NSEC);
+
+	n_tests_passed += test_is_read_scheduled(101, 600, 100, HIGHEST_NS + 500, 1, 600 + READ_INTERVAL_NSEC);
+
+	pr_err("gator: %d tests passed\n", n_tests_passed);
+}
diff --git a/drivers/gator/gator_events_meminfo.c b/drivers/gator/gator_events_meminfo.c
new file mode 100644
index 000000000000..c625ac5af9cd
--- /dev/null
+++ b/drivers/gator/gator_events_meminfo.c
@@ -0,0 +1,470 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/hardirq.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/workqueue.h>
+#include <trace/events/kmem.h>
+
+#define USE_THREAD defined(CONFIG_PREEMPT_RT_FULL)
+
+enum {
+	MEMINFO_MEMFREE,
+	MEMINFO_MEMUSED,
+	MEMINFO_BUFFERRAM,
+	MEMINFO_TOTAL,
+};
+
+enum {
+	PROC_SIZE,
+	PROC_SHARE,
+	PROC_TEXT,
+	PROC_DATA,
+	PROC_COUNT,
+};
+
+static const char * const meminfo_names[] = {
+	"Linux_meminfo_memfree",
+	"Linux_meminfo_memused",
+	"Linux_meminfo_bufferram",
+};
+
+static const char * const proc_names[] = {
+	"Linux_proc_statm_size",
+	"Linux_proc_statm_share",
+	"Linux_proc_statm_text",
+	"Linux_proc_statm_data",
+};
+
+static bool meminfo_global_enabled;
+static ulong meminfo_enabled[MEMINFO_TOTAL];
+static ulong meminfo_keys[MEMINFO_TOTAL];
+static long long meminfo_buffer[2 * (MEMINFO_TOTAL + 2)];
+static int meminfo_length;
+static bool new_data_avail;
+
+static bool proc_global_enabled;
+static ulong proc_enabled[PROC_COUNT];
+static ulong proc_keys[PROC_COUNT];
+static DEFINE_PER_CPU(long long, proc_buffer[2 * (PROC_COUNT + 3)]);
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data);
+static bool gator_meminfo_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_meminfo_sem);
+#else
+static DEFINE_SEMAPHORE(gator_meminfo_sem);
+#endif
+
+static void notify(void)
+{
+	up(&gator_meminfo_sem);
+}
+
+#else
+
+static unsigned int mem_event;
+static void wq_sched_handler(struct work_struct *wsptr);
+DECLARE_WORK(work, wq_sched_handler);
+static struct timer_list meminfo_wake_up_timer;
+static void meminfo_wake_up_handler(unsigned long unused_data);
+
+static void notify(void)
+{
+	mem_event++;
+}
+
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_page_free_direct, TP_PROTO(struct page *page, unsigned int order))
+#else
+GATOR_DEFINE_PROBE(mm_page_free, TP_PROTO(struct page *page, unsigned int order))
+#endif
+{
+	notify();
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_pagevec_free, TP_PROTO(struct page *page, int cold))
+#else
+GATOR_DEFINE_PROBE(mm_page_free_batched, TP_PROTO(struct page *page, int cold))
+#endif
+{
+	notify();
+}
+
+GATOR_DEFINE_PROBE(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype))
+{
+	notify();
+}
+
+static int gator_events_meminfo_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		dir = gatorfs_mkdir(sb, root, meminfo_names[i]);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &meminfo_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &meminfo_keys[i]);
+	}
+
+	for (i = 0; i < PROC_COUNT; ++i) {
+		dir = gatorfs_mkdir(sb, root, proc_names[i]);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &proc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &proc_keys[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_meminfo_start(void)
+{
+	int i;
+
+	new_data_avail = false;
+	meminfo_global_enabled = 0;
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		if (meminfo_enabled[i]) {
+			meminfo_global_enabled = 1;
+			break;
+		}
+	}
+
+	proc_global_enabled = 0;
+	for (i = 0; i < PROC_COUNT; ++i) {
+		if (proc_enabled[i]) {
+			proc_global_enabled = 1;
+			break;
+		}
+	}
+	if (meminfo_enabled[MEMINFO_MEMUSED])
+		proc_global_enabled = 1;
+
+	if (meminfo_global_enabled == 0)
+		return 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	if (GATOR_REGISTER_TRACE(mm_page_free_direct))
+#else
+	if (GATOR_REGISTER_TRACE(mm_page_free))
+#endif
+		goto mm_page_free_exit;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	if (GATOR_REGISTER_TRACE(mm_pagevec_free))
+#else
+	if (GATOR_REGISTER_TRACE(mm_page_free_batched))
+#endif
+		goto mm_page_free_batched_exit;
+	if (GATOR_REGISTER_TRACE(mm_page_alloc))
+		goto mm_page_alloc_exit;
+
+#if USE_THREAD
+	/* Start worker thread */
+	gator_meminfo_run = true;
+	/* Since the mutex starts unlocked, memory values will be initialized */
+	if (IS_ERR(kthread_run(gator_meminfo_func, NULL, "gator_meminfo")))
+		goto kthread_run_exit;
+#else
+	setup_timer(&meminfo_wake_up_timer, meminfo_wake_up_handler, 0);
+#endif
+
+	return 0;
+
+#if USE_THREAD
+kthread_run_exit:
+	GATOR_UNREGISTER_TRACE(mm_page_alloc);
+#endif
+mm_page_alloc_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+	GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+mm_page_free_batched_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+	GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+#else
+	GATOR_UNREGISTER_TRACE(mm_page_free);
+#endif
+mm_page_free_exit:
+	return -1;
+}
+
+static void gator_events_meminfo_stop(void)
+{
+	if (meminfo_global_enabled) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+		GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+		GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+		GATOR_UNREGISTER_TRACE(mm_page_free);
+		GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+		GATOR_UNREGISTER_TRACE(mm_page_alloc);
+
+#if USE_THREAD
+		/* Stop worker thread */
+		gator_meminfo_run = false;
+		up(&gator_meminfo_sem);
+#else
+		del_timer_sync(&meminfo_wake_up_timer);
+#endif
+	}
+}
+
+static void do_read(void)
+{
+	struct sysinfo info;
+	int i, len;
+	unsigned long long value;
+
+	meminfo_length = len = 0;
+
+	si_meminfo(&info);
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		if (meminfo_enabled[i]) {
+			switch (i) {
+			case MEMINFO_MEMFREE:
+				value = info.freeram * PAGE_SIZE;
+				break;
+			case MEMINFO_MEMUSED:
+				/* pid -1 means system wide */
+				meminfo_buffer[len++] = 1;
+				meminfo_buffer[len++] = -1;
+				/* Emit value */
+				meminfo_buffer[len++] = meminfo_keys[MEMINFO_MEMUSED];
+				meminfo_buffer[len++] = (info.totalram - info.freeram) * PAGE_SIZE;
+				/* Clear pid */
+				meminfo_buffer[len++] = 1;
+				meminfo_buffer[len++] = 0;
+				continue;
+			case MEMINFO_BUFFERRAM:
+				value = info.bufferram * PAGE_SIZE;
+				break;
+			default:
+				value = 0;
+				break;
+			}
+			meminfo_buffer[len++] = meminfo_keys[i];
+			meminfo_buffer[len++] = value;
+		}
+	}
+
+	meminfo_length = len;
+	new_data_avail = true;
+}
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data)
+{
+	for (;;) {
+		if (down_killable(&gator_meminfo_sem))
+			break;
+
+		/* Eat up any pending events */
+		while (!down_trylock(&gator_meminfo_sem))
+			;
+
+		if (!gator_meminfo_run)
+			break;
+
+		do_read();
+	}
+
+	return 0;
+}
+
+#else
+
+/* Must be run in process context as the kernel function si_meminfo() can sleep */
+static void wq_sched_handler(struct work_struct *wsptr)
+{
+	do_read();
+}
+
+static void meminfo_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&work);
+}
+
+#endif
+
+static int gator_events_meminfo_read(long long **buffer)
+{
+#if !USE_THREAD
+	static unsigned int last_mem_event;
+#endif
+
+	if (!on_primary_core() || !meminfo_global_enabled)
+		return 0;
+
+#if !USE_THREAD
+	if (last_mem_event != mem_event) {
+		last_mem_event = mem_event;
+		mod_timer(&meminfo_wake_up_timer, jiffies + 1);
+	}
+#endif
+
+	if (!new_data_avail)
+		return 0;
+
+	new_data_avail = false;
+
+	if (buffer)
+		*buffer = meminfo_buffer;
+
+	return meminfo_length;
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 34) && LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+
+static inline unsigned long gator_get_mm_counter(struct mm_struct *mm, int member)
+{
+#ifdef SPLIT_RSS_COUNTING
+	long val = atomic_long_read(&mm->rss_stat.count[member]);
+
+	if (val < 0)
+		val = 0;
+	return (unsigned long)val;
+#else
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 0, 0)
+	return mm->rss_stat.count[member];
+#else
+	return atomic_long_read(&mm->rss_stat.count[member]);
+#endif
+#endif
+}
+
+#define get_mm_counter(mm, member) gator_get_mm_counter(mm, member)
+
+#endif
+
+static int gator_events_meminfo_read_proc(long long **buffer, struct task_struct *task)
+{
+	struct mm_struct *mm;
+	u64 share = 0;
+	int i;
+	long long value;
+	int len = 0;
+	int cpu = get_physical_cpu();
+	long long *buf = per_cpu(proc_buffer, cpu);
+
+	if (!proc_global_enabled)
+		return 0;
+
+	/* Collect the memory stats of the process instead of the thread */
+	if (task->group_leader != NULL)
+		task = task->group_leader;
+
+	/* get_task_mm/mmput is not needed in this context because the task and it's mm are required as part of the sched_switch */
+	mm = task->mm;
+	if (mm == NULL)
+		return 0;
+
+	/* Derived from task_statm in fs/proc/task_mmu.c */
+	if (meminfo_enabled[MEMINFO_MEMUSED] || proc_enabled[PROC_SHARE]) {
+		share = get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+							   file_rss
+#else
+							   MM_FILEPAGES
+#endif
+							   );
+	}
+
+	/* key of 1 indicates a pid */
+	buf[len++] = 1;
+	buf[len++] = task->pid;
+
+	for (i = 0; i < PROC_COUNT; ++i) {
+		if (proc_enabled[i]) {
+			switch (i) {
+			case PROC_SIZE:
+				value = mm->total_vm;
+				break;
+			case PROC_SHARE:
+				value = share;
+				break;
+			case PROC_TEXT:
+				value = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT;
+				break;
+			case PROC_DATA:
+				value = mm->total_vm - mm->shared_vm;
+				break;
+			}
+
+			buf[len++] = proc_keys[i];
+			buf[len++] = value * PAGE_SIZE;
+		}
+	}
+
+	if (meminfo_enabled[MEMINFO_MEMUSED]) {
+		value = share + get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+									   anon_rss
+#else
+									   MM_ANONPAGES
+#endif
+									   );
+		/* Send resident for this pid */
+		buf[len++] = meminfo_keys[MEMINFO_MEMUSED];
+		buf[len++] = value * PAGE_SIZE;
+	}
+
+	/* Clear pid */
+	buf[len++] = 1;
+	buf[len++] = 0;
+
+	if (buffer)
+		*buffer = buf;
+
+	return len;
+}
+
+static struct gator_interface gator_events_meminfo_interface = {
+	.create_files = gator_events_meminfo_create_files,
+	.start = gator_events_meminfo_start,
+	.stop = gator_events_meminfo_stop,
+	.read64 = gator_events_meminfo_read,
+	.read_proc = gator_events_meminfo_read_proc,
+};
+
+int gator_events_meminfo_init(void)
+{
+	int i;
+
+	meminfo_global_enabled = 0;
+	for (i = 0; i < MEMINFO_TOTAL; i++) {
+		meminfo_enabled[i] = 0;
+		meminfo_keys[i] = gator_events_get_key();
+	}
+
+	proc_global_enabled = 0;
+	for (i = 0; i < PROC_COUNT; ++i) {
+		proc_enabled[i] = 0;
+		proc_keys[i] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_meminfo_interface);
+}
diff --git a/drivers/gator/gator_events_mmapped.c b/drivers/gator/gator_events_mmapped.c
new file mode 100644
index 000000000000..6b2af995ed41
--- /dev/null
+++ b/drivers/gator/gator_events_mmapped.c
@@ -0,0 +1,209 @@
+/*
+ * Example events provider
+ *
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Similar entries to those below must be present in the events.xml file.
+ * To add them to the events.xml, create an events-mmap.xml with the
+ * following contents and rebuild gatord:
+ *
+ * <category name="mmapped">
+ *   <event counter="mmapped_cnt0" title="Simulated1" name="Sine" display="maximum" class="absolute" description="Sort-of-sine"/>
+ *   <event counter="mmapped_cnt1" title="Simulated2" name="Triangle" display="maximum" class="absolute" description="Triangular wave"/>
+ *   <event counter="mmapped_cnt2" title="Simulated3" name="PWM" display="maximum" class="absolute" description="PWM Signal"/>
+ * </category>
+ *
+ * When adding custom events, be sure to do the following:
+ * - add any needed .c files to the gator driver Makefile
+ * - call gator_events_install in the events init function
+ * - add the init function to GATOR_EVENTS_LIST in gator_main.c
+ * - add a new events-*.xml file to the gator daemon and rebuild
+ *
+ * Troubleshooting:
+ * - verify the new events are part of events.xml, which is created when building the daemon
+ * - verify the new events exist at /dev/gator/events/ once gatord is launched
+ * - verify the counter name in the XML matches the name at /dev/gator/events
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ratelimit.h>
+
+#include "gator.h"
+
+#define MMAPPED_COUNTERS_NUM 3
+
+static int mmapped_global_enabled;
+
+static struct {
+	unsigned long enabled;
+	unsigned long key;
+} mmapped_counters[MMAPPED_COUNTERS_NUM];
+
+static int mmapped_buffer[MMAPPED_COUNTERS_NUM * 2];
+
+static s64 prev_time;
+
+/* Adds mmapped_cntX directories and enabled, event, and key files to /dev/gator/events */
+static int gator_events_mmapped_create_files(struct super_block *sb,
+					     struct dentry *root)
+{
+	int i;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		char buf[16];
+		struct dentry *dir;
+
+		snprintf(buf, sizeof(buf), "mmapped_cnt%d", i);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (WARN_ON(!dir))
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled",
+				     &mmapped_counters[i].enabled);
+		gatorfs_create_ro_ulong(sb, dir, "key",
+					&mmapped_counters[i].key);
+	}
+
+	return 0;
+}
+
+static int gator_events_mmapped_start(void)
+{
+	int i;
+	struct timespec ts;
+
+	getnstimeofday(&ts);
+	prev_time = timespec_to_ns(&ts);
+
+	mmapped_global_enabled = 0;
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		if (mmapped_counters[i].enabled) {
+			mmapped_global_enabled = 1;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static void gator_events_mmapped_stop(void)
+{
+}
+
+/* This function "simulates" counters, generating values of fancy
+ * functions like sine or triangle... */
+static int mmapped_simulate(int counter, int delta_in_us)
+{
+	int result = 0;
+
+	switch (counter) {
+	case 0:		/* sort-of-sine */
+		{
+			static int t;
+			int x;
+
+			t += delta_in_us;
+			if (t > 2048000)
+				t = 0;
+
+			if (t % 1024000 < 512000)
+				x = 512000 - (t % 512000);
+			else
+				x = t % 512000;
+
+			result = 32 * x / 512000;
+			result = result * result;
+
+			if (t < 1024000)
+				result = 1922 - result;
+		}
+		break;
+	case 1:		/* triangle */
+		{
+			static int v, d = 1;
+
+			v = v + d * delta_in_us;
+			if (v < 0) {
+				v = 0;
+				d = 1;
+			} else if (v > 1000000) {
+				v = 1000000;
+				d = -1;
+			}
+
+			result = v;
+		}
+		break;
+	case 2:		/* PWM signal */
+		{
+			static int dc, x, t;
+
+			t += delta_in_us;
+			if (t > 1000000)
+				t = 0;
+			if (x / 1000000 != (x + delta_in_us) / 1000000)
+				dc = (dc + 100000) % 1000000;
+			x += delta_in_us;
+
+			result = t < dc ? 0 : 10;
+		}
+		break;
+	}
+
+	return result;
+}
+
+static int gator_events_mmapped_read(int **buffer, bool sched_switch)
+{
+	int i;
+	int len = 0;
+	int delta_in_us;
+	struct timespec ts;
+	s64 time;
+
+	/* System wide counters - read from one core only */
+	if (!on_primary_core() || !mmapped_global_enabled)
+		return 0;
+
+	getnstimeofday(&ts);
+	time = timespec_to_ns(&ts);
+	delta_in_us = (int)(time - prev_time) / 1000;
+	prev_time = time;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		if (mmapped_counters[i].enabled) {
+			mmapped_buffer[len++] = mmapped_counters[i].key;
+			mmapped_buffer[len++] =
+			    mmapped_simulate(i, delta_in_us);
+		}
+	}
+
+	if (buffer)
+		*buffer = mmapped_buffer;
+
+	return len;
+}
+
+static struct gator_interface gator_events_mmapped_interface = {
+	.create_files = gator_events_mmapped_create_files,
+	.start = gator_events_mmapped_start,
+	.stop = gator_events_mmapped_stop,
+	.read = gator_events_mmapped_read,
+};
+
+/* Must not be static! */
+int __init gator_events_mmapped_init(void)
+{
+	int i;
+
+	for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+		mmapped_counters[i].enabled = 0;
+		mmapped_counters[i].key = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_mmapped_interface);
+}
diff --git a/drivers/gator/gator_events_net.c b/drivers/gator/gator_events_net.c
new file mode 100644
index 000000000000..d21b4db7b77c
--- /dev/null
+++ b/drivers/gator/gator_events_net.c
@@ -0,0 +1,172 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <linux/netdevice.h>
+#include <linux/hardirq.h>
+
+#define NETRX		0
+#define NETTX		1
+#define TOTALNET	2
+
+static ulong netrx_enabled;
+static ulong nettx_enabled;
+static ulong netrx_key;
+static ulong nettx_key;
+static int rx_total, tx_total;
+static ulong netPrev[TOTALNET];
+static int netGet[TOTALNET * 4];
+
+static struct timer_list net_wake_up_timer;
+
+/* Must be run in process context as the kernel function dev_get_stats() can sleep */
+static void get_network_stats(struct work_struct *wsptr)
+{
+	int rx = 0, tx = 0;
+	struct net_device *dev;
+
+	for_each_netdev(&init_net, dev) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+		const struct net_device_stats *stats = dev_get_stats(dev);
+#else
+		struct rtnl_link_stats64 temp;
+		const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
+#endif
+		rx += stats->rx_bytes;
+		tx += stats->tx_bytes;
+	}
+	rx_total = rx;
+	tx_total = tx;
+}
+
+DECLARE_WORK(wq_get_stats, get_network_stats);
+
+static void net_wake_up_handler(unsigned long unused_data)
+{
+	/* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+	schedule_work(&wq_get_stats);
+}
+
+static void calculate_delta(int *rx, int *tx)
+{
+	int rx_calc, tx_calc;
+
+	rx_calc = (int)(rx_total - netPrev[NETRX]);
+	if (rx_calc < 0)
+		rx_calc = 0;
+	netPrev[NETRX] += rx_calc;
+
+	tx_calc = (int)(tx_total - netPrev[NETTX]);
+	if (tx_calc < 0)
+		tx_calc = 0;
+	netPrev[NETTX] += tx_calc;
+
+	*rx = rx_calc;
+	*tx = tx_calc;
+}
+
+static int gator_events_net_create_files(struct super_block *sb, struct dentry *root)
+{
+	/* Network counters are not currently supported in RT-Preempt full because mod_timer is used */
+#ifndef CONFIG_PREEMPT_RT_FULL
+	struct dentry *dir;
+
+	dir = gatorfs_mkdir(sb, root, "Linux_net_rx");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &netrx_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &netrx_key);
+
+	dir = gatorfs_mkdir(sb, root, "Linux_net_tx");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &nettx_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &nettx_key);
+#endif
+
+	return 0;
+}
+
+static int gator_events_net_start(void)
+{
+	get_network_stats(0);
+	netPrev[NETRX] = rx_total;
+	netPrev[NETTX] = tx_total;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+	setup_timer(&net_wake_up_timer, net_wake_up_handler, 0);
+#else
+	setup_deferrable_timer_on_stack(&net_wake_up_timer, net_wake_up_handler, 0);
+#endif
+	return 0;
+}
+
+static void gator_events_net_stop(void)
+{
+	del_timer_sync(&net_wake_up_timer);
+	netrx_enabled = 0;
+	nettx_enabled = 0;
+}
+
+static int gator_events_net_read(int **buffer, bool sched_switch)
+{
+	int len, rx_delta, tx_delta;
+	static int last_rx_delta, last_tx_delta;
+
+	if (!on_primary_core())
+		return 0;
+
+	if (!netrx_enabled && !nettx_enabled)
+		return 0;
+
+	mod_timer(&net_wake_up_timer, jiffies + 1);
+
+	calculate_delta(&rx_delta, &tx_delta);
+
+	len = 0;
+	if (netrx_enabled && last_rx_delta != rx_delta) {
+		last_rx_delta = rx_delta;
+		netGet[len++] = netrx_key;
+		/* indicates to Streamline that rx_delta bytes were transmitted now, not since the last message */
+		netGet[len++] = 0;
+		netGet[len++] = netrx_key;
+		netGet[len++] = rx_delta;
+	}
+
+	if (nettx_enabled && last_tx_delta != tx_delta) {
+		last_tx_delta = tx_delta;
+		netGet[len++] = nettx_key;
+		/* indicates to Streamline that tx_delta bytes were transmitted now, not since the last message */
+		netGet[len++] = 0;
+		netGet[len++] = nettx_key;
+		netGet[len++] = tx_delta;
+	}
+
+	if (buffer)
+		*buffer = netGet;
+
+	return len;
+}
+
+static struct gator_interface gator_events_net_interface = {
+	.create_files = gator_events_net_create_files,
+	.start = gator_events_net_start,
+	.stop = gator_events_net_stop,
+	.read = gator_events_net_read,
+};
+
+int gator_events_net_init(void)
+{
+	netrx_key = gator_events_get_key();
+	nettx_key = gator_events_get_key();
+
+	netrx_enabled = 0;
+	nettx_enabled = 0;
+
+	return gator_events_install(&gator_events_net_interface);
+}
diff --git a/drivers/gator/gator_events_perf_pmu.c b/drivers/gator/gator_events_perf_pmu.c
new file mode 100644
index 000000000000..47cf278e508b
--- /dev/null
+++ b/drivers/gator/gator_events_perf_pmu.c
@@ -0,0 +1,574 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_armvX.c is used for Linux 2.6.x */
+#if GATOR_PERF_PMU_SUPPORT
+
+#include <linux/io.h>
+#ifdef CONFIG_OF
+#include <linux/of_address.h>
+#endif
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+
+extern bool event_based_sampling;
+
+/* Maximum number of per-core counters - currently reserves enough space for two full hardware PMUs for big.LITTLE */
+#define CNTMAX 16
+#define CCI_400 4
+#define CCN_5XX 8
+/* Maximum number of uncore counters */
+/* + 1 for the cci-400 cycles counter */
+/* + 1 for the CCN-5xx cycles counter */
+#define UCCNT (CCI_400 + 1 + CCN_5XX + 1)
+
+/* Default to 0 if unable to probe the revision which was the previous behavior */
+#define DEFAULT_CCI_REVISION 0
+
+/* A gator_attr is needed for every counter */
+struct gator_attr {
+	/* Set once in gator_events_perf_pmu_*_init - the name of the event in the gatorfs */
+	char name[40];
+	/* Exposed in gatorfs - set by gatord to enable this counter */
+	unsigned long enabled;
+	/* Set once in gator_events_perf_pmu_*_init - the perf type to use, see perf_type_id in the perf_event.h header file. */
+	unsigned long type;
+	/* Exposed in gatorfs - set by gatord to select the event to collect */
+	unsigned long event;
+	/* Exposed in gatorfs - set by gatord with the sample period to use and enable EBS for this counter */
+	unsigned long count;
+	/* Exposed as read only in gatorfs - set once in __attr_init as the key to use in the APC data */
+	unsigned long key;
+};
+
+/* Per-core counter attributes */
+static struct gator_attr attrs[CNTMAX];
+/* Number of initialized per-core counters */
+static int attr_count;
+/* Uncore counter attributes */
+static struct gator_attr uc_attrs[UCCNT];
+/* Number of initialized uncore counters */
+static int uc_attr_count;
+
+struct gator_event {
+	int curr;
+	int prev;
+	int prev_delta;
+	bool zero;
+	struct perf_event *pevent;
+	struct perf_event_attr *pevent_attr;
+};
+
+static DEFINE_PER_CPU(struct gator_event[CNTMAX], events);
+static struct gator_event uc_events[UCCNT];
+static DEFINE_PER_CPU(int[(CNTMAX + UCCNT)*2], perf_cnt);
+
+static void gator_events_perf_pmu_stop(void);
+
+static int __create_files(struct super_block *sb, struct dentry *root, struct gator_attr *const attr)
+{
+	struct dentry *dir;
+
+	if (attr->name[0] == '\0')
+		return 0;
+	dir = gatorfs_mkdir(sb, root, attr->name);
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &attr->enabled);
+	gatorfs_create_ulong(sb, dir, "count", &attr->count);
+	gatorfs_create_ro_ulong(sb, dir, "key", &attr->key);
+	gatorfs_create_ulong(sb, dir, "event", &attr->event);
+
+	return 0;
+}
+
+static int gator_events_perf_pmu_create_files(struct super_block *sb, struct dentry *root)
+{
+	int cnt;
+
+	for (cnt = 0; cnt < attr_count; cnt++) {
+		if (__create_files(sb, root, &attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__create_files(sb, root, &uc_attrs[cnt]) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void ebs_overflow_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void ebs_overflow_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+	gator_backtrace_handler(regs);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void dummy_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void dummy_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+	/* Required as perf_event_create_kernel_counter() requires an overflow handler, even though all we do is poll */
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch);
+
+static int gator_events_perf_pmu_online(int **buffer, bool migrate)
+{
+	return gator_events_perf_pmu_read(buffer, false);
+}
+
+static void __online_dispatch(int cpu, bool migrate, struct gator_attr *const attr, struct gator_event *const event)
+{
+	perf_overflow_handler_t handler;
+
+	event->zero = true;
+
+	if (event->pevent != NULL || event->pevent_attr == 0 || migrate)
+		return;
+
+	if (attr->count > 0)
+		handler = ebs_overflow_handler;
+	else
+		handler = dummy_handler;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+	event->pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler);
+#else
+	event->pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler, 0);
+#endif
+	if (IS_ERR(event->pevent)) {
+		pr_debug("gator: unable to online a counter on cpu %d\n", cpu);
+		event->pevent = NULL;
+		return;
+	}
+
+	if (event->pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		pr_debug("gator: inactive counter on cpu %d\n", cpu);
+		perf_event_release_kernel(event->pevent);
+		event->pevent = NULL;
+		return;
+	}
+}
+
+static void gator_events_perf_pmu_online_dispatch(int cpu, bool migrate)
+{
+	int cnt;
+
+	cpu = pcpu_to_lcpu(cpu);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__online_dispatch(cpu, migrate, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__online_dispatch(cpu, migrate, &uc_attrs[cnt], &uc_events[cnt]);
+	}
+}
+
+static void __offline_dispatch(int cpu, struct gator_event *const event)
+{
+	struct perf_event *pe = NULL;
+
+	if (event->pevent) {
+		pe = event->pevent;
+		event->pevent = NULL;
+	}
+
+	if (pe)
+		perf_event_release_kernel(pe);
+}
+
+static void gator_events_perf_pmu_offline_dispatch(int cpu, bool migrate)
+{
+	int cnt;
+
+	if (migrate)
+		return;
+	cpu = pcpu_to_lcpu(cpu);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__offline_dispatch(cpu, &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__offline_dispatch(cpu, &uc_events[cnt]);
+	}
+}
+
+static int __check_ebs(struct gator_attr *const attr)
+{
+	if (attr->count > 0) {
+		if (!event_based_sampling) {
+			event_based_sampling = true;
+		} else {
+			pr_warning("gator: Only one ebs counter is allowed\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int __start(struct gator_attr *const attr, struct gator_event *const event)
+{
+	u32 size = sizeof(struct perf_event_attr);
+
+	event->pevent = NULL;
+	/* Skip disabled counters */
+	if (!attr->enabled)
+		return 0;
+
+	event->prev = 0;
+	event->curr = 0;
+	event->prev_delta = 0;
+	event->pevent_attr = kmalloc(size, GFP_KERNEL);
+	if (!event->pevent_attr) {
+		gator_events_perf_pmu_stop();
+		return -1;
+	}
+
+	memset(event->pevent_attr, 0, size);
+	event->pevent_attr->type = attr->type;
+	event->pevent_attr->size = size;
+	event->pevent_attr->config = attr->event;
+	event->pevent_attr->sample_period = attr->count;
+	event->pevent_attr->pinned = 1;
+
+	return 0;
+}
+
+static int gator_events_perf_pmu_start(void)
+{
+	int cnt, cpu;
+
+	event_based_sampling = false;
+	for (cnt = 0; cnt < attr_count; cnt++) {
+		if (__check_ebs(&attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__check_ebs(&uc_attrs[cnt]) != 0)
+			return -1;
+	}
+
+	for_each_present_cpu(cpu) {
+		for (cnt = 0; cnt < attr_count; cnt++) {
+			if (__start(&attrs[cnt], &per_cpu(events, cpu)[cnt]) != 0)
+				return -1;
+		}
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++) {
+		if (__start(&uc_attrs[cnt], &uc_events[cnt]) != 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static void __event_stop(struct gator_event *const event)
+{
+	kfree(event->pevent_attr);
+	event->pevent_attr = NULL;
+}
+
+static void __attr_stop(struct gator_attr *const attr)
+{
+	attr->enabled = 0;
+	attr->event = 0;
+	attr->count = 0;
+}
+
+static void gator_events_perf_pmu_stop(void)
+{
+	unsigned int cnt, cpu;
+
+	for_each_present_cpu(cpu) {
+		for (cnt = 0; cnt < attr_count; cnt++)
+			__event_stop(&per_cpu(events, cpu)[cnt]);
+	}
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++)
+		__event_stop(&uc_events[cnt]);
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__attr_stop(&attrs[cnt]);
+
+	for (cnt = 0; cnt < uc_attr_count; cnt++)
+		__attr_stop(&uc_attrs[cnt]);
+}
+
+static void __read(int *const len, int cpu, struct gator_attr *const attr, struct gator_event *const event)
+{
+	int delta;
+	struct perf_event *const ev = event->pevent;
+
+	if (ev != NULL && ev->state == PERF_EVENT_STATE_ACTIVE) {
+		/* After creating the perf counter in __online_dispatch, there
+		 * is a race condition between gator_events_perf_pmu_online and
+		 * gator_events_perf_pmu_read. So have
+		 * gator_events_perf_pmu_online call gator_events_perf_pmu_read
+		 * and in __read check to see if it's the first call after
+		 * __online_dispatch and if so, run the online code.
+		 */
+		if (event->zero) {
+			ev->pmu->read(ev);
+			event->prev = event->curr = local64_read(&ev->count);
+			event->prev_delta = 0;
+			per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+			per_cpu(perf_cnt, cpu)[(*len)++] = 0;
+			event->zero = false;
+		} else {
+			ev->pmu->read(ev);
+			event->curr = local64_read(&ev->count);
+			delta = event->curr - event->prev;
+			if (delta != 0 || delta != event->prev_delta) {
+				event->prev_delta = delta;
+				event->prev = event->curr;
+				per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+				if (delta < 0)
+					delta *= -1;
+				per_cpu(perf_cnt, cpu)[(*len)++] = delta;
+			}
+		}
+	}
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	const int cpu = get_logical_cpu();
+
+	for (cnt = 0; cnt < attr_count; cnt++)
+		__read(&len, cpu, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+	if (cpu == 0) {
+		for (cnt = 0; cnt < uc_attr_count; cnt++)
+			__read(&len, cpu, &uc_attrs[cnt], &uc_events[cnt]);
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perf_cnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_perf_pmu_interface = {
+	.create_files = gator_events_perf_pmu_create_files,
+	.start = gator_events_perf_pmu_start,
+	.stop = gator_events_perf_pmu_stop,
+	.online = gator_events_perf_pmu_online,
+	.online_dispatch = gator_events_perf_pmu_online_dispatch,
+	.offline_dispatch = gator_events_perf_pmu_offline_dispatch,
+	.read = gator_events_perf_pmu_read,
+};
+
+static void __attr_init(struct gator_attr *const attr)
+{
+	attr->name[0] = '\0';
+	attr->enabled = 0;
+	attr->type = 0;
+	attr->event = 0;
+	attr->count = 0;
+	attr->key = gator_events_get_key();
+}
+
+#ifdef CONFIG_OF
+
+static const struct of_device_id arm_cci_matches[] = {
+	{.compatible = "arm,cci-400" },
+	{},
+};
+
+static int probe_cci_revision(void)
+{
+	struct device_node *np;
+	struct resource res;
+	void __iomem *cci_ctrl_base;
+	int rev;
+	int ret = DEFAULT_CCI_REVISION;
+
+	np = of_find_matching_node(NULL, arm_cci_matches);
+	if (!np)
+		return ret;
+
+	if (of_address_to_resource(np, 0, &res))
+		goto node_put;
+
+	cci_ctrl_base = ioremap(res.start, resource_size(&res));
+
+	rev = (readl_relaxed(cci_ctrl_base + 0xfe8) >> 4) & 0xf;
+
+	if (rev <= 4)
+		ret = 0;
+	else if (rev <= 6)
+		ret = 1;
+
+	iounmap(cci_ctrl_base);
+
+ node_put:
+	of_node_put(np);
+
+	return ret;
+}
+
+#else
+
+static int probe_cci_revision(void)
+{
+	return DEFAULT_CCI_REVISION;
+}
+
+#endif
+
+static void gator_events_perf_pmu_uncore_init(const char *const name, const int type, const int count)
+{
+	int cnt;
+
+	snprintf(uc_attrs[uc_attr_count].name, sizeof(uc_attrs[uc_attr_count].name), "%s_ccnt", name);
+	uc_attrs[uc_attr_count].type = type;
+	++uc_attr_count;
+
+	for (cnt = 0; cnt < count; ++cnt, ++uc_attr_count) {
+		struct gator_attr *const attr = &uc_attrs[uc_attr_count];
+
+		snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", name, cnt);
+		attr->type = type;
+	}
+}
+
+static void gator_events_perf_pmu_cci_init(const int type)
+{
+	const char *cci_name;
+
+	switch (probe_cci_revision()) {
+	case 0:
+		cci_name = "CCI_400";
+		break;
+	case 1:
+		cci_name = "CCI_400-r1";
+		break;
+	default:
+		pr_debug("gator: unrecognized cci-400 revision\n");
+		return;
+	}
+
+	gator_events_perf_pmu_uncore_init(cci_name, type, CCI_400);
+}
+
+static void gator_events_perf_pmu_cpu_init(const struct gator_cpu *const gator_cpu, const int type)
+{
+	int cnt;
+
+	snprintf(attrs[attr_count].name, sizeof(attrs[attr_count].name), "%s_ccnt", gator_cpu->pmnc_name);
+	attrs[attr_count].type = type;
+	++attr_count;
+
+	for (cnt = 0; cnt < gator_cpu->pmnc_counters; ++cnt, ++attr_count) {
+		struct gator_attr *const attr = &attrs[attr_count];
+
+		snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", gator_cpu->pmnc_name, cnt);
+		attr->type = type;
+	}
+}
+
+int gator_events_perf_pmu_init(void)
+{
+	struct perf_event_attr pea;
+	struct perf_event *pe;
+	const struct gator_cpu *gator_cpu;
+	int type;
+	int cpu;
+	int cnt;
+	bool found_cpu = false;
+
+	for (cnt = 0; cnt < CNTMAX; cnt++)
+		__attr_init(&attrs[cnt]);
+	for (cnt = 0; cnt < UCCNT; cnt++)
+		__attr_init(&uc_attrs[cnt]);
+
+	memset(&pea, 0, sizeof(pea));
+	pea.size = sizeof(pea);
+	pea.config = 0xFF;
+	attr_count = 0;
+	uc_attr_count = 0;
+	for (type = PERF_TYPE_MAX; type < 0x20; ++type) {
+		pea.type = type;
+
+		/* A particular PMU may work on some but not all cores, so try on each core */
+		pe = NULL;
+		for_each_present_cpu(cpu) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+			pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler);
+#else
+			pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler, 0);
+#endif
+			if (!IS_ERR(pe))
+				break;
+		}
+		/* Assume that valid PMUs are contiguous */
+		if (IS_ERR(pe)) {
+			pea.config = 0xff00;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+			pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler);
+#else
+			pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler, 0);
+#endif
+			if (IS_ERR(pe))
+				break;
+		}
+
+		if (pe->pmu != NULL && type == pe->pmu->type) {
+			if (strcmp("CCI", pe->pmu->name) == 0 || strcmp("CCI_400", pe->pmu->name) == 0 || strcmp("CCI_400-r1", pe->pmu->name) == 0) {
+				gator_events_perf_pmu_cci_init(type);
+			} else if (strcmp("ccn", pe->pmu->name) == 0) {
+				gator_events_perf_pmu_uncore_init("ARM_CCN_5XX", type, CCN_5XX);
+			} else if ((gator_cpu = gator_find_cpu_by_pmu_name(pe->pmu->name)) != NULL) {
+				found_cpu = true;
+				gator_events_perf_pmu_cpu_init(gator_cpu, type);
+			}
+			/* Initialize gator_attrs for dynamic PMUs here */
+		}
+
+		perf_event_release_kernel(pe);
+	}
+
+	if (!found_cpu) {
+		const struct gator_cpu *const gator_cpu = gator_find_cpu_by_cpuid(gator_cpuid());
+
+		if (gator_cpu == NULL)
+			return -1;
+		gator_events_perf_pmu_cpu_init(gator_cpu, PERF_TYPE_RAW);
+	}
+
+	/* Initialize gator_attrs for non-dynamic PMUs here */
+
+	if (attr_count > CNTMAX) {
+		pr_err("gator: Too many perf counters\n");
+		return -1;
+	}
+
+	if (uc_attr_count > UCCNT) {
+		pr_err("gator: Too many perf uncore counters\n");
+		return -1;
+	}
+
+	return gator_events_install(&gator_events_perf_pmu_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_sched.c b/drivers/gator/gator_events_sched.c
new file mode 100644
index 000000000000..637107d6af1d
--- /dev/null
+++ b/drivers/gator/gator_events_sched.c
@@ -0,0 +1,113 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/sched.h>
+
+#define SCHED_SWITCH	0
+#define SCHED_TOTAL		(SCHED_SWITCH+1)
+
+static ulong sched_switch_enabled;
+static ulong sched_switch_key;
+static DEFINE_PER_CPU(int[SCHED_TOTAL], schedCnt);
+static DEFINE_PER_CPU(int[SCHED_TOTAL * 2], schedGet);
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+	unsigned long flags;
+
+	/* disable interrupts to synchronize with gator_events_sched_read()
+	 * spinlocks not needed since percpu buffers are used
+	 */
+	local_irq_save(flags);
+	per_cpu(schedCnt, get_physical_cpu())[SCHED_SWITCH]++;
+	local_irq_restore(flags);
+}
+
+static int gator_events_sched_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* switch */
+	dir = gatorfs_mkdir(sb, root, "Linux_sched_switch");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &sched_switch_enabled);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_switch_key);
+
+	return 0;
+}
+
+static int gator_events_sched_start(void)
+{
+	/* register tracepoints */
+	if (sched_switch_enabled)
+		if (GATOR_REGISTER_TRACE(sched_switch))
+			goto sched_switch_exit;
+	pr_debug("gator: registered scheduler event tracepoints\n");
+
+	return 0;
+
+	/* unregister tracepoints on error */
+sched_switch_exit:
+	pr_err("gator: scheduler event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_events_sched_stop(void)
+{
+	if (sched_switch_enabled)
+		GATOR_UNREGISTER_TRACE(sched_switch);
+	pr_debug("gator: unregistered scheduler event tracepoints\n");
+
+	sched_switch_enabled = 0;
+}
+
+static int gator_events_sched_read(int **buffer, bool sched_switch)
+{
+	unsigned long flags;
+	int len, value;
+	int cpu = get_physical_cpu();
+
+	len = 0;
+	if (sched_switch_enabled) {
+		local_irq_save(flags);
+		value = per_cpu(schedCnt, cpu)[SCHED_SWITCH];
+		per_cpu(schedCnt, cpu)[SCHED_SWITCH] = 0;
+		local_irq_restore(flags);
+		per_cpu(schedGet, cpu)[len++] = sched_switch_key;
+		per_cpu(schedGet, cpu)[len++] = value;
+	}
+
+	if (buffer)
+		*buffer = per_cpu(schedGet, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_sched_interface = {
+	.create_files = gator_events_sched_create_files,
+	.start = gator_events_sched_start,
+	.stop = gator_events_sched_stop,
+	.read = gator_events_sched_read,
+};
+
+int gator_events_sched_init(void)
+{
+	sched_switch_enabled = 0;
+
+	sched_switch_key = gator_events_get_key();
+
+	return gator_events_install(&gator_events_sched_interface);
+}
diff --git a/drivers/gator/gator_events_scorpion.c b/drivers/gator/gator_events_scorpion.c
new file mode 100644
index 000000000000..49219362db09
--- /dev/null
+++ b/drivers/gator/gator_events_scorpion.c
@@ -0,0 +1,674 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E		(1 << 0)	/* Enable all counters */
+#define PMNC_P		(1 << 1)	/* Reset all counters */
+#define PMNC_C		(1 << 2)	/* Cycle counter reset */
+#define PMNC_D		(1 << 3)	/* CCNT counts every 64th cpu cycle */
+#define PMNC_X		(1 << 4)	/* Export to ETM */
+#define PMNC_DP		(1 << 5)	/* Disable CCNT if non-invasive debug */
+#define	PMNC_MASK	0x3f	/* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG	(1 << 31)
+
+#define CCNT		0
+#define CNT0		1
+#define CNTMAX		(4+1)
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+enum scorpion_perf_types {
+	SCORPION_ICACHE_EXPL_INV = 0x4c,
+	SCORPION_ICACHE_MISS = 0x4d,
+	SCORPION_ICACHE_ACCESS = 0x4e,
+	SCORPION_ICACHE_CACHEREQ_L2 = 0x4f,
+	SCORPION_ICACHE_NOCACHE_L2 = 0x50,
+	SCORPION_HIQUP_NOPED = 0x51,
+	SCORPION_DATA_ABORT = 0x52,
+	SCORPION_IRQ = 0x53,
+	SCORPION_FIQ = 0x54,
+	SCORPION_ALL_EXCPT = 0x55,
+	SCORPION_UNDEF = 0x56,
+	SCORPION_SVC = 0x57,
+	SCORPION_SMC = 0x58,
+	SCORPION_PREFETCH_ABORT = 0x59,
+	SCORPION_INDEX_CHECK = 0x5a,
+	SCORPION_NULL_CHECK = 0x5b,
+	SCORPION_EXPL_ICIALLU = 0x5c,
+	SCORPION_IMPL_ICIALLU = 0x5d,
+	SCORPION_NONICIALLU_BTAC_INV = 0x5e,
+	SCORPION_ICIMVAU_IMPL_ICIALLU = 0x5f,
+	SCORPION_SPIPE_ONLY_CYCLES = 0x60,
+	SCORPION_XPIPE_ONLY_CYCLES = 0x61,
+	SCORPION_DUAL_CYCLES = 0x62,
+	SCORPION_DISPATCH_ANY_CYCLES = 0x63,
+	SCORPION_FIFO_FULLBLK_CMT = 0x64,
+	SCORPION_FAIL_COND_INST = 0x65,
+	SCORPION_PASS_COND_INST = 0x66,
+	SCORPION_ALLOW_VU_CLK = 0x67,
+	SCORPION_VU_IDLE = 0x68,
+	SCORPION_ALLOW_L2_CLK = 0x69,
+	SCORPION_L2_IDLE = 0x6a,
+	SCORPION_DTLB_IMPL_INV_SCTLR_DACR = 0x6b,
+	SCORPION_DTLB_EXPL_INV = 0x6c,
+	SCORPION_DTLB_MISS = 0x6d,
+	SCORPION_DTLB_ACCESS = 0x6e,
+	SCORPION_ITLB_MISS = 0x6f,
+	SCORPION_ITLB_IMPL_INV = 0x70,
+	SCORPION_ITLB_EXPL_INV = 0x71,
+	SCORPION_UTLB_D_MISS = 0x72,
+	SCORPION_UTLB_D_ACCESS = 0x73,
+	SCORPION_UTLB_I_MISS = 0x74,
+	SCORPION_UTLB_I_ACCESS = 0x75,
+	SCORPION_UTLB_INV_ASID = 0x76,
+	SCORPION_UTLB_INV_MVA = 0x77,
+	SCORPION_UTLB_INV_ALL = 0x78,
+	SCORPION_S2_HOLD_RDQ_UNAVAIL = 0x79,
+	SCORPION_S2_HOLD = 0x7a,
+	SCORPION_S2_HOLD_DEV_OP = 0x7b,
+	SCORPION_S2_HOLD_ORDER = 0x7c,
+	SCORPION_S2_HOLD_BARRIER = 0x7d,
+	SCORPION_VIU_DUAL_CYCLE = 0x7e,
+	SCORPION_VIU_SINGLE_CYCLE = 0x7f,
+	SCORPION_VX_PIPE_WAR_STALL_CYCLES = 0x80,
+	SCORPION_VX_PIPE_WAW_STALL_CYCLES = 0x81,
+	SCORPION_VX_PIPE_RAW_STALL_CYCLES = 0x82,
+	SCORPION_VX_PIPE_LOAD_USE_STALL = 0x83,
+	SCORPION_VS_PIPE_WAR_STALL_CYCLES = 0x84,
+	SCORPION_VS_PIPE_WAW_STALL_CYCLES = 0x85,
+	SCORPION_VS_PIPE_RAW_STALL_CYCLES = 0x86,
+	SCORPION_EXCEPTIONS_INV_OPERATION = 0x87,
+	SCORPION_EXCEPTIONS_DIV_BY_ZERO = 0x88,
+	SCORPION_COND_INST_FAIL_VX_PIPE = 0x89,
+	SCORPION_COND_INST_FAIL_VS_PIPE = 0x8a,
+	SCORPION_EXCEPTIONS_OVERFLOW = 0x8b,
+	SCORPION_EXCEPTIONS_UNDERFLOW = 0x8c,
+	SCORPION_EXCEPTIONS_DENORM = 0x8d,
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+	SCORPIONMP_NUM_BARRIERS = 0x8e,
+	SCORPIONMP_BARRIER_CYCLES = 0x8f,
+#else
+	SCORPION_BANK_AB_HIT = 0x8e,
+	SCORPION_BANK_AB_ACCESS = 0x8f,
+	SCORPION_BANK_CD_HIT = 0x90,
+	SCORPION_BANK_CD_ACCESS = 0x91,
+	SCORPION_BANK_AB_DSIDE_HIT = 0x92,
+	SCORPION_BANK_AB_DSIDE_ACCESS = 0x93,
+	SCORPION_BANK_CD_DSIDE_HIT = 0x94,
+	SCORPION_BANK_CD_DSIDE_ACCESS = 0x95,
+	SCORPION_BANK_AB_ISIDE_HIT = 0x96,
+	SCORPION_BANK_AB_ISIDE_ACCESS = 0x97,
+	SCORPION_BANK_CD_ISIDE_HIT = 0x98,
+	SCORPION_BANK_CD_ISIDE_ACCESS = 0x99,
+	SCORPION_ISIDE_RD_WAIT = 0x9a,
+	SCORPION_DSIDE_RD_WAIT = 0x9b,
+	SCORPION_BANK_BYPASS_WRITE = 0x9c,
+	SCORPION_BANK_AB_NON_CASTOUT = 0x9d,
+	SCORPION_BANK_AB_L2_CASTOUT = 0x9e,
+	SCORPION_BANK_CD_NON_CASTOUT = 0x9f,
+	SCORPION_BANK_CD_L2_CASTOUT = 0xa0,
+#endif
+	MSM_MAX_EVT
+};
+
+struct scorp_evt {
+	u32 evt_type;
+	u32 val;
+	u8 grp;
+	u32 evt_type_act;
+};
+
+static const struct scorp_evt sc_evt[] = {
+	{SCORPION_ICACHE_EXPL_INV, 0x80000500, 0, 0x4d},
+	{SCORPION_ICACHE_MISS, 0x80050000, 0, 0x4e},
+	{SCORPION_ICACHE_ACCESS, 0x85000000, 0, 0x4f},
+	{SCORPION_ICACHE_CACHEREQ_L2, 0x86000000, 0, 0x4f},
+	{SCORPION_ICACHE_NOCACHE_L2, 0x87000000, 0, 0x4f},
+	{SCORPION_HIQUP_NOPED, 0x80080000, 0, 0x4e},
+	{SCORPION_DATA_ABORT, 0x8000000a, 0, 0x4c},
+	{SCORPION_IRQ, 0x80000a00, 0, 0x4d},
+	{SCORPION_FIQ, 0x800a0000, 0, 0x4e},
+	{SCORPION_ALL_EXCPT, 0x8a000000, 0, 0x4f},
+	{SCORPION_UNDEF, 0x8000000b, 0, 0x4c},
+	{SCORPION_SVC, 0x80000b00, 0, 0x4d},
+	{SCORPION_SMC, 0x800b0000, 0, 0x4e},
+	{SCORPION_PREFETCH_ABORT, 0x8b000000, 0, 0x4f},
+	{SCORPION_INDEX_CHECK, 0x8000000c, 0, 0x4c},
+	{SCORPION_NULL_CHECK, 0x80000c00, 0, 0x4d},
+	{SCORPION_EXPL_ICIALLU, 0x8000000d, 0, 0x4c},
+	{SCORPION_IMPL_ICIALLU, 0x80000d00, 0, 0x4d},
+	{SCORPION_NONICIALLU_BTAC_INV, 0x800d0000, 0, 0x4e},
+	{SCORPION_ICIMVAU_IMPL_ICIALLU, 0x8d000000, 0, 0x4f},
+
+	{SCORPION_SPIPE_ONLY_CYCLES, 0x80000600, 1, 0x51},
+	{SCORPION_XPIPE_ONLY_CYCLES, 0x80060000, 1, 0x52},
+	{SCORPION_DUAL_CYCLES, 0x86000000, 1, 0x53},
+	{SCORPION_DISPATCH_ANY_CYCLES, 0x89000000, 1, 0x53},
+	{SCORPION_FIFO_FULLBLK_CMT, 0x8000000d, 1, 0x50},
+	{SCORPION_FAIL_COND_INST, 0x800d0000, 1, 0x52},
+	{SCORPION_PASS_COND_INST, 0x8d000000, 1, 0x53},
+	{SCORPION_ALLOW_VU_CLK, 0x8000000e, 1, 0x50},
+	{SCORPION_VU_IDLE, 0x80000e00, 1, 0x51},
+	{SCORPION_ALLOW_L2_CLK, 0x800e0000, 1, 0x52},
+	{SCORPION_L2_IDLE, 0x8e000000, 1, 0x53},
+
+	{SCORPION_DTLB_IMPL_INV_SCTLR_DACR, 0x80000001, 2, 0x54},
+	{SCORPION_DTLB_EXPL_INV, 0x80000100, 2, 0x55},
+	{SCORPION_DTLB_MISS, 0x80010000, 2, 0x56},
+	{SCORPION_DTLB_ACCESS, 0x81000000, 2, 0x57},
+	{SCORPION_ITLB_MISS, 0x80000200, 2, 0x55},
+	{SCORPION_ITLB_IMPL_INV, 0x80020000, 2, 0x56},
+	{SCORPION_ITLB_EXPL_INV, 0x82000000, 2, 0x57},
+	{SCORPION_UTLB_D_MISS, 0x80000003, 2, 0x54},
+	{SCORPION_UTLB_D_ACCESS, 0x80000300, 2, 0x55},
+	{SCORPION_UTLB_I_MISS, 0x80030000, 2, 0x56},
+	{SCORPION_UTLB_I_ACCESS, 0x83000000, 2, 0x57},
+	{SCORPION_UTLB_INV_ASID, 0x80000400, 2, 0x55},
+	{SCORPION_UTLB_INV_MVA, 0x80040000, 2, 0x56},
+	{SCORPION_UTLB_INV_ALL, 0x84000000, 2, 0x57},
+	{SCORPION_S2_HOLD_RDQ_UNAVAIL, 0x80000800, 2, 0x55},
+	{SCORPION_S2_HOLD, 0x88000000, 2, 0x57},
+	{SCORPION_S2_HOLD_DEV_OP, 0x80000900, 2, 0x55},
+	{SCORPION_S2_HOLD_ORDER, 0x80090000, 2, 0x56},
+	{SCORPION_S2_HOLD_BARRIER, 0x89000000, 2, 0x57},
+
+	{SCORPION_VIU_DUAL_CYCLE, 0x80000001, 4, 0x5c},
+	{SCORPION_VIU_SINGLE_CYCLE, 0x80000100, 4, 0x5d},
+	{SCORPION_VX_PIPE_WAR_STALL_CYCLES, 0x80000005, 4, 0x5c},
+	{SCORPION_VX_PIPE_WAW_STALL_CYCLES, 0x80000500, 4, 0x5d},
+	{SCORPION_VX_PIPE_RAW_STALL_CYCLES, 0x80050000, 4, 0x5e},
+	{SCORPION_VX_PIPE_LOAD_USE_STALL, 0x80000007, 4, 0x5c},
+	{SCORPION_VS_PIPE_WAR_STALL_CYCLES, 0x80000008, 4, 0x5c},
+	{SCORPION_VS_PIPE_WAW_STALL_CYCLES, 0x80000800, 4, 0x5d},
+	{SCORPION_VS_PIPE_RAW_STALL_CYCLES, 0x80080000, 4, 0x5e},
+	{SCORPION_EXCEPTIONS_INV_OPERATION, 0x8000000b, 4, 0x5c},
+	{SCORPION_EXCEPTIONS_DIV_BY_ZERO, 0x80000b00, 4, 0x5d},
+	{SCORPION_COND_INST_FAIL_VX_PIPE, 0x800b0000, 4, 0x5e},
+	{SCORPION_COND_INST_FAIL_VS_PIPE, 0x8b000000, 4, 0x5f},
+	{SCORPION_EXCEPTIONS_OVERFLOW, 0x8000000c, 4, 0x5c},
+	{SCORPION_EXCEPTIONS_UNDERFLOW, 0x80000c00, 4, 0x5d},
+	{SCORPION_EXCEPTIONS_DENORM, 0x8c000000, 4, 0x5f},
+
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+	{SCORPIONMP_NUM_BARRIERS, 0x80000e00, 3, 0x59},
+	{SCORPIONMP_BARRIER_CYCLES, 0x800e0000, 3, 0x5a},
+#else
+	{SCORPION_BANK_AB_HIT, 0x80000001, 3, 0x58},
+	{SCORPION_BANK_AB_ACCESS, 0x80000100, 3, 0x59},
+	{SCORPION_BANK_CD_HIT, 0x80010000, 3, 0x5a},
+	{SCORPION_BANK_CD_ACCESS, 0x81000000, 3, 0x5b},
+	{SCORPION_BANK_AB_DSIDE_HIT, 0x80000002, 3, 0x58},
+	{SCORPION_BANK_AB_DSIDE_ACCESS, 0x80000200, 3, 0x59},
+	{SCORPION_BANK_CD_DSIDE_HIT, 0x80020000, 3, 0x5a},
+	{SCORPION_BANK_CD_DSIDE_ACCESS, 0x82000000, 3, 0x5b},
+	{SCORPION_BANK_AB_ISIDE_HIT, 0x80000003, 3, 0x58},
+	{SCORPION_BANK_AB_ISIDE_ACCESS, 0x80000300, 3, 0x59},
+	{SCORPION_BANK_CD_ISIDE_HIT, 0x80030000, 3, 0x5a},
+	{SCORPION_BANK_CD_ISIDE_ACCESS, 0x83000000, 3, 0x5b},
+	{SCORPION_ISIDE_RD_WAIT, 0x80000009, 3, 0x58},
+	{SCORPION_DSIDE_RD_WAIT, 0x80090000, 3, 0x5a},
+	{SCORPION_BANK_BYPASS_WRITE, 0x8000000a, 3, 0x58},
+	{SCORPION_BANK_AB_NON_CASTOUT, 0x8000000c, 3, 0x58},
+	{SCORPION_BANK_AB_L2_CASTOUT, 0x80000c00, 3, 0x59},
+	{SCORPION_BANK_CD_NON_CASTOUT, 0x800c0000, 3, 0x5a},
+	{SCORPION_BANK_CD_L2_CASTOUT, 0x8c000000, 3, 0x5b},
+#endif
+};
+
+static inline void scorpion_pmnc_write(u32 val)
+{
+	val &= PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+static inline u32 scorpion_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_ccnt_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_cntn_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+	return val;
+}
+
+static inline u32 scorpion_pmnc_enable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u enabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CCNT_REG;
+	else
+		val = (1 << (cnt - CNT0));
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+	return cnt;
+}
+
+static inline u32 scorpion_pmnc_disable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u disabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CCNT_REG;
+	else
+		val = (1 << (cnt - CNT0));
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+	return cnt;
+}
+
+static inline int scorpion_pmnc_select_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if ((cnt == CCNT) || (cnt >= CNTMAX)) {
+		pr_err("gator: CPU%u selecting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	val = (cnt - CNT0);
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+	return cnt;
+}
+
+static u32 scorpion_read_lpm0(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm0(u32 val)
+{
+	asm volatile("mcr p15, 0, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm1(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 1, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm1(u32 val)
+{
+	asm volatile("mcr p15, 1, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm2(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 2, %0, c15, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_lpm2(u32 val)
+{
+	asm volatile("mcr p15, 2, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_l2lpm(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 3, %0, c15, c2, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_l2lpm(u32 val)
+{
+	asm volatile("mcr p15, 3, %0, c15, c2, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_vlpm(void)
+{
+	u32 val;
+
+	asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void scorpion_write_vlpm(u32 val)
+{
+	asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val));
+}
+
+struct scorpion_access_funcs {
+	u32 (*read)(void);
+	void (*write)(u32);
+};
+
+struct scorpion_access_funcs scor_func[] = {
+	{scorpion_read_lpm0, scorpion_write_lpm0},
+	{scorpion_read_lpm1, scorpion_write_lpm1},
+	{scorpion_read_lpm2, scorpion_write_lpm2},
+	{scorpion_read_l2lpm, scorpion_write_l2lpm},
+	{scorpion_read_vlpm, scorpion_write_vlpm},
+};
+
+u32 venum_orig_val;
+u32 fp_orig_val;
+
+static void scorpion_pre_vlpm(void)
+{
+	u32 venum_new_val;
+	u32 fp_new_val;
+
+	/* CPACR Enable CP10 access */
+	asm volatile("mrc p15, 0, %0, c1, c0, 2" : "=r" (venum_orig_val));
+	venum_new_val = venum_orig_val | 0x00300000;
+	asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_new_val));
+	/* Enable FPEXC */
+	asm volatile("mrc p10, 7, %0, c8, c0, 0" : "=r" (fp_orig_val));
+	fp_new_val = fp_orig_val | 0x40000000;
+	asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_new_val));
+}
+
+static void scorpion_post_vlpm(void)
+{
+	/* Restore FPEXC */
+	asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_orig_val));
+	/* Restore CPACR */
+	asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_orig_val));
+}
+
+#define COLMN0MASK 0x000000ff
+#define COLMN1MASK 0x0000ff00
+#define COLMN2MASK 0x00ff0000
+static u32 scorpion_get_columnmask(u32 setval)
+{
+	if (setval & COLMN0MASK)
+		return 0xffffff00;
+	if (setval & COLMN1MASK)
+		return 0xffff00ff;
+	if (setval & COLMN2MASK)
+		return 0xff00ffff;
+	return 0x80ffffff;
+}
+
+static void scorpion_evt_setup(u32 gr, u32 setval)
+{
+	u32 val;
+
+	if (gr == 4)
+		scorpion_pre_vlpm();
+	val = scorpion_get_columnmask(setval) & scor_func[gr].read();
+	val = val | setval;
+	scor_func[gr].write(val);
+	if (gr == 4)
+		scorpion_post_vlpm();
+}
+
+static int get_scorpion_evtinfo(unsigned int evt_type, struct scorp_evt *evtinfo)
+{
+	u32 idx;
+
+	if ((evt_type < 0x4c) || (evt_type >= MSM_MAX_EVT))
+		return 0;
+	idx = evt_type - 0x4c;
+	if (sc_evt[idx].evt_type == evt_type) {
+		evtinfo->val = sc_evt[idx].val;
+		evtinfo->grp = sc_evt[idx].grp;
+		evtinfo->evt_type_act = sc_evt[idx].evt_type_act;
+		return 1;
+	}
+	return 0;
+}
+
+static inline void scorpion_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+	if (scorpion_pmnc_select_counter(cnt) == cnt) {
+		if (val < 0x40) {
+			asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+		} else {
+			u32 zero = 0;
+			struct scorp_evt evtinfo;
+			/* extract evtinfo.grp and evtinfo.tevt_type_act from val */
+			if (get_scorpion_evtinfo(val, &evtinfo) == 0)
+				return;
+			asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (evtinfo.evt_type_act));
+			asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (zero));
+			scorpion_evt_setup(evtinfo.grp, val);
+		}
+	}
+}
+
+static void scorpion_pmnc_reset_counter(unsigned int cnt)
+{
+	u32 val = 0;
+
+	if (cnt == CCNT) {
+		scorpion_pmnc_disable_counter(cnt);
+
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (val));
+
+		if (pmnc_enabled[cnt] != 0)
+			scorpion_pmnc_enable_counter(cnt);
+
+	} else if (cnt >= CNTMAX) {
+		pr_err("gator: CPU%u resetting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+	} else {
+		scorpion_pmnc_disable_counter(cnt);
+
+		if (scorpion_pmnc_select_counter(cnt) == cnt)
+			asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (val));
+
+		if (pmnc_enabled[cnt] != 0)
+			scorpion_pmnc_enable_counter(cnt);
+	}
+}
+
+static int gator_events_scorpion_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int i;
+
+	for (i = 0; i < pmnc_counters; i++) {
+		char buf[40];
+
+		if (i == 0)
+			snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+		else
+			snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+		dir = gatorfs_mkdir(sb, root, buf);
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+		if (i > 0)
+			gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+	}
+
+	return 0;
+}
+
+static int gator_events_scorpion_online(int **buffer, bool migrate)
+{
+	unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+	if (scorpion_pmnc_read() & PMNC_E)
+		scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+
+	/* Initialize & Reset PMNC: C bit and P bit */
+	scorpion_pmnc_write(PMNC_P | PMNC_C);
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		unsigned long event;
+
+		if (!pmnc_enabled[cnt])
+			continue;
+
+		/* disable counter */
+		scorpion_pmnc_disable_counter(cnt);
+
+		event = pmnc_event[cnt] & 255;
+
+		/* Set event (if destined for PMNx counters), We don't need to set the event if it's a cycle count */
+		if (cnt != CCNT)
+			scorpion_pmnc_write_evtsel(cnt, event);
+
+		/* reset counter */
+		scorpion_pmnc_reset_counter(cnt);
+
+		/* Enable counter, do not enable interrupt for this counter */
+		scorpion_pmnc_enable_counter(cnt);
+	}
+
+	/* enable */
+	scorpion_pmnc_write(scorpion_pmnc_read() | PMNC_E);
+
+	/* read the counters and toss the invalid data, return zero instead */
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			if (cnt == CCNT)
+				scorpion_ccnt_read();
+			else if (scorpion_pmnc_select_counter(cnt) == cnt)
+				scorpion_cntn_read();
+			scorpion_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = 0;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static int gator_events_scorpion_offline(int **buffer, bool migrate)
+{
+	scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+	return 0;
+}
+
+static void gator_events_scorpion_stop(void)
+{
+	unsigned int cnt;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+	}
+}
+
+static int gator_events_scorpion_read(int **buffer, bool sched_switch)
+{
+	int cnt, len = 0;
+	int cpu = smp_processor_id();
+
+	/* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+	if (!(scorpion_pmnc_read() & PMNC_E))
+		return 0;
+
+	for (cnt = 0; cnt < pmnc_counters; cnt++) {
+		if (pmnc_enabled[cnt]) {
+			int value;
+
+			if (cnt == CCNT)
+				value = scorpion_ccnt_read();
+			else if (scorpion_pmnc_select_counter(cnt) == cnt)
+				value = scorpion_cntn_read();
+			else
+				value = 0;
+			scorpion_pmnc_reset_counter(cnt);
+
+			per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+			per_cpu(perfCnt, cpu)[len++] = value;
+		}
+	}
+
+	if (buffer)
+		*buffer = per_cpu(perfCnt, cpu);
+
+	return len;
+}
+
+static struct gator_interface gator_events_scorpion_interface = {
+	.create_files = gator_events_scorpion_create_files,
+	.stop = gator_events_scorpion_stop,
+	.online = gator_events_scorpion_online,
+	.offline = gator_events_scorpion_offline,
+	.read = gator_events_scorpion_read,
+};
+
+int gator_events_scorpion_init(void)
+{
+	unsigned int cnt;
+
+	switch (gator_cpuid()) {
+	case SCORPION:
+		pmnc_name = "Scorpion";
+		pmnc_counters = 4;
+		break;
+	case SCORPIONMP:
+		pmnc_name = "ScorpionMP";
+		pmnc_counters = 4;
+		break;
+	default:
+		return -1;
+	}
+
+	/* CNT[n] + CCNT */
+	pmnc_counters++;
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		pmnc_enabled[cnt] = 0;
+		pmnc_event[cnt] = 0;
+		pmnc_key[cnt] = gator_events_get_key();
+	}
+
+	return gator_events_install(&gator_events_scorpion_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_fs.c b/drivers/gator/gator_fs.c
new file mode 100644
index 000000000000..d8fb357b9eda
--- /dev/null
+++ b/drivers/gator/gator_fs.c
@@ -0,0 +1,370 @@
+/**
+ * @file gatorfs.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon
+ *
+ * A simple filesystem for configuration and
+ * access of oprofile.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/uaccess.h>
+
+#define gatorfs_MAGIC 0x24051020
+#define TMPBUFSIZE 50
+DEFINE_SPINLOCK(gatorfs_lock);
+
+static struct inode *gatorfs_get_inode(struct super_block *sb, int mode)
+{
+	struct inode *inode = new_inode(sb);
+
+	if (inode) {
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 37)
+		inode->i_ino = get_next_ino();
+#endif
+		inode->i_mode = mode;
+		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	}
+	return inode;
+}
+
+static const struct super_operations s_ops = {
+	.statfs = simple_statfs,
+	.drop_inode = generic_delete_inode,
+};
+
+static ssize_t gatorfs_ulong_to_user(unsigned long val, char __user *buf, size_t count, loff_t *offset)
+{
+	char tmpbuf[TMPBUFSIZE];
+	size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%lu\n", val);
+
+	if (maxlen > TMPBUFSIZE)
+		maxlen = TMPBUFSIZE;
+	return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static ssize_t gatorfs_u64_to_user(u64 val, char __user *buf, size_t count, loff_t *offset)
+{
+	char tmpbuf[TMPBUFSIZE];
+	size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%llu\n", val);
+
+	if (maxlen > TMPBUFSIZE)
+		maxlen = TMPBUFSIZE;
+	return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static int gatorfs_ulong_from_user(unsigned long *val, char const __user *buf, size_t count)
+{
+	char tmpbuf[TMPBUFSIZE];
+	unsigned long flags;
+
+	if (!count)
+		return 0;
+
+	if (count > TMPBUFSIZE - 1)
+		return -EINVAL;
+
+	memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+	if (copy_from_user(tmpbuf, buf, count))
+		return -EFAULT;
+
+	spin_lock_irqsave(&gatorfs_lock, flags);
+	*val = simple_strtoul(tmpbuf, NULL, 0);
+	spin_unlock_irqrestore(&gatorfs_lock, flags);
+	return 0;
+}
+
+static int gatorfs_u64_from_user(u64 *val, char const __user *buf, size_t count)
+{
+	char tmpbuf[TMPBUFSIZE];
+	unsigned long flags;
+
+	if (!count)
+		return 0;
+
+	if (count > TMPBUFSIZE - 1)
+		return -EINVAL;
+
+	memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+	if (copy_from_user(tmpbuf, buf, count))
+		return -EFAULT;
+
+	spin_lock_irqsave(&gatorfs_lock, flags);
+	*val = simple_strtoull(tmpbuf, NULL, 0);
+	spin_unlock_irqrestore(&gatorfs_lock, flags);
+	return 0;
+}
+
+static ssize_t ulong_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long *val = file->private_data;
+
+	return gatorfs_ulong_to_user(*val, buf, count, offset);
+}
+
+static ssize_t u64_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	u64 *val = file->private_data;
+
+	return gatorfs_u64_to_user(*val, buf, count, offset);
+}
+
+static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long *value = file->private_data;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(value, buf, count);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static ssize_t u64_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	u64 *value = file->private_data;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_u64_from_user(value, buf, count);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static int default_open(struct inode *inode, struct file *filp)
+{
+	if (inode->i_private)
+		filp->private_data = inode->i_private;
+	return 0;
+}
+
+static const struct file_operations ulong_fops = {
+	.read = ulong_read_file,
+	.write = ulong_write_file,
+	.open = default_open,
+};
+
+static const struct file_operations u64_fops = {
+	.read = u64_read_file,
+	.write = u64_write_file,
+	.open = default_open,
+};
+
+static const struct file_operations ulong_ro_fops = {
+	.read = ulong_read_file,
+	.open = default_open,
+};
+
+static const struct file_operations u64_ro_fops = {
+	.read = u64_read_file,
+	.open = default_open,
+};
+
+static struct dentry *__gatorfs_create_file(struct super_block *sb,
+					    struct dentry *root,
+					    char const *name,
+					    const struct file_operations *fops,
+					    int perm)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(root, name);
+	if (!dentry)
+		return NULL;
+	inode = gatorfs_get_inode(sb, S_IFREG | perm);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+	inode->i_fop = fops;
+	d_add(dentry, inode);
+	return dentry;
+}
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+			 char const *name, unsigned long *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &ulong_fops, 0644);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static int gatorfs_create_u64(struct super_block *sb, struct dentry *root,
+			      char const *name, u64 *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &u64_fops, 0644);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+			    char const *name, unsigned long *val)
+{
+	struct dentry *d = __gatorfs_create_file(sb, root, name,
+						 &ulong_ro_fops, 0444);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static int gatorfs_create_ro_u64(struct super_block *sb, struct dentry *root,
+				 char const *name, u64 *val)
+{
+	struct dentry *d =
+	    __gatorfs_create_file(sb, root, name, &u64_ro_fops, 0444);
+	if (!d)
+		return -EFAULT;
+
+	d->d_inode->i_private = val;
+	return 0;
+}
+
+static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	atomic_t *val = file->private_data;
+
+	return gatorfs_ulong_to_user(atomic_read(val), buf, count, offset);
+}
+
+static const struct file_operations atomic_ro_fops = {
+	.read = atomic_read_file,
+	.open = default_open,
+};
+
+static int gatorfs_create_file(struct super_block *sb, struct dentry *root,
+			       char const *name, const struct file_operations *fops)
+{
+	if (!__gatorfs_create_file(sb, root, name, fops, 0644))
+		return -EFAULT;
+	return 0;
+}
+
+static int gatorfs_create_file_perm(struct super_block *sb, struct dentry *root,
+				    char const *name,
+				    const struct file_operations *fops, int perm)
+{
+	if (!__gatorfs_create_file(sb, root, name, fops, perm))
+		return -EFAULT;
+	return 0;
+}
+
+struct dentry *gatorfs_mkdir(struct super_block *sb,
+			     struct dentry *root, char const *name)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(root, name);
+	if (!dentry)
+		return NULL;
+	inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+	inode->i_op = &simple_dir_inode_operations;
+	inode->i_fop = &simple_dir_operations;
+	d_add(dentry, inode);
+	return dentry;
+}
+
+static int gatorfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct inode *root_inode;
+	struct dentry *root_dentry;
+
+	sb->s_blocksize = PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_magic = gatorfs_MAGIC;
+	sb->s_op = &s_ops;
+	sb->s_time_gran = 1;
+
+	root_inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+	if (!root_inode)
+		return -ENOMEM;
+	root_inode->i_op = &simple_dir_inode_operations;
+	root_inode->i_fop = &simple_dir_operations;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+	root_dentry = d_alloc_root(root_inode);
+#else
+	root_dentry = d_make_root(root_inode);
+#endif
+
+	if (!root_dentry) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+		iput(root_inode);
+#endif
+		return -ENOMEM;
+	}
+
+	sb->s_root = root_dentry;
+
+	gator_op_create_files(sb, root_dentry);
+
+	return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+static int gatorfs_get_sb(struct file_system_type *fs_type,
+			  int flags, const char *dev_name, void *data,
+			  struct vfsmount *mnt)
+{
+	return get_sb_single(fs_type, flags, data, gatorfs_fill_super, mnt);
+}
+#else
+static struct dentry *gatorfs_mount(struct file_system_type *fs_type,
+				    int flags, const char *dev_name, void *data)
+{
+	return mount_nodev(fs_type, flags, data, gatorfs_fill_super);
+}
+#endif
+
+static struct file_system_type gatorfs_type = {
+	.owner = THIS_MODULE,
+	.name = "gatorfs",
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+	.get_sb = gatorfs_get_sb,
+#else
+	.mount = gatorfs_mount,
+#endif
+
+	.kill_sb = kill_litter_super,
+};
+
+static int __init gatorfs_register(void)
+{
+	return register_filesystem(&gatorfs_type);
+}
+
+static void gatorfs_unregister(void)
+{
+	unregister_filesystem(&gatorfs_type);
+}
diff --git a/drivers/gator/gator_hrtimer_gator.c b/drivers/gator/gator_hrtimer_gator.c
new file mode 100644
index 000000000000..c1525e10a8da
--- /dev/null
+++ b/drivers/gator/gator_hrtimer_gator.c
@@ -0,0 +1,80 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+void (*callback)(void);
+DEFINE_PER_CPU(struct hrtimer, percpu_hrtimer);
+DEFINE_PER_CPU(ktime_t, hrtimer_expire);
+DEFINE_PER_CPU(int, hrtimer_is_active);
+static ktime_t profiling_interval;
+static void gator_hrtimer_online(void);
+static void gator_hrtimer_offline(void);
+
+static enum hrtimer_restart gator_hrtimer_notify(struct hrtimer *hrtimer)
+{
+	int cpu = get_logical_cpu();
+
+	hrtimer_forward(hrtimer, per_cpu(hrtimer_expire, cpu), profiling_interval);
+	per_cpu(hrtimer_expire, cpu) = ktime_add(per_cpu(hrtimer_expire, cpu), profiling_interval);
+	(*callback)();
+	return HRTIMER_RESTART;
+}
+
+static void gator_hrtimer_online(void)
+{
+	int cpu = get_logical_cpu();
+	struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+	if (per_cpu(hrtimer_is_active, cpu) || profiling_interval.tv64 == 0)
+		return;
+
+	per_cpu(hrtimer_is_active, cpu) = 1;
+	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer->function = gator_hrtimer_notify;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	hrtimer->irqsafe = 1;
+#endif
+	per_cpu(hrtimer_expire, cpu) = ktime_add(hrtimer->base->get_time(), profiling_interval);
+	hrtimer_start(hrtimer, per_cpu(hrtimer_expire, cpu), HRTIMER_MODE_ABS_PINNED);
+}
+
+static void gator_hrtimer_offline(void)
+{
+	int cpu = get_logical_cpu();
+	struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+	if (!per_cpu(hrtimer_is_active, cpu))
+		return;
+
+	per_cpu(hrtimer_is_active, cpu) = 0;
+	hrtimer_cancel(hrtimer);
+}
+
+static int gator_hrtimer_init(int interval, void (*func)(void))
+{
+	int cpu;
+
+	(callback) = (func);
+
+	for_each_present_cpu(cpu) {
+		per_cpu(hrtimer_is_active, cpu) = 0;
+	}
+
+	/* calculate profiling interval */
+	if (interval > 0)
+		profiling_interval = ns_to_ktime(1000000000UL / interval);
+	else
+		profiling_interval.tv64 = 0;
+
+	return 0;
+}
+
+static void gator_hrtimer_shutdown(void)
+{
+	/* empty */
+}
diff --git a/drivers/gator/gator_iks.c b/drivers/gator/gator_iks.c
new file mode 100644
index 000000000000..fb78c10fd987
--- /dev/null
+++ b/drivers/gator/gator_iks.c
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if GATOR_IKS_SUPPORT
+
+#include <linux/of.h>
+#include <asm/bL_switcher.h>
+#include <asm/smp_plat.h>
+#include <trace/events/power_cpu_migrate.h>
+
+static bool map_cpuids;
+static int mpidr_cpuids[NR_CPUS];
+static const struct gator_cpu *mpidr_cpus[NR_CPUS];
+static int __lcpu_to_pcpu[NR_CPUS];
+
+static const struct gator_cpu *gator_find_cpu_by_dt_name(const char *const name)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->dt_name != NULL && strcmp(gator_cpu->dt_name, name) == 0)
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+static void calc_first_cluster_size(void)
+{
+	int len;
+	const u32 *val;
+	const char *compatible;
+	struct device_node *cn = NULL;
+	int mpidr_cpuids_count = 0;
+
+	/* Zero is a valid cpuid, so initialize the array to 0xff's */
+	memset(&mpidr_cpuids, 0xff, sizeof(mpidr_cpuids));
+	memset(&mpidr_cpus, 0, sizeof(mpidr_cpus));
+
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+		BUG_ON(mpidr_cpuids_count >= NR_CPUS);
+
+		val = of_get_property(cn, "reg", &len);
+		if (!val || len != 4) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+		compatible = of_get_property(cn, "compatible", NULL);
+		if (compatible == NULL) {
+			pr_err("%s missing compatible property\n", cn->full_name);
+			continue;
+		}
+
+		mpidr_cpuids[mpidr_cpuids_count] = be32_to_cpup(val);
+		mpidr_cpus[mpidr_cpuids_count] = gator_find_cpu_by_dt_name(compatible);
+		++mpidr_cpuids_count;
+	}
+
+	map_cpuids = (mpidr_cpuids_count == nr_cpu_ids);
+}
+
+static int linearize_mpidr(int mpidr)
+{
+	int i;
+
+	for (i = 0; i < nr_cpu_ids; ++i) {
+		if (mpidr_cpuids[i] == mpidr)
+			return i;
+	}
+
+	BUG();
+}
+
+int lcpu_to_pcpu(const int lcpu)
+{
+	int pcpu;
+
+	if (!map_cpuids)
+		return lcpu;
+
+	BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+	pcpu = __lcpu_to_pcpu[lcpu];
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	return pcpu;
+}
+
+int pcpu_to_lcpu(const int pcpu)
+{
+	int lcpu;
+
+	if (!map_cpuids)
+		return pcpu;
+
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	for (lcpu = 0; lcpu < nr_cpu_ids; ++lcpu) {
+		if (__lcpu_to_pcpu[lcpu] == pcpu) {
+			BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+			return lcpu;
+		}
+	}
+	BUG();
+}
+
+static void gator_update_cpu_mapping(u32 cpu_hwid)
+{
+	int lcpu = smp_processor_id();
+	int pcpu = linearize_mpidr(cpu_hwid & MPIDR_HWID_BITMASK);
+
+	BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+	BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+	__lcpu_to_pcpu[lcpu] = pcpu;
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_begin, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	const int cpu = get_physical_cpu();
+
+	gator_timer_offline((void *)1);
+	gator_timer_offline_dispatch(cpu, true);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_finish, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	int cpu;
+
+	gator_update_cpu_mapping(cpu_hwid);
+
+	/* get_physical_cpu must be called after gator_update_cpu_mapping */
+	cpu = get_physical_cpu();
+	gator_timer_online_dispatch(cpu, true);
+	gator_timer_online((void *)1);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_current, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+	gator_update_cpu_mapping(cpu_hwid);
+}
+
+static void gator_send_iks_core_names(void)
+{
+	int cpu;
+	/* Send the cpu names */
+	preempt_disable();
+	for (cpu = 0; cpu < nr_cpu_ids; ++cpu) {
+		if (mpidr_cpus[cpu] != NULL)
+			gator_send_core_name(cpu, mpidr_cpus[cpu]->cpuid);
+	}
+	preempt_enable();
+}
+
+static int gator_migrate_start(void)
+{
+	int retval = 0;
+
+	if (!map_cpuids)
+		return retval;
+
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_begin);
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_finish);
+	if (retval == 0)
+		retval = GATOR_REGISTER_TRACE(cpu_migrate_current);
+	if (retval == 0) {
+		/* Initialize the logical to physical cpu mapping */
+		memset(&__lcpu_to_pcpu, 0xff, sizeof(__lcpu_to_pcpu));
+		bL_switcher_trace_trigger();
+	}
+	return retval;
+}
+
+static void gator_migrate_stop(void)
+{
+	if (!map_cpuids)
+		return;
+
+	GATOR_UNREGISTER_TRACE(cpu_migrate_current);
+	GATOR_UNREGISTER_TRACE(cpu_migrate_finish);
+	GATOR_UNREGISTER_TRACE(cpu_migrate_begin);
+}
+
+#else
+
+#define calc_first_cluster_size()
+#define gator_send_iks_core_names()
+#define gator_migrate_start() 0
+#define gator_migrate_stop()
+
+#endif
diff --git a/drivers/gator/gator_main.c b/drivers/gator/gator_main.c
new file mode 100644
index 000000000000..30bf60d95286
--- /dev/null
+++ b/drivers/gator/gator_main.c
@@ -0,0 +1,1491 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/* This version must match the gator daemon version */
+#define PROTOCOL_VERSION 20
+static unsigned long gator_protocol_version = PROTOCOL_VERSION;
+
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/irq.h>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/perf_event.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+#include <asm/stacktrace.h>
+#include <linux/uaccess.h>
+
+#include "gator.h"
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 32)
+#error kernels prior to 2.6.32 are not supported
+#endif
+
+#if defined(MODULE) && !defined(CONFIG_MODULES)
+#error Cannot build a module against a kernel that does not support modules. To resolve, either rebuild the kernel to support modules or build gator as part of the kernel.
+#endif
+
+#if !defined(CONFIG_GENERIC_TRACER) && !defined(CONFIG_TRACING)
+#error gator requires the kernel to have CONFIG_GENERIC_TRACER or CONFIG_TRACING defined
+#endif
+
+#ifndef CONFIG_PROFILING
+#error gator requires the kernel to have CONFIG_PROFILING defined
+#endif
+
+#ifndef CONFIG_HIGH_RES_TIMERS
+#error gator requires the kernel to have CONFIG_HIGH_RES_TIMERS defined to support PC sampling
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 12, 0) && defined(__arm__) && defined(CONFIG_SMP) && !defined(CONFIG_LOCAL_TIMERS)
+#error gator requires the kernel to have CONFIG_LOCAL_TIMERS defined on SMP systems
+#endif
+
+#if (GATOR_PERF_SUPPORT) && (!(GATOR_PERF_PMU_SUPPORT))
+#ifndef CONFIG_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_PERF_EVENTS defined to support pmu hardware counters
+#elif !defined CONFIG_HW_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_HW_PERF_EVENTS defined to support pmu hardware counters
+#endif
+#endif
+
+/******************************************************************************
+ * DEFINES
+ ******************************************************************************/
+#define SUMMARY_BUFFER_SIZE       (1*1024)
+#define BACKTRACE_BUFFER_SIZE     (128*1024)
+#define NAME_BUFFER_SIZE          (64*1024)
+#define COUNTER_BUFFER_SIZE       (64*1024)	/* counters have the core as part of the data and the core value in the frame header may be discarded */
+#define BLOCK_COUNTER_BUFFER_SIZE (128*1024)
+#define ANNOTATE_BUFFER_SIZE      (128*1024)	/* annotate counters have the core as part of the data and the core value in the frame header may be discarded */
+#define SCHED_TRACE_BUFFER_SIZE   (128*1024)
+#define IDLE_BUFFER_SIZE          (32*1024)	/* idle counters have the core as part of the data and the core value in the frame header may be discarded */
+#define ACTIVITY_BUFFER_SIZE      (128*1024)
+
+#define NO_COOKIE      0U
+#define UNRESOLVED_COOKIE ~0U
+
+#define FRAME_SUMMARY       1
+#define FRAME_BACKTRACE     2
+#define FRAME_NAME          3
+#define FRAME_COUNTER       4
+#define FRAME_BLOCK_COUNTER 5
+#define FRAME_ANNOTATE      6
+#define FRAME_SCHED_TRACE   7
+#define FRAME_IDLE          9
+#define FRAME_ACTIVITY     13
+
+#define MESSAGE_END_BACKTRACE 1
+
+/* Name Frame Messages */
+#define MESSAGE_COOKIE      1
+#define MESSAGE_THREAD_NAME 2
+#define MESSAGE_LINK        4
+
+/* Scheduler Trace Frame Messages */
+#define MESSAGE_SCHED_SWITCH 1
+#define MESSAGE_SCHED_EXIT   2
+
+/* Idle Frame Messages */
+#define MESSAGE_IDLE_ENTER 1
+#define MESSAGE_IDLE_EXIT  2
+
+/* Summary Frame Messages */
+#define MESSAGE_SUMMARY   1
+#define MESSAGE_CORE_NAME 3
+
+/* Activity Frame Messages */
+#define MESSAGE_SWITCH 2
+#define MESSAGE_EXIT   3
+
+#define MAXSIZE_PACK32     5
+#define MAXSIZE_PACK64    10
+
+#define FRAME_HEADER_SIZE 3
+
+#if defined(__arm__)
+#define PC_REG regs->ARM_pc
+#elif defined(__aarch64__)
+#define PC_REG regs->pc
+#else
+#define PC_REG regs->ip
+#endif
+
+enum {
+	SUMMARY_BUF,
+	BACKTRACE_BUF,
+	NAME_BUF,
+	COUNTER_BUF,
+	BLOCK_COUNTER_BUF,
+	ANNOTATE_BUF,
+	SCHED_TRACE_BUF,
+	IDLE_BUF,
+	ACTIVITY_BUF,
+	NUM_GATOR_BUFS
+};
+
+/******************************************************************************
+ * Globals
+ ******************************************************************************/
+static unsigned long gator_cpu_cores;
+/* Size of the largest buffer. Effectively constant, set in gator_op_create_files */
+static unsigned long userspace_buffer_size;
+static unsigned long gator_backtrace_depth;
+/* How often to commit the buffers for live in nanoseconds */
+static u64 gator_live_rate;
+
+static unsigned long gator_started;
+static u64 gator_monotonic_started;
+static u64 gator_sync_time;
+static u64 gator_hibernate_time;
+static unsigned long gator_buffer_opened;
+static unsigned long gator_timer_count;
+static unsigned long gator_response_type;
+static DEFINE_MUTEX(start_mutex);
+static DEFINE_MUTEX(gator_buffer_mutex);
+
+bool event_based_sampling;
+
+static DECLARE_WAIT_QUEUE_HEAD(gator_buffer_wait);
+static DECLARE_WAIT_QUEUE_HEAD(gator_annotate_wait);
+static struct timer_list gator_buffer_wake_up_timer;
+static bool gator_buffer_wake_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_buffer_wake_sem);
+#else
+static DEFINE_SEMAPHORE(gator_buffer_wake_sem);
+#endif
+static struct task_struct *gator_buffer_wake_thread;
+static LIST_HEAD(gator_events);
+
+static DEFINE_PER_CPU(u64, last_timestamp);
+
+static bool printed_monotonic_warning;
+
+static u32 gator_cpuids[NR_CPUS];
+static bool sent_core_name[NR_CPUS];
+
+static DEFINE_PER_CPU(bool, in_scheduler_context);
+
+/******************************************************************************
+ * Prototypes
+ ******************************************************************************/
+static u64 gator_get_time(void);
+static void gator_emit_perf_time(u64 time);
+static void gator_op_create_files(struct super_block *sb, struct dentry *root);
+
+/* gator_buffer is protected by being per_cpu and by having IRQs
+ * disabled when writing to it. Most marshal_* calls take care of this
+ * except for marshal_cookie*, marshal_backtrace* and marshal_frame
+ * where the caller is responsible for doing so. No synchronization is
+ * needed with the backtrace buffer as it is per cpu and is only used
+ * from the hrtimer. The annotate_lock must be held when using the
+ * annotation buffer as it is not per cpu. collect_counters which is
+ * the sole writer to the block counter frame is additionally
+ * protected by the per cpu collecting flag.
+ */
+
+/* Size of the buffer, must be a power of 2. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_size[NUM_GATOR_BUFS];
+/* gator_buffer_size - 1, bitwise and with pos to get offset into the array. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_mask[NUM_GATOR_BUFS];
+/* Read position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are read by userspace in userspace_buffer_read */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_read);
+/* Write position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are written to the buffer */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_write);
+/* Commit position in the buffer. Initialized to zero in gator_op_setup and incremented after a frame is ready to be read by userspace */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_commit);
+/* If set to false, decreases the number of bytes returned by
+ * buffer_bytes_available. Set in buffer_check_space if no space is
+ * remaining. Initialized to true in gator_op_setup. This means that
+ * if we run out of space, continue to report that no space is
+ * available until bytes are read by userspace
+ */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], buffer_space_available);
+/* The buffer. Allocated in gator_op_setup */
+static DEFINE_PER_CPU(char *[NUM_GATOR_BUFS], gator_buffer);
+/* The time after which the buffer should be committed for live display */
+static DEFINE_PER_CPU(u64, gator_buffer_commit_time);
+
+/* List of all gator events - new events must be added to this list */
+#define GATOR_EVENTS_LIST \
+	GATOR_EVENT(gator_events_armv6_init) \
+	GATOR_EVENT(gator_events_armv7_init) \
+	GATOR_EVENT(gator_events_block_init) \
+	GATOR_EVENT(gator_events_ccn504_init) \
+	GATOR_EVENT(gator_events_irq_init) \
+	GATOR_EVENT(gator_events_l2c310_init) \
+	GATOR_EVENT(gator_events_mali_init) \
+	GATOR_EVENT(gator_events_mali_midgard_hw_init) \
+	GATOR_EVENT(gator_events_mali_midgard_init) \
+	GATOR_EVENT(gator_events_meminfo_init) \
+	GATOR_EVENT(gator_events_mmapped_init) \
+	GATOR_EVENT(gator_events_net_init) \
+	GATOR_EVENT(gator_events_perf_pmu_init) \
+	GATOR_EVENT(gator_events_sched_init) \
+	GATOR_EVENT(gator_events_scorpion_init) \
+
+#define GATOR_EVENT(EVENT_INIT) __weak int EVENT_INIT(void);
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+
+static int (*gator_events_list[])(void) = {
+#define GATOR_EVENT(EVENT_INIT) EVENT_INIT,
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+};
+
+/******************************************************************************
+ * Application Includes
+ ******************************************************************************/
+#include "gator_fs.c"
+#include "gator_buffer_write.c"
+#include "gator_buffer.c"
+#include "gator_marshaling.c"
+#include "gator_hrtimer_gator.c"
+#include "gator_cookies.c"
+#include "gator_annotate.c"
+#include "gator_trace_sched.c"
+#include "gator_trace_power.c"
+#include "gator_trace_gpu.c"
+#include "gator_backtrace.c"
+
+/******************************************************************************
+ * Misc
+ ******************************************************************************/
+
+static const struct gator_cpu gator_cpus[] = {
+	{
+		.cpuid = ARM1136,
+		.core_name = "ARM1136",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1136",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM1156,
+		.core_name = "ARM1156",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1156",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM1176,
+		.core_name = "ARM1176",
+		.pmnc_name = "ARM_ARM11",
+		.dt_name = "arm,arm1176",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = ARM11MPCORE,
+		.core_name = "ARM11MPCore",
+		.pmnc_name = "ARM_ARM11MPCore",
+		.dt_name = "arm,arm11mpcore",
+		.pmnc_counters = 3,
+	},
+	{
+		.cpuid = CORTEX_A5,
+		.core_name = "Cortex-A5",
+		.pmnc_name = "ARMv7_Cortex_A5",
+		.dt_name = "arm,cortex-a5",
+		.pmnc_counters = 2,
+	},
+	{
+		.cpuid = CORTEX_A7,
+		.core_name = "Cortex-A7",
+		.pmnc_name = "ARMv7_Cortex_A7",
+		.dt_name = "arm,cortex-a7",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A8,
+		.core_name = "Cortex-A8",
+		.pmnc_name = "ARMv7_Cortex_A8",
+		.dt_name = "arm,cortex-a8",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A9,
+		.core_name = "Cortex-A9",
+		.pmnc_name = "ARMv7_Cortex_A9",
+		.dt_name = "arm,cortex-a9",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A15,
+		.core_name = "Cortex-A15",
+		.pmnc_name = "ARMv7_Cortex_A15",
+		.dt_name = "arm,cortex-a15",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A17,
+		.core_name = "Cortex-A17",
+		.pmnc_name = "ARMv7_Cortex_A17",
+		.dt_name = "arm,cortex-a17",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = SCORPION,
+		.core_name = "Scorpion",
+		.pmnc_name = "Scorpion",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = SCORPIONMP,
+		.core_name = "ScorpionMP",
+		.pmnc_name = "ScorpionMP",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAITSIM,
+		.core_name = "KraitSIM",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAIT,
+		.core_name = "Krait",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = KRAIT_S4_PRO,
+		.core_name = "Krait S4 Pro",
+		.pmnc_name = "Krait",
+		.pmnc_counters = 4,
+	},
+	{
+		.cpuid = CORTEX_A53,
+		.core_name = "Cortex-A53",
+		.pmnc_name = "ARM_Cortex-A53",
+		.dt_name = "arm,cortex-a53",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = CORTEX_A57,
+		.core_name = "Cortex-A57",
+		.pmnc_name = "ARM_Cortex-A57",
+		.dt_name = "arm,cortex-a57",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = AARCH64,
+		.core_name = "AArch64",
+		.pmnc_name = "ARM_AArch64",
+		.pmnc_counters = 6,
+	},
+	{
+		.cpuid = OTHER,
+		.core_name = "Other",
+		.pmnc_name = "Other",
+		.pmnc_counters = 6,
+	},
+	{}
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->cpuid == cpuid)
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name)
+{
+	int i;
+
+	for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+		const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+		if (gator_cpu->pmnc_name != NULL &&
+		    /* Do the names match exactly? */
+		    (strcasecmp(gator_cpu->pmnc_name, name) == 0 ||
+		     /* Do these names match but have the old vs new prefix? */
+		     ((strncasecmp(name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) == 0 &&
+		       strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) == 0 &&
+		       strcasecmp(name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) == 0))))
+			return gator_cpu;
+	}
+
+	return NULL;
+}
+
+u32 gator_cpuid(void)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	u32 val;
+#if !defined(__aarch64__)
+	asm volatile("mrc p15, 0, %0, c0, c0, 0" : "=r" (val));
+#else
+	asm volatile("mrs %0, midr_el1" : "=r" (val));
+#endif
+	return (val >> 4) & 0xfff;
+#else
+	return OTHER;
+#endif
+}
+
+static void gator_buffer_wake_up(unsigned long data)
+{
+	wake_up(&gator_buffer_wait);
+}
+
+static int gator_buffer_wake_func(void *data)
+{
+	for (;;) {
+		if (down_killable(&gator_buffer_wake_sem))
+			break;
+
+		/* Eat up any pending events */
+		while (!down_trylock(&gator_buffer_wake_sem))
+			;
+
+		if (!gator_buffer_wake_run)
+			break;
+
+		gator_buffer_wake_up(0);
+	}
+
+	return 0;
+}
+
+/******************************************************************************
+ * Commit interface
+ ******************************************************************************/
+static bool buffer_commit_ready(int *cpu, int *buftype)
+{
+	int cpu_x, x;
+
+	for_each_present_cpu(cpu_x) {
+		for (x = 0; x < NUM_GATOR_BUFS; x++)
+			if (per_cpu(gator_buffer_commit, cpu_x)[x] != per_cpu(gator_buffer_read, cpu_x)[x]) {
+				*cpu = cpu_x;
+				*buftype = x;
+				return true;
+			}
+	}
+	*cpu = -1;
+	*buftype = -1;
+	return false;
+}
+
+/******************************************************************************
+ * hrtimer interrupt processing
+ ******************************************************************************/
+static void gator_timer_interrupt(void)
+{
+	struct pt_regs *const regs = get_irq_regs();
+
+	gator_backtrace_handler(regs);
+}
+
+void gator_backtrace_handler(struct pt_regs *const regs)
+{
+	u64 time = gator_get_time();
+	int cpu = get_physical_cpu();
+
+	/* Output backtrace */
+	gator_add_sample(cpu, regs, time);
+
+	/* Collect counters */
+	if (!per_cpu(collecting, cpu))
+		collect_counters(time, current, false);
+
+	/* No buffer flushing occurs during sched switch for RT-Preempt full. The block counter frame will be flushed by collect_counters, but the sched buffer needs to be explicitly flushed */
+#ifdef CONFIG_PREEMPT_RT_FULL
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+#endif
+}
+
+static int gator_running;
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_offline(void *migrate)
+{
+	struct gator_interface *gi;
+	int i, len, cpu = get_physical_cpu();
+	int *buffer;
+	u64 time;
+
+	gator_trace_sched_offline();
+	gator_trace_power_offline();
+
+	if (!migrate)
+		gator_hrtimer_offline();
+
+	/* Offline any events and output counters */
+	time = gator_get_time();
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->offline) {
+				len = gi->offline(&buffer, migrate);
+				marshal_event(len, buffer);
+			}
+		}
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+	}
+
+	/* Flush all buffers on this core */
+	for (i = 0; i < NUM_GATOR_BUFS; i++)
+		gator_commit_buffer(cpu, i, time);
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_offline_dispatch(int cpu, bool migrate)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->offline_dispatch)
+			gi->offline_dispatch(cpu, migrate);
+	}
+}
+
+static void gator_timer_stop(void)
+{
+	int cpu;
+
+	if (gator_running) {
+		on_each_cpu(gator_timer_offline, NULL, 1);
+		for_each_online_cpu(cpu) {
+			gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+
+		gator_running = 0;
+		gator_hrtimer_shutdown();
+	}
+}
+
+static void gator_send_core_name(const int cpu, const u32 cpuid)
+{
+#if defined(__arm__) || defined(__aarch64__)
+	if (!sent_core_name[cpu] || (cpuid != gator_cpuids[cpu])) {
+		const struct gator_cpu *const gator_cpu = gator_find_cpu_by_cpuid(cpuid);
+		const char *core_name = NULL;
+		char core_name_buf[32];
+
+		/* Save off this cpuid */
+		gator_cpuids[cpu] = cpuid;
+		if (gator_cpu != NULL) {
+			core_name = gator_cpu->core_name;
+		} else {
+			if (cpuid == -1)
+				snprintf(core_name_buf, sizeof(core_name_buf), "Unknown");
+			else
+				snprintf(core_name_buf, sizeof(core_name_buf), "Unknown (0x%.3x)", cpuid);
+			core_name = core_name_buf;
+		}
+
+		marshal_core_name(cpu, cpuid, core_name);
+		sent_core_name[cpu] = true;
+	}
+#endif
+}
+
+static void gator_read_cpuid(void *arg)
+{
+	gator_cpuids[get_physical_cpu()] = gator_cpuid();
+}
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_online(void *migrate)
+{
+	struct gator_interface *gi;
+	int len, cpu = get_physical_cpu();
+	int *buffer;
+	u64 time;
+
+	/* Send what is currently running on this core */
+	marshal_sched_trace_switch(current->pid, 0);
+
+	gator_trace_power_online();
+
+	/* online any events and output counters */
+	time = gator_get_time();
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->online) {
+				len = gi->online(&buffer, migrate);
+				marshal_event(len, buffer);
+			}
+		}
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+	}
+
+	if (!migrate)
+		gator_hrtimer_online();
+
+	gator_send_core_name(cpu, gator_cpuid());
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_online_dispatch(int cpu, bool migrate)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->online_dispatch)
+			gi->online_dispatch(cpu, migrate);
+	}
+}
+
+#include "gator_iks.c"
+
+static int gator_timer_start(unsigned long sample_rate)
+{
+	int cpu;
+
+	if (gator_running) {
+		pr_notice("gator: already running\n");
+		return 0;
+	}
+
+	gator_running = 1;
+
+	/* event based sampling trumps hr timer based sampling */
+	if (event_based_sampling)
+		sample_rate = 0;
+
+	if (gator_hrtimer_init(sample_rate, gator_timer_interrupt) == -1)
+		return -1;
+
+	/* Send off the previously saved cpuids */
+	for_each_present_cpu(cpu) {
+		preempt_disable();
+		gator_send_core_name(cpu, gator_cpuids[cpu]);
+		preempt_enable();
+	}
+
+	gator_send_iks_core_names();
+	for_each_online_cpu(cpu) {
+		gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+	}
+	on_each_cpu(gator_timer_online, NULL, 1);
+
+	return 0;
+}
+
+static u64 gator_get_time(void)
+{
+	struct timespec ts;
+	u64 timestamp;
+	u64 prev_timestamp;
+	u64 delta;
+	int cpu = smp_processor_id();
+
+	/* Match clock_gettime(CLOCK_MONOTONIC_RAW, &ts) from userspace */
+	getrawmonotonic(&ts);
+	timestamp = timespec_to_ns(&ts);
+
+	/* getrawmonotonic is not monotonic on all systems. Detect and
+	 * attempt to correct these cases. up to 0.5ms delta has been seen
+	 * on some systems, which can skew Streamline data when viewing at
+	 * high resolution. This doesn't work well with interrupts, but that
+	 * it's OK - the real concern is to catch big jumps in time
+	 */
+	prev_timestamp = per_cpu(last_timestamp, cpu);
+	if (prev_timestamp <= timestamp) {
+		per_cpu(last_timestamp, cpu) = timestamp;
+	} else {
+		delta = prev_timestamp - timestamp;
+		/* Log the error once */
+		if (!printed_monotonic_warning && delta > 500000) {
+			pr_err("%s: getrawmonotonic is not monotonic  cpu: %i  delta: %lli\nSkew in Streamline data may be present at the fine zoom levels\n", __func__, cpu, delta);
+			printed_monotonic_warning = true;
+		}
+		timestamp = prev_timestamp;
+	}
+
+	return timestamp - gator_monotonic_started;
+}
+
+static void gator_emit_perf_time(u64 time)
+{
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 10, 0)
+	if (time >= gator_sync_time) {
+		int cpu = get_physical_cpu();
+
+		marshal_event_single64(0, -1, local_clock());
+		gator_sync_time += NSEC_PER_SEC;
+		gator_commit_buffer(cpu, COUNTER_BUF, time);
+	}
+#endif
+}
+
+/******************************************************************************
+ * cpu hotplug and pm notifiers
+ ******************************************************************************/
+static int __cpuinit gator_hotcpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	int cpu = lcpu_to_pcpu((long)hcpu);
+
+	switch (action) {
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		smp_call_function_single(cpu, gator_timer_offline, NULL, 1);
+		gator_timer_offline_dispatch(cpu, false);
+		break;
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		gator_timer_online_dispatch(cpu, false);
+		smp_call_function_single(cpu, gator_timer_online, NULL, 1);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __refdata gator_hotcpu_notifier = {
+	.notifier_call = gator_hotcpu_notify,
+};
+
+/* n.b. calling "on_each_cpu" only runs on those that are online.
+ * Registered linux events are not disabled, so their counters will
+ * continue to collect
+ */
+static int gator_pm_notify(struct notifier_block *nb, unsigned long event, void *dummy)
+{
+	int cpu;
+	struct timespec ts;
+
+	switch (event) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+		unregister_scheduler_tracepoints();
+		on_each_cpu(gator_timer_offline, NULL, 1);
+		for_each_online_cpu(cpu) {
+			gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+
+		/* Record the wallclock hibernate time */
+		getnstimeofday(&ts);
+		gator_hibernate_time = timespec_to_ns(&ts) - gator_get_time();
+		break;
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		/* Adjust gator_monotonic_started for the time spent sleeping, as gator_get_time does not account for it */
+		if (gator_hibernate_time > 0) {
+			getnstimeofday(&ts);
+			gator_monotonic_started += gator_hibernate_time + gator_get_time() - timespec_to_ns(&ts);
+			gator_hibernate_time = 0;
+		}
+
+		for_each_online_cpu(cpu) {
+			gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+		}
+		on_each_cpu(gator_timer_online, NULL, 1);
+		register_scheduler_tracepoints();
+		register_hotcpu_notifier(&gator_hotcpu_notifier);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gator_pm_notifier = {
+	.notifier_call = gator_pm_notify,
+};
+
+static int gator_notifier_start(void)
+{
+	int retval;
+
+	retval = register_hotcpu_notifier(&gator_hotcpu_notifier);
+	if (retval == 0)
+		retval = register_pm_notifier(&gator_pm_notifier);
+	return retval;
+}
+
+static void gator_notifier_stop(void)
+{
+	unregister_pm_notifier(&gator_pm_notifier);
+	unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+}
+
+/******************************************************************************
+ * Main
+ ******************************************************************************/
+static void gator_summary(void)
+{
+	u64 timestamp, uptime;
+	struct timespec ts;
+	char uname_buf[512];
+
+	snprintf(uname_buf, sizeof(uname_buf), "%s %s %s %s %s GNU/Linux", utsname()->sysname, utsname()->nodename, utsname()->release, utsname()->version, utsname()->machine);
+
+	getnstimeofday(&ts);
+	timestamp = timespec_to_ns(&ts);
+
+	/* Similar to reading /proc/uptime from fs/proc/uptime.c, calculate uptime */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 11, 0)
+	{
+		void (*m2b)(struct timespec *ts);
+
+		do_posix_clock_monotonic_gettime(&ts);
+		/* monotonic_to_bootbased is not defined for some versions of Android */
+		m2b = symbol_get(monotonic_to_bootbased);
+		if (m2b)
+			m2b(&ts);
+	}
+#else
+	get_monotonic_boottime(&ts);
+#endif
+	uptime = timespec_to_ns(&ts);
+
+	/* Disable preemption as gator_get_time calls smp_processor_id to verify time is monotonic */
+	preempt_disable();
+	/* Set monotonic_started to zero as gator_get_time is uptime minus monotonic_started */
+	gator_monotonic_started = 0;
+	gator_monotonic_started = gator_get_time();
+
+	marshal_summary(timestamp, uptime, gator_monotonic_started, uname_buf);
+	gator_sync_time = 0;
+	gator_emit_perf_time(gator_monotonic_started);	
+	preempt_enable();
+}
+
+int gator_events_install(struct gator_interface *interface)
+{
+	list_add_tail(&interface->list, &gator_events);
+
+	return 0;
+}
+
+int gator_events_get_key(void)
+{
+	/* key 0 is reserved as a timestamp. key 1 is reserved as the marker
+	 * for thread specific counters. key 2 is reserved as the marker for
+	 * core. Odd keys are assigned by the driver, even keys by the
+	 * daemon.
+	 */
+	static int key = 3;
+	const int ret = key;
+
+	key += 2;
+	return ret;
+}
+
+static int gator_init(void)
+{
+	int i;
+
+	calc_first_cluster_size();
+
+	/* events sources */
+	for (i = 0; i < ARRAY_SIZE(gator_events_list); i++)
+		if (gator_events_list[i])
+			gator_events_list[i]();
+
+	gator_trace_sched_init();
+	gator_trace_power_init();
+
+	return 0;
+}
+
+static void gator_exit(void)
+{
+	struct gator_interface *gi;
+
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->shutdown)
+			gi->shutdown();
+}
+
+static int gator_start(void)
+{
+	unsigned long cpu, i;
+	struct gator_interface *gi;
+
+	gator_buffer_wake_run = true;
+	gator_buffer_wake_thread = kthread_run(gator_buffer_wake_func, NULL, "gator_bwake");
+	if (IS_ERR(gator_buffer_wake_thread))
+		goto bwake_failure;
+
+	if (gator_migrate_start())
+		goto migrate_failure;
+
+	/* Initialize the buffer with the frame type and core */
+	for_each_present_cpu(cpu) {
+		for (i = 0; i < NUM_GATOR_BUFS; i++)
+			marshal_frame(cpu, i);
+		per_cpu(last_timestamp, cpu) = 0;
+	}
+	printed_monotonic_warning = false;
+
+	/* Capture the start time */
+	gator_summary();
+
+	/* start all events */
+	list_for_each_entry(gi, &gator_events, list) {
+		if (gi->start && gi->start() != 0) {
+			struct list_head *ptr = gi->list.prev;
+
+			while (ptr != &gator_events) {
+				gi = list_entry(ptr, struct gator_interface, list);
+
+				if (gi->stop)
+					gi->stop();
+
+				ptr = ptr->prev;
+			}
+			goto events_failure;
+		}
+	}
+
+	/* cookies shall be initialized before trace_sched_start() and gator_timer_start() */
+	if (cookies_initialize())
+		goto cookies_failure;
+	if (gator_annotate_start())
+		goto annotate_failure;
+	if (gator_trace_sched_start())
+		goto sched_failure;
+	if (gator_trace_power_start())
+		goto power_failure;
+	if (gator_trace_gpu_start())
+		goto gpu_failure;
+	if (gator_timer_start(gator_timer_count))
+		goto timer_failure;
+	if (gator_notifier_start())
+		goto notifier_failure;
+
+	return 0;
+
+notifier_failure:
+	gator_timer_stop();
+timer_failure:
+	gator_trace_gpu_stop();
+gpu_failure:
+	gator_trace_power_stop();
+power_failure:
+	gator_trace_sched_stop();
+sched_failure:
+	gator_annotate_stop();
+annotate_failure:
+	cookies_release();
+cookies_failure:
+	/* stop all events */
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->stop)
+			gi->stop();
+events_failure:
+	gator_migrate_stop();
+migrate_failure:
+	gator_buffer_wake_run = false;
+	up(&gator_buffer_wake_sem);
+	gator_buffer_wake_thread = NULL;
+bwake_failure:
+
+	return -1;
+}
+
+static void gator_stop(void)
+{
+	struct gator_interface *gi;
+
+	gator_annotate_stop();
+	gator_trace_sched_stop();
+	gator_trace_power_stop();
+	gator_trace_gpu_stop();
+
+	/* stop all interrupt callback reads before tearing down other interfaces */
+	gator_notifier_stop();	/* should be called before gator_timer_stop to avoid re-enabling the hrtimer after it has been offlined */
+	gator_timer_stop();
+
+	/* stop all events */
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->stop)
+			gi->stop();
+
+	gator_migrate_stop();
+
+	gator_buffer_wake_run = false;
+	up(&gator_buffer_wake_sem);
+	gator_buffer_wake_thread = NULL;
+}
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+/* fopen("buffer") */
+static int gator_op_setup(void)
+{
+	int err = 0;
+	int cpu, i;
+
+	mutex_lock(&start_mutex);
+
+	gator_buffer_size[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE;
+	gator_buffer_mask[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE - 1;
+
+	gator_buffer_size[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE;
+	gator_buffer_mask[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[NAME_BUF] = NAME_BUFFER_SIZE;
+	gator_buffer_mask[NAME_BUF] = NAME_BUFFER_SIZE - 1;
+
+	gator_buffer_size[COUNTER_BUF] = COUNTER_BUFFER_SIZE;
+	gator_buffer_mask[COUNTER_BUF] = COUNTER_BUFFER_SIZE - 1;
+
+	gator_buffer_size[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE;
+	gator_buffer_mask[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE - 1;
+
+	gator_buffer_size[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE;
+	gator_buffer_mask[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE;
+	gator_buffer_mask[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[IDLE_BUF] = IDLE_BUFFER_SIZE;
+	gator_buffer_mask[IDLE_BUF] = IDLE_BUFFER_SIZE - 1;
+
+	gator_buffer_size[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE;
+	gator_buffer_mask[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE - 1;
+
+	/* Initialize percpu per buffer variables */
+	for (i = 0; i < NUM_GATOR_BUFS; i++) {
+		/* Verify buffers are a power of 2 */
+		if (gator_buffer_size[i] & (gator_buffer_size[i] - 1)) {
+			err = -ENOEXEC;
+			goto setup_error;
+		}
+
+		for_each_present_cpu(cpu) {
+			per_cpu(gator_buffer_read, cpu)[i] = 0;
+			per_cpu(gator_buffer_write, cpu)[i] = 0;
+			per_cpu(gator_buffer_commit, cpu)[i] = 0;
+			per_cpu(buffer_space_available, cpu)[i] = true;
+			per_cpu(gator_buffer_commit_time, cpu) = gator_live_rate;
+
+			/* Annotation is a special case that only uses a single buffer */
+			if (cpu > 0 && i == ANNOTATE_BUF) {
+				per_cpu(gator_buffer, cpu)[i] = NULL;
+				continue;
+			}
+
+			per_cpu(gator_buffer, cpu)[i] = vmalloc(gator_buffer_size[i]);
+			if (!per_cpu(gator_buffer, cpu)[i]) {
+				err = -ENOMEM;
+				goto setup_error;
+			}
+		}
+	}
+
+setup_error:
+	mutex_unlock(&start_mutex);
+	return err;
+}
+
+/* Actually start profiling (echo 1>/dev/gator/enable) */
+static int gator_op_start(void)
+{
+	int err = 0;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started || gator_start())
+		err = -EINVAL;
+	else
+		gator_started = 1;
+
+	mutex_unlock(&start_mutex);
+
+	return err;
+}
+
+/* echo 0>/dev/gator/enable */
+static void gator_op_stop(void)
+{
+	mutex_lock(&start_mutex);
+
+	if (gator_started) {
+		gator_stop();
+
+		mutex_lock(&gator_buffer_mutex);
+
+		gator_started = 0;
+		gator_monotonic_started = 0;
+		cookies_release();
+		wake_up(&gator_buffer_wait);
+
+		mutex_unlock(&gator_buffer_mutex);
+	}
+
+	mutex_unlock(&start_mutex);
+}
+
+static void gator_shutdown(void)
+{
+	int cpu, i;
+
+	mutex_lock(&start_mutex);
+
+	for_each_present_cpu(cpu) {
+		mutex_lock(&gator_buffer_mutex);
+		for (i = 0; i < NUM_GATOR_BUFS; i++) {
+			vfree(per_cpu(gator_buffer, cpu)[i]);
+			per_cpu(gator_buffer, cpu)[i] = NULL;
+			per_cpu(gator_buffer_read, cpu)[i] = 0;
+			per_cpu(gator_buffer_write, cpu)[i] = 0;
+			per_cpu(gator_buffer_commit, cpu)[i] = 0;
+			per_cpu(buffer_space_available, cpu)[i] = true;
+			per_cpu(gator_buffer_commit_time, cpu) = 0;
+		}
+		mutex_unlock(&gator_buffer_mutex);
+	}
+
+	memset(&sent_core_name, 0, sizeof(sent_core_name));
+
+	mutex_unlock(&start_mutex);
+}
+
+static int gator_set_backtrace(unsigned long val)
+{
+	int err = 0;
+
+	mutex_lock(&start_mutex);
+
+	if (gator_started)
+		err = -EBUSY;
+	else
+		gator_backtrace_depth = val;
+
+	mutex_unlock(&start_mutex);
+
+	return err;
+}
+
+static ssize_t enable_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	return gatorfs_ulong_to_user(gator_started, buf, count, offset);
+}
+
+static ssize_t enable_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	if (val)
+		retval = gator_op_start();
+	else
+		gator_op_stop();
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static const struct file_operations enable_fops = {
+	.read = enable_read,
+	.write = enable_write,
+};
+
+static int userspace_buffer_open(struct inode *inode, struct file *file)
+{
+	int err = -EPERM;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (test_and_set_bit_lock(0, &gator_buffer_opened))
+		return -EBUSY;
+
+	err = gator_op_setup();
+	if (err)
+		goto fail;
+
+	/* NB: the actual start happens from userspace
+	 * echo 1 >/dev/gator/enable
+	 */
+
+	return 0;
+
+fail:
+	__clear_bit_unlock(0, &gator_buffer_opened);
+	return err;
+}
+
+static int userspace_buffer_release(struct inode *inode, struct file *file)
+{
+	gator_op_stop();
+	gator_shutdown();
+	__clear_bit_unlock(0, &gator_buffer_opened);
+	return 0;
+}
+
+static ssize_t userspace_buffer_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	int commit, length1, length2, read;
+	char *buffer1;
+	char *buffer2;
+	int cpu, buftype;
+	int written = 0;
+
+	/* ensure there is enough space for a whole frame */
+	if (count < userspace_buffer_size || *offset)
+		return -EINVAL;
+
+	/* sleep until the condition is true or a signal is received the
+	 * condition is checked each time gator_buffer_wait is woken up
+	 */
+	wait_event_interruptible(gator_buffer_wait, buffer_commit_ready(&cpu, &buftype) || !gator_started);
+
+	if (signal_pending(current))
+		return -EINTR;
+
+	if (buftype == -1 || cpu == -1)
+		return 0;
+
+	mutex_lock(&gator_buffer_mutex);
+
+	do {
+		read = per_cpu(gator_buffer_read, cpu)[buftype];
+		commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+
+		/* May happen if the buffer is freed during pending reads. */
+		if (!per_cpu(gator_buffer, cpu)[buftype])
+			break;
+
+		/* determine the size of two halves */
+		length1 = commit - read;
+		length2 = 0;
+		buffer1 = &(per_cpu(gator_buffer, cpu)[buftype][read]);
+		buffer2 = &(per_cpu(gator_buffer, cpu)[buftype][0]);
+		if (length1 < 0) {
+			length1 = gator_buffer_size[buftype] - read;
+			length2 = commit;
+		}
+
+		if (length1 + length2 > count - written)
+			break;
+
+		/* start, middle or end */
+		if (length1 > 0 && copy_to_user(&buf[written], buffer1, length1))
+			break;
+
+		/* possible wrap around */
+		if (length2 > 0 && copy_to_user(&buf[written + length1], buffer2, length2))
+			break;
+
+		per_cpu(gator_buffer_read, cpu)[buftype] = commit;
+		written += length1 + length2;
+
+		/* Wake up annotate_write if more space is available */
+		if (buftype == ANNOTATE_BUF)
+			wake_up(&gator_annotate_wait);
+	} while (buffer_commit_ready(&cpu, &buftype));
+
+	mutex_unlock(&gator_buffer_mutex);
+
+	/* kick just in case we've lost an SMP event */
+	wake_up(&gator_buffer_wait);
+
+	return written > 0 ? written : -EFAULT;
+}
+
+static const struct file_operations gator_event_buffer_fops = {
+	.open = userspace_buffer_open,
+	.release = userspace_buffer_release,
+	.read = userspace_buffer_read,
+};
+
+static ssize_t depth_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+	return gatorfs_ulong_to_user(gator_backtrace_depth, buf, count, offset);
+}
+
+static ssize_t depth_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = gatorfs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	retval = gator_set_backtrace(val);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+static const struct file_operations depth_fops = {
+	.read = depth_read,
+	.write = depth_write
+};
+
+static void gator_op_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	struct gator_interface *gi;
+	int cpu;
+
+	/* reinitialize default values */
+	gator_cpu_cores = 0;
+	for_each_present_cpu(cpu) {
+		gator_cpu_cores++;
+	}
+	userspace_buffer_size = BACKTRACE_BUFFER_SIZE;
+	gator_response_type = 1;
+	gator_live_rate = 0;
+
+	gatorfs_create_file(sb, root, "enable", &enable_fops);
+	gatorfs_create_file(sb, root, "buffer", &gator_event_buffer_fops);
+	gatorfs_create_file(sb, root, "backtrace_depth", &depth_fops);
+	gatorfs_create_ro_ulong(sb, root, "cpu_cores", &gator_cpu_cores);
+	gatorfs_create_ro_ulong(sb, root, "buffer_size", &userspace_buffer_size);
+	gatorfs_create_ulong(sb, root, "tick", &gator_timer_count);
+	gatorfs_create_ulong(sb, root, "response_type", &gator_response_type);
+	gatorfs_create_ro_ulong(sb, root, "version", &gator_protocol_version);
+	gatorfs_create_ro_u64(sb, root, "started", &gator_monotonic_started);
+	gatorfs_create_u64(sb, root, "live_rate", &gator_live_rate);
+
+	/* Annotate interface */
+	gator_annotate_create_files(sb, root);
+
+	/* Linux Events */
+	dir = gatorfs_mkdir(sb, root, "events");
+	list_for_each_entry(gi, &gator_events, list)
+		if (gi->create_files)
+			gi->create_files(sb, dir);
+
+	/* Sched Events */
+	sched_trace_create_files(sb, dir);
+
+	/* Power interface */
+	gator_trace_power_create_files(sb, dir);
+}
+
+/******************************************************************************
+ * Module
+ ******************************************************************************/
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 15, 0)
+
+#define GATOR_TRACEPOINTS \
+	GATOR_HANDLE_TRACEPOINT(block_rq_complete); \
+	GATOR_HANDLE_TRACEPOINT(cpu_frequency); \
+	GATOR_HANDLE_TRACEPOINT(cpu_idle); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_begin); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_current); \
+	GATOR_HANDLE_TRACEPOINT(cpu_migrate_finish); \
+	GATOR_HANDLE_TRACEPOINT(irq_handler_exit); \
+	GATOR_HANDLE_TRACEPOINT(mali_hw_counter); \
+	GATOR_HANDLE_TRACEPOINT(mali_job_slots_event); \
+	GATOR_HANDLE_TRACEPOINT(mali_mmu_as_in_use); \
+	GATOR_HANDLE_TRACEPOINT(mali_mmu_as_released); \
+	GATOR_HANDLE_TRACEPOINT(mali_page_fault_insert_pages); \
+	GATOR_HANDLE_TRACEPOINT(mali_pm_status); \
+	GATOR_HANDLE_TRACEPOINT(mali_sw_counter); \
+	GATOR_HANDLE_TRACEPOINT(mali_sw_counters); \
+	GATOR_HANDLE_TRACEPOINT(mali_timeline_event); \
+	GATOR_HANDLE_TRACEPOINT(mali_total_alloc_pages_change); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_alloc); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_free); \
+	GATOR_HANDLE_TRACEPOINT(mm_page_free_batched); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_exec); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_fork); \
+	GATOR_HANDLE_TRACEPOINT(sched_process_free); \
+	GATOR_HANDLE_TRACEPOINT(sched_switch); \
+	GATOR_HANDLE_TRACEPOINT(softirq_exit); \
+	GATOR_HANDLE_TRACEPOINT(task_rename); \
+
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+	struct tracepoint *gator_tracepoint_##probe_name
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+
+static void gator_save_tracepoint(struct tracepoint *tp, void *priv)
+{
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+	do { \
+		if (strcmp(tp->name, #probe_name) == 0) { \
+			gator_tracepoint_##probe_name = tp; \
+			return; \
+		} \
+	} while (0)
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+}
+
+#else
+
+#define for_each_kernel_tracepoint(fct, priv)
+
+#endif
+
+static int __init gator_module_init(void)
+{
+	for_each_kernel_tracepoint(gator_save_tracepoint, NULL);
+
+	if (gatorfs_register())
+		return -1;
+
+	if (gator_init()) {
+		gatorfs_unregister();
+		return -1;
+	}
+
+	setup_timer(&gator_buffer_wake_up_timer, gator_buffer_wake_up, 0);
+
+	/* Initialize the list of cpuids */
+	memset(gator_cpuids, -1, sizeof(gator_cpuids));
+	on_each_cpu(gator_read_cpuid, NULL, 1);
+
+	return 0;
+}
+
+static void __exit gator_module_exit(void)
+{
+	del_timer_sync(&gator_buffer_wake_up_timer);
+	tracepoint_synchronize_unregister();
+	gator_exit();
+	gatorfs_unregister();
+}
+
+module_init(gator_module_init);
+module_exit(gator_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("ARM Ltd");
+MODULE_DESCRIPTION("Gator system profiler");
+#define STRIFY2(ARG) #ARG
+#define STRIFY(ARG) STRIFY2(ARG)
+MODULE_VERSION(STRIFY(PROTOCOL_VERSION));
diff --git a/drivers/gator/gator_marshaling.c b/drivers/gator/gator_marshaling.c
new file mode 100644
index 000000000000..0d1167643642
--- /dev/null
+++ b/drivers/gator/gator_marshaling.c
@@ -0,0 +1,371 @@
+/**
+ * Copyright (C) ARM Limited 2012-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define NEWLINE_CANARY \
+	/* Unix */ \
+	"1\n" \
+	/* Windows */ \
+	"2\r\n" \
+	/* Mac OS */ \
+	"3\r" \
+	/* RISC OS */ \
+	"4\n\r" \
+	/* Add another character so the length isn't 0x0a bytes */ \
+	"5"
+
+#ifdef MALI_SUPPORT
+#include "gator_events_mali_common.h"
+#endif
+
+static void marshal_summary(long long timestamp, long long uptime, long long monotonic_delta, const char *uname)
+{
+	unsigned long flags;
+	int cpu = 0;
+
+	local_irq_save(flags);
+	gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_SUMMARY);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, NEWLINE_CANARY);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, timestamp);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, uptime);
+	gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, monotonic_delta);
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "uname");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, uname);
+#if GATOR_IKS_SUPPORT
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "iks");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RTB
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rtb");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rt_full");
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+	/* Let Streamline know which GPU is used so that it can label the GPU Activity appropriately. This is a temporary fix, to be improved in a future release. */
+#ifdef MALI_SUPPORT
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "mali_type");
+#if (MALI_SUPPORT == MALI_4xx)
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "4xx");
+#elif (MALI_SUPPORT == MALI_MIDGARD)
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "6xx");
+#else
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "unknown");
+#endif
+#endif
+	gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+	/* Commit the buffer now so it can be one of the first frames read by Streamline */
+	local_irq_restore(flags);
+	gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+
+static bool marshal_cookie_header(const char *text)
+{
+	int cpu = get_physical_cpu();
+
+	return buffer_check_space(cpu, NAME_BUF, strlen(text) + 3 * MAXSIZE_PACK32);
+}
+
+static void marshal_cookie(int cookie, const char *text)
+{
+	int cpu = get_physical_cpu();
+	/* buffer_check_space already called by marshal_cookie_header */
+	gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_COOKIE);
+	gator_buffer_write_packed_int(cpu, NAME_BUF, cookie);
+	gator_buffer_write_string(cpu, NAME_BUF, text);
+	buffer_check(cpu, NAME_BUF, gator_get_time());
+}
+
+static void marshal_thread_name(int pid, char *name)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, NAME_BUF, TASK_COMM_LEN + 3 * MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_THREAD_NAME);
+		gator_buffer_write_packed_int64(cpu, NAME_BUF, time);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, pid);
+		gator_buffer_write_string(cpu, NAME_BUF, name);
+	}
+	local_irq_restore(flags);
+	buffer_check(cpu, NAME_BUF, time);
+}
+
+static void marshal_link(int cookie, int tgid, int pid)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, NAME_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_LINK);
+		gator_buffer_write_packed_int64(cpu, NAME_BUF, time);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, cookie);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, tgid);
+		gator_buffer_write_packed_int(cpu, NAME_BUF, pid);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, NAME_BUF, time);
+}
+
+static bool marshal_backtrace_header(int exec_cookie, int tgid, int pid, u64 time)
+{
+	int cpu = get_physical_cpu();
+
+	if (!buffer_check_space(cpu, BACKTRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32 + gator_backtrace_depth * 2 * MAXSIZE_PACK32)) {
+		/* Check and commit; commit is set to occur once buffer is 3/4 full */
+		buffer_check(cpu, BACKTRACE_BUF, time);
+
+		return false;
+	}
+
+	gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, time);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, exec_cookie);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, tgid);
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, pid);
+
+	return true;
+}
+
+static void marshal_backtrace(unsigned long address, int cookie, int in_kernel)
+{
+	int cpu = get_physical_cpu();
+
+	if (cookie == 0 && !in_kernel)
+		cookie = UNRESOLVED_COOKIE;
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, cookie);
+	gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, address);
+}
+
+static void marshal_backtrace_footer(u64 time)
+{
+	int cpu = get_physical_cpu();
+
+	gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, MESSAGE_END_BACKTRACE);
+
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, BACKTRACE_BUF, time);
+}
+
+static bool marshal_event_header(u64 time)
+{
+	unsigned long flags, cpu = get_physical_cpu();
+	bool retval = false;
+
+	local_irq_save(flags);
+	if (buffer_check_space(cpu, BLOCK_COUNTER_BUF, MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, 0);	/* key of zero indicates a timestamp */
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, time);
+		retval = true;
+	}
+	local_irq_restore(flags);
+
+	return retval;
+}
+
+static void marshal_event(int len, int *buffer)
+{
+	unsigned long i, flags, cpu = get_physical_cpu();
+
+	if (len <= 0)
+		return;
+
+	/* length must be even since all data is a (key, value) pair */
+	if (len & 0x1) {
+		pr_err("gator: invalid counter data detected and discarded\n");
+		return;
+	}
+
+	/* events must be written in key,value pairs */
+	local_irq_save(flags);
+	for (i = 0; i < len; i += 2) {
+		if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK32))
+			break;
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i]);
+		gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i + 1]);
+	}
+	local_irq_restore(flags);
+}
+
+static void marshal_event64(int len, long long *buffer64)
+{
+	unsigned long i, flags, cpu = get_physical_cpu();
+
+	if (len <= 0)
+		return;
+
+	/* length must be even since all data is a (key, value) pair */
+	if (len & 0x1) {
+		pr_err("gator: invalid counter data detected and discarded\n");
+		return;
+	}
+
+	/* events must be written in key,value pairs */
+	local_irq_save(flags);
+	for (i = 0; i < len; i += 2) {
+		if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK64))
+			break;
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i]);
+		gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i + 1]);
+	}
+	local_irq_restore(flags);
+}
+
+static void __maybe_unused marshal_event_single(int core, int key, int value)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, COUNTER_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, value);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void __maybe_unused marshal_event_single64(int core, int key, long long value)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, COUNTER_BUF, 2 * MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+		gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+		gator_buffer_write_packed_int64(cpu, COUNTER_BUF, value);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void marshal_sched_trace_switch(int pid, int state)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_SWITCH);
+		gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, state);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+static void marshal_sched_trace_exit(int tgid, int pid)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_EXIT);
+		gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+		gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+#if GATOR_CPU_FREQ_SUPPORT
+static void marshal_idle(int core, int state)
+{
+	unsigned long flags, cpu;
+	u64 time;
+
+	local_irq_save(flags);
+	cpu = get_physical_cpu();
+	time = gator_get_time();
+	if (buffer_check_space(cpu, IDLE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, IDLE_BUF, state);
+		gator_buffer_write_packed_int64(cpu, IDLE_BUF, time);
+		gator_buffer_write_packed_int(cpu, IDLE_BUF, core);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, IDLE_BUF, time);
+}
+#endif
+
+#if defined(__arm__) || defined(__aarch64__)
+static void marshal_core_name(const int core, const int cpuid, const char *name)
+{
+	int cpu = get_physical_cpu();
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (buffer_check_space(cpu, SUMMARY_BUF, MAXSIZE_PACK32 + MAXSIZE_CORE_NAME)) {
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_CORE_NAME);
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, core);
+		gator_buffer_write_packed_int(cpu, SUMMARY_BUF, cpuid);
+		gator_buffer_write_string(cpu, SUMMARY_BUF, name);
+	}
+	/* Commit core names now so that they can show up in live */
+	local_irq_restore(flags);
+	gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+#endif
+
+static void marshal_activity_switch(int core, int key, int activity, int pid, int state)
+{
+	unsigned long cpu = get_physical_cpu(), flags;
+	u64 time;
+
+	if (!per_cpu(gator_buffer, cpu)[ACTIVITY_BUF])
+		return;
+
+	local_irq_save(flags);
+	time = gator_get_time();
+	if (buffer_check_space(cpu, ACTIVITY_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, MESSAGE_SWITCH);
+		gator_buffer_write_packed_int64(cpu, ACTIVITY_BUF, time);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, core);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, key);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, activity);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, pid);
+		gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, state);
+	}
+	local_irq_restore(flags);
+	/* Check and commit; commit is set to occur once buffer is 3/4 full */
+	buffer_check(cpu, ACTIVITY_BUF, time);
+}
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid)
+{
+	/* state is reserved for cpu use only */
+	marshal_activity_switch(core, key, activity, pid, 0);
+}
diff --git a/drivers/gator/gator_trace_gpu.c b/drivers/gator/gator_trace_gpu.c
new file mode 100644
index 000000000000..5de9152e365a
--- /dev/null
+++ b/drivers/gator/gator_trace_gpu.c
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#ifdef MALI_SUPPORT
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+#endif
+
+/*
+ * Taken from MALI_PROFILING_EVENT_TYPE_* items in Mali DDK.
+ */
+#define EVENT_TYPE_SINGLE  0
+#define EVENT_TYPE_START   1
+#define EVENT_TYPE_STOP    2
+#define EVENT_TYPE_SUSPEND 3
+#define EVENT_TYPE_RESUME  4
+
+/* Note whether tracepoints have been registered */
+static int mali_timeline_trace_registered;
+static int mali_job_slots_trace_registered;
+
+enum {
+	GPU_UNIT_NONE = 0,
+	GPU_UNIT_VP,
+	GPU_UNIT_FP,
+	GPU_UNIT_CL,
+	NUMBER_OF_GPU_UNITS
+};
+
+#if defined(MALI_SUPPORT)
+
+struct mali_activity {
+	int core;
+	int key;
+	int count;
+	int last_activity;
+	int last_pid;
+};
+
+#define NUMBER_OF_GPU_CORES 16
+static struct mali_activity mali_activities[NUMBER_OF_GPU_UNITS*NUMBER_OF_GPU_CORES];
+static DEFINE_SPINLOCK(mali_activities_lock);
+
+/* Only one event should be running on a unit and core at a time (ie,
+ * a start event can only be followed by a stop and vice versa), but
+ * because the kernel only knows when a job is enqueued and not
+ * started, it is possible for a start1, start2, stop1, stop2. Change
+ * it back into start1, stop1, start2, stop2 by queueing up start2 and
+ * releasing it when stop1 is received.
+ */
+
+static int mali_activity_index(int core, int key)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mali_activities); ++i) {
+		if ((mali_activities[i].core == core) && (mali_activities[i].key == key))
+			break;
+		if ((mali_activities[i].core == 0) && (mali_activities[i].key == 0)) {
+			mali_activities[i].core = core;
+			mali_activities[i].key = key;
+			break;
+		}
+	}
+	BUG_ON(i >= ARRAY_SIZE(mali_activities));
+
+	return i;
+}
+
+static void mali_activity_enqueue(int core, int key, int activity, int pid)
+{
+	int i;
+	int count;
+
+	spin_lock(&mali_activities_lock);
+	i = mali_activity_index(core, key);
+
+	count = mali_activities[i].count;
+	BUG_ON(count < 0);
+	++mali_activities[i].count;
+	if (count) {
+		mali_activities[i].last_activity = activity;
+		mali_activities[i].last_pid = pid;
+	}
+	spin_unlock(&mali_activities_lock);
+
+	if (!count)
+		gator_marshal_activity_switch(core, key, activity, pid);
+}
+
+static void mali_activity_stop(int core, int key)
+{
+	int i;
+	int count;
+	int last_activity = 0;
+	int last_pid = 0;
+
+	spin_lock(&mali_activities_lock);
+	i = mali_activity_index(core, key);
+
+	if (mali_activities[i].count == 0) {
+		spin_unlock(&mali_activities_lock);
+		return;
+	}
+	--mali_activities[i].count;
+	count = mali_activities[i].count;
+	if (count) {
+		last_activity = mali_activities[i].last_activity;
+		last_pid = mali_activities[i].last_pid;
+	}
+	spin_unlock(&mali_activities_lock);
+
+	gator_marshal_activity_switch(core, key, 0, 0);
+	if (count)
+		gator_marshal_activity_switch(core, key, last_activity, last_pid);
+}
+
+void mali_activity_clear(struct mali_counter mali_activity[], size_t mali_activity_size)
+{
+	int activity;
+	int cores;
+	int core;
+
+	for (activity = 0; activity < mali_activity_size; ++activity) {
+		cores = mali_activity[activity].cores;
+		if (cores < 0)
+			cores = 1;
+		for (core = 0; core < cores; ++core) {
+			if (mali_activity[activity].enabled) {
+				preempt_disable();
+				gator_marshal_activity_switch(core, mali_activity[activity].key, 0, 0);
+				preempt_enable();
+			}
+		}
+	}
+}
+
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+#include "gator_events_mali_4xx.h"
+
+/*
+ * Taken from MALI_PROFILING_EVENT_CHANNEL_* in Mali DDK.
+ */
+enum {
+	EVENT_CHANNEL_SOFTWARE = 0,
+	EVENT_CHANNEL_VP0 = 1,
+	EVENT_CHANNEL_FP0 = 5,
+	EVENT_CHANNEL_FP1,
+	EVENT_CHANNEL_FP2,
+	EVENT_CHANNEL_FP3,
+	EVENT_CHANNEL_FP4,
+	EVENT_CHANNEL_FP5,
+	EVENT_CHANNEL_FP6,
+	EVENT_CHANNEL_FP7,
+	EVENT_CHANNEL_GPU = 21
+};
+
+/**
+ * These events are applicable when the type MALI_PROFILING_EVENT_TYPE_SINGLE is used from the GPU channel
+ */
+enum {
+	EVENT_REASON_SINGLE_GPU_NONE = 0,
+	EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE = 1,
+};
+
+struct mali_counter mali_activity[2];
+
+GATOR_DEFINE_PROBE(mali_timeline_event, TP_PROTO(unsigned int event_id, unsigned int d0, unsigned int d1, unsigned int d2, unsigned int d3, unsigned int d4))
+{
+	unsigned int component, state;
+
+	/* do as much work as possible before disabling interrupts */
+	component = (event_id >> 16) & 0xFF;	/* component is an 8-bit field */
+	state = (event_id >> 24) & 0xF;	/* state is a 4-bit field */
+
+	switch (state) {
+	case EVENT_TYPE_START:
+		if (component == EVENT_CHANNEL_VP0) {
+			/* tgid = d0; pid = d1; */
+			if (mali_activity[1].enabled)
+				mali_activity_enqueue(0, mali_activity[1].key, 1, d1);
+		} else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+			/* tgid = d0; pid = d1; */
+			if (mali_activity[0].enabled)
+				mali_activity_enqueue(component - EVENT_CHANNEL_FP0, mali_activity[0].key, 1, d1);
+		}
+		break;
+
+	case EVENT_TYPE_STOP:
+		if (component == EVENT_CHANNEL_VP0) {
+			if (mali_activity[1].enabled)
+				mali_activity_stop(0, mali_activity[1].key);
+		} else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+			if (mali_activity[0].enabled)
+				mali_activity_stop(component - EVENT_CHANNEL_FP0, mali_activity[0].key);
+		}
+		break;
+
+	case EVENT_TYPE_SINGLE:
+		if (component == EVENT_CHANNEL_GPU) {
+			unsigned int reason = (event_id & 0xffff);
+
+			if (reason == EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE)
+				gator_events_mali_log_dvfs_event(d0, d1);
+		}
+		break;
+
+	default:
+		break;
+	}
+}
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+
+struct mali_counter mali_activity[3];
+
+#if defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid, unsigned char job_id))
+#else
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid))
+#endif
+{
+	unsigned int component, state, unit;
+#if !defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+	unsigned char job_id = 0;
+#endif
+
+	component = (event_id >> 16) & 0xFF;	/* component is an 8-bit field */
+	state = (event_id >> 24) & 0xF;	/* state is a 4-bit field */
+
+	switch (component) {
+	case 0:
+		unit = GPU_UNIT_FP;
+		break;
+	case 1:
+		unit = GPU_UNIT_VP;
+		break;
+	case 2:
+		unit = GPU_UNIT_CL;
+		break;
+	default:
+		unit = GPU_UNIT_NONE;
+	}
+
+	if (unit != GPU_UNIT_NONE) {
+		switch (state) {
+		case EVENT_TYPE_START:
+			if (mali_activity[component].enabled)
+				mali_activity_enqueue(0, mali_activity[component].key, 1, (pid != 0 ? pid : tgid));
+			break;
+		case EVENT_TYPE_STOP:
+		default: /* Some jobs can be soft-stopped, so ensure that this terminates the activity trace. */
+			if (mali_activity[component].enabled)
+				mali_activity_stop(0, mali_activity[component].key);
+			break;
+		}
+	}
+}
+#endif
+
+static int gator_trace_gpu_start(void)
+{
+	/*
+	 * Returns nonzero for installation failed
+	 * Absence of gpu trace points is not an error
+	 */
+
+#if defined(MALI_SUPPORT)
+	memset(&mali_activities, 0, sizeof(mali_activities));
+#endif
+	mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+	mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+	if (!GATOR_REGISTER_TRACE(mali_timeline_event))
+		mali_timeline_trace_registered = 1;
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+	mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+	if (!GATOR_REGISTER_TRACE(mali_job_slots_event))
+		mali_job_slots_trace_registered = 1;
+#endif
+
+	return 0;
+}
+
+static void gator_trace_gpu_stop(void)
+{
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+	if (mali_timeline_trace_registered)
+		GATOR_UNREGISTER_TRACE(mali_timeline_event);
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+	if (mali_job_slots_trace_registered)
+		GATOR_UNREGISTER_TRACE(mali_job_slots_event);
+#endif
+
+	mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+}
diff --git a/drivers/gator/gator_trace_power.c b/drivers/gator/gator_trace_power.c
new file mode 100644
index 000000000000..46e04b29a187
--- /dev/null
+++ b/drivers/gator/gator_trace_power.c
@@ -0,0 +1,192 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/cpufreq.h>
+#include <trace/events/power.h>
+
+#if defined(__arm__)
+
+#include <asm/mach-types.h>
+
+#define implements_wfi() (!machine_is_omap3_beagle())
+
+#else
+
+#define implements_wfi() false
+
+#endif
+
+/* cpu_frequency and cpu_idle trace points were introduced in Linux
+ * kernel v2.6.38 the now deprecated power_frequency trace point was
+ * available prior to 2.6.38, but only for x86
+ */
+#if GATOR_CPU_FREQ_SUPPORT
+enum {
+	POWER_CPU_FREQ,
+	POWER_TOTAL
+};
+
+static DEFINE_PER_CPU(ulong, idle_prev_state);
+static ulong power_cpu_enabled[POWER_TOTAL];
+static ulong power_cpu_key[POWER_TOTAL];
+static ulong power_cpu_cores;
+
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+	int cpu;
+	bool found_nonzero_freq = false;
+
+	/* Even if CONFIG_CPU_FREQ is defined, it still may not be
+	 * used. Check for non-zero values from cpufreq_quick_get
+	 */
+	for_each_online_cpu(cpu) {
+		if (cpufreq_quick_get(cpu) > 0) {
+			found_nonzero_freq = true;
+			break;
+		}
+	}
+
+	if (found_nonzero_freq) {
+		/* cpu_frequency */
+		dir = gatorfs_mkdir(sb, root, "Linux_power_cpu_freq");
+		if (!dir)
+			return -1;
+		gatorfs_create_ulong(sb, dir, "enabled", &power_cpu_enabled[POWER_CPU_FREQ]);
+		gatorfs_create_ro_ulong(sb, dir, "key", &power_cpu_key[POWER_CPU_FREQ]);
+	}
+
+	return 0;
+}
+
+/* 'cpu' may not equal smp_processor_id(), i.e. may not be running on the core that is having the freq/idle state change */
+GATOR_DEFINE_PROBE(cpu_frequency, TP_PROTO(unsigned int frequency, unsigned int cpu))
+{
+	cpu = lcpu_to_pcpu(cpu);
+	marshal_event_single64(cpu, power_cpu_key[POWER_CPU_FREQ], frequency * 1000L);
+}
+
+GATOR_DEFINE_PROBE(cpu_idle, TP_PROTO(unsigned int state, unsigned int cpu))
+{
+	cpu = lcpu_to_pcpu(cpu);
+
+	if (state == per_cpu(idle_prev_state, cpu))
+		return;
+
+	if (implements_wfi()) {
+		if (state == PWR_EVENT_EXIT) {
+			/* transition from wfi to non-wfi */
+			marshal_idle(cpu, MESSAGE_IDLE_EXIT);
+		} else {
+			/* transition from non-wfi to wfi */
+			marshal_idle(cpu, MESSAGE_IDLE_ENTER);
+		}
+	}
+
+	per_cpu(idle_prev_state, cpu) = state;
+}
+
+static void gator_trace_power_online(void)
+{
+	int pcpu = get_physical_cpu();
+	int lcpu = get_logical_cpu();
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		marshal_event_single64(pcpu, power_cpu_key[POWER_CPU_FREQ], cpufreq_quick_get(lcpu) * 1000L);
+}
+
+static void gator_trace_power_offline(void)
+{
+	/* Set frequency to zero on an offline */
+	int cpu = get_physical_cpu();
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		marshal_event_single(cpu, power_cpu_key[POWER_CPU_FREQ], 0);
+}
+
+static int gator_trace_power_start(void)
+{
+	int cpu;
+
+	/* register tracepoints */
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		if (GATOR_REGISTER_TRACE(cpu_frequency))
+			goto fail_cpu_frequency_exit;
+
+	/* Always register for cpu_idle for detecting WFI */
+	if (GATOR_REGISTER_TRACE(cpu_idle))
+		goto fail_cpu_idle_exit;
+	pr_debug("gator: registered power event tracepoints\n");
+
+	for_each_present_cpu(cpu) {
+		per_cpu(idle_prev_state, cpu) = 0;
+	}
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_cpu_idle_exit:
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		GATOR_UNREGISTER_TRACE(cpu_frequency);
+fail_cpu_frequency_exit:
+	pr_err("gator: power event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void gator_trace_power_stop(void)
+{
+	int i;
+
+	if (power_cpu_enabled[POWER_CPU_FREQ])
+		GATOR_UNREGISTER_TRACE(cpu_frequency);
+	GATOR_UNREGISTER_TRACE(cpu_idle);
+	pr_debug("gator: unregistered power event tracepoints\n");
+
+	for (i = 0; i < POWER_TOTAL; i++)
+		power_cpu_enabled[i] = 0;
+}
+
+static void gator_trace_power_init(void)
+{
+	int i;
+
+	power_cpu_cores = nr_cpu_ids;
+	for (i = 0; i < POWER_TOTAL; i++) {
+		power_cpu_enabled[i] = 0;
+		power_cpu_key[i] = gator_events_get_key();
+	}
+}
+#else
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+	return 0;
+}
+
+static void gator_trace_power_online(void)
+{
+}
+
+static void gator_trace_power_offline(void)
+{
+}
+
+static int gator_trace_power_start(void)
+{
+	return 0;
+}
+
+static void gator_trace_power_stop(void)
+{
+}
+
+static void gator_trace_power_init(void)
+{
+}
+#endif
diff --git a/drivers/gator/gator_trace_sched.c b/drivers/gator/gator_trace_sched.c
new file mode 100644
index 000000000000..6d7cbd7348e1
--- /dev/null
+++ b/drivers/gator/gator_trace_sched.c
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <trace/events/sched.h>
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+#include <trace/events/task.h>
+#endif
+
+#include "gator.h"
+
+#define TASK_MAP_ENTRIES		1024	/* must be power of 2 */
+#define TASK_MAX_COLLISIONS		2
+
+enum {
+	STATE_WAIT_ON_OTHER = 0,
+	STATE_CONTENTION,
+	STATE_WAIT_ON_IO,
+	CPU_WAIT_TOTAL
+};
+
+static DEFINE_PER_CPU(uint64_t *, taskname_keys);
+static DEFINE_PER_CPU(int, collecting);
+
+/* this array is never read as the cpu wait charts are derived
+ * counters the files are needed, nonetheless, to show that these
+ * counters are available
+ */
+static ulong cpu_wait_enabled[CPU_WAIT_TOTAL];
+static ulong sched_cpu_key[CPU_WAIT_TOTAL];
+
+static int sched_trace_create_files(struct super_block *sb, struct dentry *root)
+{
+	struct dentry *dir;
+
+	/* CPU Wait - Contention */
+	dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_contention");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_CONTENTION]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_CONTENTION]);
+
+	/* CPU Wait - I/O */
+	dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_io");
+	if (!dir)
+		return -1;
+	gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_WAIT_ON_IO]);
+	gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_WAIT_ON_IO]);
+
+	return 0;
+}
+
+static void emit_pid_name(const char *comm, struct task_struct *task)
+{
+	bool found = false;
+	char taskcomm[TASK_COMM_LEN + 3];
+	unsigned long x, cpu = get_physical_cpu();
+	uint64_t *keys = &(per_cpu(taskname_keys, cpu)[(task->pid & 0xFF) * TASK_MAX_COLLISIONS]);
+	uint64_t value;
+
+	value = gator_chksum_crc32(comm);
+	value = (value << 32) | (uint32_t)task->pid;
+
+	/* determine if the thread name was emitted already */
+	for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+		if (keys[x] == value) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		/* shift values, new value always in front */
+		uint64_t oldv, newv = value;
+
+		for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+			oldv = keys[x];
+			keys[x] = newv;
+			newv = oldv;
+		}
+
+		/* emit pid names, cannot use get_task_comm, as it's not exported on all kernel versions */
+		if (strlcpy(taskcomm, comm, TASK_COMM_LEN) == TASK_COMM_LEN - 1) {
+			/* append ellipses if comm has length of TASK_COMM_LEN - 1 */
+			strcat(taskcomm, "...");
+		}
+
+		marshal_thread_name(task->pid, taskcomm);
+	}
+}
+
+static void collect_counters(u64 time, struct task_struct *task, bool sched_switch)
+{
+	int *buffer, len, cpu = get_physical_cpu();
+	long long *buffer64;
+	struct gator_interface *gi;
+
+	if (marshal_event_header(time)) {
+		list_for_each_entry(gi, &gator_events, list) {
+			if (gi->read) {
+				len = gi->read(&buffer, sched_switch);
+				marshal_event(len, buffer);
+			} else if (gi->read64) {
+				len = gi->read64(&buffer64);
+				marshal_event64(len, buffer64);
+			}
+			if (gi->read_proc && task != NULL) {
+				len = gi->read_proc(&buffer64, task);
+				marshal_event64(len, buffer64);
+			}
+		}
+		if (cpu == 0)
+			gator_emit_perf_time(time);
+		/* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+		buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+
+		/* Commit buffers on timeout */
+		if (gator_live_rate > 0 && time >= per_cpu(gator_buffer_commit_time, cpu)) {
+			static const int buftypes[] = { NAME_BUF, COUNTER_BUF, BLOCK_COUNTER_BUF, SCHED_TRACE_BUF, ACTIVITY_BUF };
+			int i;
+
+			for (i = 0; i < ARRAY_SIZE(buftypes); ++i)
+				gator_commit_buffer(cpu, buftypes[i], time);
+
+			/* spinlocks are noops on uniprocessor machines and mutexes do
+			 * not work in sched_switch context in RT-Preempt full, so
+			 * disable proactive flushing of the annotate frame on
+			 * uniprocessor machines.
+			 */
+#ifdef CONFIG_SMP
+			/* Try to preemptively flush the annotate buffer to reduce the chance of the buffer being full */
+			if (on_primary_core() && spin_trylock(&annotate_lock)) {
+				gator_commit_buffer(0, ANNOTATE_BUF, time);
+				spin_unlock(&annotate_lock);
+			}
+#endif
+		}
+	}
+}
+
+/* special case used during a suspend of the system */
+static void trace_sched_insert_idle(void)
+{
+	marshal_sched_trace_switch(0, 0);
+}
+
+static void gator_trace_emit_link(struct task_struct *p)
+{
+	int cookie;
+	int cpu = get_physical_cpu();
+
+	cookie = get_exec_cookie(cpu, p);
+	emit_pid_name(p->comm, p);
+
+	marshal_link(cookie, p->tgid, p->pid);
+}
+
+GATOR_DEFINE_PROBE(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child))
+{
+	gator_trace_emit_link(child);
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+GATOR_DEFINE_PROBE(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm))
+{
+	gator_trace_emit_link(p);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, char *comm))
+#else
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, const char *comm))
+#endif
+{
+	emit_pid_name(comm, task);
+}
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+	int state;
+	int cpu = get_physical_cpu();
+
+	per_cpu(in_scheduler_context, cpu) = true;
+
+	/* do as much work as possible before disabling interrupts */
+	if (prev->state == TASK_RUNNING)
+		state = STATE_CONTENTION;
+	else if (prev->in_iowait)
+		state = STATE_WAIT_ON_IO;
+	else
+		state = STATE_WAIT_ON_OTHER;
+
+	per_cpu(collecting, cpu) = 1;
+	collect_counters(gator_get_time(), prev, true);
+	per_cpu(collecting, cpu) = 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+	gator_trace_emit_link(next);
+#endif
+	marshal_sched_trace_switch(next->pid, state);
+
+	per_cpu(in_scheduler_context, cpu) = false;
+}
+
+GATOR_DEFINE_PROBE(sched_process_free, TP_PROTO(struct task_struct *p))
+{
+	marshal_sched_trace_exit(p->tgid, p->pid);
+}
+
+static void do_nothing(void *info)
+{
+	/* Intentionally do nothing */
+	(void)info;
+}
+
+static int register_scheduler_tracepoints(void)
+{
+	/* register tracepoints */
+	if (GATOR_REGISTER_TRACE(sched_process_fork))
+		goto fail_sched_process_fork;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	if (GATOR_REGISTER_TRACE(sched_process_exec))
+		goto fail_sched_process_exec;
+	if (GATOR_REGISTER_TRACE(task_rename))
+		goto fail_task_rename;
+#endif
+	if (GATOR_REGISTER_TRACE(sched_switch))
+		goto fail_sched_switch;
+	if (GATOR_REGISTER_TRACE(sched_process_free))
+		goto fail_sched_process_free;
+	pr_debug("gator: registered tracepoints\n");
+
+	/* Now that the scheduler tracepoint is registered, force a context
+	 * switch on all cpus to capture what is currently running.
+	 */
+	on_each_cpu(do_nothing, NULL, 0);
+
+	return 0;
+
+	/* unregister tracepoints on error */
+fail_sched_process_free:
+	GATOR_UNREGISTER_TRACE(sched_switch);
+fail_sched_switch:
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	GATOR_UNREGISTER_TRACE(task_rename);
+fail_task_rename:
+	GATOR_UNREGISTER_TRACE(sched_process_exec);
+fail_sched_process_exec:
+#endif
+	GATOR_UNREGISTER_TRACE(sched_process_fork);
+fail_sched_process_fork:
+	pr_err("gator: tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+	return -1;
+}
+
+static void unregister_scheduler_tracepoints(void)
+{
+	GATOR_UNREGISTER_TRACE(sched_process_fork);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+	GATOR_UNREGISTER_TRACE(sched_process_exec);
+	GATOR_UNREGISTER_TRACE(task_rename);
+#endif
+	GATOR_UNREGISTER_TRACE(sched_switch);
+	GATOR_UNREGISTER_TRACE(sched_process_free);
+	pr_debug("gator: unregistered tracepoints\n");
+}
+
+static void gator_trace_sched_stop(void)
+{
+	int cpu;
+
+	unregister_scheduler_tracepoints();
+
+	for_each_present_cpu(cpu) {
+		kfree(per_cpu(taskname_keys, cpu));
+	}
+}
+
+static int gator_trace_sched_start(void)
+{
+	int cpu, size;
+	int ret;
+
+	for_each_present_cpu(cpu) {
+		size = TASK_MAP_ENTRIES * TASK_MAX_COLLISIONS * sizeof(uint64_t);
+		per_cpu(taskname_keys, cpu) = kmalloc(size, GFP_KERNEL);
+		if (!per_cpu(taskname_keys, cpu))
+			return -1;
+		memset(per_cpu(taskname_keys, cpu), 0, size);
+	}
+
+	ret = register_scheduler_tracepoints();
+
+	return ret;
+}
+
+static void gator_trace_sched_offline(void)
+{
+	trace_sched_insert_idle();
+}
+
+static void gator_trace_sched_init(void)
+{
+	int i;
+
+	for (i = 0; i < CPU_WAIT_TOTAL; i++) {
+		cpu_wait_enabled[i] = 0;
+		sched_cpu_key[i] = gator_events_get_key();
+	}
+}
diff --git a/drivers/gator/mali/mali_kbase_gator_api.h b/drivers/gator/mali/mali_kbase_gator_api.h
new file mode 100644
index 000000000000..5ed069797e36
--- /dev/null
+++ b/drivers/gator/mali/mali_kbase_gator_api.h
@@ -0,0 +1,219 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef _KBASE_GATOR_API_H_
+#define _KBASE_GATOR_API_H_
+
+/**
+ * @brief This file describes the API used by Gator to collect hardware counters data from a Mali device.
+ */
+
+/* This define is used by the gator kernel module compile to select which DDK
+ * API calling convention to use. If not defined (legacy DDK) gator assumes
+ * version 1. The version to DDK release mapping is:
+ *     Version 1 API: DDK versions r1px, r2px
+ *     Version 2 API: DDK versions r3px, r4px
+ *     Version 3 API: DDK version r5p0 and newer
+ *
+ * API Usage
+ * =========
+ *
+ * 1] Call kbase_gator_hwcnt_init_names() to return the list of short counter
+ * names for the GPU present in this device.
+ *
+ * 2] Create a kbase_gator_hwcnt_info structure and set the counter enables for
+ * the counters you want enabled. The enables can all be set for simplicity in
+ * most use cases, but disabling some will let you minimize bandwidth impact.
+ *
+ * 3] Call kbase_gator_hwcnt_init() using the above structure, to create a
+ * counter context. On successful return the DDK will have populated the
+ * structure with a variety of useful information.
+ *
+ * 4] Call kbase_gator_hwcnt_dump_irq() to queue a non-blocking request for a
+ * counter dump. If this returns a non-zero value the request has been queued,
+ * otherwise the driver has been unable to do so (typically because of another
+ * user of the instrumentation exists concurrently).
+ *
+ * 5] Call kbase_gator_hwcnt_dump_complete() to test whether the  previously
+ * requested dump has been succesful. If this returns non-zero the counter dump
+ * has resolved, but the value of *success must also be tested as the dump
+ * may have not been successful. If it returns zero the counter dump was
+ * abandoned due to the device being busy (typically because of another
+ * user of the instrumentation exists concurrently).
+ *
+ * 6] Process the counters stored in the buffer pointed to by ...
+ *
+ *        kbase_gator_hwcnt_info->kernel_dump_buffer
+ *
+ *    In pseudo code you can find all of the counters via this approach:
+ *
+ *
+ *        hwcnt_info # pointer to kbase_gator_hwcnt_info structure
+ *        hwcnt_name # pointer to name list
+ *
+ *        u32 * hwcnt_data = (u32*)hwcnt_info->kernel_dump_buffer
+ *
+ *        # Iterate over each 64-counter block in this GPU configuration
+ *        for( i = 0; i < hwcnt_info->nr_hwc_blocks; i++) {
+ *            hwc_type type = hwcnt_info->hwc_layout[i];
+ *
+ *            # Skip reserved type blocks - they contain no counters at all
+ *            if( type == RESERVED_BLOCK ) {
+ *                continue;
+ *            }
+ *
+ *            size_t name_offset = type * 64;
+ *            size_t data_offset = i * 64;
+ *
+ *            # Iterate over the names of the counters in this block type
+ *            for( j = 0; j < 64; j++) {
+ *                const char * name = hwcnt_name[name_offset+j];
+ *
+ *                # Skip empty name strings - there is no counter here
+ *                if( name[0] == '\0' ) {
+ *                    continue;
+ *                }
+ *
+ *                u32 data = hwcnt_data[data_offset+j];
+ *
+ *                printk( "COUNTER: %s DATA: %u\n", name, data );
+ *            }
+ *        }
+ *
+ *
+ *     Note that in most implementations you typically want to either SUM or
+ *     AVERAGE multiple instances of the same counter if, for example, you have
+ *     multiple shader cores or multiple L2 caches. The most sensible view for
+ *     analysis is to AVERAGE shader core counters, but SUM L2 cache and MMU
+ *     counters.
+ *
+ * 7] Goto 4, repeating until you want to stop collecting counters.
+ *
+ * 8] Release the dump resources by calling kbase_gator_hwcnt_term().
+ *
+ * 9] Release the name table resources by calling kbase_gator_hwcnt_term_names().
+ *    This function must only be called if init_names() returned a non-NULL value.
+ **/
+
+#define MALI_DDK_GATOR_API_VERSION 3
+
+#if !defined(MALI_TRUE)
+	#define MALI_TRUE                ((uint32_t)1)
+#endif
+
+#if !defined(MALI_FALSE)
+	#define MALI_FALSE               ((uint32_t)0)
+#endif
+
+enum hwc_type {
+	JM_BLOCK = 0,
+	TILER_BLOCK,
+	SHADER_BLOCK,
+	MMU_L2_BLOCK,
+	RESERVED_BLOCK
+};
+
+struct kbase_gator_hwcnt_info {
+
+	/* Passed from Gator to kbase */
+
+	/* the bitmask of enabled hardware counters for each counter block */
+	uint16_t bitmask[4];
+
+	/* Passed from kbase to Gator */
+
+	/* ptr to counter dump memory */
+	void *kernel_dump_buffer;
+
+	/* size of counter dump memory */
+	uint32_t size;
+
+	/* the ID of the Mali device */
+	uint32_t gpu_id;
+
+	/* the number of shader cores in the GPU */
+	uint32_t nr_cores;
+
+	/* the number of core groups */
+	uint32_t nr_core_groups;
+
+	/* the memory layout of the performance counters */
+	enum hwc_type *hwc_layout;
+
+	/* the total number of hardware couter blocks */
+	uint32_t nr_hwc_blocks;
+};
+
+/**
+ * @brief Opaque block of Mali data which Gator needs to return to the API later.
+ */
+struct kbase_gator_hwcnt_handles;
+
+/**
+ * @brief Initialize the resources Gator needs for performance profiling.
+ *
+ * @param in_out_info   A pointer to a structure containing the enabled counters passed from Gator and all the Mali
+ *                      specific information that will be returned to Gator. On entry Gator must have populated the
+ *                      'bitmask' field with the counters it wishes to enable for each class of counter block.
+ *                      Each entry in the array corresponds to a single counter class based on the "hwc_type"
+ *                      enumeration, and each bit corresponds to an enable for 4 sequential counters (LSB enables
+ *                      the first 4 counters in the block, and so on). See the GPU counter array as returned by
+ *                      kbase_gator_hwcnt_get_names() for the index values of each counter for the curernt GPU.
+ *
+ * @return              Pointer to an opaque handle block on success, NULL on error.
+ */
+extern struct kbase_gator_hwcnt_handles *kbase_gator_hwcnt_init(struct kbase_gator_hwcnt_info *in_out_info);
+
+/**
+ * @brief Free all resources once Gator has finished using performance counters.
+ *
+ * @param in_out_info       A pointer to a structure containing the enabled counters passed from Gator and all the
+ *                          Mali specific information that will be returned to Gator.
+ * @param opaque_handles    A wrapper structure for kbase structures.
+ */
+extern void kbase_gator_hwcnt_term(struct kbase_gator_hwcnt_info *in_out_info, struct kbase_gator_hwcnt_handles *opaque_handles);
+
+/**
+ * @brief Poll whether a counter dump is successful.
+ *
+ * @param opaque_handles    A wrapper structure for kbase structures.
+ * @param[out] success      Non-zero on success, zero on failure.
+ *
+ * @return                  Zero if the dump is still pending, non-zero if the dump has completed. Note that a
+ *                          completed dump may not have dumped succesfully, so the caller must test for both
+ *                          a completed and successful dump before processing counters.
+ */
+extern uint32_t kbase_gator_instr_hwcnt_dump_complete(struct kbase_gator_hwcnt_handles *opaque_handles, uint32_t * const success);
+
+/**
+ * @brief Request the generation of a new counter dump.
+ *
+ * @param opaque_handles    A wrapper structure for kbase structures.
+ *
+ * @return                  Zero if the hardware device is busy and cannot handle the request, non-zero otherwise.
+ */
+extern uint32_t kbase_gator_instr_hwcnt_dump_irq(struct kbase_gator_hwcnt_handles *opaque_handles);
+
+/**
+ * @brief This function is used to fetch the names table based on the Mali device in use.
+ *
+ * @param[out] total_number_of_counters The total number of counters short names in the Mali devices' list.
+ *
+ * @return                              Pointer to an array of strings of length *total_number_of_counters.
+ */
+extern const char * const *kbase_gator_hwcnt_init_names(uint32_t *total_number_of_counters);
+
+/**
+ * @brief This function is used to terminate the use of the names table.
+ *
+ * This function must only be called if the initial call to kbase_gator_hwcnt_init_names returned a non-NULL value.
+ */
+extern void kbase_gator_hwcnt_term_names(void);
+
+#endif
diff --git a/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
new file mode 100644
index 000000000000..2bc0b037eee6
--- /dev/null
+++ b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
@@ -0,0 +1,159 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+#define __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+
+/*
+ * The number of processor cores.  Update to suit your hardware implementation.
+ */
+#define MAX_NUM_FP_CORES            (4)
+#define MAX_NUM_VP_CORES            (1)
+#define MAX_NUM_L2_CACHE_CORES      (1)
+
+enum counters {
+	/* Timeline activity */
+	ACTIVITY_VP_0 = 0,
+	ACTIVITY_FP_0,
+	ACTIVITY_FP_1,
+	ACTIVITY_FP_2,
+	ACTIVITY_FP_3,
+
+	/* L2 cache counters */
+	COUNTER_L2_0_C0,
+	COUNTER_L2_0_C1,
+
+	/* Vertex processor counters */
+	COUNTER_VP_0_C0,
+	COUNTER_VP_0_C1,
+
+	/* Fragment processor counters */
+	COUNTER_FP_0_C0,
+	COUNTER_FP_0_C1,
+	COUNTER_FP_1_C0,
+	COUNTER_FP_1_C1,
+	COUNTER_FP_2_C0,
+	COUNTER_FP_2_C1,
+	COUNTER_FP_3_C0,
+	COUNTER_FP_3_C1,
+
+	/* EGL Software Counters */
+	COUNTER_EGL_BLIT_TIME,
+
+	/* GLES Software Counters */
+	COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_ARRAYS_CALLS,
+	COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_POINTS,
+	COUNTER_GLES_DRAW_LINES,
+	COUNTER_GLES_DRAW_LINE_LOOP,
+	COUNTER_GLES_DRAW_LINE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLES,
+	COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLE_FAN,
+	COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+	COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+	COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+	COUNTER_GLES_UPLOAD_VBO_TIME,
+	COUNTER_GLES_NUM_FLUSHES,
+	COUNTER_GLES_NUM_VSHADERS_GENERATED,
+	COUNTER_GLES_NUM_FSHADERS_GENERATED,
+	COUNTER_GLES_VSHADER_GEN_TIME,
+	COUNTER_GLES_FSHADER_GEN_TIME,
+	COUNTER_GLES_INPUT_TRIANGLES,
+	COUNTER_GLES_VXCACHE_HIT,
+	COUNTER_GLES_VXCACHE_MISS,
+	COUNTER_GLES_VXCACHE_COLLISION,
+	COUNTER_GLES_CULLED_TRIANGLES,
+	COUNTER_GLES_CULLED_LINES,
+	COUNTER_GLES_BACKFACE_TRIANGLES,
+	COUNTER_GLES_GBCLIP_TRIANGLES,
+	COUNTER_GLES_GBCLIP_LINES,
+	COUNTER_GLES_TRIANGLES_DRAWN,
+	COUNTER_GLES_DRAWCALL_TIME,
+	COUNTER_GLES_TRIANGLES_COUNT,
+	COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+	COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+	COUNTER_GLES_FAN_TRIANGLES_COUNT,
+	COUNTER_GLES_LINES_COUNT,
+	COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+	COUNTER_GLES_STRIP_LINES_COUNT,
+	COUNTER_GLES_LOOP_LINES_COUNT,
+
+	COUNTER_FILMSTRIP,
+	COUNTER_FREQUENCY,
+	COUNTER_VOLTAGE,
+
+	NUMBER_OF_EVENTS
+};
+
+#define FIRST_ACTIVITY_EVENT    ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT     ACTIVITY_FP_3
+
+#define FIRST_HW_COUNTER        COUNTER_L2_0_C0
+#define LAST_HW_COUNTER         COUNTER_FP_3_C1
+
+#define FIRST_SW_COUNTER        COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER         COUNTER_GLES_LOOP_LINES_COUNT
+
+/* Signifies that the system is able to report voltage and frequency numbers. */
+#define DVFS_REPORTED_BY_DDK 1
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+	u32 source0;
+	u32 value0;
+	u32 source1;
+	u32 value1;
+};
+
+/*
+ * For compatibility with utgard.
+ */
+struct _mali_profiling_l2_counter_values {
+	struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+struct _mali_profiling_mali_version {
+	u32 mali_product_id;
+	u32 mali_version_major;
+	u32 mali_version_minor;
+	u32 num_of_l2_cores;
+	u32 num_of_fp_cores;
+	u32 num_of_vp_cores;
+};
+
+extern void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+extern u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * List of possible actions allowing DDK to be controlled by Streamline.
+ * The following numbers are used by DDK to control the frame buffer dumping.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE      (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_MJOLLNIR_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali/mali_utgard_profiling_gator_api.h b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
new file mode 100644
index 000000000000..d6465312628e
--- /dev/null
+++ b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_UTGARD_PROFILING_GATOR_API_H__
+#define __MALI_UTGARD_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+#define MALI_PROFILING_API_VERSION 4
+
+#define MAX_NUM_L2_CACHE_CORES 3
+#define MAX_NUM_FP_CORES 8
+#define MAX_NUM_VP_CORES 1
+
+/** The list of events supported by the Mali DDK. */
+enum {
+	/* Vertex processor activity */
+	ACTIVITY_VP_0 = 0,
+
+	/* Fragment processor activity */
+	ACTIVITY_FP_0, /* 1 */
+	ACTIVITY_FP_1,
+	ACTIVITY_FP_2,
+	ACTIVITY_FP_3,
+	ACTIVITY_FP_4,
+	ACTIVITY_FP_5,
+	ACTIVITY_FP_6,
+	ACTIVITY_FP_7,
+
+	/* L2 cache counters */
+	COUNTER_L2_0_C0,
+	COUNTER_L2_0_C1,
+	COUNTER_L2_1_C0,
+	COUNTER_L2_1_C1,
+	COUNTER_L2_2_C0,
+	COUNTER_L2_2_C1,
+
+	/* Vertex processor counters */
+	COUNTER_VP_0_C0, /*15*/
+	COUNTER_VP_0_C1,
+
+	/* Fragment processor counters */
+	COUNTER_FP_0_C0,
+	COUNTER_FP_0_C1,
+	COUNTER_FP_1_C0,
+	COUNTER_FP_1_C1,
+	COUNTER_FP_2_C0,
+	COUNTER_FP_2_C1,
+	COUNTER_FP_3_C0,
+	COUNTER_FP_3_C1,
+	COUNTER_FP_4_C0,
+	COUNTER_FP_4_C1,
+	COUNTER_FP_5_C0,
+	COUNTER_FP_5_C1,
+	COUNTER_FP_6_C0,
+	COUNTER_FP_6_C1,
+	COUNTER_FP_7_C0,
+	COUNTER_FP_7_C1, /* 32 */
+
+	/*
+	 * If more hardware counters are added, the _mali_osk_hw_counter_table
+	 * below should also be updated.
+	 */
+
+	/* EGL software counters */
+	COUNTER_EGL_BLIT_TIME,
+
+	/* GLES software counters */
+	COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+	COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_ARRAYS_CALLS,
+	COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+	COUNTER_GLES_DRAW_POINTS,
+	COUNTER_GLES_DRAW_LINES,
+	COUNTER_GLES_DRAW_LINE_LOOP,
+	COUNTER_GLES_DRAW_LINE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLES,
+	COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+	COUNTER_GLES_DRAW_TRIANGLE_FAN,
+	COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+	COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+	COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+	COUNTER_GLES_UPLOAD_VBO_TIME,
+	COUNTER_GLES_NUM_FLUSHES,
+	COUNTER_GLES_NUM_VSHADERS_GENERATED,
+	COUNTER_GLES_NUM_FSHADERS_GENERATED,
+	COUNTER_GLES_VSHADER_GEN_TIME,
+	COUNTER_GLES_FSHADER_GEN_TIME,
+	COUNTER_GLES_INPUT_TRIANGLES,
+	COUNTER_GLES_VXCACHE_HIT,
+	COUNTER_GLES_VXCACHE_MISS,
+	COUNTER_GLES_VXCACHE_COLLISION,
+	COUNTER_GLES_CULLED_TRIANGLES,
+	COUNTER_GLES_CULLED_LINES,
+	COUNTER_GLES_BACKFACE_TRIANGLES,
+	COUNTER_GLES_GBCLIP_TRIANGLES,
+	COUNTER_GLES_GBCLIP_LINES,
+	COUNTER_GLES_TRIANGLES_DRAWN,
+	COUNTER_GLES_DRAWCALL_TIME,
+	COUNTER_GLES_TRIANGLES_COUNT,
+	COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+	COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+	COUNTER_GLES_FAN_TRIANGLES_COUNT,
+	COUNTER_GLES_LINES_COUNT,
+	COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+	COUNTER_GLES_STRIP_LINES_COUNT,
+	COUNTER_GLES_LOOP_LINES_COUNT,
+
+	/* Framebuffer capture pseudo-counter */
+	COUNTER_FILMSTRIP,
+
+	NUMBER_OF_EVENTS
+} _mali_osk_counter_id;
+
+#define FIRST_ACTIVITY_EVENT    ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT     ACTIVITY_FP_7
+
+#define FIRST_HW_COUNTER        COUNTER_L2_0_C0
+#define LAST_HW_COUNTER         COUNTER_FP_7_C1
+
+#define FIRST_SW_COUNTER        COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER         COUNTER_GLES_LOOP_LINES_COUNT
+
+#define FIRST_SPECIAL_COUNTER   COUNTER_FILMSTRIP
+#define LAST_SPECIAL_COUNTER    COUNTER_FILMSTRIP
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+	u32 source0;
+	u32 value0;
+	u32 source1;
+	u32 value1;
+};
+
+/**
+ * Structure to pass performance counter data of Mali L2 cache cores
+ */
+struct _mali_profiling_l2_counter_values {
+	struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+/**
+ * Structure to pass data defining Mali instance in use:
+ *
+ * mali_product_id - Mali product id
+ * mali_version_major - Mali version major number
+ * mali_version_minor - Mali version minor number
+ * num_of_l2_cores - number of L2 cache cores
+ * num_of_fp_cores - number of fragment processor cores
+ * num_of_vp_cores - number of vertex processor cores
+ */
+struct _mali_profiling_mali_version {
+	u32 mali_product_id;
+	u32 mali_version_major;
+	u32 mali_version_minor;
+	u32 num_of_l2_cores;
+	u32 num_of_fp_cores;
+	u32 num_of_vp_cores;
+};
+
+/*
+ * List of possible actions to be controlled by Streamline.
+ * The following numbers are used by gator to control the frame buffer dumping and s/w counter reporting.
+ * We cannot use the enums in mali_uk_types.h because they are unknown inside gator.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+void _mali_profiling_control(u32 action, u32 value);
+
+u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+int _mali_profiling_set_event(u32 counter_id, s32 event_id);
+
+u32 _mali_profiling_get_api_version(void);
+
+void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_UTGARD_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali_midgard.mk b/drivers/gator/mali_midgard.mk
new file mode 100644
index 000000000000..1b784d5c3d58
--- /dev/null
+++ b/drivers/gator/mali_midgard.mk
@@ -0,0 +1,39 @@
+# Defines for Mali-Midgard driver
+EXTRA_CFLAGS += -DMALI_USE_UMP=1 \
+                -DMALI_LICENSE_IS_GPL=1 \
+                -DMALI_BASE_TRACK_MEMLEAK=0 \
+                -DMALI_DEBUG=0 \
+                -DMALI_ERROR_INJECT_ON=0 \
+                -DMALI_CUSTOMER_RELEASE=1 \
+                -DMALI_UNIT_TEST=0 \
+                -DMALI_BACKEND_KERNEL=1 \
+                -DMALI_NO_MALI=0
+
+DDK_DIR ?= .
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/t6xx),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase/osk
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard/osk
+EXTRA_CFLAGS += -DMALI_DIR_MIDGARD=1
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard/mali_kbase_gator_api.h),)
+EXTRA_CFLAGS += -DMALI_SIMPLE_API=1
+endif
+
+UMP_DIR = $(DDK_DIR)/include/linux
+
+# Include directories in the DDK
+EXTRA_CFLAGS += -I$(KBASE_DIR)/ \
+                -I$(KBASE_DIR)/.. \
+                -I$(OSK_DIR)/.. \
+                -I$(UMP_DIR)/.. \
+                -I$(DDK_DIR)/include \
+                -I$(KBASE_DIR)/osk/src/linux/include \
+                -I$(KBASE_DIR)/platform_dummy \
+                -I$(KBASE_DIR)/src
+
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 1ac288ea810d..aa379971d703 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -895,8 +895,11 @@ static int mcp23s08_probe(struct spi_device *spi)
 			return -ENODEV;
 		}
 
-		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++)
+		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {
 			pullups[addr] = 0;
+			if (spi_present_mask & (1 << addr))
+				chips++;
+		}
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
@@ -919,12 +922,12 @@ static int mcp23s08_probe(struct spi_device *spi)
 			pullups[addr] = pdata->chip[addr].pullups;
 		}
 
-		if (!chips)
-			return -ENODEV;
-
 		base = pdata->base;
 	}
 
+	if (!chips)
+		return -ENODEV;
+
 	data = kzalloc(sizeof *data + chips * sizeof(struct mcp23s08),
 			GFP_KERNEL);
 	if (!data)
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index 532bcb336eff..8ffdd7d2bade 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -214,7 +214,8 @@ static void __init mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base)
 	ct->regs.ack = PINCTRL_IRQSTAT(port) + MXS_CLR;
 	ct->regs.mask = PINCTRL_IRQEN(port);
 
-	irq_setup_generic_chip(gc, IRQ_MSK(32), 0, IRQ_NOREQUEST, 0);
+	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
+			       IRQ_NOREQUEST, 0);
 }
 
 static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index d8e398275ca8..66a492aa4f1e 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -678,6 +678,7 @@ static void armada_load_cursor_argb(void __iomem *base, uint32_t *pix,
 				       base + LCD_SPU_SRAM_WRDAT);
 			writel_relaxed(addr | SRAM_WRITE,
 				       base + LCD_SPU_SRAM_CTRL);
+			readl_relaxed(base + LCD_SPU_HWC_OVSA_HPXL_VLN);
 			addr += 1;
 			if ((addr & 0x00ff) == 0)
 				addr += 0xf00;
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 50535fd5a88d..d830b38e54f6 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -100,7 +100,7 @@ static int ast_detect_chip(struct drm_device *dev)
 			}
 			ast->vga2_clone = false;
 		} else {
-			ast->chip = 2000;
+			ast->chip = AST2000;
 			DRM_INFO("AST 2000 detected\n");
 		}
 	}
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index cca063b11083..d2e56e95d886 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -1012,8 +1012,8 @@ static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height)
 			srcdata32[1].ul = *((u32 *)(srcxor + 4)) & 0xf0f0f0f0;
 			data32.b[0] = srcdata32[0].b[1] | (srcdata32[0].b[0] >> 4);
 			data32.b[1] = srcdata32[0].b[3] | (srcdata32[0].b[2] >> 4);
-			data32.b[2] = srcdata32[0].b[1] | (srcdata32[1].b[0] >> 4);
-			data32.b[3] = srcdata32[0].b[3] | (srcdata32[1].b[2] >> 4);
+			data32.b[2] = srcdata32[1].b[1] | (srcdata32[1].b[0] >> 4);
+			data32.b[3] = srcdata32[1].b[3] | (srcdata32[1].b[2] >> 4);
 
 			writel(data32.ul, dstxor);
 			csum += data32.ul;
diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h
index 741965c001a6..460820551b09 100644
--- a/drivers/gpu/drm/bochs/bochs.h
+++ b/drivers/gpu/drm/bochs/bochs.h
@@ -1,5 +1,6 @@
 #include <linux/io.h>
 #include <linux/fb.h>
+#include <linux/console.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc.h>
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index 395bba261c9a..9c13df29fd20 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -95,6 +95,49 @@ static struct drm_driver bochs_driver = {
 };
 
 /* ---------------------------------------------------------------------- */
+/* pm interface                                                           */
+
+static int bochs_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct bochs_device *bochs = drm_dev->dev_private;
+
+	drm_kms_helper_poll_disable(drm_dev);
+
+	if (bochs->fb.initialized) {
+		console_lock();
+		fb_set_suspend(bochs->fb.helper.fbdev, 1);
+		console_unlock();
+	}
+
+	return 0;
+}
+
+static int bochs_pm_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct bochs_device *bochs = drm_dev->dev_private;
+
+	drm_helper_resume_force_mode(drm_dev);
+
+	if (bochs->fb.initialized) {
+		console_lock();
+		fb_set_suspend(bochs->fb.helper.fbdev, 0);
+		console_unlock();
+	}
+
+	drm_kms_helper_poll_enable(drm_dev);
+	return 0;
+}
+
+static const struct dev_pm_ops bochs_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(bochs_pm_suspend,
+				bochs_pm_resume)
+};
+
+/* ---------------------------------------------------------------------- */
 /* pci interface                                                          */
 
 static int bochs_kick_out_firmware_fb(struct pci_dev *pdev)
@@ -155,6 +198,7 @@ static struct pci_driver bochs_pci_driver = {
 	.id_table =	bochs_pci_tbl,
 	.probe =	bochs_pci_probe,
 	.remove =	bochs_pci_remove,
+	.driver.pm =    &bochs_pm_ops,
 };
 
 /* ---------------------------------------------------------------------- */
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 953fc8aea69c..faa1f421f1b8 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/console.h>
 #include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
 
 #include "cirrus_drv.h"
 
@@ -31,6 +32,8 @@ static struct drm_driver driver;
 static DEFINE_PCI_DEVICE_TABLE(pciidlist) = {
 	{ PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, 0x1af4, 0x1100, 0,
 	  0, 0 },
+	{ PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_5446, PCI_VENDOR_ID_XEN,
+	  0x0001, 0, 0, 0 },
 	{0,}
 };
 
@@ -75,6 +78,41 @@ static void cirrus_pci_remove(struct pci_dev *pdev)
 	drm_put_dev(dev);
 }
 
+static int cirrus_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct cirrus_device *cdev = drm_dev->dev_private;
+
+	drm_kms_helper_poll_disable(drm_dev);
+
+	if (cdev->mode_info.gfbdev) {
+		console_lock();
+		fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 1);
+		console_unlock();
+	}
+
+	return 0;
+}
+
+static int cirrus_pm_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct cirrus_device *cdev = drm_dev->dev_private;
+
+	drm_helper_resume_force_mode(drm_dev);
+
+	if (cdev->mode_info.gfbdev) {
+		console_lock();
+		fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 0);
+		console_unlock();
+	}
+
+	drm_kms_helper_poll_enable(drm_dev);
+	return 0;
+}
+
 static const struct file_operations cirrus_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -103,11 +141,17 @@ static struct drm_driver driver = {
 	.dumb_destroy = drm_gem_dumb_destroy,
 };
 
+static const struct dev_pm_ops cirrus_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(cirrus_pm_suspend,
+				cirrus_pm_resume)
+};
+
 static struct pci_driver cirrus_pci_driver = {
 	.name = DRIVER_NAME,
 	.id_table = pciidlist,
 	.probe = cirrus_pci_probe,
 	.remove = cirrus_pci_remove,
+	.driver.pm = &cirrus_pm_ops,
 };
 
 static int __init cirrus_init(void)
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 530f78f84dee..e9c89df482b5 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -308,6 +308,9 @@ static int cirrus_crtc_mode_set(struct drm_crtc *crtc,
 
 	WREG_HDR(hdr);
 	cirrus_crtc_do_set_base(crtc, old_fb, x, y, 0);
+
+	/* Unblank (needed on S3 resume, vgabios doesn't do it then) */
+	outb(0x20, 0x3c0);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index ec7bb0fc71bc..9debd6e74439 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -614,15 +614,20 @@ static void intel_resume_hotplug(struct drm_device *dev)
 	drm_helper_hpd_irq_event(dev);
 }
 
+static int i915_drm_thaw_early(struct drm_device *dev)
+{
+	intel_uncore_early_sanitize(dev);
+	intel_uncore_sanitize(dev);
+	intel_power_domains_init_hw(dev);
+
+	return 0;
+}
+
 static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int error = 0;
 
-	intel_uncore_early_sanitize(dev);
-
-	intel_uncore_sanitize(dev);
-
 	if (drm_core_check_feature(dev, DRIVER_MODESET) &&
 	    restore_gtt_mappings) {
 		mutex_lock(&dev->struct_mutex);
@@ -630,8 +635,6 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		mutex_unlock(&dev->struct_mutex);
 	}
 
-	intel_power_domains_init_hw(dev);
-
 	i915_restore_state(dev);
 	intel_opregion_setup(dev);
 
@@ -700,19 +703,33 @@ static int i915_drm_thaw(struct drm_device *dev)
 	return __i915_drm_thaw(dev, true);
 }
 
-int i915_resume(struct drm_device *dev)
+static int i915_resume_early(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
-
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	/*
+	 * We have a resume ordering issue with the snd-hda driver also
+	 * requiring our device to be power up. Due to the lack of a
+	 * parent/child relationship we currently solve this with an early
+	 * resume hook.
+	 *
+	 * FIXME: This should be solved with a special hdmi sink device or
+	 * similar so that power domains can be employed.
+	 */
 	if (pci_enable_device(dev->pdev))
 		return -EIO;
 
 	pci_set_master(dev->pdev);
 
+	return i915_drm_thaw_early(dev);
+}
+
+int i915_resume(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
 	/*
 	 * Platforms with opregion should have sane BIOS, older ones (gen3 and
 	 * earlier) need to restore the GTT mappings since the BIOS might clear
@@ -726,6 +743,14 @@ int i915_resume(struct drm_device *dev)
 	return 0;
 }
 
+static int i915_resume_legacy(struct drm_device *dev)
+{
+	i915_resume_early(dev);
+	i915_resume(dev);
+
+	return 0;
+}
+
 /**
  * i915_reset - reset chip after a hang
  * @dev: drm device to reset
@@ -846,7 +871,6 @@ static int i915_pm_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	int error;
 
 	if (!drm_dev || !drm_dev->dev_private) {
 		dev_err(dev, "DRM not initialized, aborting suspend.\n");
@@ -856,9 +880,25 @@ static int i915_pm_suspend(struct device *dev)
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	error = i915_drm_freeze(drm_dev);
-	if (error)
-		return error;
+	return i915_drm_freeze(drm_dev);
+}
+
+static int i915_pm_suspend_late(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+
+	/*
+	 * We have a suspedn ordering issue with the snd-hda driver also
+	 * requiring our device to be power up. Due to the lack of a
+	 * parent/child relationship we currently solve this with an late
+	 * suspend hook.
+	 *
+	 * FIXME: This should be solved with a special hdmi sink device or
+	 * similar so that power domains can be employed.
+	 */
+	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+		return 0;
 
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, PCI_D3hot);
@@ -866,6 +906,14 @@ static int i915_pm_suspend(struct device *dev)
 	return 0;
 }
 
+static int i915_pm_resume_early(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+
+	return i915_resume_early(drm_dev);
+}
+
 static int i915_pm_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -887,6 +935,14 @@ static int i915_pm_freeze(struct device *dev)
 	return i915_drm_freeze(drm_dev);
 }
 
+static int i915_pm_thaw_early(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+
+	return i915_drm_thaw_early(drm_dev);
+}
+
 static int i915_pm_thaw(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -948,10 +1004,14 @@ static int i915_runtime_resume(struct device *device)
 
 static const struct dev_pm_ops i915_pm_ops = {
 	.suspend = i915_pm_suspend,
+	.suspend_late = i915_pm_suspend_late,
+	.resume_early = i915_pm_resume_early,
 	.resume = i915_pm_resume,
 	.freeze = i915_pm_freeze,
+	.thaw_early = i915_pm_thaw_early,
 	.thaw = i915_pm_thaw,
 	.poweroff = i915_pm_poweroff,
+	.restore_early = i915_pm_resume_early,
 	.restore = i915_pm_resume,
 	.runtime_suspend = i915_runtime_suspend,
 	.runtime_resume = i915_runtime_resume,
@@ -994,7 +1054,7 @@ static struct drm_driver driver = {
 
 	/* Used in place of i915_pm_ops for non-DRIVER_MODESET */
 	.suspend = i915_suspend,
-	.resume = i915_resume,
+	.resume = i915_resume_legacy,
 
 	.device_is_agp = i915_driver_device_is_agp,
 	.master_create = i915_master_create,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index df77e20e3c3d..4677af964df7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -734,6 +734,7 @@ enum intel_sbi_destination {
 #define QUIRK_PIPEA_FORCE (1<<0)
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
 #define QUIRK_INVERT_BRIGHTNESS (1<<2)
+#define QUIRK_NO_PCH_PWM_ENABLE (1<<3)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -2425,6 +2426,7 @@ extern void intel_modeset_suspend_hw(struct drm_device *dev);
 extern void intel_modeset_init(struct drm_device *dev);
 extern void intel_modeset_gem_init(struct drm_device *dev);
 extern void intel_modeset_cleanup(struct drm_device *dev);
+extern void intel_connector_unregister(struct intel_connector *);
 extern int intel_modeset_vga_set_state(struct drm_device *dev, bool state);
 extern void intel_modeset_setup_hw_state(struct drm_device *dev,
 					 bool force_restore);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 00c836154725..7410a507eacc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1426,10 +1426,13 @@ unlock:
 out:
 	switch (ret) {
 	case -EIO:
-		/* If this -EIO is due to a gpu hang, give the reset code a
-		 * chance to clean up the mess. Otherwise return the proper
-		 * SIGBUS. */
-		if (i915_terminally_wedged(&dev_priv->gpu_error)) {
+		/*
+		 * We eat errors when the gpu is terminally wedged to avoid
+		 * userspace unduly crashing (gl has no provisions for mmaps to
+		 * fail). But any other -EIO isn't ours (e.g. swap in failure)
+		 * and so needs to be reported.
+		 */
+		if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
 			ret = VM_FAULT_SIGBUS;
 			break;
 		}
@@ -3529,7 +3532,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct i915_vma *vma;
+	struct i915_vma *vma, *next;
 	int ret;
 
 	if (obj->cache_level == cache_level)
@@ -3540,7 +3543,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		return -EBUSY;
 	}
 
-	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
 		if (!i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) {
 			ret = i915_vma_unbind(vma);
 			if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d269ecf46e26..768e6665e4e3 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -766,9 +766,9 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		 * relocations were valid.
 		 */
 		for (j = 0; j < exec[i].relocation_count; j++) {
-			if (copy_to_user(&user_relocs[j].presumed_offset,
-					 &invalid_offset,
-					 sizeof(invalid_offset))) {
+			if (__copy_to_user(&user_relocs[j].presumed_offset,
+					   &invalid_offset,
+					   sizeof(invalid_offset))) {
 				ret = -EFAULT;
 				mutex_lock(&dev->struct_mutex);
 				goto err;
@@ -1329,18 +1329,21 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list,
 				     &dev_priv->gtt.base);
 	if (!ret) {
+		struct drm_i915_gem_exec_object __user *user_exec_list =
+			to_user_ptr(args->buffers_ptr);
+
 		/* Copy the new buffer offsets back to the user's exec list. */
-		for (i = 0; i < args->buffer_count; i++)
-			exec_list[i].offset = exec2_list[i].offset;
-		/* ... and back out to userspace */
-		ret = copy_to_user(to_user_ptr(args->buffers_ptr),
-				   exec_list,
-				   sizeof(*exec_list) * args->buffer_count);
-		if (ret) {
-			ret = -EFAULT;
-			DRM_DEBUG("failed to copy %d exec entries "
-				  "back to user (%d)\n",
-				  args->buffer_count, ret);
+		for (i = 0; i < args->buffer_count; i++) {
+			ret = __copy_to_user(&user_exec_list[i].offset,
+					     &exec2_list[i].offset,
+					     sizeof(user_exec_list[i].offset));
+			if (ret) {
+				ret = -EFAULT;
+				DRM_DEBUG("failed to copy %d exec entries "
+					  "back to user (%d)\n",
+					  args->buffer_count, ret);
+				break;
+			}
 		}
 	}
 
@@ -1388,14 +1391,21 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 				     &dev_priv->gtt.base);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
-		ret = copy_to_user(to_user_ptr(args->buffers_ptr),
-				   exec2_list,
-				   sizeof(*exec2_list) * args->buffer_count);
-		if (ret) {
-			ret = -EFAULT;
-			DRM_DEBUG("failed to copy %d exec entries "
-				  "back to user (%d)\n",
-				  args->buffer_count, ret);
+		struct drm_i915_gem_exec_object2 *user_exec_list =
+				   to_user_ptr(args->buffers_ptr);
+		int i;
+
+		for (i = 0; i < args->buffer_count; i++) {
+			ret = __copy_to_user(&user_exec_list[i].offset,
+					     &exec2_list[i].offset,
+					     sizeof(user_exec_list[i].offset));
+			if (ret) {
+				ret = -EFAULT;
+				DRM_DEBUG("failed to copy %d exec entries "
+					  "back to user\n",
+					  args->buffer_count);
+				break;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d278be110805..1855cdca39cd 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -827,6 +827,16 @@ void i915_check_and_clear_faults(struct drm_device *dev)
 	POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS]));
 }
 
+static void i915_ggtt_flush(struct drm_i915_private *dev_priv)
+{
+	if (INTEL_INFO(dev_priv->dev)->gen < 6) {
+		intel_gtt_chipset_flush();
+	} else {
+		I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+		POSTING_READ(GFX_FLSH_CNTL_GEN6);
+	}
+}
+
 void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -843,6 +853,8 @@ void i915_gem_suspend_gtt_mappings(struct drm_device *dev)
 				       dev_priv->gtt.base.start / PAGE_SIZE,
 				       dev_priv->gtt.base.total / PAGE_SIZE,
 				       true);
+
+	i915_ggtt_flush(dev_priv);
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
@@ -863,7 +875,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 		i915_gem_gtt_bind_object(obj, obj->cache_level);
 	}
 
-	i915_gem_chipset_flush(dev);
+	i915_ggtt_flush(dev_priv);
 }
 
 int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 28d24caa49f3..3c78b2268209 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -74,6 +74,50 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 	if (base == 0)
 		return 0;
 
+	/* make sure we don't clobber the GTT if it's within stolen memory */
+	if (INTEL_INFO(dev)->gen <= 4 && !IS_G33(dev) && !IS_G4X(dev)) {
+		struct {
+			u32 start, end;
+		} stolen[2] = {
+			{ .start = base, .end = base + dev_priv->gtt.stolen_size, },
+			{ .start = base, .end = base + dev_priv->gtt.stolen_size, },
+		};
+		u64 gtt_start, gtt_end;
+
+		gtt_start = I915_READ(PGTBL_CTL);
+		if (IS_GEN4(dev))
+			gtt_start = (gtt_start & PGTBL_ADDRESS_LO_MASK) |
+				(gtt_start & PGTBL_ADDRESS_HI_MASK) << 28;
+		else
+			gtt_start &= PGTBL_ADDRESS_LO_MASK;
+		gtt_end = gtt_start + gtt_total_entries(dev_priv->gtt) * 4;
+
+		if (gtt_start >= stolen[0].start && gtt_start < stolen[0].end)
+			stolen[0].end = gtt_start;
+		if (gtt_end > stolen[1].start && gtt_end <= stolen[1].end)
+			stolen[1].start = gtt_end;
+
+		/* pick the larger of the two chunks */
+		if (stolen[0].end - stolen[0].start >
+		    stolen[1].end - stolen[1].start) {
+			base = stolen[0].start;
+			dev_priv->gtt.stolen_size = stolen[0].end - stolen[0].start;
+		} else {
+			base = stolen[1].start;
+			dev_priv->gtt.stolen_size = stolen[1].end - stolen[1].start;
+		}
+
+		if (stolen[0].start != stolen[1].start ||
+		    stolen[0].end != stolen[1].end) {
+			DRM_DEBUG_KMS("GTT within stolen memory at 0x%llx-0x%llx\n",
+				      (unsigned long long) gtt_start,
+				      (unsigned long long) gtt_end - 1);
+			DRM_DEBUG_KMS("Stolen memory adjusted to 0x%x-0x%x\n",
+				      base, base + (u32) dev_priv->gtt.stolen_size - 1);
+		}
+	}
+
+
 	/* Verify that nothing else uses this physical address. Stolen
 	 * memory should be reserved by the BIOS and hidden from the
 	 * kernel. So if the region is already marked as busy, something
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index d554169ac592..40504504c9e2 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1252,10 +1252,20 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 	spin_lock(&dev_priv->irq_lock);
 	for (i = 1; i < HPD_NUM_PINS; i++) {
 
-		WARN_ONCE(hpd[i] & hotplug_trigger &&
-			  dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED,
-			  "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n",
-			  hotplug_trigger, i, hpd[i]);
+		if (hpd[i] & hotplug_trigger &&
+		    dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED) {
+			/*
+			 * On GMCH platforms the interrupt mask bits only
+			 * prevent irq generation, not the setting of the
+			 * hotplug bits itself. So only WARN about unexpected
+			 * interrupts on saner platforms.
+			 */
+			WARN_ONCE(INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev),
+				  "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n",
+				  hotplug_trigger, i, hpd[i]);
+
+			continue;
+		}
 
 		if (!(hpd[i] & hotplug_trigger) ||
 		    dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index a48b7cad6f11..0a3b9386eb43 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -631,6 +631,9 @@
 /*
  * Instruction and interrupt control regs
  */
+#define PGTBL_CTL	0x02020
+#define   PGTBL_ADDRESS_LO_MASK	0xfffff000 /* bits [31:12] */
+#define   PGTBL_ADDRESS_HI_MASK	0x000000f0 /* bits [35:32] (gen4) */
 #define PGTBL_ER	0x02024
 #define RENDER_RING_BASE	0x02000
 #define BSD_RING_BASE		0x04000
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 6e580c98dede..783ae08200e8 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -238,14 +238,16 @@ TRACE_EVENT(i915_gem_evict_vm,
 	    TP_ARGS(vm),
 
 	    TP_STRUCT__entry(
+			     __field(u32, dev)
 			     __field(struct i915_address_space *, vm)
 			    ),
 
 	    TP_fast_assign(
+			   __entry->dev = vm->dev->primary->index;
 			   __entry->vm = vm;
 			  ),
 
-	    TP_printk("dev=%d, vm=%p", __entry->vm->dev->primary->index, __entry->vm)
+	    TP_printk("dev=%d, vm=%p", __entry->dev, __entry->vm)
 );
 
 TRACE_EVENT(i915_gem_ring_sync_to,
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index f22041973f3a..08105fddfd2a 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -839,7 +839,7 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	}
 }
 
-static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
+static int intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
 {
 	DRM_DEBUG_KMS("Falling back to manually reading VBT from "
 		      "VBIOS ROM for %s\n",
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index e2e39e65f109..834847527982 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -750,7 +750,7 @@ static const struct drm_encoder_funcs intel_crt_enc_funcs = {
 	.destroy = intel_encoder_destroy,
 };
 
-static int __init intel_no_crt_dmi_callback(const struct dmi_system_id *id)
+static int intel_no_crt_dmi_callback(const struct dmi_system_id *id)
 {
 	DRM_INFO("Skipping CRT initialization for %s\n", id->ident);
 	return 1;
@@ -765,6 +765,14 @@ static const struct dmi_system_id intel_no_crt[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ZGB"),
 		},
 	},
+	{
+		.callback = intel_no_crt_dmi_callback,
+		.ident = "DELL XPS 8700",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 8700"),
+		},
+	},
 	{ }
 };
 
@@ -833,6 +841,7 @@ void intel_crt_init(struct drm_device *dev)
 		crt->base.get_hw_state = intel_crt_get_hw_state;
 	}
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	drm_connector_helper_add(connector, &intel_crt_connector_helper_funcs);
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9b8a7c7ea7fc..c51469051e41 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3817,7 +3817,6 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 		ironlake_fdi_disable(crtc);
 
 		ironlake_disable_pch_transcoder(dev_priv, pipe);
-		intel_set_pch_fifo_underrun_reporting(dev, pipe, true);
 
 		if (HAS_PCH_CPT(dev)) {
 			/* disable TRANS_DP_CTL */
@@ -3883,7 +3882,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 
 	if (intel_crtc->config.has_pch_encoder) {
 		lpt_disable_pch_transcoder(dev_priv);
-		intel_set_pch_fifo_underrun_reporting(dev, TRANSCODER_A, true);
 		intel_ddi_fdi_disable(crtc);
 	}
 
@@ -9354,11 +9352,22 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(pipe_src_w);
 	PIPE_CONF_CHECK_I(pipe_src_h);
 
-	PIPE_CONF_CHECK_I(gmch_pfit.control);
-	/* pfit ratios are autocomputed by the hw on gen4+ */
-	if (INTEL_INFO(dev)->gen < 4)
-		PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
-	PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
+	/*
+	 * FIXME: BIOS likes to set up a cloned config with lvds+external
+	 * screen. Since we don't yet re-compute the pipe config when moving
+	 * just the lvds port away to another pipe the sw tracking won't match.
+	 *
+	 * Proper atomic modesets with recomputed global state will fix this.
+	 * Until then just don't check gmch state for inherited modes.
+	 */
+	if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_INHERITED_MODE)) {
+		PIPE_CONF_CHECK_I(gmch_pfit.control);
+		/* pfit ratios are autocomputed by the hw on gen4+ */
+		if (INTEL_INFO(dev)->gen < 4)
+			PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
+		PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
+	}
+
 	PIPE_CONF_CHECK_I(pch_pfit.enabled);
 	if (current_config->pch_pfit.enabled) {
 		PIPE_CONF_CHECK_I(pch_pfit.pos);
@@ -10771,6 +10780,17 @@ static void quirk_invert_brightness(struct drm_device *dev)
 	DRM_INFO("applying inverted panel brightness quirk\n");
 }
 
+/*
+ * Some machines (Dell XPS13) suffer broken backlight controls if
+ * BLM_PCH_PWM_ENABLE is set.
+ */
+static void quirk_no_pcm_pwm_enable(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	dev_priv->quirks |= QUIRK_NO_PCH_PWM_ENABLE;
+	DRM_INFO("applying no-PCH_PWM_ENABLE quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -10839,6 +10859,14 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Acer Aspire 4736Z */
 	{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
+
+	/* Acer Aspire 5336 */
+	{ 0x2a42, 0x1025, 0x048a, quirk_invert_brightness },
+
+	/* Dell XPS13 HD Sandy Bridge */
+	{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
+	/* Dell XPS13 HD and XPS13 FHD Ivy Bridge */
+	{ 0x0166, 0x1028, 0x058b, quirk_no_pcm_pwm_enable },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -10962,15 +10990,6 @@ void intel_modeset_init(struct drm_device *dev)
 	intel_disable_fbc(dev);
 }
 
-static void
-intel_connector_break_all_links(struct intel_connector *connector)
-{
-	connector->base.dpms = DRM_MODE_DPMS_OFF;
-	connector->base.encoder = NULL;
-	connector->encoder->connectors_active = false;
-	connector->encoder->base.crtc = NULL;
-}
-
 static void intel_enable_pipe_a(struct drm_device *dev)
 {
 	struct intel_connector *connector;
@@ -11052,8 +11071,17 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 			if (connector->encoder->base.crtc != &crtc->base)
 				continue;
 
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
+		/* multiple connectors may have the same encoder:
+		 *  handle them and break crtc link separately */
+		list_for_each_entry(connector, &dev->mode_config.connector_list,
+				    base.head)
+			if (connector->encoder->base.crtc == &crtc->base) {
+				connector->encoder->base.crtc = NULL;
+				connector->encoder->connectors_active = false;
+			}
 
 		WARN_ON(crtc->active);
 		crtc->base.enabled = false;
@@ -11124,6 +11152,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				      drm_get_encoder_name(&encoder->base));
 			encoder->disable(encoder);
 		}
+		encoder->base.crtc = NULL;
+		encoder->connectors_active = false;
 
 		/* Inconsistent output/port/pipe state happens presumably due to
 		 * a bug in one of the get_hw_state functions. Or someplace else
@@ -11134,8 +11164,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				    base.head) {
 			if (connector->encoder != encoder)
 				continue;
-
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
 	}
 	/* Enabled encoders without active connectors will be fixed in
@@ -11177,6 +11207,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			    base.head) {
 		memset(&crtc->config, 0, sizeof(crtc->config));
 
+		crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE;
+
 		crtc->active = dev_priv->display.get_pipe_config(crtc,
 								 &crtc->config);
 
@@ -11334,6 +11366,14 @@ void intel_modeset_gem_init(struct drm_device *dev)
 	mutex_unlock(&dev->mode_config.mutex);
 }
 
+void intel_connector_unregister(struct intel_connector *intel_connector)
+{
+	struct drm_connector *connector = &intel_connector->base;
+
+	intel_panel_destroy_backlight(connector);
+	drm_sysfs_connector_remove(connector);
+}
+
 void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -11378,8 +11418,10 @@ void intel_modeset_cleanup(struct drm_device *dev)
 
 	/* destroy the backlight and sysfs files before encoders/connectors */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		intel_panel_destroy_backlight(connector);
-		drm_sysfs_connector_remove(connector);
+		struct intel_connector *intel_connector;
+
+		intel_connector = to_intel_connector(connector);
+		intel_connector->unregister(intel_connector);
 	}
 
 	drm_mode_config_cleanup(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2688f6d64bb9..b2d0887b3d12 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -744,6 +744,16 @@ out:
 	return ret;
 }
 
+static void
+intel_dp_connector_unregister(struct intel_connector *intel_connector)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(&intel_connector->base);
+
+	sysfs_remove_link(&intel_connector->base.kdev->kobj,
+			  intel_dp->adapter.dev.kobj.name);
+	intel_connector_unregister(intel_connector);
+}
+
 static int
 intel_dp_i2c_init(struct intel_dp *intel_dp,
 		  struct intel_connector *intel_connector, const char *name)
@@ -761,9 +771,19 @@ intel_dp_i2c_init(struct intel_dp *intel_dp,
 	strncpy(intel_dp->adapter.name, name, sizeof(intel_dp->adapter.name) - 1);
 	intel_dp->adapter.name[sizeof(intel_dp->adapter.name) - 1] = '\0';
 	intel_dp->adapter.algo_data = &intel_dp->algo;
-	intel_dp->adapter.dev.parent = intel_connector->base.kdev;
+	intel_dp->adapter.dev.parent = intel_connector->base.dev->dev;
 
 	ret = i2c_dp_aux_add_bus(&intel_dp->adapter);
+	if (ret < 0)
+		return ret;
+
+	ret = sysfs_create_link(&intel_connector->base.kdev->kobj,
+				&intel_dp->adapter.dev.kobj,
+				intel_dp->adapter.dev.kobj.name);
+
+	if (ret < 0)
+		i2c_del_adapter(&intel_dp->adapter);
+
 	return ret;
 }
 
@@ -3686,6 +3706,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
 	else
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_dp_connector_unregister;
 
 	intel_dp->aux_ch_ctl_reg = intel_dp->output_reg + 0x10;
 	if (HAS_DDI(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index fbfaaba5cc3b..0b59914344e4 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -187,6 +187,14 @@ struct intel_connector {
 	 * and active (i.e. dpms ON state). */
 	bool (*get_hw_state)(struct intel_connector *);
 
+	/*
+	 * Removes all interfaces through which the connector is accessible
+	 * - like sysfs, debugfs entries -, so that no new operations can be
+	 * started on the connector. Also makes sure all currently pending
+	 * operations finish before returing.
+	 */
+	void (*unregister)(struct intel_connector *);
+
 	/* Panel info for eDP and LVDS */
 	struct intel_panel panel;
 
@@ -219,7 +227,8 @@ struct intel_crtc_config {
 	 * tracked with quirk flags so that fastboot and state checker can act
 	 * accordingly.
 	 */
-#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */
+#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS	(1<<0) /* unreliable sync mode.flags */
+#define PIPE_CONFIG_QUIRK_INHERITED_MODE	(1<<1) /* mode inherited from firmware */
 	unsigned long quirks;
 
 	/* User requested mode, only valid as a starting point to
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index fabbf0d895cf..ad05683ac5b6 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -586,6 +586,7 @@ bool intel_dsi_init(struct drm_device *dev)
 	intel_encoder->get_config = intel_dsi_get_config;
 
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	for (i = 0; i < ARRAY_SIZE(intel_dsi_devices); i++) {
 		dsi = &intel_dsi_devices[i];
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index eeff998e52ef..86eeb8b7d435 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -477,6 +477,7 @@ void intel_dvo_init(struct drm_device *dev)
 	intel_encoder->compute_config = intel_dvo_compute_config;
 	intel_encoder->mode_set = intel_dvo_mode_set;
 	intel_connector->get_hw_state = intel_dvo_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	/* Now, try to find a controller */
 	for (i = 0; i < ARRAY_SIZE(intel_dvo_devices); i++) {
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ee3181ebcc92..7b277c369dce 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -841,11 +841,11 @@ static void intel_disable_hdmi(struct intel_encoder *encoder)
 	}
 }
 
-static int hdmi_portclock_limit(struct intel_hdmi *hdmi)
+static int hdmi_portclock_limit(struct intel_hdmi *hdmi, bool respect_dvi_limit)
 {
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 
-	if (!hdmi->has_hdmi_sink || IS_G4X(dev))
+	if ((respect_dvi_limit && !hdmi->has_hdmi_sink) || IS_G4X(dev))
 		return 165000;
 	else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8)
 		return 300000;
@@ -857,7 +857,8 @@ static enum drm_mode_status
 intel_hdmi_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
-	if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector)))
+	if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector),
+					       true))
 		return MODE_CLOCK_HIGH;
 	if (mode->clock < 20000)
 		return MODE_CLOCK_LOW;
@@ -875,7 +876,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode;
 	int clock_12bpc = pipe_config->adjusted_mode.crtc_clock * 3 / 2;
-	int portclock_limit = hdmi_portclock_limit(intel_hdmi);
+	int portclock_limit = hdmi_portclock_limit(intel_hdmi, false);
 	int desired_bpp;
 
 	if (intel_hdmi->color_range_auto) {
@@ -1261,6 +1262,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
 	else
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	intel_hdmi_add_properties(intel_hdmi, connector);
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 8bcb93a2a9f6..af49b24d14cb 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -544,7 +544,7 @@ static const struct drm_encoder_funcs intel_lvds_enc_funcs = {
 	.destroy = intel_encoder_destroy,
 };
 
-static int __init intel_no_lvds_dmi_callback(const struct dmi_system_id *id)
+static int intel_no_lvds_dmi_callback(const struct dmi_system_id *id)
 {
 	DRM_INFO("Skipping LVDS initialization for %s\n", id->ident);
 	return 1;
@@ -905,6 +905,17 @@ void intel_lvds_init(struct drm_device *dev)
 	int pipe;
 	u8 pin;
 
+	/*
+	 * Unlock registers and just leave them unlocked. Do this before
+	 * checking quirk lists to avoid bogus WARNINGs.
+	 */
+	if (HAS_PCH_SPLIT(dev)) {
+		I915_WRITE(PCH_PP_CONTROL,
+			   I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
+	} else {
+		I915_WRITE(PP_CONTROL,
+			   I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
+	}
 	if (!intel_lvds_supported(dev))
 		return;
 
@@ -957,6 +968,7 @@ void intel_lvds_init(struct drm_device *dev)
 	intel_encoder->get_hw_state = intel_lvds_get_hw_state;
 	intel_encoder->get_config = intel_lvds_get_config;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_LVDS;
@@ -1098,17 +1110,6 @@ out:
 	DRM_DEBUG_KMS("detected %s-link lvds configuration\n",
 		      lvds_encoder->is_dual_link ? "dual" : "single");
 
-	/*
-	 * Unlock registers and just
-	 * leave them unlocked
-	 */
-	if (HAS_PCH_SPLIT(dev)) {
-		I915_WRITE(PCH_PP_CONTROL,
-			   I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
-	} else {
-		I915_WRITE(PP_CONTROL,
-			   I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
-	}
 	lvds_connector->lid_notifier.notifier_call = intel_lid_notify;
 	if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) {
 		DRM_DEBUG_KMS("lid notifier registration failed\n");
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 079ea38f14d9..c6d9777bdb45 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -501,6 +501,7 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level,
 	enum pipe pipe = intel_get_pipe_from_connector(connector);
 	u32 freq;
 	unsigned long flags;
+	u64 n;
 
 	if (!panel->backlight.present || pipe == INVALID_PIPE)
 		return;
@@ -511,10 +512,9 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level,
 
 	/* scale to hardware max, but be careful to not overflow */
 	freq = panel->backlight.max;
-	if (freq < max)
-		level = level * freq / max;
-	else
-		level = freq / max * level;
+	n = (u64)level * freq;
+	do_div(n, max);
+	level = n;
 
 	panel->backlight.level = level;
 	if (panel->backlight.device)
@@ -645,7 +645,7 @@ static void pch_enable_backlight(struct intel_connector *connector)
 
 	cpu_ctl2 = I915_READ(BLC_PWM_CPU_CTL2);
 	if (cpu_ctl2 & BLM_PWM_ENABLE) {
-		WARN(1, "cpu backlight already enabled\n");
+		DRM_DEBUG_KMS("cpu backlight already enabled\n");
 		cpu_ctl2 &= ~BLM_PWM_ENABLE;
 		I915_WRITE(BLC_PWM_CPU_CTL2, cpu_ctl2);
 	}
@@ -671,6 +671,10 @@ static void pch_enable_backlight(struct intel_connector *connector)
 	pch_ctl2 = panel->backlight.max << 16;
 	I915_WRITE(BLC_PWM_PCH_CTL2, pch_ctl2);
 
+	/* XXX: transitional */
+	if (dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)
+		return;
+
 	pch_ctl1 = 0;
 	if (panel->backlight.active_low_pwm)
 		pch_ctl1 |= BLM_PCH_POLARITY;
@@ -689,7 +693,7 @@ static void i9xx_enable_backlight(struct intel_connector *connector)
 
 	ctl = I915_READ(BLC_PWM_CTL);
 	if (ctl & BACKLIGHT_DUTY_CYCLE_MASK_PNV) {
-		WARN(1, "backlight already enabled\n");
+		DRM_DEBUG_KMS("backlight already enabled\n");
 		I915_WRITE(BLC_PWM_CTL, 0);
 	}
 
@@ -720,7 +724,7 @@ static void i965_enable_backlight(struct intel_connector *connector)
 
 	ctl2 = I915_READ(BLC_PWM_CTL2);
 	if (ctl2 & BLM_PWM_ENABLE) {
-		WARN(1, "backlight already enabled\n");
+		DRM_DEBUG_KMS("backlight already enabled\n");
 		ctl2 &= ~BLM_PWM_ENABLE;
 		I915_WRITE(BLC_PWM_CTL2, ctl2);
 	}
@@ -732,9 +736,6 @@ static void i965_enable_backlight(struct intel_connector *connector)
 	ctl = freq << 16;
 	I915_WRITE(BLC_PWM_CTL, ctl);
 
-	/* XXX: combine this into above write? */
-	intel_panel_actually_set_backlight(connector, panel->backlight.level);
-
 	ctl2 = BLM_PIPE(pipe);
 	if (panel->backlight.combination_mode)
 		ctl2 |= BLM_COMBINATION_MODE;
@@ -743,6 +744,8 @@ static void i965_enable_backlight(struct intel_connector *connector)
 	I915_WRITE(BLC_PWM_CTL2, ctl2);
 	POSTING_READ(BLC_PWM_CTL2);
 	I915_WRITE(BLC_PWM_CTL2, ctl2 | BLM_PWM_ENABLE);
+
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
 }
 
 static void vlv_enable_backlight(struct intel_connector *connector)
@@ -755,7 +758,7 @@ static void vlv_enable_backlight(struct intel_connector *connector)
 
 	ctl2 = I915_READ(VLV_BLC_PWM_CTL2(pipe));
 	if (ctl2 & BLM_PWM_ENABLE) {
-		WARN(1, "backlight already enabled\n");
+		DRM_DEBUG_KMS("backlight already enabled\n");
 		ctl2 &= ~BLM_PWM_ENABLE;
 		I915_WRITE(VLV_BLC_PWM_CTL2(pipe), ctl2);
 	}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index e1fc35a72656..8e7245151b96 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1539,6 +1539,16 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 
 	DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
 
+	if (IS_I915GM(dev) && enabled) {
+		struct intel_framebuffer *fb;
+
+		fb = to_intel_framebuffer(enabled->fb);
+
+		/* self-refresh seems busted with untiled */
+		if (fb->obj->tiling_mode == I915_TILING_NONE)
+			enabled = NULL;
+	}
+
 	/*
 	 * Overlay gets an aggressive default since video jitter is bad.
 	 */
@@ -5128,10 +5138,25 @@ bool intel_display_power_enabled_sw(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains;
+	struct i915_power_well *power_well;
+	bool is_enabled;
+	int i;
+
+	if (dev_priv->pm.suspended)
+		return false;
 
 	power_domains = &dev_priv->power_domains;
+	is_enabled = true;
+	for_each_power_well_rev(i, power_well, BIT(domain), power_domains) {
+		if (power_well->always_on)
+			continue;
 
-	return power_domains->domain_use_count[domain];
+		if (!power_well->count) {
+			is_enabled = false;
+			break;
+		}
+	}
+	return is_enabled;
 }
 
 bool intel_display_power_enabled(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 31b36c5ac894..d488fc71ef49 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -475,6 +475,9 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		}
 	}
 
+	/* Enforce ordering by reading HEAD register back */
+	I915_READ_HEAD(ring);
+
 	/* Initialize the ring. This must happen _after_ we've cleared the ring
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 95bdfb3c431c..1890264cf115 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1383,7 +1383,9 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 			 >> SDVO_PORT_MULTIPLY_SHIFT) + 1;
 	}
 
-	dotclock = pipe_config->port_clock / pipe_config->pixel_multiplier;
+	dotclock = pipe_config->port_clock;
+	if (pipe_config->pixel_multiplier)
+		dotclock /= pipe_config->pixel_multiplier;
 
 	if (HAS_PCH_SPLIT(dev))
 		ironlake_check_encoder_dotclock(pipe_config, dotclock);
@@ -2397,6 +2399,7 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector,
 	connector->base.base.doublescan_allowed = 0;
 	connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB;
 	connector->base.get_hw_state = intel_sdvo_connector_get_hw_state;
+	connector->base.unregister = intel_connector_unregister;
 
 	intel_connector_attach_encoder(&connector->base, &encoder->base);
 	drm_sysfs_connector_add(&connector->base.base);
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 22cf0f4ba248..9c9606c8bb1a 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -854,6 +854,10 @@ intel_enable_tv(struct intel_encoder *encoder)
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	/* Prevents vblank waits from timing out in intel_tv_detect_type() */
+	intel_wait_for_vblank(encoder->base.dev,
+			      to_intel_crtc(encoder->base.crtc)->pipe);
+
 	I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE);
 }
 
@@ -1536,9 +1540,14 @@ static int tv_is_present_in_vbt(struct drm_device *dev)
 		/*
 		 * If the device type is not TV, continue.
 		 */
-		if (p_child->old.device_type != DEVICE_TYPE_INT_TV &&
-			p_child->old.device_type != DEVICE_TYPE_TV)
+		switch (p_child->old.device_type) {
+		case DEVICE_TYPE_INT_TV:
+		case DEVICE_TYPE_TV:
+		case DEVICE_TYPE_TV_SVIDEO_COMPOSITE:
+			break;
+		default:
 			continue;
+		}
 		/* Only when the addin_offset is non-zero, it is regarded
 		 * as present.
 		 */
@@ -1634,6 +1643,7 @@ intel_tv_init(struct drm_device *dev)
 	intel_encoder->disable = intel_disable_tv;
 	intel_encoder->get_hw_state = intel_tv_get_hw_state;
 	intel_connector->get_hw_state = intel_connector_get_hw_state;
+	intel_connector->unregister = intel_connector_unregister;
 
 	intel_connector_attach_encoder(intel_connector, intel_encoder);
 	intel_encoder->type = INTEL_OUTPUT_TVOUT;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 87df68f5f504..c8796316d242 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -177,6 +177,8 @@ static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
 {
 	__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
 			   _MASKED_BIT_DISABLE(0xffff));
+	__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
+			   _MASKED_BIT_DISABLE(0xffff));
 	/* something from same cacheline, but !FORCEWAKE_VLV */
 	__raw_posting_read(dev_priv, FORCEWAKE_ACK_VLV);
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c
index 7cf8b1348632..6fdf6e385bf7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c
@@ -51,6 +51,14 @@ nv04_disp_scanoutpos(struct nouveau_object *object, u32 mthd,
 	args->htotal  = nv_rd32(priv, 0x680824 + (head * 0x2000)) & 0xffff;
 	args->hblanke = args->htotal - 1;
 
+	/*
+	 * If output is vga instead of digital then vtotal/htotal is invalid
+	 * so we have to give up and trigger the timestamping fallback in the
+	 * drm core.
+	 */
+	if (!args->vtotal || !args->htotal)
+		return -ENOTSUPP;
+
 	args->time[0] = ktime_to_ns(ktime_get());
 	line = nv_rd32(priv, 0x600868 + (head * 0x2000));
 	args->time[1] = ktime_to_ns(ktime_get());
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
index 1c5e4e8b2c82..e031d7c88fa3 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
@@ -732,7 +732,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id,
 	}
 
 	if (outp == 8)
-		return false;
+		return conf;
 
 	data = exec_lookup(priv, head, outp, ctrl, dcb, &ver, &hdr, &cnt, &len, &info1);
 	if (data == 0x0000)
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c
index a86bd3352bf8..e69bfde37aef 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c
@@ -1318,10 +1318,12 @@ nv108_grctx_generate_mods(struct nvc0_graph_priv *priv, struct nvc0_grctx *info)
 	mmio_list(0x408010, 0x80000000,  0, 0);
 	mmio_list(0x419004, 0x00000000,  8, 1);
 	mmio_list(0x419008, 0x00000000,  0, 0);
+	mmio_list(0x4064cc, 0x80000000,  0, 0);
 	mmio_list(0x408004, 0x00000000,  8, 0);
 	mmio_list(0x408008, 0x80000030,  0, 0);
 	mmio_list(0x418808, 0x00000000,  8, 0);
 	mmio_list(0x41880c, 0x80000030,  0, 0);
+	mmio_list(0x4064c8, 0x00c20200,  0, 0);
 	mmio_list(0x418810, 0x80000000, 12, 2);
 	mmio_list(0x419848, 0x10000000, 12, 2);
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
index 2d9b9d7a7992..f3edd2841f2d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
@@ -124,6 +124,7 @@ dcb_outp_parse(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len,
 	       struct dcb_output *outp)
 {
 	u16 dcb = dcb_outp(bios, idx, ver, len);
+	memset(outp, 0x00, sizeof(*outp));
 	if (dcb) {
 		if (*ver >= 0x20) {
 			u32 conn = nv_ro32(bios, dcb + 0x00);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
index e8822a934c48..90d8bf8ce0dc 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
@@ -26,6 +26,7 @@
 
 const struct nouveau_mc_intr
 nv50_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP before FIFO, so pageflip-timestamping works! */
 	{ 0x00000001, NVDEV_ENGINE_MPEG },
 	{ 0x00000100, NVDEV_ENGINE_FIFO },
 	{ 0x00001000, NVDEV_ENGINE_GR },
@@ -34,7 +35,6 @@ nv50_mc_intr[] = {
 	{ 0x00020000, NVDEV_ENGINE_VP },	/* NV84- */
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
 	{ 0x00200000, NVDEV_SUBDEV_GPIO },
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
 	{ 0x0002d101, NVDEV_SUBDEV_FB },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
index f8a6f18e2d34..95b3d35388a8 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
@@ -26,6 +26,7 @@
 
 static const struct nouveau_mc_intr
 nv98_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP first, so pageflip timestamps work */
 	{ 0x00000001, NVDEV_ENGINE_PPP },
 	{ 0x00000100, NVDEV_ENGINE_FIFO },
 	{ 0x00001000, NVDEV_ENGINE_GR },
@@ -37,7 +38,6 @@ nv98_mc_intr[] = {
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
 	{ 0x00200000, NVDEV_SUBDEV_GPIO },
 	{ 0x00400000, NVDEV_ENGINE_COPY0 },	/* NVA3-     */
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
 	{ 0x0042d101, NVDEV_SUBDEV_FB },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
index 34472d317097..ac7f99a15fa7 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
@@ -26,6 +26,7 @@
 
 const struct nouveau_mc_intr
 nvc0_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP first, so pageflip timestamps work. */
 	{ 0x00000001, NVDEV_ENGINE_PPP },
 	{ 0x00000020, NVDEV_ENGINE_COPY0 },
 	{ 0x00000040, NVDEV_ENGINE_COPY1 },
@@ -40,7 +41,6 @@ nvc0_mc_intr[] = {
 	{ 0x00200000, NVDEV_SUBDEV_GPIO },
 	{ 0x01000000, NVDEV_SUBDEV_PWR },
 	{ 0x02000000, NVDEV_SUBDEV_LTCG },
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x08000000, NVDEV_SUBDEV_FB },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x40000000, NVDEV_SUBDEV_IBUS },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
index 95f6129eeede..29d4c417a5b3 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
@@ -54,8 +54,10 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target)
 
 	/* check that we're not already at the target duty cycle */
 	duty = fan->get(therm);
-	if (duty == target)
-		goto done;
+	if (duty == target) {
+		spin_unlock_irqrestore(&fan->lock, flags);
+		return 0;
+	}
 
 	/* smooth out the fanspeed increase/decrease */
 	if (!immediate && duty >= 0) {
@@ -73,8 +75,15 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target)
 
 	nv_debug(therm, "FAN update: %d\n", duty);
 	ret = fan->set(therm, duty);
-	if (ret)
-		goto done;
+	if (ret) {
+		spin_unlock_irqrestore(&fan->lock, flags);
+		return ret;
+	}
+
+	/* fan speed updated, drop the fan lock before grabbing the
+	 * alarm-scheduling lock and risking a deadlock
+	 */
+	spin_unlock_irqrestore(&fan->lock, flags);
 
 	/* schedule next fan update, if not at target speed already */
 	if (list_empty(&fan->alarm.head) && target != duty) {
@@ -92,8 +101,6 @@ nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target)
 		ptimer->alarm(ptimer, delay * 1000 * 1000, &fan->alarm);
 	}
 
-done:
-	spin_unlock_irqrestore(&fan->lock, flags);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 83face3f608f..279206997e5c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -389,9 +389,6 @@ bool nouveau_acpi_rom_supported(struct pci_dev *pdev)
 	acpi_status status;
 	acpi_handle dhandle, rom_handle;
 
-	if (!nouveau_dsm_priv.dsm_detected && !nouveau_dsm_priv.optimus_detected)
-		return false;
-
 	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 24011596af43..6601690ab29c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -734,6 +734,9 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		  fb->bits_per_pixel, fb->pitches[0], crtc->x, crtc->y,
 		  new_bo->bo.offset };
 
+	/* Keep vblanks on during flip, for the target crtc of this flip */
+	drm_vblank_get(dev, nouveau_crtc(crtc)->index);
+
 	/* Emit a page flip */
 	if (nv_device(drm->device)->card_type >= NV_50) {
 		ret = nv50_display_flip_next(crtc, fb, chan, swap_interval);
@@ -762,9 +765,9 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	}
 
 	ret = nouveau_page_flip_emit(chan, old_bo, new_bo, s, &fence);
-	mutex_unlock(&chan->cli->mutex);
 	if (ret)
 		goto fail_unreserve;
+	mutex_unlock(&chan->cli->mutex);
 
 	/* Update the crtc struct and cleanup */
 	crtc->fb = fb;
@@ -777,6 +780,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	return 0;
 
 fail_unreserve:
+	drm_vblank_put(dev, nouveau_crtc(crtc)->index);
 	ttm_bo_unreserve(&old_bo->bo);
 fail_unpin:
 	mutex_unlock(&chan->cli->mutex);
@@ -796,6 +800,7 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	struct drm_device *dev = drm->dev;
 	struct nouveau_page_flip_state *s;
 	unsigned long flags;
+	int crtcid = -1;
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 
@@ -806,8 +811,16 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	}
 
 	s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head);
-	if (s->event)
-		drm_send_vblank_event(dev, s->crtc, s->event);
+	if (s->event) {
+		/* Vblank timestamps/counts are only correct on >= NV-50 */
+		if (nv_device(drm->device)->card_type >= NV_50)
+			crtcid = s->crtc;
+
+		drm_send_vblank_event(dev, crtcid, s->event);
+	}
+
+	/* Give up ownership of vblank for page-flipped crtc */
+	drm_vblank_put(dev, s->crtc);
 
 	list_del(&s->head);
 	if (ps)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h
index 23ca7a517246..74ed08a750f4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.h
@@ -10,7 +10,7 @@
 
 #define DRIVER_MAJOR		1
 #define DRIVER_MINOR		1
-#define DRIVER_PATCHLEVEL	1
+#define DRIVER_PATCHLEVEL	2
 
 /*
  * 1.1.1:
@@ -21,6 +21,8 @@
  *        to control registers on the MPs to enable performance counters,
  *        and to control the warp error enable mask (OpenGL requires out of
  *        bounds access to local memory to be silently ignored / return 0).
+ * 1.1.2:
+ *      - fixes multiple bugs in flip completion events and timestamping
  */
 
 #include <core/client.h>
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index 471347edc27e..a92fb01459c9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -100,7 +100,16 @@ void
 nouveau_vga_fini(struct nouveau_drm *drm)
 {
 	struct drm_device *dev = drm->dev;
+	bool runtime = false;
+
+	if (nouveau_runtime_pm == 1)
+		runtime = true;
+	if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
+		runtime = true;
+
 	vga_switcheroo_unregister_client(dev->pdev);
+	if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
+		vga_switcheroo_fini_domain_pm_ops(drm->dev->dev);
 	vga_client_register(dev->pdev, NULL, NULL, NULL);
 }
 
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index f926b4caf449..56c60552abba 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -199,7 +199,7 @@ static struct dmm_txn *dmm_txn_init(struct dmm *dmm, struct tcm *tcm)
 static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
 		struct page **pages, uint32_t npages, uint32_t roll)
 {
-	dma_addr_t pat_pa = 0;
+	dma_addr_t pat_pa = 0, data_pa = 0;
 	uint32_t *data;
 	struct pat *pat;
 	struct refill_engine *engine = txn->engine_handle;
@@ -223,7 +223,9 @@ static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
 			.lut_id = engine->tcm->lut_id,
 		};
 
-	data = alloc_dma(txn, 4*i, &pat->data_pa);
+	data = alloc_dma(txn, 4*i, &data_pa);
+	/* FIXME: what if data_pa is more than 32-bit ? */
+	pat->data_pa = data_pa;
 
 	while (i--) {
 		int n = i + roll;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 5aec3e81fe24..5fd3bab8b803 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -791,7 +791,7 @@ int omap_gem_get_paddr(struct drm_gem_object *obj,
 			omap_obj->paddr = tiler_ssptr(block);
 			omap_obj->block = block;
 
-			DBG("got paddr: %08x", omap_obj->paddr);
+			DBG("got paddr: %pad", &omap_obj->paddr);
 		}
 
 		omap_obj->paddr_cnt++;
@@ -988,9 +988,9 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	off = drm_vma_node_start(&obj->vma_node);
 
-	seq_printf(m, "%08x: %2d (%2d) %08llx %08Zx (%2d) %p %4d",
+	seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
 			omap_obj->flags, obj->name, obj->refcount.refcount.counter,
-			off, omap_obj->paddr, omap_obj->paddr_cnt,
+			off, &omap_obj->paddr, omap_obj->paddr_cnt,
 			omap_obj->vaddr, omap_obj->roll);
 
 	if (omap_obj->flags & OMAP_BO_TILED) {
@@ -1468,8 +1468,8 @@ void omap_gem_init(struct drm_device *dev)
 			entry->paddr = tiler_ssptr(block);
 			entry->block = block;
 
-			DBG("%d:%d: %dx%d: paddr=%08x stride=%d", i, j, w, h,
-					entry->paddr,
+			DBG("%d:%d: %dx%d: paddr=%pad stride=%d", i, j, w, h,
+					&entry->paddr,
 					usergart[i].stride_pfn << PAGE_SHIFT);
 		}
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index 046d5e660c04..5b62e212cbe5 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -142,8 +142,8 @@ static void omap_plane_pre_apply(struct omap_drm_apply *apply)
 	DBG("%dx%d -> %dx%d (%d)", info->width, info->height,
 			info->out_width, info->out_height,
 			info->screen_width);
-	DBG("%d,%d %08x %08x", info->pos_x, info->pos_y,
-			info->paddr, info->p_uv_addr);
+	DBG("%d,%d %pad %pad", info->pos_x, info->pos_y,
+			&info->paddr, &info->p_uv_addr);
 
 	/* TODO: */
 	ilace = false;
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 798bde2e5881..c39c414c7751 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -523,7 +523,6 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc,
 	struct qxl_framebuffer *qfb;
 	struct qxl_bo *bo, *old_bo = NULL;
 	struct qxl_crtc *qcrtc = to_qxl_crtc(crtc);
-	uint32_t width, height, base_offset;
 	bool recreate_primary = false;
 	int ret;
 	int surf_id;
@@ -553,9 +552,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc,
 	if (qcrtc->index == 0)
 		recreate_primary = true;
 
-	width = mode->hdisplay;
-	height = mode->vdisplay;
-	base_offset = 0;
+	if (bo->surf.stride * bo->surf.height > qdev->vram_size) {
+		DRM_ERROR("Mode doesn't fit in vram size (vgamem)");
+		return -EINVAL;
+        }
 
 	ret = qxl_bo_reserve(bo, false);
 	if (ret != 0)
@@ -569,10 +569,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc,
 	if (recreate_primary) {
 		qxl_io_destroy_primary(qdev);
 		qxl_io_log(qdev,
-			   "recreate primary: %dx%d (was %dx%d,%d,%d)\n",
-			   width, height, bo->surf.width,
-			   bo->surf.height, bo->surf.stride, bo->surf.format);
-		qxl_io_create_primary(qdev, base_offset, bo);
+			   "recreate primary: %dx%d,%d,%d\n",
+			   bo->surf.width, bo->surf.height,
+			   bo->surf.stride, bo->surf.format);
+		qxl_io_create_primary(qdev, 0, bo);
 		bo->is_primary = true;
 		surf_id = 0;
 	} else {
diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c
index 28f84b4fce32..3485bdccf8b8 100644
--- a/drivers/gpu/drm/qxl/qxl_irq.c
+++ b/drivers/gpu/drm/qxl/qxl_irq.c
@@ -33,6 +33,9 @@ irqreturn_t qxl_irq_handler(int irq, void *arg)
 
 	pending = xchg(&qdev->ram_header->int_pending, 0);
 
+	if (!pending)
+		return IRQ_NONE;
+
 	atomic_inc(&qdev->irq_received);
 
 	if (pending & QXL_INTERRUPT_DISPLAY) {
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index c7e7e6590c2b..c82c1d6a965a 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -433,6 +433,7 @@ static int qxl_sync_obj_flush(void *sync_obj)
 
 static void qxl_sync_obj_unref(void **sync_obj)
 {
+	*sync_obj = NULL;
 }
 
 static void *qxl_sync_obj_ref(void *sync_obj)
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index daa4dd375ab1..0cca5f24196a 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -270,8 +270,6 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
 		radeon_crtc->enabled = true;
-		/* adjust pm to dpms changes BEFORE enabling crtcs */
-		radeon_pm_compute_clocks(rdev);
 		atombios_enable_crtc(crtc, ATOM_ENABLE);
 		if (ASIC_IS_DCE3(rdev) && !ASIC_IS_DCE6(rdev))
 			atombios_enable_crtc_memreq(crtc, ATOM_ENABLE);
@@ -289,10 +287,10 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 			atombios_enable_crtc_memreq(crtc, ATOM_DISABLE);
 		atombios_enable_crtc(crtc, ATOM_DISABLE);
 		radeon_crtc->enabled = false;
-		/* adjust pm to dpms changes AFTER disabling crtcs */
-		radeon_pm_compute_clocks(rdev);
 		break;
 	}
+	/* adjust pm to dpms */
+	radeon_pm_compute_clocks(rdev);
 }
 
 static void
@@ -864,14 +862,16 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v5.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
+					break;
+				}
 			}
 			args.v5.ucTransmitterID = encoder_id;
 			args.v5.ucEncoderMode = encoder_mode;
@@ -886,20 +886,22 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v6.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
-				break;
-			case 12:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
-				break;
-			case 16:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
+					break;
+				case 12:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
+					break;
+				case 16:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
+					break;
+				}
 			}
 			args.v6.ucTransmitterID = encoder_id;
 			args.v6.ucEncoderMode = encoder_mode;
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 4ad7643fce5f..5727dbdeda7f 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -386,6 +386,19 @@ static int dp_get_max_dp_pix_clock(int link_rate,
 
 /***** radeon specific DP functions *****/
 
+static int radeon_dp_get_max_link_rate(struct drm_connector *connector,
+				       u8 dpcd[DP_DPCD_SIZE])
+{
+	int max_link_rate;
+
+	if (radeon_connector_is_dp12_capable(connector))
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000);
+	else
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000);
+
+	return max_link_rate;
+}
+
 /* First get the min lane# when low rate is used according to pixel clock
  * (prefer low rate), second check max lane# supported by DP panel,
  * if the max lane# < low rate lane# then use max lane# instead.
@@ -395,7 +408,7 @@ static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
 					int pix_clock)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int max_link_rate = drm_dp_max_link_rate(dpcd);
+	int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd);
 	int max_lane_num = drm_dp_max_lane_count(dpcd);
 	int lane_num;
 	int max_dp_pix_clock;
@@ -433,7 +446,7 @@ static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
 			return 540000;
 	}
 
-	return drm_dp_max_link_rate(dpcd);
+	return radeon_dp_get_max_link_rate(connector, dpcd);
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 607dc14d195e..e7bfd5502410 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -183,7 +183,6 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 	struct backlight_properties props;
 	struct radeon_backlight_privdata *pdata;
 	struct radeon_encoder_atom_dig *dig;
-	u8 backlight_level;
 	char bl_name[16];
 
 	/* Mac laptops with multiple GPUs use the gmux driver for backlight
@@ -222,12 +221,17 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 
 	pdata->encoder = radeon_encoder;
 
-	backlight_level = radeon_atom_get_backlight_level_from_reg(rdev);
-
 	dig = radeon_encoder->enc_priv;
 	dig->bl_dev = bd;
 
 	bd->props.brightness = radeon_atom_backlight_get_brightness(bd);
+	/* Set a reasonable default here if the level is 0 otherwise
+	 * fbdev will attempt to turn the backlight on after console
+	 * unblanking and it will try and restore 0 which turns the backlight
+	 * off again.
+	 */
+	if (bd->props.brightness == 0)
+		bd->props.brightness = RADEON_MAX_BL_LEVEL;
 	bd->props.power = FB_BLANK_UNBLANK;
 	backlight_update_status(bd);
 
@@ -1898,8 +1902,11 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder)
 					args.v2.ucEncodeMode = ATOM_ENCODER_MODE_CRT;
 				else
 					args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
-			} else
+			} else if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+				args.v2.ucEncodeMode = ATOM_ENCODER_MODE_LVDS;
+			} else {
 				args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
+			}
 			switch (radeon_encoder->encoder_id) {
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 8d49104ca6c2..543ba2d4a659 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -21,8 +21,10 @@
  *
  */
 
+#include <linux/firmware.h>
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_ucode.h"
 #include "cikd.h"
 #include "r600_dpm.h"
 #include "ci_dpm.h"
@@ -849,6 +851,9 @@ static int ci_set_thermal_temperature_range(struct radeon_device *rdev,
 	WREG32_SMC(CG_THERMAL_CTRL, tmp);
 #endif
 
+	rdev->pm.dpm.thermal.min_temp = low_temp;
+	rdev->pm.dpm.thermal.max_temp = high_temp;
+
 	return 0;
 }
 
@@ -920,7 +925,18 @@ static void ci_get_leakage_voltages(struct radeon_device *rdev)
 	pi->vddc_leakage.count = 0;
 	pi->vddci_leakage.count = 0;
 
-	if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) {
+	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_EVV) {
+		for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) {
+			virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i;
+			if (radeon_atom_get_voltage_evv(rdev, virtual_voltage_id, &vddc) != 0)
+				continue;
+			if (vddc != 0 && vddc != virtual_voltage_id) {
+				pi->vddc_leakage.actual_voltage[pi->vddc_leakage.count] = vddc;
+				pi->vddc_leakage.leakage_id[pi->vddc_leakage.count] = virtual_voltage_id;
+				pi->vddc_leakage.count++;
+			}
+		}
+	} else if (radeon_atom_get_leakage_id_from_vbios(rdev, &leakage_id) == 0) {
 		for (i = 0; i < CISLANDS_MAX_LEAKAGE_COUNT; i++) {
 			virtual_voltage_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i;
 			if (radeon_atom_get_leakage_vddc_based_on_leakage_params(rdev, &vddc, &vddci,
@@ -1159,7 +1175,7 @@ static int ci_stop_dpm(struct radeon_device *rdev)
 	tmp &= ~GLOBAL_PWRMGT_EN;
 	WREG32_SMC(GENERAL_PWRMGT, tmp);
 
-	tmp = RREG32(SCLK_PWRMGT_CNTL);
+	tmp = RREG32_SMC(SCLK_PWRMGT_CNTL);
 	tmp &= ~DYNAMIC_PM_EN;
 	WREG32_SMC(SCLK_PWRMGT_CNTL, tmp);
 
@@ -5106,6 +5122,12 @@ int ci_dpm_init(struct radeon_device *rdev)
 	pi->mclk_dpm_key_disabled = 0;
 	pi->pcie_dpm_key_disabled = 0;
 
+	/* mclk dpm is unstable on some R7 260X cards with the old mc ucode */
+	if ((rdev->pdev->device == 0x6658) &&
+	    (rdev->mc_fw->size == (BONAIRE_MC_UCODE_SIZE * 4))) {
+		pi->mclk_dpm_key_disabled = 1;
+	}
+
 	pi->caps_sclk_ds = true;
 
 	pi->mclk_strobe_mode_threshold = 40000;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index bbb17841a9e5..ddf70d6c0270 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -38,6 +38,7 @@ MODULE_FIRMWARE("radeon/BONAIRE_me.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_ce.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_mec.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_mc.bin");
+MODULE_FIRMWARE("radeon/BONAIRE_mc2.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_rlc.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_sdma.bin");
 MODULE_FIRMWARE("radeon/BONAIRE_smc.bin");
@@ -46,6 +47,7 @@ MODULE_FIRMWARE("radeon/HAWAII_me.bin");
 MODULE_FIRMWARE("radeon/HAWAII_ce.bin");
 MODULE_FIRMWARE("radeon/HAWAII_mec.bin");
 MODULE_FIRMWARE("radeon/HAWAII_mc.bin");
+MODULE_FIRMWARE("radeon/HAWAII_mc2.bin");
 MODULE_FIRMWARE("radeon/HAWAII_rlc.bin");
 MODULE_FIRMWARE("radeon/HAWAII_sdma.bin");
 MODULE_FIRMWARE("radeon/HAWAII_smc.bin");
@@ -1095,7 +1097,7 @@ static const u32 spectre_golden_registers[] =
 	0x8a14, 0xf000003f, 0x00000007,
 	0x8b24, 0xffffffff, 0x00ffffff,
 	0x28350, 0x3f3f3fff, 0x00000082,
-	0x28355, 0x0000003f, 0x00000000,
+	0x28354, 0x0000003f, 0x00000000,
 	0x3e78, 0x00000001, 0x00000002,
 	0x913c, 0xffff03df, 0x00000004,
 	0xc768, 0x00000008, 0x00000008,
@@ -1702,20 +1704,20 @@ int ci_mc_load_microcode(struct radeon_device *rdev)
 	const __be32 *fw_data;
 	u32 running, blackout = 0;
 	u32 *io_mc_regs;
-	int i, ucode_size, regs_size;
+	int i, regs_size, ucode_size;
 
 	if (!rdev->mc_fw)
 		return -EINVAL;
 
+	ucode_size = rdev->mc_fw->size / 4;
+
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
 		io_mc_regs = (u32 *)&bonaire_io_mc_regs;
-		ucode_size = CIK_MC_UCODE_SIZE;
 		regs_size = BONAIRE_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_HAWAII:
 		io_mc_regs = (u32 *)&hawaii_io_mc_regs;
-		ucode_size = HAWAII_MC_UCODE_SIZE;
 		regs_size = HAWAII_IO_MC_REGS_SIZE;
 		break;
 	default:
@@ -1782,7 +1784,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	const char *chip_name;
 	size_t pfp_req_size, me_req_size, ce_req_size,
 		mec_req_size, rlc_req_size, mc_req_size = 0,
-		sdma_req_size, smc_req_size = 0;
+		sdma_req_size, smc_req_size = 0, mc2_req_size = 0;
 	char fw_name[30];
 	int err;
 
@@ -1796,7 +1798,8 @@ static int cik_init_microcode(struct radeon_device *rdev)
 		ce_req_size = CIK_CE_UCODE_SIZE * 4;
 		mec_req_size = CIK_MEC_UCODE_SIZE * 4;
 		rlc_req_size = BONAIRE_RLC_UCODE_SIZE * 4;
-		mc_req_size = CIK_MC_UCODE_SIZE * 4;
+		mc_req_size = BONAIRE_MC_UCODE_SIZE * 4;
+		mc2_req_size = BONAIRE_MC2_UCODE_SIZE * 4;
 		sdma_req_size = CIK_SDMA_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(BONAIRE_SMC_UCODE_SIZE, 4);
 		break;
@@ -1808,6 +1811,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 		mec_req_size = CIK_MEC_UCODE_SIZE * 4;
 		rlc_req_size = BONAIRE_RLC_UCODE_SIZE * 4;
 		mc_req_size = HAWAII_MC_UCODE_SIZE * 4;
+		mc2_req_size = HAWAII_MC2_UCODE_SIZE * 4;
 		sdma_req_size = CIK_SDMA_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(HAWAII_SMC_UCODE_SIZE, 4);
 		break;
@@ -1903,16 +1907,22 @@ static int cik_init_microcode(struct radeon_device *rdev)
 
 	/* No SMC, MC ucode on APUs */
 	if (!(rdev->flags & RADEON_IS_IGP)) {
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name);
 		err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
-		if (err)
-			goto out;
-		if (rdev->mc_fw->size != mc_req_size) {
+		if (err) {
+			snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+			err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
+			if (err)
+				goto out;
+		}
+		if ((rdev->mc_fw->size != mc_req_size) &&
+		    (rdev->mc_fw->size != mc2_req_size)){
 			printk(KERN_ERR
 			       "cik_mc: Bogus length %zu in firmware \"%s\"\n",
 			       rdev->mc_fw->size, fw_name);
 			err = -EINVAL;
 		}
+		DRM_INFO("%s: %zu bytes\n", fw_name, rdev->mc_fw->size);
 
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
 		err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
@@ -2209,6 +2219,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else if (num_pipe_configs == 8) {
@@ -3220,6 +3231,7 @@ static void cik_gpu_init(struct radeon_device *rdev)
 			   (rdev->pdev->device == 0x130B) ||
 			   (rdev->pdev->device == 0x130E) ||
 			   (rdev->pdev->device == 0x1315) ||
+			   (rdev->pdev->device == 0x1318) ||
 			   (rdev->pdev->device == 0x131B)) {
 			rdev->config.cik.max_cu_per_sh = 4;
 			rdev->config.cik.max_backends_per_se = 1;
@@ -3924,8 +3936,8 @@ static int cik_cp_gfx_start(struct radeon_device *rdev)
 	/* init the CE partitions.  CE only used for gfx on CIK */
 	radeon_ring_write(ring, PACKET3(PACKET3_SET_BASE, 2));
 	radeon_ring_write(ring, PACKET3_BASE_INDEX(CE_PARTITION_BASE));
-	radeon_ring_write(ring, 0xc000);
-	radeon_ring_write(ring, 0xc000);
+	radeon_ring_write(ring, 0x8000);
+	radeon_ring_write(ring, 0x8000);
 
 	/* setup clear context state */
 	radeon_ring_write(ring, PACKET3(PACKET3_PREAMBLE_CNTL, 0));
@@ -4380,7 +4392,7 @@ struct bonaire_mqd
  */
 static int cik_cp_compute_resume(struct radeon_device *rdev)
 {
-	int r, i, idx;
+	int r, i, j, idx;
 	u32 tmp;
 	bool use_doorbell = true;
 	u64 hqd_gpu_addr;
@@ -4499,7 +4511,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 		mqd->queue_state.cp_hqd_pq_wptr= 0;
 		if (RREG32(CP_HQD_ACTIVE) & 1) {
 			WREG32(CP_HQD_DEQUEUE_REQUEST, 1);
-			for (i = 0; i < rdev->usec_timeout; i++) {
+			for (j = 0; j < rdev->usec_timeout; j++) {
 				if (!(RREG32(CP_HQD_ACTIVE) & 1))
 					break;
 				udelay(1);
@@ -5533,12 +5545,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev,
 void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 {
 	struct radeon_ring *ring = &rdev->ring[ridx];
+	int usepfp = (ridx == RADEON_RING_TYPE_GFX_INDEX);
 
 	if (vm == NULL)
 		return;
 
 	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(usepfp) |
 				 WRITE_DATA_DST_SEL(0)));
 	if (vm->id < 8) {
 		radeon_ring_write(ring,
@@ -5588,7 +5601,7 @@ void cik_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	radeon_ring_write(ring, 1 << vm->id);
 
 	/* compute doesn't have PFP */
-	if (ridx == RADEON_RING_TYPE_GFX_INDEX) {
+	if (usepfp) {
 		/* sync PFP to ME, otherwise we might get invalid PFP reads */
 		radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
 		radeon_ring_write(ring, 0x0);
@@ -6521,8 +6534,8 @@ void cik_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
 		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	case CHIP_HAWAII:
-		buffer[count++] = 0x3a00161a;
-		buffer[count++] = 0x0000002e;
+		buffer[count++] = cpu_to_le32(0x3a00161a);
+		buffer[count++] = cpu_to_le32(0x0000002e);
 		break;
 	default:
 		buffer[count++] = cpu_to_le32(0x00000000);
@@ -6662,6 +6675,19 @@ static void cik_disable_interrupt_state(struct radeon_device *rdev)
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
 	}
+	/* pflip */
+	if (rdev->num_crtc >= 2) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
+	}
+	if (rdev->num_crtc >= 4) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
+	}
+	if (rdev->num_crtc >= 6) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
+	}
 
 	/* dac hotplug */
 	WREG32(DAC_AUTODETECT_INT_CONTROL, 0);
@@ -7018,6 +7044,25 @@ int cik_irq_set(struct radeon_device *rdev)
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6);
 	}
 
+	if (rdev->num_crtc >= 2) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+	if (rdev->num_crtc >= 4) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+	if (rdev->num_crtc >= 6) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+
 	WREG32(DC_HPD1_INT_CONTROL, hpd1);
 	WREG32(DC_HPD2_INT_CONTROL, hpd2);
 	WREG32(DC_HPD3_INT_CONTROL, hpd3);
@@ -7054,6 +7099,29 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 	rdev->irq.stat_regs.cik.disp_int_cont5 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE5);
 	rdev->irq.stat_regs.cik.disp_int_cont6 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE6);
 
+	rdev->irq.stat_regs.cik.d1grph_int = RREG32(GRPH_INT_STATUS +
+		EVERGREEN_CRTC0_REGISTER_OFFSET);
+	rdev->irq.stat_regs.cik.d2grph_int = RREG32(GRPH_INT_STATUS +
+		EVERGREEN_CRTC1_REGISTER_OFFSET);
+	if (rdev->num_crtc >= 4) {
+		rdev->irq.stat_regs.cik.d3grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC2_REGISTER_OFFSET);
+		rdev->irq.stat_regs.cik.d4grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC3_REGISTER_OFFSET);
+	}
+	if (rdev->num_crtc >= 6) {
+		rdev->irq.stat_regs.cik.d5grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC4_REGISTER_OFFSET);
+		rdev->irq.stat_regs.cik.d6grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC5_REGISTER_OFFSET);
+	}
+
+	if (rdev->irq.stat_regs.cik.d1grph_int & GRPH_PFLIP_INT_OCCURRED)
+		WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_CLEAR);
+	if (rdev->irq.stat_regs.cik.d2grph_int & GRPH_PFLIP_INT_OCCURRED)
+		WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_CLEAR);
 	if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT)
 		WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, VBLANK_ACK);
 	if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT)
@@ -7064,6 +7132,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(LB_VLINE_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, VLINE_ACK);
 
 	if (rdev->num_crtc >= 4) {
+		if (rdev->irq.stat_regs.cik.d3grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
+		if (rdev->irq.stat_regs.cik.d4grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
 		if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT)
 			WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VBLANK_ACK);
 		if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT)
@@ -7075,6 +7149,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 	}
 
 	if (rdev->num_crtc >= 6) {
+		if (rdev->irq.stat_regs.cik.d5grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
+		if (rdev->irq.stat_regs.cik.d6grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
 		if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT)
 			WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VBLANK_ACK);
 		if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT)
@@ -7193,6 +7273,7 @@ static inline u32 cik_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -7426,6 +7507,15 @@ restart_ih:
 				break;
 			}
 			break;
+		case 8: /* D1 page flip */
+		case 10: /* D2 page flip */
+		case 12: /* D3 page flip */
+		case 14: /* D4 page flip */
+		case 16: /* D5 page flip */
+		case 18: /* D6 page flip */
+			DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1);
+			radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1);
+			break;
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
@@ -7690,6 +7780,7 @@ restart_ih:
 static int cik_startup(struct radeon_device *rdev)
 {
 	struct radeon_ring *ring;
+	u32 nop;
 	int r;
 
 	/* enable pcie gen2/3 link */
@@ -7807,9 +7898,15 @@ static int cik_startup(struct radeon_device *rdev)
 	}
 	cik_irq_set(rdev);
 
+	if (rdev->family == CHIP_HAWAII) {
+		nop = RADEON_CP_PACKET2;
+	} else {
+		nop = PACKET3(PACKET3_NOP, 0x3FFF);
+	}
+
 	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP_RPTR_OFFSET,
-			     PACKET3(PACKET3_NOP, 0x3FFF));
+			     nop);
 	if (r)
 		return r;
 
@@ -7817,7 +7914,7 @@ static int cik_startup(struct radeon_device *rdev)
 	/* type-2 packets are deprecated on MEC, use type-3 instead */
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP1_RPTR_OFFSET,
-			     PACKET3(PACKET3_NOP, 0x3FFF));
+			     nop);
 	if (r)
 		return r;
 	ring->me = 1; /* first MEC */
@@ -7828,7 +7925,7 @@ static int cik_startup(struct radeon_device *rdev)
 	/* type-2 packets are deprecated on MEC, use type-3 instead */
 	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
 	r = radeon_ring_init(rdev, ring, ring->ring_size, RADEON_WB_CP2_RPTR_OFFSET,
-			     PACKET3(PACKET3_NOP, 0x3FFF));
+			     nop);
 	if (r)
 		return r;
 	/* dGPU only have 1 MEC */
@@ -8796,6 +8893,9 @@ void dce8_bandwidth_update(struct radeon_device *rdev)
 	u32 num_heads = 0, lb_size;
 	int i;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	for (i = 0; i < rdev->num_crtc; i++) {
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 94626ea90fa5..66ba713ba7d7 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -461,13 +461,6 @@ int cik_sdma_resume(struct radeon_device *rdev)
 {
 	int r;
 
-	/* Reset dma */
-	WREG32(SRBM_SOFT_RESET, SOFT_RESET_SDMA | SOFT_RESET_SDMA1);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-	RREG32(SRBM_SOFT_RESET);
-
 	r = cik_sdma_load_microcode(rdev);
 	if (r)
 		return r;
@@ -599,7 +592,7 @@ int cik_sdma_ring_test(struct radeon_device *rdev,
 	tmp = 0xCAFEDEAD;
 	writel(tmp, ptr);
 
-	r = radeon_ring_lock(rdev, ring, 4);
+	r = radeon_ring_lock(rdev, ring, 5);
 	if (r) {
 		DRM_ERROR("radeon: dma failed to lock ring %d (%d).\n", ring->idx, r);
 		return r;
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index 98bae9d7b74d..a0a9f974cdd7 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -882,6 +882,15 @@
 #       define DC_HPD6_RX_INTERRUPT                     (1 << 18)
 #define DISP_INTERRUPT_STATUS_CONTINUE6                 0x6780
 
+/* 0x6858, 0x7458, 0x10058, 0x10c58, 0x11858, 0x12458 */
+#define GRPH_INT_STATUS                                 0x6858
+#       define GRPH_PFLIP_INT_OCCURRED                  (1 << 0)
+#       define GRPH_PFLIP_INT_CLEAR                     (1 << 8)
+/* 0x685c, 0x745c, 0x1005c, 0x10c5c, 0x1185c, 0x1245c */
+#define GRPH_INT_CONTROL                                0x685c
+#       define GRPH_PFLIP_INT_MASK                      (1 << 0)
+#       define GRPH_PFLIP_INT_TYPE                      (1 << 8)
+
 #define	DAC_AUTODETECT_INT_CONTROL			0x67c8
 
 #define DC_HPD1_INT_STATUS                              0x601c
@@ -1736,12 +1745,12 @@
 #define		EOP_TC_WB_ACTION_EN                     (1 << 15) /* L2 */
 #define		EOP_TCL1_ACTION_EN                      (1 << 16)
 #define		EOP_TC_ACTION_EN                        (1 << 17) /* L2 */
+#define		EOP_TCL2_VOLATILE                       (1 << 24)
 #define		EOP_CACHE_POLICY(x)                     ((x) << 25)
                 /* 0 - LRU
 		 * 1 - Stream
 		 * 2 - Bypass
 		 */
-#define		EOP_TCL2_VOLATILE                       (1 << 27)
 #define		DATA_SEL(x)                             ((x) << 29)
                 /* 0 - discard
 		 * 1 - send low 32bit data
diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c
index cf783fc0ef21..cf777193c85f 100644
--- a/drivers/gpu/drm/radeon/cypress_dpm.c
+++ b/drivers/gpu/drm/radeon/cypress_dpm.c
@@ -1551,7 +1551,7 @@ int cypress_populate_smc_voltage_tables(struct radeon_device *rdev,
 
 		table->voltageMaskTable.highMask[RV770_SMC_VOLTAGEMASK_VDDCI] = 0;
 		table->voltageMaskTable.lowMask[RV770_SMC_VOLTAGEMASK_VDDCI] =
-			cpu_to_be32(eg_pi->vddc_voltage_table.mask_low);
+			cpu_to_be32(eg_pi->vddci_voltage_table.mask_low);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 94e858751994..0a65dc7e93e7 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -309,11 +309,17 @@ int dce6_audio_init(struct radeon_device *rdev)
 
 	rdev->audio.enabled = true;
 
-	if (ASIC_IS_DCE8(rdev))
+	if (ASIC_IS_DCE81(rdev)) /* KV: 4 streams, 7 endpoints */
+		rdev->audio.num_pins = 7;
+	else if (ASIC_IS_DCE83(rdev)) /* KB: 2 streams, 3 endpoints */
+		rdev->audio.num_pins = 3;
+	else if (ASIC_IS_DCE8(rdev)) /* BN/HW: 6 streams, 7 endpoints */
+		rdev->audio.num_pins = 7;
+	else if (ASIC_IS_DCE61(rdev)) /* TN: 4 streams, 6 endpoints */
 		rdev->audio.num_pins = 6;
-	else if (ASIC_IS_DCE61(rdev))
-		rdev->audio.num_pins = 4;
-	else
+	else if (ASIC_IS_DCE64(rdev)) /* OL: 2 streams, 2 endpoints */
+		rdev->audio.num_pins = 2;
+	else /* SI: 6 streams, 6 endpoints */
 		rdev->audio.num_pins = 6;
 
 	for (i = 0; i < rdev->audio.num_pins; i++) {
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 27b0ff16082e..7138f3e31b7c 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -189,7 +189,7 @@ static const u32 evergreen_golden_registers[] =
 	0x8c1c, 0xffffffff, 0x00001010,
 	0x28350, 0xffffffff, 0x00000000,
 	0xa008, 0xffffffff, 0x00010000,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x9508, 0xffffffff, 0x00000002,
 	0x913c, 0x0000000f, 0x0000000a
 };
@@ -476,7 +476,7 @@ static const u32 cedar_golden_registers[] =
 	0x8c1c, 0xffffffff, 0x00001010,
 	0x28350, 0xffffffff, 0x00000000,
 	0xa008, 0xffffffff, 0x00010000,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x9508, 0xffffffff, 0x00000002
 };
 
@@ -635,7 +635,7 @@ static const u32 juniper_mgcg_init[] =
 static const u32 supersumo_golden_registers[] =
 {
 	0x5eb4, 0xffffffff, 0x00000002,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x7030, 0xffffffff, 0x00000011,
 	0x7c30, 0xffffffff, 0x00000011,
 	0x6104, 0x01000300, 0x00000000,
@@ -719,7 +719,7 @@ static const u32 sumo_golden_registers[] =
 static const u32 wrestler_golden_registers[] =
 {
 	0x5eb4, 0xffffffff, 0x00000002,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x7030, 0xffffffff, 0x00000011,
 	0x7c30, 0xffffffff, 0x00000011,
 	0x6104, 0x01000300, 0x00000000,
@@ -2362,6 +2362,9 @@ void evergreen_bandwidth_update(struct radeon_device *rdev)
 	u32 num_heads = 0, lb_size;
 	int i;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	for (i = 0; i < rdev->num_crtc; i++) {
@@ -2570,6 +2573,7 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav
 					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
 					tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
 					WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+					WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
 				}
 			} else {
 				tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
@@ -4375,7 +4379,6 @@ int evergreen_irq_set(struct radeon_device *rdev)
 	u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0;
 	u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6;
 	u32 grbm_int_cntl = 0;
-	u32 grph1 = 0, grph2 = 0, grph3 = 0, grph4 = 0, grph5 = 0, grph6 = 0;
 	u32 afmt1 = 0, afmt2 = 0, afmt3 = 0, afmt4 = 0, afmt5 = 0, afmt6 = 0;
 	u32 dma_cntl, dma_cntl1 = 0;
 	u32 thermal_int = 0;
@@ -4558,15 +4561,21 @@ int evergreen_irq_set(struct radeon_device *rdev)
 		WREG32(INT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6);
 	}
 
-	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, grph1);
-	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, grph2);
+	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET,
+	       GRPH_PFLIP_INT_MASK);
+	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET,
+	       GRPH_PFLIP_INT_MASK);
 	if (rdev->num_crtc >= 4) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 	if (rdev->num_crtc >= 6) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 
 	WREG32(DC_HPD1_INT_CONTROL, hpd1);
@@ -4758,6 +4767,7 @@ static u32 evergreen_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -4955,6 +4965,15 @@ restart_ih:
 				break;
 			}
 			break;
+		case 8: /* D1 page flip */
+		case 10: /* D2 page flip */
+		case 12: /* D3 page flip */
+		case 14: /* D4 page flip */
+		case 16: /* D5 page flip */
+		case 18: /* D6 page flip */
+			DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1);
+			radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1);
+			break;
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
index 7cf96b15377f..94fa49e974eb 100644
--- a/drivers/gpu/drm/radeon/ni_dma.c
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -191,12 +191,6 @@ int cayman_dma_resume(struct radeon_device *rdev)
 	u32 reg_offset, wb_offset;
 	int i, r;
 
-	/* Reset dma */
-	WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA | SOFT_RESET_DMA1);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
 	for (i = 0; i < 2; i++) {
 		if (i == 0) {
 			ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX];
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index ca814276b075..03f08a3cf864 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -1315,7 +1315,7 @@ static void ni_populate_smc_voltage_tables(struct radeon_device *rdev,
 
 		table->voltageMaskTable.highMask[NISLANDS_SMC_VOLTAGEMASK_VDDCI] = 0;
 		table->voltageMaskTable.lowMask[NISLANDS_SMC_VOLTAGEMASK_VDDCI] =
-			cpu_to_be32(eg_pi->vddc_voltage_table.mask_low);
+			cpu_to_be32(eg_pi->vddci_voltage_table.mask_low);
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 3cc78bb66042..07620e198a6d 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3219,6 +3219,9 @@ void r100_bandwidth_update(struct radeon_device *rdev)
 	uint32_t pixel_bytes1 = 0;
 	uint32_t pixel_bytes2 = 0;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled) {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 647ef4079217..788f602e8989 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3509,7 +3509,6 @@ int r600_irq_set(struct radeon_device *rdev)
 	u32 hpd1, hpd2, hpd3, hpd4 = 0, hpd5 = 0, hpd6 = 0;
 	u32 grbm_int_cntl = 0;
 	u32 hdmi0, hdmi1;
-	u32 d1grph = 0, d2grph = 0;
 	u32 dma_cntl;
 	u32 thermal_int = 0;
 
@@ -3618,8 +3617,8 @@ int r600_irq_set(struct radeon_device *rdev)
 	WREG32(CP_INT_CNTL, cp_int_cntl);
 	WREG32(DMA_CNTL, dma_cntl);
 	WREG32(DxMODE_INT_MASK, mode_int);
-	WREG32(D1GRPH_INTERRUPT_CONTROL, d1grph);
-	WREG32(D2GRPH_INTERRUPT_CONTROL, d2grph);
+	WREG32(D1GRPH_INTERRUPT_CONTROL, DxGRPH_PFLIP_INT_MASK);
+	WREG32(D2GRPH_INTERRUPT_CONTROL, DxGRPH_PFLIP_INT_MASK);
 	WREG32(GRBM_INT_CNTL, grbm_int_cntl);
 	if (ASIC_IS_DCE3(rdev)) {
 		WREG32(DC_HPD1_INT_CONTROL, hpd1);
@@ -3796,6 +3795,7 @@ static u32 r600_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -3922,6 +3922,14 @@ restart_ih:
 				break;
 			}
 			break;
+		case 9: /* D1 pflip */
+			DRM_DEBUG("IH: D1 flip\n");
+			radeon_crtc_handle_flip(rdev, 0);
+			break;
+		case 11: /* D2 pflip */
+			DRM_DEBUG("IH: D2 flip\n");
+			radeon_crtc_handle_flip(rdev, 1);
+			break;
 		case 19: /* HPD/DAC hotplug */
 			switch (src_data) {
 			case 0:
diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
index b2d4c91e6272..99495513f6b1 100644
--- a/drivers/gpu/drm/radeon/r600_dma.c
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -124,15 +124,6 @@ int r600_dma_resume(struct radeon_device *rdev)
 	u32 rb_bufsz;
 	int r;
 
-	/* Reset dma */
-	if (rdev->family >= CHIP_RV770)
-		WREG32(SRBM_SOFT_RESET, RV770_SOFT_RESET_DMA);
-	else
-		WREG32(SRBM_SOFT_RESET, SOFT_RESET_DMA);
-	RREG32(SRBM_SOFT_RESET);
-	udelay(50);
-	WREG32(SRBM_SOFT_RESET, 0);
-
 	WREG32(DMA_SEM_INCOMPLETE_TIMER_CNTL, 0);
 	WREG32(DMA_SEM_WAIT_FAIL_TIMER_CNTL, 0);
 
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index e4cc9b314ce9..3334f916945b 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -158,16 +158,18 @@ u32 r600_dpm_get_vblank_time(struct radeon_device *rdev)
 	u32 line_time_us, vblank_lines;
 	u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-			line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) /
-				radeon_crtc->hw_mode.clock;
-			vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end -
-				radeon_crtc->hw_mode.crtc_vdisplay +
-				(radeon_crtc->v_border * 2);
-			vblank_time_us = vblank_lines * line_time_us;
-			break;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
+				line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) /
+					radeon_crtc->hw_mode.clock;
+				vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end -
+					radeon_crtc->hw_mode.crtc_vdisplay +
+					(radeon_crtc->v_border * 2);
+				vblank_time_us = vblank_lines * line_time_us;
+				break;
+			}
 		}
 	}
 
@@ -181,14 +183,15 @@ u32 r600_dpm_get_vrefresh(struct radeon_device *rdev)
 	struct radeon_crtc *radeon_crtc;
 	u32 vrefresh = 0;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
-			vrefresh = radeon_crtc->hw_mode.vrefresh;
-			break;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
+				vrefresh = radeon_crtc->hw_mode.vrefresh;
+				break;
+			}
 		}
 	}
-
 	return vrefresh;
 }
 
@@ -1206,7 +1209,7 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
 					(mode_info->atom_context->bios + data_offset +
 					 le16_to_cpu(ext_hdr->usPowerTuneTableOffset));
 				rdev->pm.dpm.dyn_state.cac_tdp_table->maximum_power_delivery_limit =
-					ppt->usMaximumPowerDeliveryLimit;
+					le16_to_cpu(ppt->usMaximumPowerDeliveryLimit);
 				pt = &ppt->power_tune_table;
 			} else {
 				ATOM_PPLIB_POWERTUNE_Table *ppt = (ATOM_PPLIB_POWERTUNE_Table *)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index e887d027b6d0..b837e9f9f8ce 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -294,6 +294,9 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r
 							 u16 *vddc, u16 *vddci,
 							 u16 virtual_voltage_id,
 							 u16 vbios_voltage_id);
+int radeon_atom_get_voltage_evv(struct radeon_device *rdev,
+				u16 virtual_voltage_id,
+				u16 *voltage);
 int radeon_atom_round_to_true_voltage(struct radeon_device *rdev,
 				      u8 voltage_type,
 				      u16 nominal_voltage,
@@ -733,6 +736,12 @@ struct cik_irq_stat_regs {
 	u32 disp_int_cont4;
 	u32 disp_int_cont5;
 	u32 disp_int_cont6;
+	u32 d1grph_int;
+	u32 d2grph_int;
+	u32 d3grph_int;
+	u32 d4grph_int;
+	u32 d5grph_int;
+	u32 d6grph_int;
 };
 
 union radeon_irq_stat_regs {
@@ -742,7 +751,7 @@ union radeon_irq_stat_regs {
 	struct cik_irq_stat_regs cik;
 };
 
-#define RADEON_MAX_HPD_PINS 6
+#define RADEON_MAX_HPD_PINS 7
 #define RADEON_MAX_CRTCS 6
 #define RADEON_MAX_AFMT_BLOCKS 7
 
@@ -2242,6 +2251,7 @@ struct radeon_device {
 	bool have_disp_power_ref;
 };
 
+bool radeon_is_px(struct drm_device *dev);
 int radeon_device_init(struct radeon_device *rdev,
 		       struct drm_device *ddev,
 		       struct pci_dev *pdev,
@@ -2552,6 +2562,9 @@ void r100_pll_errata_after_index(struct radeon_device *rdev);
 #define ASIC_IS_DCE64(rdev) ((rdev->family == CHIP_OLAND))
 #define ASIC_IS_NODCE(rdev) ((rdev->family == CHIP_HAINAN))
 #define ASIC_IS_DCE8(rdev) ((rdev->family >= CHIP_BONAIRE))
+#define ASIC_IS_DCE81(rdev) ((rdev->family == CHIP_KAVERI))
+#define ASIC_IS_DCE82(rdev) ((rdev->family == CHIP_BONAIRE))
+#define ASIC_IS_DCE83(rdev) ((rdev->family == CHIP_KABINI))
 
 #define ASIC_IS_LOMBOK(rdev) ((rdev->ddev->pdev->device == 0x6849) || \
 			      (rdev->ddev->pdev->device == 0x6850) || \
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index dda02bfc10a4..5600d4c5f981 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -2034,8 +2034,8 @@ static struct radeon_asic ci_asic = {
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &cik_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.copy = &cik_copy_dma,
-		.copy_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.copy = &cik_copy_cpdma,
+		.copy_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 	},
 	.surface = {
 		.set_reg = r600_set_surface_reg,
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 30844814c25a..e2de749327ad 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -447,6 +447,13 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev,
 		}
 	}
 
+	/* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */
+	if ((dev->pdev->device == 0x9805) &&
+	    (dev->pdev->subsystem_vendor == 0x1734) &&
+	    (dev->pdev->subsystem_device == 0x11bd)) {
+		if (*connector_type == DRM_MODE_CONNECTOR_VGA)
+			return false;
+	}
 
 	return true;
 }
@@ -1955,7 +1962,7 @@ static const char *thermal_controller_names[] = {
 	"adm1032",
 	"adm1030",
 	"max6649",
-	"lm64",
+	"lm63", /* lm64 */
 	"f75375",
 	"asc7xxx",
 };
@@ -1966,7 +1973,7 @@ static const char *pp_lib_thermal_controller_names[] = {
 	"adm1032",
 	"adm1030",
 	"max6649",
-	"lm64",
+	"lm63", /* lm64 */
 	"f75375",
 	"RV6xx",
 	"RV770",
@@ -2273,19 +2280,31 @@ static void radeon_atombios_add_pplib_thermal_controller(struct radeon_device *r
 				 (controller->ucFanParameters &
 				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
 			rdev->pm.int_thermal_type = THERMAL_TYPE_KV;
-		} else if ((controller->ucType ==
-			    ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) ||
-			   (controller->ucType ==
-			    ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) ||
-			   (controller->ucType ==
-			    ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL)) {
-			DRM_INFO("Special thermal controller config\n");
+		} else if (controller->ucType ==
+			   ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) {
+			DRM_INFO("External GPIO thermal controller %s fan control\n",
+				 (controller->ucFanParameters &
+				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
+			rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL_GPIO;
+		} else if (controller->ucType ==
+			   ATOM_PP_THERMALCONTROLLER_ADT7473_WITH_INTERNAL) {
+			DRM_INFO("ADT7473 with internal thermal controller %s fan control\n",
+				 (controller->ucFanParameters &
+				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
+			rdev->pm.int_thermal_type = THERMAL_TYPE_ADT7473_WITH_INTERNAL;
+		} else if (controller->ucType ==
+			   ATOM_PP_THERMALCONTROLLER_EMC2103_WITH_INTERNAL) {
+			DRM_INFO("EMC2103 with internal thermal controller %s fan control\n",
+				 (controller->ucFanParameters &
+				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
+			rdev->pm.int_thermal_type = THERMAL_TYPE_EMC2103_WITH_INTERNAL;
 		} else if (controller->ucType < ARRAY_SIZE(pp_lib_thermal_controller_names)) {
 			DRM_INFO("Possible %s thermal controller at 0x%02x %s fan control\n",
 				 pp_lib_thermal_controller_names[controller->ucType],
 				 controller->ucI2cAddress >> 1,
 				 (controller->ucFanParameters &
 				  ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with");
+			rdev->pm.int_thermal_type = THERMAL_TYPE_EXTERNAL;
 			i2c_bus = radeon_lookup_i2c_gpio(rdev, controller->ucI2cLine);
 			rdev->pm.i2c_bus = radeon_i2c_lookup(rdev, &i2c_bus);
 			if (rdev->pm.i2c_bus) {
@@ -3228,6 +3247,41 @@ int radeon_atom_get_leakage_vddc_based_on_leakage_params(struct radeon_device *r
 	return 0;
 }
 
+union get_voltage_info {
+	struct  _GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 in;
+	struct  _GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 evv_out;
+};
+
+int radeon_atom_get_voltage_evv(struct radeon_device *rdev,
+				u16 virtual_voltage_id,
+				u16 *voltage)
+{
+	int index = GetIndexIntoMasterTable(COMMAND, GetVoltageInfo);
+	u32 entry_id;
+	u32 count = rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.count;
+	union get_voltage_info args;
+
+	for (entry_id = 0; entry_id < count; entry_id++) {
+		if (rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].v ==
+		    virtual_voltage_id)
+			break;
+	}
+
+	if (entry_id >= count)
+		return -EINVAL;
+
+	args.in.ucVoltageType = VOLTAGE_TYPE_VDDC;
+	args.in.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE;
+	args.in.ulSCLKFreq =
+		cpu_to_le32(rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk.entries[entry_id].clk);
+
+	atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+
+	*voltage = le16_to_cpu(args.evv_out.usVoltageLevel);
+
+	return 0;
+}
+
 int radeon_atom_get_voltage_gpio_settings(struct radeon_device *rdev,
 					  u16 voltage_level, u8 voltage_type,
 					  u32 *gpio_value, u32 *gpio_mask)
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index fa9a9c02751e..a9fb0d016d38 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -59,7 +59,7 @@ struct atpx_mux {
 	u16 mux;
 } __packed;
 
-bool radeon_is_px(void) {
+bool radeon_has_atpx(void) {
 	return radeon_atpx_priv.atpx_detected;
 }
 
@@ -528,6 +528,13 @@ static bool radeon_atpx_detect(void)
 		has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
 	}
 
+	/* some newer PX laptops mark the dGPU as a non-VGA display device */
+	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+		vga_count++;
+
+		has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
+	}
+
 	if (has_atpx && vga_count == 2) {
 		acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
 		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index b3633d9a5317..9ab30976287d 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -196,6 +196,20 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 		}
 	}
 
+	if (!found) {
+		while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+			dhandle = ACPI_HANDLE(&pdev->dev);
+			if (!dhandle)
+				continue;
+
+			status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
+			if (!ACPI_FAILURE(status)) {
+				found = true;
+				break;
+			}
+		}
+	}
+
 	if (!found)
 		return false;
 
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 82d4f865546e..4d36b9e86275 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1402,7 +1402,7 @@ bool radeon_connector_is_dp12_capable(struct drm_connector *connector)
 	struct radeon_device *rdev = dev->dev_private;
 
 	if (ASIC_IS_DCE5(rdev) &&
-	    (rdev->clock.dp_extclk >= 53900) &&
+	    (rdev->clock.default_dispclk >= 53900) &&
 	    radeon_connector_encoder_is_hbr2(connector)) {
 		return true;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index dfb5a1db87d4..7f2d6c0d11c1 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -97,6 +97,12 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 			uint32_t domain = r->write_domain ?
 				r->write_domain : r->read_domains;
 
+			if (domain & RADEON_GEM_DOMAIN_CPU) {
+				DRM_ERROR("RADEON_GEM_DOMAIN_CPU is not valid "
+					  "for command submission\n");
+				return -EINVAL;
+			}
+
 			p->relocs[i].lobj.domain = domain;
 			if (domain == RADEON_GEM_DOMAIN_VRAM)
 				domain |= RADEON_GEM_DOMAIN_GTT;
@@ -276,10 +282,17 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			return -EINVAL;
 
 		/* we only support VM on some SI+ rings */
-		if ((p->rdev->asic->ring[p->ring]->cs_parse == NULL) &&
-		   ((p->cs_flags & RADEON_CS_USE_VM) == 0)) {
-			DRM_ERROR("Ring %d requires VM!\n", p->ring);
-			return -EINVAL;
+		if ((p->cs_flags & RADEON_CS_USE_VM) == 0) {
+			if (p->rdev->asic->ring[p->ring]->cs_parse == NULL) {
+				DRM_ERROR("Ring %d requires VM!\n", p->ring);
+				return -EINVAL;
+			}
+		} else {
+			if (p->rdev->asic->ring[p->ring]->ib_parse == NULL) {
+				DRM_ERROR("VM not supported on ring %d!\n",
+					  p->ring);
+				return -EINVAL;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 044bc98fb459..e39026cc7d07 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -102,11 +102,14 @@ static const char radeon_family_name[][16] = {
 	"LAST",
 };
 
-#if defined(CONFIG_VGA_SWITCHEROO)
-bool radeon_is_px(void);
-#else
-static inline bool radeon_is_px(void) { return false; }
-#endif
+bool radeon_is_px(struct drm_device *dev)
+{
+	struct radeon_device *rdev = dev->dev_private;
+
+	if (rdev->flags & RADEON_IS_PX)
+		return true;
+	return false;
+}
 
 /**
  * radeon_program_register_sequence - program an array of registers.
@@ -1082,7 +1085,7 @@ static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
-	if (radeon_is_px() && state == VGA_SWITCHEROO_OFF)
+	if (radeon_is_px(dev) && state == VGA_SWITCHEROO_OFF)
 		return;
 
 	if (state == VGA_SWITCHEROO_ON) {
@@ -1303,9 +1306,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	 * ignore it */
 	vga_client_register(rdev->pdev, rdev, NULL, radeon_vga_set_decode);
 
-	if (radeon_runtime_pm == 1)
-		runtime = true;
-	if ((radeon_runtime_pm == -1) && radeon_is_px())
+	if (rdev->flags & RADEON_IS_PX)
 		runtime = true;
 	vga_switcheroo_register_client(rdev->pdev, &radeon_switcheroo_ops, runtime);
 	if (runtime)
@@ -1313,7 +1314,7 @@ int radeon_device_init(struct radeon_device *rdev,
 
 	r = radeon_init(rdev);
 	if (r)
-		return r;
+		goto failed;
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -1333,7 +1334,7 @@ int radeon_device_init(struct radeon_device *rdev,
 		radeon_agp_disable(rdev);
 		r = radeon_init(rdev);
 		if (r)
-			return r;
+			goto failed;
 	}
 
 	if ((radeon_testing & 1)) {
@@ -1355,6 +1356,11 @@ int radeon_device_init(struct radeon_device *rdev,
 			DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n");
 	}
 	return 0;
+
+failed:
+	if (runtime)
+		vga_switcheroo_fini_domain_pm_ops(rdev->dev);
+	return r;
 }
 
 static void radeon_debugfs_remove_files(struct radeon_device *rdev);
@@ -1375,6 +1381,8 @@ void radeon_device_fini(struct radeon_device *rdev)
 	radeon_bo_evict_vram(rdev);
 	radeon_fini(rdev);
 	vga_switcheroo_unregister_client(rdev->pdev);
+	if (rdev->flags & RADEON_IS_PX)
+		vga_switcheroo_fini_domain_pm_ops(rdev->dev);
 	vga_client_register(rdev->pdev, NULL, NULL, NULL);
 	if (rdev->rio_mem)
 		pci_iounmap(rdev->pdev, rdev->rio_mem);
@@ -1535,6 +1543,10 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
 
 	radeon_restore_bios_scratch_regs(rdev);
 
+	/* set the power state here in case we are a PX system or headless */
+	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled)
+		radeon_pm_compute_clocks(rdev);
+
 	if (fbcon) {
 		radeon_fbdev_set_suspend(rdev, 0);
 		console_unlock();
@@ -1595,7 +1607,6 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 	radeon_save_bios_scratch_regs(rdev);
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
-	radeon_pm_suspend(rdev);
 	radeon_suspend(rdev);
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
@@ -1641,9 +1652,24 @@ retry:
 		}
 	}
 
-	radeon_pm_resume(rdev);
+	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) {
+		/* do dpm late init */
+		r = radeon_pm_late_init(rdev);
+		if (r) {
+			rdev->pm.dpm_enabled = false;
+			DRM_ERROR("radeon_pm_late_init failed, disabling dpm\n");
+		}
+	} else {
+		/* resume old pm late */
+		radeon_pm_resume(rdev);
+	}
+
 	drm_helper_resume_force_mode(rdev->ddev);
 
+	/* set the power state here in case we are a PX system or headless */
+	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled)
+		radeon_pm_compute_clocks(rdev);
+
 	ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
 	if (r) {
 		/* bad news, how to tell it to userspace ? */
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index fbd8b930f2be..11d06c7b5afa 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -282,6 +282,10 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 	u32 update_pending;
 	int vpos, hpos;
 
+	/* can happen during initialization */
+	if (radeon_crtc == NULL)
+		return;
+
 	spin_lock_irqsave(&rdev->ddev->event_lock, flags);
 	work = radeon_crtc->unpin_work;
 	if (work == NULL ||
@@ -751,6 +755,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector)
 	struct radeon_device *rdev = dev->dev_private;
 	int ret = 0;
 
+	/* don't leak the edid if we already fetched it in detect() */
+	if (radeon_connector->edid)
+		goto got_edid;
+
 	/* on hw with routers, select right port */
 	if (radeon_connector->router.ddc_valid)
 		radeon_router_select_ddc_port(radeon_connector);
@@ -790,8 +798,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector)
 			radeon_connector->edid = radeon_bios_get_hardcoded_edid(rdev);
 	}
 	if (radeon_connector->edid) {
+got_edid:
 		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
+		drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid);
 		return ret;
 	}
 	drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index f633c2782170..9c0056f0a68a 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -113,6 +113,7 @@ extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
 				      unsigned int flags,
 				      int *vpos, int *hpos, ktime_t *stime,
 				      ktime_t *etime);
+extern bool radeon_is_px(struct drm_device *dev);
 extern const struct drm_ioctl_desc radeon_ioctls_kms[];
 extern int radeon_max_kms_ioctl;
 int radeon_mmap(struct file *filp, struct vm_area_struct *vma);
@@ -142,11 +143,9 @@ void radeon_debugfs_cleanup(struct drm_minor *minor);
 #if defined(CONFIG_VGA_SWITCHEROO)
 void radeon_register_atpx_handler(void);
 void radeon_unregister_atpx_handler(void);
-bool radeon_is_px(void);
 #else
 static inline void radeon_register_atpx_handler(void) {}
 static inline void radeon_unregister_atpx_handler(void) {}
-static inline bool radeon_is_px(void) { return false; }
 #endif
 
 int radeon_no_wb;
@@ -403,12 +402,7 @@ static int radeon_pmops_runtime_suspend(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (radeon_runtime_pm == 0) {
-		pm_runtime_forbid(dev);
-		return -EBUSY;
-	}
-
-	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
+	if (!radeon_is_px(drm_dev)) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
@@ -432,10 +426,7 @@ static int radeon_pmops_runtime_resume(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (radeon_runtime_pm == 0)
-		return -EINVAL;
-
-	if (radeon_runtime_pm == -1 && !radeon_is_px())
+	if (!radeon_is_px(drm_dev))
 		return -EINVAL;
 
 	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
@@ -460,14 +451,7 @@ static int radeon_pmops_runtime_idle(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	struct drm_crtc *crtc;
 
-	if (radeon_runtime_pm == 0) {
-		pm_runtime_forbid(dev);
-		return -EBUSY;
-	}
-
-	/* are we PX enabled? */
-	if (radeon_runtime_pm == -1 && !radeon_is_px()) {
-		DRM_DEBUG_DRIVER("failing to power off - not px\n");
+	if (!radeon_is_px(drm_dev)) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h
index 614ad549297f..9da5da4ffd17 100644
--- a/drivers/gpu/drm/radeon/radeon_family.h
+++ b/drivers/gpu/drm/radeon/radeon_family.h
@@ -115,6 +115,7 @@ enum radeon_chip_flags {
 	RADEON_NEW_MEMMAP = 0x00400000UL,
 	RADEON_IS_PCI = 0x00800000UL,
 	RADEON_IS_IGPGART = 0x01000000UL,
+	RADEON_IS_PX = 0x02000000UL,
 };
 
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 089c9ffb0aa9..b3f0293ba0d8 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -202,6 +202,16 @@ static bool radeon_msi_ok(struct radeon_device *rdev)
 	if (rdev->flags & RADEON_IS_AGP)
 		return false;
 
+	/*
+	 * Older chips have a HW limitation, they can only generate 40 bits
+	 * of address for "64-bit" MSIs which breaks on some platforms, notably
+	 * IBM POWER servers, so we limit them
+	 */
+	if (rdev->family < CHIP_BONAIRE) {
+		dev_info(rdev->dev, "radeon: MSI limited to 32-bit\n");
+		rdev->pdev->no_64bit_msi = 1;
+	}
+
 	/* force MSI on */
 	if (radeon_msi == 1)
 		return true;
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 66ed3ea71440..6bffe82f241c 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -35,9 +35,9 @@
 #include <linux/pm_runtime.h>
 
 #if defined(CONFIG_VGA_SWITCHEROO)
-bool radeon_is_px(void);
+bool radeon_has_atpx(void);
 #else
-static inline bool radeon_is_px(void) { return false; }
+static inline bool radeon_has_atpx(void) { return false; }
 #endif
 
 /**
@@ -107,6 +107,11 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		flags |= RADEON_IS_PCI;
 	}
 
+	if ((radeon_runtime_pm != 0) &&
+	    radeon_has_atpx() &&
+	    ((flags & RADEON_IS_IGP) == 0))
+		flags |= RADEON_IS_PX;
+
 	/* radeon_device_init should report only fatal error
 	 * like memory allocation failure or iomapping failure,
 	 * or memory manager initialization failure, it must
@@ -137,8 +142,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
 				"Error during ACPI methods call\n");
 	}
 
-	if ((radeon_runtime_pm == 1) ||
-	    ((radeon_runtime_pm == -1) && radeon_is_px())) {
+	if (radeon_is_px(dev)) {
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
 		pm_runtime_set_active(dev->dev);
@@ -250,7 +254,14 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		}
 		break;
 	case RADEON_INFO_ACCEL_WORKING2:
-		*value = rdev->accel_working;
+		if (rdev->family == CHIP_HAWAII) {
+			if (rdev->accel_working)
+				*value = 2;
+			else
+				*value = 0;
+		} else {
+			*value = rdev->accel_working;
+		}
 		break;
 	case RADEON_INFO_TILING_CONFIG:
 		if (rdev->family >= CHIP_BONAIRE)
@@ -729,6 +740,8 @@ int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc,
 
 	/* Get associated drm_crtc: */
 	drmcrtc = &rdev->mode_info.crtcs[crtc]->base;
+	if (!drmcrtc)
+		return -EINVAL;
 
 	/* Helper routine in DRM core does all the work: */
 	return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error,
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 08595cf90b01..11bb88afbac1 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -586,22 +586,30 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	radeon_bo_check_tiling(rbo, 0, 0);
 	rdev = rbo->rdev;
-	if (bo->mem.mem_type == TTM_PL_VRAM) {
-		size = bo->mem.num_pages << PAGE_SHIFT;
-		offset = bo->mem.start << PAGE_SHIFT;
-		if ((offset + size) > rdev->mc.visible_vram_size) {
-			/* hurrah the memory is not visible ! */
-			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
-			rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
-			r = ttm_bo_validate(bo, &rbo->placement, false, false);
-			if (unlikely(r != 0))
-				return r;
-			offset = bo->mem.start << PAGE_SHIFT;
-			/* this should not happen */
-			if ((offset + size) > rdev->mc.visible_vram_size)
-				return -EINVAL;
-		}
+	if (bo->mem.mem_type != TTM_PL_VRAM)
+		return 0;
+
+	size = bo->mem.num_pages << PAGE_SHIFT;
+	offset = bo->mem.start << PAGE_SHIFT;
+	if ((offset + size) <= rdev->mc.visible_vram_size)
+		return 0;
+
+	/* hurrah the memory is not visible ! */
+	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
+	rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
+	r = ttm_bo_validate(bo, &rbo->placement, false, false);
+	if (unlikely(r == -ENOMEM)) {
+		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
+		return ttm_bo_validate(bo, &rbo->placement, false, false);
+	} else if (unlikely(r != 0)) {
+		return r;
 	}
+
+	offset = bo->mem.start << PAGE_SHIFT;
+	/* this should never happen */
+	if ((offset + size) > rdev->mc.visible_vram_size)
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 8e8153e471c2..cfb513f933d5 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -361,6 +361,11 @@ static ssize_t radeon_set_pm_profile(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
+	/* Can't set profile when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	mutex_lock(&rdev->pm.mutex);
 	if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
 		if (strncmp("default", buf, strlen("default")) == 0)
@@ -409,6 +414,13 @@ static ssize_t radeon_set_pm_method(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
+	/* Can't set method when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
+		count = -EINVAL;
+		goto fail;
+	}
+
 	/* we don't support the legacy modes with dpm */
 	if (rdev->pm.pm_method == PM_METHOD_DPM) {
 		count = -EINVAL;
@@ -472,7 +484,12 @@ static ssize_t radeon_set_dpm_state(struct device *dev,
 		goto fail;
 	}
 	mutex_unlock(&rdev->pm.mutex);
-	radeon_pm_compute_clocks(rdev);
+
+	/* Can't set dpm state when the card is off */
+	if (!(rdev->flags & RADEON_IS_PX) ||
+	    (ddev->switch_power_state == DRM_SWITCH_POWER_ON))
+		radeon_pm_compute_clocks(rdev);
+
 fail:
 	return count;
 }
@@ -485,6 +502,10 @@ static ssize_t radeon_get_dpm_forced_performance_level(struct device *dev,
 	struct radeon_device *rdev = ddev->dev_private;
 	enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;
 
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return snprintf(buf, PAGE_SIZE, "off\n");
+
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			(level == RADEON_DPM_FORCED_LEVEL_AUTO) ? "auto" :
 			(level == RADEON_DPM_FORCED_LEVEL_LOW) ? "low" : "high");
@@ -500,6 +521,11 @@ static ssize_t radeon_set_dpm_forced_performance_level(struct device *dev,
 	enum radeon_dpm_forced_level level;
 	int ret = 0;
 
+	/* Can't force performance level when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	mutex_lock(&rdev->pm.mutex);
 	if (strncmp("low", buf, strlen("low")) == 0) {
 		level = RADEON_DPM_FORCED_LEVEL_LOW;
@@ -538,8 +564,14 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev,
 				      char *buf)
 {
 	struct radeon_device *rdev = dev_get_drvdata(dev);
+	struct drm_device *ddev = rdev->ddev;
 	int temp;
 
+	/* Can't get temperature when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	if (rdev->asic->pm.get_temperature)
 		temp = radeon_get_temperature(rdev);
 	else
@@ -603,7 +635,6 @@ static const struct attribute_group *hwmon_groups[] = {
 static int radeon_hwmon_init(struct radeon_device *rdev)
 {
 	int err = 0;
-	struct device *hwmon_dev;
 
 	switch (rdev->pm.int_thermal_type) {
 	case THERMAL_TYPE_RV6XX:
@@ -616,11 +647,11 @@ static int radeon_hwmon_init(struct radeon_device *rdev)
 	case THERMAL_TYPE_KV:
 		if (rdev->asic->pm.get_temperature == NULL)
 			return err;
-		hwmon_dev = hwmon_device_register_with_groups(rdev->dev,
-							      "radeon", rdev,
-							      hwmon_groups);
-		if (IS_ERR(hwmon_dev)) {
-			err = PTR_ERR(hwmon_dev);
+		rdev->pm.int_hwmon_dev = hwmon_device_register_with_groups(rdev->dev,
+									   "radeon", rdev,
+									   hwmon_groups);
+		if (IS_ERR(rdev->pm.int_hwmon_dev)) {
+			err = PTR_ERR(rdev->pm.int_hwmon_dev);
 			dev_err(rdev->dev,
 				"Unable to register hwmon device: %d\n", err);
 		}
@@ -632,6 +663,12 @@ static int radeon_hwmon_init(struct radeon_device *rdev)
 	return err;
 }
 
+static void radeon_hwmon_fini(struct radeon_device *rdev)
+{
+	if (rdev->pm.int_hwmon_dev)
+		hwmon_device_unregister(rdev->pm.int_hwmon_dev);
+}
+
 static void radeon_dpm_thermal_work_handler(struct work_struct *work)
 {
 	struct radeon_device *rdev =
@@ -1041,7 +1078,6 @@ static void radeon_pm_resume_dpm(struct radeon_device *rdev)
 	if (ret)
 		goto dpm_resume_fail;
 	rdev->pm.dpm_enabled = true;
-	radeon_pm_compute_clocks(rdev);
 	return;
 
 dpm_resume_fail:
@@ -1235,10 +1271,7 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_RV670:
 	case CHIP_RS780:
 	case CHIP_RS880:
-	case CHIP_BARTS:
-	case CHIP_TURKS:
-	case CHIP_CAICOS:
-	case CHIP_CAYMAN:
+	case CHIP_RV770:
 		/* DPM requires the RLC, RV770+ dGPU requires SMC */
 		if (!rdev->rlc_fw)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
@@ -1251,7 +1284,6 @@ int radeon_pm_init(struct radeon_device *rdev)
 		else
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
 		break;
-	case CHIP_RV770:
 	case CHIP_RV730:
 	case CHIP_RV710:
 	case CHIP_RV740:
@@ -1263,6 +1295,10 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_PALM:
 	case CHIP_SUMO:
 	case CHIP_SUMO2:
+	case CHIP_BARTS:
+	case CHIP_TURKS:
+	case CHIP_CAICOS:
+	case CHIP_CAYMAN:
 	case CHIP_ARUBA:
 	case CHIP_TAHITI:
 	case CHIP_PITCAIRN:
@@ -1331,6 +1367,8 @@ static void radeon_pm_fini_old(struct radeon_device *rdev)
 		device_remove_file(rdev->dev, &dev_attr_power_method);
 	}
 
+	radeon_hwmon_fini(rdev);
+
 	if (rdev->pm.power_state)
 		kfree(rdev->pm.power_state);
 }
@@ -1350,6 +1388,8 @@ static void radeon_pm_fini_dpm(struct radeon_device *rdev)
 	}
 	radeon_dpm_fini(rdev);
 
+	radeon_hwmon_fini(rdev);
+
 	if (rdev->pm.power_state)
 		kfree(rdev->pm.power_state);
 }
@@ -1375,12 +1415,14 @@ static void radeon_pm_compute_clocks_old(struct radeon_device *rdev)
 
 	rdev->pm.active_crtcs = 0;
 	rdev->pm.active_crtc_count = 0;
-	list_for_each_entry(crtc,
-		&ddev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (radeon_crtc->enabled) {
-			rdev->pm.active_crtcs |= (1 << radeon_crtc->crtc_id);
-			rdev->pm.active_crtc_count++;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc,
+				    &ddev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (radeon_crtc->enabled) {
+				rdev->pm.active_crtcs |= (1 << radeon_crtc->crtc_id);
+				rdev->pm.active_crtc_count++;
+			}
 		}
 	}
 
@@ -1447,12 +1489,14 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev)
 	/* update active crtc counts */
 	rdev->pm.dpm.new_active_crtcs = 0;
 	rdev->pm.dpm.new_active_crtc_count = 0;
-	list_for_each_entry(crtc,
-		&ddev->mode_config.crtc_list, head) {
-		radeon_crtc = to_radeon_crtc(crtc);
-		if (crtc->enabled) {
-			rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id);
-			rdev->pm.dpm.new_active_crtc_count++;
+	if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(crtc,
+				    &ddev->mode_config.crtc_list, head) {
+			radeon_crtc = to_radeon_crtc(crtc);
+			if (crtc->enabled) {
+				rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id);
+				rdev->pm.dpm.new_active_crtc_count++;
+			}
 		}
 	}
 
@@ -1578,8 +1622,12 @@ static int radeon_debugfs_pm_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct radeon_device *rdev = dev->dev_private;
+	struct drm_device *ddev = rdev->ddev;
 
-	if (rdev->pm.dpm_enabled) {
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
+		seq_printf(m, "PX asic powered off\n");
+	} else if (rdev->pm.dpm_enabled) {
 		mutex_lock(&rdev->pm.mutex);
 		if (rdev->asic->dpm.debugfs_print_current_performance_level)
 			radeon_dpm_debugfs_print_current_performance_level(rdev, m);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 15e44a7281ab..8391fca52a58 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -257,6 +257,7 @@ int radeon_ib_ring_tests(struct radeon_device *rdev)
 		r = radeon_ib_test(rdev, i, ring);
 		if (r) {
 			ring->ready = false;
+			rdev->needs_reset = false;
 
 			if (i == RADEON_RING_TYPE_GFX_INDEX) {
 				/* oh, oh, that's really bad */
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 9006b32d5eed..eb7b60047e86 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -34,7 +34,7 @@
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore)
 {
-	uint32_t *cpu_addr;
+	uint64_t *cpu_addr;
 	int i, r;
 
 	*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
diff --git a/drivers/gpu/drm/radeon/radeon_ucode.h b/drivers/gpu/drm/radeon/radeon_ucode.h
index a77cd274dfc3..58d12938c0b8 100644
--- a/drivers/gpu/drm/radeon/radeon_ucode.h
+++ b/drivers/gpu/drm/radeon/radeon_ucode.h
@@ -57,9 +57,14 @@
 #define BTC_MC_UCODE_SIZE            6024
 #define CAYMAN_MC_UCODE_SIZE         6037
 #define SI_MC_UCODE_SIZE             7769
+#define TAHITI_MC_UCODE_SIZE         7808
+#define PITCAIRN_MC_UCODE_SIZE       7775
+#define VERDE_MC_UCODE_SIZE          7875
 #define OLAND_MC_UCODE_SIZE          7863
-#define CIK_MC_UCODE_SIZE            7866
+#define BONAIRE_MC_UCODE_SIZE        7866
+#define BONAIRE_MC2_UCODE_SIZE       7948
 #define HAWAII_MC_UCODE_SIZE         7933
+#define HAWAII_MC2_UCODE_SIZE        8091
 
 /* SDMA */
 #define CIK_SDMA_UCODE_SIZE          1050
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 3e6804b2b2ef..414e07928693 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -465,6 +465,10 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 	cmd = radeon_get_ib_value(p, p->idx) >> 1;
 
 	if (cmd < 0x4) {
+		if (end <= start) {
+			DRM_ERROR("invalid reloc offset %X!\n", offset);
+			return -EINVAL;
+		}
 		if ((end - start) < buf_sizes[cmd]) {
 			DRM_ERROR("buffer (%d) to small (%d / %d)!\n", cmd,
 				  (unsigned)(end - start), buf_sizes[cmd]);
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 72d3616de08e..e5619d5e2a30 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -646,8 +646,10 @@ int rs600_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
 		return -EINVAL;
 	}
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
-	addr |= R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED;
-	addr |= R600_PTE_READABLE | R600_PTE_WRITEABLE;
+	if (addr != rdev->dummy_page.addr)
+		addr |= R600_PTE_VALID | R600_PTE_READABLE |
+			R600_PTE_WRITEABLE;
+	addr |= R600_PTE_SYSTEM | R600_PTE_SNOOPED;
 	writeq(addr, ptr + (i * 8));
 	return 0;
 }
@@ -888,6 +890,9 @@ void rs600_bandwidth_update(struct radeon_device *rdev)
 	u32 d1mode_priority_a_cnt, d2mode_priority_a_cnt;
 	/* FIXME: implement full support */
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled)
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3462b64369bf..0a2d36e81108 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -579,6 +579,9 @@ void rs690_bandwidth_update(struct radeon_device *rdev)
 	u32 d1mode_priority_a_cnt, d1mode_priority_b_cnt;
 	u32 d2mode_priority_a_cnt, d2mode_priority_b_cnt;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled)
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 237dd29d9f1c..b49965a21a2d 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -1276,6 +1276,9 @@ void rv515_bandwidth_update(struct radeon_device *rdev)
 	struct drm_display_mode *mode0 = NULL;
 	struct drm_display_mode *mode1 = NULL;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	if (rdev->mode_info.crtcs[0]->base.enabled)
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index b5f63f5e22a3..8fcb932a3a55 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2332,12 +2332,6 @@ void rv770_get_engine_memory_ss(struct radeon_device *rdev)
 	pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
 						       ASIC_INTERNAL_MEMORY_SS, 0);
 
-	/* disable ss, causes hangs on some cayman boards */
-	if (rdev->family == CHIP_CAYMAN) {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
-	}
-
 	if (pi->sclk_ss || pi->mclk_ss)
 		pi->dynamic_ss = true;
 	else
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 9a124d0608b3..52b64ad285d6 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -39,30 +39,35 @@ MODULE_FIRMWARE("radeon/TAHITI_pfp.bin");
 MODULE_FIRMWARE("radeon/TAHITI_me.bin");
 MODULE_FIRMWARE("radeon/TAHITI_ce.bin");
 MODULE_FIRMWARE("radeon/TAHITI_mc.bin");
+MODULE_FIRMWARE("radeon/TAHITI_mc2.bin");
 MODULE_FIRMWARE("radeon/TAHITI_rlc.bin");
 MODULE_FIRMWARE("radeon/TAHITI_smc.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_pfp.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_me.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_ce.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_mc.bin");
+MODULE_FIRMWARE("radeon/PITCAIRN_mc2.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_rlc.bin");
 MODULE_FIRMWARE("radeon/PITCAIRN_smc.bin");
 MODULE_FIRMWARE("radeon/VERDE_pfp.bin");
 MODULE_FIRMWARE("radeon/VERDE_me.bin");
 MODULE_FIRMWARE("radeon/VERDE_ce.bin");
 MODULE_FIRMWARE("radeon/VERDE_mc.bin");
+MODULE_FIRMWARE("radeon/VERDE_mc2.bin");
 MODULE_FIRMWARE("radeon/VERDE_rlc.bin");
 MODULE_FIRMWARE("radeon/VERDE_smc.bin");
 MODULE_FIRMWARE("radeon/OLAND_pfp.bin");
 MODULE_FIRMWARE("radeon/OLAND_me.bin");
 MODULE_FIRMWARE("radeon/OLAND_ce.bin");
 MODULE_FIRMWARE("radeon/OLAND_mc.bin");
+MODULE_FIRMWARE("radeon/OLAND_mc2.bin");
 MODULE_FIRMWARE("radeon/OLAND_rlc.bin");
 MODULE_FIRMWARE("radeon/OLAND_smc.bin");
 MODULE_FIRMWARE("radeon/HAINAN_pfp.bin");
 MODULE_FIRMWARE("radeon/HAINAN_me.bin");
 MODULE_FIRMWARE("radeon/HAINAN_ce.bin");
 MODULE_FIRMWARE("radeon/HAINAN_mc.bin");
+MODULE_FIRMWARE("radeon/HAINAN_mc2.bin");
 MODULE_FIRMWARE("radeon/HAINAN_rlc.bin");
 MODULE_FIRMWARE("radeon/HAINAN_smc.bin");
 
@@ -1467,36 +1472,33 @@ int si_mc_load_microcode(struct radeon_device *rdev)
 	const __be32 *fw_data;
 	u32 running, blackout = 0;
 	u32 *io_mc_regs;
-	int i, ucode_size, regs_size;
+	int i, regs_size, ucode_size;
 
 	if (!rdev->mc_fw)
 		return -EINVAL;
 
+	ucode_size = rdev->mc_fw->size / 4;
+
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 		io_mc_regs = (u32 *)&tahiti_io_mc_regs;
-		ucode_size = SI_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_PITCAIRN:
 		io_mc_regs = (u32 *)&pitcairn_io_mc_regs;
-		ucode_size = SI_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_VERDE:
 	default:
 		io_mc_regs = (u32 *)&verde_io_mc_regs;
-		ucode_size = SI_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_OLAND:
 		io_mc_regs = (u32 *)&oland_io_mc_regs;
-		ucode_size = OLAND_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	case CHIP_HAINAN:
 		io_mc_regs = (u32 *)&hainan_io_mc_regs;
-		ucode_size = OLAND_MC_UCODE_SIZE;
 		regs_size = TAHITI_IO_MC_REGS_SIZE;
 		break;
 	}
@@ -1552,7 +1554,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	const char *chip_name;
 	const char *rlc_chip_name;
 	size_t pfp_req_size, me_req_size, ce_req_size, rlc_req_size, mc_req_size;
-	size_t smc_req_size;
+	size_t smc_req_size, mc2_req_size;
 	char fw_name[30];
 	int err;
 
@@ -1567,6 +1569,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = SI_MC_UCODE_SIZE * 4;
+		mc2_req_size = TAHITI_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(TAHITI_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_PITCAIRN:
@@ -1577,6 +1580,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = SI_MC_UCODE_SIZE * 4;
+		mc2_req_size = PITCAIRN_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(PITCAIRN_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_VERDE:
@@ -1587,6 +1591,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
 		mc_req_size = SI_MC_UCODE_SIZE * 4;
+		mc2_req_size = VERDE_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(VERDE_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_OLAND:
@@ -1596,7 +1601,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
-		mc_req_size = OLAND_MC_UCODE_SIZE * 4;
+		mc_req_size = mc2_req_size = OLAND_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(OLAND_SMC_UCODE_SIZE, 4);
 		break;
 	case CHIP_HAINAN:
@@ -1606,7 +1611,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
 		ce_req_size = SI_CE_UCODE_SIZE * 4;
 		rlc_req_size = SI_RLC_UCODE_SIZE * 4;
-		mc_req_size = OLAND_MC_UCODE_SIZE * 4;
+		mc_req_size = mc2_req_size = OLAND_MC_UCODE_SIZE * 4;
 		smc_req_size = ALIGN(HAINAN_SMC_UCODE_SIZE, 4);
 		break;
 	default: BUG();
@@ -1659,16 +1664,22 @@ static int si_init_microcode(struct radeon_device *rdev)
 		err = -EINVAL;
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name);
 	err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
-	if (err)
-		goto out;
-	if (rdev->mc_fw->size != mc_req_size) {
+	if (err) {
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+		err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
+		if (err)
+			goto out;
+	}
+	if ((rdev->mc_fw->size != mc_req_size) &&
+	    (rdev->mc_fw->size != mc2_req_size)) {
 		printk(KERN_ERR
 		       "si_mc: Bogus length %zu in firmware \"%s\"\n",
 		       rdev->mc_fw->size, fw_name);
 		err = -EINVAL;
 	}
+	DRM_INFO("%s: %zu bytes\n", fw_name, rdev->mc_fw->size);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
 	err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
@@ -2216,6 +2227,9 @@ void dce6_bandwidth_update(struct radeon_device *rdev)
 	u32 num_heads = 0, lb_size;
 	int i;
 
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	radeon_update_display_priority(rdev);
 
 	for (i = 0; i < rdev->num_crtc; i++) {
@@ -4799,7 +4813,7 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 
 	/* write new base address */
 	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
-	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
 				 WRITE_DATA_DST_SEL(0)));
 
 	if (vm->id < 8) {
@@ -5777,7 +5791,6 @@ int si_irq_set(struct radeon_device *rdev)
 	u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0;
 	u32 hpd1 = 0, hpd2 = 0, hpd3 = 0, hpd4 = 0, hpd5 = 0, hpd6 = 0;
 	u32 grbm_int_cntl = 0;
-	u32 grph1 = 0, grph2 = 0, grph3 = 0, grph4 = 0, grph5 = 0, grph6 = 0;
 	u32 dma_cntl, dma_cntl1;
 	u32 thermal_int = 0;
 
@@ -5916,16 +5929,22 @@ int si_irq_set(struct radeon_device *rdev)
 	}
 
 	if (rdev->num_crtc >= 2) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, grph1);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, grph2);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 	if (rdev->num_crtc >= 4) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 	if (rdev->num_crtc >= 6) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 
 	if (!ASIC_IS_NODCE(rdev)) {
@@ -6082,6 +6101,7 @@ static inline u32 si_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -6289,6 +6309,15 @@ restart_ih:
 				break;
 			}
 			break;
+		case 8: /* D1 page flip */
+		case 10: /* D2 page flip */
+		case 12: /* D3 page flip */
+		case 14: /* D4 page flip */
+		case 16: /* D5 page flip */
+		case 18: /* D6 page flip */
+			DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1);
+			radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1);
+			break;
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 0a2f5b4bca43..879e62844b2b 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -6200,7 +6200,7 @@ static void si_parse_pplib_clock_info(struct radeon_device *rdev,
 	if ((rps->class2 & ATOM_PPLIB_CLASSIFICATION2_ULV) &&
 	    index == 0) {
 		/* XXX disable for A0 tahiti */
-		si_pi->ulv.supported = true;
+		si_pi->ulv.supported = false;
 		si_pi->ulv.pl = *pl;
 		si_pi->ulv.one_pcie_lane_in_ulv = false;
 		si_pi->ulv.volt_change_delay = SISLANDS_ULVVOLTAGECHANGEDELAY_DFLT;
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 9239a6d29128..3007cddc7e70 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -107,8 +107,8 @@
 #define		SPLL_CHG_STATUS				(1 << 1)
 #define	SPLL_CNTL_MODE					0x618
 #define		SPLL_SW_DIR_CONTROL			(1 << 0)
-#	define SPLL_REFCLK_SEL(x)			((x) << 8)
-#	define SPLL_REFCLK_SEL_MASK			0xFF00
+#	define SPLL_REFCLK_SEL(x)			((x) << 26)
+#	define SPLL_REFCLK_SEL_MASK			(3 << 26)
 
 #define	CG_SPLL_SPREAD_SPECTRUM				0x620
 #define		SSEN					(1 << 0)
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 2da0e17eb960..d9cfa09b2e3f 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1877,7 +1877,16 @@ int trinity_dpm_init(struct radeon_device *rdev)
 	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++)
 		pi->at[i] = TRINITY_AT_DFLT;
 
-	pi->enable_bapm = false;
+	/* There are stability issues reported on with
+	 * bapm enabled when switching between AC and battery
+	 * power.  At the same time, some MSI boards hang
+	 * if it's not enabled and dpm is enabled.  Just enable
+	 * it for MSI boards right now.
+	 */
+	if (rdev->pdev->subsystem_vendor == 0x1462)
+		pi->enable_bapm = true;
+	else
+		pi->enable_bapm = false;
 	pi->enable_nbps_policy = true;
 	pi->enable_sclk_ds = true;
 	pi->enable_gfx_power_gating = true;
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index d4a68af1a279..c310a0aeebb9 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -83,7 +83,10 @@ int uvd_v1_0_init(struct radeon_device *rdev)
 	int r;
 
 	/* raise clocks while booting up the VCPU */
-	radeon_set_uvd_clocks(rdev, 53300, 40000);
+	if (rdev->family < CHIP_RV740)
+		radeon_set_uvd_clocks(rdev, 10000, 10000);
+	else
+		radeon_set_uvd_clocks(rdev, 53300, 40000);
 
 	r = uvd_v1_0_start(rdev);
 	if (r)
@@ -407,7 +410,10 @@ int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	struct radeon_fence *fence = NULL;
 	int r;
 
-	r = radeon_set_uvd_clocks(rdev, 53300, 40000);
+	if (rdev->family < CHIP_RV740)
+		r = radeon_set_uvd_clocks(rdev, 10000, 10000);
+	else
+		r = radeon_set_uvd_clocks(rdev, 53300, 40000);
 	if (r) {
 		DRM_ERROR("radeon: failed to raise UVD clocks (%d).\n", r);
 		return r;
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 171a8203892c..52b47115b5cb 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -84,6 +84,7 @@ static int modeset_init(struct drm_device *dev)
 	if ((priv->num_encoders == 0) || (priv->num_connectors == 0)) {
 		/* oh nos! */
 		dev_err(dev->dev, "no encoders/connectors found\n");
+		drm_mode_config_cleanup(dev);
 		return -ENXIO;
 	}
 
@@ -122,6 +123,7 @@ static int tilcdc_unload(struct drm_device *dev)
 	struct tilcdc_drm_private *priv = dev->dev_private;
 	struct tilcdc_module *mod, *cur;
 
+	drm_fbdev_cma_fini(priv->fbdev);
 	drm_kms_helper_poll_fini(dev);
 	drm_mode_config_cleanup(dev);
 	drm_vblank_cleanup(dev);
@@ -177,33 +179,37 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	dev->dev_private = priv;
 
 	priv->wq = alloc_ordered_workqueue("tilcdc", 0);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto fail_free_priv;
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(dev->dev, "failed to get memory resource\n");
 		ret = -EINVAL;
-		goto fail;
+		goto fail_free_wq;
 	}
 
 	priv->mmio = ioremap_nocache(res->start, resource_size(res));
 	if (!priv->mmio) {
 		dev_err(dev->dev, "failed to ioremap\n");
 		ret = -ENOMEM;
-		goto fail;
+		goto fail_free_wq;
 	}
 
 	priv->clk = clk_get(dev->dev, "fck");
 	if (IS_ERR(priv->clk)) {
 		dev_err(dev->dev, "failed to get functional clock\n");
 		ret = -ENODEV;
-		goto fail;
+		goto fail_iounmap;
 	}
 
 	priv->disp_clk = clk_get(dev->dev, "dpll_disp_ck");
 	if (IS_ERR(priv->clk)) {
 		dev_err(dev->dev, "failed to get display clock\n");
 		ret = -ENODEV;
-		goto fail;
+		goto fail_put_clk;
 	}
 
 #ifdef CONFIG_CPU_FREQ
@@ -213,7 +219,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 			CPUFREQ_TRANSITION_NOTIFIER);
 	if (ret) {
 		dev_err(dev->dev, "failed to register cpufreq notifier\n");
-		goto fail;
+		goto fail_put_disp_clk;
 	}
 #endif
 
@@ -258,13 +264,13 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	ret = modeset_init(dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize mode setting\n");
-		goto fail;
+		goto fail_cpufreq_unregister;
 	}
 
 	ret = drm_vblank_init(dev, 1);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize vblank\n");
-		goto fail;
+		goto fail_mode_config_cleanup;
 	}
 
 	pm_runtime_get_sync(dev->dev);
@@ -272,7 +278,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	pm_runtime_put_sync(dev->dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to install IRQ handler\n");
-		goto fail;
+		goto fail_vblank_cleanup;
 	}
 
 	platform_set_drvdata(pdev, dev);
@@ -288,13 +294,48 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	priv->fbdev = drm_fbdev_cma_init(dev, bpp,
 			dev->mode_config.num_crtc,
 			dev->mode_config.num_connector);
+	if (IS_ERR(priv->fbdev)) {
+		ret = PTR_ERR(priv->fbdev);
+		goto fail_irq_uninstall;
+	}
 
 	drm_kms_helper_poll_init(dev);
 
 	return 0;
 
-fail:
-	tilcdc_unload(dev);
+fail_irq_uninstall:
+	pm_runtime_get_sync(dev->dev);
+	drm_irq_uninstall(dev);
+	pm_runtime_put_sync(dev->dev);
+
+fail_vblank_cleanup:
+	drm_vblank_cleanup(dev);
+
+fail_mode_config_cleanup:
+	drm_mode_config_cleanup(dev);
+
+fail_cpufreq_unregister:
+	pm_runtime_disable(dev->dev);
+#ifdef CONFIG_CPU_FREQ
+	cpufreq_unregister_notifier(&priv->freq_transition,
+			CPUFREQ_TRANSITION_NOTIFIER);
+fail_put_disp_clk:
+	clk_put(priv->disp_clk);
+#endif
+
+fail_put_clk:
+	clk_put(priv->clk);
+
+fail_iounmap:
+	iounmap(priv->mmio);
+
+fail_free_wq:
+	flush_workqueue(priv->wq);
+	destroy_workqueue(priv->wq);
+
+fail_free_priv:
+	dev->dev_private = NULL;
+	kfree(priv);
 	return ret;
 }
 
@@ -628,10 +669,10 @@ static int __init tilcdc_drm_init(void)
 static void __exit tilcdc_drm_fini(void)
 {
 	DBG("fini");
-	tilcdc_tfp410_fini();
-	tilcdc_slave_fini();
-	tilcdc_panel_fini();
 	platform_driver_unregister(&tilcdc_platform_driver);
+	tilcdc_panel_fini();
+	tilcdc_slave_fini();
+	tilcdc_tfp410_fini();
 }
 
 late_initcall(tilcdc_drm_init);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 86c67329b605..b085dcc54fb5 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -151,6 +151,7 @@ struct panel_connector {
 static void panel_connector_destroy(struct drm_connector *connector)
 {
 	struct panel_connector *panel_connector = to_panel_connector(connector);
+	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(panel_connector);
 }
@@ -285,10 +286,8 @@ static void panel_destroy(struct tilcdc_module *mod)
 {
 	struct panel_module *panel_mod = to_panel_module(mod);
 
-	if (panel_mod->timings) {
+	if (panel_mod->timings)
 		display_timings_release(panel_mod->timings);
-		kfree(panel_mod->timings);
-	}
 
 	tilcdc_module_cleanup(mod);
 	kfree(panel_mod->info);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
index 595068ba2d5e..2f83ffb7f37e 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
@@ -166,6 +166,7 @@ struct slave_connector {
 static void slave_connector_destroy(struct drm_connector *connector)
 {
 	struct slave_connector *slave_connector = to_slave_connector(connector);
+	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(slave_connector);
 }
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index c38b56b268ac..ce75ac8de4f8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -167,6 +167,7 @@ struct tfp410_connector {
 static void tfp410_connector_destroy(struct drm_connector *connector)
 {
 	struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector);
+	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
 	kfree(tfp410_connector);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 863bef9f9234..cf4bad2c1d59 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -297,8 +297,10 @@ static void ttm_pool_update_free_locked(struct ttm_page_pool *pool,
  *
  * @pool: to free the pages from
  * @free_all: If set to true will free all pages in pool
+ * @gfp: GFP flags.
  **/
-static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free)
+static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
+			      gfp_t gfp)
 {
 	unsigned long irq_flags;
 	struct page *p;
@@ -309,8 +311,7 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free)
 	if (NUM_PAGES_TO_ALLOC < nr_free)
 		npages_to_free = NUM_PAGES_TO_ALLOC;
 
-	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
-			GFP_KERNEL);
+	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);
 	if (!pages_to_free) {
 		pr_err("Failed to allocate memory for pool free operation\n");
 		return 0;
@@ -382,32 +383,35 @@ out:
  *
  * XXX: (dchinner) Deadlock warning!
  *
- * ttm_page_pool_free() does memory allocation using GFP_KERNEL.  that means
- * this can deadlock when called a sc->gfp_mask that is not equal to
- * GFP_KERNEL.
+ * We need to pass sc->gfp_mask to ttm_page_pool_free().
  *
  * This code is crying out for a shrinker per pool....
  */
 static unsigned long
 ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
-	static atomic_t start_pool = ATOMIC_INIT(0);
+	static DEFINE_MUTEX(lock);
+	static unsigned start_pool;
 	unsigned i;
-	unsigned pool_offset = atomic_add_return(1, &start_pool);
+	unsigned pool_offset;
 	struct ttm_page_pool *pool;
 	int shrink_pages = sc->nr_to_scan;
 	unsigned long freed = 0;
 
-	pool_offset = pool_offset % NUM_POOLS;
+	if (!mutex_trylock(&lock))
+		return SHRINK_STOP;
+	pool_offset = ++start_pool % NUM_POOLS;
 	/* select start pool in round robin fashion */
 	for (i = 0; i < NUM_POOLS; ++i) {
 		unsigned nr_free = shrink_pages;
 		if (shrink_pages == 0)
 			break;
 		pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
-		shrink_pages = ttm_page_pool_free(pool, nr_free);
+		shrink_pages = ttm_page_pool_free(pool, nr_free,
+						  sc->gfp_mask);
 		freed += nr_free - shrink_pages;
 	}
+	mutex_unlock(&lock);
 	return freed;
 }
 
@@ -706,7 +710,7 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 	}
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
 	if (npages)
-		ttm_page_pool_free(pool, npages);
+		ttm_page_pool_free(pool, npages, GFP_KERNEL);
 }
 
 /*
@@ -846,7 +850,8 @@ void ttm_page_alloc_fini(void)
 	ttm_pool_mm_shrink_fini(_manager);
 
 	for (i = 0; i < NUM_POOLS; ++i)
-		ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES);
+		ttm_page_pool_free(&_manager->pools[i], FREE_ALL_PAGES,
+				   GFP_KERNEL);
 
 	kobject_put(&_manager->kobj);
 	_manager = NULL;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index fb8259f69839..ca65df144765 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -411,8 +411,10 @@ static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
  *
  * @pool: to free the pages from
  * @nr_free: If set to true will free all pages in pool
+ * @gfp: GFP flags.
  **/
-static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free)
+static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free,
+				       gfp_t gfp)
 {
 	unsigned long irq_flags;
 	struct dma_page *dma_p, *tmp;
@@ -430,8 +432,7 @@ static unsigned ttm_dma_page_pool_free(struct dma_pool *pool, unsigned nr_free)
 			 npages_to_free, nr_free);
 	}
 #endif
-	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *),
-			GFP_KERNEL);
+	pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp);
 
 	if (!pages_to_free) {
 		pr_err("%s: Failed to allocate memory for pool free operation\n",
@@ -530,7 +531,7 @@ static void ttm_dma_free_pool(struct device *dev, enum pool_type type)
 		if (pool->type != type)
 			continue;
 		/* Takes a spinlock.. */
-		ttm_dma_page_pool_free(pool, FREE_ALL_PAGES);
+		ttm_dma_page_pool_free(pool, FREE_ALL_PAGES, GFP_KERNEL);
 		WARN_ON(((pool->npages_in_use + pool->npages_free) != 0));
 		/* This code path is called after _all_ references to the
 		 * struct device has been dropped - so nobody should be
@@ -983,7 +984,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 
 	/* shrink pool if necessary (only on !is_cached pools)*/
 	if (npages)
-		ttm_dma_page_pool_free(pool, npages);
+		ttm_dma_page_pool_free(pool, npages, GFP_KERNEL);
 	ttm->state = tt_unpopulated;
 }
 EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
@@ -993,10 +994,7 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
  *
  * XXX: (dchinner) Deadlock warning!
  *
- * ttm_dma_page_pool_free() does GFP_KERNEL memory allocation, and so attention
- * needs to be paid to sc->gfp_mask to determine if this can be done or not.
- * GFP_KERNEL memory allocation in a GFP_ATOMIC reclaim context woul dbe really
- * bad.
+ * We need to pass sc->gfp_mask to ttm_dma_page_pool_free().
  *
  * I'm getting sadder as I hear more pathetical whimpers about needing per-pool
  * shrinkers
@@ -1004,9 +1002,9 @@ EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
 static unsigned long
 ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
-	static atomic_t start_pool = ATOMIC_INIT(0);
+	static unsigned start_pool;
 	unsigned idx = 0;
-	unsigned pool_offset = atomic_add_return(1, &start_pool);
+	unsigned pool_offset;
 	unsigned shrink_pages = sc->nr_to_scan;
 	struct device_pools *p;
 	unsigned long freed = 0;
@@ -1014,8 +1012,11 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	if (list_empty(&_manager->pools))
 		return SHRINK_STOP;
 
-	mutex_lock(&_manager->lock);
-	pool_offset = pool_offset % _manager->npools;
+	if (!mutex_trylock(&_manager->lock))
+		return SHRINK_STOP;
+	if (!_manager->npools)
+		goto out;
+	pool_offset = ++start_pool % _manager->npools;
 	list_for_each_entry(p, &_manager->pools, pools) {
 		unsigned nr_free;
 
@@ -1027,13 +1028,15 @@ ttm_dma_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		if (++idx < pool_offset)
 			continue;
 		nr_free = shrink_pages;
-		shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free);
+		shrink_pages = ttm_dma_page_pool_free(p->pool, nr_free,
+						      sc->gfp_mask);
 		freed += nr_free - shrink_pages;
 
 		pr_debug("%s: (%s:%d) Asked to shrink %d, have %d more to go\n",
 			 p->pool->dev_name, p->pool->name, current->pid,
 			 nr_free, shrink_pages);
 	}
+out:
 	mutex_unlock(&_manager->lock);
 	return freed;
 }
@@ -1044,7 +1047,8 @@ ttm_dma_pool_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 	struct device_pools *p;
 	unsigned long count = 0;
 
-	mutex_lock(&_manager->lock);
+	if (!mutex_trylock(&_manager->lock))
+		return 0;
 	list_for_each_entry(p, &_manager->pools, pools)
 		count += p->pool->npages_free;
 	mutex_unlock(&_manager->lock);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index 1e80152674b5..4fbcfdb02360 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -117,10 +117,10 @@ static void vmw_hw_context_destroy(struct vmw_resource *res)
 		(void) vmw_context_binding_state_kill
 			(&container_of(res, struct vmw_user_context, res)->cbs);
 		(void) vmw_gb_context_destroy(res);
+		mutex_unlock(&dev_priv->binding_mutex);
 		if (dev_priv->pinned_bo != NULL &&
 		    !dev_priv->query_cid_valid)
 			__vmw_execbuf_release_pinned_bo(dev_priv, NULL);
-		mutex_unlock(&dev_priv->binding_mutex);
 		mutex_unlock(&dev_priv->cmdbuf_mutex);
 		return;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 0083cbf99edf..fb7c36e93fd4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -688,7 +688,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		goto out_err0;
 	}
 
-	if (unlikely(dev_priv->prim_bb_mem < dev_priv->vram_size))
+	/*
+	 * Limit back buffer size to VRAM size.  Remove this once
+	 * screen targets are implemented.
+	 */
+	if (dev_priv->prim_bb_mem > dev_priv->vram_size)
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
 	mutex_unlock(&dev_priv->hw_mutex);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index efb575a7996c..a3480c13eb1b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1214,14 +1214,36 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		SVGA3dCmdSurfaceDMA dma;
 	} *cmd;
 	int ret;
+	SVGA3dCmdSurfaceDMASuffix *suffix;
+	uint32_t bo_size;
 
 	cmd = container_of(header, struct vmw_dma_cmd, header);
+	suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->dma +
+					       header->size - sizeof(*suffix));
+
+	/* Make sure device and verifier stays in sync. */
+	if (unlikely(suffix->suffixSize != sizeof(*suffix))) {
+		DRM_ERROR("Invalid DMA suffix size.\n");
+		return -EINVAL;
+	}
+
 	ret = vmw_translate_guest_ptr(dev_priv, sw_context,
 				      &cmd->dma.guest.ptr,
 				      &vmw_bo);
 	if (unlikely(ret != 0))
 		return ret;
 
+	/* Make sure DMA doesn't cross BO boundaries. */
+	bo_size = vmw_bo->base.num_pages * PAGE_SIZE;
+	if (unlikely(cmd->dma.guest.ptr.offset > bo_size)) {
+		DRM_ERROR("Invalid DMA offset.\n");
+		return -EINVAL;
+	}
+
+	bo_size -= cmd->dma.guest.ptr.offset;
+	if (unlikely(suffix->maximumOffset > bo_size))
+		suffix->maximumOffset = bo_size;
+
 	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
 				user_surface_converter, &cmd->dma.host.sid,
 				NULL);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index ed5ce2a41bbf..1b0f34bd3a03 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -147,7 +147,7 @@ static int vmw_fb_check_var(struct fb_var_screeninfo *var,
 	}
 
 	if (!vmw_kms_validate_mode_vram(vmw_priv,
-					info->fix.line_length,
+					var->xres * var->bits_per_pixel/8,
 					var->yoffset + var->yres)) {
 		DRM_ERROR("Requested geom can not fit in framebuffer\n");
 		return -EINVAL;
@@ -162,6 +162,8 @@ static int vmw_fb_set_par(struct fb_info *info)
 	struct vmw_private *vmw_priv = par->vmw_priv;
 	int ret;
 
+	info->fix.line_length = info->var.xres * info->var.bits_per_pixel/8;
+
 	ret = vmw_kms_write_svga(vmw_priv, info->var.xres, info->var.yres,
 				 info->fix.line_length,
 				 par->bpp, par->depth);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index 6ccd993e26bf..6eae14d2a3f7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -180,8 +180,9 @@ void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 
 	mutex_lock(&dev_priv->hw_mutex);
 
+	vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
 	while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0)
-		vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
+		;
 
 	dev_priv->last_read_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 8a650413dea5..c8f8ecf7b282 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1954,6 +1954,14 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 		DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC)
 	};
 	int i;
+	u32 assumed_bpp = 2;
+
+	/*
+	 * If using screen objects, then assume 32-bpp because that's what the
+	 * SVGA device is assuming
+	 */
+	if (dev_priv->sou_priv)
+		assumed_bpp = 4;
 
 	/* Add preferred mode */
 	{
@@ -1964,8 +1972,9 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 		mode->vdisplay = du->pref_height;
 		vmw_guess_mode_timing(mode);
 
-		if (vmw_kms_validate_mode_vram(dev_priv, mode->hdisplay * 2,
-					       mode->vdisplay)) {
+		if (vmw_kms_validate_mode_vram(dev_priv,
+						mode->hdisplay * assumed_bpp,
+						mode->vdisplay)) {
 			drm_mode_probed_add(connector, mode);
 		} else {
 			drm_mode_destroy(dev, mode);
@@ -1987,7 +1996,8 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 		    bmode->vdisplay > max_height)
 			continue;
 
-		if (!vmw_kms_validate_mode_vram(dev_priv, bmode->hdisplay * 2,
+		if (!vmw_kms_validate_mode_vram(dev_priv,
+						bmode->hdisplay * assumed_bpp,
 						bmode->vdisplay))
 			continue;
 
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index db9017adfe2b..498b37e39058 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -47,7 +47,7 @@ static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 	unsigned long reg;
 	int i, id;
 
-	for (i = 0; i <= BIT_WORD(host->info->nb_pts); i++) {
+	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) {
 		reg = host1x_sync_readl(host,
 			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
 		for_each_set_bit(id, &reg, BITS_PER_LONG) {
@@ -64,7 +64,7 @@ static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 {
 	u32 i;
 
-	for (i = 0; i <= BIT_WORD(host->info->nb_pts); ++i) {
+	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); ++i) {
 		host1x_sync_writel(host, 0xffffffffu,
 			HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(i));
 		host1x_sync_writel(host, 0xffffffffu,
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index ec0ae2d1686a..37ac7b5dbd06 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -623,7 +623,8 @@ static int vga_switcheroo_runtime_suspend(struct device *dev)
 	ret = dev->bus->pm->runtime_suspend(dev);
 	if (ret)
 		return ret;
-
+	if (vgasr_priv.handler->switchto)
+		vgasr_priv.handler->switchto(VGA_SWITCHEROO_IGD);
 	vga_switcheroo_power_switch(pdev, VGA_SWITCHEROO_OFF);
 	return 0;
 }
@@ -659,6 +660,12 @@ int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *
 }
 EXPORT_SYMBOL(vga_switcheroo_init_domain_pm_ops);
 
+void vga_switcheroo_fini_domain_pm_ops(struct device *dev)
+{
+	dev->pm_domain = NULL;
+}
+EXPORT_SYMBOL(vga_switcheroo_fini_domain_pm_ops);
+
 static int vga_switcheroo_runtime_resume_hdmi_audio(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c
index 1bdcccc54a1d..f745d2c1325e 100644
--- a/drivers/hid/hid-cherry.c
+++ b/drivers/hid/hid-cherry.c
@@ -28,7 +28,7 @@
 static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
+	if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
 		hid_info(hdev, "fixing up Cherry Cymotion report descriptor\n");
 		rdesc[11] = rdesc[16] = 0xff;
 		rdesc[12] = rdesc[17] = 0x03;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index cc32a6f96c64..d92c7d9b959a 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -718,6 +718,9 @@ static int hid_scan_main(struct hid_parser *parser, struct hid_item *item)
 	case HID_MAIN_ITEM_TAG_END_COLLECTION:
 		break;
 	case HID_MAIN_ITEM_TAG_INPUT:
+		/* ignore constant inputs, they will be ignored by hid-input */
+		if (data & HID_MAIN_ITEM_CONSTANT)
+			break;
 		for (i = 0; i < parser->local.usage_index; i++)
 			hid_scan_input_usage(parser, parser->local.usage[i]);
 		break;
@@ -839,7 +842,17 @@ struct hid_report *hid_validate_values(struct hid_device *hid,
 	 * ->numbered being checked, which may not always be the case when
 	 * drivers go to access report values.
 	 */
-	report = hid->report_enum[type].report_id_hash[id];
+	if (id == 0) {
+		/*
+		 * Validating on id 0 means we should examine the first
+		 * report in the list.
+		 */
+		report = list_entry(
+				hid->report_enum[type].report_list.next,
+				struct hid_report, list);
+	} else {
+		report = hid->report_enum[type].report_id_hash[id];
+	}
 	if (!report) {
 		hid_err(hid, "missing %s %u\n", hid_report_names[type], id);
 		return NULL;
@@ -1730,6 +1743,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) },
@@ -1780,8 +1794,6 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 22f28d6b33a8..4850da34d3ef 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -292,6 +292,11 @@
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7	0x73f7
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001	0xa001
 
+#define USB_VENDOR_ID_ELAN		0x04f3
+#define USB_DEVICE_ID_ELAN_TOUCHSCREEN	0x0089
+#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B	0x009b
+#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F	0x016f
+
 #define USB_VENDOR_ID_ELECOM		0x056e
 #define USB_DEVICE_ID_ELECOM_BM084	0x0061
 
@@ -506,6 +511,7 @@
 #define USB_DEVICE_ID_KYE_GPEN_560	0x5003
 #define USB_DEVICE_ID_KYE_EASYPEN_I405X	0x5010
 #define USB_DEVICE_ID_KYE_MOUSEPEN_I608X	0x5011
+#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2	0x501a
 #define USB_DEVICE_ID_KYE_EASYPEN_M610X	0x5013
 
 #define USB_VENDOR_ID_LABTEC		0x1020
@@ -624,8 +630,6 @@
 #define USB_DEVICE_ID_MS_PRESENTER_8K_USB	0x0713
 #define USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K	0x0730
 #define USB_DEVICE_ID_MS_COMFORT_MOUSE_4500	0x076c
-#define USB_DEVICE_ID_MS_TOUCH_COVER_2	0x07a7
-#define USB_DEVICE_ID_MS_TYPE_COVER_2	0x07a9
 
 #define USB_VENDOR_ID_MOJO		0x8282
 #define USB_DEVICE_ID_RETRO_ADAPTER	0x3201
@@ -830,6 +834,7 @@
 #define USB_DEVICE_ID_SYNAPTICS_LTS2	0x1d10
 #define USB_DEVICE_ID_SYNAPTICS_HD	0x0ac3
 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD	0x1ac3
+#define USB_DEVICE_ID_SYNAPTICS_TP_V103	0x5710
 
 #define USB_VENDOR_ID_THINGM		0x27b8
 #define USB_DEVICE_ID_BLINK1		0x01ed
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index a713e6211419..4b87bb164f30 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -312,6 +312,9 @@ static const struct hid_device_id hid_battery_quirks[] = {
 			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
+			       USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO),
+	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
 		USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI),
 	  HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
 	{}
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
index e77696367591..158fcf577fae 100644
--- a/drivers/hid/hid-kye.c
+++ b/drivers/hid/hid-kye.c
@@ -300,7 +300,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		 *   - change the button usage range to 4-7 for the extra
 		 *     buttons
 		 */
-		if (*rsize >= 74 &&
+		if (*rsize >= 75 &&
 			rdesc[61] == 0x05 && rdesc[62] == 0x08 &&
 			rdesc[63] == 0x19 && rdesc[64] == 0x08 &&
 			rdesc[65] == 0x29 && rdesc[66] == 0x0f &&
@@ -323,6 +323,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		}
 		break;
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 		if (*rsize == MOUSEPEN_I608X_RDESC_ORIG_SIZE) {
 			rdesc = mousepen_i608x_rdesc_fixed;
 			*rsize = sizeof(mousepen_i608x_rdesc_fixed);
@@ -415,6 +416,7 @@ static int kye_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	switch (id->product) {
 	case USB_DEVICE_ID_KYE_EASYPEN_I405X:
 	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+	case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
 	case USB_DEVICE_ID_KYE_EASYPEN_M610X:
 		ret = kye_tablet_enable(hdev);
 		if (ret) {
@@ -446,6 +448,8 @@ static const struct hid_device_id kye_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
+				USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_KYE_EASYPEN_M610X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
 				USB_DEVICE_ID_GENIUS_GILA_GAMING_MOUSE) },
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index 9fe9d4ac3114..b8207e0bfdc0 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -345,14 +345,14 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	struct usb_device_descriptor *udesc;
 	__u16 bcdDevice, rev_maj, rev_min;
 
-	if ((drv_data->quirks & LG_RDESC) && *rsize >= 90 && rdesc[83] == 0x26 &&
+	if ((drv_data->quirks & LG_RDESC) && *rsize >= 91 && rdesc[83] == 0x26 &&
 			rdesc[84] == 0x8c && rdesc[85] == 0x02) {
 		hid_info(hdev,
 			 "fixing up Logitech keyboard report descriptor\n");
 		rdesc[84] = rdesc[89] = 0x4d;
 		rdesc[85] = rdesc[90] = 0x10;
 	}
-	if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 50 &&
+	if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 51 &&
 			rdesc[32] == 0x81 && rdesc[33] == 0x06 &&
 			rdesc[49] == 0x81 && rdesc[50] == 0x06) {
 		hid_info(hdev,
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index f45279c3b11a..5da115a6fd22 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -237,13 +237,6 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev,
 		return;
 	}
 
-	if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
-	    (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
-		dev_err(&djrcv_hdev->dev, "%s: invalid device index:%d\n",
-			__func__, dj_report->device_index);
-		return;
-	}
-
 	if (djrcv_dev->paired_dj_devices[dj_report->device_index]) {
 		/* The device is already known. No need to reallocate it. */
 		dbg_hid("%s: device is already known\n", __func__);
@@ -694,7 +687,6 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 	struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev);
 	struct dj_report *dj_report = (struct dj_report *) data;
 	unsigned long flags;
-	bool report_processed = false;
 
 	dbg_hid("%s, size:%d\n", __func__, size);
 
@@ -722,27 +714,41 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 	 * anything else with it.
 	 */
 
+	/* case 1) */
+	if (data[0] != REPORT_ID_DJ_SHORT)
+		return false;
+
+	if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
+	    (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
+		/*
+		 * Device index is wrong, bail out.
+		 * This driver can ignore safely the receiver notifications,
+		 * so ignore those reports too.
+		 */
+		if (dj_report->device_index != DJ_RECEIVER_INDEX)
+			dev_err(&hdev->dev, "%s: invalid device index:%d\n",
+				__func__, dj_report->device_index);
+		return false;
+	}
+
 	spin_lock_irqsave(&djrcv_dev->lock, flags);
-	if (dj_report->report_id == REPORT_ID_DJ_SHORT) {
-		switch (dj_report->report_type) {
-		case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
-		case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
-			logi_dj_recv_queue_notification(djrcv_dev, dj_report);
-			break;
-		case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
-			if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
-			    STATUS_LINKLOSS) {
-				logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
-			}
-			break;
-		default:
-			logi_dj_recv_forward_report(djrcv_dev, dj_report);
+	switch (dj_report->report_type) {
+	case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
+	case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
+		logi_dj_recv_queue_notification(djrcv_dev, dj_report);
+		break;
+	case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
+		if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
+		    STATUS_LINKLOSS) {
+			logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
 		}
-		report_processed = true;
+		break;
+	default:
+		logi_dj_recv_forward_report(djrcv_dev, dj_report);
 	}
 	spin_unlock_irqrestore(&djrcv_dev->lock, flags);
 
-	return report_processed;
+	return true;
 }
 
 static int logi_dj_probe(struct hid_device *hdev,
diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h
index 4a4000340ce1..daeb0aa4bee9 100644
--- a/drivers/hid/hid-logitech-dj.h
+++ b/drivers/hid/hid-logitech-dj.h
@@ -27,6 +27,7 @@
 
 #define DJ_MAX_PAIRED_DEVICES			6
 #define DJ_MAX_NUMBER_NOTIFICATIONS		8
+#define DJ_RECEIVER_INDEX			0
 #define DJ_DEVICE_INDEX_MIN 			1
 #define DJ_DEVICE_INDEX_MAX 			6
 
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 3b43d1cfa936..991ba79cfc72 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -290,6 +290,11 @@ static int magicmouse_raw_event(struct hid_device *hdev,
 		if (size < 4 || ((size - 4) % 9) != 0)
 			return 0;
 		npoints = (size - 4) / 9;
+		if (npoints > 15) {
+			hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n",
+					size);
+			return 0;
+		}
 		msc->ntouches = 0;
 		for (ii = 0; ii < npoints; ii++)
 			magicmouse_emit_touch(msc, ii, data + ii * 9 + 4);
@@ -307,6 +312,11 @@ static int magicmouse_raw_event(struct hid_device *hdev,
 		if (size < 6 || ((size - 6) % 8) != 0)
 			return 0;
 		npoints = (size - 6) / 8;
+		if (npoints > 15) {
+			hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n",
+					size);
+			return 0;
+		}
 		msc->ntouches = 0;
 		for (ii = 0; ii < npoints; ii++)
 			magicmouse_emit_touch(msc, ii, data + ii * 8 + 6);
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index 404a3a8a82f1..c6ef6eed3091 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -208,10 +208,6 @@ static const struct hid_device_id ms_devices[] = {
 		.driver_data = MS_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_COMFORT_MOUSE_4500),
 		.driver_data = MS_DUPLICATE_USAGES },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2),
-		.driver_data = 0 },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2),
-		.driver_data = 0 },
 
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT),
 		.driver_data = MS_PRESENTER },
diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c
index 9e14c00eb1b6..25daf28b26bd 100644
--- a/drivers/hid/hid-monterey.c
+++ b/drivers/hid/hid-monterey.c
@@ -24,7 +24,7 @@
 static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 30 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
+	if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
 		hid_info(hdev, "fixing up button/consumer in HID report descriptor\n");
 		rdesc[30] = 0x0c;
 	}
diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c
index 736b2502df4f..6aca4f2554bf 100644
--- a/drivers/hid/hid-petalynx.c
+++ b/drivers/hid/hid-petalynx.c
@@ -25,7 +25,7 @@
 static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 60 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
+	if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
 			rdesc[41] == 0x00 && rdesc[59] == 0x26 &&
 			rdesc[60] == 0xf9 && rdesc[61] == 0x00) {
 		hid_info(hdev, "fixing up Petalynx Maxter Remote report descriptor\n");
diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c
index acbb021065ec..020df3c2e8b4 100644
--- a/drivers/hid/hid-picolcd_core.c
+++ b/drivers/hid/hid-picolcd_core.c
@@ -350,6 +350,12 @@ static int picolcd_raw_event(struct hid_device *hdev,
 	if (!data)
 		return 1;
 
+	if (size > 64) {
+		hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n",
+				size);
+		return 0;
+	}
+
 	if (report->id == REPORT_KEY_STATE) {
 		if (data->input_keys)
 			ret = picolcd_raw_keypad(data, report, raw_data+1, size-1);
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index 1a07e07d99a0..47d7e74231e5 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -35,6 +35,8 @@ static struct class *pyra_class;
 static void profile_activated(struct pyra_device *pyra,
 		unsigned int new_profile)
 {
+	if (new_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return;
 	pyra->actual_profile = new_profile;
 	pyra->actual_cpi = pyra->profile_settings[pyra->actual_profile].y_cpi;
 }
@@ -257,9 +259,11 @@ static ssize_t pyra_sysfs_write_settings(struct file *fp,
 	if (off != 0 || count != PYRA_SIZE_SETTINGS)
 		return -EINVAL;
 
-	mutex_lock(&pyra->pyra_lock);
-
 	settings = (struct pyra_settings const *)buf;
+	if (settings->startup_profile >= ARRAY_SIZE(pyra->profile_settings))
+		return -EINVAL;
+
+	mutex_lock(&pyra->pyra_lock);
 
 	retval = pyra_set_settings(usb_dev, settings);
 	if (retval) {
diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c
index 87fc91e1c8de..91072fa54663 100644
--- a/drivers/hid/hid-sunplus.c
+++ b/drivers/hid/hid-sunplus.c
@@ -24,7 +24,7 @@
 static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 107 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
+	if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
 			rdesc[106] == 0x03) {
 		hid_info(hdev, "fixing up Sunplus Wireless Desktop report descriptor\n");
 		rdesc[105] = rdesc[110] = 0x03;
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 42eebd14de1f..6e5d8fe0ce8f 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -136,6 +136,7 @@ struct i2c_hid {
 						   * descriptor. */
 	unsigned int		bufsize;	/* i2c buffer size */
 	char			*inbuf;		/* Input buffer */
+	char			*rawbuf;	/* Raw Input buffer */
 	char			*cmdbuf;	/* Command buffer */
 	char			*argsbuf;	/* Command arguments buffer */
 
@@ -355,7 +356,7 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 static void i2c_hid_get_input(struct i2c_hid *ihid)
 {
 	int ret, ret_size;
-	int size = le16_to_cpu(ihid->hdesc.wMaxInputLength);
+	int size = ihid->bufsize;
 
 	ret = i2c_master_recv(ihid->client, ihid->inbuf, size);
 	if (ret != size) {
@@ -482,9 +483,11 @@ static void i2c_hid_find_max_report(struct hid_device *hid, unsigned int type,
 static void i2c_hid_free_buffers(struct i2c_hid *ihid)
 {
 	kfree(ihid->inbuf);
+	kfree(ihid->rawbuf);
 	kfree(ihid->argsbuf);
 	kfree(ihid->cmdbuf);
 	ihid->inbuf = NULL;
+	ihid->rawbuf = NULL;
 	ihid->cmdbuf = NULL;
 	ihid->argsbuf = NULL;
 	ihid->bufsize = 0;
@@ -500,10 +503,11 @@ static int i2c_hid_alloc_buffers(struct i2c_hid *ihid, size_t report_size)
 		       report_size; /* report */
 
 	ihid->inbuf = kzalloc(report_size, GFP_KERNEL);
+	ihid->rawbuf = kzalloc(report_size, GFP_KERNEL);
 	ihid->argsbuf = kzalloc(args_len, GFP_KERNEL);
 	ihid->cmdbuf = kzalloc(sizeof(union command) + args_len, GFP_KERNEL);
 
-	if (!ihid->inbuf || !ihid->argsbuf || !ihid->cmdbuf) {
+	if (!ihid->inbuf || !ihid->rawbuf || !ihid->argsbuf || !ihid->cmdbuf) {
 		i2c_hid_free_buffers(ihid);
 		return -ENOMEM;
 	}
@@ -530,12 +534,12 @@ static int i2c_hid_get_raw_report(struct hid_device *hid,
 
 	ret = i2c_hid_get_report(client,
 			report_type == HID_FEATURE_REPORT ? 0x03 : 0x01,
-			report_number, ihid->inbuf, ask_count);
+			report_number, ihid->rawbuf, ask_count);
 
 	if (ret < 0)
 		return ret;
 
-	ret_count = ihid->inbuf[0] | (ihid->inbuf[1] << 8);
+	ret_count = ihid->rawbuf[0] | (ihid->rawbuf[1] << 8);
 
 	if (ret_count <= 2)
 		return 0;
@@ -544,7 +548,7 @@ static int i2c_hid_get_raw_report(struct hid_device *hid,
 
 	/* The query buffer contains the size, dropping it in the reply */
 	count = min(count, ret_count - 2);
-	memcpy(buf, ihid->inbuf + 2, count);
+	memcpy(buf, ihid->rawbuf + 2, count);
 
 	return count;
 }
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 44df131d390a..617c47f9ebe6 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -82,7 +82,7 @@ static int hid_start_in(struct hid_device *hid)
 	struct usbhid_device *usbhid = hid->driver_data;
 
 	spin_lock_irqsave(&usbhid->lock, flags);
-	if (hid->open > 0 &&
+	if ((hid->open > 0 || hid->quirks & HID_QUIRK_ALWAYS_POLL) &&
 			!test_bit(HID_DISCONNECTED, &usbhid->iofl) &&
 			!test_bit(HID_SUSPENDED, &usbhid->iofl) &&
 			!test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) {
@@ -292,6 +292,8 @@ static void hid_irq_in(struct urb *urb)
 	case 0:			/* success */
 		usbhid_mark_busy(usbhid);
 		usbhid->retry_delay = 0;
+		if ((hid->quirks & HID_QUIRK_ALWAYS_POLL) && !hid->open)
+			break;
 		hid_input_report(urb->context, HID_INPUT_REPORT,
 				 urb->transfer_buffer,
 				 urb->actual_length, 1);
@@ -734,8 +736,10 @@ void usbhid_close(struct hid_device *hid)
 	if (!--hid->open) {
 		spin_unlock_irq(&usbhid->lock);
 		hid_cancel_delayed_stuff(usbhid);
-		usb_kill_urb(usbhid->urbin);
-		usbhid->intf->needs_remote_wakeup = 0;
+		if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) {
+			usb_kill_urb(usbhid->urbin);
+			usbhid->intf->needs_remote_wakeup = 0;
+		}
 	} else {
 		spin_unlock_irq(&usbhid->lock);
 	}
@@ -1119,6 +1123,19 @@ static int usbhid_start(struct hid_device *hid)
 
 	set_bit(HID_STARTED, &usbhid->iofl);
 
+	if (hid->quirks & HID_QUIRK_ALWAYS_POLL) {
+		ret = usb_autopm_get_interface(usbhid->intf);
+		if (ret)
+			goto fail;
+		usbhid->intf->needs_remote_wakeup = 1;
+		ret = hid_start_in(hid);
+		if (ret) {
+			dev_err(&hid->dev,
+				"failed to start in urb: %d\n", ret);
+		}
+		usb_autopm_put_interface(usbhid->intf);
+	}
+
 	/* Some keyboards don't work until their LEDs have been set.
 	 * Since BIOSes do set the LEDs, it must be safe for any device
 	 * that supports the keyboard boot protocol.
@@ -1151,6 +1168,9 @@ static void usbhid_stop(struct hid_device *hid)
 	if (WARN_ON(!usbhid))
 		return;
 
+	if (hid->quirks & HID_QUIRK_ALWAYS_POLL)
+		usbhid->intf->needs_remote_wakeup = 0;
+
 	clear_bit(HID_STARTED, &usbhid->iofl);
 	spin_lock_irq(&usbhid->lock);	/* Sync with error and led handlers */
 	set_bit(HID_DISCONNECTED, &usbhid->iofl);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index dbd83878ff99..473c0c43af52 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -69,6 +69,9 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL },
+	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
@@ -113,12 +116,14 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_HD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103, HID_QUIRK_NO_INIT_REPORTS },
 
 	{ 0, 0 }
 };
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 69ea36f07b4d..e99e71a6ea59 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -164,8 +164,10 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	ret = vmbus_post_msg(open_msg,
 			       sizeof(struct vmbus_channel_open_channel));
 
-	if (ret != 0)
+	if (ret != 0) {
+		err = ret;
 		goto error1;
+	}
 
 	t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ);
 	if (t == 0) {
@@ -362,7 +364,6 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	u32 next_gpadl_handle;
 	unsigned long flags;
 	int ret = 0;
-	int t;
 
 	next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle);
 	atomic_inc(&vmbus_connection.next_gpadl_handle);
@@ -409,9 +410,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 
 		}
 	}
-	t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
-	BUG_ON(t == 0);
-
+	wait_for_completion(&msginfo->waitevent);
 
 	/* At this point, we received the gpadl created msg */
 	*gpadl_handle = gpadlmsg->gpadl;
@@ -434,7 +433,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	struct vmbus_channel_gpadl_teardown *msg;
 	struct vmbus_channel_msginfo *info;
 	unsigned long flags;
-	int ret, t;
+	int ret;
 
 	info = kmalloc(sizeof(*info) +
 		       sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
@@ -456,11 +455,12 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	ret = vmbus_post_msg(msg,
 			       sizeof(struct vmbus_channel_gpadl_teardown));
 
-	BUG_ON(ret != 0);
-	t = wait_for_completion_timeout(&info->waitevent, 5*HZ);
-	BUG_ON(t == 0);
+	if (ret)
+		goto post_msg_err;
+
+	wait_for_completion(&info->waitevent);
 
-	/* Received a torndown response */
+post_msg_err:
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
@@ -470,7 +470,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 }
 EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
 
-static void vmbus_close_internal(struct vmbus_channel *channel)
+static int vmbus_close_internal(struct vmbus_channel *channel)
 {
 	struct vmbus_channel_close_channel *msg;
 	int ret;
@@ -492,11 +492,28 @@ static void vmbus_close_internal(struct vmbus_channel *channel)
 
 	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel));
 
-	BUG_ON(ret != 0);
+	if (ret) {
+		pr_err("Close failed: close post msg return is %d\n", ret);
+		/*
+		 * If we failed to post the close msg,
+		 * it is perhaps better to leak memory.
+		 */
+		return ret;
+	}
+
 	/* Tear down the gpadl for the channel's ring buffer */
-	if (channel->ringbuffer_gpadlhandle)
-		vmbus_teardown_gpadl(channel,
-					  channel->ringbuffer_gpadlhandle);
+	if (channel->ringbuffer_gpadlhandle) {
+		ret = vmbus_teardown_gpadl(channel,
+					   channel->ringbuffer_gpadlhandle);
+		if (ret) {
+			pr_err("Close failed: teardown gpadl return %d\n", ret);
+			/*
+			 * If we failed to teardown gpadl,
+			 * it is perhaps better to leak memory.
+			 */
+			return ret;
+		}
+	}
 
 	/* Cleanup the ring buffers for this channel */
 	hv_ringbuffer_cleanup(&channel->outbound);
@@ -505,7 +522,7 @@ static void vmbus_close_internal(struct vmbus_channel *channel)
 	free_pages((unsigned long)channel->ringbuffer_pages,
 		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
 
-
+	return ret;
 }
 
 /*
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index fa920469bf10..505fe29c75b0 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -202,9 +202,16 @@ static void vmbus_process_rescind_offer(struct work_struct *work)
 	unsigned long flags;
 	struct vmbus_channel *primary_channel;
 	struct vmbus_channel_relid_released msg;
+	struct device *dev;
+
+	if (channel->device_obj) {
+		dev = get_device(&channel->device_obj->device);
+		if (dev) {
+			vmbus_device_unregister(channel->device_obj);
+			put_device(dev);
+		}
+	}
 
-	if (channel->device_obj)
-		vmbus_device_unregister(channel->device_obj);
 	memset(&msg, 0, sizeof(struct vmbus_channel_relid_released));
 	msg.child_relid = channel->offermsg.child_relid;
 	msg.header.msgtype = CHANNELMSG_RELID_RELEASED;
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index f2d7bf90c9fe..d8fd95cb0456 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -55,6 +55,9 @@ static __u32 vmbus_get_next_version(__u32 current_version)
 	case (VERSION_WIN8):
 		return VERSION_WIN7;
 
+	case (VERSION_WIN8_1):
+		return VERSION_WIN8;
+
 	case (VERSION_WS2008):
 	default:
 		return VERSION_INVAL;
@@ -77,7 +80,7 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
-	if (version == VERSION_WIN8)
+	if (version == VERSION_WIN8_1)
 		msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
 
 	/*
@@ -221,8 +224,8 @@ cleanup:
 		vmbus_connection.int_page = NULL;
 	}
 
-	free_pages((unsigned long)vmbus_connection.monitor_pages[0], 1);
-	free_pages((unsigned long)vmbus_connection.monitor_pages[1], 1);
+	free_pages((unsigned long)vmbus_connection.monitor_pages[0], 0);
+	free_pages((unsigned long)vmbus_connection.monitor_pages[1], 0);
 	vmbus_connection.monitor_pages[0] = NULL;
 	vmbus_connection.monitor_pages[1] = NULL;
 
@@ -316,9 +319,13 @@ static void process_chn_event(u32 relid)
 		 */
 
 		do {
-			hv_begin_read(&channel->inbound);
+			if (read_state)
+				hv_begin_read(&channel->inbound);
 			channel->onchannel_callback(arg);
-			bytes_to_read = hv_end_read(&channel->inbound);
+			if (read_state)
+				bytes_to_read = hv_end_read(&channel->inbound);
+			else
+				bytes_to_read = 0;
 		} while (read_state && (bytes_to_read != 0));
 	} else {
 		pr_err("no channel callback for relid - %u\n", relid);
@@ -401,10 +408,21 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 	 * insufficient resources. Retry the operation a couple of
 	 * times before giving up.
 	 */
-	while (retries < 3) {
-		ret =  hv_post_message(conn_id, 1, buffer, buflen);
-		if (ret != HV_STATUS_INSUFFICIENT_BUFFERS)
+	while (retries < 10) {
+		ret = hv_post_message(conn_id, 1, buffer, buflen);
+
+		switch (ret) {
+		case HV_STATUS_INSUFFICIENT_BUFFERS:
+			ret = -ENOMEM;
+		case -ENOMEM:
+			break;
+		case HV_STATUS_SUCCESS:
 			return ret;
+		default:
+			pr_err("hv_post_msg() failed; error code:%d\n", ret);
+			return -EINVAL;
+		}
+
 		retries++;
 		msleep(100);
 	}
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 7e17a5495e02..393fd8a98735 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -19,6 +19,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
+#include <linux/jiffies.h>
 #include <linux/mman.h>
 #include <linux/delay.h>
 #include <linux/init.h>
@@ -459,6 +460,11 @@ static bool do_hot_add;
  */
 static uint pressure_report_delay = 45;
 
+/*
+ * The last time we posted a pressure report to host.
+ */
+static unsigned long last_post_time;
+
 module_param(hot_add, bool, (S_IRUGO | S_IWUSR));
 MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add");
 
@@ -542,6 +548,7 @@ struct hv_dynmem_device {
 
 static struct hv_dynmem_device dm_device;
 
+static void post_status(struct hv_dynmem_device *dm);
 #ifdef CONFIG_MEMORY_HOTPLUG
 
 static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size)
@@ -612,7 +619,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 		 * have not been "onlined" within the allowed time.
 		 */
 		wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
-
+		post_status(&dm_device);
 	}
 
 	return;
@@ -951,11 +958,17 @@ static void post_status(struct hv_dynmem_device *dm)
 {
 	struct dm_status status;
 	struct sysinfo val;
+	unsigned long now = jiffies;
+	unsigned long last_post = last_post_time;
 
 	if (pressure_report_delay > 0) {
 		--pressure_report_delay;
 		return;
 	}
+
+	if (!time_after(now, (last_post_time + HZ)))
+		return;
+
 	si_meminfo(&val);
 	memset(&status, 0, sizeof(struct dm_status));
 	status.hdr.type = DM_STATUS_REPORT;
@@ -983,6 +996,14 @@ static void post_status(struct hv_dynmem_device *dm)
 	if (status.hdr.trans_id != atomic_read(&trans_id))
 		return;
 
+	/*
+	 * If the last post time that we sampled has changed,
+	 * we have raced, don't post the status.
+	 */
+	if (last_post != last_post_time)
+		return;
+
+	last_post_time = jiffies;
 	vmbus_sendpacket(dm->dev->channel, &status,
 				sizeof(struct dm_status),
 				(unsigned long)NULL,
@@ -1117,7 +1138,7 @@ static void balloon_up(struct work_struct *dummy)
 
 			if (ret == -EAGAIN)
 				msleep(20);
-
+			post_status(&dm_device);
 		} while (ret == -EAGAIN);
 
 		if (ret) {
@@ -1144,8 +1165,10 @@ static void balloon_down(struct hv_dynmem_device *dm,
 	struct dm_unballoon_response resp;
 	int i;
 
-	for (i = 0; i < range_count; i++)
+	for (i = 0; i < range_count; i++) {
 		free_balloon_pages(dm, &range_array[i]);
+		post_status(&dm_device);
+	}
 
 	if (req->more_pages == 1)
 		return;
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index 09988b289622..816782a65488 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -127,6 +127,15 @@ kvp_work_func(struct work_struct *dummy)
 	kvp_respond_to_host(NULL, HV_E_FAIL);
 }
 
+static void poll_channel(struct vmbus_channel *channel)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&channel->inbound_lock, flags);
+	hv_kvp_onchannelcallback(channel);
+	spin_unlock_irqrestore(&channel->inbound_lock, flags);
+}
+
 static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 {
 	int ret = 1;
@@ -155,7 +164,7 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 		kvp_register(dm_reg_value);
 		kvp_transaction.active = false;
 		if (kvp_transaction.kvp_context)
-			hv_kvp_onchannelcallback(kvp_transaction.kvp_context);
+			poll_channel(kvp_transaction.kvp_context);
 	}
 	return ret;
 }
@@ -568,6 +577,7 @@ response_done:
 
 	vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
 				VM_PKT_DATA_INBAND, 0);
+	poll_channel(channel);
 
 }
 
@@ -603,7 +613,7 @@ void hv_kvp_onchannelcallback(void *context)
 		return;
 	}
 
-	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
+	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen,
 			 &requestid);
 
 	if (recvlen > 0) {
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 62dfd246b948..d016be36cc03 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -312,7 +312,7 @@ static int util_probe(struct hv_device *dev,
 		(struct hv_util_service *)dev_id->driver_data;
 	int ret;
 
-	srv->recv_buffer = kmalloc(PAGE_SIZE * 2, GFP_KERNEL);
+	srv->recv_buffer = kmalloc(PAGE_SIZE * 4, GFP_KERNEL);
 	if (!srv->recv_buffer)
 		return -ENOMEM;
 	if (srv->util_init) {
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 5ce43d8dfa98..7703e3bc604b 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -971,7 +971,7 @@ config SENSORS_NCT6775
 
 config SENSORS_NTC_THERMISTOR
 	tristate "NTC thermistor support"
-	depends on (!OF && !IIO) || (OF && IIO)
+	depends on !OF || IIO=n || IIO
 	help
 	  This driver supports NTC thermistors sensor reading and its
 	  interpretation. The driver can also monitor the temperature and
diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c
index 29dd9f746dfa..233b374334ed 100644
--- a/drivers/hwmon/adm1021.c
+++ b/drivers/hwmon/adm1021.c
@@ -185,7 +185,7 @@ static ssize_t set_temp_max(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adm1021_data *data = i2c_get_clientdata(client);
 	long temp;
-	int err;
+	int reg_val, err;
 
 	err = kstrtol(buf, 10, &temp);
 	if (err)
@@ -193,10 +193,11 @@ static ssize_t set_temp_max(struct device *dev,
 	temp /= 1000;
 
 	mutex_lock(&data->update_lock);
-	data->temp_max[index] = clamp_val(temp, -128, 127);
+	reg_val = clamp_val(temp, -128, 127);
+	data->temp_max[index] = reg_val * 1000;
 	if (!read_only)
 		i2c_smbus_write_byte_data(client, ADM1021_REG_TOS_W(index),
-					  data->temp_max[index]);
+					  reg_val);
 	mutex_unlock(&data->update_lock);
 
 	return count;
@@ -210,7 +211,7 @@ static ssize_t set_temp_min(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adm1021_data *data = i2c_get_clientdata(client);
 	long temp;
-	int err;
+	int reg_val, err;
 
 	err = kstrtol(buf, 10, &temp);
 	if (err)
@@ -218,10 +219,11 @@ static ssize_t set_temp_min(struct device *dev,
 	temp /= 1000;
 
 	mutex_lock(&data->update_lock);
-	data->temp_min[index] = clamp_val(temp, -128, 127);
+	reg_val = clamp_val(temp, -128, 127);
+	data->temp_min[index] = reg_val * 1000;
 	if (!read_only)
 		i2c_smbus_write_byte_data(client, ADM1021_REG_THYST_W(index),
-					  data->temp_min[index]);
+					  reg_val);
 	mutex_unlock(&data->update_lock);
 
 	return count;
diff --git a/drivers/hwmon/adm1029.c b/drivers/hwmon/adm1029.c
index d19c790e410a..e38115ce0350 100644
--- a/drivers/hwmon/adm1029.c
+++ b/drivers/hwmon/adm1029.c
@@ -232,6 +232,9 @@ static ssize_t set_fan_div(struct device *dev,
 	/* Update the value */
 	reg = (reg & 0x3F) | (val << 6);
 
+	/* Update the cache */
+	data->fan_div[attr->index] = reg;
+
 	/* Write value */
 	i2c_smbus_write_byte_data(client,
 				  ADM1029_REG_FAN_DIV[attr->index], reg);
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index a8a540ca8c34..51c1a5a165ab 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -365,6 +365,7 @@ set_auto_temp_min(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	val = clamp_val(val, 0, 127000);
 	mutex_lock(&data->update_lock);
 	data->auto_temp[nr] = AUTO_TEMP_MIN_TO_REG(val, data->auto_temp[nr]);
 	adm1031_write_value(client, ADM1031_REG_AUTO_TEMP(nr),
@@ -394,6 +395,7 @@ set_auto_temp_max(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	val = clamp_val(val, 0, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = AUTO_TEMP_MAX_TO_REG(val, data->auto_temp[nr],
 						  data->pwm[nr]);
@@ -696,7 +698,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_min[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_MIN(nr),
@@ -717,7 +719,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_MAX(nr),
@@ -738,7 +740,7 @@ static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_crit[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_CRIT(nr),
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 7f9dc2f86b63..126516414c11 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -198,7 +198,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 		}
 
 		channel = be32_to_cpup(property);
-		if (channel > ADS1015_CHANNELS) {
+		if (channel >= ADS1015_CHANNELS) {
 			dev_err(&client->dev,
 				"invalid channel index %d on %s\n",
 				channel, node->full_name);
@@ -212,6 +212,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 				dev_err(&client->dev,
 					"invalid gain on %s\n",
 					node->full_name);
+				return -EINVAL;
 			}
 		}
 
@@ -222,6 +223,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 				dev_err(&client->dev,
 					"invalid data_rate on %s\n",
 					node->full_name);
+				return -EINVAL;
 			}
 		}
 
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index 0f4dea5ccf17..9ee3913850d6 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -515,7 +515,7 @@ static ssize_t set_temp_min(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->temp_min[attr->index] = temp;
@@ -549,7 +549,7 @@ static ssize_t set_temp_max(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->temp_max[attr->index] = temp;
@@ -826,7 +826,7 @@ static ssize_t set_pwm_tmin(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->pwm_tmin[attr->index] = temp;
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index eea817296513..8a67ec6279a4 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -360,11 +360,13 @@ static ssize_t set_pwm1_enable(
 	if (config)
 		return config;
 
+	mutex_lock(&data->update_lock);
 	config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF1);
 	if (config < 0) {
 			dev_err(&client->dev,
 			"Error reading configuration register, aborting.\n");
-			return config;
+			count = config;
+			goto unlock;
 	}
 
 	switch (val) {
@@ -381,14 +383,15 @@ static ssize_t set_pwm1_enable(
 		config |= AMC6821_CONF1_FDRC1;
 		break;
 	default:
-		return -EINVAL;
+		count = -EINVAL;
+		goto unlock;
 	}
-	mutex_lock(&data->update_lock);
 	if (i2c_smbus_write_byte_data(client, AMC6821_REG_CONF1, config)) {
 			dev_err(&client->dev,
 			"Configuration register write error, aborting.\n");
 			count = -EIO;
 	}
+unlock:
 	mutex_unlock(&data->update_lock);
 	return count;
 }
@@ -493,8 +496,9 @@ static ssize_t set_temp_auto_point_temp(
 		return -EINVAL;
 	}
 
-	data->valid = 0;
 	mutex_lock(&data->update_lock);
+	data->valid = 0;
+
 	switch (ix) {
 	case 0:
 		ptemp[0] = clamp_val(val / 1000, 0,
@@ -658,13 +662,14 @@ static ssize_t set_fan1_div(
 	if (config)
 		return config;
 
+	mutex_lock(&data->update_lock);
 	config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF4);
 	if (config < 0) {
 		dev_err(&client->dev,
 			"Error reading configuration register, aborting.\n");
-		return config;
+		count = config;
+		goto EXIT;
 	}
-	mutex_lock(&data->update_lock);
 	switch (val) {
 	case 2:
 		config &= ~AMC6821_CONF4_PSPR;
@@ -704,7 +709,7 @@ static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_MAX);
 static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_CRIT);
-static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO,
 	get_temp, NULL, IDX_TEMP2_INPUT);
 static SENSOR_DEVICE_ATTR(temp2_min, S_IRUGO | S_IWUSR, get_temp,
 	set_temp, IDX_TEMP2_MIN);
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index bbb0b0d463f7..15993103c1a2 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -369,12 +369,12 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 		if (cpu_has_tjmax(c))
 			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
 	} else {
-		val = (eax >> 16) & 0x7f;
+		val = (eax >> 16) & 0xff;
 		/*
 		 * If the TjMax is not plausible, an assumption
 		 * will be used
 		 */
-		if (val >= 85) {
+		if (val) {
 			dev_dbg(dev, "TjMax is %d degrees C\n", val);
 			return val * 1000;
 		}
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index afd31042b452..d14ab3c45daa 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -194,7 +194,7 @@ static ssize_t da9052_hwmon_show_name(struct device *dev,
 				      struct device_attribute *devattr,
 				      char *buf)
 {
-	return sprintf(buf, "da9052-hwmon\n");
+	return sprintf(buf, "da9052\n");
 }
 
 static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c
index 73b3865f1207..35eb7738d711 100644
--- a/drivers/hwmon/da9055-hwmon.c
+++ b/drivers/hwmon/da9055-hwmon.c
@@ -204,7 +204,7 @@ static ssize_t da9055_hwmon_show_name(struct device *dev,
 				      struct device_attribute *devattr,
 				      char *buf)
 {
-	return sprintf(buf, "da9055-hwmon\n");
+	return sprintf(buf, "da9055\n");
 }
 
 static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c
index 4ae3fff13f44..bea0a344fab5 100644
--- a/drivers/hwmon/dme1737.c
+++ b/drivers/hwmon/dme1737.c
@@ -247,8 +247,8 @@ struct dme1737_data {
 	u8  pwm_acz[3];
 	u8  pwm_freq[6];
 	u8  pwm_rr[2];
-	u8  zone_low[3];
-	u8  zone_abs[3];
+	s8  zone_low[3];
+	s8  zone_abs[3];
 	u8  zone_hyst[2];
 	u32 alarms;
 };
@@ -277,7 +277,7 @@ static inline int IN_FROM_REG(int reg, int nominal, int res)
 	return (reg * nominal + (3 << (res - 3))) / (3 << (res - 2));
 }
 
-static inline int IN_TO_REG(int val, int nominal)
+static inline int IN_TO_REG(long val, int nominal)
 {
 	return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255);
 }
@@ -293,7 +293,7 @@ static inline int TEMP_FROM_REG(int reg, int res)
 	return (reg * 1000) >> (res - 8);
 }
 
-static inline int TEMP_TO_REG(int val)
+static inline int TEMP_TO_REG(long val)
 {
 	return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127);
 }
@@ -308,7 +308,7 @@ static inline int TEMP_RANGE_FROM_REG(int reg)
 	return TEMP_RANGE[(reg >> 4) & 0x0f];
 }
 
-static int TEMP_RANGE_TO_REG(int val, int reg)
+static int TEMP_RANGE_TO_REG(long val, int reg)
 {
 	int i;
 
@@ -331,7 +331,7 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix)
 	return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000;
 }
 
-static inline int TEMP_HYST_TO_REG(int val, int ix, int reg)
+static inline int TEMP_HYST_TO_REG(long val, int ix, int reg)
 {
 	int hyst = clamp_val((val + 500) / 1000, 0, 15);
 
@@ -347,7 +347,7 @@ static inline int FAN_FROM_REG(int reg, int tpc)
 		return (reg == 0 || reg == 0xffff) ? 0 : 90000 * 60 / reg;
 }
 
-static inline int FAN_TO_REG(int val, int tpc)
+static inline int FAN_TO_REG(long val, int tpc)
 {
 	if (tpc) {
 		return clamp_val(val / tpc, 0, 0xffff);
@@ -379,7 +379,7 @@ static inline int FAN_TYPE_FROM_REG(int reg)
 	return (edge > 0) ? 1 << (edge - 1) : 0;
 }
 
-static inline int FAN_TYPE_TO_REG(int val, int reg)
+static inline int FAN_TYPE_TO_REG(long val, int reg)
 {
 	int edge = (val == 4) ? 3 : val;
 
@@ -402,7 +402,7 @@ static int FAN_MAX_FROM_REG(int reg)
 	return 1000 + i * 500;
 }
 
-static int FAN_MAX_TO_REG(int val)
+static int FAN_MAX_TO_REG(long val)
 {
 	int i;
 
@@ -460,7 +460,7 @@ static inline int PWM_ACZ_FROM_REG(int reg)
 	return acz[(reg >> 5) & 0x07];
 }
 
-static inline int PWM_ACZ_TO_REG(int val, int reg)
+static inline int PWM_ACZ_TO_REG(long val, int reg)
 {
 	int acz = (val == 4) ? 2 : val - 1;
 
@@ -476,7 +476,7 @@ static inline int PWM_FREQ_FROM_REG(int reg)
 	return PWM_FREQ[reg & 0x0f];
 }
 
-static int PWM_FREQ_TO_REG(int val, int reg)
+static int PWM_FREQ_TO_REG(long val, int reg)
 {
 	int i;
 
@@ -510,7 +510,7 @@ static inline int PWM_RR_FROM_REG(int reg, int ix)
 	return (rr & 0x08) ? PWM_RR[rr & 0x07] : 0;
 }
 
-static int PWM_RR_TO_REG(int val, int ix, int reg)
+static int PWM_RR_TO_REG(long val, int ix, int reg)
 {
 	int i;
 
@@ -528,7 +528,7 @@ static inline int PWM_RR_EN_FROM_REG(int reg, int ix)
 	return PWM_RR_FROM_REG(reg, ix) ? 1 : 0;
 }
 
-static inline int PWM_RR_EN_TO_REG(int val, int ix, int reg)
+static inline int PWM_RR_EN_TO_REG(long val, int ix, int reg)
 {
 	int en = (ix == 1) ? 0x80 : 0x08;
 
@@ -1481,13 +1481,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 		       const char *buf, size_t count)
 {
 	struct dme1737_data *data = dev_get_drvdata(dev);
-	long val;
+	unsigned long val;
 	int err;
 
-	err = kstrtol(buf, 10, &val);
+	err = kstrtoul(buf, 10, &val);
 	if (err)
 		return err;
 
+	if (val > 255)
+		return -EINVAL;
+
 	data->vrm = val;
 	return count;
 }
diff --git a/drivers/hwmon/ds1621.c b/drivers/hwmon/ds1621.c
index fc6f5d54e7f7..8890870309e4 100644
--- a/drivers/hwmon/ds1621.c
+++ b/drivers/hwmon/ds1621.c
@@ -309,6 +309,7 @@ static ssize_t set_convrate(struct device *dev, struct device_attribute *da,
 	data->conf |= (resol << DS1621_REG_CONFIG_RESOL_SHIFT);
 	i2c_smbus_write_byte_data(client, DS1621_REG_CONF, data->conf);
 	data->update_interval = ds1721_convrates[resol];
+	data->zbits = 7 - resol;
 	mutex_unlock(&data->update_lock);
 
 	return count;
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 90ec1173b8a1..01723f04fe45 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -163,7 +163,7 @@ static ssize_t store_hyst(struct device *dev,
 	if (retval < 0)
 		goto fail;
 
-	hyst = val - retval * 1000;
+	hyst = retval * 1000 - val;
 	hyst = DIV_ROUND_CLOSEST(hyst, 1000);
 	if (hyst < 0 || hyst > 255) {
 		retval = -ERANGE;
@@ -330,7 +330,7 @@ static int emc1403_detect(struct i2c_client *client,
 	}
 
 	id = i2c_smbus_read_byte_data(client, THERMAL_REVISION_REG);
-	if (id != 0x01)
+	if (id < 0x01 || id > 0x04)
 		return -ENODEV;
 
 	return 0;
@@ -355,9 +355,9 @@ static int emc1403_probe(struct i2c_client *client,
 	if (id->driver_data)
 		data->groups[1] = &emc1404_group;
 
-	hwmon_dev = hwmon_device_register_with_groups(&client->dev,
-						      client->name, data,
-						      data->groups);
+	hwmon_dev = devm_hwmon_device_register_with_groups(&client->dev,
+							   client->name, data,
+							   data->groups);
 	if (IS_ERR(hwmon_dev))
 		return PTR_ERR(hwmon_dev);
 
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index 2c137b26acb4..5790246a7e1d 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -250,9 +250,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *da,
 	if (result < 0)
 		return result;
 
-	val = DIV_ROUND_CLOSEST(val, 1000);
-	if ((val < -63) || (val > 127))
-		return -EINVAL;
+	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -63, 127);
 
 	mutex_lock(&data->update_lock);
 	data->temp_min[nr] = val;
@@ -274,9 +272,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *da,
 	if (result < 0)
 		return result;
 
-	val = DIV_ROUND_CLOSEST(val, 1000);
-	if ((val < -63) || (val > 127))
-		return -EINVAL;
+	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -63, 127);
 
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = val;
@@ -390,15 +386,14 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	struct i2c_client *client = to_i2c_client(dev);
-	long rpm_target;
+	unsigned long rpm_target;
 
-	int result = kstrtol(buf, 10, &rpm_target);
+	int result = kstrtoul(buf, 10, &rpm_target);
 	if (result < 0)
 		return result;
 
 	/* Datasheet states 16384 as maximum RPM target (table 3.2) */
-	if ((rpm_target < 0) || (rpm_target > 16384))
-		return -EINVAL;
+	rpm_target = clamp_val(rpm_target, 0, 16384);
 
 	mutex_lock(&data->update_lock);
 
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 73181be5b30b..814f7ee9026b 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -173,7 +173,7 @@ static int get_fan_speed_index(struct gpio_fan_data *fan_data)
 	return -ENODEV;
 }
 
-static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm)
+static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm)
 {
 	struct gpio_fan_speed *speed = fan_data->speed;
 	int i;
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 93d26e8af3e2..bfd3f3eeabcd 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -148,7 +148,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 
 	switch (reg) {
 	case INA2XX_SHUNT_VOLTAGE:
-		val = DIV_ROUND_CLOSEST(data->regs[reg],
+		/* signed register */
+		val = DIV_ROUND_CLOSEST((s16)data->regs[reg],
 					data->config->shunt_div);
 		break;
 	case INA2XX_BUS_VOLTAGE:
@@ -160,8 +161,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 		val = data->regs[reg] * data->config->power_lsb;
 		break;
 	case INA2XX_CURRENT:
-		/* LSB=1mA (selected). Is in mA */
-		val = data->regs[reg];
+		/* signed register, LSB=1mA (selected), in mA */
+		val = (s16)data->regs[reg];
 		break;
 	default:
 		/* programmer goofed */
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index 9efadfc851bc..c1eb464f0fd0 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -108,7 +108,7 @@ static inline int FAN_FROM_REG(u8 val, int div)
  * TEMP: mC (-128C to +127C)
  * REG: 1C/bit, two's complement
  */
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
 {
 	int nval = clamp_val(val, -128000, 127000) ;
 	return nval < 0 ? (nval - 500) / 1000 : (nval + 500) / 1000;
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index bed4af358308..21d6cc813a6d 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -158,7 +158,7 @@ static inline u16 FAN_TO_REG(unsigned long val)
 
 /* Temperature is reported in .001 degC increments */
 #define TEMP_TO_REG(val)	\
-		clamp_val(SCALE(val, 1000, 1), -127, 127)
+		DIV_ROUND_CLOSEST(clamp_val((val), -127000, 127000), 1000)
 #define TEMPEXT_FROM_REG(val, ext)	\
 		SCALE(((val) << 4) + (ext), 16, 1000)
 #define TEMP_FROM_REG(val)	((val) * 1000)
@@ -192,7 +192,7 @@ static const int lm85_range_map[] = {
 	13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000
 };
 
-static int RANGE_TO_REG(int range)
+static int RANGE_TO_REG(long range)
 {
 	int i;
 
@@ -214,7 +214,7 @@ static const int adm1027_freq_map[8] = { /* 1 Hz */
 	11, 15, 22, 29, 35, 44, 59, 88
 };
 
-static int FREQ_TO_REG(const int *map, int freq)
+static int FREQ_TO_REG(const int *map, unsigned long freq)
 {
 	int i;
 
@@ -463,6 +463,9 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
 	if (err)
 		return err;
 
+	if (val > 255)
+		return -EINVAL;
+
 	data->vrm = val;
 	return count;
 }
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 8a17f01e8672..e76feb86a1d4 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -44,6 +44,7 @@ struct ntc_compensation {
 	unsigned int	ohm;
 };
 
+/* Order matters, ntc_match references the entries by index */
 static const struct platform_device_id ntc_thermistor_id[] = {
 	{ "ncp15wb473", TYPE_NCPXXWB473 },
 	{ "ncp18wb473", TYPE_NCPXXWB473 },
@@ -141,7 +142,7 @@ struct ntc_data {
 	char name[PLATFORM_NAME_SIZE];
 };
 
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_IIO)
 static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 {
 	struct iio_channel *channel = pdata->chan;
@@ -163,15 +164,15 @@ static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 
 static const struct of_device_id ntc_match[] = {
 	{ .compatible = "ntc,ncp15wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[0] },
 	{ .compatible = "ntc,ncp18wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[1] },
 	{ .compatible = "ntc,ncp21wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[2] },
 	{ .compatible = "ntc,ncp03wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[3] },
 	{ .compatible = "ntc,ncp15wl333",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWL333] },
+		.data = &ntc_thermistor_id[4] },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, ntc_match);
@@ -223,6 +224,8 @@ ntc_thermistor_parse_dt(struct platform_device *pdev)
 	return NULL;
 }
 
+#define ntc_match	NULL
+
 static void ntc_iio_channel_release(struct ntc_thermistor_platform_data *pdata)
 { }
 #endif
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 3532026e25da..bf1d7893d51c 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -159,7 +159,7 @@ static inline int TEMP_FROM_REG(s8 val)
 {
 	return val * 830 + 52120;
 }
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
 {
 	int nval = clamp_val(val, -54120, 157530) ;
 	return nval < 0 ? (nval - 5212 - 415) / 830 : (nval - 5212 + 415) / 830;
diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c
index efee4c59239f..34b9a601ad07 100644
--- a/drivers/hwmon/smsc47m192.c
+++ b/drivers/hwmon/smsc47m192.c
@@ -86,7 +86,7 @@ static inline u8 IN_TO_REG(unsigned long val, int n)
  */
 static inline s8 TEMP_TO_REG(int val)
 {
-	return clamp_val(SCALE(val, 1, 1000), -128000, 127000);
+	return SCALE(clamp_val(val, -128000, 127000), 1, 1000);
 }
 
 static inline int TEMP_FROM_REG(s8 val)
@@ -384,6 +384,8 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	err = kstrtoul(buf, 10, &val);
 	if (err)
 		return err;
+	if (val > 255)
+		return -EINVAL;
 
 	data->vrm = val;
 	return count;
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index de17c5593d97..c5eec0290b37 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -110,6 +110,7 @@ config I2C_I801
 	    Wellsburg (PCH)
 	    Coleto Creek (PCH)
 	    Wildcat Point-LP (PCH)
+	    BayTrail (SOC)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index 843d01268ae9..8873d84e1d4f 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -101,6 +101,7 @@ struct at91_twi_dev {
 	unsigned twi_cwgr_reg;
 	struct at91_twi_pdata *pdata;
 	bool use_dma;
+	bool recv_len_abort;
 	struct at91_twi_dma dma;
 };
 
@@ -210,7 +211,7 @@ static void at91_twi_write_data_dma_callback(void *data)
 	struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
 
 	dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
-			 dev->buf_len, DMA_MEM_TO_DEV);
+			 dev->buf_len, DMA_TO_DEVICE);
 
 	at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
 }
@@ -267,12 +268,24 @@ static void at91_twi_read_next_byte(struct at91_twi_dev *dev)
 	*dev->buf = at91_twi_read(dev, AT91_TWI_RHR) & 0xff;
 	--dev->buf_len;
 
+	/* return if aborting, we only needed to read RHR to clear RXRDY*/
+	if (dev->recv_len_abort)
+		return;
+
 	/* handle I2C_SMBUS_BLOCK_DATA */
 	if (unlikely(dev->msg->flags & I2C_M_RECV_LEN)) {
-		dev->msg->flags &= ~I2C_M_RECV_LEN;
-		dev->buf_len += *dev->buf;
-		dev->msg->len = dev->buf_len + 1;
-		dev_dbg(dev->dev, "received block length %d\n", dev->buf_len);
+		/* ensure length byte is a valid value */
+		if (*dev->buf <= I2C_SMBUS_BLOCK_MAX && *dev->buf > 0) {
+			dev->msg->flags &= ~I2C_M_RECV_LEN;
+			dev->buf_len += *dev->buf;
+			dev->msg->len = dev->buf_len + 1;
+			dev_dbg(dev->dev, "received block length %d\n",
+					 dev->buf_len);
+		} else {
+			/* abort and send the stop by reading one more byte */
+			dev->recv_len_abort = true;
+			dev->buf_len = 1;
+		}
 	}
 
 	/* send stop if second but last byte has been read */
@@ -289,7 +302,7 @@ static void at91_twi_read_data_dma_callback(void *data)
 	struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
 
 	dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
-			 dev->buf_len, DMA_DEV_TO_MEM);
+			 dev->buf_len, DMA_FROM_DEVICE);
 
 	/* The last two bytes have to be read without using dma */
 	dev->buf += dev->buf_len - 2;
@@ -421,8 +434,8 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 		}
 	}
 
-	ret = wait_for_completion_interruptible_timeout(&dev->cmd_complete,
-							dev->adapter.timeout);
+	ret = wait_for_completion_timeout(&dev->cmd_complete,
+					     dev->adapter.timeout);
 	if (ret == 0) {
 		dev_err(dev->dev, "controller timed out\n");
 		at91_init_twi_bus(dev);
@@ -444,6 +457,12 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 		ret = -EIO;
 		goto error;
 	}
+	if (dev->recv_len_abort) {
+		dev_err(dev->dev, "invalid smbus block length recvd\n");
+		ret = -EPROTO;
+		goto error;
+	}
+
 	dev_dbg(dev->dev, "transfer complete\n");
 
 	return 0;
@@ -500,6 +519,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num)
 	dev->buf_len = m_start->len;
 	dev->buf = m_start->buf;
 	dev->msg = m_start;
+	dev->recv_len_abort = false;
 
 	ret = at91_do_twi_transfer(dev);
 
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index af0b5830303d..e3c6a96717fc 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -411,11 +411,9 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop)
 	if (dev->cmd_err & DAVINCI_I2C_STR_NACK) {
 		if (msg->flags & I2C_M_IGNORE_NAK)
 			return msg->len;
-		if (stop) {
-			w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG);
-			w |= DAVINCI_I2C_MDR_STP;
-			davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w);
-		}
+		w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG);
+		w |= DAVINCI_I2C_MDR_STP;
+		davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w);
 		return -EREMOTEIO;
 	}
 	return -EIO;
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index 14c4b30d4ccc..d95b93016b0d 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -417,6 +417,9 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
 	 */
 	dw_writel(dev, msgs[dev->msg_write_idx].addr | ic_tar, DW_IC_TAR);
 
+	/* enforce disabled interrupts (due to HW issues) */
+	i2c_dw_disable_int(dev);
+
 	/* Enable the adapter */
 	__i2c_dw_enable(dev, true);
 
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 349c2d35e792..899f55937ca6 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -60,6 +60,7 @@
   Wellsburg (PCH) MS    0x8d7f     32     hard     yes     yes     yes
   Coleto Creek (PCH)    0x23b0     32     hard     yes     yes     yes
   Wildcat Point-LP (PCH)   0x9ca2     32     hard     yes     yes     yes
+  BayTrail (SOC)        0x0f12     32     hard     yes     yes     yes
 
   Features supported by this driver:
   Software PEC                     no
@@ -161,6 +162,7 @@
 				 STATUS_ERROR_FLAGS)
 
 /* Older devices have their ID defined in <linux/pci_ids.h> */
+#define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS	0x0f12
 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS	0x1c22
 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS	0x1d22
 /* Patsburg also has three 'Integrated Device Function' SMBus controllers */
@@ -822,6 +824,7 @@ static DEFINE_PCI_DEVICE_TABLE(i801_ids) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS2) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_COLETOCREEK_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS) },
 	{ 0, }
 };
 
diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c
index 8ce4f517fc56..6e932d140573 100644
--- a/drivers/i2c/busses/i2c-ismt.c
+++ b/drivers/i2c/busses/i2c-ismt.c
@@ -497,7 +497,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr,
 			desc->wr_len_cmd = dma_size;
 			desc->control |= ISMT_DESC_BLK;
 			priv->dma_buffer[0] = command;
-			memcpy(&priv->dma_buffer[1], &data->block[1], dma_size);
+			memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1);
 		} else {
 			/* Block Read */
 			dev_dbg(dev, "I2C_SMBUS_BLOCK_DATA:  READ\n");
@@ -525,7 +525,7 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr,
 			desc->wr_len_cmd = dma_size;
 			desc->control |= ISMT_DESC_I2C;
 			priv->dma_buffer[0] = command;
-			memcpy(&priv->dma_buffer[1], &data->block[1], dma_size);
+			memcpy(&priv->dma_buffer[1], &data->block[1], dma_size - 1);
 		} else {
 			/* i2c Block Read */
 			dev_dbg(dev, "I2C_SMBUS_I2C_BLOCK_DATA:  READ\n");
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index d52d84937ad3..cf891752cc73 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -748,8 +748,7 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data,
 	}
 	tclk = clk_get_rate(drv_data->clk);
 
-	rc = of_property_read_u32(np, "clock-frequency", &bus_freq);
-	if (rc)
+	if (of_property_read_u32(np, "clock-frequency", &bus_freq))
 		bus_freq = 100000; /* 100kHz by default */
 
 	if (!mv64xxx_find_baud_factors(bus_freq, tclk,
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 90dcc2eaac5f..a6860570391f 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -926,14 +926,12 @@ omap_i2c_isr_thread(int this_irq, void *dev_id)
 		if (stat & OMAP_I2C_STAT_NACK) {
 			err |= OMAP_I2C_STAT_NACK;
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_NACK);
-			break;
 		}
 
 		if (stat & OMAP_I2C_STAT_AL) {
 			dev_err(dev->dev, "Arbitration lost\n");
 			err |= OMAP_I2C_STAT_AL;
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_AL);
-			break;
 		}
 
 		/*
@@ -958,11 +956,13 @@ omap_i2c_isr_thread(int this_irq, void *dev_id)
 			if (dev->fifo_size)
 				num_bytes = dev->buf_len;
 
-			omap_i2c_receive_data(dev, num_bytes, true);
-
-			if (dev->errata & I2C_OMAP_ERRATA_I207)
+			if (dev->errata & I2C_OMAP_ERRATA_I207) {
 				i2c_omap_errata_i207(dev, stat);
+				num_bytes = (omap_i2c_read_reg(dev,
+					OMAP_I2C_BUFSTAT_REG) >> 8) & 0x3F;
+			}
 
+			omap_i2c_receive_data(dev, num_bytes, true);
 			omap_i2c_ack_stat(dev, OMAP_I2C_STAT_RDR);
 			continue;
 		}
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 0282d4d42805..d3c5d6216575 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -561,6 +561,12 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 	ret = -EINVAL;
 	for (i = 0; i < num; i++) {
+		/* This HW can't send STOP after address phase */
+		if (msgs[i].len == 0) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
 		/*-------------- spin lock -----------------*/
 		spin_lock_irqsave(&priv->lock, flags);
 
@@ -625,7 +631,8 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 static u32 rcar_i2c_func(struct i2c_adapter *adap)
 {
-	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+	/* This HW can't do SMBUS_QUICK and NOSTART */
+	return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
 }
 
 static const struct i2c_algorithm rcar_i2c_algo = {
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 684d21e71e4a..93ec37649346 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -1247,10 +1247,10 @@ static int s3c24xx_i2c_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
 
-	i2c->suspended = 0;
 	clk_prepare_enable(i2c->clk);
 	s3c24xx_i2c_init(i2c);
 	clk_disable_unprepare(i2c->clk);
+	i2c->suspended = 0;
 
 	return 0;
 }
diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c
index bfec313492b3..6f039c300141 100644
--- a/drivers/iio/accel/bma180.c
+++ b/drivers/iio/accel/bma180.c
@@ -68,13 +68,13 @@
 /* Defaults values */
 #define BMA180_DEF_PMODE	0
 #define BMA180_DEF_BW		20
-#define BMA180_DEF_SCALE	250
+#define BMA180_DEF_SCALE	2452
 
 /* Available values for sysfs */
 #define BMA180_FLP_FREQ_AVAILABLE \
 	"10 20 40 75 150 300"
 #define BMA180_SCALE_AVAILABLE \
-	"0.000130 0.000190 0.000250 0.000380 0.000500 0.000990 0.001980"
+	"0.001275 0.001863 0.002452 0.003727 0.004903 0.009709 0.019417"
 
 struct bma180_data {
 	struct i2c_client *client;
@@ -94,7 +94,7 @@ enum bma180_axis {
 };
 
 static int bw_table[] = { 10, 20, 40, 75, 150, 300 }; /* Hz */
-static int scale_table[] = { 130, 190, 250, 380, 500, 990, 1980 };
+static int scale_table[] = { 1275, 1863, 2452, 3727, 4903, 9709, 19417 };
 
 static int bma180_get_acc_reg(struct bma180_data *data, enum bma180_axis axis)
 {
@@ -376,6 +376,8 @@ static int bma180_write_raw(struct iio_dev *indio_dev,
 		mutex_unlock(&data->mutex);
 		return ret;
 	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
+		if (val2)
+			return -EINVAL;
 		mutex_lock(&data->mutex);
 		ret = bma180_set_bw(data, val);
 		mutex_unlock(&data->mutex);
@@ -569,7 +571,7 @@ static int bma180_probe(struct i2c_client *client,
 	trig->ops = &bma180_trigger_ops;
 	iio_trigger_set_drvdata(trig, indio_dev);
 	data->trig = trig;
-	indio_dev->trig = trig;
+	indio_dev->trig = iio_trigger_get(trig);
 
 	ret = iio_trigger_register(trig);
 	if (ret)
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index 9a4e0e32a771..eb799a43aef0 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -472,7 +472,7 @@ static int ad_sd_probe_trigger(struct iio_dev *indio_dev)
 		goto error_free_irq;
 
 	/* select default trigger */
-	indio_dev->trig = sigma_delta->trig;
+	indio_dev->trig = iio_trigger_get(sigma_delta->trig);
 
 	return 0;
 
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 5b1aa027c034..e6bf77d1ec08 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -322,12 +322,11 @@ static int at91_adc_channel_init(struct iio_dev *idev)
 	return idev->num_channels;
 }
 
-static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
+static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 					     struct at91_adc_trigger *triggers,
 					     const char *trigger_name)
 {
 	struct at91_adc_state *st = iio_priv(idev);
-	u8 value = 0;
 	int i;
 
 	for (i = 0; i < st->trigger_number; i++) {
@@ -340,15 +339,16 @@ static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 			return -ENOMEM;
 
 		if (strcmp(trigger_name, name) == 0) {
-			value = triggers[i].value;
 			kfree(name);
-			break;
+			if (triggers[i].value == 0)
+				return -EINVAL;
+			return triggers[i].value;
 		}
 
 		kfree(name);
 	}
 
-	return value;
+	return -EINVAL;
 }
 
 static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
@@ -358,14 +358,14 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 	struct iio_buffer *buffer = idev->buffer;
 	struct at91_adc_reg_desc *reg = st->registers;
 	u32 status = at91_adc_readl(st, reg->trigger_register);
-	u8 value;
+	int value;
 	u8 bit;
 
 	value = at91_adc_get_trigger_value_by_name(idev,
 						   st->trigger_list,
 						   idev->trig->name);
-	if (value == 0)
-		return -EINVAL;
+	if (value < 0)
+		return value;
 
 	if (state) {
 		st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL);
@@ -765,14 +765,17 @@ static int at91_adc_probe_pdata(struct at91_adc_state *st,
 	if (!pdata)
 		return -EINVAL;
 
+	st->caps = (struct at91_adc_caps *)
+			platform_get_device_id(pdev)->driver_data;
+
 	st->use_external = pdata->use_external_triggers;
 	st->vref_mv = pdata->vref;
 	st->channels_mask = pdata->channels_used;
-	st->num_channels = pdata->num_channels;
+	st->num_channels = st->caps->num_channels;
 	st->startup_time = pdata->startup_time;
 	st->trigger_number = pdata->trigger_number;
 	st->trigger_list = pdata->trigger_list;
-	st->registers = pdata->registers;
+	st->registers = &st->caps->registers;
 
 	return 0;
 }
@@ -1101,7 +1104,6 @@ static int at91_adc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_OF
 static struct at91_adc_caps at91sam9260_caps = {
 	.calc_startup_ticks = calc_startup_ticks_9260,
 	.num_channels = 4,
@@ -1154,11 +1156,27 @@ static const struct of_device_id at91_adc_dt_ids[] = {
 	{},
 };
 MODULE_DEVICE_TABLE(of, at91_adc_dt_ids);
-#endif
+
+static const struct platform_device_id at91_adc_ids[] = {
+	{
+		.name = "at91sam9260-adc",
+		.driver_data = (unsigned long)&at91sam9260_caps,
+	}, {
+		.name = "at91sam9g45-adc",
+		.driver_data = (unsigned long)&at91sam9g45_caps,
+	}, {
+		.name = "at91sam9x5-adc",
+		.driver_data = (unsigned long)&at91sam9x5_caps,
+	}, {
+		/* terminator */
+	}
+};
+MODULE_DEVICE_TABLE(platform, at91_adc_ids);
 
 static struct platform_driver at91_adc_driver = {
 	.probe = at91_adc_probe,
 	.remove = at91_adc_remove,
+	.id_table = at91_adc_ids,
 	.driver = {
 		   .name = DRIVER_NAME,
 		   .of_match_table = of_match_ptr(at91_adc_dt_ids),
diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index 360259266d4f..ef5ffc0c37a4 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -1258,8 +1258,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1038_channels,
+		.num_channels = ARRAY_SIZE(max1038_channels),
 	},
 	[max11605] = {
 		.bits = 8,
@@ -1268,8 +1268,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1038_channels,
+		.num_channels = ARRAY_SIZE(max1038_channels),
 	},
 	[max11606] = {
 		.bits = 10,
@@ -1318,8 +1318,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1138_channels,
+		.num_channels = ARRAY_SIZE(max1138_channels),
 	},
 	[max11611] = {
 		.bits = 10,
@@ -1328,8 +1328,8 @@ static const struct max1363_chip_info max1363_chip_info_tbl[] = {
 		.num_modes = ARRAY_SIZE(max1238_mode_list),
 		.default_mode = s0to11,
 		.info = &max1238_info,
-		.channels = max1238_channels,
-		.num_channels = ARRAY_SIZE(max1238_channels),
+		.channels = max1138_channels,
+		.num_channels = ARRAY_SIZE(max1138_channels),
 	},
 	[max11612] = {
 		.bits = 12,
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index 31e786e3999b..63b2bb6bdbbc 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -375,7 +375,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 			return -EAGAIN;
 		}
 	}
-	map_val = chan->channel + TOTAL_CHANNELS;
+	map_val = adc_dev->channel_step[chan->scan_index];
 
 	/*
 	 * We check the complete FIFO. We programmed just one entry but in case
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 7dcf83998e6f..1be235b01934 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -99,7 +99,8 @@ int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name,
 		dev_err(&indio_dev->dev, "Trigger Register Failed\n");
 		goto error_free_trig;
 	}
-	indio_dev->trig = attrb->trigger = trig;
+	attrb->trigger = trig;
+	indio_dev->trig = iio_trigger_get(trig);
 
 	return ret;
 
diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c
index 1665c8e4b62b..e18bc6782256 100644
--- a/drivers/iio/common/st_sensors/st_sensors_buffer.c
+++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c
@@ -71,7 +71,7 @@ int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf)
 				goto st_sensors_free_memory;
 			}
 
-			for (i = 0; i < n * num_data_channels; i++) {
+			for (i = 0; i < n * byte_for_channel; i++) {
 				if (i < n)
 					buf[i] = rx_array[i];
 				else
diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c
index 8fc3a97eb266..8d8ca6f1e16a 100644
--- a/drivers/iio/common/st_sensors/st_sensors_trigger.c
+++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c
@@ -49,7 +49,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 		dev_err(&indio_dev->dev, "failed to register iio trigger.\n");
 		goto iio_trigger_register_error;
 	}
-	indio_dev->trig = sdata->trig;
+	indio_dev->trig = iio_trigger_get(sdata->trig);
 
 	return 0;
 
diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c
index e3b3c5084070..eef50e91f17c 100644
--- a/drivers/iio/gyro/itg3200_buffer.c
+++ b/drivers/iio/gyro/itg3200_buffer.c
@@ -132,7 +132,7 @@ int itg3200_probe_trigger(struct iio_dev *indio_dev)
 		goto error_free_irq;
 
 	/* select default trigger */
-	indio_dev->trig = st->trig;
+	indio_dev->trig = iio_trigger_get(st->trig);
 
 	return 0;
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index df7f1e1157ae..27a91768cc72 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -661,6 +661,7 @@ static int inv_mpu_probe(struct i2c_client *client,
 {
 	struct inv_mpu6050_state *st;
 	struct iio_dev *indio_dev;
+	struct inv_mpu6050_platform_data *pdata;
 	int result;
 
 	if (!i2c_check_functionality(client->adapter,
@@ -673,8 +674,10 @@ static int inv_mpu_probe(struct i2c_client *client,
 
 	st = iio_priv(indio_dev);
 	st->client = client;
-	st->plat_data = *(struct inv_mpu6050_platform_data
-				*)dev_get_platdata(&client->dev);
+	pdata = (struct inv_mpu6050_platform_data
+			*)dev_get_platdata(&client->dev);
+	if (pdata)
+		st->plat_data = *pdata;
 	/* power is turned on inside check chip type*/
 	result = inv_check_and_setup_chip(st, id);
 	if (result)
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
index 03b9372c1212..926fccea8de0 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
@@ -135,7 +135,7 @@ int inv_mpu6050_probe_trigger(struct iio_dev *indio_dev)
 	ret = iio_trigger_register(st->trig);
 	if (ret)
 		goto error_free_irq;
-	indio_dev->trig = st->trig;
+	indio_dev->trig = iio_trigger_get(st->trig);
 
 	return 0;
 
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index c67d83bdc8f0..0f1d9b2ccdfa 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -165,7 +165,8 @@ static ssize_t iio_scan_el_show(struct device *dev,
 	int ret;
 	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
 
-	ret = test_bit(to_iio_dev_attr(attr)->address,
+	/* Ensure ret is 0 or 1. */
+	ret = !!test_bit(to_iio_dev_attr(attr)->address,
 		       indio_dev->buffer->scan_mask);
 
 	return sprintf(buf, "%d\n", ret);
@@ -866,7 +867,8 @@ int iio_scan_mask_query(struct iio_dev *indio_dev,
 	if (!buffer->scan_mask)
 		return 0;
 
-	return test_bit(bit, buffer->scan_mask);
+	/* Ensure return value is 0 or 1. */
+	return !!test_bit(bit, buffer->scan_mask);
 };
 EXPORT_SYMBOL_GPL(iio_scan_mask_query);
 
@@ -951,7 +953,7 @@ static int iio_buffer_update_demux(struct iio_dev *indio_dev,
 
 	/* Now we have the two masks, work from least sig and build up sizes */
 	for_each_set_bit(out_ind,
-			 indio_dev->active_scan_mask,
+			 buffer->scan_mask,
 			 indio_dev->masklength) {
 		in_ind = find_next_bit(indio_dev->active_scan_mask,
 				       indio_dev->masklength,
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index c9c1419fe6e0..f9360f497ed4 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -343,6 +343,9 @@ static int iio_device_add_event(struct iio_dev *indio_dev,
 			&indio_dev->event_interface->dev_attr_list);
 		kfree(postfix);
 
+		if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE))
+			continue;
+
 		if (ret)
 			return ret;
 
diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index 0cf5f8e06cfc..4fc88e617acf 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -178,12 +178,12 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np,
 			index = of_property_match_string(np, "io-channel-names",
 							 name);
 		chan = of_iio_channel_get(np, index);
-		if (!IS_ERR(chan))
+		if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
 			break;
 		else if (name && index >= 0) {
 			pr_err("ERROR: could not get IIO channel %s:%s(%i)\n",
 				np->full_name, name ? name : "", index);
-			return chan;
+			return NULL;
 		}
 
 		/*
@@ -193,8 +193,9 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np,
 		 */
 		np = np->parent;
 		if (np && !of_get_property(np, "io-channel-ranges", NULL))
-			break;
+			return NULL;
 	}
+
 	return chan;
 }
 
@@ -317,6 +318,7 @@ struct iio_channel *iio_channel_get(struct device *dev,
 		if (channel != NULL)
 			return channel;
 	}
+
 	return iio_channel_get_sys(name, channel_name);
 }
 EXPORT_SYMBOL_GPL(iio_channel_get);
diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c
index 47a6dbac2d0c..d976e6ce60db 100644
--- a/drivers/iio/light/cm32181.c
+++ b/drivers/iio/light/cm32181.c
@@ -221,6 +221,7 @@ static int cm32181_read_raw(struct iio_dev *indio_dev,
 		*val = cm32181->calibscale;
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_INT_TIME:
+		*val = 0;
 		ret = cm32181_read_als_it(cm32181, val2);
 		return ret;
 	}
diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c
index a45e07492db3..39fc67e82138 100644
--- a/drivers/iio/light/cm36651.c
+++ b/drivers/iio/light/cm36651.c
@@ -652,7 +652,19 @@ static int cm36651_probe(struct i2c_client *client,
 	cm36651->client = client;
 	cm36651->ps_client = i2c_new_dummy(client->adapter,
 						     CM36651_I2C_ADDR_PS);
+	if (!cm36651->ps_client) {
+		dev_err(&client->dev, "%s: new i2c device failed\n", __func__);
+		ret = -ENODEV;
+		goto error_disable_reg;
+	}
+
 	cm36651->ara_client = i2c_new_dummy(client->adapter, CM36651_ARA);
+	if (!cm36651->ara_client) {
+		dev_err(&client->dev, "%s: new i2c device failed\n", __func__);
+		ret = -ENODEV;
+		goto error_i2c_unregister_ps;
+	}
+
 	mutex_init(&cm36651->lock);
 	indio_dev->dev.parent = &client->dev;
 	indio_dev->channels = cm36651_channels;
@@ -664,7 +676,7 @@ static int cm36651_probe(struct i2c_client *client,
 	ret = cm36651_setup_reg(cm36651);
 	if (ret) {
 		dev_err(&client->dev, "%s: register setup failed\n", __func__);
-		goto error_disable_reg;
+		goto error_i2c_unregister_ara;
 	}
 
 	ret = request_threaded_irq(client->irq, NULL, cm36651_irq_handler,
@@ -672,7 +684,7 @@ static int cm36651_probe(struct i2c_client *client,
 							"cm36651", indio_dev);
 	if (ret) {
 		dev_err(&client->dev, "%s: request irq failed\n", __func__);
-		goto error_disable_reg;
+		goto error_i2c_unregister_ara;
 	}
 
 	ret = iio_device_register(indio_dev);
@@ -685,6 +697,10 @@ static int cm36651_probe(struct i2c_client *client,
 
 error_free_irq:
 	free_irq(client->irq, indio_dev);
+error_i2c_unregister_ara:
+	i2c_unregister_device(cm36651->ara_client);
+error_i2c_unregister_ps:
+	i2c_unregister_device(cm36651->ps_client);
 error_disable_reg:
 	regulator_disable(cm36651->vled_reg);
 	return ret;
@@ -698,6 +714,8 @@ static int cm36651_remove(struct i2c_client *client)
 	iio_device_unregister(indio_dev);
 	regulator_disable(cm36651->vled_reg);
 	free_irq(client->irq, indio_dev);
+	i2c_unregister_device(cm36651->ps_client);
+	i2c_unregister_device(cm36651->ara_client);
 
 	return 0;
 }
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 05423543f89d..053117c02bbc 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -352,8 +352,6 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 {
 	struct ak8975_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	u16 meas_reg;
-	s16 raw;
 	int ret;
 
 	mutex_lock(&data->lock);
@@ -401,16 +399,11 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 		dev_err(&client->dev, "Read axis data fails\n");
 		goto exit;
 	}
-	meas_reg = ret;
 
 	mutex_unlock(&data->lock);
 
-	/* Endian conversion of the measured values. */
-	raw = (s16) (le16_to_cpu(meas_reg));
-
 	/* Clamp to valid range. */
-	raw = clamp_t(s16, raw, -4096, 4095);
-	*val = raw;
+	*val = clamp_t(s16, ret, -4096, 4095);
 	return IIO_VAL_INT;
 
 exit:
diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c
index 52bbcfa1e077..476aa132a192 100644
--- a/drivers/iio/magnetometer/st_magn_core.c
+++ b/drivers/iio/magnetometer/st_magn_core.c
@@ -42,7 +42,8 @@
 #define ST_MAGN_FS_AVL_5600MG			5600
 #define ST_MAGN_FS_AVL_8000MG			8000
 #define ST_MAGN_FS_AVL_8100MG			8100
-#define ST_MAGN_FS_AVL_10000MG			10000
+#define ST_MAGN_FS_AVL_12000MG			12000
+#define ST_MAGN_FS_AVL_16000MG			16000
 
 /* CUSTOM VALUES FOR SENSOR 1 */
 #define ST_MAGN_1_WAI_EXP			0x3c
@@ -69,20 +70,20 @@
 #define ST_MAGN_1_FS_AVL_4700_VAL		0x05
 #define ST_MAGN_1_FS_AVL_5600_VAL		0x06
 #define ST_MAGN_1_FS_AVL_8100_VAL		0x07
-#define ST_MAGN_1_FS_AVL_1300_GAIN_XY		1100
-#define ST_MAGN_1_FS_AVL_1900_GAIN_XY		855
-#define ST_MAGN_1_FS_AVL_2500_GAIN_XY		670
-#define ST_MAGN_1_FS_AVL_4000_GAIN_XY		450
-#define ST_MAGN_1_FS_AVL_4700_GAIN_XY		400
-#define ST_MAGN_1_FS_AVL_5600_GAIN_XY		330
-#define ST_MAGN_1_FS_AVL_8100_GAIN_XY		230
-#define ST_MAGN_1_FS_AVL_1300_GAIN_Z		980
-#define ST_MAGN_1_FS_AVL_1900_GAIN_Z		760
-#define ST_MAGN_1_FS_AVL_2500_GAIN_Z		600
-#define ST_MAGN_1_FS_AVL_4000_GAIN_Z		400
-#define ST_MAGN_1_FS_AVL_4700_GAIN_Z		355
-#define ST_MAGN_1_FS_AVL_5600_GAIN_Z		295
-#define ST_MAGN_1_FS_AVL_8100_GAIN_Z		205
+#define ST_MAGN_1_FS_AVL_1300_GAIN_XY		909
+#define ST_MAGN_1_FS_AVL_1900_GAIN_XY		1169
+#define ST_MAGN_1_FS_AVL_2500_GAIN_XY		1492
+#define ST_MAGN_1_FS_AVL_4000_GAIN_XY		2222
+#define ST_MAGN_1_FS_AVL_4700_GAIN_XY		2500
+#define ST_MAGN_1_FS_AVL_5600_GAIN_XY		3030
+#define ST_MAGN_1_FS_AVL_8100_GAIN_XY		4347
+#define ST_MAGN_1_FS_AVL_1300_GAIN_Z		1020
+#define ST_MAGN_1_FS_AVL_1900_GAIN_Z		1315
+#define ST_MAGN_1_FS_AVL_2500_GAIN_Z		1666
+#define ST_MAGN_1_FS_AVL_4000_GAIN_Z		2500
+#define ST_MAGN_1_FS_AVL_4700_GAIN_Z		2816
+#define ST_MAGN_1_FS_AVL_5600_GAIN_Z		3389
+#define ST_MAGN_1_FS_AVL_8100_GAIN_Z		4878
 #define ST_MAGN_1_MULTIREAD_BIT			false
 
 /* CUSTOM VALUES FOR SENSOR 2 */
@@ -105,10 +106,12 @@
 #define ST_MAGN_2_FS_MASK			0x60
 #define ST_MAGN_2_FS_AVL_4000_VAL		0x00
 #define ST_MAGN_2_FS_AVL_8000_VAL		0x01
-#define ST_MAGN_2_FS_AVL_10000_VAL		0x02
-#define ST_MAGN_2_FS_AVL_4000_GAIN		430
-#define ST_MAGN_2_FS_AVL_8000_GAIN		230
-#define ST_MAGN_2_FS_AVL_10000_GAIN		230
+#define ST_MAGN_2_FS_AVL_12000_VAL		0x02
+#define ST_MAGN_2_FS_AVL_16000_VAL		0x03
+#define ST_MAGN_2_FS_AVL_4000_GAIN		146
+#define ST_MAGN_2_FS_AVL_8000_GAIN		292
+#define ST_MAGN_2_FS_AVL_12000_GAIN		438
+#define ST_MAGN_2_FS_AVL_16000_GAIN		584
 #define ST_MAGN_2_MULTIREAD_BIT			false
 #define ST_MAGN_2_OUT_X_L_ADDR			0x28
 #define ST_MAGN_2_OUT_Y_L_ADDR			0x2a
@@ -266,9 +269,14 @@ static const struct st_sensors st_magn_sensors[] = {
 					.gain = ST_MAGN_2_FS_AVL_8000_GAIN,
 				},
 				[2] = {
-					.num = ST_MAGN_FS_AVL_10000MG,
-					.value = ST_MAGN_2_FS_AVL_10000_VAL,
-					.gain = ST_MAGN_2_FS_AVL_10000_GAIN,
+					.num = ST_MAGN_FS_AVL_12000MG,
+					.value = ST_MAGN_2_FS_AVL_12000_VAL,
+					.gain = ST_MAGN_2_FS_AVL_12000_GAIN,
+				},
+				[3] = {
+					.num = ST_MAGN_FS_AVL_16000MG,
+					.value = ST_MAGN_2_FS_AVL_16000_VAL,
+					.gain = ST_MAGN_2_FS_AVL_16000_GAIN,
 				},
 			},
 		},
diff --git a/drivers/iio/pressure/mpl3115.c b/drivers/iio/pressure/mpl3115.c
index ac8c8ab723e5..fe53669eeeeb 100644
--- a/drivers/iio/pressure/mpl3115.c
+++ b/drivers/iio/pressure/mpl3115.c
@@ -98,7 +98,7 @@ static int mpl3115_read_raw(struct iio_dev *indio_dev,
 			mutex_unlock(&data->lock);
 			if (ret < 0)
 				return ret;
-			*val = sign_extend32(be32_to_cpu(tmp) >> 12, 23);
+			*val = be32_to_cpu(tmp) >> 12;
 			return IIO_VAL_INT;
 		case IIO_TEMP: /* in 0.0625 celsius / LSB */
 			mutex_lock(&data->lock);
@@ -112,7 +112,7 @@ static int mpl3115_read_raw(struct iio_dev *indio_dev,
 			mutex_unlock(&data->lock);
 			if (ret < 0)
 				return ret;
-			*val = sign_extend32(be32_to_cpu(tmp) >> 20, 15);
+			*val = sign_extend32(be32_to_cpu(tmp) >> 20, 11);
 			return IIO_VAL_INT;
 		default:
 			return -EINVAL;
@@ -185,7 +185,7 @@ static const struct iio_chan_spec mpl3115_channels[] = {
 			BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index = 0,
 		.scan_type = {
-			.sign = 's',
+			.sign = 'u',
 			.realbits = 20,
 			.storagebits = 32,
 			.shift = 12,
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 0601b9daf840..c3239170d8b7 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -349,23 +349,6 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
 			   grh, &av->ah_attr);
 }
 
-int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac)
-{
-	struct cm_id_private *cm_id_priv;
-
-	cm_id_priv = container_of(id, struct cm_id_private, id);
-
-	if (smac != NULL)
-		memcpy(cm_id_priv->av.smac, smac, sizeof(cm_id_priv->av.smac));
-
-	if (alt_smac != NULL)
-		memcpy(cm_id_priv->alt_av.smac, alt_smac,
-		       sizeof(cm_id_priv->alt_av.smac));
-
-	return 0;
-}
-EXPORT_SYMBOL(ib_update_cm_av);
-
 static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
 {
 	struct cm_device *cm_dev;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 199958d9ddc8..42c3058e6e9c 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1284,15 +1284,6 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	struct rdma_id_private *listen_id, *conn_id;
 	struct rdma_cm_event event;
 	int offset, ret;
-	u8 smac[ETH_ALEN];
-	u8 alt_smac[ETH_ALEN];
-	u8 *psmac = smac;
-	u8 *palt_smac = alt_smac;
-	int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) ==
-			RDMA_TRANSPORT_IB) &&
-		       (rdma_port_get_link_layer(cm_id->device,
-			ib_event->param.req_rcvd.port) ==
-			IB_LINK_LAYER_ETHERNET));
 
 	listen_id = cm_id->context;
 	if (!cma_check_req_qp_type(&listen_id->id, ib_event))
@@ -1336,28 +1327,11 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	ret = conn_id->id.event_handler(&conn_id->id, &event);
 	if (ret)
 		goto err3;
-
-	if (is_iboe) {
-		if (ib_event->param.req_rcvd.primary_path != NULL)
-			rdma_addr_find_smac_by_sgid(
-				&ib_event->param.req_rcvd.primary_path->sgid,
-				psmac, NULL);
-		else
-			psmac = NULL;
-		if (ib_event->param.req_rcvd.alternate_path != NULL)
-			rdma_addr_find_smac_by_sgid(
-				&ib_event->param.req_rcvd.alternate_path->sgid,
-				palt_smac, NULL);
-		else
-			palt_smac = NULL;
-	}
 	/*
 	 * Acquire mutex to prevent user executing rdma_destroy_id()
 	 * while we're accessing the cm_id.
 	 */
 	mutex_lock(&lock);
-	if (is_iboe)
-		ib_update_cm_av(cm_id, psmac, palt_smac);
 	if (cma_comp(conn_id, RDMA_CM_CONNECT) &&
 	    (conn_id->id.qp_type != IB_QPT_UD))
 		ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 3d2e489ab732..ff9163dc1596 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -46,6 +46,7 @@
 #include <linux/completion.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/sysctl.h>
 
 #include <rdma/iw_cm.h>
 #include <rdma/ib_addr.h>
@@ -65,6 +66,20 @@ struct iwcm_work {
 	struct list_head free_list;
 };
 
+static unsigned int default_backlog = 256;
+
+static struct ctl_table_header *iwcm_ctl_table_hdr;
+static struct ctl_table iwcm_ctl_table[] = {
+	{
+		.procname	= "default_backlog",
+		.data		= &default_backlog,
+		.maxlen		= sizeof(default_backlog),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{ }
+};
+
 /*
  * The following services provide a mechanism for pre-allocating iwcm_work
  * elements.  The design pre-allocates them  based on the cm_id type:
@@ -425,6 +440,9 @@ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog)
 
 	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
 
+	if (!backlog)
+		backlog = default_backlog;
+
 	ret = alloc_work_entries(cm_id_priv, backlog);
 	if (ret)
 		return ret;
@@ -1030,11 +1048,20 @@ static int __init iw_cm_init(void)
 	if (!iwcm_wq)
 		return -ENOMEM;
 
+	iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm",
+						 iwcm_ctl_table);
+	if (!iwcm_ctl_table_hdr) {
+		pr_err("iw_cm: couldn't register sysctl paths\n");
+		destroy_workqueue(iwcm_wq);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
 static void __exit iw_cm_cleanup(void)
 {
+	unregister_net_sysctl_table(iwcm_ctl_table_hdr);
 	destroy_workqueue(iwcm_wq);
 }
 
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index f0d588f8859e..1acb99100556 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -98,7 +98,7 @@ struct ib_umad_port {
 
 struct ib_umad_device {
 	int                  start_port, end_port;
-	struct kref          ref;
+	struct kobject       kobj;
 	struct ib_umad_port  port[0];
 };
 
@@ -134,14 +134,18 @@ static DECLARE_BITMAP(dev_map, IB_UMAD_MAX_PORTS);
 static void ib_umad_add_one(struct ib_device *device);
 static void ib_umad_remove_one(struct ib_device *device);
 
-static void ib_umad_release_dev(struct kref *ref)
+static void ib_umad_release_dev(struct kobject *kobj)
 {
 	struct ib_umad_device *dev =
-		container_of(ref, struct ib_umad_device, ref);
+		container_of(kobj, struct ib_umad_device, kobj);
 
 	kfree(dev);
 }
 
+static struct kobj_type ib_umad_dev_ktype = {
+	.release = ib_umad_release_dev,
+};
+
 static int hdr_size(struct ib_umad_file *file)
 {
 	return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) :
@@ -780,27 +784,19 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 {
 	struct ib_umad_port *port;
 	struct ib_umad_file *file;
-	int ret;
+	int ret = -ENXIO;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	mutex_lock(&port->file_mutex);
 
-	if (!port->ib_dev) {
-		ret = -ENXIO;
+	if (!port->ib_dev)
 		goto out;
-	}
 
+	ret = -ENOMEM;
 	file = kzalloc(sizeof *file, GFP_KERNEL);
-	if (!file) {
-		kref_put(&port->umad_dev->ref, ib_umad_release_dev);
-		ret = -ENOMEM;
+	if (!file)
 		goto out;
-	}
 
 	mutex_init(&file->mutex);
 	spin_lock_init(&file->send_lock);
@@ -814,6 +810,13 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 	list_add_tail(&file->port_list, &port->file_list);
 
 	ret = nonseekable_open(inode, filp);
+	if (ret) {
+		list_del(&file->port_list);
+		kfree(file);
+		goto out;
+	}
+
+	kobject_get(&port->umad_dev->kobj);
 
 out:
 	mutex_unlock(&port->file_mutex);
@@ -852,7 +855,7 @@ static int ib_umad_close(struct inode *inode, struct file *filp)
 	mutex_unlock(&file->port->file_mutex);
 
 	kfree(file);
-	kref_put(&dev->ref, ib_umad_release_dev);
+	kobject_put(&dev->kobj);
 
 	return 0;
 }
@@ -880,10 +883,6 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	int ret;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	if (filp->f_flags & O_NONBLOCK) {
 		if (down_trylock(&port->sm_sem)) {
@@ -898,17 +897,27 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	}
 
 	ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
-	if (ret) {
-		up(&port->sm_sem);
-		goto fail;
-	}
+	if (ret)
+		goto err_up_sem;
 
 	filp->private_data = port;
 
-	return nonseekable_open(inode, filp);
+	ret = nonseekable_open(inode, filp);
+	if (ret)
+		goto err_clr_sm_cap;
+
+	kobject_get(&port->umad_dev->kobj);
+
+	return 0;
+
+err_clr_sm_cap:
+	swap(props.set_port_cap_mask, props.clr_port_cap_mask);
+	ib_modify_port(port->ib_dev, port->port_num, 0, &props);
+
+err_up_sem:
+	up(&port->sm_sem);
 
 fail:
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
 	return ret;
 }
 
@@ -927,7 +936,7 @@ static int ib_umad_sm_close(struct inode *inode, struct file *filp)
 
 	up(&port->sm_sem);
 
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&port->umad_dev->kobj);
 
 	return ret;
 }
@@ -995,6 +1004,7 @@ static int find_overflow_devnum(void)
 }
 
 static int ib_umad_init_port(struct ib_device *device, int port_num,
+			     struct ib_umad_device *umad_dev,
 			     struct ib_umad_port *port)
 {
 	int devnum;
@@ -1027,6 +1037,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 
 	cdev_init(&port->cdev, &umad_fops);
 	port->cdev.owner = THIS_MODULE;
+	port->cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->cdev.kobj, "umad%d", port->dev_num);
 	if (cdev_add(&port->cdev, base, 1))
 		goto err_cdev;
@@ -1045,6 +1056,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 	base += IB_UMAD_MAX_PORTS;
 	cdev_init(&port->sm_cdev, &umad_sm_fops);
 	port->sm_cdev.owner = THIS_MODULE;
+	port->sm_cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->sm_cdev.kobj, "issm%d", port->dev_num);
 	if (cdev_add(&port->sm_cdev, base, 1))
 		goto err_sm_cdev;
@@ -1138,7 +1150,7 @@ static void ib_umad_add_one(struct ib_device *device)
 	if (!umad_dev)
 		return;
 
-	kref_init(&umad_dev->ref);
+	kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype);
 
 	umad_dev->start_port = s;
 	umad_dev->end_port   = e;
@@ -1146,7 +1158,8 @@ static void ib_umad_add_one(struct ib_device *device)
 	for (i = s; i <= e; ++i) {
 		umad_dev->port[i - s].umad_dev = umad_dev;
 
-		if (ib_umad_init_port(device, i, &umad_dev->port[i - s]))
+		if (ib_umad_init_port(device, i, umad_dev,
+				      &umad_dev->port[i - s]))
 			goto err;
 	}
 
@@ -1158,7 +1171,7 @@ err:
 	while (--i >= s)
 		ib_umad_kill_port(&umad_dev->port[i - s]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static void ib_umad_remove_one(struct ib_device *device)
@@ -1172,7 +1185,7 @@ static void ib_umad_remove_one(struct ib_device *device)
 	for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
 		ib_umad_kill_port(&umad_dev->port[i]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static char *umad_devnode(struct device *dev, umode_t *mode)
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index ea6203ee7bcc..23467a2abd62 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2425,6 +2425,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	attr.grh.sgid_index    = cmd.attr.grh.sgid_index;
 	attr.grh.hop_limit     = cmd.attr.grh.hop_limit;
 	attr.grh.traffic_class = cmd.attr.grh.traffic_class;
+	attr.vlan_id           = 0;
+	memset(&attr.dmac, 0, sizeof(attr.dmac));
 	memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16);
 
 	ah = ib_create_ah(pd, &attr);
diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c
index e7bee46868d1..abd97247443e 100644
--- a/drivers/infiniband/core/uverbs_marshall.c
+++ b/drivers/infiniband/core/uverbs_marshall.c
@@ -140,5 +140,9 @@ void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst,
 	dst->packet_life_time	= src->packet_life_time;
 	dst->preference		= src->preference;
 	dst->packet_life_time_selector = src->packet_life_time_selector;
+
+	memset(dst->smac, 0, sizeof(dst->smac));
+	memset(dst->dmac, 0, sizeof(dst->dmac));
+	dst->vlan_id = 0xffff;
 }
 EXPORT_SYMBOL(ib_copy_path_rec_from_user);
diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c
index 212150c25ea0..8cc837537768 100644
--- a/drivers/infiniband/hw/ehca/ehca_cq.c
+++ b/drivers/infiniband/hw/ehca/ehca_cq.c
@@ -283,6 +283,7 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
 			(my_cq->galpas.user.fw_handle & (PAGE_SIZE - 1));
 		if (ib_copy_to_udata(udata, &resp, sizeof(resp))) {
 			ehca_err(device, "Copy to udata failed.");
+			cq = ERR_PTR(-EFAULT);
 			goto create_cq_exit4;
 		}
 	}
diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index 714293b78518..45802e97332e 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -326,7 +326,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 				   size_t count, loff_t *off)
 {
 	u32 __iomem *piobuf;
-	u32 plen, clen, pbufn;
+	u32 plen, pbufn, maxlen_reserve;
 	struct ipath_diag_pkt odp;
 	struct ipath_diag_xpkt dp;
 	u32 *tmpbuf = NULL;
@@ -335,42 +335,24 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 	u64 val;
 	u32 l_state, lt_state; /* LinkState, LinkTrainingState */
 
-	if (count < sizeof(odp)) {
-		ret = -EINVAL;
-		goto bail;
-	}
 
 	if (count == sizeof(dp)) {
 		if (copy_from_user(&dp, data, sizeof(dp))) {
 			ret = -EFAULT;
 			goto bail;
 		}
-	} else if (copy_from_user(&odp, data, sizeof(odp))) {
-		ret = -EFAULT;
-		goto bail;
-	}
-
-	/*
-	 * Due to padding/alignment issues (lessened with new struct)
-	 * the old and new structs are the same length. We need to
-	 * disambiguate them, which we can do because odp.len has never
-	 * been less than the total of LRH+BTH+DETH so far, while
-	 * dp.unit (same offset) unit is unlikely to get that high.
-	 * Similarly, dp.data, the pointer to user at the same offset
-	 * as odp.unit, is almost certainly at least one (512byte)page
-	 * "above" NULL. The if-block below can be omitted if compatibility
-	 * between a new driver and older diagnostic code is unimportant.
-	 * compatibility the other direction (new diags, old driver) is
-	 * handled in the diagnostic code, with a warning.
-	 */
-	if (dp.unit >= 20 && dp.data < 512) {
-		/* very probable version mismatch. Fix it up */
-		memcpy(&odp, &dp, sizeof(odp));
-		/* We got a legacy dp, copy elements to dp */
+	} else if (count == sizeof(odp)) {
+		if (copy_from_user(&odp, data, sizeof(odp))) {
+			ret = -EFAULT;
+			goto bail;
+		}
+		dp.len = odp.len;
 		dp.unit = odp.unit;
 		dp.data = odp.data;
-		dp.len = odp.len;
-		dp.pbc_wd = 0; /* Indicate we need to compute PBC wd */
+		dp.pbc_wd = 0;
+	} else {
+		ret = -EINVAL;
+		goto bail;
 	}
 
 	/* send count must be an exact number of dwords */
@@ -379,7 +361,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 		goto bail;
 	}
 
-	clen = dp.len >> 2;
+	plen = dp.len >> 2;
 
 	dd = ipath_lookup(dp.unit);
 	if (!dd || !(dd->ipath_flags & IPATH_PRESENT) ||
@@ -422,16 +404,22 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 		goto bail;
 	}
 
-	/* need total length before first word written */
-	/* +1 word is for the qword padding */
-	plen = sizeof(u32) + dp.len;
-
-	if ((plen + 4) > dd->ipath_ibmaxlen) {
+	/*
+	 * need total length before first word written, plus 2 Dwords. One Dword
+	 * is for padding so we get the full user data when not aligned on
+	 * a word boundary. The other Dword is to make sure we have room for the
+	 * ICRC which gets tacked on later.
+	 */
+	maxlen_reserve = 2 * sizeof(u32);
+	if (dp.len > dd->ipath_ibmaxlen - maxlen_reserve) {
 		ipath_dbg("Pkt len 0x%x > ibmaxlen %x\n",
-			  plen - 4, dd->ipath_ibmaxlen);
+			  dp.len, dd->ipath_ibmaxlen);
 		ret = -EINVAL;
-		goto bail;	/* before writing pbc */
+		goto bail;
 	}
+
+	plen = sizeof(u32) + dp.len;
+
 	tmpbuf = vmalloc(plen);
 	if (!tmpbuf) {
 		dev_info(&dd->pcidev->dev, "Unable to allocate tmp buffer, "
@@ -473,11 +461,11 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 	 */
 	if (dd->ipath_flags & IPATH_PIO_FLUSH_WC) {
 		ipath_flush_wc();
-		__iowrite32_copy(piobuf + 2, tmpbuf, clen - 1);
+		__iowrite32_copy(piobuf + 2, tmpbuf, plen - 1);
 		ipath_flush_wc();
-		__raw_writel(tmpbuf[clen - 1], piobuf + clen + 1);
+		__raw_writel(tmpbuf[plen - 1], piobuf + plen + 1);
 	} else
-		__iowrite32_copy(piobuf + 2, tmpbuf, clen);
+		__iowrite32_copy(piobuf + 2, tmpbuf, plen);
 
 	ipath_flush_wc();
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index f9c12e92fdd6..11f0606792bb 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1622,6 +1622,7 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev,
 	struct inet6_dev *in6_dev;
 	union ib_gid  *pgid;
 	struct inet6_ifaddr *ifp;
+	union ib_gid default_gid;
 #endif
 	union ib_gid gid;
 
@@ -1642,12 +1643,15 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev,
 		in_dev_put(in_dev);
 	}
 #if IS_ENABLED(CONFIG_IPV6)
+	mlx4_make_default_gid(dev, &default_gid);
 	/* IPv6 gids */
 	in6_dev = in6_dev_get(dev);
 	if (in6_dev) {
 		read_lock_bh(&in6_dev->lock);
 		list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
 			pgid = (union ib_gid *)&ifp->addr;
+			if (!memcmp(pgid, &default_gid, sizeof(*pgid)))
+				continue;
 			update_gid_table(ibdev, port, pgid, 0, 0);
 		}
 		read_unlock_bh(&in6_dev->lock);
@@ -1723,31 +1727,34 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev)
 			port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ?
 						IB_PORT_ACTIVE : IB_PORT_DOWN;
 			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
-		} else {
-			reset_gid_table(ibdev, port);
-		}
-		/* if using bonding/team and a slave port is down, we don't the bond IP
-		 * based gids in the table since flows that select port by gid may get
-		 * the down port.
-		 */
-		if (curr_master && (port_state == IB_PORT_DOWN)) {
-			reset_gid_table(ibdev, port);
-			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
-		}
-		/* if bonding is used it is possible that we add it to masters
-		 * only after IP address is assigned to the net bonding
-		 * interface.
-		*/
-		if (curr_master && (old_master != curr_master)) {
-			reset_gid_table(ibdev, port);
-			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
-			mlx4_ib_get_dev_addr(curr_master, ibdev, port);
-		}
+			/* if using bonding/team and a slave port is down, we
+			 * don't the bond IP based gids in the table since
+			 * flows that select port by gid may get the down port.
+			 */
+			if (curr_master && (port_state == IB_PORT_DOWN)) {
+				reset_gid_table(ibdev, port);
+				mlx4_ib_set_default_gid(ibdev,
+							curr_netdev, port);
+			}
+			/* if bonding is used it is possible that we add it to
+			 * masters only after IP address is assigned to the
+			 * net bonding interface.
+			*/
+			if (curr_master && (old_master != curr_master)) {
+				reset_gid_table(ibdev, port);
+				mlx4_ib_set_default_gid(ibdev,
+							curr_netdev, port);
+				mlx4_ib_get_dev_addr(curr_master, ibdev, port);
+			}
 
-		if (!curr_master && (old_master != curr_master)) {
+			if (!curr_master && (old_master != curr_master)) {
+				reset_gid_table(ibdev, port);
+				mlx4_ib_set_default_gid(ibdev,
+							curr_netdev, port);
+				mlx4_ib_get_dev_addr(curr_netdev, ibdev, port);
+			}
+		} else {
 			reset_gid_table(ibdev, port);
-			mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
-			mlx4_ib_get_dev_addr(curr_netdev, ibdev, port);
 		}
 	}
 
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index b1705ce6eb88..8c726f183980 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -32,6 +32,7 @@
 
 #include <linux/kref.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
 #include "mlx5_ib.h"
 #include "user.h"
 
@@ -540,14 +541,24 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  int *cqe_size, int *index, int *inlen)
 {
 	struct mlx5_ib_create_cq ucmd;
+	size_t ucmdlen;
 	int page_shift;
 	int npages;
 	int ncont;
 	int err;
 
-	if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)))
+	ucmdlen =
+		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+		 sizeof(ucmd)) ? (sizeof(ucmd) -
+				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+
+	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
 		return -EFAULT;
 
+	if (ucmdlen == sizeof(ucmd) &&
+	    ucmd.reserved != 0)
+		return -EINVAL;
+
 	if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128)
 		return -EINVAL;
 
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 210b3eaf188a..384af6dec5eb 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -35,6 +35,7 @@
 #include <linux/mlx5/srq.h>
 #include <linux/slab.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
 
 #include "mlx5_ib.h"
 #include "user.h"
@@ -78,16 +79,27 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct mlx5_ib_create_srq ucmd;
+	size_t ucmdlen;
 	int err;
 	int npages;
 	int page_shift;
 	int ncont;
 	u32 offset;
 
-	if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
+	ucmdlen =
+		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+		 sizeof(ucmd)) ? (sizeof(ucmd) -
+				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+
+	if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) {
 		mlx5_ib_dbg(dev, "failed copy udata\n");
 		return -EFAULT;
 	}
+
+	if (ucmdlen == sizeof(ucmd) &&
+	    ucmd.reserved != 0)
+		return -EINVAL;
+
 	srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE);
 
 	srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, buf_size,
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index 0f4f8e42a17f..d0ba264ac1ed 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -91,6 +91,7 @@ struct mlx5_ib_create_cq {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u32	cqe_size;
+	__u32	reserved; /* explicit padding (optional on i386) */
 };
 
 struct mlx5_ib_create_cq_resp {
@@ -109,6 +110,7 @@ struct mlx5_ib_create_srq {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u32	flags;
+	__u32	reserved; /* explicit padding (optional on i386) */
 };
 
 struct mlx5_ib_create_srq_resp {
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 5b71d43bd89c..42dde06fdb91 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -695,6 +695,7 @@ static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries,
 
 	if (context && ib_copy_to_udata(udata, &cq->cqn, sizeof (__u32))) {
 		mthca_free_cq(to_mdev(ibdev), cq);
+		err = -EFAULT;
 		goto err_free;
 	}
 
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 8308e3634767..eb624611f94b 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1186,7 +1186,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd,
 					nes_free_resource(nesadapter, nesadapter->allocated_qps, qp_num);
 					kfree(nesqp->allocated_buffer);
 					nes_debug(NES_DBG_QP, "ib_copy_from_udata() Failed \n");
-					return NULL;
+					return ERR_PTR(-EFAULT);
 				}
 				if (req.user_wqe_buffers) {
 					virt_wqs = 1;
diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c
index 799a0c3bffc4..6abd3ed3cd51 100644
--- a/drivers/infiniband/hw/qib/qib_debugfs.c
+++ b/drivers/infiniband/hw/qib/qib_debugfs.c
@@ -193,6 +193,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
 	struct qib_qp_iter *iter;
 	loff_t n = *pos;
 
+	rcu_read_lock();
 	iter = qib_qp_iter_init(s->private);
 	if (!iter)
 		return NULL;
@@ -224,7 +225,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr,
 
 static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr)
 {
-	/* nothing for now */
+	rcu_read_unlock();
 }
 
 static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr)
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 275f247f9fca..2023cd61b897 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -1578,7 +1578,7 @@ static int do_qib_user_sdma_queue_create(struct file *fp)
 	struct qib_ctxtdata *rcd = fd->rcd;
 	struct qib_devdata *dd = rcd->dd;
 
-	if (dd->flags & QIB_HAS_SEND_DMA)
+	if (dd->flags & QIB_HAS_SEND_DMA) {
 
 		fd->pq = qib_user_sdma_queue_create(&dd->pcidev->dev,
 						    dd->unit,
@@ -1586,6 +1586,7 @@ static int do_qib_user_sdma_queue_create(struct file *fp)
 						    fd->subctxt);
 		if (!fd->pq)
 			return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 24e802f4ea2f..76c3e177164d 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -1097,14 +1097,10 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra)
 	int ret;
 
 	dd = (struct qib_devdata *) ib_alloc_device(sizeof(*dd) + extra);
-	if (!dd) {
-		dd = ERR_PTR(-ENOMEM);
-		goto bail;
-	}
+	if (!dd)
+		return ERR_PTR(-ENOMEM);
 
-#ifdef CONFIG_DEBUG_FS
-	qib_dbg_ibdev_init(&dd->verbs_dev);
-#endif
+	INIT_LIST_HEAD(&dd->list);
 
 	idr_preload(GFP_KERNEL);
 	spin_lock_irqsave(&qib_devs_lock, flags);
@@ -1121,11 +1117,6 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra)
 	if (ret < 0) {
 		qib_early_err(&pdev->dev,
 			      "Could not allocate unit ID: error %d\n", -ret);
-#ifdef CONFIG_DEBUG_FS
-		qib_dbg_ibdev_exit(&dd->verbs_dev);
-#endif
-		ib_dealloc_device(&dd->verbs_dev.ibdev);
-		dd = ERR_PTR(ret);
 		goto bail;
 	}
 
@@ -1139,9 +1130,15 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra)
 			qib_early_err(&pdev->dev,
 				"Could not alloc cpulist info, cpu affinity might be wrong\n");
 	}
-
-bail:
+#ifdef CONFIG_DEBUG_FS
+	qib_dbg_ibdev_init(&dd->verbs_dev);
+#endif
 	return dd;
+bail:
+	if (!list_empty(&dd->list))
+		list_del_init(&dd->list);
+	ib_dealloc_device(&dd->verbs_dev.ibdev);
+	return ERR_PTR(ret);;
 }
 
 /*
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index ccb119143d20..1dd9fcbb7c9a 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -1028,7 +1028,7 @@ static int set_pkeys(struct qib_devdata *dd, u8 port, u16 *pkeys)
 
 		event.event = IB_EVENT_PKEY_CHANGE;
 		event.device = &dd->verbs_dev.ibdev;
-		event.element.port_num = 1;
+		event.element.port_num = port;
 		ib_dispatch_event(&event);
 	}
 	return 0;
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 0cad0c40d742..6a71b2b41b27 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -1324,7 +1324,6 @@ int qib_qp_iter_next(struct qib_qp_iter *iter)
 	struct qib_qp *pqp = iter->qp;
 	struct qib_qp *qp;
 
-	rcu_read_lock();
 	for (; n < dev->qp_table_size; n++) {
 		if (pqp)
 			qp = rcu_dereference(pqp->next);
@@ -1332,18 +1331,11 @@ int qib_qp_iter_next(struct qib_qp_iter *iter)
 			qp = rcu_dereference(dev->qp_table[n]);
 		pqp = qp;
 		if (qp) {
-			if (iter->qp)
-				atomic_dec(&iter->qp->refcount);
-			atomic_inc(&qp->refcount);
-			rcu_read_unlock();
 			iter->qp = qp;
 			iter->n = n;
 			return 0;
 		}
 	}
-	rcu_read_unlock();
-	if (iter->qp)
-		atomic_dec(&iter->qp->refcount);
 	return ret;
 }
 
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 8ee228e9ab5a..a96cfc31372e 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -28,6 +28,7 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/iscsi/iscsi_transport.h>
+#include <linux/semaphore.h>
 
 #include "isert_proto.h"
 #include "ib_isert.h"
@@ -111,9 +112,12 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id)
 	attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS;
 	/*
 	 * FIXME: Use devattr.max_sge - 2 for max_send_sge as
-	 * work-around for RDMA_READ..
+	 * work-around for RDMA_READs with ConnectX-2.
+	 *
+	 * Also, still make sure to have at least two SGEs for
+	 * outgoing control PDU responses.
 	 */
-	attr.cap.max_send_sge = device->dev_attr.max_sge - 2;
+	attr.cap.max_send_sge = max(2, device->dev_attr.max_sge - 2);
 	isert_conn->max_sge = attr.cap.max_send_sge;
 
 	attr.cap.max_recv_sge = 1;
@@ -219,12 +223,16 @@ isert_create_device_ib_res(struct isert_device *device)
 	struct isert_cq_desc *cq_desc;
 	struct ib_device_attr *dev_attr;
 	int ret = 0, i, j;
+	int max_rx_cqe, max_tx_cqe;
 
 	dev_attr = &device->dev_attr;
 	ret = isert_query_device(ib_dev, dev_attr);
 	if (ret)
 		return ret;
 
+	max_rx_cqe = min(ISER_MAX_RX_CQ_LEN, dev_attr->max_cqe);
+	max_tx_cqe = min(ISER_MAX_TX_CQ_LEN, dev_attr->max_cqe);
+
 	/* asign function handlers */
 	if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
 		device->use_fastreg = 1;
@@ -260,7 +268,7 @@ isert_create_device_ib_res(struct isert_device *device)
 						isert_cq_rx_callback,
 						isert_cq_event_callback,
 						(void *)&cq_desc[i],
-						ISER_MAX_RX_CQ_LEN, i);
+						max_rx_cqe, i);
 		if (IS_ERR(device->dev_rx_cq[i])) {
 			ret = PTR_ERR(device->dev_rx_cq[i]);
 			device->dev_rx_cq[i] = NULL;
@@ -272,7 +280,7 @@ isert_create_device_ib_res(struct isert_device *device)
 						isert_cq_tx_callback,
 						isert_cq_event_callback,
 						(void *)&cq_desc[i],
-						ISER_MAX_TX_CQ_LEN, i);
+						max_tx_cqe, i);
 		if (IS_ERR(device->dev_tx_cq[i])) {
 			ret = PTR_ERR(device->dev_tx_cq[i]);
 			device->dev_tx_cq[i] = NULL;
@@ -436,11 +444,18 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn)
 {
 	struct fast_reg_descriptor *fr_desc;
 	struct isert_device *device = isert_conn->conn_device;
-	int i, ret;
+	struct se_session *se_sess = isert_conn->conn->sess->se_sess;
+	struct se_node_acl *se_nacl = se_sess->se_node_acl;
+	int i, ret, tag_num;
+	/*
+	 * Setup the number of FRMRs based upon the number of tags
+	 * available to session in iscsi_target_locate_portal().
+	 */
+	tag_num = max_t(u32, ISCSIT_MIN_TAGS, se_nacl->queue_depth);
+	tag_num = (tag_num * 2) + ISCSIT_EXTRA_TAGS;
 
-	INIT_LIST_HEAD(&isert_conn->conn_fr_pool);
 	isert_conn->conn_fr_pool_size = 0;
-	for (i = 0; i < ISCSI_DEF_XMIT_CMDS_MAX; i++) {
+	for (i = 0; i < tag_num; i++) {
 		fr_desc = kzalloc(sizeof(*fr_desc), GFP_KERNEL);
 		if (!fr_desc) {
 			pr_err("Failed to allocate fast_reg descriptor\n");
@@ -481,6 +496,14 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	struct ib_device *ib_dev = cma_id->device;
 	int ret = 0;
 
+	spin_lock_bh(&np->np_thread_lock);
+	if (!np->enabled) {
+		spin_unlock_bh(&np->np_thread_lock);
+		pr_debug("iscsi_np is not enabled, reject connect request\n");
+		return rdma_reject(cma_id, NULL, 0);
+	}
+	spin_unlock_bh(&np->np_thread_lock);
+
 	pr_debug("Entering isert_connect_request cma_id: %p, context: %p\n",
 		 cma_id, cma_id->context);
 
@@ -495,9 +518,9 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	init_completion(&isert_conn->conn_wait);
 	init_completion(&isert_conn->conn_wait_comp_err);
 	kref_init(&isert_conn->conn_kref);
-	kref_get(&isert_conn->conn_kref);
 	mutex_init(&isert_conn->conn_mutex);
 	spin_lock_init(&isert_conn->conn_lock);
+	INIT_LIST_HEAD(&isert_conn->conn_fr_pool);
 
 	cma_id->context = isert_conn;
 	isert_conn->conn_cm_id = cma_id;
@@ -569,31 +592,19 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 		goto out_mr;
 	}
 
-	if (device->use_fastreg) {
-		ret = isert_conn_create_fastreg_pool(isert_conn);
-		if (ret) {
-			pr_err("Conn: %p failed to create fastreg pool\n",
-			       isert_conn);
-			goto out_fastreg;
-		}
-	}
-
 	ret = isert_conn_setup_qp(isert_conn, cma_id);
 	if (ret)
 		goto out_conn_dev;
 
 	mutex_lock(&isert_np->np_accept_mutex);
-	list_add_tail(&isert_np->np_accept_list, &isert_conn->conn_accept_node);
+	list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list);
 	mutex_unlock(&isert_np->np_accept_mutex);
 
-	pr_debug("isert_connect_request() waking up np_accept_wq: %p\n", np);
-	wake_up(&isert_np->np_accept_wq);
+	pr_debug("isert_connect_request() up np_sem np: %p\n", np);
+	up(&isert_np->np_sem);
 	return 0;
 
 out_conn_dev:
-	if (device->use_fastreg)
-		isert_conn_free_fastreg_pool(isert_conn);
-out_fastreg:
 	ib_dereg_mr(isert_conn->conn_mr);
 out_mr:
 	ib_dealloc_pd(isert_conn->conn_pd);
@@ -658,7 +669,9 @@ isert_connect_release(struct isert_conn *isert_conn)
 static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
-	return;
+	struct isert_conn *isert_conn = cma_id->context;
+
+	kref_get(&isert_conn->conn_kref);
 }
 
 static void
@@ -700,66 +713,71 @@ isert_disconnect_work(struct work_struct *work)
 		isert_put_conn(isert_conn);
 		return;
 	}
-	if (!isert_conn->logout_posted) {
-		pr_debug("Calling rdma_disconnect for !logout_posted from"
-			 " isert_disconnect_work\n");
+
+	if (isert_conn->disconnect) {
+		/* Send DREQ/DREP towards our initiator */
 		rdma_disconnect(isert_conn->conn_cm_id);
-		mutex_unlock(&isert_conn->conn_mutex);
-		iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
-		goto wake_up;
 	}
+
 	mutex_unlock(&isert_conn->conn_mutex);
 
 wake_up:
 	complete(&isert_conn->conn_wait);
-	isert_put_conn(isert_conn);
 }
 
-static void
-isert_disconnected_handler(struct rdma_cm_id *cma_id)
+static int
+isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect)
 {
-	struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context;
+	struct isert_conn *isert_conn;
+
+	if (!cma_id->qp) {
+		struct isert_np *isert_np = cma_id->context;
+
+		isert_np->np_cm_id = NULL;
+		return -1;
+	}
+
+	isert_conn = (struct isert_conn *)cma_id->context;
 
+	isert_conn->disconnect = disconnect;
 	INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work);
 	schedule_work(&isert_conn->conn_logout_work);
+
+	return 0;
 }
 
 static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
+	bool disconnect = false;
 
 	pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n",
 		 event->event, event->status, cma_id->context, cma_id);
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
-		pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n");
 		ret = isert_connect_request(cma_id, event);
+		if (ret)
+			pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n",
+				event->event, ret);
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
-		pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n");
 		isert_connected_handler(cma_id);
 		break;
-	case RDMA_CM_EVENT_DISCONNECTED:
-		pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n");
-		isert_disconnected_handler(cma_id);
-		break;
-	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
+	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
+	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
+		disconnect = true;
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
+		ret = isert_disconnected_handler(cma_id, disconnect);
 		break;
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	default:
-		pr_err("Unknown RDMA CMA event: %d\n", event->event);
+		pr_err("Unhandled RDMA CMA event: %d\n", event->event);
 		break;
 	}
 
-	if (ret != 0) {
-		pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n",
-		       event->event, ret);
-		dump_stack();
-	}
-
 	return ret;
 }
 
@@ -967,6 +985,16 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 	}
 	if (!login->login_failed) {
 		if (login->login_complete) {
+			if (!conn->sess->sess_ops->SessionType &&
+			    isert_conn->conn_device->use_fastreg) {
+				ret = isert_conn_create_fastreg_pool(isert_conn);
+				if (ret) {
+					pr_err("Conn: %p failed to create"
+					       " fastreg pool\n", isert_conn);
+					return ret;
+				}
+			}
+
 			ret = isert_alloc_rx_descriptors(isert_conn);
 			if (ret)
 				return ret;
@@ -1111,6 +1139,8 @@ sequence_cmd:
 
 	if (!rc && dump_payload == false && unsol_data)
 		iscsit_set_unsoliticed_dataout(cmd);
+	else if (dump_payload && imm_data)
+		target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
 
 	return 0;
 }
@@ -1451,7 +1481,7 @@ isert_unreg_rdma(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn)
 }
 
 static void
-isert_put_cmd(struct isert_cmd *isert_cmd)
+isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err)
 {
 	struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd;
 	struct isert_conn *isert_conn = isert_cmd->conn;
@@ -1467,8 +1497,21 @@ isert_put_cmd(struct isert_cmd *isert_cmd)
 			list_del_init(&cmd->i_conn_node);
 		spin_unlock_bh(&conn->cmd_lock);
 
-		if (cmd->data_direction == DMA_TO_DEVICE)
+		if (cmd->data_direction == DMA_TO_DEVICE) {
 			iscsit_stop_dataout_timer(cmd);
+			/*
+			 * Check for special case during comp_err where
+			 * WRITE_PENDING has been handed off from core,
+			 * but requires an extra target_put_sess_cmd()
+			 * before transport_generic_free_cmd() below.
+			 */
+			if (comp_err &&
+			    cmd->se_cmd.t_state == TRANSPORT_WRITE_PENDING) {
+				struct se_cmd *se_cmd = &cmd->se_cmd;
+
+				target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+			}
+		}
 
 		device->unreg_rdma_mem(isert_cmd, isert_conn);
 		transport_generic_free_cmd(&cmd->se_cmd, 0);
@@ -1523,7 +1566,7 @@ isert_unmap_tx_desc(struct iser_tx_desc *tx_desc, struct ib_device *ib_dev)
 
 static void
 isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd,
-		     struct ib_device *ib_dev)
+		     struct ib_device *ib_dev, bool comp_err)
 {
 	if (isert_cmd->pdu_buf_dma != 0) {
 		pr_debug("Calling ib_dma_unmap_single for isert_cmd->pdu_buf_dma\n");
@@ -1533,7 +1576,7 @@ isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd,
 	}
 
 	isert_unmap_tx_desc(tx_desc, ib_dev);
-	isert_put_cmd(isert_cmd);
+	isert_put_cmd(isert_cmd, comp_err);
 }
 
 static void
@@ -1577,28 +1620,25 @@ isert_do_control_comp(struct work_struct *work)
 		iscsit_tmr_post_handler(cmd, cmd->conn);
 
 		cmd->i_state = ISTATE_SENT_STATUS;
-		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev);
+		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false);
 		break;
 	case ISTATE_SEND_REJECT:
 		pr_debug("Got isert_do_control_comp ISTATE_SEND_REJECT: >>>\n");
 		atomic_dec(&isert_conn->post_send_buf_count);
 
 		cmd->i_state = ISTATE_SENT_STATUS;
-		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev);
+		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false);
 		break;
 	case ISTATE_SEND_LOGOUTRSP:
 		pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
-		/*
-		 * Call atomic_dec(&isert_conn->post_send_buf_count)
-		 * from isert_wait_conn()
-		 */
-		isert_conn->logout_posted = true;
+
+		atomic_dec(&isert_conn->post_send_buf_count);
 		iscsit_logout_post_handler(cmd, cmd->conn);
 		break;
 	case ISTATE_SEND_TEXTRSP:
 		atomic_dec(&isert_conn->post_send_buf_count);
 		cmd->i_state = ISTATE_SENT_STATUS;
-		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev);
+		isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false);
 		break;
 	default:
 		pr_err("Unknown do_control_comp i_state %d\n", cmd->i_state);
@@ -1629,7 +1669,7 @@ isert_response_completion(struct iser_tx_desc *tx_desc,
 	atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
 	cmd->i_state = ISTATE_SENT_STATUS;
-	isert_completion_put(tx_desc, isert_cmd, ib_dev);
+	isert_completion_put(tx_desc, isert_cmd, ib_dev, false);
 }
 
 static void
@@ -1710,7 +1750,7 @@ isert_cq_drain_comp_llist(struct isert_conn *isert_conn, struct ib_device *ib_de
 		wr = &t->isert_cmd->rdma_wr;
 
 		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
-		isert_completion_put(t, t->isert_cmd, ib_dev);
+		isert_completion_put(t, t->isert_cmd, ib_dev, true);
 	}
 }
 
@@ -1729,14 +1769,14 @@ isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn
 		wr = &t->isert_cmd->rdma_wr;
 
 		atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
-		isert_completion_put(t, t->isert_cmd, ib_dev);
+		isert_completion_put(t, t->isert_cmd, ib_dev, true);
 	}
 	tx_desc->comp_llnode_batch = NULL;
 
 	if (!isert_cmd)
 		isert_unmap_tx_desc(tx_desc, ib_dev);
 	else
-		isert_completion_put(tx_desc, isert_cmd, ib_dev);
+		isert_completion_put(tx_desc, isert_cmd, ib_dev, true);
 }
 
 static void
@@ -1762,6 +1802,8 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn)
 	isert_conn->state = ISER_CONN_DOWN;
 	mutex_unlock(&isert_conn->conn_mutex);
 
+	iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
+
 	complete(&isert_conn->conn_wait_comp_err);
 }
 
@@ -1911,7 +1953,7 @@ isert_put_response(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 		isert_cmd->tx_desc.num_sge = 2;
 	}
 
-	isert_init_send_wr(isert_conn, isert_cmd, send_wr, true);
+	isert_init_send_wr(isert_conn, isert_cmd, send_wr, false);
 
 	pr_debug("Posting SCSI Response IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
 
@@ -2018,7 +2060,7 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	int rc;
 
 	isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc);
-	rc = iscsit_build_text_rsp(cmd, conn, hdr);
+	rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_INFINIBAND);
 	if (rc < 0)
 		return rc;
 
@@ -2430,7 +2472,7 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 			     &isert_cmd->tx_desc.iscsi_header);
 	isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
 	isert_init_send_wr(isert_conn, isert_cmd,
-			   &isert_cmd->tx_desc.send_wr, true);
+			   &isert_cmd->tx_desc.send_wr, false);
 
 	atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
 
@@ -2551,7 +2593,7 @@ isert_setup_np(struct iscsi_np *np,
 		pr_err("Unable to allocate struct isert_np\n");
 		return -ENOMEM;
 	}
-	init_waitqueue_head(&isert_np->np_accept_wq);
+	sema_init(&isert_np->np_sem, 0);
 	mutex_init(&isert_np->np_accept_mutex);
 	INIT_LIST_HEAD(&isert_np->np_accept_list);
 	init_completion(&isert_np->np_login_comp);
@@ -2600,18 +2642,6 @@ out:
 }
 
 static int
-isert_check_accept_queue(struct isert_np *isert_np)
-{
-	int empty;
-
-	mutex_lock(&isert_np->np_accept_mutex);
-	empty = list_empty(&isert_np->np_accept_list);
-	mutex_unlock(&isert_np->np_accept_mutex);
-
-	return empty;
-}
-
-static int
 isert_rdma_accept(struct isert_conn *isert_conn)
 {
 	struct rdma_cm_id *cm_id = isert_conn->conn_cm_id;
@@ -2703,16 +2733,19 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	int max_accept = 0, ret;
 
 accept_wait:
-	ret = wait_event_interruptible(isert_np->np_accept_wq,
-			!isert_check_accept_queue(isert_np) ||
-			np->np_thread_state == ISCSI_NP_THREAD_RESET);
+	ret = down_interruptible(&isert_np->np_sem);
 	if (max_accept > 5)
 		return -ENODEV;
 
 	spin_lock_bh(&np->np_thread_lock);
-	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
+	if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) {
 		spin_unlock_bh(&np->np_thread_lock);
-		pr_err("ISCSI_NP_THREAD_RESET for isert_accept_np\n");
+		pr_debug("np_thread_state %d for isert_accept_np\n",
+			 np->np_thread_state);
+		/**
+		 * No point in stalling here when np_thread
+		 * is in state RESET/SHUTDOWN/EXIT - bail
+		 **/
 		return -ENODEV;
 	}
 	spin_unlock_bh(&np->np_thread_lock);
@@ -2751,7 +2784,8 @@ isert_free_np(struct iscsi_np *np)
 {
 	struct isert_np *isert_np = (struct isert_np *)np->np_context;
 
-	rdma_destroy_id(isert_np->np_cm_id);
+	if (isert_np->np_cm_id)
+		rdma_destroy_id(isert_np->np_cm_id);
 
 	np->np_context = NULL;
 	kfree(isert_np);
@@ -2762,15 +2796,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	struct isert_conn *isert_conn = conn->context;
 
 	pr_debug("isert_wait_conn: Starting \n");
-	/*
-	 * Decrement post_send_buf_count for special case when called
-	 * from isert_do_control_comp() -> iscsit_logout_post_handler()
-	 */
-	mutex_lock(&isert_conn->conn_mutex);
-	if (isert_conn->logout_posted)
-		atomic_dec(&isert_conn->post_send_buf_count);
 
-	if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) {
+	mutex_lock(&isert_conn->conn_mutex);
+	if (isert_conn->conn_cm_id) {
 		pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
 		rdma_disconnect(isert_conn->conn_cm_id);
 	}
@@ -2789,6 +2817,7 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	wait_for_completion(&isert_conn->conn_wait_comp_err);
 
 	wait_for_completion(&isert_conn->conn_wait);
+	isert_put_conn(isert_conn);
 }
 
 static void isert_free_conn(struct iscsi_conn *conn)
@@ -2845,6 +2874,7 @@ destroy_rx_wq:
 
 static void __exit isert_exit(void)
 {
+	flush_scheduled_work();
 	destroy_workqueue(isert_comp_wq);
 	destroy_workqueue(isert_rx_wq);
 	iscsit_unregister_transport(&iser_target_transport);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index f6ae7f5dd408..cbecaabe90b9 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -93,7 +93,6 @@ struct isert_device;
 
 struct isert_conn {
 	enum iser_conn_state	state;
-	bool			logout_posted;
 	int			post_recv_buf_count;
 	atomic_t		post_send_buf_count;
 	u32			responder_resources;
@@ -128,6 +127,7 @@ struct isert_conn {
 #define ISERT_COMP_BATCH_COUNT	8
 	int			conn_comp_batch;
 	struct llist_head	conn_comp_llist;
+	bool                    disconnect;
 };
 
 #define ISERT_MAX_CQ 64
@@ -158,7 +158,7 @@ struct isert_device {
 };
 
 struct isert_np {
-	wait_queue_head_t	np_accept_wq;
+	struct semaphore	np_sem;
 	struct rdma_cm_id	*np_cm_id;
 	struct mutex		np_accept_mutex;
 	struct list_head	np_accept_list;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 529b6bcdca7a..ca0bc6c67abe 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -120,6 +120,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr);
 static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event);
 
 static struct scsi_transport_template *ib_srp_transport_template;
+static struct workqueue_struct *srp_remove_wq;
 
 static struct ib_client srp_client = {
 	.name   = "srp",
@@ -539,7 +540,7 @@ static bool srp_queue_remove_work(struct srp_target_port *target)
 	spin_unlock_irq(&target->lock);
 
 	if (changed)
-		queue_work(system_long_wq, &target->remove_work);
+		queue_work(srp_remove_wq, &target->remove_work);
 
 	return changed;
 }
@@ -1576,6 +1577,12 @@ err_unmap:
 err_iu:
 	srp_put_tx_iu(target, iu, SRP_IU_CMD);
 
+	/*
+	 * Avoid that the loops that iterate over the request ring can
+	 * encounter a dangling SCSI command pointer.
+	 */
+	req->scmnd = NULL;
+
 	spin_lock_irqsave(&target->lock, flags);
 	list_add(&req->list, &target->free_reqs);
 
@@ -2880,9 +2887,10 @@ static void srp_remove_one(struct ib_device *device)
 		spin_unlock(&host->target_lock);
 
 		/*
-		 * Wait for target port removal tasks.
+		 * Wait for tl_err and target port removal tasks.
 		 */
 		flush_workqueue(system_long_wq);
+		flush_workqueue(srp_remove_wq);
 
 		kfree(host);
 	}
@@ -2934,16 +2942,22 @@ static int __init srp_init_module(void)
 		indirect_sg_entries = cmd_sg_entries;
 	}
 
+	srp_remove_wq = create_workqueue("srp_remove");
+	if (IS_ERR(srp_remove_wq)) {
+		ret = PTR_ERR(srp_remove_wq);
+		goto out;
+	}
+
+	ret = -ENOMEM;
 	ib_srp_transport_template =
 		srp_attach_transport(&ib_srp_transport_functions);
 	if (!ib_srp_transport_template)
-		return -ENOMEM;
+		goto destroy_wq;
 
 	ret = class_register(&srp_class);
 	if (ret) {
 		pr_err("couldn't register class infiniband_srp\n");
-		srp_release_transport(ib_srp_transport_template);
-		return ret;
+		goto release_tr;
 	}
 
 	ib_sa_register_client(&srp_sa_client);
@@ -2951,13 +2965,22 @@ static int __init srp_init_module(void)
 	ret = ib_register_client(&srp_client);
 	if (ret) {
 		pr_err("couldn't register IB client\n");
-		srp_release_transport(ib_srp_transport_template);
-		ib_sa_unregister_client(&srp_sa_client);
-		class_unregister(&srp_class);
-		return ret;
+		goto unreg_sa;
 	}
 
-	return 0;
+out:
+	return ret;
+
+unreg_sa:
+	ib_sa_unregister_client(&srp_sa_client);
+	class_unregister(&srp_class);
+
+release_tr:
+	srp_release_transport(ib_srp_transport_template);
+
+destroy_wq:
+	destroy_workqueue(srp_remove_wq);
+	goto out;
 }
 
 static void __exit srp_cleanup_module(void)
@@ -2966,6 +2989,7 @@ static void __exit srp_cleanup_module(void)
 	ib_sa_unregister_client(&srp_sa_client);
 	class_unregister(&srp_class);
 	srp_release_transport(ib_srp_transport_template);
+	destroy_workqueue(srp_remove_wq);
 }
 
 module_init(srp_init_module);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 0e537d8d0e47..0097b8dae5bc 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1078,6 +1078,7 @@ static void srpt_unmap_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 				 struct srpt_send_ioctx *ioctx)
 {
+	struct ib_device *dev = ch->sport->sdev->device;
 	struct se_cmd *cmd;
 	struct scatterlist *sg, *sg_orig;
 	int sg_cnt;
@@ -1124,7 +1125,7 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 
 	db = ioctx->rbufs;
 	tsize = cmd->data_length;
-	dma_len = sg_dma_len(&sg[0]);
+	dma_len = ib_sg_dma_len(dev, &sg[0]);
 	riu = ioctx->rdma_ius;
 
 	/*
@@ -1155,7 +1156,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 					++j;
 					if (j < count) {
 						sg = sg_next(sg);
-						dma_len = sg_dma_len(sg);
+						dma_len = ib_sg_dma_len(
+								dev, sg);
 					}
 				}
 			} else {
@@ -1192,8 +1194,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 	tsize = cmd->data_length;
 	riu = ioctx->rdma_ius;
 	sg = sg_orig;
-	dma_len = sg_dma_len(&sg[0]);
-	dma_addr = sg_dma_address(&sg[0]);
+	dma_len = ib_sg_dma_len(dev, &sg[0]);
+	dma_addr = ib_sg_dma_address(dev, &sg[0]);
 
 	/* this second loop is really mapped sg_addres to rdma_iu->ib_sge */
 	for (i = 0, j = 0;
@@ -1216,8 +1218,10 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
 					++j;
 					if (j < count) {
 						sg = sg_next(sg);
-						dma_len = sg_dma_len(sg);
-						dma_addr = sg_dma_address(sg);
+						dma_len = ib_sg_dma_len(
+								dev, sg);
+						dma_addr = ib_sg_dma_address(
+								dev, sg);
 					}
 				}
 			} else {
@@ -2087,6 +2091,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 	if (!qp_init)
 		goto out;
 
+retry:
 	ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch,
 			      ch->rq_size + srp_sq_size, 0);
 	if (IS_ERR(ch->cq)) {
@@ -2110,6 +2115,13 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 	ch->qp = ib_create_qp(sdev->pd, qp_init);
 	if (IS_ERR(ch->qp)) {
 		ret = PTR_ERR(ch->qp);
+		if (ret == -ENOMEM) {
+			srp_sq_size /= 2;
+			if (srp_sq_size >= MIN_SRPT_SQ_SIZE) {
+				ib_destroy_cq(ch->cq);
+				goto retry;
+			}
+		}
 		printk(KERN_ERR "failed to create_qp ret= %d\n", ret);
 		goto err_destroy_cq;
 	}
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 1c4c0db05550..29ca0bb4f561 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -257,9 +257,10 @@ static int input_handle_abs_event(struct input_dev *dev,
 }
 
 static int input_get_disposition(struct input_dev *dev,
-			  unsigned int type, unsigned int code, int value)
+			  unsigned int type, unsigned int code, int *pval)
 {
 	int disposition = INPUT_IGNORE_EVENT;
+	int value = *pval;
 
 	switch (type) {
 
@@ -357,6 +358,7 @@ static int input_get_disposition(struct input_dev *dev,
 		break;
 	}
 
+	*pval = value;
 	return disposition;
 }
 
@@ -365,7 +367,7 @@ static void input_handle_event(struct input_dev *dev,
 {
 	int disposition;
 
-	disposition = input_get_disposition(dev, type, code, value);
+	disposition = input_get_disposition(dev, type, code, &value);
 
 	if ((disposition & INPUT_PASS_TO_DEVICE) && dev->event)
 		dev->event(dev, type, code, value);
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 603fe0dd3682..517829f6a58b 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1003,9 +1003,19 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 		}
 
 		ep_irq_in = &intf->cur_altsetting->endpoint[1].desc;
-		usb_fill_bulk_urb(xpad->bulk_out, udev,
-				usb_sndbulkpipe(udev, ep_irq_in->bEndpointAddress),
-				xpad->bdata, XPAD_PKT_LEN, xpad_bulk_out, xpad);
+		if (usb_endpoint_is_bulk_out(ep_irq_in)) {
+			usb_fill_bulk_urb(xpad->bulk_out, udev,
+					  usb_sndbulkpipe(udev,
+							  ep_irq_in->bEndpointAddress),
+					  xpad->bdata, XPAD_PKT_LEN,
+					  xpad_bulk_out, xpad);
+		} else {
+			usb_fill_int_urb(xpad->bulk_out, udev,
+					 usb_sndintpipe(udev,
+							ep_irq_in->bEndpointAddress),
+					 xpad->bdata, XPAD_PKT_LEN,
+					 xpad_bulk_out, xpad, 0);
+		}
 
 		/*
 		 * Submit the int URB immediately rather than waiting for open
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 2626773ff29b..6f5d79569136 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -243,6 +243,12 @@ static void (*atkbd_platform_fixup)(struct atkbd *, const void *data);
 static void *atkbd_platform_fixup_data;
 static unsigned int (*atkbd_platform_scancode_fixup)(struct atkbd *, unsigned int);
 
+/*
+ * Certain keyboards to not like ATKBD_CMD_RESET_DIS and stop responding
+ * to many commands until full reset (ATKBD_CMD_RESET_BAT) is performed.
+ */
+static bool atkbd_skip_deactivate;
+
 static ssize_t atkbd_attr_show_helper(struct device *dev, char *buf,
 				ssize_t (*handler)(struct atkbd *, char *));
 static ssize_t atkbd_attr_set_helper(struct device *dev, const char *buf, size_t count,
@@ -768,7 +774,8 @@ static int atkbd_probe(struct atkbd *atkbd)
  * Make sure nothing is coming from the keyboard and disturbs our
  * internal state.
  */
-	atkbd_deactivate(atkbd);
+	if (!atkbd_skip_deactivate)
+		atkbd_deactivate(atkbd);
 
 	return 0;
 }
@@ -1638,6 +1645,12 @@ static int __init atkbd_setup_scancode_fixup(const struct dmi_system_id *id)
 	return 1;
 }
 
+static int __init atkbd_deactivate_fixup(const struct dmi_system_id *id)
+{
+	atkbd_skip_deactivate = true;
+	return 1;
+}
+
 static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = {
 	{
 		.matches = {
@@ -1775,6 +1788,12 @@ static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = {
 		.callback = atkbd_setup_scancode_fixup,
 		.driver_data = atkbd_oqo_01plus_scancode_fixup,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+		},
+		.callback = atkbd_deactivate_fixup,
+	},
 	{ }
 };
 
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index fb15c64ffb95..4979b00fbf04 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1047,7 +1047,13 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse)
 {
 	struct alps_data *priv = psmouse->private;
 
-	if ((psmouse->packet[0] & 0xc8) == 0x08) { /* PS/2 packet */
+	/*
+	 * Check if we are dealing with a bare PS/2 packet, presumably from
+	 * a device connected to the external PS/2 port. Because bare PS/2
+	 * protocol does not have enough constant bits to self-synchronize
+	 * properly we only do this if the device is fully synchronized.
+	 */
+	if (!psmouse->out_of_sync_cnt && (psmouse->packet[0] & 0xc8) == 0x08) {
 		if (psmouse->pktcnt == 3) {
 			alps_report_bare_ps2_packet(psmouse, psmouse->packet,
 						    true);
@@ -1071,12 +1077,27 @@ static psmouse_ret_t alps_process_byte(struct psmouse *psmouse)
 	}
 
 	/* Bytes 2 - pktsize should have 0 in the highest bit */
-	if ((priv->proto_version < ALPS_PROTO_V5) &&
+	if (priv->proto_version < ALPS_PROTO_V5 &&
 	    psmouse->pktcnt >= 2 && psmouse->pktcnt <= psmouse->pktsize &&
 	    (psmouse->packet[psmouse->pktcnt - 1] & 0x80)) {
 		psmouse_dbg(psmouse, "refusing packet[%i] = %x\n",
 			    psmouse->pktcnt - 1,
 			    psmouse->packet[psmouse->pktcnt - 1]);
+
+		if (priv->proto_version == ALPS_PROTO_V3 &&
+		    psmouse->pktcnt == psmouse->pktsize) {
+			/*
+			 * Some Dell boxes, such as Latitude E6440 or E7440
+			 * with closed lid, quite often smash last byte of
+			 * otherwise valid packet with 0xff. Given that the
+			 * next packet is very likely to be valid let's
+			 * report PSMOUSE_FULL_PACKET but not process data,
+			 * rather than reporting PSMOUSE_BAD_DATA and
+			 * filling the logs.
+			 */
+			return PSMOUSE_FULL_PACKET;
+		}
+
 		return PSMOUSE_BAD_DATA;
 	}
 
@@ -2148,6 +2169,9 @@ int alps_init(struct psmouse *psmouse)
 	/* We are having trouble resyncing ALPS touchpads so disable it for now */
 	psmouse->resync_time = 0;
 
+	/* Allow 2 invalid packets without resetting device */
+	psmouse->resetafter = psmouse->pktsize * 2;
+
 	return 0;
 
 init_fail:
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index ef1cf52f8bb9..0b75b5764f31 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/dmi.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/input.h>
@@ -472,8 +473,15 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 	input_report_key(dev, BTN_TOOL_FINGER, fingers == 1);
 	input_report_key(dev, BTN_TOOL_DOUBLETAP, fingers == 2);
 	input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3);
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
-	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_report_abs(dev, ABS_PRESSURE, pres);
 	input_report_abs(dev, ABS_TOOL_WIDTH, width);
 
@@ -483,10 +491,17 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 static void elantech_input_sync_v4(struct psmouse *psmouse)
 {
 	struct input_dev *dev = psmouse->dev;
+	struct elantech_data *etd = psmouse->private;
 	unsigned char *packet = psmouse->packet;
 
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
-	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_mt_report_pointer_emulation(dev, true);
 	input_sync(dev);
 }
@@ -831,7 +846,11 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 		break;
 
 	case 3:
-		etd->reg_10 = 0x0b;
+		if (etd->set_hw_resolution)
+			etd->reg_10 = 0x0b;
+		else
+			etd->reg_10 = 0x01;
+
 		if (elantech_write_reg(psmouse, 0x10, etd->reg_10))
 			rc = -1;
 
@@ -1234,6 +1253,13 @@ static bool elantech_is_signature_valid(const unsigned char *param)
 	if (param[1] == 0)
 		return true;
 
+	/*
+	 * Some models have a revision higher then 20. Meaning param[2] may
+	 * be 10 or 20, skip the rates check for these.
+	 */
+	if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40)
+		return true;
+
 	for (i = 0; i < ARRAY_SIZE(rates); i++)
 		if (param[2] == rates[i])
 			return false;
@@ -1331,6 +1357,23 @@ static int elantech_reconnect(struct psmouse *psmouse)
 }
 
 /*
+ * Some hw_version 3 models go into error state when we try to set
+ * bit 3 and/or bit 1 of r10.
+ */
+static const struct dmi_system_id no_hw_res_dmi_table[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+	{
+		/* Gigabyte U2442 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "U2442"),
+		},
+	},
+#endif
+	{ }
+};
+
+/*
  * determine hardware version and set some properties according to it.
  */
 static int elantech_set_properties(struct elantech_data *etd)
@@ -1389,6 +1432,9 @@ static int elantech_set_properties(struct elantech_data *etd)
 	 */
 	etd->crc_enabled = ((etd->fw_version & 0x4000) == 0x4000);
 
+	/* Enable real hardware resolution on hw_version 3 ? */
+	etd->set_hw_resolution = !dmi_check_system(no_hw_res_dmi_table);
+
 	return 0;
 }
 
diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index 036a04abaef7..9e0e2a1f340d 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -130,6 +130,7 @@ struct elantech_data {
 	bool jumpy_cursor;
 	bool reports_pressure;
 	bool crc_enabled;
+	bool set_hw_resolution;
 	unsigned char hw_version;
 	unsigned int fw_version;
 	unsigned int single_finger_reports;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index d8d49d10f9bb..a3769cf84381 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -117,6 +117,87 @@ void synaptics_reset(struct psmouse *psmouse)
 }
 
 #ifdef CONFIG_MOUSE_PS2_SYNAPTICS
+struct min_max_quirk {
+	const char * const *pnp_ids;
+	int x_min, x_max, y_min, y_max;
+};
+
+static const struct min_max_quirk min_max_pnpid_table[] = {
+	{
+		(const char * const []){"LEN0033", NULL},
+		1024, 5052, 2258, 4832
+	},
+	{
+		(const char * const []){"LEN0035", "LEN0042", NULL},
+		1232, 5710, 1156, 4696
+	},
+	{
+		(const char * const []){"LEN0034", "LEN0036", "LEN0039",
+					"LEN2002", "LEN2004", NULL},
+		1024, 5112, 2024, 4832
+	},
+	{
+		(const char * const []){"LEN2001", NULL},
+		1024, 5022, 2508, 4832
+	},
+	{
+		(const char * const []){"LEN2006", NULL},
+		1264, 5675, 1171, 4688
+	},
+	{ }
+};
+
+/* This list has been kindly provided by Synaptics. */
+static const char * const topbuttonpad_pnp_ids[] = {
+	"LEN0017",
+	"LEN0018",
+	"LEN0019",
+	"LEN0023",
+	"LEN002A",
+	"LEN002B",
+	"LEN002C",
+	"LEN002D",
+	"LEN002E",
+	"LEN0033", /* Helix */
+	"LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */
+	"LEN0035", /* X240 */
+	"LEN0036", /* T440 */
+	"LEN0037",
+	"LEN0038",
+	"LEN0039", /* T440s */
+	"LEN0041",
+	"LEN0042", /* Yoga */
+	"LEN0045",
+	"LEN0046",
+	"LEN0047",
+	"LEN0048",
+	"LEN0049",
+	"LEN2000",
+	"LEN2001", /* Edge E431 */
+	"LEN2002", /* Edge E531 */
+	"LEN2003",
+	"LEN2004", /* L440 */
+	"LEN2005",
+	"LEN2006",
+	"LEN2007",
+	"LEN2008",
+	"LEN2009",
+	"LEN200A",
+	"LEN200B",
+	NULL
+};
+
+static bool matches_pnp_id(struct psmouse *psmouse, const char * const ids[])
+{
+	int i;
+
+	if (!strncmp(psmouse->ps2dev.serio->firmware_id, "PNP:", 4))
+		for (i = 0; ids[i]; i++)
+			if (strstr(psmouse->ps2dev.serio->firmware_id, ids[i]))
+				return true;
+
+	return false;
+}
 
 /*****************************************************************************
  *	Synaptics communications functions
@@ -266,20 +347,11 @@ static int synaptics_identify(struct psmouse *psmouse)
  * Resolution is left zero if touchpad does not support the query
  */
 
-static const int *quirk_min_max;
-
 static int synaptics_resolution(struct psmouse *psmouse)
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char resp[3];
-
-	if (quirk_min_max) {
-		priv->x_min = quirk_min_max[0];
-		priv->x_max = quirk_min_max[1];
-		priv->y_min = quirk_min_max[2];
-		priv->y_max = quirk_min_max[3];
-		return 0;
-	}
+	int i;
 
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
@@ -291,6 +363,16 @@ static int synaptics_resolution(struct psmouse *psmouse)
 		}
 	}
 
+	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) {
+		if (matches_pnp_id(psmouse, min_max_pnpid_table[i].pnp_ids)) {
+			priv->x_min = min_max_pnpid_table[i].x_min;
+			priv->x_max = min_max_pnpid_table[i].x_max;
+			priv->y_min = min_max_pnpid_table[i].y_min;
+			priv->y_max = min_max_pnpid_table[i].y_max;
+			return 0;
+		}
+	}
+
 	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 5 &&
 	    SYN_CAP_MAX_DIMENSIONS(priv->ext_cap_0c)) {
 		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MAX_COORDS, resp)) {
@@ -549,10 +631,61 @@ static int synaptics_parse_hw_state(const unsigned char buf[],
 			 ((buf[0] & 0x04) >> 1) |
 			 ((buf[3] & 0x04) >> 2));
 
+		if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) ||
+			SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) &&
+		    hw->w == 2) {
+			synaptics_parse_agm(buf, priv, hw);
+			return 1;
+		}
+
+		hw->x = (((buf[3] & 0x10) << 8) |
+			 ((buf[1] & 0x0f) << 8) |
+			 buf[4]);
+		hw->y = (((buf[3] & 0x20) << 7) |
+			 ((buf[1] & 0xf0) << 4) |
+			 buf[5]);
+		hw->z = buf[2];
+
 		hw->left  = (buf[0] & 0x01) ? 1 : 0;
 		hw->right = (buf[0] & 0x02) ? 1 : 0;
 
-		if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
+		if (SYN_CAP_FORCEPAD(priv->ext_cap_0c)) {
+			/*
+			 * ForcePads, like Clickpads, use middle button
+			 * bits to report primary button clicks.
+			 * Unfortunately they report primary button not
+			 * only when user presses on the pad above certain
+			 * threshold, but also when there are more than one
+			 * finger on the touchpad, which interferes with
+			 * out multi-finger gestures.
+			 */
+			if (hw->z == 0) {
+				/* No contacts */
+				priv->press = priv->report_press = false;
+			} else if (hw->w >= 4 && ((buf[0] ^ buf[3]) & 0x01)) {
+				/*
+				 * Single-finger touch with pressure above
+				 * the threshold. If pressure stays long
+				 * enough, we'll start reporting primary
+				 * button. We rely on the device continuing
+				 * sending data even if finger does not
+				 * move.
+				 */
+				if  (!priv->press) {
+					priv->press_start = jiffies;
+					priv->press = true;
+				} else if (time_after(jiffies,
+						priv->press_start +
+							msecs_to_jiffies(50))) {
+					priv->report_press = true;
+				}
+			} else {
+				priv->press = false;
+			}
+
+			hw->left = priv->report_press;
+
+		} else if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
 			/*
 			 * Clickpad's button is transmitted as middle button,
 			 * however, since it is primary button, we will report
@@ -571,21 +704,6 @@ static int synaptics_parse_hw_state(const unsigned char buf[],
 			hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0;
 		}
 
-		if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) ||
-			SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) &&
-		    hw->w == 2) {
-			synaptics_parse_agm(buf, priv, hw);
-			return 1;
-		}
-
-		hw->x = (((buf[3] & 0x10) << 8) |
-			 ((buf[1] & 0x0f) << 8) |
-			 buf[4]);
-		hw->y = (((buf[3] & 0x20) << 7) |
-			 ((buf[1] & 0xf0) << 4) |
-			 buf[5]);
-		hw->z = buf[2];
-
 		if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) &&
 		    ((buf[0] ^ buf[3]) & 0x02)) {
 			switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) {
@@ -1255,8 +1373,10 @@ static void set_abs_position_params(struct input_dev *dev,
 	input_abs_set_res(dev, y_code, priv->y_res);
 }
 
-static void set_input_params(struct input_dev *dev, struct synaptics_data *priv)
+static void set_input_params(struct psmouse *psmouse,
+			     struct synaptics_data *priv)
 {
+	struct input_dev *dev = psmouse->dev;
 	int i;
 
 	/* Things that apply to both modes */
@@ -1325,6 +1445,8 @@ static void set_input_params(struct input_dev *dev, struct synaptics_data *priv)
 
 	if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
 		__set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
+		if (matches_pnp_id(psmouse, topbuttonpad_pnp_ids))
+			__set_bit(INPUT_PROP_TOPBUTTONPAD, dev->propbit);
 		/* Clickpads report only left button */
 		__clear_bit(BTN_RIGHT, dev->keybit);
 		__clear_bit(BTN_MIDDLE, dev->keybit);
@@ -1496,54 +1618,10 @@ static const struct dmi_system_id olpc_dmi_table[] __initconst = {
 	{ }
 };
 
-static const struct dmi_system_id min_max_dmi_table[] __initconst = {
-#if defined(CONFIG_DMI)
-	{
-		/* Lenovo ThinkPad Helix */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
-		},
-		.driver_data = (int []){1024, 5052, 2258, 4832},
-	},
-	{
-		/* Lenovo ThinkPad X240 */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"),
-		},
-		.driver_data = (int []){1232, 5710, 1156, 4696},
-	},
-	{
-		/* Lenovo ThinkPad T440s */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"),
-		},
-		.driver_data = (int []){1024, 5112, 2024, 4832},
-	},
-	{
-		/* Lenovo ThinkPad T540p */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"),
-		},
-		.driver_data = (int []){1024, 5056, 2058, 4832},
-	},
-#endif
-	{ }
-};
-
 void __init synaptics_module_init(void)
 {
-	const struct dmi_system_id *min_max_dmi;
-
 	impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table);
 	broken_olpc_ec = dmi_check_system(olpc_dmi_table);
-
-	min_max_dmi = dmi_first_match(min_max_dmi_table);
-	if (min_max_dmi)
-		quirk_min_max = min_max_dmi->driver_data;
 }
 
 static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
@@ -1593,7 +1671,7 @@ static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
 		     priv->capabilities, priv->ext_cap, priv->ext_cap_0c,
 		     priv->board_id, priv->firmware_id);
 
-	set_input_params(psmouse->dev, priv);
+	set_input_params(psmouse, priv);
 
 	/*
 	 * Encode touchpad model so that it can be used to set
diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h
index e594af0b264b..fb2e076738ae 100644
--- a/drivers/input/mouse/synaptics.h
+++ b/drivers/input/mouse/synaptics.h
@@ -78,6 +78,11 @@
  * 2	0x08	image sensor		image sensor tracks 5 fingers, but only
  *					reports 2.
  * 2	0x20	report min		query 0x0f gives min coord reported
+ * 2	0x80	forcepad		forcepad is a variant of clickpad that
+ *					does not have physical buttons but rather
+ *					uses pressure above certain threshold to
+ *					report primary clicks. Forcepads also have
+ *					clickpad bit set.
  */
 #define SYN_CAP_CLICKPAD(ex0c)		((ex0c) & 0x100000) /* 1-button ClickPad */
 #define SYN_CAP_CLICKPAD2BTN(ex0c)	((ex0c) & 0x000100) /* 2-button ClickPad */
@@ -86,6 +91,7 @@
 #define SYN_CAP_ADV_GESTURE(ex0c)	((ex0c) & 0x080000)
 #define SYN_CAP_REDUCED_FILTERING(ex0c)	((ex0c) & 0x000400)
 #define SYN_CAP_IMAGE_SENSOR(ex0c)	((ex0c) & 0x000800)
+#define SYN_CAP_FORCEPAD(ex0c)		((ex0c) & 0x008000)
 
 /* synaptics modes query bits */
 #define SYN_MODE_ABSOLUTE(m)		((m) & (1 << 7))
@@ -177,6 +183,11 @@ struct synaptics_data {
 	 */
 	struct synaptics_hw_state agm;
 	bool agm_pending;			/* new AGM packet received */
+
+	/* ForcePad handling */
+	unsigned long				press_start;
+	bool					press;
+	bool					report_press;
 };
 
 void synaptics_module_init(void);
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 0ec9abbe31fe..8fca488fdc15 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -101,6 +101,12 @@ static const struct dmi_system_id __initconst i8042_dmi_noloop_table[] = {
 	},
 	{
 		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"),
+		},
+	},
+	{
+		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
 			DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"),
 			DMI_MATCH(DMI_PRODUCT_VERSION, "8500"),
@@ -458,6 +464,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
 		},
 	},
+	{
+		/* Avatar AVIU-145A6 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Intel"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"),
+		},
+	},
 	{ }
 };
 
@@ -601,6 +614,30 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
 		},
 	},
+	{
+		/* Fujitsu A544 laptop */
+		/* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"),
+		},
+	},
+	{
+		/* Fujitsu AH544 laptop */
+		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"),
+		},
+	},
+	{
+		/* Fujitsu U574 laptop */
+		/* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"),
+		},
+	},
 	{ }
 };
 
@@ -702,6 +739,17 @@ static int i8042_pnp_aux_irq;
 static char i8042_pnp_kbd_name[32];
 static char i8042_pnp_aux_name[32];
 
+static void i8042_pnp_id_to_string(struct pnp_id *id, char *dst, int dst_size)
+{
+	strlcpy(dst, "PNP:", dst_size);
+
+	while (id) {
+		strlcat(dst, " ", dst_size);
+		strlcat(dst, id->id, dst_size);
+		id = id->next;
+	}
+}
+
 static int i8042_pnp_kbd_probe(struct pnp_dev *dev, const struct pnp_device_id *did)
 {
 	if (pnp_port_valid(dev, 0) && pnp_port_len(dev, 0) == 1)
@@ -718,6 +766,8 @@ static int i8042_pnp_kbd_probe(struct pnp_dev *dev, const struct pnp_device_id *
 		strlcat(i8042_pnp_kbd_name, ":", sizeof(i8042_pnp_kbd_name));
 		strlcat(i8042_pnp_kbd_name, pnp_dev_name(dev), sizeof(i8042_pnp_kbd_name));
 	}
+	i8042_pnp_id_to_string(dev->id, i8042_kbd_firmware_id,
+			       sizeof(i8042_kbd_firmware_id));
 
 	/* Keyboard ports are always supposed to be wakeup-enabled */
 	device_set_wakeup_enable(&dev->dev, true);
@@ -742,6 +792,8 @@ static int i8042_pnp_aux_probe(struct pnp_dev *dev, const struct pnp_device_id *
 		strlcat(i8042_pnp_aux_name, ":", sizeof(i8042_pnp_aux_name));
 		strlcat(i8042_pnp_aux_name, pnp_dev_name(dev), sizeof(i8042_pnp_aux_name));
 	}
+	i8042_pnp_id_to_string(dev->id, i8042_aux_firmware_id,
+			       sizeof(i8042_aux_firmware_id));
 
 	i8042_pnp_aux_devices++;
 	return 0;
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 020053fa5aaa..3807c3e971cc 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -87,6 +87,8 @@ MODULE_PARM_DESC(debug, "Turn i8042 debugging mode on and off");
 #endif
 
 static bool i8042_bypass_aux_irq_test;
+static char i8042_kbd_firmware_id[128];
+static char i8042_aux_firmware_id[128];
 
 #include "i8042.h"
 
@@ -1218,6 +1220,8 @@ static int __init i8042_create_kbd_port(void)
 	serio->dev.parent	= &i8042_platform_device->dev;
 	strlcpy(serio->name, "i8042 KBD port", sizeof(serio->name));
 	strlcpy(serio->phys, I8042_KBD_PHYS_DESC, sizeof(serio->phys));
+	strlcpy(serio->firmware_id, i8042_kbd_firmware_id,
+		sizeof(serio->firmware_id));
 
 	port->serio = serio;
 	port->irq = I8042_KBD_IRQ;
@@ -1244,6 +1248,8 @@ static int __init i8042_create_aux_port(int idx)
 	if (idx < 0) {
 		strlcpy(serio->name, "i8042 AUX port", sizeof(serio->name));
 		strlcpy(serio->phys, I8042_AUX_PHYS_DESC, sizeof(serio->phys));
+		strlcpy(serio->firmware_id, i8042_aux_firmware_id,
+			sizeof(serio->firmware_id));
 		serio->close = i8042_port_close;
 	} else {
 		snprintf(serio->name, sizeof(serio->name), "i8042 AUX%d port", idx);
diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index 8f4c4ab04bc2..b29134de983b 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -451,6 +451,13 @@ static ssize_t serio_set_bind_mode(struct device *dev, struct device_attribute *
 	return retval;
 }
 
+static ssize_t firmware_id_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct serio *serio = to_serio_port(dev);
+
+	return sprintf(buf, "%s\n", serio->firmware_id);
+}
+
 static DEVICE_ATTR_RO(type);
 static DEVICE_ATTR_RO(proto);
 static DEVICE_ATTR_RO(id);
@@ -473,12 +480,14 @@ static DEVICE_ATTR_RO(modalias);
 static DEVICE_ATTR_WO(drvctl);
 static DEVICE_ATTR(description, S_IRUGO, serio_show_description, NULL);
 static DEVICE_ATTR(bind_mode, S_IWUSR | S_IRUGO, serio_show_bind_mode, serio_set_bind_mode);
+static DEVICE_ATTR_RO(firmware_id);
 
 static struct attribute *serio_device_attrs[] = {
 	&dev_attr_modalias.attr,
 	&dev_attr_description.attr,
 	&dev_attr_drvctl.attr,
 	&dev_attr_bind_mode.attr,
+	&dev_attr_firmware_id.attr,
 	NULL
 };
 
@@ -921,9 +930,14 @@ static int serio_uevent(struct device *dev, struct kobj_uevent_env *env)
 	SERIO_ADD_UEVENT_VAR("SERIO_PROTO=%02x", serio->id.proto);
 	SERIO_ADD_UEVENT_VAR("SERIO_ID=%02x", serio->id.id);
 	SERIO_ADD_UEVENT_VAR("SERIO_EXTRA=%02x", serio->id.extra);
+
 	SERIO_ADD_UEVENT_VAR("MODALIAS=serio:ty%02Xpr%02Xid%02Xex%02X",
 				serio->id.type, serio->id.proto, serio->id.id, serio->id.extra);
 
+	if (serio->firmware_id[0])
+		SERIO_ADD_UEVENT_VAR("SERIO_FIRMWARE_ID=%s",
+				     serio->firmware_id);
+
 	return 0;
 }
 #undef SERIO_ADD_UEVENT_VAR
diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index 0cb7ef59071b..69175b825346 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/serio.h>
 #include <linux/tty.h>
+#include <linux/compat.h>
 
 MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
 MODULE_DESCRIPTION("Input device TTY line discipline");
@@ -198,28 +199,55 @@ static ssize_t serport_ldisc_read(struct tty_struct * tty, struct file * file, u
 	return 0;
 }
 
+static void serport_set_type(struct tty_struct *tty, unsigned long type)
+{
+	struct serport *serport = tty->disc_data;
+
+	serport->id.proto = type & 0x000000ff;
+	serport->id.id    = (type & 0x0000ff00) >> 8;
+	serport->id.extra = (type & 0x00ff0000) >> 16;
+}
+
 /*
  * serport_ldisc_ioctl() allows to set the port protocol, and device ID
  */
 
-static int serport_ldisc_ioctl(struct tty_struct * tty, struct file * file, unsigned int cmd, unsigned long arg)
+static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file,
+			       unsigned int cmd, unsigned long arg)
 {
-	struct serport *serport = (struct serport*) tty->disc_data;
-	unsigned long type;
-
 	if (cmd == SPIOCSTYPE) {
+		unsigned long type;
+
 		if (get_user(type, (unsigned long __user *) arg))
 			return -EFAULT;
 
-		serport->id.proto = type & 0x000000ff;
-		serport->id.id	  = (type & 0x0000ff00) >> 8;
-		serport->id.extra = (type & 0x00ff0000) >> 16;
+		serport_set_type(tty, type);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+#ifdef CONFIG_COMPAT
+#define COMPAT_SPIOCSTYPE	_IOW('q', 0x01, compat_ulong_t)
+static long serport_ldisc_compat_ioctl(struct tty_struct *tty,
+				       struct file *file,
+				       unsigned int cmd, unsigned long arg)
+{
+	if (cmd == COMPAT_SPIOCSTYPE) {
+		void __user *uarg = compat_ptr(arg);
+		compat_ulong_t compat_type;
+
+		if (get_user(compat_type, (compat_ulong_t __user *)uarg))
+			return -EFAULT;
 
+		serport_set_type(tty, compat_type);
 		return 0;
 	}
 
 	return -EINVAL;
 }
+#endif
 
 static void serport_ldisc_write_wakeup(struct tty_struct * tty)
 {
@@ -243,6 +271,9 @@ static struct tty_ldisc_ops serport_ldisc = {
 	.close =	serport_ldisc_close,
 	.read =		serport_ldisc_read,
 	.ioctl =	serport_ldisc_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl =	serport_ldisc_compat_ioctl,
+#endif
 	.receive_buf =	serport_ldisc_receive,
 	.write_wakeup =	serport_ldisc_write_wakeup
 };
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index faf0da4bb3a2..9cbef59d404a 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3227,14 +3227,16 @@ free_domains:
 
 static void cleanup_domain(struct protection_domain *domain)
 {
-	struct iommu_dev_data *dev_data, *next;
+	struct iommu_dev_data *entry;
 	unsigned long flags;
 
 	write_lock_irqsave(&amd_iommu_devtable_lock, flags);
 
-	list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) {
-		__detach_device(dev_data);
-		atomic_set(&dev_data->bind, 0);
+	while (!list_empty(&domain->dev_list)) {
+		entry = list_first_entry(&domain->dev_list,
+					 struct iommu_dev_data, list);
+		__detach_device(entry);
+		atomic_set(&entry->bind, 0);
 	}
 
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -3999,7 +4001,7 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	iommu_flush_dte(iommu, devid);
 	if (devid != alias) {
 		irq_lookup_table[alias] = table;
-		set_dte_irq_entry(devid, table);
+		set_dte_irq_entry(alias, table);
 		iommu_flush_dte(iommu, alias);
 	}
 
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 1d9ab39af29f..2ecac467f78f 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -794,8 +794,11 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	reg |= TTBCR_EAE |
 	      (TTBCR_SH_IS << TTBCR_SH0_SHIFT) |
 	      (TTBCR_RGN_WBWA << TTBCR_ORGN0_SHIFT) |
-	      (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT) |
-	      (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT);
+	      (TTBCR_RGN_WBWA << TTBCR_IRGN0_SHIFT);
+
+	if (!stage1)
+		reg |= (TTBCR_SL0_LVL_1 << TTBCR_SL0_SHIFT);
+
 	writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
 
 	/* MAIR0 (stage-1 only) */
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a22c86c867fa..8855ecbc36be 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1768,7 +1768,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	struct dma_pte *first_pte = NULL, *pte = NULL;
 	phys_addr_t uninitialized_var(pteval);
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
-	unsigned long sg_res;
+	unsigned long sg_res = 0;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
 
@@ -1779,10 +1779,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 
 	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
 
-	if (sg)
-		sg_res = 0;
-	else {
-		sg_res = nr_pages + 1;
+	if (!sg) {
+		sg_res = nr_pages;
 		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
 	}
 
@@ -4075,7 +4073,7 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 			     unsigned long iova, size_t size)
 {
 	struct dmar_domain *dmar_domain = domain->priv;
-	int order;
+	int order, iommu_id;
 
 	order = dma_pte_clear_range(dmar_domain, iova >> VTD_PAGE_SHIFT,
 			    (iova + size - 1) >> VTD_PAGE_SHIFT);
@@ -4083,6 +4081,22 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 	if (dmar_domain->max_addr == iova + size)
 		dmar_domain->max_addr = iova;
 
+	for_each_set_bit(iommu_id, dmar_domain->iommu_bmp, g_num_of_iommus) {
+		struct intel_iommu *iommu = g_iommus[iommu_id];
+		int num, ndomains;
+
+		/*
+		 * find bit position of dmar_domain
+		 */
+		ndomains = cap_ndoms(iommu->cap);
+		for_each_set_bit(num, iommu->domain_ids, ndomains) {
+			if (iommu->domains[num] == dmar_domain)
+				iommu_flush_iotlb_psi(iommu, num,
+						      iova >> VTD_PAGE_SHIFT,
+						      1 << order, 0);
+		}
+	}
+
 	return PAGE_SIZE << order;
 }
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 61ffdca96e25..5b55c46fcde8 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -10,6 +10,11 @@ config ARM_GIC
 config GIC_NON_BANKED
 	bool
 
+config ARM_GIC_V3
+	bool
+	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
+
 config ARM_NVIC
 	bool
 	select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 5194afb39e78..4adfda843424 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -13,7 +13,8 @@ obj-$(CONFIG_ARCH_MOXART)		+= irq-moxart.o
 obj-$(CONFIG_ORION_IRQCHIP)		+= irq-orion.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sun4i.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
-obj-$(CONFIG_ARM_GIC)			+= irq-gic.o
+obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
 obj-$(CONFIG_IMGPDC_IRQ)		+= irq-imgpdc.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 540956465ed2..939eb0d8fbf1 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -130,8 +130,7 @@ static int armada_370_xp_setup_msi_irq(struct msi_chip *chip,
 				       struct msi_desc *desc)
 {
 	struct msi_msg msg;
-	irq_hw_number_t hwirq;
-	int virq;
+	int virq, hwirq;
 
 	hwirq = armada_370_xp_alloc_msi();
 	if (hwirq < 0)
@@ -157,8 +156,19 @@ static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip,
 					   unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
+	unsigned long hwirq = d->hwirq;
+
 	irq_dispose_mapping(irq);
-	armada_370_xp_free_msi(d->hwirq);
+	armada_370_xp_free_msi(hwirq);
+}
+
+static int armada_370_xp_check_msi_device(struct msi_chip *chip, struct pci_dev *dev,
+					  int nvec, int type)
+{
+	/* We support MSI, but not MSI-X */
+	if (type == PCI_CAP_ID_MSI)
+		return 0;
+	return -EINVAL;
 }
 
 static struct irq_chip armada_370_xp_msi_irq_chip = {
@@ -199,6 +209,7 @@ static int armada_370_xp_msi_init(struct device_node *node,
 
 	msi_chip->setup_irq = armada_370_xp_setup_msi_irq;
 	msi_chip->teardown_irq = armada_370_xp_teardown_msi_irq;
+	msi_chip->check_device = armada_370_xp_check_msi_device;
 	msi_chip->of_node = node;
 
 	armada_370_xp_msi_domain =
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
new file mode 100644
index 000000000000..60ac704d2090
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include "irq-gic-common.h"
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+		       void __iomem *base, void (*sync_access)(void))
+{
+	u32 enablemask = 1 << (irq % 32);
+	u32 enableoff = (irq / 32) * 4;
+	u32 confmask = 0x2 << ((irq % 16) * 2);
+	u32 confoff = (irq / 16) * 4;
+	bool enabled = false;
+	u32 val;
+
+	/*
+	 * Read current configuration register, and insert the config
+	 * for "irq", depending on "type".
+	 */
+	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
+	if (type == IRQ_TYPE_LEVEL_HIGH)
+		val &= ~confmask;
+	else if (type == IRQ_TYPE_EDGE_RISING)
+		val |= confmask;
+
+	/*
+	 * As recommended by the spec, disable the interrupt before changing
+	 * the configuration
+	 */
+	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
+		if (sync_access)
+			sync_access();
+		enabled = true;
+	}
+
+	/*
+	 * Write back the new configuration, and possibly re-enable
+	 * the interrupt.
+	 */
+	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
+
+	if (enabled)
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+
+	if (sync_access)
+		sync_access();
+}
+
+void __init gic_dist_config(void __iomem *base, int gic_irqs,
+			    void (*sync_access)(void))
+{
+	unsigned int i;
+
+	/*
+	 * Set all global interrupts to be level triggered, active low.
+	 */
+	for (i = 32; i < gic_irqs; i += 16)
+		writel_relaxed(0, base + GIC_DIST_CONFIG + i / 4);
+
+	/*
+	 * Set priority on all global interrupts.
+	 */
+	for (i = 32; i < gic_irqs; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i);
+
+	/*
+	 * Disable all interrupts.  Leave the PPI and SGIs alone
+	 * as they are enabled by redistributor registers.
+	 */
+	for (i = 32; i < gic_irqs; i += 32)
+		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i / 8);
+
+	if (sync_access)
+		sync_access();
+}
+
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
+{
+	int i;
+
+	/*
+	 * Deal with the banked PPI and SGI interrupts - disable all
+	 * PPI interrupts, ensure all SGI interrupts are enabled.
+	 */
+	writel_relaxed(0xffff0000, base + GIC_DIST_ENABLE_CLEAR);
+	writel_relaxed(0x0000ffff, base + GIC_DIST_ENABLE_SET);
+
+	/*
+	 * Set priority on PPI and SGI interrupts
+	 */
+	for (i = 0; i < 32; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+
+	if (sync_access)
+		sync_access();
+}
diff --git a/arch/arm64/include/asm/sigcontext.h b/drivers/irqchip/irq-gic-common.h
index dca1094acc74..b41f02481c3a 100644
--- a/arch/arm64/include/asm/sigcontext.h
+++ b/drivers/irqchip/irq-gic-common.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -13,19 +13,17 @@
  * You should have received a copy of the GNU General Public License
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-#ifndef __ASM_SIGCONTEXT_H
-#define __ASM_SIGCONTEXT_H
 
-#include <uapi/asm/sigcontext.h>
+#ifndef _IRQ_GIC_COMMON_H
+#define _IRQ_GIC_COMMON_H
 
-/*
- * Auxiliary context saved in the sigcontext.__reserved array. Not exported to
- * user space as it will change with the addition of new context. User space
- * should check the magic/size information.
- */
-struct aux_context {
-	struct fpsimd_context fpsimd;
-	/* additional context to be added before "end" */
-	struct _aarch64_ctx end;
-};
-#endif
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+                       void __iomem *base, void (*sync_access)(void));
+void gic_dist_config(void __iomem *base, int gic_irqs,
+		     void (*sync_access)(void));
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void));
+
+#endif /* _IRQ_GIC_COMMON_H */
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
new file mode 100644
index 000000000000..57eaa5a0b1e3
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -0,0 +1,692 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/smp_plat.h>
+
+#include "irq-gic-common.h"
+#include "irqchip.h"
+
+struct gic_chip_data {
+	void __iomem		*dist_base;
+	void __iomem		**redist_base;
+	void __percpu __iomem	**rdist;
+	struct irq_domain	*domain;
+	u64			redist_stride;
+	u32			redist_regions;
+	unsigned int		irq_nr;
+};
+
+static struct gic_chip_data gic_data __read_mostly;
+
+#define gic_data_rdist()		(this_cpu_ptr(gic_data.rdist))
+#define gic_data_rdist_rd_base()	(*gic_data_rdist())
+#define gic_data_rdist_sgi_base()	(gic_data_rdist_rd_base() + SZ_64K)
+
+/* Our default, arbitrary priority value. Linux only uses one anyway. */
+#define DEFAULT_PMR_VALUE	0xf0
+
+static inline unsigned int gic_irq(struct irq_data *d)
+{
+	return d->hwirq;
+}
+
+static inline int gic_irq_in_rdist(struct irq_data *d)
+{
+	return gic_irq(d) < 32;
+}
+
+static inline void __iomem *gic_dist_base(struct irq_data *d)
+{
+	if (gic_irq_in_rdist(d))	/* SGI+PPI -> SGI_base for this CPU */
+		return gic_data_rdist_sgi_base();
+
+	if (d->hwirq <= 1023)		/* SPI -> dist_base */
+		return gic_data.dist_base;
+
+	if (d->hwirq >= 8192)
+		BUG();		/* LPI Detected!!! */
+
+	return NULL;
+}
+
+static void gic_do_wait_for_rwp(void __iomem *base)
+{
+	u32 count = 1000000;	/* 1s! */
+
+	while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("RWP timeout, gone fishing\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/* Wait for completion of a distributor change */
+static void gic_dist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data.dist_base);
+}
+
+/* Wait for completion of a redistributor change */
+static void gic_redist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data_rdist_rd_base());
+}
+
+/* Low level accessors */
+static u64 gic_read_iar(void)
+{
+	u64 irqstat;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	return irqstat;
+}
+
+static void gic_write_pmr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_write_ctlr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_grpen1(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_sgi1r(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_enable_sre(void)
+{
+	u64 val;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	val |= ICC_SRE_EL1_SRE;
+	asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" (val));
+	isb();
+
+	/*
+	 * Need to check that the SRE bit has actually been set. If
+	 * not, it means that SRE is disabled at EL2. We're going to
+	 * die painfully, and there is nothing we can do about it.
+	 *
+	 * Kindly inform the luser.
+	 */
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	if (!(val & ICC_SRE_EL1_SRE))
+		pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
+}
+
+static void gic_enable_redist(void)
+{
+	void __iomem *rbase;
+	u32 count = 1000000;	/* 1s! */
+	u32 val;
+
+	rbase = gic_data_rdist_rd_base();
+
+	/* Wake up this CPU redistributor */
+	val = readl_relaxed(rbase + GICR_WAKER);
+	val &= ~GICR_WAKER_ProcessorSleep;
+	writel_relaxed(val, rbase + GICR_WAKER);
+
+	while (readl_relaxed(rbase + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("redist didn't wake up...\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/*
+ * Routines to disable, enable, EOI and route interrupts
+ */
+static void gic_poke_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	writel_relaxed(mask, base + offset + (gic_irq(d) / 32) * 4);
+	rwp_wait();
+}
+
+static int gic_peek_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d))
+		base = gic_data_rdist_sgi_base();
+	else
+		base = gic_data.dist_base;
+
+	return !!(readl_relaxed(base + offset + (gic_irq(d) / 32) * 4) & mask);
+}
+
+static void gic_mask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ICENABLER);
+}
+
+static void gic_unmask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ISENABLER);
+}
+
+static void gic_eoi_irq(struct irq_data *d)
+{
+	gic_write_eoir(gic_irq(d));
+}
+
+static int gic_set_type(struct irq_data *d, unsigned int type)
+{
+	unsigned int irq = gic_irq(d);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	/* Interrupt configuration for SGIs can't be changed */
+	if (irq < 16)
+		return -EINVAL;
+
+	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+		return -EINVAL;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	gic_configure_irq(irq, type, base, rwp_wait);
+
+	return 0;
+}
+
+static u64 gic_mpidr_to_affinity(u64 mpidr)
+{
+	u64 aff;
+
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8  |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	return aff;
+}
+
+static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+{
+	u64 irqnr;
+
+	do {
+		irqnr = gic_read_iar();
+
+		if (likely(irqnr > 15 && irqnr < 1020)) {
+			u64 irq = irq_find_mapping(gic_data.domain, irqnr);
+			if (likely(irq)) {
+				handle_IRQ(irq, regs);
+				continue;
+			}
+
+			WARN_ONCE(true, "Unexpected SPI received!\n");
+			gic_write_eoir(irqnr);
+		}
+		if (irqnr < 16) {
+			gic_write_eoir(irqnr);
+#ifdef CONFIG_SMP
+			handle_IPI(irqnr, regs);
+#else
+			WARN_ONCE(true, "Unexpected SGI received!\n");
+#endif
+			continue;
+		}
+	} while (irqnr != ICC_IAR1_EL1_SPURIOUS);
+}
+
+static void __init gic_dist_init(void)
+{
+	unsigned int i;
+	u64 affinity;
+	void __iomem *base = gic_data.dist_base;
+
+	/* Disable the distributor */
+	writel_relaxed(0, base + GICD_CTLR);
+	gic_dist_wait_for_rwp();
+
+	gic_dist_config(base, gic_data.irq_nr, gic_dist_wait_for_rwp);
+
+	/* Enable distributor with ARE, Group1 */
+	writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1,
+		       base + GICD_CTLR);
+
+	/*
+	 * Set all global interrupts to the boot CPU only. ARE must be
+	 * enabled.
+	 */
+	affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id()));
+	for (i = 32; i < gic_data.irq_nr; i++)
+		writeq_relaxed(affinity, base + GICD_IROUTER + i * 8);
+}
+
+static int gic_populate_rdist(void)
+{
+	u64 mpidr = cpu_logical_map(smp_processor_id());
+	u64 typer;
+	u32 aff;
+	int i;
+
+	/*
+	 * Convert affinity to a 32bit value that can be matched to
+	 * GICR_TYPER bits [63:32].
+	 */
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	for (i = 0; i < gic_data.redist_regions; i++) {
+		void __iomem *ptr = gic_data.redist_base[i];
+		u32 reg;
+
+		reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
+		if (reg != GIC_PIDR2_ARCH_GICv3 &&
+		    reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */
+			pr_warn("No redistributor present @%p\n", ptr);
+			break;
+		}
+
+		do {
+			typer = readq_relaxed(ptr + GICR_TYPER);
+			if ((typer >> 32) == aff) {
+				gic_data_rdist_rd_base() = ptr;
+				pr_info("CPU%d: found redistributor %llx @%p\n",
+					smp_processor_id(),
+					(unsigned long long)mpidr, ptr);
+				return 0;
+			}
+
+			if (gic_data.redist_stride) {
+				ptr += gic_data.redist_stride;
+			} else {
+				ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */
+				if (typer & GICR_TYPER_VLPIS)
+					ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */
+			}
+		} while (!(typer & GICR_TYPER_LAST));
+	}
+
+	/* We couldn't even deal with ourselves... */
+	WARN(true, "CPU%d: mpidr %llx has no re-distributor!\n",
+	     smp_processor_id(), (unsigned long long)mpidr);
+	return -ENODEV;
+}
+
+static void gic_cpu_init(void)
+{
+	void __iomem *rbase;
+
+	/* Register ourselves with the rest of the world */
+	if (gic_populate_rdist())
+		return;
+
+	gic_enable_redist();
+
+	rbase = gic_data_rdist_sgi_base();
+
+	gic_cpu_config(rbase, gic_redist_wait_for_rwp);
+
+	/* Enable system registers */
+	gic_enable_sre();
+
+	/* Set priority mask register */
+	gic_write_pmr(DEFAULT_PMR_VALUE);
+
+	/* EOI deactivates interrupt too (mode 0) */
+	gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
+
+	/* ... and let's hit the road... */
+	gic_write_grpen1(1);
+}
+
+#ifdef CONFIG_SMP
+static int gic_secondary_init(struct notifier_block *nfb,
+			      unsigned long action, void *hcpu)
+{
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		gic_cpu_init();
+	return NOTIFY_OK;
+}
+
+/*
+ * Notifier for enabling the GIC CPU interface. Set an arbitrarily high
+ * priority because the GIC needs to be up before the ARM generic timers.
+ */
+static struct notifier_block gic_cpu_notifier = {
+	.notifier_call = gic_secondary_init,
+	.priority = 100,
+};
+
+static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
+				   u64 cluster_id)
+{
+	int cpu = *base_cpu;
+	u64 mpidr = cpu_logical_map(cpu);
+	u16 tlist = 0;
+
+	while (cpu < nr_cpu_ids) {
+		/*
+		 * If we ever get a cluster of more than 16 CPUs, just
+		 * scream and skip that CPU.
+		 */
+		if (WARN_ON((mpidr & 0xff) >= 16))
+			goto out;
+
+		tlist |= 1 << (mpidr & 0xf);
+
+		cpu = cpumask_next(cpu, mask);
+		if (cpu == nr_cpu_ids)
+			goto out;
+
+		mpidr = cpu_logical_map(cpu);
+
+		if (cluster_id != (mpidr & ~0xffUL)) {
+			cpu--;
+			goto out;
+		}
+	}
+out:
+	*base_cpu = cpu;
+	return tlist;
+}
+
+static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
+{
+	u64 val;
+
+	val = (MPIDR_AFFINITY_LEVEL(cluster_id, 3) << 48	|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 2) << 32	|
+	       irq << 24			    		|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 1) << 16	|
+	       tlist);
+
+	pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
+	gic_write_sgi1r(val);
+}
+
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+{
+	int cpu;
+
+	if (WARN_ON(irq >= 16))
+		return;
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	smp_wmb();
+
+	for_each_cpu_mask(cpu, *mask) {
+		u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL;
+		u16 tlist;
+
+		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
+		gic_send_sgi(cluster_id, tlist, irq);
+	}
+
+	/* Force the above writes to ICC_SGI1R_EL1 to be executed */
+	isb();
+}
+
+static void gic_smp_init(void)
+{
+	set_smp_cross_call(gic_raise_softirq);
+	register_cpu_notifier(&gic_cpu_notifier);
+}
+
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+			    bool force)
+{
+	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	void __iomem *reg;
+	int enabled;
+	u64 val;
+
+	if (gic_irq_in_rdist(d))
+		return -EINVAL;
+
+	/* If interrupt was enabled, disable it first */
+	enabled = gic_peek_irq(d, GICD_ISENABLER);
+	if (enabled)
+		gic_mask_irq(d);
+
+	reg = gic_dist_base(d) + GICD_IROUTER + (gic_irq(d) * 8);
+	val = gic_mpidr_to_affinity(cpu_logical_map(cpu));
+
+	writeq_relaxed(val, reg);
+
+	/*
+	 * If the interrupt was enabled, enabled it again. Otherwise,
+	 * just wait for the distributor to have digested our changes.
+	 */
+	if (enabled)
+		gic_unmask_irq(d);
+	else
+		gic_dist_wait_for_rwp();
+
+	return IRQ_SET_MASK_OK;
+}
+#else
+#define gic_set_affinity	NULL
+#define gic_smp_init()		do { } while(0)
+#endif
+
+static struct irq_chip gic_chip = {
+	.name			= "GICv3",
+	.irq_mask		= gic_mask_irq,
+	.irq_unmask		= gic_unmask_irq,
+	.irq_eoi		= gic_eoi_irq,
+	.irq_set_type		= gic_set_type,
+	.irq_set_affinity	= gic_set_affinity,
+};
+
+static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	/* SGIs are private to the core kernel */
+	if (hw < 16)
+		return -EPERM;
+	/* PPIs */
+	if (hw < 32) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_percpu_devid_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+	}
+	/* SPIs */
+	if (hw >= 32 && hw < gic_data.irq_nr) {
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_fasteoi_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	}
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static int gic_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 3)
+		return -EINVAL;
+
+	switch(intspec[0]) {
+	case 0:			/* SPI */
+		*out_hwirq = intspec[1] + 32;
+		break;
+	case 1:			/* PPI */
+		*out_hwirq = intspec[1] + 16;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+
+static const struct irq_domain_ops gic_irq_domain_ops = {
+	.map = gic_irq_domain_map,
+	.xlate = gic_irq_domain_xlate,
+};
+
+static int __init gic_of_init(struct device_node *node, struct device_node *parent)
+{
+	void __iomem *dist_base;
+	void __iomem **redist_base;
+	u64 redist_stride;
+	u32 redist_regions;
+	u32 reg;
+	int gic_irqs;
+	int err;
+	int i;
+
+	dist_base = of_iomap(node, 0);
+	if (!dist_base) {
+		pr_err("%s: unable to map gic dist registers\n",
+			node->full_name);
+		return -ENXIO;
+	}
+
+	reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+	if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) {
+		pr_err("%s: no distributor detected, giving up\n",
+			node->full_name);
+		err = -ENODEV;
+		goto out_unmap_dist;
+	}
+
+	if (of_property_read_u32(node, "#redistributor-regions", &redist_regions))
+		redist_regions = 1;
+
+	redist_base = kzalloc(sizeof(*redist_base) * redist_regions, GFP_KERNEL);
+	if (!redist_base) {
+		err = -ENOMEM;
+		goto out_unmap_dist;
+	}
+
+	for (i = 0; i < redist_regions; i++) {
+		redist_base[i] = of_iomap(node, 1 + i);
+		if (!redist_base[i]) {
+			pr_err("%s: couldn't map region %d\n",
+			       node->full_name, i);
+			err = -ENODEV;
+			goto out_unmap_rdist;
+		}
+	}
+
+	if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
+		redist_stride = 0;
+
+	gic_data.dist_base = dist_base;
+	gic_data.redist_base = redist_base;
+	gic_data.redist_regions = redist_regions;
+	gic_data.redist_stride = redist_stride;
+
+	/*
+	 * Find out how many interrupts are supported.
+	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
+	 */
+	gic_irqs = readl_relaxed(gic_data.dist_base + GICD_TYPER) & 0x1f;
+	gic_irqs = (gic_irqs + 1) * 32;
+	if (gic_irqs > 1020)
+		gic_irqs = 1020;
+	gic_data.irq_nr = gic_irqs;
+
+	gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops,
+					      &gic_data);
+	gic_data.rdist = alloc_percpu(typeof(*gic_data.rdist));
+
+	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdist)) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	set_handle_irq(gic_handle_irq);
+
+	gic_smp_init();
+	gic_dist_init();
+	gic_cpu_init();
+
+	return 0;
+
+out_free:
+	if (gic_data.domain)
+		irq_domain_remove(gic_data.domain);
+	free_percpu(gic_data.rdist);
+out_unmap_rdist:
+	for (i = 0; i < redist_regions; i++)
+		if (redist_base[i])
+			iounmap(redist_base[i]);
+	kfree(redist_base);
+out_unmap_dist:
+	iounmap(dist_base);
+	return err;
+}
+
+IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 341c6016812d..4b959e606fe8 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/arm/common/gic.c
- *
  *  Copyright (C) 2002 ARM Limited, All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -42,15 +40,17 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/arm-gic.h>
 
+#include <asm/cputype.h>
 #include <asm/irq.h>
 #include <asm/exception.h>
 #include <asm/smp_plat.h>
 
+#include "irq-gic-common.h"
 #include "irqchip.h"
 
 union gic_base {
 	void __iomem *common_base;
-	void __percpu __iomem **percpu_base;
+	void __percpu * __iomem *percpu_base;
 };
 
 struct gic_chip_data {
@@ -188,12 +188,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 {
 	void __iomem *base = gic_dist_base(d);
 	unsigned int gicirq = gic_irq(d);
-	u32 enablemask = 1 << (gicirq % 32);
-	u32 enableoff = (gicirq / 32) * 4;
-	u32 confmask = 0x2 << ((gicirq % 16) * 2);
-	u32 confoff = (gicirq / 16) * 4;
-	bool enabled = false;
-	u32 val;
 
 	/* Interrupt configuration for SGIs can't be changed */
 	if (gicirq < 16)
@@ -207,25 +201,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
 
-	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
-	if (type == IRQ_TYPE_LEVEL_HIGH)
-		val &= ~confmask;
-	else if (type == IRQ_TYPE_EDGE_RISING)
-		val |= confmask;
-
-	/*
-	 * As recommended by the spec, disable the interrupt before changing
-	 * the configuration
-	 */
-	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
-		enabled = true;
-	}
-
-	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
-
-	if (enabled)
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+	gic_configure_irq(gicirq, type, base, NULL);
 
 	raw_spin_unlock(&irq_controller_lock);
 
@@ -246,10 +222,14 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
-	unsigned int shift = (gic_irq(d) % 4) * 8;
-	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	unsigned int cpu, shift = (gic_irq(d) % 4) * 8;
 	u32 val, mask, bit;
 
+	if (!force)
+		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	else
+		cpu = cpumask_first(mask_val);
+
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
@@ -279,7 +259,7 @@ static int gic_set_wake(struct irq_data *d, unsigned int on)
 #define gic_set_wake	NULL
 #endif
 
-static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
 	u32 irqstat, irqnr;
 	struct gic_chip_data *gic = &gic_data[0];
@@ -287,7 +267,7 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 
 	do {
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
-		irqnr = irqstat & ~0x1c00;
+		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
 		if (likely(irqnr > 15 && irqnr < 1021)) {
 			irqnr = irq_find_mapping(gic->domain, irqnr);
@@ -383,12 +363,6 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	writel_relaxed(0, base + GIC_DIST_CTRL);
 
 	/*
-	 * Set all global interrupts to be level triggered, active low.
-	 */
-	for (i = 32; i < gic_irqs; i += 16)
-		writel_relaxed(0, base + GIC_DIST_CONFIG + i * 4 / 16);
-
-	/*
 	 * Set all global interrupts to this CPU only.
 	 */
 	cpumask = gic_get_cpumask(gic);
@@ -397,18 +371,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
-	/*
-	 * Set priority on all global interrupts.
-	 */
-	for (i = 32; i < gic_irqs; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
-
-	/*
-	 * Disable all interrupts.  Leave the PPI and SGIs alone
-	 * as these enables are banked registers.
-	 */
-	for (i = 32; i < gic_irqs; i += 32)
-		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
+	gic_dist_config(base, gic_irqs, NULL);
 
 	writel_relaxed(1, base + GIC_DIST_CTRL);
 }
@@ -435,18 +398,7 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 		if (i != cpu)
 			gic_cpu_map[i] &= ~cpu_mask;
 
-	/*
-	 * Deal with the banked PPI and SGI interrupts - disable all
-	 * PPI interrupts, ensure all SGI interrupts are enabled.
-	 */
-	writel_relaxed(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
-	writel_relaxed(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
-
-	/*
-	 * Set priority on PPI and SGI interrupts
-	 */
-	for (i = 0; i < 32; i += 4)
-		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
+	gic_cpu_config(dist_base, NULL);
 
 	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
 	writel_relaxed(1, base + GIC_CPU_CTRL);
@@ -648,7 +600,7 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 #endif
 
 #ifdef CONFIG_SMP
-void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	int cpu;
 	unsigned long flags, map = 0;
@@ -661,9 +613,9 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 	/*
 	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before issuing the IPI.
+	 * other CPUs before they observe us issuing the IPI.
 	 */
-	dsb();
+	dmb(ishst);
 
 	/* this always happens on GIC0 */
 	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
@@ -824,16 +776,25 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 		irq_set_chip_and_handler(irq, &gic_chip,
 					 handle_fasteoi_irq);
 		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+
+		gic_routable_irq_domain_ops->map(d, irq, hw);
 	}
 	irq_set_chip_data(irq, d->host_data);
 	return 0;
 }
 
+static void gic_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	gic_routable_irq_domain_ops->unmap(d, irq);
+}
+
 static int gic_irq_domain_xlate(struct irq_domain *d,
 				struct device_node *controller,
 				const u32 *intspec, unsigned int intsize,
 				unsigned long *out_hwirq, unsigned int *out_type)
 {
+	unsigned long ret = 0;
+
 	if (d->of_node != controller)
 		return -EINVAL;
 	if (intsize < 3)
@@ -843,11 +804,20 @@ static int gic_irq_domain_xlate(struct irq_domain *d,
 	*out_hwirq = intspec[1] + 16;
 
 	/* For SPIs, we need to add 16 more to get the GIC irq ID number */
-	if (!intspec[0])
-		*out_hwirq += 16;
+	if (!intspec[0]) {
+		ret = gic_routable_irq_domain_ops->xlate(d, controller,
+							 intspec,
+							 intsize,
+							 out_hwirq,
+							 out_type);
+
+		if (IS_ERR_VALUE(ret))
+			return ret;
+	}
 
 	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
-	return 0;
+
+	return ret;
 }
 
 #ifdef CONFIG_SMP
@@ -869,11 +839,43 @@ static struct notifier_block gic_cpu_notifier = {
 };
 #endif
 
-const struct irq_domain_ops gic_irq_domain_ops = {
+static const struct irq_domain_ops gic_irq_domain_ops = {
 	.map = gic_irq_domain_map,
+	.unmap = gic_irq_domain_unmap,
 	.xlate = gic_irq_domain_xlate,
 };
 
+/* Default functions for routable irq domain */
+static int gic_routable_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	return 0;
+}
+
+static void gic_routable_irq_domain_unmap(struct irq_domain *d,
+					  unsigned int irq)
+{
+}
+
+static int gic_routable_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq,
+				unsigned int *out_type)
+{
+	*out_hwirq += 16;
+	return 0;
+}
+
+const struct irq_domain_ops gic_default_routable_irq_domain_ops = {
+	.map = gic_routable_irq_domain_map,
+	.unmap = gic_routable_irq_domain_unmap,
+	.xlate = gic_routable_irq_domain_xlate,
+};
+
+const struct irq_domain_ops *gic_routable_irq_domain_ops =
+					&gic_default_routable_irq_domain_ops;
+
 void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 			   void __iomem *dist_base, void __iomem *cpu_base,
 			   u32 percpu_offset, struct device_node *node)
@@ -881,6 +883,7 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	irq_hw_number_t hwirq_base;
 	struct gic_chip_data *gic;
 	int gic_irqs, irq_base, i;
+	int nr_routable_irqs;
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
@@ -899,7 +902,9 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 		}
 
 		for_each_possible_cpu(cpu) {
-			unsigned long offset = percpu_offset * cpu_logical_map(cpu);
+			u32 mpidr = cpu_logical_map(cpu);
+			u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+			unsigned long offset = percpu_offset * core_id;
 			*per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset;
 			*per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset;
 		}
@@ -946,14 +951,25 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	gic->gic_irqs = gic_irqs;
 
 	gic_irqs -= hwirq_base; /* calculate # of irqs to allocate */
-	irq_base = irq_alloc_descs(irq_start, 16, gic_irqs, numa_node_id());
-	if (IS_ERR_VALUE(irq_base)) {
-		WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
-		     irq_start);
-		irq_base = irq_start;
+
+	if (of_property_read_u32(node, "arm,routable-irqs",
+				 &nr_routable_irqs)) {
+		irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
+					   numa_node_id());
+		if (IS_ERR_VALUE(irq_base)) {
+			WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+			     irq_start);
+			irq_base = irq_start;
+		}
+
+		gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
+					hwirq_base, &gic_irq_domain_ops, gic);
+	} else {
+		gic->domain = irq_domain_add_linear(node, nr_routable_irqs,
+						    &gic_irq_domain_ops,
+						    gic);
 	}
-	gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
-				    hwirq_base, &gic_irq_domain_ops, gic);
+
 	if (WARN_ON(!gic->domain))
 		return;
 
@@ -974,7 +990,8 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 #ifdef CONFIG_OF
 static int gic_cnt __initdata;
 
-int __init gic_of_init(struct device_node *node, struct device_node *parent)
+static int __init
+gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *cpu_base;
 	void __iomem *dist_base;
@@ -1004,8 +1021,10 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 	gic_cnt++;
 	return 0;
 }
+IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init);
 IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init);
 IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init);
+IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
 IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
 IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
 
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 8527743b5cef..391b9cea73ed 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -125,7 +125,7 @@ static struct spear_shirq spear320_shirq_ras2 = {
 };
 
 static struct spear_shirq spear320_shirq_ras3 = {
-	.irq_nr = 3,
+	.irq_nr = 7,
 	.irq_bit_off = 0,
 	.invalid_irq = 1,
 	.regs = {
diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c
index 02125e6a9109..5a4da94aefb0 100644
--- a/drivers/isdn/isdnloop/isdnloop.c
+++ b/drivers/isdn/isdnloop/isdnloop.c
@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] =
 static void
 isdnloop_fake_err(isdnloop_card *card)
 {
-	char buf[60];
+	char buf[64];
 
-	sprintf(buf, "E%s", card->omsg);
+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
 	isdnloop_fake(card, buf, -1);
 	isdnloop_fake(card, "NAK", -1);
 }
@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card *card)
 	case 7:
 		/* 0x;EAZ */
 		p += 3;
+		if (strlen(p) >= sizeof(card->eazlist[0]))
+			break;
 		strcpy(card->eazlist[ch - 1], p);
 		break;
 	case 8:
@@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
 		return -EBUSY;
 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
 		return -EFAULT;
+
+	for (i = 0; i < 3; i++) {
+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+			return -EINVAL;
+	}
+
 	spin_lock_irqsave(&card->isdnloop_lock, flags);
 	switch (sdef.ptype) {
 	case ISDN_PTYPE_EURO:
@@ -1127,7 +1135,7 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 {
 	ulong a;
 	int i;
-	char cbuf[60];
+	char cbuf[80];
 	isdn_ctrl cmd;
 	isdnloop_cdef cdef;
 
@@ -1192,7 +1200,6 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			break;
 		if ((c->arg & 255) < ISDNLOOP_BCH) {
 			char *p;
-			char dial[50];
 			char dcode[4];
 
 			a = c->arg;
@@ -1204,10 +1211,10 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
 			} else
 				/* Normal Dial */
 				strcpy(dcode, "CAL");
-			strcpy(dial, p);
-			sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-				dcode, dial, c->parm.setup.si1,
-				c->parm.setup.si2, c->parm.setup.eazmsn);
+			snprintf(cbuf, sizeof(cbuf),
+				 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+				 dcode, p, c->parm.setup.si1,
+				 c->parm.setup.si2, c->parm.setup.eazmsn);
 			i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
 		}
 		break;
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index 605047428b5a..a7b369fc3554 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -84,6 +84,15 @@ static inline size_t sizeof_pwm_leds_priv(int num_leds)
 		      (sizeof(struct led_pwm_data) * num_leds);
 }
 
+static void led_pwm_cleanup(struct led_pwm_priv *priv)
+{
+	while (priv->num_leds--) {
+		led_classdev_unregister(&priv->leds[priv->num_leds].cdev);
+		if (priv->leds[priv->num_leds].can_sleep)
+			cancel_work_sync(&priv->leds[priv->num_leds].work);
+	}
+}
+
 static int led_pwm_create_of(struct platform_device *pdev,
 			     struct led_pwm_priv *priv)
 {
@@ -131,8 +140,7 @@ static int led_pwm_create_of(struct platform_device *pdev,
 
 	return 0;
 err:
-	while (priv->num_leds--)
-		led_classdev_unregister(&priv->leds[priv->num_leds].cdev);
+	led_pwm_cleanup(priv);
 
 	return ret;
 }
@@ -200,8 +208,8 @@ static int led_pwm_probe(struct platform_device *pdev)
 	return 0;
 
 err:
-	while (i--)
-		led_classdev_unregister(&priv->leds[i].cdev);
+	priv->num_leds = i;
+	led_pwm_cleanup(priv);
 
 	return ret;
 }
@@ -209,13 +217,8 @@ err:
 static int led_pwm_remove(struct platform_device *pdev)
 {
 	struct led_pwm_priv *priv = platform_get_drvdata(pdev);
-	int i;
 
-	for (i = 0; i < priv->num_leds; i++) {
-		led_classdev_unregister(&priv->leds[i].cdev);
-		if (priv->leds[i].can_sleep)
-			cancel_work_sync(&priv->leds[i].work);
-	}
+	led_pwm_cleanup(priv);
 
 	return 0;
 }
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index e0facb34084a..2fa343a196f3 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -1,3 +1,7 @@
+# Generic MAILBOX API
+
+obj-$(CONFIG_MAILBOX)		+= mailbox.o
+
 obj-$(CONFIG_PL320_MBOX)	+= pl320-ipc.o
 
 obj-$(CONFIG_OMAP_MBOX)		+= omap-mailbox.o
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
new file mode 100644
index 000000000000..afcb430508ec
--- /dev/null
+++ b/drivers/mailbox/mailbox.c
@@ -0,0 +1,465 @@
+/*
+ * Mailbox: Common code for Mailbox controllers and users
+ *
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ * Author: Jassi Brar <jassisinghbrar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/bitops.h>
+#include <linux/mailbox_client.h>
+#include <linux/mailbox_controller.h>
+
+#define TXDONE_BY_IRQ	BIT(0) /* controller has remote RTR irq */
+#define TXDONE_BY_POLL	BIT(1) /* controller can read status of last TX */
+#define TXDONE_BY_ACK	BIT(2) /* S/W ACK recevied by Client ticks the TX */
+
+static LIST_HEAD(mbox_cons);
+static DEFINE_MUTEX(con_mutex);
+
+static int add_to_rbuf(struct mbox_chan *chan, void *mssg)
+{
+	int idx;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	/* See if there is any space left */
+	if (chan->msg_count == MBOX_TX_QUEUE_LEN) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -ENOBUFS;
+	}
+
+	idx = chan->msg_free;
+	chan->msg_data[idx] = mssg;
+	chan->msg_count++;
+
+	if (idx == MBOX_TX_QUEUE_LEN - 1)
+		chan->msg_free = 0;
+	else
+		chan->msg_free++;
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return idx;
+}
+
+static void msg_submit(struct mbox_chan *chan)
+{
+	unsigned count, idx;
+	unsigned long flags;
+	void *data;
+	int err;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	if (!chan->msg_count || chan->active_req)
+		goto exit;
+
+	count = chan->msg_count;
+	idx = chan->msg_free;
+	if (idx >= count)
+		idx -= count;
+	else
+		idx += MBOX_TX_QUEUE_LEN - count;
+
+	data = chan->msg_data[idx];
+
+	/* Try to submit a message to the MBOX controller */
+	err = chan->mbox->ops->send_data(chan, data);
+	if (!err) {
+		chan->active_req = data;
+		chan->msg_count--;
+	}
+exit:
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+static void tx_tick(struct mbox_chan *chan, int r)
+{
+	unsigned long flags;
+	void *mssg;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	mssg = chan->active_req;
+	chan->active_req = NULL;
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	/* Submit next message */
+	msg_submit(chan);
+
+	/* Notify the client */
+	if (mssg && chan->cl->tx_done)
+		chan->cl->tx_done(chan->cl, mssg, r);
+
+	if (chan->cl->tx_block)
+		complete(&chan->tx_complete);
+}
+
+static void poll_txdone(unsigned long data)
+{
+	struct mbox_controller *mbox = (struct mbox_controller *)data;
+	bool txdone, resched = false;
+	int i;
+
+	for (i = 0; i < mbox->num_chans; i++) {
+		struct mbox_chan *chan = &mbox->chans[i];
+
+		if (chan->active_req && chan->cl) {
+			resched = true;
+			txdone = chan->mbox->ops->last_tx_done(chan);
+			if (txdone)
+				tx_tick(chan, 0);
+		}
+	}
+
+	if (resched)
+		mod_timer(&mbox->poll, jiffies +
+				msecs_to_jiffies(mbox->txpoll_period));
+}
+
+/**
+ * mbox_chan_received_data - A way for controller driver to push data
+ *				received from remote to the upper layer.
+ * @chan: Pointer to the mailbox channel on which RX happened.
+ * @mssg: Client specific message typecasted as void *
+ *
+ * After startup and before shutdown any data received on the chan
+ * is passed on to the API via atomic mbox_chan_received_data().
+ * The controller should ACK the RX only after this call returns.
+ */
+void mbox_chan_received_data(struct mbox_chan *chan, void *mssg)
+{
+	/* No buffering the received data */
+	if (chan->cl->rx_callback)
+		chan->cl->rx_callback(chan->cl, mssg);
+}
+EXPORT_SYMBOL_GPL(mbox_chan_received_data);
+
+/**
+ * mbox_chan_txdone - A way for controller driver to notify the
+ *			framework that the last TX has completed.
+ * @chan: Pointer to the mailbox chan on which TX happened.
+ * @r: Status of last TX - OK or ERROR
+ *
+ * The controller that has IRQ for TX ACK calls this atomic API
+ * to tick the TX state machine. It works only if txdone_irq
+ * is set by the controller.
+ */
+void mbox_chan_txdone(struct mbox_chan *chan, int r)
+{
+	if (unlikely(!(chan->txdone_method & TXDONE_BY_IRQ))) {
+		dev_err(chan->mbox->dev,
+		       "Controller can't run the TX ticker\n");
+		return;
+	}
+
+	tx_tick(chan, r);
+}
+EXPORT_SYMBOL_GPL(mbox_chan_txdone);
+
+/**
+ * mbox_client_txdone - The way for a client to run the TX state machine.
+ * @chan: Mailbox channel assigned to this client.
+ * @r: Success status of last transmission.
+ *
+ * The client/protocol had received some 'ACK' packet and it notifies
+ * the API that the last packet was sent successfully. This only works
+ * if the controller can't sense TX-Done.
+ */
+void mbox_client_txdone(struct mbox_chan *chan, int r)
+{
+	if (unlikely(!(chan->txdone_method & TXDONE_BY_ACK))) {
+		dev_err(chan->mbox->dev, "Client can't run the TX ticker\n");
+		return;
+	}
+
+	tx_tick(chan, r);
+}
+EXPORT_SYMBOL_GPL(mbox_client_txdone);
+
+/**
+ * mbox_client_peek_data - A way for client driver to pull data
+ *			received from remote by the controller.
+ * @chan: Mailbox channel assigned to this client.
+ *
+ * A poke to controller driver for any received data.
+ * The data is actually passed onto client via the
+ * mbox_chan_received_data()
+ * The call can be made from atomic context, so the controller's
+ * implementation of peek_data() must not sleep.
+ *
+ * Return: True, if controller has, and is going to push after this,
+ *          some data.
+ *         False, if controller doesn't have any data to be read.
+ */
+bool mbox_client_peek_data(struct mbox_chan *chan)
+{
+	if (chan->mbox->ops->peek_data)
+		return chan->mbox->ops->peek_data(chan);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(mbox_client_peek_data);
+
+/**
+ * mbox_send_message -	For client to submit a message to be
+ *				sent to the remote.
+ * @chan: Mailbox channel assigned to this client.
+ * @mssg: Client specific message typecasted.
+ *
+ * For client to submit data to the controller destined for a remote
+ * processor. If the client had set 'tx_block', the call will return
+ * either when the remote receives the data or when 'tx_tout' millisecs
+ * run out.
+ *  In non-blocking mode, the requests are buffered by the API and a
+ * non-negative token is returned for each queued request. If the request
+ * is not queued, a negative token is returned. Upon failure or successful
+ * TX, the API calls 'tx_done' from atomic context, from which the client
+ * could submit yet another request.
+ * The pointer to message should be preserved until it is sent
+ * over the chan, i.e, tx_done() is made.
+ * This function could be called from atomic context as it simply
+ * queues the data and returns a token against the request.
+ *
+ * Return: Non-negative integer for successful submission (non-blocking mode)
+ *	or transmission over chan (blocking mode).
+ *	Negative value denotes failure.
+ */
+int mbox_send_message(struct mbox_chan *chan, void *mssg)
+{
+	int t;
+
+	if (!chan || !chan->cl)
+		return -EINVAL;
+
+	t = add_to_rbuf(chan, mssg);
+	if (t < 0) {
+		dev_err(chan->mbox->dev, "Try increasing MBOX_TX_QUEUE_LEN\n");
+		return t;
+	}
+
+	msg_submit(chan);
+
+	if (chan->txdone_method	== TXDONE_BY_POLL)
+		poll_txdone((unsigned long)chan->mbox);
+
+	if (chan->cl->tx_block && chan->active_req) {
+		unsigned long wait;
+		int ret;
+
+		if (!chan->cl->tx_tout) /* wait forever */
+			wait = msecs_to_jiffies(3600000);
+		else
+			wait = msecs_to_jiffies(chan->cl->tx_tout);
+
+		ret = wait_for_completion_timeout(&chan->tx_complete, wait);
+		if (ret == 0) {
+			t = -EIO;
+			tx_tick(chan, -EIO);
+		}
+	}
+
+	return t;
+}
+EXPORT_SYMBOL_GPL(mbox_send_message);
+
+/**
+ * mbox_request_channel - Request a mailbox channel.
+ * @cl: Identity of the client requesting the channel.
+ * @index: Index of mailbox specifier in 'mboxes' property.
+ *
+ * The Client specifies its requirements and capabilities while asking for
+ * a mailbox channel. It can't be called from atomic context.
+ * The channel is exclusively allocated and can't be used by another
+ * client before the owner calls mbox_free_channel.
+ * After assignment, any packet received on this channel will be
+ * handed over to the client via the 'rx_callback'.
+ * The framework holds reference to the client, so the mbox_client
+ * structure shouldn't be modified until the mbox_free_channel returns.
+ *
+ * Return: Pointer to the channel assigned to the client if successful.
+ *		ERR_PTR for request failure.
+ */
+struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index)
+{
+	struct device *dev = cl->dev;
+	struct mbox_controller *mbox;
+	struct of_phandle_args spec;
+	struct mbox_chan *chan;
+	unsigned long flags;
+	int ret;
+
+	if (!dev || !dev->of_node) {
+		pr_debug("%s: No owner device node\n", __func__);
+		return ERR_PTR(-ENODEV);
+	}
+
+	mutex_lock(&con_mutex);
+
+	if (of_parse_phandle_with_args(dev->of_node, "mboxes",
+				       "#mbox-cells", index, &spec)) {
+		dev_dbg(dev, "%s: can't parse \"mboxes\" property\n", __func__);
+		mutex_unlock(&con_mutex);
+		return ERR_PTR(-ENODEV);
+	}
+
+	chan = NULL;
+	list_for_each_entry(mbox, &mbox_cons, node)
+		if (mbox->dev->of_node == spec.np) {
+			chan = mbox->of_xlate(mbox, &spec);
+			break;
+		}
+
+	of_node_put(spec.np);
+
+	if (!chan || chan->cl || !try_module_get(mbox->dev->driver->owner)) {
+		dev_dbg(dev, "%s: mailbox not free\n", __func__);
+		mutex_unlock(&con_mutex);
+		return ERR_PTR(-EBUSY);
+	}
+
+	spin_lock_irqsave(&chan->lock, flags);
+	chan->msg_free = 0;
+	chan->msg_count = 0;
+	chan->active_req = NULL;
+	chan->cl = cl;
+	init_completion(&chan->tx_complete);
+
+	if (chan->txdone_method	== TXDONE_BY_POLL && cl->knows_txdone)
+		chan->txdone_method |= TXDONE_BY_ACK;
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	ret = chan->mbox->ops->startup(chan);
+	if (ret) {
+		dev_err(dev, "Unable to startup the chan (%d)\n", ret);
+		mbox_free_channel(chan);
+		chan = ERR_PTR(ret);
+	}
+
+	mutex_unlock(&con_mutex);
+	return chan;
+}
+EXPORT_SYMBOL_GPL(mbox_request_channel);
+
+/**
+ * mbox_free_channel - The client relinquishes control of a mailbox
+ *			channel by this call.
+ * @chan: The mailbox channel to be freed.
+ */
+void mbox_free_channel(struct mbox_chan *chan)
+{
+	unsigned long flags;
+
+	if (!chan || !chan->cl)
+		return;
+
+	chan->mbox->ops->shutdown(chan);
+
+	/* The queued TX requests are simply aborted, no callbacks are made */
+	spin_lock_irqsave(&chan->lock, flags);
+	chan->cl = NULL;
+	chan->active_req = NULL;
+	if (chan->txdone_method == (TXDONE_BY_POLL | TXDONE_BY_ACK))
+		chan->txdone_method = TXDONE_BY_POLL;
+
+	module_put(chan->mbox->dev->driver->owner);
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+EXPORT_SYMBOL_GPL(mbox_free_channel);
+
+static struct mbox_chan *
+of_mbox_index_xlate(struct mbox_controller *mbox,
+		    const struct of_phandle_args *sp)
+{
+	int ind = sp->args[0];
+
+	if (ind >= mbox->num_chans)
+		return NULL;
+
+	return &mbox->chans[ind];
+}
+
+/**
+ * mbox_controller_register - Register the mailbox controller
+ * @mbox:	Pointer to the mailbox controller.
+ *
+ * The controller driver registers its communication channels
+ */
+int mbox_controller_register(struct mbox_controller *mbox)
+{
+	int i, txdone;
+
+	/* Sanity check */
+	if (!mbox || !mbox->dev || !mbox->ops || !mbox->num_chans)
+		return -EINVAL;
+
+	if (mbox->txdone_irq)
+		txdone = TXDONE_BY_IRQ;
+	else if (mbox->txdone_poll)
+		txdone = TXDONE_BY_POLL;
+	else /* It has to be ACK then */
+		txdone = TXDONE_BY_ACK;
+
+	if (txdone == TXDONE_BY_POLL) {
+		mbox->poll.function = &poll_txdone;
+		mbox->poll.data = (unsigned long)mbox;
+		init_timer(&mbox->poll);
+	}
+
+	for (i = 0; i < mbox->num_chans; i++) {
+		struct mbox_chan *chan = &mbox->chans[i];
+
+		chan->cl = NULL;
+		chan->mbox = mbox;
+		chan->txdone_method = txdone;
+		spin_lock_init(&chan->lock);
+	}
+
+	if (!mbox->of_xlate)
+		mbox->of_xlate = of_mbox_index_xlate;
+
+	mutex_lock(&con_mutex);
+	list_add_tail(&mbox->node, &mbox_cons);
+	mutex_unlock(&con_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mbox_controller_register);
+
+/**
+ * mbox_controller_unregister - Unregister the mailbox controller
+ * @mbox:	Pointer to the mailbox controller.
+ */
+void mbox_controller_unregister(struct mbox_controller *mbox)
+{
+	int i;
+
+	if (!mbox)
+		return;
+
+	mutex_lock(&con_mutex);
+
+	list_del(&mbox->node);
+
+	for (i = 0; i < mbox->num_chans; i++)
+		mbox_free_channel(&mbox->chans[i]);
+
+	if (mbox->txdone_poll)
+		del_timer_sync(&mbox->poll);
+
+	mutex_unlock(&con_mutex);
+}
+EXPORT_SYMBOL_GPL(mbox_controller_unregister);
diff --git a/drivers/mailbox/pl320-ipc.c b/drivers/mailbox/pl320-ipc.c
index d873cbae2fbb..f3755e0aa935 100644
--- a/drivers/mailbox/pl320-ipc.c
+++ b/drivers/mailbox/pl320-ipc.c
@@ -26,7 +26,7 @@
 #include <linux/device.h>
 #include <linux/amba/bus.h>
 
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
 
 #define IPCMxSOURCE(m)		((m) * 0x40)
 #define IPCMxDSET(m)		(((m) * 0x40) + 0x004)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 4195a01b1535..8e51b3a3e7b9 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -883,7 +883,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 {
 	unsigned long i;
 	int dirty, need_write;
-	int wait = 0;
 
 	if (!bitmap || !bitmap->storage.filemap ||
 	    test_bit(BITMAP_STALE, &bitmap->flags))
@@ -901,16 +900,13 @@ void bitmap_unplug(struct bitmap *bitmap)
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			write_page(bitmap, bitmap->storage.filemap[i], 0);
 		}
-		if (dirty)
-			wait = 1;
-	}
-	if (wait) { /* if any writes were performed, we need to wait on them */
-		if (bitmap->storage.file)
-			wait_event(bitmap->write_wait,
-				   atomic_read(&bitmap->pending_writes)==0);
-		else
-			md_super_wait(bitmap->mddev);
 	}
+	if (bitmap->storage.file)
+		wait_event(bitmap->write_wait,
+			   atomic_read(&bitmap->pending_writes)==0);
+	else
+		md_super_wait(bitmap->mddev);
+
 	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		bitmap_file_kick(bitmap);
 }
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 66c5d130c8c2..03c872fd5d5c 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -465,6 +465,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty)
 	c->n_buffers[dirty]++;
 	b->list_mode = dirty;
 	list_move(&b->lru_list, &c->lru[dirty]);
+	b->last_accessed = jiffies;
 }
 
 /*----------------------------------------------------------------
@@ -531,6 +532,19 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
 		end_io(&b->bio, r);
 }
 
+static void inline_endio(struct bio *bio, int error)
+{
+	bio_end_io_t *end_fn = bio->bi_private;
+
+	/*
+	 * Reset the bio to free any attached resources
+	 * (e.g. bio integrity profiles).
+	 */
+	bio_reset(bio);
+
+	end_fn(bio, error);
+}
+
 static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 			   bio_end_io_t *end_io)
 {
@@ -542,7 +556,12 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 	b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
 	b->bio.bi_iter.bi_sector = block << b->c->sectors_per_block_bits;
 	b->bio.bi_bdev = b->c->bdev;
-	b->bio.bi_end_io = end_io;
+	b->bio.bi_end_io = inline_endio;
+	/*
+	 * Use of .bi_private isn't a problem here because
+	 * the dm_buffer's inline bio is local to bufio.
+	 */
+	b->bio.bi_private = end_io;
 
 	/*
 	 * We assume that if len >= PAGE_SIZE ptr is page-aligned.
@@ -1447,9 +1466,9 @@ static void drop_buffers(struct dm_bufio_client *c)
 
 /*
  * Test if the buffer is unused and too old, and commit it.
- * At if noio is set, we must not do any I/O because we hold
- * dm_bufio_clients_lock and we would risk deadlock if the I/O gets rerouted to
- * different bufio client.
+ * And if GFP_NOFS is used, we must not do any I/O because we hold
+ * dm_bufio_clients_lock and we would risk deadlock if the I/O gets
+ * rerouted to different bufio client.
  */
 static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp,
 				unsigned long max_jiffies)
@@ -1457,7 +1476,7 @@ static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp,
 	if (jiffies - b->last_accessed < max_jiffies)
 		return 0;
 
-	if (!(gfp & __GFP_IO)) {
+	if (!(gfp & __GFP_FS)) {
 		if (test_bit(B_READING, &b->state) ||
 		    test_bit(B_WRITING, &b->state) ||
 		    test_bit(B_DIRTY, &b->state))
@@ -1485,9 +1504,9 @@ static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 		list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
 			freed += __cleanup_old_buffer(b, gfp_mask, 0);
 			if (!--nr_to_scan)
-				break;
+				return freed;
+			dm_bufio_cond_resched();
 		}
-		dm_bufio_cond_resched();
 	}
 	return freed;
 }
@@ -1499,7 +1518,7 @@ dm_bufio_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	unsigned long freed;
 
 	c = container_of(shrink, struct dm_bufio_client, shrinker);
-	if (sc->gfp_mask & __GFP_IO)
+	if (sc->gfp_mask & __GFP_FS)
 		dm_bufio_lock(c);
 	else if (!dm_bufio_trylock(c))
 		return SHRINK_STOP;
@@ -1516,7 +1535,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 	unsigned long count;
 
 	c = container_of(shrink, struct dm_bufio_client, shrinker);
-	if (sc->gfp_mask & __GFP_IO)
+	if (sc->gfp_mask & __GFP_FS)
 		dm_bufio_lock(c);
 	else if (!dm_bufio_trylock(c))
 		return 0;
@@ -1541,7 +1560,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 	BUG_ON(block_size < 1 << SECTOR_SHIFT ||
 	       (block_size & (block_size - 1)));
 
-	c = kmalloc(sizeof(*c), GFP_KERNEL);
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c) {
 		r = -ENOMEM;
 		goto bad_client;
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 9ef0752e8a08..a87d3fab0271 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -120,6 +120,12 @@ struct dm_cache_metadata {
 	unsigned policy_version[CACHE_POLICY_VERSION_SIZE];
 	size_t policy_hint_size;
 	struct dm_cache_statistics stats;
+
+	/*
+	 * Reading the space map root can fail, so we read it into this
+	 * buffer before the superblock is locked and updated.
+	 */
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 /*-------------------------------------------------------------------
@@ -260,11 +266,31 @@ static void __setup_mapping_info(struct dm_cache_metadata *cmd)
 	}
 }
 
+static int __save_sm_root(struct dm_cache_metadata *cmd)
+{
+	int r;
+	size_t metadata_len;
+
+	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(cmd->metadata_sm, &cmd->metadata_space_map_root,
+			       metadata_len);
+}
+
+static void __copy_sm_root(struct dm_cache_metadata *cmd,
+			   struct cache_disk_superblock *disk_super)
+{
+	memcpy(&disk_super->metadata_space_map_root,
+	       &cmd->metadata_space_map_root,
+	       sizeof(cmd->metadata_space_map_root));
+}
+
 static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 {
 	int r;
 	struct dm_block *sblock;
-	size_t metadata_len;
 	struct cache_disk_superblock *disk_super;
 	sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT;
 
@@ -272,12 +298,16 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS)
 		bdev_size = DM_CACHE_METADATA_MAX_SECTORS;
 
-	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	r = dm_tm_pre_commit(cmd->tm);
 	if (r < 0)
 		return r;
 
-	r = dm_tm_pre_commit(cmd->tm);
-	if (r < 0)
+	/*
+	 * dm_sm_copy_root() can fail.  So we need to do it before we start
+	 * updating the superblock.
+	 */
+	r = __save_sm_root(cmd);
+	if (r)
 		return r;
 
 	r = superblock_lock_zero(cmd, &sblock);
@@ -293,10 +323,7 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version));
 	disk_super->policy_hint_size = 0;
 
-	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto bad_locked;
+	__copy_sm_root(cmd, disk_super);
 
 	disk_super->mapping_root = cpu_to_le64(cmd->root);
 	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
@@ -313,10 +340,6 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	disk_super->write_misses = cpu_to_le32(0);
 
 	return dm_tm_commit(cmd->tm, sblock);
-
-bad_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 static int __format_metadata(struct dm_cache_metadata *cmd)
@@ -402,6 +425,15 @@ static int __open_metadata(struct dm_cache_metadata *cmd)
 
 	disk_super = dm_block_data(sblock);
 
+	/* Verify the data block size hasn't changed */
+	if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) {
+		DMERR("changing the data block size (from %u to %llu) is not supported",
+		      le32_to_cpu(disk_super->data_block_size),
+		      (unsigned long long)cmd->data_block_size);
+		r = -EINVAL;
+		goto bad;
+	}
+
 	r = __check_incompat_features(disk_super, cmd);
 	if (r < 0)
 		goto bad;
@@ -530,8 +562,9 @@ static int __begin_transaction_flags(struct dm_cache_metadata *cmd,
 	disk_super = dm_block_data(sblock);
 	update_flags(disk_super, mutator);
 	read_superblock_fields(cmd, disk_super);
+	dm_bm_unlock(sblock);
 
-	return dm_bm_flush_and_unlock(cmd->bm, sblock);
+	return dm_bm_flush(cmd->bm);
 }
 
 static int __begin_transaction(struct dm_cache_metadata *cmd)
@@ -559,7 +592,6 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 				flags_mutator mutator)
 {
 	int r;
-	size_t metadata_len;
 	struct cache_disk_superblock *disk_super;
 	struct dm_block *sblock;
 
@@ -577,8 +609,8 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	if (r < 0)
 		return r;
 
-	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
-	if (r < 0)
+	r = __save_sm_root(cmd);
+	if (r)
 		return r;
 
 	r = superblock_lock(cmd, &sblock);
@@ -605,13 +637,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses);
 	disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits);
 	disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses);
-
-	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0) {
-		dm_bm_unlock(sblock);
-		return r;
-	}
+	__copy_sm_root(cmd, disk_super);
 
 	return dm_tm_commit(cmd->tm, sblock);
 }
@@ -1228,22 +1254,12 @@ static int begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *po
 	return 0;
 }
 
-int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock, uint32_t hint)
 {
+	struct dm_cache_metadata *cmd = context;
+	__le32 value = cpu_to_le32(hint);
 	int r;
 
-	down_write(&cmd->root_lock);
-	r = begin_hints(cmd, policy);
-	up_write(&cmd->root_lock);
-
-	return r;
-}
-
-static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
-		     uint32_t hint)
-{
-	int r;
-	__le32 value = cpu_to_le32(hint);
 	__dm_bless_for_disk(&value);
 
 	r = dm_array_set_value(&cmd->hint_info, cmd->hint_root,
@@ -1253,16 +1269,25 @@ static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
 	return r;
 }
 
-int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
-		       uint32_t hint)
+static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
 {
 	int r;
 
-	if (!hints_array_initialized(cmd))
-		return 0;
+	r = begin_hints(cmd, policy);
+	if (r) {
+		DMERR("begin_hints failed");
+		return r;
+	}
+
+	return policy_walk_mappings(policy, save_hint, cmd);
+}
+
+int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+{
+	int r;
 
 	down_write(&cmd->root_lock);
-	r = save_hint(cmd, cblock, hint);
+	r = write_hints(cmd, policy);
 	up_write(&cmd->root_lock);
 
 	return r;
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index cd906f14f98d..f0fb1dd26524 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -128,14 +128,7 @@ void dm_cache_dump(struct dm_cache_metadata *cmd);
  * rather than querying the policy for each cblock, we let it walk its data
  * structures and fill in the hints in whatever order it wishes.
  */
-
-int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p);
-
-/*
- * requests hints for every cblock and stores in the metadata device.
- */
-int dm_cache_save_hint(struct dm_cache_metadata *cmd,
-		       dm_cblock_t cblock, uint32_t hint);
+int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p);
 
 /*
  * Query method.  Are all the blocks in the cache clean?
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 074b9c8e4cf0..ff284b7a17bd 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -231,7 +231,7 @@ struct cache {
 	/*
 	 * cache_size entries, dirty if set
 	 */
-	dm_cblock_t nr_dirty;
+	atomic_t nr_dirty;
 	unsigned long *dirty_bitset;
 
 	/*
@@ -239,7 +239,7 @@ struct cache {
 	 */
 	dm_dblock_t discard_nr_blocks;
 	unsigned long *discard_bitset;
-	uint32_t discard_block_size; /* a power of 2 times sectors per block */
+	uint32_t discard_block_size;
 
 	/*
 	 * Rather than reconstructing the table line for the status we just
@@ -493,7 +493,7 @@ static bool is_dirty(struct cache *cache, dm_cblock_t b)
 static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock)
 {
 	if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) {
-		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1);
+		atomic_inc(&cache->nr_dirty);
 		policy_set_dirty(cache->policy, oblock);
 	}
 }
@@ -502,8 +502,7 @@ static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cbl
 {
 	if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) {
 		policy_clear_dirty(cache->policy, oblock);
-		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1);
-		if (!from_cblock(cache->nr_dirty))
+		if (atomic_dec_return(&cache->nr_dirty) == 0)
 			dm_table_event(cache->ti->table);
 	}
 }
@@ -891,8 +890,8 @@ static void migration_success_pre_commit(struct dm_cache_migration *mg)
 	struct cache *cache = mg->cache;
 
 	if (mg->writeback) {
-		cell_defer(cache, mg->old_ocell, false);
 		clear_dirty(cache, mg->old_oblock, mg->cblock);
+		cell_defer(cache, mg->old_ocell, false);
 		cleanup_migration(mg);
 		return;
 
@@ -947,13 +946,17 @@ static void migration_success_post_commit(struct dm_cache_migration *mg)
 		}
 
 	} else {
-		if (mg->requeue_holder)
+		if (mg->requeue_holder) {
+			clear_dirty(cache, mg->new_oblock, mg->cblock);
 			cell_defer(cache, mg->new_ocell, true);
-		else {
+		} else {
+			/*
+			 * The block was promoted via an overwrite, so it's dirty.
+			 */
+			set_dirty(cache, mg->new_oblock, mg->cblock);
 			bio_endio(mg->new_ocell->holder, 0);
 			cell_defer(cache, mg->new_ocell, false);
 		}
-		clear_dirty(cache, mg->new_oblock, mg->cblock);
 		cleanup_migration(mg);
 	}
 }
@@ -1061,7 +1064,8 @@ static void issue_copy(struct dm_cache_migration *mg)
 
 		avoid = is_discarded_oblock(cache, mg->new_oblock);
 
-		if (!avoid && bio_writes_complete_block(cache, bio)) {
+		if (writeback_mode(&cache->features) &&
+		    !avoid && bio_writes_complete_block(cache, bio)) {
 			issue_overwrite(mg, bio);
 			return;
 		}
@@ -2171,35 +2175,6 @@ static int create_cache_policy(struct cache *cache, struct cache_args *ca,
 	return 0;
 }
 
-/*
- * We want the discard block size to be a power of two, at least the size
- * of the cache block size, and have no more than 2^14 discard blocks
- * across the origin.
- */
-#define MAX_DISCARD_BLOCKS (1 << 14)
-
-static bool too_many_discard_blocks(sector_t discard_block_size,
-				    sector_t origin_size)
-{
-	(void) sector_div(origin_size, discard_block_size);
-
-	return origin_size > MAX_DISCARD_BLOCKS;
-}
-
-static sector_t calculate_discard_block_size(sector_t cache_block_size,
-					     sector_t origin_size)
-{
-	sector_t discard_block_size;
-
-	discard_block_size = roundup_pow_of_two(cache_block_size);
-
-	if (origin_size)
-		while (too_many_discard_blocks(discard_block_size, origin_size))
-			discard_block_size *= 2;
-
-	return discard_block_size;
-}
-
 #define DEFAULT_MIGRATION_THRESHOLD 2048
 
 static int cache_create(struct cache_args *ca, struct cache **result)
@@ -2224,6 +2199,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	ti->num_discard_bios = 1;
 	ti->discards_supported = true;
 	ti->discard_zeroes_data_unsupported = true;
+	/* Discard bios must be split on a block boundary */
+	ti->split_discard_bios = true;
 
 	cache->features = ca->features;
 	ti->per_bio_data_size = get_per_bio_data_size(cache);
@@ -2313,7 +2290,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	atomic_set(&cache->quiescing_ack, 0);
 
 	r = -ENOMEM;
-	cache->nr_dirty = 0;
+	atomic_set(&cache->nr_dirty, 0);
 	cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size));
 	if (!cache->dirty_bitset) {
 		*error = "could not allocate dirty bitset";
@@ -2321,9 +2298,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	}
 	clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size));
 
-	cache->discard_block_size =
-		calculate_discard_block_size(cache->sectors_per_block,
-					     cache->origin_sectors);
+	cache->discard_block_size = cache->sectors_per_block;
 	cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks);
 	cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks));
 	if (!cache->discard_bitset) {
@@ -2537,6 +2512,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio)
 
 		} else {
 			inc_hit_counter(cache, bio);
+			pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);
 
 			if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) &&
 			    !is_dirty(cache, lookup_result.cblock))
@@ -2631,30 +2607,6 @@ static int write_discard_bitset(struct cache *cache)
 	return 0;
 }
 
-static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock,
-		     uint32_t hint)
-{
-	struct cache *cache = context;
-	return dm_cache_save_hint(cache->cmd, cblock, hint);
-}
-
-static int write_hints(struct cache *cache)
-{
-	int r;
-
-	r = dm_cache_begin_hints(cache->cmd, cache->policy);
-	if (r) {
-		DMERR("dm_cache_begin_hints failed");
-		return r;
-	}
-
-	r = policy_walk_mappings(cache->policy, save_hint, cache);
-	if (r)
-		DMERR("policy_walk_mappings failed");
-
-	return r;
-}
-
 /*
  * returns true on success
  */
@@ -2672,7 +2624,7 @@ static bool sync_metadata(struct cache *cache)
 
 	save_stats(cache);
 
-	r3 = write_hints(cache);
+	r3 = dm_cache_write_hints(cache->cmd, cache->policy);
 	if (r3)
 		DMERR("could not write hints");
 
@@ -2880,7 +2832,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 
 		residency = policy_residency(cache->policy);
 
-		DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %llu ",
+		DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ",
 		       (unsigned)(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT),
 		       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
 		       (unsigned long long)nr_blocks_metadata,
@@ -2893,7 +2845,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 		       (unsigned) atomic_read(&cache->stats.write_miss),
 		       (unsigned) atomic_read(&cache->stats.demotion),
 		       (unsigned) atomic_read(&cache->stats.promotion),
-		       (unsigned long long) from_cblock(cache->nr_dirty));
+		       (unsigned long) atomic_read(&cache->nr_dirty));
 
 		if (writethrough_mode(&cache->features))
 			DMEMIT("1 writethrough ");
@@ -3120,7 +3072,7 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 	/*
 	 * FIXME: these limits may be incompatible with the cache device
 	 */
-	limits->max_discard_sectors = cache->discard_block_size * 1024;
+	limits->max_discard_sectors = cache->discard_block_size;
 	limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT;
 }
 
@@ -3145,7 +3097,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {1, 3, 0},
+	.version = {1, 4, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 784695d22fde..4a8d19d0a5a4 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -19,7 +19,6 @@
 #include <linux/crypto.h>
 #include <linux/workqueue.h>
 #include <linux/backing-dev.h>
-#include <linux/percpu.h>
 #include <linux/atomic.h>
 #include <linux/scatterlist.h>
 #include <asm/page.h>
@@ -43,6 +42,7 @@ struct convert_context {
 	struct bvec_iter iter_out;
 	sector_t cc_sector;
 	atomic_t cc_pending;
+	struct ablkcipher_request *req;
 };
 
 /*
@@ -111,15 +111,7 @@ struct iv_tcw_private {
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID };
 
 /*
- * Duplicated per-CPU state for cipher.
- */
-struct crypt_cpu {
-	struct ablkcipher_request *req;
-};
-
-/*
- * The fields in here must be read only after initialization,
- * changing state should be in crypt_cpu.
+ * The fields in here must be read only after initialization.
  */
 struct crypt_config {
 	struct dm_dev *dev;
@@ -150,12 +142,6 @@ struct crypt_config {
 	sector_t iv_offset;
 	unsigned int iv_size;
 
-	/*
-	 * Duplicated per cpu state. Access through
-	 * per_cpu_ptr() only.
-	 */
-	struct crypt_cpu __percpu *cpu;
-
 	/* ESSIV: struct crypto_cipher *essiv_tfm */
 	void *iv_private;
 	struct crypto_ablkcipher **tfms;
@@ -192,11 +178,6 @@ static void clone_init(struct dm_crypt_io *, struct bio *);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
 static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);
 
-static struct crypt_cpu *this_crypt_config(struct crypt_config *cc)
-{
-	return this_cpu_ptr(cc->cpu);
-}
-
 /*
  * Use this to access cipher attributes that are the same for each CPU.
  */
@@ -728,7 +709,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 	for (i = 0; i < ((1 << SECTOR_SHIFT) / 8); i++)
 		crypto_xor(data + i * 8, buf, 8);
 out:
-	memset(buf, 0, sizeof(buf));
+	memzero_explicit(buf, sizeof(buf));
 	return r;
 }
 
@@ -903,16 +884,15 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 static void crypt_alloc_req(struct crypt_config *cc,
 			    struct convert_context *ctx)
 {
-	struct crypt_cpu *this_cc = this_crypt_config(cc);
 	unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
 
-	if (!this_cc->req)
-		this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO);
+	if (!ctx->req)
+		ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);
 
-	ablkcipher_request_set_tfm(this_cc->req, cc->tfms[key_index]);
-	ablkcipher_request_set_callback(this_cc->req,
+	ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
+	ablkcipher_request_set_callback(ctx->req,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-	    kcryptd_async_done, dmreq_of_req(cc, this_cc->req));
+	    kcryptd_async_done, dmreq_of_req(cc, ctx->req));
 }
 
 /*
@@ -921,7 +901,6 @@ static void crypt_alloc_req(struct crypt_config *cc,
 static int crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx)
 {
-	struct crypt_cpu *this_cc = this_crypt_config(cc);
 	int r;
 
 	atomic_set(&ctx->cc_pending, 1);
@@ -932,7 +911,7 @@ static int crypt_convert(struct crypt_config *cc,
 
 		atomic_inc(&ctx->cc_pending);
 
-		r = crypt_convert_block(cc, ctx, this_cc->req);
+		r = crypt_convert_block(cc, ctx, ctx->req);
 
 		switch (r) {
 		/* async */
@@ -941,7 +920,7 @@ static int crypt_convert(struct crypt_config *cc,
 			reinit_completion(&ctx->restart);
 			/* fall through*/
 		case -EINPROGRESS:
-			this_cc->req = NULL;
+			ctx->req = NULL;
 			ctx->cc_sector++;
 			continue;
 
@@ -1040,6 +1019,7 @@ static struct dm_crypt_io *crypt_io_alloc(struct crypt_config *cc,
 	io->sector = sector;
 	io->error = 0;
 	io->base_io = NULL;
+	io->ctx.req = NULL;
 	atomic_set(&io->io_pending, 0);
 
 	return io;
@@ -1065,6 +1045,8 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	if (!atomic_dec_and_test(&io->io_pending))
 		return;
 
+	if (io->ctx.req)
+		mempool_free(io->ctx.req, cc->req_pool);
 	mempool_free(io, cc->io_pool);
 
 	if (likely(!base_io))
@@ -1492,8 +1474,6 @@ static int crypt_wipe_key(struct crypt_config *cc)
 static void crypt_dtr(struct dm_target *ti)
 {
 	struct crypt_config *cc = ti->private;
-	struct crypt_cpu *cpu_cc;
-	int cpu;
 
 	ti->private = NULL;
 
@@ -1505,13 +1485,6 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->crypt_queue)
 		destroy_workqueue(cc->crypt_queue);
 
-	if (cc->cpu)
-		for_each_possible_cpu(cpu) {
-			cpu_cc = per_cpu_ptr(cc->cpu, cpu);
-			if (cpu_cc->req)
-				mempool_free(cpu_cc->req, cc->req_pool);
-		}
-
 	crypt_free_tfms(cc);
 
 	if (cc->bs)
@@ -1530,9 +1503,6 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->dev)
 		dm_put_device(ti, cc->dev);
 
-	if (cc->cpu)
-		free_percpu(cc->cpu);
-
 	kzfree(cc->cipher);
 	kzfree(cc->cipher_string);
 
@@ -1588,13 +1558,6 @@ static int crypt_ctr_cipher(struct dm_target *ti,
 	if (tmp)
 		DMWARN("Ignoring unexpected additional cipher options");
 
-	cc->cpu = __alloc_percpu(sizeof(*(cc->cpu)),
-				 __alignof__(struct crypt_cpu));
-	if (!cc->cpu) {
-		ti->error = "Cannot allocate per cpu state";
-		goto bad_mem;
-	}
-
 	/*
 	 * For compatibility with the original dm-crypt mapping format, if
 	 * only the cipher name is supplied, use cbc-plain.
@@ -1718,6 +1681,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	unsigned int key_size, opt_params;
 	unsigned long long tmpll;
 	int ret;
+	size_t iv_size_padding;
 	struct dm_arg_set as;
 	const char *opt_string;
 	char dummy;
@@ -1754,12 +1718,23 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	cc->dmreq_start = sizeof(struct ablkcipher_request);
 	cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
-	cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment());
-	cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) &
-			   ~(crypto_tfm_ctx_alignment() - 1);
+	cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
+
+	if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
+		/* Allocate the padding exactly */
+		iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
+				& crypto_ablkcipher_alignmask(any_tfm(cc));
+	} else {
+		/*
+		 * If the cipher requires greater alignment than kmalloc
+		 * alignment, we don't know the exact position of the
+		 * initialization vector. We must assume worst case.
+		 */
+		iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
+	}
 
 	cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
-			sizeof(struct dm_crypt_request) + cc->iv_size);
+			sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
 	if (!cc->req_pool) {
 		ti->error = "Cannot allocate crypt request mempool";
 		goto bad;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 3842ac738f98..db404a0f7e2c 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -10,6 +10,7 @@
 #include <linux/device-mapper.h>
 
 #include <linux/bio.h>
+#include <linux/completion.h>
 #include <linux/mempool.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -32,7 +33,7 @@ struct dm_io_client {
 struct io {
 	unsigned long error_bits;
 	atomic_t count;
-	struct task_struct *sleeper;
+	struct completion *wait;
 	struct dm_io_client *client;
 	io_notify_fn callback;
 	void *context;
@@ -121,8 +122,8 @@ static void dec_count(struct io *io, unsigned int region, int error)
 			invalidate_kernel_vmap_range(io->vma_invalidate_address,
 						     io->vma_invalidate_size);
 
-		if (io->sleeper)
-			wake_up_process(io->sleeper);
+		if (io->wait)
+			complete(io->wait);
 
 		else {
 			unsigned long r = io->error_bits;
@@ -387,6 +388,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	 */
 	volatile char io_[sizeof(struct io) + __alignof__(struct io) - 1];
 	struct io *io = (struct io *)PTR_ALIGN(&io_, __alignof__(struct io));
+	DECLARE_COMPLETION_ONSTACK(wait);
 
 	if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
 		WARN_ON(1);
@@ -395,7 +397,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
-	io->sleeper = current;
+	io->wait = &wait;
 	io->client = client;
 
 	io->vma_invalidate_address = dp->vma_invalidate_address;
@@ -403,15 +405,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 	dispatch_io(rw, num_regions, where, dp, io, 1);
 
-	while (1) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-
-		if (!atomic_read(&io->count))
-			break;
-
-		io_schedule();
-	}
-	set_current_state(TASK_RUNNING);
+	wait_for_completion_io(&wait);
 
 	if (error_bits)
 		*error_bits = io->error_bits;
@@ -434,7 +428,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
-	io->sleeper = NULL;
+	io->wait = NULL;
 	io->client = client;
 	io->callback = fn;
 	io->context = context;
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 08d9a207259a..c69d0b787746 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -272,7 +272,7 @@ int dm_ulog_tfr_init(void)
 
 	r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback);
 	if (r) {
-		cn_del_callback(&ulog_cn_id);
+		kfree(prealloced_cn_msg);
 		return r;
 	}
 
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 4880b69e2e9e..59715389b3cf 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -785,8 +785,7 @@ struct dm_raid_superblock {
 	__le32 layout;
 	__le32 stripe_sectors;
 
-	__u8 pad[452];		/* Round struct to 512 bytes. */
-				/* Always set to 0 when writing. */
+	/* Remainder of a logical block is zero-filled when writing (see super_sync()). */
 } __packed;
 
 static int read_disk_sb(struct md_rdev *rdev, int size)
@@ -823,7 +822,7 @@ static void super_sync(struct mddev *mddev, struct md_rdev *rdev)
 		    test_bit(Faulty, &(rs->dev[i].rdev.flags)))
 			failed_devices |= (1ULL << i);
 
-	memset(sb, 0, sizeof(*sb));
+	memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
 
 	sb->magic = cpu_to_le32(DM_RAID_MAGIC);
 	sb->features = cpu_to_le32(0);	/* No features yet */
@@ -858,7 +857,11 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 	uint64_t events_sb, events_refsb;
 
 	rdev->sb_start = 0;
-	rdev->sb_size = sizeof(*sb);
+	rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev);
+	if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) {
+		DMERR("superblock size of a logical block is no longer valid");
+		return -EINVAL;
+	}
 
 	ret = read_disk_sb(rdev, rdev->sb_size);
 	if (ret)
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index fb9efc829182..e9d33ad59df5 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -192,6 +192,13 @@ struct dm_pool_metadata {
 	 * operation possible in this state is the closing of the device.
 	 */
 	bool fail_io:1;
+
+	/*
+	 * Reading the space map roots can fail, so we read it into these
+	 * buffers before the superblock is locked and updated.
+	 */
+	__u8 data_space_map_root[SPACE_MAP_ROOT_SIZE];
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 struct dm_thin_device {
@@ -431,26 +438,53 @@ static void __setup_btree_details(struct dm_pool_metadata *pmd)
 	pmd->details_info.value_type.equal = NULL;
 }
 
+static int save_sm_roots(struct dm_pool_metadata *pmd)
+{
+	int r;
+	size_t len;
+
+	r = dm_sm_root_size(pmd->metadata_sm, &len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_copy_root(pmd->metadata_sm, &pmd->metadata_space_map_root, len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_root_size(pmd->data_sm, &len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(pmd->data_sm, &pmd->data_space_map_root, len);
+}
+
+static void copy_sm_roots(struct dm_pool_metadata *pmd,
+			  struct thin_disk_superblock *disk)
+{
+	memcpy(&disk->metadata_space_map_root,
+	       &pmd->metadata_space_map_root,
+	       sizeof(pmd->metadata_space_map_root));
+
+	memcpy(&disk->data_space_map_root,
+	       &pmd->data_space_map_root,
+	       sizeof(pmd->data_space_map_root));
+}
+
 static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 {
 	int r;
 	struct dm_block *sblock;
-	size_t metadata_len, data_len;
 	struct thin_disk_superblock *disk_super;
 	sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT;
 
 	if (bdev_size > THIN_METADATA_MAX_SECTORS)
 		bdev_size = THIN_METADATA_MAX_SECTORS;
 
-	r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
-	if (r < 0)
-		return r;
-
-	r = dm_sm_root_size(pmd->data_sm, &data_len);
+	r = dm_sm_commit(pmd->data_sm);
 	if (r < 0)
 		return r;
 
-	r = dm_sm_commit(pmd->data_sm);
+	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;
 
@@ -471,15 +505,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	disk_super->trans_id = 0;
 	disk_super->held_root = 0;
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto bad_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto bad_locked;
+	copy_sm_roots(pmd, disk_super);
 
 	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
 	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
@@ -488,10 +514,6 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-bad_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 static int __format_metadata(struct dm_pool_metadata *pmd)
@@ -591,6 +613,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 
 	disk_super = dm_block_data(sblock);
 
+	/* Verify the data block size hasn't changed */
+	if (le32_to_cpu(disk_super->data_block_size) != pmd->data_block_size) {
+		DMERR("changing the data block size (from %u to %llu) is not supported",
+		      le32_to_cpu(disk_super->data_block_size),
+		      (unsigned long long)pmd->data_block_size);
+		r = -EINVAL;
+		goto bad_unlock_sblock;
+	}
+
 	r = __check_incompat_features(disk_super, pmd);
 	if (r < 0)
 		goto bad_unlock_sblock;
@@ -769,6 +800,10 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
+	r = save_sm_roots(pmd);
+	if (r < 0)
+		return r;
+
 	r = superblock_lock(pmd, &sblock);
 	if (r)
 		return r;
@@ -780,21 +815,9 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	disk_super->trans_id = cpu_to_le64(pmd->trans_id);
 	disk_super->flags = cpu_to_le32(pmd->flags);
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto out_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto out_locked;
+	copy_sm_roots(pmd, disk_super);
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-out_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index be70d38745f7..f7e052c7ab5f 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -25,6 +25,9 @@
 #define MAPPING_POOL_SIZE 1024
 #define PRISON_CELLS 1024
 #define COMMIT_PERIOD HZ
+#define NO_SPACE_TIMEOUT_SECS 60
+
+static unsigned no_space_timeout_secs = NO_SPACE_TIMEOUT_SECS;
 
 DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle,
 		"A percentage of time allocated for copy on write");
@@ -173,6 +176,7 @@ struct pool {
 	struct workqueue_struct *wq;
 	struct work_struct worker;
 	struct delayed_work waker;
+	struct delayed_work no_space_timeout;
 
 	unsigned long last_commit_jiffies;
 	unsigned ref_count;
@@ -912,6 +916,24 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	}
 }
 
+static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
+
+static void check_for_space(struct pool *pool)
+{
+	int r;
+	dm_block_t nr_free;
+
+	if (get_pool_mode(pool) != PM_OUT_OF_DATA_SPACE)
+		return;
+
+	r = dm_pool_get_free_block_count(pool->pmd, &nr_free);
+	if (r)
+		return;
+
+	if (nr_free)
+		set_pool_mode(pool, PM_WRITE);
+}
+
 /*
  * A non-zero return indicates read_only or fail_io mode.
  * Many callers don't care about the return value.
@@ -920,12 +942,14 @@ static int commit(struct pool *pool)
 {
 	int r;
 
-	if (get_pool_mode(pool) != PM_WRITE)
+	if (get_pool_mode(pool) >= PM_READ_ONLY)
 		return -EINVAL;
 
 	r = dm_pool_commit_metadata(pool->pmd);
 	if (r)
 		metadata_operation_failed(pool, "dm_pool_commit_metadata", r);
+	else
+		check_for_space(pool);
 
 	return r;
 }
@@ -944,8 +968,6 @@ static void check_low_water_mark(struct pool *pool, dm_block_t free_blocks)
 	}
 }
 
-static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
-
 static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 {
 	int r;
@@ -1392,9 +1414,9 @@ static void process_deferred_bios(struct pool *pool)
 		 */
 		if (ensure_next_mapping(pool)) {
 			spin_lock_irqsave(&pool->lock, flags);
+			bio_list_add(&pool->deferred_bios, bio);
 			bio_list_merge(&pool->deferred_bios, &bios);
 			spin_unlock_irqrestore(&pool->lock, flags);
-
 			break;
 		}
 
@@ -1449,6 +1471,20 @@ static void do_waker(struct work_struct *ws)
 	queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
 }
 
+/*
+ * We're holding onto IO to allow userland time to react.  After the
+ * timeout either the pool will have been resized (and thus back in
+ * PM_WRITE mode), or we degrade to PM_READ_ONLY and start erroring IO.
+ */
+static void do_no_space_timeout(struct work_struct *ws)
+{
+	struct pool *pool = container_of(to_delayed_work(ws), struct pool,
+					 no_space_timeout);
+
+	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space)
+		set_pool_mode(pool, PM_READ_ONLY);
+}
+
 /*----------------------------------------------------------------*/
 
 struct noflush_work {
@@ -1513,6 +1549,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 	struct pool_c *pt = pool->ti->private;
 	bool needs_check = dm_pool_metadata_needs_check(pool->pmd);
 	enum pool_mode old_mode = get_pool_mode(pool);
+	unsigned long no_space_timeout = ACCESS_ONCE(no_space_timeout_secs) * HZ;
 
 	/*
 	 * Never allow the pool to transition to PM_WRITE mode if user
@@ -1573,7 +1610,10 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_discard;
 		pool->process_prepared_mapping = process_prepared_mapping;
-		pool->process_prepared_discard = process_prepared_discard_passdown;
+		pool->process_prepared_discard = process_prepared_discard;
+
+		if (!pool->pf.error_if_no_space && no_space_timeout)
+			queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout);
 		break;
 
 	case PM_WRITE:
@@ -1682,6 +1722,14 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_SUBMITTED;
 	}
 
+	/*
+	 * We must hold the virtual cell before doing the lookup, otherwise
+	 * there's a race with discard.
+	 */
+	build_virtual_key(tc->td, block, &key);
+	if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result))
+		return DM_MAPIO_SUBMITTED;
+
 	r = dm_thin_find_block(td, block, 0, &result);
 
 	/*
@@ -1705,13 +1753,10 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 			 * shared flag will be set in their case.
 			 */
 			thin_defer_bio(tc, bio);
+			cell_defer_no_holder_no_free(tc, &cell1);
 			return DM_MAPIO_SUBMITTED;
 		}
 
-		build_virtual_key(tc->td, block, &key);
-		if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result))
-			return DM_MAPIO_SUBMITTED;
-
 		build_data_key(tc->td, result.block, &key);
 		if (dm_bio_detain(tc->pool->prison, &key, bio, &cell2, &cell_result)) {
 			cell_defer_no_holder_no_free(tc, &cell1);
@@ -1732,6 +1777,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 			 * of doing so.
 			 */
 			handle_unserviceable_bio(tc->pool, bio);
+			cell_defer_no_holder_no_free(tc, &cell1);
 			return DM_MAPIO_SUBMITTED;
 		}
 		/* fall through */
@@ -1742,6 +1788,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		 * provide the hint to load the metadata into cache.
 		 */
 		thin_defer_bio(tc, bio);
+		cell_defer_no_holder_no_free(tc, &cell1);
 		return DM_MAPIO_SUBMITTED;
 
 	default:
@@ -1751,6 +1798,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		 * pool is switched to fail-io mode.
 		 */
 		bio_io_error(bio);
+		cell_defer_no_holder_no_free(tc, &cell1);
 		return DM_MAPIO_SUBMITTED;
 	}
 }
@@ -1956,6 +2004,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 
 	INIT_WORK(&pool->worker, do_worker);
 	INIT_DELAYED_WORK(&pool->waker, do_waker);
+	INIT_DELAYED_WORK(&pool->no_space_timeout, do_no_space_timeout);
 	spin_lock_init(&pool->lock);
 	bio_list_init(&pool->deferred_bios);
 	bio_list_init(&pool->deferred_flush_bios);
@@ -2519,6 +2568,7 @@ static void pool_postsuspend(struct dm_target *ti)
 	struct pool *pool = pt->pool;
 
 	cancel_delayed_work(&pool->waker);
+	cancel_delayed_work(&pool->no_space_timeout);
 	flush_workqueue(pool->wq);
 	(void) commit(pool);
 }
@@ -2901,7 +2951,8 @@ static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
 	 */
 	if (pt->adjusted_pf.discard_passdown) {
 		data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
-		limits->discard_granularity = data_limits->discard_granularity;
+		limits->discard_granularity = max(data_limits->discard_granularity,
+						  pool->sectors_per_block << SECTOR_SHIFT);
 	} else
 		limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 }
@@ -3305,6 +3356,9 @@ static void dm_thin_exit(void)
 module_init(dm_thin_init);
 module_exit(dm_thin_exit);
 
+module_param_named(no_space_timeout, no_space_timeout_secs, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(no_space_timeout, "Out of data space queue IO timeout in seconds");
+
 MODULE_DESCRIPTION(DM_NAME " thin provisioning target");
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index 796007a5e0e1..7a7bab8947ae 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -330,15 +330,17 @@ test_block_hash:
 				return r;
 			}
 		}
-
 		todo = 1 << v->data_dev_block_bits;
-		while (io->iter.bi_size) {
+		do {
 			u8 *page;
+			unsigned len;
 			struct bio_vec bv = bio_iter_iovec(bio, io->iter);
 
 			page = kmap_atomic(bv.bv_page);
-			r = crypto_shash_update(desc, page + bv.bv_offset,
-						bv.bv_len);
+			len = bv.bv_len;
+			if (likely(len >= todo))
+				len = todo;
+			r = crypto_shash_update(desc, page + bv.bv_offset, len);
 			kunmap_atomic(page);
 
 			if (r < 0) {
@@ -346,8 +348,9 @@ test_block_hash:
 				return r;
 			}
 
-			bio_advance_iter(bio, &io->iter, bv.bv_len);
-		}
+			bio_advance_iter(bio, &io->iter, len);
+			todo -= len;
+		} while (todo);
 
 		if (!v->version) {
 			r = crypto_shash_update(desc, v->salt, v->salt_size);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8c53b09b9a2c..65ee3a0d4683 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -54,6 +54,8 @@ static void do_deferred_remove(struct work_struct *w);
 
 static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
 
+static struct workqueue_struct *deferred_remove_workqueue;
+
 /*
  * For bio-based dm.
  * One of these is allocated per bio.
@@ -283,16 +285,24 @@ static int __init local_init(void)
 	if (r)
 		goto out_free_rq_tio_cache;
 
+	deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1);
+	if (!deferred_remove_workqueue) {
+		r = -ENOMEM;
+		goto out_uevent_exit;
+	}
+
 	_major = major;
 	r = register_blkdev(_major, _name);
 	if (r < 0)
-		goto out_uevent_exit;
+		goto out_free_workqueue;
 
 	if (!_major)
 		_major = r;
 
 	return 0;
 
+out_free_workqueue:
+	destroy_workqueue(deferred_remove_workqueue);
 out_uevent_exit:
 	dm_uevent_exit();
 out_free_rq_tio_cache:
@@ -306,6 +316,7 @@ out_free_io_cache:
 static void local_exit(void)
 {
 	flush_scheduled_work();
+	destroy_workqueue(deferred_remove_workqueue);
 
 	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_io_cache);
@@ -414,7 +425,7 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 
 	if (atomic_dec_and_test(&md->open_count) &&
 	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
-		schedule_work(&deferred_remove_work);
+		queue_work(deferred_remove_workqueue, &deferred_remove_work);
 
 	dm_put(md);
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ad5cc4e63e8..40959ee73583 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5333,6 +5333,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		printk("md: %s still in use.\n",mdname(mddev));
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			md_wakeup_thread(mddev->thread);
 		}
 		err = -EBUSY;
@@ -5347,6 +5348,8 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		mddev->ro = 1;
 		set_disk_ro(mddev->gendisk, 1);
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		md_wakeup_thread(mddev->thread);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 		err = 0;
 	}
@@ -5390,6 +5393,7 @@ static int do_md_stop(struct mddev * mddev, int mode,
 		mutex_unlock(&mddev->open_mutex);
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			md_wakeup_thread(mddev->thread);
 		}
 		return -EBUSY;
@@ -7395,8 +7399,10 @@ void md_do_sync(struct md_thread *thread)
 	/* just incase thread restarts... */
 	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
 		return;
-	if (mddev->ro) /* never try to sync a read-only array */
+	if (mddev->ro) {/* never try to sync a read-only array */
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		return;
+	}
 
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
 		if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
@@ -7503,6 +7509,19 @@ void md_do_sync(struct md_thread *thread)
 			    rdev->recovery_offset < j)
 				j = rdev->recovery_offset;
 		rcu_read_unlock();
+
+		/* If there is a bitmap, we need to make sure all
+		 * writes that started before we added a spare
+		 * complete before we start doing a recovery.
+		 * Otherwise the write might complete and (via
+		 * bitmap_endwrite) set a bit in the bitmap after the
+		 * recovery has checked that bit and skipped that
+		 * region.
+		 */
+		if (mddev->bitmap) {
+			mddev->pers->quiesce(mddev, 1);
+			mddev->pers->quiesce(mddev, 0);
+		}
 	}
 
 	printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev));
@@ -7838,6 +7857,7 @@ void md_check_recovery(struct mddev *mddev)
 			/* There is no thread, but we need to call
 			 * ->spare_active and clear saved_raid_disk
 			 */
+			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			md_reap_sync_thread(mddev);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			goto unlock;
@@ -8530,7 +8550,8 @@ static int md_notify_reboot(struct notifier_block *this,
 		if (mddev_trylock(mddev)) {
 			if (mddev->pers)
 				__md_stop_writes(mddev);
-			mddev->safemode = 2;
+			if (mddev->persistent)
+				mddev->safemode = 2;
 			mddev_unlock(mddev);
 		}
 		need_delay = 1;
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 455f79279a16..087411c95ffc 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -595,25 +595,14 @@ int dm_bm_unlock(struct dm_block *b)
 }
 EXPORT_SYMBOL_GPL(dm_bm_unlock);
 
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock)
+int dm_bm_flush(struct dm_block_manager *bm)
 {
-	int r;
-
 	if (bm->read_only)
 		return -EPERM;
 
-	r = dm_bufio_write_dirty_buffers(bm->bufio);
-	if (unlikely(r)) {
-		dm_bm_unlock(superblock);
-		return r;
-	}
-
-	dm_bm_unlock(superblock);
-
 	return dm_bufio_write_dirty_buffers(bm->bufio);
 }
-EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock);
+EXPORT_SYMBOL_GPL(dm_bm_flush);
 
 void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b)
 {
diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h
index 13cd58e1fe69..1b95dfc17786 100644
--- a/drivers/md/persistent-data/dm-block-manager.h
+++ b/drivers/md/persistent-data/dm-block-manager.h
@@ -105,8 +105,7 @@ int dm_bm_unlock(struct dm_block *b);
  *
  * This method always blocks.
  */
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock);
+int dm_bm_flush(struct dm_block_manager *bm);
 
 /*
  * Request data is prefetched into the cache.
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index 37d367bb9aa8..bf2b80d5c470 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -42,6 +42,12 @@ struct btree_node {
 } __packed;
 
 
+/*
+ * Locks a block using the btree node validator.
+ */
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+		 struct dm_block **result);
+
 void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
 		  struct dm_btree_value_type *vt);
 
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index cf9fd676ae44..1b5e13ec7f96 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -92,7 +92,7 @@ struct dm_block_validator btree_node_validator = {
 
 /*----------------------------------------------------------------*/
 
-static int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
 		 struct dm_block **result)
 {
 	return dm_tm_read_lock(info->tm, b, &btree_node_validator, result);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 416060c25709..200ac12a1d40 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -847,22 +847,26 @@ EXPORT_SYMBOL_GPL(dm_btree_find_lowest_key);
  * FIXME: We shouldn't use a recursive algorithm when we have limited stack
  * space.  Also this only works for single level trees.
  */
-static int walk_node(struct ro_spine *s, dm_block_t block,
+static int walk_node(struct dm_btree_info *info, dm_block_t block,
 		     int (*fn)(void *context, uint64_t *keys, void *leaf),
 		     void *context)
 {
 	int r;
 	unsigned i, nr;
+	struct dm_block *node;
 	struct btree_node *n;
 	uint64_t keys;
 
-	r = ro_step(s, block);
-	n = ro_node(s);
+	r = bn_read_lock(info, block, &node);
+	if (r)
+		return r;
+
+	n = dm_block_data(node);
 
 	nr = le32_to_cpu(n->header.nr_entries);
 	for (i = 0; i < nr; i++) {
 		if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) {
-			r = walk_node(s, value64(n, i), fn, context);
+			r = walk_node(info, value64(n, i), fn, context);
 			if (r)
 				goto out;
 		} else {
@@ -874,7 +878,7 @@ static int walk_node(struct ro_spine *s, dm_block_t block,
 	}
 
 out:
-	ro_pop(s);
+	dm_tm_unlock(info->tm, node);
 	return r;
 }
 
@@ -882,15 +886,7 @@ int dm_btree_walk(struct dm_btree_info *info, dm_block_t root,
 		  int (*fn)(void *context, uint64_t *keys, void *leaf),
 		  void *context)
 {
-	int r;
-	struct ro_spine spine;
-
 	BUG_ON(info->levels > 1);
-
-	init_ro_spine(&spine, info);
-	r = walk_node(&spine, root, fn, context);
-	exit_ro_spine(&spine);
-
-	return r;
+	return walk_node(info, root, fn, context);
 }
 EXPORT_SYMBOL_GPL(dm_btree_walk);
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 786b689bdfc7..f4e22bcc7fb8 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -564,7 +564,9 @@ static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count
 {
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
-	return smm->ll.nr_blocks;
+	*count = smm->ll.nr_blocks;
+
+	return 0;
 }
 
 static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index 81da1a26042e..3bc30a0ae3d6 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -154,7 +154,7 @@ int dm_tm_pre_commit(struct dm_transaction_manager *tm)
 	if (r < 0)
 		return r;
 
-	return 0;
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_pre_commit);
 
@@ -164,8 +164,9 @@ int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root)
 		return -EWOULDBLOCK;
 
 	wipe_shadow_table(tm);
+	dm_bm_unlock(root);
 
-	return dm_bm_flush_and_unlock(tm->bm, root);
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_commit);
 
diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h
index b5b139076ca5..2772ed2a781a 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.h
+++ b/drivers/md/persistent-data/dm-transaction-manager.h
@@ -38,18 +38,17 @@ struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transac
 /*
  * We use a 2-phase commit here.
  *
- * i) In the first phase the block manager is told to start flushing, and
- * the changes to the space map are written to disk.  You should interrogate
- * your particular space map to get detail of its root node etc. to be
- * included in your superblock.
+ * i) Make all changes for the transaction *except* for the superblock.
+ * Then call dm_tm_pre_commit() to flush them to disk.
  *
- * ii) @root will be committed last.  You shouldn't use more than the
- * first 512 bytes of @root if you wish the transaction to survive a power
- * failure.  You *must* have a write lock held on @root for both stage (i)
- * and (ii).  The commit will drop the write lock.
+ * ii) Lock your superblock.  Update.  Then call dm_tm_commit() which will
+ * unlock the superblock and flush it.  No other blocks should be updated
+ * during this period.  Care should be taken to never unlock a partially
+ * updated superblock; perform any operations that could fail *before* you
+ * take the superblock lock.
  */
 int dm_tm_pre_commit(struct dm_transaction_manager *tm);
-int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root);
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *superblock);
 
 /*
  * These methods are the only way to get hold of a writeable block.
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4a6ca1cb2e78..55de4f6f7eaf 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -97,6 +97,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	struct pool_info *pi = data;
 	struct r1bio *r1_bio;
 	struct bio *bio;
+	int need_pages;
 	int i, j;
 
 	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
@@ -119,15 +120,15 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * RESYNC_PAGES for each bio.
 	 */
 	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
-		j = pi->raid_disks;
+		need_pages = pi->raid_disks;
 	else
-		j = 1;
-	while(j--) {
+		need_pages = 1;
+	for (j = 0; j < need_pages; j++) {
 		bio = r1_bio->bios[j];
 		bio->bi_vcnt = RESYNC_PAGES;
 
 		if (bio_alloc_pages(bio, gfp_flags))
-			goto out_free_bio;
+			goto out_free_pages;
 	}
 	/* If not user-requests, copy the page pointers to all bios */
 	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
@@ -141,6 +142,14 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 	return r1_bio;
 
+out_free_pages:
+	while (--j >= 0) {
+		struct bio_vec *bv;
+
+		bio_for_each_segment_all(bv, r1_bio->bios[j], i)
+			__free_page(bv->bv_page);
+	}
+
 out_free_bio:
 	while (++j < pi->raid_disks)
 		bio_put(r1_bio->bios[j]);
@@ -531,11 +540,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	has_nonrot_disk = 0;
 	choose_next_idle = 0;
 
-	if (conf->mddev->recovery_cp < MaxSector &&
-	    (this_sector + sectors >= conf->next_resync))
-		choose_first = 1;
-	else
-		choose_first = 0;
+	choose_first = (conf->mddev->recovery_cp < this_sector + sectors);
 
 	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
 		sector_t dist;
@@ -822,7 +827,7 @@ static void flush_pending_writes(struct r1conf *conf)
  *    there is no normal IO happeing.  It must arrange to call
  *    lower_barrier when the particular background IO completes.
  */
-static void raise_barrier(struct r1conf *conf)
+static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
 {
 	spin_lock_irq(&conf->resync_lock);
 
@@ -832,6 +837,7 @@ static void raise_barrier(struct r1conf *conf)
 
 	/* block any new IO from starting */
 	conf->barrier++;
+	conf->next_resync = sector_nr;
 
 	/* For these conditions we must wait:
 	 * A: while the array is in frozen state
@@ -840,14 +846,17 @@ static void raise_barrier(struct r1conf *conf)
 	 * C: next_resync + RESYNC_SECTORS > start_next_window, meaning
 	 *    next resync will reach to the window which normal bios are
 	 *    handling.
+	 * D: while there are any active requests in the current window.
 	 */
 	wait_event_lock_irq(conf->wait_barrier,
 			    !conf->array_frozen &&
 			    conf->barrier < RESYNC_DEPTH &&
+			    conf->current_window_requests == 0 &&
 			    (conf->start_next_window >=
 			     conf->next_resync + RESYNC_SECTORS),
 			    conf->resync_lock);
 
+	conf->nr_pending++;
 	spin_unlock_irq(&conf->resync_lock);
 }
 
@@ -857,6 +866,7 @@ static void lower_barrier(struct r1conf *conf)
 	BUG_ON(conf->barrier <= 0);
 	spin_lock_irqsave(&conf->resync_lock, flags);
 	conf->barrier--;
+	conf->nr_pending--;
 	spin_unlock_irqrestore(&conf->resync_lock, flags);
 	wake_up(&conf->wait_barrier);
 }
@@ -868,12 +878,10 @@ static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio)
 	if (conf->array_frozen || !bio)
 		wait = true;
 	else if (conf->barrier && bio_data_dir(bio) == WRITE) {
-		if (conf->next_resync < RESYNC_WINDOW_SECTORS)
-			wait = true;
-		else if ((conf->next_resync - RESYNC_WINDOW_SECTORS
-				>= bio_end_sector(bio)) ||
-			 (conf->next_resync + NEXT_NORMALIO_DISTANCE
-				<= bio->bi_iter.bi_sector))
+		if ((conf->mddev->curr_resync_completed
+		     >= bio_end_sector(bio)) ||
+		    (conf->next_resync + NEXT_NORMALIO_DISTANCE
+		     <= bio->bi_iter.bi_sector))
 			wait = false;
 		else
 			wait = true;
@@ -910,8 +918,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 	}
 
 	if (bio && bio_data_dir(bio) == WRITE) {
-		if (conf->next_resync + NEXT_NORMALIO_DISTANCE
-		    <= bio->bi_iter.bi_sector) {
+		if (bio->bi_iter.bi_sector >=
+		    conf->mddev->curr_resync_completed) {
 			if (conf->start_next_window == MaxSector)
 				conf->start_next_window =
 					conf->next_resync +
@@ -1177,6 +1185,7 @@ read_again:
 				   atomic_read(&bitmap->behind_writes) == 0);
 		}
 		r1_bio->read_disk = rdisk;
+		r1_bio->start_next_window = 0;
 
 		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
 		bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
@@ -1492,12 +1501,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
-		/*
-		 * if recovery is running, make sure it aborts.
-		 */
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	/*
+	 * if recovery is running, make sure it aborts.
+	 */
+	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	printk(KERN_ALERT
 	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
@@ -1539,8 +1548,13 @@ static void close_sync(struct r1conf *conf)
 	mempool_destroy(conf->r1buf_pool);
 	conf->r1buf_pool = NULL;
 
+	spin_lock_irq(&conf->resync_lock);
 	conf->next_resync = 0;
 	conf->start_next_window = MaxSector;
+	conf->current_window_requests +=
+		conf->next_window_requests;
+	conf->next_window_requests = 0;
+	spin_unlock_irq(&conf->resync_lock);
 }
 
 static int raid1_spare_active(struct mddev *mddev)
@@ -2141,7 +2155,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags))
+			    !test_bit(Faulty, &rdev->flags))
 				r1_sync_page_io(rdev, sect, s,
 						conf->tmppage, WRITE);
 		}
@@ -2153,7 +2167,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags)) {
+			    !test_bit(Faulty, &rdev->flags)) {
 				if (r1_sync_page_io(rdev, sect, s,
 						    conf->tmppage, READ)) {
 					atomic_add(s, &rdev->corrected_errors);
@@ -2532,9 +2546,8 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 
 	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
 	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
-	raise_barrier(conf);
 
-	conf->next_resync = sector_nr;
+	raise_barrier(conf, sector_nr);
 
 	rcu_read_lock();
 	/*
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 33fc408e5eac..a46124ecafc7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1172,6 +1172,13 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	int max_sectors;
 	int sectors;
 
+	/*
+	 * Register the new request and wait if the reconstruction
+	 * thread has put up a bar for new requests.
+	 * Continue immediately if no resync is active currently.
+	 */
+	wait_barrier(conf);
+
 	sectors = bio_sectors(bio);
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio->bi_iter.bi_sector < conf->reshape_progress &&
@@ -1552,12 +1559,6 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 
 	md_write_start(mddev, bio);
 
-	/*
-	 * Register the new request and wait if the reconstruction
-	 * thread has put up a bar for new requests.
-	 * Continue immediately if no resync is active currently.
-	 */
-	wait_barrier(conf);
 
 	do {
 
@@ -1683,13 +1684,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 		return;
 	}
-	if (test_and_clear_bit(In_sync, &rdev->flags)) {
+	if (test_and_clear_bit(In_sync, &rdev->flags))
 		mddev->degraded++;
-			/*
-		 * if recovery is running, make sure it aborts.
-		 */
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-	}
+	/*
+	 * If recovery is running, make sure it aborts.
+	 */
+	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -2953,6 +2953,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		 */
 		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
 			end_reshape(conf);
+			close_sync(conf);
 			return 0;
 		}
 
@@ -4410,7 +4411,7 @@ read_more:
 	read_bio->bi_private = r10_bio;
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
-	read_bio->bi_flags &= ~(BIO_POOL_MASK - 1);
+	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
 	read_bio->bi_flags |= 1 << BIO_UPTODATE;
 	read_bio->bi_vcnt = 0;
 	read_bio->bi_iter.bi_size = 0;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 16f5c21963db..4913c0690872 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -64,6 +64,10 @@
 #define cpu_to_group(cpu) cpu_to_node(cpu)
 #define ANY_GROUP NUMA_NO_NODE
 
+static bool devices_handle_discard_safely = false;
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
 static struct workqueue_struct *raid5_wq;
 /*
  * Stripe cache
@@ -3779,6 +3783,8 @@ static void handle_stripe(struct stripe_head *sh)
 				set_bit(R5_Wantwrite, &dev->flags);
 				if (prexor)
 					continue;
+				if (s.failed > 1)
+					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
 				    ((i == sh->pd_idx || i == sh->qd_idx)  &&
 				     s.failed == 0))
@@ -6115,7 +6121,7 @@ static int run(struct mddev *mddev)
 		mddev->queue->limits.discard_granularity = stripe;
 		/*
 		 * unaligned part of discard request will be ignored, so can't
-		 * guarantee discard_zerors_data
+		 * guarantee discard_zeroes_data
 		 */
 		mddev->queue->limits.discard_zeroes_data = 0;
 
@@ -6140,6 +6146,18 @@ static int run(struct mddev *mddev)
 			    !bdev_get_queue(rdev->bdev)->
 						limits.discard_zeroes_data)
 				discard_supported = false;
+			/* Unfortunately, discard_zeroes_data is not currently
+			 * a guarantee - just a hint.  So we only allow DISCARD
+			 * if the sysadmin has confirmed that only safe devices
+			 * are in use by setting a module parameter.
+			 */
+			if (!devices_handle_discard_safely) {
+				if (discard_supported) {
+					pr_info("md/raid456: discard support disabled due to uncertainty.\n");
+					pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
+				}
+				discard_supported = false;
+			}
 		}
 
 		if (discard_supported &&
diff --git a/drivers/media/common/siano/Kconfig b/drivers/media/common/siano/Kconfig
index f953d33ee151..4bfbd5f463d1 100644
--- a/drivers/media/common/siano/Kconfig
+++ b/drivers/media/common/siano/Kconfig
@@ -22,8 +22,7 @@ config SMS_SIANO_DEBUGFS
 	bool "Enable debugfs for smsdvb"
 	depends on SMS_SIANO_MDTV
 	depends on DEBUG_FS
-	depends on SMS_USB_DRV
-	depends on CONFIG_SMS_USB_DRV = CONFIG_SMS_SDIO_DRV
+	depends on SMS_USB_DRV = SMS_SDIO_DRV
 
 	---help---
 	  Choose Y to enable visualizing a dump of the frontend
diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h
index f19a2ccd1e4b..fabe2fce9bc5 100644
--- a/drivers/media/dvb-core/dvb-usb-ids.h
+++ b/drivers/media/dvb-core/dvb-usb-ids.h
@@ -257,6 +257,7 @@
 #define USB_PID_TERRATEC_T5				0x10a1
 #define USB_PID_NOXON_DAB_STICK				0x00b3
 #define USB_PID_NOXON_DAB_STICK_REV2			0x00e0
+#define USB_PID_NOXON_DAB_STICK_REV3			0x00b4
 #define USB_PID_PINNACLE_EXPRESSCARD_320CX		0x022e
 #define USB_PID_PINNACLE_PCTV2000E			0x022c
 #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH		0x0228
@@ -278,6 +279,8 @@
 #define USB_PID_PCTV_400E				0x020f
 #define USB_PID_PCTV_450E				0x0222
 #define USB_PID_PCTV_452E				0x021f
+#define USB_PID_PCTV_78E				0x025a
+#define USB_PID_PCTV_79E				0x0262
 #define USB_PID_REALTEK_RTL2831U			0x2831
 #define USB_PID_REALTEK_RTL2832U			0x2832
 #define USB_PID_TECHNOTREND_CONNECT_S2_3600		0x3007
@@ -360,6 +363,7 @@
 #define USB_PID_FRIIO_WHITE				0x0001
 #define USB_PID_TVWAY_PLUS				0x0002
 #define USB_PID_SVEON_STV20				0xe39d
+#define USB_PID_SVEON_STV20_RTL2832U			0xd39d
 #define USB_PID_SVEON_STV22				0xe401
 #define USB_PID_SVEON_STV22_IT9137			0xe411
 #define USB_PID_AZUREWAVE_AZ6027			0x3275
@@ -374,4 +378,5 @@
 #define USB_PID_CTVDIGDUAL_V2				0xe410
 #define USB_PID_PCTV_2002E                              0x025c
 #define USB_PID_PCTV_2002E_SE                           0x025d
+#define USB_PID_SVEON_STV27                             0xd3af
 #endif
diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c
index 1e344b033277..22e8c2032f6d 100644
--- a/drivers/media/dvb-frontends/ds3000.c
+++ b/drivers/media/dvb-frontends/ds3000.c
@@ -864,6 +864,13 @@ struct dvb_frontend *ds3000_attach(const struct ds3000_config *config,
 	memcpy(&state->frontend.ops, &ds3000_ops,
 			sizeof(struct dvb_frontend_ops));
 	state->frontend.demodulator_priv = state;
+
+	/*
+	 * Some devices like T480 starts with voltage on. Be sure
+	 * to turn voltage off during init, as this can otherwise
+	 * interfere with Unicable SCR systems.
+	 */
+	ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF);
 	return &state->frontend;
 
 error3:
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index b2351466b0da..32cffca14d0b 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -715,6 +715,22 @@ static int m88rs2000_get_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
+static int m88rs2000_get_tune_settings(struct dvb_frontend *fe,
+	struct dvb_frontend_tune_settings *tune)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	if (c->symbol_rate > 3000000)
+		tune->min_delay_ms = 2000;
+	else
+		tune->min_delay_ms = 3000;
+
+	tune->step_size = c->symbol_rate / 16000;
+	tune->max_drift = c->symbol_rate / 2000;
+
+	return 0;
+}
+
 static int m88rs2000_i2c_gate_ctrl(struct dvb_frontend *fe, int enable)
 {
 	struct m88rs2000_state *state = fe->demodulator_priv;
@@ -746,7 +762,7 @@ static struct dvb_frontend_ops m88rs2000_ops = {
 		.symbol_rate_tolerance	= 500,	/* ppm */
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		      FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
-		      FE_CAN_QPSK |
+		      FE_CAN_QPSK | FE_CAN_INVERSION_AUTO |
 		      FE_CAN_FEC_AUTO
 	},
 
@@ -766,6 +782,7 @@ static struct dvb_frontend_ops m88rs2000_ops = {
 
 	.set_frontend = m88rs2000_set_frontend,
 	.get_frontend = m88rs2000_get_frontend,
+	.get_tune_settings = m88rs2000_get_tune_settings,
 };
 
 struct dvb_frontend *m88rs2000_attach(const struct m88rs2000_config *config,
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 8ad3a57cf640..287b977862e2 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -667,6 +667,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i;
 	u8 mode, rolloff, pilot, inversion, div;
+	fe_modulation_t modulation;
 
 	dev_dbg(&priv->i2c->dev, "%s: delivery_system=%d modulation=%d " \
 		"frequency=%d symbol_rate=%d inversion=%d pilot=%d " \
@@ -701,10 +702,13 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 
 	switch (c->delivery_system) {
 	case SYS_DVBS:
+		modulation = QPSK;
 		rolloff = 0;
 		pilot = 2;
 		break;
 	case SYS_DVBS2:
+		modulation = c->modulation;
+
 		switch (c->rolloff) {
 		case ROLLOFF_20:
 			rolloff = 2;
@@ -749,7 +753,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 
 	for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) {
 		if (c->delivery_system == TDA10071_MODCOD[i].delivery_system &&
-			c->modulation == TDA10071_MODCOD[i].modulation &&
+			modulation == TDA10071_MODCOD[i].modulation &&
 			c->fec_inner == TDA10071_MODCOD[i].fec) {
 			mode = TDA10071_MODCOD[i].val;
 			dev_dbg(&priv->i2c->dev, "%s: mode found=%02x\n",
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index 71c8570bd9ea..112394d138c9 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -1984,7 +1984,7 @@ static int adv7604_log_status(struct v4l2_subdev *sd)
 	v4l2_info(sd, "HDCP keys read: %s%s\n",
 			(hdmi_read(sd, 0x04) & 0x20) ? "yes" : "no",
 			(hdmi_read(sd, 0x04) & 0x10) ? "ERROR" : "");
-	if (!is_hdmi(sd)) {
+	if (is_hdmi(sd)) {
 		bool audio_pll_locked = hdmi_read(sd, 0x04) & 0x01;
 		bool audio_sample_packet_detect = hdmi_read(sd, 0x18) & 0x01;
 		bool audio_mute = io_read(sd, 0x65) & 0x40;
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index 36c504b78f2c..008ac87a9031 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -305,8 +305,8 @@ mt9v032_update_hblank(struct mt9v032 *mt9v032)
 
 	if (mt9v032->version->version == MT9V034_CHIP_ID_REV1)
 		min_hblank += (mt9v032->hratio - 1) * 10;
-	min_hblank = max_t(unsigned int, (int)mt9v032->model->data->min_row_time - crop->width,
-			   (int)min_hblank);
+	min_hblank = max_t(int, mt9v032->model->data->min_row_time - crop->width,
+			   min_hblank);
 	hblank = max_t(unsigned int, mt9v032->hblank, min_hblank);
 
 	return mt9v032_write(client, MT9V032_HORIZONTAL_BLANKING, hblank);
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index e8a1ce204036..cdd7c1b7259b 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1109,7 +1109,7 @@ static int ov7670_enum_framesizes(struct v4l2_subdev *sd,
 	 * windows that fall outside that.
 	 */
 	for (i = 0; i < n_win_sizes; i++) {
-		struct ov7670_win_size *win = &info->devtype->win_sizes[index];
+		struct ov7670_win_size *win = &info->devtype->win_sizes[i];
 		if (info->min_width && win->width < info->min_width)
 			continue;
 		if (info->min_height && win->height < info->min_height)
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 8741cae9c9f2..7026ab08ec91 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2138,7 +2138,7 @@ static int smiapp_set_selection(struct v4l2_subdev *subdev,
 		ret = smiapp_set_compose(subdev, fh, sel);
 		break;
 	default:
-		BUG();
+		ret = -EINVAL;
 	}
 
 	mutex_unlock(&sensor->mutex);
diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c
index 72af644fa051..cf93021a6500 100644
--- a/drivers/media/i2c/tda7432.c
+++ b/drivers/media/i2c/tda7432.c
@@ -293,7 +293,7 @@ static int tda7432_s_ctrl(struct v4l2_ctrl *ctrl)
 		if (t->mute->val) {
 			lf |= TDA7432_MUTE;
 			lr |= TDA7432_MUTE;
-			lf |= TDA7432_MUTE;
+			rf |= TDA7432_MUTE;
 			rr |= TDA7432_MUTE;
 		}
 		/* Mute & update balance*/
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index d5a7a135f75d..88c1606fd555 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -93,6 +93,7 @@ static long media_device_enum_entities(struct media_device *mdev,
 	struct media_entity *ent;
 	struct media_entity_desc u_ent;
 
+	memset(&u_ent, 0, sizeof(u_ent));
 	if (copy_from_user(&u_ent.id, &uent->id, sizeof(u_ent.id)))
 		return -EFAULT;
 
@@ -105,8 +106,6 @@ static long media_device_enum_entities(struct media_device *mdev,
 	if (ent->name) {
 		strncpy(u_ent.name, ent->name, sizeof(u_ent.name));
 		u_ent.name[sizeof(u_ent.name) - 1] = '\0';
-	} else {
-		memset(u_ent.name, 0, sizeof(u_ent.name));
 	}
 	u_ent.type = ent->type;
 	u_ent.revision = ent->revision;
diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 716bdc57fac6..83f5074706f9 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -1091,6 +1091,7 @@ static int cx18_probe(struct pci_dev *pci_dev,
 		setup.addr = ADDR_UNSET;
 		setup.type = cx->options.tuner;
 		setup.mode_mask = T_ANALOG_TV;  /* matches TV tuners */
+		setup.config = NULL;
 		if (cx->options.radio > 0)
 			setup.mode_mask |= T_RADIO;
 		setup.tuner_callback = (setup.type == TUNER_XC2028) ?
diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
index e1863dbf4edc..7a9b98bc208b 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
@@ -159,6 +159,12 @@ static int snd_ivtv_pcm_capture_open(struct snd_pcm_substream *substream)
 
 	/* Instruct the CX2341[56] to start sending packets */
 	snd_ivtv_lock(itvsc);
+
+	if (ivtv_init_on_first_open(itv)) {
+		snd_ivtv_unlock(itvsc);
+		return -ENXIO;
+	}
+
 	s = &itv->streams[IVTV_ENC_STREAM_TYPE_PCM];
 
 	v4l2_fh_init(&item.fh, s->vdev);
diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c
index c9b2350e92c8..6e4bdb90aa92 100644
--- a/drivers/media/pci/saa7134/saa7134-cards.c
+++ b/drivers/media/pci/saa7134/saa7134-cards.c
@@ -8045,8 +8045,8 @@ int saa7134_board_init2(struct saa7134_dev *dev)
 		break;
 	} /* switch() */
 
-	/* initialize tuner */
-	if (TUNER_ABSENT != dev->tuner_type) {
+	/* initialize tuner (don't do this when resuming) */
+	if (!dev->insuspend && TUNER_ABSENT != dev->tuner_type) {
 		int has_demod = (dev->tda9887_conf & TDA9887_PRESENT);
 
 		/* Note: radio tuner address is always filled in,
diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c
index eb472b5b26a0..40396e8b16a8 100644
--- a/drivers/media/pci/saa7134/saa7134-video.c
+++ b/drivers/media/pci/saa7134/saa7134-video.c
@@ -1243,6 +1243,7 @@ static int video_release(struct file *file)
 		videobuf_streamoff(&dev->cap);
 		res_free(dev, fh, RESOURCE_VIDEO);
 		videobuf_mmap_free(&dev->cap);
+		INIT_LIST_HEAD(&dev->cap.stream);
 	}
 	if (dev->cap.read_buf) {
 		buffer_release(&dev->cap, dev->cap.read_buf);
@@ -1254,6 +1255,7 @@ static int video_release(struct file *file)
 		videobuf_stop(&dev->vbi);
 		res_free(dev, fh, RESOURCE_VBI);
 		videobuf_mmap_free(&dev->vbi);
+		INIT_LIST_HEAD(&dev->vbi.stream);
 	}
 
 	/* ts-capture will not work in planar mode, so turn it off Hac: 04.05*/
@@ -1987,17 +1989,12 @@ int saa7134_streamoff(struct file *file, void *priv,
 					enum v4l2_buf_type type)
 {
 	struct saa7134_dev *dev = video_drvdata(file);
-	int err;
 	int res = saa7134_resource(file);
 
 	if (res != RESOURCE_EMPRESS)
 		pm_qos_remove_request(&dev->qos_request);
 
-	err = videobuf_streamoff(saa7134_queue(file));
-	if (err < 0)
-		return err;
-	res_free(dev, priv, res);
-	return 0;
+	return videobuf_streamoff(saa7134_queue(file));
 }
 EXPORT_SYMBOL_GPL(saa7134_streamoff);
 
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index 1c776c1186f1..1dbff1472809 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -1079,6 +1079,7 @@ static void preview_config_input_format(struct isp_prev_device *prev,
  */
 static void preview_config_input_size(struct isp_prev_device *prev, u32 active)
 {
+	const struct v4l2_mbus_framefmt *format = &prev->formats[PREV_PAD_SINK];
 	struct isp_device *isp = to_isp_device(prev);
 	unsigned int sph = prev->crop.left;
 	unsigned int eph = prev->crop.left + prev->crop.width - 1;
@@ -1086,6 +1087,14 @@ static void preview_config_input_size(struct isp_prev_device *prev, u32 active)
 	unsigned int elv = prev->crop.top + prev->crop.height - 1;
 	u32 features;
 
+	if (format->code != V4L2_MBUS_FMT_Y8_1X8 &&
+	    format->code != V4L2_MBUS_FMT_Y10_1X10) {
+		sph -= 2;
+		eph += 2;
+		slv -= 2;
+		elv += 2;
+	}
+
 	features = (prev->params.params[0].features & active)
 		 | (prev->params.params[1].features & ~active);
 
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index b4687a834f85..7245cca89257 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -635,8 +635,6 @@ static int vsp1_video_buffer_prepare(struct vb2_buffer *vb)
 	if (vb->num_planes < format->num_planes)
 		return -EINVAL;
 
-	buf->video = video;
-
 	for (i = 0; i < vb->num_planes; ++i) {
 		buf->addr[i] = vb2_dma_contig_plane_dma_addr(vb, i);
 		buf->length[i] = vb2_plane_size(vb, i);
diff --git a/drivers/media/platform/vsp1/vsp1_video.h b/drivers/media/platform/vsp1/vsp1_video.h
index d8612a378345..47b7a8ab5e2f 100644
--- a/drivers/media/platform/vsp1/vsp1_video.h
+++ b/drivers/media/platform/vsp1/vsp1_video.h
@@ -89,7 +89,6 @@ static inline struct vsp1_pipeline *to_vsp1_pipeline(struct media_entity *e)
 }
 
 struct vsp1_video_buffer {
-	struct vsp1_video *video;
 	struct vb2_buffer buf;
 	struct list_head queue;
 
diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c
index 3aecaf465094..f0c9c42867de 100644
--- a/drivers/media/tuners/fc2580.c
+++ b/drivers/media/tuners/fc2580.c
@@ -195,7 +195,7 @@ static int fc2580_set_params(struct dvb_frontend *fe)
 
 	f_ref = 2UL * priv->cfg->clock / r_val;
 	n_val = div_u64_rem(f_vco, f_ref, &k_val);
-	k_val_reg = 1UL * k_val * (1 << 20) / f_ref;
+	k_val_reg = div_u64(1ULL * k_val * (1 << 20), f_ref);
 
 	ret = fc2580_wr_reg(priv, 0x18, r18_val | ((k_val_reg >> 16) & 0xff));
 	if (ret < 0)
@@ -348,8 +348,8 @@ static int fc2580_set_params(struct dvb_frontend *fe)
 	if (ret < 0)
 		goto err;
 
-	ret = fc2580_wr_reg(priv, 0x37, 1UL * priv->cfg->clock * \
-			fc2580_if_filter_lut[i].mul / 1000000000);
+	ret = fc2580_wr_reg(priv, 0x37, div_u64(1ULL * priv->cfg->clock *
+			fc2580_if_filter_lut[i].mul, 1000000000));
 	if (ret < 0)
 		goto err;
 
diff --git a/drivers/media/tuners/fc2580_priv.h b/drivers/media/tuners/fc2580_priv.h
index be38a9e637e0..646c99452136 100644
--- a/drivers/media/tuners/fc2580_priv.h
+++ b/drivers/media/tuners/fc2580_priv.h
@@ -22,6 +22,7 @@
 #define FC2580_PRIV_H
 
 #include "fc2580.h"
+#include <linux/math64.h>
 
 struct fc2580_reg_val {
 	u8 reg;
diff --git a/drivers/media/tuners/m88ts2022.c b/drivers/media/tuners/m88ts2022.c
index 40c42dec721b..7a62097aa9ea 100644
--- a/drivers/media/tuners/m88ts2022.c
+++ b/drivers/media/tuners/m88ts2022.c
@@ -314,7 +314,7 @@ static int m88ts2022_set_params(struct dvb_frontend *fe)
 	div_min = gdiv28 * 78 / 100;
 	div_max = clamp_val(div_max, 0U, 63U);
 
-	f_3db_hz = c->symbol_rate * 135UL / 200UL;
+	f_3db_hz = mult_frac(c->symbol_rate, 135, 200);
 	f_3db_hz +=  2000000U + (frequency_offset_khz * 1000U);
 	f_3db_hz = clamp(f_3db_hz, 7000000U, 40000000U);
 
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index 2018befabb5a..e71decbfd0af 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -93,7 +93,7 @@ struct xc4000_priv {
 	struct firmware_description *firm;
 	int	firm_size;
 	u32	if_khz;
-	u32	freq_hz;
+	u32	freq_hz, freq_offset;
 	u32	bandwidth;
 	u8	video_standard;
 	u8	rf_mode;
@@ -1157,14 +1157,14 @@ static int xc4000_set_params(struct dvb_frontend *fe)
 	case SYS_ATSC:
 		dprintk(1, "%s() VSB modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_AIR;
-		priv->freq_hz = c->frequency - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = XC4000_DTV6;
 		type = DTV6;
 		break;
 	case SYS_DVBC_ANNEX_B:
 		dprintk(1, "%s() QAM modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_CABLE;
-		priv->freq_hz = c->frequency - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = XC4000_DTV6;
 		type = DTV6;
 		break;
@@ -1173,23 +1173,23 @@ static int xc4000_set_params(struct dvb_frontend *fe)
 		dprintk(1, "%s() OFDM\n", __func__);
 		if (bw == 0) {
 			if (c->frequency < 400000000) {
-				priv->freq_hz = c->frequency - 2250000;
+				priv->freq_offset = 2250000;
 			} else {
-				priv->freq_hz = c->frequency - 2750000;
+				priv->freq_offset = 2750000;
 			}
 			priv->video_standard = XC4000_DTV7_8;
 			type = DTV78;
 		} else if (bw <= 6000000) {
 			priv->video_standard = XC4000_DTV6;
-			priv->freq_hz = c->frequency - 1750000;
+			priv->freq_offset = 1750000;
 			type = DTV6;
 		} else if (bw <= 7000000) {
 			priv->video_standard = XC4000_DTV7;
-			priv->freq_hz = c->frequency - 2250000;
+			priv->freq_offset = 2250000;
 			type = DTV7;
 		} else {
 			priv->video_standard = XC4000_DTV8;
-			priv->freq_hz = c->frequency - 2750000;
+			priv->freq_offset = 2750000;
 			type = DTV8;
 		}
 		priv->rf_mode = XC_RF_MODE_AIR;
@@ -1200,6 +1200,8 @@ static int xc4000_set_params(struct dvb_frontend *fe)
 		goto fail;
 	}
 
+	priv->freq_hz = c->frequency - priv->freq_offset;
+
 	dprintk(1, "%s() frequency=%d (compensated)\n",
 		__func__, priv->freq_hz);
 
@@ -1520,7 +1522,7 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq)
 {
 	struct xc4000_priv *priv = fe->tuner_priv;
 
-	*freq = priv->freq_hz;
+	*freq = priv->freq_hz + priv->freq_offset;
 
 	if (debug) {
 		mutex_lock(&priv->lock);
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index 5cd09a681b6a..b2d9e9cb97f7 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -55,7 +55,7 @@ struct xc5000_priv {
 
 	u32 if_khz;
 	u16 xtal_khz;
-	u32 freq_hz;
+	u32 freq_hz, freq_offset;
 	u32 bandwidth;
 	u8  video_standard;
 	u8  rf_mode;
@@ -755,13 +755,13 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 	case SYS_ATSC:
 		dprintk(1, "%s() VSB modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_AIR;
-		priv->freq_hz = freq - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = DTV6;
 		break;
 	case SYS_DVBC_ANNEX_B:
 		dprintk(1, "%s() QAM modulation\n", __func__);
 		priv->rf_mode = XC_RF_MODE_CABLE;
-		priv->freq_hz = freq - 1750000;
+		priv->freq_offset = 1750000;
 		priv->video_standard = DTV6;
 		break;
 	case SYS_ISDBT:
@@ -776,15 +776,15 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 		switch (bw) {
 		case 6000000:
 			priv->video_standard = DTV6;
-			priv->freq_hz = freq - 1750000;
+			priv->freq_offset = 1750000;
 			break;
 		case 7000000:
 			priv->video_standard = DTV7;
-			priv->freq_hz = freq - 2250000;
+			priv->freq_offset = 2250000;
 			break;
 		case 8000000:
 			priv->video_standard = DTV8;
-			priv->freq_hz = freq - 2750000;
+			priv->freq_offset = 2750000;
 			break;
 		default:
 			printk(KERN_ERR "xc5000 bandwidth not set!\n");
@@ -798,15 +798,15 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 		priv->rf_mode = XC_RF_MODE_CABLE;
 		if (bw <= 6000000) {
 			priv->video_standard = DTV6;
-			priv->freq_hz = freq - 1750000;
+			priv->freq_offset = 1750000;
 			b = 6;
 		} else if (bw <= 7000000) {
 			priv->video_standard = DTV7;
-			priv->freq_hz = freq - 2250000;
+			priv->freq_offset = 2250000;
 			b = 7;
 		} else {
 			priv->video_standard = DTV7_8;
-			priv->freq_hz = freq - 2750000;
+			priv->freq_offset = 2750000;
 			b = 8;
 		}
 		dprintk(1, "%s() Bandwidth %dMHz (%d)\n", __func__,
@@ -817,6 +817,8 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 		return -EINVAL;
 	}
 
+	priv->freq_hz = freq - priv->freq_offset;
+
 	dprintk(1, "%s() frequency=%d (compensated to %d)\n",
 		__func__, freq, priv->freq_hz);
 
@@ -1067,7 +1069,7 @@ static int xc5000_get_frequency(struct dvb_frontend *fe, u32 *freq)
 {
 	struct xc5000_priv *priv = fe->tuner_priv;
 	dprintk(1, "%s()\n", __func__);
-	*freq = priv->freq_hz;
+	*freq = priv->freq_hz + priv->freq_offset;
 	return 0;
 }
 
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index f6154546b5c0..7ed75efa1c36 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -787,11 +787,27 @@ static int au0828_i2s_init(struct au0828_dev *dev)
 
 /*
  * Auvitek au0828 analog stream enable
- * Please set interface0 to AS5 before enable the stream
  */
 static int au0828_analog_stream_enable(struct au0828_dev *d)
 {
+	struct usb_interface *iface;
+	int ret;
+
 	dprintk(1, "au0828_analog_stream_enable called\n");
+
+	iface = usb_ifnum_to_if(d->usbdev, 0);
+	if (iface && iface->cur_altsetting->desc.bAlternateSetting != 5) {
+		dprintk(1, "Changing intf#0 to alt 5\n");
+		/* set au0828 interface0 to AS5 here again */
+		ret = usb_set_interface(d->usbdev, 0, 5);
+		if (ret < 0) {
+			printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
+			return -EBUSY;
+		}
+	}
+
+	/* FIXME: size should be calculated using d->width, d->height */
+
 	au0828_writereg(d, AU0828_SENSORCTRL_VBI_103, 0x00);
 	au0828_writereg(d, 0x106, 0x00);
 	/* set x position */
@@ -1002,15 +1018,6 @@ static int au0828_v4l2_open(struct file *filp)
 		return -ERESTARTSYS;
 	}
 	if (dev->users == 0) {
-		/* set au0828 interface0 to AS5 here again */
-		ret = usb_set_interface(dev->usbdev, 0, 5);
-		if (ret < 0) {
-			mutex_unlock(&dev->lock);
-			printk(KERN_INFO "Au0828 can't set alternate to 5!\n");
-			kfree(fh);
-			return -EBUSY;
-		}
-
 		au0828_analog_stream_enable(dev);
 		au0828_analog_stream_reset(dev);
 
@@ -1252,13 +1259,6 @@ static int au0828_set_format(struct au0828_dev *dev, unsigned int cmd,
 		}
 	}
 
-	/* set au0828 interface0 to AS5 here again */
-	ret = usb_set_interface(dev->usbdev, 0, 5);
-	if (ret < 0) {
-		printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
-		return -EBUSY;
-	}
-
 	au0828_analog_stream_enable(dev);
 
 	return 0;
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 8ede8ea762e6..88228f735342 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -1541,6 +1541,10 @@ static const struct usb_device_id af9035_id_table[] = {
 		&af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900,
 		&af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_78E,
+		&af9035_props, "PCTV 78e", RC_MAP_IT913X_V1) },
+	{ DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_79E,
+		&af9035_props, "PCTV 79e", RC_MAP_IT913X_V2) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, af9035_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index fda5c64ba0e8..fd1312d0b078 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1382,6 +1382,7 @@ static const struct dvb_usb_device_properties rtl2832u_props = {
 };
 
 static const struct usb_device_id rtl28xxu_id_table[] = {
+	/* RTL2831U devices: */
 	{ DVB_USB_DEVICE(USB_VID_REALTEK, USB_PID_REALTEK_RTL2831U,
 		&rtl2831u_props, "Realtek RTL2831U reference design", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_FREECOM_DVBT,
@@ -1389,6 +1390,7 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 	{ DVB_USB_DEVICE(USB_VID_WIDEVIEW, USB_PID_FREECOM_DVBT_2,
 		&rtl2831u_props, "Freecom USB2.0 DVB-T", NULL) },
 
+	/* RTL2832U devices: */
 	{ DVB_USB_DEVICE(USB_VID_REALTEK, 0x2832,
 		&rtl2832u_props, "Realtek RTL2832U reference design", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_REALTEK, 0x2838,
@@ -1401,6 +1403,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 		&rtl2832u_props, "TerraTec NOXON DAB Stick", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_TERRATEC, USB_PID_NOXON_DAB_STICK_REV2,
 		&rtl2832u_props, "TerraTec NOXON DAB Stick (rev 2)", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_TERRATEC, USB_PID_NOXON_DAB_STICK_REV3,
+		&rtl2832u_props, "TerraTec NOXON DAB Stick (rev 3)", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_GTEK, USB_PID_TREKSTOR_TERRES_2_0,
 		&rtl2832u_props, "Trekstor DVB-T Stick Terres 2.0", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_DEXATEK, 0x1101,
@@ -1429,7 +1433,16 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 		&rtl2832u_props, "Leadtek WinFast DTV Dongle mini", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_GTEK, USB_PID_CPYTO_REDI_PC50A,
 		&rtl2832u_props, "Crypto ReDi PC 50 A", NULL) },
-
+	{ DVB_USB_DEVICE(USB_VID_KYE, 0x707f,
+		&rtl2832u_props, "Genius TVGo DVB-T03", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, 0xd395,
+		&rtl2832u_props, "Peak DVB-T USB", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_SVEON_STV20_RTL2832U,
+		&rtl2832u_props, "Sveon STV20", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_SVEON_STV27,
+		&rtl2832u_props, "Sveon STV27", NULL) },
+
+	/* RTL2832P devices: */
 	{ DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131,
 		&rtl2832u_props, "Astrometa DVB-T2", NULL) },
 	{ }
diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c
index 05e9bd11a3ff..dfdfa772eb1e 100644
--- a/drivers/media/usb/em28xx/em28xx-audio.c
+++ b/drivers/media/usb/em28xx/em28xx-audio.c
@@ -252,7 +252,7 @@ static int snd_em28xx_capture_open(struct snd_pcm_substream *substream)
 {
 	struct em28xx *dev = snd_pcm_substream_chip(substream);
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	int ret = 0;
+	int nonblock, ret = 0;
 
 	if (!dev) {
 		em28xx_err("BUG: em28xx can't find device struct."
@@ -265,15 +265,15 @@ static int snd_em28xx_capture_open(struct snd_pcm_substream *substream)
 
 	dprintk("opening device and trying to acquire exclusive lock\n");
 
+	nonblock = !!(substream->f_flags & O_NONBLOCK);
+	if (nonblock) {
+		if (!mutex_trylock(&dev->lock))
+		return -EAGAIN;
+	} else
+		mutex_lock(&dev->lock);
+
 	runtime->hw = snd_em28xx_hw_capture;
 	if ((dev->alt == 0 || dev->is_audio_only) && dev->adev.users == 0) {
-		int nonblock = !!(substream->f_flags & O_NONBLOCK);
-
-		if (nonblock) {
-			if (!mutex_trylock(&dev->lock))
-				return -EAGAIN;
-		} else
-			mutex_lock(&dev->lock);
 		if (dev->is_audio_only)
 			/* vendor audio is on a separate interface */
 			dev->alt = 1;
@@ -299,11 +299,11 @@ static int snd_em28xx_capture_open(struct snd_pcm_substream *substream)
 		ret = em28xx_audio_analog_set(dev);
 		if (ret < 0)
 			goto err;
-
-		dev->adev.users++;
-		mutex_unlock(&dev->lock);
 	}
 
+	dev->adev.users++;
+	mutex_unlock(&dev->lock);
+
 	/* Dynamically adjust the period size */
 	snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
 	snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_BYTES,
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 4d97a76cc3b0..c1a3f8f95750 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -2993,16 +2993,6 @@ static int em28xx_init_dev(struct em28xx *dev, struct usb_device *udev,
 		}
 	}
 
-	if (dev->chip_id == CHIP_ID_EM2870 ||
-	    dev->chip_id == CHIP_ID_EM2874 ||
-	    dev->chip_id == CHIP_ID_EM28174 ||
-	    dev->chip_id == CHIP_ID_EM28178) {
-		/* Digital only device - don't load any alsa module */
-		dev->audio_mode.has_audio = false;
-		dev->has_audio_class = false;
-		dev->has_alsa_audio = false;
-	}
-
 	if (chip_name != default_chip_name)
 		printk(KERN_INFO DRIVER_NAME
 		       ": chip ID is %s\n", chip_name);
@@ -3272,7 +3262,6 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 	dev->alt   = -1;
 	dev->is_audio_only = has_audio && !(has_video || has_dvb);
 	dev->has_alsa_audio = has_audio;
-	dev->audio_mode.has_audio = has_audio;
 	dev->has_video = has_video;
 	dev->ifnum = ifnum;
 
diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index 898fb9bd88a2..97fd881a4e7b 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -506,8 +506,18 @@ int em28xx_audio_setup(struct em28xx *dev)
 	int vid1, vid2, feat, cfg;
 	u32 vid;
 
-	if (!dev->audio_mode.has_audio)
+	if (dev->chip_id == CHIP_ID_EM2870 ||
+	    dev->chip_id == CHIP_ID_EM2874 ||
+	    dev->chip_id == CHIP_ID_EM28174 ||
+	    dev->chip_id == CHIP_ID_EM28178) {
+		/* Digital only device - don't load any alsa module */
+		dev->audio_mode.has_audio = false;
+		dev->has_audio_class = false;
+		dev->has_alsa_audio = false;
 		return 0;
+	}
+
+	dev->audio_mode.has_audio = true;
 
 	/* See how this device is configured */
 	cfg = em28xx_read_reg(dev, EM28XX_R00_CHIPCFG);
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index a0a669e81362..1373cfa4e974 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -693,7 +693,8 @@ static void pctv_520e_init(struct em28xx *dev)
 static int em28xx_pctv_290e_set_lna(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	struct em28xx *dev = fe->dvb->priv;
+	struct em28xx_i2c_bus *i2c_bus = fe->dvb->priv;
+	struct em28xx *dev = i2c_bus->dev;
 #ifdef CONFIG_GPIOLIB
 	struct em28xx_dvb *dvb = dev->dvb;
 	int ret;
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index c3c928937dcd..e24ee08e634e 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -953,13 +953,16 @@ static int em28xx_stop_streaming(struct vb2_queue *vq)
 	}
 
 	spin_lock_irqsave(&dev->slock, flags);
+	if (dev->usb_ctl.vid_buf != NULL) {
+		vb2_buffer_done(&dev->usb_ctl.vid_buf->vb, VB2_BUF_STATE_ERROR);
+		dev->usb_ctl.vid_buf = NULL;
+	}
 	while (!list_empty(&vidq->active)) {
 		struct em28xx_buffer *buf;
 		buf = list_entry(vidq->active.next, struct em28xx_buffer, list);
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
-	dev->usb_ctl.vid_buf = NULL;
 	spin_unlock_irqrestore(&dev->slock, flags);
 
 	return 0;
@@ -981,13 +984,16 @@ int em28xx_stop_vbi_streaming(struct vb2_queue *vq)
 	}
 
 	spin_lock_irqsave(&dev->slock, flags);
+	if (dev->usb_ctl.vbi_buf != NULL) {
+		vb2_buffer_done(&dev->usb_ctl.vbi_buf->vb, VB2_BUF_STATE_ERROR);
+		dev->usb_ctl.vbi_buf = NULL;
+	}
 	while (!list_empty(&vbiq->active)) {
 		struct em28xx_buffer *buf;
 		buf = list_entry(vbiq->active.next, struct em28xx_buffer, list);
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
-	dev->usb_ctl.vbi_buf = NULL;
 	spin_unlock_irqrestore(&dev->slock, flags);
 
 	return 0;
diff --git a/drivers/media/usb/gspca/pac7302.c b/drivers/media/usb/gspca/pac7302.c
index 2fd1c5e31a0f..339adce7c7a5 100644
--- a/drivers/media/usb/gspca/pac7302.c
+++ b/drivers/media/usb/gspca/pac7302.c
@@ -928,6 +928,7 @@ static const struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x093a, 0x2620)},
 	{USB_DEVICE(0x093a, 0x2621)},
 	{USB_DEVICE(0x093a, 0x2622), .driver_info = FL_VFLIP},
+	{USB_DEVICE(0x093a, 0x2623), .driver_info = FL_VFLIP},
 	{USB_DEVICE(0x093a, 0x2624), .driver_info = FL_VFLIP},
 	{USB_DEVICE(0x093a, 0x2625)},
 	{USB_DEVICE(0x093a, 0x2626)},
diff --git a/drivers/media/usb/gspca/sn9c20x.c b/drivers/media/usb/gspca/sn9c20x.c
index 2a38621cf718..41a9a892f79c 100644
--- a/drivers/media/usb/gspca/sn9c20x.c
+++ b/drivers/media/usb/gspca/sn9c20x.c
@@ -2359,6 +2359,7 @@ static const struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x045e, 0x00f4), SN9C20X(OV9650, 0x30, 0)},
 	{USB_DEVICE(0x145f, 0x013d), SN9C20X(OV7660, 0x21, 0)},
 	{USB_DEVICE(0x0458, 0x7029), SN9C20X(HV7131R, 0x11, 0)},
+	{USB_DEVICE(0x0458, 0x7045), SN9C20X(MT9M112, 0x5d, LED_REVERSE)},
 	{USB_DEVICE(0x0458, 0x704a), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0x0458, 0x704c), SN9C20X(MT9M112, 0x5d, 0)},
 	{USB_DEVICE(0xa168, 0x0610), SN9C20X(HV7131R, 0x11, 0)},
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index 0500c4175d5f..6bce01a674f9 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -82,7 +82,7 @@ static void hdpvr_read_bulk_callback(struct urb *urb)
 }
 
 /*=========================================================================*/
-/* bufffer bits */
+/* buffer bits */
 
 /* function expects dev->io_mutex to be hold by caller */
 int hdpvr_cancel_queue(struct hdpvr_device *dev)
@@ -926,7 +926,7 @@ static int hdpvr_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_AUDIO_ENCODING:
 		if (dev->flags & HDPVR_FLAG_AC3_CAP) {
 			opt->audio_codec = ctrl->val;
-			return hdpvr_set_audio(dev, opt->audio_input,
+			return hdpvr_set_audio(dev, opt->audio_input + 1,
 					      opt->audio_codec);
 		}
 		return 0;
@@ -1198,7 +1198,7 @@ int hdpvr_register_videodev(struct hdpvr_device *dev, struct device *parent,
 	v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
 		V4L2_CID_MPEG_AUDIO_ENCODING,
 		ac3 ? V4L2_MPEG_AUDIO_ENCODING_AC3 : V4L2_MPEG_AUDIO_ENCODING_AAC,
-		0x7, V4L2_MPEG_AUDIO_ENCODING_AAC);
+		0x7, ac3 ? dev->options.audio_codec : V4L2_MPEG_AUDIO_ENCODING_AAC);
 	v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
 		V4L2_CID_MPEG_VIDEO_ENCODING,
 		V4L2_MPEG_VIDEO_ENCODING_MPEG_4_AVC, 0x3,
diff --git a/drivers/media/usb/stk1160/stk1160-core.c b/drivers/media/usb/stk1160/stk1160-core.c
index 34a26e0cfe77..03504dcf3c52 100644
--- a/drivers/media/usb/stk1160/stk1160-core.c
+++ b/drivers/media/usb/stk1160/stk1160-core.c
@@ -67,17 +67,25 @@ int stk1160_read_reg(struct stk1160 *dev, u16 reg, u8 *value)
 {
 	int ret;
 	int pipe = usb_rcvctrlpipe(dev->udev, 0);
+	u8 *buf;
 
 	*value = 0;
+
+	buf = kmalloc(sizeof(u8), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 	ret = usb_control_msg(dev->udev, pipe, 0x00,
 			USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			0x00, reg, value, sizeof(u8), HZ);
+			0x00, reg, buf, sizeof(u8), HZ);
 	if (ret < 0) {
 		stk1160_err("read failed on reg 0x%x (%d)\n",
 			reg, ret);
+		kfree(buf);
 		return ret;
 	}
 
+	*value = *buf;
+	kfree(buf);
 	return 0;
 }
 
diff --git a/drivers/media/usb/stk1160/stk1160.h b/drivers/media/usb/stk1160/stk1160.h
index 05b05b160e1e..abdea484c998 100644
--- a/drivers/media/usb/stk1160/stk1160.h
+++ b/drivers/media/usb/stk1160/stk1160.h
@@ -143,7 +143,6 @@ struct stk1160 {
 	int num_alt;
 
 	struct stk1160_isoc_ctl isoc_ctl;
-	char urb_buf[255];	 /* urb control msg buffer */
 
 	/* frame properties */
 	int width;		  /* current frame width */
diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
index 5c45c9d0712d..9c29552aedec 100644
--- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c
+++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
@@ -156,6 +156,9 @@ static int ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struc
 		   0x00, 0x00, 0x00, 0x00,
 		   0x00, 0x00 };
 
+	if (cmd->msg_len > sizeof(b) - 4)
+		return -EINVAL;
+
 	memcpy(&b[4], cmd->msg, cmd->msg_len);
 
 	state->config->send_command(fe, 0x72,
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index c3bb2502225b..753ad4cfc118 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -2210,6 +2210,15 @@ static struct usb_device_id uvc_ids[] = {
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= UVC_QUIRK_PROBE_DEF },
+	/* Dell XPS M1330 (OmniVision OV7670 webcam) */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x05a9,
+	  .idProduct		= 0x7670,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_QUIRK_PROBE_DEF },
 	/* Apple Built-In iSight */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 898c208889cd..2ef5b0f8ef77 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -361,6 +361,14 @@ static int uvc_commit_video(struct uvc_streaming *stream,
  * Clocks and timestamps
  */
 
+static inline void uvc_video_get_ts(struct timespec *ts)
+{
+	if (uvc_clock_param == CLOCK_MONOTONIC)
+		ktime_get_ts(ts);
+	else
+		ktime_get_real_ts(ts);
+}
+
 static void
 uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
 		       const __u8 *data, int len)
@@ -420,7 +428,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
 	stream->clock.last_sof = dev_sof;
 
 	host_sof = usb_get_current_frame_number(stream->dev->udev);
-	ktime_get_ts(&ts);
+	uvc_video_get_ts(&ts);
 
 	/* The UVC specification allows device implementations that can't obtain
 	 * the USB frame number to keep their own frame counters as long as they
@@ -1011,10 +1019,7 @@ static int uvc_video_decode_start(struct uvc_streaming *stream,
 			return -ENODATA;
 		}
 
-		if (uvc_clock_param == CLOCK_MONOTONIC)
-			ktime_get_ts(&ts);
-		else
-			ktime_get_real_ts(&ts);
+		uvc_video_get_ts(&ts);
 
 		buf->buf.v4l2_buf.sequence = stream->sequence;
 		buf->buf.v4l2_buf.timestamp.tv_sec = ts.tv_sec;
@@ -1847,7 +1852,25 @@ int uvc_video_enable(struct uvc_streaming *stream, int enable)
 
 	if (!enable) {
 		uvc_uninit_video(stream, 1);
-		usb_set_interface(stream->dev->udev, stream->intfnum, 0);
+		if (stream->intf->num_altsetting > 1) {
+			usb_set_interface(stream->dev->udev,
+					  stream->intfnum, 0);
+		} else {
+			/* UVC doesn't specify how to inform a bulk-based device
+			 * when the video stream is stopped. Windows sends a
+			 * CLEAR_FEATURE(HALT) request to the video streaming
+			 * bulk endpoint, mimic the same behaviour.
+			 */
+			unsigned int epnum = stream->header.bEndpointAddress
+					   & USB_ENDPOINT_NUMBER_MASK;
+			unsigned int dir = stream->header.bEndpointAddress
+					 & USB_ENDPOINT_DIR_MASK;
+			unsigned int pipe;
+
+			pipe = usb_sndbulkpipe(stream->dev->udev, epnum) | dir;
+			usb_clear_halt(stream->dev->udev, pipe);
+		}
+
 		uvc_queue_enable(&stream->queue, 0);
 		uvc_video_clock_cleanup(stream);
 		return 0;
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 433d6d77942e..c5521cec933b 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -431,16 +431,13 @@ static unsigned int clamp_align(unsigned int x, unsigned int min,
 	/* Bits that must be zero to be aligned */
 	unsigned int mask = ~((1 << align) - 1);
 
+	/* Clamp to aligned min and max */
+	x = clamp(x, (min + ~mask) & mask, max & mask);
+
 	/* Round to nearest aligned value */
 	if (align)
 		x = (x + (1 << (align - 1))) & mask;
 
-	/* Clamp to aligned value of min and max */
-	if (x < min)
-		x = (min + ~mask) & mask;
-	else if (x > max)
-		x = max & mask;
-
 	return x;
 }
 
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 8f7a6a454a4c..fca336b65351 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -178,6 +178,9 @@ struct v4l2_create_buffers32 {
 
 static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
+	if (get_user(kp->type, &up->type))
+		return -EFAULT;
+
 	switch (kp->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
@@ -204,17 +207,16 @@ static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __us
 
 static int get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)) ||
-			get_user(kp->type, &up->type))
-			return -EFAULT;
+	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)))
+		return -EFAULT;
 	return __get_v4l2_format32(kp, up);
 }
 
 static int get_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up)
 {
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_create_buffers32)) ||
-	    copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format.fmt)))
-			return -EFAULT;
+	    copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format)))
+		return -EFAULT;
 	return __get_v4l2_format32(&kp->format, &up->format);
 }
 
@@ -787,8 +789,8 @@ static int put_v4l2_subdev_edid32(struct v4l2_subdev_edid *kp, struct v4l2_subde
 #define VIDIOC_DQBUF32		_IOWR('V', 17, struct v4l2_buffer32)
 #define VIDIOC_ENUMSTD32	_IOWR('V', 25, struct v4l2_standard32)
 #define VIDIOC_ENUMINPUT32	_IOWR('V', 26, struct v4l2_input32)
-#define VIDIOC_SUBDEV_G_EDID32	_IOWR('V', 63, struct v4l2_subdev_edid32)
-#define VIDIOC_SUBDEV_S_EDID32	_IOWR('V', 64, struct v4l2_subdev_edid32)
+#define VIDIOC_SUBDEV_G_EDID32	_IOWR('V', 40, struct v4l2_subdev_edid32)
+#define VIDIOC_SUBDEV_S_EDID32	_IOWR('V', 41, struct v4l2_subdev_edid32)
 #define VIDIOC_TRY_FMT32      	_IOWR('V', 64, struct v4l2_format32)
 #define VIDIOC_G_EXT_CTRLS32    _IOWR('V', 71, struct v4l2_ext_controls32)
 #define VIDIOC_S_EXT_CTRLS32    _IOWR('V', 72, struct v4l2_ext_controls32)
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index f7902fe8a526..78d99b137d91 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -26,6 +26,10 @@
 #include <linux/v4l2-dv-timings.h>
 #include <media/v4l2-dv-timings.h>
 
+MODULE_AUTHOR("Hans Verkuil");
+MODULE_DESCRIPTION("V4L2 DV Timings Helper Functions");
+MODULE_LICENSE("GPL");
+
 const struct v4l2_dv_timings v4l2_dv_timings_presets[] = {
 	V4L2_DV_BT_CEA_640X480P59_94,
 	V4L2_DV_BT_CEA_720X480I59_94,
@@ -591,10 +595,10 @@ struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait)
 		aspect.denominator = 9;
 	} else if (ratio == 34) {
 		aspect.numerator = 4;
-		aspect.numerator = 3;
+		aspect.denominator = 3;
 	} else if (ratio == 68) {
 		aspect.numerator = 15;
-		aspect.numerator = 9;
+		aspect.denominator = 9;
 	} else {
 		aspect.numerator = hor_landscape + 99;
 		aspect.denominator = 100;
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index a127925c9d61..06faea4d60ee 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -745,6 +745,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 	 * to the userspace.
 	 */
 	req->count = allocated_buffers;
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	return 0;
 }
@@ -793,6 +794,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
 		memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
 		q->memory = create->memory;
+		q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 	}
 
 	num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers);
@@ -1447,6 +1449,7 @@ static int vb2_internal_qbuf(struct vb2_queue *q, struct v4l2_buffer *b)
 	 * dequeued in dqbuf.
 	 */
 	list_add_tail(&vb->queued_entry, &q->queued_list);
+	q->waiting_for_buffers = false;
 	vb->state = VB2_BUF_STATE_QUEUED;
 
 	/*
@@ -1841,6 +1844,7 @@ static int vb2_internal_streamoff(struct vb2_queue *q, enum v4l2_buf_type type)
 	 * and videobuf, effectively returning control over them to userspace.
 	 */
 	__vb2_queue_cancel(q);
+	q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
 
 	dprintk(3, "Streamoff successful\n");
 	return 0;
@@ -2150,9 +2154,16 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait)
 	}
 
 	/*
-	 * There is nothing to wait for if no buffers have already been queued.
+	 * There is nothing to wait for if the queue isn't streaming.
 	 */
-	if (list_empty(&q->queued_list))
+	if (!vb2_is_streaming(q))
+		return res | POLLERR;
+	/*
+	 * For compatibility with vb1: if QBUF hasn't been called yet, then
+	 * return POLLERR as well. This only affects capture queues, output
+	 * queues will always initialize waiting_for_buffers to false.
+	 */
+	if (q->waiting_for_buffers)
 		return res | POLLERR;
 
 	if (list_empty(&q->done_list))
diff --git a/drivers/memory/mvebu-devbus.c b/drivers/memory/mvebu-devbus.c
index 110c03627051..b59a17fb7c3e 100644
--- a/drivers/memory/mvebu-devbus.c
+++ b/drivers/memory/mvebu-devbus.c
@@ -108,8 +108,19 @@ static int devbus_set_timing_params(struct devbus *devbus,
 			node->full_name);
 		return err;
 	}
-	/* Convert bit width to byte width */
-	r.bus_width /= 8;
+
+	/*
+	 * The bus width is encoded into the register as 0 for 8 bits,
+	 * and 1 for 16 bits, so we do the necessary conversion here.
+	 */
+	if (r.bus_width == 8)
+		r.bus_width = 0;
+	else if (r.bus_width == 16)
+		r.bus_width = 1;
+	else {
+		dev_err(devbus->dev, "invalid bus width %d\n", r.bus_width);
+		return -EINVAL;
+	}
 
 	err = get_timing_param_ps(devbus, node, "devbus,badr-skew-ps",
 				 &r.badr_skew);
diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c
index 5653e505f91f..424f51d1e2ce 100644
--- a/drivers/message/fusion/mptspi.c
+++ b/drivers/message/fusion/mptspi.c
@@ -1422,6 +1422,11 @@ mptspi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_mptspi_probe;
         }
 
+	/* VMWare emulation doesn't properly implement WRITE_SAME
+	 */
+	if (pdev->subsystem_vendor == 0x15AD)
+		sh->no_write_same = 1;
+
 	spin_lock_irqsave(&ioc->FreeQlock, flags);
 
 	/* Attach the SCSI Host to the IOC structure
diff --git a/drivers/mfd/88pm800.c b/drivers/mfd/88pm800.c
index 7dca1e640970..841717a2842c 100644
--- a/drivers/mfd/88pm800.c
+++ b/drivers/mfd/88pm800.c
@@ -571,7 +571,7 @@ static int pm800_probe(struct i2c_client *client,
 	ret = pm800_pages_init(chip);
 	if (ret) {
 		dev_err(&client->dev, "pm800_pages_init failed!\n");
-		goto err_page_init;
+		goto err_device_init;
 	}
 
 	ret = device_800_init(chip, pdata);
@@ -587,7 +587,6 @@ static int pm800_probe(struct i2c_client *client,
 
 err_device_init:
 	pm800_pages_exit(chip);
-err_page_init:
 err_subchip_alloc:
 	pm80x_deinit();
 out_init:
diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index c9b1f6422941..bcfc9e85b4a0 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -1179,12 +1179,18 @@ static int pm860x_probe(struct i2c_client *client,
 		chip->companion_addr = pdata->companion_addr;
 		chip->companion = i2c_new_dummy(chip->client->adapter,
 						chip->companion_addr);
+		if (!chip->companion) {
+			dev_err(&client->dev,
+				"Failed to allocate I2C companion device\n");
+			return -ENODEV;
+		}
 		chip->regmap_companion = regmap_init_i2c(chip->companion,
 							&pm860x_regmap_config);
 		if (IS_ERR(chip->regmap_companion)) {
 			ret = PTR_ERR(chip->regmap_companion);
 			dev_err(&chip->companion->dev,
 				"Failed to allocate register map: %d\n", ret);
+			i2c_unregister_device(chip->companion);
 			return ret;
 		}
 		i2c_set_clientdata(chip->companion, chip);
diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index d3e23278d299..38917a822335 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -322,9 +322,12 @@ static int kempld_detect_device(struct kempld_device_data *pld)
 		return -ENODEV;
 	}
 
-	/* Release hardware mutex if aquired */
-	if (!(index_reg & KEMPLD_MUTEX_KEY))
+	/* Release hardware mutex if acquired */
+	if (!(index_reg & KEMPLD_MUTEX_KEY)) {
 		iowrite8(KEMPLD_MUTEX_KEY, pld->io_index);
+		/* PXT and COMe-cPC2 boards may require a second release */
+		iowrite8(KEMPLD_MUTEX_KEY, pld->io_index);
+	}
 
 	mutex_unlock(&pld->lock);
 
diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c
index f53d5823a3f7..e5fce765accb 100644
--- a/drivers/mfd/max77686.c
+++ b/drivers/mfd/max77686.c
@@ -121,6 +121,10 @@ static int max77686_i2c_probe(struct i2c_client *i2c,
 		dev_info(max77686->dev, "device found\n");
 
 	max77686->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+	if (!max77686->rtc) {
+		dev_err(max77686->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max77686->rtc, max77686);
 
 	max77686_irq_init(max77686);
diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
index e0859987ab6b..c5535f018466 100644
--- a/drivers/mfd/max77693.c
+++ b/drivers/mfd/max77693.c
@@ -148,9 +148,18 @@ static int max77693_i2c_probe(struct i2c_client *i2c,
 		dev_info(max77693->dev, "device ID: 0x%x\n", reg_data);
 
 	max77693->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+	if (!max77693->muic) {
+		dev_err(max77693->dev, "Failed to allocate I2C device for MUIC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max77693->muic, max77693);
 
 	max77693->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+	if (!max77693->haptic) {
+		dev_err(max77693->dev, "Failed to allocate I2C device for Haptic\n");
+		ret = -ENODEV;
+		goto err_i2c_haptic;
+	}
 	i2c_set_clientdata(max77693->haptic, max77693);
 
 	/*
@@ -184,8 +193,9 @@ err_mfd:
 	max77693_irq_exit(max77693);
 err_irq:
 err_regmap_muic:
-	i2c_unregister_device(max77693->muic);
 	i2c_unregister_device(max77693->haptic);
+err_i2c_haptic:
+	i2c_unregister_device(max77693->muic);
 	return ret;
 }
 
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index 176aa26fc787..a83eed5c15ca 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -181,9 +181,18 @@ static int max8925_probe(struct i2c_client *client,
 	mutex_init(&chip->io_lock);
 
 	chip->rtc = i2c_new_dummy(chip->i2c->adapter, RTC_I2C_ADDR);
+	if (!chip->rtc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->rtc, chip);
 
 	chip->adc = i2c_new_dummy(chip->i2c->adapter, ADC_I2C_ADDR);
+	if (!chip->adc) {
+		dev_err(chip->dev, "Failed to allocate I2C device for ADC\n");
+		i2c_unregister_device(chip->rtc);
+		return -ENODEV;
+	}
 	i2c_set_clientdata(chip->adc, chip);
 
 	device_init_wakeup(&client->dev, 1);
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index 5adede0fb04c..8cf7a015cfe5 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -208,10 +208,26 @@ static int max8997_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&max8997->iolock);
 
 	max8997->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+	if (!max8997->rtc) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8997->rtc, max8997);
+
 	max8997->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+	if (!max8997->haptic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for Haptic\n");
+		ret = -ENODEV;
+		goto err_i2c_haptic;
+	}
 	i2c_set_clientdata(max8997->haptic, max8997);
+
 	max8997->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+	if (!max8997->muic) {
+		dev_err(max8997->dev, "Failed to allocate I2C device for MUIC\n");
+		ret = -ENODEV;
+		goto err_i2c_muic;
+	}
 	i2c_set_clientdata(max8997->muic, max8997);
 
 	pm_runtime_set_active(max8997->dev);
@@ -239,7 +255,9 @@ static int max8997_i2c_probe(struct i2c_client *i2c,
 err_mfd:
 	mfd_remove_devices(max8997->dev);
 	i2c_unregister_device(max8997->muic);
+err_i2c_muic:
 	i2c_unregister_device(max8997->haptic);
+err_i2c_haptic:
 	i2c_unregister_device(max8997->rtc);
 	return ret;
 }
diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c
index 5d5e186b5d8b..592db06098e6 100644
--- a/drivers/mfd/max8998.c
+++ b/drivers/mfd/max8998.c
@@ -215,6 +215,10 @@ static int max8998_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&max8998->iolock);
 
 	max8998->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+	if (!max8998->rtc) {
+		dev_err(&i2c->dev, "Failed to allocate I2C device for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(max8998->rtc, max8998);
 
 	max8998_irq_init(max8998);
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 90b630ccc8bc..0aefe501fd3c 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -445,7 +445,7 @@ static unsigned omap_usbhs_rev1_hostconfig(struct usbhs_hcd_omap *omap,
 
 		for (i = 0; i < omap->nports; i++) {
 			if (is_ehci_phy_mode(pdata->port_mode[i])) {
-				reg &= OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
+				reg &= ~OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
 				break;
 			}
 		}
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index 1d15735f9ef9..89b4c4216d0c 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -1177,7 +1177,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	pcr->msi_en = msi_en;
 	if (pcr->msi_en) {
 		ret = pci_enable_msi(pcidev);
-		if (ret < 0)
+		if (ret)
 			pcr->msi_en = false;
 	}
 
diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index 714e2135210e..a76cd85a2868 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -252,6 +252,10 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 	}
 
 	sec_pmic->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+	if (!sec_pmic->rtc) {
+		dev_err(&i2c->dev, "Failed to allocate I2C for RTC\n");
+		return -ENODEV;
+	}
 	i2c_set_clientdata(sec_pmic->rtc, sec_pmic);
 
 	sec_pmic->regmap_rtc = devm_regmap_init_i2c(sec_pmic->rtc,
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 11c19e538551..48579e5ef02c 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -263,6 +263,17 @@ static int tc6393xb_ohci_disable(struct platform_device *dev)
 	return 0;
 }
 
+static int tc6393xb_ohci_suspend(struct platform_device *dev)
+{
+	struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent);
+
+	/* We can't properly store/restore OHCI state, so fail here */
+	if (tcpd->resume_restore)
+		return -EBUSY;
+
+	return tc6393xb_ohci_disable(dev);
+}
+
 static int tc6393xb_fb_enable(struct platform_device *dev)
 {
 	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
@@ -403,7 +414,7 @@ static struct mfd_cell tc6393xb_cells[] = {
 		.num_resources = ARRAY_SIZE(tc6393xb_ohci_resources),
 		.resources = tc6393xb_ohci_resources,
 		.enable = tc6393xb_ohci_enable,
-		.suspend = tc6393xb_ohci_disable,
+		.suspend = tc6393xb_ohci_suspend,
 		.resume = tc6393xb_ohci_enable,
 		.disable = tc6393xb_ohci_disable,
 	},
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index d4e860413bb5..e87a2485468f 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -54,11 +54,11 @@ void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val)
 	unsigned long flags;
 
 	spin_lock_irqsave(&tsadc->reg_lock, flags);
-	tsadc->reg_se_cache = val;
+	tsadc->reg_se_cache |= val;
 	if (tsadc->adc_waiting)
 		wake_up(&tsadc->reg_se_wait);
 	else if (!tsadc->adc_in_use)
-		tscadc_writel(tsadc, REG_SE, val);
+		tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache);
 
 	spin_unlock_irqrestore(&tsadc->reg_lock, flags);
 }
@@ -97,6 +97,7 @@ static void am335x_tscadc_need_adc(struct ti_tscadc_dev *tsadc)
 void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val)
 {
 	spin_lock_irq(&tsadc->reg_lock);
+	tsadc->reg_se_cache |= val;
 	am335x_tscadc_need_adc(tsadc);
 
 	tscadc_writel(tsadc, REG_SE, val);
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index 1f142d76cbbc..d6573318977f 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -255,8 +255,10 @@ static int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 	ret = regmap_add_irq_chip(tps65910->regmap, tps65910->chip_irq,
 		IRQF_ONESHOT, pdata->irq_base,
 		tps6591x_irqs_chip, &tps65910->irq_data);
-	if (ret < 0)
+	if (ret < 0) {
 		dev_warn(tps65910->dev, "Failed to add irq_chip %d\n", ret);
+		tps65910->chip_irq = 0;
+	}
 	return ret;
 }
 
diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index ed718328eff1..e87140bef667 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -282,11 +282,11 @@ static struct reg_default twl4030_49_defaults[] = {
 static bool twl4030_49_nop_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
-	case 0:
-	case 3:
-	case 40:
-	case 41:
-	case 42:
+	case 0x00:
+	case 0x03:
+	case 0x40:
+	case 0x41:
+	case 0x42:
 		return false;
 	default:
 		return true;
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 6b1a6ef9f1a8..0c3a64708409 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -490,6 +490,8 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr,
 				 m->nr_pages,
 				 1,		/* write by caller */
 				 m->page_list);	/* ptrs to pages */
+	if (rc < 0)
+		goto fail_get_user_pages;
 
 	/* assumption: get_user_pages can be killed by signals. */
 	if (rc < m->nr_pages) {
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 4bc7d620d695..9a07bba3ade4 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -71,7 +71,7 @@ static int mei_cl_device_probe(struct device *dev)
 
 	dev_dbg(dev, "Device probe\n");
 
-	strncpy(id.name, dev_name(dev), sizeof(id.name));
+	strlcpy(id.name, dev_name(dev), sizeof(id.name));
 
 	return driver->probe(device, &id);
 }
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 89a557972d1b..540fe114ec60 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -74,23 +74,69 @@ int mei_me_cl_by_id(struct mei_device *dev, u8 client_id)
 
 
 /**
- * mei_io_list_flush - removes list entry belonging to cl.
+ * mei_cl_cmp_id - tells if the clients are the same
  *
- * @list:  An instance of our list structure
- * @cl: host client
+ * @cl1: host client 1
+ * @cl2: host client 2
+ *
+ * returns true  - if the clients has same host and me ids
+ *         false - otherwise
+ */
+static inline bool mei_cl_cmp_id(const struct mei_cl *cl1,
+				const struct mei_cl *cl2)
+{
+	return cl1 && cl2 &&
+		(cl1->host_client_id == cl2->host_client_id) &&
+		(cl1->me_client_id == cl2->me_client_id);
+}
+
+/**
+ * mei_io_list_flush - removes cbs belonging to cl.
+ *
+ * @list:  an instance of our list structure
+ * @cl:    host client, can be NULL for flushing the whole list
+ * @free:  whether to free the cbs
  */
-void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl)
+static void __mei_io_list_flush(struct mei_cl_cb *list,
+				struct mei_cl *cl, bool free)
 {
 	struct mei_cl_cb *cb;
 	struct mei_cl_cb *next;
 
+	/* enable removing everything if no cl is specified */
 	list_for_each_entry_safe(cb, next, &list->list, list) {
-		if (cb->cl && mei_cl_cmp_id(cl, cb->cl))
+		if (!cl || (cb->cl && mei_cl_cmp_id(cl, cb->cl))) {
 			list_del(&cb->list);
+			if (free)
+				mei_io_cb_free(cb);
+		}
 	}
 }
 
 /**
+ * mei_io_list_flush - removes list entry belonging to cl.
+ *
+ * @list:  An instance of our list structure
+ * @cl: host client
+ */
+static inline void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl)
+{
+	__mei_io_list_flush(list, cl, false);
+}
+
+
+/**
+ * mei_io_list_free - removes cb belonging to cl and free them
+ *
+ * @list:  An instance of our list structure
+ * @cl: host client
+ */
+static inline void mei_io_list_free(struct mei_cl_cb *list, struct mei_cl *cl)
+{
+	__mei_io_list_flush(list, cl, true);
+}
+
+/**
  * mei_io_cb_free - free mei_cb_private related memory
  *
  * @cb: mei callback struct
@@ -196,8 +242,8 @@ int mei_cl_flush_queues(struct mei_cl *cl)
 
 	cl_dbg(dev, cl, "remove list entry belonging to cl\n");
 	mei_io_list_flush(&cl->dev->read_list, cl);
-	mei_io_list_flush(&cl->dev->write_list, cl);
-	mei_io_list_flush(&cl->dev->write_waiting_list, cl);
+	mei_io_list_free(&cl->dev->write_list, cl);
+	mei_io_list_free(&cl->dev->write_waiting_list, cl);
 	mei_io_list_flush(&cl->dev->ctrl_wr_list, cl);
 	mei_io_list_flush(&cl->dev->ctrl_rd_list, cl);
 	mei_io_list_flush(&cl->dev->amthif_cmd_list, cl);
@@ -413,6 +459,7 @@ int mei_cl_disconnect(struct mei_cl *cl)
 			cl_err(dev, cl, "failed to disconnect.\n");
 			goto free;
 		}
+		cl->timer_count = MEI_CONNECT_TIMEOUT;
 		mdelay(10); /* Wait for hardware disconnection ready */
 		list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
 	} else {
@@ -517,6 +564,7 @@ int mei_cl_connect(struct mei_cl *cl, struct file *file)
 		cl->timer_count = MEI_CONNECT_TIMEOUT;
 		list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
 	} else {
+		cl->state = MEI_FILE_INITIALIZING;
 		list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
 	}
 
@@ -942,20 +990,8 @@ void mei_cl_all_wakeup(struct mei_device *dev)
  */
 void mei_cl_all_write_clear(struct mei_device *dev)
 {
-	struct mei_cl_cb *cb, *next;
-	struct list_head *list;
-
-	list = &dev->write_list.list;
-	list_for_each_entry_safe(cb, next, list, list) {
-		list_del(&cb->list);
-		mei_io_cb_free(cb);
-	}
-
-	list = &dev->write_waiting_list.list;
-	list_for_each_entry_safe(cb, next, list, list) {
-		list_del(&cb->list);
-		mei_io_cb_free(cb);
-	}
+	mei_io_list_free(&dev->write_list, NULL);
+	mei_io_list_free(&dev->write_waiting_list, NULL);
 }
 
 
diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h
index c8396e582f1c..0820e121d137 100644
--- a/drivers/misc/mei/client.h
+++ b/drivers/misc/mei/client.h
@@ -45,8 +45,6 @@ static inline void mei_io_list_init(struct mei_cl_cb *list)
 {
 	INIT_LIST_HEAD(&list->list);
 }
-void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl);
-
 /*
  * MEI Host Client Functions
  */
@@ -61,22 +59,6 @@ int mei_cl_unlink(struct mei_cl *cl);
 int mei_cl_flush_queues(struct mei_cl *cl);
 struct mei_cl_cb *mei_cl_find_read_cb(struct mei_cl *cl);
 
-/**
- * mei_cl_cmp_id - tells if file private data have same id
- *
- * @fe1: private data of 1. file object
- * @fe2: private data of 2. file object
- *
- * returns true  - if ids are the same and not NULL
- */
-static inline bool mei_cl_cmp_id(const struct mei_cl *cl1,
-				const struct mei_cl *cl2)
-{
-	return cl1 && cl2 &&
-		(cl1->host_client_id == cl2->host_client_id) &&
-		(cl1->me_client_id == cl2->me_client_id);
-}
-
 
 int mei_cl_flow_ctrl_creds(struct mei_cl *cl);
 
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 66f411a6e8ea..cabc04383685 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -115,6 +115,11 @@
 #define MEI_DEV_ID_LPT_HR     0x8CBA  /* Lynx Point H Refresh */
 
 #define MEI_DEV_ID_WPT_LP     0x9CBA  /* Wildcat Point LP */
+
+/* Host Firmware Status Registers in PCI Config Space */
+#define PCI_CFG_HFS_1         0x40
+#define PCI_CFG_HFS_2         0x48
+
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 6f656c053b14..fbc4a7bbdfa9 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -164,6 +164,9 @@ static void mei_me_hw_reset_release(struct mei_device *dev)
 	hcsr |= H_IG;
 	hcsr &= ~H_RST;
 	mei_hcsr_set(hw, hcsr);
+
+	/* complete this write before we set host ready on another CPU */
+	mmiowb();
 }
 /**
  * mei_me_hw_reset - resets fw via mei csr register.
@@ -183,8 +186,21 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 	else
 		hcsr &= ~H_IE;
 
+	dev->recvd_hw_ready = false;
 	mei_me_reg_write(hw, H_CSR, hcsr);
 
+	/*
+	 * Host reads the H_CSR once to ensure that the
+	 * posted write to H_CSR completes.
+	 */
+	hcsr = mei_hcsr_read(hw);
+
+	if ((hcsr & H_RST) == 0)
+		dev_warn(&dev->pdev->dev, "H_RST is not set = 0x%08X", hcsr);
+
+	if ((hcsr & H_RDY) == H_RDY)
+		dev_warn(&dev->pdev->dev, "H_RDY is not cleared 0x%08X", hcsr);
+
 	if (intr_enable == false)
 		mei_me_hw_reset_release(dev);
 
@@ -201,6 +217,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable)
 static void mei_me_host_set_ready(struct mei_device *dev)
 {
 	struct mei_me_hw *hw = to_me_hw(dev);
+	hw->host_hw_state = mei_hcsr_read(hw);
 	hw->host_hw_state |= H_IE | H_IG | H_RDY;
 	mei_hcsr_set(hw, hw->host_hw_state);
 }
@@ -233,10 +250,7 @@ static bool mei_me_hw_is_ready(struct mei_device *dev)
 static int mei_me_hw_ready_wait(struct mei_device *dev)
 {
 	int err;
-	if (mei_me_hw_is_ready(dev))
-		return 0;
 
-	dev->recvd_hw_ready = false;
 	mutex_unlock(&dev->device_lock);
 	err = wait_event_interruptible_timeout(dev->wait_hw_ready,
 			dev->recvd_hw_ready,
@@ -491,14 +505,13 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	/*  check if we need to start the dev */
 	if (!mei_host_is_ready(dev)) {
 		if (mei_hw_is_ready(dev)) {
+			mei_me_hw_reset_release(dev);
 			dev_dbg(&dev->pdev->dev, "we need to start the dev.\n");
 
 			dev->recvd_hw_ready = true;
 			wake_up_interruptible(&dev->wait_hw_ready);
 		} else {
-
-			dev_dbg(&dev->pdev->dev, "Reset Completed.\n");
-			mei_me_hw_reset_release(dev);
+			dev_dbg(&dev->pdev->dev, "Spurious Interrupt\n");
 		}
 		goto end;
 	}
diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
index f0fbb5179f80..d36286874946 100644
--- a/drivers/misc/mei/interrupt.c
+++ b/drivers/misc/mei/interrupt.c
@@ -428,8 +428,7 @@ int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list)
 
 		cl->status = 0;
 		list_del(&cb->list);
-		if (MEI_WRITING == cl->writing_state &&
-		    cb->fop_type == MEI_FOP_WRITE &&
+		if (cb->fop_type == MEI_FOP_WRITE &&
 		    cl != &dev->iamthif_cl) {
 			cl_dbg(dev, cl, "MEI WRITE COMPLETE\n");
 			cl->writing_state = MEI_WRITE_COMPLETE;
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 5424f8ff3f7f..cfe1789923a3 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -653,8 +653,7 @@ static unsigned int mei_poll(struct file *file, poll_table *wait)
 		goto out;
 	}
 
-	if (MEI_WRITE_COMPLETE == cl->writing_state)
-		mask |= (POLLIN | POLLRDNORM);
+	mask |= (POLLIN | POLLRDNORM);
 
 out:
 	mutex_unlock(&dev->device_lock);
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index a58320c0c049..31149010224b 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -342,9 +342,10 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	ndev = (struct mei_nfc_dev *) cldev->priv_data;
 	dev = ndev->cl->dev;
 
+	err = -ENOMEM;
 	mei_buf = kzalloc(length + MEI_NFC_HEADER_SIZE, GFP_KERNEL);
 	if (!mei_buf)
-		return -ENOMEM;
+		goto out;
 
 	hdr = (struct mei_nfc_hci_hdr *) mei_buf;
 	hdr->cmd = MEI_NFC_CMD_HCI_SEND;
@@ -354,12 +355,9 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	hdr->data_size = length;
 
 	memcpy(mei_buf + MEI_NFC_HEADER_SIZE, buf, length);
-
 	err = __mei_cl_send(ndev->cl, mei_buf, length + MEI_NFC_HEADER_SIZE);
 	if (err < 0)
-		return err;
-
-	kfree(mei_buf);
+		goto out;
 
 	if (!wait_event_interruptible_timeout(ndev->send_wq,
 				ndev->recv_req_id == ndev->req_id, HZ)) {
@@ -368,7 +366,8 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	} else {
 		ndev->req_id++;
 	}
-
+out:
+	kfree(mei_buf);
 	return err;
 }
 
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index ddadd08956f4..bf4bb74c39ff 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -100,15 +100,31 @@ static bool mei_me_quirk_probe(struct pci_dev *pdev,
 				const struct pci_device_id *ent)
 {
 	u32 reg;
-	if (ent->device == MEI_DEV_ID_PBG_1) {
-		pci_read_config_dword(pdev, 0x48, &reg);
-		/* make sure that bit 9 is up and bit 10 is down */
-		if ((reg & 0x600) == 0x200) {
-			dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
-			return false;
-		}
+	/* Cougar Point || Patsburg */
+	if (ent->device == MEI_DEV_ID_CPT_1 ||
+	    ent->device == MEI_DEV_ID_PBG_1) {
+		pci_read_config_dword(pdev, PCI_CFG_HFS_2, &reg);
+		/* make sure that bit 9 (NM) is up and bit 10 (DM) is down */
+		if ((reg & 0x600) == 0x200)
+			goto no_mei;
 	}
+
+	/* Lynx Point */
+	if (ent->device == MEI_DEV_ID_LPT_H  ||
+	    ent->device == MEI_DEV_ID_LPT_W  ||
+	    ent->device == MEI_DEV_ID_LPT_HR) {
+		/* Read ME FW Status check for SPS Firmware */
+		pci_read_config_dword(pdev, PCI_CFG_HFS_1, &reg);
+		/* if bits [19:16] = 15, running SPS Firmware */
+		if ((reg & 0xf0000) == 0xf0000)
+			goto no_mei;
+	}
+
 	return true;
+
+no_mei:
+	dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
+	return false;
 }
 /**
  * mei_probe - Device Initialization Routine
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 7b5424f398ac..df72c478c5a2 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -260,7 +260,7 @@ static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr,
 	int ret;
 	struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
 
-	ret = snprintf(buf, PAGE_SIZE, "%d",
+	ret = snprintf(buf, PAGE_SIZE, "%d\n",
 		       get_disk_ro(dev_to_disk(dev)) ^
 		       md->read_only);
 	mmc_blk_put(md);
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 55cd110a49c4..caed9d53e8fa 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -632,6 +632,13 @@ static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data)
 
 	WARN_ON(!(data->flags & MMC_DATA_READ));
 
+	/*
+	 * CDTHRCTL doesn't exist prior to 240A (in fact that register offset is
+	 * in the FIFO region, so we really shouldn't access it).
+	 */
+	if (host->verid < DW_MMC_240A)
+		return;
+
 	if (host->timing != MMC_TIMING_MMC_HS200 &&
 	    host->timing != MMC_TIMING_UHS_SDR104)
 		goto disable;
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index c46feda07d56..ca297d741207 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -246,6 +246,9 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	case MMC_RSP_R1:
 		rsp_type = SD_RSP_TYPE_R1;
 		break;
+	case MMC_RSP_R1 & ~MMC_RSP_CRC:
+		rsp_type = SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7;
+		break;
 	case MMC_RSP_R1B:
 		rsp_type = SD_RSP_TYPE_R1b;
 		break;
@@ -339,6 +342,13 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	}
 
 	if (rsp_type == SD_RSP_TYPE_R2) {
+		/*
+		 * The controller offloads the last byte {CRC-7, end bit 1'b1}
+		 * of response type R2. Assign dummy CRC, 0, and end bit to the
+		 * byte(ptr[16], goes into the LSB of resp[3] later).
+		 */
+		ptr[16] = 1;
+
 		for (i = 0; i < 4; i++) {
 			cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4);
 			dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n",
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index 7a190fe4dff1..e5565aa5ed36 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -314,7 +314,7 @@ err_pltfm_free:
 	return ret;
 }
 
-static int __exit sdhci_bcm_kona_remove(struct platform_device *pdev)
+static int sdhci_bcm_kona_remove(struct platform_device *pdev)
 {
 	return sdhci_pltfm_unregister(pdev);
 }
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index f49666bcc52a..257e9ca30166 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -88,8 +88,6 @@ void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip)
 		return;
 	scratch_32 &= ~((1 << 21) | (1 << 30));
 
-	/* Set RTD3 function disabled */
-	scratch_32 |= ((1 << 29) | (1 << 28));
 	pci_write_config_dword(chip->pdev, O2_SD_FUNC_REG3, scratch_32);
 
 	/* Set L1 Entrance Timer */
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 0955777b6c7e..19bfa0ad70c4 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -103,6 +103,10 @@ static const struct sdhci_pci_fixes sdhci_cafe = {
 			  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL,
 };
 
+static const struct sdhci_pci_fixes sdhci_intel_qrk = {
+	.quirks		= SDHCI_QUIRK_NO_HISPD_BIT,
+};
+
 static int mrst_hc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA;
@@ -733,6 +737,14 @@ static const struct pci_device_id pci_ids[] = {
 
 	{
 		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_QRK_SD,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_qrk,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
 		.device		= PCI_DEVICE_ID_INTEL_MRST_SD0,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 6d718719659e..c101477ef3be 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -17,6 +17,7 @@
 #define PCI_DEVICE_ID_INTEL_CLV_SDIO2	0x08fb
 #define PCI_DEVICE_ID_INTEL_CLV_EMMC0	0x08e5
 #define PCI_DEVICE_ID_INTEL_CLV_EMMC1	0x08e6
+#define PCI_DEVICE_ID_INTEL_QRK_SD	0x08A7
 
 /*
  * PCI registers
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 9ddef4763541..7e0176321aff 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1343,6 +1343,8 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	sdhci_runtime_pm_get(host);
 
+	present = mmc_gpio_get_cd(host->mmc);
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	WARN_ON(host->mrq != NULL);
@@ -1371,7 +1373,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	 *     zero: cd-gpio is used, and card is removed
 	 *     one: cd-gpio is used, and card is present
 	 */
-	present = mmc_gpio_get_cd(host->mmc);
 	if (present < 0) {
 		/* If polling, assume that the card is always present. */
 		if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
@@ -2082,15 +2083,18 @@ static void sdhci_card_event(struct mmc_host *mmc)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
 	unsigned long flags;
+	int present;
 
 	/* First check if client has provided their own card event */
 	if (host->ops->card_event)
 		host->ops->card_event(host);
 
+	present = sdhci_do_get_cd(host);
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	/* Check host->mrq first in case we are runtime suspended */
-	if (host->mrq && !sdhci_do_get_cd(host)) {
+	if (host->mrq && !present) {
 		pr_err("%s: Card removed during transfer!\n",
 			mmc_hostname(host->mmc));
 		pr_err("%s: Resetting controller.\n",
diff --git a/drivers/mtd/devices/elm.c b/drivers/mtd/devices/elm.c
index d1dd6a33a050..3059a7a53bff 100644
--- a/drivers/mtd/devices/elm.c
+++ b/drivers/mtd/devices/elm.c
@@ -428,6 +428,7 @@ static int elm_context_save(struct elm_info *info)
 					ELM_SYNDROME_FRAGMENT_1 + offset);
 			regs->elm_syndrome_fragment_0[i] = elm_read_reg(info,
 					ELM_SYNDROME_FRAGMENT_0 + offset);
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -466,6 +467,7 @@ static int elm_context_restore(struct elm_info *info)
 					regs->elm_syndrome_fragment_1[i]);
 			elm_write_reg(info, ELM_SYNDROME_FRAGMENT_0 + offset,
 					regs->elm_syndrome_fragment_0[i]);
+			break;
 		default:
 			return -EINVAL;
 		}
diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c
index 19d637266fcd..71e4f6ccae2f 100644
--- a/drivers/mtd/ftl.c
+++ b/drivers/mtd/ftl.c
@@ -1075,7 +1075,6 @@ static void ftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 			return;
 	}
 
-	ftl_freepart(partition);
 	kfree(partition);
 }
 
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index c36e9b84487c..2c059890a394 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -1220,6 +1220,7 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
 		goto err;
 	}
 
+	nand_chip->options |= NAND_NO_SUBPAGE_WRITE;
 	nand_chip->ecc.read_page = atmel_nand_pmecc_read_page;
 	nand_chip->ecc.write_page = atmel_nand_pmecc_write_page;
 
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index fec31d71b84e..fe8a020ecf25 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -1438,7 +1438,7 @@ static int __init doc_probe(unsigned long physadr)
 	int reg, len, numchips;
 	int ret = 0;
 
-	if (!request_mem_region(physadr, DOC_IOREMAP_LEN, NULL))
+	if (!request_mem_region(physadr, DOC_IOREMAP_LEN, "DiskOnChip"))
 		return -EBUSY;
 	virtadr = ioremap(physadr, DOC_IOREMAP_LEN);
 	if (!virtadr) {
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index bcf60800c3ce..c09ab95a2219 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -724,6 +724,19 @@ static int fsl_elbc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return 0;
 }
 
+/* ECC will be calculated automatically, and errors will be detected in
+ * waitfunc.
+ */
+static int fsl_elbc_write_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+				uint32_t offset, uint32_t data_len,
+				const uint8_t *buf, int oob_required)
+{
+	fsl_elbc_write_buf(mtd, buf, mtd->writesize);
+	fsl_elbc_write_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+	return 0;
+}
+
 static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 {
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
@@ -762,6 +775,7 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 
 	chip->ecc.read_page = fsl_elbc_read_page;
 	chip->ecc.write_page = fsl_elbc_write_page;
+	chip->ecc.write_subpage = fsl_elbc_write_subpage;
 
 	/* If CS Base Register selects full hardware ECC then use it */
 	if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index 9ee09a8177c6..7360f7872d9a 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -225,7 +225,7 @@ static void nuc900_nand_enable(struct nuc900_nand *nand)
 	val = __raw_readl(nand->reg + REG_FMICSR);
 
 	if (!(val & NAND_EN))
-		__raw_writel(val | NAND_EN, REG_FMICSR);
+		__raw_writel(val | NAND_EN, nand->reg + REG_FMICSR);
 
 	val = __raw_readl(nand->reg + REG_SMCSR);
 
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index bf642ceef681..64d8e32b6ca0 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -933,7 +933,7 @@ static int omap_calculate_ecc(struct mtd_info *mtd, const u_char *dat,
 	u32 val;
 
 	val = readl(info->reg.gpmc_ecc_config);
-	if (((val >> ECC_CONFIG_CS_SHIFT)  & ~CS_MASK) != info->gpmc_cs)
+	if (((val >> ECC_CONFIG_CS_SHIFT) & CS_MASK) != info->gpmc_cs)
 		return -EINVAL;
 
 	/* read ecc result */
@@ -1451,7 +1451,7 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 
 	/* Check if any error reported */
 	if (!is_error_reported)
-		return 0;
+		return stat;
 
 	/* Decode BCH error using ELM module */
 	elm_decode_bch_error_page(info->elm_dev, ecc_vec, err_vec);
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 2a7a0b27ac38..51e15fd53108 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -128,10 +128,10 @@
 
 /* macros for registers read/write */
 #define nand_writel(info, off, val)	\
-	__raw_writel((val), (info)->mmio_base + (off))
+	writel_relaxed((val), (info)->mmio_base + (off))
 
 #define nand_readl(info, off)		\
-	__raw_readl((info)->mmio_base + (off))
+	readl_relaxed((info)->mmio_base + (off))
 
 /* error code and state */
 enum {
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index 4b8e89583f2a..cf49c22673b9 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -59,15 +59,12 @@ static struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl)
 	struct attribute_group *attr_group;
 	struct attribute **attributes;
 	struct sm_sysfs_attribute *vendor_attribute;
+	char *vendor;
 
-	int vendor_len = strnlen(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
-					SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET);
-
-	char *vendor = kmalloc(vendor_len, GFP_KERNEL);
+	vendor = kstrndup(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
+			  SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET, GFP_KERNEL);
 	if (!vendor)
 		goto error1;
-	memcpy(vendor, ftl->cis_buffer + SM_CIS_VENDOR_OFFSET, vendor_len);
-	vendor[vendor_len] = 0;
 
 	/* Initialize sysfs attributes */
 	vendor_attribute =
@@ -78,7 +75,7 @@ static struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl)
 	sysfs_attr_init(&vendor_attribute->dev_attr.attr);
 
 	vendor_attribute->data = vendor;
-	vendor_attribute->len = vendor_len;
+	vendor_attribute->len = strlen(vendor);
 	vendor_attribute->dev_attr.attr.name = "vendor";
 	vendor_attribute->dev_attr.attr.mode = S_IRUGO;
 	vendor_attribute->dev_attr.show = sm_attr_show;
diff --git a/drivers/mtd/tests/torturetest.c b/drivers/mtd/tests/torturetest.c
index eeab96973cf0..b55bc52a1340 100644
--- a/drivers/mtd/tests/torturetest.c
+++ b/drivers/mtd/tests/torturetest.c
@@ -264,7 +264,9 @@ static int __init tort_init(void)
 		int i;
 		void *patt;
 
-		mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt);
+		err = mtdtest_erase_good_eraseblocks(mtd, bad_ebs, eb, ebcnt);
+		if (err)
+			goto out;
 
 		/* Check if the eraseblocks contain only 0xFF bytes */
 		if (check) {
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index c5dad652614d..904b4517fc1e 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -330,6 +330,7 @@ static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		av = tmp_av;
 	else {
 		ubi_err("orphaned volume in fastmap pool!");
+		kmem_cache_free(ai->aeb_slab_cache, new_aeb);
 		return UBI_BAD_FASTMAP;
 	}
 
diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index ec2c2dc1c1ca..2a1b6e037e1a 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -133,6 +133,10 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 	ubi_assert(!vol->updating && !vol->changing_leb);
 	vol->updating = 1;
 
+	vol->upd_buf = vmalloc(ubi->leb_size);
+	if (!vol->upd_buf)
+		return -ENOMEM;
+
 	err = set_update_marker(ubi, vol);
 	if (err)
 		return err;
@@ -152,14 +156,12 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol,
 		err = clear_update_marker(ubi, vol, 0);
 		if (err)
 			return err;
+
+		vfree(vol->upd_buf);
 		vol->updating = 0;
 		return 0;
 	}
 
-	vol->upd_buf = vmalloc(ubi->leb_size);
-	if (!vol->upd_buf)
-		return -ENOMEM;
-
 	vol->upd_ebs = div_u64(bytes + vol->usable_leb_size - 1,
 			       vol->usable_leb_size);
 	vol->upd_bytes = bytes;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 02317c1c0238..68b924ec222e 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1205,7 +1205,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 
 	err = do_sync_erase(ubi, e1, vol_id, lnum, 0);
 	if (err) {
-		kmem_cache_free(ubi_wl_entry_slab, e1);
 		if (e2)
 			kmem_cache_free(ubi_wl_entry_slab, e2);
 		goto out_ro;
@@ -1219,10 +1218,8 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 		dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase",
 		       e2->pnum, vol_id, lnum);
 		err = do_sync_erase(ubi, e2, vol_id, lnum, 0);
-		if (err) {
-			kmem_cache_free(ubi_wl_entry_slab, e2);
+		if (err)
 			goto out_ro;
-		}
 	}
 
 	dbg_wl("done");
@@ -1258,10 +1255,9 @@ out_not_moved:
 
 	ubi_free_vid_hdr(ubi, vid_hdr);
 	err = do_sync_erase(ubi, e2, vol_id, lnum, torture);
-	if (err) {
-		kmem_cache_free(ubi_wl_entry_slab, e2);
+	if (err)
 		goto out_ro;
-	}
+
 	mutex_unlock(&ubi->move_mutex);
 	return 0;
 
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 494b888a6568..7e5c6a8b89e7 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -135,6 +135,7 @@ config MACVLAN
 config MACVTAP
 	tristate "MAC-VLAN based tap driver"
 	depends on MACVLAN
+	depends on INET
 	help
 	  This adds a specialized tap character device driver that is based
 	  on the MAC-VLAN network interface, called macvtap. A macvtap device
@@ -205,6 +206,7 @@ config RIONET_RX_SIZE
 
 config TUN
 	tristate "Universal TUN/TAP device driver support"
+	depends on INET
 	select CRC32
 	---help---
 	  TUN/TAP provides packet reception and transmission for user space
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e5628fc725c3..15379824d77d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2450,9 +2450,9 @@ static void bond_loadbalance_arp_mon(struct work_struct *work)
 		if (!rtnl_trylock())
 			goto re_arm;
 
-		if (slave_state_changed) {
+		if (slave_state_changed)
 			bond_slave_state_change(bond);
-		} else if (do_failover) {
+		if (do_failover) {
 			/* the bond_select_active_slave must hold RTNL
 			 * and curr_slave_lock for write.
 			 */
@@ -3624,8 +3624,14 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev
 		else
 			bond_xmit_slave_id(bond, skb, 0);
 	} else {
-		slave_id = bond_rr_gen_slave_id(bond);
-		bond_xmit_slave_id(bond, skb, slave_id % bond->slave_cnt);
+		int slave_cnt = ACCESS_ONCE(bond->slave_cnt);
+
+		if (likely(slave_cnt)) {
+			slave_id = bond_rr_gen_slave_id(bond);
+			bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
+		} else {
+			dev_kfree_skb_any(skb);
+		}
 	}
 
 	return NETDEV_TX_OK;
@@ -3656,8 +3662,13 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d
 static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
+	int slave_cnt = ACCESS_ONCE(bond->slave_cnt);
 
-	bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb, bond->slave_cnt));
+	if (likely(slave_cnt))
+		bond_xmit_slave_id(bond, skb,
+				   bond_xmit_hash(bond, skb, bond->slave_cnt));
+	else
+		dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
 }
@@ -4068,7 +4079,7 @@ static int bond_check_params(struct bond_params *params)
 	}
 
 	if (ad_select) {
-		bond_opt_initstr(&newval, lacp_rate);
+		bond_opt_initstr(&newval, ad_select);
 		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT),
 					&newval);
 		if (!valptr) {
@@ -4536,6 +4547,7 @@ static int __init bonding_init(void)
 out:
 	return res;
 err:
+	bond_destroy_debugfs();
 	bond_netlink_fini();
 err_link:
 	unregister_pernet_subsys(&bond_net_ops);
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 298c26509095..a937a37ae89f 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -70,6 +70,7 @@ static struct bond_opt_value bond_fail_over_mac_tbl[] = {
 static struct bond_opt_value bond_intmax_tbl[] = {
 	{ "off",     0,       BOND_VALFLAG_DEFAULT},
 	{ "maxval",  INT_MAX, BOND_VALFLAG_MAX},
+	{ NULL,      -1,      0}
 };
 
 static struct bond_opt_value bond_lacp_rate_tbl[] = {
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index fc59bc6f040b..cc11f7f5e91d 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -384,7 +384,7 @@ void can_free_echo_skb(struct net_device *dev, unsigned int idx)
 	BUG_ON(idx >= priv->echo_skb_max);
 
 	if (priv->echo_skb[idx]) {
-		kfree_skb(priv->echo_skb[idx]);
+		dev_kfree_skb_any(priv->echo_skb[idx]);
 		priv->echo_skb[idx] = NULL;
 	}
 }
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 065ca49eb45e..546a848add37 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -551,7 +551,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct sja1000_priv *priv;
 	struct peak_pci_chan *chan;
-	struct net_device *dev;
+	struct net_device *dev, *prev_dev;
 	void __iomem *cfg_base, *reg_base;
 	u16 sub_sys_id, icr;
 	int i, err, channels;
@@ -687,11 +687,13 @@ failure_remove_channels:
 	writew(0x0, cfg_base + PITA_ICR + 2);
 
 	chan = NULL;
-	for (dev = pci_get_drvdata(pdev); dev; dev = chan->prev_dev) {
-		unregister_sja1000dev(dev);
-		free_sja1000dev(dev);
+	for (dev = pci_get_drvdata(pdev); dev; dev = prev_dev) {
 		priv = netdev_priv(dev);
 		chan = priv->priv;
+		prev_dev = chan->prev_dev;
+
+		unregister_sja1000dev(dev);
+		free_sja1000dev(dev);
 	}
 
 	/* free any PCIeC resources too */
@@ -725,10 +727,12 @@ static void peak_pci_remove(struct pci_dev *pdev)
 
 	/* Loop over all registered devices */
 	while (1) {
+		struct net_device *prev_dev = chan->prev_dev;
+
 		dev_info(&pdev->dev, "removing device %s\n", dev->name);
 		unregister_sja1000dev(dev);
 		free_sja1000dev(dev);
-		dev = chan->prev_dev;
+		dev = prev_dev;
 
 		if (!dev) {
 			/* do that only for first channel */
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 3fcdae266377..1d0dab854b90 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -52,6 +52,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/workqueue.h>
 #include <linux/can.h>
 #include <linux/can/skb.h>
 
@@ -85,6 +86,7 @@ struct slcan {
 	struct tty_struct	*tty;		/* ptr to TTY structure	     */
 	struct net_device	*dev;		/* easy for intr handling    */
 	spinlock_t		lock;
+	struct work_struct	tx_work;	/* Flushes transmit buffer   */
 
 	/* These are pointers to the malloc()ed frame buffers. */
 	unsigned char		rbuff[SLC_MTU];	/* receiver buffer	     */
@@ -309,34 +311,44 @@ static void slc_encaps(struct slcan *sl, struct can_frame *cf)
 	sl->dev->stats.tx_bytes += cf->can_dlc;
 }
 
-/*
- * Called by the driver when there's room for more data.  If we have
- * more packets to send, we send them here.
- */
-static void slcan_write_wakeup(struct tty_struct *tty)
+/* Write out any remaining transmit buffer. Scheduled when tty is writable */
+static void slcan_transmit(struct work_struct *work)
 {
+	struct slcan *sl = container_of(work, struct slcan, tx_work);
 	int actual;
-	struct slcan *sl = (struct slcan *) tty->disc_data;
 
+	spin_lock_bh(&sl->lock);
 	/* First make sure we're connected. */
-	if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev))
+	if (!sl->tty || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev)) {
+		spin_unlock_bh(&sl->lock);
 		return;
+	}
 
-	spin_lock(&sl->lock);
 	if (sl->xleft <= 0)  {
 		/* Now serial buffer is almost free & we can start
 		 * transmission of another packet */
 		sl->dev->stats.tx_packets++;
-		clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
-		spin_unlock(&sl->lock);
+		clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
+		spin_unlock_bh(&sl->lock);
 		netif_wake_queue(sl->dev);
 		return;
 	}
 
-	actual = tty->ops->write(tty, sl->xhead, sl->xleft);
+	actual = sl->tty->ops->write(sl->tty, sl->xhead, sl->xleft);
 	sl->xleft -= actual;
 	sl->xhead += actual;
-	spin_unlock(&sl->lock);
+	spin_unlock_bh(&sl->lock);
+}
+
+/*
+ * Called by the driver when there's room for more data.
+ * Schedule the transmit.
+ */
+static void slcan_write_wakeup(struct tty_struct *tty)
+{
+	struct slcan *sl = tty->disc_data;
+
+	schedule_work(&sl->tx_work);
 }
 
 /* Send a can_frame to a TTY queue. */
@@ -522,6 +534,7 @@ static struct slcan *slc_alloc(dev_t line)
 	sl->magic = SLCAN_MAGIC;
 	sl->dev	= dev;
 	spin_lock_init(&sl->lock);
+	INIT_WORK(&sl->tx_work, slcan_transmit);
 	slcan_devs[i] = dev;
 
 	return sl;
@@ -620,8 +633,12 @@ static void slcan_close(struct tty_struct *tty)
 	if (!sl || sl->magic != SLCAN_MAGIC || sl->tty != tty)
 		return;
 
+	spin_lock_bh(&sl->lock);
 	tty->disc_data = NULL;
 	sl->tty = NULL;
+	spin_unlock_bh(&sl->lock);
+
+	flush_work(&sl->tx_work);
 
 	/* Flush network side */
 	unregister_netdev(sl->dev);
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 7fbe85935f1d..f34f7fa1f901 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -1141,6 +1141,7 @@ static void esd_usb2_disconnect(struct usb_interface *intf)
 			}
 		}
 		unlink_all_urbs(dev);
+		kfree(dev);
 	}
 }
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 0b7a4c3b01a2..03e7f0cbda8c 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -734,7 +734,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
 	if (!dev->cmd_buf) {
 		err = -ENOMEM;
-		goto lbl_set_intf_data;
+		goto lbl_free_candev;
 	}
 
 	dev->udev = usb_dev;
@@ -773,7 +773,7 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	err = register_candev(netdev);
 	if (err) {
 		dev_err(&intf->dev, "couldn't register CAN device: %d\n", err);
-		goto lbl_free_cmd_buf;
+		goto lbl_restore_intf_data;
 	}
 
 	if (dev->prev_siblings)
@@ -786,14 +786,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 	if (dev->adapter->dev_init) {
 		err = dev->adapter->dev_init(dev);
 		if (err)
-			goto lbl_free_cmd_buf;
+			goto lbl_unregister_candev;
 	}
 
 	/* set bus off */
 	if (dev->adapter->dev_set_bus) {
 		err = dev->adapter->dev_set_bus(dev, 0);
 		if (err)
-			goto lbl_free_cmd_buf;
+			goto lbl_unregister_candev;
 	}
 
 	/* get device number early */
@@ -805,11 +805,14 @@ static int peak_usb_create_dev(struct peak_usb_adapter *peak_usb_adapter,
 
 	return 0;
 
-lbl_free_cmd_buf:
-	kfree(dev->cmd_buf);
+lbl_unregister_candev:
+	unregister_candev(netdev);
 
-lbl_set_intf_data:
+lbl_restore_intf_data:
 	usb_set_intfdata(intf, dev->prev_siblings);
+	kfree(dev->cmd_buf);
+
+lbl_free_candev:
 	free_candev(netdev);
 
 	return err;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 263dd921edc4..f7f796a2c50b 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -333,8 +333,6 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id,
 	if (!(dev->state & PCAN_USB_STATE_CONNECTED))
 		return 0;
 
-	memset(req_addr, '\0', req_size);
-
 	req_type = USB_TYPE_VENDOR | USB_RECIP_OTHER;
 
 	switch (req_id) {
@@ -345,6 +343,7 @@ static int pcan_usb_pro_send_req(struct peak_usb_device *dev, int req_id,
 	default:
 		p = usb_rcvctrlpipe(dev->udev, 0);
 		req_type |= USB_DIR_IN;
+		memset(req_addr, '\0', req_size);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 511f6eecd58b..62db510b70ea 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -725,6 +725,7 @@ static int emac_open(struct net_device *dev)
 
 	ret = emac_mdio_probe(dev);
 	if (ret < 0) {
+		free_irq(dev->irq, dev);
 		netdev_err(dev, "cannot probe MDIO bus\n");
 		return ret;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 391f29ef6d2e..1fbeaa9dd202 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -337,6 +337,7 @@ struct sw_tx_bd {
 	u8		flags;
 /* Set on the first BD descriptor when there is a split BD */
 #define BNX2X_TSO_SPLIT_BD		(1<<0)
+#define BNX2X_HAS_SECOND_PBD		(1<<1)
 };
 
 struct sw_rx_page {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index dbcff509dc3f..afa4a1f63270 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -223,6 +223,12 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	--nbd;
 	bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
 
+	if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) {
+		/* Skip second parse bd... */
+		--nbd;
+		bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
+	}
+
 	/* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
 	if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
 		tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
@@ -793,7 +799,8 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 
 		return;
 	}
-	bnx2x_frag_free(fp, new_data);
+	if (new_data)
+		bnx2x_frag_free(fp, new_data);
 drop:
 	/* drop the packet and keep the buffer in the bin */
 	DP(NETIF_MSG_RX_STATUS,
@@ -3867,6 +3874,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			/* set encapsulation flag in start BD */
 			SET_FLAG(tx_start_bd->general_data,
 				 ETH_TX_START_BD_TUNNEL_EXIST, 1);
+
+			tx_buf->flags |= BNX2X_HAS_SECOND_PBD;
+
 			nbd++;
 		} else if (xmit_type & XMIT_CSUM) {
 			/* Set PBD in checksum offload case w/o encapsulation */
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 70a225c8df5c..086eac5af5c2 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6923,7 +6923,8 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 		skb->protocol = eth_type_trans(skb, tp->dev);
 
 		if (len > (tp->dev->mtu + ETH_HLEN) &&
-		    skb->protocol != htons(ETH_P_8021Q)) {
+		    skb->protocol != htons(ETH_P_8021Q) &&
+		    skb->protocol != htons(ETH_P_8021AD)) {
 			dev_kfree_skb(skb);
 			goto drop_it_no_recycle;
 		}
@@ -7915,8 +7916,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	entry = tnapi->tx_prod;
 	base_flags = 0;
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		base_flags |= TXD_FLAG_TCPUDP_CSUM;
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (mss) {
@@ -7932,6 +7931,13 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - ETH_HLEN;
 
+		/* HW/FW can not correctly segment packets that have been
+		 * vlan encapsulated.
+		 */
+		if (skb->protocol == htons(ETH_P_8021Q) ||
+		    skb->protocol == htons(ETH_P_8021AD))
+			return tg3_tso_bug(tp, skb);
+
 		if (!skb_is_gso_v6(skb)) {
 			iph->check = 0;
 			iph->tot_len = htons(mss + hdr_len);
@@ -7978,6 +7984,17 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				base_flags |= tsflags << 12;
 			}
 		}
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		/* HW/FW can not correctly checksum packets that have been
+		 * vlan encapsulated.
+		 */
+		if (skb->protocol == htons(ETH_P_8021Q) ||
+		    skb->protocol == htons(ETH_P_8021AD)) {
+			if (skb_checksum_help(skb))
+				goto drop;
+		} else  {
+			base_flags |= TXD_FLAG_TCPUDP_CSUM;
+		}
 	}
 
 	if (tg3_flag(tp, USE_JUMBO_BDFLAG) &&
@@ -8531,7 +8548,8 @@ static int tg3_init_rings(struct tg3 *tp)
 		if (tnapi->rx_rcb)
 			memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp));
 
-		if (tg3_rx_prodring_alloc(tp, &tnapi->prodring)) {
+		if (tnapi->prodring.rx_std &&
+		    tg3_rx_prodring_alloc(tp, &tnapi->prodring)) {
 			tg3_free_rings(tp);
 			return -ENOMEM;
 		}
@@ -12294,7 +12312,9 @@ static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *e
 	if (tg3_flag(tp, MAX_RXPEND_64) &&
 	    tp->rx_pending > 63)
 		tp->rx_pending = 63;
-	tp->rx_jumbo_pending = ering->rx_jumbo_pending;
+
+	if (tg3_flag(tp, JUMBO_RING_ENABLE))
+		tp->rx_jumbo_pending = ering->rx_jumbo_pending;
 
 	for (i = 0; i < tp->irq_max; i++)
 		tp->napi[i].tx_pending = ering->tx_pending;
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 4ad1187e82fb..669eeb4eb247 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -600,9 +600,9 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget)
 	prefetch(bnad->netdev);
 
 	cq = ccb->sw_q;
-	cmpl = &cq[ccb->producer_index];
 
 	while (packets < budget) {
+		cmpl = &cq[ccb->producer_index];
 		if (!cmpl->valid)
 			break;
 		/* The 'valid' field is set by the adapter, only after writing
diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index ce75de9bae9e..4a79edaf3885 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -342,6 +342,9 @@ static int __init at91ether_probe(struct platform_device *pdev)
 	}
 	clk_enable(lp->pclk);
 
+	lp->hclk = ERR_PTR(-ENOENT);
+	lp->tx_clk = ERR_PTR(-ENOENT);
+
 	/* Install the interrupt handler */
 	dev->irq = platform_get_irq(pdev, 0);
 	res = devm_request_irq(&pdev->dev, dev->irq, at91ether_interrupt, 0, dev->name, dev);
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index d0c38e01e99f..0085476a0258 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -30,7 +30,6 @@
 #include <linux/of_device.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-#include <linux/pinctrl/consumer.h>
 
 #include "macb.h"
 
@@ -1810,7 +1809,6 @@ static int __init macb_probe(struct platform_device *pdev)
 	struct phy_device *phydev;
 	u32 config;
 	int err = -ENXIO;
-	struct pinctrl *pinctrl;
 	const char *mac;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1819,15 +1817,6 @@ static int __init macb_probe(struct platform_device *pdev)
 		goto err_out;
 	}
 
-	pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
-	if (IS_ERR(pinctrl)) {
-		err = PTR_ERR(pinctrl);
-		if (err == -EPROBE_DEFER)
-			goto err_out;
-
-		dev_warn(&pdev->dev, "No pinctrl provided\n");
-	}
-
 	err = -ENOMEM;
 	dev = alloc_etherdev(sizeof(*bp));
 	if (!dev)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 36c80612e21a..80bfa0391913 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2797,7 +2797,7 @@ static int be_open(struct net_device *netdev)
 	for_all_evt_queues(adapter, eqo, i) {
 		napi_enable(&eqo->napi);
 		be_enable_busy_poll(eqo);
-		be_eq_notify(adapter, eqo->q.id, true, false, 0);
+		be_eq_notify(adapter, eqo->q.id, true, true, 0);
 	}
 	adapter->flags |= BE_FLAGS_NAPI_ENABLED;
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 1fc8334fc181..55e3075492da 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -292,6 +292,18 @@ failure:
 	atomic_add(buffers_added, &(pool->available));
 }
 
+/*
+ * The final 8 bytes of the buffer list is a counter of frames dropped
+ * because there was not a buffer in the buffer list capable of holding
+ * the frame.
+ */
+static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter)
+{
+	__be64 *p = adapter->buffer_list_addr + 4096 - 8;
+
+	adapter->rx_no_buffer = be64_to_cpup(p);
+}
+
 /* replenish routine */
 static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
 {
@@ -307,8 +319,7 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
 			ibmveth_replenish_buffer_pool(adapter, pool);
 	}
 
-	adapter->rx_no_buffer = *(u64 *)(((char*)adapter->buffer_list_addr) +
-						4096 - 8);
+	ibmveth_update_rx_no_buffer(adapter);
 }
 
 /* empty and free ana buffer pool - also used to do cleanup in error paths */
@@ -698,8 +709,7 @@ static int ibmveth_close(struct net_device *netdev)
 
 	free_irq(netdev->irq, netdev);
 
-	adapter->rx_no_buffer = *(u64 *)(((char *)adapter->buffer_list_addr) +
-						4096 - 8);
+	ibmveth_update_rx_no_buffer(adapter);
 
 	ibmveth_cleanup(adapter);
 
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 42f0f6717511..70e16f71f574 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1374,7 +1374,7 @@ static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index)
 	/* RAR[1-6] are owned by manageability.  Skip those and program the
 	 * next address into the SHRA register array.
 	 */
-	if (index < (u32)(hw->mac.rar_entry_count - 6)) {
+	if (index < (u32)(hw->mac.rar_entry_count)) {
 		s32 ret_val;
 
 		ret_val = e1000_acquire_swflag_ich8lan(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index 217090df33e7..59865695b282 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -98,7 +98,7 @@
 #define PCIE_ICH8_SNOOP_ALL	PCIE_NO_SNOOP_ALL
 
 #define E1000_ICH_RAR_ENTRIES	7
-#define E1000_PCH2_RAR_ENTRIES	11      /* RAR[0-6], SHRA[0-3] */
+#define E1000_PCH2_RAR_ENTRIES	5	/* RAR[0], SHRA[0-3] */
 #define E1000_PCH_LPT_RAR_ENTRIES	12	/* RAR[0], SHRA[0-10] */
 
 #define PHY_PAGE_SHIFT		5
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 6d91933c4cdd..0af6e060e238 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2976,11 +2976,21 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter)
 	u32 rctl, rfctl;
 	u32 pages = 0;
 
-	/* Workaround Si errata on PCHx - configure jumbo frame flow */
-	if ((hw->mac.type >= e1000_pch2lan) &&
-	    (adapter->netdev->mtu > ETH_DATA_LEN) &&
-	    e1000_lv_jumbo_workaround_ich8lan(hw, true))
-		e_dbg("failed to enable jumbo frame workaround mode\n");
+	/* Workaround Si errata on PCHx - configure jumbo frame flow.
+	 * If jumbo frames not set, program related MAC/PHY registers
+	 * to h/w defaults
+	 */
+	if (hw->mac.type >= e1000_pch2lan) {
+		s32 ret_val;
+
+		if (adapter->netdev->mtu > ETH_DATA_LEN)
+			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true);
+		else
+			ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false);
+
+		if (ret_val)
+			e_dbg("failed to enable|disable jumbo frame workaround mode\n");
+	}
 
 	/* Program MC offset vector base */
 	rctl = er32(RCTL);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b901371ca361..5d3206d5cb07 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4024,6 +4024,9 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 				       DCB_CAP_DCBX_VER_IEEE;
 			pf->flags |= I40E_FLAG_DCB_ENABLED;
 		}
+	} else {
+		dev_info(&pf->pdev->dev, "AQ Querying DCB configuration failed: %d\n",
+			 pf->hw.aq.asq_last_status);
 	}
 
 out:
@@ -8003,7 +8006,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err) {
 		dev_info(&pdev->dev, "init_pf_dcb failed: %d\n", err);
 		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
-		goto err_init_dcb;
+		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */
 
@@ -8119,9 +8122,6 @@ err_vsis:
 err_switch_setup:
 	i40e_reset_interrupt_capability(pf);
 	del_timer_sync(&pf->service_timer);
-#ifdef CONFIG_I40E_DCB
-err_init_dcb:
-#endif /* CONFIG_I40E_DCB */
 err_mac_addr:
 err_configure_lan_hmc:
 	(void)i40e_shutdown_lan_hmc(hw);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index b9d1c1c8ca5a..178506a201d5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1776,7 +1776,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, u16 vf_id, u32 v_opcode,
 			   u32 v_retval, u8 *msg, u16 msglen)
 {
 	struct i40e_hw *hw = &pf->hw;
-	int local_vf_id = vf_id - hw->func_caps.vf_base_id;
+	unsigned int local_vf_id = vf_id - hw->func_caps.vf_base_id;
 	struct i40e_vf *vf;
 	int ret;
 
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 06df6928f44c..4fa5c2a77d49 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -1492,6 +1492,13 @@ static s32 igb_init_hw_82575(struct e1000_hw *hw)
 	s32 ret_val;
 	u16 i, rar_count = mac->rar_entry_count;
 
+	if ((hw->mac.type >= e1000_i210) &&
+	    !(igb_get_flash_presence_i210(hw))) {
+		ret_val = igb_pll_workaround_i210(hw);
+		if (ret_val)
+			return ret_val;
+	}
+
 	/* Initialize identification LED */
 	ret_val = igb_id_led_init(hw);
 	if (ret_val) {
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 0571b973be80..20b37668284a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -46,14 +46,15 @@
 /* Extended Device Control */
 #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Defineable Pin 3 */
 /* Physical Func Reset Done Indication */
-#define E1000_CTRL_EXT_PFRSTD    0x00004000
-#define E1000_CTRL_EXT_LINK_MODE_MASK 0x00C00000
-#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES  0x00C00000
-#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX  0x00400000
-#define E1000_CTRL_EXT_LINK_MODE_SGMII   0x00800000
-#define E1000_CTRL_EXT_LINK_MODE_GMII   0x00000000
-#define E1000_CTRL_EXT_EIAME          0x01000000
-#define E1000_CTRL_EXT_IRCA           0x00000001
+#define E1000_CTRL_EXT_PFRSTD	0x00004000
+#define E1000_CTRL_EXT_SDLPE	0X00040000  /* SerDes Low Power Enable */
+#define E1000_CTRL_EXT_LINK_MODE_MASK	0x00C00000
+#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES	0x00C00000
+#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX	0x00400000
+#define E1000_CTRL_EXT_LINK_MODE_SGMII	0x00800000
+#define E1000_CTRL_EXT_LINK_MODE_GMII	0x00000000
+#define E1000_CTRL_EXT_EIAME	0x01000000
+#define E1000_CTRL_EXT_IRCA		0x00000001
 /* Interrupt delay cancellation */
 /* Driver loaded bit for FW */
 #define E1000_CTRL_EXT_DRV_LOAD       0x10000000
@@ -62,6 +63,7 @@
 /* packet buffer parity error detection enabled */
 /* descriptor FIFO parity error detection enable */
 #define E1000_CTRL_EXT_PBA_CLR		0x80000000 /* PBA Clear */
+#define E1000_CTRL_EXT_PHYPDEN		0x00100000
 #define E1000_I2CCMD_REG_ADDR_SHIFT	16
 #define E1000_I2CCMD_PHY_ADDR_SHIFT	24
 #define E1000_I2CCMD_OPCODE_READ	0x08000000
diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h
index ab99e2b582a8..b79980ad225b 100644
--- a/drivers/net/ethernet/intel/igb/e1000_hw.h
+++ b/drivers/net/ethernet/intel/igb/e1000_hw.h
@@ -572,4 +572,7 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw);
 /* These functions must be implemented by drivers */
 s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value);
 s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value);
+
+void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
+void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
 #endif /* _E1000_HW_H_ */
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index 0c0393316a3a..0217d4e229a0 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -835,3 +835,69 @@ s32 igb_init_nvm_params_i210(struct e1000_hw *hw)
 	}
 	return ret_val;
 }
+
+/**
+ * igb_pll_workaround_i210
+ * @hw: pointer to the HW structure
+ *
+ * Works around an errata in the PLL circuit where it occasionally
+ * provides the wrong clock frequency after power up.
+ **/
+s32 igb_pll_workaround_i210(struct e1000_hw *hw)
+{
+	s32 ret_val;
+	u32 wuc, mdicnfg, ctrl, ctrl_ext, reg_val;
+	u16 nvm_word, phy_word, pci_word, tmp_nvm;
+	int i;
+
+	/* Get and set needed register values */
+	wuc = rd32(E1000_WUC);
+	mdicnfg = rd32(E1000_MDICNFG);
+	reg_val = mdicnfg & ~E1000_MDICNFG_EXT_MDIO;
+	wr32(E1000_MDICNFG, reg_val);
+
+	/* Get data from NVM, or set default */
+	ret_val = igb_read_invm_word_i210(hw, E1000_INVM_AUTOLOAD,
+					  &nvm_word);
+	if (ret_val)
+		nvm_word = E1000_INVM_DEFAULT_AL;
+	tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL;
+	for (i = 0; i < E1000_MAX_PLL_TRIES; i++) {
+		/* check current state directly from internal PHY */
+		igb_read_phy_reg_gs40g(hw, (E1000_PHY_PLL_FREQ_PAGE |
+					 E1000_PHY_PLL_FREQ_REG), &phy_word);
+		if ((phy_word & E1000_PHY_PLL_UNCONF)
+		    != E1000_PHY_PLL_UNCONF) {
+			ret_val = 0;
+			break;
+		} else {
+			ret_val = -E1000_ERR_PHY;
+		}
+		/* directly reset the internal PHY */
+		ctrl = rd32(E1000_CTRL);
+		wr32(E1000_CTRL, ctrl|E1000_CTRL_PHY_RST);
+
+		ctrl_ext = rd32(E1000_CTRL_EXT);
+		ctrl_ext |= (E1000_CTRL_EXT_PHYPDEN | E1000_CTRL_EXT_SDLPE);
+		wr32(E1000_CTRL_EXT, ctrl_ext);
+
+		wr32(E1000_WUC, 0);
+		reg_val = (E1000_INVM_AUTOLOAD << 4) | (tmp_nvm << 16);
+		wr32(E1000_EEARBC_I210, reg_val);
+
+		igb_read_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		pci_word |= E1000_PCI_PMCSR_D3;
+		igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		usleep_range(1000, 2000);
+		pci_word &= ~E1000_PCI_PMCSR_D3;
+		igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		reg_val = (E1000_INVM_AUTOLOAD << 4) | (nvm_word << 16);
+		wr32(E1000_EEARBC_I210, reg_val);
+
+		/* restore WUC register */
+		wr32(E1000_WUC, wuc);
+	}
+	/* restore MDICNFG setting */
+	wr32(E1000_MDICNFG, mdicnfg);
+	return ret_val;
+}
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h
index 2d913716573a..710f8e9f10fb 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.h
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.h
@@ -46,6 +46,7 @@ s32 igb_read_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 *data);
 s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data);
 s32 igb_init_nvm_params_i210(struct e1000_hw *hw);
 bool igb_get_flash_presence_i210(struct e1000_hw *hw);
+s32 igb_pll_workaround_i210(struct e1000_hw *hw);
 
 #define E1000_STM_OPCODE		0xDB00
 #define E1000_EEPROM_FLASH_SIZE_WORD	0x11
@@ -91,4 +92,15 @@ enum E1000_INVM_STRUCTURE_TYPE {
 #define NVM_LED_1_CFG_DEFAULT_I211	0x0184
 #define NVM_LED_0_2_CFG_DEFAULT_I211	0x200C
 
+/* PLL Defines */
+#define E1000_PCI_PMCSR			0x44
+#define E1000_PCI_PMCSR_D3		0x03
+#define E1000_MAX_PLL_TRIES		5
+#define E1000_PHY_PLL_UNCONF		0xFF
+#define E1000_PHY_PLL_FREQ_PAGE		0xFC0000
+#define E1000_PHY_PLL_FREQ_REG		0x000E
+#define E1000_INVM_DEFAULT_AL		0x202F
+#define E1000_INVM_AUTOLOAD		0x0A
+#define E1000_INVM_PLL_WO_VAL		0x0010
+
 #endif
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 82632c6c53af..7156981ec813 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -69,6 +69,7 @@
 #define E1000_PBA      0x01000  /* Packet Buffer Allocation - RW */
 #define E1000_PBS      0x01008  /* Packet Buffer Size */
 #define E1000_EEMNGCTL 0x01010  /* MNG EEprom Control */
+#define E1000_EEARBC_I210 0x12024  /* EEPROM Auto Read Bus Control */
 #define E1000_EEWR     0x0102C  /* EEPROM Write Register - RW */
 #define E1000_I2CCMD   0x01028  /* SFPI2C Command Register - RW */
 #define E1000_FRTIMER  0x01048  /* Free Running Timer - RW */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 46d31a49f5ea..206e79d29c79 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1014,6 +1014,12 @@ static void igb_reset_q_vector(struct igb_adapter *adapter, int v_idx)
 {
 	struct igb_q_vector *q_vector = adapter->q_vector[v_idx];
 
+	/* Coming from igb_set_interrupt_capability, the vectors are not yet
+	 * allocated. So, q_vector is NULL so we should stop here.
+	 */
+	if (!q_vector)
+		return;
+
 	if (q_vector->tx.ring)
 		adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
 
@@ -1121,6 +1127,7 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix)
 
 	/* If we can't do MSI-X, try MSI */
 msi_only:
+	adapter->flags &= ~IGB_FLAG_HAS_MSIX;
 #ifdef CONFIG_PCI_IOV
 	/* disable SR-IOV for non MSI-X configurations */
 	if (adapter->vf_data) {
@@ -1606,6 +1613,8 @@ void igb_power_up_link(struct igb_adapter *adapter)
 		igb_power_up_phy_copper(&adapter->hw);
 	else
 		igb_power_up_serdes_link_82575(&adapter->hw);
+
+	igb_setup_link(&adapter->hw);
 }
 
 /**
@@ -7121,6 +7130,20 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	}
 }
 
+void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+	struct igb_adapter *adapter = hw->back;
+
+	pci_read_config_word(adapter->pdev, reg, value);
+}
+
+void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+	struct igb_adapter *adapter = hw->back;
+
+	pci_write_config_word(adapter->pdev, reg, *value);
+}
+
 s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value)
 {
 	struct igb_adapter *adapter = hw->back;
@@ -7484,6 +7507,8 @@ static int igb_sriov_reinit(struct pci_dev *dev)
 
 	if (netif_running(netdev))
 		igb_close(netdev);
+	else
+		igb_reset(adapter);
 
 	igb_clear_interrupt_scheme(adapter);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 8d76fca7fde7..96fc7fe8519f 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -89,9 +89,8 @@
 #define      MVNETA_TX_IN_PRGRS                  BIT(1)
 #define      MVNETA_TX_FIFO_EMPTY                BIT(8)
 #define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
-#define MVNETA_SERDES_CFG			 0x24A0
+#define MVNETA_SGMII_SERDES_CFG			 0x24A0
 #define      MVNETA_SGMII_SERDES_PROTO		 0x0cc7
-#define      MVNETA_RGMII_SERDES_PROTO		 0x0667
 #define MVNETA_TYPE_PRIO                         0x24bc
 #define      MVNETA_FORCE_UNI                    BIT(21)
 #define MVNETA_TXQ_CMD_1                         0x24e4
@@ -214,7 +213,7 @@
 /* Various constants */
 
 /* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS		16
+#define MVNETA_TXDONE_COAL_PKTS		1
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
@@ -712,6 +711,35 @@ static void mvneta_rxq_bm_disable(struct mvneta_port *pp,
 	mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
 }
 
+
+
+/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */
+static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable)
+{
+	u32  val;
+
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+
+	if (enable)
+		val |= MVNETA_GMAC2_PORT_RGMII;
+	else
+		val &= ~MVNETA_GMAC2_PORT_RGMII;
+
+	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+}
+
+/* Config SGMII port */
+static void mvneta_port_sgmii_config(struct mvneta_port *pp)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+	val |= MVNETA_GMAC2_PCS_ENABLE;
+	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+
+	mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
+}
+
 /* Start the Ethernet port RX and TX activity */
 static void mvneta_port_up(struct mvneta_port *pp)
 {
@@ -1189,7 +1217,7 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 	command =  l3_offs    << MVNETA_TX_L3_OFF_SHIFT;
 	command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT;
 
-	if (l3_proto == swab16(ETH_P_IP))
+	if (l3_proto == htons(ETH_P_IP))
 		command |= MVNETA_TXD_IP_CSUM;
 	else
 		command |= MVNETA_TX_L3_IP6;
@@ -1584,6 +1612,7 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
 	u16 txq_id = skb_get_queue_mapping(skb);
 	struct mvneta_tx_queue *txq = &pp->txqs[txq_id];
 	struct mvneta_tx_desc *tx_desc;
+	int len = skb->len;
 	struct netdev_queue *nq;
 	int frags = 0;
 	u32 tx_cmd;
@@ -1647,7 +1676,7 @@ out:
 
 		u64_stats_update_begin(&stats->syncp);
 		stats->tx_packets++;
-		stats->tx_bytes  += skb->len;
+		stats->tx_bytes  += len;
 		u64_stats_update_end(&stats->syncp);
 	} else {
 		dev->stats.tx_dropped++;
@@ -2365,7 +2394,7 @@ static void mvneta_adjust_link(struct net_device *ndev)
 
 			if (phydev->speed == SPEED_1000)
 				val |= MVNETA_GMAC_CONFIG_GMII_SPEED;
-			else
+			else if (phydev->speed == SPEED_100)
 				val |= MVNETA_GMAC_CONFIG_MII_SPEED;
 
 			mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
@@ -2729,15 +2758,12 @@ static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
 
 	if (phy_mode == PHY_INTERFACE_MODE_SGMII)
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-	else
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO);
+		mvneta_port_sgmii_config(pp);
 
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-
-	val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII;
+	mvneta_gmac_rgmii_set(pp, 1);
 
 	/* Cancel Port Reset */
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
 	val &= ~MVNETA_GMAC2_PORT_RESET;
 	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 70e95324a97d..c2cd8d31bcad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -66,7 +66,6 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 
 	cq->ring = ring;
 	cq->is_tx = mode;
-	spin_lock_init(&cq->lock);
 
 	/* Allocate HW buffers on provided NUMA node.
 	 * dev->numa_node is used in mtt range allocation flow.
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 84a96f70dfb5..2f83f3489fdb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1315,15 +1315,11 @@ static void mlx4_en_netpoll(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_cq *cq;
-	unsigned long flags;
 	int i;
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		cq = priv->rx_cq[i];
-		spin_lock_irqsave(&cq->lock, flags);
-		napi_synchronize(&cq->napi);
-		mlx4_en_process_rx_cq(dev, cq, 0);
-		spin_unlock_irqrestore(&cq->lock, flags);
+		napi_schedule(&cq->napi);
 	}
 }
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 7e2995ecea6f..84e41920b5ff 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -398,7 +398,7 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port,
 
 	MLX4_GET(func_cap->flags1, outbox, QUERY_FUNC_CAP_FLAGS1_OFFSET);
 	if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_ETH) {
-		if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_OFFSET) {
+		if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_FORCE_VLAN) {
 			mlx4_err(dev, "VLAN is enforced on this port\n");
 			err = -EPROTONOSUPPORT;
 			goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index d413e60071d4..4a13b0001471 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2275,13 +2275,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	/* Allow large DMA segments, up to the firmware limit of 1 GB */
 	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
-
-	dev       = &priv->dev;
+	dev       = pci_get_drvdata(pdev);
+	priv      = mlx4_priv(dev);
 	dev->pdev = pdev;
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
@@ -2399,7 +2394,8 @@ slave_start:
 	 * No return code for this call, just warn the user in case of PCI
 	 * express device capabilities are under-satisfied by the bus.
 	 */
-	mlx4_check_pcie_caps(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_check_pcie_caps(dev);
 
 	/* In master functions, the communication channel must be initialized
 	 * after obtaining its address from fw */
@@ -2464,8 +2460,7 @@ slave_start:
 	mlx4_sense_init(dev);
 	mlx4_start_sense(dev);
 
-	priv->pci_dev_data = pci_dev_data;
-	pci_set_drvdata(pdev, dev);
+	priv->removed = 0;
 
 	return 0;
 
@@ -2531,84 +2526,108 @@ err_disable_pdev:
 
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct mlx4_priv *priv;
+	struct mlx4_dev *dev;
+
 	printk_once(KERN_INFO "%s", mlx4_version);
 
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev       = &priv->dev;
+	pci_set_drvdata(pdev, dev);
+	priv->pci_dev_data = id->driver_data;
+
 	return __mlx4_init_one(pdev, id->driver_data);
 }
 
-static void mlx4_remove_one(struct pci_dev *pdev)
+static void __mlx4_remove_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	int               pci_dev_data;
 	int p;
 
-	if (dev) {
-		/* in SRIOV it is not allowed to unload the pf's
-		 * driver while there are alive vf's */
-		if (mlx4_is_master(dev)) {
-			if (mlx4_how_many_lives_vf(dev))
-				printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
-		}
-		mlx4_stop_sense(dev);
-		mlx4_unregister_device(dev);
+	if (priv->removed)
+		return;
 
-		for (p = 1; p <= dev->caps.num_ports; p++) {
-			mlx4_cleanup_port_info(&priv->port[p]);
-			mlx4_CLOSE_PORT(dev, p);
-		}
+	pci_dev_data = priv->pci_dev_data;
 
-		if (mlx4_is_master(dev))
-			mlx4_free_resource_tracker(dev,
-						   RES_TR_FREE_SLAVES_ONLY);
-
-		mlx4_cleanup_counters_table(dev);
-		mlx4_cleanup_qp_table(dev);
-		mlx4_cleanup_srq_table(dev);
-		mlx4_cleanup_cq_table(dev);
-		mlx4_cmd_use_polling(dev);
-		mlx4_cleanup_eq_table(dev);
-		mlx4_cleanup_mcg_table(dev);
-		mlx4_cleanup_mr_table(dev);
-		mlx4_cleanup_xrcd_table(dev);
-		mlx4_cleanup_pd_table(dev);
+	/* in SRIOV it is not allowed to unload the pf's
+	 * driver while there are alive vf's */
+	if (mlx4_is_master(dev) && mlx4_how_many_lives_vf(dev))
+		printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
+	mlx4_stop_sense(dev);
+	mlx4_unregister_device(dev);
 
-		if (mlx4_is_master(dev))
-			mlx4_free_resource_tracker(dev,
-						   RES_TR_FREE_STRUCTS_ONLY);
-
-		iounmap(priv->kar);
-		mlx4_uar_free(dev, &priv->driver_uar);
-		mlx4_cleanup_uar_table(dev);
-		if (!mlx4_is_slave(dev))
-			mlx4_clear_steering(dev);
-		mlx4_free_eq_table(dev);
-		if (mlx4_is_master(dev))
-			mlx4_multi_func_cleanup(dev);
-		mlx4_close_hca(dev);
-		if (mlx4_is_slave(dev))
-			mlx4_multi_func_cleanup(dev);
-		mlx4_cmd_cleanup(dev);
-
-		if (dev->flags & MLX4_FLAG_MSI_X)
-			pci_disable_msix(pdev);
-		if (dev->flags & MLX4_FLAG_SRIOV) {
-			mlx4_warn(dev, "Disabling SR-IOV\n");
-			pci_disable_sriov(pdev);
-		}
+	for (p = 1; p <= dev->caps.num_ports; p++) {
+		mlx4_cleanup_port_info(&priv->port[p]);
+		mlx4_CLOSE_PORT(dev, p);
+	}
+
+	if (mlx4_is_master(dev))
+		mlx4_free_resource_tracker(dev,
+					   RES_TR_FREE_SLAVES_ONLY);
+
+	mlx4_cleanup_counters_table(dev);
+	mlx4_cleanup_qp_table(dev);
+	mlx4_cleanup_srq_table(dev);
+	mlx4_cleanup_cq_table(dev);
+	mlx4_cmd_use_polling(dev);
+	mlx4_cleanup_eq_table(dev);
+	mlx4_cleanup_mcg_table(dev);
+	mlx4_cleanup_mr_table(dev);
+	mlx4_cleanup_xrcd_table(dev);
+	mlx4_cleanup_pd_table(dev);
 
-		if (!mlx4_is_slave(dev))
-			mlx4_free_ownership(dev);
+	if (mlx4_is_master(dev))
+		mlx4_free_resource_tracker(dev,
+					   RES_TR_FREE_STRUCTS_ONLY);
 
-		kfree(dev->caps.qp0_tunnel);
-		kfree(dev->caps.qp0_proxy);
-		kfree(dev->caps.qp1_tunnel);
-		kfree(dev->caps.qp1_proxy);
+	iounmap(priv->kar);
+	mlx4_uar_free(dev, &priv->driver_uar);
+	mlx4_cleanup_uar_table(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_clear_steering(dev);
+	mlx4_free_eq_table(dev);
+	if (mlx4_is_master(dev))
+		mlx4_multi_func_cleanup(dev);
+	mlx4_close_hca(dev);
+	if (mlx4_is_slave(dev))
+		mlx4_multi_func_cleanup(dev);
+	mlx4_cmd_cleanup(dev);
 
-		kfree(priv);
-		pci_release_regions(pdev);
-		pci_disable_device(pdev);
-		pci_set_drvdata(pdev, NULL);
+	if (dev->flags & MLX4_FLAG_MSI_X)
+		pci_disable_msix(pdev);
+	if (dev->flags & MLX4_FLAG_SRIOV) {
+		mlx4_warn(dev, "Disabling SR-IOV\n");
+		pci_disable_sriov(pdev);
 	}
+
+	if (!mlx4_is_slave(dev))
+		mlx4_free_ownership(dev);
+
+	kfree(dev->caps.qp0_tunnel);
+	kfree(dev->caps.qp0_proxy);
+	kfree(dev->caps.qp1_tunnel);
+	kfree(dev->caps.qp1_proxy);
+
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	memset(priv, 0, sizeof(*priv));
+	priv->pci_dev_data = pci_dev_data;
+	priv->removed = 1;
+}
+
+static void mlx4_remove_one(struct pci_dev *pdev)
+{
+	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	__mlx4_remove_one(pdev);
+	kfree(priv);
+	pci_set_drvdata(pdev, NULL);
 }
 
 int mlx4_restart_one(struct pci_dev *pdev)
@@ -2618,7 +2637,7 @@ int mlx4_restart_one(struct pci_dev *pdev)
 	int		  pci_dev_data;
 
 	pci_dev_data = priv->pci_dev_data;
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 	return __mlx4_init_one(pdev, pci_dev_data);
 }
 
@@ -2673,7 +2692,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table);
 static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 					      pci_channel_state_t state)
 {
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -2681,11 +2700,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 
 static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 {
-	const struct pci_device_id *id;
-	int ret;
+	struct mlx4_dev	 *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int               ret;
 
-	id = pci_match_id(mlx4_pci_table, pdev);
-	ret = __mlx4_init_one(pdev, id->driver_data);
+	ret = __mlx4_init_one(pdev, priv->pci_dev_data);
 
 	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
@@ -2699,7 +2718,7 @@ static struct pci_driver mlx4_driver = {
 	.name		= DRV_NAME,
 	.id_table	= mlx4_pci_table,
 	.probe		= mlx4_init_one,
-	.shutdown	= mlx4_remove_one,
+	.shutdown	= __mlx4_remove_one,
 	.remove		= mlx4_remove_one,
 	.err_handler    = &mlx4_err_handler,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 7aec6c833973..99d7a28a2ada 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -796,6 +796,7 @@ struct mlx4_priv {
 	spinlock_t		ctx_lock;
 
 	int			pci_dev_data;
+	int                     removed;
 
 	struct list_head        pgdir_list;
 	struct mutex            pgdir_mutex;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index b57e8c87a34e..72db9bedd765 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -309,7 +309,6 @@ struct mlx4_en_cq {
 	struct mlx4_cq          mcq;
 	struct mlx4_hwq_resources wqres;
 	int                     ring;
-	spinlock_t              lock;
 	struct net_device      *dev;
 	struct napi_struct	napi;
 	int size;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 57428a0cb9dd..1e8a4b411dc6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1456,7 +1456,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 
 	switch (op) {
 	case RES_OP_RESERVE:
-		count = get_param_l(&in_param);
+		count = get_param_l(&in_param) & 0xffffff;
 		align = get_param_h(&in_param);
 		err = mlx4_grant_resource(dev, slave, RES_QP, count, 0);
 		if (err)
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 68026f7e8ba3..4a474dd9c910 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -872,6 +872,10 @@ static int myri10ge_dma_test(struct myri10ge_priv *mgp, int test_type)
 		return -ENOMEM;
 	dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE,
 				   DMA_BIDIRECTIONAL);
+	if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) {
+		__free_page(dmatest_page);
+		return -ENOMEM;
+	}
 
 	/* Run a small DMA test.
 	 * The magic multipliers to the length tell the firmware
@@ -1293,6 +1297,7 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 			int bytes, int watchdog)
 {
 	struct page *page;
+	dma_addr_t bus;
 	int idx;
 #if MYRI10GE_ALLOC_SIZE > 4096
 	int end_offset;
@@ -1317,11 +1322,21 @@ myri10ge_alloc_rx_pages(struct myri10ge_priv *mgp, struct myri10ge_rx_buf *rx,
 					rx->watchdog_needed = 1;
 				return;
 			}
+
+			bus = pci_map_page(mgp->pdev, page, 0,
+					   MYRI10GE_ALLOC_SIZE,
+					   PCI_DMA_FROMDEVICE);
+			if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+				__free_pages(page, MYRI10GE_ALLOC_ORDER);
+				if (rx->fill_cnt - rx->cnt < 16)
+					rx->watchdog_needed = 1;
+				return;
+			}
+
 			rx->page = page;
 			rx->page_offset = 0;
-			rx->bus = pci_map_page(mgp->pdev, page, 0,
-					       MYRI10GE_ALLOC_SIZE,
-					       PCI_DMA_FROMDEVICE);
+			rx->bus = bus;
+
 		}
 		rx->info[idx].page = rx->page;
 		rx->info[idx].page_offset = rx->page_offset;
@@ -2765,6 +2780,35 @@ myri10ge_submit_req(struct myri10ge_tx_buf *tx, struct mcp_kreq_ether_send *src,
 	mb();
 }
 
+static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp,
+				  struct myri10ge_tx_buf *tx, int idx)
+{
+	unsigned int len;
+	int last_idx;
+
+	/* Free any DMA resources we've alloced and clear out the skb slot */
+	last_idx = (idx + 1) & tx->mask;
+	idx = tx->req & tx->mask;
+	do {
+		len = dma_unmap_len(&tx->info[idx], len);
+		if (len) {
+			if (tx->info[idx].skb != NULL)
+				pci_unmap_single(mgp->pdev,
+						 dma_unmap_addr(&tx->info[idx],
+								bus), len,
+						 PCI_DMA_TODEVICE);
+			else
+				pci_unmap_page(mgp->pdev,
+					       dma_unmap_addr(&tx->info[idx],
+							      bus), len,
+					       PCI_DMA_TODEVICE);
+			dma_unmap_len_set(&tx->info[idx], len, 0);
+			tx->info[idx].skb = NULL;
+		}
+		idx = (idx + 1) & tx->mask;
+	} while (idx != last_idx);
+}
+
 /*
  * Transmit a packet.  We need to split the packet so that a single
  * segment does not cross myri10ge->tx_boundary, so this makes segment
@@ -2788,7 +2832,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb,
 	u32 low;
 	__be32 high_swapped;
 	unsigned int len;
-	int idx, last_idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
+	int idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
 	u16 pseudo_hdr_offset, cksum_offset, queue;
 	int cum_len, seglen, boundary, rdma_count;
 	u8 flags, odd_flag;
@@ -2885,9 +2929,12 @@ again:
 
 	/* map the skb for DMA */
 	len = skb_headlen(skb);
+	bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
+	if (unlikely(pci_dma_mapping_error(mgp->pdev, bus)))
+		goto drop;
+
 	idx = tx->req & tx->mask;
 	tx->info[idx].skb = skb;
-	bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
 	dma_unmap_addr_set(&tx->info[idx], bus, bus);
 	dma_unmap_len_set(&tx->info[idx], len, len);
 
@@ -2986,12 +3033,16 @@ again:
 			break;
 
 		/* map next fragment for DMA */
-		idx = (count + tx->req) & tx->mask;
 		frag = &skb_shinfo(skb)->frags[frag_idx];
 		frag_idx++;
 		len = skb_frag_size(frag);
 		bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len,
 				       DMA_TO_DEVICE);
+		if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+			myri10ge_unmap_tx_dma(mgp, tx, idx);
+			goto drop;
+		}
+		idx = (count + tx->req) & tx->mask;
 		dma_unmap_addr_set(&tx->info[idx], bus, bus);
 		dma_unmap_len_set(&tx->info[idx], len, len);
 	}
@@ -3022,31 +3073,8 @@ again:
 	return NETDEV_TX_OK;
 
 abort_linearize:
-	/* Free any DMA resources we've alloced and clear out the skb
-	 * slot so as to not trip up assertions, and to avoid a
-	 * double-free if linearizing fails */
+	myri10ge_unmap_tx_dma(mgp, tx, idx);
 
-	last_idx = (idx + 1) & tx->mask;
-	idx = tx->req & tx->mask;
-	tx->info[idx].skb = NULL;
-	do {
-		len = dma_unmap_len(&tx->info[idx], len);
-		if (len) {
-			if (tx->info[idx].skb != NULL)
-				pci_unmap_single(mgp->pdev,
-						 dma_unmap_addr(&tx->info[idx],
-								bus), len,
-						 PCI_DMA_TODEVICE);
-			else
-				pci_unmap_page(mgp->pdev,
-					       dma_unmap_addr(&tx->info[idx],
-							      bus), len,
-					       PCI_DMA_TODEVICE);
-			dma_unmap_len_set(&tx->info[idx], len, 0);
-			tx->info[idx].skb = NULL;
-		}
-		idx = (idx + 1) & tx->mask;
-	} while (idx != last_idx);
 	if (skb_is_gso(skb)) {
 		netdev_err(mgp->dev, "TSO but wanted to linearize?!?!?\n");
 		goto drop;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
index 7d4f54912bad..3e46c894a107 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c
@@ -1022,6 +1022,7 @@ static int qlcnic_dcb_peer_app_info(struct net_device *netdev,
 	struct qlcnic_dcb_cee *peer;
 	int i;
 
+	memset(info, 0, sizeof(*info));
 	*app_count = 0;
 
 	if (!test_bit(QLCNIC_DCB_STATE, &adapter->dcb->state))
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 040cb94e8219..957f0ffe31c4 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -301,6 +301,27 @@ static const u16 sh_eth_offset_fast_sh4[SH_ETH_MAX_REGISTER_OFFSET] = {
 };
 
 static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = {
+	[EDMR]		= 0x0000,
+	[EDTRR]		= 0x0004,
+	[EDRRR]		= 0x0008,
+	[TDLAR]		= 0x000c,
+	[RDLAR]		= 0x0010,
+	[EESR]		= 0x0014,
+	[EESIPR]	= 0x0018,
+	[TRSCER]	= 0x001c,
+	[RMFCR]		= 0x0020,
+	[TFTR]		= 0x0024,
+	[FDR]		= 0x0028,
+	[RMCR]		= 0x002c,
+	[EDOCR]		= 0x0030,
+	[FCFTR]		= 0x0034,
+	[RPADIR]	= 0x0038,
+	[TRIMD]		= 0x003c,
+	[RBWAR]		= 0x0040,
+	[RDFAR]		= 0x0044,
+	[TBRAR]		= 0x004c,
+	[TDFAR]		= 0x0050,
+
 	[ECMR]		= 0x0160,
 	[ECSR]		= 0x0164,
 	[ECSIPR]	= 0x0168,
@@ -539,7 +560,6 @@ static struct sh_eth_cpu_data sh7757_data = {
 	.register_type	= SH_ETH_REG_FAST_SH4,
 
 	.eesipr_value	= DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
-	.rmcr_value	= RMCR_RNC,
 
 	.tx_check	= EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
 	.eesr_err_check	= EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
@@ -617,7 +637,6 @@ static struct sh_eth_cpu_data sh7757_data_giga = {
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000072f,
-	.rmcr_value	= RMCR_RNC,
 
 	.irq_flags	= IRQF_SHARED,
 	.apr		= 1,
@@ -745,7 +764,6 @@ static struct sh_eth_cpu_data r8a7740_data = {
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000070f,
-	.rmcr_value	= RMCR_RNC,
 
 	.apr		= 1,
 	.mpr		= 1,
@@ -777,7 +795,6 @@ static struct sh_eth_cpu_data r7s72100_data = {
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000070f,
-	.rmcr_value	= RMCR_RNC,
 
 	.no_psr		= 1,
 	.apr		= 1,
@@ -826,9 +843,6 @@ static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd)
 	if (!cd->fdr_value)
 		cd->fdr_value = DEFAULT_FDR_INIT;
 
-	if (!cd->rmcr_value)
-		cd->rmcr_value = DEFAULT_RMCR_VALUE;
-
 	if (!cd->tx_check)
 		cd->tx_check = DEFAULT_TX_CHECK;
 
@@ -1281,8 +1295,8 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start)
 	sh_eth_write(ndev, mdp->cd->fdr_value, FDR);
 	sh_eth_write(ndev, 0, TFTR);
 
-	/* Frame recv control */
-	sh_eth_write(ndev, mdp->cd->rmcr_value, RMCR);
+	/* Frame recv control (enable multiple-packets per rx irq) */
+	sh_eth_write(ndev, RMCR_RNC, RMCR);
 
 	sh_eth_write(ndev, DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2, TRSCER);
 
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 6075915b88ec..a096b4bf9799 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -320,7 +320,6 @@ enum TD_STS_BIT {
 enum RMCR_BIT {
 	RMCR_RNC = 0x00000001,
 };
-#define DEFAULT_RMCR_VALUE	0x00000000
 
 /* ECMR */
 enum FELIC_MODE_BIT {
@@ -467,7 +466,6 @@ struct sh_eth_cpu_data {
 	unsigned long fdr_value;
 	unsigned long fcftr_value;
 	unsigned long rpadir_value;
-	unsigned long rmcr_value;
 
 	/* interrupt checking mask */
 	unsigned long tx_check;
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 174a92f5fe51..7645a3ce3854 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -565,10 +565,17 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
 	 * several of each (in fact that's the only option if host
 	 * page size is >4K).  So we may allocate some extra VIs just
 	 * for writing PIO buffers through.
+	 *
+	 * The UC mapping contains (min_vis - 1) complete VIs and the
+	 * first half of the next VI.  Then the WC mapping begins with
+	 * the second half of this last VI.
 	 */
 	uc_mem_map_size = PAGE_ALIGN((min_vis - 1) * EFX_VI_PAGE_SIZE +
 				     ER_DZ_TX_PIOBUF);
 	if (nic_data->n_piobufs) {
+		/* pio_write_vi_base rounds down to give the number of complete
+		 * VIs inside the UC mapping.
+		 */
 		pio_write_vi_base = uc_mem_map_size / EFX_VI_PAGE_SIZE;
 		wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base +
 					       nic_data->n_piobufs) *
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 83d464347021..f06c790fba5a 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1603,6 +1603,8 @@ static int efx_probe_nic(struct efx_nic *efx)
 	if (rc)
 		goto fail1;
 
+	efx_set_channels(efx);
+
 	rc = efx->type->dimension_resources(efx);
 	if (rc)
 		goto fail2;
@@ -1613,7 +1615,6 @@ static int efx_probe_nic(struct efx_nic *efx)
 		efx->rx_indir_table[i] =
 			ethtool_rxfh_indir_default(i, efx->rss_spread);
 
-	efx_set_channels(efx);
 	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
 	netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
 
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 4d3f119b67b3..afb94aa2c15e 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -66,10 +66,17 @@
 #define EFX_USE_QWORD_IO 1
 #endif
 
+/* Hardware issue requires that only 64-bit naturally aligned writes
+ * are seen by hardware. Its not strictly necessary to restrict to
+ * x86_64 arch, but done for safety since unusual write combining behaviour
+ * can break PIO.
+ */
+#ifdef CONFIG_X86_64
 /* PIO is a win only if write-combining is possible */
 #ifdef ARCH_HAS_IOREMAP_WC
 #define EFX_USE_PIO 1
 #endif
+#endif
 
 #ifdef EFX_USE_QWORD_IO
 static inline void _efx_writeq(struct efx_nic *efx, __le64 value,
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 79226b19e3c4..cb3fb9dba8fb 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -156,13 +156,15 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
 	efx->net_dev->rx_cpu_rmap = NULL;
 #endif
 
-	/* Disable MSI/MSI-X interrupts */
-	efx_for_each_channel(channel, efx)
-		free_irq(channel->irq, &efx->msi_context[channel->channel]);
-
-	/* Disable legacy interrupt */
-	if (efx->legacy_irq)
+	if (EFX_INT_MODE_USE_MSI(efx)) {
+		/* Disable MSI/MSI-X interrupts */
+		efx_for_each_channel(channel, efx)
+			free_irq(channel->irq,
+				 &efx->msi_context[channel->channel]);
+	} else {
+		/* Disable legacy interrupt */
 		free_irq(efx->legacy_irq, efx);
+	}
 }
 
 /* Register dump */
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 75d11fa4eb0a..d79c842680a5 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -189,6 +189,18 @@ struct efx_short_copy_buffer {
 	u8 buf[L1_CACHE_BYTES];
 };
 
+/* Copy in explicit 64-bit writes. */
+static void efx_memcpy_64(void __iomem *dest, void *src, size_t len)
+{
+	u64 *src64 = src;
+	u64 __iomem *dest64 = dest;
+	size_t l64 = len / 8;
+	size_t i;
+
+	for (i = 0; i < l64; i++)
+		writeq(src64[i], &dest64[i]);
+}
+
 /* Copy to PIO, respecting that writes to PIO buffers must be dword aligned.
  * Advances piobuf pointer. Leaves additional data in the copy buffer.
  */
@@ -198,7 +210,7 @@ static void efx_memcpy_toio_aligned(struct efx_nic *efx, u8 __iomem **piobuf,
 {
 	int block_len = len & ~(sizeof(copy_buf->buf) - 1);
 
-	memcpy_toio(*piobuf, data, block_len);
+	efx_memcpy_64(*piobuf, data, block_len);
 	*piobuf += block_len;
 	len -= block_len;
 
@@ -230,7 +242,7 @@ static void efx_memcpy_toio_aligned_cb(struct efx_nic *efx, u8 __iomem **piobuf,
 		if (copy_buf->used < sizeof(copy_buf->buf))
 			return;
 
-		memcpy_toio(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+		efx_memcpy_64(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
 		*piobuf += sizeof(copy_buf->buf);
 		data += copy_to_buf;
 		len -= copy_to_buf;
@@ -245,7 +257,7 @@ static void efx_flush_copy_buffer(struct efx_nic *efx, u8 __iomem *piobuf,
 {
 	/* if there's anything in it, write the whole buffer, including junk */
 	if (copy_buf->used)
-		memcpy_toio(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+		efx_memcpy_64(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
 }
 
 /* Traverse skb structure and copy fragments in to PIO buffer.
@@ -304,8 +316,8 @@ efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 		 */
 		BUILD_BUG_ON(L1_CACHE_BYTES >
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
-		memcpy_toio(tx_queue->piobuf, skb->data,
-			    ALIGN(skb->len, L1_CACHE_BYTES));
+		efx_memcpy_64(tx_queue->piobuf, skb->data,
+			      ALIGN(skb->len, L1_CACHE_BYTES));
 	}
 
 	EFX_POPULATE_QWORD_5(buffer->option,
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 6382b7c416f4..e10f5ed26181 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1341,6 +1341,42 @@ static void smsc911x_rx_multicast_update_workaround(struct smsc911x_data *pdata)
 	spin_unlock(&pdata->mac_lock);
 }
 
+static int smsc911x_phy_general_power_up(struct smsc911x_data *pdata)
+{
+	int rc = 0;
+
+	if (!pdata->phy_dev)
+		return rc;
+
+	/* If the internal PHY is in General Power-Down mode, all, except the
+	 * management interface, is powered-down and stays in that condition as
+	 * long as Phy register bit 0.11 is HIGH.
+	 *
+	 * In that case, clear the bit 0.11, so the PHY powers up and we can
+	 * access to the phy registers.
+	 */
+	rc = phy_read(pdata->phy_dev, MII_BMCR);
+	if (rc < 0) {
+		SMSC_WARN(pdata, drv, "Failed reading PHY control reg");
+		return rc;
+	}
+
+	/* If the PHY general power-down bit is not set is not necessary to
+	 * disable the general power down-mode.
+	 */
+	if (rc & BMCR_PDOWN) {
+		rc = phy_write(pdata->phy_dev, MII_BMCR, rc & ~BMCR_PDOWN);
+		if (rc < 0) {
+			SMSC_WARN(pdata, drv, "Failed writing PHY control reg");
+			return rc;
+		}
+
+		usleep_range(1000, 1500);
+	}
+
+	return 0;
+}
+
 static int smsc911x_phy_disable_energy_detect(struct smsc911x_data *pdata)
 {
 	int rc = 0;
@@ -1414,6 +1450,16 @@ static int smsc911x_soft_reset(struct smsc911x_data *pdata)
 	int ret;
 
 	/*
+	 * Make sure to power-up the PHY chip before doing a reset, otherwise
+	 * the reset fails.
+	 */
+	ret = smsc911x_phy_general_power_up(pdata);
+	if (ret) {
+		SMSC_WARN(pdata, drv, "Failed to power-up the PHY chip");
+		return ret;
+	}
+
+	/*
 	 * LAN9210/LAN9211/LAN9220/LAN9221 chips have an internal PHY that
 	 * are initialized in a Energy Detect Power-Down mode that prevents
 	 * the MAC chip to be software reseted. So we have to wakeup the PHY
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 1c24a8f368bd..03ae9def0e0c 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -656,7 +656,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	spin_lock_irqsave(&port->vio.lock, flags);
 
 	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		if (!netif_queue_stopped(dev)) {
 			netif_stop_queue(dev);
 
@@ -704,7 +704,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.tx_bytes += skb->len;
 
 	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		netif_stop_queue(dev);
 		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
 			netif_wake_queue(dev);
@@ -1083,6 +1083,24 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac)
 	return vp;
 }
 
+static void vnet_cleanup(void)
+{
+	struct vnet *vp;
+	struct net_device *dev;
+
+	mutex_lock(&vnet_list_mutex);
+	while (!list_empty(&vnet_list)) {
+		vp = list_first_entry(&vnet_list, struct vnet, list);
+		list_del(&vp->list);
+		dev = vp->dev;
+		/* vio_unregister_driver() should have cleaned up port_list */
+		BUG_ON(!list_empty(&vp->port_list));
+		unregister_netdev(dev);
+		free_netdev(dev);
+	}
+	mutex_unlock(&vnet_list_mutex);
+}
+
 static const char *local_mac_prop = "local-mac-address";
 
 static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
@@ -1240,7 +1258,6 @@ static int vnet_port_remove(struct vio_dev *vdev)
 
 		kfree(port);
 
-		unregister_netdev(vp->dev);
 	}
 	return 0;
 }
@@ -1268,6 +1285,7 @@ static int __init vnet_init(void)
 static void __exit vnet_exit(void)
 {
 	vio_unregister_driver(&vnet_port_driver);
+	vnet_cleanup();
 }
 
 module_init(vnet_init);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 7d6d8ec676c8..921b9df2faca 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1884,18 +1884,12 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
 		phyid = be32_to_cpup(parp+1);
 		mdio = of_find_device_by_node(mdio_node);
-
-		if (strncmp(mdio->name, "gpio", 4) == 0) {
-			/* GPIO bitbang MDIO driver attached */
-			struct mii_bus *bus = dev_get_drvdata(&mdio->dev);
-
-			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
-				 PHY_ID_FMT, bus->id, phyid);
-		} else {
-			/* davinci MDIO driver attached */
-			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
-				 PHY_ID_FMT, mdio->name, phyid);
+		if (!mdio) {
+			pr_err("Missing mdio platform device\n");
+			return -EINVAL;
 		}
+		snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
+			 PHY_ID_FMT, mdio->name, phyid);
 
 		mac_addr = of_get_mac_address(slave_node);
 		if (mac_addr)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index d6fce9750b95..3c1c33ceffba 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -146,6 +146,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	struct hv_netvsc_packet *packet;
 	int ret;
 	unsigned int i, num_pages, npg_data;
+	u32 skb_length = skb->len;
 
 	/* Add multipages for skb->data and additional 2 for RNDIS */
 	npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1)
@@ -216,7 +217,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	ret = rndis_filter_send(net_device_ctx->device_ctx,
 				  packet);
 	if (ret == 0) {
-		net->stats.tx_bytes += skb->len;
+		net->stats.tx_bytes += skb_length;
 		net->stats.tx_packets++;
 	} else {
 		kfree(packet);
diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c
index bf0d55e2dd63..6adbef89c4b0 100644
--- a/drivers/net/ieee802154/fakehard.c
+++ b/drivers/net/ieee802154/fakehard.c
@@ -376,17 +376,20 @@ static int ieee802154fake_probe(struct platform_device *pdev)
 
 	err = wpan_phy_register(phy);
 	if (err)
-		goto out;
+		goto err_phy_reg;
 
 	err = register_netdev(dev);
-	if (err < 0)
-		goto out;
+	if (err)
+		goto err_netdev_reg;
 
 	dev_info(&pdev->dev, "Added ieee802154 HardMAC hardware\n");
 	return 0;
 
-out:
-	unregister_netdev(dev);
+err_netdev_reg:
+	wpan_phy_unregister(phy);
+err_phy_reg:
+	free_netdev(dev);
+	wpan_phy_free(phy);
 	return err;
 }
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 1831fb7cd017..fbf7dcdc22b0 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -263,11 +263,9 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct macvlan_port *port = vlan->port;
 	const struct macvlan_dev *dest;
-	__u8 ip_summed = skb->ip_summed;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
 		const struct ethhdr *eth = (void *)skb->data;
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
 		/* send to other bridge ports directly */
 		if (is_multicast_ether_addr(eth->h_dest)) {
@@ -285,7 +283,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 xmit_world:
-	skb->ip_summed = ip_summed;
 	skb->dev = vlan->lowerdev;
 	return dev_queue_xmit(skb);
 }
@@ -461,8 +458,10 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change)
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct net_device *lowerdev = vlan->lowerdev;
 
-	if (change & IFF_ALLMULTI)
-		dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+	if (dev->flags & IFF_UP) {
+		if (change & IFF_ALLMULTI)
+			dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+	}
 }
 
 static void macvlan_set_mac_lists(struct net_device *dev)
@@ -518,6 +517,11 @@ static struct lock_class_key macvlan_netdev_addr_lock_key;
 #define MACVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
+static int macvlan_get_nest_level(struct net_device *dev)
+{
+	return ((struct macvlan_dev *)netdev_priv(dev))->nest_level;
+}
+
 static void macvlan_set_lockdep_class_one(struct net_device *dev,
 					  struct netdev_queue *txq,
 					  void *_unused)
@@ -528,8 +532,9 @@ static void macvlan_set_lockdep_class_one(struct net_device *dev,
 
 static void macvlan_set_lockdep_class(struct net_device *dev)
 {
-	lockdep_set_class(&dev->addr_list_lock,
-			  &macvlan_netdev_addr_lock_key);
+	lockdep_set_class_and_subclass(&dev->addr_list_lock,
+				       &macvlan_netdev_addr_lock_key,
+				       macvlan_get_nest_level(dev));
 	netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL);
 }
 
@@ -543,6 +548,7 @@ static int macvlan_init(struct net_device *dev)
 				  (lowerdev->state & MACVLAN_STATE_MASK);
 	dev->features 		= lowerdev->features & MACVLAN_FEATURES;
 	dev->features		|= ALWAYS_ON_FEATURES;
+	dev->vlan_features	= lowerdev->vlan_features & MACVLAN_FEATURES;
 	dev->gso_max_size	= lowerdev->gso_max_size;
 	dev->iflink		= lowerdev->ifindex;
 	dev->hard_header_len	= lowerdev->hard_header_len;
@@ -703,6 +709,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
 					     features,
 					     mask);
 	features |= ALWAYS_ON_FEATURES;
+	features &= ~NETIF_F_NETNS_LOCAL;
 
 	return features;
 }
@@ -731,6 +738,7 @@ static const struct net_device_ops macvlan_netdev_ops = {
 	.ndo_fdb_add		= macvlan_fdb_add,
 	.ndo_fdb_del		= macvlan_fdb_del,
 	.ndo_fdb_dump		= ndo_dflt_fdb_dump,
+	.ndo_get_lock_subclass  = macvlan_get_nest_level,
 };
 
 void macvlan_common_setup(struct net_device *dev)
@@ -859,6 +867,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	vlan->dev      = dev;
 	vlan->port     = port;
 	vlan->set_features = MACVLAN_FEATURES;
+	vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1;
 
 	vlan->mode     = MACVLAN_MODE_VEPA;
 	if (data && data[IFLA_MACVLAN_MODE])
@@ -1036,7 +1045,6 @@ static int macvlan_device_event(struct notifier_block *unused,
 		list_for_each_entry_safe(vlan, next, &port->vlans, list)
 			vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill);
 		unregister_netdevice_many(&list_kill);
-		list_del(&list_kill);
 		break;
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid underlaying device to change its type. */
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index ff111a89e17f..07c942b6ae01 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -16,6 +16,7 @@
 #include <linux/idr.h>
 #include <linux/fs.h>
 
+#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/rtnetlink.h>
 #include <net/sock.h>
@@ -112,17 +113,15 @@ out:
 	return err;
 }
 
+/* Requires RTNL */
 static int macvtap_set_queue(struct net_device *dev, struct file *file,
 			     struct macvtap_queue *q)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
-	int err = -EBUSY;
 
-	rtnl_lock();
 	if (vlan->numqueues == MAX_MACVTAP_QUEUES)
-		goto out;
+		return -EBUSY;
 
-	err = 0;
 	rcu_assign_pointer(q->vlan, vlan);
 	rcu_assign_pointer(vlan->taps[vlan->numvtaps], q);
 	sock_hold(&q->sk);
@@ -136,9 +135,7 @@ static int macvtap_set_queue(struct net_device *dev, struct file *file,
 	vlan->numvtaps++;
 	vlan->numqueues++;
 
-out:
-	rtnl_unlock();
-	return err;
+	return 0;
 }
 
 static int macvtap_disable_queue(struct macvtap_queue *q)
@@ -322,6 +319,15 @@ static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb)
 			segs = nskb;
 		}
 	} else {
+		/* If we receive a partial checksum and the tap side
+		 * doesn't support checksum offload, compute the checksum.
+		 * Note: it doesn't matter which checksum feature to
+		 *        check, we either support them all or none.
+		 */
+		if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		    !(features & NETIF_F_ALL_CSUM) &&
+		    skb_checksum_help(skb))
+			goto drop;
 		skb_queue_tail(&q->sk.sk_receive_queue, skb);
 	}
 
@@ -445,11 +451,12 @@ static void macvtap_sock_destruct(struct sock *sk)
 static int macvtap_open(struct inode *inode, struct file *file)
 {
 	struct net *net = current->nsproxy->net_ns;
-	struct net_device *dev = dev_get_by_macvtap_minor(iminor(inode));
+	struct net_device *dev;
 	struct macvtap_queue *q;
-	int err;
+	int err = -ENODEV;
 
-	err = -ENODEV;
+	rtnl_lock();
+	dev = dev_get_by_macvtap_minor(iminor(inode));
 	if (!dev)
 		goto out;
 
@@ -489,6 +496,7 @@ out:
 	if (dev)
 		dev_put(dev);
 
+	rtnl_unlock();
 	return err;
 }
 
@@ -563,6 +571,8 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
+			if (skb->protocol == htons(ETH_P_IPV6))
+				ipv6_proxy_select_ident(skb);
 			break;
 		default:
 			return -EINVAL;
@@ -619,6 +629,8 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
 		vnet_hdr->csum_start = skb_checksum_start_offset(skb);
+		if (vlan_tx_tag_present(skb))
+			vnet_hdr->csum_start += VLAN_HLEN;
 		vnet_hdr->csum_offset = skb->csum_offset;
 	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2f6989b1e0dc..25f74191a788 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -353,7 +353,7 @@ int phy_device_register(struct phy_device *phydev)
 	phydev->bus->phy_map[phydev->addr] = phydev;
 
 	/* Run all of the fixups for this PHY */
-	err = phy_init_hw(phydev);
+	err = phy_scan_fixups(phydev);
 	if (err) {
 		pr_err("PHY %d failed to initialize\n", phydev->addr);
 		goto out;
@@ -613,8 +613,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	err = phy_init_hw(phydev);
 	if (err)
 		phy_detach(phydev);
-
-	phy_resume(phydev);
+	else
+		phy_resume(phydev);
 
 	return err;
 }
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 72ff14b811c6..5a1897d86e94 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -601,7 +601,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			if (file == ppp->owner)
 				ppp_shutdown_interface(ppp);
 		}
-		if (atomic_long_read(&file->f_count) <= 2) {
+		if (atomic_long_read(&file->f_count) < 2) {
 			ppp_release(NULL, file);
 			err = 0;
 		} else
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 2ea7efd11857..6c9c16d76935 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -675,7 +675,7 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 		po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
 				   dev->hard_header_len);
 
-		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr);
+		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
 		po->chan.private = sk;
 		po->chan.ops = &pppoe_chan_ops;
 
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 01805319e1e0..1dc628ffce2b 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	nf_reset(skb);
 
 	skb->ip_summed = CHECKSUM_NONE;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	ip_local_out(skb);
@@ -506,7 +506,9 @@ static int pptp_getname(struct socket *sock, struct sockaddr *uaddr,
 	int len = sizeof(struct sockaddr_pppox);
 	struct sockaddr_pppox sp;
 
-	sp.sa_family	  = AF_PPPOX;
+	memset(&sp.sa_addr, 0, sizeof(sp.sa_addr));
+
+	sp.sa_family    = AF_PPPOX;
 	sp.sa_protocol  = PX_PROTO_PPTP;
 	sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr;
 
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index cc70ecfc7062..87526443841f 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -83,6 +83,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 #include "slip.h"
 #ifdef CONFIG_INET
 #include <linux/ip.h>
@@ -416,34 +417,44 @@ static void sl_encaps(struct slip *sl, unsigned char *icp, int len)
 #endif
 }
 
-/*
- * Called by the driver when there's room for more data.  If we have
- * more packets to send, we send them here.
- */
-static void slip_write_wakeup(struct tty_struct *tty)
+/* Write out any remaining transmit buffer. Scheduled when tty is writable */
+static void slip_transmit(struct work_struct *work)
 {
+	struct slip *sl = container_of(work, struct slip, tx_work);
 	int actual;
-	struct slip *sl = tty->disc_data;
 
+	spin_lock_bh(&sl->lock);
 	/* First make sure we're connected. */
-	if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev))
+	if (!sl->tty || sl->magic != SLIP_MAGIC || !netif_running(sl->dev)) {
+		spin_unlock_bh(&sl->lock);
 		return;
+	}
 
-	spin_lock(&sl->lock);
 	if (sl->xleft <= 0)  {
 		/* Now serial buffer is almost free & we can start
 		 * transmission of another packet */
 		sl->dev->stats.tx_packets++;
-		clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
-		spin_unlock(&sl->lock);
+		clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
+		spin_unlock_bh(&sl->lock);
 		sl_unlock(sl);
 		return;
 	}
 
-	actual = tty->ops->write(tty, sl->xhead, sl->xleft);
+	actual = sl->tty->ops->write(sl->tty, sl->xhead, sl->xleft);
 	sl->xleft -= actual;
 	sl->xhead += actual;
-	spin_unlock(&sl->lock);
+	spin_unlock_bh(&sl->lock);
+}
+
+/*
+ * Called by the driver when there's room for more data.
+ * Schedule the transmit.
+ */
+static void slip_write_wakeup(struct tty_struct *tty)
+{
+	struct slip *sl = tty->disc_data;
+
+	schedule_work(&sl->tx_work);
 }
 
 static void sl_tx_timeout(struct net_device *dev)
@@ -749,6 +760,7 @@ static struct slip *sl_alloc(dev_t line)
 	sl->magic       = SLIP_MAGIC;
 	sl->dev	      	= dev;
 	spin_lock_init(&sl->lock);
+	INIT_WORK(&sl->tx_work, slip_transmit);
 	sl->mode        = SL_MODE_DEFAULT;
 #ifdef CONFIG_SLIP_SMART
 	/* initialize timer_list struct */
@@ -872,8 +884,12 @@ static void slip_close(struct tty_struct *tty)
 	if (!sl || sl->magic != SLIP_MAGIC || sl->tty != tty)
 		return;
 
+	spin_lock_bh(&sl->lock);
 	tty->disc_data = NULL;
 	sl->tty = NULL;
+	spin_unlock_bh(&sl->lock);
+
+	flush_work(&sl->tx_work);
 
 	/* VSV = very important to remove timers */
 #ifdef CONFIG_SLIP_SMART
diff --git a/drivers/net/slip/slip.h b/drivers/net/slip/slip.h
index 67673cf1266b..cf32aadf508f 100644
--- a/drivers/net/slip/slip.h
+++ b/drivers/net/slip/slip.h
@@ -53,6 +53,7 @@ struct slip {
   struct tty_struct	*tty;		/* ptr to TTY structure		*/
   struct net_device	*dev;		/* easy for intr handling	*/
   spinlock_t		lock;
+  struct work_struct	tx_work;	/* Flushes transmit buffer	*/
 
 #ifdef SL_INCLUDE_CSLIP
   struct slcompress	*slcomp;	/* for header compression 	*/
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index c8624a8235ab..979fe433278c 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -647,7 +647,7 @@ static void team_notify_peers(struct team *team)
 {
 	if (!team->notify_peers.count || !netif_running(team->dev))
 		return;
-	atomic_set(&team->notify_peers.count_pending, team->notify_peers.count);
+	atomic_add(team->notify_peers.count, &team->notify_peers.count_pending);
 	schedule_delayed_work(&team->notify_peers.dw, 0);
 }
 
@@ -687,7 +687,7 @@ static void team_mcast_rejoin(struct team *team)
 {
 	if (!team->mcast_rejoin.count || !netif_running(team->dev))
 		return;
-	atomic_set(&team->mcast_rejoin.count_pending, team->mcast_rejoin.count);
+	atomic_add(team->mcast_rejoin.count, &team->mcast_rejoin.count_pending);
 	schedule_delayed_work(&team->mcast_rejoin.dw, 0);
 }
 
@@ -1732,6 +1732,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 	 * to traverse list in reverse under rcu_read_lock
 	 */
 	mutex_lock(&team->lock);
+	team->port_mtu_change_allowed = true;
 	list_for_each_entry(port, &team->port_list, list) {
 		err = dev_set_mtu(port->dev, new_mtu);
 		if (err) {
@@ -1740,6 +1741,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 			goto unwind;
 		}
 	}
+	team->port_mtu_change_allowed = false;
 	mutex_unlock(&team->lock);
 
 	dev->mtu = new_mtu;
@@ -1749,6 +1751,7 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		dev_set_mtu(port->dev, dev->mtu);
+	team->port_mtu_change_allowed = false;
 	mutex_unlock(&team->lock);
 
 	return err;
@@ -2857,7 +2860,9 @@ static int team_device_event(struct notifier_block *unused,
 		break;
 	case NETDEV_PRECHANGEMTU:
 		/* Forbid to change mtu of underlaying device */
-		return NOTIFY_BAD;
+		if (!port->team->port_mtu_change_allowed)
+			return NOTIFY_BAD;
+		break;
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid to change type of underlaying device */
 		return NOTIFY_BAD;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 26f8635b027d..ec63314d6480 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -65,6 +65,7 @@
 #include <linux/nsproxy.h>
 #include <linux/virtio_net.h>
 #include <linux/rcupdate.h>
+#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
@@ -1140,6 +1141,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		break;
 	}
 
+	skb_reset_network_header(skb);
+
 	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		pr_debug("GSO!\n");
 		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -1151,6 +1154,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+			if (skb->protocol == htons(ETH_P_IPV6))
+				ipv6_proxy_select_ident(skb);
 			break;
 		default:
 			tun->dev->stats.rx_frame_errors++;
@@ -1180,7 +1185,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
 	}
 
-	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb, 0);
 
 	rxhash = skb_get_hash(skb);
@@ -1222,6 +1226,10 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	struct tun_pi pi = { 0, skb->protocol };
 	ssize_t total = 0;
 	int vlan_offset = 0, copied;
+	int vlan_hlen = 0;
+
+	if (vlan_tx_tag_present(skb))
+		vlan_hlen = VLAN_HLEN;
 
 	if (!(tun->flags & TUN_NO_PI)) {
 		if ((len -= sizeof(pi)) < 0)
@@ -1273,7 +1281,8 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			gso.csum_start = skb_checksum_start_offset(skb);
+			gso.csum_start = skb_checksum_start_offset(skb) +
+					 vlan_hlen;
 			gso.csum_offset = skb->csum_offset;
 		} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 			gso.flags = VIRTIO_NET_HDR_F_DATA_VALID;
@@ -1286,10 +1295,9 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	}
 
 	copied = total;
-	total += skb->len;
-	if (!vlan_tx_tag_present(skb)) {
-		len = min_t(int, skb->len, len);
-	} else {
+	len = min_t(int, skb->len + vlan_hlen, len);
+	total += skb->len + vlan_hlen;
+	if (vlan_hlen) {
 		int copy, ret;
 		struct {
 			__be16 h_vlan_proto;
@@ -1300,8 +1308,6 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
 
 		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
-		len = min_t(int, skb->len + VLAN_HLEN, len);
-		total += VLAN_HLEN;
 
 		copy = min_t(int, vlan_offset, len);
 		ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 054e59ca6946..8cee173eefb2 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -696,6 +696,7 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p)
 {
 	struct usbnet *dev = netdev_priv(net);
 	struct sockaddr *addr = p;
+	int ret;
 
 	if (netif_running(net))
 		return -EBUSY;
@@ -705,8 +706,12 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p)
 	memcpy(net->dev_addr, addr->sa_data, ETH_ALEN);
 
 	/* Set the MAC address */
-	return ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN,
+	ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN,
 				 ETH_ALEN, net->dev_addr);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static const struct net_device_ops ax88179_netdev_ops = {
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index c9f3281506af..2e025ddcef21 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -120,6 +120,16 @@ static void cdc_mbim_unbind(struct usbnet *dev, struct usb_interface *intf)
 	cdc_ncm_unbind(dev, intf);
 }
 
+/* verify that the ethernet protocol is IPv4 or IPv6 */
+static bool is_ip_proto(__be16 proto)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+	case htons(ETH_P_IPV6):
+		return true;
+	}
+	return false;
+}
 
 static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
 {
@@ -128,6 +138,7 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 	struct cdc_ncm_ctx *ctx = info->ctx;
 	__le32 sign = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN);
 	u16 tci = 0;
+	bool is_ip;
 	u8 *c;
 
 	if (!ctx)
@@ -137,25 +148,32 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 		if (skb->len <= ETH_HLEN)
 			goto error;
 
+		/* Some applications using e.g. packet sockets will
+		 * bypass the VLAN acceleration and create tagged
+		 * ethernet frames directly.  We primarily look for
+		 * the accelerated out-of-band tag, but fall back if
+		 * required
+		 */
+		skb_reset_mac_header(skb);
+		if (vlan_get_tag(skb, &tci) < 0 && skb->len > VLAN_ETH_HLEN &&
+		    __vlan_get_tag(skb, &tci) == 0) {
+			is_ip = is_ip_proto(vlan_eth_hdr(skb)->h_vlan_encapsulated_proto);
+			skb_pull(skb, VLAN_ETH_HLEN);
+		} else {
+			is_ip = is_ip_proto(eth_hdr(skb)->h_proto);
+			skb_pull(skb, ETH_HLEN);
+		}
+
 		/* mapping VLANs to MBIM sessions:
 		 *   no tag     => IPS session <0>
 		 *   1 - 255    => IPS session <vlanid>
 		 *   256 - 511  => DSS session <vlanid - 256>
 		 *   512 - 4095 => unsupported, drop
 		 */
-		vlan_get_tag(skb, &tci);
-
 		switch (tci & 0x0f00) {
 		case 0x0000: /* VLAN ID 0 - 255 */
-			/* verify that datagram is IPv4 or IPv6 */
-			skb_reset_mac_header(skb);
-			switch (eth_hdr(skb)->h_proto) {
-			case htons(ETH_P_IP):
-			case htons(ETH_P_IPV6):
-				break;
-			default:
+			if (!is_ip)
 				goto error;
-			}
 			c = (u8 *)&sign;
 			c[3] = tci;
 			break;
@@ -169,7 +187,6 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 				  "unsupported tci=0x%04x\n", tci);
 			goto error;
 		}
-		skb_pull(skb, ETH_HLEN);
 	}
 
 	spin_lock_bh(&ctx->mtx);
@@ -204,17 +221,23 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci)
 		return;
 
 	/* need to send the NA on the VLAN dev, if any */
-	if (tci)
+	rcu_read_lock();
+	if (tci) {
 		netdev = __vlan_find_dev_deep(dev->net, htons(ETH_P_8021Q),
 					      tci);
-	else
+		if (!netdev) {
+			rcu_read_unlock();
+			return;
+		}
+	} else {
 		netdev = dev->net;
-	if (!netdev)
-		return;
+	}
+	dev_hold(netdev);
+	rcu_read_unlock();
 
 	in6_dev = in6_dev_get(netdev);
 	if (!in6_dev)
-		return;
+		goto out;
 	is_router = !!in6_dev->cnf.forwarding;
 	in6_dev_put(in6_dev);
 
@@ -224,6 +247,8 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci)
 				 true /* solicited */,
 				 false /* override */,
 				 true /* inc_opt */);
+out:
+	dev_put(netdev);
 }
 
 static bool is_neigh_solicit(u8 *buf, size_t len)
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index d350d2795e10..75d7d9dbbe35 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -768,7 +768,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	    skb_out->len > CDC_NCM_MIN_TX_PKT)
 		memset(skb_put(skb_out, ctx->tx_max - skb_out->len), 0,
 		       ctx->tx_max - skb_out->len);
-	else if ((skb_out->len % dev->maxpacket) == 0)
+	else if (skb_out->len < ctx->tx_max && (skb_out->len % dev->maxpacket) == 0)
 		*skb_put(skb_out, 1) = 0;	/* force short packet */
 
 	/* set final frame length */
diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c
index 312178d7b698..a01462523bc7 100644
--- a/drivers/net/usb/huawei_cdc_ncm.c
+++ b/drivers/net/usb/huawei_cdc_ncm.c
@@ -84,12 +84,13 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev,
 	ctx = drvstate->ctx;
 
 	if (usbnet_dev->status)
-		/* CDC-WMC r1.1 requires wMaxCommand to be "at least 256
-		 * decimal (0x100)"
+		/* The wMaxCommand buffer must be big enough to hold
+		 * any message from the modem. Experience has shown
+		 * that some replies are more than 256 bytes long
 		 */
 		subdriver = usb_cdc_wdm_register(ctx->control,
 						 &usbnet_dev->status->desc,
-						 256, /* wMaxCommand */
+						 1024, /* wMaxCommand */
 						 huawei_cdc_ncm_wdm_manage_power);
 	if (IS_ERR(subdriver)) {
 		ret = PTR_ERR(subdriver);
@@ -206,6 +207,9 @@ static const struct usb_device_id huawei_cdc_ncm_devs[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x76),
 	  .driver_info = (unsigned long)&huawei_cdc_ncm_info,
 	},
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x03, 0x16),
+	  .driver_info = (unsigned long)&huawei_cdc_ncm_info,
+	},
 
 	/* Terminating entry */
 	{
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 313cb6cd4848..db21af8de9f6 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -660,8 +660,25 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
 	{QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
+	{QMI_FIXED_INTF(0x0846, 0x68a2, 8)},
 	{QMI_FIXED_INTF(0x12d1, 0x140c, 1)},	/* Huawei E173 */
 	{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)},	/* Huawei E1820 */
+	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
+	{QMI_FIXED_INTF(0x16d8, 0x6007, 0)},	/* CMOTech CHE-628S */
+	{QMI_FIXED_INTF(0x16d8, 0x6008, 0)},	/* CMOTech CMU-301 */
+	{QMI_FIXED_INTF(0x16d8, 0x6280, 0)},	/* CMOTech CHU-628 */
+	{QMI_FIXED_INTF(0x16d8, 0x7001, 0)},	/* CMOTech CHU-720S */
+	{QMI_FIXED_INTF(0x16d8, 0x7002, 0)},	/* CMOTech 7002 */
+	{QMI_FIXED_INTF(0x16d8, 0x7003, 4)},	/* CMOTech CHU-629K */
+	{QMI_FIXED_INTF(0x16d8, 0x7004, 3)},	/* CMOTech 7004 */
+	{QMI_FIXED_INTF(0x16d8, 0x7006, 5)},	/* CMOTech CGU-629 */
+	{QMI_FIXED_INTF(0x16d8, 0x700a, 4)},	/* CMOTech CHU-629S */
+	{QMI_FIXED_INTF(0x16d8, 0x7211, 0)},	/* CMOTech CHU-720I */
+	{QMI_FIXED_INTF(0x16d8, 0x7212, 0)},	/* CMOTech 7212 */
+	{QMI_FIXED_INTF(0x16d8, 0x7213, 0)},	/* CMOTech 7213 */
+	{QMI_FIXED_INTF(0x16d8, 0x7251, 1)},	/* CMOTech 7251 */
+	{QMI_FIXED_INTF(0x16d8, 0x7252, 1)},	/* CMOTech 7252 */
+	{QMI_FIXED_INTF(0x16d8, 0x7253, 1)},	/* CMOTech 7253 */
 	{QMI_FIXED_INTF(0x19d2, 0x0002, 1)},
 	{QMI_FIXED_INTF(0x19d2, 0x0012, 1)},
 	{QMI_FIXED_INTF(0x19d2, 0x0017, 3)},
@@ -718,21 +735,41 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1424, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1425, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
+	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 19)},	/* Sierra Wireless MC7710 in QMI mode */
+	{QMI_FIXED_INTF(0x1199, 0x68c0, 8)},	/* Sierra Wireless MC73xx */
+	{QMI_FIXED_INTF(0x1199, 0x68c0, 10)},	/* Sierra Wireless MC73xx */
+	{QMI_FIXED_INTF(0x1199, 0x68c0, 11)},	/* Sierra Wireless MC73xx */
 	{QMI_FIXED_INTF(0x1199, 0x901c, 8)},    /* Sierra Wireless EM7700 */
+	{QMI_FIXED_INTF(0x1199, 0x901f, 8)},    /* Sierra Wireless EM7355 */
+	{QMI_FIXED_INTF(0x1199, 0x9041, 8)},	/* Sierra Wireless MC7305/MC7355 */
 	{QMI_FIXED_INTF(0x1199, 0x9051, 8)},	/* Netgear AirCard 340U */
+	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
+	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
-	{QMI_FIXED_INTF(0x0b3c, 0xc005, 6)},    /* Olivetti Olicard 200 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc004, 6)},	/* Olivetti Olicard 155 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc005, 6)},	/* Olivetti Olicard 200 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)},	/* Olivetti Olicard 160 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)},	/* Olivetti Olicard 500 */
 	{QMI_FIXED_INTF(0x1e2d, 0x0060, 4)},	/* Cinterion PLxx */
 	{QMI_FIXED_INTF(0x1e2d, 0x0053, 4)},	/* Cinterion PHxx,PXxx */
+	{QMI_FIXED_INTF(0x413c, 0x81a2, 8)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a3, 8)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a8, 8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x03f0, 0x581d, 4)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 
 	/* 4. Gobi 1000 devices */
 	{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)},	/* Acer Gobi Modem Device */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 1236812c7be6..5988910db23e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -279,13 +279,15 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
 	return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
 }
 
-/* Find VXLAN socket based on network namespace and UDP port */
-static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port)
+/* Find VXLAN socket based on network namespace, address family and UDP port */
+static struct vxlan_sock *vxlan_find_sock(struct net *net,
+					  sa_family_t family, __be16 port)
 {
 	struct vxlan_sock *vs;
 
 	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
-		if (inet_sk(vs->sock->sk)->inet_sport == port)
+		if (inet_sk(vs->sock->sk)->inet_sport == port &&
+		    inet_sk(vs->sock->sk)->sk.sk_family == family)
 			return vs;
 	}
 	return NULL;
@@ -304,11 +306,12 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id)
 }
 
 /* Look up VNI in a per net namespace table */
-static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id, __be16 port)
+static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id,
+					sa_family_t family, __be16 port)
 {
 	struct vxlan_sock *vs;
 
-	vs = vxlan_find_sock(net, port);
+	vs = vxlan_find_sock(net, family, port);
 	if (!vs)
 		return NULL;
 
@@ -871,6 +874,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
+		return -EAFNOSUPPORT;
+
 	spin_lock_bh(&vxlan->hash_lock);
 	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, vni, ifindex, ndm->ndm_flags);
@@ -1331,7 +1337,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
 	} else if (vxlan->flags & VXLAN_F_L3MISS) {
 		union vxlan_addr ipa = {
 			.sin.sin_addr.s_addr = tip,
-			.sa.sa_family = AF_INET,
+			.sin.sin_family = AF_INET,
 		};
 
 		vxlan_ip_miss(dev, &ipa);
@@ -1444,9 +1450,6 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 	if (!in6_dev)
 		goto out;
 
-	if (!pskb_may_pull(skb, skb->len))
-		goto out;
-
 	iphdr = ipv6_hdr(skb);
 	saddr = &iphdr->saddr;
 	daddr = &iphdr->daddr;
@@ -1492,7 +1495,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
 	} else if (vxlan->flags & VXLAN_F_L3MISS) {
 		union vxlan_addr ipa = {
 			.sin6.sin6_addr = msg->target,
-			.sa.sa_family = AF_INET6,
+			.sin6.sin6_family = AF_INET6,
 		};
 
 		vxlan_ip_miss(dev, &ipa);
@@ -1525,7 +1528,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 		if (!n && (vxlan->flags & VXLAN_F_L3MISS)) {
 			union vxlan_addr ipa = {
 				.sin.sin_addr.s_addr = pip->daddr,
-				.sa.sa_family = AF_INET,
+				.sin.sin_family = AF_INET,
 			};
 
 			vxlan_ip_miss(dev, &ipa);
@@ -1546,7 +1549,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 		if (!n && (vxlan->flags & VXLAN_F_L3MISS)) {
 			union vxlan_addr ipa = {
 				.sin6.sin6_addr = pip6->daddr,
-				.sa.sa_family = AF_INET6,
+				.sin6.sin6_family = AF_INET6,
 			};
 
 			vxlan_ip_miss(dev, &ipa);
@@ -1767,6 +1770,8 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 	struct pcpu_sw_netstats *tx_stats, *rx_stats;
 	union vxlan_addr loopback;
 	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
+	struct net_device *dev = skb->dev;
+	int len = skb->len;
 
 	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
 	rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
@@ -1790,16 +1795,16 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
 
 	u64_stats_update_begin(&tx_stats->syncp);
 	tx_stats->tx_packets++;
-	tx_stats->tx_bytes += skb->len;
+	tx_stats->tx_bytes += len;
 	u64_stats_update_end(&tx_stats->syncp);
 
 	if (netif_rx(skb) == NET_RX_SUCCESS) {
 		u64_stats_update_begin(&rx_stats->syncp);
 		rx_stats->rx_packets++;
-		rx_stats->rx_bytes += skb->len;
+		rx_stats->rx_bytes += len;
 		u64_stats_update_end(&rx_stats->syncp);
 	} else {
-		skb->dev->stats.rx_dropped++;
+		dev->stats.rx_dropped++;
 	}
 }
 
@@ -1870,7 +1875,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			struct vxlan_dev *dst_vxlan;
 
 			ip_rt_put(rt);
-			dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+			dst_vxlan = vxlan_find_vni(dev_net(dev), vni,
+						   dst->sa.sa_family, dst_port);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1923,7 +1929,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			struct vxlan_dev *dst_vxlan;
 
 			dst_release(ndst);
-			dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+			dst_vxlan = vxlan_find_vni(dev_net(dev), vni,
+						   dst->sa.sa_family, dst_port);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1974,7 +1981,8 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 			return arp_reduce(dev, skb);
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
-			 skb->len >= sizeof(struct ipv6hdr) + sizeof(struct nd_msg) &&
+			 pskb_may_pull(skb, sizeof(struct ipv6hdr)
+				       + sizeof(struct nd_msg)) &&
 			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
 				struct nd_msg *msg;
 
@@ -1983,6 +1991,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 				    msg->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
 					return neigh_reduce(dev, skb);
 		}
+		eth = eth_hdr(skb);
 #endif
 	}
 
@@ -2079,6 +2088,7 @@ static int vxlan_init(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+	bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
 	struct vxlan_sock *vs;
 	int i;
 
@@ -2094,10 +2104,10 @@ static int vxlan_init(struct net_device *dev)
 
 
 	spin_lock(&vn->sock_lock);
-	vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port);
-	if (vs) {
+	vs = vxlan_find_sock(dev_net(dev), ipv6 ? AF_INET6 : AF_INET,
+			     vxlan->dst_port);
+	if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) {
 		/* If we have a socket with same port already, reuse it */
-		atomic_inc(&vs->refcnt);
 		vxlan_vs_add_dev(vs, vxlan);
 	} else {
 		/* otherwise make new socket outside of RTNL */
@@ -2279,9 +2289,9 @@ static void vxlan_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
 	if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
-		dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
 	else
-		dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = free_netdev;
@@ -2562,13 +2572,10 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 		return vs;
 
 	spin_lock(&vn->sock_lock);
-	vs = vxlan_find_sock(net, port);
-	if (vs) {
-		if (vs->rcv == rcv)
-			atomic_inc(&vs->refcnt);
-		else
+	vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
+	if (vs && ((vs->rcv != rcv) ||
+		   !atomic_add_unless(&vs->refcnt, 1, 0)))
 			vs = ERR_PTR(-EBUSY);
-	}
 	spin_unlock(&vn->sock_lock);
 
 	if (!vs)
@@ -2612,9 +2619,10 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
 	dst->remote_vni = vni;
 
+	/* Unless IPv6 is explicitly requested, assume IPv4 */
+	dst->remote_ip.sa.sa_family = AF_INET;
 	if (data[IFLA_VXLAN_GROUP]) {
 		dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
-		dst->remote_ip.sa.sa_family = AF_INET;
 	} else if (data[IFLA_VXLAN_GROUP6]) {
 		if (!IS_ENABLED(CONFIG_IPV6))
 			return -EPFNOSUPPORT;
@@ -2663,8 +2671,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 		if (!tb[IFLA_MTU])
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
-		/* update header length based on lower device */
-		dev->hard_header_len = lowerdev->hard_header_len +
+		dev->needed_headroom = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 	} else if (use_ipv6)
 		vxlan->flags |= VXLAN_F_IPV6;
@@ -2708,7 +2715,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	if (data[IFLA_VXLAN_PORT])
 		vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
 
-	if (vxlan_find_vni(net, vni, vxlan->dst_port)) {
+	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
+			   vxlan->dst_port)) {
 		pr_info("duplicate VNI %u\n", vni);
 		return -EEXIST;
 	}
diff --git a/drivers/net/wireless/ath/ath5k/qcu.c b/drivers/net/wireless/ath/ath5k/qcu.c
index 0583c69d26db..ddaad712c59a 100644
--- a/drivers/net/wireless/ath/ath5k/qcu.c
+++ b/drivers/net/wireless/ath/ath5k/qcu.c
@@ -225,13 +225,7 @@ ath5k_hw_setup_tx_queue(struct ath5k_hw *ah, enum ath5k_tx_queue queue_type,
 	} else {
 		switch (queue_type) {
 		case AR5K_TX_QUEUE_DATA:
-			for (queue = AR5K_TX_QUEUE_ID_DATA_MIN;
-				ah->ah_txq[queue].tqi_type !=
-				AR5K_TX_QUEUE_INACTIVE; queue++) {
-
-				if (queue > AR5K_TX_QUEUE_ID_DATA_MAX)
-					return -EINVAL;
-			}
+			queue = queue_info->tqi_subtype;
 			break;
 		case AR5K_TX_QUEUE_UAPSD:
 			queue = AR5K_TX_QUEUE_ID_UAPSD;
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index 09facba1dc6d..390c2de5a73e 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -647,6 +647,19 @@ static void ar9003_hw_override_ini(struct ath_hw *ah)
 		ah->enabled_cals |= TX_CL_CAL;
 	else
 		ah->enabled_cals &= ~TX_CL_CAL;
+
+	if (AR_SREV_9340(ah) || AR_SREV_9531(ah) || AR_SREV_9550(ah)) {
+		if (ah->is_clk_25mhz) {
+			REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x17c << 1);
+			REG_WRITE(ah, AR_SLP32_MODE, 0x0010f3d7);
+			REG_WRITE(ah, AR_SLP32_INC, 0x0001e7ae);
+		} else {
+			REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x261 << 1);
+			REG_WRITE(ah, AR_SLP32_MODE, 0x0010f400);
+			REG_WRITE(ah, AR_SLP32_INC, 0x0001e800);
+		}
+		udelay(100);
+	}
 }
 
 static void ar9003_hw_prog_ini(struct ath_hw *ah,
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 9078a6c5a74e..dcc14940c9df 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -858,19 +858,6 @@ static void ath9k_hw_init_pll(struct ath_hw *ah,
 	udelay(RTC_PLL_SETTLE_DELAY);
 
 	REG_WRITE(ah, AR_RTC_SLEEP_CLK, AR_RTC_FORCE_DERIVED_CLK);
-
-	if (AR_SREV_9340(ah) || AR_SREV_9550(ah)) {
-		if (ah->is_clk_25mhz) {
-			REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x17c << 1);
-			REG_WRITE(ah, AR_SLP32_MODE, 0x0010f3d7);
-			REG_WRITE(ah,  AR_SLP32_INC, 0x0001e7ae);
-		} else {
-			REG_WRITE(ah, AR_RTC_DERIVED_CLK, 0x261 << 1);
-			REG_WRITE(ah, AR_SLP32_MODE, 0x0010f400);
-			REG_WRITE(ah,  AR_SLP32_INC, 0x0001e800);
-		}
-		udelay(100);
-	}
 }
 
 static void ath9k_hw_init_interrupt_masks(struct ath_hw *ah,
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 0acd4b5a4892..32ae0a47fed0 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -216,8 +216,8 @@
 #define AH_WOW_BEACON_MISS		BIT(3)
 
 enum ath_hw_txq_subtype {
-	ATH_TXQ_AC_BE = 0,
-	ATH_TXQ_AC_BK = 1,
+	ATH_TXQ_AC_BK = 0,
+	ATH_TXQ_AC_BE = 1,
 	ATH_TXQ_AC_VI = 2,
 	ATH_TXQ_AC_VO = 3,
 };
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index 5f727588ca27..8f93ed373fb5 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -311,14 +311,7 @@ int ath9k_hw_setuptxqueue(struct ath_hw *ah, enum ath9k_tx_queue type,
 		q = ATH9K_NUM_TX_QUEUES - 3;
 		break;
 	case ATH9K_TX_QUEUE_DATA:
-		for (q = 0; q < ATH9K_NUM_TX_QUEUES; q++)
-			if (ah->txq[q].tqi_type ==
-			    ATH9K_TX_QUEUE_INACTIVE)
-				break;
-		if (q == ATH9K_NUM_TX_QUEUES) {
-			ath_err(common, "No available TX queue\n");
-			return -1;
-		}
+		q = qinfo->tqi_subtype;
 		break;
 	default:
 		ath_err(common, "Invalid TX queue type: %u\n", type);
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 55897d508a76..0fe7674ad100 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -890,6 +890,15 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 
 		tx_info = IEEE80211_SKB_CB(skb);
 		tx_info->flags &= ~IEEE80211_TX_CTL_CLEAR_PS_FILT;
+
+		/*
+		 * No aggregation session is running, but there may be frames
+		 * from a previous session or a failed attempt in the queue.
+		 * Send them out as normal data frames
+		 */
+		if (!tid->active)
+			tx_info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+
 		if (!(tx_info->flags & IEEE80211_TX_CTL_AMPDU)) {
 			bf->bf_state.bf_type = 0;
 			return bf;
@@ -1698,7 +1707,7 @@ int ath_cabq_update(struct ath_softc *sc)
 
 	ath9k_hw_get_txq_props(sc->sc_ah, qnum, &qi);
 
-	qi.tqi_readyTime = (cur_conf->beacon_interval *
+	qi.tqi_readyTime = (TU_TO_USEC(cur_conf->beacon_interval) *
 			    ATH_CABQ_READY_TIME) / 100;
 	ath_txq_update(sc, qnum, &qi);
 
diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h
index 8596aba34f96..237d0cda1bcb 100644
--- a/drivers/net/wireless/ath/carl9170/carl9170.h
+++ b/drivers/net/wireless/ath/carl9170/carl9170.h
@@ -256,6 +256,7 @@ struct ar9170 {
 	atomic_t rx_work_urbs;
 	atomic_t rx_pool_urbs;
 	kernel_ulong_t features;
+	bool usb_ep_cmd_is_bulk;
 
 	/* firmware settings */
 	struct completion fw_load_wait;
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index ca115f33746f..bc931f6f1f0f 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -621,9 +621,16 @@ int __carl9170_exec_cmd(struct ar9170 *ar, struct carl9170_cmd *cmd,
 		goto err_free;
 	}
 
-	usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev,
-		AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4,
-		carl9170_usb_cmd_complete, ar, 1);
+	if (ar->usb_ep_cmd_is_bulk)
+		usb_fill_bulk_urb(urb, ar->udev,
+				  usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD),
+				  cmd, cmd->hdr.len + 4,
+				  carl9170_usb_cmd_complete, ar);
+	else
+		usb_fill_int_urb(urb, ar->udev,
+				 usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD),
+				 cmd, cmd->hdr.len + 4,
+				 carl9170_usb_cmd_complete, ar, 1);
 
 	if (free_buf)
 		urb->transfer_flags |= URB_FREE_BUFFER;
@@ -1032,9 +1039,10 @@ static void carl9170_usb_firmware_step2(const struct firmware *fw,
 static int carl9170_usb_probe(struct usb_interface *intf,
 			      const struct usb_device_id *id)
 {
+	struct usb_endpoint_descriptor *ep;
 	struct ar9170 *ar;
 	struct usb_device *udev;
-	int err;
+	int i, err;
 
 	err = usb_reset_device(interface_to_usbdev(intf));
 	if (err)
@@ -1050,6 +1058,21 @@ static int carl9170_usb_probe(struct usb_interface *intf,
 	ar->intf = intf;
 	ar->features = id->driver_info;
 
+	/* We need to remember the type of endpoint 4 because it differs
+	 * between high- and full-speed configuration. The high-speed
+	 * configuration specifies it as interrupt and the full-speed
+	 * configuration as bulk endpoint. This information is required
+	 * later when sending urbs to that endpoint.
+	 */
+	for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) {
+		ep = &intf->cur_altsetting->endpoint[i].desc;
+
+		if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD &&
+		    usb_endpoint_dir_out(ep) &&
+		    usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK)
+			ar->usb_ep_cmd_is_bulk = true;
+	}
+
 	usb_set_intfdata(intf, ar);
 	SET_IEEE80211_DEV(ar->hw, &intf->dev);
 
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 05ee7f10cc8f..24ccbe96e0c8 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -5176,22 +5176,22 @@ static void b43_nphy_channel_setup(struct b43_wldev *dev,
 	int ch = new_channel->hw_value;
 
 	u16 old_band_5ghz;
-	u32 tmp32;
+	u16 tmp16;
 
 	old_band_5ghz =
 		b43_phy_read(dev, B43_NPHY_BANDCTL) & B43_NPHY_BANDCTL_5GHZ;
 	if (new_channel->band == IEEE80211_BAND_5GHZ && !old_band_5ghz) {
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_set(dev, B43_PHY_B_BBCFG, 0xC000);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 		b43_phy_set(dev, B43_NPHY_BANDCTL, B43_NPHY_BANDCTL_5GHZ);
 	} else if (new_channel->band == IEEE80211_BAND_2GHZ && old_band_5ghz) {
 		b43_phy_mask(dev, B43_NPHY_BANDCTL, ~B43_NPHY_BANDCTL_5GHZ);
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_mask(dev, B43_PHY_B_BBCFG, 0x3FFF);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 	}
 
 	b43_chantab_phy_upload(dev, e);
diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c
index 50e5ddb12fb3..628ff628e04a 100644
--- a/drivers/net/wireless/b43/xmit.c
+++ b/drivers/net/wireless/b43/xmit.c
@@ -810,9 +810,13 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		break;
 	case B43_PHYTYPE_G:
 		status.band = IEEE80211_BAND_2GHZ;
-		/* chanid is the radio channel cookie value as used
-		 * to tune the radio. */
-		status.freq = chanid + 2400;
+		/* Somewhere between 478.104 and 508.1084 firmware for G-PHY
+		 * has been modified to be compatible with N-PHY and others.
+		 */
+		if (dev->fw.rev >= 508)
+			status.freq = ieee80211_channel_to_frequency(chanid, status.band);
+		else
+			status.freq = chanid + 2400;
 		break;
 	case B43_PHYTYPE_N:
 	case B43_PHYTYPE_LP:
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c
index fad77dd2a3a5..3f9cb894d001 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.c
@@ -185,7 +185,13 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr,
 		  ifevent->action, ifevent->ifidx, ifevent->bssidx,
 		  ifevent->flags, ifevent->role);
 
-	if (ifevent->flags & BRCMF_E_IF_FLAG_NOIF) {
+	/* The P2P Device interface event must not be ignored
+	 * contrary to what firmware tells us. The only way to
+	 * distinguish the P2P Device is by looking at the ifidx
+	 * and bssidx received.
+	 */
+	if (!(ifevent->ifidx == 0 && ifevent->bssidx == 1) &&
+	    (ifevent->flags & BRCMF_E_IF_FLAG_NOIF)) {
 		brcmf_dbg(EVENT, "event can be ignored\n");
 		return;
 	}
@@ -210,12 +216,12 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr,
 				return;
 	}
 
-	if (ifevent->action == BRCMF_E_IF_CHANGE)
+	if (ifp && ifevent->action == BRCMF_E_IF_CHANGE)
 		brcmf_fws_reset_interface(ifp);
 
 	err = brcmf_fweh_call_event_handler(ifp, emsg->event_code, emsg, data);
 
-	if (ifevent->action == BRCMF_E_IF_DEL) {
+	if (ifp && ifevent->action == BRCMF_E_IF_DEL) {
 		brcmf_fws_del_interface(ifp);
 		brcmf_del_if(drvr, ifevent->bssidx);
 	}
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h
index 51b53a73d074..d26b47698f68 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/fweh.h
+++ b/drivers/net/wireless/brcm80211/brcmfmac/fweh.h
@@ -167,6 +167,8 @@ enum brcmf_fweh_event_code {
 #define BRCMF_E_IF_ROLE_STA			0
 #define BRCMF_E_IF_ROLE_AP			1
 #define BRCMF_E_IF_ROLE_WDS			2
+#define BRCMF_E_IF_ROLE_P2P_GO			3
+#define BRCMF_E_IF_ROLE_P2P_CLIENT		4
 
 /**
  * definitions for event packet validation.
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c
index 82bf3c5d3cdc..2de2736eb332 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/sdio_chip.c
@@ -300,10 +300,10 @@ brcmf_sdio_ai_coredisable(struct brcmf_sdio_dev *sdiodev,
 
 	wrapbase = ci->c_inf[idx].wrapbase;
 
-	/* if core is already in reset, just return */
+	/* if core is already in reset, skip reset */
 	regdata = brcmf_sdiod_regrl(sdiodev, wrapbase + BCMA_RESET_CTL, NULL);
 	if ((regdata & BCMA_RESET_CTL_RESET) != 0)
-		return;
+		goto post_reset_config;
 
 	/* configure reset */
 	brcmf_sdiod_regwl(sdiodev, wrapbase + BCMA_IOCTL, pre_resetbits |
@@ -319,6 +319,7 @@ brcmf_sdio_ai_coredisable(struct brcmf_sdio_dev *sdiodev,
 	SPINWAIT(brcmf_sdiod_regrl(sdiodev, wrapbase + BCMA_RESET_CTL, NULL) !=
 		 BCMA_RESET_CTL_RESET, 300);
 
+post_reset_config:
 	/* post reset configure */
 	brcmf_sdiod_regwl(sdiodev, wrapbase + BCMA_IOCTL, pre_resetbits |
 			  BCMA_IOCTL_FGC | BCMA_IOCTL_CLK, NULL);
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index 925034b80e9c..93598cd7ee6a 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -426,6 +426,12 @@ static int brcms_ops_start(struct ieee80211_hw *hw)
 	bool blocked;
 	int err;
 
+	if (!wl->ucode.bcm43xx_bomminor) {
+		err = brcms_request_fw(wl, wl->wlc->hw->d11core);
+		if (err)
+			return -ENOENT;
+	}
+
 	ieee80211_wake_queues(hw);
 	spin_lock_bh(&wl->lock);
 	blocked = brcms_rfkill_set_hw_state(wl);
@@ -433,14 +439,6 @@ static int brcms_ops_start(struct ieee80211_hw *hw)
 	if (!blocked)
 		wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy);
 
-	if (!wl->ucode.bcm43xx_bomminor) {
-		err = brcms_request_fw(wl, wl->wlc->hw->d11core);
-		if (err) {
-			brcms_remove(wl->wlc->hw->d11core);
-			return -ENOENT;
-		}
-	}
-
 	spin_lock_bh(&wl->lock);
 	/* avoid acknowledging frames before a non-monitor device is added */
 	wl->mute_tx = true;
diff --git a/drivers/net/wireless/iwlwifi/dvm/main.c b/drivers/net/wireless/iwlwifi/dvm/main.c
index ba1b1ea54252..ea7e70cb34f0 100644
--- a/drivers/net/wireless/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/iwlwifi/dvm/main.c
@@ -252,13 +252,17 @@ static void iwl_bg_bt_runtime_config(struct work_struct *work)
 	struct iwl_priv *priv =
 		container_of(work, struct iwl_priv, bt_runtime_config);
 
+	mutex_lock(&priv->mutex);
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status))
-		return;
+		goto out;
 
 	/* dont send host command if rf-kill is on */
 	if (!iwl_is_ready_rf(priv))
-		return;
+		goto out;
+
 	iwlagn_send_advance_bt_config(priv);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static void iwl_bg_bt_full_concurrency(struct work_struct *work)
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index 2a59da2ff87a..e1d546665ae8 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -67,8 +67,8 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL7260_UCODE_API_MAX	8
-#define IWL3160_UCODE_API_MAX	8
+#define IWL7260_UCODE_API_MAX	9
+#define IWL3160_UCODE_API_MAX	9
 
 /* Oldest version we won't warn about */
 #define IWL7260_UCODE_API_OK	7
@@ -223,3 +223,4 @@ const struct iwl_cfg iwl7265_n_cfg = {
 
 MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
 MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL3160_UCODE_API_OK));
+MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h
index 1ced525157dc..b45d78f53f08 100644
--- a/drivers/net/wireless/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/iwlwifi/iwl-config.h
@@ -119,6 +119,8 @@ enum iwl_led_mode {
 #define IWL_LONG_WD_TIMEOUT	10000
 #define IWL_MAX_WD_TIMEOUT	120000
 
+#define IWL_DEFAULT_MAX_TX_POWER 22
+
 /* Antenna presence definitions */
 #define	ANT_NONE	0x0
 #define	ANT_A		BIT(0)
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index 725e954d8475..3c3eb7842c62 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -118,8 +118,6 @@ static const u8 iwl_nvm_channels[] = {
 #define LAST_2GHZ_HT_PLUS	9
 #define LAST_5GHZ_HT		161
 
-#define DEFAULT_MAX_TX_POWER 16
-
 /* rate data (static) */
 static struct ieee80211_rate iwl_cfg80211_rates[] = {
 	{ .bitrate = 1 * 10, .hw_value = 0, .hw_value_short = 0, },
@@ -242,7 +240,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 		 * Default value - highest tx power value.  max_power
 		 * is not used in mvm, and is used for backwards compatibility
 		 */
-		channel->max_power = DEFAULT_MAX_TX_POWER;
+		channel->max_power = IWL_DEFAULT_MAX_TX_POWER;
 		is_5ghz = channel->band == IEEE80211_BAND_5GHZ;
 		IWL_DEBUG_EEPROM(dev,
 				 "Ch. %d [%sGHz] %s%s%s%s%s%s(0x%02x %ddBm): Ad-Hoc %ssupported\n",
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h
index 1f065cf4a4ba..d090ed79ada0 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/iwlwifi/iwl-trans.h
@@ -514,6 +514,7 @@ enum iwl_trans_state {
  *	Set during transport allocation.
  * @hw_id_str: a string with info about HW ID. Set during transport allocation.
  * @pm_support: set to true in start_hw if link pm is supported
+ * @ltr_enabled: set to true if the LTR is enabled
  * @dev_cmd_pool: pool for Tx cmd allocation - for internal use only.
  *	The user should use iwl_trans_{alloc,free}_tx_cmd.
  * @dev_cmd_headroom: room needed for the transport's private use before the
@@ -539,6 +540,7 @@ struct iwl_trans {
 	u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size;
 
 	bool pm_support;
+	bool ltr_enabled;
 
 	/* The following fields are internal only */
 	struct kmem_cache *dev_cmd_pool;
diff --git a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
index 18a895a949d4..6b22681068a7 100644
--- a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
@@ -188,7 +188,7 @@ static const __le32 iwl_combined_lookup[BT_COEX_MAX_LUT][BT_COEX_LUT_SIZE] = {
 		cpu_to_le32(0xcc00aaaa),
 		cpu_to_le32(0x0000aaaa),
 		cpu_to_le32(0xc0004000),
-		cpu_to_le32(0x00000000),
+		cpu_to_le32(0x00004000),
 		cpu_to_le32(0xf0005000),
 		cpu_to_le32(0xf0005000),
 	},
@@ -211,16 +211,16 @@ static const __le32 iwl_combined_lookup[BT_COEX_MAX_LUT][BT_COEX_LUT_SIZE] = {
 		/* Tx Tx disabled */
 		cpu_to_le32(0xaaaaaaaa),
 		cpu_to_le32(0xaaaaaaaa),
-		cpu_to_le32(0xaaaaaaaa),
+		cpu_to_le32(0xeeaaaaaa),
 		cpu_to_le32(0xaaaaaaaa),
 		cpu_to_le32(0xcc00ff28),
 		cpu_to_le32(0x0000aaaa),
 		cpu_to_le32(0xcc00aaaa),
 		cpu_to_le32(0x0000aaaa),
-		cpu_to_le32(0xC0004000),
-		cpu_to_le32(0xC0004000),
-		cpu_to_le32(0xF0005000),
-		cpu_to_le32(0xF0005000),
+		cpu_to_le32(0xc0004000),
+		cpu_to_le32(0xc0004000),
+		cpu_to_le32(0xf0005000),
+		cpu_to_le32(0xf0005000),
 	},
 };
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
index 884c08725308..fa66471283d9 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
@@ -66,13 +66,46 @@
 
 /* Power Management Commands, Responses, Notifications */
 
+/**
+ * enum iwl_ltr_config_flags - masks for LTR config command flags
+ * @LTR_CFG_FLAG_FEATURE_ENABLE: Feature operational status
+ * @LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS: allow LTR change on shadow
+ *	memory access
+ * @LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH: allow LTR msg send on ANY LTR
+ *	reg change
+ * @LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3: allow LTR msg send on transition from
+ *	D0 to D3
+ * @LTR_CFG_FLAG_SW_SET_SHORT: fixed static short LTR register
+ * @LTR_CFG_FLAG_SW_SET_LONG: fixed static short LONG register
+ * @LTR_CFG_FLAG_DENIE_C10_ON_PD: allow going into C10 on PD
+ */
+enum iwl_ltr_config_flags {
+	LTR_CFG_FLAG_FEATURE_ENABLE = BIT(0),
+	LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS = BIT(1),
+	LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH = BIT(2),
+	LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3 = BIT(3),
+	LTR_CFG_FLAG_SW_SET_SHORT = BIT(4),
+	LTR_CFG_FLAG_SW_SET_LONG = BIT(5),
+	LTR_CFG_FLAG_DENIE_C10_ON_PD = BIT(6),
+};
+
+/**
+ * struct iwl_ltr_config_cmd - configures the LTR
+ * @flags: See %enum iwl_ltr_config_flags
+ */
+struct iwl_ltr_config_cmd {
+	__le32 flags;
+	__le32 static_long;
+	__le32 static_short;
+} __packed;
+
 /* Radio LP RX Energy Threshold measured in dBm */
 #define POWER_LPRX_RSSI_THRESHOLD	75
 #define POWER_LPRX_RSSI_THRESHOLD_MAX	94
 #define POWER_LPRX_RSSI_THRESHOLD_MIN	30
 
 /**
- * enum iwl_scan_flags - masks for power table command flags
+ * enum iwl_power_flags - masks for power table command flags
  * @POWER_FLAGS_POWER_SAVE_ENA_MSK: '1' Allow to save power by turning off
  *		receiver and transmitter. '0' - does not allow.
  * @POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK: '0' Driver disables power management,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
index 989d7dbdca6c..60dc387cc554 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
@@ -142,6 +142,7 @@ enum {
 	/* Power - legacy power table command */
 	POWER_TABLE_CMD = 0x77,
 	PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION = 0x78,
+	LTR_CONFIG = 0xee,
 
 	/* Thermal Throttling*/
 	REPLY_THERMAL_MNG_BACKOFF = 0x7e,
@@ -1393,7 +1394,7 @@ enum iwl_sf_scenario {
 #define SF_NUM_TIMEOUT_TYPES 2		/* Aging timer and Idle timer */
 
 /* smart FIFO default values */
-#define SF_W_MARK_SISO 4096
+#define SF_W_MARK_SISO 6144
 #define SF_W_MARK_MIMO2 8192
 #define SF_W_MARK_MIMO3 6144
 #define SF_W_MARK_LEGACY 4096
@@ -1415,14 +1416,14 @@ enum iwl_sf_scenario {
 
 /**
  * Smart Fifo configuration command.
- * @state: smart fifo state, types listed in iwl_sf_sate.
+ * @state: smart fifo state, types listed in enum %iwl_sf_sate.
  * @watermark: Minimum allowed availabe free space in RXF for transient state.
  * @long_delay_timeouts: aging and idle timer values for each scenario
  * in long delay state.
  * @full_on_timeouts: timer values for each scenario in full on state.
  */
 struct iwl_sf_cfg_cmd {
-	enum iwl_sf_state state;
+	__le32 state;
 	__le32 watermark[SF_TRANSIENT_STATES_NUMBER];
 	__le32 long_delay_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES];
 	__le32 full_on_timeouts[SF_NUM_SCENARIO][SF_NUM_TIMEOUT_TYPES];
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c
index c03d39541f9e..2ef344fc0acb 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/iwlwifi/mvm/fw.c
@@ -439,6 +439,15 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 			goto error;
 	}
 
+	if (mvm->trans->ltr_enabled) {
+		struct iwl_ltr_config_cmd cmd = {
+			.flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE),
+		};
+
+		WARN_ON(iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0,
+					     sizeof(cmd), &cmd));
+	}
+
 	ret = iwl_mvm_power_update_device_mode(mvm);
 	if (ret)
 		goto error;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
index ba723d50939a..820797af7abf 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
@@ -651,13 +651,9 @@ static void iwl_mvm_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 	if (vif->bss_conf.qos)
 		cmd->qos_flags |= cpu_to_le32(MAC_QOS_FLG_UPDATE_EDCA);
 
-	/* Don't use cts to self as the fw doesn't support it currently. */
-	if (vif->bss_conf.use_cts_prot) {
+	if (vif->bss_conf.use_cts_prot)
 		cmd->protection_flags |= cpu_to_le32(MAC_PROT_FLG_TGG_PROTECT);
-		if (IWL_UCODE_API(mvm->fw->ucode_ver) >= 8)
-			cmd->protection_flags |=
-				cpu_to_le32(MAC_PROT_FLG_SELF_CTS_EN);
-	}
+
 	IWL_DEBUG_RATE(mvm, "use_cts_prot %d, ht_operation_mode %d\n",
 		       vif->bss_conf.use_cts_prot,
 		       vif->bss_conf.ht_operation_mode);
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index c35b8661b395..d06414ef15c5 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -179,7 +179,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	    !iwlwifi_mod_params.sw_crypto)
 		hw->flags |= IEEE80211_HW_MFP_CAPABLE;
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT) {
+	if (0 && mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT) {
 		hw->flags |= IEEE80211_HW_SUPPORTS_UAPSD;
 		hw->uapsd_queues = IWL_UAPSD_AC_INFO;
 		hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP;
@@ -606,7 +606,7 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 	if (ret)
 		goto out_remove_mac;
 
-	if (!mvm->bf_allowed_vif &&
+	if (!mvm->bf_allowed_vif && false &&
 	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
 	    mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BF_UPDATED){
 		mvm->bf_allowed_vif = mvmvif;
@@ -796,7 +796,7 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac,
 	memcpy(cmd->bssid, vif->bss_conf.bssid, ETH_ALEN);
 	len = roundup(sizeof(*cmd) + cmd->count * ETH_ALEN, 4);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_SYNC, len, cmd);
+	ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_ASYNC, len, cmd);
 	if (ret)
 		IWL_ERR(mvm, "mcast filter cmd error. ret=%d\n", ret);
 }
@@ -812,7 +812,7 @@ static void iwl_mvm_recalc_multicast(struct iwl_mvm *mvm)
 	if (WARN_ON_ONCE(!mvm->mcast_filter_cmd))
 		return;
 
-	ieee80211_iterate_active_interfaces(
+	ieee80211_iterate_active_interfaces_atomic(
 		mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
 		iwl_mvm_mc_iface_iterator, &iter_data);
 }
@@ -971,6 +971,7 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 		 */
 		iwl_mvm_remove_time_event(mvm, mvmvif,
 					  &mvmvif->time_event_data);
+		iwl_mvm_sf_update(mvm, vif, false);
 	} else if (changes & (BSS_CHANGED_PS | BSS_CHANGED_P2P_PS |
 			      BSS_CHANGED_QOS)) {
 		ret = iwl_mvm_power_update_mode(mvm, vif);
diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c
index a3d43de342d7..dbff7f0bc6a8 100644
--- a/drivers/net/wireless/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/iwlwifi/mvm/ops.c
@@ -313,6 +313,7 @@ static const char *iwl_mvm_cmd_strings[REPLY_MAX] = {
 	CMD(REPLY_BEACON_FILTERING_CMD),
 	CMD(REPLY_THERMAL_MNG_BACKOFF),
 	CMD(MAC_PM_POWER_TABLE),
+	CMD(LTR_CONFIG),
 	CMD(BT_COEX_CI),
 	CMD(PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION),
 };
diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c
index 6abf74e1351f..03179d0b08c2 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/rs.c
@@ -59,7 +59,7 @@
 /* max allowed rate miss before sync LQ cmd */
 #define IWL_MISSED_RATE_MAX		15
 #define RS_STAY_IN_COLUMN_TIMEOUT       (5*HZ)
-
+#define RS_IDLE_TIMEOUT                 (5*HZ)
 
 static u8 rs_ht_to_legacy[] = {
 	[IWL_RATE_MCS_0_INDEX] = IWL_RATE_6M_INDEX,
@@ -142,7 +142,7 @@ enum rs_column_mode {
 	RS_MIMO2,
 };
 
-#define MAX_NEXT_COLUMNS 5
+#define MAX_NEXT_COLUMNS 7
 #define MAX_COLUMN_CHECKS 3
 
 typedef bool (*allow_column_func_t) (struct iwl_mvm *mvm,
@@ -211,7 +211,9 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.next_columns = {
 			RS_COLUMN_LEGACY_ANT_B,
 			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_MIMO2,
+			RS_COLUMN_SISO_ANT_B,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
 		},
@@ -221,8 +223,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.ant = ANT_B,
 		.next_columns = {
 			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_SISO_ANT_A,
 			RS_COLUMN_SISO_ANT_B,
-			RS_COLUMN_MIMO2,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
 		},
@@ -234,7 +238,9 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
 			RS_COLUMN_SISO_ANT_A_SGI,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_B_SGI,
+			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_LEGACY_ANT_B,
 			RS_COLUMN_INVALID,
 		},
 		.checks = {
@@ -248,7 +254,9 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_A,
 			RS_COLUMN_MIMO2,
 			RS_COLUMN_SISO_ANT_B_SGI,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_A_SGI,
+			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_LEGACY_ANT_B,
 			RS_COLUMN_INVALID,
 		},
 		.checks = {
@@ -263,8 +271,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_B_SGI,
 			RS_COLUMN_MIMO2_SGI,
 			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_B,
+			RS_COLUMN_MIMO2,
+			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_LEGACY_ANT_B,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -279,8 +289,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_A_SGI,
 			RS_COLUMN_MIMO2_SGI,
 			RS_COLUMN_SISO_ANT_B,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_SISO_ANT_A,
+			RS_COLUMN_MIMO2,
+			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_LEGACY_ANT_B,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -292,10 +304,12 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.ant = ANT_AB,
 		.next_columns = {
 			RS_COLUMN_SISO_ANT_A,
+			RS_COLUMN_SISO_ANT_B,
+			RS_COLUMN_SISO_ANT_A_SGI,
+			RS_COLUMN_SISO_ANT_B_SGI,
 			RS_COLUMN_MIMO2_SGI,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_LEGACY_ANT_B,
 		},
 		.checks = {
 			rs_mimo_allow,
@@ -307,10 +321,12 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.sgi = true,
 		.next_columns = {
 			RS_COLUMN_SISO_ANT_A_SGI,
+			RS_COLUMN_SISO_ANT_B_SGI,
+			RS_COLUMN_SISO_ANT_A,
+			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
-			RS_COLUMN_INVALID,
+			RS_COLUMN_LEGACY_ANT_A,
+			RS_COLUMN_LEGACY_ANT_B,
 		},
 		.checks = {
 			rs_mimo_allow,
@@ -503,6 +519,16 @@ static void rs_rate_scale_clear_window(struct iwl_rate_scale_data *window)
 	window->average_tpt = IWL_INVALID_VALUE;
 }
 
+static void rs_rate_scale_clear_tbl_windows(struct iwl_mvm *mvm,
+					    struct iwl_scale_tbl_info *tbl)
+{
+	int i;
+
+	IWL_DEBUG_RATE(mvm, "Clearing up window stats\n");
+	for (i = 0; i < IWL_RATE_COUNT; i++)
+		rs_rate_scale_clear_window(&tbl->win[i]);
+}
+
 static inline u8 rs_is_valid_ant(u8 valid_antenna, u8 ant_type)
 {
 	return (ant_type & valid_antenna) == ant_type;
@@ -975,6 +1001,13 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband,
 		return;
 	}
 
+#ifdef CPTCFG_MAC80211_DEBUGFS
+	/* Disable last tx check if we are debugging with fixed rate */
+	if (lq_sta->dbg_fixed_rate) {
+		IWL_DEBUG_RATE(mvm, "Fixed rate. avoid rate scaling\n");
+		return;
+	}
+#endif
 	if (!ieee80211_is_data(hdr->frame_control) ||
 	    info->flags & IEEE80211_TX_CTL_NO_ACK)
 		return;
@@ -1017,6 +1050,18 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband,
 			mac_index++;
 	}
 
+	if (time_after(jiffies,
+		       (unsigned long)(lq_sta->last_tx + RS_IDLE_TIMEOUT))) {
+		int tid;
+		IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n");
+		for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++)
+			ieee80211_stop_tx_ba_session(sta, tid);
+
+		iwl_mvm_rs_rate_init(mvm, sta, sband->band, false);
+		return;
+	}
+	lq_sta->last_tx = jiffies;
+
 	/* Here we actually compare this rate to the latest LQ command */
 	if ((mac_index < 0) ||
 	    (rate.sgi != !!(mac_flags & IEEE80211_TX_RC_SHORT_GI)) ||
@@ -1362,7 +1407,6 @@ static u32 rs_bw_from_sta_bw(struct ieee80211_sta *sta)
 static void rs_stay_in_table(struct iwl_lq_sta *lq_sta, bool force_search)
 {
 	struct iwl_scale_tbl_info *tbl;
-	int i;
 	int active_tbl;
 	int flush_interval_passed = 0;
 	struct iwl_mvm *mvm;
@@ -1423,9 +1467,7 @@ static void rs_stay_in_table(struct iwl_lq_sta *lq_sta, bool force_search)
 
 				IWL_DEBUG_RATE(mvm,
 					       "LQ: stay in table clear win\n");
-				for (i = 0; i < IWL_RATE_COUNT; i++)
-					rs_rate_scale_clear_window(
-						&(tbl->win[i]));
+				rs_rate_scale_clear_tbl_windows(mvm, tbl);
 			}
 		}
 
@@ -1433,9 +1475,7 @@ static void rs_stay_in_table(struct iwl_lq_sta *lq_sta, bool force_search)
 		 * bitmaps and stats in active table (this will become the new
 		 * "search" table). */
 		if (lq_sta->rs_state == RS_STATE_SEARCH_CYCLE_STARTED) {
-			IWL_DEBUG_RATE(mvm, "Clearing up window stats\n");
-			for (i = 0; i < IWL_RATE_COUNT; i++)
-				rs_rate_scale_clear_window(&(tbl->win[i]));
+			rs_rate_scale_clear_tbl_windows(mvm, tbl);
 		}
 	}
 }
@@ -1628,85 +1668,76 @@ static enum rs_action rs_get_rate_action(struct iwl_mvm *mvm,
 {
 	enum rs_action action = RS_ACTION_STAY;
 
-	/* Too many failures, decrease rate */
 	if ((sr <= RS_SR_FORCE_DECREASE) || (current_tpt == 0)) {
 		IWL_DEBUG_RATE(mvm,
-			       "decrease rate because of low SR\n");
-		action = RS_ACTION_DOWNSCALE;
-	/* No throughput measured yet for adjacent rates; try increase. */
-	} else if ((low_tpt == IWL_INVALID_VALUE) &&
-		   (high_tpt == IWL_INVALID_VALUE)) {
-		if (high != IWL_RATE_INVALID && sr >= IWL_RATE_INCREASE_TH) {
-			IWL_DEBUG_RATE(mvm,
-				       "Good SR and no high rate measurement. "
-				       "Increase rate\n");
-			action = RS_ACTION_UPSCALE;
-		} else if (low != IWL_RATE_INVALID) {
-			IWL_DEBUG_RATE(mvm,
-				       "Remain in current rate\n");
-			action = RS_ACTION_STAY;
-		}
+			       "Decrease rate because of low SR\n");
+		return RS_ACTION_DOWNSCALE;
 	}
 
-	/* Both adjacent throughputs are measured, but neither one has better
-	 * throughput; we're using the best rate, don't change it!
-	 */
-	else if ((low_tpt != IWL_INVALID_VALUE) &&
-		 (high_tpt != IWL_INVALID_VALUE) &&
-		 (low_tpt < current_tpt) &&
-		 (high_tpt < current_tpt)) {
+	if ((low_tpt == IWL_INVALID_VALUE) &&
+	    (high_tpt == IWL_INVALID_VALUE) &&
+	    (high != IWL_RATE_INVALID)) {
 		IWL_DEBUG_RATE(mvm,
-			       "Both high and low are worse. "
-			       "Maintain rate\n");
-		action = RS_ACTION_STAY;
+			       "No data about high/low rates. Increase rate\n");
+		return RS_ACTION_UPSCALE;
 	}
 
-	/* At least one adjacent rate's throughput is measured,
-	 * and may have better performance.
-	 */
-	else {
-		/* Higher adjacent rate's throughput is measured */
-		if (high_tpt != IWL_INVALID_VALUE) {
-			/* Higher rate has better throughput */
-			if (high_tpt > current_tpt &&
-			    sr >= IWL_RATE_INCREASE_TH) {
-				IWL_DEBUG_RATE(mvm,
-					       "Higher rate is better and good "
-					       "SR. Increate rate\n");
-				action = RS_ACTION_UPSCALE;
-			} else {
-				IWL_DEBUG_RATE(mvm,
-					       "Higher rate isn't better OR "
-					       "no good SR. Maintain rate\n");
-				action = RS_ACTION_STAY;
-			}
+	if ((high_tpt == IWL_INVALID_VALUE) &&
+	    (high != IWL_RATE_INVALID) &&
+	    (low_tpt != IWL_INVALID_VALUE) &&
+	    (low_tpt < current_tpt)) {
+		IWL_DEBUG_RATE(mvm,
+			       "No data about high rate and low rate is worse. Increase rate\n");
+		return RS_ACTION_UPSCALE;
+	}
 
-		/* Lower adjacent rate's throughput is measured */
-		} else if (low_tpt != IWL_INVALID_VALUE) {
-			/* Lower rate has better throughput */
-			if (low_tpt > current_tpt) {
-				IWL_DEBUG_RATE(mvm,
-					       "Lower rate is better. "
-					       "Decrease rate\n");
-				action = RS_ACTION_DOWNSCALE;
-			} else if (sr >= IWL_RATE_INCREASE_TH) {
-				IWL_DEBUG_RATE(mvm,
-					       "Lower rate isn't better and "
-					       "good SR. Increase rate\n");
-				action = RS_ACTION_UPSCALE;
-			}
-		}
+	if ((high_tpt != IWL_INVALID_VALUE) &&
+	    (high_tpt > current_tpt)) {
+		IWL_DEBUG_RATE(mvm,
+			       "Higher rate is better. Increate rate\n");
+		return RS_ACTION_UPSCALE;
 	}
 
-	/* Sanity check; asked for decrease, but success rate or throughput
-	 * has been good at old rate.  Don't change it.
-	 */
-	if ((action == RS_ACTION_DOWNSCALE) && (low != IWL_RATE_INVALID) &&
-	    ((sr > IWL_RATE_HIGH_TH) ||
-	     (current_tpt > (100 * tbl->expected_tpt[low])))) {
+	if ((low_tpt != IWL_INVALID_VALUE) &&
+	    (high_tpt != IWL_INVALID_VALUE) &&
+	    (low_tpt < current_tpt) &&
+	    (high_tpt < current_tpt)) {
+		IWL_DEBUG_RATE(mvm,
+			       "Both high and low are worse. Maintain rate\n");
+		return RS_ACTION_STAY;
+	}
+
+	if ((low_tpt != IWL_INVALID_VALUE) &&
+	    (low_tpt > current_tpt)) {
+		IWL_DEBUG_RATE(mvm,
+			       "Lower rate is better\n");
+		action = RS_ACTION_DOWNSCALE;
+		goto out;
+	}
+
+	if ((low_tpt == IWL_INVALID_VALUE) &&
+	    (low != IWL_RATE_INVALID)) {
 		IWL_DEBUG_RATE(mvm,
-			       "Sanity check failed. Maintain rate\n");
-		action = RS_ACTION_STAY;
+			       "No data about lower rate\n");
+		action = RS_ACTION_DOWNSCALE;
+		goto out;
+	}
+
+	IWL_DEBUG_RATE(mvm, "Maintain rate\n");
+
+out:
+	if ((action == RS_ACTION_DOWNSCALE) && (low != IWL_RATE_INVALID)) {
+		if (sr >= RS_SR_NO_DECREASE) {
+			IWL_DEBUG_RATE(mvm,
+				       "SR is above NO DECREASE. Avoid downscale\n");
+			action = RS_ACTION_STAY;
+		} else if (current_tpt > (100 * tbl->expected_tpt[low])) {
+			IWL_DEBUG_RATE(mvm,
+				       "Current TPT is higher than max expected in low rate. Avoid downscale\n");
+			action = RS_ACTION_STAY;
+		} else {
+			IWL_DEBUG_RATE(mvm, "Decrease rate\n");
+		}
 	}
 
 	return action;
@@ -1725,7 +1756,6 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm,
 	int low = IWL_RATE_INVALID;
 	int high = IWL_RATE_INVALID;
 	int index;
-	int i;
 	struct iwl_rate_scale_data *window = NULL;
 	int current_tpt = IWL_INVALID_VALUE;
 	int low_tpt = IWL_INVALID_VALUE;
@@ -1781,6 +1811,7 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm,
 			       "Aggregation changed: prev %d current %d. Update expected TPT table\n",
 			       prev_agg, lq_sta->is_agg);
 		rs_set_expected_tpt_table(lq_sta, tbl);
+		rs_rate_scale_clear_tbl_windows(mvm, tbl);
 	}
 
 	/* current tx rate */
@@ -2010,8 +2041,7 @@ lq_update:
 		if (lq_sta->search_better_tbl) {
 			/* Access the "search" table, clear its history. */
 			tbl = &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]);
-			for (i = 0; i < IWL_RATE_COUNT; i++)
-				rs_rate_scale_clear_window(&(tbl->win[i]));
+			rs_rate_scale_clear_tbl_windows(mvm, tbl);
 
 			/* Use new "search" start rate */
 			index = tbl->rate.index;
@@ -2032,8 +2062,18 @@ lq_update:
 		 * stay with best antenna legacy modulation for a while
 		 * before next round of mode comparisons. */
 		tbl1 = &(lq_sta->lq_info[lq_sta->active_tbl]);
-		if (is_legacy(&tbl1->rate) && !sta->ht_cap.ht_supported) {
+		if (is_legacy(&tbl1->rate)) {
 			IWL_DEBUG_RATE(mvm, "LQ: STAY in legacy table\n");
+
+			if (tid != IWL_MAX_TID_COUNT) {
+				tid_data = &sta_priv->tid_data[tid];
+				if (tid_data->state != IWL_AGG_OFF) {
+					IWL_DEBUG_RATE(mvm,
+						       "Stop aggregation on tid %d\n",
+						       tid);
+					ieee80211_stop_tx_ba_session(sta, tid);
+				}
+			}
 			rs_set_stay_in_table(mvm, 1, lq_sta);
 		} else {
 		/* If we're in an HT mode, and all 3 mode switch actions
@@ -2265,10 +2305,10 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	lq_sta->lq.sta_id = sta_priv->sta_id;
 
 	for (j = 0; j < LQ_SIZE; j++)
-		for (i = 0; i < IWL_RATE_COUNT; i++)
-			rs_rate_scale_clear_window(&lq_sta->lq_info[j].win[i]);
+		rs_rate_scale_clear_tbl_windows(mvm, &lq_sta->lq_info[j]);
 
 	lq_sta->flush_timer = 0;
+	lq_sta->last_tx = jiffies;
 
 	IWL_DEBUG_RATE(mvm,
 		       "LQ: *** rate scale station global init for station %d ***\n",
@@ -2469,6 +2509,7 @@ static void rs_build_rates_table(struct iwl_mvm *mvm,
 	if (is_siso(&rate)) {
 		num_rates = RS_SECONDARY_SISO_NUM_RATES;
 		num_retries = RS_SECONDARY_SISO_RETRIES;
+		lq_cmd->mimo_delim = index;
 	} else if (is_legacy(&rate)) {
 		num_rates = RS_SECONDARY_LEGACY_NUM_RATES;
 		num_retries = RS_LEGACY_RETRIES_PER_RATE;
diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.h b/drivers/net/wireless/iwlwifi/mvm/rs.h
index 7bc6404f6986..f23b68b8eeff 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rs.h
+++ b/drivers/net/wireless/iwlwifi/mvm/rs.h
@@ -156,6 +156,7 @@ enum {
 #define IWL_RATE_HIGH_TH		10880	/*  85% */
 #define IWL_RATE_INCREASE_TH		6400	/*  50% */
 #define RS_SR_FORCE_DECREASE		1920	/*  15% */
+#define RS_SR_NO_DECREASE		10880	/*  85% */
 
 #define LINK_QUAL_AGG_TIME_LIMIT_DEF	(4000) /* 4 milliseconds */
 #define LINK_QUAL_AGG_TIME_LIMIT_MAX	(8000)
@@ -310,6 +311,7 @@ struct iwl_lq_sta {
 	u32 visited_columns;    /* Bitmask marking which Tx columns were
 				 * explored during a search cycle
 				 */
+	u64 last_tx;
 	bool is_vht;
 	enum ieee80211_band band;
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/sf.c b/drivers/net/wireless/iwlwifi/mvm/sf.c
index 8401627c0030..dab8fd13857a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sf.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sf.c
@@ -172,7 +172,7 @@ static int iwl_mvm_sf_config(struct iwl_mvm *mvm, u8 sta_id,
 			     enum iwl_sf_state new_state)
 {
 	struct iwl_sf_cfg_cmd sf_cmd = {
-		.state = new_state,
+		.state = cpu_to_le32(new_state),
 	};
 	struct ieee80211_sta *sta;
 	int ret = 0;
@@ -274,7 +274,8 @@ int iwl_mvm_sf_update(struct iwl_mvm *mvm, struct ieee80211_vif *changed_vif,
 				return -EINVAL;
 			if (changed_vif->type != NL80211_IFTYPE_STATION) {
 				new_state = SF_UNINIT;
-			} else if (changed_vif->bss_conf.assoc) {
+			} else if (changed_vif->bss_conf.assoc &&
+				   changed_vif->bss_conf.dtim_period) {
 				mvmvif = iwl_mvm_vif_from_mac80211(changed_vif);
 				sta_id = mvmvif->ap_sta_id;
 				new_state = SF_FULL_ON;
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 3872ead75488..1ac33d9cd396 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -272,6 +272,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)},
@@ -315,6 +317,8 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)},
 	{IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)},
@@ -366,18 +370,21 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5510, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5200, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5002, iwl7265_n_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5102, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5202, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9010, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9012, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9112, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x9200, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)},
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index f9507807b486..fb62927ca44d 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -94,6 +94,7 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u16 lctl;
+	u16 cap;
 
 	/*
 	 * HW bug W/A for instability in PCIe bus L0S->L1 transition.
@@ -104,16 +105,17 @@ static void iwl_pcie_apm_config(struct iwl_trans *trans)
 	 *    power savings, even without L1.
 	 */
 	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl);
-	if (lctl & PCI_EXP_LNKCTL_ASPM_L1) {
-		/* L1-ASPM enabled; disable(!) L0S */
+	if (lctl & PCI_EXP_LNKCTL_ASPM_L1)
 		iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
-		dev_info(trans->dev, "L1 Enabled; Disabling L0S\n");
-	} else {
-		/* L1-ASPM disabled; enable(!) L0S */
+	else
 		iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
-		dev_info(trans->dev, "L1 Disabled; Enabling L0S\n");
-	}
 	trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S);
+
+	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap);
+	trans->ltr_enabled = cap & PCI_EXP_DEVCTL2_LTR_EN;
+	dev_info(trans->dev, "L1 %sabled - LTR %sabled\n",
+		 (lctl & PCI_EXP_LNKCTL_ASPM_L1) ? "En" : "Dis",
+		 trans->ltr_enabled ? "En" : "Dis");
 }
 
 /*
@@ -318,6 +320,7 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 {
 	int ret;
 	int t = 0;
+	int iter;
 
 	IWL_DEBUG_INFO(trans, "iwl_trans_prepare_card_hw enter\n");
 
@@ -326,18 +329,23 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 	if (ret >= 0)
 		return 0;
 
-	/* If HW is not ready, prepare the conditions to check again */
-	iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
-		    CSR_HW_IF_CONFIG_REG_PREPARE);
+	for (iter = 0; iter < 10; iter++) {
+		/* If HW is not ready, prepare the conditions to check again */
+		iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
+			    CSR_HW_IF_CONFIG_REG_PREPARE);
 
-	do {
-		ret = iwl_pcie_set_hw_ready(trans);
-		if (ret >= 0)
-			return 0;
+		do {
+			ret = iwl_pcie_set_hw_ready(trans);
+			if (ret >= 0)
+				return 0;
 
-		usleep_range(200, 1000);
-		t += 200;
-	} while (t < 150000);
+			usleep_range(200, 1000);
+			t += 200;
+		} while (t < 150000);
+		msleep(25);
+	}
+
+	IWL_DEBUG_INFO(trans, "got NIC after %d iterations\n", iter);
 
 	return ret;
 }
@@ -1563,6 +1571,10 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	 * PCI Tx retries from interfering with C3 CPU state */
 	pci_write_config_byte(pdev, PCI_CFG_RETRY_TIMEOUT, 0x00);
 
+	trans->dev = &pdev->dev;
+	trans_pcie->pci_dev = pdev;
+	iwl_disable_interrupts(trans);
+
 	err = pci_enable_msi(pdev);
 	if (err) {
 		dev_err(&pdev->dev, "pci_enable_msi failed(0X%x)\n", err);
@@ -1574,8 +1586,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		}
 	}
 
-	trans->dev = &pdev->dev;
-	trans_pcie->pci_dev = pdev;
 	trans->hw_rev = iwl_read32(trans, CSR_HW_REV);
 	trans->hw_id = (pdev->device << 16) + pdev->subsystem_device;
 	snprintf(trans->hw_id_str, sizeof(trans->hw_id_str),
@@ -1601,8 +1611,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		goto out_pci_disable_msi;
 	}
 
-	trans_pcie->inta_mask = CSR_INI_SET_MASK;
-
 	if (iwl_pcie_alloc_ict(trans))
 		goto out_free_cmd_pool;
 
@@ -1614,6 +1622,8 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		goto out_free_ict;
 	}
 
+	trans_pcie->inta_mask = CSR_INI_SET_MASK;
+
 	return trans;
 
 out_free_ict:
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 69d4c3179d04..505ff601d9f4 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1974,7 +1974,7 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2,
 	if (err != 0) {
 		printk(KERN_DEBUG "mac80211_hwsim: device_bind_driver failed (%d)\n",
 		       err);
-		goto failed_hw;
+		goto failed_bind;
 	}
 
 	skb_queue_head_init(&data->pending);
@@ -2157,6 +2157,8 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2,
 	return idx;
 
 failed_hw:
+	device_release_driver(data->dev);
+failed_bind:
 	device_unregister(data->dev);
 failed_drvdata:
 	ieee80211_free_hw(hw);
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 9d3d2758ec35..952a47f6554e 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -646,6 +646,7 @@ mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 	tx_info->pkt_len = skb->len;
diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c
index 2f1cd929c6f6..a511cccc9f01 100644
--- a/drivers/net/wireless/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/rt2x00/rt2500pci.c
@@ -1681,8 +1681,13 @@ static int rt2500pci_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	/*
 	 * Detect if this device has an hardware controlled radio.
 	 */
-	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO))
+	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO)) {
 		__set_bit(CAPABILITY_HW_BUTTON, &rt2x00dev->cap_flags);
+		/*
+		 * On this device RFKILL initialized during probe does not work.
+		 */
+		__set_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags);
+	}
 
 	/*
 	 * Check if the BBP tuning should be enabled.
diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h
index a394a9a95919..ebd5625d13f1 100644
--- a/drivers/net/wireless/rt2x00/rt2800.h
+++ b/drivers/net/wireless/rt2x00/rt2800.h
@@ -52,6 +52,7 @@
  * RF5592 2.4G/5G 2T2R
  * RF3070 2.4G 1T1R
  * RF5360 2.4G 1T1R
+ * RF5362 2.4G 1T1R
  * RF5370 2.4G 1T1R
  * RF5390 2.4G 1T1R
  */
@@ -72,6 +73,7 @@
 #define RF3070				0x3070
 #define RF3290				0x3290
 #define RF5360				0x5360
+#define RF5362				0x5362
 #define RF5370				0x5370
 #define RF5372				0x5372
 #define RF5390				0x5390
@@ -2039,7 +2041,7 @@ struct mac_iveiv_entry {
  * 2 - drop tx power by 12dBm,
  * 3 - increase tx power by 6dBm
  */
-#define BBP1_TX_POWER_CTRL		FIELD8(0x07)
+#define BBP1_TX_POWER_CTRL		FIELD8(0x03)
 #define BBP1_TX_ANTENNA			FIELD8(0x18)
 
 /*
@@ -2145,7 +2147,7 @@ struct mac_iveiv_entry {
 /* Bits [7-4] for RF3320 (RT3370/RT3390), on other chipsets reserved */
 #define RFCSR3_PA1_BIAS_CCK		FIELD8(0x70)
 #define RFCSR3_PA2_CASCODE_BIAS_CCKK	FIELD8(0x80)
-/* Bits for RF3290/RF5360/RF5370/RF5372/RF5390/RF5392 */
+/* Bits for RF3290/RF5360/RF5362/RF5370/RF5372/RF5390/RF5392 */
 #define RFCSR3_VCOCAL_EN		FIELD8(0x80)
 /* Bits for RF3050 */
 #define RFCSR3_BIT1			FIELD8(0x02)
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 41d4a8167dc3..4e16d4da9d82 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -3142,6 +3142,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 		break;
 	case RF3070:
 	case RF5360:
+	case RF5362:
 	case RF5370:
 	case RF5372:
 	case RF5390:
@@ -3159,6 +3160,7 @@ static void rt2800_config_channel(struct rt2x00_dev *rt2x00dev,
 	    rt2x00_rf(rt2x00dev, RF3290) ||
 	    rt2x00_rf(rt2x00dev, RF3322) ||
 	    rt2x00_rf(rt2x00dev, RF5360) ||
+	    rt2x00_rf(rt2x00dev, RF5362) ||
 	    rt2x00_rf(rt2x00dev, RF5370) ||
 	    rt2x00_rf(rt2x00dev, RF5372) ||
 	    rt2x00_rf(rt2x00dev, RF5390) ||
@@ -4273,6 +4275,7 @@ void rt2800_vco_calibration(struct rt2x00_dev *rt2x00dev)
 	case RF3070:
 	case RF3290:
 	case RF5360:
+	case RF5362:
 	case RF5370:
 	case RF5372:
 	case RF5390:
@@ -7073,6 +7076,7 @@ static int rt2800_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	case RF3320:
 	case RF3322:
 	case RF5360:
+	case RF5362:
 	case RF5370:
 	case RF5372:
 	case RF5390:
@@ -7529,6 +7533,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev)
 	case RF3320:
 	case RF3322:
 	case RF5360:
+	case RF5362:
 	case RF5370:
 	case RF5372:
 	case RF5390:
@@ -7658,6 +7663,7 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev)
 	case RF3070:
 	case RF3290:
 	case RF5360:
+	case RF5362:
 	case RF5370:
 	case RF5372:
 	case RF5390:
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index caddc1b427a9..57d3967de32f 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -1062,6 +1062,7 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	/* Ovislink */
 	{ USB_DEVICE(0x1b75, 0x3071) },
 	{ USB_DEVICE(0x1b75, 0x3072) },
+	{ USB_DEVICE(0x1b75, 0xa200) },
 	/* Para */
 	{ USB_DEVICE(0x20b8, 0x8888) },
 	/* Pegatron */
@@ -1235,6 +1236,8 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	/* Arcadyan */
 	{ USB_DEVICE(0x043e, 0x7a12) },
 	{ USB_DEVICE(0x043e, 0x7a32) },
+	/* ASUS */
+	{ USB_DEVICE(0x0b05, 0x17e8) },
 	/* Azurewave */
 	{ USB_DEVICE(0x13d3, 0x3329) },
 	{ USB_DEVICE(0x13d3, 0x3365) },
@@ -1271,6 +1274,7 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	{ USB_DEVICE(0x057c, 0x8501) },
 	/* Buffalo */
 	{ USB_DEVICE(0x0411, 0x0241) },
+	{ USB_DEVICE(0x0411, 0x0253) },
 	/* D-Link */
 	{ USB_DEVICE(0x2001, 0x3c1a) },
 	{ USB_DEVICE(0x2001, 0x3c21) },
@@ -1361,6 +1365,7 @@ static struct usb_device_id rt2800usb_device_table[] = {
 	{ USB_DEVICE(0x0df6, 0x0053) },
 	{ USB_DEVICE(0x0df6, 0x0069) },
 	{ USB_DEVICE(0x0df6, 0x006f) },
+	{ USB_DEVICE(0x0df6, 0x0078) },
 	/* SMC */
 	{ USB_DEVICE(0x083a, 0xa512) },
 	{ USB_DEVICE(0x083a, 0xc522) },
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index e3b885d8f7db..5d45a1a740a4 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -693,6 +693,7 @@ enum rt2x00_capability_flags {
 	REQUIRE_SW_SEQNO,
 	REQUIRE_HT_TX_DESC,
 	REQUIRE_PS_AUTOWAKE,
+	REQUIRE_DELAYED_RFKILL,
 
 	/*
 	 * Capabilities
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 2bde6729f5e6..4fa43a2eeb73 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -1126,9 +1126,10 @@ static void rt2x00lib_uninitialize(struct rt2x00_dev *rt2x00dev)
 		return;
 
 	/*
-	 * Unregister extra components.
+	 * Stop rfkill polling.
 	 */
-	rt2x00rfkill_unregister(rt2x00dev);
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
 
 	/*
 	 * Allow the HW to uninitialize.
@@ -1166,6 +1167,12 @@ static int rt2x00lib_initialize(struct rt2x00_dev *rt2x00dev)
 
 	set_bit(DEVICE_STATE_INITIALIZED, &rt2x00dev->flags);
 
+	/*
+	 * Start rfkill polling.
+	 */
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
+
 	return 0;
 }
 
@@ -1375,7 +1382,12 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
 	rt2x00link_register(rt2x00dev);
 	rt2x00leds_register(rt2x00dev);
 	rt2x00debug_register(rt2x00dev);
-	rt2x00rfkill_register(rt2x00dev);
+
+	/*
+	 * Start rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
 
 	return 0;
 
@@ -1391,6 +1403,12 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev)
 	clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
 
 	/*
+	 * Stop rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
+
+	/*
 	 * Disable radio.
 	 */
 	rt2x00lib_disable_radio(rt2x00dev);
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index ddeb5a709aa3..87a8ad5d2eb7 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -487,6 +487,8 @@ int rt2x00mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	crypto.cipher = rt2x00crypto_key_to_cipher(key);
 	if (crypto.cipher == CIPHER_NONE)
 		return -EOPNOTSUPP;
+	if (crypto.cipher == CIPHER_TKIP && rt2x00_is_usb(rt2x00dev))
+		return -EOPNOTSUPP;
 
 	crypto.cmd = cmd;
 
@@ -621,20 +623,18 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
 				      bss_conf->bssid);
 
 	/*
-	 * Update the beacon. This is only required on USB devices. PCI
-	 * devices fetch beacons periodically.
-	 */
-	if (changes & BSS_CHANGED_BEACON && rt2x00_is_usb(rt2x00dev))
-		rt2x00queue_update_beacon(rt2x00dev, vif);
-
-	/*
 	 * Start/stop beaconing.
 	 */
 	if (changes & BSS_CHANGED_BEACON_ENABLED) {
 		if (!bss_conf->enable_beacon && intf->enable_beacon) {
-			rt2x00queue_clear_beacon(rt2x00dev, vif);
 			rt2x00dev->intf_beaconing--;
 			intf->enable_beacon = false;
+			/*
+			 * Clear beacon in the H/W for this vif. This is needed
+			 * to disable beaconing on this particular interface
+			 * and keep it running on other interfaces.
+			 */
+			rt2x00queue_clear_beacon(rt2x00dev, vif);
 
 			if (rt2x00dev->intf_beaconing == 0) {
 				/*
@@ -645,11 +645,15 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
 				rt2x00queue_stop_queue(rt2x00dev->bcn);
 				mutex_unlock(&intf->beacon_skb_mutex);
 			}
-
-
 		} else if (bss_conf->enable_beacon && !intf->enable_beacon) {
 			rt2x00dev->intf_beaconing++;
 			intf->enable_beacon = true;
+			/*
+			 * Upload beacon to the H/W. This is only required on
+			 * USB devices. PCI devices fetch beacons periodically.
+			 */
+			if (rt2x00_is_usb(rt2x00dev))
+				rt2x00queue_update_beacon(rt2x00dev, vif);
 
 			if (rt2x00dev->intf_beaconing == 1) {
 				/*
diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c
index 5642ccceca7c..22d49d575d3f 100644
--- a/drivers/net/wireless/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/rt2x00/rt2x00queue.c
@@ -158,55 +158,29 @@ void rt2x00queue_align_frame(struct sk_buff *skb)
 	skb_trim(skb, frame_length);
 }
 
-void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int header_length)
+/*
+ * H/W needs L2 padding between the header and the paylod if header size
+ * is not 4 bytes aligned.
+ */
+void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int hdr_len)
 {
-	unsigned int payload_length = skb->len - header_length;
-	unsigned int header_align = ALIGN_SIZE(skb, 0);
-	unsigned int payload_align = ALIGN_SIZE(skb, header_length);
-	unsigned int l2pad = payload_length ? L2PAD_SIZE(header_length) : 0;
+	unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0;
 
-	/*
-	 * Adjust the header alignment if the payload needs to be moved more
-	 * than the header.
-	 */
-	if (payload_align > header_align)
-		header_align += 4;
-
-	/* There is nothing to do if no alignment is needed */
-	if (!header_align)
+	if (!l2pad)
 		return;
 
-	/* Reserve the amount of space needed in front of the frame */
-	skb_push(skb, header_align);
-
-	/*
-	 * Move the header.
-	 */
-	memmove(skb->data, skb->data + header_align, header_length);
-
-	/* Move the payload, if present and if required */
-	if (payload_length && payload_align)
-		memmove(skb->data + header_length + l2pad,
-			skb->data + header_length + l2pad + payload_align,
-			payload_length);
-
-	/* Trim the skb to the correct size */
-	skb_trim(skb, header_length + l2pad + payload_length);
+	skb_push(skb, l2pad);
+	memmove(skb->data, skb->data + l2pad, hdr_len);
 }
 
-void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int header_length)
+void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int hdr_len)
 {
-	/*
-	 * L2 padding is only present if the skb contains more than just the
-	 * IEEE 802.11 header.
-	 */
-	unsigned int l2pad = (skb->len > header_length) ?
-				L2PAD_SIZE(header_length) : 0;
+	unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0;
 
 	if (!l2pad)
 		return;
 
-	memmove(skb->data + l2pad, skb->data, header_length);
+	memmove(skb->data + l2pad, skb->data, hdr_len);
 	skb_pull(skb, l2pad);
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
index e06971be7df7..f923d8c9a296 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
@@ -1025,9 +1025,20 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	bool rtstatus = true;
 	int err = 0;
 	u8 tmp_u1b, u1byte;
+	unsigned long flags;
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "Rtl8188EE hw init\n");
 	rtlpriv->rtlhal.being_init_adapter = true;
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	tmp_u1b = rtl_read_byte(rtlpriv, REG_SYS_CLKR+1);
@@ -1043,7 +1054,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	if (rtstatus != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl88e_download_fw(hw, false);
@@ -1051,8 +1062,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		rtlhal->fw_ready = false;
-		return err;
+		goto exit;
 	} else {
 		rtlhal->fw_ready = true;
 	}
@@ -1135,10 +1145,12 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	}
 	rtl_write_byte(rtlpriv, REG_NAV_CTRL+2,  ((30000+127)/128));
 	rtl88e_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpriv->rtlhal.being_init_adapter = false;
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "end of Rtl8188EE hw init %x\n",
 		 err);
-	return 0;
+	return err;
 }
 
 static enum version_8188e _rtl88ee_read_chip_version(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
index aece6c9cccf1..7622e44567cc 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
@@ -293,7 +293,7 @@ static void _rtl88ee_translate_rx_signal_stuff(struct ieee80211_hw *hw,
 	u8 *psaddr;
 	__le16 fc;
 	u16 type, ufc;
-	bool match_bssid, packet_toself, packet_beacon, addr;
+	bool match_bssid, packet_toself, packet_beacon = false, addr;
 
 	tmp_buf = skb->data + pstatus->rx_drvinfo_size + pstatus->rx_bufshift;
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
index 468bf73cc883..472e592b32ec 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
@@ -985,19 +985,30 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	int err = 0;
 	static bool iqk_initialized;
+	unsigned long flags;
+
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
 
 	rtlhal->hw_type = HARDWARE_TYPE_RTL8192CU;
 	err = _rtl92cu_init_mac(hw);
 	if (err) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "init mac failed!\n");
-		return err;
+		goto exit;
 	}
 	err = rtl92c_download_fw(hw);
 	if (err) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 	rtlhal->last_hmeboxnum = 0; /* h2c */
 	_rtl92cu_phy_param_tab_init(hw);
@@ -1034,6 +1045,8 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw)
 	_InitPABias(hw);
 	_update_mac_setting(hw);
 	rtl92c_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	return err;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
index c61311084d7e..f58316769159 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
@@ -317,6 +317,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = {
 	{RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/
 	{RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
 	{RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
+	{RTL_USB_DEVICE(0x0df6, 0x0070, rtl92cu_hal_cfg)}, /*Sitecom - 150N */
 	{RTL_USB_DEVICE(0x0df6, 0x0077, rtl92cu_hal_cfg)}, /*Sitecom-WLA2100V2*/
 	{RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/
 	{RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
index 4f461786a7eb..c471400fe8f0 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
@@ -955,7 +955,7 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	u8 tmp_byte = 0;
-
+	unsigned long flags;
 	bool rtstatus = true;
 	u8 tmp_u1b;
 	int err = false;
@@ -967,6 +967,16 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpci->being_init_adapter = true;
 
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	/* 1. MAC Initialize */
@@ -984,7 +994,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now... "
 			 "Please copy FW into /lib/firmware/rtlwifi\n");
-		return 1;
+		err = 1;
+		goto exit;
 	}
 
 	/* After FW download, we have to reset MAC register */
@@ -997,7 +1008,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 3. Initialize MAC/PHY Config by MACPHY_reg.txt */
 	if (!rtl92s_phy_mac_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "MAC Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* because last function modify RCR, so we update
@@ -1016,7 +1028,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 4. Initialize BB After MAC Config PHY_reg.txt, AGC_Tab.txt */
 	if (!rtl92s_phy_bb_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG, "BB Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* 5. Initiailze RF RAIO_A.txt RF RAIO_B.txt */
@@ -1033,7 +1046,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	if (!rtl92s_phy_rf_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "RF Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* After read predefined TXT, we must set BB/MAC/RF
@@ -1122,8 +1136,9 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_ON);
 	rtl92s_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpci->being_init_adapter = false;
-
 	return err;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
index 27efbcdac6a9..d27abef140f0 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
@@ -49,6 +49,12 @@ static u8 _rtl92se_map_hwqueue_to_fwqueue(struct sk_buff *skb,	u8 skb_queue)
 	if (ieee80211_is_nullfunc(fc))
 		return QSLT_HIGH;
 
+	/* Kernel commit 1bf4bbb4024dcdab changed EAPOL packets to use
+	 * queue V0 at priority 7; however, the RTL8192SE appears to have
+	 * that queue at priority 6
+	 */
+	if (skb->priority == 7)
+		return QSLT_VO;
 	return skb->priority;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
index c333dfd116b8..99f6bc5fa986 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
@@ -880,14 +880,25 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 	bool rtstatus = true;
 	int err;
 	u8 tmp_u1b;
+	unsigned long flags;
 
 	rtlpriv->rtlhal.being_init_adapter = true;
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 	rtstatus = _rtl8712e_init_mac(hw);
 	if (rtstatus != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl8723ae_download_fw(hw);
@@ -895,8 +906,7 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		rtlhal->fw_ready = false;
-		return err;
+		goto exit;
 	} else {
 		rtlhal->fw_ready = true;
 	}
@@ -971,6 +981,8 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n");
 	}
 	rtl8723ae_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpriv->rtlhal.being_init_adapter = false;
 	return err;
 }
diff --git a/drivers/net/wireless/ti/wl18xx/event.h b/drivers/net/wireless/ti/wl18xx/event.h
index 398f3d2c0a6c..a76e98eb8372 100644
--- a/drivers/net/wireless/ti/wl18xx/event.h
+++ b/drivers/net/wireless/ti/wl18xx/event.h
@@ -68,6 +68,26 @@ struct wl18xx_event_mailbox {
 
 	/* bitmap of inactive stations (by HLID) */
 	__le32 inactive_sta_bitmap;
+
+	/* rx BA win size indicated by RX_BA_WIN_SIZE_CHANGE_EVENT_ID */
+	u8 rx_ba_role_id;
+	u8 rx_ba_link_id;
+	u8 rx_ba_win_size;
+	u8 padding;
+
+	/* smart config */
+	u8 sc_ssid_len;
+	u8 sc_pwd_len;
+	u8 sc_token_len;
+	u8 padding1;
+	u8 sc_ssid[32];
+	u8 sc_pwd[32];
+	u8 sc_token[32];
+
+	/* smart config sync channel */
+	u8 sc_sync_channel;
+	u8 sc_sync_band;
+	u8 padding2[2];
 } __packed;
 
 int wl18xx_wait_for_event(struct wl1271 *wl, enum wlcore_wait_event event,
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index ae413a2cbee7..4bf5b334664e 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -113,6 +113,11 @@ struct xenvif {
 	domid_t          domid;
 	unsigned int     handle;
 
+	/* Is this interface disabled? True when backend discovers
+	 * frontend is rogue.
+	 */
+	bool disabled;
+
 	/* Use NAPI for guest TX */
 	struct napi_struct napi;
 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 301cc037fda8..2e92d52c0a6d 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -62,6 +62,15 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 	struct xenvif *vif = container_of(napi, struct xenvif, napi);
 	int work_done;
 
+	/* This vif is rogue, we pretend we've there is nothing to do
+	 * for this vif to deschedule it from NAPI. But this interface
+	 * will be turned off in thread context later.
+	 */
+	if (unlikely(vif->disabled)) {
+		napi_complete(napi);
+		return 0;
+	}
+
 	work_done = xenvif_tx_action(vif, budget);
 
 	if (work_done < budget) {
@@ -321,6 +330,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->ip_csum = 1;
 	vif->dev = dev;
 
+	vif->disabled = false;
+
 	vif->credit_bytes = vif->remaining_credit = ~0UL;
 	vif->credit_usec  = 0UL;
 	init_timer(&vif->credit_timeout);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 438d0c09b7e6..97030c193afd 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -192,8 +192,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 * into multiple copies tend to give large frags their
 	 * own buffers as before.
 	 */
-	if ((offset + size > MAX_BUFFER_OFFSET) &&
-	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+	BUG_ON(size > MAX_BUFFER_OFFSET);
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
 		return true;
 
 	return false;
@@ -482,6 +482,8 @@ static void xenvif_rx_action(struct xenvif *vif)
 
 	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
 		RING_IDX max_slots_needed;
+		RING_IDX old_req_cons;
+		RING_IDX ring_slots_used;
 		int i;
 
 		/* We need a cheap worse case estimate for the number of
@@ -493,9 +495,28 @@ static void xenvif_rx_action(struct xenvif *vif)
 						PAGE_SIZE);
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			unsigned int size;
+			unsigned int offset;
+
 			size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
-			max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE);
+			offset = skb_shinfo(skb)->frags[i].page_offset;
+
+			/* For a worse-case estimate we need to factor in
+			 * the fragment page offset as this will affect the
+			 * number of times xenvif_gop_frag_copy() will
+			 * call start_new_rx_buffer().
+			 */
+			max_slots_needed += DIV_ROUND_UP(offset + size,
+							 PAGE_SIZE);
 		}
+
+		/* To avoid the estimate becoming too pessimal for some
+		 * frontends that limit posted rx requests, cap the estimate
+		 * at MAX_SKB_FRAGS.
+		 */
+		if (max_slots_needed > MAX_SKB_FRAGS)
+			max_slots_needed = MAX_SKB_FRAGS;
+
+		/* We may need one more slot for GSO metadata */
 		if (skb_is_gso(skb) &&
 		   (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
 		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
@@ -511,8 +532,12 @@ static void xenvif_rx_action(struct xenvif *vif)
 			vif->rx_last_skb_slots = 0;
 
 		sco = (struct skb_cb_overlay *)skb->cb;
+
+		old_req_cons = vif->rx.req_cons;
 		sco->meta_slots_used = xenvif_gop_skb(skb, &npo);
-		BUG_ON(sco->meta_slots_used > max_slots_needed);
+		ring_slots_used = vif->rx.req_cons - old_req_cons;
+
+		BUG_ON(ring_slots_used > max_slots_needed);
 
 		__skb_queue_tail(&rxq, skb);
 	}
@@ -655,7 +680,8 @@ static void xenvif_tx_err(struct xenvif *vif,
 static void xenvif_fatal_tx_err(struct xenvif *vif)
 {
 	netdev_err(vif->dev, "fatal error; disabling device\n");
-	xenvif_carrier_off(vif);
+	vif->disabled = true;
+	xenvif_kick_thread(vif);
 }
 
 static int xenvif_count_requests(struct xenvif *vif,
@@ -1126,7 +1152,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
 				   vif->tx.sring->req_prod, vif->tx.req_cons,
 				   XEN_NETIF_TX_RING_SIZE);
 			xenvif_fatal_tx_err(vif);
-			continue;
+			break;
 		}
 
 		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
@@ -1548,7 +1574,18 @@ int xenvif_kthread(void *data)
 	while (!kthread_should_stop()) {
 		wait_event_interruptible(vif->wq,
 					 rx_work_todo(vif) ||
+					 vif->disabled ||
 					 kthread_should_stop());
+
+		/* This frontend is found to be rogue, disable it in
+		 * kthread context. Currently this is only set when
+		 * netback finds out frontend sends malformed packet,
+		 * but we cannot disable the interface in softirq
+		 * context so we defer it here.
+		 */
+		if (unlikely(vif->disabled && netif_carrier_ok(vif->dev)))
+			xenvif_carrier_off(vif);
+
 		if (kthread_should_stop())
 			break;
 
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index e30d80033cbc..19db057658c5 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -469,9 +469,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		len = skb_frag_size(frag);
 		offset = frag->page_offset;
 
-		/* Data must not cross a page boundary. */
-		BUG_ON(len + offset > PAGE_SIZE<<compound_order(page));
-
 		/* Skip unused frames from start of page */
 		page += offset >> PAGE_SHIFT;
 		offset &= ~PAGE_MASK;
@@ -479,8 +476,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		while (len > 0) {
 			unsigned long bytes;
 
-			BUG_ON(offset >= PAGE_SIZE);
-
 			bytes = PAGE_SIZE - offset;
 			if (bytes > len)
 				bytes = len;
diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c
index f868333271aa..963a4a5dc88e 100644
--- a/drivers/nfc/microread/microread.c
+++ b/drivers/nfc/microread/microread.c
@@ -501,9 +501,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate,
 		targets->sens_res =
 			 be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A_ATQA]);
 		targets->sel_res = skb->data[MICROREAD_EMCF_A_SAK];
-		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID],
-		       skb->data[MICROREAD_EMCF_A_LEN]);
 		targets->nfcid1_len = skb->data[MICROREAD_EMCF_A_LEN];
+		if (targets->nfcid1_len > sizeof(targets->nfcid1)) {
+			r = -EINVAL;
+			goto exit_free;
+		}
+		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID],
+		       targets->nfcid1_len);
 		break;
 	case MICROREAD_GATE_ID_MREAD_ISO_A_3:
 		targets->supported_protocols =
@@ -511,9 +515,13 @@ static void microread_target_discovered(struct nfc_hci_dev *hdev, u8 gate,
 		targets->sens_res =
 			 be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A3_ATQA]);
 		targets->sel_res = skb->data[MICROREAD_EMCF_A3_SAK];
-		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID],
-		       skb->data[MICROREAD_EMCF_A3_LEN]);
 		targets->nfcid1_len = skb->data[MICROREAD_EMCF_A3_LEN];
+		if (targets->nfcid1_len > sizeof(targets->nfcid1)) {
+			r = -EINVAL;
+			goto exit_free;
+		}
+		memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID],
+		       targets->nfcid1_len);
 		break;
 	case MICROREAD_GATE_ID_MREAD_ISO_B:
 		targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK;
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index c6973f101a3e..ec919a9160a5 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -28,6 +28,7 @@ config OF_SELFTEST
 config OF_FLATTREE
 	bool
 	select DTC
+	select LIBFDT
 
 config OF_EARLY_FLATTREE
 	bool
@@ -75,4 +76,10 @@ config OF_MTD
 	depends on MTD
 	def_bool y
 
+config OF_RESERVED_MEM
+	depends on OF_EARLY_FLATTREE
+	bool
+	help
+	  Helpers to allow for reservation of memory regions
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index efd05102c405..9891232f999e 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -9,3 +9,6 @@ obj-$(CONFIG_OF_MDIO)	+= of_mdio.o
 obj-$(CONFIG_OF_PCI)	+= of_pci.o
 obj-$(CONFIG_OF_PCI_IRQ)  += of_pci_irq.o
 obj-$(CONFIG_OF_MTD)	+= of_mtd.o
+obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
+
+CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 1a54f1ffaadb..005c65715846 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -401,6 +401,21 @@ static struct of_bus *of_match_bus(struct device_node *np)
 	return NULL;
 }
 
+static int of_empty_ranges_quirk(void)
+{
+	if (IS_ENABLED(CONFIG_PPC)) {
+		/* To save cycles, we cache the result */
+		static int quirk_state = -1;
+
+		if (quirk_state < 0)
+			quirk_state =
+				of_machine_is_compatible("Power Macintosh") ||
+				of_machine_is_compatible("MacRISC");
+		return quirk_state;
+	}
+	return false;
+}
+
 static int of_translate_one(struct device_node *parent, struct of_bus *bus,
 			    struct of_bus *pbus, __be32 *addr,
 			    int na, int ns, int pna, const char *rprop)
@@ -426,12 +441,10 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus,
 	 * This code is only enabled on powerpc. --gcl
 	 */
 	ranges = of_get_property(parent, rprop, &rlen);
-#if !defined(CONFIG_PPC)
-	if (ranges == NULL) {
+	if (ranges == NULL && !of_empty_ranges_quirk()) {
 		pr_err("OF: no ranges; cannot translate\n");
 		return 1;
 	}
-#endif /* !defined(CONFIG_PPC) */
 	if (ranges == NULL || rlen == 0) {
 		offset = of_read_number(addr, na);
 		memset(addr, 0, pna * 4);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 89e888a78899..ac26e58e3686 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -21,6 +21,7 @@
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_graph.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
@@ -1117,52 +1118,6 @@ int of_property_read_string(struct device_node *np, const char *propname,
 EXPORT_SYMBOL_GPL(of_property_read_string);
 
 /**
- * of_property_read_string_index - Find and read a string from a multiple
- * strings property.
- * @np:		device node from which the property value is to be read.
- * @propname:	name of the property to be searched.
- * @index:	index of the string in the list of strings
- * @out_string:	pointer to null terminated return string, modified only if
- *		return value is 0.
- *
- * Search for a property in a device tree node and retrieve a null
- * terminated string value (pointer to data, not a copy) in the list of strings
- * contained in that property.
- * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if
- * property does not have a value, and -EILSEQ if the string is not
- * null-terminated within the length of the property data.
- *
- * The out_string pointer is modified only if a valid string can be decoded.
- */
-int of_property_read_string_index(struct device_node *np, const char *propname,
-				  int index, const char **output)
-{
-	struct property *prop = of_find_property(np, propname, NULL);
-	int i = 0;
-	size_t l = 0, total = 0;
-	const char *p;
-
-	if (!prop)
-		return -EINVAL;
-	if (!prop->value)
-		return -ENODATA;
-	if (strnlen(prop->value, prop->length) >= prop->length)
-		return -EILSEQ;
-
-	p = prop->value;
-
-	for (i = 0; total < prop->length; total += l, p += l) {
-		l = strlen(p) + 1;
-		if (i++ == index) {
-			*output = p;
-			return 0;
-		}
-	}
-	return -ENODATA;
-}
-EXPORT_SYMBOL_GPL(of_property_read_string_index);
-
-/**
  * of_property_match_string() - Find string in a list and return index
  * @np: pointer to node containing string list property
  * @propname: string list property name
@@ -1188,7 +1143,7 @@ int of_property_match_string(struct device_node *np, const char *propname,
 	end = p + prop->length;
 
 	for (i = 0; p < end; i++, p += l) {
-		l = strlen(p) + 1;
+		l = strnlen(p, end - p) + 1;
 		if (p + l > end)
 			return -EILSEQ;
 		pr_debug("comparing %s with %s\n", string, p);
@@ -1200,39 +1155,41 @@ int of_property_match_string(struct device_node *np, const char *propname,
 EXPORT_SYMBOL_GPL(of_property_match_string);
 
 /**
- * of_property_count_strings - Find and return the number of strings from a
- * multiple strings property.
+ * of_property_read_string_util() - Utility helper for parsing string properties
  * @np:		device node from which the property value is to be read.
  * @propname:	name of the property to be searched.
+ * @out_strs:	output array of string pointers.
+ * @sz:		number of array elements to read.
+ * @skip:	Number of strings to skip over at beginning of list.
  *
- * Search for a property in a device tree node and retrieve the number of null
- * terminated string contain in it. Returns the number of strings on
- * success, -EINVAL if the property does not exist, -ENODATA if property
- * does not have a value, and -EILSEQ if the string is not null-terminated
- * within the length of the property data.
+ * Don't call this function directly. It is a utility helper for the
+ * of_property_read_string*() family of functions.
  */
-int of_property_count_strings(struct device_node *np, const char *propname)
+int of_property_read_string_helper(struct device_node *np, const char *propname,
+				   const char **out_strs, size_t sz, int skip)
 {
 	struct property *prop = of_find_property(np, propname, NULL);
-	int i = 0;
-	size_t l = 0, total = 0;
-	const char *p;
+	int l = 0, i = 0;
+	const char *p, *end;
 
 	if (!prop)
 		return -EINVAL;
 	if (!prop->value)
 		return -ENODATA;
-	if (strnlen(prop->value, prop->length) >= prop->length)
-		return -EILSEQ;
-
 	p = prop->value;
+	end = p + prop->length;
 
-	for (i = 0; total < prop->length; total += l, p += l, i++)
-		l = strlen(p) + 1;
-
-	return i;
+	for (i = 0; p < end && (!out_strs || i < skip + sz); i++, p += l) {
+		l = strnlen(p, end - p) + 1;
+		if (p + l > end)
+			return -EILSEQ;
+		if (out_strs && i >= skip)
+			*out_strs++ = p;
+	}
+	i -= skip;
+	return i <= 0 ? -ENODATA : i;
 }
-EXPORT_SYMBOL_GPL(of_property_count_strings);
+EXPORT_SYMBOL_GPL(of_property_read_string_helper);
 
 void of_print_phandle_args(const char *msg, const struct of_phandle_args *args)
 {
@@ -1982,3 +1939,154 @@ struct device_node *of_find_next_cache_node(const struct device_node *np)
 
 	return NULL;
 }
+
+/**
+ * of_graph_parse_endpoint() - parse common endpoint node properties
+ * @node: pointer to endpoint device_node
+ * @endpoint: pointer to the OF endpoint data structure
+ *
+ * The caller should hold a reference to @node.
+ */
+int of_graph_parse_endpoint(const struct device_node *node,
+			    struct of_endpoint *endpoint)
+{
+	struct device_node *port_node = of_get_parent(node);
+
+	WARN_ONCE(!port_node, "%s(): endpoint %s has no parent node\n",
+		  __func__, node->full_name);
+
+	memset(endpoint, 0, sizeof(*endpoint));
+
+	endpoint->local_node = node;
+	/*
+	 * It doesn't matter whether the two calls below succeed.
+	 * If they don't then the default value 0 is used.
+	 */
+	of_property_read_u32(port_node, "reg", &endpoint->port);
+	of_property_read_u32(node, "reg", &endpoint->id);
+
+	of_node_put(port_node);
+
+	return 0;
+}
+EXPORT_SYMBOL(of_graph_parse_endpoint);
+
+/**
+ * of_graph_get_next_endpoint() - get next endpoint node
+ * @parent: pointer to the parent device node
+ * @prev: previous endpoint node, or NULL to get first
+ *
+ * Return: An 'endpoint' node pointer with refcount incremented. Refcount
+ * of the passed @prev node is not decremented, the caller have to use
+ * of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+					struct device_node *prev)
+{
+	struct device_node *endpoint;
+	struct device_node *port;
+
+	if (!parent)
+		return NULL;
+
+	/*
+	 * Start by locating the port node. If no previous endpoint is specified
+	 * search for the first port node, otherwise get the previous endpoint
+	 * parent port node.
+	 */
+	if (!prev) {
+		struct device_node *node;
+
+		node = of_get_child_by_name(parent, "ports");
+		if (node)
+			parent = node;
+
+		port = of_get_child_by_name(parent, "port");
+		of_node_put(node);
+
+		if (!port) {
+			pr_err("%s(): no port node found in %s\n",
+			       __func__, parent->full_name);
+			return NULL;
+		}
+	} else {
+		port = of_get_parent(prev);
+		if (WARN_ONCE(!port, "%s(): endpoint %s has no parent node\n",
+			      __func__, prev->full_name))
+			return NULL;
+
+		/*
+		 * Avoid dropping prev node refcount to 0 when getting the next
+		 * child below.
+		 */
+		of_node_get(prev);
+	}
+
+	while (1) {
+		/*
+		 * Now that we have a port node, get the next endpoint by
+		 * getting the next child. If the previous endpoint is NULL this
+		 * will return the first child.
+		 */
+		endpoint = of_get_next_child(port, prev);
+		if (endpoint) {
+			of_node_put(port);
+			return endpoint;
+		}
+
+		/* No more endpoints under this port, try the next one. */
+		prev = NULL;
+
+		do {
+			port = of_get_next_child(parent, port);
+			if (!port)
+				return NULL;
+		} while (of_node_cmp(port->name, "port"));
+	}
+}
+EXPORT_SYMBOL(of_graph_get_next_endpoint);
+
+/**
+ * of_graph_get_remote_port_parent() - get remote port's parent node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote device node associated with remote endpoint node linked
+ *	   to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port_parent(
+			       const struct device_node *node)
+{
+	struct device_node *np;
+	unsigned int depth;
+
+	/* Get remote endpoint node. */
+	np = of_parse_phandle(node, "remote-endpoint", 0);
+
+	/* Walk 3 levels up only if there is 'ports' node. */
+	for (depth = 3; depth && np; depth--) {
+		np = of_get_next_parent(np);
+		if (depth == 2 && of_node_cmp(np->name, "ports"))
+			break;
+	}
+	return np;
+}
+EXPORT_SYMBOL(of_graph_get_remote_port_parent);
+
+/**
+ * of_graph_get_remote_port() - get remote port node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote port node associated with remote endpoint node linked
+ *	   to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port(const struct device_node *node)
+{
+	struct device_node *np;
+
+	/* Get remote endpoint node. */
+	np = of_parse_phandle(node, "remote-endpoint", 0);
+	if (!np)
+		return NULL;
+	return of_get_next_parent(np);
+}
+EXPORT_SYMBOL(of_graph_get_remote_port);
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 758b4f8b30b7..024b8f99d480 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -15,9 +15,12 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/sizes.h>
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/libfdt.h>
 
 #include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
 #ifdef CONFIG_PPC
@@ -26,54 +29,6 @@
 
 #include <asm/page.h>
 
-char *of_fdt_get_string(struct boot_param_header *blob, u32 offset)
-{
-	return ((char *)blob) +
-		be32_to_cpu(blob->off_dt_strings) + offset;
-}
-
-/**
- * of_fdt_get_property - Given a node in the given flat blob, return
- * the property ptr
- */
-void *of_fdt_get_property(struct boot_param_header *blob,
-		       unsigned long node, const char *name,
-		       unsigned long *size)
-{
-	unsigned long p = node;
-
-	do {
-		u32 tag = be32_to_cpup((__be32 *)p);
-		u32 sz, noff;
-		const char *nstr;
-
-		p += 4;
-		if (tag == OF_DT_NOP)
-			continue;
-		if (tag != OF_DT_PROP)
-			return NULL;
-
-		sz = be32_to_cpup((__be32 *)p);
-		noff = be32_to_cpup((__be32 *)(p + 4));
-		p += 8;
-		if (be32_to_cpu(blob->version) < 0x10)
-			p = ALIGN(p, sz >= 8 ? 8 : 4);
-
-		nstr = of_fdt_get_string(blob, noff);
-		if (nstr == NULL) {
-			pr_warning("Can't find property index name !\n");
-			return NULL;
-		}
-		if (strcmp(name, nstr) == 0) {
-			if (size)
-				*size = sz;
-			return (void *)p;
-		}
-		p += sz;
-		p = ALIGN(p, 4);
-	} while (1);
-}
-
 /**
  * of_fdt_is_compatible - Return true if given node from the given blob has
  * compat in its compatible list
@@ -88,9 +43,10 @@ int of_fdt_is_compatible(struct boot_param_header *blob,
 		      unsigned long node, const char *compat)
 {
 	const char *cp;
-	unsigned long cplen, l, score = 0;
+	int cplen;
+	unsigned long l, score = 0;
 
-	cp = of_fdt_get_property(blob, node, "compatible", &cplen);
+	cp = fdt_getprop(blob, node, "compatible", &cplen);
 	if (cp == NULL)
 		return 0;
 	while (cplen > 0) {
@@ -149,28 +105,27 @@ static void *unflatten_dt_alloc(void **mem, unsigned long size,
  */
 static void * unflatten_dt_node(struct boot_param_header *blob,
 				void *mem,
-				void **p,
+				int *poffset,
 				struct device_node *dad,
 				struct device_node ***allnextpp,
 				unsigned long fpsize)
 {
+	const __be32 *p;
 	struct device_node *np;
 	struct property *pp, **prev_pp = NULL;
-	char *pathp;
-	u32 tag;
+	const char *pathp;
 	unsigned int l, allocl;
+	static int depth = 0;
+	int old_depth;
+	int offset;
 	int has_name = 0;
 	int new_format = 0;
 
-	tag = be32_to_cpup(*p);
-	if (tag != OF_DT_BEGIN_NODE) {
-		pr_err("Weird tag at start of node: %x\n", tag);
+	pathp = fdt_get_name(blob, *poffset, &l);
+	if (!pathp)
 		return mem;
-	}
-	*p += 4;
-	pathp = *p;
-	l = allocl = strlen(pathp) + 1;
-	*p = PTR_ALIGN(*p + l, 4);
+
+	allocl = l++;
 
 	/* version 0x10 has a more compact unit name here instead of the full
 	 * path. we accumulate the full path size using "fpsize", we'll rebuild
@@ -188,7 +143,7 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 			fpsize = 1;
 			allocl = 2;
 			l = 1;
-			*pathp = '\0';
+			pathp = "";
 		} else {
 			/* account for '/' and path size minus terminal 0
 			 * already in 'l'
@@ -235,32 +190,23 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 		kref_init(&np->kref);
 	}
 	/* process properties */
-	while (1) {
-		u32 sz, noff;
-		char *pname;
-
-		tag = be32_to_cpup(*p);
-		if (tag == OF_DT_NOP) {
-			*p += 4;
-			continue;
-		}
-		if (tag != OF_DT_PROP)
+	for (offset = fdt_first_property_offset(blob, *poffset);
+	     (offset >= 0);
+	     (offset = fdt_next_property_offset(blob, offset))) {
+		const char *pname;
+		u32 sz;
+
+		if (!(p = fdt_getprop_by_offset(blob, offset, &pname, &sz))) {
+			offset = -FDT_ERR_INTERNAL;
 			break;
-		*p += 4;
-		sz = be32_to_cpup(*p);
-		noff = be32_to_cpup(*p + 4);
-		*p += 8;
-		if (be32_to_cpu(blob->version) < 0x10)
-			*p = PTR_ALIGN(*p, sz >= 8 ? 8 : 4);
-
-		pname = of_fdt_get_string(blob, noff);
+		}
+
 		if (pname == NULL) {
 			pr_info("Can't find property name in list !\n");
 			break;
 		}
 		if (strcmp(pname, "name") == 0)
 			has_name = 1;
-		l = strlen(pname) + 1;
 		pp = unflatten_dt_alloc(&mem, sizeof(struct property),
 					__alignof__(struct property));
 		if (allnextpp) {
@@ -272,26 +218,25 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 			if ((strcmp(pname, "phandle") == 0) ||
 			    (strcmp(pname, "linux,phandle") == 0)) {
 				if (np->phandle == 0)
-					np->phandle = be32_to_cpup((__be32*)*p);
+					np->phandle = be32_to_cpup(p);
 			}
 			/* And we process the "ibm,phandle" property
 			 * used in pSeries dynamic device tree
 			 * stuff */
 			if (strcmp(pname, "ibm,phandle") == 0)
-				np->phandle = be32_to_cpup((__be32 *)*p);
-			pp->name = pname;
+				np->phandle = be32_to_cpup(p);
+			pp->name = (char *)pname;
 			pp->length = sz;
-			pp->value = *p;
+			pp->value = (__be32 *)p;
 			*prev_pp = pp;
 			prev_pp = &pp->next;
 		}
-		*p = PTR_ALIGN((*p) + sz, 4);
 	}
 	/* with version 0x10 we may not have the name property, recreate
 	 * it here from the unit name if absent
 	 */
 	if (!has_name) {
-		char *p1 = pathp, *ps = pathp, *pa = NULL;
+		const char *p1 = pathp, *ps = pathp, *pa = NULL;
 		int sz;
 
 		while (*p1) {
@@ -328,19 +273,18 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 		if (!np->type)
 			np->type = "<NULL>";
 	}
-	while (tag == OF_DT_BEGIN_NODE || tag == OF_DT_NOP) {
-		if (tag == OF_DT_NOP)
-			*p += 4;
-		else
-			mem = unflatten_dt_node(blob, mem, p, np, allnextpp,
-						fpsize);
-		tag = be32_to_cpup(*p);
-	}
-	if (tag != OF_DT_END_NODE) {
-		pr_err("Weird tag at end of node: %x\n", tag);
-		return mem;
-	}
-	*p += 4;
+
+	old_depth = depth;
+	*poffset = fdt_next_node(blob, *poffset, &depth);
+	if (depth < 0)
+		depth = 0;
+	while (*poffset > 0 && depth > old_depth)
+		mem = unflatten_dt_node(blob, mem, poffset, np, allnextpp,
+					fpsize);
+
+	if (*poffset < 0 && *poffset != -FDT_ERR_NOTFOUND)
+		pr_err("unflatten: error %d processing FDT\n", *poffset);
+
 	return mem;
 }
 
@@ -361,7 +305,8 @@ static void __unflatten_device_tree(struct boot_param_header *blob,
 			     void * (*dt_alloc)(u64 size, u64 align))
 {
 	unsigned long size;
-	void *start, *mem;
+	int start;
+	void *mem;
 	struct device_node **allnextp = mynodes;
 
 	pr_debug(" -> unflatten_device_tree()\n");
@@ -382,7 +327,7 @@ static void __unflatten_device_tree(struct boot_param_header *blob,
 	}
 
 	/* First pass, scan for size */
-	start = ((void *)blob) + be32_to_cpu(blob->off_dt_struct);
+	start = 0;
 	size = (unsigned long)unflatten_dt_node(blob, 0, &start, NULL, NULL, 0);
 	size = ALIGN(size, 4);
 
@@ -397,10 +342,8 @@ static void __unflatten_device_tree(struct boot_param_header *blob,
 	pr_debug("  unflattening %p...\n", mem);
 
 	/* Second pass, do actual unflattening */
-	start = ((void *)blob) + be32_to_cpu(blob->off_dt_struct);
+	start = 0;
 	unflatten_dt_node(blob, mem, &start, NULL, &allnextp, 0);
-	if (be32_to_cpup(start) != OF_DT_END)
-		pr_warning("Weird tag at end of tree: %08x\n", be32_to_cpup(start));
 	if (be32_to_cpup(mem + size) != 0xdeadbeef)
 		pr_warning("End of tree marker overwritten: %08x\n",
 			   be32_to_cpup(mem + size));
@@ -440,6 +383,129 @@ struct boot_param_header *initial_boot_params;
 #ifdef CONFIG_OF_EARLY_FLATTREE
 
 /**
+ * res_mem_reserve_reg() - reserve all memory described in 'reg' property
+ */
+static int __init __reserved_mem_reserve_reg(unsigned long node,
+					     const char *uname)
+{
+	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+	phys_addr_t base, size;
+	int len;
+	const __be32 *prop;
+	int nomap, first = 1;
+
+	prop = of_get_flat_dt_prop(node, "reg", &len);
+	if (!prop)
+		return -ENOENT;
+
+	if (len && len % t_len != 0) {
+		pr_err("Reserved memory: invalid reg property in '%s', skipping node.\n",
+		       uname);
+		return -EINVAL;
+	}
+
+	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+	while (len >= t_len) {
+		base = dt_mem_next_cell(dt_root_addr_cells, &prop);
+		size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+		if (base && size &&
+		    early_init_dt_reserve_memory_arch(base, size, nomap) == 0)
+			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+		else
+			pr_info("Reserved memory: failed to reserve memory for node '%s': base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+
+		len -= t_len;
+		if (first) {
+			fdt_reserved_mem_save_node(node, uname, base, size);
+			first = 0;
+		}
+	}
+	return 0;
+}
+
+/**
+ * __reserved_mem_check_root() - check if #size-cells, #address-cells provided
+ * in /reserved-memory matches the values supported by the current implementation,
+ * also check if ranges property has been provided
+ */
+static int __init __reserved_mem_check_root(unsigned long node)
+{
+	const __be32 *prop;
+
+	prop = of_get_flat_dt_prop(node, "#size-cells", NULL);
+	if (!prop || be32_to_cpup(prop) != dt_root_size_cells)
+		return -EINVAL;
+
+	prop = of_get_flat_dt_prop(node, "#address-cells", NULL);
+	if (!prop || be32_to_cpup(prop) != dt_root_addr_cells)
+		return -EINVAL;
+
+	prop = of_get_flat_dt_prop(node, "ranges", NULL);
+	if (!prop)
+		return -EINVAL;
+	return 0;
+}
+
+/**
+ * fdt_scan_reserved_mem() - scan a single FDT node for reserved memory
+ */
+static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
+					  int depth, void *data)
+{
+	static int found;
+	const char *status;
+	int err;
+
+	if (!found && depth == 1 && strcmp(uname, "reserved-memory") == 0) {
+		if (__reserved_mem_check_root(node) != 0) {
+			pr_err("Reserved memory: unsupported node format, ignoring\n");
+			/* break scan */
+			return 1;
+		}
+		found = 1;
+		/* scan next node */
+		return 0;
+	} else if (!found) {
+		/* scan next node */
+		return 0;
+	} else if (found && depth < 2) {
+		/* scanning of /reserved-memory has been finished */
+		return 1;
+	}
+
+	status = of_get_flat_dt_prop(node, "status", NULL);
+	if (status && strcmp(status, "okay") != 0 && strcmp(status, "ok") != 0)
+		return 0;
+
+	err = __reserved_mem_reserve_reg(node, uname);
+	if (err == -ENOENT && of_get_flat_dt_prop(node, "size", NULL))
+		fdt_reserved_mem_save_node(node, uname, 0, 0);
+
+	/* scan next node */
+	return 0;
+}
+
+/**
+ * early_init_fdt_scan_reserved_mem() - create reserved memory regions
+ *
+ * This function grabs memory from early allocator for device exclusive use
+ * defined in device tree structures. It should be called by arch specific code
+ * once the early allocator (i.e. memblock) has been fully activated.
+ */
+void __init early_init_fdt_scan_reserved_mem(void)
+{
+	if (!initial_boot_params)
+		return;
+
+	of_scan_flat_dt(__fdt_scan_reserved_mem, NULL);
+	fdt_init_reserved_mem();
+}
+
+/**
  * of_scan_flat_dt - scan flattened tree blob and call callback on each.
  * @it: callback function
  * @data: context data pointer
@@ -453,47 +519,19 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
 				     void *data),
 			   void *data)
 {
-	unsigned long p = ((unsigned long)initial_boot_params) +
-		be32_to_cpu(initial_boot_params->off_dt_struct);
-	int rc = 0;
-	int depth = -1;
-
-	do {
-		u32 tag = be32_to_cpup((__be32 *)p);
-		const char *pathp;
-
-		p += 4;
-		if (tag == OF_DT_END_NODE) {
-			depth--;
-			continue;
-		}
-		if (tag == OF_DT_NOP)
-			continue;
-		if (tag == OF_DT_END)
-			break;
-		if (tag == OF_DT_PROP) {
-			u32 sz = be32_to_cpup((__be32 *)p);
-			p += 8;
-			if (be32_to_cpu(initial_boot_params->version) < 0x10)
-				p = ALIGN(p, sz >= 8 ? 8 : 4);
-			p += sz;
-			p = ALIGN(p, 4);
-			continue;
-		}
-		if (tag != OF_DT_BEGIN_NODE) {
-			pr_err("Invalid tag %x in flat device tree!\n", tag);
-			return -EINVAL;
-		}
-		depth++;
-		pathp = (char *)p;
-		p = ALIGN(p + strlen(pathp) + 1, 4);
+	const void *blob = initial_boot_params;
+	const char *pathp;
+	int offset, rc = 0, depth = -1;
+
+        for (offset = fdt_next_node(blob, -1, &depth);
+             offset >= 0 && depth >= 0 && !rc;
+             offset = fdt_next_node(blob, offset, &depth)) {
+
+		pathp = fdt_get_name(blob, offset, NULL);
 		if (*pathp == '/')
 			pathp = kbasename(pathp);
-		rc = it(p, pathp, depth, data);
-		if (rc != 0)
-			break;
-	} while (1);
-
+		rc = it(offset, pathp, depth, data);
+	}
 	return rc;
 }
 
@@ -502,14 +540,7 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
  */
 unsigned long __init of_get_flat_dt_root(void)
 {
-	unsigned long p = ((unsigned long)initial_boot_params) +
-		be32_to_cpu(initial_boot_params->off_dt_struct);
-
-	while (be32_to_cpup((__be32 *)p) == OF_DT_NOP)
-		p += 4;
-	BUG_ON(be32_to_cpup((__be32 *)p) != OF_DT_BEGIN_NODE);
-	p += 4;
-	return ALIGN(p + strlen((char *)p) + 1, 4);
+	return 0;
 }
 
 /**
@@ -518,10 +549,10 @@ unsigned long __init of_get_flat_dt_root(void)
  * This function can be used within scan_flattened_dt callback to get
  * access to properties
  */
-void *__init of_get_flat_dt_prop(unsigned long node, const char *name,
-				 unsigned long *size)
+const void *__init of_get_flat_dt_prop(unsigned long node, const char *name,
+				       int *size)
 {
-	return of_fdt_get_property(initial_boot_params, node, name, size);
+	return fdt_getprop(initial_boot_params, node, name, size);
 }
 
 /**
@@ -551,73 +582,6 @@ struct fdt_scan_status {
 	void *data;
 };
 
-/**
- * fdt_scan_node_by_path - iterator for of_scan_flat_dt_by_path function
- */
-static int __init fdt_scan_node_by_path(unsigned long node, const char *uname,
-					int depth, void *data)
-{
-	struct fdt_scan_status *st = data;
-
-	/*
-	 * if scan at the requested fdt node has been completed,
-	 * return -ENXIO to abort further scanning
-	 */
-	if (depth <= st->depth)
-		return -ENXIO;
-
-	/* requested fdt node has been found, so call iterator function */
-	if (st->found)
-		return st->iterator(node, uname, depth, st->data);
-
-	/* check if scanning automata is entering next level of fdt nodes */
-	if (depth == st->depth + 1 &&
-	    strncmp(st->name, uname, st->namelen) == 0 &&
-	    uname[st->namelen] == 0) {
-		st->depth += 1;
-		if (st->name[st->namelen] == 0) {
-			st->found = 1;
-		} else {
-			const char *next = st->name + st->namelen + 1;
-			st->name = next;
-			st->namelen = strcspn(next, "/");
-		}
-		return 0;
-	}
-
-	/* scan next fdt node */
-	return 0;
-}
-
-/**
- * of_scan_flat_dt_by_path - scan flattened tree blob and call callback on each
- *			     child of the given path.
- * @path: path to start searching for children
- * @it: callback function
- * @data: context data pointer
- *
- * This function is used to scan the flattened device-tree starting from the
- * node given by path. It is used to extract information (like reserved
- * memory), which is required on ealy boot before we can unflatten the tree.
- */
-int __init of_scan_flat_dt_by_path(const char *path,
-	int (*it)(unsigned long node, const char *name, int depth, void *data),
-	void *data)
-{
-	struct fdt_scan_status st = {path, 0, -1, 0, it, data};
-	int ret = 0;
-
-	if (initial_boot_params)
-                ret = of_scan_flat_dt(fdt_scan_node_by_path, &st);
-
-	if (!st.found)
-		return -ENOENT;
-	else if (ret == -ENXIO)	/* scan has been completed */
-		return 0;
-	else
-		return ret;
-}
-
 const char * __init of_flat_dt_get_machine_name(void)
 {
 	const char *name;
@@ -657,7 +621,7 @@ const void * __init of_flat_dt_match_machine(const void *default_match,
 	}
 	if (!best_data) {
 		const char *prop;
-		long size;
+		int size;
 
 		pr_err("\n unrecognized device tree list:\n[ ");
 
@@ -686,8 +650,8 @@ const void * __init of_flat_dt_match_machine(const void *default_match,
 static void __init early_init_dt_check_for_initrd(unsigned long node)
 {
 	u64 start, end;
-	unsigned long len;
-	__be32 *prop;
+	int len;
+	const __be32 *prop;
 
 	pr_debug("Looking for initrd properties... ");
 
@@ -720,7 +684,7 @@ static inline void early_init_dt_check_for_initrd(unsigned long node)
 int __init early_init_dt_scan_root(unsigned long node, const char *uname,
 				   int depth, void *data)
 {
-	__be32 *prop;
+	const __be32 *prop;
 
 	if (depth != 0)
 		return 0;
@@ -742,9 +706,9 @@ int __init early_init_dt_scan_root(unsigned long node, const char *uname,
 	return 1;
 }
 
-u64 __init dt_mem_next_cell(int s, __be32 **cellp)
+u64 __init dt_mem_next_cell(int s, const __be32 **cellp)
 {
-	__be32 *p = *cellp;
+	const __be32 *p = *cellp;
 
 	*cellp = p + s;
 	return of_read_number(p, s);
@@ -756,9 +720,9 @@ u64 __init dt_mem_next_cell(int s, __be32 **cellp)
 int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 				     int depth, void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	__be32 *reg, *endp;
-	unsigned long l;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *reg, *endp;
+	int l;
 
 	/* We are scanning "memory" nodes only */
 	if (type == NULL) {
@@ -779,7 +743,7 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 
 	endp = reg + (l / sizeof(__be32));
 
-	pr_debug("memory scan node %s, reg size %ld, data: %x %x %x %x,\n",
+	pr_debug("memory scan node %s, reg size %d, data: %x %x %x %x,\n",
 	    uname, l, reg[0], reg[1], reg[2], reg[3]);
 
 	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
@@ -802,8 +766,8 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data)
 {
-	unsigned long l;
-	char *p;
+	int l;
+	const char *p;
 
 	pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
 
@@ -856,6 +820,16 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+					phys_addr_t size, bool nomap)
+{
+	if (memblock_is_region_reserved(base, size))
+		return -EBUSY;
+	if (nomap)
+		return memblock_remove(base, size);
+	return memblock_reserve(base, size);
+}
+
 /*
  * called from unflatten_device_tree() to bootstrap devicetree itself
  * Architectures can override this definition if memblock isn't used
@@ -864,6 +838,14 @@ void * __init __weak early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
 	return __va(memblock_alloc(size, align));
 }
+#else
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+					phys_addr_t size, bool nomap)
+{
+	pr_err("Reserved memory not supported, ignoring range 0x%llx - 0x%llx%s\n",
+		  base, size, nomap ? " (nomap)" : "");
+	return -ENOSYS;
+}
 #endif
 
 bool __init early_init_dt_scan(void *params)
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 9bcf2cf19357..48f20ff1add9 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -301,16 +301,17 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 	/* Get the reg property (if any) */
 	addr = of_get_property(device, "reg", NULL);
 
+	/* Try the new-style interrupts-extended first */
+	res = of_parse_phandle_with_args(device, "interrupts-extended",
+					"#interrupt-cells", index, out_irq);
+	if (!res)
+		return of_irq_parse_raw(addr, out_irq);
+
 	/* Get the interrupts property */
 	intspec = of_get_property(device, "interrupts", &intlen);
-	if (intspec == NULL) {
-		/* Try the new-style interrupts-extended */
-		res = of_parse_phandle_with_args(device, "interrupts-extended",
-						"#interrupt-cells", index, out_irq);
-		if (res)
-			return -EINVAL;
-		return of_irq_parse_raw(addr, out_irq);
-	}
+	if (intspec == NULL)
+		return -EINVAL;
+
 	intlen /= sizeof(*intspec);
 
 	pr_debug(" intspec=%d intlen=%d\n", be32_to_cpup(intspec), intlen);
@@ -380,6 +381,32 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
 EXPORT_SYMBOL_GPL(of_irq_to_resource);
 
 /**
+ * of_irq_get - Decode a node's IRQ and return it as a Linux irq number
+ * @dev: pointer to device tree node
+ * @index: zero-based index of the irq
+ *
+ * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
+ * is not yet created.
+ *
+ */
+int of_irq_get(struct device_node *dev, int index)
+{
+	int rc;
+	struct of_phandle_args oirq;
+	struct irq_domain *domain;
+
+	rc = of_irq_parse_one(dev, index, &oirq);
+	if (rc)
+		return rc;
+
+	domain = irq_find_host(oirq.np);
+	if (!domain)
+		return -EPROBE_DEFER;
+
+	return irq_create_of_mapping(&oirq);
+}
+
+/**
  * of_irq_count - Count the number of IRQs a node uses
  * @dev: pointer to device tree node
  */
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
new file mode 100644
index 000000000000..e420eb52e5c9
--- /dev/null
+++ b/drivers/of/of_reserved_mem.c
@@ -0,0 +1,217 @@
+/*
+ * Device tree based initialization code for reserved memory.
+ *
+ * Copyright (c) 2013, The Linux Foundation. All Rights Reserved.
+ * Copyright (c) 2013,2014 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ * Author: Marek Szyprowski <m.szyprowski@samsung.com>
+ * Author: Josh Cartwright <joshc@codeaurora.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/mm.h>
+#include <linux/sizes.h>
+#include <linux/of_reserved_mem.h>
+
+#define MAX_RESERVED_REGIONS	16
+static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
+static int reserved_mem_count;
+
+#if defined(CONFIG_HAVE_MEMBLOCK)
+#include <linux/memblock.h>
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+	phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+	phys_addr_t *res_base)
+{
+	/*
+	 * We use __memblock_alloc_base() because memblock_alloc_base()
+	 * panic()s on allocation failure.
+	 */
+	phys_addr_t base = __memblock_alloc_base(size, align, end);
+	if (!base)
+		return -ENOMEM;
+
+	/*
+	 * Check if the allocated region fits in to start..end window
+	 */
+	if (base < start) {
+		memblock_free(base, size);
+		return -ENOMEM;
+	}
+
+	*res_base = base;
+	if (nomap)
+		return memblock_remove(base, size);
+	return 0;
+}
+#else
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+	phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+	phys_addr_t *res_base)
+{
+	pr_err("Reserved memory not supported, ignoring region 0x%llx%s\n",
+		  size, nomap ? " (nomap)" : "");
+	return -ENOSYS;
+}
+#endif
+
+/**
+ * res_mem_save_node() - save fdt node for second pass initialization
+ */
+void __init fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+				      phys_addr_t base, phys_addr_t size)
+{
+	struct reserved_mem *rmem = &reserved_mem[reserved_mem_count];
+
+	if (reserved_mem_count == ARRAY_SIZE(reserved_mem)) {
+		pr_err("Reserved memory: not enough space all defined regions.\n");
+		return;
+	}
+
+	rmem->fdt_node = node;
+	rmem->name = uname;
+	rmem->base = base;
+	rmem->size = size;
+
+	reserved_mem_count++;
+	return;
+}
+
+/**
+ * res_mem_alloc_size() - allocate reserved memory described by 'size', 'align'
+ *			  and 'alloc-ranges' properties
+ */
+static int __init __reserved_mem_alloc_size(unsigned long node,
+	const char *uname, phys_addr_t *res_base, phys_addr_t *res_size)
+{
+	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+	phys_addr_t start = 0, end = 0;
+	phys_addr_t base = 0, align = 0, size;
+	int len;
+	const __be32 *prop;
+	int nomap;
+	int ret;
+
+	prop = of_get_flat_dt_prop(node, "size", &len);
+	if (!prop)
+		return -EINVAL;
+
+	if (len != dt_root_size_cells * sizeof(__be32)) {
+		pr_err("Reserved memory: invalid size property in '%s' node.\n",
+				uname);
+		return -EINVAL;
+	}
+	size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+	prop = of_get_flat_dt_prop(node, "alignment", &len);
+	if (prop) {
+		if (len != dt_root_addr_cells * sizeof(__be32)) {
+			pr_err("Reserved memory: invalid alignment property in '%s' node.\n",
+				uname);
+			return -EINVAL;
+		}
+		align = dt_mem_next_cell(dt_root_addr_cells, &prop);
+	}
+
+	prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
+	if (prop) {
+
+		if (len % t_len != 0) {
+			pr_err("Reserved memory: invalid alloc-ranges property in '%s', skipping node.\n",
+			       uname);
+			return -EINVAL;
+		}
+
+		base = 0;
+
+		while (len > 0) {
+			start = dt_mem_next_cell(dt_root_addr_cells, &prop);
+			end = start + dt_mem_next_cell(dt_root_size_cells,
+						       &prop);
+
+			ret = early_init_dt_alloc_reserved_memory_arch(size,
+					align, start, end, nomap, &base);
+			if (ret == 0) {
+				pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+					uname, &base,
+					(unsigned long)size / SZ_1M);
+				break;
+			}
+			len -= t_len;
+		}
+
+	} else {
+		ret = early_init_dt_alloc_reserved_memory_arch(size, align,
+							0, 0, nomap, &base);
+		if (ret == 0)
+			pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+	}
+
+	if (base == 0) {
+		pr_info("Reserved memory: failed to allocate memory for node '%s'\n",
+			uname);
+		return -ENOMEM;
+	}
+
+	*res_base = base;
+	*res_size = size;
+
+	return 0;
+}
+
+static const struct of_device_id __rmem_of_table_sentinel
+	__used __section(__reservedmem_of_table_end);
+
+/**
+ * res_mem_init_node() - call region specific reserved memory init code
+ */
+static int __init __reserved_mem_init_node(struct reserved_mem *rmem)
+{
+	extern const struct of_device_id __reservedmem_of_table[];
+	const struct of_device_id *i;
+
+	for (i = __reservedmem_of_table; i < &__rmem_of_table_sentinel; i++) {
+		reservedmem_of_init_fn initfn = i->data;
+		const char *compat = i->compatible;
+
+		if (!of_flat_dt_is_compatible(rmem->fdt_node, compat))
+			continue;
+
+		if (initfn(rmem, rmem->fdt_node, rmem->name) == 0) {
+			pr_info("Reserved memory: initialized node %s, compatible id %s\n",
+				rmem->name, compat);
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
+/**
+ * fdt_init_reserved_mem - allocate and init all saved reserved memory regions
+ */
+void __init fdt_init_reserved_mem(void)
+{
+	int i;
+	for (i = 0; i < reserved_mem_count; i++) {
+		struct reserved_mem *rmem = &reserved_mem[i];
+		unsigned long node = rmem->fdt_node;
+		int err = 0;
+
+		if (rmem->size == 0)
+			err = __reserved_mem_alloc_size(node, rmem->name,
+						 &rmem->base, &rmem->size);
+		if (err == 0)
+			__reserved_mem_init_node(rmem);
+	}
+}
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 404d1daebefa..bd47fbc53dc9 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -168,7 +168,9 @@ struct platform_device *of_device_alloc(struct device_node *np,
 			rc = of_address_to_resource(np, i, res);
 			WARN_ON(rc);
 		}
-		WARN_ON(of_irq_to_resource_table(np, res, num_irq) != num_irq);
+		if (of_irq_to_resource_table(np, res, num_irq) != num_irq)
+			pr_debug("not all legacy IRQ resources mapped for %s\n",
+				 np->name);
 	}
 
 	dev->dev.of_node = of_node_get(np);
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index 6643d1920985..70c61d75b75e 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -132,8 +132,9 @@ static void __init of_selftest_parse_phandle_with_args(void)
 	selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
 }
 
-static void __init of_selftest_property_match_string(void)
+static void __init of_selftest_property_string(void)
 {
+	const char *strings[4];
 	struct device_node *np;
 	int rc;
 
@@ -150,13 +151,66 @@ static void __init of_selftest_property_match_string(void)
 	rc = of_property_match_string(np, "phandle-list-names", "third");
 	selftest(rc == 2, "third expected:0 got:%i\n", rc);
 	rc = of_property_match_string(np, "phandle-list-names", "fourth");
-	selftest(rc == -ENODATA, "unmatched string; rc=%i", rc);
+	selftest(rc == -ENODATA, "unmatched string; rc=%i\n", rc);
 	rc = of_property_match_string(np, "missing-property", "blah");
-	selftest(rc == -EINVAL, "missing property; rc=%i", rc);
+	selftest(rc == -EINVAL, "missing property; rc=%i\n", rc);
 	rc = of_property_match_string(np, "empty-property", "blah");
-	selftest(rc == -ENODATA, "empty property; rc=%i", rc);
+	selftest(rc == -ENODATA, "empty property; rc=%i\n", rc);
 	rc = of_property_match_string(np, "unterminated-string", "blah");
-	selftest(rc == -EILSEQ, "unterminated string; rc=%i", rc);
+	selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+
+	/* of_property_count_strings() tests */
+	rc = of_property_count_strings(np, "string-property");
+	selftest(rc == 1, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_count_strings(np, "phandle-list-names");
+	selftest(rc == 3, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_count_strings(np, "unterminated-string");
+	selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+	rc = of_property_count_strings(np, "unterminated-string-list");
+	selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc);
+
+	/* of_property_read_string_index() tests */
+	rc = of_property_read_string_index(np, "string-property", 0, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "foobar"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "string-property", 1, strings);
+	selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "phandle-list-names", 0, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "phandle-list-names", 1, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "second"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "phandle-list-names", 2, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "third"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "phandle-list-names", 3, strings);
+	selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "unterminated-string", 0, strings);
+	selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	rc = of_property_read_string_index(np, "unterminated-string-list", 0, strings);
+	selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[0] = NULL;
+	rc = of_property_read_string_index(np, "unterminated-string-list", 2, strings); /* should fail */
+	selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+	strings[1] = NULL;
+
+	/* of_property_read_string_array() tests */
+	rc = of_property_read_string_array(np, "string-property", strings, 4);
+	selftest(rc == 1, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_read_string_array(np, "phandle-list-names", strings, 4);
+	selftest(rc == 3, "Incorrect string count; rc=%i\n", rc);
+	rc = of_property_read_string_array(np, "unterminated-string", strings, 4);
+	selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+	/* -- An incorrectly formed string should cause a failure */
+	rc = of_property_read_string_array(np, "unterminated-string-list", strings, 4);
+	selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc);
+	/* -- parsing the correctly formed strings should still work: */
+	strings[2] = NULL;
+	rc = of_property_read_string_array(np, "unterminated-string-list", strings, 2);
+	selftest(rc == 2 && strings[2] == NULL, "of_property_read_string_array() failure; rc=%i\n", rc);
+	strings[1] = NULL;
+	rc = of_property_read_string_array(np, "phandle-list-names", strings, 1);
+	selftest(rc == 1 && strings[1] == NULL, "Overwrote end of string array; rc=%i, str='%s'\n", rc, strings[1]);
 }
 
 static void __init of_selftest_parse_interrupts(void)
@@ -379,7 +433,7 @@ static int __init of_selftest(void)
 
 	pr_info("start of selftest - you will see error messages\n");
 	of_selftest_parse_phandle_with_args();
-	of_selftest_property_match_string();
+	of_selftest_property_string();
 	of_selftest_parse_interrupts();
 	of_selftest_parse_interrupts_extended();
 	of_selftest_match_node();
diff --git a/drivers/of/testcase-data/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi
index 0007d3cd7dc2..eedee37d70d7 100644
--- a/drivers/of/testcase-data/tests-phandle.dtsi
+++ b/drivers/of/testcase-data/tests-phandle.dtsi
@@ -32,7 +32,9 @@
 				phandle-list-bad-args = <&provider2 1 0>,
 							<&provider3 0>;
 				empty-property;
+				string-property = "foobar";
 				unterminated-string = [40 41 42 43];
+				unterminated-string-list = "first", "second", [40 41 42 43];
 			};
 		};
 	};
diff --git a/drivers/parport/Kconfig b/drivers/parport/Kconfig
index 2872ece81f35..44333bd8f908 100644
--- a/drivers/parport/Kconfig
+++ b/drivers/parport/Kconfig
@@ -5,6 +5,12 @@
 # Parport configuration.
 #
 
+config ARCH_MIGHT_HAVE_PC_PARPORT
+	bool
+	help
+	  Select this config option from the architecture Kconfig if
+	  the architecture might have PC parallel port hardware.
+
 menuconfig PARPORT
 	tristate "Parallel port support"
 	depends on HAS_IOMEM
@@ -31,12 +37,6 @@ menuconfig PARPORT
 
 	  If unsure, say Y.
 
-config ARCH_MIGHT_HAVE_PC_PARPORT
-	bool
-	help
-	  Select this config option from the architecture Kconfig if
-	  the architecture might have PC parallel port hardware.
-
 if PARPORT
 
 config PARPORT_PC
diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c
index e8663a8c3406..ee082509b0ba 100644
--- a/drivers/pci/host/pci-imx6.c
+++ b/drivers/pci/host/pci-imx6.c
@@ -424,20 +424,40 @@ static void imx6_pcie_reset_phy(struct pcie_port *pp)
 
 static int imx6_pcie_link_up(struct pcie_port *pp)
 {
-	u32 rc, ltssm, rx_valid;
+	u32 rc, debug_r0, rx_valid;
+	int count = 5;
 
 	/*
-	 * Test if the PHY reports that the link is up and also that
-	 * the link training finished.  It might happen that the PHY
-	 * reports the link is already up, but the link training bit
-	 * is still set, so make sure to check the training is done
-	 * as well here.
+	 * Test if the PHY reports that the link is up and also that the LTSSM
+	 * training finished. There are three possible states of the link when
+	 * this code is called:
+	 * 1) The link is DOWN (unlikely)
+	 *     The link didn't come up yet for some reason. This usually means
+	 *     we have a real problem somewhere. Reset the PHY and exit. This
+	 *     state calls for inspection of the DEBUG registers.
+	 * 2) The link is UP, but still in LTSSM training
+	 *     Wait for the training to finish, which should take a very short
+	 *     time. If the training does not finish, we have a problem and we
+	 *     need to inspect the DEBUG registers. If the training does finish,
+	 *     the link is up and operating correctly.
+	 * 3) The link is UP and no longer in LTSSM training
+	 *     The link is up and operating correctly.
 	 */
-	rc = readl(pp->dbi_base + PCIE_PHY_DEBUG_R1);
-	if ((rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_UP) &&
-	    !(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_IN_TRAINING))
-		return 1;
-
+	while (1) {
+		rc = readl(pp->dbi_base + PCIE_PHY_DEBUG_R1);
+		if (!(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_UP))
+			break;
+		if (!(rc & PCIE_PHY_DEBUG_R1_XMLH_LINK_IN_TRAINING))
+			return 1;
+		if (!count--)
+			break;
+		dev_dbg(pp->dev, "Link is up, but still in training\n");
+		/*
+		 * Wait a little bit, then re-check if the link finished
+		 * the training.
+		 */
+		usleep_range(1000, 2000);
+	}
 	/*
 	 * From L0, initiate MAC entry to gen2 if EP/RC supports gen2.
 	 * Wait 2ms (LTSSM timeout is 24ms, PHY lock is ~5us in gen2).
@@ -446,15 +466,16 @@ static int imx6_pcie_link_up(struct pcie_port *pp)
 	 * to gen2 is stuck
 	 */
 	pcie_phy_read(pp->dbi_base, PCIE_PHY_RX_ASIC_OUT, &rx_valid);
-	ltssm = readl(pp->dbi_base + PCIE_PHY_DEBUG_R0) & 0x3F;
+	debug_r0 = readl(pp->dbi_base + PCIE_PHY_DEBUG_R0);
 
 	if (rx_valid & 0x01)
 		return 0;
 
-	if (ltssm != 0x0d)
+	if ((debug_r0 & 0x3f) != 0x0d)
 		return 0;
 
 	dev_err(pp->dev, "transition to gen2 is stuck, reset PHY!\n");
+	dev_dbg(pp->dev, "debug_r0=%08x debug_r1=%08x\n", debug_r0, rc);
 
 	imx6_pcie_reset_phy(pp);
 
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 0e79665afd44..97736674ddcd 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -291,6 +291,58 @@ static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port,
 	return PCIBIOS_SUCCESSFUL;
 }
 
+/*
+ * Remove windows, starting from the largest ones to the smallest
+ * ones.
+ */
+static void mvebu_pcie_del_windows(struct mvebu_pcie_port *port,
+				   phys_addr_t base, size_t size)
+{
+	while (size) {
+		size_t sz = 1 << (fls(size) - 1);
+
+		mvebu_mbus_del_window(base, sz);
+		base += sz;
+		size -= sz;
+	}
+}
+
+/*
+ * MBus windows can only have a power of two size, but PCI BARs do not
+ * have this constraint. Therefore, we have to split the PCI BAR into
+ * areas each having a power of two size. We start from the largest
+ * one (i.e highest order bit set in the size).
+ */
+static void mvebu_pcie_add_windows(struct mvebu_pcie_port *port,
+				   unsigned int target, unsigned int attribute,
+				   phys_addr_t base, size_t size,
+				   phys_addr_t remap)
+{
+	size_t size_mapped = 0;
+
+	while (size) {
+		size_t sz = 1 << (fls(size) - 1);
+		int ret;
+
+		ret = mvebu_mbus_add_window_remap_by_id(target, attribute, base,
+							sz, remap);
+		if (ret) {
+			dev_err(&port->pcie->pdev->dev,
+				"Could not create MBus window at 0x%x, size 0x%x: %d\n",
+				base, sz, ret);
+			mvebu_pcie_del_windows(port, base - size_mapped,
+					       size_mapped);
+			return;
+		}
+
+		size -= sz;
+		size_mapped += sz;
+		base += sz;
+		if (remap != MVEBU_MBUS_NO_REMAP)
+			remap += sz;
+	}
+}
+
 static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 {
 	phys_addr_t iobase;
@@ -302,8 +354,8 @@ static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 
 		/* If a window was configured, remove it */
 		if (port->iowin_base) {
-			mvebu_mbus_del_window(port->iowin_base,
-					      port->iowin_size);
+			mvebu_pcie_del_windows(port, port->iowin_base,
+					       port->iowin_size);
 			port->iowin_base = 0;
 			port->iowin_size = 0;
 		}
@@ -329,11 +381,11 @@ static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 	port->iowin_base = port->pcie->io.start + iobase;
 	port->iowin_size = ((0xFFF | ((port->bridge.iolimit & 0xF0) << 8) |
 			    (port->bridge.iolimitupper << 16)) -
-			    iobase);
+			    iobase) + 1;
 
-	mvebu_mbus_add_window_remap_by_id(port->io_target, port->io_attr,
-					  port->iowin_base, port->iowin_size,
-					  iobase);
+	mvebu_pcie_add_windows(port, port->io_target, port->io_attr,
+			       port->iowin_base, port->iowin_size,
+			       iobase);
 }
 
 static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
@@ -344,8 +396,8 @@ static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
 
 		/* If a window was configured, remove it */
 		if (port->memwin_base) {
-			mvebu_mbus_del_window(port->memwin_base,
-					      port->memwin_size);
+			mvebu_pcie_del_windows(port, port->memwin_base,
+					       port->memwin_size);
 			port->memwin_base = 0;
 			port->memwin_size = 0;
 		}
@@ -362,10 +414,11 @@ static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
 	port->memwin_base  = ((port->bridge.membase & 0xFFF0) << 16);
 	port->memwin_size  =
 		(((port->bridge.memlimit & 0xFFF0) << 16) | 0xFFFFF) -
-		port->memwin_base;
+		port->memwin_base + 1;
 
-	mvebu_mbus_add_window_by_id(port->mem_target, port->mem_attr,
-				    port->memwin_base, port->memwin_size);
+	mvebu_pcie_add_windows(port, port->mem_target, port->mem_attr,
+			       port->memwin_base, port->memwin_size,
+			       MVEBU_MBUS_NO_REMAP);
 }
 
 /*
@@ -721,14 +774,21 @@ static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 
 	/*
 	 * On the PCI-to-PCI bridge side, the I/O windows must have at
-	 * least a 64 KB size and be aligned on their size, and the
-	 * memory windows must have at least a 1 MB size and be
-	 * aligned on their size
+	 * least a 64 KB size and the memory windows must have at
+	 * least a 1 MB size. Moreover, MBus windows need to have a
+	 * base address aligned on their size, and their size must be
+	 * a power of two. This means that if the BAR doesn't have a
+	 * power of two size, several MBus windows will actually be
+	 * created. We need to ensure that the biggest MBus window
+	 * (which will be the first one) is aligned on its size, which
+	 * explains the rounddown_pow_of_two() being done here.
 	 */
 	if (res->flags & IORESOURCE_IO)
-		return round_up(start, max_t(resource_size_t, SZ_64K, size));
+		return round_up(start, max_t(resource_size_t, SZ_64K,
+					     rounddown_pow_of_two(size)));
 	else if (res->flags & IORESOURCE_MEM)
-		return round_up(start, max_t(resource_size_t, SZ_1M, size));
+		return round_up(start, max_t(resource_size_t, SZ_1M,
+					     rounddown_pow_of_two(size)));
 	else
 		return start;
 }
@@ -795,9 +855,9 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 	rangesz = pna + na + ns;
 	nranges = rlen / sizeof(__be32) / rangesz;
 
-	for (i = 0; i < nranges; i++) {
+	for (i = 0; i < nranges; i++, range += rangesz) {
 		u32 flags = of_read_number(range, 1);
-		u32 slot = of_read_number(range, 2);
+		u32 slot = of_read_number(range + 1, 1);
 		u64 cpuaddr = of_read_number(range + na, pna);
 		unsigned long rtype;
 
@@ -805,14 +865,14 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 			rtype = IORESOURCE_IO;
 		else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32)
 			rtype = IORESOURCE_MEM;
+		else
+			continue;
 
 		if (slot == PCI_SLOT(devfn) && type == rtype) {
 			*tgt = DT_CPUADDR_TO_TARGET(cpuaddr);
 			*attr = DT_CPUADDR_TO_ATTR(cpuaddr);
 			return 0;
 		}
-
-		range += rangesz;
 	}
 
 	return -ENOENT;
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 17ce88f79d2b..f173dd09fce4 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -522,13 +522,13 @@ static void dw_pcie_prog_viewport_cfg1(struct pcie_port *pp, u32 busdev)
 	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
 			  PCIE_ATU_VIEWPORT);
 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG1, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 	dw_pcie_writel_rc(pp, pp->cfg1_base, PCIE_ATU_LOWER_BASE);
 	dw_pcie_writel_rc(pp, (pp->cfg1_base >> 32), PCIE_ATU_UPPER_BASE);
 	dw_pcie_writel_rc(pp, pp->cfg1_base + pp->config.cfg1_size - 1,
 			  PCIE_ATU_LIMIT);
 	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
 	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 }
 
 static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
@@ -537,7 +537,6 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
 	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0,
 			  PCIE_ATU_VIEWPORT);
 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_MEM, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 	dw_pcie_writel_rc(pp, pp->mem_base, PCIE_ATU_LOWER_BASE);
 	dw_pcie_writel_rc(pp, (pp->mem_base >> 32), PCIE_ATU_UPPER_BASE);
 	dw_pcie_writel_rc(pp, pp->mem_base + pp->config.mem_size - 1,
@@ -545,6 +544,7 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
 	dw_pcie_writel_rc(pp, pp->config.mem_bus_addr, PCIE_ATU_LOWER_TARGET);
 	dw_pcie_writel_rc(pp, upper_32_bits(pp->config.mem_bus_addr),
 			  PCIE_ATU_UPPER_TARGET);
+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 }
 
 static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
@@ -553,7 +553,6 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
 	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
 			  PCIE_ATU_VIEWPORT);
 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_IO, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 	dw_pcie_writel_rc(pp, pp->io_base, PCIE_ATU_LOWER_BASE);
 	dw_pcie_writel_rc(pp, (pp->io_base >> 32), PCIE_ATU_UPPER_BASE);
 	dw_pcie_writel_rc(pp, pp->io_base + pp->config.io_size - 1,
@@ -561,6 +560,7 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
 	dw_pcie_writel_rc(pp, pp->config.io_bus_addr, PCIE_ATU_LOWER_TARGET);
 	dw_pcie_writel_rc(pp, upper_32_bits(pp->config.io_bus_addr),
 			  PCIE_ATU_UPPER_TARGET);
+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 }
 
 static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
@@ -800,7 +800,7 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 
 	/* setup RC BARs */
 	dw_pcie_writel_rc(pp, 0x00000004, PCI_BASE_ADDRESS_0);
-	dw_pcie_writel_rc(pp, 0x00000004, PCI_BASE_ADDRESS_1);
+	dw_pcie_writel_rc(pp, 0x00000000, PCI_BASE_ADDRESS_1);
 
 	/* setup interrupt pins */
 	dw_pcie_readl_rc(pp, PCI_INTERRUPT_LINE, &val);
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 58499277903a..6efc2ec5e4db 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -282,8 +282,8 @@ static int board_added(struct slot *p_slot)
 		return WRONG_BUS_FREQUENCY;
 	}
 
-	bsp = ctrl->pci_dev->bus->cur_bus_speed;
-	msp = ctrl->pci_dev->bus->max_bus_speed;
+	bsp = ctrl->pci_dev->subordinate->cur_bus_speed;
+	msp = ctrl->pci_dev->subordinate->max_bus_speed;
 
 	/* Check if there are other slots or devices on the same bus */
 	if (!list_empty(&ctrl->pci_dev->subordinate->devices))
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 955ab7990c5b..ced17f2ac782 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -414,7 +414,7 @@ static void free_msi_irqs(struct pci_dev *dev)
 	if (dev->msi_irq_groups) {
 		sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups);
 		msi_attrs = dev->msi_irq_groups[0]->attrs;
-		list_for_each_entry(entry, &dev->msi_list, list) {
+		while (msi_attrs[count]) {
 			dev_attr = container_of(msi_attrs[count],
 						struct device_attribute, attr);
 			kfree(dev_attr->attr.name);
@@ -599,6 +599,20 @@ error_attrs:
 	return ret;
 }
 
+static int msi_verify_entries(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		if (!dev->no_64bit_msi || !entry->msg.address_hi)
+			continue;
+		dev_err(&dev->dev, "Device has broken 64-bit MSI but arch"
+			" tried to assign one above 4G\n");
+		return -EIO;
+	}
+	return 0;
+}
+
 /**
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
@@ -652,6 +666,13 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 		return ret;
 	}
 
+	ret = msi_verify_entries(dev);
+	if (ret) {
+		msi_mask_irq(entry, mask, ~mask);
+		free_msi_irqs(dev);
+		return ret;
+	}
+
 	ret = populate_msi_sysfs(dev);
 	if (ret) {
 		msi_mask_irq(entry, mask, ~mask);
@@ -767,6 +788,11 @@ static int msix_capability_init(struct pci_dev *dev,
 	if (ret)
 		goto out_avail;
 
+	/* Check if all MSI entries honor device restrictions */
+	ret = msi_verify_entries(dev);
+	if (ret)
+		goto out_free;
+
 	/*
 	 * Some devices require MSI-X to be enabled before we can touch the
 	 * MSI-X registers.  We need to mask all the vectors to prevent
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
index 45113daaa778..e27a3dc9f4e8 100644
--- a/drivers/pci/pci-label.c
+++ b/drivers/pci/pci-label.c
@@ -168,8 +168,8 @@ enum acpi_attr_enum {
 static void dsm_label_utf16s_to_utf8s(union acpi_object *obj, char *buf)
 {
 	int len;
-	len = utf16s_to_utf8s((const wchar_t *)obj->string.pointer,
-			      obj->string.length,
+	len = utf16s_to_utf8s((const wchar_t *)obj->buffer.pointer,
+			      obj->buffer.length,
 			      UTF16_LITTLE_ENDIAN,
 			      buf, PAGE_SIZE);
 	buf[len] = '\n';
@@ -194,16 +194,22 @@ dsm_get_label(struct device *dev, char *buf, enum acpi_attr_enum attr)
 	tmp = obj->package.elements;
 	if (obj->type == ACPI_TYPE_PACKAGE && obj->package.count == 2 &&
 	    tmp[0].type == ACPI_TYPE_INTEGER &&
-	    tmp[1].type == ACPI_TYPE_STRING) {
+	    (tmp[1].type == ACPI_TYPE_STRING ||
+	     tmp[1].type == ACPI_TYPE_BUFFER)) {
 		/*
 		 * The second string element is optional even when
 		 * this _DSM is implemented; when not implemented,
 		 * this entry must return a null string.
 		 */
-		if (attr == ACPI_ATTR_INDEX_SHOW)
+		if (attr == ACPI_ATTR_INDEX_SHOW) {
 			scnprintf(buf, PAGE_SIZE, "%llu\n", tmp->integer.value);
-		else if (attr == ACPI_ATTR_LABEL_SHOW)
-			dsm_label_utf16s_to_utf8s(tmp + 1, buf);
+		} else if (attr == ACPI_ATTR_LABEL_SHOW) {
+			if (tmp[1].type == ACPI_TYPE_STRING)
+				scnprintf(buf, PAGE_SIZE, "%s\n",
+					  tmp[1].string.pointer);
+			else if (tmp[1].type == ACPI_TYPE_BUFFER)
+				dsm_label_utf16s_to_utf8s(tmp + 1, buf);
+		}
 		len = strlen(buf) > 0 ? strlen(buf) : -1;
 	}
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 276ef9c18802..a943c6c0f206 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -178,7 +178,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 
-	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n",
+	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n",
 		       pci_dev->vendor, pci_dev->device,
 		       pci_dev->subsystem_vendor, pci_dev->subsystem_device,
 		       (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8),
@@ -186,9 +186,9 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(modalias);
 
-static ssize_t enabled_store(struct device *dev,
-			     struct device_attribute *attr, const char *buf,
-			     size_t count)
+static ssize_t enable_store(struct device *dev,
+			    struct device_attribute *attr, const char *buf,
+			    size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	unsigned long val;
@@ -212,15 +212,15 @@ static ssize_t enabled_store(struct device *dev,
 	return result < 0 ? result : count;
 }
 
-static ssize_t enabled_show(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t enable_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev;
 
 	pdev = to_pci_dev (dev);
 	return sprintf (buf, "%u\n", atomic_read(&pdev->enable_cnt));
 }
-static DEVICE_ATTR_RW(enabled);
+static DEVICE_ATTR_RW(enable);
 
 #ifdef CONFIG_NUMA
 static ssize_t
@@ -526,7 +526,7 @@ static struct attribute *pci_dev_attrs[] = {
 #endif
 	&dev_attr_dma_mask_bits.attr,
 	&dev_attr_consistent_dma_mask_bits.attr,
-	&dev_attr_enabled.attr,
+	&dev_attr_enable.attr,
 	&dev_attr_broken_parity_status.attr,
 	&dev_attr_msi_bus.attr,
 #if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index fdbc294821e6..dae70d216762 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -830,12 +830,6 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 	if (!__pci_complete_power_transition(dev, state))
 		error = 0;
-	/*
-	 * When aspm_policy is "powersave" this call ensures
-	 * that ASPM is configured.
-	 */
-	if (!error && dev->bus->self)
-		pcie_aspm_powersave_config_link(dev->bus->self);
 
 	return error;
 }
@@ -1181,12 +1175,18 @@ EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state);
 static int do_pci_enable_device(struct pci_dev *dev, int bars)
 {
 	int err;
+	struct pci_dev *bridge;
 	u16 cmd;
 	u8 pin;
 
 	err = pci_set_power_state(dev, PCI_D0);
 	if (err < 0 && err != -EIO)
 		return err;
+
+	bridge = pci_upstream_bridge(dev);
+	if (bridge)
+		pcie_aspm_powersave_config_link(bridge);
+
 	err = pcibios_enable_device(dev, bars);
 	if (err < 0)
 		return err;
@@ -3043,7 +3043,8 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return 1;
 
-	return pci_wait_for_pending(dev, PCI_EXP_DEVSTA, PCI_EXP_DEVSTA_TRPND);
+	return pci_wait_for_pending(dev, pci_pcie_cap(dev) + PCI_EXP_DEVSTA,
+				    PCI_EXP_DEVSTA_TRPND);
 }
 EXPORT_SYMBOL(pci_wait_for_pending_transaction);
 
@@ -3084,8 +3085,13 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
 	if (probe)
 		return 0;
 
-	/* Wait for Transaction Pending bit clean */
-	if (pci_wait_for_pending(dev, PCI_AF_STATUS, PCI_AF_STATUS_TP))
+	/*
+	 * Wait for Transaction Pending bit to clear.  A word-aligned test
+	 * is used, so we use the conrol offset rather than status and shift
+	 * the test bit to match.
+	 */
+	if (pci_wait_for_pending(dev, pos + PCI_AF_CTRL,
+				 PCI_AF_STATUS_TP << 8))
 		goto clear;
 
 	dev_err(&dev->dev, "transaction is not cleared; "
@@ -4101,7 +4107,7 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
 	u16 cmd;
 	int rc;
 
-	WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) & (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)));
+	WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) && (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)));
 
 	/* ARCH specific VGA enables */
 	rc = pci_set_vga_state_arch(dev, decode, command_bits, flags);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 6e34498ec9f0..5b428db6a150 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -214,14 +214,17 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		res->flags |= IORESOURCE_SIZEALIGN;
 		if (res->flags & IORESOURCE_IO) {
 			l &= PCI_BASE_ADDRESS_IO_MASK;
+			sz &= PCI_BASE_ADDRESS_IO_MASK;
 			mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT;
 		} else {
 			l &= PCI_BASE_ADDRESS_MEM_MASK;
+			sz &= PCI_BASE_ADDRESS_MEM_MASK;
 			mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
 		}
 	} else {
 		res->flags |= (l & IORESOURCE_ROM_ENABLE);
 		l &= PCI_ROM_ADDRESS_MASK;
+		sz &= PCI_ROM_ADDRESS_MASK;
 		mask = (u32)PCI_ROM_ADDRESS_MASK;
 	}
 
@@ -395,15 +398,16 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 {
 	struct pci_dev *dev = child->self;
 	u16 mem_base_lo, mem_limit_lo;
-	unsigned long base, limit;
+	u64 base64, limit64;
+	dma_addr_t base, limit;
 	struct pci_bus_region region;
 	struct resource *res;
 
 	res = child->resource[2];
 	pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo);
 	pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo);
-	base = ((unsigned long) mem_base_lo & PCI_PREF_RANGE_MASK) << 16;
-	limit = ((unsigned long) mem_limit_lo & PCI_PREF_RANGE_MASK) << 16;
+	base64 = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16;
+	limit64 = (mem_limit_lo & PCI_PREF_RANGE_MASK) << 16;
 
 	if ((mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) {
 		u32 mem_base_hi, mem_limit_hi;
@@ -417,18 +421,20 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 		 * this, just assume they are not being used.
 		 */
 		if (mem_base_hi <= mem_limit_hi) {
-#if BITS_PER_LONG == 64
-			base |= ((unsigned long) mem_base_hi) << 32;
-			limit |= ((unsigned long) mem_limit_hi) << 32;
-#else
-			if (mem_base_hi || mem_limit_hi) {
-				dev_err(&dev->dev, "can't handle 64-bit "
-					"address space for bridge\n");
-				return;
-			}
-#endif
+			base64 |= (u64) mem_base_hi << 32;
+			limit64 |= (u64) mem_limit_hi << 32;
 		}
 	}
+
+	base = (dma_addr_t) base64;
+	limit = (dma_addr_t) limit64;
+
+	if (base != base64) {
+		dev_err(&dev->dev, "can't handle bridge window above 4GB (bus address %#010llx)\n",
+			(unsigned long long) base64);
+		return;
+	}
+
 	if (base <= limit) {
 		res->flags = (mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) |
 					 IORESOURCE_MEM | IORESOURCE_PREFETCH;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 5cb726c193de..6e8776b59a2c 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -24,6 +24,7 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/mm.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -287,6 +288,25 @@ static void quirk_citrine(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM,	PCI_DEVICE_ID_IBM_CITRINE,	quirk_citrine);
 
+/*  On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
+static void quirk_extend_bar_to_page(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
+			r->end = PAGE_SIZE - 1;
+			r->start = 0;
+			r->flags |= IORESOURCE_UNSET;
+			dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n",
+				 i, r);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page);
+
 /*
  *  S3 868 and 968 chips report region size equal to 32M, but they decode 64M.
  *  If it's needed, re-allocate the region.
@@ -2949,6 +2969,7 @@ static void disable_igfx_irq(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0152, disable_igfx_irq);
 
 /*
  * PCI devices which are on Intel chips can skip the 10ms delay
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 6c738376daff..34d56f7864d6 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -553,8 +553,9 @@ struct phy *phy_create(struct device *dev, const struct phy_ops *ops,
 	return phy;
 
 put_dev:
-	put_device(&phy->dev);
-	ida_remove(&phy_ida, phy->id);
+	put_device(&phy->dev);  /* calls phy_release() which frees resources */
+	return ERR_PTR(ret);
+
 free_phy:
 	kfree(phy);
 	return ERR_PTR(ret);
@@ -738,7 +739,7 @@ static void phy_release(struct device *dev)
 
 	phy = to_phy(dev);
 	dev_vdbg(dev, "releasing '%s'\n", dev_name(dev));
-	ida_remove(&phy_ida, phy->id);
+	ida_simple_remove(&phy_ida, phy->id);
 	kfree(phy);
 }
 
diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c
index 7f139326a642..ff026689358c 100644
--- a/drivers/phy/phy-exynos-mipi-video.c
+++ b/drivers/phy/phy-exynos-mipi-video.c
@@ -101,7 +101,7 @@ static struct phy *exynos_mipi_video_phy_xlate(struct device *dev,
 {
 	struct exynos_mipi_video_phy *state = dev_get_drvdata(dev);
 
-	if (WARN_ON(args->args[0] > EXYNOS_MIPI_PHYS_NUM))
+	if (WARN_ON(args->args[0] >= EXYNOS_MIPI_PHYS_NUM))
 		return ERR_PTR(-ENODEV);
 
 	return state->phys[args->args[0]].phy;
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index c3ace1db8136..aaac3594f83b 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -34,6 +34,7 @@
 #include <linux/delay.h>
 #include <linux/usb/otg.h>
 #include <linux/phy/phy.h>
+#include <linux/pm_runtime.h>
 #include <linux/usb/musb-omap.h>
 #include <linux/usb/ulpi.h>
 #include <linux/i2c/twl.h>
@@ -422,37 +423,55 @@ static void twl4030_phy_power(struct twl4030_usb *twl, int on)
 	}
 }
 
-static int twl4030_phy_power_off(struct phy *phy)
+static int twl4030_usb_runtime_suspend(struct device *dev)
 {
-	struct twl4030_usb *twl = phy_get_drvdata(phy);
+	struct twl4030_usb *twl = dev_get_drvdata(dev);
 
+	dev_dbg(twl->dev, "%s\n", __func__);
 	if (twl->asleep)
 		return 0;
 
 	twl4030_phy_power(twl, 0);
 	twl->asleep = 1;
-	dev_dbg(twl->dev, "%s\n", __func__);
+
 	return 0;
 }
 
-static void __twl4030_phy_power_on(struct twl4030_usb *twl)
+static int twl4030_usb_runtime_resume(struct device *dev)
 {
+	struct twl4030_usb *twl = dev_get_drvdata(dev);
+
+	dev_dbg(twl->dev, "%s\n", __func__);
+	if (!twl->asleep)
+		return 0;
+
 	twl4030_phy_power(twl, 1);
-	twl4030_i2c_access(twl, 1);
-	twl4030_usb_set_mode(twl, twl->usb_mode);
-	if (twl->usb_mode == T2_USB_MODE_ULPI)
-		twl4030_i2c_access(twl, 0);
+	twl->asleep = 0;
+
+	return 0;
+}
+
+static int twl4030_phy_power_off(struct phy *phy)
+{
+	struct twl4030_usb *twl = phy_get_drvdata(phy);
+
+	dev_dbg(twl->dev, "%s\n", __func__);
+	pm_runtime_mark_last_busy(twl->dev);
+	pm_runtime_put_autosuspend(twl->dev);
+
+	return 0;
 }
 
 static int twl4030_phy_power_on(struct phy *phy)
 {
 	struct twl4030_usb *twl = phy_get_drvdata(phy);
 
-	if (!twl->asleep)
-		return 0;
-	__twl4030_phy_power_on(twl);
-	twl->asleep = 0;
 	dev_dbg(twl->dev, "%s\n", __func__);
+	pm_runtime_get_sync(twl->dev);
+	twl4030_i2c_access(twl, 1);
+	twl4030_usb_set_mode(twl, twl->usb_mode);
+	if (twl->usb_mode == T2_USB_MODE_ULPI)
+		twl4030_i2c_access(twl, 0);
 
 	/*
 	 * XXX When VBUS gets driven after musb goes to A mode,
@@ -558,9 +577,27 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl)
 		 * USB_LINK_VBUS state.  musb_hdrc won't care until it
 		 * starts to handle softconnect right.
 		 */
+		if ((status == OMAP_MUSB_VBUS_VALID) ||
+		    (status == OMAP_MUSB_ID_GROUND)) {
+			if (twl->asleep)
+				pm_runtime_get_sync(twl->dev);
+		} else {
+			if (!twl->asleep) {
+				pm_runtime_mark_last_busy(twl->dev);
+				pm_runtime_put_autosuspend(twl->dev);
+			}
+		}
 		omap_musb_mailbox(status);
 	}
-	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
+
+	/* don't schedule during sleep - irq works right then */
+	if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) {
+		cancel_delayed_work(&twl->id_workaround_work);
+		schedule_delayed_work(&twl->id_workaround_work, HZ);
+	}
+
+	if (irq)
+		sysfs_notify(&twl->dev->kobj, NULL, "vbus");
 
 	return IRQ_HANDLED;
 }
@@ -569,29 +606,8 @@ static void twl4030_id_workaround_work(struct work_struct *work)
 {
 	struct twl4030_usb *twl = container_of(work, struct twl4030_usb,
 		id_workaround_work.work);
-	enum omap_musb_vbus_id_status status;
-	bool status_changed = false;
-
-	status = twl4030_usb_linkstat(twl);
-
-	spin_lock_irq(&twl->lock);
-	if (status >= 0 && status != twl->linkstat) {
-		twl->linkstat = status;
-		status_changed = true;
-	}
-	spin_unlock_irq(&twl->lock);
-
-	if (status_changed) {
-		dev_dbg(twl->dev, "handle missing status change to %d\n",
-				status);
-		omap_musb_mailbox(status);
-	}
 
-	/* don't schedule during sleep - irq works right then */
-	if (status == OMAP_MUSB_ID_GROUND && !twl->asleep) {
-		cancel_delayed_work(&twl->id_workaround_work);
-		schedule_delayed_work(&twl->id_workaround_work, HZ);
-	}
+	twl4030_usb_irq(0, twl);
 }
 
 static int twl4030_phy_init(struct phy *phy)
@@ -599,22 +615,17 @@ static int twl4030_phy_init(struct phy *phy)
 	struct twl4030_usb *twl = phy_get_drvdata(phy);
 	enum omap_musb_vbus_id_status status;
 
-	/*
-	 * Start in sleep state, we'll get called through set_suspend()
-	 * callback when musb is runtime resumed and it's time to start.
-	 */
-	__twl4030_phy_power(twl, 0);
-	twl->asleep = 1;
-
+	pm_runtime_get_sync(twl->dev);
 	status = twl4030_usb_linkstat(twl);
 	twl->linkstat = status;
 
-	if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID) {
+	if (status == OMAP_MUSB_ID_GROUND || status == OMAP_MUSB_VBUS_VALID)
 		omap_musb_mailbox(twl->linkstat);
-		twl4030_phy_power_on(phy);
-	}
 
 	sysfs_notify(&twl->dev->kobj, NULL, "vbus");
+	pm_runtime_mark_last_busy(twl->dev);
+	pm_runtime_put_autosuspend(twl->dev);
+
 	return 0;
 }
 
@@ -650,6 +661,11 @@ static const struct phy_ops ops = {
 	.owner		= THIS_MODULE,
 };
 
+static const struct dev_pm_ops twl4030_usb_pm_ops = {
+	SET_RUNTIME_PM_OPS(twl4030_usb_runtime_suspend,
+			   twl4030_usb_runtime_resume, NULL)
+};
+
 static int twl4030_usb_probe(struct platform_device *pdev)
 {
 	struct twl4030_usb_data *pdata = dev_get_platdata(&pdev->dev);
@@ -726,6 +742,11 @@ static int twl4030_usb_probe(struct platform_device *pdev)
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&twl->phy.notifier);
 
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 2000);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+
 	/* Our job is to use irqs and status from the power module
 	 * to keep the transceiver disabled when nothing's connected.
 	 *
@@ -744,6 +765,9 @@ static int twl4030_usb_probe(struct platform_device *pdev)
 		return status;
 	}
 
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(twl->dev);
+
 	dev_info(&pdev->dev, "Initialized TWL4030 USB module\n");
 	return 0;
 }
@@ -753,6 +777,7 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 	struct twl4030_usb *twl = platform_get_drvdata(pdev);
 	int val;
 
+	pm_runtime_get_sync(twl->dev);
 	cancel_delayed_work(&twl->id_workaround_work);
 	device_remove_file(twl->dev, &dev_attr_vbus);
 
@@ -772,9 +797,8 @@ static int twl4030_usb_remove(struct platform_device *pdev)
 
 	/* disable complete OTG block */
 	twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB);
-
-	if (!twl->asleep)
-		twl4030_phy_power(twl, 0);
+	pm_runtime_mark_last_busy(twl->dev);
+	pm_runtime_put(twl->dev);
 
 	return 0;
 }
@@ -792,6 +816,7 @@ static struct platform_driver twl4030_usb_driver = {
 	.remove		= twl4030_usb_remove,
 	.driver		= {
 		.name	= "twl4030_usb",
+		.pm	= &twl4030_usb_pm_ops,
 		.owner	= THIS_MODULE,
 		.of_match_table = of_match_ptr(twl4030_usb_id_table),
 	},
diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c
index 92ed4b2e3c07..c862f9c0e9ce 100644
--- a/drivers/pinctrl/pinctrl-as3722.c
+++ b/drivers/pinctrl/pinctrl-as3722.c
@@ -64,7 +64,6 @@ struct as3722_pin_function {
 };
 
 struct as3722_gpio_pin_control {
-	bool enable_gpio_invert;
 	unsigned mode_prop;
 	int io_function;
 };
@@ -320,10 +319,8 @@ static int as3722_pinctrl_gpio_set_direction(struct pinctrl_dev *pctldev,
 		return mode;
 	}
 
-	if (as_pci->gpio_control[offset].enable_gpio_invert)
-		mode |= AS3722_GPIO_INV;
-
-	return as3722_write(as3722, AS3722_GPIOn_CONTROL_REG(offset), mode);
+	return as3722_update_bits(as3722, AS3722_GPIOn_CONTROL_REG(offset),
+				AS3722_GPIO_MODE_MASK, mode);
 }
 
 static const struct pinmux_ops as3722_pinmux_ops = {
@@ -496,10 +493,18 @@ static void as3722_gpio_set(struct gpio_chip *chip, unsigned offset,
 {
 	struct as3722_pctrl_info *as_pci = to_as_pci(chip);
 	struct as3722 *as3722 = as_pci->as3722;
-	int en_invert = as_pci->gpio_control[offset].enable_gpio_invert;
+	int en_invert;
 	u32 val;
 	int ret;
 
+	ret = as3722_read(as3722, AS3722_GPIOn_CONTROL_REG(offset), &val);
+	if (ret < 0) {
+		dev_err(as_pci->dev,
+			"GPIO_CONTROL%d_REG read failed: %d\n", offset, ret);
+		return;
+	}
+	en_invert = !!(val & AS3722_GPIO_INV);
+
 	if (value)
 		val = (en_invert) ? 0 : AS3722_GPIOn_SIGNAL(offset);
 	else
diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c
index 665b96bc0c3a..eb9f1906952a 100644
--- a/drivers/pinctrl/pinctrl-baytrail.c
+++ b/drivers/pinctrl/pinctrl-baytrail.c
@@ -263,7 +263,7 @@ static int byt_gpio_direction_output(struct gpio_chip *chip,
 	spin_lock_irqsave(&vg->lock, flags);
 
 	reg_val = readl(reg) | BYT_DIR_MASK;
-	reg_val &= ~BYT_OUTPUT_EN;
+	reg_val &= ~(BYT_OUTPUT_EN | BYT_INPUT_EN);
 
 	if (value)
 		writel(reg_val | BYT_LEVEL, reg);
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index c91f69b39db4..dcfcaea76048 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -570,6 +570,17 @@ static const struct dmi_system_id video_vendor_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5750"),
 		},
 	},
+	{
+		/*
+		 * Note no video_set_backlight_video_vendor, we must use the
+		 * acer interface, as there is no native backlight interface.
+		 */
+		.ident = "Acer KAV80",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "KAV80"),
+		},
+	},
 	{}
 };
 
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index 390e8e33d5e3..25721bf20092 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -163,18 +163,24 @@ static void dell_wmi_notify(u32 value, void *context)
 		const struct key_entry *key;
 		int reported_key;
 		u16 *buffer_entry = (u16 *)obj->buffer.pointer;
+		int buffer_size = obj->buffer.length/2;
 
-		if (dell_new_hk_type && (buffer_entry[1] != 0x10)) {
+		if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) {
 			pr_info("Received unknown WMI event (0x%x)\n",
 				buffer_entry[1]);
 			kfree(obj);
 			return;
 		}
 
-		if (dell_new_hk_type || buffer_entry[1] == 0x0)
+		if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0))
 			reported_key = (int)buffer_entry[2];
-		else
+		else if (buffer_size >= 2)
 			reported_key = (int)buffer_entry[1] & 0xffff;
+		else {
+			pr_info("Received unknown WMI event\n");
+			kfree(obj);
+			return;
+		}
 
 		key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
 							reported_key);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index defb6afc1409..e2a91c845ac9 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -8447,9 +8447,21 @@ static void mute_led_exit(void)
 		tpacpi_led_set(i, false);
 }
 
+static void mute_led_resume(void)
+{
+	int i;
+
+	for (i = 0; i < TPACPI_LED_MAX; i++) {
+		struct tp_led_table *t = &led_tables[i];
+		if (t->state >= 0)
+			mute_led_on_off(t, t->state);
+	}
+}
+
 static struct ibm_struct mute_led_driver_data = {
 	.name = "mute_led",
 	.exit = mute_led_exit,
+	.resume = mute_led_resume,
 };
 
 /****************************************************************************
diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c
index 9f611cbbc294..da1c6cb1a41e 100644
--- a/drivers/pnp/pnpacpi/core.c
+++ b/drivers/pnp/pnpacpi/core.c
@@ -83,8 +83,7 @@ static int pnpacpi_set_resources(struct pnp_dev *dev)
 {
 	struct acpi_device *acpi_dev;
 	acpi_handle handle;
-	struct acpi_buffer buffer;
-	int ret;
+	int ret = 0;
 
 	pnp_dbg(&dev->dev, "set resources\n");
 
@@ -97,19 +96,26 @@ static int pnpacpi_set_resources(struct pnp_dev *dev)
 	if (WARN_ON_ONCE(acpi_dev != dev->data))
 		dev->data = acpi_dev;
 
-	ret = pnpacpi_build_resource_template(dev, &buffer);
-	if (ret)
-		return ret;
-	ret = pnpacpi_encode_resources(dev, &buffer);
-	if (ret) {
+	if (acpi_has_method(handle, METHOD_NAME__SRS)) {
+		struct acpi_buffer buffer;
+
+		ret = pnpacpi_build_resource_template(dev, &buffer);
+		if (ret)
+			return ret;
+
+		ret = pnpacpi_encode_resources(dev, &buffer);
+		if (!ret) {
+			acpi_status status;
+
+			status = acpi_set_current_resources(handle, &buffer);
+			if (ACPI_FAILURE(status))
+				ret = -EIO;
+		}
 		kfree(buffer.pointer);
-		return ret;
 	}
-	if (ACPI_FAILURE(acpi_set_current_resources(handle, &buffer)))
-		ret = -EINVAL;
-	else if (acpi_bus_power_manageable(handle))
+	if (!ret && acpi_bus_power_manageable(handle))
 		ret = acpi_bus_set_power(handle, ACPI_STATE_D0);
-	kfree(buffer.pointer);
+
 	return ret;
 }
 
@@ -117,7 +123,7 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev)
 {
 	struct acpi_device *acpi_dev;
 	acpi_handle handle;
-	int ret;
+	acpi_status status;
 
 	dev_dbg(&dev->dev, "disable resources\n");
 
@@ -128,13 +134,15 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev)
 	}
 
 	/* acpi_unregister_gsi(pnp_irq(dev, 0)); */
-	ret = 0;
 	if (acpi_bus_power_manageable(handle))
 		acpi_bus_set_power(handle, ACPI_STATE_D3_COLD);
-		/* continue even if acpi_bus_set_power() fails */
-	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DIS", NULL, NULL)))
-		ret = -ENODEV;
-	return ret;
+
+	/* continue even if acpi_bus_set_power() fails */
+	status = acpi_evaluate_object(handle, "_DIS", NULL, NULL);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND)
+		return -ENODEV;
+
+	return 0;
 }
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -331,8 +339,7 @@ static int __init acpi_pnp_match(struct device *dev, void *_pnp)
 	struct pnp_dev *pnp = _pnp;
 
 	/* true means it matched */
-	return !acpi->physical_node_count
-	    && compare_pnp_id(pnp->id, acpi_device_hid(acpi));
+	return pnp->data == acpi;
 }
 
 static struct acpi_device * __init acpi_pnp_find_companion(struct device *dev)
diff --git a/drivers/power/bq2415x_charger.c b/drivers/power/bq2415x_charger.c
index 79a37f6d3307..1f49986fc605 100644
--- a/drivers/power/bq2415x_charger.c
+++ b/drivers/power/bq2415x_charger.c
@@ -840,8 +840,7 @@ static int bq2415x_notifier_call(struct notifier_block *nb,
 	if (bq->automode < 1)
 		return NOTIFY_OK;
 
-	sysfs_notify(&bq->charger.dev->kobj, NULL, "reported_mode");
-	bq2415x_set_mode(bq, bq->reported_mode);
+	schedule_delayed_work(&bq->work, 0);
 
 	return NOTIFY_OK;
 }
@@ -892,6 +891,11 @@ static void bq2415x_timer_work(struct work_struct *work)
 	int error;
 	int boost;
 
+	if (bq->automode > 0 && (bq->reported_mode != bq->mode)) {
+		sysfs_notify(&bq->charger.dev->kobj, NULL, "reported_mode");
+		bq2415x_set_mode(bq, bq->reported_mode);
+	}
+
 	if (!bq->autotimer)
 		return;
 
@@ -1575,8 +1579,15 @@ static int bq2415x_probe(struct i2c_client *client,
 	if (np) {
 		bq->notify_psy = power_supply_get_by_phandle(np, "ti,usb-charger-detection");
 
-		if (!bq->notify_psy)
-			return -EPROBE_DEFER;
+		if (IS_ERR(bq->notify_psy)) {
+			dev_info(&client->dev,
+				"no 'ti,usb-charger-detection' property (err=%ld)\n",
+				PTR_ERR(bq->notify_psy));
+			bq->notify_psy = NULL;
+		} else if (!bq->notify_psy) {
+			ret = -EPROBE_DEFER;
+			goto error_2;
+		}
 	}
 	else if (pdata->notify_device)
 		bq->notify_psy = power_supply_get_by_name(pdata->notify_device);
@@ -1598,27 +1609,27 @@ static int bq2415x_probe(struct i2c_client *client,
 		ret = of_property_read_u32(np, "ti,current-limit",
 				&bq->init_data.current_limit);
 		if (ret)
-			return ret;
+			goto error_2;
 		ret = of_property_read_u32(np, "ti,weak-battery-voltage",
 				&bq->init_data.weak_battery_voltage);
 		if (ret)
-			return ret;
+			goto error_2;
 		ret = of_property_read_u32(np, "ti,battery-regulation-voltage",
 				&bq->init_data.battery_regulation_voltage);
 		if (ret)
-			return ret;
+			goto error_2;
 		ret = of_property_read_u32(np, "ti,charge-current",
 				&bq->init_data.charge_current);
 		if (ret)
-			return ret;
+			goto error_2;
 		ret = of_property_read_u32(np, "ti,termination-current",
 				&bq->init_data.termination_current);
 		if (ret)
-			return ret;
+			goto error_2;
 		ret = of_property_read_u32(np, "ti,resistor-sense",
 				&bq->init_data.resistor_sense);
 		if (ret)
-			return ret;
+			goto error_2;
 	} else {
 		memcpy(&bq->init_data, pdata, sizeof(bq->init_data));
 	}
diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c
index 9e4dab46eefd..03bfac3655ef 100644
--- a/drivers/power/charger-manager.c
+++ b/drivers/power/charger-manager.c
@@ -97,6 +97,7 @@ static struct charger_global_desc *g_desc; /* init with setup_charger_manager */
 static bool is_batt_present(struct charger_manager *cm)
 {
 	union power_supply_propval val;
+	struct power_supply *psy;
 	bool present = false;
 	int i, ret;
 
@@ -107,16 +108,27 @@ static bool is_batt_present(struct charger_manager *cm)
 	case CM_NO_BATTERY:
 		break;
 	case CM_FUEL_GAUGE:
-		ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+		psy = power_supply_get_by_name(cm->desc->psy_fuel_gauge);
+		if (!psy)
+			break;
+
+		ret = psy->get_property(psy,
 				POWER_SUPPLY_PROP_PRESENT, &val);
 		if (ret == 0 && val.intval)
 			present = true;
 		break;
 	case CM_CHARGER_STAT:
-		for (i = 0; cm->charger_stat[i]; i++) {
-			ret = cm->charger_stat[i]->get_property(
-					cm->charger_stat[i],
-					POWER_SUPPLY_PROP_PRESENT, &val);
+		for (i = 0; cm->desc->psy_charger_stat[i]; i++) {
+			psy = power_supply_get_by_name(
+					cm->desc->psy_charger_stat[i]);
+			if (!psy) {
+				dev_err(cm->dev, "Cannot find power supply \"%s\"\n",
+					cm->desc->psy_charger_stat[i]);
+				continue;
+			}
+
+			ret = psy->get_property(psy, POWER_SUPPLY_PROP_PRESENT,
+					&val);
 			if (ret == 0 && val.intval) {
 				present = true;
 				break;
@@ -139,14 +151,20 @@ static bool is_batt_present(struct charger_manager *cm)
 static bool is_ext_pwr_online(struct charger_manager *cm)
 {
 	union power_supply_propval val;
+	struct power_supply *psy;
 	bool online = false;
 	int i, ret;
 
 	/* If at least one of them has one, it's yes. */
-	for (i = 0; cm->charger_stat[i]; i++) {
-		ret = cm->charger_stat[i]->get_property(
-				cm->charger_stat[i],
-				POWER_SUPPLY_PROP_ONLINE, &val);
+	for (i = 0; cm->desc->psy_charger_stat[i]; i++) {
+		psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]);
+		if (!psy) {
+			dev_err(cm->dev, "Cannot find power supply \"%s\"\n",
+					cm->desc->psy_charger_stat[i]);
+			continue;
+		}
+
+		ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val);
 		if (ret == 0 && val.intval) {
 			online = true;
 			break;
@@ -167,12 +185,14 @@ static bool is_ext_pwr_online(struct charger_manager *cm)
 static int get_batt_uV(struct charger_manager *cm, int *uV)
 {
 	union power_supply_propval val;
+	struct power_supply *fuel_gauge;
 	int ret;
 
-	if (!cm->fuel_gauge)
+	fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge);
+	if (!fuel_gauge)
 		return -ENODEV;
 
-	ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+	ret = fuel_gauge->get_property(fuel_gauge,
 				POWER_SUPPLY_PROP_VOLTAGE_NOW, &val);
 	if (ret)
 		return ret;
@@ -189,6 +209,7 @@ static bool is_charging(struct charger_manager *cm)
 {
 	int i, ret;
 	bool charging = false;
+	struct power_supply *psy;
 	union power_supply_propval val;
 
 	/* If there is no battery, it cannot be charged */
@@ -196,17 +217,22 @@ static bool is_charging(struct charger_manager *cm)
 		return false;
 
 	/* If at least one of the charger is charging, return yes */
-	for (i = 0; cm->charger_stat[i]; i++) {
+	for (i = 0; cm->desc->psy_charger_stat[i]; i++) {
 		/* 1. The charger sholuld not be DISABLED */
 		if (cm->emergency_stop)
 			continue;
 		if (!cm->charger_enabled)
 			continue;
 
+		psy = power_supply_get_by_name(cm->desc->psy_charger_stat[i]);
+		if (!psy) {
+			dev_err(cm->dev, "Cannot find power supply \"%s\"\n",
+					cm->desc->psy_charger_stat[i]);
+			continue;
+		}
+
 		/* 2. The charger should be online (ext-power) */
-		ret = cm->charger_stat[i]->get_property(
-				cm->charger_stat[i],
-				POWER_SUPPLY_PROP_ONLINE, &val);
+		ret = psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &val);
 		if (ret) {
 			dev_warn(cm->dev, "Cannot read ONLINE value from %s\n",
 				 cm->desc->psy_charger_stat[i]);
@@ -219,9 +245,7 @@ static bool is_charging(struct charger_manager *cm)
 		 * 3. The charger should not be FULL, DISCHARGING,
 		 * or NOT_CHARGING.
 		 */
-		ret = cm->charger_stat[i]->get_property(
-				cm->charger_stat[i],
-				POWER_SUPPLY_PROP_STATUS, &val);
+		ret = psy->get_property(psy, POWER_SUPPLY_PROP_STATUS, &val);
 		if (ret) {
 			dev_warn(cm->dev, "Cannot read STATUS value from %s\n",
 				 cm->desc->psy_charger_stat[i]);
@@ -248,6 +272,7 @@ static bool is_full_charged(struct charger_manager *cm)
 {
 	struct charger_desc *desc = cm->desc;
 	union power_supply_propval val;
+	struct power_supply *fuel_gauge;
 	int ret = 0;
 	int uV;
 
@@ -255,11 +280,15 @@ static bool is_full_charged(struct charger_manager *cm)
 	if (!is_batt_present(cm))
 		return false;
 
-	if (cm->fuel_gauge && desc->fullbatt_full_capacity > 0) {
+	fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge);
+	if (!fuel_gauge)
+		return false;
+
+	if (desc->fullbatt_full_capacity > 0) {
 		val.intval = 0;
 
 		/* Not full if capacity of fuel gauge isn't full */
-		ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+		ret = fuel_gauge->get_property(fuel_gauge,
 				POWER_SUPPLY_PROP_CHARGE_FULL, &val);
 		if (!ret && val.intval > desc->fullbatt_full_capacity)
 			return true;
@@ -273,10 +302,10 @@ static bool is_full_charged(struct charger_manager *cm)
 	}
 
 	/* Full, if the capacity is more than fullbatt_soc */
-	if (cm->fuel_gauge && desc->fullbatt_soc > 0) {
+	if (desc->fullbatt_soc > 0) {
 		val.intval = 0;
 
-		ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+		ret = fuel_gauge->get_property(fuel_gauge,
 				POWER_SUPPLY_PROP_CAPACITY, &val);
 		if (!ret && val.intval >= desc->fullbatt_soc)
 			return true;
@@ -551,6 +580,20 @@ static int check_charging_duration(struct charger_manager *cm)
 	return ret;
 }
 
+static int cm_get_battery_temperature_by_psy(struct charger_manager *cm,
+					int *temp)
+{
+	struct power_supply *fuel_gauge;
+
+	fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge);
+	if (!fuel_gauge)
+		return -ENODEV;
+
+	return fuel_gauge->get_property(fuel_gauge,
+				POWER_SUPPLY_PROP_TEMP,
+				(union power_supply_propval *)temp);
+}
+
 static int cm_get_battery_temperature(struct charger_manager *cm,
 					int *temp)
 {
@@ -560,15 +603,18 @@ static int cm_get_battery_temperature(struct charger_manager *cm,
 		return -ENODEV;
 
 #ifdef CONFIG_THERMAL
-	ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp);
-	if (!ret)
-		/* Calibrate temperature unit */
-		*temp /= 100;
-#else
-	ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
-				POWER_SUPPLY_PROP_TEMP,
-				(union power_supply_propval *)temp);
+	if (cm->tzd_batt) {
+		ret = thermal_zone_get_temp(cm->tzd_batt, (unsigned long *)temp);
+		if (!ret)
+			/* Calibrate temperature unit */
+			*temp /= 100;
+	} else
 #endif
+	{
+		/* if-else continued from CONFIG_THERMAL */
+		ret = cm_get_battery_temperature_by_psy(cm, temp);
+	}
+
 	return ret;
 }
 
@@ -827,6 +873,7 @@ static int charger_get_property(struct power_supply *psy,
 	struct charger_manager *cm = container_of(psy,
 			struct charger_manager, charger_psy);
 	struct charger_desc *desc = cm->desc;
+	struct power_supply *fuel_gauge;
 	int ret = 0;
 	int uV;
 
@@ -857,14 +904,20 @@ static int charger_get_property(struct power_supply *psy,
 		ret = get_batt_uV(cm, &val->intval);
 		break;
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
-		ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+		fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge);
+		if (!fuel_gauge) {
+			ret = -ENODEV;
+			break;
+		}
+		ret = fuel_gauge->get_property(fuel_gauge,
 				POWER_SUPPLY_PROP_CURRENT_NOW, val);
 		break;
 	case POWER_SUPPLY_PROP_TEMP:
 	case POWER_SUPPLY_PROP_TEMP_AMBIENT:
 		return cm_get_battery_temperature(cm, &val->intval);
 	case POWER_SUPPLY_PROP_CAPACITY:
-		if (!cm->fuel_gauge) {
+		fuel_gauge = power_supply_get_by_name(cm->desc->psy_fuel_gauge);
+		if (!fuel_gauge) {
 			ret = -ENODEV;
 			break;
 		}
@@ -875,7 +928,7 @@ static int charger_get_property(struct power_supply *psy,
 			break;
 		}
 
-		ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+		ret = fuel_gauge->get_property(fuel_gauge,
 					POWER_SUPPLY_PROP_CAPACITY, val);
 		if (ret)
 			break;
@@ -924,7 +977,14 @@ static int charger_get_property(struct power_supply *psy,
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_NOW:
 		if (is_charging(cm)) {
-			ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+			fuel_gauge = power_supply_get_by_name(
+					cm->desc->psy_fuel_gauge);
+			if (!fuel_gauge) {
+				ret = -ENODEV;
+				break;
+			}
+
+			ret = fuel_gauge->get_property(fuel_gauge,
 						POWER_SUPPLY_PROP_CHARGE_NOW,
 						val);
 			if (ret) {
@@ -1485,14 +1545,15 @@ err:
 	return ret;
 }
 
-static int cm_init_thermal_data(struct charger_manager *cm)
+static int cm_init_thermal_data(struct charger_manager *cm,
+		struct power_supply *fuel_gauge)
 {
 	struct charger_desc *desc = cm->desc;
 	union power_supply_propval val;
 	int ret;
 
 	/* Verify whether fuel gauge provides battery temperature */
-	ret = cm->fuel_gauge->get_property(cm->fuel_gauge,
+	ret = fuel_gauge->get_property(fuel_gauge,
 					POWER_SUPPLY_PROP_TEMP, &val);
 
 	if (!ret) {
@@ -1502,8 +1563,6 @@ static int cm_init_thermal_data(struct charger_manager *cm)
 		cm->desc->measure_battery_temp = true;
 	}
 #ifdef CONFIG_THERMAL
-	cm->tzd_batt = cm->fuel_gauge->tzd;
-
 	if (ret && desc->thermal_zone) {
 		cm->tzd_batt =
 			thermal_zone_get_zone_by_name(desc->thermal_zone);
@@ -1666,6 +1725,7 @@ static int charger_manager_probe(struct platform_device *pdev)
 	int ret = 0, i = 0;
 	int j = 0;
 	union power_supply_propval val;
+	struct power_supply *fuel_gauge;
 
 	if (g_desc && !rtc_dev && g_desc->rtc_name) {
 		rtc_dev = rtc_class_open(g_desc->rtc_name);
@@ -1720,27 +1780,29 @@ static int charger_manager_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	if (!desc->psy_fuel_gauge) {
+		dev_err(&pdev->dev, "No fuel gauge power supply defined\n");
+		return -EINVAL;
+	}
+
 	/* Counting index only */
 	while (desc->psy_charger_stat[i])
 		i++;
 
-	cm->charger_stat = devm_kzalloc(&pdev->dev,
-				sizeof(struct power_supply *) * i, GFP_KERNEL);
-	if (!cm->charger_stat)
-		return -ENOMEM;
-
+	/* Check if charger's supplies are present at probe */
 	for (i = 0; desc->psy_charger_stat[i]; i++) {
-		cm->charger_stat[i] = power_supply_get_by_name(
-					desc->psy_charger_stat[i]);
-		if (!cm->charger_stat[i]) {
+		struct power_supply *psy;
+
+		psy = power_supply_get_by_name(desc->psy_charger_stat[i]);
+		if (!psy) {
 			dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n",
 				desc->psy_charger_stat[i]);
 			return -ENODEV;
 		}
 	}
 
-	cm->fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge);
-	if (!cm->fuel_gauge) {
+	fuel_gauge = power_supply_get_by_name(desc->psy_fuel_gauge);
+	if (!fuel_gauge) {
 		dev_err(&pdev->dev, "Cannot find power supply \"%s\"\n",
 			desc->psy_fuel_gauge);
 		return -ENODEV;
@@ -1783,13 +1845,13 @@ static int charger_manager_probe(struct platform_device *pdev)
 	cm->charger_psy.num_properties = psy_default.num_properties;
 
 	/* Find which optional psy-properties are available */
-	if (!cm->fuel_gauge->get_property(cm->fuel_gauge,
+	if (!fuel_gauge->get_property(fuel_gauge,
 					  POWER_SUPPLY_PROP_CHARGE_NOW, &val)) {
 		cm->charger_psy.properties[cm->charger_psy.num_properties] =
 				POWER_SUPPLY_PROP_CHARGE_NOW;
 		cm->charger_psy.num_properties++;
 	}
-	if (!cm->fuel_gauge->get_property(cm->fuel_gauge,
+	if (!fuel_gauge->get_property(fuel_gauge,
 					  POWER_SUPPLY_PROP_CURRENT_NOW,
 					  &val)) {
 		cm->charger_psy.properties[cm->charger_psy.num_properties] =
@@ -1797,7 +1859,7 @@ static int charger_manager_probe(struct platform_device *pdev)
 		cm->charger_psy.num_properties++;
 	}
 
-	ret = cm_init_thermal_data(cm);
+	ret = cm_init_thermal_data(cm, fuel_gauge);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize thermal data\n");
 		cm->desc->measure_battery_temp = false;
@@ -2054,8 +2116,8 @@ static bool find_power_supply(struct charger_manager *cm,
 	int i;
 	bool found = false;
 
-	for (i = 0; cm->charger_stat[i]; i++) {
-		if (psy == cm->charger_stat[i]) {
+	for (i = 0; cm->desc->psy_charger_stat[i]; i++) {
+		if (!strcmp(psy->name, cm->desc->psy_charger_stat[i])) {
 			found = true;
 			break;
 		}
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 91245f5dbe81..47257b6eea84 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -287,6 +287,12 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
 			"desc %p not ACKed\n", tx_desc);
 	}
 
+	if (ret == NULL) {
+		dev_dbg(bdma_chan->dchan.device->dev,
+			"%s: unable to obtain tx descriptor\n", __func__);
+		goto err_out;
+	}
+
 	i = bdma_chan->wr_count_next % bdma_chan->bd_num;
 	if (i == bdma_chan->bd_num - 1) {
 		i = 0;
@@ -297,7 +303,7 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
 	tx_desc->txd.phys = bdma_chan->bd_phys +
 				i * sizeof(struct tsi721_dma_desc);
 	tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i];
-
+err_out:
 	spin_unlock_bh(&bdma_chan->lock);
 
 	return ret;
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index 4f6c2055f6b2..8b963a757883 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -141,8 +141,6 @@ static struct regulator_ops arizona_ldo1_ops = {
 	.map_voltage = regulator_map_voltage_linear,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
-	.get_bypass = regulator_get_bypass_regmap,
-	.set_bypass = regulator_set_bypass_regmap,
 };
 
 static const struct regulator_desc arizona_ldo1 = {
@@ -153,11 +151,9 @@ static const struct regulator_desc arizona_ldo1 = {
 
 	.vsel_reg = ARIZONA_LDO1_CONTROL_1,
 	.vsel_mask = ARIZONA_LDO1_VSEL_MASK,
-	.bypass_reg = ARIZONA_LDO1_CONTROL_1,
-	.bypass_mask = ARIZONA_LDO1_BYPASS,
 	.min_uV = 900000,
-	.uV_step = 50000,
-	.n_voltages = 7,
+	.uV_step = 25000,
+	.n_voltages = 13,
 	.enable_time = 500,
 
 	.owner = THIS_MODULE,
@@ -203,6 +199,7 @@ static int arizona_ldo1_probe(struct platform_device *pdev)
 	 */
 	switch (arizona->type) {
 	case WM5102:
+	case WM8997:
 		desc = &arizona_ldo1_hc;
 		ldo1->init_data = arizona_ldo1_dvfs;
 		break;
diff --git a/drivers/regulator/max77693.c b/drivers/regulator/max77693.c
index 5fb899f461d0..24c926bfe6d4 100644
--- a/drivers/regulator/max77693.c
+++ b/drivers/regulator/max77693.c
@@ -232,7 +232,7 @@ static int max77693_pmic_probe(struct platform_device *pdev)
 	struct max77693_pmic_dev *max77693_pmic;
 	struct max77693_regulator_data *rdata = NULL;
 	int num_rdata, i;
-	struct regulator_config config;
+	struct regulator_config config = { };
 
 	num_rdata = max77693_pmic_init_rdata(&pdev->dev, &rdata);
 	if (!rdata || num_rdata <= 0) {
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 3281c90691c3..44fe83ee9bee 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -48,6 +48,7 @@ struct at91_rtc_config {
 
 static const struct at91_rtc_config *at91_rtc_config;
 static DECLARE_COMPLETION(at91_rtc_updated);
+static DECLARE_COMPLETION(at91_rtc_upd_rdy);
 static unsigned int at91_alarm_year = AT91_RTC_EPOCH;
 static void __iomem *at91_rtc_regs;
 static int irq;
@@ -161,6 +162,8 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec);
 
+	wait_for_completion(&at91_rtc_upd_rdy);
+
 	/* Stop Time/Calendar from counting */
 	cr = at91_rtc_read(AT91_RTC_CR);
 	at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM);
@@ -183,7 +186,9 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 
 	/* Restart Time/Calendar */
 	cr = at91_rtc_read(AT91_RTC_CR);
+	at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_SECEV);
 	at91_rtc_write(AT91_RTC_CR, cr & ~(AT91_RTC_UPDCAL | AT91_RTC_UPDTIM));
+	at91_rtc_write_ier(AT91_RTC_SECEV);
 
 	return 0;
 }
@@ -290,8 +295,10 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 	if (rtsr) {		/* this interrupt is shared!  Is it ours? */
 		if (rtsr & AT91_RTC_ALARM)
 			events |= (RTC_AF | RTC_IRQF);
-		if (rtsr & AT91_RTC_SECEV)
-			events |= (RTC_UF | RTC_IRQF);
+		if (rtsr & AT91_RTC_SECEV) {
+			complete(&at91_rtc_upd_rdy);
+			at91_rtc_write_idr(AT91_RTC_SECEV);
+		}
 		if (rtsr & AT91_RTC_ACKUPD)
 			complete(&at91_rtc_updated);
 
@@ -413,6 +420,11 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(rtc);
 	platform_set_drvdata(pdev, rtc);
 
+	/* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy
+	 * completion.
+	 */
+	at91_rtc_write_ier(AT91_RTC_SECEV);
+
 	dev_info(&pdev->dev, "AT91 Real Time Clock driver.\n");
 	return 0;
 }
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index bd628a6f981d..e5f13c4310fe 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -569,6 +569,9 @@ static int hym8563_probe(struct i2c_client *client,
 	if (IS_ERR(hym8563->rtc))
 		return PTR_ERR(hym8563->rtc);
 
+	/* the hym8563 alarm only supports a minute accuracy */
+	hym8563->rtc->uie_unsupported = 1;
+
 #ifdef CONFIG_COMMON_CLK
 	hym8563_clkout_register_clk(hym8563);
 #endif
diff --git a/drivers/rtc/rtc-isl12057.c b/drivers/rtc/rtc-isl12057.c
index 7854a656628f..110eab817a4f 100644
--- a/drivers/rtc/rtc-isl12057.c
+++ b/drivers/rtc/rtc-isl12057.c
@@ -89,7 +89,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs)
 	tm->tm_min = bcd2bin(regs[ISL12057_REG_RTC_MN]);
 
 	if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_MIL) { /* AM/PM */
-		tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x0f);
+		tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x1f);
 		if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_PM)
 			tm->tm_hour += 12;
 	} else {					    /* 24 hour mode */
@@ -98,7 +98,7 @@ static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs)
 
 	tm->tm_mday = bcd2bin(regs[ISL12057_REG_RTC_DT]);
 	tm->tm_wday = bcd2bin(regs[ISL12057_REG_RTC_DW]) - 1; /* starts at 1 */
-	tm->tm_mon  = bcd2bin(regs[ISL12057_REG_RTC_MO]) - 1; /* starts at 1 */
+	tm->tm_mon  = bcd2bin(regs[ISL12057_REG_RTC_MO] & 0x1f) - 1; /* ditto */
 	tm->tm_year = bcd2bin(regs[ISL12057_REG_RTC_YR]) + 100;
 }
 
diff --git a/drivers/rtc/rtc-puv3.c b/drivers/rtc/rtc-puv3.c
index 1ecfe3bd92ac..1cff2a21db67 100644
--- a/drivers/rtc/rtc-puv3.c
+++ b/drivers/rtc/rtc-puv3.c
@@ -71,7 +71,7 @@ static int puv3_rtc_setpie(struct device *dev, int enabled)
 {
 	unsigned int tmp;
 
-	dev_debug(dev, "%s: pie=%d\n", __func__, enabled);
+	dev_dbg(dev, "%s: pie=%d\n", __func__, enabled);
 
 	spin_lock_irq(&puv3_rtc_pie_lock);
 	tmp = readl(RTC_RTSR) & ~RTC_RTSR_HZE;
@@ -140,7 +140,7 @@ static int puv3_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	rtc_tm_to_time(tm, &rtcalarm_count);
 	writel(rtcalarm_count, RTC_RTAR);
 
-	puv3_rtc_setaie(&dev->dev, alrm->enabled);
+	puv3_rtc_setaie(dev, alrm->enabled);
 
 	if (alrm->enabled)
 		enable_irq_wake(puv3_rtc_alarmno);
diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c
index 3eb3642ae299..d2b1ab3162c2 100644
--- a/drivers/rtc/rtc-sirfsoc.c
+++ b/drivers/rtc/rtc-sirfsoc.c
@@ -290,14 +290,6 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev)
 	rtc_div = ((32768 / RTC_HZ) / 2) - 1;
 	sirfsoc_rtc_iobrg_writel(rtc_div, rtcdrv->rtc_base + RTC_DIV);
 
-	rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
-			&sirfsoc_rtc_ops, THIS_MODULE);
-	if (IS_ERR(rtcdrv->rtc)) {
-		err = PTR_ERR(rtcdrv->rtc);
-		dev_err(&pdev->dev, "can't register RTC device\n");
-		return err;
-	}
-
 	/* 0x3 -> RTC_CLK */
 	sirfsoc_rtc_iobrg_writel(SIRFSOC_RTC_CLK,
 			rtcdrv->rtc_base + RTC_CLOCK_SWITCH);
@@ -312,6 +304,14 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev)
 	rtcdrv->overflow_rtc =
 		sirfsoc_rtc_iobrg_readl(rtcdrv->rtc_base + RTC_SW_VALUE);
 
+	rtcdrv->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
+			&sirfsoc_rtc_ops, THIS_MODULE);
+	if (IS_ERR(rtcdrv->rtc)) {
+		err = PTR_ERR(rtcdrv->rtc);
+		dev_err(&pdev->dev, "can't register RTC device\n");
+		return err;
+	}
+
 	rtcdrv->irq = platform_get_irq(pdev, 0);
 	err = devm_request_irq(
 			&pdev->dev,
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index eb5d22795c47..bb86494e2b7b 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -922,7 +922,7 @@ static int __init con3215_init(void)
 		raw3215_freelist = req;
 	}
 
-	cdev = ccw_device_probe_console();
+	cdev = ccw_device_probe_console(&raw3215_ccw_driver);
 	if (IS_ERR(cdev))
 		return -ENODEV;
 
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index 699fd3e363df..bb6b0df50b33 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -576,7 +576,6 @@ static struct console con3270 = {
 static int __init
 con3270_init(void)
 {
-	struct ccw_device *cdev;
 	struct raw3270 *rp;
 	void *cbuf;
 	int i;
@@ -591,10 +590,7 @@ con3270_init(void)
 		cpcmd("TERM AUTOCR OFF", NULL, 0, NULL);
 	}
 
-	cdev = ccw_device_probe_console();
-	if (IS_ERR(cdev))
-		return -ENODEV;
-	rp = raw3270_setup_console(cdev);
+	rp = raw3270_setup_console();
 	if (IS_ERR(rp))
 		return PTR_ERR(rp);
 
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 2cdec21e8924..de2c0483949f 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -776,16 +776,24 @@ raw3270_setup_device(struct ccw_device *cdev, struct raw3270 *rp, char *ascebc)
 }
 
 #ifdef CONFIG_TN3270_CONSOLE
+/* Tentative definition - see below for actual definition. */
+static struct ccw_driver raw3270_ccw_driver;
+
 /*
  * Setup 3270 device configured as console.
  */
-struct raw3270 __init *raw3270_setup_console(struct ccw_device *cdev)
+struct raw3270 __init *raw3270_setup_console(void)
 {
+	struct ccw_device *cdev;
 	unsigned long flags;
 	struct raw3270 *rp;
 	char *ascebc;
 	int rc;
 
+	cdev = ccw_device_probe_console(&raw3270_ccw_driver);
+	if (IS_ERR(cdev))
+		return ERR_CAST(cdev);
+
 	rp = kzalloc(sizeof(struct raw3270), GFP_KERNEL | GFP_DMA);
 	ascebc = kzalloc(256, GFP_KERNEL);
 	rc = raw3270_setup_device(cdev, rp, ascebc);
diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h
index 7b73ff8c1bd7..359276a88396 100644
--- a/drivers/s390/char/raw3270.h
+++ b/drivers/s390/char/raw3270.h
@@ -190,7 +190,7 @@ raw3270_put_view(struct raw3270_view *view)
 		wake_up(&raw3270_wait_queue);
 }
 
-struct raw3270 *raw3270_setup_console(struct ccw_device *cdev);
+struct raw3270 *raw3270_setup_console(void);
 void raw3270_wait_cons_dev(struct raw3270 *);
 
 /* Notifier for device addition/removal */
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 9f0ea6cb6922..e3bf885f4a6c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -541,18 +541,27 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area)
 
 static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 {
-	do {
+	static int ntsm_unsupported;
+
+	while (true) {
 		memset(sei, 0, sizeof(*sei));
 		sei->request.length = 0x0010;
 		sei->request.code = 0x000e;
-		sei->ntsm = ntsm;
+		if (!ntsm_unsupported)
+			sei->ntsm = ntsm;
 
 		if (chsc(sei))
 			break;
 
 		if (sei->response.code != 0x0001) {
-			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n",
-				      sei->response.code);
+			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x, ntsm=%llx)\n",
+				      sei->response.code, sei->ntsm);
+
+			if (sei->response.code == 3 && sei->ntsm) {
+				/* Fallback for old firmware. */
+				ntsm_unsupported = 1;
+				continue;
+			}
 			break;
 		}
 
@@ -568,7 +577,10 @@ static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 			CIO_CRW_EVENT(2, "chsc: unhandled nt: %d\n", sei->nt);
 			break;
 		}
-	} while (sei->u.nt0_area.flags & 0x80);
+
+		if (!(sei->u.nt0_area.flags & 0x80))
+			break;
+	}
 }
 
 /*
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index e9d783563cbb..4283dd3cdd49 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1609,7 +1609,7 @@ out_unlock:
 	return rc;
 }
 
-struct ccw_device *ccw_device_probe_console(void)
+struct ccw_device *ccw_device_probe_console(struct ccw_driver *drv)
 {
 	struct io_subchannel_private *io_priv;
 	struct ccw_device *cdev;
@@ -1631,6 +1631,7 @@ struct ccw_device *ccw_device_probe_console(void)
 		kfree(io_priv);
 		return cdev;
 	}
+	cdev->drv = drv;
 	set_io_private(sch, io_priv);
 	ret = ccw_device_console_enable(cdev, sch);
 	if (ret) {
diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c
index 160e7510aca6..0787b9756165 100644
--- a/drivers/sbus/char/bbc_envctrl.c
+++ b/drivers/sbus/char/bbc_envctrl.c
@@ -452,6 +452,9 @@ static void attach_one_temp(struct bbc_i2c_bus *bp, struct platform_device *op,
 	if (!tp)
 		return;
 
+	INIT_LIST_HEAD(&tp->bp_list);
+	INIT_LIST_HEAD(&tp->glob_list);
+
 	tp->client = bbc_i2c_attach(bp, op);
 	if (!tp->client) {
 		kfree(tp);
@@ -497,6 +500,9 @@ static void attach_one_fan(struct bbc_i2c_bus *bp, struct platform_device *op,
 	if (!fp)
 		return;
 
+	INIT_LIST_HEAD(&fp->bp_list);
+	INIT_LIST_HEAD(&fp->glob_list);
+
 	fp->client = bbc_i2c_attach(bp, op);
 	if (!fp->client) {
 		kfree(fp);
diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c
index c7763e482eb2..812b5f0361b6 100644
--- a/drivers/sbus/char/bbc_i2c.c
+++ b/drivers/sbus/char/bbc_i2c.c
@@ -300,13 +300,18 @@ static struct bbc_i2c_bus * attach_one_i2c(struct platform_device *op, int index
 	if (!bp)
 		return NULL;
 
+	INIT_LIST_HEAD(&bp->temps);
+	INIT_LIST_HEAD(&bp->fans);
+
 	bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs");
 	if (!bp->i2c_control_regs)
 		goto fail;
 
-	bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
-	if (!bp->i2c_bussel_reg)
-		goto fail;
+	if (op->num_resources == 2) {
+		bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
+		if (!bp->i2c_bussel_reg)
+			goto fail;
+	}
 
 	bp->waiting = 0;
 	init_waitqueue_head(&bp->wq);
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index 1e9d6ad9302b..7563b3d9cc76 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -2655,14 +2655,14 @@ static void NCR5380_dma_complete(NCR5380_instance * instance) {
  *
  * Purpose : abort a command
  *
- * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the 
- *      host byte of the result field to, if zero DID_ABORTED is 
+ * Inputs : cmd - the Scsi_Cmnd to abort, code - code to set the
+ *      host byte of the result field to, if zero DID_ABORTED is
  *      used.
  *
- * Returns : 0 - success, -1 on failure.
+ * Returns : SUCCESS - success, FAILED on failure.
  *
- *	XXX - there is no way to abort the command that is currently 
- *	connected, you have to wait for it to complete.  If this is 
+ *	XXX - there is no way to abort the command that is currently
+ *	connected, you have to wait for it to complete.  If this is
  *	a problem, we could implement longjmp() / setjmp(), setjmp()
  *	called where the loop started in NCR5380_main().
  *
@@ -2712,7 +2712,7 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
  * aborted flag and get back into our main loop.
  */
 
-		return 0;
+		return SUCCESS;
 	}
 #endif
 
diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
index 5f3101797c93..31ace4bef8fe 100644
--- a/drivers/scsi/aha1740.c
+++ b/drivers/scsi/aha1740.c
@@ -531,7 +531,7 @@ static int aha1740_eh_abort_handler (Scsi_Cmnd *dummy)
  * quiet as possible...
  */
 
-	return 0;
+	return SUCCESS;
 }
 
 static struct scsi_host_template aha1740_template = {
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 4f6a30b8e5f9..652b41b4ddbd 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -2500,16 +2500,15 @@ static int arcmsr_polling_ccbdone(struct AdapterControlBlock *acb,
 static int arcmsr_iop_confirm(struct AdapterControlBlock *acb)
 {
 	uint32_t cdb_phyaddr, cdb_phyaddr_hi32;
-	dma_addr_t dma_coherent_handle;
+
 	/*
 	********************************************************************
 	** here we need to tell iop 331 our freeccb.HighPart
 	** if freeccb.HighPart is not zero
 	********************************************************************
 	*/
-	dma_coherent_handle = acb->dma_coherent_handle;
-	cdb_phyaddr = (uint32_t)(dma_coherent_handle);
-	cdb_phyaddr_hi32 = (uint32_t)((cdb_phyaddr >> 16) >> 16);
+	cdb_phyaddr = lower_32_bits(acb->dma_coherent_handle);
+	cdb_phyaddr_hi32 = upper_32_bits(acb->dma_coherent_handle);
 	acb->cdb_phyaddr_hi32 = cdb_phyaddr_hi32;
 	/*
 	***********************************************************************
diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c
index 0f3cdbc80ba6..30073d43d87b 100644
--- a/drivers/scsi/atari_NCR5380.c
+++ b/drivers/scsi/atari_NCR5380.c
@@ -2613,7 +2613,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
  *	host byte of the result field to, if zero DID_ABORTED is
  *	used.
  *
- * Returns : 0 - success, -1 on failure.
+ * Returns : SUCCESS - success, FAILED on failure.
  *
  * XXX - there is no way to abort the command that is currently
  *	 connected, you have to wait for it to complete.  If this is
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index b2fcac78feaa..5bb9406688c9 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -897,17 +897,20 @@ mgmt_static_ip_modify(struct beiscsi_hba *phba,
 
 	if (ip_action == IP_ACTION_ADD) {
 		memcpy(req->ip_params.ip_record.ip_addr.addr, ip_param->value,
-		       ip_param->len);
+		       sizeof(req->ip_params.ip_record.ip_addr.addr));
 
 		if (subnet_param)
 			memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
-			       subnet_param->value, subnet_param->len);
+			       subnet_param->value,
+			       sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
 	} else {
 		memcpy(req->ip_params.ip_record.ip_addr.addr,
-		       if_info->ip_addr.addr, ip_param->len);
+		       if_info->ip_addr.addr,
+		       sizeof(req->ip_params.ip_record.ip_addr.addr));
 
 		memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
-		       if_info->ip_addr.subnet_mask, ip_param->len);
+		       if_info->ip_addr.subnet_mask,
+		       sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
 	}
 
 	rc = mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
@@ -935,7 +938,7 @@ static int mgmt_modify_gateway(struct beiscsi_hba *phba, uint8_t *gt_addr,
 	req->action = gtway_action;
 	req->ip_addr.ip_type = BE2_IPV4;
 
-	memcpy(req->ip_addr.addr, gt_addr, param_len);
+	memcpy(req->ip_addr.addr, gt_addr, sizeof(req->ip_addr.addr));
 
 	return mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
 }
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index 2e28392c2fb6..a38aafa030b3 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -72,7 +72,7 @@ struct bfa_sge_s {
 } while (0)
 
 #define bfa_swap_words(_x)  (	\
-	((_x) << 32) | ((_x) >> 32))
+	((u64)(_x) << 32) | ((u64)(_x) >> 32))
 
 #ifdef __BIG_ENDIAN
 #define bfa_sge_to_be(_x)
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 9b948505d118..cc6b13b81c53 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -411,6 +411,7 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct fc_frame_header *fh;
 	struct fcoe_rcv_info *fr;
 	struct fcoe_percpu_s *bg;
+	struct sk_buff *tmp_skb;
 	unsigned short oxid;
 
 	interface = container_of(ptype, struct bnx2fc_interface,
@@ -423,6 +424,12 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto err;
 	}
 
+	tmp_skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!tmp_skb)
+		goto err;
+
+	skb = tmp_skb;
+
 	if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) {
 		printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n");
 		goto err;
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index f37f3e3dd5d5..28fe6feae44c 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -1057,7 +1057,7 @@ int esas2r_eh_abort(struct scsi_cmnd *cmd)
 
 		cmd->scsi_done(cmd);
 
-		return 0;
+		return SUCCESS;
 	}
 
 	spin_lock_irqsave(&a->queue_lock, flags);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 868318a7067c..528bff5ec91f 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3131,7 +3131,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 		}
 		if (ioc->Request.Type.Direction == XFER_WRITE) {
 			if (copy_from_user(buff[sg_used], data_ptr, sz)) {
-				status = -ENOMEM;
+				status = -EFAULT;
 				goto cleanup1;
 			}
 		} else
@@ -4367,9 +4367,9 @@ static inline void hpsa_set_driver_support_bits(struct ctlr_info *h)
 {
 	u32 driver_support;
 
-#ifdef CONFIG_X86
-	/* Need to enable prefetch in the SCSI core for 6400 in x86 */
 	driver_support = readl(&(h->cfgtable->driver_support));
+	/* Need to enable prefetch in the SCSI core for 6400 in x86 */
+#ifdef CONFIG_X86
 	driver_support |= ENABLE_SCSI_PREFETCH;
 #endif
 	driver_support |= ENABLE_UNIT_ATTN;
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index fa764406df68..c5bb0e0a36b9 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -185,6 +185,11 @@ static struct viosrp_crq *crq_queue_next_crq(struct crq_queue *queue)
 	if (crq->valid & 0x80) {
 		if (++queue->cur == queue->size)
 			queue->cur = 0;
+
+		/* Ensure the read of the valid bit occurs before reading any
+		 * other bits of the CRQ entry
+		 */
+		rmb();
 	} else
 		crq = NULL;
 	spin_unlock_irqrestore(&queue->lock, flags);
@@ -203,6 +208,11 @@ static int ibmvscsi_send_crq(struct ibmvscsi_host_data *hostdata,
 {
 	struct vio_dev *vdev = to_vio_dev(hostdata->dev);
 
+	/*
+	 * Ensure the command buffer is flushed to memory before handing it
+	 * over to the VIOS to prevent it from fetching any stale data.
+	 */
+	mb();
 	return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2);
 }
 
@@ -797,7 +807,8 @@ static void purge_requests(struct ibmvscsi_host_data *hostdata, int error_code)
 				       evt->hostdata->dev);
 			if (evt->cmnd_done)
 				evt->cmnd_done(evt->cmnd);
-		} else if (evt->done)
+		} else if (evt->done && evt->crq.format != VIOSRP_MAD_FORMAT &&
+			   evt->iu.srp.login_req.opcode != SRP_LOGIN_REQ)
 			evt->done(evt);
 		free_event_struct(&evt->hostdata->pool, evt);
 		spin_lock_irqsave(hostdata->host->host_lock, flags);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 40462415291e..454998669c2a 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -717,11 +717,21 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
 			return NULL;
 		}
 
+		if (data_size > ISCSI_DEF_MAX_RECV_SEG_LEN) {
+			iscsi_conn_printk(KERN_ERR, conn, "Invalid buffer len of %u for login task. Max len is %u\n", data_size, ISCSI_DEF_MAX_RECV_SEG_LEN);
+			return NULL;
+		}
+
 		task = conn->login_task;
 	} else {
 		if (session->state != ISCSI_STATE_LOGGED_IN)
 			return NULL;
 
+		if (data_size != 0) {
+			iscsi_conn_printk(KERN_ERR, conn, "Can not send data buffer of len %u for op 0x%x\n", data_size, opcode);
+			return NULL;
+		}
+
 		BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE);
 		BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED);
 
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 816db12ef5d5..52587ceac099 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -1967,7 +1967,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
 	     cmd->device->id, cmd->device->lun);
 
 	if(list_empty(&adapter->pending_list))
-		return FALSE;
+		return FAILED;
 
 	list_for_each_safe(pos, next, &adapter->pending_list) {
 
@@ -1990,7 +1990,7 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
 					(aor==SCB_ABORT) ? "ABORTING":"RESET",
 					scb->idx);
 
-				return FALSE;
+				return FAILED;
 			}
 			else {
 
@@ -2015,12 +2015,12 @@ megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
 				list_add_tail(SCSI_LIST(cmd),
 						&adapter->completed_list);
 
-				return TRUE;
+				return SUCCESS;
 			}
 		}
 	}
 
-	return FALSE;
+	return FAILED;
 }
 
 static inline int
diff --git a/drivers/scsi/megaraid/megaraid_mm.c b/drivers/scsi/megaraid/megaraid_mm.c
index dfffd0f37916..a70692779a16 100644
--- a/drivers/scsi/megaraid/megaraid_mm.c
+++ b/drivers/scsi/megaraid/megaraid_mm.c
@@ -486,6 +486,8 @@ mimd_to_kioc(mimd_t __user *umimd, mraid_mmadp_t *adp, uioc_t *kioc)
 
 	pthru32->dataxferaddr	= kioc->buf_paddr;
 	if (kioc->data_dir & UIOC_WR) {
+		if (pthru32->dataxferlen > kioc->xferlen)
+			return -EINVAL;
 		if (copy_from_user(kioc->buf_vaddr, kioc->user_data,
 						pthru32->dataxferlen)) {
 			return (-EFAULT);
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 3b7ad10497fe..c80afde97e96 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -953,7 +953,7 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 		cpu_to_le32(upper_32_bits(cmd_to_abort->frame_phys_addr));
 
 	cmd->sync_cmd = 1;
-	cmd->cmd_status = 0xFF;
+	cmd->cmd_status = ENODATA;
 
 	instance->instancet->issue_dcmd(instance, cmd);
 
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 7f0af4fcc001..6fd7d40b2c4d 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -8293,7 +8293,6 @@ _scsih_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	mpt2sas_base_free_resources(ioc);
 	pci_save_state(pdev);
-	pci_disable_device(pdev);
 	pci_set_power_state(pdev, device_state);
 	return 0;
 }
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 89a53002b585..23c1b0cd3074 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2536,7 +2536,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    ha->flags.enable_64bit_addressing ? "enable" :
 	    "disable");
 	ret = qla2x00_mem_alloc(ha, req_length, rsp_length, &req, &rsp);
-	if (!ret) {
+	if (ret) {
 		ql_log_pci(ql_log_fatal, pdev, 0x0031,
 		    "Failed to allocate memory for adapter, aborting.\n");
 
@@ -3039,10 +3039,8 @@ qla2x00_unmap_iobases(struct qla_hw_data *ha)
 }
 
 static void
-qla2x00_clear_drv_active(scsi_qla_host_t *vha)
+qla2x00_clear_drv_active(struct qla_hw_data *ha)
 {
-	struct qla_hw_data *ha = vha->hw;
-
 	if (IS_QLA8044(ha)) {
 		qla8044_idc_lock(ha);
 		qla8044_clear_drv_active(ha);
@@ -3111,7 +3109,7 @@ qla2x00_remove_one(struct pci_dev *pdev)
 
 	scsi_host_put(base_vha->host);
 
-	qla2x00_clear_drv_active(base_vha);
+	qla2x00_clear_drv_active(ha);
 
 	qla2x00_unmap_iobases(ha);
 
@@ -3478,10 +3476,10 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 	else {
 		qla2x00_set_reserved_loop_ids(ha);
 		ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0123,
-		    "loop_id_map=%p. \n", ha->loop_id_map);
+		    "loop_id_map=%p.\n", ha->loop_id_map);
 	}
 
-	return 1;
+	return 0;
 
 fail_async_pd:
 	dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 0cb73074c199..2f264ac79546 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1382,12 +1382,10 @@ static inline void qlt_unmap_sg(struct scsi_qla_host *vha,
 static int qlt_check_reserve_free_req(struct scsi_qla_host *vha,
 	uint32_t req_cnt)
 {
-	struct qla_hw_data *ha = vha->hw;
-	device_reg_t __iomem *reg = ha->iobase;
 	uint32_t cnt;
 
 	if (vha->req->cnt < (req_cnt + 2)) {
-		cnt = (uint16_t)RD_REG_DWORD(&reg->isp24.req_q_out);
+		cnt = (uint16_t)RD_REG_DWORD(vha->req->req_q_out);
 
 		ql_dbg(ql_dbg_tgt, vha, 0xe00a,
 		    "Request ring circled: cnt=%d, vha->->ring_index=%d, "
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 788c4fe2b0c9..9d81f7693f99 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -707,7 +707,16 @@ static void tcm_qla2xxx_clear_nacl_from_fcport_map(struct qla_tgt_sess *sess)
 	pr_debug("fc_rport domain: port_id 0x%06x\n", nacl->nport_id);
 
 	node = btree_remove32(&lport->lport_fcport_map, nacl->nport_id);
-	WARN_ON(node && (node != se_nacl));
+	if (WARN_ON(node && (node != se_nacl))) {
+		/*
+		 * The nacl no longer matches what we think it should be.
+		 * Most likely a new dynamic acl has been added while
+		 * someone dropped the hardware lock.  It clearly is a
+		 * bug elsewhere, but this bit can't make things worse.
+		 */
+		btree_insert32(&lport->lport_fcport_map, nacl->nport_id,
+			       node, GFP_ATOMIC);
+	}
 
 	pr_debug("Removed from fcport_map: %p for WWNN: 0x%016LX, port_id: 0x%06x\n",
 	    se_nacl, nacl->nport_wwnn, nacl->nport_id);
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index f969aca0b54e..c1d04d4d3c6c 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -202,6 +202,7 @@ static struct {
 	{"IOMEGA", "Io20S         *F", NULL, BLIST_KEY},
 	{"INSITE", "Floptical   F*8I", NULL, BLIST_KEY},
 	{"INSITE", "I325VM", NULL, BLIST_KEY},
+	{"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC},
 	{"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN},
 	{"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
@@ -222,6 +223,7 @@ static struct {
 	{"PIONEER", "CD-ROM DRM-602X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"PIONEER", "CD-ROM DRM-604X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"PIONEER", "CD-ROM DRM-624X", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
+	{"Promise", "VTrak E610f", NULL, BLIST_SPARSELUN | BLIST_NO_RSOC},
 	{"Promise", "", NULL, BLIST_SPARSELUN},
 	{"QUANTUM", "XP34301", "1071", BLIST_NOTQ},
 	{"REGAL", "CDC-4X", NULL, BLIST_MAX5LUN | BLIST_SINGLELUN},
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 78b004da2885..96b6664bb1cf 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -131,7 +131,7 @@ scmd_eh_abort_handler(struct work_struct *work)
 				    "aborting command %p\n", scmd));
 		rtn = scsi_try_to_abort_cmd(sdev->host->hostt, scmd);
 		if (rtn == SUCCESS) {
-			scmd->result |= DID_TIME_OUT << 16;
+			set_host_byte(scmd, DID_TIME_OUT);
 			if (scsi_host_eh_past_deadline(sdev->host)) {
 				SCSI_LOG_ERROR_RECOVERY(3,
 					scmd_printk(KERN_INFO, scmd,
@@ -167,7 +167,7 @@ scmd_eh_abort_handler(struct work_struct *work)
 			scmd_printk(KERN_WARNING, scmd,
 				    "scmd %p terminate "
 				    "aborted command\n", scmd));
-		scmd->result |= DID_TIME_OUT << 16;
+		set_host_byte(scmd, DID_TIME_OUT);
 		scsi_finish_command(scmd);
 	}
 }
@@ -290,7 +290,7 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 		if (scsi_abort_command(scmd) == SUCCESS)
 			return BLK_EH_NOT_HANDLED;
 
-	scmd->result |= DID_TIME_OUT << 16;
+	set_host_byte(scmd, DID_TIME_OUT);
 
 	if (unlikely(rtn == BLK_EH_NOT_HANDLED &&
 		     !scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD)))
@@ -1157,6 +1157,15 @@ int scsi_eh_get_sense(struct list_head *work_q,
 					     __func__));
 			break;
 		}
+		if (status_byte(scmd->result) != CHECK_CONDITION)
+			/*
+			 * don't request sense if there's no check condition
+			 * status because the error we're processing isn't one
+			 * that has a sense code (and some devices get
+			 * confused by sense requests out of the blue)
+			 */
+			continue;
+
 		SCSI_LOG_ERROR_RECOVERY(2, scmd_printk(KERN_INFO, scmd,
 						  "%s: requesting sense\n",
 						  current->comm));
@@ -1764,7 +1773,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 		break;
 	case DID_ABORT:
 		if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) {
-			scmd->result |= DID_TIME_OUT << 16;
+			set_host_byte(scmd, DID_TIME_OUT);
 			return SUCCESS;
 		}
 	case DID_NO_CONNECT:
@@ -1975,8 +1984,10 @@ static void scsi_restart_operations(struct Scsi_Host *shost)
 	 * is no point trying to lock the door of an off-line device.
 	 */
 	shost_for_each_device(sdev, shost) {
-		if (scsi_device_online(sdev) && sdev->locked)
+		if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) {
 			scsi_eh_lock_door(sdev);
+			sdev->was_reset = 0;
+		}
 	}
 
 	/*
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 62ec84b42e31..64e487a8bf59 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -831,6 +831,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			scsi_next_command(cmd);
 			return;
 		}
+	} else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
+		/*
+		 * Certain non BLOCK_PC requests are commands that don't
+		 * actually transfer anything (FLUSH), so cannot use
+		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
+		 * This sets the error explicitly for the problem case.
+		 */
+		error = __scsi_error_from_host_byte(cmd, result);
 	}
 
 	/* no bidi support for !REQ_TYPE_BLOCK_PC yet */
diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c
index fe30ea94ffe6..109802f776ed 100644
--- a/drivers/scsi/scsi_netlink.c
+++ b/drivers/scsi/scsi_netlink.c
@@ -77,7 +77,7 @@ scsi_nl_rcv_msg(struct sk_buff *skb)
 			goto next_msg;
 		}
 
-		if (!capable(CAP_SYS_ADMIN)) {
+		if (!netlink_capable(skb, CAP_SYS_ADMIN)) {
 			err = -EPERM;
 			goto next_msg;
 		}
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 307a81137607..054ec2c412a4 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -320,6 +320,7 @@ static void scsi_target_destroy(struct scsi_target *starget)
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
 	unsigned long flags;
 
+	starget->state = STARGET_DEL;
 	transport_destroy_device(dev);
 	spin_lock_irqsave(shost->host_lock, flags);
 	if (shost->hostt->target_destroy)
@@ -371,6 +372,37 @@ static struct scsi_target *__scsi_find_target(struct device *parent,
 }
 
 /**
+ * scsi_target_reap_ref_release - remove target from visibility
+ * @kref: the reap_ref in the target being released
+ *
+ * Called on last put of reap_ref, which is the indication that no device
+ * under this target is visible anymore, so render the target invisible in
+ * sysfs.  Note: we have to be in user context here because the target reaps
+ * should be done in places where the scsi device visibility is being removed.
+ */
+static void scsi_target_reap_ref_release(struct kref *kref)
+{
+	struct scsi_target *starget
+		= container_of(kref, struct scsi_target, reap_ref);
+
+	/*
+	 * if we get here and the target is still in the CREATED state that
+	 * means it was allocated but never made visible (because a scan
+	 * turned up no LUNs), so don't call device_del() on it.
+	 */
+	if (starget->state != STARGET_CREATED) {
+		transport_remove_device(&starget->dev);
+		device_del(&starget->dev);
+	}
+	scsi_target_destroy(starget);
+}
+
+static void scsi_target_reap_ref_put(struct scsi_target *starget)
+{
+	kref_put(&starget->reap_ref, scsi_target_reap_ref_release);
+}
+
+/**
  * scsi_alloc_target - allocate a new or find an existing target
  * @parent:	parent of the target (need not be a scsi host)
  * @channel:	target channel number (zero if no channels)
@@ -392,7 +424,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 		+ shost->transportt->target_size;
 	struct scsi_target *starget;
 	struct scsi_target *found_target;
-	int error;
+	int error, ref_got;
 
 	starget = kzalloc(size, GFP_KERNEL);
 	if (!starget) {
@@ -401,7 +433,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	}
 	dev = &starget->dev;
 	device_initialize(dev);
-	starget->reap_ref = 1;
+	kref_init(&starget->reap_ref);
 	dev->parent = get_device(parent);
 	dev_set_name(dev, "target%d:%d:%d", shost->host_no, channel, id);
 	dev->bus = &scsi_bus_type;
@@ -441,29 +473,36 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	return starget;
 
  found:
-	found_target->reap_ref++;
+	/*
+	 * release routine already fired if kref is zero, so if we can still
+	 * take the reference, the target must be alive.  If we can't, it must
+	 * be dying and we need to wait for a new target
+	 */
+	ref_got = kref_get_unless_zero(&found_target->reap_ref);
+
 	spin_unlock_irqrestore(shost->host_lock, flags);
-	if (found_target->state != STARGET_DEL) {
+	if (ref_got) {
 		put_device(dev);
 		return found_target;
 	}
-	/* Unfortunately, we found a dying target; need to
-	 * wait until it's dead before we can get a new one */
+	/*
+	 * Unfortunately, we found a dying target; need to wait until it's
+	 * dead before we can get a new one.  There is an anomaly here.  We
+	 * *should* call scsi_target_reap() to balance the kref_get() of the
+	 * reap_ref above.  However, since the target being released, it's
+	 * already invisible and the reap_ref is irrelevant.  If we call
+	 * scsi_target_reap() we might spuriously do another device_del() on
+	 * an already invisible target.
+	 */
 	put_device(&found_target->dev);
-	flush_scheduled_work();
+	/*
+	 * length of time is irrelevant here, we just want to yield the CPU
+	 * for a tick to avoid busy waiting for the target to die.
+	 */
+	msleep(1);
 	goto retry;
 }
 
-static void scsi_target_reap_usercontext(struct work_struct *work)
-{
-	struct scsi_target *starget =
-		container_of(work, struct scsi_target, ew.work);
-
-	transport_remove_device(&starget->dev);
-	device_del(&starget->dev);
-	scsi_target_destroy(starget);
-}
-
 /**
  * scsi_target_reap - check to see if target is in use and destroy if not
  * @starget: target to be checked
@@ -474,28 +513,13 @@ static void scsi_target_reap_usercontext(struct work_struct *work)
  */
 void scsi_target_reap(struct scsi_target *starget)
 {
-	struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
-	unsigned long flags;
-	enum scsi_target_state state;
-	int empty = 0;
-
-	spin_lock_irqsave(shost->host_lock, flags);
-	state = starget->state;
-	if (--starget->reap_ref == 0 && list_empty(&starget->devices)) {
-		empty = 1;
-		starget->state = STARGET_DEL;
-	}
-	spin_unlock_irqrestore(shost->host_lock, flags);
-
-	if (!empty)
-		return;
-
-	BUG_ON(state == STARGET_DEL);
-	if (state == STARGET_CREATED)
-		scsi_target_destroy(starget);
-	else
-		execute_in_process_context(scsi_target_reap_usercontext,
-					   &starget->ew);
+	/*
+	 * serious problem if this triggers: STARGET_DEL is only set in the if
+	 * the reap_ref drops to zero, so we're trying to do another final put
+	 * on an already released kref
+	 */
+	BUG_ON(starget->state == STARGET_DEL);
+	scsi_target_reap_ref_put(starget);
 }
 
 /**
@@ -898,6 +922,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	if (*bflags & BLIST_USE_10_BYTE_MS)
 		sdev->use_10_for_ms = 1;
 
+	/* some devices don't like REPORT SUPPORTED OPERATION CODES
+	 * and will simply timeout causing sd_mod init to take a very
+	 * very long time */
+	if (*bflags & BLIST_NO_RSOC)
+		sdev->no_report_opcodes = 1;
+
 	/* set the device running here so that slave configure
 	 * may do I/O */
 	ret = scsi_device_set_state(sdev, SDEV_RUNNING);
@@ -926,7 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 
 	sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT;
 
-	if (*bflags & BLIST_SKIP_VPD_PAGES)
+	if (*bflags & BLIST_TRY_VPD_PAGES)
+		sdev->try_vpd_pages = 1;
+	else if (*bflags & BLIST_SKIP_VPD_PAGES)
 		sdev->skip_vpd_pages = 1;
 
 	transport_configure_device(&sdev->sdev_gendev);
@@ -1212,6 +1244,12 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget,
 		max_dev_lun = min(8U, max_dev_lun);
 
 	/*
+	 * Stop scanning at 255 unless BLIST_SCSI3LUN
+	 */
+	if (!(bflags & BLIST_SCSI3LUN))
+		max_dev_lun = min(256U, max_dev_lun);
+
+	/*
 	 * We have already scanned LUN 0, so start at LUN 1. Keep scanning
 	 * until we reach the max, or no LUN is found and we are not
 	 * sparse_lun.
@@ -1532,6 +1570,10 @@ struct scsi_device *__scsi_add_device(struct Scsi_Host *shost, uint channel,
 	}
 	mutex_unlock(&shost->scan_mutex);
 	scsi_autopm_put_target(starget);
+	/*
+	 * paired with scsi_alloc_target().  Target will be destroyed unless
+	 * scsi_probe_and_add_lun made an underlying device visible
+	 */
 	scsi_target_reap(starget);
 	put_device(&starget->dev);
 
@@ -1612,8 +1654,10 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel,
 
  out_reap:
 	scsi_autopm_put_target(starget);
-	/* now determine if the target has any children at all
-	 * and if not, nuke it */
+	/*
+	 * paired with scsi_alloc_target(): determine if the target has
+	 * any children at all and if not, nuke it
+	 */
 	scsi_target_reap(starget);
 
 	put_device(&starget->dev);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 9117d0bf408e..665acbf83693 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -383,17 +383,14 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 {
 	struct scsi_device *sdev;
 	struct device *parent;
-	struct scsi_target *starget;
 	struct list_head *this, *tmp;
 	unsigned long flags;
 
 	sdev = container_of(work, struct scsi_device, ew.work);
 
 	parent = sdev->sdev_gendev.parent;
-	starget = to_scsi_target(parent);
 
 	spin_lock_irqsave(sdev->host->host_lock, flags);
-	starget->reap_ref++;
 	list_del(&sdev->siblings);
 	list_del(&sdev->same_target_siblings);
 	list_del(&sdev->starved_entry);
@@ -413,8 +410,6 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 	/* NULL queue means the device can't be used */
 	sdev->request_queue = NULL;
 
-	scsi_target_reap(scsi_target(sdev));
-
 	kfree(sdev->inquiry);
 	kfree(sdev);
 
@@ -1071,6 +1066,13 @@ void __scsi_remove_device(struct scsi_device *sdev)
 		sdev->host->hostt->slave_destroy(sdev);
 	transport_destroy_device(dev);
 
+	/*
+	 * Paired with the kref_get() in scsi_sysfs_initialize().  We have
+	 * remoed sysfs visibility from the device, so make the target
+	 * invisible if this was the last device underneath it.
+	 */
+	scsi_target_reap(scsi_target(sdev));
+
 	put_device(dev);
 }
 
@@ -1133,7 +1135,7 @@ void scsi_remove_target(struct device *dev)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
 			/* assuming new targets arrive at the end */
-			starget->reap_ref++;
+			kref_get(&starget->reap_ref);
 			spin_unlock_irqrestore(shost->host_lock, flags);
 			if (last)
 				scsi_target_reap(last);
@@ -1217,6 +1219,12 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev)
 	list_add_tail(&sdev->same_target_siblings, &starget->devices);
 	list_add_tail(&sdev->siblings, &shost->__devices);
 	spin_unlock_irqrestore(shost->host_lock, flags);
+	/*
+	 * device can now only be removed via __scsi_remove_device() so hold
+	 * the target.  Target will be held in CREATED state until something
+	 * beneath it becomes visible (in which case it moves to RUNNING)
+	 */
+	kref_get(&starget->reap_ref);
 }
 
 int scsi_is_sdev_device(const struct device *dev)
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 1b681427dde0..c341f855fadc 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -1621,8 +1621,6 @@ void sas_rphy_free(struct sas_rphy *rphy)
 	list_del(&rphy->list);
 	mutex_unlock(&sas_host->lock);
 
-	sas_bsg_remove(shost, rphy);
-
 	transport_destroy_device(dev);
 
 	put_device(dev);
@@ -1681,6 +1679,7 @@ sas_rphy_remove(struct sas_rphy *rphy)
 	}
 
 	sas_rphy_unlink(rphy);
+	sas_bsg_remove(NULL, rphy);
 	transport_remove_device(dev);
 	device_del(dev);
 }
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index d47ffc8d3e43..e3e794ee7ddd 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -473,7 +473,8 @@ static void __srp_start_tl_fail_timers(struct srp_rport *rport)
 	if (delay > 0)
 		queue_delayed_work(system_long_wq, &rport->reconnect_work,
 				   1UL * delay * HZ);
-	if (srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) {
+	if ((fast_io_fail_tmo >= 0 || dev_loss_tmo >= 0) &&
+	    srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) {
 		pr_debug("%s new state: %d\n", dev_name(&shost->shost_gendev),
 			 rport->state);
 		scsi_target_block(&shost->shost_gendev);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 470954aba728..e8abb731c7ec 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1463,8 +1463,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
 			sd_print_sense_hdr(sdkp, &sshdr);
 		/* we need to evaluate the error return  */
 		if (scsi_sense_valid(&sshdr) &&
-			/* 0x3a is medium not present */
-			sshdr.asc == 0x3a)
+			(sshdr.asc == 0x3a ||	/* medium not present */
+			 sshdr.asc == 0x20))	/* invalid command */
 				/* this is no error here */
 				return 0;
 
@@ -2686,6 +2686,11 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer)
 
 static int sd_try_extended_inquiry(struct scsi_device *sdp)
 {
+	/* Attempt VPD inquiry if the device blacklist explicitly calls
+	 * for it.
+	 */
+	if (sdp->try_vpd_pages)
+		return 1;
 	/*
 	 * Although VPD inquiries can go to SCSI-2 type devices,
 	 * some USB ones crash on receiving them, and the pages
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 9969fa1ef7c4..ed0f899e8aa5 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -33,6 +33,7 @@
 #include <linux/device.h>
 #include <linux/hyperv.h>
 #include <linux/mempool.h>
+#include <linux/blkdev.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -330,17 +331,17 @@ static int storvsc_timeout = 180;
 
 static void storvsc_on_channel_callback(void *context);
 
-/*
- * In Hyper-V, each port/path/target maps to 1 scsi host adapter.  In
- * reality, the path/target is not used (ie always set to 0) so our
- * scsi host adapter essentially has 1 bus with 1 target that contains
- * up to 256 luns.
- */
-#define STORVSC_MAX_LUNS_PER_TARGET			64
-#define STORVSC_MAX_TARGETS				1
-#define STORVSC_MAX_CHANNELS				1
+#define STORVSC_MAX_LUNS_PER_TARGET			255
+#define STORVSC_MAX_TARGETS				2
+#define STORVSC_MAX_CHANNELS				8
 
+#define STORVSC_FC_MAX_LUNS_PER_TARGET			255
+#define STORVSC_FC_MAX_TARGETS				128
+#define STORVSC_FC_MAX_CHANNELS				8
 
+#define STORVSC_IDE_MAX_LUNS_PER_TARGET			64
+#define STORVSC_IDE_MAX_TARGETS				1
+#define STORVSC_IDE_MAX_CHANNELS			1
 
 struct storvsc_cmd_request {
 	struct list_head entry;
@@ -1017,6 +1018,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 		case ATA_12:
 			set_host_byte(scmnd, DID_PASSTHROUGH);
 			break;
+		/*
+		 * On Some Windows hosts TEST_UNIT_READY command can return
+		 * SRB_STATUS_ERROR, let the upper level code deal with it
+		 * based on the sense information.
+		 */
+		case TEST_UNIT_READY:
+			break;
 		default:
 			set_host_byte(scmnd, DID_TARGET_FAILURE);
 		}
@@ -1518,6 +1526,16 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
 	return SUCCESS;
 }
 
+/*
+ * The host guarantees to respond to each command, although I/O latencies might
+ * be unbounded on Azure.  Reset the timer unconditionally to give the host a
+ * chance to perform EH.
+ */
+static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
+{
+	return BLK_EH_RESET_TIMER;
+}
+
 static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd)
 {
 	bool allowed = true;
@@ -1553,9 +1571,19 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	struct vmscsi_request *vm_srb;
 	struct stor_mem_pools *memp = scmnd->device->hostdata;
 
-	if (!storvsc_scsi_cmd_ok(scmnd)) {
-		scmnd->scsi_done(scmnd);
-		return 0;
+	if (vmstor_current_major <= VMSTOR_WIN8_MAJOR) {
+		/*
+		 * On legacy hosts filter unimplemented commands.
+		 * Future hosts are expected to correctly handle
+		 * unsupported commands. Furthermore, it is
+		 * possible that some of the currently
+		 * unsupported commands maybe supported in
+		 * future versions of the host.
+		 */
+		if (!storvsc_scsi_cmd_ok(scmnd)) {
+			scmnd->scsi_done(scmnd);
+			return 0;
+		}
 	}
 
 	request_size = sizeof(struct storvsc_cmd_request);
@@ -1580,26 +1608,24 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	vm_srb = &cmd_request->vstor_packet.vm_srb;
 	vm_srb->win8_extension.time_out_value = 60;
 
+	vm_srb->win8_extension.srb_flags |=
+		(SRB_FLAGS_QUEUE_ACTION_ENABLE |
+		SRB_FLAGS_DISABLE_SYNCH_TRANSFER);
 
 	/* Build the SRB */
 	switch (scmnd->sc_data_direction) {
 	case DMA_TO_DEVICE:
 		vm_srb->data_in = WRITE_TYPE;
 		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_OUT;
-		vm_srb->win8_extension.srb_flags |=
-			(SRB_FLAGS_QUEUE_ACTION_ENABLE |
-			SRB_FLAGS_DISABLE_SYNCH_TRANSFER);
 		break;
 	case DMA_FROM_DEVICE:
 		vm_srb->data_in = READ_TYPE;
 		vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_IN;
-		vm_srb->win8_extension.srb_flags |=
-			(SRB_FLAGS_QUEUE_ACTION_ENABLE |
-			SRB_FLAGS_DISABLE_SYNCH_TRANSFER);
 		break;
 	default:
 		vm_srb->data_in = UNKNOWN_TYPE;
-		vm_srb->win8_extension.srb_flags = 0;
+		vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN |
+						     SRB_FLAGS_DATA_OUT);
 		break;
 	}
 
@@ -1687,11 +1713,11 @@ static struct scsi_host_template scsi_driver = {
 	.bios_param =		storvsc_get_chs,
 	.queuecommand =		storvsc_queuecommand,
 	.eh_host_reset_handler =	storvsc_host_reset_handler,
+	.eh_timed_out =		storvsc_eh_timed_out,
 	.slave_alloc =		storvsc_device_alloc,
 	.slave_destroy =	storvsc_device_destroy,
 	.slave_configure =	storvsc_device_configure,
-	.cmd_per_lun =		1,
-	/* 64 max_queue * 1 target */
+	.cmd_per_lun =		255,
 	.can_queue =		STORVSC_MAX_IO_REQUESTS*STORVSC_MAX_TARGETS,
 	.this_id =		-1,
 	/* no use setting to 0 since ll_blk_rw reset it to 1 */
@@ -1743,19 +1769,25 @@ static int storvsc_probe(struct hv_device *device,
 	 * set state to properly communicate with the host.
 	 */
 
-	if (vmbus_proto_version == VERSION_WIN8) {
-		sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE;
-		vmscsi_size_delta = 0;
-		vmstor_current_major = VMSTOR_WIN8_MAJOR;
-		vmstor_current_minor = VMSTOR_WIN8_MINOR;
-	} else {
+	switch (vmbus_proto_version) {
+	case VERSION_WS2008:
+	case VERSION_WIN7:
 		sense_buffer_size = PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE;
 		vmscsi_size_delta = sizeof(struct vmscsi_win8_extension);
 		vmstor_current_major = VMSTOR_WIN7_MAJOR;
 		vmstor_current_minor = VMSTOR_WIN7_MINOR;
+		break;
+	default:
+		sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE;
+		vmscsi_size_delta = 0;
+		vmstor_current_major = VMSTOR_WIN8_MAJOR;
+		vmstor_current_minor = VMSTOR_WIN8_MINOR;
+		break;
 	}
 
-
+	if (dev_id->driver_data == SFC_GUID)
+		scsi_driver.can_queue = (STORVSC_MAX_IO_REQUESTS *
+					 STORVSC_FC_MAX_TARGETS);
 	host = scsi_host_alloc(&scsi_driver,
 			       sizeof(struct hv_host_device));
 	if (!host)
@@ -1789,12 +1821,25 @@ static int storvsc_probe(struct hv_device *device,
 	host_dev->path = stor_device->path_id;
 	host_dev->target = stor_device->target_id;
 
-	/* max # of devices per target */
-	host->max_lun = STORVSC_MAX_LUNS_PER_TARGET;
-	/* max # of targets per channel */
-	host->max_id = STORVSC_MAX_TARGETS;
-	/* max # of channels */
-	host->max_channel = STORVSC_MAX_CHANNELS - 1;
+	switch (dev_id->driver_data) {
+	case SFC_GUID:
+		host->max_lun = STORVSC_FC_MAX_LUNS_PER_TARGET;
+		host->max_id = STORVSC_FC_MAX_TARGETS;
+		host->max_channel = STORVSC_FC_MAX_CHANNELS - 1;
+		break;
+
+	case SCSI_GUID:
+		host->max_lun = STORVSC_MAX_LUNS_PER_TARGET;
+		host->max_id = STORVSC_MAX_TARGETS;
+		host->max_channel = STORVSC_MAX_CHANNELS - 1;
+		break;
+
+	default:
+		host->max_lun = STORVSC_IDE_MAX_LUNS_PER_TARGET;
+		host->max_id = STORVSC_IDE_MAX_TARGETS;
+		host->max_channel = STORVSC_IDE_MAX_CHANNELS - 1;
+		break;
+	}
 	/* max cmd length */
 	host->max_cmd_len = STORVSC_MAX_CMD_LEN;
 
diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c
index 636bbe0ea84c..fc57c8aec2b3 100644
--- a/drivers/scsi/sun3_NCR5380.c
+++ b/drivers/scsi/sun3_NCR5380.c
@@ -2597,15 +2597,15 @@ static void NCR5380_reselect (struct Scsi_Host *instance)
  * Purpose : abort a command
  *
  * Inputs : cmd - the struct scsi_cmnd to abort, code - code to set the
- * 	host byte of the result field to, if zero DID_ABORTED is 
+ *	host byte of the result field to, if zero DID_ABORTED is
  *	used.
  *
- * Returns : 0 - success, -1 on failure.
+ * Returns : SUCCESS - success, FAILED on failure.
  *
- * XXX - there is no way to abort the command that is currently 
- * 	 connected, you have to wait for it to complete.  If this is 
+ * XXX - there is no way to abort the command that is currently
+ *	 connected, you have to wait for it to complete.  If this is
  *	 a problem, we could implement longjmp() / setjmp(), setjmp()
- * 	 called where the loop started in NCR5380_main().
+ *	 called where the loop started in NCR5380_main().
  */
 
 static int NCR5380_abort(struct scsi_cmnd *cmd)
diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c
index d92fe4037e94..6b349e301869 100644
--- a/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -3000,7 +3000,11 @@ sym_dequeue_from_squeue(struct sym_hcb *np, int i, int target, int lun, int task
 		if ((target == -1 || cp->target == target) &&
 		    (lun    == -1 || cp->lun    == lun)    &&
 		    (task   == -1 || cp->tag    == task)) {
+#ifdef SYM_OPT_HANDLE_DEVICE_QUEUEING
 			sym_set_cam_status(cp->cmd, DID_SOFT_ERROR);
+#else
+			sym_set_cam_status(cp->cmd, DID_REQUEUE);
+#endif
 			sym_remque(&cp->link_ccbq);
 			sym_insque_tail(&cp->link_ccbq, &np->comp_ccbq);
 		}
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 16bfd50cd3fe..8490aa411739 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -273,6 +273,16 @@ static void virtscsi_req_done(struct virtqueue *vq)
 	virtscsi_vq_done(vscsi, req_vq, virtscsi_complete_cmd);
 };
 
+static void virtscsi_poll_requests(struct virtio_scsi *vscsi)
+{
+	int i, num_vqs;
+
+	num_vqs = vscsi->num_queues;
+	for (i = 0; i < num_vqs; i++)
+		virtscsi_vq_done(vscsi, &vscsi->req_vqs[i],
+				 virtscsi_complete_cmd);
+}
+
 static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_cmd *cmd = buf;
@@ -291,6 +301,8 @@ static void virtscsi_ctrl_done(struct virtqueue *vq)
 	virtscsi_vq_done(vscsi, &vscsi->ctrl_vq, virtscsi_complete_free);
 };
 
+static void virtscsi_handle_event(struct work_struct *work);
+
 static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 			       struct virtio_scsi_event_node *event_node)
 {
@@ -298,6 +310,7 @@ static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 	struct scatterlist sg;
 	unsigned long flags;
 
+	INIT_WORK(&event_node->work, virtscsi_handle_event);
 	sg_init_one(&sg, &event_node->event, sizeof(struct virtio_scsi_event));
 
 	spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);
@@ -415,7 +428,6 @@ static void virtscsi_complete_event(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_event_node *event_node = buf;
 
-	INIT_WORK(&event_node->work, virtscsi_handle_event);
 	schedule_work(&event_node->work);
 }
 
@@ -605,6 +617,18 @@ static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
 	    cmd->resp.tmf.response == VIRTIO_SCSI_S_FUNCTION_SUCCEEDED)
 		ret = SUCCESS;
 
+	/*
+	 * The spec guarantees that all requests related to the TMF have
+	 * been completed, but the callback might not have run yet if
+	 * we're using independent interrupts (e.g. MSI).  Poll the
+	 * virtqueues once.
+	 *
+	 * In the abort case, sc->scsi_done will do nothing, because
+	 * the block layer must have detected a timeout and as a result
+	 * REQ_ATOM_COMPLETE has been set.
+	 */
+	virtscsi_poll_requests(vscsi);
+
 out:
 	mempool_free(cmd, virtscsi_cmd_pool);
 	return ret;
@@ -750,8 +774,12 @@ static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
 
 		vscsi->affinity_hint_set = true;
 	} else {
-		for (i = 0; i < vscsi->num_queues; i++)
+		for (i = 0; i < vscsi->num_queues; i++) {
+			if (!vscsi->req_vqs[i].vq)
+				continue;
+
 			virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1);
+		}
 
 		vscsi->affinity_hint_set = false;
 	}
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 6d207afec8cb..a4c45ea8f688 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -89,7 +89,13 @@ err_exit:
 
 static void mid_spi_dma_exit(struct dw_spi *dws)
 {
+	if (!dws->dma_inited)
+		return;
+
+	dmaengine_terminate_all(dws->txchan);
 	dma_release_channel(dws->txchan);
+
+	dmaengine_terminate_all(dws->rxchan);
 	dma_release_channel(dws->rxchan);
 }
 
@@ -136,7 +142,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	txconf.dst_addr = dws->dma_addr;
 	txconf.dst_maxburst = LNW_DMA_MSIZE_16;
 	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	txconf.dst_addr_width = dws->dma_width;
 	txconf.device_fc = false;
 
 	txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
@@ -159,7 +165,7 @@ static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
 	rxconf.src_addr = dws->dma_addr;
 	rxconf.src_maxburst = LNW_DMA_MSIZE_16;
 	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+	rxconf.src_addr_width = dws->dma_width;
 	rxconf.device_fc = false;
 
 	rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
diff --git a/drivers/spi/spi-dw-pci.c b/drivers/spi/spi-dw-pci.c
index 3f3dc1226edf..e14960470d8d 100644
--- a/drivers/spi/spi-dw-pci.c
+++ b/drivers/spi/spi-dw-pci.c
@@ -62,6 +62,8 @@ static int spi_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
+	dws->regs = pcim_iomap_table(pdev)[pci_bar];
+
 	dws->bus_num = 0;
 	dws->num_cs = 4;
 	dws->irq = pdev->irq;
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index bf98d63d92b3..e543b80d610e 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -394,9 +394,6 @@ static void pump_transfers(unsigned long data)
 	chip = dws->cur_chip;
 	spi = message->spi;
 
-	if (unlikely(!chip->clk_div))
-		chip->clk_div = dws->max_freq / chip->speed_hz;
-
 	if (message->state == ERROR_STATE) {
 		message->status = -EIO;
 		goto early_exit;
@@ -437,7 +434,7 @@ static void pump_transfers(unsigned long data)
 	if (transfer->speed_hz) {
 		speed = chip->speed_hz;
 
-		if (transfer->speed_hz != speed) {
+		if ((transfer->speed_hz != speed) || (!chip->clk_div)) {
 			speed = transfer->speed_hz;
 			if (speed > dws->max_freq) {
 				printk(KERN_ERR "MRST SPI0: unsupported"
@@ -659,7 +656,6 @@ static int dw_spi_setup(struct spi_device *spi)
 		dev_err(&spi->dev, "No max speed HZ parameter\n");
 		return -EINVAL;
 	}
-	chip->speed_hz = spi->max_speed_hz;
 
 	chip->tmode = 0; /* Tx & Rx */
 	/* Default SPI mode is SCPOL = 0, SCPH = 0 */
@@ -671,12 +667,6 @@ static int dw_spi_setup(struct spi_device *spi)
 	return 0;
 }
 
-static void dw_spi_cleanup(struct spi_device *spi)
-{
-	struct chip_data *chip = spi_get_ctldata(spi);
-	kfree(chip);
-}
-
 static int init_queue(struct dw_spi *dws)
 {
 	INIT_LIST_HEAD(&dws->queue);
@@ -806,7 +796,6 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
 	master->bus_num = dws->bus_num;
 	master->num_chipselect = dws->num_cs;
-	master->cleanup = dw_spi_cleanup;
 	master->setup = dw_spi_setup;
 	master->transfer = dw_spi_transfer;
 
diff --git a/drivers/spi/spi-efm32.c b/drivers/spi/spi-efm32.c
index d4d3cc534792..8933eb7ab79b 100644
--- a/drivers/spi/spi-efm32.c
+++ b/drivers/spi/spi-efm32.c
@@ -487,6 +487,9 @@ static int efm32_spi_remove(struct platform_device *pdev)
 
 static const struct of_device_id efm32_spi_dt_ids[] = {
 	{
+		.compatible = "energymicro,efm32-spi",
+	}, {
+		/* doesn't follow the "vendor,device" scheme, don't use */
 		.compatible = "efm32,spi",
 	}, {
 		/* sentinel */
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index a25392065d9b..a5db6f930fa3 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -45,7 +45,7 @@
 
 #define SPI_TCR			0x08
 
-#define SPI_CTAR(x)		(0x0c + (x * 4))
+#define SPI_CTAR(x)		(0x0c + (((x) & 0x3) * 4))
 #define SPI_CTAR_FMSZ(x)	(((x) & 0x0000000f) << 27)
 #define SPI_CTAR_CPOL(x)	((x) << 26)
 #define SPI_CTAR_CPHA(x)	((x) << 25)
@@ -69,7 +69,7 @@
 
 #define SPI_PUSHR		0x34
 #define SPI_PUSHR_CONT		(1 << 31)
-#define SPI_PUSHR_CTAS(x)	(((x) & 0x00000007) << 28)
+#define SPI_PUSHR_CTAS(x)	(((x) & 0x00000003) << 28)
 #define SPI_PUSHR_EOQ		(1 << 27)
 #define SPI_PUSHR_CTCNT	(1 << 26)
 #define SPI_PUSHR_PCS(x)	(((1 << x) & 0x0000003f) << 16)
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 119f7af94537..4dcb2929c01f 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -362,18 +362,28 @@ static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
 static void fsl_spi_do_one_msg(struct spi_message *m)
 {
 	struct spi_device *spi = m->spi;
-	struct spi_transfer *t;
+	struct spi_transfer *t, *first;
 	unsigned int cs_change;
 	const int nsecs = 50;
 	int status;
 
-	cs_change = 1;
-	status = 0;
+	/* Don't allow changes if CS is active */
+	first = list_first_entry(&m->transfers, struct spi_transfer,
+			transfer_list);
 	list_for_each_entry(t, &m->transfers, transfer_list) {
-		if (t->bits_per_word || t->speed_hz) {
-			/* Don't allow changes if CS is active */
+		if ((first->bits_per_word != t->bits_per_word) ||
+			(first->speed_hz != t->speed_hz)) {
 			status = -EINVAL;
+			dev_err(&spi->dev,
+				"bits_per_word/speed_hz should be same for the same SPI transfer\n");
+			return;
+		}
+	}
 
+	cs_change = 1;
+	status = -EINVAL;
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		if (t->bits_per_word || t->speed_hz) {
 			if (cs_change)
 				status = fsl_spi_setup_transfer(spi, t);
 			if (status < 0)
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index a72127f08e39..b0059e7552b0 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -147,6 +147,7 @@ struct omap2_mcspi_cs {
 	void __iomem		*base;
 	unsigned long		phys;
 	int			word_len;
+	u16			mode;
 	struct list_head	node;
 	/* Context save and restore shadow register */
 	u32			chconf0;
@@ -320,7 +321,8 @@ static void omap2_mcspi_set_fifo(const struct spi_device *spi,
 disable_fifo:
 	if (t->rx_buf != NULL)
 		chconf &= ~OMAP2_MCSPI_CHCONF_FFER;
-	else
+
+	if (t->tx_buf != NULL)
 		chconf &= ~OMAP2_MCSPI_CHCONF_FFET;
 
 	mcspi_write_chconf0(spi, chconf);
@@ -899,6 +901,8 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 
 	mcspi_write_chconf0(spi, l);
 
+	cs->mode = spi->mode;
+
 	dev_dbg(&spi->dev, "setup: speed %d, sample %s edge, clk %s\n",
 			OMAP2_MCSPI_MAX_FREQ >> div,
 			(spi->mode & SPI_CPHA) ? "trailing" : "leading",
@@ -971,6 +975,7 @@ static int omap2_mcspi_setup(struct spi_device *spi)
 			return -ENOMEM;
 		cs->base = mcspi->base + spi->chip_select * 0x14;
 		cs->phys = mcspi->phys + spi->chip_select * 0x14;
+		cs->mode = 0;
 		cs->chconf0 = 0;
 		spi->controller_state = cs;
 		/* Link this to context save list */
@@ -1051,6 +1056,16 @@ static void omap2_mcspi_work(struct omap2_mcspi *mcspi, struct spi_message *m)
 	cs = spi->controller_state;
 	cd = spi->controller_data;
 
+	/*
+	 * The slave driver could have changed spi->mode in which case
+	 * it will be different from cs->mode (the current hardware setup).
+	 * If so, set par_override (even though its not a parity issue) so
+	 * omap2_mcspi_setup_transfer will be called to configure the hardware
+	 * with the correct mode on the first iteration of the loop below.
+	 */
+	if (spi->mode != cs->mode)
+		par_override = 1;
+
 	omap2_mcspi_set_enable(spi, 0);
 	list_for_each_entry(t, &m->transfers, transfer_list) {
 		if (t->tx_buf == NULL && t->rx_buf == NULL && t->len) {
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 7f2121fe2622..977b0619bb78 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -404,8 +404,6 @@ static int orion_spi_probe(struct platform_device *pdev)
 	struct resource *r;
 	unsigned long tclk_hz;
 	int status = 0;
-	const u32 *iprop;
-	int size;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(*spi));
 	if (master == NULL) {
@@ -416,10 +414,10 @@ static int orion_spi_probe(struct platform_device *pdev)
 	if (pdev->id != -1)
 		master->bus_num = pdev->id;
 	if (pdev->dev.of_node) {
-		iprop = of_get_property(pdev->dev.of_node, "cell-index",
-					&size);
-		if (iprop && size == sizeof(*iprop))
-			master->bus_num = *iprop;
+		u32 cell_index;
+		if (!of_property_read_u32(pdev->dev.of_node, "cell-index",
+					  &cell_index))
+			master->bus_num = cell_index;
 	}
 
 	/* we support only mode 0, and no options */
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 2789b452e711..971855e859c7 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -1075,7 +1075,7 @@ err_rxdesc:
 		     pl022->sgt_tx.nents, DMA_TO_DEVICE);
 err_tx_sgmap:
 	dma_unmap_sg(rxchan->device->dev, pl022->sgt_rx.sgl,
-		     pl022->sgt_tx.nents, DMA_FROM_DEVICE);
+		     pl022->sgt_rx.nents, DMA_FROM_DEVICE);
 err_rx_sgmap:
 	sg_free_table(&pl022->sgt_tx);
 err_alloc_tx_sg:
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index c702fc536a77..7ab3ccb592eb 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1078,6 +1078,7 @@ static struct acpi_device_id pxa2xx_spi_acpi_match[] = {
 	{ "INT3430", 0 },
 	{ "INT3431", 0 },
 	{ "80860F0E", 0 },
+	{ "8086228E", 0 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match);
@@ -1279,7 +1280,9 @@ static int pxa2xx_spi_suspend(struct device *dev)
 	if (status != 0)
 		return status;
 	write_SSCR0(0, drv_data->ioaddr);
-	clk_disable_unprepare(ssp->clk);
+
+	if (!pm_runtime_suspended(dev))
+		clk_disable_unprepare(ssp->clk);
 
 	return 0;
 }
@@ -1293,7 +1296,8 @@ static int pxa2xx_spi_resume(struct device *dev)
 	pxa2xx_spi_dma_resume(drv_data);
 
 	/* Enable the SSP clock */
-	clk_prepare_enable(ssp->clk);
+	if (!pm_runtime_suspended(dev))
+		clk_prepare_enable(ssp->clk);
 
 	/* Restore LPSS private register bits */
 	lpss_ssp_setup(drv_data);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index d0b28bba38be..fbf3b22efe5a 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1568,7 +1568,7 @@ EXPORT_SYMBOL_GPL(spi_busnum_to_master);
  */
 int spi_setup(struct spi_device *spi)
 {
-	unsigned	bad_bits;
+	unsigned	bad_bits, ugly_bits;
 	int		status = 0;
 
 	/* check mode to prevent that DUAL and QUAD set at the same time
@@ -1588,6 +1588,15 @@ int spi_setup(struct spi_device *spi)
 	 * that aren't supported with their current master
 	 */
 	bad_bits = spi->mode & ~spi->master->mode_bits;
+	ugly_bits = bad_bits &
+		    (SPI_TX_DUAL | SPI_TX_QUAD | SPI_RX_DUAL | SPI_RX_QUAD);
+	if (ugly_bits) {
+		dev_warn(&spi->dev,
+			 "setup: ignoring unsupported mode bits %x\n",
+			 ugly_bits);
+		spi->mode &= ~ugly_bits;
+		bad_bits &= ~ugly_bits;
+	}
 	if (bad_bits) {
 		dev_err(&spi->dev, "setup: unsupported mode bits %x\n",
 			bad_bits);
diff --git a/drivers/staging/comedi/comedi_buf.c b/drivers/staging/comedi/comedi_buf.c
index 924fce977985..257595016161 100644
--- a/drivers/staging/comedi/comedi_buf.c
+++ b/drivers/staging/comedi/comedi_buf.c
@@ -61,6 +61,8 @@ static void __comedi_buf_free(struct comedi_device *dev,
 			      struct comedi_subdevice *s)
 {
 	struct comedi_async *async = s->async;
+	struct comedi_buf_map *bm;
+	unsigned long flags;
 
 	if (async->prealloc_buf) {
 		vunmap(async->prealloc_buf);
@@ -68,8 +70,11 @@ static void __comedi_buf_free(struct comedi_device *dev,
 		async->prealloc_bufsz = 0;
 	}
 
-	comedi_buf_map_put(async->buf_map);
+	spin_lock_irqsave(&s->spin_lock, flags);
+	bm = async->buf_map;
 	async->buf_map = NULL;
+	spin_unlock_irqrestore(&s->spin_lock, flags);
+	comedi_buf_map_put(bm);
 }
 
 static void __comedi_buf_alloc(struct comedi_device *dev,
@@ -80,6 +85,7 @@ static void __comedi_buf_alloc(struct comedi_device *dev,
 	struct page **pages = NULL;
 	struct comedi_buf_map *bm;
 	struct comedi_buf_page *buf;
+	unsigned long flags;
 	unsigned i;
 
 	if (!IS_ENABLED(CONFIG_HAS_DMA) && s->async_dma_dir != DMA_NONE) {
@@ -92,8 +98,10 @@ static void __comedi_buf_alloc(struct comedi_device *dev,
 	if (!bm)
 		return;
 
-	async->buf_map = bm;
 	kref_init(&bm->refcount);
+	spin_lock_irqsave(&s->spin_lock, flags);
+	async->buf_map = bm;
+	spin_unlock_irqrestore(&s->spin_lock, flags);
 	bm->dma_dir = s->async_dma_dir;
 	if (bm->dma_dir != DMA_NONE)
 		/* Need ref to hardware device to free buffer later. */
@@ -127,7 +135,9 @@ static void __comedi_buf_alloc(struct comedi_device *dev,
 
 		pages[i] = virt_to_page(buf->virt_addr);
 	}
+	spin_lock_irqsave(&s->spin_lock, flags);
 	bm->n_pages = i;
+	spin_unlock_irqrestore(&s->spin_lock, flags);
 
 	/* vmap the prealloc_buf if all the pages were allocated */
 	if (i == n_pages)
@@ -150,6 +160,29 @@ int comedi_buf_map_put(struct comedi_buf_map *bm)
 	return 1;
 }
 
+/* returns s->async->buf_map and increments its kref refcount */
+struct comedi_buf_map *
+comedi_buf_map_from_subdev_get(struct comedi_subdevice *s)
+{
+	struct comedi_async *async = s->async;
+	struct comedi_buf_map *bm = NULL;
+	unsigned long flags;
+
+	if (!async)
+		return NULL;
+
+	spin_lock_irqsave(&s->spin_lock, flags);
+	bm = async->buf_map;
+	/* only want it if buffer pages allocated */
+	if (bm && bm->n_pages)
+		comedi_buf_map_get(bm);
+	else
+		bm = NULL;
+	spin_unlock_irqrestore(&s->spin_lock, flags);
+
+	return bm;
+}
+
 bool comedi_buf_is_mmapped(struct comedi_async *async)
 {
 	struct comedi_buf_map *bm = async->buf_map;
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index c22c617b0da1..eae3ee139330 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -1923,14 +1923,21 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 	struct comedi_device *dev = file->private_data;
 	struct comedi_subdevice *s;
 	struct comedi_async *async;
-	struct comedi_buf_map *bm;
+	struct comedi_buf_map *bm = NULL;
 	unsigned long start = vma->vm_start;
 	unsigned long size;
 	int n_pages;
 	int i;
 	int retval;
 
-	mutex_lock(&dev->mutex);
+	/*
+	 * 'trylock' avoids circular dependency with current->mm->mmap_sem
+	 * and down-reading &dev->attach_lock should normally succeed without
+	 * contention unless the device is in the process of being attached
+	 * or detached.
+	 */
+	if (!down_read_trylock(&dev->attach_lock))
+		return -EAGAIN;
 
 	if (!dev->attached) {
 		dev_dbg(dev->class_dev, "no driver attached\n");
@@ -1970,7 +1977,9 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 	}
 
 	n_pages = size >> PAGE_SHIFT;
-	bm = async->buf_map;
+
+	/* get reference to current buf map (if any) */
+	bm = comedi_buf_map_from_subdev_get(s);
 	if (!bm || n_pages > bm->n_pages) {
 		retval = -EINVAL;
 		goto done;
@@ -1994,7 +2003,8 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 
 	retval = 0;
 done:
-	mutex_unlock(&dev->mutex);
+	up_read(&dev->attach_lock);
+	comedi_buf_map_put(bm);	/* put reference to buf map - okay if NULL */
 	return retval;
 }
 
diff --git a/drivers/staging/comedi/comedi_internal.h b/drivers/staging/comedi/comedi_internal.h
index 9a746570f161..a492f2d2436e 100644
--- a/drivers/staging/comedi/comedi_internal.h
+++ b/drivers/staging/comedi/comedi_internal.h
@@ -19,6 +19,8 @@ void comedi_buf_reset(struct comedi_async *async);
 bool comedi_buf_is_mmapped(struct comedi_async *async);
 void comedi_buf_map_get(struct comedi_buf_map *bm);
 int comedi_buf_map_put(struct comedi_buf_map *bm);
+struct comedi_buf_map *comedi_buf_map_from_subdev_get(
+		struct comedi_subdevice *s);
 unsigned int comedi_buf_write_n_allocated(struct comedi_async *async);
 void comedi_device_cancel_all(struct comedi_device *dev);
 
diff --git a/drivers/staging/comedi/drivers/8255_pci.c b/drivers/staging/comedi/drivers/8255_pci.c
index 8a57c3c1ade0..1097dc6a3086 100644
--- a/drivers/staging/comedi/drivers/8255_pci.c
+++ b/drivers/staging/comedi/drivers/8255_pci.c
@@ -56,6 +56,7 @@ Configuration Options: not applicable, uses PCI auto config
 #include "../comedidev.h"
 
 #include "8255.h"
+#include "mite.h"
 
 enum pci_8255_boardid {
 	BOARD_ADLINK_PCI7224,
@@ -79,6 +80,7 @@ struct pci_8255_boardinfo {
 	const char *name;
 	int dio_badr;
 	int n_8255;
+	unsigned int has_mite:1;
 };
 
 static const struct pci_8255_boardinfo pci_8255_boards[] = {
@@ -126,36 +128,43 @@ static const struct pci_8255_boardinfo pci_8255_boards[] = {
 		.name		= "ni_pci-dio-96",
 		.dio_badr	= 1,
 		.n_8255		= 4,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCIDIO96B] = {
 		.name		= "ni_pci-dio-96b",
 		.dio_badr	= 1,
 		.n_8255		= 4,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PXI6508] = {
 		.name		= "ni_pxi-6508",
 		.dio_badr	= 1,
 		.n_8255		= 4,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCI6503] = {
 		.name		= "ni_pci-6503",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCI6503B] = {
 		.name		= "ni_pci-6503b",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PCI6503X] = {
 		.name		= "ni_pci-6503x",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 	[BOARD_NI_PXI_6503] = {
 		.name		= "ni_pxi-6503",
 		.dio_badr	= 1,
 		.n_8255		= 1,
+		.has_mite	= 1,
 	},
 };
 
@@ -163,6 +172,25 @@ struct pci_8255_private {
 	void __iomem *mmio_base;
 };
 
+static int pci_8255_mite_init(struct pci_dev *pcidev)
+{
+	void __iomem *mite_base;
+	u32 main_phys_addr;
+
+	/* ioremap the MITE registers (BAR 0) temporarily */
+	mite_base = pci_ioremap_bar(pcidev, 0);
+	if (!mite_base)
+		return -ENOMEM;
+
+	/* set data window to main registers (BAR 1) */
+	main_phys_addr = pci_resource_start(pcidev, 1);
+	writel(main_phys_addr | WENAB, mite_base + MITE_IODWBSR);
+
+	/* finished with MITE registers */
+	iounmap(mite_base);
+	return 0;
+}
+
 static int pci_8255_mmio(int dir, int port, int data, unsigned long iobase)
 {
 	void __iomem *mmio_base = (void __iomem *)iobase;
@@ -201,6 +229,12 @@ static int pci_8255_auto_attach(struct comedi_device *dev,
 	if (ret)
 		return ret;
 
+	if (board->has_mite) {
+		ret = pci_8255_mite_init(pcidev);
+		if (ret)
+			return ret;
+	}
+
 	is_mmio = (pci_resource_flags(pcidev, board->dio_badr) &
 		   IORESOURCE_MEM) != 0;
 	if (is_mmio) {
diff --git a/drivers/staging/comedi/drivers/ni_daq_700.c b/drivers/staging/comedi/drivers/ni_daq_700.c
index e4cdca349157..6417af0bdaab 100644
--- a/drivers/staging/comedi/drivers/ni_daq_700.c
+++ b/drivers/staging/comedi/drivers/ni_daq_700.c
@@ -122,6 +122,8 @@ static int daq700_ai_rinsn(struct comedi_device *dev,
 	/* write channel to multiplexer */
 	/* set mask scan bit high to disable scanning */
 	outb(chan | 0x80, dev->iobase + CMD_R1);
+	/* mux needs 2us to really settle [Fred Brooks]. */
+	udelay(2);
 
 	/* convert n samples */
 	for (n = 0; n < insn->n; n++) {
diff --git a/drivers/staging/comedi/drivers/usbdux.c b/drivers/staging/comedi/drivers/usbdux.c
index 71db683098d6..b59af0303581 100644
--- a/drivers/staging/comedi/drivers/usbdux.c
+++ b/drivers/staging/comedi/drivers/usbdux.c
@@ -493,7 +493,7 @@ static void usbduxsub_ao_isoc_irq(struct urb *urb)
 			/* pointer to the DA */
 			*datap++ = val & 0xff;
 			*datap++ = (val >> 8) & 0xff;
-			*datap++ = chan;
+			*datap++ = chan << 6;
 			devpriv->ao_readback[chan] = val;
 
 			s->async->events |= COMEDI_CB_BLOCK;
@@ -1040,11 +1040,8 @@ static int usbdux_ao_cmd(struct comedi_device *dev, struct comedi_subdevice *s)
 	/* set current channel of the running acquisition to zero */
 	s->async->cur_chan = 0;
 
-	for (i = 0; i < cmd->chanlist_len; ++i) {
-		unsigned int chan = CR_CHAN(cmd->chanlist[i]);
-
-		devpriv->ao_chanlist[i] = chan << 6;
-	}
+	for (i = 0; i < cmd->chanlist_len; ++i)
+		devpriv->ao_chanlist[i] = CR_CHAN(cmd->chanlist[i]);
 
 	/* we count in steps of 1ms (125us) */
 	/* 125us mode not used yet */
diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c
index e516bb69f3b4..907aa3078946 100644
--- a/drivers/staging/et131x/et131x.c
+++ b/drivers/staging/et131x/et131x.c
@@ -1422,22 +1422,16 @@ static int et131x_mii_read(struct et131x_adapter *adapter, u8 reg, u16 *value)
  * @reg: the register to read
  * @value: 16-bit value to write
  */
-static int et131x_mii_write(struct et131x_adapter *adapter, u8 reg, u16 value)
+static int et131x_mii_write(struct et131x_adapter *adapter, u8 addr, u8 reg,
+			    u16 value)
 {
 	struct mac_regs __iomem *mac = &adapter->regs->mac;
-	struct phy_device *phydev = adapter->phydev;
 	int status = 0;
-	u8 addr;
 	u32 delay = 0;
 	u32 mii_addr;
 	u32 mii_cmd;
 	u32 mii_indicator;
 
-	if (!phydev)
-		return -EIO;
-
-	addr = phydev->addr;
-
 	/* Save a local copy of the registers we are dealing with so we can
 	 * set them back
 	 */
@@ -1632,17 +1626,7 @@ static int et131x_mdio_write(struct mii_bus *bus, int phy_addr,
 	struct net_device *netdev = bus->priv;
 	struct et131x_adapter *adapter = netdev_priv(netdev);
 
-	return et131x_mii_write(adapter, reg, value);
-}
-
-static int et131x_mdio_reset(struct mii_bus *bus)
-{
-	struct net_device *netdev = bus->priv;
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	et131x_mii_write(adapter, MII_BMCR, BMCR_RESET);
-
-	return 0;
+	return et131x_mii_write(adapter, phy_addr, reg, value);
 }
 
 /*	et1310_phy_power_switch	-	PHY power control
@@ -1657,18 +1641,20 @@ static int et131x_mdio_reset(struct mii_bus *bus)
 static void et1310_phy_power_switch(struct et131x_adapter *adapter, bool down)
 {
 	u16 data;
+	struct  phy_device *phydev = adapter->phydev;
 
 	et131x_mii_read(adapter, MII_BMCR, &data);
 	data &= ~BMCR_PDOWN;
 	if (down)
 		data |= BMCR_PDOWN;
-	et131x_mii_write(adapter, MII_BMCR, data);
+	et131x_mii_write(adapter, phydev->addr, MII_BMCR, data);
 }
 
 /* et131x_xcvr_init - Init the phy if we are setting it into force mode */
 static void et131x_xcvr_init(struct et131x_adapter *adapter)
 {
 	u16 lcr2;
+	struct  phy_device *phydev = adapter->phydev;
 
 	/* Set the LED behavior such that LED 1 indicates speed (off =
 	 * 10Mbits, blink = 100Mbits, on = 1000Mbits) and LED 2 indicates
@@ -1689,7 +1675,7 @@ static void et131x_xcvr_init(struct et131x_adapter *adapter)
 		else
 			lcr2 |= (LED_VAL_LINKON << LED_TXRX_SHIFT);
 
-		et131x_mii_write(adapter, PHY_LED_2, lcr2);
+		et131x_mii_write(adapter, phydev->addr, PHY_LED_2, lcr2);
 	}
 }
 
@@ -3638,14 +3624,14 @@ static void et131x_adjust_link(struct net_device *netdev)
 
 			et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG,
 					 &register18);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18 | 0x4);
-			et131x_mii_write(adapter, PHY_INDEX_REG,
+			et131x_mii_write(adapter, phydev->addr,
+					 PHY_MPHY_CONTROL_REG, register18 | 0x4);
+			et131x_mii_write(adapter, phydev->addr, PHY_INDEX_REG,
 					 register18 | 0x8402);
-			et131x_mii_write(adapter, PHY_DATA_REG,
+			et131x_mii_write(adapter, phydev->addr, PHY_DATA_REG,
 					 register18 | 511);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18);
+			et131x_mii_write(adapter, phydev->addr,
+					 PHY_MPHY_CONTROL_REG, register18);
 		}
 
 		et1310_config_flow_control(adapter);
@@ -3657,7 +3643,8 @@ static void et131x_adjust_link(struct net_device *netdev)
 			et131x_mii_read(adapter, PHY_CONFIG, &reg);
 			reg &= ~ET_PHY_CONFIG_TX_FIFO_DEPTH;
 			reg |= ET_PHY_CONFIG_FIFO_DEPTH_32;
-			et131x_mii_write(adapter, PHY_CONFIG, reg);
+			et131x_mii_write(adapter, phydev->addr, PHY_CONFIG,
+					 reg);
 		}
 
 		et131x_set_rx_dma_timer(adapter);
@@ -3670,14 +3657,14 @@ static void et131x_adjust_link(struct net_device *netdev)
 
 			et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG,
 					 &register18);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18 | 0x4);
-			et131x_mii_write(adapter, PHY_INDEX_REG,
-					 register18 | 0x8402);
-			et131x_mii_write(adapter, PHY_DATA_REG,
-					 register18 | 511);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_MPHY_CONTROL_REG, register18 | 0x4);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_INDEX_REG, register18 | 0x8402);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_DATA_REG, register18 | 511);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_MPHY_CONTROL_REG, register18);
 		}
 
 		/* Free the packets being actively sent & stopped */
@@ -4646,10 +4633,6 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	/* Copy address into the net_device struct */
 	memcpy(netdev->dev_addr, adapter->addr, ETH_ALEN);
 
-	/* Init variable for counting how long we do not have link status */
-	adapter->boot_coma = 0;
-	et1310_disable_phy_coma(adapter);
-
 	rc = -ENOMEM;
 
 	/* Setup the mii_bus struct */
@@ -4665,7 +4648,6 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	adapter->mii_bus->priv = netdev;
 	adapter->mii_bus->read = et131x_mdio_read;
 	adapter->mii_bus->write = et131x_mdio_write;
-	adapter->mii_bus->reset = et131x_mdio_reset;
 	adapter->mii_bus->irq = kmalloc_array(PHY_MAX_ADDR, sizeof(int),
 					      GFP_KERNEL);
 	if (!adapter->mii_bus->irq)
@@ -4689,6 +4671,10 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	/* Setup et1310 as per the documentation */
 	et131x_adapter_setup(adapter);
 
+	/* Init variable for counting how long we do not have link status */
+	adapter->boot_coma = 0;
+	et1310_disable_phy_coma(adapter);
+
 	/* We can enable interrupts now
 	 *
 	 *  NOTE - Because registration of interrupt handler is done in the
diff --git a/drivers/staging/iio/adc/ad7291.c b/drivers/staging/iio/adc/ad7291.c
index 357cef2a6f4c..7194bd138762 100644
--- a/drivers/staging/iio/adc/ad7291.c
+++ b/drivers/staging/iio/adc/ad7291.c
@@ -465,7 +465,7 @@ static int ad7291_probe(struct i2c_client *client,
 	struct ad7291_platform_data *pdata = client->dev.platform_data;
 	struct ad7291_chip_info *chip;
 	struct iio_dev *indio_dev;
-	int ret = 0;
+	int ret;
 
 	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*chip));
 	if (!indio_dev)
@@ -475,7 +475,7 @@ static int ad7291_probe(struct i2c_client *client,
 	if (pdata && pdata->use_external_ref) {
 		chip->reg = devm_regulator_get(&client->dev, "vref");
 		if (IS_ERR(chip->reg))
-			return ret;
+			return PTR_ERR(chip->reg);
 
 		ret = regulator_enable(chip->reg);
 		if (ret)
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index 514844efac75..9ec1df9cff95 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -846,6 +846,14 @@ static int mxs_lradc_read_single(struct iio_dev *iio_dev, int chan, int *val)
 			LRADC_CTRL1);
 	mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0);
 
+	/* Enable / disable the divider per requirement */
+	if (test_bit(chan, &lradc->is_divided))
+		mxs_lradc_reg_set(lradc, 1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
+			LRADC_CTRL2);
+	else
+		mxs_lradc_reg_clear(lradc,
+			1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET, LRADC_CTRL2);
+
 	/* Clean the slot's previous content, then set new one. */
 	mxs_lradc_reg_clear(lradc, LRADC_CTRL4_LRADCSELECT_MASK(0), LRADC_CTRL4);
 	mxs_lradc_reg_set(lradc, chan, LRADC_CTRL4);
@@ -964,15 +972,11 @@ static int mxs_lradc_write_raw(struct iio_dev *iio_dev,
 		if (val == scale_avail[MXS_LRADC_DIV_DISABLED].integer &&
 		    val2 == scale_avail[MXS_LRADC_DIV_DISABLED].nano) {
 			/* divider by two disabled */
-			writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
-			       lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_CLR);
 			clear_bit(chan->channel, &lradc->is_divided);
 			ret = 0;
 		} else if (val == scale_avail[MXS_LRADC_DIV_ENABLED].integer &&
 			   val2 == scale_avail[MXS_LRADC_DIV_ENABLED].nano) {
 			/* divider by two enabled */
-			writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
-			       lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_SET);
 			set_bit(chan->channel, &lradc->is_divided);
 			ret = 0;
 		}
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 2b96665da8a2..97d4b3fb7e95 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -115,6 +115,7 @@ static const struct iio_chan_spec ad5933_channels[] = {
 		.channel = 0,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
 		.address = AD5933_REG_TEMP_DATA,
+		.scan_index = -1,
 		.scan_type = {
 			.sign = 's',
 			.realbits = 14,
@@ -124,9 +125,7 @@ static const struct iio_chan_spec ad5933_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "real_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
-		BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "real",
 		.address = AD5933_REG_REAL_DATA,
 		.scan_index = 0,
 		.scan_type = {
@@ -138,9 +137,7 @@ static const struct iio_chan_spec ad5933_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "imag_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
-		BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "imag",
 		.address = AD5933_REG_IMAG_DATA,
 		.scan_index = 1,
 		.scan_type = {
@@ -748,14 +745,14 @@ static int ad5933_probe(struct i2c_client *client,
 	indio_dev->name = id->name;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->channels = ad5933_channels;
-	indio_dev->num_channels = 1; /* only register temp0_input */
+	indio_dev->num_channels = ARRAY_SIZE(ad5933_channels);
 
 	ret = ad5933_register_ring_funcs_and_init(indio_dev);
 	if (ret)
 		goto error_disable_reg;
 
-	/* skip temp0_input, register in0_(real|imag)_raw */
-	ret = iio_buffer_register(indio_dev, &ad5933_channels[1], 2);
+	ret = iio_buffer_register(indio_dev, ad5933_channels,
+		ARRAY_SIZE(ad5933_channels));
 	if (ret)
 		goto error_unreg_ring;
 
diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c
index 1e538086d48b..ce1e74e000bb 100644
--- a/drivers/staging/iio/light/tsl2x7x_core.c
+++ b/drivers/staging/iio/light/tsl2x7x_core.c
@@ -667,9 +667,13 @@ static int tsl2x7x_chip_on(struct iio_dev *indio_dev)
 	chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] =
 			chip->tsl2x7x_settings.prox_pulse_count;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] =
-	chip->tsl2x7x_settings.prox_thres_low;
+			(chip->tsl2x7x_settings.prox_thres_low) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] =
-			chip->tsl2x7x_settings.prox_thres_high;
+			(chip->tsl2x7x_settings.prox_thres_high) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF;
 
 	/* and make sure we're not already on */
 	if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) {
diff --git a/drivers/staging/iio/meter/ade7758.h b/drivers/staging/iio/meter/ade7758.h
index 07318203a836..e8c98cf57070 100644
--- a/drivers/staging/iio/meter/ade7758.h
+++ b/drivers/staging/iio/meter/ade7758.h
@@ -119,7 +119,6 @@ struct ade7758_state {
 	u8			*tx;
 	u8			*rx;
 	struct mutex		buf_lock;
-	const struct iio_chan_spec *ade7758_ring_channels;
 	struct spi_transfer	ring_xfer[4];
 	struct spi_message	ring_msg;
 	/*
diff --git a/drivers/staging/iio/meter/ade7758_core.c b/drivers/staging/iio/meter/ade7758_core.c
index cba183e24838..94d9914a602c 100644
--- a/drivers/staging/iio/meter/ade7758_core.c
+++ b/drivers/staging/iio/meter/ade7758_core.c
@@ -630,9 +630,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_VOLTAGE),
 		.scan_index = 0,
 		.scan_type = {
@@ -644,9 +641,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_CURRENT,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_CURRENT),
 		.scan_index = 1,
 		.scan_type = {
@@ -658,9 +652,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "apparent_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "apparent",
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_APP_PWR),
 		.scan_index = 2,
 		.scan_type = {
@@ -672,9 +664,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "active_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "active",
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_ACT_PWR),
 		.scan_index = 3,
 		.scan_type = {
@@ -686,9 +676,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 0,
-		.extend_name = "reactive_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "reactive",
 		.address = AD7758_WT(AD7758_PHASE_A, AD7758_REACT_PWR),
 		.scan_index = 4,
 		.scan_type = {
@@ -700,9 +688,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_VOLTAGE),
 		.scan_index = 5,
 		.scan_type = {
@@ -714,9 +699,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_CURRENT,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_CURRENT),
 		.scan_index = 6,
 		.scan_type = {
@@ -728,9 +710,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "apparent_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "apparent",
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_APP_PWR),
 		.scan_index = 7,
 		.scan_type = {
@@ -742,9 +722,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "active_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "active",
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_ACT_PWR),
 		.scan_index = 8,
 		.scan_type = {
@@ -756,9 +734,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 1,
-		.extend_name = "reactive_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "reactive",
 		.address = AD7758_WT(AD7758_PHASE_B, AD7758_REACT_PWR),
 		.scan_index = 9,
 		.scan_type = {
@@ -770,9 +746,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_VOLTAGE,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_VOLTAGE),
 		.scan_index = 10,
 		.scan_type = {
@@ -784,9 +757,6 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_CURRENT,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_CURRENT),
 		.scan_index = 11,
 		.scan_type = {
@@ -798,9 +768,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "apparent_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "apparent",
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_APP_PWR),
 		.scan_index = 12,
 		.scan_type = {
@@ -812,9 +780,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "active_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "active",
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_ACT_PWR),
 		.scan_index = 13,
 		.scan_type = {
@@ -826,9 +792,7 @@ static const struct iio_chan_spec ade7758_channels[] = {
 		.type = IIO_POWER,
 		.indexed = 1,
 		.channel = 2,
-		.extend_name = "reactive_raw",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+		.extend_name = "reactive",
 		.address = AD7758_WT(AD7758_PHASE_C, AD7758_REACT_PWR),
 		.scan_index = 14,
 		.scan_type = {
@@ -869,13 +833,14 @@ static int ade7758_probe(struct spi_device *spi)
 		goto error_free_rx;
 	}
 	st->us = spi;
-	st->ade7758_ring_channels = &ade7758_channels[0];
 	mutex_init(&st->buf_lock);
 
 	indio_dev->name = spi->dev.driver->name;
 	indio_dev->dev.parent = &spi->dev;
 	indio_dev->info = &ade7758_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->channels = ade7758_channels;
+	indio_dev->num_channels = ARRAY_SIZE(ade7758_channels);
 
 	ret = ade7758_configure_ring(indio_dev);
 	if (ret)
diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c
index c0accf8cce93..6e9006490742 100644
--- a/drivers/staging/iio/meter/ade7758_ring.c
+++ b/drivers/staging/iio/meter/ade7758_ring.c
@@ -85,17 +85,16 @@ static irqreturn_t ade7758_trigger_handler(int irq, void *p)
  **/
 static int ade7758_ring_preenable(struct iio_dev *indio_dev)
 {
-	struct ade7758_state *st = iio_priv(indio_dev);
 	unsigned channel;
 
-	if (!bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength))
+	if (bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength))
 		return -EINVAL;
 
 	channel = find_first_bit(indio_dev->active_scan_mask,
 				 indio_dev->masklength);
 
 	ade7758_write_waveform_type(&indio_dev->dev,
-		st->ade7758_ring_channels[channel].address);
+		indio_dev->channels[channel].address);
 
 	return 0;
 }
diff --git a/drivers/staging/iio/meter/ade7758_trigger.c b/drivers/staging/iio/meter/ade7758_trigger.c
index 7a94ddd42f59..8c4f2896cd0d 100644
--- a/drivers/staging/iio/meter/ade7758_trigger.c
+++ b/drivers/staging/iio/meter/ade7758_trigger.c
@@ -85,7 +85,7 @@ int ade7758_probe_trigger(struct iio_dev *indio_dev)
 	ret = iio_trigger_register(st->trig);
 
 	/* select default trigger */
-	indio_dev->trig = st->trig;
+	indio_dev->trig = iio_trigger_get(st->trig);
 	if (ret)
 		goto error_free_irq;
 
diff --git a/drivers/staging/imx-drm/ipuv3-plane.c b/drivers/staging/imx-drm/ipuv3-plane.c
index 34b642a12f8b..c70f1734b274 100644
--- a/drivers/staging/imx-drm/ipuv3-plane.c
+++ b/drivers/staging/imx-drm/ipuv3-plane.c
@@ -277,7 +277,8 @@ static void ipu_plane_dpms(struct ipu_plane *ipu_plane, int mode)
 
 		ipu_idmac_put(ipu_plane->ipu_ch);
 		ipu_dmfc_put(ipu_plane->dmfc);
-		ipu_dp_put(ipu_plane->dp);
+		if (ipu_plane->dp)
+			ipu_dp_put(ipu_plane->dp);
 	}
 }
 
diff --git a/drivers/staging/lustre/lustre/Kconfig b/drivers/staging/lustre/lustre/Kconfig
index 209e4c7e6f8a..4f65ba1158bf 100644
--- a/drivers/staging/lustre/lustre/Kconfig
+++ b/drivers/staging/lustre/lustre/Kconfig
@@ -57,4 +57,5 @@ config LUSTRE_TRANSLATE_ERRNOS
 config LUSTRE_LLITE_LLOOP
 	tristate "Lustre virtual block device"
 	depends on LUSTRE_FS && BLOCK
+	depends on !PPC_64K_PAGES && !ARM64_64K_PAGES
 	default m
diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c
index b2cd3a85166d..bbf236e842a9 100644
--- a/drivers/staging/media/bcm2048/radio-bcm2048.c
+++ b/drivers/staging/media/bcm2048/radio-bcm2048.c
@@ -737,7 +737,7 @@ static int bcm2048_set_region(struct bcm2048_device *bdev, u8 region)
 	int err;
 	u32 new_frequency = 0;
 
-	if (region > ARRAY_SIZE(region_configs))
+	if (region >= ARRAY_SIZE(region_configs))
 		return -EINVAL;
 
 	mutex_lock(&bdev->mutex);
diff --git a/drivers/staging/media/omap4iss/Kconfig b/drivers/staging/media/omap4iss/Kconfig
index b9fe753969bd..15940f8fdd24 100644
--- a/drivers/staging/media/omap4iss/Kconfig
+++ b/drivers/staging/media/omap4iss/Kconfig
@@ -1,6 +1,6 @@
 config VIDEO_OMAP4
 	bool "OMAP 4 Camera support"
-	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && I2C && ARCH_OMAP4
+	depends on VIDEO_V4L2=y && VIDEO_V4L2_SUBDEV_API && I2C=y && ARCH_OMAP4
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  Driver for an OMAP 4 ISS controller.
diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c
index 51dbc13e757f..5a40925680ac 100644
--- a/drivers/staging/mt29f_spinand/mt29f_spinand.c
+++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c
@@ -924,6 +924,7 @@ static int spinand_remove(struct spi_device *spi)
 
 static const struct of_device_id spinand_dt[] = {
 	{ .compatible = "spinand,mt29f", },
+	{}
 };
 
 /*
diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c
index c9c180649c12..cec3f1628cd8 100644
--- a/drivers/staging/rtl8188eu/core/rtw_recv.c
+++ b/drivers/staging/rtl8188eu/core/rtw_recv.c
@@ -542,7 +542,7 @@ _func_exit_;
 /* set the security information in the recv_frame */
 static union recv_frame *portctrl(struct adapter *adapter, union recv_frame *precv_frame)
 {
-	u8   *psta_addr = NULL, *ptr;
+	u8   *psta_addr, *ptr;
 	uint  auth_alg;
 	struct recv_frame_hdr *pfhdr;
 	struct sta_info *psta;
@@ -556,7 +556,6 @@ static union recv_frame *portctrl(struct adapter *adapter, union recv_frame *pre
 _func_enter_;
 
 	pstapriv = &adapter->stapriv;
-	psta = rtw_get_stainfo(pstapriv, psta_addr);
 
 	auth_alg = adapter->securitypriv.dot11AuthAlgrthm;
 
@@ -564,6 +563,7 @@ _func_enter_;
 	pfhdr = &precv_frame->u.hdr;
 	pattrib = &pfhdr->attrib;
 	psta_addr = pattrib->ta;
+	psta = rtw_get_stainfo(pstapriv, psta_addr);
 
 	prtnframe = NULL;
 
diff --git a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
index 96df62f95b6b..9b4678c73c0d 100644
--- a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
+++ b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c
@@ -1601,13 +1601,18 @@ int update_sta_support_rate(struct adapter *padapter, u8 *pvar_ie, uint var_ie_l
 	pIE = (struct ndis_802_11_var_ie *)rtw_get_ie(pvar_ie, _SUPPORTEDRATES_IE_, &ie_len, var_ie_len);
 	if (pIE == NULL)
 		return _FAIL;
+	if (ie_len > NDIS_802_11_LENGTH_RATES_EX)
+		return _FAIL;
 
 	memcpy(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates, pIE->data, ie_len);
 	supportRateNum = ie_len;
 
 	pIE = (struct ndis_802_11_var_ie *)rtw_get_ie(pvar_ie, _EXT_SUPPORTEDRATES_IE_, &ie_len, var_ie_len);
-	if (pIE)
+	if (pIE) {
+		if (supportRateNum + ie_len > NDIS_802_11_LENGTH_RATES_EX)
+			return _FAIL;
 		memcpy((pmlmeinfo->FW_sta_info[cam_idx].SupportedRates + supportRateNum), pIE->data, ie_len);
+	}
 
 	return _SUCCESS;
 }
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index 2f40ff5901d6..2185a71055f2 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -53,9 +53,12 @@ static struct usb_device_id rtw_usb_id_tbl[] = {
 	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */
 	/*=== Customer ID ===*/
 	/****** 8188EUS ********/
+	{USB_DEVICE(0x056e, 0x4008)}, /* Elecom WDC-150SU2M */
 	{USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */
 	{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
 	{USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */
+	{USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */
+	{USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */
 	{}	/* Terminating entry */
 };
 
diff --git a/drivers/staging/rtl8192e/rtllib_tx.c b/drivers/staging/rtl8192e/rtllib_tx.c
index 77964885b3f2..334d949afd63 100644
--- a/drivers/staging/rtl8192e/rtllib_tx.c
+++ b/drivers/staging/rtl8192e/rtllib_tx.c
@@ -171,7 +171,7 @@ inline int rtllib_put_snap(u8 *data, u16 h_proto)
 	snap->oui[1] = oui[1];
 	snap->oui[2] = oui[2];
 
-	*(u16 *)(data + SNAP_SIZE) = h_proto;
+	*(__be16 *)(data + SNAP_SIZE) = htons(h_proto);
 
 	return SNAP_SIZE + sizeof(u16);
 }
diff --git a/drivers/staging/rtl8712/rtl871x_recv.c b/drivers/staging/rtl8712/rtl871x_recv.c
index 23ec684b60e1..274c359279ef 100644
--- a/drivers/staging/rtl8712/rtl871x_recv.c
+++ b/drivers/staging/rtl8712/rtl871x_recv.c
@@ -254,7 +254,7 @@ union recv_frame *r8712_portctrl(struct _adapter *adapter,
 	struct sta_info *psta;
 	struct	sta_priv *pstapriv;
 	union recv_frame *prtnframe;
-	u16 ether_type = 0;
+	u16 ether_type;
 
 	pstapriv = &adapter->stapriv;
 	ptr = get_recvframe_data(precv_frame);
@@ -263,15 +263,14 @@ union recv_frame *r8712_portctrl(struct _adapter *adapter,
 	psta = r8712_get_stainfo(pstapriv, psta_addr);
 	auth_alg = adapter->securitypriv.AuthAlgrthm;
 	if (auth_alg == 2) {
+		/* get ether_type */
+		ptr = ptr + pfhdr->attrib.hdrlen + LLC_HEADER_SIZE;
+		memcpy(&ether_type, ptr, 2);
+		ether_type = ntohs((unsigned short)ether_type);
+
 		if ((psta != NULL) && (psta->ieee8021x_blocked)) {
 			/* blocked
 			 * only accept EAPOL frame */
-			prtnframe = precv_frame;
-			/*get ether_type */
-			ptr = ptr + pfhdr->attrib.hdrlen +
-			      pfhdr->attrib.iv_len + LLC_HEADER_SIZE;
-			memcpy(&ether_type, ptr, 2);
-			ether_type = ntohs((unsigned short)ether_type);
 			if (ether_type == 0x888e)
 				prtnframe = precv_frame;
 			else {
diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c
index f0fcbf7c7d7f..868226953d5c 100644
--- a/drivers/staging/serqt_usb2/serqt_usb2.c
+++ b/drivers/staging/serqt_usb2/serqt_usb2.c
@@ -724,7 +724,7 @@ static int qt_startup(struct usb_serial *serial)
 		goto startup_error;
 	}
 
-	switch (serial->dev->descriptor.idProduct) {
+	switch (le16_to_cpu(serial->dev->descriptor.idProduct)) {
 	case QUATECH_DSU100:
 	case QUATECH_QSU100:
 	case QUATECH_ESU100A:
diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c
index ef5933b93590..f61f9cf95ed7 100644
--- a/drivers/staging/speakup/main.c
+++ b/drivers/staging/speakup/main.c
@@ -2218,6 +2218,7 @@ static void __exit speakup_exit(void)
 	unregister_keyboard_notifier(&keyboard_notifier_block);
 	unregister_vt_notifier(&vt_notifier_block);
 	speakup_unregister_devsynth();
+	speakup_cancel_paste();
 	del_timer(&cursor_timer);
 	kthread_stop(speakup_task);
 	speakup_task = NULL;
diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c
index f0fb00392d6b..ca04d3669acc 100644
--- a/drivers/staging/speakup/selection.c
+++ b/drivers/staging/speakup/selection.c
@@ -4,6 +4,10 @@
 #include <linux/sched.h>
 #include <linux/device.h> /* for dev_warn */
 #include <linux/selection.h>
+#include <linux/workqueue.h>
+#include <linux/tty.h>
+#include <linux/tty_flip.h>
+#include <asm/cmpxchg.h>
 
 #include "speakup.h"
 
@@ -121,31 +125,61 @@ int speakup_set_selection(struct tty_struct *tty)
 	return 0;
 }
 
-/* TODO: move to some helper thread, probably.  That'd fix having to check for
- * in_atomic().  */
-int speakup_paste_selection(struct tty_struct *tty)
+struct speakup_paste_work {
+	struct work_struct work;
+	struct tty_struct *tty;
+};
+
+static void __speakup_paste_selection(struct work_struct *work)
 {
+	struct speakup_paste_work *spw =
+		container_of(work, struct speakup_paste_work, work);
+	struct tty_struct *tty = xchg(&spw->tty, NULL);
 	struct vc_data *vc = (struct vc_data *) tty->driver_data;
 	int pasted = 0, count;
+	struct tty_ldisc *ld;
 	DECLARE_WAITQUEUE(wait, current);
+
+	ld = tty_ldisc_ref_wait(tty);
+	tty_buffer_lock_exclusive(&vc->port);
+
 	add_wait_queue(&vc->paste_wait, &wait);
 	while (sel_buffer && sel_buffer_lth > pasted) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (test_bit(TTY_THROTTLED, &tty->flags)) {
-			if (in_atomic())
-				/* if we are in an interrupt handler, abort */
-				break;
 			schedule();
 			continue;
 		}
 		count = sel_buffer_lth - pasted;
-		count = min_t(int, count, tty->receive_room);
-		tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
-			NULL, count);
+		count = tty_ldisc_receive_buf(ld, sel_buffer + pasted, NULL,
+					      count);
 		pasted += count;
 	}
 	remove_wait_queue(&vc->paste_wait, &wait);
 	current->state = TASK_RUNNING;
+
+	tty_buffer_unlock_exclusive(&vc->port);
+	tty_ldisc_deref(ld);
+	tty_kref_put(tty);
+}
+
+static struct speakup_paste_work speakup_paste_work = {
+	.work = __WORK_INITIALIZER(speakup_paste_work.work,
+				   __speakup_paste_selection)
+};
+
+int speakup_paste_selection(struct tty_struct *tty)
+{
+	if (cmpxchg(&speakup_paste_work.tty, NULL, tty) != NULL)
+		return -EBUSY;
+
+	tty_kref_get(tty);
+	schedule_work_on(WORK_CPU_UNBOUND, &speakup_paste_work.work);
 	return 0;
 }
 
+void speakup_cancel_paste(void)
+{
+	cancel_work_sync(&speakup_paste_work.work);
+	tty_kref_put(speakup_paste_work.tty);
+}
diff --git a/drivers/staging/speakup/speakup.h b/drivers/staging/speakup/speakup.h
index 0126f714821a..74fe72429b2d 100644
--- a/drivers/staging/speakup/speakup.h
+++ b/drivers/staging/speakup/speakup.h
@@ -77,6 +77,7 @@ extern void synth_buffer_clear(void);
 extern void speakup_clear_selection(void);
 extern int speakup_set_selection(struct tty_struct *tty);
 extern int speakup_paste_selection(struct tty_struct *tty);
+extern void speakup_cancel_paste(void);
 extern void speakup_register_devsynth(void);
 extern void speakup_unregister_devsynth(void);
 extern void synth_write(const char *buf, size_t count);
diff --git a/drivers/staging/tidspbridge/core/dsp-clock.c b/drivers/staging/tidspbridge/core/dsp-clock.c
index 2f084e181d39..a1aca4416ca7 100644
--- a/drivers/staging/tidspbridge/core/dsp-clock.c
+++ b/drivers/staging/tidspbridge/core/dsp-clock.c
@@ -226,7 +226,7 @@ int dsp_clk_enable(enum dsp_clk_id clk_id)
 	case GPT_CLK:
 		status = omap_dm_timer_start(timer[clk_id - 1]);
 		break;
-#ifdef CONFIG_OMAP_MCBSP
+#ifdef CONFIG_SND_OMAP_SOC_MCBSP
 	case MCBSP_CLK:
 		omap_mcbsp_request(MCBSP_ID(clk_id));
 		omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PAD_SRC);
@@ -302,7 +302,7 @@ int dsp_clk_disable(enum dsp_clk_id clk_id)
 	case GPT_CLK:
 		status = omap_dm_timer_stop(timer[clk_id - 1]);
 		break;
-#ifdef CONFIG_OMAP_MCBSP
+#ifdef CONFIG_SND_OMAP_SOC_MCBSP
 	case MCBSP_CLK:
 		omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PRCM_SRC);
 		omap_mcbsp_free(MCBSP_ID(clk_id));
diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c
index d7efd0173a9a..7d7578872a84 100644
--- a/drivers/staging/vt6655/bssdb.c
+++ b/drivers/staging/vt6655/bssdb.c
@@ -983,7 +983,7 @@ start:
 		pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1));
 	}
 
-	{
+	if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) {
 		pDevice->byReAssocCount++;
 		/* 10 sec timeout */
 		if ((pDevice->byReAssocCount > 10) && (!pDevice->bLinkPass)) {
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index a952df1bf9d6..6f13f0e597f8 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -2430,6 +2430,7 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 	int             handled = 0;
 	unsigned char byData = 0;
 	int             ii = 0;
+	unsigned long flags;
 //    unsigned char byRSSI;
 
 	MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr);
@@ -2455,7 +2456,8 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 
 	handled = 1;
 	MACvIntDisable(pDevice->PortOffset);
-	spin_lock_irq(&pDevice->lock);
+
+	spin_lock_irqsave(&pDevice->lock, flags);
 
 	//Make sure current page is 0
 	VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel);
@@ -2696,7 +2698,8 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 		MACvSelectPage1(pDevice->PortOffset);
 	}
 
-	spin_unlock_irq(&pDevice->lock);
+	spin_unlock_irqrestore(&pDevice->lock, flags);
+
 	MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE);
 
 	return IRQ_RETVAL(handled);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index b83ec378d04f..104f29e6b290 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -460,6 +460,7 @@ int iscsit_del_np(struct iscsi_np *np)
 	spin_lock_bh(&np->np_thread_lock);
 	np->np_exports--;
 	if (np->np_exports) {
+		np->enabled = true;
 		spin_unlock_bh(&np->np_thread_lock);
 		return 0;
 	}
@@ -1289,7 +1290,7 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf,
 	if (cmd->data_direction != DMA_TO_DEVICE) {
 		pr_err("Command ITT: 0x%08x received DataOUT for a"
 			" NON-WRITE command.\n", cmd->init_task_tag);
-		return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, buf);
+		return iscsit_dump_data_payload(conn, payload_length, 1);
 	}
 	se_cmd = &cmd->se_cmd;
 	iscsit_mod_dataout_timer(cmd);
@@ -1564,7 +1565,9 @@ int iscsit_process_nop_out(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	 * Initiator is expecting a NopIN ping reply..
 	 */
 	if (hdr->itt != RESERVED_ITT) {
-		BUG_ON(!cmd);
+		if (!cmd)
+			return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+						(unsigned char *)hdr);
 
 		spin_lock_bh(&conn->cmd_lock);
 		list_add_tail(&cmd->i_conn_node, &conn->conn_cmd_list);
@@ -2468,6 +2471,7 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn)
 {
 	struct iscsi_cmd *cmd;
 	struct iscsi_conn *conn_p;
+	bool found = false;
 
 	/*
 	 * Only send a Asynchronous Message on connections whos network
@@ -2476,11 +2480,12 @@ static void iscsit_build_conn_drop_async_message(struct iscsi_conn *conn)
 	list_for_each_entry(conn_p, &conn->sess->sess_conn_list, conn_list) {
 		if (conn_p->conn_state == TARG_CONN_STATE_LOGGED_IN) {
 			iscsit_inc_conn_usage_count(conn_p);
+			found = true;
 			break;
 		}
 	}
 
-	if (!conn_p)
+	if (!found)
 		return;
 
 	cmd = iscsit_allocate_cmd(conn_p, TASK_RUNNING);
@@ -3356,7 +3361,9 @@ static bool iscsit_check_inaddr_any(struct iscsi_np *np)
 
 #define SENDTARGETS_BUF_LIMIT 32768U
 
-static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd)
+static int
+iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
+				  enum iscsit_transport_type network_transport)
 {
 	char *payload = NULL;
 	struct iscsi_conn *conn = cmd->conn;
@@ -3433,6 +3440,9 @@ static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd)
 				struct iscsi_np *np = tpg_np->tpg_np;
 				bool inaddr_any = iscsit_check_inaddr_any(np);
 
+				if (np->np_network_transport != network_transport)
+					continue;
+
 				if (!target_name_printed) {
 					len = sprintf(buf, "TargetName=%s",
 						      tiqn->tiqn);
@@ -3486,11 +3496,12 @@ eob:
 
 int
 iscsit_build_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
-		      struct iscsi_text_rsp *hdr)
+		      struct iscsi_text_rsp *hdr,
+		      enum iscsit_transport_type network_transport)
 {
 	int text_length, padding;
 
-	text_length = iscsit_build_sendtargets_response(cmd);
+	text_length = iscsit_build_sendtargets_response(cmd, network_transport);
 	if (text_length < 0)
 		return text_length;
 
@@ -3528,7 +3539,7 @@ static int iscsit_send_text_rsp(
 	u32 tx_size = 0;
 	int text_length, iov_count = 0, rc;
 
-	rc = iscsit_build_text_rsp(cmd, conn, hdr);
+	rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_TCP);
 	if (rc < 0)
 		return rc;
 
@@ -4200,8 +4211,6 @@ int iscsit_close_connection(
 	if (conn->conn_transport->iscsit_wait_conn)
 		conn->conn_transport->iscsit_wait_conn(conn);
 
-	iscsit_free_queue_reqs_for_conn(conn);
-
 	/*
 	 * During Connection recovery drop unacknowledged out of order
 	 * commands for this connection, and prepare the other commands
@@ -4218,6 +4227,7 @@ int iscsit_close_connection(
 		iscsit_clear_ooo_cmdsns_for_conn(conn);
 		iscsit_release_commands_from_conn(conn);
 	}
+	iscsit_free_queue_reqs_for_conn(conn);
 
 	/*
 	 * Handle decrementing session or connection usage count if
@@ -4503,6 +4513,7 @@ static void iscsit_logout_post_handler_diffcid(
 {
 	struct iscsi_conn *l_conn;
 	struct iscsi_session *sess = conn->sess;
+	bool conn_found = false;
 
 	if (!sess)
 		return;
@@ -4511,12 +4522,13 @@ static void iscsit_logout_post_handler_diffcid(
 	list_for_each_entry(l_conn, &sess->sess_conn_list, conn_list) {
 		if (l_conn->cid == cid) {
 			iscsit_inc_conn_usage_count(l_conn);
+			conn_found = true;
 			break;
 		}
 	}
 	spin_unlock_bh(&sess->conn_lock);
 
-	if (!l_conn)
+	if (!conn_found)
 		return;
 
 	if (l_conn->sock)
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index de77d9aa22c6..6689de6c5591 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -314,6 +314,16 @@ static int chap_server_compute_md5(
 		goto out;
 	}
 	/*
+	 * During mutual authentication, the CHAP_C generated by the
+	 * initiator must not match the original CHAP_C generated by
+	 * the target.
+	 */
+	if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) {
+		pr_err("initiator CHAP_C matches target CHAP_C, failing"
+		       " login attempt\n");
+		goto out;
+	}
+	/*
 	 * Generate CHAP_N and CHAP_R for mutual authentication.
 	 */
 	tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 48f7b3bf4e8c..1d4a8c86551f 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -773,6 +773,7 @@ struct iscsi_np {
 	int			np_ip_proto;
 	int			np_sock_type;
 	enum np_thread_state_table np_thread_state;
+	bool                    enabled;
 	enum iscsi_timer_flags_table np_login_timer_flags;
 	u32			np_exports;
 	enum np_flags_table	np_flags;
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index e29279e6b577..d509aa74cfa1 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -249,6 +249,28 @@ static void iscsi_login_set_conn_values(
 	mutex_unlock(&auth_id_lock);
 }
 
+static __printf(2, 3) int iscsi_change_param_sprintf(
+	struct iscsi_conn *conn,
+	const char *fmt, ...)
+{
+	va_list args;
+	unsigned char buf[64];
+
+	memset(buf, 0, sizeof buf);
+
+	va_start(args, fmt);
+	vsnprintf(buf, sizeof buf, fmt, args);
+	va_end(args);
+
+	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
+		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+		return -1;
+	}
+
+	return 0;
+}
+
 /*
  *	This is the leading connection of a new session,
  *	or session reinstatement.
@@ -337,7 +359,6 @@ static int iscsi_login_zero_tsih_s2(
 {
 	struct iscsi_node_attrib *na;
 	struct iscsi_session *sess = conn->sess;
-	unsigned char buf[32];
 	bool iser = false;
 
 	sess->tpg = conn->tpg;
@@ -378,26 +399,16 @@ static int iscsi_login_zero_tsih_s2(
 	 *
 	 * In our case, we have already located the struct iscsi_tiqn at this point.
 	 */
-	memset(buf, 0, 32);
-	sprintf(buf, "TargetPortalGroupTag=%hu", sess->tpg->tpgt);
-	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+	if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt))
 		return -1;
-	}
 
 	/*
 	 * Workaround for Initiators that have broken connection recovery logic.
 	 *
 	 * "We would really like to get rid of this." Linux-iSCSI.org team
 	 */
-	memset(buf, 0, 32);
-	sprintf(buf, "ErrorRecoveryLevel=%d", na->default_erl);
-	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+	if (iscsi_change_param_sprintf(conn, "ErrorRecoveryLevel=%d", na->default_erl))
 		return -1;
-	}
 
 	if (iscsi_login_disable_FIM_keys(conn->param_list, conn) < 0)
 		return -1;
@@ -409,12 +420,9 @@ static int iscsi_login_zero_tsih_s2(
 		unsigned long mrdsl, off;
 		int rc;
 
-		sprintf(buf, "RDMAExtensions=Yes");
-		if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+		if (iscsi_change_param_sprintf(conn, "RDMAExtensions=Yes"))
 			return -1;
-		}
+
 		/*
 		 * Make MaxRecvDataSegmentLength PAGE_SIZE aligned for
 		 * Immediate Data + Unsolicitied Data-OUT if necessary..
@@ -444,12 +452,8 @@ static int iscsi_login_zero_tsih_s2(
 		pr_warn("Aligning ISER MaxRecvDataSegmentLength: %lu down"
 			" to PAGE_SIZE\n", mrdsl);
 
-		sprintf(buf, "MaxRecvDataSegmentLength=%lu\n", mrdsl);
-		if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+		if (iscsi_change_param_sprintf(conn, "MaxRecvDataSegmentLength=%lu\n", mrdsl))
 			return -1;
-		}
 	}
 
 	return 0;
@@ -591,13 +595,8 @@ static int iscsi_login_non_zero_tsih_s2(
 	 *
 	 * In our case, we have already located the struct iscsi_tiqn at this point.
 	 */
-	memset(buf, 0, 32);
-	sprintf(buf, "TargetPortalGroupTag=%hu", sess->tpg->tpgt);
-	if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
-		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
-				ISCSI_LOGIN_STATUS_NO_RESOURCES);
+	if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt))
 		return -1;
-	}
 
 	return iscsi_login_disable_FIM_keys(conn->param_list, conn);
 }
@@ -982,6 +981,7 @@ int iscsi_target_setup_login_socket(
 	}
 
 	np->np_transport = t;
+	np->enabled = true;
 	return 0;
 }
 
@@ -1196,7 +1196,7 @@ old_sess_out:
 static int __iscsi_target_login_thread(struct iscsi_np *np)
 {
 	u8 *buffer, zero_tsih = 0;
-	int ret = 0, rc, stop;
+	int ret = 0, rc;
 	struct iscsi_conn *conn = NULL;
 	struct iscsi_login *login;
 	struct iscsi_portal_group *tpg = NULL;
@@ -1210,6 +1210,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
 		np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 		complete(&np->np_restart_comp);
+	} else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) {
+		spin_unlock_bh(&np->np_thread_lock);
+		goto exit;
 	} else {
 		np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 	}
@@ -1402,10 +1405,8 @@ old_sess_out:
 	}
 
 out:
-	stop = kthread_should_stop();
-	/* Wait for another socket.. */
-	if (!stop)
-		return 1;
+	return 1;
+
 exit:
 	iscsi_stop_login_thread_timer(np);
 	spin_lock_bh(&np->np_thread_lock);
@@ -1422,7 +1423,7 @@ int iscsi_target_login_thread(void *arg)
 
 	allow_signal(SIGINT);
 
-	while (!kthread_should_stop()) {
+	while (1) {
 		ret = __iscsi_target_login_thread(np);
 		/*
 		 * We break and exit here unless another sock_accept() call
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 4d2e23fc76fd..43b7e6a616b8 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -601,7 +601,7 @@ int iscsi_copy_param_list(
 	param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL);
 	if (!param_list) {
 		pr_err("Unable to allocate memory for struct iscsi_param_list.\n");
-		goto err_out;
+		return -1;
 	}
 	INIT_LIST_HEAD(&param_list->param_list);
 	INIT_LIST_HEAD(&param_list->extra_response_list);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 44a5471de00f..d875f7972325 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -184,6 +184,8 @@ static void iscsit_clear_tpg_np_login_thread(
 		return;
 	}
 
+	if (shutdown)
+		tpg_np->tpg_np->enabled = false;
 	iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg, shutdown);
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index e655b042ed18..ab77f80ead2b 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1295,6 +1295,8 @@ int iscsit_tx_login_rsp(struct iscsi_conn *conn, u8 status_class, u8 status_deta
 	login->login_failed = 1;
 	iscsit_collect_login_stats(conn, status_class, status_detail);
 
+	memset(&login->rsp[0], 0, ISCSI_HDR_LEN);
+
 	hdr	= (struct iscsi_login_rsp *)&login->rsp[0];
 	hdr->opcode		= ISCSI_OP_LOGIN_RSP;
 	hdr->status_class	= status_class;
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index c3d9df6aaf5f..f0f0cc0e5752 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -564,7 +564,16 @@ static inline int core_alua_state_standby(
 	case REPORT_LUNS:
 	case RECEIVE_DIAGNOSTIC:
 	case SEND_DIAGNOSTIC:
+	case READ_CAPACITY:
 		return 0;
+	case SERVICE_ACTION_IN:
+		switch (cdb[1] & 0x1f) {
+		case SAI_READ_CAPACITY_16:
+			return 0;
+		default:
+			*alua_ascq = ASCQ_04H_ALUA_TG_PT_STANDBY;
+			return 1;
+		}
 	case MAINTENANCE_IN:
 		switch (cdb[1] & 0x1f) {
 		case MI_REPORT_TARGET_PGS:
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index f0e85b119692..f30385385544 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2223,6 +2223,11 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_access_state(
 			" tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id);
 		return -EINVAL;
 	}
+	if (!(dev->dev_flags & DF_CONFIGURED)) {
+		pr_err("Unable to set alua_access_state while device is"
+		       " not configured\n");
+		return -ENODEV;
+	}
 
 	ret = kstrtoul(page, 0, &tmp);
 	if (ret < 0) {
@@ -2354,7 +2359,7 @@ static ssize_t target_core_alua_tg_pt_gp_store_attr_alua_support_##_name(\
 		pr_err("Invalid value '%ld', must be '0' or '1'\n", tmp); \
 		return -EINVAL;						\
 	}								\
-	if (!tmp)							\
+	if (tmp)							\
 		t->_var |= _bit;					\
 	else								\
 		t->_var &= ~_bit;					\
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 65001e133670..38b4be24d13f 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -616,6 +616,7 @@ void core_dev_unexport(
 	dev->export_count--;
 	spin_unlock(&hba->device_lock);
 
+	lun->lun_sep = NULL;
 	lun->lun_se_dev = NULL;
 }
 
@@ -798,10 +799,10 @@ int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
 		pr_err("emulate_write_cache not supported for pSCSI\n");
 		return -EINVAL;
 	}
-	if (dev->transport->get_write_cache) {
-		pr_warn("emulate_write_cache cannot be changed when underlying"
-			" HW reports WriteCacheEnabled, ignoring request\n");
-		return 0;
+	if (flag &&
+	    dev->transport->get_write_cache) {
+		pr_err("emulate_write_cache not supported for this device\n");
+		return -EINVAL;
 	}
 
 	dev->dev_attrib.emulate_write_cache = flag;
@@ -936,6 +937,10 @@ int se_dev_set_pi_prot_type(struct se_device *dev, int flag)
 		return 0;
 	}
 	if (!dev->transport->init_prot || !dev->transport->free_prot) {
+		/* 0 is only allowed value for non-supporting backends */
+		if (flag == 0)
+			return 0;
+
 		pr_err("DIF protection not supported by backend: %s\n",
 		       dev->transport->name);
 		return -ENOSYS;
@@ -1404,7 +1409,8 @@ int core_dev_add_initiator_node_lun_acl(
 	 * Check to see if there are any existing persistent reservation APTPL
 	 * pre-registrations that need to be enabled for this LUN ACL..
 	 */
-	core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, lacl);
+	core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, nacl,
+					    lacl->mapped_lun);
 	return 0;
 }
 
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 554d4f75a75a..9e0232cca92e 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -203,10 +203,9 @@ static void iblock_free_device(struct se_device *dev)
 
 	if (ib_dev->ibd_bd != NULL)
 		blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL);
-	if (ib_dev->ibd_bio_set != NULL) {
-		bioset_integrity_free(ib_dev->ibd_bio_set);
+	if (ib_dev->ibd_bio_set != NULL)
 		bioset_free(ib_dev->ibd_bio_set);
-	}
+
 	kfree(ib_dev);
 }
 
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 3013287a2aaa..1205dbd4f83d 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -944,10 +944,10 @@ int core_scsi3_check_aptpl_registration(
 	struct se_device *dev,
 	struct se_portal_group *tpg,
 	struct se_lun *lun,
-	struct se_lun_acl *lun_acl)
+	struct se_node_acl *nacl,
+	u32 mapped_lun)
 {
-	struct se_node_acl *nacl = lun_acl->se_lun_nacl;
-	struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun];
+	struct se_dev_entry *deve = nacl->device_list[mapped_lun];
 
 	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
 		return 0;
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index 2ee2936fa0bd..749fd7bb7510 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -60,7 +60,7 @@ extern int core_scsi3_alloc_aptpl_registration(
 			unsigned char *, u16, u32, int, int, u8);
 extern int core_scsi3_check_aptpl_registration(struct se_device *,
 			struct se_portal_group *, struct se_lun *,
-			struct se_lun_acl *);
+			struct se_node_acl *, u32);
 extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *,
 					     struct se_node_acl *);
 extern void core_scsi3_free_all_registrations(struct se_device *);
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 66a5aba5a0d9..7b331b95a3ef 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -158,7 +158,7 @@ static int rd_allocate_sgl_table(struct rd_dev *rd_dev, struct rd_dev_sg_table *
 						- 1;
 
 		for (j = 0; j < sg_per_table; j++) {
-			pg = alloc_pages(GFP_KERNEL, 0);
+			pg = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
 			if (!pg) {
 				pr_err("Unable to allocate scatterlist"
 					" pages for struct rd_dev_sg_table\n");
@@ -242,7 +242,7 @@ static void rd_release_prot_space(struct rd_dev *rd_dev)
 	rd_dev->sg_prot_count = 0;
 }
 
-static int rd_build_prot_space(struct rd_dev *rd_dev, int prot_length)
+static int rd_build_prot_space(struct rd_dev *rd_dev, int prot_length, int block_size)
 {
 	struct rd_dev_sg_table *sg_table;
 	u32 total_sg_needed, sg_tables;
@@ -252,8 +252,13 @@ static int rd_build_prot_space(struct rd_dev *rd_dev, int prot_length)
 
 	if (rd_dev->rd_flags & RDF_NULLIO)
 		return 0;
-
-	total_sg_needed = rd_dev->rd_page_count / prot_length;
+	/*
+	 * prot_length=8byte dif data
+	 * tot sg needed = rd_page_count * (PGSZ/block_size) *
+	 * 		   (prot_length/block_size) + pad
+	 * PGSZ canceled each other.
+	 */
+	total_sg_needed = (rd_dev->rd_page_count * prot_length / block_size) + 1;
 
 	sg_tables = (total_sg_needed / max_sg_per_table) + 1;
 
@@ -606,7 +611,8 @@ static int rd_init_prot(struct se_device *dev)
         if (!dev->dev_attrib.pi_prot_type)
 		return 0;
 
-	return rd_build_prot_space(rd_dev, dev->prot_length);
+	return rd_build_prot_space(rd_dev, dev->prot_length,
+				   dev->dev_attrib.block_size);
 }
 
 static void rd_free_prot(struct se_device *dev)
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 77e6531fb0a1..379033f5903b 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -81,7 +81,7 @@ sbc_emulate_readcapacity(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8);
 	return 0;
 }
 
@@ -134,7 +134,7 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 32);
 	return 0;
 }
 
@@ -425,13 +425,14 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd)
 		goto out;
 	}
 
-	write_sg = kzalloc(sizeof(struct scatterlist) * cmd->t_data_nents,
+	write_sg = kmalloc(sizeof(struct scatterlist) * cmd->t_data_nents,
 			   GFP_KERNEL);
 	if (!write_sg) {
 		pr_err("Unable to allocate compare_and_write sg\n");
 		ret = TCM_OUT_OF_RESOURCES;
 		goto out;
 	}
+	sg_init_table(write_sg, cmd->t_data_nents);
 	/*
 	 * Setup verify and write data payloads from total NumberLBAs.
 	 */
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 3bebc71ea033..fcdf98fc947c 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -714,6 +714,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 	unsigned char *buf;
 	sense_reason_t ret;
 	int p;
+	int len = 0;
 
 	buf = kzalloc(SE_INQUIRY_BUF, GFP_KERNEL);
 	if (!buf) {
@@ -735,6 +736,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		}
 
 		ret = spc_emulate_inquiry_std(cmd, buf);
+		len = buf[4] + 5;
 		goto out;
 	}
 
@@ -742,6 +744,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		if (cdb[2] == evpd_handlers[p].page) {
 			buf[1] = cdb[2];
 			ret = evpd_handlers[p].emulate(cmd, buf);
+			len = get_unaligned_be16(&buf[2]) + 4;
 			goto out;
 		}
 	}
@@ -758,7 +761,7 @@ out:
 	kfree(buf);
 
 	if (!ret)
-		target_complete_cmd(cmd, GOOD);
+		target_complete_cmd_with_length(cmd, GOOD, len);
 	return ret;
 }
 
@@ -1089,7 +1092,7 @@ set_length:
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, length);
 	return 0;
 }
 
@@ -1266,7 +1269,7 @@ done:
 	buf[3] = (lun_count & 0xff);
 	transport_kunmap_data_sg(cmd);
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8);
 	return 0;
 }
 EXPORT_SYMBOL(spc_emulate_report_luns);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index c036595b17cf..fb8a1a12dda9 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -40,6 +40,7 @@
 #include <target/target_core_fabric.h>
 
 #include "target_core_internal.h"
+#include "target_core_pr.h"
 
 extern struct se_device *g_lun0_dev;
 
@@ -166,6 +167,13 @@ void core_tpg_add_node_to_devs(
 
 		core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun,
 				lun_access, acl, tpg);
+		/*
+		 * Check to see if there are any existing persistent reservation
+		 * APTPL pre-registrations that need to be enabled for this dynamic
+		 * LUN ACL now..
+		 */
+		core_scsi3_check_aptpl_registration(dev, tpg, lun, acl,
+						    lun->unpacked_lun);
 		spin_lock(&tpg->tpg_lun_lock);
 	}
 	spin_unlock(&tpg->tpg_lun_lock);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 2956250b7225..e6463ef33cd2 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -560,7 +560,7 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return 1;
 	}
 
@@ -676,7 +676,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	if (cmd->transport_state & CMD_T_ABORTED &&
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	} else if (!success) {
 		INIT_WORK(&cmd->work, target_complete_failure_work);
@@ -692,6 +692,23 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 }
 EXPORT_SYMBOL(target_complete_cmd);
 
+void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length)
+{
+	if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) {
+		if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
+			cmd->residual_count += cmd->data_length - length;
+		} else {
+			cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT;
+			cmd->residual_count = cmd->data_length - length;
+		}
+
+		cmd->data_length = length;
+	}
+
+	target_complete_cmd(cmd, scsi_status);
+}
+EXPORT_SYMBOL(target_complete_cmd_with_length);
+
 static void target_add_to_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -1102,6 +1119,7 @@ void transport_init_se_cmd(
 	init_completion(&cmd->cmd_wait_comp);
 	init_completion(&cmd->task_stop_comp);
 	spin_lock_init(&cmd->t_state_lock);
+	kref_init(&cmd->cmd_kref);
 	cmd->transport_state = CMD_T_DEV_ACTIVE;
 
 	cmd->se_tfo = tfo;
@@ -1747,7 +1765,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 			cmd->se_tfo->get_task_tag(cmd));
 
 		spin_unlock_irq(&cmd->t_state_lock);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	}
 
@@ -1837,8 +1855,7 @@ static void transport_complete_qf(struct se_cmd *cmd)
 	if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
 		trace_target_cmd_complete(cmd);
 		ret = cmd->se_tfo->queue_status(cmd);
-		if (ret)
-			goto out;
+		goto out;
 	}
 
 	switch (cmd->data_direction) {
@@ -2213,7 +2230,7 @@ transport_generic_new_cmd(struct se_cmd *cmd)
 	 * and let it call back once the write buffers are ready.
 	 */
 	target_add_to_state_list(cmd);
-	if (cmd->data_direction != DMA_TO_DEVICE) {
+	if (cmd->data_direction != DMA_TO_DEVICE || cmd->data_length == 0) {
 		target_execute_cmd(cmd);
 		return 0;
 	}
@@ -2292,7 +2309,6 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd,
 	unsigned long flags;
 	int ret = 0;
 
-	kref_init(&se_cmd->cmd_kref);
 	/*
 	 * Add a second kref if the fabric caller is expecting to handle
 	 * fabric acknowledgement that requires two target_put_sess_cmd()
@@ -2342,6 +2358,10 @@ static void target_release_cmd_kref(struct kref *kref)
  */
 int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd)
 {
+	if (!se_sess) {
+		se_cmd->se_tfo->release_cmd(se_cmd);
+		return 1;
+	}
 	return kref_put_spinlock_irqsave(&se_cmd->cmd_kref, target_release_cmd_kref,
 			&se_sess->sess_cmd_lock);
 }
@@ -2864,6 +2884,12 @@ static void target_tmr_work(struct work_struct *work)
 int transport_generic_handle_tmr(
 	struct se_cmd *cmd)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	cmd->transport_state |= CMD_T_ACTIVE;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	INIT_WORK(&cmd->work, target_tmr_work);
 	queue_work(cmd->se_dev->tmr_wq, &cmd->work);
 	return 0;
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 8b2c1aaf81de..d22cdc77e9d4 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -90,18 +90,18 @@ static void ft_free_cmd(struct ft_cmd *cmd)
 {
 	struct fc_frame *fp;
 	struct fc_lport *lport;
-	struct se_session *se_sess;
+	struct ft_sess *sess;
 
 	if (!cmd)
 		return;
-	se_sess = cmd->sess->se_sess;
+	sess = cmd->sess;
 	fp = cmd->req_frame;
 	lport = fr_dev(fp);
 	if (fr_seq(fp))
 		lport->tt.seq_release(fr_seq(fp));
 	fc_frame_free(fp);
-	percpu_ida_free(&se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
-	ft_sess_put(cmd->sess);	/* undo get from lookup at recv */
+	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	ft_sess_put(sess);	/* undo get from lookup at recv */
 }
 
 void ft_release_cmd(struct se_cmd *se_cmd)
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index ae52c08dad09..e9fe60fa7df1 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -68,6 +68,7 @@ static struct ft_tport *ft_tport_create(struct fc_lport *lport)
 
 	if (tport) {
 		tport->tpg = tpg;
+		tpg->tport = tport;
 		return tport;
 	}
 
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index 04b1be7fa018..4b2b999b7611 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -156,8 +156,8 @@ static int of_thermal_bind(struct thermal_zone_device *thermal,
 
 			ret = thermal_zone_bind_cooling_device(thermal,
 						tbp->trip_id, cdev,
-						tbp->min,
-						tbp->max);
+						tbp->max,
+						tbp->min);
 			if (ret)
 				return ret;
 		}
@@ -712,11 +712,12 @@ thermal_of_build_thermal_zone(struct device_node *np)
 	}
 
 	i = 0;
-	for_each_child_of_node(child, gchild)
+	for_each_child_of_node(child, gchild) {
 		ret = thermal_of_populate_bind_params(gchild, &tz->tbps[i++],
 						      tz->trips, tz->ntrips);
 		if (ret)
 			goto free_tbps;
+	}
 
 finish:
 	of_node_put(child);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 71b0ec0c370d..284733e1fb6f 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1824,10 +1824,10 @@ static int __init thermal_init(void)
 
 exit_netlink:
 	genetlink_exit();
-unregister_governors:
-	thermal_unregister_governors();
 unregister_class:
 	class_unregister(&thermal_class);
+unregister_governors:
+	thermal_unregister_governors();
 error:
 	idr_destroy(&thermal_tz_idr);
 	idr_destroy(&thermal_cdev_idr);
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index fdb07199d9c2..1967bee4f076 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -140,6 +140,12 @@ thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
 	return NULL;
 }
 
+static bool thermal_zone_crit_temp_valid(struct thermal_zone_device *tz)
+{
+	unsigned long temp;
+	return tz->ops->get_crit_temp && !tz->ops->get_crit_temp(tz, &temp);
+}
+
 int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 {
 	struct thermal_hwmon_device *hwmon;
@@ -189,21 +195,18 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 	if (result)
 		goto free_temp_mem;
 
-	if (tz->ops->get_crit_temp) {
-		unsigned long temperature;
-		if (!tz->ops->get_crit_temp(tz, &temperature)) {
-			snprintf(temp->temp_crit.name,
-				 sizeof(temp->temp_crit.name),
+	if (thermal_zone_crit_temp_valid(tz)) {
+		snprintf(temp->temp_crit.name,
+				sizeof(temp->temp_crit.name),
 				"temp%d_crit", hwmon->count);
-			temp->temp_crit.attr.attr.name = temp->temp_crit.name;
-			temp->temp_crit.attr.attr.mode = 0444;
-			temp->temp_crit.attr.show = temp_crit_show;
-			sysfs_attr_init(&temp->temp_crit.attr.attr);
-			result = device_create_file(hwmon->device,
-						    &temp->temp_crit.attr);
-			if (result)
-				goto unregister_input;
-		}
+		temp->temp_crit.attr.attr.name = temp->temp_crit.name;
+		temp->temp_crit.attr.attr.mode = 0444;
+		temp->temp_crit.attr.show = temp_crit_show;
+		sysfs_attr_init(&temp->temp_crit.attr.attr);
+		result = device_create_file(hwmon->device,
+					    &temp->temp_crit.attr);
+		if (result)
+			goto unregister_input;
 	}
 
 	mutex_lock(&thermal_hwmon_list_lock);
@@ -250,7 +253,7 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
 	}
 
 	device_remove_file(hwmon->device, &temp->temp_input.attr);
-	if (tz->ops->get_crit_temp)
+	if (thermal_zone_crit_temp_valid(tz))
 		device_remove_file(hwmon->device, &temp->temp_crit.attr);
 
 	mutex_lock(&thermal_hwmon_list_lock);
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 50b46881b6ca..0ff7fda0742f 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -31,6 +31,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/major.h>
+#include <linux/atomic.h>
 #include <linux/sysrq.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
@@ -70,6 +71,9 @@ static struct task_struct *hvc_task;
 /* Picks up late kicks after list walk but before schedule() */
 static int hvc_kicked;
 
+/* hvc_init is triggered from hvc_alloc, i.e. only when actually used */
+static atomic_t hvc_needs_init __read_mostly = ATOMIC_INIT(-1);
+
 static int hvc_init(void);
 
 #ifdef CONFIG_MAGIC_SYSRQ
@@ -186,7 +190,7 @@ static struct tty_driver *hvc_console_device(struct console *c, int *index)
 	return hvc_driver;
 }
 
-static int __init hvc_console_setup(struct console *co, char *options)
+static int hvc_console_setup(struct console *co, char *options)
 {	
 	if (co->index < 0 || co->index >= MAX_NR_HVC_CONSOLES)
 		return -ENODEV;
@@ -851,7 +855,7 @@ struct hvc_struct *hvc_alloc(uint32_t vtermno, int data,
 	int i;
 
 	/* We wait until a driver actually comes along */
-	if (!hvc_driver) {
+	if (atomic_inc_not_zero(&hvc_needs_init)) {
 		int err = hvc_init();
 		if (err)
 			return ERR_PTR(err);
diff --git a/drivers/tty/ipwireless/tty.c b/drivers/tty/ipwireless/tty.c
index ebd5bff0f5c1..17ee3bf0926b 100644
--- a/drivers/tty/ipwireless/tty.c
+++ b/drivers/tty/ipwireless/tty.c
@@ -176,9 +176,6 @@ void ipwireless_tty_received(struct ipw_tty *tty, unsigned char *data,
 				": %d chars not inserted to flip buffer!\n",
 				length - work);
 
-	/*
-	 * This may sleep if ->low_latency is set
-	 */
 	if (work)
 		tty_flip_buffer_push(&tty->port);
 }
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index d15624c1b751..d46b4ccec8cd 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -321,7 +321,8 @@ static void n_tty_check_unthrottle(struct tty_struct *tty)
 
 static inline void put_tty_queue(unsigned char c, struct n_tty_data *ldata)
 {
-	*read_buf_addr(ldata, ldata->read_head++) = c;
+	*read_buf_addr(ldata, ldata->read_head) = c;
+	ldata->read_head++;
 }
 
 /**
@@ -1214,15 +1215,16 @@ static void n_tty_receive_parity_error(struct tty_struct *tty, unsigned char c)
 {
 	struct n_tty_data *ldata = tty->disc_data;
 
-	if (I_IGNPAR(tty))
-		return;
-	if (I_PARMRK(tty)) {
-		put_tty_queue('\377', ldata);
-		put_tty_queue('\0', ldata);
-		put_tty_queue(c, ldata);
-	} else	if (I_INPCK(tty))
-		put_tty_queue('\0', ldata);
-	else
+	if (I_INPCK(tty)) {
+		if (I_IGNPAR(tty))
+			return;
+		if (I_PARMRK(tty)) {
+			put_tty_queue('\377', ldata);
+			put_tty_queue('\0', ldata);
+			put_tty_queue(c, ldata);
+		} else
+			put_tty_queue('\0', ldata);
+	} else
 		put_tty_queue(c, ldata);
 	if (waitqueue_active(&tty->read_wait))
 		wake_up_interruptible(&tty->read_wait);
@@ -2356,8 +2358,12 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file,
 			if (tty->ops->flush_chars)
 				tty->ops->flush_chars(tty);
 		} else {
+			struct n_tty_data *ldata = tty->disc_data;
+
 			while (nr > 0) {
+				mutex_lock(&ldata->output_lock);
 				c = tty->ops->write(tty, b, nr);
+				mutex_unlock(&ldata->output_lock);
 				if (c < 0) {
 					retval = c;
 					goto break_out;
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 69932b7556cf..612dfc720738 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -555,7 +555,7 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 	 */
 	if ((p->port.type == PORT_XR17V35X) ||
 	   (p->port.type == PORT_XR17D15X)) {
-		serial_out(p, UART_EXAR_SLEEP, 0xff);
+		serial_out(p, UART_EXAR_SLEEP, sleep ? 0xff : 0);
 		return;
 	}
 
@@ -1520,7 +1520,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 			status = serial8250_rx_chars(up, status);
 	}
 	serial8250_modem_status(up);
-	if (status & UART_LSR_THRE)
+	if (!up->dma && (status & UART_LSR_THRE))
 		serial8250_tx_chars(up);
 
 	spin_unlock_irqrestore(&port->lock, flags);
@@ -2356,7 +2356,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index 7046769608d4..148ffe4c232f 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -20,12 +20,15 @@ static void __dma_tx_complete(void *param)
 	struct uart_8250_port	*p = param;
 	struct uart_8250_dma	*dma = p->dma;
 	struct circ_buf		*xmit = &p->port.state->xmit;
-
-	dma->tx_running = 0;
+	unsigned long	flags;
 
 	dma_sync_single_for_cpu(dma->txchan->device->dev, dma->tx_addr,
 				UART_XMIT_SIZE, DMA_TO_DEVICE);
 
+	spin_lock_irqsave(&p->port.lock, flags);
+
+	dma->tx_running = 0;
+
 	xmit->tail += dma->tx_size;
 	xmit->tail &= UART_XMIT_SIZE - 1;
 	p->port.icount.tx += dma->tx_size;
@@ -35,6 +38,8 @@ static void __dma_tx_complete(void *param)
 
 	if (!uart_circ_empty(xmit) && !uart_tx_stopped(&p->port))
 		serial8250_tx_dma(p);
+
+	spin_unlock_irqrestore(&p->port.lock, flags);
 }
 
 static void __dma_rx_complete(void *param)
@@ -187,21 +192,28 @@ int serial8250_request_dma(struct uart_8250_port *p)
 
 	dma->rx_buf = dma_alloc_coherent(dma->rxchan->device->dev, dma->rx_size,
 					&dma->rx_addr, GFP_KERNEL);
-	if (!dma->rx_buf) {
-		dma_release_channel(dma->rxchan);
-		dma_release_channel(dma->txchan);
-		return -ENOMEM;
-	}
+	if (!dma->rx_buf)
+		goto err;
 
 	/* TX buffer */
 	dma->tx_addr = dma_map_single(dma->txchan->device->dev,
 					p->port.state->xmit.buf,
 					UART_XMIT_SIZE,
 					DMA_TO_DEVICE);
+	if (dma_mapping_error(dma->txchan->device->dev, dma->tx_addr)) {
+		dma_free_coherent(dma->rxchan->device->dev, dma->rx_size,
+				  dma->rx_buf, dma->rx_addr);
+		goto err;
+	}
 
 	dev_dbg_ratelimited(p->port.dev, "got both dma channels\n");
 
 	return 0;
+err:
+	dma_release_channel(dma->rxchan);
+	dma_release_channel(dma->txchan);
+
+	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(serial8250_request_dma);
 
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index c100d6343d50..4858b8a99d3b 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -35,18 +35,8 @@
 #include <linux/serial_8250.h>
 #include <asm/io.h>
 #include <asm/serial.h>
-#ifdef CONFIG_FIX_EARLYCON_MEM
-#include <asm/pgtable.h>
-#include <asm/fixmap.h>
-#endif
 
-struct early_serial8250_device {
-	struct uart_port port;
-	char options[16];		/* e.g., 115200n8 */
-	unsigned int baud;
-};
-
-static struct early_serial8250_device early_device;
+static struct earlycon_device *early_device;
 
 unsigned int __weak __init serial8250_early_in(struct uart_port *port, int offset)
 {
@@ -100,7 +90,7 @@ static void __init serial_putc(struct uart_port *port, int c)
 static void __init early_serial8250_write(struct console *console,
 					const char *s, unsigned int count)
 {
-	struct uart_port *port = &early_device.port;
+	struct uart_port *port = &early_device->port;
 	unsigned int ier;
 
 	/* Save the IER and disable interrupts */
@@ -129,7 +119,7 @@ static unsigned int __init probe_baud(struct uart_port *port)
 	return (port->uartclk / 16) / quot;
 }
 
-static void __init init_port(struct early_serial8250_device *device)
+static void __init init_port(struct earlycon_device *device)
 {
 	struct uart_port *port = &device->port;
 	unsigned int divisor;
@@ -148,128 +138,45 @@ static void __init init_port(struct early_serial8250_device *device)
 	serial8250_early_out(port, UART_LCR, c & ~UART_LCR_DLAB);
 }
 
-static int __init parse_options(struct early_serial8250_device *device,
-								char *options)
+static int __init early_serial8250_setup(struct earlycon_device *device,
+					 const char *options)
 {
-	struct uart_port *port = &device->port;
-	int mmio, mmio32, length;
-
-	if (!options)
-		return -ENODEV;
-
-	port->uartclk = BASE_BAUD * 16;
-
-	mmio = !strncmp(options, "mmio,", 5);
-	mmio32 = !strncmp(options, "mmio32,", 7);
-	if (mmio || mmio32) {
-		port->iotype = (mmio ? UPIO_MEM : UPIO_MEM32);
-		port->mapbase = simple_strtoul(options + (mmio ? 5 : 7),
-					       &options, 0);
-		if (mmio32)
-			port->regshift = 2;
-#ifdef CONFIG_FIX_EARLYCON_MEM
-		set_fixmap_nocache(FIX_EARLYCON_MEM_BASE,
-					port->mapbase & PAGE_MASK);
-		port->membase =
-			(void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
-		port->membase += port->mapbase & ~PAGE_MASK;
-#else
-		port->membase = ioremap_nocache(port->mapbase, 64);
-		if (!port->membase) {
-			printk(KERN_ERR "%s: Couldn't ioremap 0x%llx\n",
-				__func__,
-			       (unsigned long long) port->mapbase);
-			return -ENOMEM;
-		}
-#endif
-	} else if (!strncmp(options, "io,", 3)) {
-		port->iotype = UPIO_PORT;
-		port->iobase = simple_strtoul(options + 3, &options, 0);
-		mmio = 0;
-	} else
-		return -EINVAL;
+	if (!(device->port.membase || device->port.iobase))
+		return 0;
 
-	options = strchr(options, ',');
-	if (options) {
-		options++;
-		device->baud = simple_strtoul(options, NULL, 0);
-		length = min(strcspn(options, " ") + 1,
-			     (size_t)(sizeof(device->options)));
-		strlcpy(device->options, options, length);
-	} else {
-		device->baud = probe_baud(port);
+	if (!device->baud) {
+		device->baud = probe_baud(&device->port);
 		snprintf(device->options, sizeof(device->options), "%u",
-			device->baud);
+			 device->baud);
 	}
 
-	if (mmio || mmio32)
-		printk(KERN_INFO
-		       "Early serial console at MMIO%s 0x%llx (options '%s')\n",
-			mmio32 ? "32" : "",
-			(unsigned long long)port->mapbase,
-			device->options);
-	else
-		printk(KERN_INFO
-		      "Early serial console at I/O port 0x%lx (options '%s')\n",
-			port->iobase,
-			device->options);
-
-	return 0;
-}
-
-static struct console early_serial8250_console __initdata = {
-	.name	= "uart",
-	.write	= early_serial8250_write,
-	.flags	= CON_PRINTBUFFER | CON_BOOT,
-	.index	= -1,
-};
-
-static int __init early_serial8250_setup(char *options)
-{
-	struct early_serial8250_device *device = &early_device;
-	int err;
-
-	if (device->port.membase || device->port.iobase)
-		return 0;
-
-	err = parse_options(device, options);
-	if (err < 0)
-		return err;
-
 	init_port(device);
+
+	early_device = device;
+	device->con->write = early_serial8250_write;
 	return 0;
 }
+EARLYCON_DECLARE(uart8250, early_serial8250_setup);
+EARLYCON_DECLARE(uart, early_serial8250_setup);
 
 int __init setup_early_serial8250_console(char *cmdline)
 {
-	char *options;
-	int err;
+	char match[] = "uart8250";
 
-	options = strstr(cmdline, "uart8250,");
-	if (!options) {
-		options = strstr(cmdline, "uart,");
-		if (!options)
-			return 0;
-	}
-
-	options = strchr(cmdline, ',') + 1;
-	err = early_serial8250_setup(options);
-	if (err < 0)
-		return err;
-
-	register_console(&early_serial8250_console);
+	if (cmdline && cmdline[4] == ',')
+		match[4] = '\0';
 
-	return 0;
+	return setup_earlycon(cmdline, match, early_serial8250_setup);
 }
 
 int serial8250_find_port_for_earlycon(void)
 {
-	struct early_serial8250_device *device = &early_device;
-	struct uart_port *port = &device->port;
+	struct earlycon_device *device = early_device;
+	struct uart_port *port = device ? &device->port : NULL;
 	int line;
 	int ret;
 
-	if (!device->port.membase && !device->port.iobase)
+	if (!port || (!port->membase && !port->iobase))
 		return -ENODEV;
 
 	line = serial8250_find_port(port);
@@ -284,5 +191,3 @@ int serial8250_find_port_for_earlycon(void)
 
 	return ret;
 }
-
-early_param("earlycon", setup_early_serial8250_console);
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 0ff3e3624d4c..feda34404ed0 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1766,6 +1766,7 @@ pci_wch_ch353_setup(struct serial_private *priv,
 #define PCI_DEVICE_ID_COMMTECH_4222PCIE	0x0022
 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a
 #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e
+#define PCI_DEVICE_ID_INTEL_QRK_UART	0x0936
 
 #define PCI_VENDOR_ID_SUNIX		0x1fd4
 #define PCI_DEVICE_ID_SUNIX_1999	0x1999
@@ -1876,6 +1877,13 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 		.subdevice	= PCI_ANY_ID,
 		.setup		= byt_serial_setup,
 	},
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_QRK_UART,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= pci_default_setup,
+	},
 	/*
 	 * ITE
 	 */
@@ -2710,6 +2718,7 @@ enum pci_board_num_t {
 	pbn_ADDIDATA_PCIe_8_3906250,
 	pbn_ce4100_1_115200,
 	pbn_byt,
+	pbn_qrk,
 	pbn_omegapci,
 	pbn_NETMOS9900_2s_115200,
 	pbn_brcm_trumanage,
@@ -3456,6 +3465,12 @@ static struct pciserial_board pci_boards[] = {
 		.uart_offset	= 0x80,
 		.reg_shift      = 2,
 	},
+	[pbn_qrk] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 1,
+		.base_baud	= 2764800,
+		.reg_shift	= 2,
+	},
 	[pbn_omegapci] = {
 		.flags		= FL_BASE0,
 		.num_ports	= 8,
@@ -5150,6 +5165,12 @@ static struct pci_device_id serial_pci_tbl[] = {
 		pbn_byt },
 
 	/*
+	 * Intel Quark x1000
+	 */
+	{	PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QRK_UART,
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_qrk },
+	/*
 	 * Cronyx Omega PCI
 	 */
 	{	PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_CRONYX_OMEGA,
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index 23329918f229..7f96b50a3ce2 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -61,6 +61,7 @@ config SERIAL_8250_CONSOLE
 	bool "Console on 8250/16550 and compatible serial port"
 	depends on SERIAL_8250=y
 	select SERIAL_CORE_CONSOLE
+	select SERIAL_EARLYCON
 	---help---
 	  If you say Y here, it will be possible to use a serial port as the
 	  system console (the system console is the device which receives all
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index a3815eaed421..108bd797ab44 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -7,6 +7,13 @@ if TTY
 menu "Serial drivers"
 	depends on HAS_IOMEM
 
+config SERIAL_EARLYCON
+	bool
+	help
+	  Support for early consoles with the earlycon parameter. This enables
+	  the console before standard serial driver is probed. The console is
+	  enabled when early_param is processed.
+
 source "drivers/tty/serial/8250/Kconfig"
 
 comment "Non-8250 serial port support"
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index 3680854fef41..8af1415a6366 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -5,6 +5,8 @@
 obj-$(CONFIG_SERIAL_CORE) += serial_core.o
 obj-$(CONFIG_SERIAL_21285) += 21285.o
 
+obj-$(CONFIG_SERIAL_EARLYCON) += earlycon.o
+
 # These Sparc drivers have to appear before others such as 8250
 # which share ttySx minor node space.  Otherwise console device
 # names change and other unplesantries.
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 501667e3e3f5..323376668b72 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -185,6 +185,12 @@ static void altera_uart_set_termios(struct uart_port *port,
 	uart_update_timeout(port, termios->c_cflag, baud);
 	altera_uart_writel(port, baudclk, ALTERA_UART_DIVISOR_REG);
 	spin_unlock_irqrestore(&port->lock, flags);
+
+	/*
+	 * FIXME: port->read_status_mask and port->ignore_status_mask
+	 * need to be initialized based on termios settings for
+	 * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT
+	 */
 }
 
 static void altera_uart_rx_chars(struct altera_uart *pp)
diff --git a/drivers/tty/serial/amba-pl010.c b/drivers/tty/serial/amba-pl010.c
index 01c9e72433e1..971af1e22d0f 100644
--- a/drivers/tty/serial/amba-pl010.c
+++ b/drivers/tty/serial/amba-pl010.c
@@ -420,7 +420,7 @@ pl010_set_termios(struct uart_port *port, struct ktermios *termios,
 	uap->port.read_status_mask = UART01x_RSR_OE;
 	if (termios->c_iflag & INPCK)
 		uap->port.read_status_mask |= UART01x_RSR_FE | UART01x_RSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uap->port.read_status_mask |= UART01x_RSR_BE;
 
 	/*
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index d58783d364e3..b569011ac713 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1744,7 +1744,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = UART011_DR_OE | 255;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART011_DR_FE | UART011_DR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART011_DR_BE;
 
 	/*
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index a49f10d269b2..ce352b81e230 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1811,7 +1811,7 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = ATMEL_US_OVRE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (ATMEL_US_FRAME | ATMEL_US_PARE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= ATMEL_US_RXBRK;
 
 	if (atmel_use_pdc_rx(port))
diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index 78e82b017b92..e0b87d507670 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -565,7 +565,7 @@ static void bcm_uart_set_termios(struct uart_port *port,
 		port->read_status_mask |= UART_FIFO_FRAMEERR_MASK;
 		port->read_status_mask |= UART_FIFO_PARERR_MASK;
 	}
-	if (new->c_iflag & (BRKINT))
+	if (new->c_iflag & (IGNBRK | BRKINT))
 		port->read_status_mask |= UART_FIFO_BRKDET_MASK;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/bfin_uart.c b/drivers/tty/serial/bfin_uart.c
index 869ceba2ec57..ac86a20992e9 100644
--- a/drivers/tty/serial/bfin_uart.c
+++ b/drivers/tty/serial/bfin_uart.c
@@ -833,7 +833,7 @@ bfin_serial_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = OE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (FE | PE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= BI;
 
 	/*
diff --git a/drivers/tty/serial/dz.c b/drivers/tty/serial/dz.c
index 2f2b2e538a54..cdbbc788230a 100644
--- a/drivers/tty/serial/dz.c
+++ b/drivers/tty/serial/dz.c
@@ -625,7 +625,7 @@ static void dz_set_termios(struct uart_port *uport, struct ktermios *termios,
 	dport->port.read_status_mask = DZ_OERR;
 	if (termios->c_iflag & INPCK)
 		dport->port.read_status_mask |= DZ_FERR | DZ_PERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		dport->port.read_status_mask |= DZ_BREAK;
 
 	/* characters to ignore */
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
new file mode 100644
index 000000000000..4f27f788ac6f
--- /dev/null
+++ b/drivers/tty/serial/earlycon.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Rob Herring <robh@kernel.org>
+ *
+ * Based on 8250 earlycon:
+ * (c) Copyright 2004 Hewlett-Packard Development Company, L.P.
+ *	Bjorn Helgaas <bjorn.helgaas@hp.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/serial_core.h>
+
+#ifdef CONFIG_FIX_EARLYCON_MEM
+#include <asm/fixmap.h>
+#endif
+
+#include <asm/serial.h>
+
+static struct console early_con = {
+	.name =		"uart", /* 8250 console switch requires this name */
+	.flags =	CON_PRINTBUFFER | CON_BOOT,
+	.index =	-1,
+};
+
+static struct earlycon_device early_console_dev = {
+	.con = &early_con,
+};
+
+static void __iomem * __init earlycon_map(unsigned long paddr, size_t size)
+{
+	void __iomem *base;
+#ifdef CONFIG_FIX_EARLYCON_MEM
+	set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr & PAGE_MASK);
+	base = (void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
+	base += paddr & ~PAGE_MASK;
+#else
+	base = ioremap(paddr, size);
+#endif
+	if (!base)
+		pr_err("%s: Couldn't map 0x%llx\n", __func__,
+		       (unsigned long long)paddr);
+
+	return base;
+}
+
+static int __init parse_options(struct earlycon_device *device,
+				char *options)
+{
+	struct uart_port *port = &device->port;
+	int mmio, mmio32, length, ret;
+	unsigned long addr;
+
+	if (!options)
+		return -ENODEV;
+
+	mmio = !strncmp(options, "mmio,", 5);
+	mmio32 = !strncmp(options, "mmio32,", 7);
+	if (mmio || mmio32) {
+		port->iotype = (mmio ? UPIO_MEM : UPIO_MEM32);
+		options += mmio ? 5 : 7;
+		ret = kstrtoul(options, 0, &addr);
+		if (ret)
+			return ret;
+		port->mapbase = addr;
+		if (mmio32)
+			port->regshift = 2;
+	} else if (!strncmp(options, "io,", 3)) {
+		port->iotype = UPIO_PORT;
+		options += 3;
+		ret = kstrtoul(options, 0, &addr);
+		if (ret)
+			return ret;
+		port->iobase = addr;
+		mmio = 0;
+	} else if (!strncmp(options, "0x", 2)) {
+		port->iotype = UPIO_MEM;
+		ret = kstrtoul(options, 0, &addr);
+		if (ret)
+			return ret;
+		port->mapbase = addr;
+	} else {
+		return -EINVAL;
+	}
+
+	port->uartclk = BASE_BAUD * 16;
+
+	options = strchr(options, ',');
+	if (options) {
+		options++;
+		ret = kstrtouint(options, 0, &device->baud);
+		if (ret)
+			return ret;
+		length = min(strcspn(options, " ") + 1,
+			     (size_t)(sizeof(device->options)));
+		strlcpy(device->options, options, length);
+	}
+
+	if (mmio || mmio32)
+		pr_info("Early serial console at MMIO%s 0x%llx (options '%s')\n",
+			mmio32 ? "32" : "",
+			(unsigned long long)port->mapbase,
+			device->options);
+	else
+		pr_info("Early serial console at I/O port 0x%lx (options '%s')\n",
+			port->iobase,
+			device->options);
+
+	return 0;
+}
+
+int __init setup_earlycon(char *buf, const char *match,
+			  int (*setup)(struct earlycon_device *, const char *))
+{
+	int err;
+	size_t len;
+	struct uart_port *port = &early_console_dev.port;
+
+	if (!buf || !match || !setup)
+		return 0;
+
+	len = strlen(match);
+	if (strncmp(buf, match, len))
+		return 0;
+	if (buf[len] && (buf[len] != ','))
+		return 0;
+
+	buf += len + 1;
+
+	err = parse_options(&early_console_dev, buf);
+	/* On parsing error, pass the options buf to the setup function */
+	if (!err)
+		buf = NULL;
+
+	if (port->mapbase)
+		port->membase = earlycon_map(port->mapbase, 64);
+
+	early_console_dev.con->data = &early_console_dev;
+	err = setup(&early_console_dev, buf);
+	if (err < 0)
+		return err;
+	if (!early_console_dev.con->write)
+		return -ENODEV;
+
+	register_console(early_console_dev.con);
+	return 0;
+}
diff --git a/drivers/tty/serial/efm32-uart.c b/drivers/tty/serial/efm32-uart.c
index 0eb5b5673ede..948f17b6b497 100644
--- a/drivers/tty/serial/efm32-uart.c
+++ b/drivers/tty/serial/efm32-uart.c
@@ -407,7 +407,7 @@ static void efm32_uart_set_termios(struct uart_port *port,
 	if (new->c_iflag & INPCK)
 		port->read_status_mask |=
 			UARTn_RXDATAX_FERR | UARTn_RXDATAX_PERR;
-	if (new->c_iflag & (BRKINT | PARMRK))
+	if (new->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SW_UARTn_RXDATAX_BERR;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 8978dc9a58b7..175f123f4f09 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -496,7 +496,7 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios,
 	sport->port.read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
 		sport->port.read_status_mask |=	(UARTSR1_FE | UARTSR1_PE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		sport->port.read_status_mask |= UARTSR1_FE;
 
 	/* characters to ignore */
diff --git a/drivers/tty/serial/ip22zilog.c b/drivers/tty/serial/ip22zilog.c
index 1d9420548e16..1efd4c36ba0c 100644
--- a/drivers/tty/serial/ip22zilog.c
+++ b/drivers/tty/serial/ip22zilog.c
@@ -850,7 +850,7 @@ ip22zilog_convert_to_zs(struct uart_ip22zilog_port *up, unsigned int cflag,
 	up->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= BRK_ABRT;
 
 	up->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/m32r_sio.c b/drivers/tty/serial/m32r_sio.c
index 9cd9b4eba9fc..68f2c53e0b54 100644
--- a/drivers/tty/serial/m32r_sio.c
+++ b/drivers/tty/serial/m32r_sio.c
@@ -737,7 +737,7 @@ static void m32r_sio_set_termios(struct uart_port *port,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 8d71e4047bb3..558af637cd0c 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -842,7 +842,7 @@ static void max310x_set_termios(struct uart_port *port,
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= MAX310X_LSR_RXPAR_BIT |
 					  MAX310X_LSR_FRERR_BIT;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= MAX310X_LSR_RXBRK_BIT;
 
 	/* Set status ignore mask */
diff --git a/drivers/tty/serial/mcf.c b/drivers/tty/serial/mcf.c
index 0edfaf8cd269..a6f085717f94 100644
--- a/drivers/tty/serial/mcf.c
+++ b/drivers/tty/serial/mcf.c
@@ -248,6 +248,12 @@ static void mcf_set_termios(struct uart_port *port, struct ktermios *termios,
 		mr1 |= MCFUART_MR1_PARITYNONE;
 	}
 
+	/*
+	 * FIXME: port->read_status_mask and port->ignore_status_mask
+	 * need to be initialized based on termios settings for
+	 * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT
+	 */
+
 	if (termios->c_cflag & CSTOPB)
 		mr2 |= MCFUART_MR2_STOP2;
 	else
diff --git a/drivers/tty/serial/mfd.c b/drivers/tty/serial/mfd.c
index 52c930fac210..445799dc9846 100644
--- a/drivers/tty/serial/mfd.c
+++ b/drivers/tty/serial/mfd.c
@@ -977,7 +977,7 @@ serial_hsu_set_termios(struct uart_port *port, struct ktermios *termios,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/* Characters to ignore */
diff --git a/drivers/tty/serial/mpsc.c b/drivers/tty/serial/mpsc.c
index e30a3ca3cea3..759c6a6fa74a 100644
--- a/drivers/tty/serial/mpsc.c
+++ b/drivers/tty/serial/mpsc.c
@@ -1458,7 +1458,7 @@ static void mpsc_set_termios(struct uart_port *port, struct ktermios *termios,
 		pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_PE
 			| SDMA_DESC_CMDSTAT_FR;
 
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_BR;
 
 	/* Characters/events to ignore */
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index b5d779cd3c2b..c0f2b3e5452f 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -570,7 +570,7 @@ static void msm_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART_SR_PAR_FRAME_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_SR_RX_BREAK;
 
 	uart_update_timeout(port, termios->c_cflag, baud);
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index aa97fd845b4d..d98f1d4a9bd3 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -604,7 +604,7 @@ static void mxs_auart_settermios(struct uart_port *u,
 
 	if (termios->c_iflag & INPCK)
 		u->read_status_mask |= AUART_STAT_PERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		u->read_status_mask |= AUART_STAT_BERR;
 
 	/*
diff --git a/drivers/tty/serial/netx-serial.c b/drivers/tty/serial/netx-serial.c
index 0a4dd70d29eb..7a6745601d4e 100644
--- a/drivers/tty/serial/netx-serial.c
+++ b/drivers/tty/serial/netx-serial.c
@@ -419,7 +419,7 @@ netx_set_termios(struct uart_port *port, struct ktermios *termios,
 	}
 
 	port->read_status_mask = 0;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SR_BE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= SR_PE | SR_FE;
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 77f035158d6c..f4e68b3fc39d 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -225,14 +225,19 @@ static inline void serial_omap_enable_wakeirq(struct uart_omap_port *up,
 	if (enable)
 		enable_irq(up->wakeirq);
 	else
-		disable_irq(up->wakeirq);
+		disable_irq_nosync(up->wakeirq);
 }
 
 static void serial_omap_enable_wakeup(struct uart_omap_port *up, bool enable)
 {
 	struct omap_uart_port_info *pdata = dev_get_platdata(up->dev);
 
+	if (enable == up->wakeups_enabled)
+		return;
+
 	serial_omap_enable_wakeirq(up, enable);
+	up->wakeups_enabled = enable;
+
 	if (!pdata || !pdata->enable_wakeup)
 		return;
 
@@ -255,8 +260,16 @@ serial_omap_baud_is_mode16(struct uart_port *port, unsigned int baud)
 {
 	unsigned int n13 = port->uartclk / (13 * baud);
 	unsigned int n16 = port->uartclk / (16 * baud);
-	int baudAbsDiff13 = baud - (port->uartclk / (13 * n13));
-	int baudAbsDiff16 = baud - (port->uartclk / (16 * n16));
+	int baudAbsDiff13;
+	int baudAbsDiff16;
+
+	if (n13 == 0)
+		n13 = 1;
+	if (n16 == 0)
+		n16 = 1;
+
+	baudAbsDiff13 = baud - (port->uartclk / (13 * n13));
+	baudAbsDiff16 = baud - (port->uartclk / (16 * n16));
 	if (baudAbsDiff13 < 0)
 		baudAbsDiff13 = -baudAbsDiff13;
 	if (baudAbsDiff16 < 0)
@@ -1488,6 +1501,11 @@ static int serial_omap_suspend(struct device *dev)
 	uart_suspend_port(&serial_omap_reg, &up->port);
 	flush_work(&up->qos_work);
 
+	if (device_may_wakeup(dev))
+		serial_omap_enable_wakeup(up, true);
+	else
+		serial_omap_enable_wakeup(up, false);
+
 	return 0;
 }
 
@@ -1495,6 +1513,9 @@ static int serial_omap_resume(struct device *dev)
 {
 	struct uart_omap_port *up = dev_get_drvdata(dev);
 
+	if (device_may_wakeup(dev))
+		serial_omap_enable_wakeup(up, false);
+
 	uart_resume_port(&serial_omap_reg, &up->port);
 
 	return 0;
@@ -1870,17 +1891,7 @@ static int serial_omap_runtime_suspend(struct device *dev)
 
 	up->context_loss_cnt = serial_omap_get_context_loss_count(up);
 
-	if (device_may_wakeup(dev)) {
-		if (!up->wakeups_enabled) {
-			serial_omap_enable_wakeup(up, true);
-			up->wakeups_enabled = true;
-		}
-	} else {
-		if (up->wakeups_enabled) {
-			serial_omap_enable_wakeup(up, false);
-			up->wakeups_enabled = false;
-		}
-	}
+	serial_omap_enable_wakeup(up, true);
 
 	up->latency = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE;
 	schedule_work(&up->qos_work);
@@ -1894,6 +1905,8 @@ static int serial_omap_runtime_resume(struct device *dev)
 
 	int loss_cnt = serial_omap_get_context_loss_count(up);
 
+	serial_omap_enable_wakeup(up, false);
+
 	if (loss_cnt < 0) {
 		dev_dbg(dev, "serial_omap_get_context_loss_count failed : %d\n",
 			loss_cnt);
diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c
index e9d420ff3931..8193635103ee 100644
--- a/drivers/tty/serial/pmac_zilog.c
+++ b/drivers/tty/serial/pmac_zilog.c
@@ -1092,7 +1092,7 @@ static void pmz_convert_to_zs(struct uart_pmac_port *uap, unsigned int cflag,
 	uap->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		uap->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		uap->port.read_status_mask |= BRK_ABRT;
 
 	uap->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/pnx8xxx_uart.c b/drivers/tty/serial/pnx8xxx_uart.c
index de6c05c63683..2ba24a45c97f 100644
--- a/drivers/tty/serial/pnx8xxx_uart.c
+++ b/drivers/tty/serial/pnx8xxx_uart.c
@@ -477,7 +477,7 @@ pnx8xxx_set_termios(struct uart_port *port, struct ktermios *termios,
 		sport->port.read_status_mask |=
 			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE) |
 			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		sport->port.read_status_mask |=
 			ISTAT_TO_SM(PNX8XXX_UART_INT_BREAK);
 
diff --git a/drivers/tty/serial/pxa.c b/drivers/tty/serial/pxa.c
index f9f20f383760..fc3f308cd6c1 100644
--- a/drivers/tty/serial/pxa.c
+++ b/drivers/tty/serial/pxa.c
@@ -492,7 +492,7 @@ serial_pxa_set_termios(struct uart_port *port, struct ktermios *termios,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 9cd706df3b33..7d3a3f5cb5ba 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -544,11 +544,15 @@ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level,
 			      unsigned int old)
 {
 	struct s3c24xx_uart_port *ourport = to_ourport(port);
+	int timeout = 10000;
 
 	ourport->pm_level = level;
 
 	switch (level) {
 	case 3:
+		while (--timeout && !s3c24xx_serial_txempty_nofifo(port))
+			udelay(100);
+
 		if (!IS_ERR(ourport->baudclk))
 			clk_disable_unprepare(ourport->baudclk);
 
diff --git a/drivers/tty/serial/sb1250-duart.c b/drivers/tty/serial/sb1250-duart.c
index a7cdec2962dd..771f361c47ea 100644
--- a/drivers/tty/serial/sb1250-duart.c
+++ b/drivers/tty/serial/sb1250-duart.c
@@ -596,7 +596,7 @@ static void sbd_set_termios(struct uart_port *uport, struct ktermios *termios,
 	if (termios->c_iflag & INPCK)
 		uport->read_status_mask |= M_DUART_FRM_ERR |
 					   M_DUART_PARITY_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uport->read_status_mask |= M_DUART_RCVD_BRK;
 
 	uport->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c
index a447f71538ef..75ea83278ba4 100644
--- a/drivers/tty/serial/sccnxp.c
+++ b/drivers/tty/serial/sccnxp.c
@@ -667,7 +667,7 @@ static void sccnxp_set_termios(struct uart_port *port,
 	port->read_status_mask = SR_OVR;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= SR_PE | SR_FE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SR_BRK;
 
 	/* Set status ignore mask */
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index ece2049bd270..27b5554e20d9 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -235,6 +235,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state)
 		/*
 		 * Turn off DTR and RTS early.
 		 */
+		if (uart_console(uport) && tty)
+			uport->cons->cflag = tty->termios.c_cflag;
+
 		if (!tty || (tty->termios.c_cflag & HUPCL))
 			uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS);
 
@@ -350,7 +353,7 @@ uart_get_baud_rate(struct uart_port *port, struct ktermios *termios,
 		 * The spd_hi, spd_vhi, spd_shi, spd_warp kludge...
 		 * Die! Die! Die!
 		 */
-		if (baud == 38400)
+		if (try == 0 && baud == 38400)
 			baud = altbaud;
 
 		/*
diff --git a/drivers/tty/serial/serial_ks8695.c b/drivers/tty/serial/serial_ks8695.c
index e1caa99e3d3b..5c79bdab985d 100644
--- a/drivers/tty/serial/serial_ks8695.c
+++ b/drivers/tty/serial/serial_ks8695.c
@@ -437,7 +437,7 @@ static void ks8695uart_set_termios(struct uart_port *port, struct ktermios *term
 	port->read_status_mask = URLS_URROE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (URLS_URFE | URLS_URPE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= URLS_URBI;
 
 	/*
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index 90a080b1f9ee..cbf501da5df3 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -702,7 +702,7 @@ serial_txx9_set_termios(struct uart_port *port, struct ktermios *termios,
 		TXX9_SIDISR_TDIS | TXX9_SIDISR_RDIS;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= TXX9_SIDISR_UFER | TXX9_SIDISR_UPER;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= TXX9_SIDISR_UBRK;
 
 	/*
diff --git a/drivers/tty/serial/sirfsoc_uart.c b/drivers/tty/serial/sirfsoc_uart.c
index b7bfe24d4ebc..020fe220d0e9 100644
--- a/drivers/tty/serial/sirfsoc_uart.c
+++ b/drivers/tty/serial/sirfsoc_uart.c
@@ -908,7 +908,7 @@ static void sirfsoc_uart_set_termios(struct uart_port *port,
 		if (termios->c_iflag & INPCK)
 			port->read_status_mask |= uint_en->sirfsoc_frm_err_en;
 	}
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 			port->read_status_mask |= uint_en->sirfsoc_rxd_brk_en;
 	if (sirfport->uart_reg->uart_type == SIRF_REAL_UART) {
 		if (termios->c_iflag & IGNPAR)
diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index 21e6e84c0df8..0ee31755cb5a 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -547,7 +547,7 @@ static void asc_set_termios(struct uart_port *port, struct ktermios *termios,
 	ascport->port.read_status_mask = ASC_RXBUF_DUMMY_OE;
 	if (termios->c_iflag & INPCK)
 		ascport->port.read_status_mask |= ASC_RXBUF_FE | ASC_RXBUF_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		ascport->port.read_status_mask |= ASC_RXBUF_DUMMY_BE;
 
 	/*
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 5faa8e905e98..e8f77606561b 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -157,6 +157,15 @@ receive_chars(struct uart_sunsab_port *up,
 	    (up->port.line == up->port.cons->index))
 		saw_console_brk = 1;
 
+	if (count == 0) {
+		if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) {
+			stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR |
+					     SAB82532_ISR0_FERR);
+			up->port.icount.brk++;
+			uart_handle_break(&up->port);
+		}
+	}
+
 	for (i = 0; i < count; i++) {
 		unsigned char ch = buf[i], flag;
 
@@ -719,7 +728,7 @@ static void sunsab_convert_to_sab(struct uart_sunsab_port *up, unsigned int cfla
 	if (iflag & INPCK)
 		up->port.read_status_mask |= (SAB82532_ISR0_PERR |
 					      SAB82532_ISR0_FERR);
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= (SAB82532_ISR1_BRK << 8);
 
 	/*
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index 9a0f24f83720..5326ae195e5f 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -834,7 +834,7 @@ sunsu_change_speed(struct uart_port *port, unsigned int cflag,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index a2c40ed287d2..a85db8b87156 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -915,7 +915,7 @@ sunzilog_convert_to_zs(struct uart_sunzilog_port *up, unsigned int cflag,
 	up->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= BRK_ABRT;
 
 	up->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index d569ca58bab6..1c52074c38df 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -936,7 +936,7 @@ static void qe_uart_set_termios(struct uart_port *port,
 	port->read_status_mask = BD_SC_EMPTY | BD_SC_OV;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= BD_SC_FR | BD_SC_PR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= BD_SC_BR;
 
 	/*
diff --git a/drivers/tty/serial/vr41xx_siu.c b/drivers/tty/serial/vr41xx_siu.c
index a63c14bc9a24..db0c8a4ab03e 100644
--- a/drivers/tty/serial/vr41xx_siu.c
+++ b/drivers/tty/serial/vr41xx_siu.c
@@ -559,7 +559,7 @@ static void siu_set_termios(struct uart_port *port, struct ktermios *new,
 	port->read_status_mask = UART_LSR_THRE | UART_LSR_OE | UART_LSR_DR;
 	if (c_iflag & INPCK)
 		port->read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (c_iflag & (BRKINT | PARMRK))
+	if (c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_LSR_BI;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/zs.c b/drivers/tty/serial/zs.c
index 6a169877109b..2b65bb7ffb8a 100644
--- a/drivers/tty/serial/zs.c
+++ b/drivers/tty/serial/zs.c
@@ -923,7 +923,7 @@ static void zs_set_termios(struct uart_port *uport, struct ktermios *termios,
 	uport->read_status_mask = Rx_OVR;
 	if (termios->c_iflag & INPCK)
 		uport->read_status_mask |= FRM_ERR | PAR_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uport->read_status_mask |= Rx_BRK;
 
 	uport->ignore_status_mask = 0;
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 765125dff20e..143deb62467d 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -60,6 +60,7 @@ void tty_buffer_lock_exclusive(struct tty_port *port)
 	atomic_inc(&buf->priority);
 	mutex_lock(&buf->lock);
 }
+EXPORT_SYMBOL_GPL(tty_buffer_lock_exclusive);
 
 void tty_buffer_unlock_exclusive(struct tty_port *port)
 {
@@ -73,6 +74,7 @@ void tty_buffer_unlock_exclusive(struct tty_port *port)
 	if (restart)
 		queue_work(system_unbound_wq, &buf->work);
 }
+EXPORT_SYMBOL_GPL(tty_buffer_unlock_exclusive);
 
 /**
  *	tty_buffer_space_avail	-	return unused buffer space
@@ -258,7 +260,11 @@ static int __tty_buffer_request_room(struct tty_port *port, size_t size,
 			n->flags = flags;
 			buf->tail = n;
 			b->commit = b->used;
-			smp_mb();
+			/* paired w/ barrier in flush_to_ldisc(); ensures the
+			 * latest commit value can be read before the head is
+			 * advanced to the next buffer
+			 */
+			smp_wmb();
 			b->next = n;
 		} else if (change)
 			size = 0;
@@ -351,14 +357,11 @@ EXPORT_SYMBOL(tty_insert_flip_string_flags);
  *	Takes any pending buffers and transfers their ownership to the
  *	ldisc side of the queue. It then schedules those characters for
  *	processing by the line discipline.
- *	Note that this function can only be used when the low_latency flag
- *	is unset. Otherwise the workqueue won't be flushed.
  */
 
 void tty_schedule_flip(struct tty_port *port)
 {
 	struct tty_bufhead *buf = &port->buf;
-	WARN_ON(port->low_latency);
 
 	buf->tail->commit = buf->tail->used;
 	schedule_work(&buf->work);
@@ -447,17 +450,24 @@ static void flush_to_ldisc(struct work_struct *work)
 
 	while (1) {
 		struct tty_buffer *head = buf->head;
+		struct tty_buffer *next;
 		int count;
 
 		/* Ldisc or user is trying to gain exclusive access */
 		if (atomic_read(&buf->priority))
 			break;
 
+		next = head->next;
+		/* paired w/ barrier in __tty_buffer_request_room();
+		 * ensures commit value read is not stale if the head
+		 * is advancing to the next buffer
+		 */
+		smp_rmb();
 		count = head->commit - head->read;
 		if (!count) {
-			if (head->next == NULL)
+			if (next == NULL)
 				break;
-			buf->head = head->next;
+			buf->head = next;
 			tty_buffer_free(port, head);
 			continue;
 		}
@@ -482,17 +492,15 @@ static void flush_to_ldisc(struct work_struct *work)
  */
 void tty_flush_to_ldisc(struct tty_struct *tty)
 {
-	if (!tty->port->low_latency)
-		flush_work(&tty->port->buf.work);
+	flush_work(&tty->port->buf.work);
 }
 
 /**
  *	tty_flip_buffer_push	-	terminal
  *	@port: tty port to push
  *
- *	Queue a push of the terminal flip buffers to the line discipline. This
- *	function must not be called from IRQ context if port->low_latency is
- *	set.
+ *	Queue a push of the terminal flip buffers to the line discipline.
+ *	Can be called from IRQ/atomic context.
  *
  *	In the event of the queue being busy for flipping the work will be
  *	held off and retried later.
@@ -500,14 +508,7 @@ void tty_flush_to_ldisc(struct tty_struct *tty)
 
 void tty_flip_buffer_push(struct tty_port *port)
 {
-	struct tty_bufhead *buf = &port->buf;
-
-	buf->tail->commit = buf->tail->used;
-
-	if (port->low_latency)
-		flush_to_ldisc(&buf->work);
-	else
-		schedule_work(&buf->work);
+	tty_schedule_flip(port);
 }
 EXPORT_SYMBOL(tty_flip_buffer_push);
 
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index c74a00ad7add..25d07412e08e 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1271,12 +1271,13 @@ static void pty_line_name(struct tty_driver *driver, int index, char *p)
  *
  *	Locking: None
  */
-static void tty_line_name(struct tty_driver *driver, int index, char *p)
+static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p)
 {
 	if (driver->flags & TTY_DRIVER_UNNUMBERED_NODE)
-		strcpy(p, driver->name);
+		return sprintf(p, "%s", driver->name);
 	else
-		sprintf(p, "%s%d", driver->name, index + driver->name_base);
+		return sprintf(p, "%s%d", driver->name,
+			       index + driver->name_base);
 }
 
 /**
@@ -1700,6 +1701,7 @@ int tty_release(struct inode *inode, struct file *filp)
 	int	pty_master, tty_closing, o_tty_closing, do_sleep;
 	int	idx;
 	char	buf[64];
+	long	timeout = 0;
 
 	if (tty_paranoia_check(tty, inode, __func__))
 		return 0;
@@ -1784,7 +1786,11 @@ int tty_release(struct inode *inode, struct file *filp)
 				__func__, tty_name(tty, buf));
 		tty_unlock_pair(tty, o_tty);
 		mutex_unlock(&tty_mutex);
-		schedule();
+		schedule_timeout_killable(timeout);
+		if (timeout < 120 * HZ)
+			timeout = 2 * timeout + 1;
+		else
+			timeout = MAX_SCHEDULE_TIMEOUT;
 	}
 
 	/*
@@ -3545,9 +3551,19 @@ static ssize_t show_cons_active(struct device *dev,
 		if (i >= ARRAY_SIZE(cs))
 			break;
 	}
-	while (i--)
-		count += sprintf(buf + count, "%s%d%c",
-				 cs[i]->name, cs[i]->index, i ? ' ':'\n');
+	while (i--) {
+		int index = cs[i]->index;
+		struct tty_driver *drv = cs[i]->device(cs[i], &index);
+
+		/* don't resolve tty0 as some programs depend on it */
+		if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR))
+			count += tty_line_name(drv, index, buf + count);
+		else
+			count += sprintf(buf + count, "%s%d",
+					 cs[i]->name, cs[i]->index);
+
+		count += sprintf(buf + count, "%c", i ? ' ':'\n');
+	}
 	console_unlock();
 
 	return count;
diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c
index 2d51d852b474..ca1123d415c5 100644
--- a/drivers/usb/chipidea/ci_hdrc_msm.c
+++ b/drivers/usb/chipidea/ci_hdrc_msm.c
@@ -20,13 +20,13 @@
 static void ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event)
 {
 	struct device *dev = ci->gadget.dev.parent;
-	int val;
 
 	switch (event) {
 	case CI_HDRC_CONTROLLER_RESET_EVENT:
 		dev_dbg(dev, "CI_HDRC_CONTROLLER_RESET_EVENT received\n");
 		writel(0, USB_AHBBURST);
 		writel(0, USB_AHBMODE);
+		usb_phy_init(ci->transceiver);
 		break;
 	case CI_HDRC_CONTROLLER_STOPPED_EVENT:
 		dev_dbg(dev, "CI_HDRC_CONTROLLER_STOPPED_EVENT received\n");
@@ -34,10 +34,7 @@ static void ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event)
 		 * Put the transceiver in non-driving mode. Otherwise host
 		 * may not detect soft-disconnection.
 		 */
-		val = usb_phy_io_read(ci->transceiver, ULPI_FUNC_CTRL);
-		val &= ~ULPI_FUNC_CTRL_OPMODE_MASK;
-		val |= ULPI_FUNC_CTRL_OPMODE_NONDRIVING;
-		usb_phy_io_write(ci->transceiver, val, ULPI_FUNC_CTRL);
+		usb_phy_notify_disconnect(ci->transceiver, USB_SPEED_UNKNOWN);
 		break;
 	default:
 		dev_dbg(dev, "unknown ci_hdrc event\n");
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 4ab2cb62dfce..86b1fd673749 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1179,8 +1179,8 @@ static int ep_enable(struct usb_ep *ep,
 
 	if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
 		cap |= QH_IOS;
-	if (hwep->num)
-		cap |= QH_ZLT;
+
+	cap |= QH_ZLT;
 	cap |= (hwep->ep.maxpacket << __ffs(QH_MAX_PKT)) & QH_MAX_PKT;
 	/*
 	 * For ISO-TX, we set mult at QH as the largest value, and use
@@ -1326,6 +1326,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
 	struct ci_hw_ep  *hwep  = container_of(ep,  struct ci_hw_ep, ep);
 	struct ci_hw_req *hwreq = container_of(req, struct ci_hw_req, req);
 	unsigned long flags;
+	struct td_node *node, *tmpnode;
 
 	if (ep == NULL || req == NULL || hwreq->req.status != -EALREADY ||
 		hwep->ep.desc == NULL || list_empty(&hwreq->queue) ||
@@ -1336,6 +1337,12 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
 
 	hw_ep_flush(hwep->ci, hwep->num, hwep->dir);
 
+	list_for_each_entry_safe(node, tmpnode, &hwreq->tds, td) {
+		dma_pool_free(hwep->td_pool, node->ptr, node->dma);
+		list_del(&node->td);
+		kfree(node);
+	}
+
 	/* pop request */
 	list_del_init(&hwreq->queue);
 
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 900f7ff805ee..d7049c393a33 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -122,13 +122,23 @@ static void acm_release_minor(struct acm *acm)
 static int acm_ctrl_msg(struct acm *acm, int request, int value,
 							void *buf, int len)
 {
-	int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
+	int retval;
+
+	retval = usb_autopm_get_interface(acm->control);
+	if (retval)
+		return retval;
+
+	retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
 		request, USB_RT_ACM, value,
 		acm->control->altsetting[0].desc.bInterfaceNumber,
 		buf, len, 5000);
+
 	dev_dbg(&acm->control->dev,
 			"%s - rq 0x%02x, val %#x, len %#x, result %d\n",
 			__func__, request, value, len, retval);
+
+	usb_autopm_put_interface(acm->control);
+
 	return retval < 0 ? retval : 0;
 }
 
@@ -496,6 +506,7 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty)
 {
 	struct acm *acm = container_of(port, struct acm, port);
 	int retval = -ENODEV;
+	int i;
 
 	dev_dbg(&acm->control->dev, "%s\n", __func__);
 
@@ -544,6 +555,8 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty)
 	return 0;
 
 error_submit_read_urbs:
+	for (i = 0; i < acm->rx_buflimit; i++)
+		usb_kill_urb(acm->read_urbs[i]);
 	acm->ctrlout = 0;
 	acm_set_control(acm, acm->ctrlout);
 error_set_control:
@@ -571,21 +584,35 @@ static void acm_port_destruct(struct tty_port *port)
 static void acm_port_shutdown(struct tty_port *port)
 {
 	struct acm *acm = container_of(port, struct acm, port);
+	struct urb *urb;
+	struct acm_wb *wb;
 	int i;
+	int pm_err;
 
 	dev_dbg(&acm->control->dev, "%s\n", __func__);
 
 	mutex_lock(&acm->mutex);
 	if (!acm->disconnected) {
-		usb_autopm_get_interface(acm->control);
+		pm_err = usb_autopm_get_interface(acm->control);
 		acm_set_control(acm, acm->ctrlout = 0);
+
+		for (;;) {
+			urb = usb_get_from_anchor(&acm->delayed);
+			if (!urb)
+				break;
+			wb = urb->context;
+			wb->use = 0;
+			usb_autopm_put_interface_async(acm->control);
+		}
+
 		usb_kill_urb(acm->ctrlurb);
 		for (i = 0; i < ACM_NW; i++)
 			usb_kill_urb(acm->wb[i].urb);
 		for (i = 0; i < acm->rx_buflimit; i++)
 			usb_kill_urb(acm->read_urbs[i]);
 		acm->control->needs_remote_wakeup = 0;
-		usb_autopm_put_interface(acm->control);
+		if (!pm_err)
+			usb_autopm_put_interface(acm->control);
 	}
 	mutex_unlock(&acm->mutex);
 }
@@ -644,14 +671,17 @@ static int acm_tty_write(struct tty_struct *tty,
 	memcpy(wb->buf, buf, count);
 	wb->len = count;
 
-	usb_autopm_get_interface_async(acm->control);
+	stat = usb_autopm_get_interface_async(acm->control);
+	if (stat) {
+		wb->use = 0;
+		spin_unlock_irqrestore(&acm->write_lock, flags);
+		return stat;
+	}
+
 	if (acm->susp_count) {
-		if (!acm->delayed_wb)
-			acm->delayed_wb = wb;
-		else
-			usb_autopm_put_interface_async(acm->control);
+		usb_anchor_urb(wb->urb, &acm->delayed);
 		spin_unlock_irqrestore(&acm->write_lock, flags);
-		return count;	/* A white lie */
+		return count;
 	}
 	usb_mark_last_busy(acm->dev);
 
@@ -935,11 +965,12 @@ static void acm_tty_set_termios(struct tty_struct *tty,
 	/* FIXME: Needs to clear unsupported bits in the termios */
 	acm->clocal = ((termios->c_cflag & CLOCAL) != 0);
 
-	if (!newline.dwDTERate) {
+	if (C_BAUD(tty) == B0) {
 		newline.dwDTERate = acm->line.dwDTERate;
 		newctrl &= ~ACM_CTRL_DTR;
-	} else
+	} else if (termios_old && (termios_old->c_cflag & CBAUD) == B0) {
 		newctrl |=  ACM_CTRL_DTR;
+	}
 
 	if (newctrl != acm->ctrlout)
 		acm_set_control(acm, acm->ctrlout = newctrl);
@@ -1138,10 +1169,11 @@ next_desc:
 	} else {
 		control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0);
 		data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0));
-		if (!control_interface || !data_interface) {
-			dev_dbg(&intf->dev, "no interfaces\n");
-			return -ENODEV;
-		}
+	}
+
+	if (!control_interface || !data_interface) {
+		dev_dbg(&intf->dev, "no interfaces\n");
+		return -ENODEV;
 	}
 
 	if (data_interface_num != call_interface_num)
@@ -1267,6 +1299,7 @@ made_compressed_probe:
 		acm->bInterval = epread->bInterval;
 	tty_port_init(&acm->port);
 	acm->port.ops = &acm_port_ops;
+	init_usb_anchor(&acm->delayed);
 
 	buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
 	if (!buf) {
@@ -1416,6 +1449,7 @@ alloc_fail8:
 				&dev_attr_wCountryCodes);
 		device_remove_file(&acm->control->dev,
 				&dev_attr_iCountryCodeRelDate);
+		kfree(acm->country_codes);
 	}
 	device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
 alloc_fail7:
@@ -1512,18 +1546,15 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 	struct acm *acm = usb_get_intfdata(intf);
 	int cnt;
 
+	spin_lock_irq(&acm->read_lock);
+	spin_lock(&acm->write_lock);
 	if (PMSG_IS_AUTO(message)) {
-		int b;
-
-		spin_lock_irq(&acm->write_lock);
-		b = acm->transmitting;
-		spin_unlock_irq(&acm->write_lock);
-		if (b)
+		if (acm->transmitting) {
+			spin_unlock(&acm->write_lock);
+			spin_unlock_irq(&acm->read_lock);
 			return -EBUSY;
+		}
 	}
-
-	spin_lock_irq(&acm->read_lock);
-	spin_lock(&acm->write_lock);
 	cnt = acm->susp_count++;
 	spin_unlock(&acm->write_lock);
 	spin_unlock_irq(&acm->read_lock);
@@ -1531,8 +1562,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 	if (cnt)
 		return 0;
 
-	if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags))
-		stop_data_traffic(acm);
+	stop_data_traffic(acm);
 
 	return 0;
 }
@@ -1540,29 +1570,24 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 static int acm_resume(struct usb_interface *intf)
 {
 	struct acm *acm = usb_get_intfdata(intf);
-	struct acm_wb *wb;
+	struct urb *urb;
 	int rv = 0;
-	int cnt;
 
 	spin_lock_irq(&acm->read_lock);
-	acm->susp_count -= 1;
-	cnt = acm->susp_count;
-	spin_unlock_irq(&acm->read_lock);
+	spin_lock(&acm->write_lock);
 
-	if (cnt)
-		return 0;
+	if (--acm->susp_count)
+		goto out;
 
 	if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) {
-		rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO);
-
-		spin_lock_irq(&acm->write_lock);
-		if (acm->delayed_wb) {
-			wb = acm->delayed_wb;
-			acm->delayed_wb = NULL;
-			spin_unlock_irq(&acm->write_lock);
-			acm_start_wb(acm, wb);
-		} else {
-			spin_unlock_irq(&acm->write_lock);
+		rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC);
+
+		for (;;) {
+			urb = usb_get_from_anchor(&acm->delayed);
+			if (!urb)
+				break;
+
+			acm_start_wb(acm, urb->context);
 		}
 
 		/*
@@ -1570,12 +1595,14 @@ static int acm_resume(struct usb_interface *intf)
 		 * do the write path at all cost
 		 */
 		if (rv < 0)
-			goto err_out;
+			goto out;
 
-		rv = acm_submit_read_urbs(acm, GFP_NOIO);
+		rv = acm_submit_read_urbs(acm, GFP_ATOMIC);
 	}
+out:
+	spin_unlock(&acm->write_lock);
+	spin_unlock_irq(&acm->read_lock);
 
-err_out:
 	return rv;
 }
 
@@ -1648,17 +1675,32 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x0572, 0x1328), /* Shiro / Aztech USB MODEM UM-3100 */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
+	{ USB_DEVICE(0x2184, 0x001c) },	/* GW Instek AFG-2225 */
 	{ USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */
 	},
 	/* Motorola H24 HSPA module: */
 	{ USB_DEVICE(0x22b8, 0x2d91) }, /* modem                                */
-	{ USB_DEVICE(0x22b8, 0x2d92) }, /* modem           + diagnostics        */
-	{ USB_DEVICE(0x22b8, 0x2d93) }, /* modem + AT port                      */
-	{ USB_DEVICE(0x22b8, 0x2d95) }, /* modem + AT port + diagnostics        */
-	{ USB_DEVICE(0x22b8, 0x2d96) }, /* modem                         + NMEA */
-	{ USB_DEVICE(0x22b8, 0x2d97) }, /* modem           + diagnostics + NMEA */
-	{ USB_DEVICE(0x22b8, 0x2d99) }, /* modem + AT port               + NMEA */
-	{ USB_DEVICE(0x22b8, 0x2d9a) }, /* modem + AT port + diagnostics + NMEA */
+	{ USB_DEVICE(0x22b8, 0x2d92),   /* modem           + diagnostics        */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d93),   /* modem + AT port                      */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d95),   /* modem + AT port + diagnostics        */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d96),   /* modem                         + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d97),   /* modem           + diagnostics + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d99),   /* modem + AT port               + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
+	{ USB_DEVICE(0x22b8, 0x2d9a),   /* modem + AT port + diagnostics + NMEA */
+	.driver_info = NO_UNION_NORMAL, /* handle only modem interface          */
+	},
 
 	{ USB_DEVICE(0x0572, 0x1329), /* Hummingbird huc56s (Conexant) */
 	.driver_info = NO_UNION_NORMAL, /* union descriptor misplaced on
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index e38dc785808f..80826f843e04 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -120,7 +120,7 @@ struct acm {
 	unsigned int throttled:1;			/* actually throttled */
 	unsigned int throttle_req:1;			/* throttle requested */
 	u8 bInterval;
-	struct acm_wb *delayed_wb;			/* write queued for a device about to be woken */
+	struct usb_anchor delayed;			/* writes queued for a device about to be woken */
 };
 
 #define CDC_DATA_INTERFACE_TYPE	0x0a
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 90e18f6fa2bb..9ca77166d37e 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -1411,7 +1411,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
 	u = (is_in ? URB_DIR_IN : URB_DIR_OUT);
 	if (uurb->flags & USBDEVFS_URB_ISO_ASAP)
 		u |= URB_ISO_ASAP;
-	if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK)
+	if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK && is_in)
 		u |= URB_SHORT_NOT_OK;
 	if (uurb->flags & USBDEVFS_URB_NO_FSBR)
 		u |= URB_NO_FSBR;
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index ab90a0156828..39c7cd6ffa4b 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -990,8 +990,7 @@ EXPORT_SYMBOL_GPL(usb_deregister);
  * it doesn't support pre_reset/post_reset/reset_resume or
  * because it doesn't support suspend/resume.
  *
- * The caller must hold @intf's device's lock, but not its pm_mutex
- * and not @intf->dev.sem.
+ * The caller must hold @intf's device's lock, but not @intf's lock.
  */
 void usb_forced_unbind_intf(struct usb_interface *intf)
 {
@@ -1004,16 +1003,37 @@ void usb_forced_unbind_intf(struct usb_interface *intf)
 	intf->needs_binding = 1;
 }
 
+/*
+ * Unbind drivers for @udev's marked interfaces.  These interfaces have
+ * the needs_binding flag set, for example by usb_resume_interface().
+ *
+ * The caller must hold @udev's device lock.
+ */
+static void unbind_marked_interfaces(struct usb_device *udev)
+{
+	struct usb_host_config	*config;
+	int			i;
+	struct usb_interface	*intf;
+
+	config = udev->actconfig;
+	if (config) {
+		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
+			intf = config->interface[i];
+			if (intf->dev.driver && intf->needs_binding)
+				usb_forced_unbind_intf(intf);
+		}
+	}
+}
+
 /* Delayed forced unbinding of a USB interface driver and scan
  * for rebinding.
  *
- * The caller must hold @intf's device's lock, but not its pm_mutex
- * and not @intf->dev.sem.
+ * The caller must hold @intf's device's lock, but not @intf's lock.
  *
  * Note: Rebinds will be skipped if a system sleep transition is in
  * progress and the PM "complete" callback hasn't occurred yet.
  */
-void usb_rebind_intf(struct usb_interface *intf)
+static void usb_rebind_intf(struct usb_interface *intf)
 {
 	int rc;
 
@@ -1030,68 +1050,66 @@ void usb_rebind_intf(struct usb_interface *intf)
 	}
 }
 
-#ifdef CONFIG_PM
-
-/* Unbind drivers for @udev's interfaces that don't support suspend/resume
- * There is no check for reset_resume here because it can be determined
- * only during resume whether reset_resume is needed.
+/*
+ * Rebind drivers to @udev's marked interfaces.  These interfaces have
+ * the needs_binding flag set.
  *
  * The caller must hold @udev's device lock.
  */
-static void unbind_no_pm_drivers_interfaces(struct usb_device *udev)
+static void rebind_marked_interfaces(struct usb_device *udev)
 {
 	struct usb_host_config	*config;
 	int			i;
 	struct usb_interface	*intf;
-	struct usb_driver	*drv;
 
 	config = udev->actconfig;
 	if (config) {
 		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
 			intf = config->interface[i];
-
-			if (intf->dev.driver) {
-				drv = to_usb_driver(intf->dev.driver);
-				if (!drv->suspend || !drv->resume)
-					usb_forced_unbind_intf(intf);
-			}
+			if (intf->needs_binding)
+				usb_rebind_intf(intf);
 		}
 	}
 }
 
-/* Unbind drivers for @udev's interfaces that failed to support reset-resume.
- * These interfaces have the needs_binding flag set by usb_resume_interface().
+/*
+ * Unbind all of @udev's marked interfaces and then rebind all of them.
+ * This ordering is necessary because some drivers claim several interfaces
+ * when they are first probed.
  *
  * The caller must hold @udev's device lock.
  */
-static void unbind_no_reset_resume_drivers_interfaces(struct usb_device *udev)
+void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev)
 {
-	struct usb_host_config	*config;
-	int			i;
-	struct usb_interface	*intf;
-
-	config = udev->actconfig;
-	if (config) {
-		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
-			intf = config->interface[i];
-			if (intf->dev.driver && intf->needs_binding)
-				usb_forced_unbind_intf(intf);
-		}
-	}
+	unbind_marked_interfaces(udev);
+	rebind_marked_interfaces(udev);
 }
 
-static void do_rebind_interfaces(struct usb_device *udev)
+#ifdef CONFIG_PM
+
+/* Unbind drivers for @udev's interfaces that don't support suspend/resume
+ * There is no check for reset_resume here because it can be determined
+ * only during resume whether reset_resume is needed.
+ *
+ * The caller must hold @udev's device lock.
+ */
+static void unbind_no_pm_drivers_interfaces(struct usb_device *udev)
 {
 	struct usb_host_config	*config;
 	int			i;
 	struct usb_interface	*intf;
+	struct usb_driver	*drv;
 
 	config = udev->actconfig;
 	if (config) {
 		for (i = 0; i < config->desc.bNumInterfaces; ++i) {
 			intf = config->interface[i];
-			if (intf->needs_binding)
-				usb_rebind_intf(intf);
+
+			if (intf->dev.driver) {
+				drv = to_usb_driver(intf->dev.driver);
+				if (!drv->suspend || !drv->resume)
+					usb_forced_unbind_intf(intf);
+			}
 		}
 	}
 }
@@ -1420,7 +1438,7 @@ int usb_resume_complete(struct device *dev)
 	 * whose needs_binding flag is set
 	 */
 	if (udev->state != USB_STATE_NOTATTACHED)
-		do_rebind_interfaces(udev);
+		rebind_marked_interfaces(udev);
 	return 0;
 }
 
@@ -1442,7 +1460,7 @@ int usb_resume(struct device *dev, pm_message_t msg)
 		pm_runtime_disable(dev);
 		pm_runtime_set_active(dev);
 		pm_runtime_enable(dev);
-		unbind_no_reset_resume_drivers_interfaces(udev);
+		unbind_marked_interfaces(udev);
 	}
 
 	/* Avoid PM error messages for devices disconnected while suspended
@@ -1783,10 +1801,13 @@ int usb_runtime_suspend(struct device *dev)
 	if (status == -EAGAIN || status == -EBUSY)
 		usb_mark_last_busy(udev);
 
-	/* The PM core reacts badly unless the return code is 0,
-	 * -EAGAIN, or -EBUSY, so always return -EBUSY on an error.
+	/*
+	 * The PM core reacts badly unless the return code is 0,
+	 * -EAGAIN, or -EBUSY, so always return -EBUSY on an error
+	 * (except for root hubs, because they don't suspend through
+	 * an upstream port like other USB devices).
 	 */
-	if (status != 0)
+	if (status != 0 && udev->parent)
 		return -EBUSY;
 	return status;
 }
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index d59d99347d54..1f02e65fe305 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -75,7 +75,7 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd,
 				PCI_SLOT(companion->devfn) != slot)
 			continue;
 		companion_hcd = pci_get_drvdata(companion);
-		if (!companion_hcd)
+		if (!companion_hcd || !companion_hcd->self.root_hub)
 			continue;
 		fn(pdev, hcd, companion, companion_hcd);
 	}
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 2518c3250750..ef6ec13b6ae5 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2057,6 +2057,8 @@ int usb_alloc_streams(struct usb_interface *interface,
 		return -EINVAL;
 	if (dev->speed != USB_SPEED_SUPER)
 		return -EINVAL;
+	if (dev->state < USB_STATE_CONFIGURED)
+		return -ENODEV;
 
 	/* Streams only apply to bulk endpoints. */
 	for (i = 0; i < num_eps; i++)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 64ea21971be2..d2bd9d7c8f4b 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -884,6 +884,25 @@ static int hub_usb3_port_disable(struct usb_hub *hub, int port1)
 	if (!hub_is_superspeed(hub->hdev))
 		return -EINVAL;
 
+	ret = hub_port_status(hub, port1, &portstatus, &portchange);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * USB controller Advanced Micro Devices, Inc. [AMD] FCH USB XHCI
+	 * Controller [1022:7814] will have spurious result making the following
+	 * usb 3.0 device hotplugging route to the 2.0 root hub and recognized
+	 * as high-speed device if we set the usb 3.0 port link state to
+	 * Disabled. Since it's already in USB_SS_PORT_LS_RX_DETECT state, we
+	 * check the state here to avoid the bug.
+	 */
+	if ((portstatus & USB_PORT_STAT_LINK_STATE) ==
+				USB_SS_PORT_LS_RX_DETECT) {
+		dev_dbg(&hub->ports[port1 - 1]->dev,
+			 "Not disabling port; link state is RxDetect\n");
+		return ret;
+	}
+
 	ret = hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_SS_DISABLED);
 	if (ret)
 		return ret;
@@ -1676,11 +1695,28 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	 * - Change autosuspend delay of hub can avoid unnecessary auto
 	 *   suspend timer for hub, also may decrease power consumption
 	 *   of USB bus.
+	 *
+	 * - If user has indicated to prevent autosuspend by passing
+	 *   usbcore.autosuspend = -1 then keep autosuspend disabled.
+	 */
+#ifdef CONFIG_PM_RUNTIME
+	if (hdev->dev.power.autosuspend_delay >= 0)
+		pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+#endif
+
+	/*
+	 * Hubs have proper suspend/resume support, except for root hubs
+	 * where the controller driver doesn't have bus_suspend and
+	 * bus_resume methods.
 	 */
-	pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+	if (hdev->parent) {		/* normal device */
+		usb_enable_autosuspend(hdev);
+	} else {			/* root hub */
+		const struct hc_driver *drv = bus_to_hcd(hdev->bus)->driver;
 
-	/* Hubs have proper suspend/resume support. */
-	usb_enable_autosuspend(hdev);
+		if (drv->bus_suspend && drv->bus_resume)
+			usb_enable_autosuspend(hdev);
+	}
 
 	if (hdev->level == MAX_TOPO_LEVEL) {
 		dev_err(&intf->dev,
@@ -1912,8 +1948,10 @@ void usb_set_device_state(struct usb_device *udev,
 					|| new_state == USB_STATE_SUSPENDED)
 				;	/* No change to wakeup settings */
 			else if (new_state == USB_STATE_CONFIGURED)
-				wakeup = udev->actconfig->desc.bmAttributes
-					 & USB_CONFIG_ATT_WAKEUP;
+				wakeup = (udev->quirks &
+					USB_QUIRK_IGNORE_REMOTE_WAKEUP) ? 0 :
+					udev->actconfig->desc.bmAttributes &
+					USB_CONFIG_ATT_WAKEUP;
 			else
 				wakeup = 0;
 		}
@@ -3144,6 +3182,43 @@ static int finish_port_resume(struct usb_device *udev)
 }
 
 /*
+ * There are some SS USB devices which take longer time for link training.
+ * XHCI specs 4.19.4 says that when Link training is successful, port
+ * sets CSC bit to 1. So if SW reads port status before successful link
+ * training, then it will not find device to be present.
+ * USB Analyzer log with such buggy devices show that in some cases
+ * device switch on the RX termination after long delay of host enabling
+ * the VBUS. In few other cases it has been seen that device fails to
+ * negotiate link training in first attempt. It has been
+ * reported till now that few devices take as long as 2000 ms to train
+ * the link after host enabling its VBUS and termination. Following
+ * routine implements a 2000 ms timeout for link training. If in a case
+ * link trains before timeout, loop will exit earlier.
+ *
+ * FIXME: If a device was connected before suspend, but was removed
+ * while system was asleep, then the loop in the following routine will
+ * only exit at timeout.
+ *
+ * This routine should only be called when persist is enabled for a SS
+ * device.
+ */
+static int wait_for_ss_port_enable(struct usb_device *udev,
+		struct usb_hub *hub, int *port1,
+		u16 *portchange, u16 *portstatus)
+{
+	int status = 0, delay_ms = 0;
+
+	while (delay_ms < 2000) {
+		if (status || *portstatus & USB_PORT_STAT_CONNECTION)
+			break;
+		msleep(20);
+		delay_ms += 20;
+		status = hub_port_status(hub, *port1, portstatus, portchange);
+	}
+	return status;
+}
+
+/*
  * usb_port_resume - re-activate a suspended usb device's upstream port
  * @udev: device to re-activate, not a root hub
  * Context: must be able to sleep; device not locked; pm locks held
@@ -3245,6 +3320,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 
 	clear_bit(port1, hub->busy_bits);
 
+	if (udev->persist_enabled && hub_is_superspeed(hub->hdev))
+		status = wait_for_ss_port_enable(udev, hub, &port1, &portchange,
+				&portstatus);
+
 	status = check_port_resume_type(udev,
 			hub, port1, status, portchange, portstatus);
 	if (status == 0)
@@ -4299,6 +4378,9 @@ check_highspeed (struct usb_hub *hub, struct usb_device *udev, int port1)
 	struct usb_qualifier_descriptor	*qual;
 	int				status;
 
+	if (udev->quirks & USB_QUIRK_DEVICE_QUALIFIER)
+		return;
+
 	qual = kmalloc (sizeof *qual, GFP_KERNEL);
 	if (qual == NULL)
 		return;
@@ -4687,9 +4769,10 @@ static void hub_events(void)
 
 		hub = list_entry(tmp, struct usb_hub, event_list);
 		kref_get(&hub->kref);
+		hdev = hub->hdev;
+		usb_get_dev(hdev);
 		spin_unlock_irq(&hub_event_lock);
 
-		hdev = hub->hdev;
 		hub_dev = hub->intfdev;
 		intf = to_usb_interface(hub_dev);
 		dev_dbg(hub_dev, "state %d ports %d chg %04x evt %04x\n",
@@ -4902,6 +4985,7 @@ static void hub_events(void)
 		usb_autopm_put_interface(intf);
  loop_disconnected:
 		usb_unlock_device(hdev);
+		usb_put_dev(hdev);
 		kref_put(&hub->kref, hub_release);
 
 	} /* end while (1) */
@@ -5340,10 +5424,11 @@ int usb_reset_device(struct usb_device *udev)
 				else if (cintf->condition ==
 						USB_INTERFACE_BOUND)
 					rebind = 1;
+				if (rebind)
+					cintf->needs_binding = 1;
 			}
-			if (ret == 0 && rebind)
-				usb_rebind_intf(cintf);
 		}
+		usb_unbind_and_rebind_marked_interfaces(udev);
 	}
 
 	usb_autosuspend_device(udev);
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 739ee8e8bdfd..b195fdb1effc 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -44,6 +44,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Microsoft Wireless Laser Mouse 6000 Receiver */
+	{ USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Microsoft LifeCam-VX700 v2.0 */
 	{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -93,6 +96,16 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x04e8, 0x6601), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
 
+	/* Elan Touchscreen */
+	{ USB_DEVICE(0x04f3, 0x0089), .driver_info =
+			USB_QUIRK_DEVICE_QUALIFIER },
+
+	{ USB_DEVICE(0x04f3, 0x009b), .driver_info =
+			USB_QUIRK_DEVICE_QUALIFIER },
+
+	{ USB_DEVICE(0x04f3, 0x016f), .driver_info =
+			USB_QUIRK_DEVICE_QUALIFIER },
+
 	/* Roland SC-8820 */
 	{ USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -160,6 +173,10 @@ static const struct usb_device_id usb_interface_quirk_list[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x046d, USB_CLASS_VIDEO, 1, 0),
 	  .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* ASUS Base Station(T100) */
+	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
 	{ }  /* terminating entry must be last */
 };
 
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 823857767a16..0923add72b59 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -55,7 +55,7 @@ extern int usb_match_one_id_intf(struct usb_device *dev,
 extern int usb_match_device(struct usb_device *dev,
 			    const struct usb_device_id *id);
 extern void usb_forced_unbind_intf(struct usb_interface *intf);
-extern void usb_rebind_intf(struct usb_interface *intf);
+extern void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev);
 
 extern int usb_hub_claim_port(struct usb_device *hdev, unsigned port,
 		struct dev_state *owner);
diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index e2c730fc9a90..b78ffc281d36 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -90,4 +90,11 @@ config USB_DWC3_VERBOSE
 	help
 	  Say Y here to enable verbose debugging messages on DWC3 Driver.
 
+config DWC3_HOST_USB3_LPM_ENABLE
+	bool "Enable USB3 LPM Capability"
+	depends on USB_DWC3_HOST=y || USB_DWC3_DUAL_ROLE=y
+	default n
+	help
+	  Select this when you want to enable USB3 LPM with dwc3 xhci host.
+
 endif
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index a49217ae3533..fc06c52ecc7e 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -61,9 +61,10 @@ void dwc3_set_mode(struct dwc3 *dwc, u32 mode)
  * dwc3_core_soft_reset - Issues core soft reset and PHY reset
  * @dwc: pointer to our context structure
  */
-static void dwc3_core_soft_reset(struct dwc3 *dwc)
+static int dwc3_core_soft_reset(struct dwc3 *dwc)
 {
 	u32		reg;
+	int		ret;
 
 	/* Before Resetting PHY, put Core in Reset */
 	reg = dwc3_readl(dwc->regs, DWC3_GCTL);
@@ -82,6 +83,15 @@ static void dwc3_core_soft_reset(struct dwc3 *dwc)
 
 	usb_phy_init(dwc->usb2_phy);
 	usb_phy_init(dwc->usb3_phy);
+	ret = phy_init(dwc->usb2_generic_phy);
+	if (ret < 0)
+		return ret;
+
+	ret = phy_init(dwc->usb3_generic_phy);
+	if (ret < 0) {
+		phy_exit(dwc->usb2_generic_phy);
+		return ret;
+	}
 	mdelay(100);
 
 	/* Clear USB3 PHY reset */
@@ -100,6 +110,8 @@ static void dwc3_core_soft_reset(struct dwc3 *dwc)
 	reg = dwc3_readl(dwc->regs, DWC3_GCTL);
 	reg &= ~DWC3_GCTL_CORESOFTRESET;
 	dwc3_writel(dwc->regs, DWC3_GCTL, reg);
+
+	return 0;
 }
 
 /**
@@ -242,6 +254,90 @@ static void dwc3_event_buffers_cleanup(struct dwc3 *dwc)
 	}
 }
 
+static int dwc3_alloc_scratch_buffers(struct dwc3 *dwc)
+{
+	if (!dwc->has_hibernation)
+		return 0;
+
+	if (!dwc->nr_scratch)
+		return 0;
+
+	dwc->scratchbuf = kmalloc_array(dwc->nr_scratch,
+			DWC3_SCRATCHBUF_SIZE, GFP_KERNEL);
+	if (!dwc->scratchbuf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int dwc3_setup_scratch_buffers(struct dwc3 *dwc)
+{
+	dma_addr_t scratch_addr;
+	u32 param;
+	int ret;
+
+	if (!dwc->has_hibernation)
+		return 0;
+
+	if (!dwc->nr_scratch)
+		return 0;
+
+	 /* should never fall here */
+	if (!WARN_ON(dwc->scratchbuf))
+		return 0;
+
+	scratch_addr = dma_map_single(dwc->dev, dwc->scratchbuf,
+			dwc->nr_scratch * DWC3_SCRATCHBUF_SIZE,
+			DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dwc->dev, scratch_addr)) {
+		dev_err(dwc->dev, "failed to map scratch buffer\n");
+		ret = -EFAULT;
+		goto err0;
+	}
+
+	dwc->scratch_addr = scratch_addr;
+
+	param = lower_32_bits(scratch_addr);
+
+	ret = dwc3_send_gadget_generic_command(dwc,
+			DWC3_DGCMD_SET_SCRATCHPAD_ADDR_LO, param);
+	if (ret < 0)
+		goto err1;
+
+	param = upper_32_bits(scratch_addr);
+
+	ret = dwc3_send_gadget_generic_command(dwc,
+			DWC3_DGCMD_SET_SCRATCHPAD_ADDR_HI, param);
+	if (ret < 0)
+		goto err1;
+
+	return 0;
+
+err1:
+	dma_unmap_single(dwc->dev, dwc->scratch_addr, dwc->nr_scratch *
+			DWC3_SCRATCHBUF_SIZE, DMA_BIDIRECTIONAL);
+
+err0:
+	return ret;
+}
+
+static void dwc3_free_scratch_buffers(struct dwc3 *dwc)
+{
+	if (!dwc->has_hibernation)
+		return;
+
+	if (!dwc->nr_scratch)
+		return;
+
+	 /* should never fall here */
+	if (!WARN_ON(dwc->scratchbuf))
+		return;
+
+	dma_unmap_single(dwc->dev, dwc->scratch_addr, dwc->nr_scratch *
+			DWC3_SCRATCHBUF_SIZE, DMA_BIDIRECTIONAL);
+	kfree(dwc->scratchbuf);
+}
+
 static void dwc3_core_num_eps(struct dwc3 *dwc)
 {
 	struct dwc3_hwparams	*parms = &dwc->hwparams;
@@ -277,6 +373,7 @@ static void dwc3_cache_hwparams(struct dwc3 *dwc)
 static int dwc3_core_init(struct dwc3 *dwc)
 {
 	unsigned long		timeout;
+	u32			hwparams4 = dwc->hwparams.hwparams4;
 	u32			reg;
 	int			ret;
 
@@ -306,7 +403,9 @@ static int dwc3_core_init(struct dwc3 *dwc)
 		cpu_relax();
 	} while (true);
 
-	dwc3_core_soft_reset(dwc);
+	ret = dwc3_core_soft_reset(dwc);
+	if (ret)
+		goto err0;
 
 	reg = dwc3_readl(dwc->regs, DWC3_GCTL);
 	reg &= ~DWC3_GCTL_SCALEDOWN_MASK;
@@ -314,7 +413,29 @@ static int dwc3_core_init(struct dwc3 *dwc)
 
 	switch (DWC3_GHWPARAMS1_EN_PWROPT(dwc->hwparams.hwparams1)) {
 	case DWC3_GHWPARAMS1_EN_PWROPT_CLK:
-		reg &= ~DWC3_GCTL_DSBLCLKGTNG;
+		/**
+		 * WORKAROUND: DWC3 revisions between 2.10a and 2.50a have an
+		 * issue which would cause xHCI compliance tests to fail.
+		 *
+		 * Because of that we cannot enable clock gating on such
+		 * configurations.
+		 *
+		 * Refers to:
+		 *
+		 * STAR#9000588375: Clock Gating, SOF Issues when ref_clk-Based
+		 * SOF/ITP Mode Used
+		 */
+		if ((dwc->dr_mode == USB_DR_MODE_HOST ||
+				dwc->dr_mode == USB_DR_MODE_OTG) &&
+				(dwc->revision >= DWC3_REVISION_210A &&
+				dwc->revision <= DWC3_REVISION_250A))
+			reg |= DWC3_GCTL_DSBLCLKGTNG | DWC3_GCTL_SOFITPSYNC;
+		else
+			reg &= ~DWC3_GCTL_DSBLCLKGTNG;
+		break;
+	case DWC3_GHWPARAMS1_EN_PWROPT_HIB:
+		/* enable hibernation here */
+		dwc->nr_scratch = DWC3_GHWPARAMS4_HIBER_SCRATCHBUFS(hwparams4);
 		break;
 	default:
 		dev_dbg(dwc->dev, "No power optimization available\n");
@@ -333,16 +454,34 @@ static int dwc3_core_init(struct dwc3 *dwc)
 
 	dwc3_writel(dwc->regs, DWC3_GCTL, reg);
 
+	ret = dwc3_alloc_scratch_buffers(dwc);
+	if (ret)
+		goto err1;
+
+	ret = dwc3_setup_scratch_buffers(dwc);
+	if (ret)
+		goto err2;
+
 	return 0;
 
+err2:
+	dwc3_free_scratch_buffers(dwc);
+
+err1:
+	usb_phy_shutdown(dwc->usb2_phy);
+	usb_phy_shutdown(dwc->usb3_phy);
+
 err0:
 	return ret;
 }
 
 static void dwc3_core_exit(struct dwc3 *dwc)
 {
+	dwc3_free_scratch_buffers(dwc);
 	usb_phy_shutdown(dwc->usb2_phy);
 	usb_phy_shutdown(dwc->usb3_phy);
+	phy_exit(dwc->usb2_generic_phy);
+	phy_exit(dwc->usb3_generic_phy);
 }
 
 #define DWC3_ALIGN_MASK		(16 - 1)
@@ -411,32 +550,52 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	if (IS_ERR(dwc->usb2_phy)) {
 		ret = PTR_ERR(dwc->usb2_phy);
-
-		/*
-		 * if -ENXIO is returned, it means PHY layer wasn't
-		 * enabled, so it makes no sense to return -EPROBE_DEFER
-		 * in that case, since no PHY driver will ever probe.
-		 */
-		if (ret == -ENXIO)
+		if (ret == -ENXIO || ret == -ENODEV) {
+			dwc->usb2_phy = NULL;
+		} else if (ret == -EPROBE_DEFER) {
 			return ret;
-
-		dev_err(dev, "no usb2 phy configured\n");
-		return -EPROBE_DEFER;
+		} else {
+			dev_err(dev, "no usb2 phy configured\n");
+			return ret;
+		}
 	}
 
 	if (IS_ERR(dwc->usb3_phy)) {
 		ret = PTR_ERR(dwc->usb3_phy);
+		if (ret == -ENXIO || ret == -ENODEV) {
+			dwc->usb3_phy = NULL;
+		} else if (ret == -EPROBE_DEFER) {
+			return ret;
+		} else {
+			dev_err(dev, "no usb3 phy configured\n");
+			return ret;
+		}
+	}
 
-		/*
-		 * if -ENXIO is returned, it means PHY layer wasn't
-		 * enabled, so it makes no sense to return -EPROBE_DEFER
-		 * in that case, since no PHY driver will ever probe.
-		 */
-		if (ret == -ENXIO)
+	dwc->usb2_generic_phy = devm_phy_get(dev, "usb2-phy");
+	if (IS_ERR(dwc->usb2_generic_phy)) {
+		ret = PTR_ERR(dwc->usb2_generic_phy);
+		if (ret == -ENOSYS || ret == -ENODEV) {
+			dwc->usb2_generic_phy = NULL;
+		} else if (ret == -EPROBE_DEFER) {
 			return ret;
+		} else {
+			dev_err(dev, "no usb2 phy configured\n");
+			return ret;
+		}
+	}
 
-		dev_err(dev, "no usb3 phy configured\n");
-		return -EPROBE_DEFER;
+	dwc->usb3_generic_phy = devm_phy_get(dev, "usb3-phy");
+	if (IS_ERR(dwc->usb3_generic_phy)) {
+		ret = PTR_ERR(dwc->usb3_generic_phy);
+		if (ret == -ENOSYS || ret == -ENODEV) {
+			dwc->usb3_generic_phy = NULL;
+		} else if (ret == -EPROBE_DEFER) {
+			return ret;
+		} else {
+			dev_err(dev, "no usb3 phy configured\n");
+			return ret;
+		}
 	}
 
 	dwc->xhci_resources[0].start = res->start;
@@ -479,6 +638,14 @@ static int dwc3_probe(struct platform_device *pdev)
 		goto err0;
 	}
 
+	if (IS_ENABLED(CONFIG_USB_DWC3_HOST))
+		dwc->dr_mode = USB_DR_MODE_HOST;
+	else if (IS_ENABLED(CONFIG_USB_DWC3_GADGET))
+		dwc->dr_mode = USB_DR_MODE_PERIPHERAL;
+
+	if (dwc->dr_mode == USB_DR_MODE_UNKNOWN)
+		dwc->dr_mode = USB_DR_MODE_OTG;
+
 	ret = dwc3_core_init(dwc);
 	if (ret) {
 		dev_err(dev, "failed to initialize core\n");
@@ -487,21 +654,20 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	usb_phy_set_suspend(dwc->usb2_phy, 0);
 	usb_phy_set_suspend(dwc->usb3_phy, 0);
+	ret = phy_power_on(dwc->usb2_generic_phy);
+	if (ret < 0)
+		goto err1;
+
+	ret = phy_power_on(dwc->usb3_generic_phy);
+	if (ret < 0)
+		goto err_usb2phy_power;
 
 	ret = dwc3_event_buffers_setup(dwc);
 	if (ret) {
 		dev_err(dwc->dev, "failed to setup event buffers\n");
-		goto err1;
+		goto err_usb3phy_power;
 	}
 
-	if (IS_ENABLED(CONFIG_USB_DWC3_HOST))
-		dwc->dr_mode = USB_DR_MODE_HOST;
-	else if (IS_ENABLED(CONFIG_USB_DWC3_GADGET))
-		dwc->dr_mode = USB_DR_MODE_PERIPHERAL;
-
-	if (dwc->dr_mode == USB_DR_MODE_UNKNOWN)
-		dwc->dr_mode = USB_DR_MODE_OTG;
-
 	switch (dwc->dr_mode) {
 	case USB_DR_MODE_PERIPHERAL:
 		dwc3_set_mode(dwc, DWC3_GCTL_PRTCAP_DEVICE);
@@ -568,6 +734,12 @@ err3:
 err2:
 	dwc3_event_buffers_cleanup(dwc);
 
+err_usb3phy_power:
+	phy_power_off(dwc->usb3_generic_phy);
+
+err_usb2phy_power:
+	phy_power_off(dwc->usb2_generic_phy);
+
 err1:
 	usb_phy_set_suspend(dwc->usb2_phy, 1);
 	usb_phy_set_suspend(dwc->usb3_phy, 1);
@@ -583,12 +755,6 @@ static int dwc3_remove(struct platform_device *pdev)
 {
 	struct dwc3	*dwc = platform_get_drvdata(pdev);
 
-	usb_phy_set_suspend(dwc->usb2_phy, 1);
-	usb_phy_set_suspend(dwc->usb3_phy, 1);
-
-	pm_runtime_put_sync(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
-
 	dwc3_debugfs_exit(dwc);
 
 	switch (dwc->dr_mode) {
@@ -609,8 +775,18 @@ static int dwc3_remove(struct platform_device *pdev)
 
 	dwc3_event_buffers_cleanup(dwc);
 	dwc3_free_event_buffers(dwc);
+
+	usb_phy_set_suspend(dwc->usb2_phy, 1);
+	usb_phy_set_suspend(dwc->usb3_phy, 1);
+
+	phy_power_off(dwc->usb2_generic_phy);
+	phy_power_off(dwc->usb3_generic_phy);
+
 	dwc3_core_exit(dwc);
 
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
 	return 0;
 }
 
@@ -645,6 +821,7 @@ static void dwc3_complete(struct device *dev)
 
 	spin_lock_irqsave(&dwc->lock, flags);
 
+	dwc3_event_buffers_setup(dwc);
 	switch (dwc->dr_mode) {
 	case USB_DR_MODE_PERIPHERAL:
 	case USB_DR_MODE_OTG:
@@ -652,7 +829,6 @@ static void dwc3_complete(struct device *dev)
 		/* FALLTHROUGH */
 	case USB_DR_MODE_HOST:
 	default:
-		dwc3_event_buffers_setup(dwc);
 		break;
 	}
 
@@ -682,6 +858,8 @@ static int dwc3_suspend(struct device *dev)
 
 	usb_phy_shutdown(dwc->usb3_phy);
 	usb_phy_shutdown(dwc->usb2_phy);
+	phy_exit(dwc->usb2_generic_phy);
+	phy_exit(dwc->usb3_generic_phy);
 
 	return 0;
 }
@@ -690,9 +868,17 @@ static int dwc3_resume(struct device *dev)
 {
 	struct dwc3	*dwc = dev_get_drvdata(dev);
 	unsigned long	flags;
+	int		ret;
 
 	usb_phy_init(dwc->usb3_phy);
 	usb_phy_init(dwc->usb2_phy);
+	ret = phy_init(dwc->usb2_generic_phy);
+	if (ret < 0)
+		return ret;
+
+	ret = phy_init(dwc->usb3_generic_phy);
+	if (ret < 0)
+		goto err_usb2phy_init;
 
 	spin_lock_irqsave(&dwc->lock, flags);
 
@@ -716,6 +902,11 @@ static int dwc3_resume(struct device *dev)
 	pm_runtime_enable(dev);
 
 	return 0;
+
+err_usb2phy_init:
+	phy_exit(dwc->usb2_generic_phy);
+
+	return ret;
 }
 
 static const struct dev_pm_ops dwc3_dev_pm_ops = {
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index f8af8d44af85..b451900ad5c7 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -31,11 +31,14 @@
 #include <linux/usb/gadget.h>
 #include <linux/usb/otg.h>
 
+#include <linux/phy/phy.h>
+
 /* Global constants */
 #define DWC3_EP0_BOUNCE_SIZE	512
 #define DWC3_ENDPOINTS_NUM	32
 #define DWC3_XHCI_RESOURCES_NUM	2
 
+#define DWC3_SCRATCHBUF_SIZE	4096	/* each buffer is assumed to be 4KiB */
 #define DWC3_EVENT_SIZE		4	/* bytes */
 #define DWC3_EVENT_MAX_NUM	64	/* 2 events/endpoint */
 #define DWC3_EVENT_BUFFERS_SIZE	(DWC3_EVENT_SIZE * DWC3_EVENT_MAX_NUM)
@@ -157,6 +160,7 @@
 #define DWC3_GCTL_PRTCAP_OTG	3
 
 #define DWC3_GCTL_CORESOFTRESET		(1 << 11)
+#define DWC3_GCTL_SOFITPSYNC		(1 << 10)
 #define DWC3_GCTL_SCALEDOWN(n)		((n) << 4)
 #define DWC3_GCTL_SCALEDOWN_MASK	DWC3_GCTL_SCALEDOWN(3)
 #define DWC3_GCTL_DISSCRAMBLE		(1 << 3)
@@ -598,6 +602,7 @@ struct dwc3_scratchpad_array {
  * @ep0_trb: dma address of ep0_trb
  * @ep0_usb_req: dummy req used while handling STD USB requests
  * @ep0_bounce_addr: dma address of ep0_bounce
+ * @scratch_addr: dma address of scratchbuf
  * @lock: for synchronizing
  * @dev: pointer to our struct device
  * @xhci: pointer to our xHCI child
@@ -606,6 +611,7 @@ struct dwc3_scratchpad_array {
  * @gadget_driver: pointer to the gadget driver
  * @regs: base address for our registers
  * @regs_size: address space size
+ * @nr_scratch: number of scratch buffers
  * @num_event_buffers: calculated number of event buffers
  * @u1u2: only used on revisions <1.83a for workaround
  * @maximum_speed: maximum speed requested (mainly for testing purposes)
@@ -613,16 +619,10 @@ struct dwc3_scratchpad_array {
  * @dr_mode: requested mode of operation
  * @usb2_phy: pointer to USB2 PHY
  * @usb3_phy: pointer to USB3 PHY
+ * @usb2_generic_phy: pointer to USB2 PHY
+ * @usb3_generic_phy: pointer to USB3 PHY
  * @dcfg: saved contents of DCFG register
  * @gctl: saved contents of GCTL register
- * @is_selfpowered: true when we are selfpowered
- * @three_stage_setup: set if we perform a three phase setup
- * @ep0_bounced: true when we used bounce buffer
- * @ep0_expect_in: true when we expect a DATA IN transfer
- * @start_config_issued: true when StartConfig command has been issued
- * @setup_packet_pending: true when there's a Setup Packet in FIFO. Workaround
- * @needs_fifo_resize: not all users might want fifo resizing, flag it
- * @resize_fifos: tells us it's ok to reconfigure our TxFIFO sizes.
  * @isoch_delay: wValue from Set Isochronous Delay request;
  * @u2sel: parameter from Set SEL request.
  * @u2pel: parameter from Set SEL request.
@@ -637,15 +637,31 @@ struct dwc3_scratchpad_array {
  * @mem: points to start of memory which is used for this struct.
  * @hwparams: copy of hwparams registers
  * @root: debugfs root folder pointer
+ * @regset: debugfs pointer to regdump file
+ * @test_mode: true when we're entering a USB test mode
+ * @test_mode_nr: test feature selector
+ * @delayed_status: true when gadget driver asks for delayed status
+ * @ep0_bounced: true when we used bounce buffer
+ * @ep0_expect_in: true when we expect a DATA IN transfer
+ * @has_hibernation: true when dwc3 was configured with Hibernation
+ * @is_selfpowered: true when we are selfpowered
+ * @needs_fifo_resize: not all users might want fifo resizing, flag it
+ * @pullups_connected: true when Run/Stop bit is set
+ * @resize_fifos: tells us it's ok to reconfigure our TxFIFO sizes.
+ * @setup_packet_pending: true when there's a Setup Packet in FIFO. Workaround
+ * @start_config_issued: true when StartConfig command has been issued
+ * @three_stage_setup: set if we perform a three phase setup
  */
 struct dwc3 {
 	struct usb_ctrlrequest	*ctrl_req;
 	struct dwc3_trb		*ep0_trb;
 	void			*ep0_bounce;
+	void			*scratchbuf;
 	u8			*setup_buf;
 	dma_addr_t		ctrl_req_addr;
 	dma_addr_t		ep0_trb_addr;
 	dma_addr_t		ep0_bounce_addr;
+	dma_addr_t		scratch_addr;
 	struct dwc3_request	ep0_usb_req;
 
 	/* device lock */
@@ -665,6 +681,9 @@ struct dwc3 {
 	struct usb_phy		*usb2_phy;
 	struct usb_phy		*usb3_phy;
 
+	struct phy		*usb2_generic_phy;
+	struct phy		*usb3_generic_phy;
+
 	void __iomem		*regs;
 	size_t			regs_size;
 
@@ -674,6 +693,7 @@ struct dwc3 {
 	u32			dcfg;
 	u32			gctl;
 
+	u32			nr_scratch;
 	u32			num_event_buffers;
 	u32			u1u2;
 	u32			maximum_speed;
@@ -696,17 +716,6 @@ struct dwc3 {
 #define DWC3_REVISION_240A	0x5533240a
 #define DWC3_REVISION_250A	0x5533250a
 
-	unsigned		is_selfpowered:1;
-	unsigned		three_stage_setup:1;
-	unsigned		ep0_bounced:1;
-	unsigned		ep0_expect_in:1;
-	unsigned		start_config_issued:1;
-	unsigned		setup_packet_pending:1;
-	unsigned		delayed_status:1;
-	unsigned		needs_fifo_resize:1;
-	unsigned		resize_fifos:1;
-	unsigned		pullups_connected:1;
-
 	enum dwc3_ep0_next	ep0_next_event;
 	enum dwc3_ep0_state	ep0state;
 	enum dwc3_link_state	link_state;
@@ -730,6 +739,18 @@ struct dwc3 {
 
 	u8			test_mode;
 	u8			test_mode_nr;
+
+	unsigned		delayed_status:1;
+	unsigned		ep0_bounced:1;
+	unsigned		ep0_expect_in:1;
+	unsigned		has_hibernation:1;
+	unsigned		is_selfpowered:1;
+	unsigned		needs_fifo_resize:1;
+	unsigned		pullups_connected:1;
+	unsigned		resize_fifos:1;
+	unsigned		setup_packet_pending:1;
+	unsigned		start_config_issued:1;
+	unsigned		three_stage_setup:1;
 };
 
 /* -------------------------------------------------------------------------- */
@@ -815,15 +836,15 @@ struct dwc3_event_depevt {
  *	12	- VndrDevTstRcved
  * @reserved15_12: Reserved, not used
  * @event_info: Information about this event
- * @reserved31_24: Reserved, not used
+ * @reserved31_25: Reserved, not used
  */
 struct dwc3_event_devt {
 	u32	one_bit:1;
 	u32	device_event:7;
 	u32	type:4;
 	u32	reserved15_12:4;
-	u32	event_info:8;
-	u32	reserved31_24:8;
+	u32	event_info:9;
+	u32	reserved31_25:7;
 } __packed;
 
 /**
@@ -856,6 +877,19 @@ union dwc3_event {
 	struct dwc3_event_gevt		gevt;
 };
 
+/**
+ * struct dwc3_gadget_ep_cmd_params - representation of endpoint command
+ * parameters
+ * @param2: third parameter
+ * @param1: second parameter
+ * @param0: first parameter
+ */
+struct dwc3_gadget_ep_cmd_params {
+	u32	param2;
+	u32	param1;
+	u32	param0;
+};
+
 /*
  * DWC3 Features to be used as Driver Data
  */
@@ -881,11 +915,31 @@ static inline void dwc3_host_exit(struct dwc3 *dwc)
 #if IS_ENABLED(CONFIG_USB_DWC3_GADGET) || IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE)
 int dwc3_gadget_init(struct dwc3 *dwc);
 void dwc3_gadget_exit(struct dwc3 *dwc);
+int dwc3_gadget_set_test_mode(struct dwc3 *dwc, int mode);
+int dwc3_gadget_get_link_state(struct dwc3 *dwc);
+int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state);
+int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
+		unsigned cmd, struct dwc3_gadget_ep_cmd_params *params);
+int dwc3_send_gadget_generic_command(struct dwc3 *dwc, int cmd, u32 param);
 #else
 static inline int dwc3_gadget_init(struct dwc3 *dwc)
 { return 0; }
 static inline void dwc3_gadget_exit(struct dwc3 *dwc)
 { }
+static inline int dwc3_gadget_set_test_mode(struct dwc3 *dwc, int mode)
+{ return 0; }
+static inline int dwc3_gadget_get_link_state(struct dwc3 *dwc)
+{ return 0; }
+static inline int dwc3_gadget_set_link_state(struct dwc3 *dwc,
+		enum dwc3_link_state state)
+{ return 0; }
+
+static inline int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
+		unsigned cmd, struct dwc3_gadget_ep_cmd_params *params)
+{ return 0; }
+static inline int dwc3_send_gadget_generic_command(struct dwc3 *dwc,
+		int cmd, u32 param)
+{ return 0; }
 #endif
 
 /* power management interface */
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index b269dbd47fc4..2a6841c95b64 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -582,9 +582,9 @@ static int dwc3_omap_remove(struct platform_device *pdev)
 	if (omap->extcon_id_dev.edev)
 		extcon_unregister_interest(&omap->extcon_id_dev);
 	dwc3_omap_disable_irqs(omap);
+	device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core);
 
 	return 0;
 }
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 21a352079bc2..0985ff715c0c 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -251,7 +251,7 @@ static void dwc3_ep0_stall_and_restart(struct dwc3 *dwc)
 
 	/* stall is always issued on EP0 */
 	dep = dwc->eps[0];
-	__dwc3_gadget_ep_set_halt(dep, 1);
+	__dwc3_gadget_ep_set_halt(dep, 1, false);
 	dep->flags = DWC3_EP_ENABLED;
 	dwc->delayed_status = false;
 
@@ -461,7 +461,7 @@ static int dwc3_ep0_handle_feature(struct dwc3 *dwc,
 				return -EINVAL;
 			if (set == 0 && (dep->flags & DWC3_EP_WEDGE))
 				break;
-			ret = __dwc3_gadget_ep_set_halt(dep, set);
+			ret = __dwc3_gadget_ep_set_halt(dep, set, true);
 			if (ret)
 				return -EINVAL;
 			break;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 2da0a5a2803a..5bdbcff83bd5 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -532,12 +532,11 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep,
 		if (!usb_endpoint_xfer_isoc(desc))
 			return 0;
 
-		memset(&trb_link, 0, sizeof(trb_link));
-
 		/* Link TRB for ISOC. The HWO bit is never reset */
 		trb_st_hw = &dep->trb_pool[0];
 
 		trb_link = &dep->trb_pool[DWC3_TRB_NUM - 1];
+		memset(trb_link, 0, sizeof(*trb_link));
 
 		trb_link->bpl = lower_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw));
 		trb_link->bph = upper_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw));
@@ -586,6 +585,10 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep)
 
 	dwc3_remove_requests(dwc, dep);
 
+	/* make sure HW endpoint isn't stalled */
+	if (dep->flags & DWC3_EP_STALL)
+		__dwc3_gadget_ep_set_halt(dep, 0, false);
+
 	reg = dwc3_readl(dwc->regs, DWC3_DALEPENA);
 	reg &= ~DWC3_DALEPENA_EP(dep->number);
 	dwc3_writel(dwc->regs, DWC3_DALEPENA, reg);
@@ -1182,7 +1185,7 @@ out0:
 	return ret;
 }
 
-int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value)
+int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
 {
 	struct dwc3_gadget_ep_cmd_params	params;
 	struct dwc3				*dwc = dep->dwc;
@@ -1191,6 +1194,14 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value)
 	memset(&params, 0x00, sizeof(params));
 
 	if (value) {
+		if (!protocol && ((dep->direction && dep->flags & DWC3_EP_BUSY) ||
+				(!list_empty(&dep->req_queued) ||
+				 !list_empty(&dep->request_list)))) {
+			dev_dbg(dwc->dev, "%s: pending request, cannot halt\n",
+					dep->name);
+			return -EAGAIN;
+		}
+
 		ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
 			DWC3_DEPCMD_SETSTALL, &params);
 		if (ret)
@@ -1230,7 +1241,7 @@ static int dwc3_gadget_ep_set_halt(struct usb_ep *ep, int value)
 		goto out;
 	}
 
-	ret = __dwc3_gadget_ep_set_halt(dep, value);
+	ret = __dwc3_gadget_ep_set_halt(dep, value, false);
 out:
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -1250,7 +1261,7 @@ static int dwc3_gadget_ep_set_wedge(struct usb_ep *ep)
 	if (dep->number == 0 || dep->number == 1)
 		return dwc3_gadget_ep0_set_halt(ep, 1);
 	else
-		return dwc3_gadget_ep_set_halt(ep, 1);
+		return __dwc3_gadget_ep_set_halt(dep, 1, false);
 }
 
 /* -------------------------------------------------------------------------- */
@@ -2381,6 +2392,30 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc,
 	dev_vdbg(dwc->dev, "%s link %d\n", __func__, dwc->link_state);
 }
 
+static void dwc3_gadget_hibernation_interrupt(struct dwc3 *dwc,
+		unsigned int evtinfo)
+{
+	unsigned int is_ss = evtinfo & BIT(4);
+
+	/**
+	 * WORKAROUND: DWC3 revison 2.20a with hibernation support
+	 * have a known issue which can cause USB CV TD.9.23 to fail
+	 * randomly.
+	 *
+	 * Because of this issue, core could generate bogus hibernation
+	 * events which SW needs to ignore.
+	 *
+	 * Refers to:
+	 *
+	 * STAR#9000546576: Device Mode Hibernation: Issue in USB 2.0
+	 * Device Fallback from SuperSpeed
+	 */
+	if (is_ss ^ (dwc->speed == USB_SPEED_SUPER))
+		return;
+
+	/* enter hibernation here */
+}
+
 static void dwc3_gadget_interrupt(struct dwc3 *dwc,
 		const struct dwc3_event_devt *event)
 {
@@ -2397,6 +2432,13 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc,
 	case DWC3_DEVICE_EVENT_WAKEUP:
 		dwc3_gadget_wakeup_interrupt(dwc);
 		break;
+	case DWC3_DEVICE_EVENT_HIBER_REQ:
+		if (dev_WARN_ONCE(dwc->dev, !dwc->has_hibernation,
+					"unexpected hibernation event\n"))
+			break;
+
+		dwc3_gadget_hibernation_interrupt(dwc, event->event_info);
+		break;
 	case DWC3_DEVICE_EVENT_LINK_STATUS_CHANGE:
 		dwc3_gadget_linksts_change_interrupt(dwc, event->event_info);
 		break;
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index febe1aa7b714..ac62558231be 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -56,12 +56,6 @@ struct dwc3;
 /* DEPXFERCFG parameter 0 */
 #define DWC3_DEPXFERCFG_NUM_XFER_RES(n)	((n) & 0xffff)
 
-struct dwc3_gadget_ep_cmd_params {
-	u32	param2;
-	u32	param1;
-	u32	param0;
-};
-
 /* -------------------------------------------------------------------------- */
 
 #define to_dwc3_request(r)	(container_of(r, struct dwc3_request, request))
@@ -85,19 +79,13 @@ static inline void dwc3_gadget_move_request_queued(struct dwc3_request *req)
 void dwc3_gadget_giveback(struct dwc3_ep *dep, struct dwc3_request *req,
 		int status);
 
-int dwc3_gadget_set_test_mode(struct dwc3 *dwc, int mode);
-int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state);
-
 void dwc3_ep0_interrupt(struct dwc3 *dwc,
 		const struct dwc3_event_depevt *event);
 void dwc3_ep0_out_start(struct dwc3 *dwc);
 int dwc3_gadget_ep0_set_halt(struct usb_ep *ep, int value);
 int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request,
 		gfp_t gfp_flags);
-int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value);
-int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
-		unsigned cmd, struct dwc3_gadget_ep_cmd_params *params);
-int dwc3_send_gadget_generic_command(struct dwc3 *dwc, int cmd, u32 param);
+int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol);
 
 /**
  * dwc3_gadget_ep_get_transfer_index - Gets transfer index from HW
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 32db328cc769..dcb8ca084598 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -16,12 +16,14 @@
  */
 
 #include <linux/platform_device.h>
+#include <linux/usb/xhci_pdriver.h>
 
 #include "core.h"
 
 int dwc3_host_init(struct dwc3 *dwc)
 {
 	struct platform_device	*xhci;
+	struct usb_xhci_pdata	pdata;
 	int			ret;
 
 	xhci = platform_device_alloc("xhci-hcd", PLATFORM_DEVID_AUTO);
@@ -46,6 +48,18 @@ int dwc3_host_init(struct dwc3 *dwc)
 		goto err1;
 	}
 
+	memset(&pdata, 0, sizeof(pdata));
+
+#ifdef CONFIG_DWC3_HOST_USB3_LPM_ENABLE
+	pdata.usb3_lpm_capable = 1;
+#endif
+
+	ret = platform_device_add_data(xhci, &pdata, sizeof(pdata));
+	if (ret) {
+		dev_err(dwc->dev, "couldn't add platform data to xHCI device\n");
+		goto err1;
+	}
+
 	ret = platform_device_add(xhci);
 	if (ret) {
 		dev_err(dwc->dev, "failed to register xHCI device\n");
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 8154165aa601..fd13ef0a96c9 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -445,7 +445,7 @@ config USB_GOKU
 	   gadget drivers to also be dynamically linked.
 
 config USB_EG20T
-	tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
+	tristate "Intel QUARK X1000/EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
 	depends on PCI
 	help
 	  This is a USB device driver for EG20T PCH.
@@ -466,6 +466,7 @@ config USB_EG20T
 	  ML7213/ML7831 is companion chip for Intel Atom E6xx series.
 	  ML7213/ML7831 is completely compatible for Intel EG20T PCH.
 
+	  This driver can be used with Intel's Quark X1000 SOC platform
 #
 # LAST -- dummy/emulated controller
 #
diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c
index cea8c20a1425..1926925a52a9 100644
--- a/drivers/usb/gadget/at91_udc.c
+++ b/drivers/usb/gadget/at91_udc.c
@@ -1709,16 +1709,6 @@ static int at91udc_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	if (pdev->num_resources != 2) {
-		DBG("invalid num_resources\n");
-		return -ENODEV;
-	}
-	if ((pdev->resource[0].flags != IORESOURCE_MEM)
-			|| (pdev->resource[1].flags != IORESOURCE_IRQ)) {
-		DBG("invalid resource type\n");
-		return -ENODEV;
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -ENXIO;
diff --git a/drivers/usb/gadget/atmel_usba_udc.c b/drivers/usb/gadget/atmel_usba_udc.c
index 52771d4c44bc..167843de2d8a 100644
--- a/drivers/usb/gadget/atmel_usba_udc.c
+++ b/drivers/usb/gadget/atmel_usba_udc.c
@@ -1827,12 +1827,12 @@ static int atmel_usba_stop(struct usb_gadget *gadget,
 	toggle_bias(0);
 	usba_writel(udc, CTRL, USBA_DISABLE_MASK);
 
-	udc->driver = NULL;
-
 	clk_disable_unprepare(udc->hclk);
 	clk_disable_unprepare(udc->pclk);
 
-	DBG(DBG_GADGET, "unregistered driver `%s'\n", driver->driver.name);
+	DBG(DBG_GADGET, "unregistered driver `%s'\n", udc->driver->driver.name);
+
+	udc->driver = NULL;
 
 	return 0;
 }
diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c
index ab1065afbbd0..3384486c2884 100644
--- a/drivers/usb/gadget/f_acm.c
+++ b/drivers/usb/gadget/f_acm.c
@@ -430,11 +430,12 @@ static int acm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (acm->notify->driver_data) {
 			VDBG(cdev, "reset acm control interface %d\n", intf);
 			usb_ep_disable(acm->notify);
-		} else {
-			VDBG(cdev, "init acm ctrl interface %d\n", intf);
+		}
+
+		if (!acm->notify->desc)
 			if (config_ep_by_speed(cdev->gadget, f, acm->notify))
 				return -EINVAL;
-		}
+
 		usb_ep_enable(acm->notify);
 		acm->notify->driver_data = acm;
 
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 2b4334394076..afd0a159fe61 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1227,11 +1227,13 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev)
 	ffs->ep0req->context = ffs;
 
 	lang = ffs->stringtabs;
-	for (lang = ffs->stringtabs; *lang; ++lang) {
-		struct usb_string *str = (*lang)->strings;
-		int id = first_id;
-		for (; str->s; ++id, ++str)
-			str->id = id;
+	if (lang) {
+		for (; *lang; ++lang) {
+			struct usb_string *str = (*lang)->strings;
+			int id = first_id;
+			for (; str->s; ++id, ++str)
+				str->id = id;
+		}
 	}
 
 	ffs->gadget = cdev->gadget;
@@ -1993,8 +1995,6 @@ static inline struct f_fs_opts *ffs_do_functionfs_bind(struct usb_function *f,
 	func->conf = c;
 	func->gadget = c->cdev->gadget;
 
-	ffs_data_get(func->ffs);
-
 	/*
 	 * in drivers/usb/gadget/configfs.c:configfs_composite_bind()
 	 * configurations are bound in sequence with list_for_each_entry,
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index b94c049ab0d0..4ac9e9928d67 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -1504,7 +1504,7 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 		}
 		break;
 
-#ifndef	CONFIG_USB_GADGET_PXA25X
+#ifndef	CONFIG_USB_PXA25X
 	/* PXA automagically handles this request too */
 	case USB_REQ_GET_CONFIGURATION:
 		if (ctrl->bRequestType != 0x80)
diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c
index eb8c3bedb57a..460d953c91b6 100644
--- a/drivers/usb/gadget/pch_udc.c
+++ b/drivers/usb/gadget/pch_udc.c
@@ -343,6 +343,7 @@ struct pch_vbus_gpio_data {
  * @setup_data:		Received setup data
  * @phys_addr:		of device memory
  * @base_addr:		for mapped device memory
+ * @bar:		Indicates which PCI BAR for USB regs
  * @irq:		IRQ line for the device
  * @cfg_data:		current cfg, intf, and alt in use
  * @vbus_gpio:		GPIO informaton for detecting VBUS
@@ -370,14 +371,17 @@ struct pch_udc_dev {
 	struct usb_ctrlrequest		setup_data;
 	unsigned long			phys_addr;
 	void __iomem			*base_addr;
+	unsigned			bar;
 	unsigned			irq;
 	struct pch_udc_cfg_data		cfg_data;
 	struct pch_vbus_gpio_data	vbus_gpio;
 };
 #define to_pch_udc(g)	(container_of((g), struct pch_udc_dev, gadget))
 
+#define PCH_UDC_PCI_BAR_QUARK_X1000	0
 #define PCH_UDC_PCI_BAR			1
 #define PCI_DEVICE_ID_INTEL_EG20T_UDC	0x8808
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC	0x0939
 #define PCI_VENDOR_ID_ROHM		0x10DB
 #define PCI_DEVICE_ID_ML7213_IOH_UDC	0x801D
 #define PCI_DEVICE_ID_ML7831_IOH_UDC	0x8808
@@ -3076,7 +3080,7 @@ static void pch_udc_remove(struct pci_dev *pdev)
 		iounmap(dev->base_addr);
 	if (dev->mem_region)
 		release_mem_region(dev->phys_addr,
-				   pci_resource_len(pdev, PCH_UDC_PCI_BAR));
+				   pci_resource_len(pdev, dev->bar));
 	if (dev->active)
 		pci_disable_device(pdev);
 	kfree(dev);
@@ -3144,9 +3148,15 @@ static int pch_udc_probe(struct pci_dev *pdev,
 	dev->active = 1;
 	pci_set_drvdata(pdev, dev);
 
+	/* Determine BAR based on PCI ID */
+	if (id->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC)
+		dev->bar = PCH_UDC_PCI_BAR_QUARK_X1000;
+	else
+		dev->bar = PCH_UDC_PCI_BAR;
+
 	/* PCI resource allocation */
-	resource = pci_resource_start(pdev, 1);
-	len = pci_resource_len(pdev, 1);
+	resource = pci_resource_start(pdev, dev->bar);
+	len = pci_resource_len(pdev, dev->bar);
 
 	if (!request_mem_region(resource, len, KBUILD_MODNAME)) {
 		dev_err(&pdev->dev, "%s: pci device used already\n", __func__);
@@ -3212,6 +3222,12 @@ finished:
 
 static const struct pci_device_id pch_udc_pcidev_id[] = {
 	{
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL,
+			   PCI_DEVICE_ID_INTEL_QUARK_X1000_UDC),
+		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class_mask = 0xffffffff,
+	},
+	{
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EG20T_UDC),
 		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
 		.class_mask = 0xffffffff,
diff --git a/drivers/usb/gadget/tcm_usb_gadget.c b/drivers/usb/gadget/tcm_usb_gadget.c
index 0f8aad78b54f..460c266b8e24 100644
--- a/drivers/usb/gadget/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/tcm_usb_gadget.c
@@ -1613,7 +1613,7 @@ static struct se_wwn *usbg_make_tport(
 		return ERR_PTR(-ENOMEM);
 	}
 	tport->tport_wwpn = wwpn;
-	snprintf(tport->tport_name, sizeof(tport->tport_name), wnn_name);
+	snprintf(tport->tport_name, sizeof(tport->tport_name), "%s", wnn_name);
 	return &tport->tport_wwn;
 }
 
diff --git a/drivers/usb/gadget/u_serial.c b/drivers/usb/gadget/u_serial.c
index b369292d4b90..ad0aca812002 100644
--- a/drivers/usb/gadget/u_serial.c
+++ b/drivers/usb/gadget/u_serial.c
@@ -549,8 +549,8 @@ static void gs_rx_push(unsigned long _port)
 		port->read_started--;
 	}
 
-	/* Push from tty to ldisc; without low_latency set this is handled by
-	 * a workqueue, so we won't get callbacks and can hold port_lock
+	/* Push from tty to ldisc; this is handled by a workqueue,
+	 * so we won't get callbacks and can hold port_lock
 	 */
 	if (do_push)
 		tty_flip_buffer_push(&port->port);
diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c
index 27768a7d986a..9ce0b135c8c8 100644
--- a/drivers/usb/gadget/udc-core.c
+++ b/drivers/usb/gadget/udc-core.c
@@ -456,6 +456,11 @@ static ssize_t usb_udc_softconn_store(struct device *dev,
 {
 	struct usb_udc		*udc = container_of(dev, struct usb_udc, dev);
 
+	if (!udc->driver) {
+		dev_err(dev, "soft-connect without a gadget driver\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (sysfs_streq(buf, "connect")) {
 		usb_gadget_udc_start(udc->gadget, udc->driver);
 		usb_gadget_connect(udc->gadget);
diff --git a/drivers/usb/gadget/zero.c b/drivers/usb/gadget/zero.c
index 9f170c53e3d9..134f354ede62 100644
--- a/drivers/usb/gadget/zero.c
+++ b/drivers/usb/gadget/zero.c
@@ -300,7 +300,7 @@ static int __init zero_bind(struct usb_composite_dev *cdev)
 	ss_opts->isoc_interval = gzero_options.isoc_interval;
 	ss_opts->isoc_maxpacket = gzero_options.isoc_maxpacket;
 	ss_opts->isoc_mult = gzero_options.isoc_mult;
-	ss_opts->isoc_maxburst = gzero_options.isoc_maxpacket;
+	ss_opts->isoc_maxburst = gzero_options.isoc_maxburst;
 	ss_opts->bulk_buflen = gzero_options.bulk_buflen;
 
 	func_ss = usb_get_function(func_inst_ss);
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index a9707da7da0b..8a21d6a12423 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -158,6 +158,13 @@ config USB_EHCI_HCD_SPEAR
           Enables support for the on-chip EHCI controller on
           ST SPEAr chips.
 
+config USB_EHCI_HCD_SYNOPSYS
+       tristate "Support for Synopsys Host-AHB USB 2.0 controller"
+	depends on USB_EHCI_HCD && USB_PHY
+	---help---
+	  Enable support for onchip USB controllers based on DesignWare USB 2.0
+	  Host-AHB Controller IP from Synopsys.
+
 config USB_EHCI_HCD_AT91
         tristate  "Support for Atmel on-chip EHCI USB controller"
         depends on USB_EHCI_HCD && ARCH_AT91
diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile
index 7530468c9a4f..968d9214fe49 100644
--- a/drivers/usb/host/Makefile
+++ b/drivers/usb/host/Makefile
@@ -33,6 +33,8 @@ obj-$(CONFIG_USB_EHCI_HCD_OMAP)	+= ehci-omap.o
 obj-$(CONFIG_USB_EHCI_HCD_ORION)	+= ehci-orion.o
 obj-$(CONFIG_USB_EHCI_HCD_SPEAR)	+= ehci-spear.o
 obj-$(CONFIG_USB_EHCI_EXYNOS)	+= ehci-exynos.o
+obj-$(CONFIG_USB_EHCI_S5P)	+= ehci-s5p.o
+obj-$(CONFIG_USB_EHCI_HCD_SYNOPSYS)	+= ehci-h20ahb.o
 obj-$(CONFIG_USB_EHCI_HCD_AT91) += ehci-atmel.o
 obj-$(CONFIG_USB_EHCI_MSM)	+= ehci-msm.o
 obj-$(CONFIG_USB_EHCI_TEGRA)	+= ehci-tegra.o
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index 6f2c8d3899d2..cf2734b532a7 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -248,7 +248,8 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd,
 		break;
 	}
 
-	if (pdata->have_sysif_regs && pdata->controller_ver &&
+	if (pdata->have_sysif_regs &&
+	    pdata->controller_ver > FSL_USB_VER_1_6 &&
 	    (phy_mode == FSL_USB2_PHY_ULPI)) {
 		/* check PHY_CLK_VALID to get phy clk valid */
 		if (!(spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) &
diff --git a/drivers/usb/host/ehci-h20ahb.c b/drivers/usb/host/ehci-h20ahb.c
new file mode 100644
index 000000000000..7724bab1828b
--- /dev/null
+++ b/drivers/usb/host/ehci-h20ahb.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright (C) 2007-2013 Texas Instruments, Inc.
+ *	Author: Vikram Pandita <vikram.pandita@ti.com>
+ *	Author: Anand Gadiyar <gadiyar@ti.com>
+ *	Author: Keshava Munegowda <keshava_mgowda@ti.com>
+ *	Author: Roger Quadros <rogerq@ti.com>
+ *
+ * Copyright (C) 2009 Nokia Corporation
+ *	Contact: Felipe Balbi <felipe.balbi@nokia.com>
+ *
+ * Based on ehci-omap.c - driver for USBHOST on OMAP3/4 processors
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/usb/ulpi.h>
+#include <linux/pm_runtime.h>
+#include <linux/gpio.h>
+#include <linux/clk.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+#include <linux/of.h>
+#include <linux/dma-mapping.h>
+
+#include "ehci.h"
+
+#define H20AHB_HS_USB_PORTS	1
+
+/* EHCI Synopsys-specific Register Set */
+#define EHCI_INSNREG04					(0xA0)
+#define EHCI_INSNREG04_DISABLE_UNSUSPEND		(1 << 5)
+#define	EHCI_INSNREG05_ULPI				(0xA4)
+#define	EHCI_INSNREG05_ULPI_CONTROL_SHIFT		31
+#define	EHCI_INSNREG05_ULPI_PORTSEL_SHIFT		24
+#define	EHCI_INSNREG05_ULPI_OPSEL_SHIFT			22
+#define	EHCI_INSNREG05_ULPI_REGADD_SHIFT		16
+#define	EHCI_INSNREG05_ULPI_EXTREGADD_SHIFT		8
+#define	EHCI_INSNREG05_ULPI_WRDATA_SHIFT		0
+
+#define DRIVER_DESC "H20AHB-EHCI Host Controller driver"
+
+static const char hcd_name[] = "ehci-h20ahb";
+
+/*-------------------------------------------------------------------------*/
+
+struct h20ahb_hcd {
+	struct usb_phy *phy[H20AHB_HS_USB_PORTS]; /* one PHY for each port */
+	int nports;
+};
+
+static inline void ehci_write(void __iomem *base, u32 reg, u32 val)
+{
+	writel_relaxed(val, base + reg);
+}
+
+static inline u32 ehci_read(void __iomem *base, u32 reg)
+{
+	return readl_relaxed(base + reg);
+}
+
+/* configure so an HC device and id are always provided */
+/* always called with process context; sleeping is OK */
+
+static struct hc_driver __read_mostly ehci_h20ahb_hc_driver;
+
+static const struct ehci_driver_overrides ehci_h20ahb_overrides __initdata = {
+	.extra_priv_size = sizeof(struct h20ahb_hcd),
+};
+
+static int ehci_h20ahb_phy_read(struct usb_phy *x, u32 reg)
+{
+	u32 val = (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT) |
+		(1 << EHCI_INSNREG05_ULPI_PORTSEL_SHIFT) |
+		(3 << EHCI_INSNREG05_ULPI_OPSEL_SHIFT) |
+		(reg << EHCI_INSNREG05_ULPI_REGADD_SHIFT);
+	ehci_write(x->io_priv, 0, val);
+	while ((val = ehci_read(x->io_priv, 0)) &
+		(1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT));
+	return val & 0xff;
+}
+
+static int ehci_h20ahb_phy_write(struct usb_phy *x, u32 val, u32 reg)
+{
+	u32 v = (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT) |
+		(1 << EHCI_INSNREG05_ULPI_PORTSEL_SHIFT) |
+		(2 << EHCI_INSNREG05_ULPI_OPSEL_SHIFT) |
+		(reg << EHCI_INSNREG05_ULPI_REGADD_SHIFT) |
+		(val & 0xff);
+	ehci_write(x->io_priv, 0, v);
+	while ((v = ehci_read(x->io_priv, 0)) &
+		(1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT));
+	return 0;
+}
+
+static struct usb_phy_io_ops ehci_h20ahb_phy_io_ops = {
+	.read = ehci_h20ahb_phy_read,
+	.write = ehci_h20ahb_phy_write,
+};
+
+
+/**
+ * ehci_hcd_h20ahb_probe - initialize Synopsis-based HCDs
+ *
+ * Allocates basic resources for this USB host controller, and
+ * then invokes the start() method for the HCD associated with it
+ * through the hotplug entry's driver_data.
+ */
+static int ehci_hcd_h20ahb_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource	*res;
+	struct usb_hcd	*hcd;
+	void __iomem *regs;
+	int ret;
+	int irq;
+	int i;
+	struct h20ahb_hcd	*h20ahb;
+
+	if (usb_disabled())
+		return -ENODEV;
+
+	/* if (!dev->parent) {
+		dev_err(dev, "Missing parent device\n");
+		return -ENODEV;
+		}*/
+
+	/* For DT boot, get platform data from parent. i.e. usbhshost */
+	/*if (dev->of_node) {
+		pdata = dev_get_platdata(dev->parent);
+		dev->platform_data = pdata;
+	}
+
+	if (!pdata) {
+		dev_err(dev, "Missing platform data\n");
+		return -ENODEV;
+		}*/
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "EHCI irq failed\n");
+		return -ENODEV;
+	}
+
+	res =  platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	/*
+	 * Right now device-tree probed devices don't get dma_mask set.
+	 * Since shared usb code relies on it, set it here for now.
+	 * Once we have dma capability bindings this can go away.
+	 */
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	ret = -ENODEV;
+	hcd = usb_create_hcd(&ehci_h20ahb_hc_driver, dev,
+			dev_name(dev));
+	if (!hcd) {
+		dev_err(dev, "Failed to create HCD\n");
+		return -ENOMEM;
+	}
+
+	hcd->rsrc_start = res->start;
+	hcd->rsrc_len = resource_size(res);
+	hcd->regs = regs;
+	hcd_to_ehci(hcd)->caps = regs;
+
+	h20ahb = (struct h20ahb_hcd *)hcd_to_ehci(hcd)->priv;
+	h20ahb->nports = 1;
+
+	platform_set_drvdata(pdev, hcd);
+
+	/* get the PHY devices if needed */
+	for (i = 0 ; i < h20ahb->nports ; i++) {
+		struct usb_phy *phy;
+
+		/* get the PHY device */
+#if 0
+		if (dev->of_node)
+			phy = devm_usb_get_phy_by_phandle(dev, "phys", i);
+		else
+			phy = devm_usb_get_phy_dev(dev, i);
+#endif
+		phy = otg_ulpi_create(&ehci_h20ahb_phy_io_ops, 0);
+		if (IS_ERR(phy)) {
+			ret = PTR_ERR(phy);
+			dev_err(dev, "Can't get PHY device for port %d: %d\n",
+					i, ret);
+			goto err_phy;
+		}
+		phy->dev = dev;
+		usb_add_phy_dev(phy);
+
+		h20ahb->phy[i] = phy;
+		phy->io_priv = hcd->regs + EHCI_INSNREG05_ULPI;
+
+#if 0
+		usb_phy_init(h20ahb->phy[i]);
+		/* bring PHY out of suspend */
+		usb_phy_set_suspend(h20ahb->phy[i], 0);
+#endif
+	}
+
+	/* make the first port's phy the one used by hcd as well */
+	hcd->phy = h20ahb->phy[0];
+
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+
+	/*
+	 * An undocumented "feature" in the H20AHB EHCI controller,
+	 * causes suspended ports to be taken out of suspend when
+	 * the USBCMD.Run/Stop bit is cleared (for example when
+	 * we do ehci_bus_suspend).
+	 * This breaks suspend-resume if the root-hub is allowed
+	 * to suspend. Writing 1 to this undocumented register bit
+	 * disables this feature and restores normal behavior.
+	 */
+	ehci_write(regs, EHCI_INSNREG04,
+				EHCI_INSNREG04_DISABLE_UNSUSPEND);
+
+	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
+	if (ret) {
+		dev_err(dev, "failed to add hcd with err %d\n", ret);
+		goto err_pm_runtime;
+	}
+	device_wakeup_enable(hcd->self.controller);
+
+	/*
+	 * Bring PHYs out of reset for non PHY modes.
+	 * Even though HSIC mode is a PHY-less mode, the reset
+	 * line exists between the chips and can be modelled
+	 * as a PHY device for reset control.
+	 */
+	for (i = 0; i < h20ahb->nports; i++) {
+		usb_phy_init(h20ahb->phy[i]);
+		/* bring PHY out of suspend */
+		usb_phy_set_suspend(h20ahb->phy[i], 0);
+	}
+
+	return 0;
+
+err_pm_runtime:
+	pm_runtime_put_sync(dev);
+
+err_phy:
+	for (i = 0; i < h20ahb->nports; i++) {
+		if (h20ahb->phy[i])
+			usb_phy_shutdown(h20ahb->phy[i]);
+	}
+
+	usb_put_hcd(hcd);
+
+	return ret;
+}
+
+
+/**
+ * ehci_hcd_h20ahb_remove - shutdown processing for EHCI HCDs
+ * @pdev: USB Host Controller being removed
+ *
+ * Reverses the effect of usb_ehci_hcd_h20ahb_probe(), first invoking
+ * the HCD's stop() method.  It is always called from a thread
+ * context, normally "rmmod", "apmd", or something similar.
+ */
+static int ehci_hcd_h20ahb_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct usb_hcd *hcd = dev_get_drvdata(dev);
+	struct h20ahb_hcd *h20ahb = (struct h20ahb_hcd *)hcd_to_ehci(hcd)->priv;
+	int i;
+
+	usb_remove_hcd(hcd);
+
+	for (i = 0; i < h20ahb->nports; i++) {
+		if (h20ahb->phy[i])
+			usb_phy_shutdown(h20ahb->phy[i]);
+	}
+
+	usb_put_hcd(hcd);
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
+	return 0;
+}
+
+static const struct of_device_id h20ahb_ehci_dt_ids[] = {
+	{ .compatible = "snps,ehci-h20ahb" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, h20ahb_ehci_dt_ids);
+
+static struct platform_driver ehci_hcd_h20ahb_driver = {
+	.probe			= ehci_hcd_h20ahb_probe,
+	.remove			= ehci_hcd_h20ahb_remove,
+	.shutdown		= usb_hcd_platform_shutdown,
+	/*.suspend		= ehci_hcd_h20ahb_suspend, */
+	/*.resume		= ehci_hcd_h20ahb_resume, */
+	.driver = {
+		.name		= hcd_name,
+		.of_match_table = h20ahb_ehci_dt_ids,
+	}
+};
+
+/*-------------------------------------------------------------------------*/
+
+static int __init ehci_h20ahb_init(void)
+{
+	if (usb_disabled())
+		return -ENODEV;
+
+	pr_info("%s: " DRIVER_DESC "\n", hcd_name);
+
+	ehci_init_driver(&ehci_h20ahb_hc_driver, &ehci_h20ahb_overrides);
+	return platform_driver_register(&ehci_hcd_h20ahb_driver);
+}
+module_init(ehci_h20ahb_init);
+
+static void __exit ehci_h20ahb_cleanup(void)
+{
+	platform_driver_unregister(&ehci_hcd_h20ahb_driver);
+}
+module_exit(ehci_h20ahb_cleanup);
+
+MODULE_ALIAS("platform:ehci-h20ahb");
+MODULE_AUTHOR("Liviu Dudau <Liviu.Dudau@arm.com>");
+
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 81cda09b47e3..992ca7d2f14d 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -590,11 +590,16 @@ static int ehci_run (struct usb_hcd *hcd)
 	 */
 	hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params);
 	if (HCC_64BIT_ADDR(hcc_params)) {
-		ehci_writel(ehci, 0, &ehci->regs->segment);
-#if 0
-// this is deeply broken on almost all architectures
+#ifdef CONFIG_ARM64
+		ehci_writel(ehci, ehci->periodic_dma >> 32, &ehci->regs->segment);
+		/*
+		 * this is deeply broken on almost all architectures
+		 * but arm64 can use it so enable it
+		 */
 		if (!dma_set_mask(hcd->self.controller, DMA_BIT_MASK(64)))
 			ehci_info(ehci, "enabled 64bit DMA\n");
+#else
+		ehci_writel(ehci, 0, &ehci->regs->segment);
 #endif
 	}
 
@@ -965,8 +970,6 @@ rescan:
 	}
 
 	qh->exception = 1;
-	if (ehci->rh_state < EHCI_RH_RUNNING)
-		qh->qh_state = QH_STATE_IDLE;
 	switch (qh->qh_state) {
 	case QH_STATE_LINKED:
 		WARN_ON(!list_empty(&qh->qtd_list));
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 7ae0c4d51741..7d6f64c447bf 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -1239,7 +1239,7 @@ static int ehci_hub_control (
 			if (selector == EHSET_TEST_SINGLE_STEP_SET_FEATURE) {
 				spin_unlock_irqrestore(&ehci->lock, flags);
 				retval = ehset_single_step_set_feature(hcd,
-									wIndex);
+								wIndex + 1);
 				spin_lock_irqsave(&ehci->lock, flags);
 				break;
 			}
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 3e86bf4371b3..ca7b964124af 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -35,6 +35,21 @@ static const char hcd_name[] = "ehci-pci";
 #define PCI_DEVICE_ID_INTEL_CE4100_USB	0x2e70
 
 /*-------------------------------------------------------------------------*/
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC		0x0939
+static inline bool is_intel_quark_x1000(struct pci_dev *pdev)
+{
+	return pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		pdev->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC;
+}
+
+/*
+ * 0x84 is the offset of in/out threshold register,
+ * and it is the same offset as the register of 'hostpc'.
+ */
+#define	intel_quark_x1000_insnreg01	hostpc
+
+/* Maximum usable threshold value is 0x7f dwords for both IN and OUT */
+#define INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD	0x007f007f
 
 /* called after powerup, by probe or system-pm "wakeup" */
 static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
@@ -50,6 +65,16 @@ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
 	if (!retval)
 		ehci_dbg(ehci, "MWI active\n");
 
+	/* Reset the threshold limit */
+	if (is_intel_quark_x1000(pdev)) {
+		/*
+		 * For the Intel QUARK X1000, raise the I/O threshold to the
+		 * maximum usable value in order to improve performance.
+		 */
+		ehci_writel(ehci, INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD,
+			ehci->regs->intel_quark_x1000_insnreg01);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c
index af28b748e87a..633dbea28f30 100644
--- a/drivers/usb/host/ehci-tegra.c
+++ b/drivers/usb/host/ehci-tegra.c
@@ -513,8 +513,31 @@ static struct platform_driver tegra_ehci_driver = {
 	}
 };
 
+static int tegra_ehci_reset(struct usb_hcd *hcd)
+{
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+	int retval;
+	int txfifothresh;
+
+	retval = ehci_setup(hcd);
+	if (retval)
+		return retval;
+
+	/*
+	 * We should really pull this value out of tegra_ehci_soc_config, but
+	 * to avoid needing access to it, make use of the fact that Tegra20 is
+	 * the only one so far that needs a value of 10, and Tegra20 is the
+	 * only one which doesn't set has_hostpc.
+	 */
+	txfifothresh = ehci->has_hostpc ? 0x10 : 10;
+	ehci_writel(ehci, txfifothresh << 16, &ehci->regs->txfill_tuning);
+
+	return 0;
+}
+
 static const struct ehci_driver_overrides tegra_overrides __initconst = {
 	.extra_priv_size	= sizeof(struct tegra_ehci_hcd),
+	.reset			= tegra_ehci_reset,
 };
 
 static int __init ehci_tegra_init(void)
diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c
index 45032e933e18..04f2186939d2 100644
--- a/drivers/usb/host/ohci-dbg.c
+++ b/drivers/usb/host/ohci-dbg.c
@@ -236,7 +236,7 @@ ohci_dump_roothub (
 	}
 }
 
-static void ohci_dump (struct ohci_hcd *controller, int verbose)
+static void ohci_dump(struct ohci_hcd *controller)
 {
 	ohci_dbg (controller, "OHCI controller state\n");
 
@@ -464,15 +464,16 @@ show_list (struct ohci_hcd *ohci, char *buf, size_t count, struct ed *ed)
 static ssize_t fill_async_buffer(struct debug_buffer *buf)
 {
 	struct ohci_hcd		*ohci;
-	size_t			temp;
+	size_t			temp, size;
 	unsigned long		flags;
 
 	ohci = buf->ohci;
+	size = PAGE_SIZE;
 
 	/* display control and bulk lists together, for simplicity */
 	spin_lock_irqsave (&ohci->lock, flags);
-	temp = show_list(ohci, buf->page, buf->count, ohci->ed_controltail);
-	temp += show_list(ohci, buf->page + temp, buf->count - temp,
+	temp = show_list(ohci, buf->page, size, ohci->ed_controltail);
+	temp += show_list(ohci, buf->page + temp, size - temp,
 			  ohci->ed_bulktail);
 	spin_unlock_irqrestore (&ohci->lock, flags);
 
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 3586460fb2a1..34fc86ccb591 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -76,8 +76,8 @@ static const char	hcd_name [] = "ohci_hcd";
 #include "ohci.h"
 #include "pci-quirks.h"
 
-static void ohci_dump (struct ohci_hcd *ohci, int verbose);
-static void ohci_stop (struct usb_hcd *hcd);
+static void ohci_dump(struct ohci_hcd *ohci);
+static void ohci_stop(struct usb_hcd *hcd);
 
 #include "ohci-hub.c"
 #include "ohci-dbg.c"
@@ -744,7 +744,7 @@ retry:
 		ohci->ed_to_check = NULL;
 	}
 
-	ohci_dump (ohci, 1);
+	ohci_dump(ohci);
 
 	return 0;
 }
@@ -825,7 +825,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd)
 			usb_hc_died(hcd);
 		}
 
-		ohci_dump (ohci, 1);
+		ohci_dump(ohci);
 		ohci_usb_reset (ohci);
 	}
 
@@ -925,7 +925,7 @@ static void ohci_stop (struct usb_hcd *hcd)
 {
 	struct ohci_hcd		*ohci = hcd_to_ohci (hcd);
 
-	ohci_dump (ohci, 1);
+	ohci_dump(ohci);
 
 	if (quirk_nec(ohci))
 		flush_work(&ohci->nec_work);
diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c
index c81c8721cc5a..cd871b895013 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -90,6 +90,24 @@ __acquires(ohci->lock)
 	dl_done_list (ohci);
 	finish_unlinks (ohci, ohci_frame_no(ohci));
 
+	/*
+	 * Some controllers don't handle "global" suspend properly if
+	 * there are unsuspended ports.  For these controllers, put all
+	 * the enabled ports into suspend before suspending the root hub.
+	 */
+	if (ohci->flags & OHCI_QUIRK_GLOBAL_SUSPEND) {
+		__hc32 __iomem	*portstat = ohci->regs->roothub.portstatus;
+		int		i;
+		unsigned	temp;
+
+		for (i = 0; i < ohci->num_ports; (++i, ++portstat)) {
+			temp = ohci_readl(ohci, portstat);
+			if ((temp & (RH_PS_PES | RH_PS_PSS)) ==
+					RH_PS_PES)
+				ohci_writel(ohci, RH_PS_PSS, portstat);
+		}
+	}
+
 	/* maybe resume can wake root hub */
 	if (ohci_to_hcd(ohci)->self.root_hub->do_remote_wakeup || autostop) {
 		ohci->hc_control |= OHCI_CTRL_RWE;
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index 90879e9ccbec..bb1509675727 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -160,6 +160,7 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd)
 		ohci_dbg(ohci, "enabled AMD prefetch quirk\n");
 	}
 
+	ohci->flags |= OHCI_QUIRK_GLOBAL_SUSPEND;
 	return 0;
 }
 
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index d4253e319428..a8bde5b8cbdd 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -311,8 +311,7 @@ static void periodic_unlink (struct ohci_hcd *ohci, struct ed *ed)
  *  - ED_OPER: when there's any request queued, the ED gets rescheduled
  *    immediately.  HC should be working on them.
  *
- *  - ED_IDLE:  when there's no TD queue. there's no reason for the HC
- *    to care about this ED; safe to disable the endpoint.
+ *  - ED_IDLE: when there's no TD queue or the HC isn't running.
  *
  * When finish_unlinks() runs later, after SOF interrupt, it will often
  * complete one or more URB unlinks before making that state change.
@@ -926,6 +925,10 @@ rescan_all:
 		int			completed, modified;
 		__hc32			*prev;
 
+		/* Is this ED already invisible to the hardware? */
+		if (ed->state == ED_IDLE)
+			goto ed_idle;
+
 		/* only take off EDs that the HC isn't using, accounting for
 		 * frame counter wraps and EDs with partially retired TDs
 		 */
@@ -955,12 +958,20 @@ skip_ed:
 			}
 		}
 
+		/* ED's now officially unlinked, hc doesn't see */
+		ed->state = ED_IDLE;
+		if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
+			ohci->eds_scheduled--;
+		ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
+		ed->hwNextED = 0;
+		wmb();
+		ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE);
+ed_idle:
+
 		/* reentrancy:  if we drop the schedule lock, someone might
 		 * have modified this list.  normally it's just prepending
 		 * entries (which we'd ignore), but paranoia won't hurt.
 		 */
-		*last = ed->ed_next;
-		ed->ed_next = NULL;
 		modified = 0;
 
 		/* unlink urbs as requested, but rescan the list after
@@ -1018,19 +1029,20 @@ rescan_this:
 		if (completed && !list_empty (&ed->td_list))
 			goto rescan_this;
 
-		/* ED's now officially unlinked, hc doesn't see */
-		ed->state = ED_IDLE;
-		if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
-			ohci->eds_scheduled--;
-		ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
-		ed->hwNextED = 0;
-		wmb ();
-		ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE);
-
-		/* but if there's work queued, reschedule */
-		if (!list_empty (&ed->td_list)) {
-			if (ohci->rh_state == OHCI_RH_RUNNING)
-				ed_schedule (ohci, ed);
+		/*
+		 * If no TDs are queued, take ED off the ed_rm_list.
+		 * Otherwise, if the HC is running, reschedule.
+		 * If not, leave it on the list for further dequeues.
+		 */
+		if (list_empty(&ed->td_list)) {
+			*last = ed->ed_next;
+			ed->ed_next = NULL;
+		} else if (ohci->rh_state == OHCI_RH_RUNNING) {
+			*last = ed->ed_next;
+			ed->ed_next = NULL;
+			ed_schedule(ohci, ed);
+		} else {
+			last = &ed->ed_next;
 		}
 
 		if (modified)
diff --git a/drivers/usb/host/ohci.h b/drivers/usb/host/ohci.h
index 9250cada13f0..4550ce05af7f 100644
--- a/drivers/usb/host/ohci.h
+++ b/drivers/usb/host/ohci.h
@@ -405,6 +405,8 @@ struct ohci_hcd {
 #define	OHCI_QUIRK_HUB_POWER	0x100			/* distrust firmware power/oc setup */
 #define	OHCI_QUIRK_AMD_PLL	0x200			/* AMD PLL quirk*/
 #define	OHCI_QUIRK_AMD_PREFETCH	0x400			/* pre-fetch for ISO transfer */
+#define	OHCI_QUIRK_GLOBAL_SUSPEND	0x800		/* must suspend ports */
+
 	// there are also chip quirks/bugs in init logic
 
 	struct work_struct	nec_work;	/* Worker for NEC quirk */
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 00661d305143..2f3acebb577a 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -656,6 +656,14 @@ static const struct dmi_system_id ehci_dmi_nohandoff_table[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"),
 		},
 	},
+	{
+		/* HASEE E200 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"),
+			DMI_MATCH(DMI_BOARD_NAME, "E210"),
+			DMI_MATCH(DMI_BIOS_VERSION, "6.00"),
+		},
+	},
 	{ }
 };
 
@@ -665,9 +673,14 @@ static void ehci_bios_handoff(struct pci_dev *pdev,
 {
 	int try_handoff = 1, tried_handoff = 0;
 
-	/* The Pegatron Lucid tablet sporadically waits for 98 seconds trying
-	 * the handoff on its unused controller.  Skip it. */
-	if (pdev->vendor == 0x8086 && pdev->device == 0x283a) {
+	/*
+	 * The Pegatron Lucid tablet sporadically waits for 98 seconds trying
+	 * the handoff on its unused controller.  Skip it.
+	 *
+	 * The HASEE E200 hangs when the semaphore is set (bugzilla #77021).
+	 */
+	if (pdev->vendor == 0x8086 && (pdev->device == 0x283a ||
+			pdev->device == 0x27cc)) {
 		if (dmi_check_system(ehci_dmi_nohandoff_table))
 			try_handoff = 0;
 	}
@@ -847,6 +860,13 @@ void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev)
 	bool		ehci_found = false;
 	struct pci_dev	*companion = NULL;
 
+	/* Sony VAIO t-series with subsystem device ID 90a8 is not capable of
+	 * switching ports from EHCI to xHCI
+	 */
+	if (xhci_pdev->subsystem_vendor == PCI_VENDOR_ID_SONY &&
+	    xhci_pdev->subsystem_device == 0x90a8)
+		return;
+
 	/* make sure an intel EHCI controller exists */
 	for_each_pci_dev(companion) {
 		if (companion->class == PCI_CLASS_SERIAL_USB_EHCI &&
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 9992fbfec85f..93fe089cd51a 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -470,7 +470,8 @@ static void xhci_hub_report_usb2_link_state(u32 *status, u32 status_reg)
 }
 
 /* Updates Link Status for super Speed port */
-static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg)
+static void xhci_hub_report_usb3_link_state(struct xhci_hcd *xhci,
+		u32 *status, u32 status_reg)
 {
 	u32 pls = status_reg & PORT_PLS_MASK;
 
@@ -509,7 +510,8 @@ static void xhci_hub_report_usb3_link_state(u32 *status, u32 status_reg)
 		 * in which sometimes the port enters compliance mode
 		 * caused by a delay on the host-device negotiation.
 		 */
-		if (pls == USB_SS_PORT_LS_COMP_MOD)
+		if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) &&
+				(pls == USB_SS_PORT_LS_COMP_MOD))
 			pls |= USB_PORT_STAT_CONNECTION;
 	}
 
@@ -668,7 +670,7 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
 	}
 	/* Update Port Link State */
 	if (hcd->speed == HCD_USB3) {
-		xhci_hub_report_usb3_link_state(&status, raw_port_status);
+		xhci_hub_report_usb3_link_state(xhci, &status, raw_port_status);
 		/*
 		 * Verify if all USB3 Ports Have entered U0 already.
 		 * Delete Compliance Mode Timer if so.
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index bce4391a0e7d..9bce4f0e99be 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1722,6 +1722,16 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 		kfree(cur_cd);
 	}
 
+	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
+	for (i = 0; i < num_ports && xhci->rh_bw; i++) {
+		struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table;
+		for (j = 0; j < XHCI_MAX_INTERVAL; j++) {
+			struct list_head *ep = &bwt->interval_bw[j].endpoints;
+			while (!list_empty(ep))
+				list_del_init(ep->next);
+		}
+	}
+
 	for (i = 1; i < MAX_HC_SLOTS; ++i)
 		xhci_free_virt_device(xhci, i);
 
@@ -1757,16 +1767,6 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	if (!xhci->rh_bw)
 		goto no_bw;
 
-	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
-	for (i = 0; i < num_ports; i++) {
-		struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table;
-		for (j = 0; j < XHCI_MAX_INTERVAL; j++) {
-			struct list_head *ep = &bwt->interval_bw[j].endpoints;
-			while (!list_empty(ep))
-				list_del_init(ep->next);
-		}
-	}
-
 	for (i = 0; i < num_ports; i++) {
 		struct xhci_tt_bw_info *tt, *n;
 		list_for_each_entry_safe(tt, n, &xhci->rh_bw[i].tts, tt_list) {
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 04f986d9234f..73c43e5e231b 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -101,6 +101,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	/* AMD PLL quirk */
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
 		xhci->quirks |= XHCI_AMD_PLL_FIX;
+
+	if (pdev->vendor == PCI_VENDOR_ID_AMD)
+		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
 		xhci->quirks |= XHCI_INTEL_HOST;
@@ -134,6 +138,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		 */
 		if (pdev->subsystem_vendor == PCI_VENDOR_ID_HP)
 			xhci->quirks |= XHCI_SPURIOUS_WAKEUP;
+
+		xhci->quirks |= XHCI_SPURIOUS_REBOOT;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
 			pdev->device == PCI_DEVICE_ID_ASROCK_P67) {
@@ -143,9 +149,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
-			pdev->device == 0x0015 &&
-			pdev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG &&
-			pdev->subsystem_device == 0xc0cd)
+			pdev->device == 0x0015)
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
 	if (pdev->vendor == PCI_VENDOR_ID_VIA)
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
@@ -190,6 +194,10 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	struct usb_hcd *hcd;
 
 	driver = (struct hc_driver *)id->driver_data;
+
+	/* Prevent runtime suspending between USB-2 and USB-3 initialization */
+	pm_runtime_get_noresume(&dev->dev);
+
 	/* Register the USB 2.0 roothub.
 	 * FIXME: USB core must know to register the USB 2.0 roothub first.
 	 * This is sort of silly, because we could just set the HCD driver flags
@@ -199,7 +207,7 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	retval = usb_hcd_pci_probe(dev, id);
 
 	if (retval)
-		return retval;
+		goto put_runtime_pm;
 
 	/* USB 2.0 roothub is stored in the PCI device now. */
 	hcd = dev_get_drvdata(&dev->dev);
@@ -228,12 +236,17 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (xhci->quirks & XHCI_LPM_SUPPORT)
 		hcd_to_bus(xhci->shared_hcd)->root_hub->lpm_capable = 1;
 
+	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
+	pm_runtime_put_noidle(&dev->dev);
+
 	return 0;
 
 put_usb3_hcd:
 	usb_put_hcd(xhci->shared_hcd);
 dealloc_usb2_hcd:
 	usb_hcd_pci_remove(dev);
+put_runtime_pm:
+	pm_runtime_put_noidle(&dev->dev);
 	return retval;
 }
 
@@ -268,7 +281,7 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 	if (xhci_compliance_mode_recovery_timer_quirk_check())
 		pdev->no_d3cold = true;
 
-	return xhci_suspend(xhci);
+	return xhci_suspend(xhci, do_wakeup);
 }
 
 static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated)
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 8abda5c73ca1..d6f70a223a43 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -11,11 +11,12 @@
  * version 2 as published by the Free Software Foundation.
  */
 
-#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/usb/xhci_pdriver.h>
 
 #include "xhci.h"
 
@@ -87,6 +88,8 @@ static const struct hc_driver xhci_plat_xhci_driver = {
 
 static int xhci_plat_probe(struct platform_device *pdev)
 {
+	struct device_node	*node = pdev->dev.of_node;
+	struct usb_xhci_pdata	*pdata = dev_get_platdata(&pdev->dev);
 	const struct hc_driver	*driver;
 	struct xhci_hcd		*xhci;
 	struct resource         *res;
@@ -152,6 +155,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
 		goto dealloc_usb2_hcd;
 	}
 
+	if ((node && of_property_read_bool(node, "usb3-lpm-capable")) ||
+			(pdata && pdata->usb3_lpm_capable))
+		xhci->quirks |= XHCI_LPM_SUPPORT;
 	/*
 	 * Set the xHCI pointer before xhci_plat_setup() (aka hcd_driver.reset)
 	 * is called by usb_add_hcd().
@@ -205,7 +211,15 @@ static int xhci_plat_suspend(struct device *dev)
 	struct usb_hcd	*hcd = dev_get_drvdata(dev);
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
 
-	return xhci_suspend(xhci);
+	/*
+	 * xhci_suspend() needs `do_wakeup` to know whether host is allowed
+	 * to do wakeup during suspend. Since xhci_plat_suspend is currently
+	 * only designed for system suspend, device_may_wakeup() is enough
+	 * to dertermine whether host is allowed to do wakeup. Need to
+	 * reconsider this when xhci_plat_suspend enlarges its scope, e.g.,
+	 * also applies to runtime suspend.
+	 */
+	return xhci_suspend(xhci, device_may_wakeup(dev));
 }
 
 static int xhci_plat_resume(struct device *dev)
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 0ed64eb68e48..faa8b98954d9 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -550,6 +550,7 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 	struct xhci_generic_trb *trb;
 	struct xhci_ep_ctx *ep_ctx;
 	dma_addr_t addr;
+	u64 hw_dequeue;
 
 	ep_ring = xhci_triad_to_transfer_ring(xhci, slot_id,
 			ep_index, stream_id);
@@ -559,56 +560,57 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 				stream_id);
 		return;
 	}
-	state->new_cycle_state = 0;
-	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
-			"Finding segment containing stopped TRB.");
-	state->new_deq_seg = find_trb_seg(cur_td->start_seg,
-			dev->eps[ep_index].stopped_trb,
-			&state->new_cycle_state);
-	if (!state->new_deq_seg) {
-		WARN_ON(1);
-		return;
-	}
 
 	/* Dig out the cycle state saved by the xHC during the stop ep cmd */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Finding endpoint context");
 	ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
-	state->new_cycle_state = 0x1 & le64_to_cpu(ep_ctx->deq);
+	hw_dequeue = le64_to_cpu(ep_ctx->deq);
+
+	/* Find virtual address and segment of hardware dequeue pointer */
+	state->new_deq_seg = ep_ring->deq_seg;
+	state->new_deq_ptr = ep_ring->dequeue;
+	while (xhci_trb_virt_to_dma(state->new_deq_seg, state->new_deq_ptr)
+			!= (dma_addr_t)(hw_dequeue & ~0xf)) {
+		next_trb(xhci, ep_ring, &state->new_deq_seg,
+					&state->new_deq_ptr);
+		if (state->new_deq_ptr == ep_ring->dequeue) {
+			WARN_ON(1);
+			return;
+		}
+	}
+	/*
+	 * Find cycle state for last_trb, starting at old cycle state of
+	 * hw_dequeue. If there is only one segment ring, find_trb_seg() will
+	 * return immediately and cannot toggle the cycle state if this search
+	 * wraps around, so add one more toggle manually in that case.
+	 */
+	state->new_cycle_state = hw_dequeue & 0x1;
+	if (ep_ring->first_seg == ep_ring->first_seg->next &&
+			cur_td->last_trb < state->new_deq_ptr)
+		state->new_cycle_state ^= 0x1;
 
 	state->new_deq_ptr = cur_td->last_trb;
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Finding segment containing last TRB in TD.");
 	state->new_deq_seg = find_trb_seg(state->new_deq_seg,
-			state->new_deq_ptr,
-			&state->new_cycle_state);
+			state->new_deq_ptr, &state->new_cycle_state);
 	if (!state->new_deq_seg) {
 		WARN_ON(1);
 		return;
 	}
 
+	/* Increment to find next TRB after last_trb. Cycle if appropriate. */
 	trb = &state->new_deq_ptr->generic;
 	if (TRB_TYPE_LINK_LE32(trb->field[3]) &&
 	    (trb->field[3] & cpu_to_le32(LINK_TOGGLE)))
 		state->new_cycle_state ^= 0x1;
 	next_trb(xhci, ep_ring, &state->new_deq_seg, &state->new_deq_ptr);
 
-	/*
-	 * If there is only one segment in a ring, find_trb_seg()'s while loop
-	 * will not run, and it will return before it has a chance to see if it
-	 * needs to toggle the cycle bit.  It can't tell if the stalled transfer
-	 * ended just before the link TRB on a one-segment ring, or if the TD
-	 * wrapped around the top of the ring, because it doesn't have the TD in
-	 * question.  Look for the one-segment case where stalled TRB's address
-	 * is greater than the new dequeue pointer address.
-	 */
-	if (ep_ring->first_seg == ep_ring->first_seg->next &&
-			state->new_deq_ptr < dev->eps[ep_index].stopped_trb)
-		state->new_cycle_state ^= 0x1;
+	/* Don't update the ring cycle state for the producer (us). */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"Cycle state = 0x%x", state->new_cycle_state);
 
-	/* Don't update the ring cycle state for the producer (us). */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 			"New dequeue segment = %p (virtual)",
 			state->new_deq_seg);
@@ -791,7 +793,6 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id,
 	if (list_empty(&ep->cancelled_td_list)) {
 		xhci_stop_watchdog_timer_in_irq(xhci, ep);
 		ep->stopped_td = NULL;
-		ep->stopped_trb = NULL;
 		ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 		return;
 	}
@@ -859,11 +860,9 @@ remove_finished_td:
 		ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 	}
 
-	/* Clear stopped_td and stopped_trb if endpoint is not halted */
-	if (!(ep->ep_state & EP_HALTED)) {
+	/* Clear stopped_td if endpoint is not halted */
+	if (!(ep->ep_state & EP_HALTED))
 		ep->stopped_td = NULL;
-		ep->stopped_trb = NULL;
-	}
 
 	/*
 	 * Drop the lock and complete the URBs in the cancelled TD list.
@@ -1181,9 +1180,8 @@ static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id,
 				false);
 		xhci_ring_cmd_db(xhci);
 	} else {
-		/* Clear our internal halted state and restart the ring(s) */
+		/* Clear our internal halted state */
 		xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_HALTED;
-		ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 	}
 }
 
@@ -1579,8 +1577,11 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 		xhci_handle_cmd_reset_ep(xhci, slot_id, cmd_trb, cmd_comp_code);
 		break;
 	case TRB_RESET_DEV:
-		WARN_ON(slot_id != TRB_TO_SLOT_ID(
-				le32_to_cpu(cmd_trb->generic.field[3])));
+		/* SLOT_ID field in reset device cmd completion event TRB is 0.
+		 * Use the SLOT_ID from the command TRB instead (xhci 4.6.11)
+		 */
+		slot_id = TRB_TO_SLOT_ID(
+				le32_to_cpu(cmd_trb->generic.field[3]));
 		xhci_handle_cmd_reset_dev(xhci, slot_id, event);
 		break;
 	case TRB_NEC_GET_FW:
@@ -1908,14 +1909,12 @@ static void xhci_cleanup_halted_endpoint(struct xhci_hcd *xhci,
 	struct xhci_virt_ep *ep = &xhci->devs[slot_id]->eps[ep_index];
 	ep->ep_state |= EP_HALTED;
 	ep->stopped_td = td;
-	ep->stopped_trb = event_trb;
 	ep->stopped_stream = stream_id;
 
 	xhci_queue_reset_ep(xhci, slot_id, ep_index);
 	xhci_cleanup_stalled_ring(xhci, td->urb->dev, ep_index);
 
 	ep->stopped_td = NULL;
-	ep->stopped_trb = NULL;
 	ep->stopped_stream = 0;
 
 	xhci_ring_cmd_db(xhci);
@@ -1997,26 +1996,15 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td,
 		 * the ring dequeue pointer or take this TD off any lists yet.
 		 */
 		ep->stopped_td = td;
-		ep->stopped_trb = event_trb;
 		return 0;
 	} else {
-		if (trb_comp_code == COMP_STALL) {
-			/* The transfer is completed from the driver's
-			 * perspective, but we need to issue a set dequeue
-			 * command for this stalled endpoint to move the dequeue
-			 * pointer past the TD.  We can't do that here because
-			 * the halt condition must be cleared first.  Let the
-			 * USB class driver clear the stall later.
-			 */
-			ep->stopped_td = td;
-			ep->stopped_trb = event_trb;
-			ep->stopped_stream = ep_ring->stream_id;
-		} else if (xhci_requires_manual_halt_cleanup(xhci,
-					ep_ctx, trb_comp_code)) {
-			/* Other types of errors halt the endpoint, but the
-			 * class driver doesn't call usb_reset_endpoint() unless
-			 * the error is -EPIPE.  Clear the halted status in the
-			 * xHCI hardware manually.
+		if (trb_comp_code == COMP_STALL ||
+		    xhci_requires_manual_halt_cleanup(xhci, ep_ctx,
+						      trb_comp_code)) {
+			/* Issue a reset endpoint command to clear the host side
+			 * halt, followed by a set dequeue command to move the
+			 * dequeue pointer past the TD.
+			 * The class driver clears the device side halt later.
 			 */
 			xhci_cleanup_halted_endpoint(xhci,
 					slot_id, ep_index, ep_ring->stream_id,
@@ -2136,9 +2124,7 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
 		else
 			td->urb->actual_length = 0;
 
-		xhci_cleanup_halted_endpoint(xhci,
-			slot_id, ep_index, 0, td, event_trb);
-		return finish_td(xhci, td, event_trb, event, ep, status, true);
+		return finish_td(xhci, td, event_trb, event, ep, status, false);
 	}
 	/*
 	 * Did we transfer any data, despite the errors that might have
@@ -2614,7 +2600,8 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		 * last TRB of the previous TD. The command completion handle
 		 * will take care the rest.
 		 */
-		if (!event_seg && trb_comp_code == COMP_STOP_INVAL) {
+		if (!event_seg && (trb_comp_code == COMP_STOP ||
+				   trb_comp_code == COMP_STOP_INVAL)) {
 			ret = 0;
 			goto cleanup;
 		}
@@ -2626,7 +2613,7 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 				 * successful event after a short transfer.
 				 * Ignore it.
 				 */
-				if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && 
+				if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) &&
 						ep_ring->last_td_was_short) {
 					ep_ring->last_td_was_short = false;
 					ret = 0;
@@ -2691,17 +2678,8 @@ cleanup:
 		if (ret) {
 			urb = td->urb;
 			urb_priv = urb->hcpriv;
-			/* Leave the TD around for the reset endpoint function
-			 * to use(but only if it's not a control endpoint,
-			 * since we already queued the Set TR dequeue pointer
-			 * command for stalled control endpoints).
-			 */
-			if (usb_endpoint_xfer_control(&urb->ep->desc) ||
-				(trb_comp_code != COMP_STALL &&
-					trb_comp_code != COMP_BABBLE))
-				xhci_urb_free_priv(xhci, urb_priv);
-			else
-				kfree(urb_priv);
+
+			xhci_urb_free_priv(xhci, urb_priv);
 
 			usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb);
 			if ((urb->actual_length != urb->transfer_buffer_length &&
@@ -3668,7 +3646,7 @@ static unsigned int xhci_get_burst_count(struct xhci_hcd *xhci,
 		return 0;
 
 	max_burst = urb->ep->ss_ep_comp.bMaxBurst;
-	return roundup(total_packet_count, max_burst + 1) - 1;
+	return DIV_ROUND_UP(total_packet_count, max_burst + 1) - 1;
 }
 
 /*
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 924a6ccdb622..16f4f8dc1ae9 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -35,6 +35,8 @@
 #define DRIVER_AUTHOR "Sarah Sharp"
 #define DRIVER_DESC "'eXtensible' Host Controller (xHC) Driver"
 
+#define	PORT_WAKE_BITS	(PORT_WKOC_E | PORT_WKDISC_E | PORT_WKCONN_E)
+
 /* Some 0.95 hardware can't handle the chain bit on a Link TRB being cleared */
 static int link_quirk;
 module_param(link_quirk, int, S_IRUGO | S_IWUSR);
@@ -404,16 +406,16 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd)
 
 #else
 
-static int xhci_try_enable_msi(struct usb_hcd *hcd)
+static inline int xhci_try_enable_msi(struct usb_hcd *hcd)
 {
 	return 0;
 }
 
-static void xhci_cleanup_msix(struct xhci_hcd *xhci)
+static inline void xhci_cleanup_msix(struct xhci_hcd *xhci)
 {
 }
 
-static void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
+static inline void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
 {
 }
 
@@ -842,13 +844,47 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci)
 	xhci_set_cmd_ring_deq(xhci);
 }
 
+static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
+{
+	int port_index;
+	__le32 __iomem **port_array;
+	unsigned long flags;
+	u32 t1, t2;
+
+	spin_lock_irqsave(&xhci->lock, flags);
+
+	/* disble usb3 ports Wake bits*/
+	port_index = xhci->num_usb3_ports;
+	port_array = xhci->usb3_ports;
+	while (port_index--) {
+		t1 = readl(port_array[port_index]);
+		t1 = xhci_port_state_to_neutral(t1);
+		t2 = t1 & ~PORT_WAKE_BITS;
+		if (t1 != t2)
+			writel(t2, port_array[port_index]);
+	}
+
+	/* disble usb2 ports Wake bits*/
+	port_index = xhci->num_usb2_ports;
+	port_array = xhci->usb2_ports;
+	while (port_index--) {
+		t1 = readl(port_array[port_index]);
+		t1 = xhci_port_state_to_neutral(t1);
+		t2 = t1 & ~PORT_WAKE_BITS;
+		if (t1 != t2)
+			writel(t2, port_array[port_index]);
+	}
+
+	spin_unlock_irqrestore(&xhci->lock, flags);
+}
+
 /*
  * Stop HC (not bus-specific)
  *
  * This is called when the machine transition into S3/S4 mode.
  *
  */
-int xhci_suspend(struct xhci_hcd *xhci)
+int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup)
 {
 	int			rc = 0;
 	unsigned int		delay = XHCI_MAX_HALT_USEC;
@@ -859,6 +895,10 @@ int xhci_suspend(struct xhci_hcd *xhci)
 			xhci->shared_hcd->state != HC_STATE_SUSPENDED)
 		return -EINVAL;
 
+	/* Clear root port wake on bits if wakeup not allowed. */
+	if (!do_wakeup)
+		xhci_disable_port_wake_on_bits(xhci);
+
 	/* Don't poll the roothubs on bus suspend. */
 	xhci_dbg(xhci, "%s: stopping port polling.\n", __func__);
 	clear_bit(HCD_FLAG_POLL_RH, &hcd->flags);
@@ -928,7 +968,7 @@ int xhci_suspend(struct xhci_hcd *xhci)
  */
 int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 {
-	u32			command, temp = 0;
+	u32			command, temp = 0, status;
 	struct usb_hcd		*hcd = xhci_to_hcd(xhci);
 	struct usb_hcd		*secondary_hcd;
 	int			retval = 0;
@@ -1046,8 +1086,12 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 
  done:
 	if (retval == 0) {
-		usb_hcd_resume_root_hub(hcd);
-		usb_hcd_resume_root_hub(xhci->shared_hcd);
+		/* Resume root hubs only when have pending events. */
+		status = readl(&xhci->op_regs->status);
+		if (status & STS_EINT) {
+			usb_hcd_resume_root_hub(hcd);
+			usb_hcd_resume_root_hub(xhci->shared_hcd);
+		}
 	}
 
 	/*
@@ -2881,64 +2925,33 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci,
 	}
 }
 
-/* Deal with stalled endpoints.  The core should have sent the control message
- * to clear the halt condition.  However, we need to make the xHCI hardware
- * reset its sequence number, since a device will expect a sequence number of
- * zero after the halt condition is cleared.
+/* Called when clearing halted device. The core should have sent the control
+ * message to clear the device halt condition. The host side of the halt should
+ * already be cleared with a reset endpoint command issued when the STALL tx
+ * event was received.
+ *
  * Context: in_interrupt
  */
+
 void xhci_endpoint_reset(struct usb_hcd *hcd,
 		struct usb_host_endpoint *ep)
 {
 	struct xhci_hcd *xhci;
-	struct usb_device *udev;
-	unsigned int ep_index;
-	unsigned long flags;
-	int ret;
-	struct xhci_virt_ep *virt_ep;
 
 	xhci = hcd_to_xhci(hcd);
-	udev = (struct usb_device *) ep->hcpriv;
-	/* Called with a root hub endpoint (or an endpoint that wasn't added
-	 * with xhci_add_endpoint()
-	 */
-	if (!ep->hcpriv)
-		return;
-	ep_index = xhci_get_endpoint_index(&ep->desc);
-	virt_ep = &xhci->devs[udev->slot_id]->eps[ep_index];
-	if (!virt_ep->stopped_td) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
-			"Endpoint 0x%x not halted, refusing to reset.",
-			ep->desc.bEndpointAddress);
-		return;
-	}
-	if (usb_endpoint_xfer_control(&ep->desc)) {
-		xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
-				"Control endpoint stall already handled.");
-		return;
-	}
 
-	xhci_dbg_trace(xhci, trace_xhci_dbg_reset_ep,
-			"Queueing reset endpoint command");
-	spin_lock_irqsave(&xhci->lock, flags);
-	ret = xhci_queue_reset_ep(xhci, udev->slot_id, ep_index);
 	/*
-	 * Can't change the ring dequeue pointer until it's transitioned to the
-	 * stopped state, which is only upon a successful reset endpoint
-	 * command.  Better hope that last command worked!
+	 * We might need to implement the config ep cmd in xhci 4.8.1 note:
+	 * The Reset Endpoint Command may only be issued to endpoints in the
+	 * Halted state. If software wishes reset the Data Toggle or Sequence
+	 * Number of an endpoint that isn't in the Halted state, then software
+	 * may issue a Configure Endpoint Command with the Drop and Add bits set
+	 * for the target endpoint. that is in the Stopped state.
 	 */
-	if (!ret) {
-		xhci_cleanup_stalled_ring(xhci, udev, ep_index);
-		kfree(virt_ep->stopped_td);
-		xhci_ring_cmd_db(xhci);
-	}
-	virt_ep->stopped_td = NULL;
-	virt_ep->stopped_trb = NULL;
-	virt_ep->stopped_stream = 0;
-	spin_unlock_irqrestore(&xhci->lock, flags);
 
-	if (ret)
-		xhci_warn(xhci, "FIXME allocate a new ring segment\n");
+	/* For now just print debug to follow the situation */
+	xhci_dbg(xhci, "Endpoint 0x%x ep reset callback called\n",
+		 ep->desc.bEndpointAddress);
 }
 
 static int xhci_check_streams_endpoint(struct xhci_hcd *xhci,
@@ -3925,13 +3938,21 @@ static int __maybe_unused xhci_change_max_exit_latency(struct xhci_hcd *xhci,
 	int ret;
 
 	spin_lock_irqsave(&xhci->lock, flags);
-	if (max_exit_latency == xhci->devs[udev->slot_id]->current_mel) {
+
+	virt_dev = xhci->devs[udev->slot_id];
+
+	/*
+	 * virt_dev might not exists yet if xHC resumed from hibernate (S4) and
+	 * xHC was re-initialized. Exit latency will be set later after
+	 * hub_port_finish_reset() is done and xhci->devs[] are re-allocated
+	 */
+
+	if (!virt_dev || max_exit_latency == virt_dev->current_mel) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
 		return 0;
 	}
 
 	/* Attempt to issue an Evaluate Context command to change the MEL. */
-	virt_dev = xhci->devs[udev->slot_id];
 	command = xhci->lpm_command;
 	ctrl_ctx = xhci_get_input_control_ctx(xhci, command->in_ctx);
 	if (!ctrl_ctx) {
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 58ed9d088e63..96e9e780ccae 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -864,8 +864,6 @@ struct xhci_virt_ep {
 #define EP_GETTING_NO_STREAMS	(1 << 5)
 	/* ----  Related to URB cancellation ---- */
 	struct list_head	cancelled_td_list;
-	/* The TRB that was last reported in a stopped endpoint ring */
-	union xhci_trb		*stopped_trb;
 	struct xhci_td		*stopped_td;
 	unsigned int		stopped_stream;
 	/* Watchdog timer for stop endpoint command to cancel URBs */
@@ -1762,7 +1760,7 @@ void xhci_shutdown(struct usb_hcd *hcd);
 int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks);
 
 #ifdef	CONFIG_PM
-int xhci_suspend(struct xhci_hcd *xhci);
+int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup);
 int xhci_resume(struct xhci_hcd *xhci, bool hibernated);
 #else
 #define	xhci_suspend	NULL
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index de98906f786d..0aef801edbc1 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -3248,6 +3248,7 @@ static const struct usb_device_id sisusb_table[] = {
 	{ USB_DEVICE(0x0711, 0x0918) },
 	{ USB_DEVICE(0x0711, 0x0920) },
 	{ USB_DEVICE(0x0711, 0x0950) },
+	{ USB_DEVICE(0x0711, 0x5200) },
 	{ USB_DEVICE(0x182d, 0x021c) },
 	{ USB_DEVICE(0x182d, 0x0269) },
 	{ }
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index f6568b5e9b06..71dcacbab398 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -7,7 +7,7 @@
 #include <linux/moduleparam.h>
 #include <linux/scatterlist.h>
 #include <linux/mutex.h>
-
+#include <linux/timer.h>
 #include <linux/usb.h>
 
 #define SIMPLE_IO_TIMEOUT	10000	/* in milliseconds */
@@ -484,6 +484,14 @@ alloc_sglist(int nents, int max, int vary)
 	return sg;
 }
 
+static void sg_timeout(unsigned long _req)
+{
+	struct usb_sg_request	*req = (struct usb_sg_request *) _req;
+
+	req->status = -ETIMEDOUT;
+	usb_sg_cancel(req);
+}
+
 static int perform_sglist(
 	struct usbtest_dev	*tdev,
 	unsigned		iterations,
@@ -495,6 +503,9 @@ static int perform_sglist(
 {
 	struct usb_device	*udev = testdev_to_usbdev(tdev);
 	int			retval = 0;
+	struct timer_list	sg_timer;
+
+	setup_timer_on_stack(&sg_timer, sg_timeout, (unsigned long) req);
 
 	while (retval == 0 && iterations-- > 0) {
 		retval = usb_sg_init(req, udev, pipe,
@@ -505,7 +516,10 @@ static int perform_sglist(
 
 		if (retval)
 			break;
+		mod_timer(&sg_timer, jiffies +
+				msecs_to_jiffies(SIMPLE_IO_TIMEOUT));
 		usb_sg_wait(req);
+		del_timer_sync(&sg_timer);
 		retval = req->status;
 
 		/* FIXME check resulting data pattern */
@@ -1320,6 +1334,11 @@ static int unlink1(struct usbtest_dev *dev, int pipe, int size, int async)
 	urb->context = &completion;
 	urb->complete = unlink1_callback;
 
+	if (usb_pipeout(urb->pipe)) {
+		simple_fill_buf(urb);
+		urb->transfer_flags |= URB_ZERO_PACKET;
+	}
+
 	/* keep the endpoint busy.  there are lots of hc/hcd-internal
 	 * states, and testing should get to all of them over time.
 	 *
@@ -1450,6 +1469,11 @@ static int unlink_queued(struct usbtest_dev *dev, int pipe, unsigned num,
 				unlink_queued_callback, &ctx);
 		ctx.urbs[i]->transfer_dma = buf_dma;
 		ctx.urbs[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP;
+
+		if (usb_pipeout(ctx.urbs[i]->pipe)) {
+			simple_fill_buf(ctx.urbs[i]);
+			ctx.urbs[i]->transfer_flags |= URB_ZERO_PACKET;
+		}
 	}
 
 	/* Submit all the URBs and then unlink URBs num - 4 and num - 2. */
diff --git a/drivers/usb/musb/musb_am335x.c b/drivers/usb/musb/musb_am335x.c
index d2353781bd2d..1e58ed2361cc 100644
--- a/drivers/usb/musb/musb_am335x.c
+++ b/drivers/usb/musb/musb_am335x.c
@@ -19,21 +19,6 @@ err:
 	return ret;
 }
 
-static int of_remove_populated_child(struct device *dev, void *d)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-
-	of_device_unregister(pdev);
-	return 0;
-}
-
-static int am335x_child_remove(struct platform_device *pdev)
-{
-	device_for_each_child(&pdev->dev, NULL, of_remove_populated_child);
-	pm_runtime_disable(&pdev->dev);
-	return 0;
-}
-
 static const struct of_device_id am335x_child_of_match[] = {
 	{ .compatible = "ti,am33xx-usb" },
 	{  },
@@ -42,13 +27,17 @@ MODULE_DEVICE_TABLE(of, am335x_child_of_match);
 
 static struct platform_driver am335x_child_driver = {
 	.probe		= am335x_child_probe,
-	.remove         = am335x_child_remove,
 	.driver         = {
 		.name   = "am335x-usb-childs",
 		.of_match_table	= am335x_child_of_match,
 	},
 };
 
-module_platform_driver(am335x_child_driver);
+static int __init am335x_child_init(void)
+{
+	return platform_driver_register(&am335x_child_driver);
+}
+module_init(am335x_child_init);
+
 MODULE_DESCRIPTION("AM33xx child devices");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 239ad0b1ceb6..07576907e2c6 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -438,7 +438,6 @@ void musb_hnp_stop(struct musb *musb)
 static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 				u8 devctl)
 {
-	struct usb_otg *otg = musb->xceiv->otg;
 	irqreturn_t handled = IRQ_NONE;
 
 	dev_dbg(musb->controller, "<== DevCtl=%02x, int_usb=0x%x\n", devctl,
@@ -656,7 +655,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 				break;
 		case OTG_STATE_B_PERIPHERAL:
 			musb_g_suspend(musb);
-			musb->is_active = otg->gadget->b_hnp_enable;
+			musb->is_active = musb->g.b_hnp_enable;
 			if (musb->is_active) {
 				musb->xceiv->state = OTG_STATE_B_WAIT_ACON;
 				dev_dbg(musb->controller, "HNP: Setting timer for b_ase0_brst\n");
@@ -672,7 +671,7 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 			break;
 		case OTG_STATE_A_HOST:
 			musb->xceiv->state = OTG_STATE_A_SUSPEND;
-			musb->is_active = otg->host->b_hnp_enable;
+			musb->is_active = musb->hcd->self.b_hnp_enable;
 			break;
 		case OTG_STATE_B_HOST:
 			/* Transition to B_PERIPHERAL, see 6.8.2.6 p 44 */
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index f88929609bac..1d29bbfeb9d5 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -190,7 +190,8 @@ static enum hrtimer_restart cppi41_recheck_tx_req(struct hrtimer *timer)
 		}
 	}
 
-	if (!list_empty(&controller->early_tx_list)) {
+	if (!list_empty(&controller->early_tx_list) &&
+	    !hrtimer_is_queued(&controller->early_tx)) {
 		ret = HRTIMER_RESTART;
 		hrtimer_forward_now(&controller->early_tx,
 				ktime_set(0, 150 * NSEC_PER_USEC));
@@ -266,7 +267,7 @@ static void cppi41_dma_callback(void *private_data)
 		}
 		list_add_tail(&cppi41_channel->tx_check,
 				&controller->early_tx_list);
-		if (!hrtimer_active(&controller->early_tx)) {
+		if (!hrtimer_is_queued(&controller->early_tx)) {
 			hrtimer_start_range_ns(&controller->early_tx,
 				ktime_set(0, 140 * NSEC_PER_USEC),
 				40 * NSEC_PER_USEC,
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 7a109eae9b9a..865243e818b7 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -707,6 +707,7 @@ static int dsps_suspend(struct device *dev)
 	struct musb *musb = platform_get_drvdata(glue->musb);
 	void __iomem *mbase = musb->ctrl_base;
 
+	del_timer_sync(&glue->timer);
 	glue->context.control = dsps_readl(mbase, wrp->control);
 	glue->context.epintr = dsps_readl(mbase, wrp->epintr_set);
 	glue->context.coreintr = dsps_readl(mbase, wrp->coreintr_set);
@@ -732,6 +733,9 @@ static int dsps_resume(struct device *dev)
 	dsps_writel(mbase, wrp->mode, glue->context.mode);
 	dsps_writel(mbase, wrp->tx_mode, glue->context.tx_mode);
 	dsps_writel(mbase, wrp->rx_mode, glue->context.rx_mode);
+	if (musb->xceiv->state == OTG_STATE_B_IDLE &&
+	    musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
+		mod_timer(&glue->timer, jiffies + wrp->poll_seconds * HZ);
 
 	return 0;
 }
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 8aa59a2c5eb2..8e90d327e52b 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -416,6 +416,7 @@ static int omap2430_musb_init(struct musb *musb)
 		omap_musb_set_mailbox(glue);
 
 	phy_init(musb->phy);
+	phy_power_on(musb->phy);
 
 	pm_runtime_put_noidle(musb->controller);
 	return 0;
@@ -478,6 +479,7 @@ static int omap2430_musb_exit(struct musb *musb)
 	del_timer_sync(&musb_idle_timer);
 
 	omap2430_low_level_exit(musb);
+	phy_power_off(musb->phy);
 	phy_exit(musb->phy);
 
 	return 0;
diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c
index c2e45e632723..f202e5088461 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -274,7 +274,6 @@ static int ux500_probe(struct platform_device *pdev)
 	musb->dev.parent		= &pdev->dev;
 	musb->dev.dma_mask		= &pdev->dev.coherent_dma_mask;
 	musb->dev.coherent_dma_mask	= pdev->dev.coherent_dma_mask;
-	musb->dev.of_node		= pdev->dev.of_node;
 
 	glue->dev			= &pdev->dev;
 	glue->musb			= musb;
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 7d1451d5bbea..5998c1d491ef 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -253,7 +253,7 @@ config USB_RCAR_GEN2_PHY
 
 config USB_ULPI
 	bool "Generic ULPI Transceiver Driver"
-	depends on ARM
+	depends on ARM || ARM64
 	help
 	  Enable this to support ULPI connected USB OTG transceivers which
 	  are likely found on embedded boards.
diff --git a/drivers/usb/phy/phy-am335x-control.c b/drivers/usb/phy/phy-am335x-control.c
index d75196ad5f2f..35b6083b7999 100644
--- a/drivers/usb/phy/phy-am335x-control.c
+++ b/drivers/usb/phy/phy-am335x-control.c
@@ -3,6 +3,7 @@
 #include <linux/err.h>
 #include <linux/of.h>
 #include <linux/io.h>
+#include <linux/delay.h>
 #include "am35x-phy-control.h"
 
 struct am335x_control_usb {
@@ -86,6 +87,14 @@ static void am335x_phy_power(struct phy_control *phy_ctrl, u32 id, bool on)
 	}
 
 	writel(val, usb_ctrl->phy_reg + reg);
+
+	/*
+	 * Give the PHY ~1ms to complete the power up operation.
+	 * Tests have shown unstable behaviour if other USB PHY related
+	 * registers are written too shortly after such a transition.
+	 */
+	if (on)
+		mdelay(1);
 }
 
 static const struct phy_control ctrl_am335x = {
diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c
index 6e146d723b37..69e49be8866b 100644
--- a/drivers/usb/phy/phy-isp1301-omap.c
+++ b/drivers/usb/phy/phy-isp1301-omap.c
@@ -1295,7 +1295,7 @@ isp1301_set_host(struct usb_otg *otg, struct usb_bus *host)
 		return isp1301_otg_enable(isp);
 	return 0;
 
-#elif	!defined(CONFIG_USB_GADGET_OMAP)
+#elif !IS_ENABLED(CONFIG_USB_OMAP)
 	// FIXME update its refcount
 	otg->host = host;
 
diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c
index bbe4f8e6e8d7..8834b70c868c 100644
--- a/drivers/usb/phy/phy-tegra-usb.c
+++ b/drivers/usb/phy/phy-tegra-usb.c
@@ -881,8 +881,8 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy,
 		return -ENOMEM;
 	}
 
-	tegra_phy->config = devm_kzalloc(&pdev->dev,
-		sizeof(*tegra_phy->config), GFP_KERNEL);
+	tegra_phy->config = devm_kzalloc(&pdev->dev, sizeof(*config),
+					 GFP_KERNEL);
 	if (!tegra_phy->config) {
 		dev_err(&pdev->dev,
 			"unable to allocate memory for USB UTMIP config\n");
diff --git a/drivers/usb/phy/phy-ulpi.c b/drivers/usb/phy/phy-ulpi.c
index 217339dd7a90..4e3877c329f2 100644
--- a/drivers/usb/phy/phy-ulpi.c
+++ b/drivers/usb/phy/phy-ulpi.c
@@ -47,6 +47,9 @@ struct ulpi_info {
 static struct ulpi_info ulpi_ids[] = {
 	ULPI_INFO(ULPI_ID(0x04cc, 0x1504), "NXP ISP1504"),
 	ULPI_INFO(ULPI_ID(0x0424, 0x0006), "SMSC USB331x"),
+	ULPI_INFO(ULPI_ID(0x0424, 0x0007), "SMSC USB3320"),
+	ULPI_INFO(ULPI_ID(0x0424, 0x0009), "SMSC USB334x"),
+	ULPI_INFO(ULPI_ID(0x0451, 0x1507), "TI TUSB1210"),
 };
 
 static int ulpi_set_otg_flags(struct usb_phy *phy)
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index 8afa813d690b..0180eef05656 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -229,6 +229,9 @@ struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index)
 	phy = __usb_find_phy_dev(dev, &phy_bind_list, index);
 	if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) {
 		dev_dbg(dev, "unable to find transceiver\n");
+		if (!IS_ERR(phy))
+			phy = ERR_PTR(-ENODEV);
+
 		goto err0;
 	}
 
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 35a2373cde67..9374bd2aba20 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -97,13 +97,19 @@ static int usb_serial_device_remove(struct device *dev)
 	struct usb_serial_port *port;
 	int retval = 0;
 	int minor;
+	int autopm_err;
 
 	port = to_usb_serial_port(dev);
 	if (!port)
 		return -ENODEV;
 
-	/* make sure suspend/resume doesn't race against port_remove */
-	usb_autopm_get_interface(port->serial->interface);
+	/*
+	 * Make sure suspend/resume doesn't race against port_remove.
+	 *
+	 * Note that no further runtime PM callbacks will be made if
+	 * autopm_get fails.
+	 */
+	autopm_err = usb_autopm_get_interface(port->serial->interface);
 
 	minor = port->minor;
 	tty_unregister_device(usb_serial_tty_driver, minor);
@@ -117,7 +123,9 @@ static int usb_serial_device_remove(struct device *dev)
 	dev_info(dev, "%s converter now disconnected from ttyUSB%d\n",
 		 driver->description, minor);
 
-	usb_autopm_put_interface(port->serial->interface);
+	if (!autopm_err)
+		usb_autopm_put_interface(port->serial->interface);
+
 	return retval;
 }
 
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 95fa1217afdd..5741e9405069 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -104,6 +104,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8218) }, /* Lipowsky Industrie Elektronik GmbH, HARP-1 */
 	{ USB_DEVICE(0x10C4, 0x822B) }, /* Modem EDGE(GSM) Comander 2 */
 	{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */
+	{ USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */
 	{ USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */
 	{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
 	{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
@@ -119,8 +120,10 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
 	{ USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */
 	{ USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */
+	{ USB_DEVICE(0x10C4, 0x8875) }, /* CEL MeshConnect USB Stick */
 	{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
 	{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+	{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
 	{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
 	{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
@@ -152,7 +155,10 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
+	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
+	{ USB_DEVICE(0x1BA4, 0x0002) },	/* Silicon Labs 358x factory default */
 	{ USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */
+	{ USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */
 	{ USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */
 	{ USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */
 	{ USB_DEVICE(0x1FB9, 0x0100) }, /* Lake Shore Model 121 Current Source */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 44ab12986805..debcdef4cbf0 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -145,12 +145,14 @@ static struct ftdi_sio_quirk ftdi_8u2232c_quirk = {
  * /sys/bus/usb-serial/drivers/ftdi_sio/new_id and send a patch or report.
  */
 static const struct usb_device_id id_table_combined[] = {
+	{ USB_DEVICE(FTDI_VID, FTDI_BRICK_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ZEITCONTROL_TAGTRACE_MIFARE_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CTI_MINI_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CTI_NANO_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_BM_ATOM_NANO_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) },
@@ -481,6 +483,39 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FD_PID) },
 	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FE_PID) },
 	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FF_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_4701_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9300_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9301_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9302_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9303_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9304_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9305_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9306_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9307_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9308_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9309_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930A_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930B_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930C_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930D_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930E_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930F_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9310_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9311_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9312_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9313_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9314_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9315_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9316_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9317_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9318_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9319_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931A_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931B_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931C_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931D_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931E_PID) },
+	{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931F_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PERLE_ULTRAPORT_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PIEGROUP_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TNC_X_PID) },
@@ -580,6 +615,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_TAVIR_STK500_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TIAO_UMPA_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID),
+		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	/*
 	 * ELV devices:
 	 */
@@ -671,6 +708,10 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) },
@@ -718,7 +759,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) },
-	{ USB_DEVICE(TESTO_VID, TESTO_USB_INTERFACE_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_1_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_3_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_GAMMA_SCOUT_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13M_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13S_PID) },
@@ -735,6 +777,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk },
 	{ USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) },
+	{ USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) },
 	{ USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S03_PID) },
 	{ USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_59_PID) },
 	{ USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_57A_PID) },
@@ -909,6 +952,45 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) },
 	/* Cressi Devices */
 	{ USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) },
+	/* Brainboxes Devices */
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_001_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_012_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_023_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_034_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_101_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_4_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_5_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_6_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_7_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_8_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_257_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_4_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_313_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_324_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_357_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_1_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) },
+	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) },
+	/* ekey Devices */
+	{ USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) },
+	/* Infineon Devices */
+	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
+	/* GE Healthcare devices */
+	{ USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) },
 	{ }					/* Terminating entry */
 };
 
@@ -1531,14 +1613,17 @@ static void ftdi_set_max_packet_size(struct usb_serial_port *port)
 	struct usb_device *udev = serial->dev;
 
 	struct usb_interface *interface = serial->interface;
-	struct usb_endpoint_descriptor *ep_desc = &interface->cur_altsetting->endpoint[1].desc;
+	struct usb_endpoint_descriptor *ep_desc;
 
 	unsigned num_endpoints;
-	int i;
+	unsigned i;
 
 	num_endpoints = interface->cur_altsetting->desc.bNumEndpoints;
 	dev_info(&udev->dev, "Number of endpoints %d\n", num_endpoints);
 
+	if (!num_endpoints)
+		return;
+
 	/* NOTE: some customers have programmed FT232R/FT245R devices
 	 * with an endpoint size of 0 - not good.  In this case, we
 	 * want to override the endpoint descriptor setting and use a
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index e599fbfcde5f..e52409c9be99 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -30,6 +30,12 @@
 
 /*** third-party PIDs (using FTDI_VID) ***/
 
+/*
+ * Certain versions of the official Windows FTDI driver reprogrammed
+ * counterfeit FTDI devices to PID 0. Support these devices anyway.
+ */
+#define FTDI_BRICK_PID		0x0000
+
 #define FTDI_LUMEL_PD12_PID	0x6002
 
 /*
@@ -42,6 +48,8 @@
 /* www.candapter.com Ewert Energy Systems CANdapter device */
 #define FTDI_CANDAPTER_PID 0x9F80 /* Product Id */
 
+#define FTDI_BM_ATOM_NANO_PID	0xa559	/* Basic Micro ATOM Nano USB2Serial */
+
 /*
  * Texas Instruments XDS100v2 JTAG / BeagleBone A3
  * http://processors.wiki.ti.com/index.php/XDS100
@@ -140,12 +148,19 @@
 /*
  * Xsens Technologies BV products (http://www.xsens.com).
  */
-#define XSENS_CONVERTER_0_PID	0xD388
-#define XSENS_CONVERTER_1_PID	0xD389
+#define XSENS_VID		0x2639
+#define XSENS_AWINDA_STATION_PID 0x0101
+#define XSENS_AWINDA_DONGLE_PID 0x0102
+#define XSENS_MTW_PID		0x0200	/* Xsens MTw */
+#define XSENS_CONVERTER_PID	0xD00D	/* Xsens USB-serial converter */
+
+/* Xsens devices using FTDI VID */
+#define XSENS_CONVERTER_0_PID	0xD388	/* Xsens USB converter */
+#define XSENS_CONVERTER_1_PID	0xD389	/* Xsens Wireless Receiver */
 #define XSENS_CONVERTER_2_PID	0xD38A
-#define XSENS_CONVERTER_3_PID	0xD38B
-#define XSENS_CONVERTER_4_PID	0xD38C
-#define XSENS_CONVERTER_5_PID	0xD38D
+#define XSENS_CONVERTER_3_PID	0xD38B	/* Xsens USB-serial converter */
+#define XSENS_CONVERTER_4_PID	0xD38C	/* Xsens Wireless Receiver */
+#define XSENS_CONVERTER_5_PID	0xD38D	/* Xsens Awinda Station */
 #define XSENS_CONVERTER_6_PID	0xD38E
 #define XSENS_CONVERTER_7_PID	0xD38F
 
@@ -538,6 +553,11 @@
  */
 #define FTDI_TIAO_UMPA_PID	0x8a98	/* TIAO/DIYGADGET USB Multi-Protocol Adapter */
 
+/*
+ * NovaTech product ids (FTDI_VID)
+ */
+#define FTDI_NT_ORIONLXM_PID	0x7c90	/* OrionLXm Substation Automation Platform */
+
 
 /********************************/
 /** third-party VID/PID combos **/
@@ -579,6 +599,12 @@
 #define RATOC_PRODUCT_ID_USB60F	0xb020
 
 /*
+ * Infineon Technologies
+ */
+#define INFINEON_VID		0x058b
+#define INFINEON_TRIBOARD_PID	0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+
+/*
  * Acton Research Corp.
  */
 #define ACTON_VID		0x0647	/* Vendor ID */
@@ -793,7 +819,8 @@
  * Submitted by Colin Leroy
  */
 #define TESTO_VID			0x128D
-#define TESTO_USB_INTERFACE_PID		0x0001
+#define TESTO_1_PID			0x0001
+#define TESTO_3_PID			0x0003
 
 /*
  * Mobility Electronics products.
@@ -820,6 +847,12 @@
 #define TELLDUS_TELLSTICK_PID		0x0C30	/* RF control dongle 433 MHz using FT232RL */
 
 /*
+ * NOVITUS printers
+ */
+#define NOVITUS_VID			0x1a28
+#define NOVITUS_BONO_E_PID		0x6010
+
+/*
  * RT Systems programming cables for various ham radios
  */
 #define RTSYSTEMS_VID		0x2100	/* Vendor ID */
@@ -893,8 +926,8 @@
 #define BAYER_CONTOUR_CABLE_PID        0x6001
 
 /*
- * The following are the values for the Matrix Orbital FTDI Range
- * Anything in this range will use an FT232RL.
+ * Matrix Orbital Intelligent USB displays.
+ * http://www.matrixorbital.com
  */
 #define MTXORB_VID			0x1B3D
 #define MTXORB_FTDI_RANGE_0100_PID	0x0100
@@ -1153,8 +1186,39 @@
 #define MTXORB_FTDI_RANGE_01FD_PID	0x01FD
 #define MTXORB_FTDI_RANGE_01FE_PID	0x01FE
 #define MTXORB_FTDI_RANGE_01FF_PID	0x01FF
-
-
+#define MTXORB_FTDI_RANGE_4701_PID	0x4701
+#define MTXORB_FTDI_RANGE_9300_PID	0x9300
+#define MTXORB_FTDI_RANGE_9301_PID	0x9301
+#define MTXORB_FTDI_RANGE_9302_PID	0x9302
+#define MTXORB_FTDI_RANGE_9303_PID	0x9303
+#define MTXORB_FTDI_RANGE_9304_PID	0x9304
+#define MTXORB_FTDI_RANGE_9305_PID	0x9305
+#define MTXORB_FTDI_RANGE_9306_PID	0x9306
+#define MTXORB_FTDI_RANGE_9307_PID	0x9307
+#define MTXORB_FTDI_RANGE_9308_PID	0x9308
+#define MTXORB_FTDI_RANGE_9309_PID	0x9309
+#define MTXORB_FTDI_RANGE_930A_PID	0x930A
+#define MTXORB_FTDI_RANGE_930B_PID	0x930B
+#define MTXORB_FTDI_RANGE_930C_PID	0x930C
+#define MTXORB_FTDI_RANGE_930D_PID	0x930D
+#define MTXORB_FTDI_RANGE_930E_PID	0x930E
+#define MTXORB_FTDI_RANGE_930F_PID	0x930F
+#define MTXORB_FTDI_RANGE_9310_PID	0x9310
+#define MTXORB_FTDI_RANGE_9311_PID	0x9311
+#define MTXORB_FTDI_RANGE_9312_PID	0x9312
+#define MTXORB_FTDI_RANGE_9313_PID	0x9313
+#define MTXORB_FTDI_RANGE_9314_PID	0x9314
+#define MTXORB_FTDI_RANGE_9315_PID	0x9315
+#define MTXORB_FTDI_RANGE_9316_PID	0x9316
+#define MTXORB_FTDI_RANGE_9317_PID	0x9317
+#define MTXORB_FTDI_RANGE_9318_PID	0x9318
+#define MTXORB_FTDI_RANGE_9319_PID	0x9319
+#define MTXORB_FTDI_RANGE_931A_PID	0x931A
+#define MTXORB_FTDI_RANGE_931B_PID	0x931B
+#define MTXORB_FTDI_RANGE_931C_PID	0x931C
+#define MTXORB_FTDI_RANGE_931D_PID	0x931D
+#define MTXORB_FTDI_RANGE_931E_PID	0x931E
+#define MTXORB_FTDI_RANGE_931F_PID	0x931F
 
 /*
  * The Mobility Lab (TML)
@@ -1326,3 +1390,51 @@
  * Manufacturer: Cressi
  */
 #define FTDI_CRESSI_PID		0x87d0
+
+/*
+ * Brainboxes devices
+ */
+#define BRAINBOXES_VID			0x05d1
+#define BRAINBOXES_VX_001_PID		0x1001 /* VX-001 ExpressCard 1 Port RS232 */
+#define BRAINBOXES_VX_012_PID		0x1002 /* VX-012 ExpressCard 2 Port RS232 */
+#define BRAINBOXES_VX_023_PID		0x1003 /* VX-023 ExpressCard 1 Port RS422/485 */
+#define BRAINBOXES_VX_034_PID		0x1004 /* VX-034 ExpressCard 2 Port RS422/485 */
+#define BRAINBOXES_US_101_PID		0x1011 /* US-101 1xRS232 */
+#define BRAINBOXES_US_324_PID		0x1013 /* US-324 1xRS422/485 1Mbaud */
+#define BRAINBOXES_US_606_1_PID		0x2001 /* US-606 6 Port RS232 Serial Port 1 and 2 */
+#define BRAINBOXES_US_606_2_PID		0x2002 /* US-606 6 Port RS232 Serial Port 3 and 4 */
+#define BRAINBOXES_US_606_3_PID		0x2003 /* US-606 6 Port RS232 Serial Port 4 and 6 */
+#define BRAINBOXES_US_701_1_PID		0x2011 /* US-701 4xRS232 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_701_2_PID		0x2012 /* US-701 4xRS422 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_279_1_PID		0x2021 /* US-279 8xRS422 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_279_2_PID		0x2022 /* US-279 8xRS422 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_279_3_PID		0x2023 /* US-279 8xRS422 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_279_4_PID		0x2024 /* US-279 8xRS422 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_346_1_PID		0x3011 /* US-346 4xRS422/485 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_346_2_PID		0x3012 /* US-346 4xRS422/485 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_257_PID		0x5001 /* US-257 2xRS232 1Mbaud */
+#define BRAINBOXES_US_313_PID		0x6001 /* US-313 2xRS422/485 1Mbaud */
+#define BRAINBOXES_US_357_PID		0x7001 /* US_357 1xRS232/422/485 */
+#define BRAINBOXES_US_842_1_PID		0x8001 /* US-842 8xRS422/485 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_842_2_PID		0x8002 /* US-842 8xRS422/485 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_842_3_PID		0x8003 /* US-842 8xRS422/485 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_842_4_PID		0x8004 /* US-842 8xRS422/485 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_160_1_PID		0x9001 /* US-160 16xRS232 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_160_2_PID		0x9002 /* US-160 16xRS232 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_160_3_PID		0x9003 /* US-160 16xRS232 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_160_4_PID		0x9004 /* US-160 16xRS232 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_160_5_PID		0x9005 /* US-160 16xRS232 1Mbaud Port 9 and 10 */
+#define BRAINBOXES_US_160_6_PID		0x9006 /* US-160 16xRS232 1Mbaud Port 11 and 12 */
+#define BRAINBOXES_US_160_7_PID		0x9007 /* US-160 16xRS232 1Mbaud Port 13 and 14 */
+#define BRAINBOXES_US_160_8_PID		0x9008 /* US-160 16xRS232 1Mbaud Port 15 and 16 */
+
+/*
+ * ekey biometric systems GmbH (http://ekey.net/)
+ */
+#define FTDI_EKEY_CONV_USB_PID		0xCB08	/* Converter USB */
+
+/*
+ * GE Healthcare devices
+ */
+#define GE_HEALTHCARE_VID		0x1901
+#define GE_HEALTHCARE_NEMO_TRACKER_PID	0x0015
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index a2db5be9c305..c0a42e9e6777 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -28,6 +28,7 @@
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
 #include <linux/serial.h>
+#include <linux/swab.h>
 #include <linux/kfifo.h>
 #include <linux/ioctl.h>
 #include <linux/firmware.h>
@@ -280,7 +281,7 @@ static int read_download_mem(struct usb_device *dev, int start_address,
 {
 	int status = 0;
 	__u8 read_length;
-	__be16 be_start_address;
+	u16 be_start_address;
 
 	dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, length);
 
@@ -296,10 +297,14 @@ static int read_download_mem(struct usb_device *dev, int start_address,
 		if (read_length > 1) {
 			dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, read_length);
 		}
-		be_start_address = cpu_to_be16(start_address);
+		/*
+		 * NOTE: Must use swab as wIndex is sent in little-endian
+		 *       byte order regardless of host byte order.
+		 */
+		be_start_address = swab16((u16)start_address);
 		status = ti_vread_sync(dev, UMPC_MEMORY_READ,
 					(__u16)address_type,
-					(__force __u16)be_start_address,
+					be_start_address,
 					buffer, read_length);
 
 		if (status) {
@@ -394,7 +399,7 @@ static int write_i2c_mem(struct edgeport_serial *serial,
 	struct device *dev = &serial->serial->dev->dev;
 	int status = 0;
 	int write_length;
-	__be16 be_start_address;
+	u16 be_start_address;
 
 	/* We can only send a maximum of 1 aligned byte page at a time */
 
@@ -409,11 +414,16 @@ static int write_i2c_mem(struct edgeport_serial *serial,
 		__func__, start_address, write_length);
 	usb_serial_debug_data(dev, __func__, write_length, buffer);
 
-	/* Write first page */
-	be_start_address = cpu_to_be16(start_address);
+	/*
+	 * Write first page.
+	 *
+	 * NOTE: Must use swab as wIndex is sent in little-endian byte order
+	 *       regardless of host byte order.
+	 */
+	be_start_address = swab16((u16)start_address);
 	status = ti_vsend_sync(serial->serial->dev,
 				UMPC_MEMORY_WRITE, (__u16)address_type,
-				(__force __u16)be_start_address,
+				be_start_address,
 				buffer,	write_length);
 	if (status) {
 		dev_dbg(dev, "%s - ERROR %d\n", __func__, status);
@@ -436,11 +446,16 @@ static int write_i2c_mem(struct edgeport_serial *serial,
 			__func__, start_address, write_length);
 		usb_serial_debug_data(dev, __func__, write_length, buffer);
 
-		/* Write next page */
-		be_start_address = cpu_to_be16(start_address);
+		/*
+		 * Write next page.
+		 *
+		 * NOTE: Must use swab as wIndex is sent in little-endian byte
+		 *       order regardless of host byte order.
+		 */
+		be_start_address = swab16((u16)start_address);
 		status = ti_vsend_sync(serial->serial->dev, UMPC_MEMORY_WRITE,
 				(__u16)address_type,
-				(__force __u16)be_start_address,
+				be_start_address,
 				buffer, write_length);
 		if (status) {
 			dev_err(dev, "%s - ERROR %d\n", __func__, status);
@@ -585,8 +600,8 @@ static int get_descriptor_addr(struct edgeport_serial *serial,
 		if (rom_desc->Type == desc_type)
 			return start_address;
 
-		start_address = start_address + sizeof(struct ti_i2c_desc)
-							+ rom_desc->Size;
+		start_address = start_address + sizeof(struct ti_i2c_desc) +
+						le16_to_cpu(rom_desc->Size);
 
 	} while ((start_address < TI_MAX_I2C_SIZE) && rom_desc->Type);
 
@@ -599,7 +614,7 @@ static int valid_csum(struct ti_i2c_desc *rom_desc, __u8 *buffer)
 	__u16 i;
 	__u8 cs = 0;
 
-	for (i = 0; i < rom_desc->Size; i++)
+	for (i = 0; i < le16_to_cpu(rom_desc->Size); i++)
 		cs = (__u8)(cs + buffer[i]);
 
 	if (cs != rom_desc->CheckSum) {
@@ -650,7 +665,7 @@ static int check_i2c_image(struct edgeport_serial *serial)
 			break;
 
 		if ((start_address + sizeof(struct ti_i2c_desc) +
-					rom_desc->Size) > TI_MAX_I2C_SIZE) {
+			le16_to_cpu(rom_desc->Size)) > TI_MAX_I2C_SIZE) {
 			status = -ENODEV;
 			dev_dbg(dev, "%s - structure too big, erroring out.\n", __func__);
 			break;
@@ -665,7 +680,8 @@ static int check_i2c_image(struct edgeport_serial *serial)
 			/* Read the descriptor data */
 			status = read_rom(serial, start_address +
 						sizeof(struct ti_i2c_desc),
-						rom_desc->Size, buffer);
+						le16_to_cpu(rom_desc->Size),
+						buffer);
 			if (status)
 				break;
 
@@ -674,7 +690,7 @@ static int check_i2c_image(struct edgeport_serial *serial)
 				break;
 		}
 		start_address = start_address + sizeof(struct ti_i2c_desc) +
-								rom_desc->Size;
+						le16_to_cpu(rom_desc->Size);
 
 	} while ((rom_desc->Type != I2C_DESC_TYPE_ION) &&
 				(start_address < TI_MAX_I2C_SIZE));
@@ -712,7 +728,7 @@ static int get_manuf_info(struct edgeport_serial *serial, __u8 *buffer)
 
 	/* Read the descriptor data */
 	status = read_rom(serial, start_address+sizeof(struct ti_i2c_desc),
-						rom_desc->Size, buffer);
+					le16_to_cpu(rom_desc->Size), buffer);
 	if (status)
 		goto exit;
 
@@ -805,7 +821,7 @@ static int build_i2c_fw_hdr(__u8 *header, struct device *dev)
 	firmware_rec =  (struct ti_i2c_firmware_rec*)i2c_header->Data;
 
 	i2c_header->Type	= I2C_DESC_TYPE_FIRMWARE_BLANK;
-	i2c_header->Size	= (__u16)buffer_size;
+	i2c_header->Size	= cpu_to_le16(buffer_size);
 	i2c_header->CheckSum	= cs;
 	firmware_rec->Ver_Major	= OperationalMajorVersion;
 	firmware_rec->Ver_Minor	= OperationalMinorVersion;
diff --git a/drivers/usb/serial/io_usbvend.h b/drivers/usb/serial/io_usbvend.h
index 51f83fbb73bb..6f6a856bc37c 100644
--- a/drivers/usb/serial/io_usbvend.h
+++ b/drivers/usb/serial/io_usbvend.h
@@ -594,7 +594,7 @@ struct edge_boot_descriptor {
 
 struct ti_i2c_desc {
 	__u8	Type;			// Type of descriptor
-	__u16	Size;			// Size of data only not including header
+	__le16	Size;			// Size of data only not including header
 	__u8	CheckSum;		// Checksum (8 bit sum of data only)
 	__u8	Data[0];		// Data starts here
 } __attribute__((packed));
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index 265c6776b081..49101fe45d38 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -311,24 +311,30 @@ static void	usa26_indat_callback(struct urb *urb)
 		if ((data[0] & 0x80) == 0) {
 			/* no errors on individual bytes, only
 			   possible overrun err */
-			if (data[0] & RXERROR_OVERRUN)
-				err = TTY_OVERRUN;
-			else
-				err = 0;
+			if (data[0] & RXERROR_OVERRUN) {
+				tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+			}
 			for (i = 1; i < urb->actual_length ; ++i)
-				tty_insert_flip_char(&port->port, data[i], err);
+				tty_insert_flip_char(&port->port, data[i],
+								TTY_NORMAL);
 		} else {
 			/* some bytes had errors, every byte has status */
 			dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__);
 			for (i = 0; i + 1 < urb->actual_length; i += 2) {
-				int stat = data[i], flag = 0;
-				if (stat & RXERROR_OVERRUN)
-					flag |= TTY_OVERRUN;
-				if (stat & RXERROR_FRAMING)
-					flag |= TTY_FRAME;
-				if (stat & RXERROR_PARITY)
-					flag |= TTY_PARITY;
+				int stat = data[i];
+				int flag = TTY_NORMAL;
+
+				if (stat & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				/* XXX should handle break (0x10) */
+				if (stat & RXERROR_PARITY)
+					flag = TTY_PARITY;
+				else if (stat & RXERROR_FRAMING)
+					flag = TTY_FRAME;
+
 				tty_insert_flip_char(&port->port, data[i+1],
 						flag);
 			}
@@ -666,14 +672,19 @@ static void	usa49_indat_callback(struct urb *urb)
 		} else {
 			/* some bytes had errors, every byte has status */
 			for (i = 0; i + 1 < urb->actual_length; i += 2) {
-				int stat = data[i], flag = 0;
-				if (stat & RXERROR_OVERRUN)
-					flag |= TTY_OVERRUN;
-				if (stat & RXERROR_FRAMING)
-					flag |= TTY_FRAME;
-				if (stat & RXERROR_PARITY)
-					flag |= TTY_PARITY;
+				int stat = data[i];
+				int flag = TTY_NORMAL;
+
+				if (stat & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				/* XXX should handle break (0x10) */
+				if (stat & RXERROR_PARITY)
+					flag = TTY_PARITY;
+				else if (stat & RXERROR_FRAMING)
+					flag = TTY_FRAME;
+
 				tty_insert_flip_char(&port->port, data[i+1],
 						flag);
 			}
@@ -730,15 +741,19 @@ static void usa49wg_indat_callback(struct urb *urb)
 			 */
 			for (x = 0; x + 1 < len &&
 				    i + 1 < urb->actual_length; x += 2) {
-				int stat = data[i], flag = 0;
+				int stat = data[i];
+				int flag = TTY_NORMAL;
 
-				if (stat & RXERROR_OVERRUN)
-					flag |= TTY_OVERRUN;
-				if (stat & RXERROR_FRAMING)
-					flag |= TTY_FRAME;
-				if (stat & RXERROR_PARITY)
-					flag |= TTY_PARITY;
+				if (stat & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				/* XXX should handle break (0x10) */
+				if (stat & RXERROR_PARITY)
+					flag = TTY_PARITY;
+				else if (stat & RXERROR_FRAMING)
+					flag = TTY_FRAME;
+
 				tty_insert_flip_char(&port->port, data[i+1],
 						     flag);
 				i += 2;
@@ -790,25 +805,31 @@ static void usa90_indat_callback(struct urb *urb)
 			if ((data[0] & 0x80) == 0) {
 				/* no errors on individual bytes, only
 				   possible overrun err*/
-				if (data[0] & RXERROR_OVERRUN)
-					err = TTY_OVERRUN;
-				else
-					err = 0;
+				if (data[0] & RXERROR_OVERRUN) {
+					tty_insert_flip_char(&port->port, 0,
+								TTY_OVERRUN);
+				}
 				for (i = 1; i < urb->actual_length ; ++i)
 					tty_insert_flip_char(&port->port,
-							data[i], err);
+							data[i], TTY_NORMAL);
 			}  else {
 			/* some bytes had errors, every byte has status */
 				dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__);
 				for (i = 0; i + 1 < urb->actual_length; i += 2) {
-					int stat = data[i], flag = 0;
-					if (stat & RXERROR_OVERRUN)
-						flag |= TTY_OVERRUN;
-					if (stat & RXERROR_FRAMING)
-						flag |= TTY_FRAME;
-					if (stat & RXERROR_PARITY)
-						flag |= TTY_PARITY;
+					int stat = data[i];
+					int flag = TTY_NORMAL;
+
+					if (stat & RXERROR_OVERRUN) {
+						tty_insert_flip_char(
+								&port->port, 0,
+								TTY_OVERRUN);
+					}
 					/* XXX should handle break (0x10) */
+					if (stat & RXERROR_PARITY)
+						flag = TTY_PARITY;
+					else if (stat & RXERROR_FRAMING)
+						flag = TTY_FRAME;
+
 					tty_insert_flip_char(&port->port,
 							data[i+1], flag);
 				}
diff --git a/drivers/usb/serial/kobil_sct.c b/drivers/usb/serial/kobil_sct.c
index 618c1c1f227e..5cdb32b37e85 100644
--- a/drivers/usb/serial/kobil_sct.c
+++ b/drivers/usb/serial/kobil_sct.c
@@ -335,7 +335,8 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port,
 			port->interrupt_out_urb->transfer_buffer_length = length;
 
 			priv->cur_pos = priv->cur_pos + length;
-			result = usb_submit_urb(port->interrupt_out_urb, GFP_NOIO);
+			result = usb_submit_urb(port->interrupt_out_urb,
+					GFP_ATOMIC);
 			dev_dbg(&port->dev, "%s - Send write URB returns: %i\n", __func__, result);
 			todo = priv->filled - priv->cur_pos;
 
@@ -350,7 +351,7 @@ static int kobil_write(struct tty_struct *tty, struct usb_serial_port *port,
 		if (priv->device_type == KOBIL_ADAPTER_B_PRODUCT_ID ||
 			priv->device_type == KOBIL_ADAPTER_K_PRODUCT_ID) {
 			result = usb_submit_urb(port->interrupt_in_urb,
-								GFP_NOIO);
+					GFP_ATOMIC);
 			dev_dbg(&port->dev, "%s - Send read URB returns: %i\n", __func__, result);
 		}
 	}
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index 4856fb7e637e..4b7bfb394a32 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -215,7 +215,7 @@ static int opticon_write(struct tty_struct *tty, struct usb_serial_port *port,
 
 	/* The connected devices do not have a bulk write endpoint,
 	 * to transmit data to de barcode device the control endpoint is used */
-	dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_NOIO);
+	dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC);
 	if (!dr) {
 		count = -ENOMEM;
 		goto error_no_dr;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 68fc9fe65936..8b3484134ab0 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -161,6 +161,7 @@ static void option_instat_callback(struct urb *urb);
 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_FULLSPEED	0x9000
 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED	0x9001
 #define NOVATELWIRELESS_PRODUCT_E362		0x9010
+#define NOVATELWIRELESS_PRODUCT_E371		0x9011
 #define NOVATELWIRELESS_PRODUCT_G2		0xA010
 #define NOVATELWIRELESS_PRODUCT_MC551		0xB001
 
@@ -234,8 +235,31 @@ static void option_instat_callback(struct urb *urb);
 #define QUALCOMM_VENDOR_ID			0x05C6
 
 #define CMOTECH_VENDOR_ID			0x16d8
-#define CMOTECH_PRODUCT_6008			0x6008
-#define CMOTECH_PRODUCT_6280			0x6280
+#define CMOTECH_PRODUCT_6001			0x6001
+#define CMOTECH_PRODUCT_CMU_300			0x6002
+#define CMOTECH_PRODUCT_6003			0x6003
+#define CMOTECH_PRODUCT_6004			0x6004
+#define CMOTECH_PRODUCT_6005			0x6005
+#define CMOTECH_PRODUCT_CGU_628A		0x6006
+#define CMOTECH_PRODUCT_CHE_628S		0x6007
+#define CMOTECH_PRODUCT_CMU_301			0x6008
+#define CMOTECH_PRODUCT_CHU_628			0x6280
+#define CMOTECH_PRODUCT_CHU_628S		0x6281
+#define CMOTECH_PRODUCT_CDU_680			0x6803
+#define CMOTECH_PRODUCT_CDU_685A		0x6804
+#define CMOTECH_PRODUCT_CHU_720S		0x7001
+#define CMOTECH_PRODUCT_7002			0x7002
+#define CMOTECH_PRODUCT_CHU_629K		0x7003
+#define CMOTECH_PRODUCT_7004			0x7004
+#define CMOTECH_PRODUCT_7005			0x7005
+#define CMOTECH_PRODUCT_CGU_629			0x7006
+#define CMOTECH_PRODUCT_CHU_629S		0x700a
+#define CMOTECH_PRODUCT_CHU_720I		0x7211
+#define CMOTECH_PRODUCT_7212			0x7212
+#define CMOTECH_PRODUCT_7213			0x7213
+#define CMOTECH_PRODUCT_7251			0x7251
+#define CMOTECH_PRODUCT_7252			0x7252
+#define CMOTECH_PRODUCT_7253			0x7253
 
 #define TELIT_VENDOR_ID				0x1bc7
 #define TELIT_PRODUCT_UC864E			0x1003
@@ -243,15 +267,21 @@ static void option_instat_callback(struct urb *urb);
 #define TELIT_PRODUCT_CC864_DUAL		0x1005
 #define TELIT_PRODUCT_CC864_SINGLE		0x1006
 #define TELIT_PRODUCT_DE910_DUAL		0x1010
+#define TELIT_PRODUCT_UE910_V2			0x1012
 #define TELIT_PRODUCT_LE920			0x1200
+#define TELIT_PRODUCT_LE910			0x1201
 
 /* ZTE PRODUCTS */
 #define ZTE_VENDOR_ID				0x19d2
 #define ZTE_PRODUCT_MF622			0x0001
 #define ZTE_PRODUCT_MF628			0x0015
 #define ZTE_PRODUCT_MF626			0x0031
-#define ZTE_PRODUCT_MC2718			0xffe8
 #define ZTE_PRODUCT_AC2726			0xfff1
+#define ZTE_PRODUCT_CDMA_TECH			0xfffe
+#define ZTE_PRODUCT_AC8710T			0xffff
+#define ZTE_PRODUCT_MC2718			0xffe8
+#define ZTE_PRODUCT_AD3812			0xffeb
+#define ZTE_PRODUCT_MC2716			0xffed
 
 #define BENQ_VENDOR_ID				0x04a5
 #define BENQ_PRODUCT_H10			0x4068
@@ -286,6 +316,7 @@ static void option_instat_callback(struct urb *urb);
 #define ALCATEL_PRODUCT_X060S_X200		0x0000
 #define ALCATEL_PRODUCT_X220_X500D		0x0017
 #define ALCATEL_PRODUCT_L100V			0x011e
+#define ALCATEL_PRODUCT_L800MA			0x0203
 
 #define PIRELLI_VENDOR_ID			0x1266
 #define PIRELLI_PRODUCT_C100_1			0x1002
@@ -326,8 +357,12 @@ static void option_instat_callback(struct urb *urb);
 /* Zoom */
 #define ZOOM_PRODUCT_4597			0x9607
 
+/* SpeedUp SU9800 usb 3g modem */
+#define SPEEDUP_PRODUCT_SU9800			0x9800
+
 /* Haier products */
 #define HAIER_VENDOR_ID				0x201e
+#define HAIER_PRODUCT_CE81B			0x10f8
 #define HAIER_PRODUCT_CE100			0x2009
 
 /* Cinterion (formerly Siemens) products */
@@ -346,8 +381,13 @@ static void option_instat_callback(struct urb *urb);
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
 #define OLIVETTI_PRODUCT_OLICARD100		0xc000
+#define OLIVETTI_PRODUCT_OLICARD120		0xc001
+#define OLIVETTI_PRODUCT_OLICARD140		0xc002
 #define OLIVETTI_PRODUCT_OLICARD145		0xc003
+#define OLIVETTI_PRODUCT_OLICARD155		0xc004
 #define OLIVETTI_PRODUCT_OLICARD200		0xc005
+#define OLIVETTI_PRODUCT_OLICARD160		0xc00a
+#define OLIVETTI_PRODUCT_OLICARD500		0xc00b
 
 /* Celot products */
 #define CELOT_VENDOR_ID				0x211f
@@ -460,6 +500,10 @@ static void option_instat_callback(struct urb *urb);
 #define INOVIA_VENDOR_ID			0x20a6
 #define INOVIA_SEW858				0x1105
 
+/* VIA Telecom */
+#define VIATELECOM_VENDOR_ID			0x15eb
+#define VIATELECOM_PRODUCT_CDS7			0x0001
+
 /* some devices interfaces need special handling due to a number of reasons */
 enum option_blacklist_reason {
 		OPTION_BLACKLIST_NONE = 0,
@@ -493,14 +537,26 @@ static const struct option_blacklist_info zte_k3765_z_blacklist = {
 	.reserved = BIT(4),
 };
 
+static const struct option_blacklist_info zte_ad3812_z_blacklist = {
+	.sendsetup = BIT(0) | BIT(1) | BIT(2),
+};
+
 static const struct option_blacklist_info zte_mc2718_z_blacklist = {
 	.sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info zte_mc2716_z_blacklist = {
+	.sendsetup = BIT(1) | BIT(2) | BIT(3),
+};
+
 static const struct option_blacklist_info huawei_cdc12_blacklist = {
 	.reserved = BIT(1) | BIT(2),
 };
 
+static const struct option_blacklist_info net_intf0_blacklist = {
+	.reserved = BIT(0),
+};
+
 static const struct option_blacklist_info net_intf1_blacklist = {
 	.reserved = BIT(1),
 };
@@ -534,6 +590,11 @@ static const struct option_blacklist_info zte_1255_blacklist = {
 	.reserved = BIT(3) | BIT(4),
 };
 
+static const struct option_blacklist_info telit_le910_blacklist = {
+	.sendsetup = BIT(0),
+	.reserved = BIT(1) | BIT(2),
+};
+
 static const struct option_blacklist_info telit_le920_blacklist = {
 	.sendsetup = BIT(0),
 	.reserved = BIT(1) | BIT(5),
@@ -982,6 +1043,7 @@ static const struct usb_device_id option_ids[] = {
 	/* Novatel Ovation MC551 a.k.a. Verizon USB551L */
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC551, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E362, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E371, 0xff, 0xff, 0xff) },
 
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) },
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) },
@@ -1031,16 +1093,59 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(BANDRICH_VENDOR_ID, BANDRICH_PRODUCT_1012, 0xff) },
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) },
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
-	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6280) }, /* BP3-USB & BP3-EXT HSDPA */
-	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6008) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6004) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6005) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_628A) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHE_628S),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_301),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628S) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_680) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_685A) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720S),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7002),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629K),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7004),
+	  .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7005) },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_629),
+	  .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629S),
+	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720I),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7212),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7213),
+	  .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7251),
+	  .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7252),
+	  .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
+	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7253),
+	  .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864E) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864G) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_DUAL) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) },
+	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
+		.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
 		.driver_info = (kernel_ulong_t)&telit_le920_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
@@ -1408,6 +1513,8 @@ static const struct usb_device_id option_ids[] = {
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1426, 0xff, 0xff, 0xff),  /* ZTE MF91 */
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff),  /* Telewell TW-LTE 4G v2 */
+		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) },
@@ -1463,13 +1570,18 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) },
 
-	/* NOTE: most ZTE CDMA devices should be driven by zte_ev, not option */
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff),
 	 .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
 
 	{ USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) },
 	{ USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) },
@@ -1498,14 +1610,18 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L100V),
 	  .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L800MA),
+	  .driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) },
 	{ USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14),
   	  .driver_info = (kernel_ulong_t)&four_g_w14_blacklist
   	},
+	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) },
 	{ USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HAIER_VENDOR_ID, HAIER_PRODUCT_CE81B, 0xff, 0xff, 0xff) },
 	/* Pirelli  */
 	{ USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_1, 0xff) },
 	{ USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_2, 0xff) },
@@ -1537,12 +1653,21 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
-
-	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD140),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD155),
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200),
-		.driver_info = (kernel_ulong_t)&net_intf6_blacklist
-	},
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD160),
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD500),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */
 	{ USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/
 	{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM600) },
@@ -1631,6 +1756,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
 	{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
+	{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
@@ -1824,6 +1950,8 @@ static void option_instat_callback(struct urb *urb)
 			dev_dbg(dev, "%s: type %x req %x\n", __func__,
 				req_pkt->bRequestType, req_pkt->bRequest);
 		}
+	} else if (status == -ENOENT || status == -ESHUTDOWN) {
+		dev_dbg(dev, "%s: urb stopped: %d\n", __func__, status);
 	} else
 		dev_err(dev, "%s: error %d\n", __func__, status);
 
@@ -1848,6 +1976,7 @@ static int option_send_setup(struct usb_serial_port *port)
 	struct option_private *priv = intfdata->private;
 	struct usb_wwan_port_private *portdata;
 	int val = 0;
+	int res;
 
 	portdata = usb_get_serial_port_data(port);
 
@@ -1856,9 +1985,17 @@ static int option_send_setup(struct usb_serial_port *port)
 	if (portdata->rts_state)
 		val |= 0x02;
 
-	return usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
+	res = usb_autopm_get_interface(serial->interface);
+	if (res)
+		return res;
+
+	res = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
 				0x22, 0x21, val, priv->bInterfaceNumber, NULL,
 				0, USB_CTRL_SET_TIMEOUT);
+
+	usb_autopm_put_interface(serial->interface);
+
+	return res;
 }
 
 MODULE_AUTHOR(DRIVER_AUTHOR);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 2e22fc22c382..e9bad928039f 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -45,6 +45,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) },
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) },
 	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) },
+	{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ZTEK) },
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) },
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) },
 	{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) },
@@ -83,6 +84,9 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(YCCABLE_VENDOR_ID, YCCABLE_PRODUCT_ID) },
 	{ USB_DEVICE(SUPERIAL_VENDOR_ID, SUPERIAL_PRODUCT_ID) },
 	{ USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LD960_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) },
+	{ USB_DEVICE(HP_VENDOR_ID, HP_LCM960_PRODUCT_ID) },
 	{ USB_DEVICE(CRESSI_VENDOR_ID, CRESSI_EDY_PRODUCT_ID) },
 	{ USB_DEVICE(ZEAGLE_VENDOR_ID, ZEAGLE_N2ITION3_PRODUCT_ID) },
 	{ USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) },
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index c38b8c00c06f..71fd9da1d6e7 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -22,6 +22,7 @@
 #define PL2303_PRODUCT_ID_GPRS		0x0609
 #define PL2303_PRODUCT_ID_HCR331	0x331a
 #define PL2303_PRODUCT_ID_MOTOROLA	0x0307
+#define PL2303_PRODUCT_ID_ZTEK		0xe1f1
 
 #define ATEN_VENDOR_ID		0x0557
 #define ATEN_VENDOR_ID2		0x0547
@@ -121,8 +122,11 @@
 #define SUPERIAL_VENDOR_ID	0x5372
 #define SUPERIAL_PRODUCT_ID	0x2303
 
-/* Hewlett-Packard LD220-HP POS Pole Display */
+/* Hewlett-Packard POS Pole Displays */
 #define HP_VENDOR_ID		0x03f0
+#define HP_LD960_PRODUCT_ID	0x0b39
+#define HP_LCM220_PRODUCT_ID	0x3139
+#define HP_LCM960_PRODUCT_ID	0x3239
 #define HP_LD220_PRODUCT_ID	0x3524
 
 /* Cressi Edy (diving computer) PC interface */
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 968a40201e5f..43d93dbf7d71 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -136,12 +136,57 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 0)},	/* Sierra Wireless MC7710 Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 2)},	/* Sierra Wireless MC7710 NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 3)},	/* Sierra Wireless MC7710 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 0)},	/* Sierra Wireless MC73xx Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 2)},	/* Sierra Wireless MC73xx NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 3)},	/* Sierra Wireless MC73xx Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)},	/* Sierra Wireless EM7700 Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)},	/* Sierra Wireless EM7700 NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)},	/* Sierra Wireless EM7700 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 0)},	/* Sierra Wireless EM7355 Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 2)},	/* Sierra Wireless EM7355 NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 3)},	/* Sierra Wireless EM7355 Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 0)},	/* Sierra Wireless MC7305/MC7355 Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 2)},	/* Sierra Wireless MC7305/MC7355 NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 3)},	/* Sierra Wireless MC7305/MC7355 Modem */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)},	/* Netgear AirCard 340U Device Management */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)},	/* Netgear AirCard 340U NMEA */
 	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)},	/* Netgear AirCard 340U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 0)},	/* Netgear AirCard 341U Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 2)},	/* Netgear AirCard 341U NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 3)},	/* Netgear AirCard 341U Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 0)},	/* Sierra Wireless Modem Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 2)},	/* Sierra Wireless Modem NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 3)},	/* Sierra Wireless Modem Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 0)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 2)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 3)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 0)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 2)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 3)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 0)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 2)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 3)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 0)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 2)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+	{USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 3)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Modem */
 
 	{ }				/* Terminating entry */
 };
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index a9eb6221a815..74a9375a9bb5 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -58,6 +58,7 @@ struct sierra_intf_private {
 	spinlock_t susp_lock;
 	unsigned int suspended:1;
 	int in_flight;
+	unsigned int open_ports;
 };
 
 static int sierra_set_power_state(struct usb_device *udev, __u16 swiState)
@@ -281,17 +282,21 @@ static const struct usb_device_id id_table[] = {
 	/* Sierra Wireless HSPA Non-Composite Device */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6892, 0xFF, 0xFF, 0xFF)},
 	{ USB_DEVICE(0x1199, 0x6893) },	/* Sierra Wireless Device */
-	{ USB_DEVICE(0x1199, 0x68A3), 	/* Sierra Wireless Direct IP modems */
+	/* Sierra Wireless Direct IP modems */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68A3, 0xFF, 0xFF, 0xFF),
+	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
+	},
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
 	/* AT&T Direct IP LTE modems */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
-	{ USB_DEVICE(0x0f3d, 0x68A3), 	/* Airprime/Sierra Wireless Direct IP modems */
+	/* Airprime/Sierra Wireless Direct IP modems */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68A3, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
-       { USB_DEVICE(0x413C, 0x08133) }, /* Dell Computer Corp. Wireless 5720 VZW Mobile Broadband (EVDO Rev-A) Minicard GPS Port */
 
 	{ }
 };
@@ -760,6 +765,7 @@ static void sierra_close(struct usb_serial_port *port)
 	struct usb_serial *serial = port->serial;
 	struct sierra_port_private *portdata;
 	struct sierra_intf_private *intfdata = port->serial->private;
+	struct urb *urb;
 
 	portdata = usb_get_serial_port_data(port);
 
@@ -768,7 +774,6 @@ static void sierra_close(struct usb_serial_port *port)
 
 	mutex_lock(&serial->disc_mutex);
 	if (!serial->disconnected) {
-		serial->interface->needs_remote_wakeup = 0;
 		/* odd error handling due to pm counters */
 		if (!usb_autopm_get_interface(serial->interface))
 			sierra_send_setup(port);
@@ -779,8 +784,22 @@ static void sierra_close(struct usb_serial_port *port)
 	mutex_unlock(&serial->disc_mutex);
 	spin_lock_irq(&intfdata->susp_lock);
 	portdata->opened = 0;
+	if (--intfdata->open_ports == 0)
+		serial->interface->needs_remote_wakeup = 0;
 	spin_unlock_irq(&intfdata->susp_lock);
 
+	for (;;) {
+		urb = usb_get_from_anchor(&portdata->delayed);
+		if (!urb)
+			break;
+		kfree(urb->transfer_buffer);
+		usb_free_urb(urb);
+		usb_autopm_put_interface_async(serial->interface);
+		spin_lock(&portdata->lock);
+		portdata->outstanding_urbs--;
+		spin_unlock(&portdata->lock);
+	}
+
 	sierra_stop_rx_urbs(port);
 	for (i = 0; i < portdata->num_in_urbs; i++) {
 		sierra_release_urb(portdata->in_urbs[i]);
@@ -817,23 +836,29 @@ static int sierra_open(struct tty_struct *tty, struct usb_serial_port *port)
 			usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN);
 
 	err = sierra_submit_rx_urbs(port, GFP_KERNEL);
-	if (err) {
-		/* get rid of everything as in close */
-		sierra_close(port);
-		/* restore balance for autopm */
-		if (!serial->disconnected)
-			usb_autopm_put_interface(serial->interface);
-		return err;
-	}
+	if (err)
+		goto err_submit;
+
 	sierra_send_setup(port);
 
-	serial->interface->needs_remote_wakeup = 1;
 	spin_lock_irq(&intfdata->susp_lock);
 	portdata->opened = 1;
+	if (++intfdata->open_ports == 1)
+		serial->interface->needs_remote_wakeup = 1;
 	spin_unlock_irq(&intfdata->susp_lock);
 	usb_autopm_put_interface(serial->interface);
 
 	return 0;
+
+err_submit:
+	sierra_stop_rx_urbs(port);
+
+	for (i = 0; i < portdata->num_in_urbs; i++) {
+		sierra_release_urb(portdata->in_urbs[i]);
+		portdata->in_urbs[i] = NULL;
+	}
+
+	return err;
 }
 
 
@@ -929,6 +954,7 @@ static int sierra_port_remove(struct usb_serial_port *port)
 	struct sierra_port_private *portdata;
 
 	portdata = usb_get_serial_port_data(port);
+	usb_set_serial_port_data(port, NULL);
 	kfree(portdata);
 
 	return 0;
@@ -945,6 +971,8 @@ static void stop_read_write_urbs(struct usb_serial *serial)
 	for (i = 0; i < serial->num_ports; ++i) {
 		port = serial->port[i];
 		portdata = usb_get_serial_port_data(port);
+		if (!portdata)
+			continue;
 		sierra_stop_rx_urbs(port);
 		usb_kill_anchored_urbs(&portdata->active);
 	}
@@ -987,6 +1015,9 @@ static int sierra_resume(struct usb_serial *serial)
 		port = serial->port[i];
 		portdata = usb_get_serial_port_data(port);
 
+		if (!portdata)
+			continue;
+
 		while ((urb = usb_get_from_anchor(&portdata->delayed))) {
 			usb_anchor_urb(urb, &portdata->active);
 			intfdata->in_flight++;
@@ -994,8 +1025,12 @@ static int sierra_resume(struct usb_serial *serial)
 			if (err < 0) {
 				intfdata->in_flight--;
 				usb_unanchor_urb(urb);
-				usb_scuttle_anchored_urbs(&portdata->delayed);
-				break;
+				kfree(urb->transfer_buffer);
+				usb_free_urb(urb);
+				spin_lock(&portdata->lock);
+				portdata->outstanding_urbs--;
+				spin_unlock(&portdata->lock);
+				continue;
 			}
 		}
 
diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c
index a7fe664b6b7d..70a098de429f 100644
--- a/drivers/usb/serial/ssu100.c
+++ b/drivers/usb/serial/ssu100.c
@@ -490,10 +490,9 @@ static void ssu100_update_lsr(struct usb_serial_port *port, u8 lsr,
 			if (*tty_flag == TTY_NORMAL)
 				*tty_flag = TTY_FRAME;
 		}
-		if (lsr & UART_LSR_OE){
+		if (lsr & UART_LSR_OE) {
 			port->icount.overrun++;
-			if (*tty_flag == TTY_NORMAL)
-				*tty_flag = TTY_OVERRUN;
+			tty_insert_flip_char(&port->port, 0, TTY_OVERRUN);
 		}
 	}
 
@@ -511,12 +510,8 @@ static void ssu100_process_read_urb(struct urb *urb)
 	if ((len >= 4) &&
 	    (packet[0] == 0x1b) && (packet[1] == 0x1b) &&
 	    ((packet[2] == 0x00) || (packet[2] == 0x01))) {
-		if (packet[2] == 0x00) {
+		if (packet[2] == 0x00)
 			ssu100_update_lsr(port, packet[3], &flag);
-			if (flag == TTY_OVERRUN)
-				tty_insert_flip_char(&port->port, 0,
-						TTY_OVERRUN);
-		}
 		if (packet[2] == 0x01)
 			ssu100_update_msr(port, packet[3]);
 
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 7c9dc28640bb..9a08e18e09b9 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -764,29 +764,39 @@ static int usb_serial_probe(struct usb_interface *interface,
 		if (usb_endpoint_is_bulk_in(endpoint)) {
 			/* we found a bulk in endpoint */
 			dev_dbg(ddev, "found bulk in on endpoint %d\n", i);
-			bulk_in_endpoint[num_bulk_in] = endpoint;
-			++num_bulk_in;
+			if (num_bulk_in < MAX_NUM_PORTS) {
+				bulk_in_endpoint[num_bulk_in] = endpoint;
+				++num_bulk_in;
+			}
 		}
 
 		if (usb_endpoint_is_bulk_out(endpoint)) {
 			/* we found a bulk out endpoint */
 			dev_dbg(ddev, "found bulk out on endpoint %d\n", i);
-			bulk_out_endpoint[num_bulk_out] = endpoint;
-			++num_bulk_out;
+			if (num_bulk_out < MAX_NUM_PORTS) {
+				bulk_out_endpoint[num_bulk_out] = endpoint;
+				++num_bulk_out;
+			}
 		}
 
 		if (usb_endpoint_is_int_in(endpoint)) {
 			/* we found a interrupt in endpoint */
 			dev_dbg(ddev, "found interrupt in on endpoint %d\n", i);
-			interrupt_in_endpoint[num_interrupt_in] = endpoint;
-			++num_interrupt_in;
+			if (num_interrupt_in < MAX_NUM_PORTS) {
+				interrupt_in_endpoint[num_interrupt_in] =
+						endpoint;
+				++num_interrupt_in;
+			}
 		}
 
 		if (usb_endpoint_is_int_out(endpoint)) {
 			/* we found an interrupt out endpoint */
 			dev_dbg(ddev, "found interrupt out on endpoint %d\n", i);
-			interrupt_out_endpoint[num_interrupt_out] = endpoint;
-			++num_interrupt_out;
+			if (num_interrupt_out < MAX_NUM_PORTS) {
+				interrupt_out_endpoint[num_interrupt_out] =
+						endpoint;
+				++num_interrupt_out;
+			}
 		}
 	}
 
@@ -809,8 +819,10 @@ static int usb_serial_probe(struct usb_interface *interface,
 				if (usb_endpoint_is_int_in(endpoint)) {
 					/* we found a interrupt in endpoint */
 					dev_dbg(ddev, "found interrupt in for Prolific device on separate interface\n");
-					interrupt_in_endpoint[num_interrupt_in] = endpoint;
-					++num_interrupt_in;
+					if (num_interrupt_in < MAX_NUM_PORTS) {
+						interrupt_in_endpoint[num_interrupt_in] = endpoint;
+						++num_interrupt_in;
+					}
 				}
 			}
 		}
@@ -850,6 +862,11 @@ static int usb_serial_probe(struct usb_interface *interface,
 			num_ports = type->num_ports;
 	}
 
+	if (num_ports > MAX_NUM_PORTS) {
+		dev_warn(ddev, "too many ports requested: %d\n", num_ports);
+		num_ports = MAX_NUM_PORTS;
+	}
+
 	serial->num_ports = num_ports;
 	serial->num_bulk_in = num_bulk_in;
 	serial->num_bulk_out = num_bulk_out;
@@ -1348,10 +1365,12 @@ static int usb_serial_register(struct usb_serial_driver *driver)
 static void usb_serial_deregister(struct usb_serial_driver *device)
 {
 	pr_info("USB Serial deregistering driver %s\n", device->description);
+
 	mutex_lock(&table_lock);
 	list_del(&device->driver_list);
-	usb_serial_bus_deregister(device);
 	mutex_unlock(&table_lock);
+
+	usb_serial_bus_deregister(device);
 }
 
 /**
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index 640fe0173236..d91a9883e869 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -228,8 +228,10 @@ int usb_wwan_write(struct tty_struct *tty, struct usb_serial_port *port,
 			usb_pipeendpoint(this_urb->pipe), i);
 
 		err = usb_autopm_get_interface_async(port->serial->interface);
-		if (err < 0)
+		if (err < 0) {
+			clear_bit(i, &portdata->out_busy);
 			break;
+		}
 
 		/* send the data */
 		memcpy(this_urb->transfer_buffer, buf, todo);
@@ -386,6 +388,14 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port)
 	portdata = usb_get_serial_port_data(port);
 	intfdata = serial->private;
 
+	if (port->interrupt_in_urb) {
+		err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
+		if (err) {
+			dev_dbg(&port->dev, "%s: submit int urb failed: %d\n",
+				__func__, err);
+		}
+	}
+
 	/* Start reading from the IN endpoint */
 	for (i = 0; i < N_IN_URB; i++) {
 		urb = portdata->in_urbs[i];
@@ -412,12 +422,26 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port)
 }
 EXPORT_SYMBOL(usb_wwan_open);
 
+static void unbusy_queued_urb(struct urb *urb,
+					struct usb_wwan_port_private *portdata)
+{
+	int i;
+
+	for (i = 0; i < N_OUT_URB; i++) {
+		if (urb == portdata->out_urbs[i]) {
+			clear_bit(i, &portdata->out_busy);
+			break;
+		}
+	}
+}
+
 void usb_wwan_close(struct usb_serial_port *port)
 {
 	int i;
 	struct usb_serial *serial = port->serial;
 	struct usb_wwan_port_private *portdata;
 	struct usb_wwan_intf_private *intfdata = port->serial->private;
+	struct urb *urb;
 
 	portdata = usb_get_serial_port_data(port);
 
@@ -426,10 +450,19 @@ void usb_wwan_close(struct usb_serial_port *port)
 	portdata->opened = 0;
 	spin_unlock_irq(&intfdata->susp_lock);
 
+	for (;;) {
+		urb = usb_get_from_anchor(&portdata->delayed);
+		if (!urb)
+			break;
+		unbusy_queued_urb(urb, portdata);
+		usb_autopm_put_interface_async(serial->interface);
+	}
+
 	for (i = 0; i < N_IN_URB; i++)
 		usb_kill_urb(portdata->in_urbs[i]);
 	for (i = 0; i < N_OUT_URB; i++)
 		usb_kill_urb(portdata->out_urbs[i]);
+	usb_kill_urb(port->interrupt_in_urb);
 
 	/* balancing - important as an error cannot be handled*/
 	usb_autopm_get_interface_no_resume(serial->interface);
@@ -463,9 +496,11 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 	struct usb_wwan_port_private *portdata;
 	struct urb *urb;
 	u8 *buffer;
-	int err;
 	int i;
 
+	if (!port->bulk_in_size || !port->bulk_out_size)
+		return -ENODEV;
+
 	portdata = kzalloc(sizeof(*portdata), GFP_KERNEL);
 	if (!portdata)
 		return -ENOMEM;
@@ -473,9 +508,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 	init_usb_anchor(&portdata->delayed);
 
 	for (i = 0; i < N_IN_URB; i++) {
-		if (!port->bulk_in_size)
-			break;
-
 		buffer = (u8 *)__get_free_page(GFP_KERNEL);
 		if (!buffer)
 			goto bail_out_error;
@@ -489,9 +521,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 	}
 
 	for (i = 0; i < N_OUT_URB; i++) {
-		if (!port->bulk_out_size)
-			break;
-
 		buffer = kmalloc(OUT_BUFLEN, GFP_KERNEL);
 		if (!buffer)
 			goto bail_out_error2;
@@ -506,13 +535,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port)
 
 	usb_set_serial_port_data(port, portdata);
 
-	if (port->interrupt_in_urb) {
-		err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
-		if (err)
-			dev_dbg(&port->dev, "%s: submit irq_in urb failed %d\n",
-				__func__, err);
-	}
-
 	return 0;
 
 bail_out_error2:
@@ -580,44 +602,29 @@ static void stop_read_write_urbs(struct usb_serial *serial)
 int usb_wwan_suspend(struct usb_serial *serial, pm_message_t message)
 {
 	struct usb_wwan_intf_private *intfdata = serial->private;
-	int b;
 
+	spin_lock_irq(&intfdata->susp_lock);
 	if (PMSG_IS_AUTO(message)) {
-		spin_lock_irq(&intfdata->susp_lock);
-		b = intfdata->in_flight;
-		spin_unlock_irq(&intfdata->susp_lock);
-
-		if (b)
+		if (intfdata->in_flight) {
+			spin_unlock_irq(&intfdata->susp_lock);
 			return -EBUSY;
+		}
 	}
-
-	spin_lock_irq(&intfdata->susp_lock);
 	intfdata->suspended = 1;
 	spin_unlock_irq(&intfdata->susp_lock);
+
 	stop_read_write_urbs(serial);
 
 	return 0;
 }
 EXPORT_SYMBOL(usb_wwan_suspend);
 
-static void unbusy_queued_urb(struct urb *urb, struct usb_wwan_port_private *portdata)
-{
-	int i;
-
-	for (i = 0; i < N_OUT_URB; i++) {
-		if (urb == portdata->out_urbs[i]) {
-			clear_bit(i, &portdata->out_busy);
-			break;
-		}
-	}
-}
-
-static void play_delayed(struct usb_serial_port *port)
+static int play_delayed(struct usb_serial_port *port)
 {
 	struct usb_wwan_intf_private *data;
 	struct usb_wwan_port_private *portdata;
 	struct urb *urb;
-	int err;
+	int err = 0;
 
 	portdata = usb_get_serial_port_data(port);
 	data = port->serial->private;
@@ -634,6 +641,8 @@ static void play_delayed(struct usb_serial_port *port)
 			break;
 		}
 	}
+
+	return err;
 }
 
 int usb_wwan_resume(struct usb_serial *serial)
@@ -643,54 +652,51 @@ int usb_wwan_resume(struct usb_serial *serial)
 	struct usb_wwan_intf_private *intfdata = serial->private;
 	struct usb_wwan_port_private *portdata;
 	struct urb *urb;
-	int err = 0;
-
-	/* get the interrupt URBs resubmitted unconditionally */
-	for (i = 0; i < serial->num_ports; i++) {
-		port = serial->port[i];
-		if (!port->interrupt_in_urb) {
-			dev_dbg(&port->dev, "%s: No interrupt URB for port\n", __func__);
-			continue;
-		}
-		err = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO);
-		dev_dbg(&port->dev, "Submitted interrupt URB for port (result %d)\n", err);
-		if (err < 0) {
-			dev_err(&port->dev, "%s: Error %d for interrupt URB\n",
-				__func__, err);
-			goto err_out;
-		}
-	}
+	int err;
+	int err_count = 0;
 
+	spin_lock_irq(&intfdata->susp_lock);
 	for (i = 0; i < serial->num_ports; i++) {
 		/* walk all ports */
 		port = serial->port[i];
 		portdata = usb_get_serial_port_data(port);
 
 		/* skip closed ports */
-		spin_lock_irq(&intfdata->susp_lock);
-		if (!portdata || !portdata->opened) {
-			spin_unlock_irq(&intfdata->susp_lock);
+		if (!portdata || !portdata->opened)
 			continue;
+
+		if (port->interrupt_in_urb) {
+			err = usb_submit_urb(port->interrupt_in_urb,
+					GFP_ATOMIC);
+			if (err) {
+				dev_err(&port->dev,
+					"%s: submit int urb failed: %d\n",
+					__func__, err);
+				err_count++;
+			}
 		}
 
+		err = play_delayed(port);
+		if (err)
+			err_count++;
+
 		for (j = 0; j < N_IN_URB; j++) {
 			urb = portdata->in_urbs[j];
 			err = usb_submit_urb(urb, GFP_ATOMIC);
 			if (err < 0) {
 				dev_err(&port->dev, "%s: Error %d for bulk URB %d\n",
 					__func__, err, i);
-				spin_unlock_irq(&intfdata->susp_lock);
-				goto err_out;
+				err_count++;
 			}
 		}
-		play_delayed(port);
-		spin_unlock_irq(&intfdata->susp_lock);
 	}
-	spin_lock_irq(&intfdata->susp_lock);
 	intfdata->suspended = 0;
 	spin_unlock_irq(&intfdata->susp_lock);
-err_out:
-	return err;
+
+	if (err_count)
+		return -EIO;
+
+	return 0;
 }
 EXPORT_SYMBOL(usb_wwan_resume);
 #endif
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index e62f2dff8b7d..6c3734d2b45a 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -514,6 +514,10 @@ static void command_port_read_callback(struct urb *urb)
 		dev_dbg(&urb->dev->dev, "%s - command_info is NULL, exiting.\n", __func__);
 		return;
 	}
+	if (!urb->actual_length) {
+		dev_dbg(&urb->dev->dev, "%s - empty response, exiting.\n", __func__);
+		return;
+	}
 	if (status) {
 		dev_dbg(&urb->dev->dev, "%s - nonzero urb status: %d\n", __func__, status);
 		if (status != -ENOENT)
@@ -534,7 +538,8 @@ static void command_port_read_callback(struct urb *urb)
 		/* These are unsolicited reports from the firmware, hence no
 		   waiting command to wakeup */
 		dev_dbg(&urb->dev->dev, "%s - event received\n", __func__);
-	} else if (data[0] == WHITEHEAT_GET_DTR_RTS) {
+	} else if ((data[0] == WHITEHEAT_GET_DTR_RTS) &&
+		(urb->actual_length - 1 <= sizeof(command_info->result_buffer))) {
 		memcpy(command_info->result_buffer, &data[1],
 						urb->actual_length - 1);
 		command_info->command_finished = WHITEHEAT_CMD_COMPLETE;
diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c
index e40ab739c4a6..c9bb107d5e5c 100644
--- a/drivers/usb/serial/zte_ev.c
+++ b/drivers/usb/serial/zte_ev.c
@@ -272,28 +272,16 @@ static void zte_ev_usb_serial_close(struct usb_serial_port *port)
 }
 
 static const struct usb_device_id id_table[] = {
-	/* AC8710, AC8710T */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffff, 0xff, 0xff, 0xff) },
-	 /* AC8700 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfffe, 0xff, 0xff, 0xff) },
-	/* MG880 */
-	{ USB_DEVICE(0x19d2, 0xfffd) },
-	{ USB_DEVICE(0x19d2, 0xfffc) },
-	{ USB_DEVICE(0x19d2, 0xfffb) },
-	/* AC8710_V3 */
+	{ USB_DEVICE(0x19d2, 0xffec) },
+	{ USB_DEVICE(0x19d2, 0xffee) },
 	{ USB_DEVICE(0x19d2, 0xfff6) },
 	{ USB_DEVICE(0x19d2, 0xfff7) },
 	{ USB_DEVICE(0x19d2, 0xfff8) },
 	{ USB_DEVICE(0x19d2, 0xfff9) },
-	{ USB_DEVICE(0x19d2, 0xffee) },
-	/* AC2716, MC2716 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffed, 0xff, 0xff, 0xff) },
-	/* AD3812 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffeb, 0xff, 0xff, 0xff) },
-	{ USB_DEVICE(0x19d2, 0xffec) },
-	{ USB_DEVICE(0x05C6, 0x3197) },
-	{ USB_DEVICE(0x05C6, 0x6000) },
-	{ USB_DEVICE(0x05C6, 0x9008) },
+	{ USB_DEVICE(0x19d2, 0xfffb) },
+	{ USB_DEVICE(0x19d2, 0xfffc) },
+	/* MG880 */
+	{ USB_DEVICE(0x19d2, 0xfffd) },
 	{ },
 };
 MODULE_DEVICE_TABLE(usb, id_table);
diff --git a/drivers/usb/storage/shuttle_usbat.c b/drivers/usb/storage/shuttle_usbat.c
index 4ef2a80728f7..008d805c3d21 100644
--- a/drivers/usb/storage/shuttle_usbat.c
+++ b/drivers/usb/storage/shuttle_usbat.c
@@ -1851,7 +1851,7 @@ static int usbat_probe(struct usb_interface *intf,
 	us->transport_name = "Shuttle USBAT";
 	us->transport = usbat_flash_transport;
 	us->transport_reset = usb_stor_CB_reset;
-	us->max_lun = 1;
+	us->max_lun = 0;
 
 	result = usb_stor_probe2(us);
 	return result;
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 22c7d4360fa2..b1d815eb6d0b 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -1118,6 +1118,31 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us)
 		 */
 		if (result == USB_STOR_XFER_LONG)
 			fake_sense = 1;
+
+		/*
+		 * Sometimes a device will mistakenly skip the data phase
+		 * and go directly to the status phase without sending a
+		 * zero-length packet.  If we get a 13-byte response here,
+		 * check whether it really is a CSW.
+		 */
+		if (result == USB_STOR_XFER_SHORT &&
+				srb->sc_data_direction == DMA_FROM_DEVICE &&
+				transfer_length - scsi_get_resid(srb) ==
+					US_BULK_CS_WRAP_LEN) {
+			struct scatterlist *sg = NULL;
+			unsigned int offset = 0;
+
+			if (usb_stor_access_xfer_buf((unsigned char *) bcs,
+					US_BULK_CS_WRAP_LEN, srb, &sg,
+					&offset, FROM_XFER_BUF) ==
+						US_BULK_CS_WRAP_LEN &&
+					bcs->Signature ==
+						cpu_to_le32(US_BULK_CS_SIGN)) {
+				usb_stor_dbg(us, "Device skipped data phase\n");
+				scsi_set_resid(srb, transfer_length);
+				goto skipped_data_phase;
+			}
+		}
 	}
 
 	/* See flow chart on pg 15 of the Bulk Only Transport spec for
@@ -1153,6 +1178,7 @@ int usb_stor_Bulk_transport(struct scsi_cmnd *srb, struct us_data *us)
 	if (result != USB_STOR_XFER_GOOD)
 		return USB_STOR_TRANSPORT_ERROR;
 
+ skipped_data_phase:
 	/* check bulk status */
 	residue = le32_to_cpu(bcs->Residue);
 	usb_stor_dbg(us, "Bulk Status S 0x%x T 0x%x R %u Stat 0x%x\n",
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index adbeb255616a..7f625306ea80 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -101,6 +101,12 @@ UNUSUAL_DEV(  0x03f0, 0x4002, 0x0001, 0x0001,
 		"PhotoSmart R707",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_FIX_CAPACITY),
 
+UNUSUAL_DEV(  0x03f3, 0x0001, 0x0000, 0x9999,
+		"Adaptec",
+		"USBConnect 2000",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Reported by Sebastian Kapfer <sebastian_kapfer@gmx.net>
  * and Olaf Hering <olh@suse.de> (different bcd's, same vendor/product)
  * for USB floppies that need the SINGLE_LUN enforcement.
@@ -234,6 +240,20 @@ UNUSUAL_DEV(  0x0421, 0x0495, 0x0370, 0x0370,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_MAX_SECTORS_64 ),
 
+/* Reported by Daniele Forsi <dforsi@gmail.com> */
+UNUSUAL_DEV(  0x0421, 0x04b9, 0x0350, 0x0350,
+		"Nokia",
+		"5300",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64 ),
+
+/* Patch submitted by Victor A. Santos <victoraur.santos@gmail.com> */
+UNUSUAL_DEV(  0x0421, 0x05af, 0x0742, 0x0742,
+		"Nokia",
+		"305",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64),
+
 /* Patch submitted by Mikhail Zolotaryov <lebon@lebon.org.ua> */
 UNUSUAL_DEV(  0x0421, 0x06aa, 0x1110, 0x1110,
 		"Nokia",
@@ -727,6 +747,12 @@ UNUSUAL_DEV(  0x059b, 0x0001, 0x0100, 0x0100,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_SINGLE_LUN ),
 
+UNUSUAL_DEV(  0x059b, 0x0040, 0x0100, 0x0100,
+		"Iomega",
+		"Jaz USB Adapter",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_SINGLE_LUN ),
+
 /* Reported by <Hendryk.Pfeiffer@gmx.de> */
 UNUSUAL_DEV(  0x059f, 0x0643, 0x0000, 0x0000,
 		"LaCie",
@@ -1099,6 +1125,18 @@ UNUSUAL_DEV(  0x0851, 0x1543, 0x0200, 0x0200,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NOT_LOCKABLE),
 
+UNUSUAL_DEV(  0x085a, 0x0026, 0x0100, 0x0133,
+		"Xircom",
+		"PortGear USB-SCSI (Mac USB Dock)",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
+UNUSUAL_DEV(  0x085a, 0x0028, 0x0100, 0x0133,
+		"Xircom",
+		"PortGear USB to SCSI Converter",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Submitted by Jan De Luyck <lkml@kcore.org> */
 UNUSUAL_DEV(  0x08bd, 0x1100, 0x0000, 0x0000,
 		"CITIZEN",
@@ -1931,6 +1969,14 @@ UNUSUAL_DEV(  0x152d, 0x2329, 0x0100, 0x0100,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ),
 
+/* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI)
+ * and Mac USB Dock USB-SCSI */
+UNUSUAL_DEV(  0x1645, 0x0007, 0x0100, 0x0133,
+		"Entrega Technologies",
+		"USB to SCSI Converter",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Reported by Robert Schedel <r.schedel@yahoo.de>
  * Note: this is a 'super top' device like the above 14cd/6600 device */
 UNUSUAL_DEV(  0x1652, 0x6600, 0x0201, 0x0201,
@@ -1953,6 +1999,12 @@ UNUSUAL_DEV(  0x177f, 0x0400, 0x0000, 0x0000,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ),
 
+UNUSUAL_DEV(  0x1822, 0x0001, 0x0000, 0x9999,
+		"Ariston Technologies",
+		"iConnect USB to SCSI adapter",
+		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		US_FL_SCM_MULT_TARG ),
+
 /* Reported by Hans de Goede <hdegoede@redhat.com>
  * These Appotech controllers are found in Picture Frames, they provide a
  * (buggy) emulation of a cdrom drive which contains the windows software
diff --git a/drivers/uwb/lc-dev.c b/drivers/uwb/lc-dev.c
index 80079b8fed15..d0303f0dbe15 100644
--- a/drivers/uwb/lc-dev.c
+++ b/drivers/uwb/lc-dev.c
@@ -431,16 +431,19 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce)
 	uwb_dev->mac_addr = *bce->mac_addr;
 	uwb_dev->dev_addr = bce->dev_addr;
 	dev_set_name(&uwb_dev->dev, "%s", macbuf);
+
+	/* plug the beacon cache */
+	bce->uwb_dev = uwb_dev;
+	uwb_dev->bce = bce;
+	uwb_bce_get(bce);		/* released in uwb_dev_sys_release() */
+
 	result = uwb_dev_add(uwb_dev, &rc->uwb_dev.dev, rc);
 	if (result < 0) {
 		dev_err(dev, "new device %s: cannot instantiate device\n",
 			macbuf);
 		goto error_dev_add;
 	}
-	/* plug the beacon cache */
-	bce->uwb_dev = uwb_dev;
-	uwb_dev->bce = bce;
-	uwb_bce_get(bce);		/* released in uwb_dev_sys_release() */
+
 	dev_info(dev, "uwb device (mac %s dev %s) connected to %s %s\n",
 		 macbuf, devbuf, rc->uwb_dev.dev.parent->bus->name,
 		 dev_name(rc->uwb_dev.dev.parent));
@@ -448,6 +451,8 @@ void uwbd_dev_onair(struct uwb_rc *rc, struct uwb_beca_e *bce)
 	return;
 
 error_dev_add:
+	bce->uwb_dev = NULL;
+	uwb_bce_put(bce);
 	kfree(uwb_dev);
 	return;
 }
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index e48d4a672580..5d0b7b846440 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1200,6 +1200,7 @@ static int
 vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 			struct vhost_scsi_target *t)
 {
+	struct se_portal_group *se_tpg;
 	struct tcm_vhost_tport *tv_tport;
 	struct tcm_vhost_tpg *tpg;
 	struct tcm_vhost_tpg **vs_tpg;
@@ -1247,6 +1248,21 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 				ret = -EEXIST;
 				goto out;
 			}
+			/*
+			 * In order to ensure individual vhost-scsi configfs
+			 * groups cannot be removed while in use by vhost ioctl,
+			 * go ahead and take an explicit se_tpg->tpg_group.cg_item
+			 * dependency now.
+			 */
+			se_tpg = &tpg->se_tpg;
+			ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
+						   &se_tpg->tpg_group.cg_item);
+			if (ret) {
+				pr_warn("configfs_depend_item() failed: %d\n", ret);
+				kfree(vs_tpg);
+				mutex_unlock(&tpg->tv_tpg_mutex);
+				goto out;
+			}
 			tpg->tv_tpg_vhost_count++;
 			tpg->vhost_scsi = vs;
 			vs_tpg[tpg->tport_tpgt] = tpg;
@@ -1289,6 +1305,7 @@ static int
 vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
 			  struct vhost_scsi_target *t)
 {
+	struct se_portal_group *se_tpg;
 	struct tcm_vhost_tport *tv_tport;
 	struct tcm_vhost_tpg *tpg;
 	struct vhost_virtqueue *vq;
@@ -1337,6 +1354,13 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
 		vs->vs_tpg[target] = NULL;
 		match = true;
 		mutex_unlock(&tpg->tv_tpg_mutex);
+		/*
+		 * Release se_tpg->tpg_group.cg_item configfs dependency now
+		 * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur.
+		 */
+		se_tpg = &tpg->se_tpg;
+		configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
+				       &se_tpg->tpg_group.cg_item);
 	}
 	if (match) {
 		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index dade5b7699bc..e711c513063b 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -39,6 +39,11 @@ config VIDEOMODE_HELPERS
 config HDMI
 	bool
 
+config VEXPRESS_DVI_CONTROL
+	bool "Versatile Express DVI control"
+	depends on FB && VEXPRESS_CONFIG
+	default y
+
 menuconfig FB
 	tristate "Support for frame buffer devices"
 	---help---
@@ -327,6 +332,21 @@ config FB_ARMCLCD
 	  here and read <file:Documentation/kbuild/modules.txt>.  The module
 	  will be called amba-clcd.
 
+config FB_ARMHDLCD
+	tristate "ARM High Definition LCD support"
+	depends on FB && ARM
+	select FB_CFB_FILLRECT
+	select FB_CFB_COPYAREA
+	select FB_CFB_IMAGEBLIT
+	help
+	  This framebuffer device driver is for the ARM High Definition
+	  Colour LCD controller.
+
+	  If you want to compile this as a module (=code which can be
+	  inserted into and removed from the running kernel), say M
+	  here and read <file:Documentation/kbuild/modules.txt>.  The module
+	  will be called arm-hdlcd.
+
 config FB_ACORN
 	bool "Acorn VIDC support"
 	depends on (FB = y) && ARM && ARCH_ACORN
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index ae17ddf49a00..2889346c1956 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -99,6 +99,7 @@ obj-$(CONFIG_FB_ATMEL)		  += atmel_lcdfb.o
 obj-$(CONFIG_FB_PVR2)             += pvr2fb.o
 obj-$(CONFIG_FB_VOODOO1)          += sstfb.o
 obj-$(CONFIG_FB_ARMCLCD)	  += amba-clcd.o
+obj-$(CONFIG_FB_ARMHDLCD)	  += arm-hdlcd.o
 obj-$(CONFIG_FB_GOLDFISH)         += goldfishfb.o
 obj-$(CONFIG_FB_68328)            += 68328fb.o
 obj-$(CONFIG_FB_GBE)              += gbefb.o
@@ -178,3 +179,6 @@ obj-$(CONFIG_VIDEOMODE_HELPERS) += display_timing.o videomode.o
 ifeq ($(CONFIG_OF),y)
 obj-$(CONFIG_VIDEOMODE_HELPERS) += of_display_timing.o of_videomode.o
 endif
+
+# platform specific output drivers
+obj-$(CONFIG_VEXPRESS_DVI_CONTROL) += vexpress-dvi.o
diff --git a/drivers/video/amba-clcd.c b/drivers/video/amba-clcd.c
index 14d6b3793e0a..12f8c4640397 100644
--- a/drivers/video/amba-clcd.c
+++ b/drivers/video/amba-clcd.c
@@ -17,7 +17,10 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
+#include <linux/of.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
@@ -31,8 +34,20 @@
 
 #define to_clcd(info)	container_of(info, struct clcd_fb, fb)
 
+#ifdef CONFIG_ARM
+#define clcdfb_dma_alloc	dma_alloc_writecombine
+#define clcdfb_dma_free		dma_free_writecombine
+#define clcdfb_dma_mmap		dma_mmap_writecombine
+#else
+#define clcdfb_dma_alloc	dma_alloc_coherent
+#define clcdfb_dma_free		dma_free_coherent
+#define clcdfb_dma_mmap		dma_mmap_coherent
+#endif
+
 /* This is limited to 16 characters when displayed by X startup */
 static const char *clcd_name = "CLCD FB";
+static char *def_mode;
+module_param_named(mode, def_mode, charp, 0);
 
 /*
  * Unfortunately, the enable/disable functions may be called either from
@@ -234,6 +249,17 @@ clcdfb_set_bitfields(struct clcd_fb *fb, struct fb_var_screeninfo *var)
 		bgr = caps & CLCD_CAP_BGR && var->blue.offset == 0;
 		rgb = caps & CLCD_CAP_RGB && var->red.offset == 0;
 
+		/*
+		 * Seems that for 32-bit mode there is confusion about RGB
+		 * ordering somewhere between user-side, kernel and hardware.
+		 * The following hack seems get things working, at least on
+		 * vexpress hardware and models...
+		 */
+		if (var->bits_per_pixel == 32) {
+			bgr = false;
+			rgb = true;
+		}
+
 		if (!bgr && !rgb)
 			/*
 			 * The requested format was not possible, try just
@@ -393,6 +419,44 @@ static int clcdfb_blank(int blank_mode, struct fb_info *info)
 	return 0;
 }
 
+int clcdfb_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+	return clcdfb_dma_mmap(&fb->dev->dev, vma,
+			       fb->fb.screen_base,
+			       fb->fb.fix.smem_start,
+			       fb->fb.fix.smem_len);
+}
+
+int clcdfb_mmap_io(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+	unsigned long user_count, count, pfn, off;
+
+	user_count	= (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	count		= PAGE_ALIGN(fb->fb.fix.smem_len) >> PAGE_SHIFT;
+	pfn		= fb->fb.fix.smem_start >> PAGE_SHIFT;
+	off		= vma->vm_pgoff;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (off < count && user_count <= (count - off))
+		return remap_pfn_range(vma, vma->vm_start, pfn + off,
+				       user_count << PAGE_SHIFT,
+				       vma->vm_page_prot);
+
+	return -ENXIO;
+}
+
+void clcdfb_remove_dma(struct clcd_fb *fb)
+{
+	clcdfb_dma_free(&fb->dev->dev, fb->fb.fix.smem_len,
+			fb->fb.screen_base, fb->fb.fix.smem_start);
+}
+
+void clcdfb_remove_io(struct clcd_fb *fb)
+{
+	iounmap(fb->fb.screen_base);
+}
+
 static int clcdfb_mmap(struct fb_info *info,
 		       struct vm_area_struct *vma)
 {
@@ -543,14 +607,247 @@ static int clcdfb_register(struct clcd_fb *fb)
 	return ret;
 }
 
+struct string_lookup {
+	const char *string;
+	const u32	val;
+};
+
+static struct string_lookup vmode_lookups[] = {
+	{ "FB_VMODE_NONINTERLACED", FB_VMODE_NONINTERLACED},
+	{ "FB_VMODE_INTERLACED",    FB_VMODE_INTERLACED},
+	{ "FB_VMODE_DOUBLE",        FB_VMODE_DOUBLE},
+	{ "FB_VMODE_ODD_FLD_FIRST", FB_VMODE_ODD_FLD_FIRST},
+	{ NULL, 0 },
+};
+
+static struct string_lookup tim2_lookups[] = {
+	{ "TIM2_CLKSEL", TIM2_CLKSEL},
+	{ "TIM2_IVS",    TIM2_IVS},
+	{ "TIM2_IHS",    TIM2_IHS},
+	{ "TIM2_IPC",    TIM2_IPC},
+	{ "TIM2_IOE",    TIM2_IOE},
+	{ "TIM2_BCD",    TIM2_BCD},
+	{ NULL, 0},
+};
+static struct string_lookup cntl_lookups[] = {
+	{"CNTL_LCDEN",        CNTL_LCDEN},
+	{"CNTL_LCDBPP1",      CNTL_LCDBPP1},
+	{"CNTL_LCDBPP2",      CNTL_LCDBPP2},
+	{"CNTL_LCDBPP4",      CNTL_LCDBPP4},
+	{"CNTL_LCDBPP8",      CNTL_LCDBPP8},
+	{"CNTL_LCDBPP16",     CNTL_LCDBPP16},
+	{"CNTL_LCDBPP16_565", CNTL_LCDBPP16_565},
+	{"CNTL_LCDBPP16_444", CNTL_LCDBPP16_444},
+	{"CNTL_LCDBPP24",     CNTL_LCDBPP24},
+	{"CNTL_LCDBW",        CNTL_LCDBW},
+	{"CNTL_LCDTFT",       CNTL_LCDTFT},
+	{"CNTL_LCDMONO8",     CNTL_LCDMONO8},
+	{"CNTL_LCDDUAL",      CNTL_LCDDUAL},
+	{"CNTL_BGR",          CNTL_BGR},
+	{"CNTL_BEBO",         CNTL_BEBO},
+	{"CNTL_BEPO",         CNTL_BEPO},
+	{"CNTL_LCDPWR",       CNTL_LCDPWR},
+	{"CNTL_LCDVCOMP(1)",  CNTL_LCDVCOMP(1)},
+	{"CNTL_LCDVCOMP(2)",  CNTL_LCDVCOMP(2)},
+	{"CNTL_LCDVCOMP(3)",  CNTL_LCDVCOMP(3)},
+	{"CNTL_LCDVCOMP(4)",  CNTL_LCDVCOMP(4)},
+	{"CNTL_LCDVCOMP(5)",  CNTL_LCDVCOMP(5)},
+	{"CNTL_LCDVCOMP(6)",  CNTL_LCDVCOMP(6)},
+	{"CNTL_LCDVCOMP(7)",  CNTL_LCDVCOMP(7)},
+	{"CNTL_LDMAFIFOTIME", CNTL_LDMAFIFOTIME},
+	{"CNTL_WATERMARK",    CNTL_WATERMARK},
+	{ NULL, 0},
+};
+static struct string_lookup caps_lookups[] = {
+	{"CLCD_CAP_RGB444",  CLCD_CAP_RGB444},
+	{"CLCD_CAP_RGB5551", CLCD_CAP_RGB5551},
+	{"CLCD_CAP_RGB565",  CLCD_CAP_RGB565},
+	{"CLCD_CAP_RGB888",  CLCD_CAP_RGB888},
+	{"CLCD_CAP_BGR444",  CLCD_CAP_BGR444},
+	{"CLCD_CAP_BGR5551", CLCD_CAP_BGR5551},
+	{"CLCD_CAP_BGR565",  CLCD_CAP_BGR565},
+	{"CLCD_CAP_BGR888",  CLCD_CAP_BGR888},
+	{"CLCD_CAP_444",     CLCD_CAP_444},
+	{"CLCD_CAP_5551",    CLCD_CAP_5551},
+	{"CLCD_CAP_565",     CLCD_CAP_565},
+	{"CLCD_CAP_888",     CLCD_CAP_888},
+	{"CLCD_CAP_RGB",     CLCD_CAP_RGB},
+	{"CLCD_CAP_BGR",     CLCD_CAP_BGR},
+	{"CLCD_CAP_ALL",     CLCD_CAP_ALL},
+	{ NULL, 0},
+};
+
+u32 parse_setting(struct string_lookup *lookup, const char *name)
+{
+	int i = 0;
+	while (lookup[i].string != NULL) {
+		if (strcmp(lookup[i].string, name) == 0)
+			return lookup[i].val;
+		++i;
+	}
+	return -EINVAL;
+}
+
+u32 get_string_lookup(struct device_node *node, const char *name,
+		      struct string_lookup *lookup)
+{
+	const char *string;
+	int count, i, ret = 0;
+
+	count = of_property_count_strings(node, name);
+	if (count >= 0)
+		for (i = 0; i < count; i++)
+			if (of_property_read_string_index(node, name, i,
+					&string) == 0)
+				ret |= parse_setting(lookup, string);
+	return ret;
+}
+
+int get_val(struct device_node *node, const char *string)
+{
+	u32 ret = 0;
+
+	if (of_property_read_u32(node, string, &ret))
+		ret = -1;
+	return ret;
+}
+
+struct clcd_panel *getPanel(struct device_node *node)
+{
+	static struct clcd_panel panel;
+
+	panel.mode.refresh      = get_val(node, "refresh");
+	panel.mode.xres         = get_val(node, "xres");
+	panel.mode.yres         = get_val(node, "yres");
+	panel.mode.pixclock     = get_val(node, "pixclock");
+	panel.mode.left_margin  = get_val(node, "left_margin");
+	panel.mode.right_margin = get_val(node, "right_margin");
+	panel.mode.upper_margin = get_val(node, "upper_margin");
+	panel.mode.lower_margin = get_val(node, "lower_margin");
+	panel.mode.hsync_len    = get_val(node, "hsync_len");
+	panel.mode.vsync_len    = get_val(node, "vsync_len");
+	panel.mode.sync         = get_val(node, "sync");
+	panel.bpp               = get_val(node, "bpp");
+	panel.width             = (signed short) get_val(node, "width");
+	panel.height            = (signed short) get_val(node, "height");
+
+	panel.mode.vmode = get_string_lookup(node, "vmode", vmode_lookups);
+	panel.tim2       = get_string_lookup(node, "tim2",  tim2_lookups);
+	panel.cntl       = get_string_lookup(node, "cntl",  cntl_lookups);
+	panel.caps       = get_string_lookup(node, "caps",  caps_lookups);
+
+	return &panel;
+}
+
+struct clcd_panel *clcdfb_get_panel(const char *name)
+{
+	struct device_node *node = NULL;
+	const char *mode;
+	struct clcd_panel *panel = NULL;
+
+	do {
+		node = of_find_compatible_node(node, NULL, "panel");
+		if (node)
+			if (of_property_read_string(node, "mode", &mode) == 0)
+				if (strcmp(mode, name) == 0) {
+					panel = getPanel(node);
+					panel->mode.name = name;
+				}
+	} while (node != NULL);
+
+	return panel;
+}
+
+#ifdef CONFIG_OF
+static int clcdfb_dt_init(struct clcd_fb *fb)
+{
+	int err = 0;
+	struct device_node *node;
+	const char *mode;
+	dma_addr_t dma;
+	u32 use_dma;
+	const __be32 *prop;
+	int len, na, ns;
+	phys_addr_t fb_base, fb_size;
+
+	node = fb->dev->dev.of_node;
+	if (!node)
+		return -ENODEV;
+
+	na = of_n_addr_cells(node);
+	ns = of_n_size_cells(node);
+
+	if (def_mode && strlen(def_mode) > 0) {
+		fb->panel = clcdfb_get_panel(def_mode);
+		if (!fb->panel)
+			printk(KERN_ERR "CLCD: invalid mode specified on the command line (%s)\n", def_mode);
+	}
+
+	if (!fb->panel) {
+		if (WARN_ON(of_property_read_string(node, "mode", &mode)))
+			return -ENODEV;
+		fb->panel = clcdfb_get_panel(mode);
+	}
+
+	if (!fb->panel)
+		return -EINVAL;
+	fb->fb.fix.smem_len = fb->panel->mode.xres * fb->panel->mode.yres * 4;
+
+	fb->board->name		= "Device Tree CLCD PL111";
+	fb->board->caps		= CLCD_CAP_5551 | CLCD_CAP_565 | CLCD_CAP_888;
+	fb->board->check	= clcdfb_check;
+	fb->board->decode	= clcdfb_decode;
+
+	if (of_property_read_u32(node, "use_dma", &use_dma))
+		use_dma = 0;
+
+	if (use_dma) {
+		fb->fb.screen_base = clcdfb_dma_alloc(&fb->dev->dev,
+						      fb->fb.fix.smem_len,
+						      &dma, GFP_KERNEL);
+		if (!fb->fb.screen_base) {
+			pr_err("CLCD: unable to map framebuffer\n");
+			return -ENOMEM;
+		}
+
+		fb->fb.fix.smem_start	= dma;
+		fb->board->mmap		= clcdfb_mmap_dma;
+		fb->board->remove	= clcdfb_remove_dma;
+	} else {
+		prop = of_get_property(node, "framebuffer", &len);
+		if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+			return -EINVAL;
+
+		fb_base = of_read_number(prop, na);
+		fb_size = of_read_number(prop + na, ns);
+
+		fb->fb.fix.smem_start	= fb_base;
+		fb->fb.screen_base	= ioremap_wc(fb_base, fb_size);
+		fb->board->mmap		= clcdfb_mmap_io;
+		fb->board->remove	= clcdfb_remove_io;
+	}
+
+	return err;
+}
+#endif /* CONFIG_OF */
+
 static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id)
 {
 	struct clcd_board *board = dev_get_platdata(&dev->dev);
 	struct clcd_fb *fb;
 	int ret;
 
-	if (!board)
-		return -EINVAL;
+	if (!board) {
+#ifdef CONFIG_OF
+		if (dev->dev.of_node) {
+			board = kzalloc(sizeof(struct clcd_board), GFP_KERNEL);
+			if (!board)
+				return -ENOMEM;
+			board->setup   = clcdfb_dt_init;
+		} else
+#endif
+			return -EINVAL;
+	}
 
 	ret = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32));
 	if (ret)
diff --git a/drivers/video/arm-hdlcd.c b/drivers/video/arm-hdlcd.c
new file mode 100644
index 000000000000..cfd631e3dc52
--- /dev/null
+++ b/drivers/video/arm-hdlcd.c
@@ -0,0 +1,844 @@
+/*
+ * drivers/video/arm-hdlcd.c
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ *  ARM HDLCD Controller
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/fb.h>
+#include <linux/clk.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/memblock.h>
+#include <linux/arm-hdlcd.h>
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#endif
+
+#include "edid.h"
+
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+int get_edid(u8 *msgbuf);
+#else
+#endif
+
+#define to_hdlcd_device(info)	container_of(info, struct hdlcd_device, fb)
+
+static struct of_device_id  hdlcd_of_matches[] = {
+	{ .compatible	= "arm,hdlcd" },
+	{},
+};
+
+/* Framebuffer size.  */
+static unsigned long framebuffer_size;
+
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+static unsigned long buffer_underrun_events;
+static DEFINE_SPINLOCK(hdlcd_underrun_lock);
+
+static void hdlcd_underrun_set(unsigned long val)
+{
+	spin_lock(&hdlcd_underrun_lock);
+	buffer_underrun_events = val;
+	spin_unlock(&hdlcd_underrun_lock);
+}
+
+static unsigned long hdlcd_underrun_get(void)
+{
+	unsigned long val;
+	spin_lock(&hdlcd_underrun_lock);
+	val = buffer_underrun_events;
+	spin_unlock(&hdlcd_underrun_lock);
+	return val;
+}
+
+#ifdef CONFIG_PROC_FS
+static int hdlcd_underrun_show(struct seq_file *m, void *v)
+{
+	unsigned char underrun_string[32];
+	snprintf(underrun_string, 32, "%lu\n", hdlcd_underrun_get());
+	seq_puts(m, underrun_string);
+	return 0;
+}
+
+static int proc_hdlcd_underrun_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hdlcd_underrun_show, NULL);
+}
+
+static const struct file_operations proc_hdlcd_underrun_operations = {
+	.open		= proc_hdlcd_underrun_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hdlcd_underrun_init(void)
+{
+	hdlcd_underrun_set(0);
+	proc_create("hdlcd_underrun", 0, NULL, &proc_hdlcd_underrun_operations);
+	return 0;
+}
+static void hdlcd_underrun_close(void)
+{
+	remove_proc_entry("hdlcd_underrun", NULL);
+}
+#else
+static int hdlcd_underrun_init(void) { return 0; }
+static void hdlcd_underrun_close(void) { }
+#endif
+#endif
+
+static char *fb_mode = "1680x1050-32@60\0\0\0\0\0";
+
+static struct fb_var_screeninfo cached_var_screeninfo;
+
+static struct fb_videomode hdlcd_default_mode = {
+	.refresh	= 60,
+	.xres		= 1680,
+	.yres		= 1050,
+	.pixclock	= 8403,
+	.left_margin	= 80,
+	.right_margin	= 48,
+	.upper_margin	= 21,
+	.lower_margin	= 3,
+	.hsync_len	= 32,
+	.vsync_len	= 6,
+	.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+	.vmode		= FB_VMODE_NONINTERLACED
+};
+
+static inline void hdlcd_enable(struct hdlcd_device *hdlcd)
+{
+	dev_dbg(hdlcd->dev, "HDLCD: output enabled\n");
+	writel(1, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static inline void hdlcd_disable(struct hdlcd_device *hdlcd)
+{
+	dev_dbg(hdlcd->dev, "HDLCD: output disabled\n");
+	writel(0, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static int hdlcd_set_bitfields(struct hdlcd_device *hdlcd,
+				struct fb_var_screeninfo *var)
+{
+	int ret = 0;
+
+	memset(&var->transp, 0, sizeof(var->transp));
+	var->red.msb_right = 0;
+	var->green.msb_right = 0;
+	var->blue.msb_right = 0;
+	var->blue.offset = 0;
+
+	switch (var->bits_per_pixel) {
+	case 8:
+		/* pseudocolor */
+		var->red.length = 8;
+		var->green.length = 8;
+		var->blue.length = 8;
+		break;
+	case 16:
+		/* 565 format */
+		var->red.length = 5;
+		var->green.length = 6;
+		var->blue.length = 5;
+		break;
+	case 32:
+		var->transp.length = 8;
+	case 24:
+		var->red.length = 8;
+		var->green.length = 8;
+		var->blue.length = 8;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	if (!ret) {
+		if(var->bits_per_pixel != 32)
+		{
+			var->green.offset = var->blue.length;
+			var->red.offset = var->green.offset + var->green.length;
+		}
+		else
+		{
+			/* Previously, the byte ordering for 32-bit color was
+			 * (msb)<alpha><red><green><blue>(lsb)
+			 * but this does not match what android expects and
+			 * the colors are odd. Instead, use
+			 * <alpha><blue><green><red>
+			 * Since we tell fb what we are doing, console
+			 * , X and directfb access should work fine.
+			 */
+			var->green.offset = var->red.length;
+			var->blue.offset = var->green.offset + var->green.length;
+			var->transp.offset = var->blue.offset + var->blue.length;
+		}
+	}
+
+	return ret;
+}
+
+static int hdlcd_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	int bytes_per_pixel = var->bits_per_pixel / 8;
+
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+	var->yres_virtual = var->yres;
+#else
+	var->yres_virtual = 2 * var->yres;
+#endif
+
+	if ((var->xres_virtual * bytes_per_pixel * var->yres_virtual) > hdlcd->fb.fix.smem_len)
+		return -ENOMEM;
+
+	if (var->xres > HDLCD_MAX_XRES || var->yres > HDLCD_MAX_YRES)
+		return -EINVAL;
+
+	/* make sure the bitfields are set appropriately */
+	return hdlcd_set_bitfields(hdlcd, var);
+}
+
+/* prototype */
+static int hdlcd_pan_display(struct fb_var_screeninfo *var,
+	struct fb_info *info);
+
+#define WRITE_HDLCD_REG(reg, value)	writel((value), hdlcd->base + (reg))
+#define READ_HDLCD_REG(reg)		readl(hdlcd->base + (reg))
+
+static int hdlcd_set_par(struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	int bytes_per_pixel = hdlcd->fb.var.bits_per_pixel / 8;
+	int polarities;
+	int old_yoffset;
+
+	/* check for shortcuts */
+	old_yoffset = cached_var_screeninfo.yoffset;
+	cached_var_screeninfo.yoffset = info->var.yoffset;
+	if (!memcmp(&info->var, &cached_var_screeninfo,
+				sizeof(struct fb_var_screeninfo))) {
+		if(old_yoffset != info->var.yoffset) {
+			/* we only changed yoffset, and we already
+			 * already recorded it a couple lines up
+			 */
+			hdlcd_pan_display(&info->var, info);
+		}
+		/* or no change */
+		return 0;
+	}
+
+	hdlcd->fb.fix.line_length = hdlcd->fb.var.xres * bytes_per_pixel;
+
+	if (hdlcd->fb.var.bits_per_pixel >= 16)
+		hdlcd->fb.fix.visual = FB_VISUAL_TRUECOLOR;
+	else
+		hdlcd->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR;
+
+	memcpy(&cached_var_screeninfo, &info->var, sizeof(struct fb_var_screeninfo));
+
+	polarities = HDLCD_POLARITY_DATAEN |
+#ifndef CONFIG_ARCH_TUSCAN
+		HDLCD_POLARITY_PIXELCLK |
+#endif
+		HDLCD_POLARITY_DATA;
+	polarities |= (hdlcd->fb.var.sync & FB_SYNC_HOR_HIGH_ACT) ? HDLCD_POLARITY_HSYNC : 0;
+	polarities |= (hdlcd->fb.var.sync & FB_SYNC_VERT_HIGH_ACT) ? HDLCD_POLARITY_VSYNC : 0;
+
+	hdlcd_disable(hdlcd);
+
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_LENGTH, hdlcd->fb.var.xres * bytes_per_pixel);
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_PITCH, hdlcd->fb.var.xres * bytes_per_pixel);
+	WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_COUNT, hdlcd->fb.var.yres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_SYNC, hdlcd->fb.var.vsync_len - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_BACK_PORCH, hdlcd->fb.var.upper_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_DATA, hdlcd->fb.var.yres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_V_FRONT_PORCH, hdlcd->fb.var.lower_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_SYNC, hdlcd->fb.var.hsync_len - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_BACK_PORCH, hdlcd->fb.var.left_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_DATA, hdlcd->fb.var.xres - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_H_FRONT_PORCH, hdlcd->fb.var.right_margin - 1);
+	WRITE_HDLCD_REG(HDLCD_REG_POLARITIES, polarities);
+	WRITE_HDLCD_REG(HDLCD_REG_PIXEL_FORMAT, (bytes_per_pixel - 1) << 3);
+#ifdef HDLCD_RED_DEFAULT_COLOUR
+	WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, (0x00ff0000 | (hdlcd->fb.var.red.length & 0xf) << 8) \
+													  | hdlcd->fb.var.red.offset);
+#else
+	WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, ((hdlcd->fb.var.red.length & 0xf) << 8) | hdlcd->fb.var.red.offset);
+#endif
+	WRITE_HDLCD_REG(HDLCD_REG_GREEN_SELECT, ((hdlcd->fb.var.green.length & 0xf) << 8) | hdlcd->fb.var.green.offset);
+	WRITE_HDLCD_REG(HDLCD_REG_BLUE_SELECT, ((hdlcd->fb.var.blue.length & 0xf) << 8) | hdlcd->fb.var.blue.offset);
+
+	clk_set_rate(hdlcd->clk, (1000000000 / hdlcd->fb.var.pixclock) * 1000);
+	clk_enable(hdlcd->clk);
+
+	hdlcd_enable(hdlcd);
+
+	return 0;
+}
+
+static int hdlcd_setcolreg(unsigned int regno, unsigned int red, unsigned int green,
+		unsigned int blue, unsigned int transp, struct fb_info *info)
+{
+	if (regno < 16) {
+		u32 *pal = info->pseudo_palette;
+
+		pal[regno] = ((red >> 8) << info->var.red.offset) |
+			((green >> 8) << info->var.green.offset) |
+			((blue >> 8) << info->var.blue.offset);
+	}
+
+	return 0;
+}
+
+static irqreturn_t hdlcd_irq(int irq, void *data)
+{
+	struct hdlcd_device *hdlcd = data;
+	unsigned long irq_mask, irq_status;
+
+	irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+	irq_status = READ_HDLCD_REG(HDLCD_REG_INT_STATUS);
+
+	/* acknowledge interrupt(s) */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_CLEAR, irq_status);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	if (irq_status & HDLCD_INTERRUPT_UNDERRUN) {
+		/* increment the count */
+		hdlcd_underrun_set(hdlcd_underrun_get() + 1);
+	}
+#endif
+	if (irq_status & HDLCD_INTERRUPT_VSYNC) {
+		/* disable future VSYNC interrupts */
+		WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask & ~HDLCD_INTERRUPT_VSYNC);
+
+		complete(&hdlcd->vsync_completion);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int hdlcd_wait_for_vsync(struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	unsigned long irq_mask;
+	int err;
+
+	/* enable VSYNC interrupt */
+	irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask | HDLCD_INTERRUPT_VSYNC);
+
+	err = wait_for_completion_interruptible_timeout(&hdlcd->vsync_completion,
+							msecs_to_jiffies(100));
+
+	if (!err)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int hdlcd_blank(int blank_mode, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+	switch (blank_mode) {
+	case FB_BLANK_POWERDOWN:
+		clk_disable(hdlcd->clk);
+	case FB_BLANK_NORMAL:
+		hdlcd_disable(hdlcd);
+		break;
+	case FB_BLANK_UNBLANK:
+		clk_enable(hdlcd->clk);
+		hdlcd_enable(hdlcd);
+		break;
+	case FB_BLANK_VSYNC_SUSPEND:
+	case FB_BLANK_HSYNC_SUSPEND:
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+static void hdlcd_mmap_open(struct vm_area_struct *vma)
+{
+}
+
+static void hdlcd_mmap_close(struct vm_area_struct *vma)
+{
+}
+
+static struct vm_operations_struct hdlcd_mmap_ops = {
+	.open	= hdlcd_mmap_open,
+	.close	= hdlcd_mmap_close,
+};
+
+static int hdlcd_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+	unsigned long off;
+	unsigned long start;
+	unsigned long len = hdlcd->fb.fix.smem_len;
+
+	if (vma->vm_end - vma->vm_start == 0)
+		return 0;
+	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
+		return -EINVAL;
+
+	off = vma->vm_pgoff << PAGE_SHIFT;
+	if ((off >= len) || (vma->vm_end - vma->vm_start + off) > len)
+		return -EINVAL;
+
+	start = hdlcd->fb.fix.smem_start;
+	off += start;
+
+	vma->vm_pgoff = off >> PAGE_SHIFT;
+	vma->vm_flags |= VM_IO;
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	vma->vm_ops = &hdlcd_mmap_ops;
+	if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
+				vma->vm_end - vma->vm_start,
+				vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+static int hdlcd_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+	hdlcd->fb.var.yoffset = var->yoffset;
+	WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start +
+			(var->yoffset * hdlcd->fb.fix.line_length));
+
+	hdlcd_wait_for_vsync(info);
+
+	return 0;
+}
+
+static int hdlcd_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
+{
+	int err;
+
+	switch (cmd) {
+	case FBIO_WAITFORVSYNC:
+		err = hdlcd_wait_for_vsync(info);
+		break;
+	default:
+		err = -ENOIOCTLCMD;
+		break;
+	}
+
+	return err;
+}
+
+static struct fb_ops hdlcd_ops = {
+	.owner			= THIS_MODULE,
+	.fb_check_var		= hdlcd_check_var,
+	.fb_set_par		= hdlcd_set_par,
+	.fb_setcolreg		= hdlcd_setcolreg,
+	.fb_blank		= hdlcd_blank,
+	.fb_fillrect		= cfb_fillrect,
+	.fb_copyarea		= cfb_copyarea,
+	.fb_imageblit		= cfb_imageblit,
+	.fb_mmap		= hdlcd_mmap,
+	.fb_pan_display		= hdlcd_pan_display,
+	.fb_ioctl		= hdlcd_ioctl,
+	.fb_compat_ioctl	= hdlcd_ioctl
+};
+
+static int hdlcd_setup(struct hdlcd_device *hdlcd)
+{
+	u32 version;
+	int err = -EFAULT;
+
+	hdlcd->fb.device = hdlcd->dev;
+
+	hdlcd->clk = clk_get(hdlcd->dev, NULL);
+	if (IS_ERR(hdlcd->clk)) {
+		dev_err(hdlcd->dev, "HDLCD: unable to find clock data\n");
+		return PTR_ERR(hdlcd->clk);
+	}
+
+	err = clk_prepare(hdlcd->clk);
+	if (err)
+		goto clk_prepare_err;
+
+	hdlcd->base = ioremap_nocache(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+	if (!hdlcd->base) {
+		dev_err(hdlcd->dev, "HDLCD: unable to map registers\n");
+		goto remap_err;
+	}
+
+	hdlcd->fb.pseudo_palette = kmalloc(sizeof(u32) * 16, GFP_KERNEL);
+	if (!hdlcd->fb.pseudo_palette) {
+		dev_err(hdlcd->dev, "HDLCD: unable to allocate pseudo_palette memory\n");
+		err = -ENOMEM;
+		goto kmalloc_err;
+	}
+
+	version = readl(hdlcd->base + HDLCD_REG_VERSION);
+	if ((version & HDLCD_PRODUCT_MASK) != HDLCD_PRODUCT_ID) {
+		dev_err(hdlcd->dev, "HDLCD: unknown product id: 0x%x\n", version);
+		err = -EINVAL;
+		goto kmalloc_err;
+	}
+	dev_info(hdlcd->dev, "HDLCD: found ARM HDLCD version r%dp%d\n",
+		(version & HDLCD_VERSION_MAJOR_MASK) >> 8,
+		version & HDLCD_VERSION_MINOR_MASK);
+
+	strcpy(hdlcd->fb.fix.id, "hdlcd");
+	hdlcd->fb.fbops			= &hdlcd_ops;
+	hdlcd->fb.flags			= FBINFO_FLAG_DEFAULT/* | FBINFO_VIRTFB*/;
+
+	hdlcd->fb.fix.type		= FB_TYPE_PACKED_PIXELS;
+	hdlcd->fb.fix.type_aux		= 0;
+	hdlcd->fb.fix.xpanstep		= 0;
+	hdlcd->fb.fix.ypanstep		= 1;
+	hdlcd->fb.fix.ywrapstep		= 0;
+	hdlcd->fb.fix.accel		= FB_ACCEL_NONE;
+
+	hdlcd->fb.var.nonstd		= 0;
+	hdlcd->fb.var.activate		= FB_ACTIVATE_NOW;
+	hdlcd->fb.var.height		= -1;
+	hdlcd->fb.var.width		= -1;
+	hdlcd->fb.var.accel_flags	= 0;
+
+	init_completion(&hdlcd->vsync_completion);
+
+	if (hdlcd->edid) {
+		/* build modedb from EDID */
+		fb_edid_to_monspecs(hdlcd->edid, &hdlcd->fb.monspecs);
+		fb_videomode_to_modelist(hdlcd->fb.monspecs.modedb,
+					hdlcd->fb.monspecs.modedb_len,
+					&hdlcd->fb.modelist);
+		fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode,
+			hdlcd->fb.monspecs.modedb,
+			hdlcd->fb.monspecs.modedb_len,
+			&hdlcd_default_mode, 32);
+	} else {
+		hdlcd->fb.monspecs.hfmin	= 0;
+		hdlcd->fb.monspecs.hfmax	= 100000;
+		hdlcd->fb.monspecs.vfmin	= 0;
+		hdlcd->fb.monspecs.vfmax	= 400;
+		hdlcd->fb.monspecs.dclkmin	= 1000000;
+		hdlcd->fb.monspecs.dclkmax	= 100000000;
+		fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode, NULL, 0, &hdlcd_default_mode, 32);
+	}
+
+	dev_info(hdlcd->dev, "using %dx%d-%d@%d mode\n", hdlcd->fb.var.xres,
+		hdlcd->fb.var.yres, hdlcd->fb.var.bits_per_pixel,
+		hdlcd->fb.mode ? hdlcd->fb.mode->refresh : 60);
+	hdlcd->fb.var.xres_virtual	= hdlcd->fb.var.xres;
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+	hdlcd->fb.var.yres_virtual	= hdlcd->fb.var.yres;
+#else
+	hdlcd->fb.var.yres_virtual	= hdlcd->fb.var.yres * 2;
+#endif
+
+	/* initialise and set the palette */
+	if (fb_alloc_cmap(&hdlcd->fb.cmap, NR_PALETTE, 0)) {
+		dev_err(hdlcd->dev, "failed to allocate cmap memory\n");
+		err = -ENOMEM;
+		goto setup_err;
+	}
+	fb_set_cmap(&hdlcd->fb.cmap, &hdlcd->fb);
+
+	/* Allow max number of outstanding requests with the largest beat burst */
+	WRITE_HDLCD_REG(HDLCD_REG_BUS_OPTIONS, HDLCD_BUS_MAX_OUTSTAND | HDLCD_BUS_BURST_16);
+	/* Set the framebuffer base to start of allocated memory */
+	WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	/* turn on underrun interrupt for counting */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, HDLCD_INTERRUPT_UNDERRUN);
+#else
+	/* Ensure interrupts are disabled */
+	WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, 0);
+#endif	
+	fb_set_var(&hdlcd->fb, &hdlcd->fb.var);
+
+	if (!register_framebuffer(&hdlcd->fb)) {
+		return 0;
+	}
+
+	dev_err(hdlcd->dev, "HDLCD: cannot register framebuffer\n");
+
+	fb_dealloc_cmap(&hdlcd->fb.cmap);
+setup_err:
+	iounmap(hdlcd->base);
+kmalloc_err:
+	kfree(hdlcd->fb.pseudo_palette);
+remap_err:
+	clk_unprepare(hdlcd->clk);
+clk_prepare_err:
+	clk_put(hdlcd->clk);
+	return err;
+}
+
+static inline unsigned char atohex(u8 data)
+{
+	if (!isxdigit(data))
+		return 0;
+	/* truncate the upper nibble and add 9 to non-digit values */
+	return (data > 0x39) ? ((data & 0xf) + 9) : (data & 0xf);
+}
+
+/* EDID data is passed from devicetree in a literal string that can contain spaces and
+   the hexadecimal dump of the data */
+static int parse_edid_data(struct hdlcd_device *hdlcd, const u8 *edid_data, int data_len)
+{
+	int i, j;
+
+	if (!edid_data)
+		return -EINVAL;
+
+	hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+	if (!hdlcd->edid)
+		return -ENOMEM;
+
+	for (i = 0, j = 0; i < data_len; i++) {
+		if (isspace(edid_data[i]))
+			continue;
+		hdlcd->edid[j++] = atohex(edid_data[i]);
+		if (j >= EDID_LENGTH)
+			break;
+	}
+
+	if (j < EDID_LENGTH) {
+		kfree(hdlcd->edid);
+		hdlcd->edid = NULL;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hdlcd_probe(struct platform_device *pdev)
+{
+	int err = 0, i;
+	struct hdlcd_device *hdlcd;
+	struct resource *mem;
+#ifdef CONFIG_OF
+	struct device_node *of_node;
+#endif
+
+	memset(&cached_var_screeninfo, 0, sizeof(struct fb_var_screeninfo));
+
+	dev_dbg(&pdev->dev, "HDLCD: probing\n");
+
+	hdlcd = kzalloc(sizeof(*hdlcd), GFP_KERNEL);
+	if (!hdlcd)
+		return -ENOMEM;
+
+#ifdef CONFIG_OF
+	of_node = pdev->dev.of_node;
+	if (of_node) {
+		int len;
+		const u8 *edid;
+		const __be32 *prop = of_get_property(of_node, "mode", &len);
+		if (prop)
+			strncpy(fb_mode, (char *)prop, len);
+		prop = of_get_property(of_node, "framebuffer", &len);
+		if (prop) {
+			hdlcd->fb.fix.smem_start = of_read_ulong(prop,
+					of_n_addr_cells(of_node));
+			prop += of_n_addr_cells(of_node);
+			framebuffer_size = of_read_ulong(prop,
+					of_n_size_cells(of_node));
+			if (framebuffer_size > HDLCD_MAX_FRAMEBUFFER_SIZE)
+				framebuffer_size = HDLCD_MAX_FRAMEBUFFER_SIZE;
+			dev_dbg(&pdev->dev, "HDLCD: phys_addr = 0x%lx, size = 0x%lx\n",
+				hdlcd->fb.fix.smem_start, framebuffer_size);
+		}
+		edid = of_get_property(of_node, "edid", &len);
+		if (edid) {
+			err = parse_edid_data(hdlcd, edid, len);
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+		} else {
+			/* ask the firmware to fetch the EDID */
+			dev_dbg(&pdev->dev, "HDLCD: Requesting EDID data\n");
+			hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+			if (!hdlcd->edid)
+				return -ENOMEM;
+			err = get_edid(hdlcd->edid);
+#endif /* CONFIG_SERIAL_AMBA_PCU_UART */
+		}
+		if (err)
+			dev_info(&pdev->dev, "HDLCD: Failed to parse EDID data\n");
+	}
+#endif /* CONFIG_OF */
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem) {
+		dev_err(&pdev->dev, "HDLCD: cannot get platform resources\n");
+		err = -EINVAL;
+		goto resource_err;
+	}
+
+	i = platform_get_irq(pdev, 0);
+	if (i < 0) {
+		dev_err(&pdev->dev, "HDLCD: no irq defined for vsync\n");
+		err = -ENOENT;
+		goto resource_err;
+	} else {
+		err = request_irq(i, hdlcd_irq, 0, dev_name(&pdev->dev), hdlcd);
+		if (err) {
+			dev_err(&pdev->dev, "HDLCD: unable to request irq\n");
+			goto resource_err;
+		}
+		hdlcd->irq = i;
+	}
+
+	if (!request_mem_region(mem->start, resource_size(mem),	dev_name(&pdev->dev))) {
+		err = -ENXIO;
+		goto request_err;
+	}
+
+	if (!hdlcd->fb.fix.smem_start) {
+		dev_err(&pdev->dev, "platform did not allocate frame buffer memory\n");
+		err = -ENOMEM;
+		goto memalloc_err;
+	}
+	hdlcd->fb.screen_base = ioremap_wc(hdlcd->fb.fix.smem_start, framebuffer_size);
+	if (!hdlcd->fb.screen_base) {
+		dev_err(&pdev->dev, "unable to ioremap framebuffer\n");
+		err = -ENOMEM;
+		goto probe_err;
+	}
+
+	hdlcd->fb.screen_size = framebuffer_size;
+	hdlcd->fb.fix.smem_len = framebuffer_size;
+	hdlcd->fb.fix.mmio_start = mem->start;
+	hdlcd->fb.fix.mmio_len = resource_size(mem);
+
+	/* Clear the framebuffer */
+	memset(hdlcd->fb.screen_base, 0, framebuffer_size);
+
+	hdlcd->dev = &pdev->dev;
+
+	dev_dbg(&pdev->dev, "HDLCD: framebuffer virt base %p, phys base 0x%lX\n",
+		hdlcd->fb.screen_base, (unsigned long)hdlcd->fb.fix.smem_start);
+
+	err = hdlcd_setup(hdlcd);
+
+	if (err)
+		goto probe_err;
+
+	platform_set_drvdata(pdev, hdlcd);
+	return 0;
+
+probe_err:
+	iounmap(hdlcd->fb.screen_base);
+	memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+
+memalloc_err:
+	release_mem_region(mem->start, resource_size(mem));
+
+request_err:
+	free_irq(hdlcd->irq, hdlcd);
+
+resource_err:
+	kfree(hdlcd);
+
+	return err;
+}
+
+static int hdlcd_remove(struct platform_device *pdev)
+{
+	struct hdlcd_device *hdlcd = platform_get_drvdata(pdev);
+
+	clk_disable(hdlcd->clk);
+	clk_unprepare(hdlcd->clk);
+	clk_put(hdlcd->clk);
+
+	/* unmap memory */
+	iounmap(hdlcd->fb.screen_base);
+	iounmap(hdlcd->base);
+
+	/* deallocate fb memory */
+	fb_dealloc_cmap(&hdlcd->fb.cmap);
+	kfree(hdlcd->fb.pseudo_palette);
+	memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+	release_mem_region(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+
+	free_irq(hdlcd->irq, NULL);
+	kfree(hdlcd);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int hdlcd_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	/* not implemented yet */
+	return 0;
+}
+
+static int hdlcd_resume(struct platform_device *pdev)
+{
+	/* not implemented yet */
+	return 0;
+}
+#else
+#define hdlcd_suspend	NULL
+#define hdlcd_resume	NULL
+#endif
+
+static struct platform_driver hdlcd_driver = {
+	.probe		= hdlcd_probe,
+	.remove		= hdlcd_remove,
+	.suspend	= hdlcd_suspend,
+	.resume		= hdlcd_resume,
+	.driver	= {
+		.name		= "hdlcd",
+		.owner		= THIS_MODULE,
+		.of_match_table	= hdlcd_of_matches,
+	},
+};
+
+static int __init hdlcd_init(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	int err = platform_driver_register(&hdlcd_driver);
+	if (!err)
+		hdlcd_underrun_init();
+	return err;
+#else
+	return platform_driver_register(&hdlcd_driver);
+#endif
+}
+
+void __exit hdlcd_exit(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+	hdlcd_underrun_close();
+#endif
+	platform_driver_unregister(&hdlcd_driver);
+}
+
+module_init(hdlcd_init);
+module_exit(hdlcd_exit);
+
+MODULE_AUTHOR("Liviu Dudau");
+MODULE_DESCRIPTION("ARM HDLCD core driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c
index cd961622f9c1..b74e5f5ddac8 100644
--- a/drivers/video/atmel_lcdfb.c
+++ b/drivers/video/atmel_lcdfb.c
@@ -1298,6 +1298,12 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 		goto unregister_irqs;
 	}
 
+	ret = atmel_lcdfb_set_par(info);
+	if (ret < 0) {
+		dev_err(dev, "set par failed: %d\n", ret);
+		goto unregister_irqs;
+	}
+
 	dev_set_drvdata(dev, info);
 
 	/*
diff --git a/drivers/video/aty/mach64_accel.c b/drivers/video/aty/mach64_accel.c
index e45833ce975b..182bd680141f 100644
--- a/drivers/video/aty/mach64_accel.c
+++ b/drivers/video/aty/mach64_accel.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/delay.h>
+#include <asm/unaligned.h>
 #include <linux/fb.h>
 #include <video/mach64.h>
 #include "atyfb.h"
@@ -419,7 +420,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image)
 		u32 *pbitmap, dwords = (src_bytes + 3) / 4;
 		for (pbitmap = (u32*)(image->data); dwords; dwords--, pbitmap++) {
 			wait_for_fifo(1, par);
-			aty_st_le32(HOST_DATA0, le32_to_cpup(pbitmap), par);
+			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}
 
diff --git a/drivers/video/aty/mach64_cursor.c b/drivers/video/aty/mach64_cursor.c
index 95ec042ddbf8..0fe02e22d9a4 100644
--- a/drivers/video/aty/mach64_cursor.c
+++ b/drivers/video/aty/mach64_cursor.c
@@ -5,6 +5,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include "../fb_draw.h"
 
 #include <asm/io.h>
 
@@ -157,24 +158,33 @@ static int atyfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 
 	    for (i = 0; i < height; i++) {
 		for (j = 0; j < width; j++) {
+			u16 l = 0xaaaa;
 			b = *src++;
 			m = *msk++;
 			switch (cursor->rop) {
 			case ROP_XOR:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b ^ m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b ^ m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b ^ m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b ^ m) & 0x0f] << 8);
 			    break;
 			case ROP_COPY:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b & m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b & m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b & m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b & m) & 0x0f] << 8);
 			    break;
 			}
+			/*
+			 * If cursor size is not a multiple of 8 characters
+			 * we must pad it with transparent pattern (0xaaaa).
+			 */
+			if ((j + 1) * 8 > cursor->image.width) {
+				l = comp(l, 0xaaaa,
+				    (1 << ((cursor->image.width & 7) * 2)) - 1);
+			}
+			fb_writeb(l & 0xff, dst++);
+			fb_writeb(l >> 8, dst++);
 		}
 		dst += offset;
 	    }
diff --git a/drivers/video/cfbcopyarea.c b/drivers/video/cfbcopyarea.c
index bb5a96b1645d..bcb57235fcc7 100644
--- a/drivers/video/cfbcopyarea.c
+++ b/drivers/video/cfbcopyarea.c
@@ -43,13 +43,22 @@
      */
 
 static void
-bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int const shift = dst_idx-src_idx;
-	int left, right;
+
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
 
 	first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
 	last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
@@ -98,9 +107,8 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 		unsigned long d0, d1;
 		int m;
 
-		right = shift & (bits - 1);
-		left = -shift & (bits - 1);
-		bswapmask &= shift;
+		int const left = shift & (bits - 1);
+		int const right = -shift & (bits - 1);
 
 		if (dst_idx+n <= bits) {
 			// Single destination word
@@ -110,15 +118,15 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			if (shift > 0) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else if (src_idx+n <= bits) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src + 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0<<left | d1>>right;
+				d0 = d0 >> right | d1 << left;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -135,60 +143,59 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			if (shift > 0) {
 				// Single source word
 				d1 = d0;
-				d0 >>= right;
-				dst++;
+				d0 <<= left;
 				n -= bits - dst_idx;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
 
-				d0 = d0<<left | d1>>right;
-				dst++;
+				d0 = d0 >> right | d1 << left;
 				n -= bits - dst_idx;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
 			d0 = d1;
+			dst++;
 
 			// Main chunk
 			m = n % bits;
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 << left | d1 >> right;
+				d0 = d0 >> right | d1 << left;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst++);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= right) {
+			if (m) {
+				if (m <= bits - right) {
 					// Single source word
-					d0 <<= left;
+					d0 >>= right;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0<<left | d1>>right;
+					d0 = d0 >> right | d1 << left;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -202,43 +209,46 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
      */
 
 static void
-bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int shift;
 
-	dst += (n-1)/bits;
-	src += (n-1)/bits;
-	if ((n-1) % bits) {
-		dst_idx += (n-1) % bits;
-		dst += dst_idx >> (ffs(bits) - 1);
-		dst_idx &= bits - 1;
-		src_idx += (n-1) % bits;
-		src += src_idx >> (ffs(bits) - 1);
-		src_idx &= bits - 1;
-	}
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
+
+	dst += (dst_idx + n - 1) / bits;
+	src += (src_idx + n - 1) / bits;
+	dst_idx = (dst_idx + n - 1) % bits;
+	src_idx = (src_idx + n - 1) % bits;
 
 	shift = dst_idx-src_idx;
 
-	first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits),
-					    bswapmask);
+	first = ~fb_shifted_pixels_mask_long(p, (dst_idx + 1) % bits, bswapmask);
+	last = fb_shifted_pixels_mask_long(p, (bits + dst_idx + 1 - n) % bits, bswapmask);
 
 	if (!shift) {
 		// Same alignment for source and dest
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single word
-			if (last)
-				first &= last;
-			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
+			if (first)
+				last &= first;
+			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 
 			// Leading bits
-			if (first != ~0UL) {
+			if (first) {
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
 				dst--;
 				src--;
@@ -262,7 +272,7 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 				FB_WRITEL(FB_READL(src--), dst--);
 
 			// Trailing bits
-			if (last)
+			if (last != -1UL)
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		}
 	} else {
@@ -270,29 +280,28 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 		unsigned long d0, d1;
 		int m;
 
-		int const left = -shift & (bits-1);
-		int const right = shift & (bits-1);
-		bswapmask &= shift;
+		int const left = shift & (bits-1);
+		int const right = -shift & (bits-1);
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single destination word
-			if (last)
-				first &= last;
+			if (first)
+				last &= first;
 			d0 = FB_READL(src);
 			if (shift < 0) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else if (1+(unsigned long)src_idx >= n) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src - 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
-			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+			FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 			/** We must always remember the last value read, because in case
@@ -307,12 +316,12 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			if (shift < 0) {
 				// Single source word
 				d1 = d0;
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -325,39 +334,39 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 >> right | d1 << left;
+				d0 = d0 << left | d1 >> right;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst--);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= left) {
+			if (m) {
+				if (m <= bits - left) {
 					// Single source word
-					d0 >>= right;
+					d0 <<= left;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0>>right | d1<<left;
+					d0 = d0 << left | d1 >> right;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -371,9 +380,9 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 	u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
 	u32 height = area->height, width = area->width;
 	unsigned long const bits_per_line = p->fix.line_length*8u;
-	unsigned long __iomem *dst = NULL, *src = NULL;
+	unsigned long __iomem *base = NULL;
 	int bits = BITS_PER_LONG, bytes = bits >> 3;
-	int dst_idx = 0, src_idx = 0, rev_copy = 0;
+	unsigned dst_idx = 0, src_idx = 0, rev_copy = 0;
 	u32 bswapmask = fb_compute_bswapmask(p);
 
 	if (p->state != FBINFO_STATE_RUNNING)
@@ -389,7 +398,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 
 	// split the base of the framebuffer into a long-aligned address and the
 	// index of the first bit
-	dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
+	base = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
 	dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1));
 	// add offset of source and target area
 	dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel;
@@ -402,20 +411,14 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 		while (height--) {
 			dst_idx -= bits_per_line;
 			src_idx -= bits_per_line;
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy_rev(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 		}
 	} else {
 		while (height--) {
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 			dst_idx += bits_per_line;
 			src_idx += bits_per_line;
diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c
index 61b182bf32a2..dbfe4eecf12e 100644
--- a/drivers/video/console/bitblit.c
+++ b/drivers/video/console/bitblit.c
@@ -205,7 +205,6 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info,
 static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 			      int bottom_only)
 {
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 	unsigned int cw = vc->vc_font.width;
 	unsigned int ch = vc->vc_font.height;
 	unsigned int rw = info->var.xres - (vc->vc_cols*cw);
@@ -214,7 +213,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bs = info->var.yres - bh;
 	struct fb_fillrect region;
 
-	region.color = attr_bgcol_ec(bgshift, vc, info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c
index 41b32ae23dac..5a3cbf6dff4d 100644
--- a/drivers/video/console/fbcon_ccw.c
+++ b/drivers/video/console/fbcon_ccw.c
@@ -197,9 +197,8 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bh = info->var.xres - (vc->vc_rows*ch);
 	unsigned int bs = vc->vc_rows*ch;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_cw.c b/drivers/video/console/fbcon_cw.c
index a93670ef7f89..e7ee44db4e98 100644
--- a/drivers/video/console/fbcon_cw.c
+++ b/drivers/video/console/fbcon_cw.c
@@ -180,9 +180,8 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bh = info->var.xres - (vc->vc_rows*ch);
 	unsigned int rs = info->var.yres - rw;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_ud.c b/drivers/video/console/fbcon_ud.c
index ff0872c0498b..19e3714abfe8 100644
--- a/drivers/video/console/fbcon_ud.c
+++ b/drivers/video/console/fbcon_ud.c
@@ -227,9 +227,8 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int rw = info->var.xres - (vc->vc_cols*cw);
 	unsigned int bh = info->var.yres - (vc->vc_rows*ch);
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/fb-puv3.c b/drivers/video/fb-puv3.c
index 6db9ebd042a3..88fa2e70a0bb 100644
--- a/drivers/video/fb-puv3.c
+++ b/drivers/video/fb-puv3.c
@@ -18,8 +18,10 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/console.h>
+#include <linux/mm.h>
 
 #include <asm/sizes.h>
+#include <asm/pgtable.h>
 #include <mach/hardware.h>
 
 /* Platform_data reserved for unifb registers. */
diff --git a/drivers/video/matrox/matroxfb_accel.c b/drivers/video/matrox/matroxfb_accel.c
index 8335a6fe303e..0d5cb85d071a 100644
--- a/drivers/video/matrox/matroxfb_accel.c
+++ b/drivers/video/matrox/matroxfb_accel.c
@@ -192,10 +192,18 @@ void matrox_cfbX_init(struct matrox_fb_info *minfo)
 	minfo->accel.m_dwg_rect = M_DWG_TRAP | M_DWG_SOLID | M_DWG_ARZERO | M_DWG_SGNZERO | M_DWG_SHIFTZERO;
 	if (isMilleniumII(minfo)) minfo->accel.m_dwg_rect |= M_DWG_TRANSC;
 	minfo->accel.m_opmode = mopmode;
+	minfo->accel.m_access = maccess;
+	minfo->accel.m_pitch = mpitch;
 }
 
 EXPORT_SYMBOL(matrox_cfbX_init);
 
+static void matrox_accel_restore_maccess(struct matrox_fb_info *minfo)
+{
+	mga_outl(M_MACCESS, minfo->accel.m_access);
+	mga_outl(M_PITCH, minfo->accel.m_pitch);
+}
+
 static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 			       int sx, int dy, int dx, int height, int width)
 {
@@ -207,7 +215,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			 M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);
@@ -215,7 +224,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);
@@ -224,7 +234,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(4);
+	mga_fifo(6);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -246,7 +257,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);
@@ -254,7 +266,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);
@@ -263,7 +276,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -298,7 +312,8 @@ static void matroxfb_accel_clear(struct matrox_fb_info *minfo, u_int32_t color,
 
 	CRITBEGIN
 
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE);
 	mga_outl(M_FCOL, color);
 	mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -341,7 +356,8 @@ static void matroxfb_cfb4_clear(struct matrox_fb_info *minfo, u_int32_t bgx,
 	width >>= 1;
 	sx >>= 1;
 	if (width) {
-		mga_fifo(5);
+		mga_fifo(7);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE2);
 		mga_outl(M_FCOL, bgx);
 		mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -415,7 +431,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 
 	CRITBEGIN
 
-	mga_fifo(3);
+	mga_fifo(5);
+	matrox_accel_restore_maccess(minfo);
 	if (easy)
 		mga_outl(M_DWGCTL, M_DWG_ILOAD | M_DWG_SGNZERO | M_DWG_SHIFTZERO | M_DWG_BMONOWF | M_DWG_LINEAR | M_DWG_REPLACE);
 	else
@@ -425,7 +442,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 	fxbndry = ((xx + width - 1) << 16) | xx;
 	mmio = minfo->mmio.vbase;
 
-	mga_fifo(6);
+	mga_fifo(8);
+	matrox_accel_restore_maccess(minfo);
 	mga_writel(mmio, M_FXBNDRY, fxbndry);
 	mga_writel(mmio, M_AR0, ar0);
 	mga_writel(mmio, M_AR3, 0);
diff --git a/drivers/video/matrox/matroxfb_base.h b/drivers/video/matrox/matroxfb_base.h
index 11ed57bb704e..89a8a89a5eb2 100644
--- a/drivers/video/matrox/matroxfb_base.h
+++ b/drivers/video/matrox/matroxfb_base.h
@@ -307,6 +307,8 @@ struct matrox_accel_data {
 #endif
 	u_int32_t	m_dwg_rect;
 	u_int32_t	m_opmode;
+	u_int32_t	m_access;
+	u_int32_t	m_pitch;
 };
 
 struct v4l2_queryctrl;
@@ -696,7 +698,7 @@ void matroxfb_unregister_driver(struct matroxfb_driver* drv);
 
 #define mga_fifo(n)	do {} while ((mga_inl(M_FIFOSTATUS) & 0xFF) < (n))
 
-#define WaitTillIdle()	do {} while (mga_inl(M_STATUS) & 0x10000)
+#define WaitTillIdle()	do { mga_inl(M_STATUS); do {} while (mga_inl(M_STATUS) & 0x10000); } while (0)
 
 /* code speedup */
 #ifdef CONFIG_FB_MATROX_MILLENIUM
diff --git a/drivers/video/tgafb.c b/drivers/video/tgafb.c
index 07c7df9ee77b..3d5bce517d8e 100644
--- a/drivers/video/tgafb.c
+++ b/drivers/video/tgafb.c
@@ -182,6 +182,8 @@ tgafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 	if (var->xres_virtual != var->xres || var->yres_virtual != var->yres)
 		return -EINVAL;
+	if (var->xres * var->yres * (var->bits_per_pixel >> 3) > info->fix.smem_len)
+		return -EINVAL;
 	if (var->nonstd)
 		return -EINVAL;
 	if (1000000000 / var->pixclock > TGA_PLL_MAX_FREQ)
@@ -262,6 +264,7 @@ tgafb_set_par(struct fb_info *info)
 	par->yres = info->var.yres;
 	par->pll_freq = pll_freq = 1000000000 / info->var.pixclock;
 	par->bits_per_pixel = info->var.bits_per_pixel;
+	info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
 
 	tga_type = par->tga_type;
 
@@ -1136,222 +1139,57 @@ copyarea_line_32bpp(struct fb_info *info, u32 dy, u32 sy,
 	__raw_writel(TGA_MODE_SBM_24BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
 }
 
-/* The general case of forward copy in 8bpp mode.  */
+/* The (almost) general case of backward copy in 8bpp mode.  */
 static inline void
-copyarea_foreward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length)
+copyarea_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
+	      u32 height, u32 width, u32 line_length,
+	      const struct fb_copyarea *area)
 {
 	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, copied, left;
-	unsigned long dpos, spos, dalign, salign, yincr;
-	u32 smask_first, dmask_first, dmask_last;
-	int pixel_shift, need_prime, need_second;
-	unsigned long n64, n32, xincr_first;
+	unsigned i, yincr;
+	int depos, sepos, backward, last_step, step;
+	u32 mask_last;
+	unsigned n32;
 	void __iomem *tga_regs;
 	void __iomem *tga_fb;
 
-	yincr = line_length;
-	if (dy > sy) {
-		dy += height - 1;
-		sy += height - 1;
-		yincr = -yincr;
-	}
-
-	/* Compute the offsets and alignments in the frame buffer.
-	   More than anything else, these control how we do copies.  */
-	dpos = dy * line_length + dx;
-	spos = sy * line_length + sx;
-	dalign = dpos & 7;
-	salign = spos & 7;
-	dpos &= -8;
-	spos &= -8;
-
-	/* Compute the value for the PIXELSHIFT register.  This controls
-	   both non-co-aligned source and destination and copy direction.  */
-	if (dalign >= salign)
-		pixel_shift = dalign - salign;
-	else
-		pixel_shift = 8 - (salign - dalign);
-
-	/* Figure out if we need an additional priming step for the
-	   residue register.  */
-	need_prime = (salign > dalign);
-	if (need_prime)
-		dpos -= 8;
-
-	/* Begin by copying the leading unaligned destination.  Copy enough
-	   to make the next destination address 32-byte aligned.  */
-	copied = 32 - (dalign + (dpos & 31));
-	if (copied == 32)
-		copied = 0;
-	xincr_first = (copied + 7) & -8;
-	smask_first = dmask_first = (1ul << copied) - 1;
-	smask_first <<= salign;
-	dmask_first <<= dalign + need_prime*8;
-	if (need_prime && copied > 24)
-		copied -= 8;
-	left = width - copied;
-
-	/* Care for small copies.  */
-	if (copied > width) {
-		u32 t;
-		t = (1ul << width) - 1;
-		t <<= dalign + need_prime*8;
-		dmask_first &= t;
-		left = 0;
-	}
-
-	/* Attempt to use 64-byte copies.  This is only possible if the
-	   source and destination are co-aligned at 64 bytes.  */
-	n64 = need_second = 0;
-	if ((dpos & 63) == (spos & 63)
-	    && (height == 1 || line_length % 64 == 0)) {
-		/* We may need a 32-byte copy to ensure 64 byte alignment.  */
-		need_second = (dpos + xincr_first) & 63;
-		if ((need_second & 32) != need_second)
-			printk(KERN_ERR "tgafb: need_second wrong\n");
-		if (left >= need_second + 64) {
-			left -= need_second;
-			n64 = left / 64;
-			left %= 64;
-		} else
-			need_second = 0;
-	}
-
-	/* Copy trailing full 32-byte sections.  This will be the main
-	   loop if the 64 byte loop can't be used.  */
-	n32 = left / 32;
-	left %= 32;
-
-	/* Copy the trailing unaligned destination.  */
-	dmask_last = (1ul << left) - 1;
-
-	tga_regs = par->tga_regs_base;
-	tga_fb = par->tga_fb_base;
-
-	/* Set up the MODE and PIXELSHIFT registers.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_COPY, tga_regs+TGA_MODE_REG);
-	__raw_writel(pixel_shift, tga_regs+TGA_PIXELSHIFT_REG);
-	wmb();
-
-	for (i = 0; i < height; ++i) {
-		unsigned long j;
-		void __iomem *sfb;
-		void __iomem *dfb;
-
-		sfb = tga_fb + spos;
-		dfb = tga_fb + dpos;
-		if (dmask_first) {
-			__raw_writel(smask_first, sfb);
-			wmb();
-			__raw_writel(dmask_first, dfb);
-			wmb();
-			sfb += xincr_first;
-			dfb += xincr_first;
-		}
-
-		if (need_second) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (n64 && (((unsigned long)sfb | (unsigned long)dfb) & 63))
-			printk(KERN_ERR
-			       "tgafb: misaligned copy64 (s:%p, d:%p)\n",
-			       sfb, dfb);
-
-		for (j = 0; j < n64; ++j) {
-			__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
-			wmb();
-			__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
-			wmb();
-			sfb += 64;
-			dfb += 64;
-		}
-
-		for (j = 0; j < n32; ++j) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (dmask_last) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(dmask_last, dfb);
-			wmb();
-		}
-
-		spos += yincr;
-		dpos += yincr;
+	/* Do acceleration only if we are aligned on 8 pixels */
+	if ((dx | sx | width) & 7) {
+		cfb_copyarea(info, area);
+		return;
 	}
 
-	/* Reset the MODE register to normal.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
-}
-
-/* The (almost) general case of backward copy in 8bpp mode.  */
-static inline void
-copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length,
-		       const struct fb_copyarea *area)
-{
-	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, left, yincr;
-	unsigned long depos, sepos, dealign, sealign;
-	u32 mask_first, mask_last;
-	unsigned long n32;
-	void __iomem *tga_regs;
-	void __iomem *tga_fb;
-
 	yincr = line_length;
 	if (dy > sy) {
 		dy += height - 1;
 		sy += height - 1;
 		yincr = -yincr;
 	}
+	backward = dy == sy && dx > sx && dx < sx + width;
 
 	/* Compute the offsets and alignments in the frame buffer.
 	   More than anything else, these control how we do copies.  */
-	depos = dy * line_length + dx + width;
-	sepos = sy * line_length + sx + width;
-	dealign = depos & 7;
-	sealign = sepos & 7;
-
-	/* ??? The documentation appears to be incorrect (or very
-	   misleading) wrt how pixel shifting works in backward copy
-	   mode, i.e. when PIXELSHIFT is negative.  I give up for now.
-	   Do handle the common case of co-aligned backward copies,
-	   but frob everything else back on generic code.  */
-	if (dealign != sealign) {
-		cfb_copyarea(info, area);
-		return;
-	}
-
-	/* We begin the copy with the trailing pixels of the
-	   unaligned destination.  */
-	mask_first = (1ul << dealign) - 1;
-	left = width - dealign;
-
-	/* Care for small copies.  */
-	if (dealign > width) {
-		mask_first ^= (1ul << (dealign - width)) - 1;
-		left = 0;
-	}
+	depos = dy * line_length + dx;
+	sepos = sy * line_length + sx;
+	if (backward)
+		depos += width, sepos += width;
 
 	/* Next copy full words at a time.  */
-	n32 = left / 32;
-	left %= 32;
+	n32 = width / 32;
+	last_step = width % 32;
 
 	/* Finally copy the unaligned head of the span.  */
-	mask_last = -1 << (32 - left);
+	mask_last = (1ul << last_step) - 1;
+
+	if (!backward) {
+		step = 32;
+		last_step = 32;
+	} else {
+		step = -32;
+		last_step = -last_step;
+		sepos -= 32;
+		depos -= 32;
+	}
 
 	tga_regs = par->tga_regs_base;
 	tga_fb = par->tga_fb_base;
@@ -1368,25 +1206,33 @@ copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
 
 		sfb = tga_fb + sepos;
 		dfb = tga_fb + depos;
-		if (mask_first) {
-			__raw_writel(mask_first, sfb);
-			wmb();
-			__raw_writel(mask_first, dfb);
-			wmb();
-		}
 
-		for (j = 0; j < n32; ++j) {
-			sfb -= 32;
-			dfb -= 32;
+		for (j = 0; j < n32; j++) {
+			if (j < 2 && j + 1 < n32 && !backward &&
+			    !(((unsigned long)sfb | (unsigned long)dfb) & 63)) {
+				do {
+					__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
+					wmb();
+					__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
+					wmb();
+					sfb += 64;
+					dfb += 64;
+					j += 2;
+				} while (j + 1 < n32);
+				j--;
+				continue;
+			}
 			__raw_writel(0xffffffff, sfb);
 			wmb();
 			__raw_writel(0xffffffff, dfb);
 			wmb();
+			sfb += step;
+			dfb += step;
 		}
 
 		if (mask_last) {
-			sfb -= 32;
-			dfb -= 32;
+			sfb += last_step - step;
+			dfb += last_step - step;
 			__raw_writel(mask_last, sfb);
 			wmb();
 			__raw_writel(mask_last, dfb);
@@ -1447,14 +1293,9 @@ tgafb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
 	else if (bpp == 32)
 		cfb_copyarea(info, area);
 
-	/* Detect overlapping source and destination that requires
-	   a backward copy.  */
-	else if (dy == sy && dx > sx && dx < sx + width)
-		copyarea_backward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length, area);
 	else
-		copyarea_foreward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length);
+		copyarea_8bpp(info, dx, dy, sx, sy, height,
+			      width, line_length, area);
 }
 
 
@@ -1470,6 +1311,7 @@ tgafb_init_fix(struct fb_info *info)
 	int tga_bus_tc = TGA_BUS_TC(par->dev);
 	u8 tga_type = par->tga_type;
 	const char *tga_type_name = NULL;
+	unsigned memory_size;
 
 	switch (tga_type) {
 	case TGA_TYPE_8PLANE:
@@ -1477,22 +1319,27 @@ tgafb_init_fix(struct fb_info *info)
 			tga_type_name = "Digital ZLXp-E1";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E1";
+		memory_size = 2097152;
 		break;
 	case TGA_TYPE_24PLANE:
 		if (tga_bus_pci)
 			tga_type_name = "Digital ZLXp-E2";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E2";
+		memory_size = 8388608;
 		break;
 	case TGA_TYPE_24PLUSZ:
 		if (tga_bus_pci)
 			tga_type_name = "Digital ZLXp-E3";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E3";
+		memory_size = 16777216;
 		break;
 	}
-	if (!tga_type_name)
+	if (!tga_type_name) {
 		tga_type_name = "Unknown";
+		memory_size = 16777216;
+	}
 
 	strlcpy(info->fix.id, tga_type_name, sizeof(info->fix.id));
 
@@ -1502,9 +1349,8 @@ tgafb_init_fix(struct fb_info *info)
 			    ? FB_VISUAL_PSEUDOCOLOR
 			    : FB_VISUAL_DIRECTCOLOR);
 
-	info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
 	info->fix.smem_start = (size_t) par->tga_fb_base;
-	info->fix.smem_len = info->fix.line_length * par->yres;
+	info->fix.smem_len = memory_size;
 	info->fix.mmio_start = (size_t) par->tga_regs_base;
 	info->fix.mmio_len = 512;
 
@@ -1628,6 +1474,9 @@ static int tgafb_register(struct device *dev)
 		modedb_tga = &modedb_tc;
 		modedbsize_tga = 1;
 	}
+
+	tgafb_init_fix(info);
+
 	ret = fb_find_mode(&info->var, info,
 			   mode_option ? mode_option : mode_option_tga,
 			   modedb_tga, modedbsize_tga, NULL,
@@ -1645,7 +1494,6 @@ static int tgafb_register(struct device *dev)
 	}
 
 	tgafb_set_par(info);
-	tgafb_init_fix(info);
 
 	if (register_framebuffer(info) < 0) {
 		printk(KERN_ERR "tgafb: Could not register framebuffer\n");
diff --git a/drivers/video/vexpress-dvi.c b/drivers/video/vexpress-dvi.c
new file mode 100644
index 000000000000..f08753450ee4
--- /dev/null
+++ b/drivers/video/vexpress-dvi.c
@@ -0,0 +1,220 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#define pr_fmt(fmt) "vexpress-dvi: " fmt
+
+#include <linux/fb.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/vexpress.h>
+
+
+static struct vexpress_config_func *vexpress_dvimode_func;
+
+static struct {
+	u32 xres, yres, mode;
+} vexpress_dvi_dvimodes[] = {
+	{ 640, 480, 0 }, /* VGA */
+	{ 800, 600, 1 }, /* SVGA */
+	{ 1024, 768, 2 }, /* XGA */
+	{ 1280, 1024, 3 }, /* SXGA */
+	{ 1600, 1200, 4 }, /* UXGA */
+	{ 1920, 1080, 5 }, /* HD1080 */
+};
+
+static void vexpress_dvi_mode_set(struct fb_info *info, u32 xres, u32 yres)
+{
+	int err = -ENOENT;
+	int i;
+
+	if (!vexpress_dvimode_func)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(vexpress_dvi_dvimodes); i++) {
+		if (vexpress_dvi_dvimodes[i].xres == xres &&
+				vexpress_dvi_dvimodes[i].yres == yres) {
+			pr_debug("mode: %ux%u = %d\n", xres, yres,
+					vexpress_dvi_dvimodes[i].mode);
+			err = vexpress_config_write(vexpress_dvimode_func, 0,
+					vexpress_dvi_dvimodes[i].mode);
+			break;
+		}
+	}
+
+	if (err)
+		pr_warn("Failed to set %ux%u mode! (%d)\n", xres, yres, err);
+}
+
+
+static struct vexpress_config_func *vexpress_muxfpga_func;
+static int vexpress_dvi_fb = -1;
+
+static int vexpress_dvi_mux_set(struct fb_info *info)
+{
+	int err;
+	u32 site = vexpress_get_site_by_dev(info->device);
+
+	if (!vexpress_muxfpga_func)
+		return -ENXIO;
+
+	err = vexpress_config_write(vexpress_muxfpga_func, 0, site);
+	if (!err) {
+		pr_debug("Selected MUXFPGA input %d (fb%d)\n", site,
+				info->node);
+		vexpress_dvi_fb = info->node;
+		vexpress_dvi_mode_set(info, info->var.xres,
+				info->var.yres);
+	} else {
+		pr_warn("Failed to select MUXFPGA input %d (fb%d)! (%d)\n",
+				site, info->node, err);
+	}
+
+	return err;
+}
+
+static int vexpress_dvi_fb_select(int fb)
+{
+	int err;
+	struct fb_info *info;
+
+	/* fb0 is the default */
+	if (fb < 0)
+		fb = 0;
+
+	info = registered_fb[fb];
+	if (!info || !lock_fb_info(info))
+		return -ENODEV;
+
+	err = vexpress_dvi_mux_set(info);
+
+	unlock_fb_info(info);
+
+	return err;
+}
+
+static ssize_t vexpress_dvi_fb_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", vexpress_dvi_fb);
+}
+
+static ssize_t vexpress_dvi_fb_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	long value;
+	int err = kstrtol(buf, 0, &value);
+
+	if (!err)
+		err = vexpress_dvi_fb_select(value);
+
+	return err ? err : count;
+}
+
+DEVICE_ATTR(fb, S_IRUGO | S_IWUSR, vexpress_dvi_fb_show,
+		vexpress_dvi_fb_store);
+
+
+static int vexpress_dvi_fb_event_notify(struct notifier_block *self,
+			      unsigned long action, void *data)
+{
+	struct fb_event *event = data;
+	struct fb_info *info = event->info;
+	struct fb_videomode *mode = event->data;
+
+	switch (action) {
+	case FB_EVENT_FB_REGISTERED:
+		if (vexpress_dvi_fb < 0)
+			vexpress_dvi_mux_set(info);
+		break;
+	case FB_EVENT_MODE_CHANGE:
+	case FB_EVENT_MODE_CHANGE_ALL:
+		if (info->node == vexpress_dvi_fb)
+			vexpress_dvi_mode_set(info, mode->xres, mode->yres);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block vexpress_dvi_fb_notifier = {
+	.notifier_call = vexpress_dvi_fb_event_notify,
+};
+static bool vexpress_dvi_fb_notifier_registered;
+
+
+enum vexpress_dvi_func { FUNC_MUXFPGA, FUNC_DVIMODE };
+
+static struct of_device_id vexpress_dvi_of_match[] = {
+	{
+		.compatible = "arm,vexpress-muxfpga",
+		.data = (void *)FUNC_MUXFPGA,
+	}, {
+		.compatible = "arm,vexpress-dvimode",
+		.data = (void *)FUNC_DVIMODE,
+	},
+	{}
+};
+
+static int vexpress_dvi_probe(struct platform_device *pdev)
+{
+	enum vexpress_dvi_func func;
+	const struct of_device_id *match =
+			of_match_device(vexpress_dvi_of_match, &pdev->dev);
+
+	if (match)
+		func = (enum vexpress_dvi_func)match->data;
+	else
+		func = pdev->id_entry->driver_data;
+
+	switch (func) {
+	case FUNC_MUXFPGA:
+		vexpress_muxfpga_func =
+				vexpress_config_func_get_by_dev(&pdev->dev);
+		device_create_file(&pdev->dev, &dev_attr_fb);
+		break;
+	case FUNC_DVIMODE:
+		vexpress_dvimode_func =
+				vexpress_config_func_get_by_dev(&pdev->dev);
+		break;
+	}
+
+	if (!vexpress_dvi_fb_notifier_registered) {
+		fb_register_client(&vexpress_dvi_fb_notifier);
+		vexpress_dvi_fb_notifier_registered = true;
+	}
+
+	vexpress_dvi_fb_select(vexpress_dvi_fb);
+
+	return 0;
+}
+
+static const struct platform_device_id vexpress_dvi_id_table[] = {
+	{ .name = "vexpress-muxfpga", .driver_data = FUNC_MUXFPGA, },
+	{ .name = "vexpress-dvimode", .driver_data = FUNC_DVIMODE, },
+	{}
+};
+
+static struct platform_driver vexpress_dvi_driver = {
+	.probe = vexpress_dvi_probe,
+	.driver = {
+		.name = "vexpress-dvi",
+		.of_match_table = vexpress_dvi_of_match,
+	},
+	.id_table = vexpress_dvi_id_table,
+};
+
+static int __init vexpress_dvi_init(void)
+{
+	return platform_driver_register(&vexpress_dvi_driver);
+}
+device_initcall(vexpress_dvi_init);
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 34bdabaecbd6..36e7859a31aa 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -310,6 +310,12 @@ static int balloon(void *_vballoon)
 		else if (diff < 0)
 			leak_balloon(vb, -diff);
 		update_balloon_size(vb);
+
+		/*
+		 * For large balloon changes, we could spend a lot of time
+		 * and always have work to do.  Be nice if preempt disabled.
+		 */
+		cond_resched();
 	}
 	return 0;
 }
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index a416f9b2a7f6..827b5f8e6297 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -791,6 +791,7 @@ static int virtio_pci_restore(struct device *dev)
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
 	struct virtio_driver *drv;
+	unsigned status = 0;
 	int ret;
 
 	drv = container_of(vp_dev->vdev.dev.driver,
@@ -801,14 +802,40 @@ static int virtio_pci_restore(struct device *dev)
 		return ret;
 
 	pci_set_master(pci_dev);
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up. */
+	vp_reset(&vp_dev->vdev);
+
+	/* Acknowledge that we've seen the device. */
+	status |= VIRTIO_CONFIG_S_ACKNOWLEDGE;
+	vp_set_status(&vp_dev->vdev, status);
+
+	/* Maybe driver failed before freeze.
+	 * Restore the failed status, for debugging. */
+	status |= vp_dev->saved_status & VIRTIO_CONFIG_S_FAILED;
+	vp_set_status(&vp_dev->vdev, status);
+
+	if (!drv)
+		return 0;
+
+	/* We have a driver! */
+	status |= VIRTIO_CONFIG_S_DRIVER;
+	vp_set_status(&vp_dev->vdev, status);
+
 	vp_finalize_features(&vp_dev->vdev);
 
-	if (drv && drv->restore)
+	if (drv->restore) {
 		ret = drv->restore(&vp_dev->vdev);
+		if (ret) {
+			status |= VIRTIO_CONFIG_S_FAILED;
+			vp_set_status(&vp_dev->vdev, status);
+			return ret;
+		}
+	}
 
 	/* Finally, tell the device we're all set */
-	if (!ret)
-		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+	status |= VIRTIO_CONFIG_S_DRIVER_OK;
+	vp_set_status(&vp_dev->vdev, status);
 
 	return ret;
 }
diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c
index 40788c925d1c..73705aff53cb 100644
--- a/drivers/w1/w1_netlink.c
+++ b/drivers/w1/w1_netlink.c
@@ -54,28 +54,29 @@ static void w1_send_slave(struct w1_master *dev, u64 rn)
 	struct w1_netlink_msg *hdr = (struct w1_netlink_msg *)(msg + 1);
 	struct w1_netlink_cmd *cmd = (struct w1_netlink_cmd *)(hdr + 1);
 	int avail;
+	u64 *data;
 
 	/* update kernel slave list */
 	w1_slave_found(dev, rn);
 
 	avail = dev->priv_size - cmd->len;
 
-	if (avail > 8) {
-		u64 *data = (void *)(cmd + 1) + cmd->len;
+	if (avail < 8) {
+		msg->ack++;
+		cn_netlink_send(msg, 0, GFP_KERNEL);
 
-		*data = rn;
-		cmd->len += 8;
-		hdr->len += 8;
-		msg->len += 8;
-		return;
+		msg->len = sizeof(struct w1_netlink_msg) +
+			sizeof(struct w1_netlink_cmd);
+		hdr->len = sizeof(struct w1_netlink_cmd);
+		cmd->len = 0;
 	}
 
-	msg->ack++;
-	cn_netlink_send(msg, 0, GFP_KERNEL);
+	data = (void *)(cmd + 1) + cmd->len;
 
-	msg->len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd);
-	hdr->len = sizeof(struct w1_netlink_cmd);
-	cmd->len = 0;
+	*data = rn;
+	cmd->len += 8;
+	hdr->len += 8;
+	msg->len += 8;
 }
 
 static int w1_process_search_command(struct w1_master *dev, struct cn_msg *msg,
diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c
index 9fa1f69dac13..61098cd5439e 100644
--- a/drivers/watchdog/ath79_wdt.c
+++ b/drivers/watchdog/ath79_wdt.c
@@ -20,6 +20,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bitops.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/init.h>
@@ -91,6 +92,15 @@ static inline void ath79_wdt_keepalive(void)
 static inline void ath79_wdt_enable(void)
 {
 	ath79_wdt_keepalive();
+
+	/*
+	 * Updating the TIMER register requires a few microseconds
+	 * on the AR934x SoCs at least. Use a small delay to ensure
+	 * that the TIMER register is updated within the hardware
+	 * before enabling the watchdog.
+	 */
+	udelay(2);
+
 	ath79_wdt_wr(WDOG_REG_CTRL, WDOG_CTRL_ACTION_FCR);
 	/* flush write */
 	ath79_wdt_rr(WDOG_REG_CTRL);
diff --git a/drivers/watchdog/kempld_wdt.c b/drivers/watchdog/kempld_wdt.c
index 20dc73844737..d9c1a1601926 100644
--- a/drivers/watchdog/kempld_wdt.c
+++ b/drivers/watchdog/kempld_wdt.c
@@ -162,7 +162,7 @@ static int kempld_wdt_set_stage_timeout(struct kempld_wdt_data *wdt_data,
 	kempld_get_mutex(pld);
 	stage_cfg = kempld_read8(pld, KEMPLD_WDT_STAGE_CFG(stage->id));
 	stage_cfg &= ~STAGE_CFG_PRESCALER_MASK;
-	stage_cfg |= STAGE_CFG_SET_PRESCALER(prescaler);
+	stage_cfg |= STAGE_CFG_SET_PRESCALER(PRESCALER_21);
 	kempld_write8(pld, KEMPLD_WDT_STAGE_CFG(stage->id), stage_cfg);
 	kempld_write32(pld, KEMPLD_WDT_STAGE_TIMEOUT(stage->id),
 			stage_timeout);
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 3f786ce0a6f2..88bcdfb9f68f 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -60,7 +60,6 @@
  * @adev: amba device structure of wdt
  * @status: current status of wdt
  * @load_val: load value to be set for current timeout
- * @timeout: current programmed timeout
  */
 struct sp805_wdt {
 	struct watchdog_device		wdd;
@@ -69,7 +68,6 @@ struct sp805_wdt {
 	struct clk			*clk;
 	struct amba_device		*adev;
 	unsigned int			load_val;
-	unsigned int			timeout;
 };
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
@@ -99,7 +97,7 @@ static int wdt_setload(struct watchdog_device *wdd, unsigned int timeout)
 	spin_lock(&wdt->lock);
 	wdt->load_val = load;
 	/* roundup timeout to closest positive integer value */
-	wdt->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
+	wdd->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
 	spin_unlock(&wdt->lock);
 
 	return 0;
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 61a6ac8fa8fc..08834b565aab 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -426,20 +426,18 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 		 * p2m are consistent.
 		 */
 		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long p;
-			struct page   *scratch_page = get_balloon_scratch_page();
-
 			if (!PageHighMem(page)) {
+				struct page *scratch_page = get_balloon_scratch_page();
+
 				ret = HYPERVISOR_update_va_mapping(
 						(unsigned long)__va(pfn << PAGE_SHIFT),
 						pfn_pte(page_to_pfn(scratch_page),
 							PAGE_KERNEL_RO), 0);
 				BUG_ON(ret);
-			}
-			p = page_to_pfn(scratch_page);
-			__set_phys_to_machine(pfn, pfn_to_mfn(p));
 
-			put_balloon_scratch_page();
+				put_balloon_scratch_page();
+			}
+			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 		}
 #endif
 
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 1de2a191b395..ef7d446e07ee 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -66,7 +66,21 @@ static DEFINE_PER_CPU(struct evtchn_fifo_queue, cpu_queue);
 static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly;
 static unsigned event_array_pages __read_mostly;
 
+/*
+ * sync_set_bit() and friends must be unsigned long aligned.
+ */
+#if BITS_PER_LONG > 32
+
+#define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL)
+#define EVTCHN_FIFO_BIT(b, w) \
+    (((unsigned long)w & 0x4UL) ? (EVTCHN_FIFO_ ##b + 32) : EVTCHN_FIFO_ ##b)
+
+#else
+
 #define BM(w) ((unsigned long *)(w))
+#define EVTCHN_FIFO_BIT(b, w) EVTCHN_FIFO_ ##b
+
+#endif
 
 static inline event_word_t *event_word_from_port(unsigned port)
 {
@@ -85,6 +99,25 @@ static unsigned evtchn_fifo_nr_channels(void)
 	return event_array_pages * EVENT_WORDS_PER_PAGE;
 }
 
+static int init_control_block(int cpu,
+                              struct evtchn_fifo_control_block *control_block)
+{
+	struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
+	struct evtchn_init_control init_control;
+	unsigned int i;
+
+	/* Reset the control block and the local HEADs. */
+	clear_page(control_block);
+	for (i = 0; i < EVTCHN_FIFO_MAX_QUEUES; i++)
+		q->head[i] = 0;
+
+	init_control.control_gfn = virt_to_mfn(control_block);
+	init_control.offset      = 0;
+	init_control.vcpu        = cpu;
+
+	return HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control);
+}
+
 static void free_unused_array_pages(void)
 {
 	unsigned i;
@@ -161,33 +194,38 @@ static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu)
 static void evtchn_fifo_clear_pending(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	sync_clear_bit(EVTCHN_FIFO_PENDING, BM(word));
+	sync_clear_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
 static void evtchn_fifo_set_pending(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	sync_set_bit(EVTCHN_FIFO_PENDING, BM(word));
+	sync_set_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
 static bool evtchn_fifo_is_pending(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	return sync_test_bit(EVTCHN_FIFO_PENDING, BM(word));
+	return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
 static bool evtchn_fifo_test_and_set_mask(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	return sync_test_and_set_bit(EVTCHN_FIFO_MASKED, BM(word));
+	return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
 }
 
 static void evtchn_fifo_mask(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	sync_set_bit(EVTCHN_FIFO_MASKED, BM(word));
+	sync_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
 }
 
+static bool evtchn_fifo_is_masked(unsigned port)
+{
+	event_word_t *word = event_word_from_port(port);
+	return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
+}
 /*
  * Clear MASKED, spinning if BUSY is set.
  */
@@ -211,7 +249,7 @@ static void evtchn_fifo_unmask(unsigned port)
 	BUG_ON(!irqs_disabled());
 
 	clear_masked(word);
-	if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))) {
+	if (evtchn_fifo_is_pending(port)) {
 		struct evtchn_unmask unmask = { .port = port };
 		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
 	}
@@ -247,7 +285,7 @@ static void handle_irq_for_port(unsigned port)
 
 static void consume_one_event(unsigned cpu,
 			      struct evtchn_fifo_control_block *control_block,
-			      unsigned priority, uint32_t *ready)
+			      unsigned priority, unsigned long *ready)
 {
 	struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
 	uint32_t head;
@@ -277,10 +315,9 @@ static void consume_one_event(unsigned cpu,
 	 * copy of the ready word.
 	 */
 	if (head == 0)
-		clear_bit(priority, BM(ready));
+		clear_bit(priority, ready);
 
-	if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))
-	    && !sync_test_bit(EVTCHN_FIFO_MASKED, BM(word)))
+	if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port))
 		handle_irq_for_port(port);
 
 	q->head[priority] = head;
@@ -289,7 +326,7 @@ static void consume_one_event(unsigned cpu,
 static void evtchn_fifo_handle_events(unsigned cpu)
 {
 	struct evtchn_fifo_control_block *control_block;
-	uint32_t ready;
+	unsigned long ready;
 	unsigned q;
 
 	control_block = per_cpu(cpu_control_block, cpu);
@@ -309,7 +346,6 @@ static void evtchn_fifo_resume(void)
 
 	for_each_possible_cpu(cpu) {
 		void *control_block = per_cpu(cpu_control_block, cpu);
-		struct evtchn_init_control init_control;
 		int ret;
 
 		if (!control_block)
@@ -326,12 +362,7 @@ static void evtchn_fifo_resume(void)
 			continue;
 		}
 
-		init_control.control_gfn = virt_to_mfn(control_block);
-		init_control.offset = 0;
-		init_control.vcpu = cpu;
-
-		ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control,
-						  &init_control);
+		ret = init_control_block(cpu, control_block);
 		if (ret < 0)
 			BUG();
 	}
@@ -359,30 +390,25 @@ static const struct evtchn_ops evtchn_ops_fifo = {
 	.resume            = evtchn_fifo_resume,
 };
 
-static int evtchn_fifo_init_control_block(unsigned cpu)
+static int evtchn_fifo_alloc_control_block(unsigned cpu)
 {
-	struct page *control_block = NULL;
-	struct evtchn_init_control init_control;
+	void *control_block = NULL;
 	int ret = -ENOMEM;
 
-	control_block = alloc_page(GFP_KERNEL|__GFP_ZERO);
+	control_block = (void *)__get_free_page(GFP_KERNEL);
 	if (control_block == NULL)
 		goto error;
 
-	init_control.control_gfn = virt_to_mfn(page_address(control_block));
-	init_control.offset      = 0;
-	init_control.vcpu        = cpu;
-
-	ret = HYPERVISOR_event_channel_op(EVTCHNOP_init_control, &init_control);
+	ret = init_control_block(cpu, control_block);
 	if (ret < 0)
 		goto error;
 
-	per_cpu(cpu_control_block, cpu) = page_address(control_block);
+	per_cpu(cpu_control_block, cpu) = control_block;
 
 	return 0;
 
   error:
-	__free_page(control_block);
+	free_page((unsigned long)control_block);
 	return ret;
 }
 
@@ -396,7 +422,7 @@ static int evtchn_fifo_cpu_notification(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 		if (!per_cpu(cpu_control_block, cpu))
-			ret = evtchn_fifo_init_control_block(cpu);
+			ret = evtchn_fifo_alloc_control_block(cpu);
 		break;
 	default:
 		break;
@@ -413,7 +439,7 @@ int __init xen_evtchn_fifo_init(void)
 	int cpu = get_cpu();
 	int ret;
 
-	ret = evtchn_fifo_init_control_block(cpu);
+	ret = evtchn_fifo_alloc_control_block(cpu);
 	if (ret < 0)
 		goto out;
 
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 624e8dc24532..602913d7ae03 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -111,16 +111,11 @@ static void do_suspend(void)
 
 	shutting_down = SHUTDOWN_SUSPEND;
 
-#ifdef CONFIG_PREEMPT
-	/* If the kernel is preemptible, we need to freeze all the processes
-	   to prevent them from being in the middle of a pagetable update
-	   during suspend. */
 	err = freeze_processes();
 	if (err) {
 		pr_err("%s: freeze failed %d\n", __func__, err);
 		goto out;
 	}
-#endif
 
 	err = dpm_suspend_start(PMSG_FREEZE);
 	if (err) {
@@ -169,10 +164,8 @@ out_resume:
 	dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
 
 out_thaw:
-#ifdef CONFIG_PREEMPT
 	thaw_processes();
 out:
-#endif
 	shutting_down = SHUTDOWN_INVALID;
 }
 #endif	/* CONFIG_HIBERNATE_CALLBACKS */
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index ebd8f218a788..9df5d6ec7eec 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -96,8 +96,6 @@ static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
 	dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT;
 	phys_addr_t paddr = dma;
 
-	BUG_ON(paddr != dma); /* truncation has occurred, should never happen */
-
 	paddr |= baddr & ~PAGE_MASK;
 
 	return paddr;
@@ -447,11 +445,11 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	xen_dma_unmap_page(hwdev, paddr, size, dir, attrs);
+	xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
+		swiotlb_tbl_unmap_single(hwdev, dev_addr, size, dir);
 		return;
 	}
 
@@ -495,14 +493,14 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 	BUG_ON(dir == DMA_NONE);
 
 	if (target == SYNC_FOR_CPU)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr))
 		swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
 
 	if (target == SYNC_FOR_DEVICE)
-		xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+		xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir);
 
 	if (dir != DMA_FROM_DEVICE)
 		return;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index d098731b82ff..9a5b19dc899d 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -336,8 +336,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
 				&blocksize,&sbi->s_prefix,
 				sbi->s_volume, &mount_flags)) {
 		printk(KERN_ERR "AFFS: Error parsing options\n");
-		kfree(sbi->s_prefix);
-		kfree(sbi);
 		return -EINVAL;
 	}
 	/* N.B. after this point s_prefix must be released */
diff --git a/fs/aio.c b/fs/aio.c
index 062a5f6a1448..2f7e8c2e3e76 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -52,7 +52,8 @@
 struct aio_ring {
 	unsigned	id;	/* kernel internal index number */
 	unsigned	nr;	/* number of io_events */
-	unsigned	head;
+	unsigned	head;	/* Written to by userland or under ring_lock
+				 * mutex by aio_read_events_ring(). */
 	unsigned	tail;
 
 	unsigned	magic;
@@ -111,6 +112,11 @@ struct kioctx {
 
 	struct work_struct	free_work;
 
+	/*
+	 * signals when all in-flight requests are done
+	 */
+	struct completion *requests_done;
+
 	struct {
 		/*
 		 * This counts the number of available slots in the ringbuffer,
@@ -135,6 +141,7 @@ struct kioctx {
 
 	struct {
 		unsigned	tail;
+		unsigned	completed_events;
 		spinlock_t	completion_lock;
 	} ____cacheline_aligned_in_smp;
 
@@ -158,6 +165,15 @@ static struct vfsmount *aio_mnt;
 static const struct file_operations aio_ring_fops;
 static const struct address_space_operations aio_ctx_aops;
 
+/* Backing dev info for aio fs.
+ * -no dirty page accounting or writeback happens
+ */
+static struct backing_dev_info aio_fs_backing_dev_info = {
+	.name           = "aiofs",
+	.state          = 0,
+	.capabilities   = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY,
+};
+
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
 	struct qstr this = QSTR_INIT("[aio]", 5);
@@ -169,6 +185,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
 	inode->i_mapping->private_data = ctx;
+	inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
@@ -214,6 +231,9 @@ static int __init aio_setup(void)
 	if (IS_ERR(aio_mnt))
 		panic("Failed to create aio fs mount.");
 
+	if (bdi_init(&aio_fs_backing_dev_info))
+		panic("Failed to init aio fs backing dev info.");
+
 	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
@@ -243,6 +263,11 @@ static void aio_free_ring(struct kioctx *ctx)
 {
 	int i;
 
+	/* Disconnect the kiotx from the ring file.  This prevents future
+	 * accesses to the kioctx from page migration.
+	 */
+	put_aio_ring_file(ctx);
+
 	for (i = 0; i < ctx->nr_pages; i++) {
 		struct page *page;
 		pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
@@ -254,8 +279,6 @@ static void aio_free_ring(struct kioctx *ctx)
 		put_page(page);
 	}
 
-	put_aio_ring_file(ctx);
-
 	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) {
 		kfree(ctx->ring_pages);
 		ctx->ring_pages = NULL;
@@ -272,40 +295,44 @@ static const struct file_operations aio_ring_fops = {
 	.mmap = aio_ring_mmap,
 };
 
-static int aio_set_page_dirty(struct page *page)
-{
-	return 0;
-}
-
 #if IS_ENABLED(CONFIG_MIGRATION)
 static int aio_migratepage(struct address_space *mapping, struct page *new,
 			struct page *old, enum migrate_mode mode)
 {
 	struct kioctx *ctx;
 	unsigned long flags;
+	pgoff_t idx;
 	int rc;
 
 	rc = 0;
 
-	/* Make sure the old page hasn't already been changed */
+	/* mapping->private_lock here protects against the kioctx teardown.  */
 	spin_lock(&mapping->private_lock);
 	ctx = mapping->private_data;
-	if (ctx) {
-		pgoff_t idx;
-		spin_lock_irqsave(&ctx->completion_lock, flags);
-		idx = old->index;
-		if (idx < (pgoff_t)ctx->nr_pages) {
-			if (ctx->ring_pages[idx] != old)
-				rc = -EAGAIN;
-		} else
-			rc = -EINVAL;
-		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	if (!ctx) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	/* The ring_lock mutex.  The prevents aio_read_events() from writing
+	 * to the ring's head, and prevents page migration from mucking in
+	 * a partially initialized kiotx.
+	 */
+	if (!mutex_trylock(&ctx->ring_lock)) {
+		rc = -EAGAIN;
+		goto out;
+	}
+
+	idx = old->index;
+	if (idx < (pgoff_t)ctx->nr_pages) {
+		/* Make sure the old page hasn't already been changed */
+		if (ctx->ring_pages[idx] != old)
+			rc = -EAGAIN;
 	} else
 		rc = -EINVAL;
-	spin_unlock(&mapping->private_lock);
 
 	if (rc != 0)
-		return rc;
+		goto out_unlock;
 
 	/* Writeback must be complete */
 	BUG_ON(PageWriteback(old));
@@ -314,44 +341,32 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
 	rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
 	if (rc != MIGRATEPAGE_SUCCESS) {
 		put_page(new);
-		return rc;
+		goto out_unlock;
 	}
 
-	/* We can potentially race against kioctx teardown here.  Use the
-	 * address_space's private data lock to protect the mapping's
-	 * private_data.
+	/* Take completion_lock to prevent other writes to the ring buffer
+	 * while the old page is copied to the new.  This prevents new
+	 * events from being lost.
 	 */
-	spin_lock(&mapping->private_lock);
-	ctx = mapping->private_data;
-	if (ctx) {
-		pgoff_t idx;
-		spin_lock_irqsave(&ctx->completion_lock, flags);
-		migrate_page_copy(new, old);
-		idx = old->index;
-		if (idx < (pgoff_t)ctx->nr_pages) {
-			/* And only do the move if things haven't changed */
-			if (ctx->ring_pages[idx] == old)
-				ctx->ring_pages[idx] = new;
-			else
-				rc = -EAGAIN;
-		} else
-			rc = -EINVAL;
-		spin_unlock_irqrestore(&ctx->completion_lock, flags);
-	} else
-		rc = -EBUSY;
-	spin_unlock(&mapping->private_lock);
+	spin_lock_irqsave(&ctx->completion_lock, flags);
+	migrate_page_copy(new, old);
+	BUG_ON(ctx->ring_pages[idx] != old);
+	ctx->ring_pages[idx] = new;
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
-	if (rc == MIGRATEPAGE_SUCCESS)
-		put_page(old);
-	else
-		put_page(new);
+	/* The old page is no longer accessible. */
+	put_page(old);
 
+out_unlock:
+	mutex_unlock(&ctx->ring_lock);
+out:
+	spin_unlock(&mapping->private_lock);
 	return rc;
 }
 #endif
 
 static const struct address_space_operations aio_ctx_aops = {
-	.set_page_dirty = aio_set_page_dirty,
+	.set_page_dirty = __set_page_dirty_no_writeback,
 #if IS_ENABLED(CONFIG_MIGRATION)
 	.migratepage	= aio_migratepage,
 #endif
@@ -380,7 +395,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 	file = aio_private_file(ctx, nr_pages);
 	if (IS_ERR(file)) {
 		ctx->aio_ring_file = NULL;
-		return -EAGAIN;
+		return -ENOMEM;
 	}
 
 	ctx->aio_ring_file = file;
@@ -406,7 +421,6 @@ static int aio_setup_ring(struct kioctx *ctx)
 		pr_debug("pid(%d) page[%d]->count=%d\n",
 			 current->pid, i, page_count(page));
 		SetPageUptodate(page);
-		SetPageDirty(page);
 		unlock_page(page);
 
 		ctx->ring_pages[i] = page;
@@ -415,7 +429,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	if (unlikely(i != nr_pages)) {
 		aio_free_ring(ctx);
-		return -EAGAIN;
+		return -ENOMEM;
 	}
 
 	ctx->mmap_size = nr_pages * PAGE_SIZE;
@@ -429,7 +443,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 	if (IS_ERR((void *)ctx->mmap_base)) {
 		ctx->mmap_size = 0;
 		aio_free_ring(ctx);
-		return -EAGAIN;
+		return -ENOMEM;
 	}
 
 	pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
@@ -507,6 +521,10 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 {
 	struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
 
+	/* At this point we know that there are no any in-flight requests */
+	if (ctx->requests_done)
+		complete(ctx->requests_done);
+
 	INIT_WORK(&ctx->free_work, free_ioctx);
 	schedule_work(&ctx->free_work);
 }
@@ -556,6 +574,10 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 					rcu_read_unlock();
 					spin_unlock(&mm->ioctx_lock);
 
+					/* While kioctx setup is in progress,
+					 * we are protected from page migration
+					 * changes ring_pages by ->ring_lock.
+					 */
 					ring = kmap_atomic(ctx->ring_pages[0]);
 					ring->id = ctx->id;
 					kunmap_atomic(ring);
@@ -640,24 +662,28 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	ctx->max_reqs = nr_events;
 
-	if (percpu_ref_init(&ctx->users, free_ioctx_users))
-		goto err;
-
-	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
-		goto err;
-
 	spin_lock_init(&ctx->ctx_lock);
 	spin_lock_init(&ctx->completion_lock);
 	mutex_init(&ctx->ring_lock);
+	/* Protect against page migration throughout kiotx setup by keeping
+	 * the ring_lock mutex held until setup is complete. */
+	mutex_lock(&ctx->ring_lock);
 	init_waitqueue_head(&ctx->wait);
 
 	INIT_LIST_HEAD(&ctx->active_reqs);
 
+	if (percpu_ref_init(&ctx->users, free_ioctx_users))
+		goto err;
+
+	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
+		goto err;
+
 	ctx->cpu = alloc_percpu(struct kioctx_cpu);
 	if (!ctx->cpu)
 		goto err;
 
-	if (aio_setup_ring(ctx) < 0)
+	err = aio_setup_ring(ctx);
+	if (err < 0)
 		goto err;
 
 	atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
@@ -683,6 +709,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	if (err)
 		goto err_cleanup;
 
+	/* Release the ring_lock mutex now that all setup is complete. */
+	mutex_unlock(&ctx->ring_lock);
+
 	pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
 		 ctx, ctx->user_id, mm, ctx->nr_events);
 	return ctx;
@@ -692,6 +721,7 @@ err_cleanup:
 err_ctx:
 	aio_free_ring(ctx);
 err:
+	mutex_unlock(&ctx->ring_lock);
 	free_percpu(ctx->cpu);
 	free_percpu(ctx->reqs.pcpu_count);
 	free_percpu(ctx->users.pcpu_count);
@@ -705,7 +735,8 @@ err:
  *	when the processes owning a context have all exited to encourage
  *	the rapid destruction of the kioctx.
  */
-static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
+static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
+		struct completion *requests_done)
 {
 	if (!atomic_xchg(&ctx->dead, 1)) {
 		struct kioctx_table *table;
@@ -734,7 +765,11 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
 		if (ctx->mmap_size)
 			vm_munmap(ctx->mmap_base, ctx->mmap_size);
 
+		ctx->requests_done = requests_done;
 		percpu_ref_kill(&ctx->users);
+	} else {
+		if (requests_done)
+			complete(requests_done);
 	}
 }
 
@@ -769,6 +804,9 @@ void exit_aio(struct mm_struct *mm)
 	unsigned i = 0;
 
 	while (1) {
+		struct completion requests_done =
+			COMPLETION_INITIALIZER_ONSTACK(requests_done);
+
 		rcu_read_lock();
 		table = rcu_dereference(mm->ioctx_table);
 
@@ -796,23 +834,30 @@ void exit_aio(struct mm_struct *mm)
 		 */
 		ctx->mmap_size = 0;
 
-		kill_ioctx(mm, ctx);
+		kill_ioctx(mm, ctx, &requests_done);
+
+		/* Wait until all IO for the context are done. */
+		wait_for_completion(&requests_done);
 	}
 }
 
 static void put_reqs_available(struct kioctx *ctx, unsigned nr)
 {
 	struct kioctx_cpu *kcpu;
+	unsigned long flags;
 
 	preempt_disable();
 	kcpu = this_cpu_ptr(ctx->cpu);
 
+	local_irq_save(flags);
 	kcpu->reqs_available += nr;
+
 	while (kcpu->reqs_available >= ctx->req_batch * 2) {
 		kcpu->reqs_available -= ctx->req_batch;
 		atomic_add(ctx->req_batch, &ctx->reqs_available);
 	}
 
+	local_irq_restore(flags);
 	preempt_enable();
 }
 
@@ -820,10 +865,12 @@ static bool get_reqs_available(struct kioctx *ctx)
 {
 	struct kioctx_cpu *kcpu;
 	bool ret = false;
+	unsigned long flags;
 
 	preempt_disable();
 	kcpu = this_cpu_ptr(ctx->cpu);
 
+	local_irq_save(flags);
 	if (!kcpu->reqs_available) {
 		int old, avail = atomic_read(&ctx->reqs_available);
 
@@ -842,10 +889,73 @@ static bool get_reqs_available(struct kioctx *ctx)
 	ret = true;
 	kcpu->reqs_available--;
 out:
+	local_irq_restore(flags);
 	preempt_enable();
 	return ret;
 }
 
+/* refill_reqs_available
+ *	Updates the reqs_available reference counts used for tracking the
+ *	number of free slots in the completion ring.  This can be called
+ *	from aio_complete() (to optimistically update reqs_available) or
+ *	from aio_get_req() (the we're out of events case).  It must be
+ *	called holding ctx->completion_lock.
+ */
+static void refill_reqs_available(struct kioctx *ctx, unsigned head,
+                                  unsigned tail)
+{
+	unsigned events_in_ring, completed;
+
+	/* Clamp head since userland can write to it. */
+	head %= ctx->nr_events;
+	if (head <= tail)
+		events_in_ring = tail - head;
+	else
+		events_in_ring = ctx->nr_events - (head - tail);
+
+	completed = ctx->completed_events;
+	if (events_in_ring < completed)
+		completed -= events_in_ring;
+	else
+		completed = 0;
+
+	if (!completed)
+		return;
+
+	ctx->completed_events -= completed;
+	put_reqs_available(ctx, completed);
+}
+
+/* user_refill_reqs_available
+ *	Called to refill reqs_available when aio_get_req() encounters an
+ *	out of space in the completion ring.
+ */
+static void user_refill_reqs_available(struct kioctx *ctx)
+{
+	spin_lock_irq(&ctx->completion_lock);
+	if (ctx->completed_events) {
+		struct aio_ring *ring;
+		unsigned head;
+
+		/* Access of ring->head may race with aio_read_events_ring()
+		 * here, but that's okay since whether we read the old version
+		 * or the new version, and either will be valid.  The important
+		 * part is that head cannot pass tail since we prevent
+		 * aio_complete() from updating tail by holding
+		 * ctx->completion_lock.  Even if head is invalid, the check
+		 * against ctx->completed_events below will make sure we do the
+		 * safe/right thing.
+		 */
+		ring = kmap_atomic(ctx->ring_pages[0]);
+		head = ring->head;
+		kunmap_atomic(ring);
+
+		refill_reqs_available(ctx, head, ctx->tail);
+	}
+
+	spin_unlock_irq(&ctx->completion_lock);
+}
+
 /* aio_get_req
  *	Allocate a slot for an aio request.
  * Returns NULL if no requests are free.
@@ -854,8 +964,11 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx)
 {
 	struct kiocb *req;
 
-	if (!get_reqs_available(ctx))
-		return NULL;
+	if (!get_reqs_available(ctx)) {
+		user_refill_reqs_available(ctx);
+		if (!get_reqs_available(ctx))
+			return NULL;
+	}
 
 	req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
 	if (unlikely(!req))
@@ -914,8 +1027,8 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 	struct kioctx	*ctx = iocb->ki_ctx;
 	struct aio_ring	*ring;
 	struct io_event	*ev_page, *event;
+	unsigned tail, pos, head;
 	unsigned long	flags;
-	unsigned tail, pos;
 
 	/*
 	 * Special case handling for sync iocbs:
@@ -976,10 +1089,14 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 	ctx->tail = tail;
 
 	ring = kmap_atomic(ctx->ring_pages[0]);
+	head = ring->head;
 	ring->tail = tail;
 	kunmap_atomic(ring);
 	flush_dcache_page(ctx->ring_pages[0]);
 
+	ctx->completed_events++;
+	if (ctx->completed_events > 1)
+		refill_reqs_available(ctx, head, tail);
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
 	pr_debug("added to ring %p at [%u]\n", iocb, tail);
@@ -1024,16 +1141,26 @@ static long aio_read_events_ring(struct kioctx *ctx,
 
 	mutex_lock(&ctx->ring_lock);
 
+	/* Access to ->ring_pages here is protected by ctx->ring_lock. */
 	ring = kmap_atomic(ctx->ring_pages[0]);
 	head = ring->head;
 	tail = ring->tail;
 	kunmap_atomic(ring);
 
+	/*
+	 * Ensure that once we've read the current tail pointer, that
+	 * we also see the events that were stored up to the tail.
+	 */
+	smp_rmb();
+
 	pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events);
 
 	if (head == tail)
 		goto out;
 
+	head %= ctx->nr_events;
+	tail %= ctx->nr_events;
+
 	while (ret < nr) {
 		long avail;
 		struct io_event *ev;
@@ -1072,8 +1199,6 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	flush_dcache_page(ctx->ring_pages[0]);
 
 	pr_debug("%li  h%u t%u\n", ret, head, tail);
-
-	put_reqs_available(ctx, ret);
 out:
 	mutex_unlock(&ctx->ring_lock);
 
@@ -1171,7 +1296,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
 		if (ret)
-			kill_ioctx(current->mm, ioctx);
+			kill_ioctx(current->mm, ioctx, NULL);
 		percpu_ref_put(&ioctx->users);
 	}
 
@@ -1189,8 +1314,22 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 {
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
-		kill_ioctx(current->mm, ioctx);
+		struct completion requests_done =
+			COMPLETION_INITIALIZER_ONSTACK(requests_done);
+
+		/* Pass requests_done to kill_ioctx() where it can be set
+		 * in a thread-safe way. If we try to set it here then we have
+		 * a race condition if two io_destroy() called simultaneously.
+		 */
+		kill_ioctx(current->mm, ioctx, &requests_done);
 		percpu_ref_put(&ioctx->users);
+
+		/* Wait until all IO for the context are done. Otherwise kernel
+		 * keep using user-space buffers even if user thinks the context
+		 * is destroyed.
+		 */
+		wait_for_completion(&requests_done);
+
 		return 0;
 	}
 	pr_debug("EINVAL: io_destroy: invalid context id\n");
@@ -1285,10 +1424,8 @@ rw_common:
 						&iovec, compat)
 			: aio_setup_single_vector(req, rw, buf, &nr_segs,
 						  iovec);
-		if (ret)
-			return ret;
-
-		ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+		if (!ret)
+			ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
 		if (ret < 0) {
 			if (iovec != &inline_vec)
 				kfree(iovec);
diff --git a/fs/attr.c b/fs/attr.c
index 5d4e59d56e85..6530ced19697 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -50,14 +50,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 	if ((ia_valid & ATTR_UID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	     !uid_eq(attr->ia_uid, inode->i_uid)) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure caller can chgrp. */
 	if ((ia_valid & ATTR_GID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	    (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure a caller can chmod. */
@@ -67,7 +67,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 		/* Also check the setgid bit! */
 		if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
 				inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			attr->ia_mode &= ~S_ISGID;
 	}
 
@@ -160,7 +160,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 		umode_t mode = attr->ia_mode;
 
 		if (!in_group_p(inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			mode &= ~S_ISGID;
 		inode->i_mode = mode;
 	}
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 2caf36ac3e93..cc87c1abac97 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -179,7 +179,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 		spin_lock(&active->d_lock);
 
 		/* Already gone? */
-		if (!d_count(active))
+		if ((int) d_count(active) <= 0)
 			goto next;
 
 		qstr = &active->d_name;
@@ -230,7 +230,7 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
 
 		spin_lock(&expiring->d_lock);
 
-		/* Bad luck, we've already been dentry_iput */
+		/* We've already been dentry_iput or unlinked */
 		if (!expiring->d_inode)
 			goto next;
 
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index a66768ebc8d1..3def5122904a 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -1,5 +1,6 @@
 config BTRFS_FS
 	tristate "Btrfs filesystem support"
+	select LIBCRC32C
 	select CRYPTO
 	select CRYPTO_CRC32C
 	select ZLIB_INFLATE
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index aded3ef3d3d4..6244f9cf8ae3 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -275,9 +275,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 			}
 			if (ret > 0)
 				goto next;
-			ret = ulist_add_merge(parents, eb->start,
-					      (uintptr_t)eie,
-					      (u64 *)&old, GFP_NOFS);
+			ret = ulist_add_merge_ptr(parents, eb->start,
+						  eie, (void **)&old, GFP_NOFS);
 			if (ret < 0)
 				break;
 			if (!ret && extent_item_pos) {
@@ -972,11 +971,12 @@ again:
 				goto out;
 		}
 		if (ref->count && ref->parent) {
-			if (extent_item_pos && !ref->inode_list) {
+			if (extent_item_pos && !ref->inode_list &&
+			    ref->level == 0) {
 				u32 bsz;
 				struct extent_buffer *eb;
 				bsz = btrfs_level_size(fs_info->extent_root,
-							info_level);
+							ref->level);
 				eb = read_tree_block(fs_info->extent_root,
 							   ref->parent, bsz, 0);
 				if (!eb || !extent_buffer_uptodate(eb)) {
@@ -984,16 +984,19 @@ again:
 					ret = -EIO;
 					goto out;
 				}
+				btrfs_tree_read_lock(eb);
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 				ret = find_extent_in_eb(eb, bytenr,
 							*extent_item_pos, &eie);
+				btrfs_tree_read_unlock_blocking(eb);
 				free_extent_buffer(eb);
 				if (ret < 0)
 					goto out;
 				ref->inode_list = eie;
 			}
-			ret = ulist_add_merge(refs, ref->parent,
-					      (uintptr_t)ref->inode_list,
-					      (u64 *)&eie, GFP_NOFS);
+			ret = ulist_add_merge_ptr(refs, ref->parent,
+						  ref->inode_list,
+						  (void **)&eie, GFP_NOFS);
 			if (ret < 0)
 				goto out;
 			if (!ret && extent_item_pos) {
@@ -1411,9 +1414,10 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
  * returns <0 on error
  */
 static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				struct btrfs_extent_inline_ref **out_eiref,
-				int *out_type)
+				   struct btrfs_key *key,
+				   struct btrfs_extent_item *ei, u32 item_size,
+				   struct btrfs_extent_inline_ref **out_eiref,
+				   int *out_type)
 {
 	unsigned long end;
 	u64 flags;
@@ -1423,19 +1427,26 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
 		/* first call */
 		flags = btrfs_extent_flags(eb, ei);
 		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-			info = (struct btrfs_tree_block_info *)(ei + 1);
-			*out_eiref =
-				(struct btrfs_extent_inline_ref *)(info + 1);
+			if (key->type == BTRFS_METADATA_ITEM_KEY) {
+				/* a skinny metadata extent */
+				*out_eiref =
+				     (struct btrfs_extent_inline_ref *)(ei + 1);
+			} else {
+				WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY);
+				info = (struct btrfs_tree_block_info *)(ei + 1);
+				*out_eiref =
+				   (struct btrfs_extent_inline_ref *)(info + 1);
+			}
 		} else {
 			*out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1);
 		}
 		*ptr = (unsigned long)*out_eiref;
-		if ((void *)*ptr >= (void *)ei + item_size)
+		if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size)
 			return -ENOENT;
 	}
 
 	end = (unsigned long)ei + item_size;
-	*out_eiref = (struct btrfs_extent_inline_ref *)*ptr;
+	*out_eiref = (struct btrfs_extent_inline_ref *)(*ptr);
 	*out_type = btrfs_extent_inline_ref_type(eb, *out_eiref);
 
 	*ptr += btrfs_extent_inline_ref_size(*out_type);
@@ -1454,8 +1465,8 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
  * <0 on error.
  */
 int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				u64 *out_root, u8 *out_level)
+			    struct btrfs_key *key, struct btrfs_extent_item *ei,
+			    u32 item_size, u64 *out_root, u8 *out_level)
 {
 	int ret;
 	int type;
@@ -1466,8 +1477,8 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 		return 1;
 
 	while (1) {
-		ret = __get_extent_inline_ref(ptr, eb, ei, item_size,
-						&eiref, &type);
+		ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size,
+					      &eiref, &type);
 		if (ret < 0)
 			return ret;
 
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index a910b27a8ad9..519b49e51f57 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -40,8 +40,8 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 			u64 *flags);
 
 int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				u64 *out_root, u8 *out_level);
+			    struct btrfs_key *key, struct btrfs_extent_item *ei,
+			    u32 item_size, u64 *out_root, u8 *out_level);
 
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 				u64 extent_item_objectid,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b01fb6c527e3..d43c544d3b68 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, pg_index);
 		rcu_read_unlock();
-		if (page) {
+		if (page && !radix_tree_exceptional_entry(page)) {
 			misses++;
 			if (misses > 4)
 				break;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2c1a42ca519f..d3511cc17091 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1104,6 +1104,12 @@ struct btrfs_qgroup_limit_item {
 	__le64 rsv_excl;
 } __attribute__ ((__packed__));
 
+/* For raid type sysfs entries */
+struct raid_kobject {
+	int raid_type;
+	struct kobject kobj;
+};
+
 struct btrfs_space_info {
 	spinlock_t lock;
 
@@ -1154,7 +1160,7 @@ struct btrfs_space_info {
 	wait_queue_head_t wait;
 
 	struct kobject kobj;
-	struct kobject block_group_kobjs[BTRFS_NR_RAID_TYPES];
+	struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES];
 };
 
 #define	BTRFS_BLOCK_RSV_GLOBAL		1
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 451b00c86f6c..12e35566d2fc 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1854,6 +1854,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
 
+	/*
+	 * we don't do delayed inode updates during log recovery because it
+	 * leads to enospc problems.  This means we also can't do
+	 * delayed inode refs
+	 */
+	if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+		return -EAGAIN;
+
 	delayed_node = btrfs_get_or_create_delayed_node(inode);
 	if (IS_ERR(delayed_node))
 		return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 81ea55314b1f..0db8ded65923 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3244,6 +3244,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 	/* send down all the barriers */
 	head = &info->fs_devices->devices;
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors_send++;
 			continue;
@@ -3258,6 +3260,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 
 	/* wait for all the barriers */
 	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (dev->missing)
+			continue;
 		if (!dev->bdev) {
 			errors_wait++;
 			continue;
@@ -3594,6 +3598,11 @@ int close_ctree(struct btrfs_root *root)
 
 	btrfs_free_block_groups(fs_info);
 
+	/*
+	 * we must make sure there is not any read request to
+	 * submit after we stopping all workers.
+	 */
+	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
 	free_root_pointers(fs_info, 1);
@@ -3969,12 +3978,6 @@ again:
 		if (ret)
 			break;
 
-		/* opt_discard */
-		if (btrfs_test_opt(root, DISCARD))
-			ret = btrfs_error_discard_extent(root, start,
-							 end + 1 - start,
-							 NULL);
-
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		btrfs_error_unpin_extent_range(root, start, end);
 		cond_resched();
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 32312e09f0f5..d2f1c011d73a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2444,7 +2444,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			spin_unlock(&locked_ref->lock);
 			spin_lock(&delayed_refs->lock);
 			spin_lock(&locked_ref->lock);
-			if (rb_first(&locked_ref->ref_root)) {
+			if (rb_first(&locked_ref->ref_root) ||
+			    locked_ref->extent_op) {
 				spin_unlock(&locked_ref->lock);
 				spin_unlock(&delayed_refs->lock);
 				continue;
@@ -3399,10 +3400,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 		return ret;
 	}
 
-	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
 		INIT_LIST_HEAD(&found->block_groups[i]);
-		kobject_init(&found->block_group_kobjs[i], &btrfs_raid_ktype);
-	}
 	init_rwsem(&found->groups_sem);
 	spin_lock_init(&found->lock);
 	found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
@@ -5504,7 +5503,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	update_global_block_rsv(fs_info);
 }
 
-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
+			      const bool return_free_space)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_group_cache *cache = NULL;
@@ -5528,7 +5528,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 
 		if (start < cache->last_byte_to_unpin) {
 			len = min(len, cache->last_byte_to_unpin - start);
-			btrfs_add_free_space(cache, start, len);
+			if (return_free_space)
+				btrfs_add_free_space(cache, start, len);
 		}
 
 		start += len;
@@ -5591,7 +5592,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 						   end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
-		unpin_extent_range(root, start, end);
+		unpin_extent_range(root, start, end, true);
 		cond_resched();
 	}
 
@@ -8327,8 +8328,9 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		list_del(&space_info->list);
 		for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
 			struct kobject *kobj;
-			kobj = &space_info->block_group_kobjs[i];
-			if (kobj->parent) {
+			kobj = space_info->block_group_kobjs[i];
+			space_info->block_group_kobjs[i] = NULL;
+			if (kobj) {
 				kobject_del(kobj);
 				kobject_put(kobj);
 			}
@@ -8343,22 +8345,35 @@ static void __link_block_group(struct btrfs_space_info *space_info,
 			       struct btrfs_block_group_cache *cache)
 {
 	int index = get_block_group_index(cache);
+	bool first = false;
 
 	down_write(&space_info->groups_sem);
-	if (list_empty(&space_info->block_groups[index])) {
-		struct kobject *kobj = &space_info->block_group_kobjs[index];
+	if (list_empty(&space_info->block_groups[index]))
+		first = true;
+	list_add_tail(&cache->list, &space_info->block_groups[index]);
+	up_write(&space_info->groups_sem);
+
+	if (first) {
+		struct raid_kobject *rkobj;
 		int ret;
 
-		kobject_get(&space_info->kobj); /* put in release */
-		ret = kobject_add(kobj, &space_info->kobj, "%s",
-				  get_raid_name(index));
+		rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS);
+		if (!rkobj)
+			goto out_err;
+		rkobj->raid_type = index;
+		kobject_init(&rkobj->kobj, &btrfs_raid_ktype);
+		ret = kobject_add(&rkobj->kobj, &space_info->kobj,
+				  "%s", get_raid_name(index));
 		if (ret) {
-			pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n");
-			kobject_put(&space_info->kobj);
+			kobject_put(&rkobj->kobj);
+			goto out_err;
 		}
+		space_info->block_group_kobjs[index] = &rkobj->kobj;
 	}
-	list_add_tail(&cache->list, &space_info->block_groups[index]);
-	up_write(&space_info->groups_sem);
+
+	return;
+out_err:
+	pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n");
 }
 
 static struct btrfs_block_group_cache *
@@ -8693,6 +8708,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_root *tree_root = root->fs_info->tree_root;
 	struct btrfs_key key;
 	struct inode *inode;
+	struct kobject *kobj = NULL;
 	int ret;
 	int index;
 	int factor;
@@ -8792,11 +8808,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 */
 	list_del_init(&block_group->list);
 	if (list_empty(&block_group->space_info->block_groups[index])) {
-		kobject_del(&block_group->space_info->block_group_kobjs[index]);
-		kobject_put(&block_group->space_info->block_group_kobjs[index]);
+		kobj = block_group->space_info->block_group_kobjs[index];
+		block_group->space_info->block_group_kobjs[index] = NULL;
 		clear_avail_alloc_bits(root->fs_info, block_group->flags);
 	}
 	up_write(&block_group->space_info->groups_sem);
+	if (kobj) {
+		kobject_del(kobj);
+		kobject_put(kobj);
+	}
 
 	if (block_group->cached == BTRFS_CACHE_STARTED)
 		wait_block_group_cache_done(block_group);
@@ -8868,7 +8888,7 @@ out:
 
 int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 {
-	return unpin_extent_range(root, start, end);
+	return unpin_extent_range(root, start, end, false);
 }
 
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 85bbd01f1271..1a858947006e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1686,6 +1686,7 @@ again:
 		 * shortening the size of the delalloc range we're searching
 		 */
 		free_extent_state(cached_state);
+		cached_state = NULL;
 		if (!loops) {
 			max_bytes = PAGE_CACHE_SIZE;
 			loops = 1;
@@ -2346,7 +2347,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 {
 	int uptodate = (err == 0);
 	struct extent_io_tree *tree;
-	int ret;
+	int ret = 0;
 
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
 
@@ -2360,6 +2361,8 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 	if (!uptodate) {
 		ClearPageUptodate(page);
 		SetPageError(page);
+		ret = ret < 0 ? ret : -EIO;
+		mapping_set_error(page->mapping, ret);
 	}
 	return 0;
 }
@@ -2522,6 +2525,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
 					uptodate = 0;
+				offset += len;
 				continue;
 			}
 		}
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 996ad56b57db..82845a6c63c2 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -290,8 +290,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
 	if (!em)
 		goto out;
 
-	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
-		list_move(&em->list, &tree->modified_extents);
 	em->generation = gen;
 	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 	em->mod_start = em->start;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 127555b29f58..196b089b0052 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -423,7 +423,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	ret = 0;
 fail:
 	while (ret < 0 && !list_empty(&tmplist)) {
-		sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+		sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -756,7 +756,7 @@ again:
 				found_next = 1;
 			if (ret != 0)
 				goto insert;
-			slot = 0;
+			slot = path->slots[0];
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
 		if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 0165b8672f09..f6d00df99a8c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -425,13 +425,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		struct page *page = prepared_pages[pg];
 		/*
 		 * Copy data from userspace to the current page
-		 *
-		 * Disable pagefault to avoid recursive lock since
-		 * the pages are already locked
 		 */
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, count);
-		pagefault_enable();
 
 		/* Flush processor's dcache for this page */
 		flush_dcache_page(page);
@@ -2510,23 +2505,28 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
-	u64 lockstart = *offset;
-	u64 lockend = i_size_read(inode);
-	u64 start = *offset;
-	u64 len = i_size_read(inode);
+	u64 lockstart;
+	u64 lockend;
+	u64 start;
+	u64 len;
 	int ret = 0;
 
-	lockend = max_t(u64, root->sectorsize, lockend);
+	if (inode->i_size == 0)
+		return -ENXIO;
+
+	/*
+	 * *offset can be negative, in this case we start finding DATA/HOLE from
+	 * the very start of the file.
+	 */
+	start = max_t(loff_t, 0, *offset);
+
+	lockstart = round_down(start, root->sectorsize);
+	lockend = round_up(i_size_read(inode), root->sectorsize);
 	if (lockend <= lockstart)
 		lockend = lockstart + root->sectorsize;
-
 	lockend--;
 	len = lockend - lockstart + 1;
 
-	len = max_t(u64, len, root->sectorsize);
-	if (inode->i_size == 0)
-		return -ENXIO;
-
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0,
 			 &cached_state);
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 73f3de7a083c..a6bd654dcd47 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -831,7 +831,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 
 	if (!matched) {
 		__btrfs_remove_free_space_cache(ctl);
-		btrfs_err(fs_info, "block group %llu has wrong amount of free space",
+		btrfs_warn(fs_info, "block group %llu has wrong amount of free space",
 			block_group->key.objectid);
 		ret = -1;
 	}
@@ -843,7 +843,7 @@ out:
 		spin_unlock(&block_group->lock);
 		ret = 0;
 
-		btrfs_err(fs_info, "failed to load free space cache for block group %llu",
+		btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now",
 			block_group->key.objectid);
 	}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d3d44486290b..d68a7250f00b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -701,6 +701,18 @@ retry:
 				unlock_extent(io_tree, async_extent->start,
 					      async_extent->start +
 					      async_extent->ram_size - 1);
+
+				/*
+				 * we need to redirty the pages if we decide to
+				 * fallback to uncompressed IO, otherwise we
+				 * will not submit these pages down to lower
+				 * layers.
+				 */
+				extent_range_redirty_for_io(inode,
+						async_extent->start,
+						async_extent->start +
+						async_extent->ram_size - 1);
+
 				goto retry;
 			}
 			goto out_free;
@@ -3584,7 +3596,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	 * without delay
 	 */
 	if (!btrfs_is_free_space_inode(inode)
-	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
+	    && !root->fs_info->log_root_recovering) {
 		btrfs_update_root_times(trans, root);
 
 		ret = btrfs_delayed_update_inode(trans, root, inode);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a6d8efa46bfe..0b72006aecbe 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -302,6 +302,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 			goto out_drop;
 
 	} else {
+		ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
+		if (ret && ret != -ENODATA)
+			goto out_drop;
 		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
 	}
 
@@ -4750,6 +4753,12 @@ long btrfs_ioctl(struct file *file, unsigned int
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(file->f_dentry->d_sb, 1);
+		/*
+		 * The transaction thread may want to do more work,
+		 * namely it pokes the cleaner ktread that will start
+		 * processing uncleaned subvols.
+		 */
+		wake_up_process(root->fs_info->transaction_kthread);
 		return ret;
 	}
 	case BTRFS_IOC_START_SYNC:
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 07b3b36f40ee..01f977e3ce09 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -736,7 +736,8 @@ again:
 		err = ret;
 		goto out;
 	}
-	BUG_ON(!ret || !path1->slots[0]);
+	ASSERT(ret);
+	ASSERT(path1->slots[0]);
 
 	path1->slots[0]--;
 
@@ -746,10 +747,10 @@ again:
 		 * the backref was added previously when processing
 		 * backref of type BTRFS_TREE_BLOCK_REF_KEY
 		 */
-		BUG_ON(!list_is_singular(&cur->upper));
+		ASSERT(list_is_singular(&cur->upper));
 		edge = list_entry(cur->upper.next, struct backref_edge,
 				  list[LOWER]);
-		BUG_ON(!list_empty(&edge->list[UPPER]));
+		ASSERT(list_empty(&edge->list[UPPER]));
 		exist = edge->node[UPPER];
 		/*
 		 * add the upper level block to pending list if we need
@@ -831,7 +832,7 @@ again:
 					cur->cowonly = 1;
 			}
 #else
-		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
+		ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
 #endif
 			if (key.objectid == key.offset) {
@@ -840,7 +841,7 @@ again:
 				 * backref of this type.
 				 */
 				root = find_reloc_root(rc, cur->bytenr);
-				BUG_ON(!root);
+				ASSERT(root);
 				cur->root = root;
 				break;
 			}
@@ -868,7 +869,7 @@ again:
 			} else {
 				upper = rb_entry(rb_node, struct backref_node,
 						 rb_node);
-				BUG_ON(!upper->checked);
+				ASSERT(upper->checked);
 				INIT_LIST_HEAD(&edge->list[UPPER]);
 			}
 			list_add_tail(&edge->list[LOWER], &cur->upper);
@@ -892,7 +893,7 @@ again:
 
 		if (btrfs_root_level(&root->root_item) == cur->level) {
 			/* tree root */
-			BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+			ASSERT(btrfs_root_bytenr(&root->root_item) ==
 			       cur->bytenr);
 			if (should_ignore_root(root))
 				list_add(&cur->list, &useless);
@@ -927,7 +928,7 @@ again:
 		need_check = true;
 		for (; level < BTRFS_MAX_LEVEL; level++) {
 			if (!path2->nodes[level]) {
-				BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+				ASSERT(btrfs_root_bytenr(&root->root_item) ==
 				       lower->bytenr);
 				if (should_ignore_root(root))
 					list_add(&lower->list, &useless);
@@ -976,12 +977,15 @@ again:
 					need_check = false;
 					list_add_tail(&edge->list[UPPER],
 						      &list);
-				} else
+				} else {
+					if (upper->checked)
+						need_check = true;
 					INIT_LIST_HEAD(&edge->list[UPPER]);
+				}
 			} else {
 				upper = rb_entry(rb_node, struct backref_node,
 						 rb_node);
-				BUG_ON(!upper->checked);
+				ASSERT(upper->checked);
 				INIT_LIST_HEAD(&edge->list[UPPER]);
 				if (!upper->owner)
 					upper->owner = btrfs_header_owner(eb);
@@ -1025,7 +1029,7 @@ next:
 	 * everything goes well, connect backref nodes and insert backref nodes
 	 * into the cache.
 	 */
-	BUG_ON(!node->checked);
+	ASSERT(node->checked);
 	cowonly = node->cowonly;
 	if (!cowonly) {
 		rb_node = tree_insert(&cache->rb_root, node->bytenr,
@@ -1061,8 +1065,21 @@ next:
 			continue;
 		}
 
-		BUG_ON(!upper->checked);
-		BUG_ON(cowonly != upper->cowonly);
+		if (!upper->checked) {
+			/*
+			 * Still want to blow up for developers since this is a
+			 * logic bug.
+			 */
+			ASSERT(0);
+			err = -EINVAL;
+			goto out;
+		}
+		if (cowonly != upper->cowonly) {
+			ASSERT(0);
+			err = -EINVAL;
+			goto out;
+		}
+
 		if (!cowonly) {
 			rb_node = tree_insert(&cache->rb_root, upper->bytenr,
 					      &upper->rb_node);
@@ -1085,7 +1102,7 @@ next:
 	while (!list_empty(&useless)) {
 		upper = list_entry(useless.next, struct backref_node, list);
 		list_del_init(&upper->list);
-		BUG_ON(!list_empty(&upper->upper));
+		ASSERT(list_empty(&upper->upper));
 		if (upper == node)
 			node = NULL;
 		if (upper->lowest) {
@@ -1118,29 +1135,45 @@ out:
 	if (err) {
 		while (!list_empty(&useless)) {
 			lower = list_entry(useless.next,
-					   struct backref_node, upper);
-			list_del_init(&lower->upper);
+					   struct backref_node, list);
+			list_del_init(&lower->list);
 		}
-		upper = node;
-		INIT_LIST_HEAD(&list);
-		while (upper) {
-			if (RB_EMPTY_NODE(&upper->rb_node)) {
-				list_splice_tail(&upper->upper, &list);
-				free_backref_node(cache, upper);
-			}
-
-			if (list_empty(&list))
-				break;
-
-			edge = list_entry(list.next, struct backref_edge,
-					  list[LOWER]);
+		while (!list_empty(&list)) {
+			edge = list_first_entry(&list, struct backref_edge,
+						list[UPPER]);
+			list_del(&edge->list[UPPER]);
 			list_del(&edge->list[LOWER]);
+			lower = edge->node[LOWER];
 			upper = edge->node[UPPER];
 			free_backref_edge(cache, edge);
+
+			/*
+			 * Lower is no longer linked to any upper backref nodes
+			 * and isn't in the cache, we can free it ourselves.
+			 */
+			if (list_empty(&lower->upper) &&
+			    RB_EMPTY_NODE(&lower->rb_node))
+				list_add(&lower->list, &useless);
+
+			if (!RB_EMPTY_NODE(&upper->rb_node))
+				continue;
+
+			/* Add this guy's upper edges to the list to proces */
+			list_for_each_entry(edge, &upper->upper, list[LOWER])
+				list_add_tail(&edge->list[UPPER], &list);
+			if (list_empty(&upper->upper))
+				list_add(&upper->list, &useless);
+		}
+
+		while (!list_empty(&useless)) {
+			lower = list_entry(useless.next,
+					   struct backref_node, list);
+			list_del_init(&lower->list);
+			free_backref_node(cache, lower);
 		}
 		return ERR_PTR(err);
 	}
-	BUG_ON(node && node->detached);
+	ASSERT(!node || !node->detached);
 	return node;
 }
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index efba5d1282ee..f6666d9b41cf 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -577,8 +577,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 
 	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
-			ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
-							&ref_root, &ref_level);
+			ret = tree_backref_for_extent(&ptr, eb, &found_key, ei,
+						      item_size, &ref_root,
+						      &ref_level);
 			printk_in_rcu(KERN_WARNING
 				"BTRFS: %s at logical %llu on dev %s, "
 				"sector %llu: metadata %s (level %d) in tree "
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 9dde9717c1b9..20d793542096 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1589,6 +1589,10 @@ static int lookup_dir_item_inode(struct btrfs_root *root,
 		goto out;
 	}
 	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+	if (key.type == BTRFS_ROOT_ITEM_KEY) {
+		ret = -ENOENT;
+		goto out;
+	}
 	*found_inode = key.objectid;
 	*found_type = btrfs_dir_type(path->nodes[0], di);
 
@@ -4724,7 +4728,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 
 	if (S_ISREG(sctx->cur_inode_mode)) {
 		if (need_send_hole(sctx)) {
-			if (sctx->cur_inode_last_extent == (u64)-1) {
+			if (sctx->cur_inode_last_extent == (u64)-1 ||
+			    sctx->cur_inode_last_extent <
+			    sctx->cur_inode_size) {
 				ret = get_last_extent(sctx, (u64)-1);
 				if (ret)
 					goto out;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 865f4cf9a769..ff286f372ff4 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -253,6 +253,7 @@ static ssize_t global_rsv_reserved_show(struct kobject *kobj,
 BTRFS_ATTR(global_rsv_reserved, 0444, global_rsv_reserved_show);
 
 #define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj)
+#define to_raid_kobj(_kobj) container_of(_kobj, struct raid_kobject, kobj)
 
 static ssize_t raid_bytes_show(struct kobject *kobj,
 			       struct kobj_attribute *attr, char *buf);
@@ -265,7 +266,7 @@ static ssize_t raid_bytes_show(struct kobject *kobj,
 {
 	struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
 	struct btrfs_block_group_cache *block_group;
-	int index = kobj - sinfo->block_group_kobjs;
+	int index = to_raid_kobj(kobj)->raid_type;
 	u64 val = 0;
 
 	down_read(&sinfo->groups_sem);
@@ -287,7 +288,7 @@ static struct attribute *raid_attributes[] = {
 
 static void release_raid_kobj(struct kobject *kobj)
 {
-	kobject_put(kobj->parent);
+	kfree(to_raid_kobj(kobj));
 }
 
 struct kobj_type btrfs_raid_ktype = {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 34cd83184c4a..a0b65a01fed7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -592,7 +592,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 		if (transid <= root->fs_info->last_trans_committed)
 			goto out;
 
-		ret = -EINVAL;
 		/* find specified transaction */
 		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry(t, &root->fs_info->trans_list, list) {
@@ -608,9 +607,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 			}
 		}
 		spin_unlock(&root->fs_info->trans_lock);
-		/* The specified transaction doesn't exist */
-		if (!cur_trans)
+
+		/*
+		 * The specified transaction doesn't exist, or we
+		 * raced with btrfs_commit_transaction
+		 */
+		if (!cur_trans) {
+			if (transid > root->fs_info->last_trans_committed)
+				ret = -EINVAL;
 			goto out;
+		}
 	} else {
 		/* find newest transaction that is committing | committed */
 		spin_lock(&root->fs_info->trans_lock);
@@ -683,7 +689,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
 
-	if (--trans->use_count) {
+	if (trans->use_count > 1) {
+		trans->use_count--;
 		trans->block_rsv = trans->orig_rsv;
 		return 0;
 	}
@@ -731,17 +738,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	}
 
 	if (lock && ACCESS_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
-		if (throttle) {
-			/*
-			 * We may race with somebody else here so end up having
-			 * to call end_transaction on ourselves again, so inc
-			 * our use_count.
-			 */
-			trans->use_count++;
+		if (throttle)
 			return btrfs_commit_transaction(trans, root);
-		} else {
+		else
 			wake_up_process(info->transaction_kthread);
-		}
 	}
 
 	if (trans->type & __TRANS_FREEZABLE)
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index 7f78cbf5cf41..4c29db604bbe 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -57,6 +57,21 @@ void ulist_free(struct ulist *ulist);
 int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask);
 int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
 		    u64 *old_aux, gfp_t gfp_mask);
+
+/* just like ulist_add_merge() but take a pointer for the aux data */
+static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux,
+				      void **old_aux, gfp_t gfp_mask)
+{
+#if BITS_PER_LONG == 32
+	u64 old64 = (uintptr_t)*old_aux;
+	int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask);
+	*old_aux = (void *)((uintptr_t)old64);
+	return ret;
+#else
+	return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask);
+#endif
+}
+
 struct ulist_node *ulist_next(struct ulist *ulist,
 			      struct ulist_iterator *uiter);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bab0b84d8f80..e46d3d72a9c9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1438,6 +1438,22 @@ out:
 	return ret;
 }
 
+/*
+ * Function to update ctime/mtime for a given device path.
+ * Mainly used for ctime/mtime based probe like libblkid.
+ */
+static void update_dev_time(char *path_name)
+{
+	struct file *filp;
+
+	filp = filp_open(path_name, O_RDWR, 0);
+	if (!filp)
+		return;
+	file_update_time(filp);
+	filp_close(filp, NULL);
+	return;
+}
+
 static int btrfs_rm_dev_item(struct btrfs_root *root,
 			     struct btrfs_device *device)
 {
@@ -1660,11 +1676,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		struct btrfs_fs_devices *fs_devices;
 		fs_devices = root->fs_info->fs_devices;
 		while (fs_devices) {
-			if (fs_devices->seed == cur_devices)
+			if (fs_devices->seed == cur_devices) {
+				fs_devices->seed = cur_devices->seed;
 				break;
+			}
 			fs_devices = fs_devices->seed;
 		}
-		fs_devices->seed = cur_devices->seed;
 		cur_devices->seed = NULL;
 		lock_chunks(root);
 		__btrfs_close_devices(cur_devices);
@@ -1690,10 +1707,14 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 
 	ret = 0;
 
-	/* Notify udev that device has changed */
-	if (bdev)
+	if (bdev) {
+		/* Notify udev that device has changed */
 		btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
+		/* Update ctime/mtime for device path for libblkid */
+		update_dev_time(device_path);
+	}
+
 error_brelse:
 	brelse(bh);
 	if (bdev)
@@ -1869,7 +1890,6 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
 	fs_devices->seeding = 0;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
-	fs_devices->total_devices = 0;
 	fs_devices->seed = seed_devices;
 
 	generate_random_uuid(fs_devices->fsid);
@@ -2132,6 +2152,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		ret = btrfs_commit_transaction(trans, root);
 	}
 
+	/* Update ctime/mtime for libblkid */
+	update_dev_time(device_path);
 	return ret;
 
 error_trans:
@@ -6035,10 +6057,14 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info)
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
 
-	mutex_lock(&fs_devices->device_list_mutex);
-	list_for_each_entry(device, &fs_devices->devices, dev_list)
-		device->dev_root = fs_info->dev_root;
-	mutex_unlock(&fs_devices->device_list_mutex);
+	while (fs_devices) {
+		mutex_lock(&fs_devices->device_list_mutex);
+		list_for_each_entry(device, &fs_devices->devices, dev_list)
+			device->dev_root = fs_info->dev_root;
+		mutex_unlock(&fs_devices->device_list_mutex);
+
+		fs_devices = fs_devices->seed;
+	}
 }
 
 static void __btrfs_reset_dev_stats(struct btrfs_device *dev)
diff --git a/fs/buffer.c b/fs/buffer.c
index 27265a8b43c1..4d06a573d199 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1029,7 +1029,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 		bh = page_buffers(page);
 		if (bh->b_size == size) {
 			end_block = init_page_buffers(page, bdev,
-						index << sizebits, size);
+						(sector_t)index << sizebits,
+						size);
 			goto done;
 		}
 		if (!try_to_free_buffers(page))
@@ -1050,7 +1051,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	 */
 	spin_lock(&inode->i_mapping->private_lock);
 	link_dev_buffers(page, bh);
-	end_block = init_page_buffers(page, bdev, index << sizebits, size);
+	end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
+			size);
 	spin_unlock(&inode->i_mapping->private_lock);
 done:
 	ret = (block < end_block) ? 1 : -ENXIO;
@@ -2075,6 +2077,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
+	loff_t old_size = inode->i_size;
 	int i_size_changed = 0;
 
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
@@ -2094,6 +2097,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
 	/*
 	 * Don't mark the inode dirty under page lock. First, it unnecessarily
 	 * makes the holding time of page lock longer. Second, it forces lock
@@ -2311,6 +2316,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		err = 0;
 
 		balance_dirty_pages_ratelimited(mapping);
+
+		if (unlikely(fatal_signal_pending(current))) {
+			err = -EINTR;
+			goto out;
+		}
 	}
 
 	/* page covers the boundary, find the boundary offset */
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b53278c9fd97..94a85ee5b990 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -676,7 +676,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	int rc = 0;
 	unsigned wsize = 1 << inode->i_blkbits;
 	struct ceph_osd_request *req = NULL;
-	int do_sync;
+	int do_sync = 0;
 	u64 truncate_size, snap_size;
 	u32 truncate_seq;
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 45eda6d7a40c..5e0982aa7000 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -446,7 +446,6 @@ more:
 	if (atomic_read(&ci->i_release_count) == fi->dir_release_count) {
 		dout(" marking %p complete\n", inode);
 		__ceph_dir_set_complete(ci, fi->dir_release_count);
-		ci->i_max_offset = ctx->pos;
 	}
 	spin_unlock(&ci->i_ceph_lock);
 
@@ -932,14 +931,16 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 * to do it here.
 		 */
 
-		/* d_move screws up d_subdirs order */
-		ceph_dir_clear_complete(new_dir);
-
 		d_move(old_dentry, new_dentry);
 
 		/* ensure target dentry is invalidated, despite
 		   rehashing bug in vfs_rename_dir */
 		ceph_invalidate_dentry_lease(new_dentry);
+
+		/* d_move screws up sibling dentries' offsets */
+		ceph_dir_clear_complete(old_dir);
+		ceph_dir_clear_complete(new_dir);
+
 	}
 	ceph_mdsc_put_request(req);
 	return err;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 32d519d8a2e2..6471f9c83428 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -752,7 +752,6 @@ static int fill_inode(struct inode *inode,
 	    !__ceph_dir_is_complete(ci)) {
 		dout(" marking %p complete (empty)\n", inode);
 		__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
-		ci->i_max_offset = 2;
 	}
 no_change:
 	spin_unlock(&ci->i_ceph_lock);
@@ -890,41 +889,6 @@ out_unlock:
 }
 
 /*
- * Set dentry's directory position based on the current dir's max, and
- * order it in d_subdirs, so that dcache_readdir behaves.
- *
- * Always called under directory's i_mutex.
- */
-static void ceph_set_dentry_offset(struct dentry *dn)
-{
-	struct dentry *dir = dn->d_parent;
-	struct inode *inode = dir->d_inode;
-	struct ceph_inode_info *ci;
-	struct ceph_dentry_info *di;
-
-	BUG_ON(!inode);
-
-	ci = ceph_inode(inode);
-	di = ceph_dentry(dn);
-
-	spin_lock(&ci->i_ceph_lock);
-	if (!__ceph_dir_is_complete(ci)) {
-		spin_unlock(&ci->i_ceph_lock);
-		return;
-	}
-	di->offset = ceph_inode(inode)->i_max_offset++;
-	spin_unlock(&ci->i_ceph_lock);
-
-	spin_lock(&dir->d_lock);
-	spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
-	list_move(&dn->d_u.d_child, &dir->d_subdirs);
-	dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
-	     dn->d_u.d_child.prev, dn->d_u.d_child.next);
-	spin_unlock(&dn->d_lock);
-	spin_unlock(&dir->d_lock);
-}
-
-/*
  * splice a dentry to an inode.
  * caller must hold directory i_mutex for this to be safe.
  *
@@ -933,7 +897,7 @@ static void ceph_set_dentry_offset(struct dentry *dn)
  * the caller) if we fail.
  */
 static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
-				    bool *prehash, bool set_offset)
+				    bool *prehash)
 {
 	struct dentry *realdn;
 
@@ -965,8 +929,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	}
 	if ((!prehash || *prehash) && d_unhashed(dn))
 		d_rehash(dn);
-	if (set_offset)
-		ceph_set_dentry_offset(dn);
 out:
 	return dn;
 }
@@ -987,7 +949,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 {
 	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
 	struct inode *in = NULL;
-	struct ceph_mds_reply_inode *ininfo;
 	struct ceph_vino vino;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 	int err = 0;
@@ -1112,6 +1073,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 
 		/* rename? */
 		if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) {
+			struct inode *olddir = req->r_old_dentry_dir;
+			BUG_ON(!olddir);
+
 			dout(" src %p '%.*s' dst %p '%.*s'\n",
 			     req->r_old_dentry,
 			     req->r_old_dentry->d_name.len,
@@ -1131,13 +1095,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			   rehashing bug in vfs_rename_dir */
 			ceph_invalidate_dentry_lease(dn);
 
-			/*
-			 * d_move() puts the renamed dentry at the end of
-			 * d_subdirs.  We need to assign it an appropriate
-			 * directory offset so we can behave when dir is
-			 * complete.
-			 */
-			ceph_set_dentry_offset(req->r_old_dentry);
+			/* d_move screws up sibling dentries' offsets */
+			ceph_dir_clear_complete(dir);
+			ceph_dir_clear_complete(olddir);
+
 			dout("dn %p gets new offset %lld\n", req->r_old_dentry,
 			     ceph_dentry(req->r_old_dentry)->offset);
 
@@ -1164,8 +1125,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 
 		/* attach proper inode */
 		if (!dn->d_inode) {
+			ceph_dir_clear_complete(dir);
 			ihold(in);
-			dn = splice_dentry(dn, in, &have_lease, true);
+			dn = splice_dentry(dn, in, &have_lease);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
@@ -1186,17 +1148,16 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		   (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
 		    req->r_op == CEPH_MDS_OP_MKSNAP)) {
 		struct dentry *dn = req->r_dentry;
+		struct inode *dir = req->r_locked_dir;
 
 		/* fill out a snapdir LOOKUPSNAP dentry */
 		BUG_ON(!dn);
-		BUG_ON(!req->r_locked_dir);
-		BUG_ON(ceph_snap(req->r_locked_dir) != CEPH_SNAPDIR);
-		ininfo = rinfo->targeti.in;
-		vino.ino = le64_to_cpu(ininfo->ino);
-		vino.snap = le64_to_cpu(ininfo->snapid);
+		BUG_ON(!dir);
+		BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR);
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
+		ceph_dir_clear_complete(dir);
 		ihold(in);
-		dn = splice_dentry(dn, in, NULL, true);
+		dn = splice_dentry(dn, in, NULL);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
@@ -1358,7 +1319,7 @@ retry_lookup:
 		}
 
 		if (!dn->d_inode) {
-			dn = splice_dentry(dn, in, NULL, false);
+			dn = splice_dentry(dn, in, NULL);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				dn = NULL;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f4f050a69a48..339c41216d14 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1461,15 +1461,18 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
 
 	dout("discard_cap_releases mds%d\n", session->s_mds);
 
-	/* zero out the in-progress message */
-	msg = list_first_entry(&session->s_cap_releases,
-			       struct ceph_msg, list_head);
-	head = msg->front.iov_base;
-	num = le32_to_cpu(head->num);
-	dout("discard_cap_releases mds%d %p %u\n", session->s_mds, msg, num);
-	head->num = cpu_to_le32(0);
-	msg->front.iov_len = sizeof(*head);
-	session->s_num_cap_releases += num;
+	if (!list_empty(&session->s_cap_releases)) {
+		/* zero out the in-progress message */
+		msg = list_first_entry(&session->s_cap_releases,
+					struct ceph_msg, list_head);
+		head = msg->front.iov_base;
+		num = le32_to_cpu(head->num);
+		dout("discard_cap_releases mds%d %p %u\n",
+		     session->s_mds, msg, num);
+		head->num = cpu_to_le32(0);
+		msg->front.iov_len = sizeof(*head);
+		session->s_num_cap_releases += num;
+	}
 
 	/* requeue completed messages */
 	while (!list_empty(&session->s_cap_releases_done)) {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d8801a95b685..df2caa84b94f 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -266,7 +266,6 @@ struct ceph_inode_info {
 	struct timespec i_rctime;
 	u64 i_rbytes, i_rfiles, i_rsubdirs;
 	u64 i_files, i_subdirs;
-	u64 i_max_offset;  /* largest readdir offset, set with complete dir */
 
 	struct rb_root i_fragtree;
 	struct mutex i_fragtree_mutex;
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 0227b45ef00a..15e9505aa35f 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -290,7 +290,8 @@ int
 cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		 const struct nls_table *cp, int mapChars)
 {
-	int i, j, charlen;
+	int i, charlen;
+	int j = 0;
 	char src_char;
 	__le16 dst_char;
 	wchar_t tmp;
@@ -298,12 +299,11 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	if (!mapChars)
 		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
 
-	for (i = 0, j = 0; i < srclen; j++) {
+	for (i = 0; i < srclen; j++) {
 		src_char = source[i];
 		charlen = 1;
 		switch (src_char) {
 		case 0:
-			put_unaligned(0, &target[j]);
 			goto ctoUTF16_out;
 		case ':':
 			dst_char = cpu_to_le16(UNI_COLON);
@@ -350,6 +350,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	}
 
 ctoUTF16_out:
+	put_unaligned(0, &target[j]); /* Null terminate target unicode string */
 	return j;
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 849f6132b327..7c6b73c72210 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -253,6 +253,11 @@ cifs_alloc_inode(struct super_block *sb)
 	cifs_set_oplock_level(cifs_inode, 0);
 	cifs_inode->delete_pending = false;
 	cifs_inode->invalid_mapping = false;
+	clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cifs_inode->flags);
+	clear_bit(CIFS_INODE_PENDING_WRITERS, &cifs_inode->flags);
+	clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cifs_inode->flags);
+	spin_lock_init(&cifs_inode->writers_lock);
+	cifs_inode->writers = 0;
 	cifs_inode->vfs_inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
 	cifs_inode->server_eof = 0;
 	cifs_inode->uniqueid = 0;
@@ -731,19 +736,26 @@ static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 				   unsigned long nr_segs, loff_t pos)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
+	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	ssize_t written;
 	int rc;
 
+	written = cifs_get_writer(cinode);
+	if (written)
+		return written;
+
 	written = generic_file_aio_write(iocb, iov, nr_segs, pos);
 
 	if (CIFS_CACHE_WRITE(CIFS_I(inode)))
-		return written;
+		goto out;
 
 	rc = filemap_fdatawrite(inode->i_mapping);
 	if (rc)
 		cifs_dbg(FYI, "cifs_file_aio_write: %d rc on %p inode\n",
 			 rc, inode);
 
+out:
+	cifs_put_writer(cinode);
 	return written;
 }
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index c0f3718b77a8..5d12d69e2045 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -70,11 +70,6 @@
 #define SERVER_NAME_LENGTH 40
 #define SERVER_NAME_LEN_WITH_NULL     (SERVER_NAME_LENGTH + 1)
 
-/* used to define string lengths for reversing unicode strings */
-/*         (256+1)*2 = 514                                     */
-/*           (max path length + 1 for null) * 2 for unicode    */
-#define MAX_NAME 514
-
 /* SMB echo "timeout" -- FIXME: tunable? */
 #define SMB_ECHO_INTERVAL (60 * HZ)
 
@@ -228,6 +223,8 @@ struct smb_version_operations {
 	/* verify the message */
 	int (*check_message)(char *, unsigned int);
 	bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+	void (*downgrade_oplock)(struct TCP_Server_Info *,
+					struct cifsInodeInfo *, bool);
 	/* process transaction2 response */
 	bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *,
 			     char *, int);
@@ -402,6 +399,8 @@ struct smb_version_operations {
 			const struct cifs_fid *, u32 *);
 	int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *,
 			int);
+	/* check if we need to issue closedir */
+	bool (*dir_needs_close)(struct cifsFileInfo *);
 };
 
 struct smb_version_values {
@@ -1113,6 +1112,12 @@ struct cifsInodeInfo {
 	unsigned int epoch;		/* used to track lease state changes */
 	bool delete_pending;		/* DELETE_ON_CLOSE is set */
 	bool invalid_mapping;		/* pagecache is invalid */
+	unsigned long flags;
+#define CIFS_INODE_PENDING_OPLOCK_BREAK   (0) /* oplock break in progress */
+#define CIFS_INODE_PENDING_WRITERS	  (1) /* Writes in progress */
+#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */
+	spinlock_t writers_lock;
+	unsigned int writers;		/* Number of writers on this inode */
 	unsigned long time;		/* jiffies of last update of inode */
 	u64  server_eof;		/* current file size on server -- protected by i_lock */
 	u64  uniqueid;			/* server inode number */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index acc4ee8ed075..ca7980a1e303 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -127,6 +127,9 @@ extern u64 cifs_UnixTimeToNT(struct timespec);
 extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
 				      int offset);
 extern void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock);
+extern int cifs_get_writer(struct cifsInodeInfo *cinode);
+extern void cifs_put_writer(struct cifsInodeInfo *cinode);
+extern void cifs_done_oplock_break(struct cifsInodeInfo *cinode);
 extern int cifs_unlock_range(struct cifsFileInfo *cfile,
 			     struct file_lock *flock, const unsigned int xid);
 extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 834fce759d80..d375322b6cec 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -762,7 +762,7 @@ int cifs_closedir(struct inode *inode, struct file *file)
 
 	cifs_dbg(FYI, "Freeing private data in close dir\n");
 	spin_lock(&cifs_file_list_lock);
-	if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) {
+	if (server->ops->dir_needs_close(cfile)) {
 		cfile->invalidHandle = true;
 		spin_unlock(&cifs_file_list_lock);
 		if (server->ops->close_dir)
@@ -2608,12 +2608,20 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	ssize_t written;
 
+	written = cifs_get_writer(cinode);
+	if (written)
+		return written;
+
 	if (CIFS_CACHE_WRITE(cinode)) {
 		if (cap_unix(tcon->ses) &&
 		(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))
-		    && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
-			return generic_file_aio_write(iocb, iov, nr_segs, pos);
-		return cifs_writev(iocb, iov, nr_segs, pos);
+		  && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
+			written = generic_file_aio_write(
+					iocb, iov, nr_segs, pos);
+			goto out;
+		}
+		written = cifs_writev(iocb, iov, nr_segs, pos);
+		goto out;
 	}
 	/*
 	 * For non-oplocked files in strict cache mode we need to write the data
@@ -2633,6 +2641,8 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
 			 inode);
 		cinode->oplock = 0;
 	}
+out:
+	cifs_put_writer(cinode);
 	return written;
 }
 
@@ -2834,7 +2844,7 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 		total_read += result;
 	}
 
-	return total_read > 0 ? total_read : result;
+	return total_read > 0 && result != -EAGAIN ? total_read : result;
 }
 
 static ssize_t
@@ -3257,7 +3267,7 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 		total_read += result;
 	}
 
-	return total_read > 0 ? total_read : result;
+	return total_read > 0 && result != -EAGAIN ? total_read : result;
 }
 
 static int cifs_readpages(struct file *file, struct address_space *mapping,
@@ -3644,6 +3654,13 @@ static int cifs_launder_page(struct page *page)
 	return rc;
 }
 
+static int
+cifs_pending_writers_wait(void *unused)
+{
+	schedule();
+	return 0;
+}
+
 void cifs_oplock_break(struct work_struct *work)
 {
 	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
@@ -3651,8 +3668,15 @@ void cifs_oplock_break(struct work_struct *work)
 	struct inode *inode = cfile->dentry->d_inode;
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
+	struct TCP_Server_Info *server = tcon->ses->server;
 	int rc = 0;
 
+	wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
+			cifs_pending_writers_wait, TASK_UNINTERRUPTIBLE);
+
+	server->ops->downgrade_oplock(server, cinode,
+		test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags));
+
 	if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) &&
 						cifs_has_mand_locks(cinode)) {
 		cifs_dbg(FYI, "Reset oplock to None for inode=%p due to mand locks\n",
@@ -3689,6 +3713,7 @@ void cifs_oplock_break(struct work_struct *work)
 							     cinode);
 		cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
 	}
+	cifs_done_oplock_break(cinode);
 }
 
 /*
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index aadc2b68678b..f2ddcf7ac9c3 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1706,13 +1706,22 @@ cifs_rename(struct inode *source_dir, struct dentry *source_dentry,
 unlink_target:
 	/* Try unlinking the target dentry if it's not negative */
 	if (target_dentry->d_inode && (rc == -EACCES || rc == -EEXIST)) {
-		tmprc = cifs_unlink(target_dir, target_dentry);
+		if (d_is_dir(target_dentry))
+			tmprc = cifs_rmdir(target_dir, target_dentry);
+		else
+			tmprc = cifs_unlink(target_dir, target_dentry);
 		if (tmprc)
 			goto cifs_rename_exit;
 		rc = cifs_do_rename(xid, source_dentry, from_name,
 				    target_dentry, to_name);
 	}
 
+	/* force revalidate to go get info when needed */
+	CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0;
+
+	source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime =
+		target_dir->i_mtime = current_fs_time(source_dir->i_sb);
+
 cifs_rename_exit:
 	kfree(info_buf_source);
 	kfree(from_name);
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 264ece71bdb2..a5c2812ead68 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -213,8 +213,12 @@ create_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		goto out;
 
-	rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, cifs_sb,
-					fromName, buf, &bytes_written);
+	if (tcon->ses->server->ops->create_mf_symlink)
+		rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon,
+					cifs_sb, fromName, buf, &bytes_written);
+	else
+		rc = -EOPNOTSUPP;
+
 	if (rc)
 		goto out;
 
@@ -374,7 +378,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	oparms.cifs_sb = cifs_sb;
 	oparms.desired_access = GENERIC_WRITE;
 	oparms.create_options = create_options;
-	oparms.disposition = FILE_OPEN;
+	oparms.disposition = FILE_CREATE;
 	oparms.path = path;
 	oparms.fid = &fid;
 	oparms.reconnect = false;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 2f9f3790679d..3b0c62e622da 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -466,8 +466,22 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
 				cifs_dbg(FYI, "file id match, oplock break\n");
 				pCifsInode = CIFS_I(netfile->dentry->d_inode);
 
-				cifs_set_oplock_level(pCifsInode,
-					pSMB->OplockLevel ? OPLOCK_READ : 0);
+				set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
+					&pCifsInode->flags);
+
+				/*
+				 * Set flag if the server downgrades the oplock
+				 * to L2 else clear.
+				 */
+				if (pSMB->OplockLevel)
+					set_bit(
+					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
+					   &pCifsInode->flags);
+				else
+					clear_bit(
+					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
+					   &pCifsInode->flags);
+
 				queue_work(cifsiod_wq,
 					   &netfile->oplock_break);
 				netfile->oplock_break_cancelled = false;
@@ -551,6 +565,62 @@ void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock)
 		cinode->oplock = 0;
 }
 
+static int
+cifs_oplock_break_wait(void *unused)
+{
+	schedule();
+	return signal_pending(current) ? -ERESTARTSYS : 0;
+}
+
+/*
+ * We wait for oplock breaks to be processed before we attempt to perform
+ * writes.
+ */
+int cifs_get_writer(struct cifsInodeInfo *cinode)
+{
+	int rc;
+
+start:
+	rc = wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK,
+				   cifs_oplock_break_wait, TASK_KILLABLE);
+	if (rc)
+		return rc;
+
+	spin_lock(&cinode->writers_lock);
+	if (!cinode->writers)
+		set_bit(CIFS_INODE_PENDING_WRITERS, &cinode->flags);
+	cinode->writers++;
+	/* Check to see if we have started servicing an oplock break */
+	if (test_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags)) {
+		cinode->writers--;
+		if (cinode->writers == 0) {
+			clear_bit(CIFS_INODE_PENDING_WRITERS, &cinode->flags);
+			wake_up_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS);
+		}
+		spin_unlock(&cinode->writers_lock);
+		goto start;
+	}
+	spin_unlock(&cinode->writers_lock);
+	return 0;
+}
+
+void cifs_put_writer(struct cifsInodeInfo *cinode)
+{
+	spin_lock(&cinode->writers_lock);
+	cinode->writers--;
+	if (cinode->writers == 0) {
+		clear_bit(CIFS_INODE_PENDING_WRITERS, &cinode->flags);
+		wake_up_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS);
+	}
+	spin_unlock(&cinode->writers_lock);
+}
+
+void cifs_done_oplock_break(struct cifsInodeInfo *cinode)
+{
+	clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags);
+	wake_up_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK);
+}
+
 bool
 backup_cred(struct cifs_sb_info *cifs_sb)
 {
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index b15862e0f68c..b334a89d6a66 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -593,11 +593,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
 		/* close and restart search */
 		cifs_dbg(FYI, "search backing up - close and restart search\n");
 		spin_lock(&cifs_file_list_lock);
-		if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) {
+		if (server->ops->dir_needs_close(cfile)) {
 			cfile->invalidHandle = true;
 			spin_unlock(&cifs_file_list_lock);
-			if (server->ops->close)
-				server->ops->close(xid, tcon, &cfile->fid);
+			if (server->ops->close_dir)
+				server->ops->close_dir(xid, tcon, &cfile->fid);
 		} else
 			spin_unlock(&cifs_file_list_lock);
 		if (cfile->srch_inf.ntwrk_buf_start) {
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 526fb89f9230..e9ad8d37bb00 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -372,6 +372,16 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)
 	return 0;
 }
 
+static void
+cifs_downgrade_oplock(struct TCP_Server_Info *server,
+			struct cifsInodeInfo *cinode, bool set_level2)
+{
+	if (set_level2)
+		cifs_set_oplock_level(cinode, OPLOCK_READ);
+	else
+		cifs_set_oplock_level(cinode, 0);
+}
+
 static bool
 cifs_check_trans2(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 		  char *buf, int malformed)
@@ -576,7 +586,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 		tmprc = CIFS_open(xid, &oparms, &oplock, NULL);
 		if (tmprc == -EOPNOTSUPP)
 			*symlink = true;
-		else
+		else if (tmprc == 0)
 			CIFSSMBClose(xid, tcon, fid.netfid);
 	}
 
@@ -999,6 +1009,12 @@ cifs_is_read_op(__u32 oplock)
 	return oplock == OPLOCK_READ;
 }
 
+static bool
+cifs_dir_needs_close(struct cifsFileInfo *cfile)
+{
+	return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
+}
+
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -1019,6 +1035,7 @@ struct smb_version_operations smb1_operations = {
 	.clear_stats = cifs_clear_stats,
 	.print_stats = cifs_print_stats,
 	.is_oplock_break = is_valid_oplock_break,
+	.downgrade_oplock = cifs_downgrade_oplock,
 	.check_trans2 = cifs_check_trans2,
 	.need_neg = cifs_need_neg,
 	.negotiate = cifs_negotiate,
@@ -1067,6 +1084,7 @@ struct smb_version_operations smb1_operations = {
 	.query_mf_symlink = cifs_query_mf_symlink,
 	.create_mf_symlink = cifs_create_mf_symlink,
 	.is_read_op = cifs_is_read_op,
+	.dir_needs_close = cifs_dir_needs_close,
 #ifdef CONFIG_CIFS_XATTR
 	.query_all_EAs = CIFSSMBQAllEAs,
 	.set_EA = CIFSSMBSetEA,
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 3f17b4550831..45992944e238 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -50,7 +50,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 		goto out;
 	}
 
-	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			    GFP_KERNEL);
 	if (smb2_data == NULL) {
 		rc = -ENOMEM;
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 84c012a6aba0..215f8d3e3e53 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -131,7 +131,7 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 	*adjust_tz = false;
 	*symlink = false;
 
-	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			    GFP_KERNEL);
 	if (smb2_data == NULL)
 		return -ENOMEM;
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 94bd4fbb13d3..a491814cb2c0 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -214,7 +214,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"},
 	{STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"},
 	{STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"},
-	{STATUS_NO_MORE_FILES, -EIO, "STATUS_NO_MORE_FILES"},
+	{STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"},
 	{STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"},
 	{STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"},
 	{STATUS_NO_INHERITANCE, -EIO, "STATUS_NO_INHERITANCE"},
@@ -256,6 +256,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_DLL_MIGHT_BE_INCOMPATIBLE, -EIO,
 	"STATUS_DLL_MIGHT_BE_INCOMPATIBLE"},
 	{STATUS_STOPPED_ON_SYMLINK, -EOPNOTSUPP, "STATUS_STOPPED_ON_SYMLINK"},
+	{STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EOPNOTSUPP,
+	"STATUS_REPARSE_NOT_HANDLED"},
 	{STATUS_DEVICE_REQUIRES_CLEANING, -EIO,
 	"STATUS_DEVICE_REQUIRES_CLEANING"},
 	{STATUS_DEVICE_DOOR_OPEN, -EIO, "STATUS_DEVICE_DOOR_OPEN"},
@@ -605,7 +607,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_MAPPED_FILE_SIZE_ZERO, -EIO, "STATUS_MAPPED_FILE_SIZE_ZERO"},
 	{STATUS_TOO_MANY_OPENED_FILES, -EMFILE, "STATUS_TOO_MANY_OPENED_FILES"},
 	{STATUS_CANCELLED, -EIO, "STATUS_CANCELLED"},
-	{STATUS_CANNOT_DELETE, -EIO, "STATUS_CANNOT_DELETE"},
+	{STATUS_CANNOT_DELETE, -EACCES, "STATUS_CANNOT_DELETE"},
 	{STATUS_INVALID_COMPUTER_NAME, -EIO, "STATUS_INVALID_COMPUTER_NAME"},
 	{STATUS_FILE_DELETED, -EIO, "STATUS_FILE_DELETED"},
 	{STATUS_SPECIAL_ACCOUNT, -EIO, "STATUS_SPECIAL_ACCOUNT"},
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index fb3966265b6e..b8021fde987d 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -575,9 +575,21 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 				else
 					cfile->oplock_break_cancelled = false;
 
-				server->ops->set_oplock_level(cinode,
-				  rsp->OplockLevel ? SMB2_OPLOCK_LEVEL_II : 0,
-				  0, NULL);
+				set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK,
+					&cinode->flags);
+
+				/*
+				 * Set flag if the server downgrades the oplock
+				 * to L2 else clear.
+				 */
+				if (rsp->OplockLevel)
+					set_bit(
+					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
+					   &cinode->flags);
+				else
+					clear_bit(
+					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
+					   &cinode->flags);
 
 				queue_work(cifsiod_wq, &cfile->oplock_break);
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 192f51a12cf1..34a17d425be6 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -339,7 +339,7 @@ smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc;
 	struct smb2_file_all_info *smb2_data;
 
-	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+	smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			    GFP_KERNEL);
 	if (smb2_data == NULL)
 		return -ENOMEM;
@@ -905,6 +905,17 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 }
 
 static void
+smb2_downgrade_oplock(struct TCP_Server_Info *server,
+			struct cifsInodeInfo *cinode, bool set_level2)
+{
+	if (set_level2)
+		server->ops->set_oplock_level(cinode, SMB2_OPLOCK_LEVEL_II,
+						0, NULL);
+	else
+		server->ops->set_oplock_level(cinode, 0, 0, NULL);
+}
+
+static void
 smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
 		      unsigned int epoch, bool *purge_cache)
 {
@@ -1091,6 +1102,12 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch)
 	return le32_to_cpu(lc->lcontext.LeaseState);
 }
 
+static bool
+smb2_dir_needs_close(struct cifsFileInfo *cfile)
+{
+	return !cfile->invalidHandle;
+}
+
 struct smb_version_operations smb20_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -1110,6 +1127,7 @@ struct smb_version_operations smb20_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
 	.negotiate_wsize = smb2_negotiate_wsize,
@@ -1163,6 +1181,7 @@ struct smb_version_operations smb20_operations = {
 	.create_lease_buf = smb2_create_lease_buf,
 	.parse_lease_buf = smb2_parse_lease_buf,
 	.clone_range = smb2_clone_range,
+	.dir_needs_close = smb2_dir_needs_close,
 };
 
 struct smb_version_operations smb21_operations = {
@@ -1184,6 +1203,7 @@ struct smb_version_operations smb21_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
 	.negotiate_wsize = smb2_negotiate_wsize,
@@ -1237,6 +1257,7 @@ struct smb_version_operations smb21_operations = {
 	.create_lease_buf = smb2_create_lease_buf,
 	.parse_lease_buf = smb2_parse_lease_buf,
 	.clone_range = smb2_clone_range,
+	.dir_needs_close = smb2_dir_needs_close,
 };
 
 struct smb_version_operations smb30_operations = {
@@ -1259,6 +1280,7 @@ struct smb_version_operations smb30_operations = {
 	.print_stats = smb2_print_stats,
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
 	.negotiate_wsize = smb2_negotiate_wsize,
@@ -1314,6 +1336,7 @@ struct smb_version_operations smb30_operations = {
 	.parse_lease_buf = smb3_parse_lease_buf,
 	.clone_range = smb2_clone_range,
 	.validate_negotiate = smb3_validate_negotiate,
+	.dir_needs_close = smb2_dir_needs_close,
 };
 
 struct smb_version_values smb20_values = {
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 860344701067..348792911e1f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -916,7 +916,8 @@ tcon_exit:
 tcon_error_exit:
 	if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
-		tcon->bad_network_name = true;
+		if (tcon)
+			tcon->bad_network_name = true;
 	}
 	goto tcon_exit;
 }
@@ -1089,6 +1090,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	int rc = 0;
 	unsigned int num_iovecs = 2;
 	__u32 file_attributes = 0;
+	char *dhc_buf = NULL, *lc_buf = NULL;
 
 	cifs_dbg(FYI, "create/open\n");
 
@@ -1155,6 +1157,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			kfree(copy_path);
 			return rc;
 		}
+		lc_buf = iov[num_iovecs-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
@@ -1169,9 +1172,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		if (rc) {
 			cifs_small_buf_release(req);
 			kfree(copy_path);
-			kfree(iov[num_iovecs-1].iov_base);
+			kfree(lc_buf);
 			return rc;
 		}
+		dhc_buf = iov[num_iovecs-1].iov_base;
 	}
 
 	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
@@ -1203,6 +1207,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		*oplock = rsp->OplockLevel;
 creat_exit:
 	kfree(copy_path);
+	kfree(lc_buf);
+	kfree(dhc_buf);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -1534,7 +1540,7 @@ SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
 			  FILE_ALL_INFORMATION,
-			  sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+			  sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
 			  sizeof(struct smb2_file_all_info), data);
 }
 
@@ -2130,6 +2136,10 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base;
 
 	if (rc) {
+		if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) {
+			srch_inf->endOfSearch = true;
+			rc = 0;
+		}
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
 		goto qdir_exit;
 	}
@@ -2167,11 +2177,6 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	else
 		cifs_dbg(VFS, "illegal search buffer type\n");
 
-	if (rsp->hdr.Status == STATUS_NO_MORE_FILES)
-		srch_inf->endOfSearch = 1;
-	else
-		srch_inf->endOfSearch = 0;
-
 	return rc;
 
 qdir_exit:
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index a81147e2e4ef..4d24d17bcfc1 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -88,6 +88,11 @@ static void cputime_to_compat_timeval(const cputime_t cputime,
 #define	ELF_HWCAP		COMPAT_ELF_HWCAP
 #endif
 
+#ifdef	COMPAT_ELF_HWCAP2
+#undef	ELF_HWCAP2
+#define	ELF_HWCAP2		COMPAT_ELF_HWCAP2
+#endif
+
 #ifdef	COMPAT_ARCH_DLINFO
 #undef	ARCH_DLINFO
 #define	ARCH_DLINFO		COMPAT_ARCH_DLINFO
diff --git a/fs/coredump.c b/fs/coredump.c
index e3ad709a4232..a93f7e6ea4cf 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -73,10 +73,15 @@ static int expand_corename(struct core_name *cn, int size)
 static int cn_vprintf(struct core_name *cn, const char *fmt, va_list arg)
 {
 	int free, need;
+	va_list arg_copy;
 
 again:
 	free = cn->size - cn->used;
-	need = vsnprintf(cn->corename + cn->used, free, fmt, arg);
+
+	va_copy(arg_copy, arg);
+	need = vsnprintf(cn->corename + cn->used, free, fmt, arg_copy);
+	va_end(arg_copy);
+
 	if (need < free) {
 		cn->used += need;
 		return 0;
@@ -301,7 +306,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 	if (unlikely(nr < 0))
 		return nr;
 
-	tsk->flags = PF_DUMPCORE;
+	tsk->flags |= PF_DUMPCORE;
 	if (atomic_read(&mm->mm_users) == nr + 1)
 		goto done;
 	/*
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 06610cf94d57..a1f801c14fbc 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 		struct page *page = NULL;
 
 		if (blocknr + i < devsize) {
-			page = read_mapping_page_async(mapping, blocknr + i,
-									NULL);
+			page = read_mapping_page(mapping, blocknr + i, NULL);
 			/* synchronous error? */
 			if (IS_ERR(page))
 				page = NULL;
diff --git a/fs/dcache.c b/fs/dcache.c
index ca02c13a84aa..436612777203 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -106,8 +106,7 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
 					unsigned int hash)
 {
 	hash += (unsigned long) parent / L1_CACHE_BYTES;
-	hash = hash + (hash >> d_hash_shift);
-	return dentry_hashtable + (hash & d_hash_mask);
+	return dentry_hashtable + hash_32(hash, d_hash_shift);
 }
 
 /* Statistics gathering. */
@@ -1647,8 +1646,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 	unsigned add_flags = d_flags_for_inode(inode);
 
 	spin_lock(&dentry->d_lock);
-	dentry->d_flags &= ~DCACHE_ENTRY_TYPE;
-	dentry->d_flags |= add_flags;
+	__d_set_type(dentry, add_flags);
 	if (inode)
 		hlist_add_head(&dentry->d_alias, &inode->i_dentry);
 	dentry->d_inode = inode;
@@ -2826,6 +2824,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen)
  * the beginning of the name. The sequence number check at the caller will
  * retry it again when a d_move() does happen. So any garbage in the buffer
  * due to mismatched pointer and length will be discarded.
+ *
+ * Data dependency barrier is needed to make sure that we see that terminating
+ * NUL.  Alpha strikes again, film at 11...
  */
 static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 {
@@ -2833,6 +2834,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 	u32 dlen = ACCESS_ONCE(name->len);
 	char *p;
 
+	smp_read_barrier_depends();
+
 	*buflen -= dlen + 1;
 	if (*buflen < 0)
 		return -ENAMETOOLONG;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 9c0444cccbe1..15761957cc3f 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -533,7 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
  */
 void debugfs_remove_recursive(struct dentry *dentry)
 {
-	struct dentry *child, *next, *parent;
+	struct dentry *child, *parent;
 
 	if (IS_ERR_OR_NULL(dentry))
 		return;
@@ -545,30 +545,49 @@ void debugfs_remove_recursive(struct dentry *dentry)
 	parent = dentry;
  down:
 	mutex_lock(&parent->d_inode->i_mutex);
-	list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) {
+ loop:
+	/*
+	 * The parent->d_subdirs is protected by the d_lock. Outside that
+	 * lock, the child can be unlinked and set to be freed which can
+	 * use the d_u.d_child as the rcu head and corrupt this list.
+	 */
+	spin_lock(&parent->d_lock);
+	list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) {
 		if (!debugfs_positive(child))
 			continue;
 
 		/* perhaps simple_empty(child) makes more sense */
 		if (!list_empty(&child->d_subdirs)) {
+			spin_unlock(&parent->d_lock);
 			mutex_unlock(&parent->d_inode->i_mutex);
 			parent = child;
 			goto down;
 		}
- up:
+
+		spin_unlock(&parent->d_lock);
+
 		if (!__debugfs_remove(child, parent))
 			simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+
+		/*
+		 * The parent->d_lock protects agaist child from unlinking
+		 * from d_subdirs. When releasing the parent->d_lock we can
+		 * no longer trust that the next pointer is valid.
+		 * Restart the loop. We'll skip this one with the
+		 * debugfs_positive() check.
+		 */
+		goto loop;
 	}
+	spin_unlock(&parent->d_lock);
 
 	mutex_unlock(&parent->d_inode->i_mutex);
 	child = parent;
 	parent = parent->d_parent;
 	mutex_lock(&parent->d_inode->i_mutex);
 
-	if (child != dentry) {
-		next = list_next_entry(child, d_u.d_child);
-		goto up;
-	}
+	if (child != dentry)
+		/* go up */
+		goto loop;
 
 	if (!__debugfs_remove(child, parent))
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 2f6735dbf1a9..31b148f3e772 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1917,7 +1917,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size,
 			break;
 		case 2:
 			dst[dst_byte_offset++] |= (src_byte);
-			dst[dst_byte_offset] = 0;
 			current_bit_offset = 0;
 			break;
 		}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index b1eaa7a1f82c..03df50211c48 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -191,23 +191,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 {
 	int rc = 0;
 	struct ecryptfs_crypt_stat *crypt_stat = NULL;
-	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct dentry *ecryptfs_dentry = file->f_path.dentry;
 	/* Private value of ecryptfs_dentry allocated in
 	 * ecryptfs_lookup() */
 	struct ecryptfs_file_info *file_info;
 
-	mount_crypt_stat = &ecryptfs_superblock_to_private(
-		ecryptfs_dentry->d_sb)->mount_crypt_stat;
-	if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
-	    && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
-		|| (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
-		|| (file->f_flags & O_APPEND))) {
-		printk(KERN_WARNING "Mount has encrypted view enabled; "
-		       "files may only be read\n");
-		rc = -EPERM;
-		goto out;
-	}
 	/* Released in ecryptfs_release or end of function if failure */
 	file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
 	ecryptfs_set_file_private(file, file_info);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index b167ca48b8ee..a85ceb7c91bc 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1039,7 +1039,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	}
 
 	rc = vfs_setxattr(lower_dentry, name, value, size, flags);
-	if (!rc)
+	if (!rc && dentry->d_inode)
 		fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
 out:
 	return rc;
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 1b119d3bf924..34eb8433d93f 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -493,6 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 {
 	struct super_block *s;
 	struct ecryptfs_sb_info *sbi;
+	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct ecryptfs_dentry_info *root_info;
 	const char *err = "Getting sb failed";
 	struct inode *inode;
@@ -511,6 +512,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		err = "Error parsing options";
 		goto out;
 	}
+	mount_crypt_stat = &sbi->mount_crypt_stat;
 
 	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s)) {
@@ -557,11 +559,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 
 	/**
 	 * Set the POSIX ACL flag based on whether they're enabled in the lower
-	 * mount. Force a read-only eCryptfs mount if the lower mount is ro.
-	 * Allow a ro eCryptfs mount even when the lower mount is rw.
+	 * mount.
 	 */
 	s->s_flags = flags & ~MS_POSIXACL;
-	s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+	s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
+
+	/**
+	 * Force a read-only eCryptfs mount when:
+	 *   1) The lower mount is ro
+	 *   2) The ecryptfs_encrypted_view mount option is specified
+	 */
+	if (path.dentry->d_sb->s_flags & MS_RDONLY ||
+	    mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+		s->s_flags |= MS_RDONLY;
 
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index af903128891c..f50d79eb52db 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -910,7 +910,7 @@ static const struct file_operations eventpoll_fops = {
 void eventpoll_release_file(struct file *file)
 {
 	struct eventpoll *ep;
-	struct epitem *epi;
+	struct epitem *epi, *next;
 
 	/*
 	 * We don't want to get "file->f_lock" because it is not
@@ -926,7 +926,7 @@ void eventpoll_release_file(struct file *file)
 	 * Besides, ep_remove() acquires the lock, so we can't hold it here.
 	 */
 	mutex_lock(&epmutex);
-	list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
+	list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
 		ep = epi->ep;
 		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
@@ -1852,7 +1852,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */
-	ep_take_care_of_epollwakeup(&epds);
+	if (ep_op_has_event(op))
+		ep_take_care_of_epollwakeup(&epds);
 
 	/*
 	 * We have to check that the file structure underneath the file descriptor
diff --git a/fs/exec.c b/fs/exec.c
index 3d78fccdd723..ea4449d0536a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/swap.h>
@@ -654,10 +655,10 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	unsigned long rlim_stack;
 
 #ifdef CONFIG_STACK_GROWSUP
-	/* Limit stack size to 1GB */
+	/* Limit stack size */
 	stack_base = rlimit_max(RLIMIT_STACK);
-	if (stack_base > (1 << 30))
-		stack_base = 1 << 30;
+	if (stack_base > STACK_SIZE_MAX)
+		stack_base = STACK_SIZE_MAX;
 
 	/* Make sure we didn't let the argument array grow too large. */
 	if (vma->vm_end - vma->vm_start > stack_base)
@@ -820,7 +821,7 @@ EXPORT_SYMBOL(read_code);
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
-	struct mm_struct * old_mm, *active_mm;
+	struct mm_struct *old_mm, *active_mm;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
@@ -846,6 +847,8 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
+	tsk->mm->vmacache_seqnum = 0;
+	vmacache_flush(tsk);
 	task_unlock(tsk);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 37fd31ed16e7..0498390f309e 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1354,13 +1354,6 @@ set_qf_format:
 					"not specified.");
 			return 0;
 		}
-	} else {
-		if (sbi->s_jquota_fmt) {
-			ext3_msg(sb, KERN_ERR, "error: journaled quota format "
-					"specified with no journaling "
-					"enabled.");
-			return 0;
-		}
 	}
 #endif
 	return 1;
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index 3285aa5a706a..b610779a958c 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -24,8 +24,7 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 	__u32 provided, calculated;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo);
@@ -46,8 +45,7 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 	__u32 csum;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
@@ -65,8 +63,7 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo);
@@ -91,8 +88,7 @@ void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 	__u32 csum;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index d3a534fdc5ff..2a6830a7af33 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2110,6 +2110,7 @@ int do_journal_get_write_access(handle_t *handle,
 #define CONVERT_INLINE_DATA	 2
 
 extern struct inode *ext4_iget(struct super_block *, unsigned long);
+extern struct inode *ext4_iget_normal(struct super_block *, unsigned long);
 extern int  ext4_write_inode(struct inode *, struct writeback_control *);
 extern int  ext4_setattr(struct dentry *, struct iattr *);
 extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -2340,10 +2341,18 @@ extern int ext4_register_li_request(struct super_block *sb,
 static inline int ext4_has_group_desc_csum(struct super_block *sb)
 {
 	return EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					  EXT4_FEATURE_RO_COMPAT_GDT_CSUM |
-					  EXT4_FEATURE_RO_COMPAT_METADATA_CSUM);
+					  EXT4_FEATURE_RO_COMPAT_GDT_CSUM) ||
+	       (EXT4_SB(sb)->s_chksum_driver != NULL);
 }
 
+static inline int ext4_has_metadata_csum(struct super_block *sb)
+{
+	WARN_ON_ONCE(EXT4_HAS_RO_COMPAT_FEATURE(sb,
+			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+		     !EXT4_SB(sb)->s_chksum_driver);
+
+	return (EXT4_SB(sb)->s_chksum_driver != NULL);
+}
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
 	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
@@ -2462,23 +2471,6 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
 	up_write(&EXT4_I(inode)->i_data_sem);
 }
 
-/*
- * Update i_disksize after writeback has been started. Races with truncate
- * are avoided by checking i_size under i_data_sem.
- */
-static inline void ext4_wb_update_i_disksize(struct inode *inode, loff_t newsize)
-{
-	loff_t i_size;
-
-	down_write(&EXT4_I(inode)->i_data_sem);
-	i_size = i_size_read(inode);
-	if (newsize > i_size)
-		newsize = i_size;
-	if (newsize > EXT4_I(inode)->i_disksize)
-		EXT4_I(inode)->i_disksize = newsize;
-	up_write(&EXT4_I(inode)->i_data_sem);
-}
-
 struct ext4_group_info {
 	unsigned long   bb_state;
 	struct rb_root  bb_free_root;
@@ -2781,7 +2773,8 @@ extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
 			       int len,
-			       struct writeback_control *wbc);
+			       struct writeback_control *wbc,
+			       bool keep_towrite);
 
 /* mmp.c */
 extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74bc2d549c58..96a1ce159f51 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -74,8 +74,7 @@ static int ext4_extent_block_csum_verify(struct inode *inode,
 {
 	struct ext4_extent_tail *et;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	et = find_ext4_extent_tail(eh);
@@ -89,8 +88,7 @@ static void ext4_extent_block_csum_set(struct inode *inode,
 {
 	struct ext4_extent_tail *et;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	et = find_ext4_extent_tail(eh);
@@ -2585,6 +2583,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	ex_ee_block = le32_to_cpu(ex->ee_block);
 	ex_ee_len = ext4_ext_get_actual_len(ex);
 
+	/*
+	 * If we're starting with an extent other than the last one in the
+	 * node, we need to see if it shares a cluster with the extent to
+	 * the right (towards the end of the file). If its leftmost cluster
+	 * is this extent's rightmost cluster and it is not cluster aligned,
+	 * we'll mark it as a partial that is not to be deallocated.
+	 */
+
+	if (ex != EXT_LAST_EXTENT(eh)) {
+		ext4_fsblk_t current_pblk, right_pblk;
+		long long current_cluster, right_cluster;
+
+		current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+		current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+		right_pblk = ext4_ext_pblock(ex + 1);
+		right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+		if (current_cluster == right_cluster &&
+			EXT4_PBLK_COFF(sbi, right_pblk))
+			*partial_cluster = -right_cluster;
+	}
+
 	trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
 
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
@@ -2710,10 +2729,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 		err = ext4_ext_correct_indexes(handle, inode, path);
 
 	/*
-	 * Free the partial cluster only if the current extent does not
-	 * reference it. Otherwise we might free used cluster.
+	 * If there's a partial cluster and at least one extent remains in
+	 * the leaf, free the partial cluster if it isn't shared with the
+	 * current extent.  If there's a partial cluster and no extents
+	 * remain in the leaf, it can't be freed here.  It can only be
+	 * freed when it's possible to determine if it's not shared with
+	 * any other extent - when the next leaf is processed or when space
+	 * removal is complete.
 	 */
-	if (*partial_cluster > 0 &&
+	if (*partial_cluster > 0 && eh->eh_entries &&
 	    (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
 	     *partial_cluster)) {
 		int flags = get_default_free_blocks_flags(inode);
@@ -4128,7 +4152,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	struct ext4_extent newex, *ex, *ex2;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	ext4_fsblk_t newblock = 0;
-	int free_on_err = 0, err = 0, depth;
+	int free_on_err = 0, err = 0, depth, ret;
 	unsigned int allocated = 0, offset = 0;
 	unsigned int allocated_clusters = 0;
 	struct ext4_allocation_request ar;
@@ -4189,9 +4213,13 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			if (!ext4_ext_is_uninitialized(ex))
 				goto out;
 
-			allocated = ext4_ext_handle_uninitialized_extents(
+			ret = ext4_ext_handle_uninitialized_extents(
 				handle, inode, map, path, flags,
 				allocated, newblock);
+			if (ret < 0)
+				err = ret;
+			else
+				allocated = ret;
 			goto out3;
 		}
 	}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 3981ff783950..171b9fa0f27a 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -962,10 +962,10 @@ retry:
 			continue;
 		}
 
-		if (ei->i_es_lru_nr == 0 || ei == locked_ei)
+		if (ei->i_es_lru_nr == 0 || ei == locked_ei ||
+		    !write_trylock(&ei->i_es_lock))
 			continue;
 
-		write_lock(&ei->i_es_lock);
 		shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
 		if (ei->i_es_lru_nr == 0)
 			list_del_init(&ei->i_es_lru);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1a5073959f32..2a8b2e15dcc4 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -82,7 +82,7 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
 	size_t count = iov_length(iov, nr_segs);
 	loff_t final_size = pos + count;
 
-	if (pos >= inode->i_size)
+	if (pos >= i_size_read(inode))
 		return 0;
 
 	if ((pos & blockmask) || (final_size & blockmask))
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 0ee59a6644e2..a8d1a64d8cb0 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -851,12 +851,23 @@ got:
 		goto out;
 	}
 
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (ext4_has_group_desc_csum(sb) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		struct buffer_head *block_bitmap_bh;
 
 		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (!block_bitmap_bh) {
+			err = -EIO;
+			goto out;
+		}
 		BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
 		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
 		if (err) {
@@ -887,13 +898,6 @@ got:
 		}
 	}
 
-	BUFFER_TRACE(group_desc_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, group_desc_bh);
-	if (err) {
-		ext4_std_error(sb, err);
-		goto out;
-	}
-
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
@@ -988,8 +992,7 @@ got:
 	spin_unlock(&sbi->s_next_gen_lock);
 
 	/* Precompute checksum seed for inode metadata */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+	if (ext4_has_metadata_csum(sb)) {
 		__u32 csum;
 		__le32 inum = cpu_to_le32(inode->i_ino);
 		__le32 gen = cpu_to_le32(inode->i_generation);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 594009f5f523..e6574d7b6642 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -389,7 +389,13 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 	return 0;
 failed:
 	for (; i >= 0; i--) {
-		if (i != indirect_blks && branch[i].bh)
+		/*
+		 * We want to ext4_forget() only freshly allocated indirect
+		 * blocks.  Buffer for new_blocks[i-1] is at branch[i].bh and
+		 * buffer at branch[0].bh is indirect block / inode already
+		 * existing before ext4_alloc_branch() was called.
+		 */
+		if (i > 0 && i != indirect_blks && branch[i].bh)
 			ext4_forget(handle, 1, inode, branch[i].bh,
 				    branch[i].bh->b_blocknr);
 		ext4_free_blocks(handle, inode, NULL, new_blocks[i],
@@ -1312,16 +1318,24 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode,
 		blk = *i_data;
 		if (level > 0) {
 			ext4_lblk_t first2;
+			ext4_lblk_t count2;
+
 			bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
 			if (!bh) {
 				EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
 						       "Read failure");
 				return -EIO;
 			}
-			first2 = (first > offset) ? first - offset : 0;
+			if (first > offset) {
+				first2 = first - offset;
+				count2 = count;
+			} else {
+				first2 = 0;
+				count2 = count - (offset - first);
+			}
 			ret = free_hole_blocks(handle, inode, bh,
 					       (__le32 *)bh->b_data, level - 1,
-					       first2, count - offset,
+					       first2, count2,
 					       inode->i_sb->s_blocksize >> 2);
 			if (ret) {
 				brelse(bh);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 82edf5b93352..8c03b747021b 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1128,8 +1128,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 	memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE,
 		inline_size - EXT4_INLINE_DOTDOT_SIZE);
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	inode->i_size = inode->i_sb->s_blocksize;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 24bfd7ff3049..3a7e0341447f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -83,8 +83,7 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
 
 	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
 	    cpu_to_le32(EXT4_OS_LINUX) ||
-	    !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	    !ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	provided = le16_to_cpu(raw->i_checksum_lo);
@@ -105,8 +104,7 @@ static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
 
 	if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
 	    cpu_to_le32(EXT4_OS_LINUX) ||
-	    !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	    !ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	csum = ext4_inode_csum(inode, raw, ei);
@@ -515,6 +513,10 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
 		  (unsigned long) map->m_lblk);
 
+	/* We can handle the block number less than EXT_MAX_BLOCKS */
+	if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS))
+		return -EIO;
+
 	/* Lookup extent status tree firstly */
 	if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
 		ext4_es_lru_add(inode);
@@ -1831,6 +1833,7 @@ static int ext4_writepage(struct page *page,
 	struct buffer_head *page_bufs = NULL;
 	struct inode *inode = page->mapping->host;
 	struct ext4_io_submit io_submit;
+	bool keep_towrite = false;
 
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
@@ -1861,6 +1864,7 @@ static int ext4_writepage(struct page *page,
 			unlock_page(page);
 			return 0;
 		}
+		keep_towrite = true;
 	}
 
 	if (PageChecked(page) && ext4_should_journal_data(inode))
@@ -1877,7 +1881,7 @@ static int ext4_writepage(struct page *page,
 		unlock_page(page);
 		return -ENOMEM;
 	}
-	ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+	ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
 	ext4_io_submit(&io_submit);
 	/* Drop io_end reference we got from init */
 	ext4_put_io_end_defer(io_submit.io_end);
@@ -1896,7 +1900,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 	else
 		len = PAGE_CACHE_SIZE;
 	clear_page_dirty_for_io(page);
-	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
 	if (!err)
 		mpd->wbc->nr_to_write--;
 	mpd->first_page++;
@@ -2189,6 +2193,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 	struct ext4_map_blocks *map = &mpd->map;
 	int err;
 	loff_t disksize;
+	int progress = 0;
 
 	mpd->io_submit.io_end->offset =
 				((loff_t)map->m_lblk) << inode->i_blkbits;
@@ -2205,8 +2210,11 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			 * is non-zero, a commit should free up blocks.
 			 */
 			if ((err == -ENOMEM) ||
-			    (err == -ENOSPC && ext4_count_free_clusters(sb)))
+			    (err == -ENOSPC && ext4_count_free_clusters(sb))) {
+				if (progress)
+					goto update_disksize;
 				return err;
+			}
 			ext4_msg(sb, KERN_CRIT,
 				 "Delayed block allocation failed for "
 				 "inode %lu at logical offset %llu with"
@@ -2223,22 +2231,34 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			*give_up_on_write = true;
 			return err;
 		}
+		progress = 1;
 		/*
 		 * Update buffer state, submit mapped pages, and get us new
 		 * extent to map
 		 */
 		err = mpage_map_and_submit_buffers(mpd);
 		if (err < 0)
-			return err;
+			goto update_disksize;
 	} while (map->m_len);
 
-	/* Update on-disk size after IO is submitted */
+update_disksize:
+	/*
+	 * Update on-disk size after IO is submitted.  Races with
+	 * truncate are avoided by checking i_size under i_data_sem.
+	 */
 	disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
 	if (disksize > EXT4_I(inode)->i_disksize) {
 		int err2;
-
-		ext4_wb_update_i_disksize(inode, disksize);
+		loff_t i_size;
+
+		down_write(&EXT4_I(inode)->i_data_sem);
+		i_size = i_size_read(inode);
+		if (disksize > i_size)
+			disksize = i_size;
+		if (disksize > EXT4_I(inode)->i_disksize)
+			EXT4_I(inode)->i_disksize = disksize;
 		err2 = ext4_mark_inode_dirty(handle, inode);
+		up_write(&EXT4_I(inode)->i_data_sem);
 		if (err2)
 			ext4_error(inode->i_sb,
 				   "Failed to mark inode %lu dirty",
@@ -2611,6 +2631,20 @@ static int ext4_nonda_switch(struct super_block *sb)
 	return 0;
 }
 
+/* We always reserve for an inode update; the superblock could be there too */
+static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len)
+{
+	if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+				EXT4_FEATURE_RO_COMPAT_LARGE_FILE)))
+		return 1;
+
+	if (pos + len <= 0x7fffffffULL)
+		return 1;
+
+	/* We might need to update the superblock to set LARGE_FILE */
+	return 2;
+}
+
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			       loff_t pos, unsigned len, unsigned flags,
 			       struct page **pagep, void **fsdata)
@@ -2661,7 +2695,8 @@ retry_grab:
 	 * of file which has an already mapped buffer.
 	 */
 retry_journal:
-	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1);
+	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+				ext4_da_write_credits(inode, pos, len));
 	if (IS_ERR(handle)) {
 		page_cache_release(page);
 		return PTR_ERR(handle);
@@ -4039,8 +4074,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ei->i_extra_isize = 0;
 
 	/* Precompute checksum seed for inode metadata */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+	if (ext4_has_metadata_csum(sb)) {
 		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 		__u32 csum;
 		__le32 inum = cpu_to_le32(inode->i_ino);
@@ -4228,6 +4262,13 @@ bad_inode:
 	return ERR_PTR(ret);
 }
 
+struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino)
+{
+	if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
+		return ERR_PTR(-EIO);
+	return ext4_iget(sb, ino);
+}
+
 static int ext4_inode_blocks_set(handle_t *handle,
 				struct ext4_inode *raw_inode,
 				struct ext4_inode_info *ei)
@@ -4623,8 +4664,12 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				ext4_orphan_del(NULL, inode);
 				goto err_out;
 			}
-		} else
+		} else {
+			loff_t oldsize = inode->i_size;
+
 			i_size_write(inode, attr->ia_size);
+			pagecache_isize_extended(inode, oldsize, inode->i_size);
+		}
 
 		/*
 		 * Blocks are going to be removed from the inode. Wait
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index a2a837f00407..dfe982dee0b3 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -343,8 +343,7 @@ flags_out:
 		if (!inode_owner_or_capable(inode))
 			return -EPERM;
 
-		if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+		if (ext4_has_metadata_csum(inode->i_sb)) {
 			ext4_warning(sb, "Setting inode version is not "
 				     "supported with metadata_csum enabled.");
 			return -ENOTTY;
@@ -544,9 +543,17 @@ group_add_out:
 	}
 
 	case EXT4_IOC_SWAP_BOOT:
+	{
+		int err;
 		if (!(filp->f_mode & FMODE_WRITE))
 			return -EBADF;
-		return swap_inode_boot_loader(sb, inode);
+		err = mnt_want_write_file(filp);
+		if (err)
+			return err;
+		err = swap_inode_boot_loader(sb, inode);
+		mnt_drop_write_file(filp);
+		return err;
+	}
 
 	case EXT4_IOC_RESIZE_FS: {
 		ext4_fsblk_t n_blocks_count;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 04a5c7504be9..242226a87be7 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -751,8 +751,8 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 
 	if (free != grp->bb_free) {
 		ext4_grp_locked_error(sb, group, 0, 0,
-				      "%u clusters in bitmap, %u in gd; "
-				      "block bitmap corrupt.",
+				      "block bitmap and bg descriptor "
+				      "inconsistent: %u vs %u free clusters",
 				      free, grp->bb_free);
 		/*
 		 * If we intend to continue, we consider group descriptor
@@ -1398,6 +1398,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	int last = first + count - 1;
 	struct super_block *sb = e4b->bd_sb;
 
+	if (WARN_ON(count == 0))
+		return;
 	BUG_ON(last >= (sb->s_blocksize << 3));
 	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	/* Don't bother if the block group is corrupt. */
@@ -3135,7 +3137,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	}
 	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
 			start > ac->ac_o_ex.fe_logical);
-	BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 
 	/* now prepare goal request */
 
@@ -3196,8 +3198,30 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
 static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 {
 	struct ext4_prealloc_space *pa = ac->ac_pa;
+	struct ext4_buddy e4b;
+	int err;
 
-	if (pa && pa->pa_type == MB_INODE_PA)
+	if (pa == NULL) {
+		if (ac->ac_f_ex.fe_len == 0)
+			return;
+		err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
+		if (err) {
+			/*
+			 * This should never happen since we pin the
+			 * pages in the ext4_allocation_context so
+			 * ext4_mb_load_buddy() should never fail.
+			 */
+			WARN(1, "mb_load_buddy failed (%d)", err);
+			return;
+		}
+		ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
+			       ac->ac_f_ex.fe_len);
+		ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		ext4_mb_unload_buddy(&e4b);
+		return;
+	}
+	if (pa->pa_type == MB_INODE_PA)
 		pa->pa_free += ac->ac_b_ex.fe_len;
 }
 
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 04434ad3e8e0..1268a1b5afa9 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -20,8 +20,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
 
 int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
@@ -29,8 +28,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
 
 void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	mmp->mmp_checksum = ext4_mmp_csum(sb, mmp);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index d050e043e884..2dcbfb6245d8 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -123,8 +123,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 		       "directory leaf block found instead of index block");
 		return ERR_PTR(-EIO);
 	}
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) ||
+	if (!ext4_has_metadata_csum(inode->i_sb) ||
 	    buffer_verified(bh))
 		return bh;
 
@@ -339,8 +338,7 @@ int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent)
 {
 	struct ext4_dir_entry_tail *t;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	t = get_dirent_tail(inode, dirent);
@@ -361,8 +359,7 @@ static void ext4_dirent_csum_set(struct inode *inode,
 {
 	struct ext4_dir_entry_tail *t;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	t = get_dirent_tail(inode, dirent);
@@ -437,8 +434,7 @@ static int ext4_dx_csum_verify(struct inode *inode,
 	struct dx_tail *t;
 	int count_offset, limit, count;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return 1;
 
 	c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -467,8 +463,7 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent)
 	struct dx_tail *t;
 	int count_offset, limit, count;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	c = get_dx_countlimit(inode, dirent, &count_offset);
@@ -556,8 +551,7 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
 		EXT4_DIR_REC_LEN(2) - infosize;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		entry_space -= sizeof(struct dx_tail);
 	return entry_space / sizeof(struct dx_entry);
 }
@@ -566,8 +560,7 @@ static inline unsigned dx_node_limit(struct inode *dir)
 {
 	unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		entry_space -= sizeof(struct dx_tail);
 	return entry_space / sizeof(struct dx_entry);
 }
@@ -1429,7 +1422,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 					 dentry);
 			return ERR_PTR(-EIO);
 		}
-		inode = ext4_iget(dir->i_sb, ino);
+		inode = ext4_iget_normal(dir->i_sb, ino);
 		if (inode == ERR_PTR(-ESTALE)) {
 			EXT4_ERROR_INODE(dir,
 					 "deleted inode referenced: %u",
@@ -1460,7 +1453,7 @@ struct dentry *ext4_get_parent(struct dentry *child)
 		return ERR_PTR(-EIO);
 	}
 
-	return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino));
+	return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino));
 }
 
 /*
@@ -1534,8 +1527,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	int	csum_size = 0;
 	int	err = 0, i;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	bh2 = ext4_append(handle, dir, &newblock);
@@ -1704,8 +1696,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	int		csum_size = 0;
 	int		err;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	if (!de) {
@@ -1772,8 +1763,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	struct fake_dirent *fde;
 	int		csum_size = 0;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	blocksize =  dir->i_sb->s_blocksize;
@@ -1889,8 +1879,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	ext4_lblk_t block, blocks;
 	int	csum_size = 0;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(inode->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	sb = dir->i_sb;
@@ -2152,8 +2141,7 @@ static int ext4_delete_entry(handle_t *handle,
 			return err;
 	}
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	BUFFER_TRACE(bh, "get_write_access");
@@ -2372,8 +2360,7 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 	int csum_size = 0;
 	int err;
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(dir->i_sb))
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index ab95508e3d40..b6a3804a9855 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -308,13 +308,14 @@ static void ext4_end_bio(struct bio *bio, int error)
 	if (error) {
 		struct inode *inode = io_end->inode;
 
-		ext4_warning(inode->i_sb, "I/O error writing to inode %lu "
+		ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu "
 			     "(offset %llu size %ld starting block %llu)",
-			     inode->i_ino,
+			     error, inode->i_ino,
 			     (unsigned long long) io_end->offset,
 			     (long) io_end->size,
 			     (unsigned long long)
 			     bi_sector >> (inode->i_blkbits - 9));
+		mapping_set_error(inode->i_mapping, error);
 	}
 
 	if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
@@ -400,7 +401,8 @@ submit_and_retry:
 int ext4_bio_write_page(struct ext4_io_submit *io,
 			struct page *page,
 			int len,
-			struct writeback_control *wbc)
+			struct writeback_control *wbc,
+			bool keep_towrite)
 {
 	struct inode *inode = page->mapping->host;
 	unsigned block_start, blocksize;
@@ -413,10 +415,24 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
 
-	set_page_writeback(page);
+	if (keep_towrite)
+		set_page_writeback_keepwrite(page);
+	else
+		set_page_writeback(page);
 	ClearPageError(page);
 
 	/*
+	 * Comments copied from block_write_full_page_endio:
+	 *
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	if (len < PAGE_CACHE_SIZE)
+		zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	/*
 	 * In the first loop we prepare and mark buffers to submit. We have to
 	 * mark all buffers in the page before submitting so that
 	 * end_page_writeback() cannot be called from ext4_bio_end_io() when IO
@@ -427,19 +443,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	do {
 		block_start = bh_offset(bh);
 		if (block_start >= len) {
-			/*
-			 * Comments copied from block_write_full_page_endio:
-			 *
-			 * The page straddles i_size.  It must be zeroed out on
-			 * each and every writepage invocation because it may
-			 * be mmapped.  "A file is mapped in multiples of the
-			 * page size.  For a file that is not a multiple of
-			 * the  page size, the remaining memory is zeroed when
-			 * mapped, and writes to that region are not written
-			 * out to the file."
-			 */
-			zero_user_segment(page, block_start,
-					  block_start + blocksize);
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index f3b84cd9de56..2400ad1c3d12 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1071,7 +1071,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data,
 			break;
 
 		if (meta_bg == 0)
-			backup_block = group * bpg + blk_off;
+			backup_block = ((ext4_fsblk_t)group) * bpg + blk_off;
 		else
 			backup_block = (ext4_group_first_block_no(sb, group) +
 					ext4_bg_has_super(sb, group));
@@ -1200,8 +1200,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb,
 {
 	struct buffer_head *bh;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 0;
 
 	bh = ext4_get_bitmap(sb, group_data->inode_bitmap);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 710fed2377d4..9fb3e6c0c578 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -140,8 +140,7 @@ static __le32 ext4_superblock_csum(struct super_block *sb,
 int ext4_superblock_csum_verify(struct super_block *sb,
 				struct ext4_super_block *es)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return 1;
 
 	return es->s_checksum == ext4_superblock_csum(sb, es);
@@ -151,8 +150,7 @@ void ext4_superblock_csum_set(struct super_block *sb)
 {
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(sb))
 		return;
 
 	es->s_checksum = ext4_superblock_csum(sb, es);
@@ -996,7 +994,7 @@ static struct inode *ext4_nfs_get_inode(struct super_block *sb,
 	 * Currently we don't know the generation for parent directory, so
 	 * a generation of 0 means "accept any"
 	 */
-	inode = ext4_iget(sb, ino);
+	inode = ext4_iget_normal(sb, ino);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 	if (generation && inode->i_generation != generation) {
@@ -1519,8 +1517,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
 		sbi->s_commit_interval = HZ * arg;
 	} else if (token == Opt_max_batch_time) {
-		if (arg == 0)
-			arg = EXT4_DEF_MAX_BATCH_TIME;
 		sbi->s_max_batch_time = arg;
 	} else if (token == Opt_min_batch_time) {
 		sbi->s_min_batch_time = arg;
@@ -1708,13 +1704,6 @@ static int parse_options(char *options, struct super_block *sb,
 					"not specified");
 			return 0;
 		}
-	} else {
-		if (sbi->s_jquota_fmt) {
-			ext4_msg(sb, KERN_ERR, "journaled quota format "
-					"specified with no journaling "
-					"enabled");
-			return 0;
-		}
 	}
 #endif
 	if (test_opt(sb, DIOREAD_NOLOCK)) {
@@ -2012,8 +2001,7 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
 	__u16 crc = 0;
 	__le32 le_group = cpu_to_le32(block_group);
 
-	if ((sbi->s_es->s_feature_ro_compat &
-	     cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) {
+	if (ext4_has_metadata_csum(sbi->s_sb)) {
 		/* Use new metadata_csum algorithm */
 		__le16 save_csum;
 		__u32 csum32;
@@ -2031,6 +2019,10 @@ static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
 	}
 
 	/* old crc16 code */
+	if (!(sbi->s_es->s_feature_ro_compat &
+	      cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)))
+		return 0;
+
 	offset = offsetof(struct ext4_group_desc, bg_checksum);
 
 	crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
@@ -2793,10 +2785,11 @@ static void print_daily_error_info(unsigned long arg)
 	es = sbi->s_es;
 
 	if (es->s_error_count)
-		ext4_msg(sb, KERN_NOTICE, "error count: %u",
+		/* fsck newer than v1.41.13 is needed to clean this condition. */
+		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
@@ -2810,7 +2803,7 @@ static void print_daily_error_info(unsigned long arg)
 		printk("\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
@@ -3168,11 +3161,10 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 	int compat, incompat;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
-		/* journal checksum v2 */
+	if (ext4_has_metadata_csum(sb)) {
+		/* journal checksum v3 */
 		compat = 0;
-		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
 	} else {
 		/* journal checksum v1 */
 		compat = JBD2_FEATURE_COMPAT_CHECKSUM;
@@ -3194,6 +3186,7 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 		jbd2_journal_clear_features(sbi->s_journal,
 				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
 				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
+				JBD2_FEATURE_INCOMPAT_CSUM_V3 |
 				JBD2_FEATURE_INCOMPAT_CSUM_V2);
 	}
 
@@ -3475,8 +3468,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* Precompute checksum seed for all metadata */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-			EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (ext4_has_metadata_csum(sb))
 		sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
 					       sizeof(es->s_uuid));
 
@@ -3494,6 +3486,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
+	/* don't forget to enable journal_csum when metadata_csum is enabled. */
+	if (ext4_has_metadata_csum(sb))
+		set_opt(sb, JOURNAL_CHECKSUM);
+
 	if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
 		set_opt(sb, JOURNAL_DATA);
 	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index e175e94116ac..8825154b20b6 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -141,8 +141,7 @@ static int ext4_xattr_block_csum_verify(struct inode *inode,
 					sector_t block_nr,
 					struct ext4_xattr_header *hdr)
 {
-	if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+	if (ext4_has_metadata_csum(inode->i_sb) &&
 	    (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr)))
 		return 0;
 	return 1;
@@ -152,8 +151,7 @@ static void ext4_xattr_block_csum_set(struct inode *inode,
 				      sector_t block_nr,
 				      struct ext4_xattr_header *hdr)
 {
-	if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
-		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+	if (!ext4_has_metadata_csum(inode->i_sb))
 		return;
 
 	hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr);
@@ -189,14 +187,28 @@ ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
 }
 
 static int
-ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
+ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
+		       void *value_start)
 {
-	while (!IS_LAST_ENTRY(entry)) {
-		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry);
+	struct ext4_xattr_entry *e = entry;
+
+	while (!IS_LAST_ENTRY(e)) {
+		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
 		if ((void *)next >= end)
 			return -EIO;
-		entry = next;
+		e = next;
+	}
+
+	while (!IS_LAST_ENTRY(entry)) {
+		if (entry->e_value_size != 0 &&
+		    (value_start + le16_to_cpu(entry->e_value_offs) <
+		     (void *)e + sizeof(__u32) ||
+		     value_start + le16_to_cpu(entry->e_value_offs) +
+		    le32_to_cpu(entry->e_value_size) > end))
+			return -EIO;
+		entry = EXT4_XATTR_NEXT(entry);
 	}
+
 	return 0;
 }
 
@@ -213,7 +225,8 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
 		return -EIO;
 	if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
 		return -EIO;
-	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
+	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
+				       bh->b_data);
 	if (!error)
 		set_buffer_verified(bh);
 	return error;
@@ -329,7 +342,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(entry, end);
+	error = ext4_xattr_check_names(entry, end, entry);
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_find_entry(&entry, name_index, name,
@@ -457,7 +470,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	raw_inode = ext4_raw_inode(&iloc);
 	header = IHDR(inode, raw_inode);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
-	error = ext4_xattr_check_names(IFIRST(header), end);
+	error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
 	if (error)
 		goto cleanup;
 	error = ext4_xattr_list_entries(dentry, IFIRST(header),
@@ -517,8 +530,8 @@ static void ext4_xattr_update_super_block(handle_t *handle,
 }
 
 /*
- * Release the xattr block BH: If the reference count is > 1, decrement
- * it; otherwise free the block.
+ * Release the xattr block BH: If the reference count is > 1, decrement it;
+ * otherwise free the block.
  */
 static void
 ext4_xattr_release_block(handle_t *handle, struct inode *inode,
@@ -538,16 +551,31 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		if (ce)
 			mb_cache_entry_free(ce);
 		get_bh(bh);
+		unlock_buffer(bh);
 		ext4_free_blocks(handle, inode, bh, 0, 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
-		unlock_buffer(bh);
 	} else {
 		le32_add_cpu(&BHDR(bh)->h_refcount, -1);
 		if (ce)
 			mb_cache_entry_release(ce);
+		/*
+		 * Beware of this ugliness: Releasing of xattr block references
+		 * from different inodes can race and so we have to protect
+		 * from a race where someone else frees the block (and releases
+		 * its journal_head) before we are done dirtying the buffer. In
+		 * nojournal mode this race is harmless and we actually cannot
+		 * call ext4_handle_dirty_xattr_block() with locked buffer as
+		 * that function can call sync_dirty_buffer() so for that case
+		 * we handle the dirtying after unlocking the buffer.
+		 */
+		if (ext4_handle_valid(handle))
+			error = ext4_handle_dirty_xattr_block(handle, inode,
+							      bh);
 		unlock_buffer(bh);
-		error = ext4_handle_dirty_xattr_block(handle, inode, bh);
+		if (!ext4_handle_valid(handle))
+			error = ext4_handle_dirty_xattr_block(handle, inode,
+							      bh);
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 		dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
@@ -957,7 +985,8 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 	is->s.here = is->s.first;
 	is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
 	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
-		error = ext4_xattr_check_names(IFIRST(header), is->s.end);
+		error = ext4_xattr_check_names(IFIRST(header), is->s.end,
+					       IFIRST(header));
 		if (error)
 			return error;
 		/* Find the named attribute. */
diff --git a/fs/file_table.c b/fs/file_table.c
index 5b24008ea4f6..79ecae62209a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -209,10 +209,10 @@ static void drop_file_write_access(struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 
-	put_write_access(inode);
-
 	if (special_file(inode->i_mode))
 		return;
+
+	put_write_access(inode);
 	if (file_check_writeable(file) != 0)
 		return;
 	__mnt_drop_write(mnt);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index d754e3cf99a8..23a51f08e3b5 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -89,16 +89,29 @@ static inline struct inode *wb_inode(struct list_head *head)
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+{
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
 			   struct wb_writeback_work *work)
 {
 	trace_writeback_queue(bdi, work);
 
 	spin_lock_bh(&bdi->wb_lock);
+	if (!test_bit(BDI_registered, &bdi->state)) {
+		if (work->done)
+			complete(work->done);
+		goto out_unlock;
+	}
 	list_add_tail(&work->list, &bdi->work_list);
-	spin_unlock_bh(&bdi->wb_lock);
-
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -114,7 +127,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
 		trace_writeback_nowork(bdi);
-		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+		bdi_wakeup_thread(bdi);
 		return;
 	}
 
@@ -161,7 +174,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	bdi_wakeup_thread(bdi);
 }
 
 /*
@@ -463,12 +476,28 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	 * write_inode()
 	 */
 	spin_lock(&inode->i_lock);
-	/* Clear I_DIRTY_PAGES if we've written out all dirty pages */
-	if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
-		inode->i_state &= ~I_DIRTY_PAGES;
+
 	dirty = inode->i_state & I_DIRTY;
-	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+	inode->i_state &= ~I_DIRTY;
+
+	/*
+	 * Paired with smp_mb() in __mark_inode_dirty().  This allows
+	 * __mark_inode_dirty() to test i_state without grabbing i_lock -
+	 * either they see the I_DIRTY bits cleared or we see the dirtied
+	 * inode.
+	 *
+	 * I_DIRTY_PAGES is always cleared together above even if @mapping
+	 * still has dirty pages.  The flag is reinstated after smp_mb() if
+	 * necessary.  This guarantees that either __mark_inode_dirty()
+	 * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
+	 */
+	smp_mb();
+
+	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+		inode->i_state |= I_DIRTY_PAGES;
+
 	spin_unlock(&inode->i_lock);
+
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
 	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		int err = write_inode(inode, wbc);
@@ -1017,7 +1046,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   list_empty(&bdi->bdi_list))) {
+		   !test_bit(BDI_registered, &bdi->state))) {
 		/*
 		 * The normal path.  Keep writing back @bdi until its
 		 * work_list is empty.  Note that this path is also taken
@@ -1039,10 +1068,10 @@ void bdi_writeback_workfn(struct work_struct *work)
 		trace_writeback_pages_written(pages_written);
 	}
 
-	if (!list_empty(&bdi->work_list) ||
-	    (wb_has_dirty_io(wb) && dirty_writeback_interval))
-		queue_delayed_work(bdi_wq, &wb->dwork,
-			msecs_to_jiffies(dirty_writeback_interval * 10));
+	if (!list_empty(&bdi->work_list))
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+		bdi_wakeup_thread_delayed(bdi);
 
 	current->flags &= ~PF_SWAPWRITE;
 }
@@ -1132,12 +1161,11 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	}
 
 	/*
-	 * make sure that changes are seen by all cpus before we test i_state
-	 * -- mikulas
+	 * Paired with smp_mb() in __writeback_single_inode() for the
+	 * following lockless i_state test.  See there for details.
 	 */
 	smp_mb();
 
-	/* avoid the locking if we can */
 	if ((inode->i_state & flags) == flags)
 		return;
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 1d1292c581c3..342f0239fcbf 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -198,7 +198,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 	inode = ACCESS_ONCE(entry->d_inode);
 	if (inode && is_bad_inode(inode))
 		goto invalid;
-	else if (fuse_dentry_time(entry) < get_jiffies_64()) {
+	else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) ||
+		 (flags & LOOKUP_REVAL)) {
 		int err;
 		struct fuse_entry_out outarg;
 		struct fuse_req *req;
@@ -925,7 +926,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
 	int err;
 	bool r;
 
-	if (fi->i_time < get_jiffies_64()) {
+	if (time_before64(fi->i_time, get_jiffies_64())) {
 		r = true;
 		err = fuse_do_getattr(inode, stat, file);
 	} else {
@@ -1111,7 +1112,7 @@ static int fuse_permission(struct inode *inode, int mask)
 	    ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
 		struct fuse_inode *fi = get_fuse_inode(inode);
 
-		if (fi->i_time < get_jiffies_64()) {
+		if (time_before64(fi->i_time, get_jiffies_64())) {
 			refreshed = true;
 
 			err = fuse_perm_getattr(inode, mask);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 77bcc303c3ae..a91d3b4d32f3 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1003,9 +1003,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		mark_page_accessed(page);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d468643a68b2..73f6bcb44ea8 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -461,6 +461,17 @@ static const match_table_t tokens = {
 	{OPT_ERR,			NULL}
 };
 
+static int fuse_match_uint(substring_t *s, unsigned int *res)
+{
+	int err = -ENOMEM;
+	char *buf = match_strdup(s);
+	if (buf) {
+		err = kstrtouint(buf, 10, res);
+		kfree(buf);
+	}
+	return err;
+}
+
 static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 {
 	char *p;
@@ -471,6 +482,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 	while ((p = strsep(&opt, ",")) != NULL) {
 		int token;
 		int value;
+		unsigned uv;
 		substring_t args[MAX_OPT_ARGS];
 		if (!*p)
 			continue;
@@ -494,18 +506,18 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 			break;
 
 		case OPT_USER_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->user_id = make_kuid(current_user_ns(), value);
+			d->user_id = make_kuid(current_user_ns(), uv);
 			if (!uid_valid(d->user_id))
 				return 0;
 			d->user_id_present = 1;
 			break;
 
 		case OPT_GROUP_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->group_id = make_kgid(current_user_ns(), value);
+			d->group_id = make_kgid(current_user_ns(), uv);
 			if (!gid_valid(d->group_id))
 				return 0;
 			d->group_id_present = 1;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 5c524180c98e..bc643b97423c 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -606,8 +606,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (!IS_ERR(inode)) {
 		d = d_splice_alias(inode, dentry);
 		error = PTR_ERR(d);
-		if (IS_ERR(d))
+		if (IS_ERR(d)) {
+			inode = ERR_CAST(d);
 			goto fail_gunlock;
+		}
 		error = 0;
 		if (file) {
 			if (S_ISREG(inode->i_mode)) {
@@ -823,7 +825,6 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 
 	d = d_splice_alias(inode, dentry);
 	if (IS_ERR(d)) {
-		iput(inode);
 		gfs2_glock_dq_uninit(&gh);
 		return d;
 	}
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index c7f24690ed05..b82a9c99e18b 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -97,6 +97,11 @@ const struct address_space_operations gfs2_meta_aops = {
 	.releasepage = gfs2_releasepage,
 };
 
+const struct address_space_operations gfs2_rgrp_aops = {
+	.writepage = gfs2_aspace_writepage,
+	.releasepage = gfs2_releasepage,
+};
+
 /**
  * gfs2_getbuf - Get a buffer with a given address space
  * @gl: the glock
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 4823b934208a..ac5d8027d335 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -38,12 +38,15 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh,
 }
 
 extern const struct address_space_operations gfs2_meta_aops;
+extern const struct address_space_operations gfs2_rgrp_aops;
 
 static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 	if (mapping->a_ops == &gfs2_meta_aops)
 		return (((struct gfs2_glock *)mapping) - 1)->gl_sbd;
+	else if (mapping->a_ops == &gfs2_rgrp_aops)
+		return container_of(mapping, struct gfs2_sbd, sd_aspace);
 	else
 		return inode->i_sb->s_fs_info;
 }
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index c6872d09561a..f6c9d83aa39b 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -104,7 +104,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	mapping = &sdp->sd_aspace;
 
 	address_space_init_once(mapping);
-	mapping->a_ops = &gfs2_meta_aops;
+	mapping->a_ops = &gfs2_rgrp_aops;
 	mapping->host = sb->s_bdev->bd_inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d19b30ababf1..a4a8ed56e438 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1017,6 +1017,11 @@ static int __init init_hugetlbfs_fs(void)
 	int error;
 	int i;
 
+	if (!hugepages_supported()) {
+		pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n");
+		return -ENOTSUPP;
+	}
+
 	error = bdi_init(&hugetlbfs_backing_dev_info);
 	if (error)
 		return error;
diff --git a/fs/inode.c b/fs/inode.c
index 4bcdad3c9361..e846a32e8d6e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1840,14 +1840,18 @@ EXPORT_SYMBOL(inode_init_owner);
  * inode_owner_or_capable - check current task permissions to inode
  * @inode: inode being checked
  *
- * Return true if current either has CAP_FOWNER to the inode, or
- * owns the file.
+ * Return true if current either has CAP_FOWNER in a namespace with the
+ * inode owner uid mapped, or owns the file.
  */
 bool inode_owner_or_capable(const struct inode *inode)
 {
+	struct user_namespace *ns;
+
 	if (uid_eq(current_fsuid(), inode->i_uid))
 		return true;
-	if (inode_capable(inode, CAP_FOWNER))
+
+	ns = current_user_ns();
+	if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
 		return true;
 	return false;
 }
diff --git a/fs/ioprio.c b/fs/ioprio.c
index e50170ca7c33..31666c92b46a 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -157,14 +157,16 @@ out:
 
 int ioprio_best(unsigned short aprio, unsigned short bprio)
 {
-	unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
-	unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+	unsigned short aclass;
+	unsigned short bclass;
 
-	if (aclass == IOPRIO_CLASS_NONE)
-		aclass = IOPRIO_CLASS_BE;
-	if (bclass == IOPRIO_CLASS_NONE)
-		bclass = IOPRIO_CLASS_BE;
+	if (!ioprio_valid(aprio))
+		aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+	if (!ioprio_valid(bprio))
+		bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 
+	aclass = IOPRIO_PRIO_CLASS(aprio);
+	bclass = IOPRIO_PRIO_CLASS(bprio);
 	if (aclass == bclass)
 		return min(aprio, bprio);
 	if (aclass > bclass)
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 4a9e10ea13f2..a9daccbd8fe7 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -61,7 +61,7 @@ static void isofs_put_super(struct super_block *sb)
 	return;
 }
 
-static int isofs_read_inode(struct inode *);
+static int isofs_read_inode(struct inode *, int relocated);
 static int isofs_statfs (struct dentry *, struct kstatfs *);
 
 static struct kmem_cache *isofs_inode_cachep;
@@ -1258,7 +1258,7 @@ out_toomany:
 	goto out;
 }
 
-static int isofs_read_inode(struct inode *inode)
+static int isofs_read_inode(struct inode *inode, int relocated)
 {
 	struct super_block *sb = inode->i_sb;
 	struct isofs_sb_info *sbi = ISOFS_SB(sb);
@@ -1403,7 +1403,7 @@ static int isofs_read_inode(struct inode *inode)
 	 */
 
 	if (!high_sierra) {
-		parse_rock_ridge_inode(de, inode);
+		parse_rock_ridge_inode(de, inode, relocated);
 		/* if we want uid/gid set, override the rock ridge setting */
 		if (sbi->s_uid_set)
 			inode->i_uid = sbi->s_uid;
@@ -1482,9 +1482,10 @@ static int isofs_iget5_set(struct inode *ino, void *data)
  * offset that point to the underlying meta-data for the inode.  The
  * code below is otherwise similar to the iget() code in
  * include/linux/fs.h */
-struct inode *isofs_iget(struct super_block *sb,
-			 unsigned long block,
-			 unsigned long offset)
+struct inode *__isofs_iget(struct super_block *sb,
+			   unsigned long block,
+			   unsigned long offset,
+			   int relocated)
 {
 	unsigned long hashval;
 	struct inode *inode;
@@ -1506,7 +1507,7 @@ struct inode *isofs_iget(struct super_block *sb,
 		return ERR_PTR(-ENOMEM);
 
 	if (inode->i_state & I_NEW) {
-		ret = isofs_read_inode(inode);
+		ret = isofs_read_inode(inode, relocated);
 		if (ret < 0) {
 			iget_failed(inode);
 			inode = ERR_PTR(ret);
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 99167238518d..0ac4c1f73fbd 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -107,7 +107,7 @@ extern int iso_date(char *, int);
 
 struct inode;		/* To make gcc happy */
 
-extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *);
+extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated);
 extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *);
 extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *);
 
@@ -118,9 +118,24 @@ extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int
 extern struct buffer_head *isofs_bread(struct inode *, sector_t);
 extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long);
 
-extern struct inode *isofs_iget(struct super_block *sb,
-                                unsigned long block,
-                                unsigned long offset);
+struct inode *__isofs_iget(struct super_block *sb,
+			   unsigned long block,
+			   unsigned long offset,
+			   int relocated);
+
+static inline struct inode *isofs_iget(struct super_block *sb,
+				       unsigned long block,
+				       unsigned long offset)
+{
+	return __isofs_iget(sb, block, offset, 0);
+}
+
+static inline struct inode *isofs_iget_reloc(struct super_block *sb,
+					     unsigned long block,
+					     unsigned long offset)
+{
+	return __isofs_iget(sb, block, offset, 1);
+}
 
 /* Because the inode number is no longer relevant to finding the
  * underlying meta-data for an inode, we are free to choose a more
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index c0bf42472e40..735d7522a3a9 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -30,6 +30,7 @@ struct rock_state {
 	int cont_size;
 	int cont_extent;
 	int cont_offset;
+	int cont_loops;
 	struct inode *inode;
 };
 
@@ -73,6 +74,9 @@ static void init_rock_state(struct rock_state *rs, struct inode *inode)
 	rs->inode = inode;
 }
 
+/* Maximum number of Rock Ridge continuation entries */
+#define RR_MAX_CE_ENTRIES 32
+
 /*
  * Returns 0 if the caller should continue scanning, 1 if the scan must end
  * and -ve on error.
@@ -105,6 +109,8 @@ static int rock_continue(struct rock_state *rs)
 			goto out;
 		}
 		ret = -EIO;
+		if (++rs->cont_loops >= RR_MAX_CE_ENTRIES)
+			goto out;
 		bh = sb_bread(rs->inode->i_sb, rs->cont_extent);
 		if (bh) {
 			memcpy(rs->buffer, bh->b_data + rs->cont_offset,
@@ -288,12 +294,16 @@ eio:
 	goto out;
 }
 
+#define RR_REGARD_XA 1
+#define RR_RELOC_DE 2
+
 static int
 parse_rock_ridge_inode_internal(struct iso_directory_record *de,
-				struct inode *inode, int regard_xa)
+				struct inode *inode, int flags)
 {
 	int symlink_len = 0;
 	int cnt, sig;
+	unsigned int reloc_block;
 	struct inode *reloc;
 	struct rock_ridge *rr;
 	int rootflag;
@@ -305,7 +315,7 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de,
 
 	init_rock_state(&rs, inode);
 	setup_rock_ridge(de, inode, &rs);
-	if (regard_xa) {
+	if (flags & RR_REGARD_XA) {
 		rs.chr += 14;
 		rs.len -= 14;
 		if (rs.len < 0)
@@ -352,6 +362,9 @@ repeat:
 			rs.cont_size = isonum_733(rr->u.CE.size);
 			break;
 		case SIG('E', 'R'):
+			/* Invalid length of ER tag id? */
+			if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len)
+				goto out;
 			ISOFS_SB(inode->i_sb)->s_rock = 1;
 			printk(KERN_DEBUG "ISO 9660 Extensions: ");
 			{
@@ -485,12 +498,22 @@ repeat:
 					"relocated directory\n");
 			goto out;
 		case SIG('C', 'L'):
-			ISOFS_I(inode)->i_first_extent =
-			    isonum_733(rr->u.CL.location);
-			reloc =
-			    isofs_iget(inode->i_sb,
-				       ISOFS_I(inode)->i_first_extent,
-				       0);
+			if (flags & RR_RELOC_DE) {
+				printk(KERN_ERR
+				       "ISOFS: Recursive directory relocation "
+				       "is not supported\n");
+				goto eio;
+			}
+			reloc_block = isonum_733(rr->u.CL.location);
+			if (reloc_block == ISOFS_I(inode)->i_iget5_block &&
+			    ISOFS_I(inode)->i_iget5_offset == 0) {
+				printk(KERN_ERR
+				       "ISOFS: Directory relocation points to "
+				       "itself\n");
+				goto eio;
+			}
+			ISOFS_I(inode)->i_first_extent = reloc_block;
+			reloc = isofs_iget_reloc(inode->i_sb, reloc_block, 0);
 			if (IS_ERR(reloc)) {
 				ret = PTR_ERR(reloc);
 				goto out;
@@ -637,9 +660,11 @@ static char *get_symlink_chunk(char *rpnt, struct rock_ridge *rr, char *plimit)
 	return rpnt;
 }
 
-int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode)
+int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode,
+			   int relocated)
 {
-	int result = parse_rock_ridge_inode_internal(de, inode, 0);
+	int flags = relocated ? RR_RELOC_DE : 0;
+	int result = parse_rock_ridge_inode_internal(de, inode, flags);
 
 	/*
 	 * if rockridge flag was reset and we didn't look for attributes
@@ -647,7 +672,8 @@ int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode)
 	 */
 	if ((ISOFS_SB(inode->i_sb)->s_rock_offset == -1)
 	    && (ISOFS_SB(inode->i_sb)->s_rock == 2)) {
-		result = parse_rock_ridge_inode_internal(de, inode, 14);
+		result = parse_rock_ridge_inode_internal(de, inode,
+							 flags | RR_REGARD_XA);
 	}
 	return result;
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index cf2fc0594063..9181c2b22b3c 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -97,7 +97,7 @@ static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh)
 	struct commit_header *h;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	h = (struct commit_header *)(bh->b_data);
@@ -313,11 +313,11 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
 	return checksum;
 }
 
-static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
 				   unsigned long long block)
 {
 	tag->t_blocknr = cpu_to_be32(block & (u32)~0);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT))
 		tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
 }
 
@@ -327,7 +327,7 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 	struct jbd2_journal_block_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
@@ -340,12 +340,13 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	struct page *page = bh->b_page;
 	__u8 *addr;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	seq = cpu_to_be32(sequence);
@@ -355,8 +356,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 			     bh->b_size);
 	kunmap_atomic(addr);
 
-	/* We only have space to store the lower 16 bits of the crc32c. */
-	tag->t_checksum = cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		tag3->t_checksum = cpu_to_be32(csum32);
+	else
+		tag->t_checksum = cpu_to_be16(csum32);
 }
 /*
  * jbd2_journal_commit_transaction
@@ -396,7 +399,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	LIST_HEAD(io_bufs);
 	LIST_HEAD(log_bufs);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_block_tail);
 
 	/*
@@ -692,7 +695,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			tag_flag |= JBD2_FLAG_SAME_UUID;
 
 		tag = (journal_block_tag_t *) tagp;
-		write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
+		write_tag_block(journal, tag, jh2bh(jh)->b_blocknr);
 		tag->t_flags = cpu_to_be16(tag_flag);
 		jbd2_block_tag_csum_set(journal, tag, wbuf[bufs],
 					commit_transaction->t_tid);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 5fa344afb49a..f2d78a3dae43 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug);
 /* Checksumming functions */
 int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum_type == JBD2_CRC32C_CHKSUM;
@@ -145,7 +145,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
 
 int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum == jbd2_superblock_csum(j, sb);
@@ -153,7 +153,7 @@ int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 
 void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	sb->s_checksum = jbd2_superblock_csum(j, sb);
@@ -1522,21 +1522,29 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
-	if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
-	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal) &&
+	    JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
 		/* Can't have checksum v1 and v2 on at the same time! */
 		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
 		       "at the same time!\n");
 		goto out;
 	}
 
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) &&
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+		/* Can't have checksum v2 and v3 at the same time! */
+		printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 "
+		       "at the same time!\n");
+		goto out;
+	}
+
 	if (!jbd2_verify_csum_type(journal, sb)) {
 		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;
 	}
 
 	/* Load the checksum driver */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal)) {
 		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
 			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
@@ -1553,7 +1561,7 @@ static int journal_get_superblock(journal_t *journal)
 	}
 
 	/* Precompute checksum seed for all metadata */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
 
@@ -1813,8 +1821,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
 		return 0;
 
-	/* Asking for checksumming v2 and v1?  Only give them v2. */
-	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 &&
+	/* If enabling v2 checksums, turn on v3 instead */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) {
+		incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3;
+	}
+
+	/* Asking for checksumming v3 and v1?  Only give them v3. */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 &&
 	    compat & JBD2_FEATURE_COMPAT_CHECKSUM)
 		compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM;
 
@@ -1823,8 +1837,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 
 	sb = journal->j_superblock;
 
-	/* If enabling v2 checksums, update superblock */
-	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	/* If enabling v3 checksums, update superblock */
+	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
 		sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
 		sb->s_feature_compat &=
 			~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
@@ -1842,8 +1856,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 		}
 
 		/* Precompute checksum seed for all metadata */
-		if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					      JBD2_FEATURE_INCOMPAT_CSUM_V2))
+		if (jbd2_journal_has_csum_v2or3(journal))
 			journal->j_csum_seed = jbd2_chksum(journal, ~0,
 							   sb->s_uuid,
 							   sizeof(sb->s_uuid));
@@ -1852,7 +1865,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	/* If enabling v1 checksums, downgrade superblock */
 	if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM))
 		sb->s_feature_incompat &=
-			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2);
+			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 |
+				     JBD2_FEATURE_INCOMPAT_CSUM_V3);
 
 	sb->s_feature_compat    |= cpu_to_be32(compat);
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
@@ -2165,16 +2179,20 @@ int jbd2_journal_blocks_per_page(struct inode *inode)
  */
 size_t journal_tag_bytes(journal_t *journal)
 {
-	journal_block_tag_t tag;
-	size_t x = 0;
+	size_t sz;
+
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return sizeof(journal_block_tag3_t);
+
+	sz = sizeof(journal_block_tag_t);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
-		x += sizeof(tag.t_checksum);
+		sz += sizeof(__u16);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
-		return x + JBD2_TAG_SIZE64;
+		return sz;
 	else
-		return x + JBD2_TAG_SIZE32;
+		return sz - sizeof(__u32);
 }
 
 /*
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 3b6bb19d60b1..bcbef08a4d8f 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -181,7 +181,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
@@ -205,7 +205,7 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 	int			nr = 0, size = journal->j_blocksize;
 	int			tag_bytes = journal_tag_bytes(journal);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		size -= sizeof(struct jbd2_journal_block_tail);
 
 	tagp = &bh->b_data[sizeof(journal_header_t)];
@@ -338,10 +338,11 @@ int jbd2_journal_skip_recovery(journal_t *journal)
 	return err;
 }
 
-static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+static inline unsigned long long read_tag_block(journal_t *journal,
+						journal_block_tag_t *tag)
 {
 	unsigned long long block = be32_to_cpu(tag->t_blocknr);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
 		block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
 	return block;
 }
@@ -384,7 +385,7 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	h = buf;
@@ -399,17 +400,21 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 				      void *buf, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	seq = cpu_to_be32(sequence);
 	csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
 	csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
 
-	return tag->t_checksum == cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return tag3->t_checksum == cpu_to_be32(csum32);
+	else
+		return tag->t_checksum == cpu_to_be16(csum32);
 }
 
 static int do_one_pass(journal_t *journal,
@@ -426,6 +431,7 @@ static int do_one_pass(journal_t *journal,
 	int			tag_bytes = journal_tag_bytes(journal);
 	__u32			crc32_sum = ~0; /* Transactional Checksums */
 	int			descr_csum_size = 0;
+	int			block_error = 0;
 
 	/*
 	 * First thing is to establish what we expect to find in the log
@@ -512,14 +518,14 @@ static int do_one_pass(journal_t *journal,
 		switch(blocktype) {
 		case JBD2_DESCRIPTOR_BLOCK:
 			/* Verify checksum first */
-			if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					JBD2_FEATURE_INCOMPAT_CSUM_V2))
+			if (jbd2_journal_has_csum_v2or3(journal))
 				descr_csum_size =
 					sizeof(struct jbd2_journal_block_tail);
 			if (descr_csum_size > 0 &&
 			    !jbd2_descr_block_csum_verify(journal,
 							  bh->b_data)) {
 				err = -EIO;
+				brelse(bh);
 				goto failed;
 			}
 
@@ -574,7 +580,7 @@ static int do_one_pass(journal_t *journal,
 					unsigned long long blocknr;
 
 					J_ASSERT(obh != NULL);
-					blocknr = read_tag_block(tag_bytes,
+					blocknr = read_tag_block(journal,
 								 tag);
 
 					/* If the block has been
@@ -598,7 +604,8 @@ static int do_one_pass(journal_t *journal,
 						       "checksum recovering "
 						       "block %llu in log\n",
 						       blocknr);
-						continue;
+						block_error = 1;
+						goto skip_write;
 					}
 
 					/* Find a buffer for the new
@@ -797,7 +804,8 @@ static int do_one_pass(journal_t *journal,
 				success = -EIO;
 		}
 	}
-
+	if (block_error && success == 0)
+		success = -EIO;
 	return success;
 
  failed:
@@ -811,7 +819,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 198c9c10276d..d5e95a175c92 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -91,8 +91,8 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bio.h>
-#endif
 #include <linux/log2.h>
+#endif
 
 static struct kmem_cache *jbd2_revoke_record_cache;
 static struct kmem_cache *jbd2_revoke_table_cache;
@@ -597,7 +597,7 @@ static void write_one_revoke_record(journal_t *journal,
 	offset = *offsetp;
 
 	/* Do we need to leave space at the end for a checksum? */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_revoke_tail);
 
 	/* Make sure we have a descriptor with space left for the record */
@@ -644,7 +644,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
 	struct jbd2_journal_revoke_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 60bb365f54a5..f8a5d6a166fb 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1590,9 +1590,12 @@ int jbd2_journal_stop(handle_t *handle)
 	 * to perform a synchronous write.  We do this to detect the
 	 * case where a single process is doing a stream of sync
 	 * writes.  No point in waiting for joiners in that case.
+	 *
+	 * Setting max_batch_time to 0 disables this completely.
 	 */
 	pid = current->pid;
-	if (handle->h_sync && journal->j_last_sync_writer != pid) {
+	if (handle->h_sync && journal->j_last_sync_writer != pid &&
+	    journal->j_max_batch_time) {
 		u64 commit_time, trans_time;
 
 		journal->j_last_sync_writer = pid;
diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c
index 16a5047903a6..406d9cc84ba8 100644
--- a/fs/jffs2/compr_rtime.c
+++ b/fs/jffs2/compr_rtime.c
@@ -33,7 +33,7 @@ static int jffs2_rtime_compress(unsigned char *data_in,
 				unsigned char *cpage_out,
 				uint32_t *sourcelen, uint32_t *dstlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;
 
@@ -74,7 +74,7 @@ static int jffs2_rtime_decompress(unsigned char *data_in,
 				  unsigned char *cpage_out,
 				  uint32_t srclen, uint32_t destlen)
 {
-	short positions[256];
+	unsigned short positions[256];
 	int outpos = 0;
 	int pos=0;
 
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index a69e426435dd..5b234db85854 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c,
 	struct inode *inode = OFNI_EDONI_2SFFJ(f);
 	struct page *pg;
 
-	pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
+	pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
 			     (void *)jffs2_do_readpage_unlock, inode);
 	if (IS_ERR(pg))
 		return (void *)pg;
diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h
index 413ef89c2d1b..046fee8b6e9b 100644
--- a/fs/jffs2/jffs2_fs_sb.h
+++ b/fs/jffs2/jffs2_fs_sb.h
@@ -134,8 +134,6 @@ struct jffs2_sb_info {
 	struct rw_semaphore wbuf_sem;	/* Protects the write buffer */
 
 	struct delayed_work wbuf_dwork; /* write-buffer write-out work */
-	int wbuf_queued;                /* non-zero delayed work is queued */
-	spinlock_t wbuf_dwork_lock;     /* protects wbuf_dwork and and wbuf_queued */
 
 	unsigned char *oobbuf;
 	int oobavail; /* How many bytes are available for JFFS2 in OOB */
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index e4619b00f7c5..fa35ff79ab35 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -231,7 +231,7 @@ struct jffs2_tmp_dnode_info
 	uint32_t version;
 	uint32_t data_crc;
 	uint32_t partial_crc;
-	uint16_t csize;
+	uint32_t csize;
 	uint16_t overlapped;
 };
 
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index 03310721712f..b6bd4affd9ad 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -179,6 +179,7 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
 					spin_unlock(&c->erase_completion_lock);
 
 					schedule();
+					remove_wait_queue(&c->erase_wait, &wait);
 				} else
 					spin_unlock(&c->erase_completion_lock);
 			} else if (ret)
@@ -211,20 +212,25 @@ out:
 int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
 			   uint32_t *len, uint32_t sumsize)
 {
-	int ret = -EAGAIN;
+	int ret;
 	minsize = PAD(minsize);
 
 	jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize);
 
-	spin_lock(&c->erase_completion_lock);
-	while(ret == -EAGAIN) {
+	while (true) {
+		spin_lock(&c->erase_completion_lock);
 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
 		if (ret) {
 			jffs2_dbg(1, "%s(): looping, ret is %d\n",
 				  __func__, ret);
 		}
+		spin_unlock(&c->erase_completion_lock);
+
+		if (ret == -EAGAIN)
+			cond_resched();
+		else
+			break;
 	}
-	spin_unlock(&c->erase_completion_lock);
 	if (!ret)
 		ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);
 
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index a6597d60d76d..09ed55190ee2 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work)
 	struct jffs2_sb_info *c = work_to_sb(work);
 	struct super_block *sb = OFNI_BS_2SFFJ(c);
 
-	spin_lock(&c->wbuf_dwork_lock);
-	c->wbuf_queued = 0;
-	spin_unlock(&c->wbuf_dwork_lock);
-
 	if (!(sb->s_flags & MS_RDONLY)) {
 		jffs2_dbg(1, "%s()\n", __func__);
 		jffs2_flush_wbuf_gc(c, 0);
@@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c)
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
-	spin_lock(&c->wbuf_dwork_lock);
-	if (!c->wbuf_queued) {
+	delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+	if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay))
 		jffs2_dbg(1, "%s()\n", __func__);
-		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-		queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay);
-		c->wbuf_queued = 1;
-	}
-	spin_unlock(&c->wbuf_dwork_lock);
 }
 
 int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
@@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
 
 	/* Initialise write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize = c->mtd->writesize;
 	c->wbuf_ofs = 0xFFFFFFFF;
@@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize =  c->mtd->erasesize;
 
@@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize = c->mtd->writesize;
@@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) {
 		return 0;
 
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize =  c->mtd->writesize;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index bd6e18be6e1a..39c0143fb3af 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -37,7 +37,7 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns)
 	hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
 	hash &= 0x7fffffffU;
 	/* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
-	if (hash < 1)
+	if (hash < 2)
 		hash += 2;
 	if (hash >= INT_MAX)
 		hash = INT_MAX - 1;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index dbf397bfdff2..d29640b49be3 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -476,6 +476,8 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ops = kernfs_ops(of->kn);
 	rc = ops->mmap(of, vma);
+	if (rc)
+		goto out_put;
 
 	/*
 	 * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index e55126f85bd2..553946c9d952 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -48,14 +48,18 @@ void __init kernfs_inode_init(void)
 
 static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
 {
+	static DEFINE_MUTEX(iattr_mutex);
+	struct kernfs_iattrs *ret;
 	struct iattr *iattrs;
 
+	mutex_lock(&iattr_mutex);
+
 	if (kn->iattr)
-		return kn->iattr;
+		goto out_unlock;
 
 	kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL);
 	if (!kn->iattr)
-		return NULL;
+		goto out_unlock;
 	iattrs = &kn->iattr->ia_iattr;
 
 	/* assign default attributes */
@@ -65,8 +69,10 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
 	iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
 
 	simple_xattrs_init(&kn->iattr->xattrs);
-
-	return kn->iattr;
+out_unlock:
+	ret = kn->iattr;
+	mutex_unlock(&iattr_mutex);
+	return ret;
 }
 
 static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1812f026960c..6ae664b489af 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
 
 	msg.rpc_proc = &clnt->cl_procinfo[proc];
 	status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+	if (status == -ECONNREFUSED) {
+		dprintk("lockd:	NSM upcall RPC failed, status=%d, forcing rebind\n",
+				status);
+		rpc_force_rebind(clnt);
+		status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+	}
 	if (status < 0)
 		dprintk("lockd: NSM upcall RPC failed, status=%d\n",
 				status);
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 10d6c41aecad..223e1cb14345 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -235,6 +235,7 @@ out_err:
 	if (warned++ == 0)
 		printk(KERN_WARNING
 			"lockd_up: makesock failed, error=%d\n", err);
+	svc_shutdown_net(serv, net);
 	return err;
 }
 
@@ -252,13 +253,11 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net)
 
 	error = make_socks(serv, net);
 	if (error < 0)
-		goto err_socks;
+		goto err_bind;
 	set_grace_period(net);
 	dprintk("lockd_up_net: per-net data created; net=%p\n", net);
 	return 0;
 
-err_socks:
-	svc_rpcb_cleanup(serv, net);
 err_bind:
 	ln->nlmsvc_users--;
 	return error;
diff --git a/fs/locks.c b/fs/locks.c
index 92a0f0a52b06..2c61c4e9368c 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1376,11 +1376,10 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 
 restart:
 	break_time = flock->fl_break_time;
-	if (break_time != 0) {
+	if (break_time != 0)
 		break_time -= jiffies;
-		if (break_time == 0)
-			break_time++;
-	}
+	if (break_time == 0)
+		break_time++;
 	locks_insert_block(flock, new_fl);
 	spin_unlock(&inode->i_lock);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
@@ -2236,16 +2235,28 @@ void locks_remove_flock(struct file *filp)
 
 	while ((fl = *before) != NULL) {
 		if (fl->fl_file == filp) {
-			if (IS_FLOCK(fl)) {
-				locks_delete_lock(before);
-				continue;
-			}
 			if (IS_LEASE(fl)) {
 				lease_modify(before, F_UNLCK);
 				continue;
 			}
-			/* What? */
-			BUG();
+
+			/*
+			 * There's a leftover lock on the list of a type that
+			 * we didn't expect to see. Most likely a classic
+			 * POSIX lock that ended up not getting released
+			 * properly, or that raced onto the list somehow. Log
+			 * some info about it and then just remove it from
+			 * the list.
+			 */
+			WARN(!IS_FLOCK(fl),
+				"leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n",
+				MAJOR(inode->i_sb->s_dev),
+				MINOR(inode->i_sb->s_dev), inode->i_ino,
+				fl->fl_type, fl->fl_flags,
+				fl->fl_start, fl->fl_end);
+
+			locks_delete_lock(before);
+			continue;
  		}
 		before = &fl->fl_next;
 	}
diff --git a/fs/namei.c b/fs/namei.c
index 4b491b431990..0dd72c8e65fd 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -34,6 +34,7 @@
 #include <linux/device_cgroup.h>
 #include <linux/fs_struct.h>
 #include <linux/posix_acl.h>
+#include <linux/hash.h>
 #include <asm/uaccess.h>
 
 #include "internal.h"
@@ -332,10 +333,11 @@ int generic_permission(struct inode *inode, int mask)
 
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 		if (!(mask & MAY_WRITE))
-			if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+			if (capable_wrt_inode_uidgid(inode,
+						     CAP_DAC_READ_SEARCH))
 				return 0;
 		return -EACCES;
 	}
@@ -345,7 +347,7 @@ int generic_permission(struct inode *inode, int mask)
 	 * at least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 
 	/*
@@ -353,7 +355,7 @@ int generic_permission(struct inode *inode, int mask)
 	 */
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 	if (mask == MAY_READ)
-		if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
 			return 0;
 
 	return -EACCES;
@@ -640,24 +642,22 @@ static int complete_walk(struct nameidata *nd)
 
 static __always_inline void set_root(struct nameidata *nd)
 {
-	if (!nd->root.mnt)
-		get_fs_root(current->fs, &nd->root);
+	get_fs_root(current->fs, &nd->root);
 }
 
 static int link_path_walk(const char *, struct nameidata *);
 
-static __always_inline void set_root_rcu(struct nameidata *nd)
+static __always_inline unsigned set_root_rcu(struct nameidata *nd)
 {
-	if (!nd->root.mnt) {
-		struct fs_struct *fs = current->fs;
-		unsigned seq;
+	struct fs_struct *fs = current->fs;
+	unsigned seq, res;
 
-		do {
-			seq = read_seqcount_begin(&fs->seq);
-			nd->root = fs->root;
-			nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
-		} while (read_seqcount_retry(&fs->seq, seq));
-	}
+	do {
+		seq = read_seqcount_begin(&fs->seq);
+		nd->root = fs->root;
+		res = __read_seqcount_begin(&nd->root.dentry->d_seq);
+	} while (read_seqcount_retry(&fs->seq, seq));
+	return res;
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -857,7 +857,8 @@ follow_link(struct path *link, struct nameidata *nd, void **p)
 			return PTR_ERR(s);
 		}
 		if (*s == '/') {
-			set_root(nd);
+			if (!nd->root.mnt)
+				set_root(nd);
 			path_put(&nd->path);
 			nd->path = nd->root;
 			path_get(&nd->root);
@@ -1130,7 +1131,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 
 static int follow_dotdot_rcu(struct nameidata *nd)
 {
-	set_root_rcu(nd);
+	if (!nd->root.mnt)
+		set_root_rcu(nd);
 
 	while (1) {
 		if (nd->path.dentry == nd->root.dentry &&
@@ -1242,7 +1244,8 @@ static void follow_mount(struct path *path)
 
 static void follow_dotdot(struct nameidata *nd)
 {
-	set_root(nd);
+	if (!nd->root.mnt)
+		set_root(nd);
 
 	while(1) {
 		struct dentry *old = nd->path.dentry;
@@ -1537,7 +1540,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path,
 		inode = path->dentry->d_inode;
 	}
 	err = -ENOENT;
-	if (!inode)
+	if (!inode || d_is_negative(path->dentry))
 		goto out_path_put;
 
 	if (should_follow_link(path->dentry, follow)) {
@@ -1623,8 +1626,7 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
 
 static inline unsigned int fold_hash(unsigned long hash)
 {
-	hash += hash >> (8*sizeof(int));
-	return hash;
+	return hash_64(hash, 32);
 }
 
 #else	/* 32-bit case */
@@ -1796,7 +1798,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			if (err)
 				return err;
 		}
-		if (!d_is_directory(nd->path.dentry)) {
+		if (!d_can_lookup(nd->path.dentry)) {
 			err = -ENOTDIR; 
 			break;
 		}
@@ -1817,7 +1819,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
 		if (*name) {
-			if (!d_is_directory(root))
+			if (!d_can_lookup(root))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
 			if (retval)
@@ -1841,7 +1843,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	if (*name=='/') {
 		if (flags & LOOKUP_RCU) {
 			rcu_read_lock();
-			set_root_rcu(nd);
+			nd->seq = set_root_rcu(nd);
 		} else {
 			set_root(nd);
 			path_get(&nd->root);
@@ -1873,7 +1875,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		dentry = f.file->f_path.dentry;
 
 		if (*name) {
-			if (!d_is_directory(dentry)) {
+			if (!d_can_lookup(dentry)) {
 				fdput(f);
 				return -ENOTDIR;
 			}
@@ -1955,7 +1957,7 @@ static int path_lookupat(int dfd, const char *name,
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY) {
-		if (!d_is_directory(nd->path.dentry)) {
+		if (!d_can_lookup(nd->path.dentry)) {
 			path_put(&nd->path);
 			err = -ENOTDIR;
 		}
@@ -2240,15 +2242,16 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 	mutex_unlock(&dir->d_inode->i_mutex);
 
 done:
-	if (!dentry->d_inode) {
+	if (!dentry->d_inode || d_is_negative(dentry)) {
 		error = -ENOENT;
 		dput(dentry);
 		goto out;
 	}
 	path->dentry = dentry;
-	path->mnt = mntget(nd->path.mnt);
+	path->mnt = nd->path.mnt;
 	if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW))
 		return 1;
+	mntget(path->mnt);
 	follow_mount(path);
 	error = 0;
 out:
@@ -2370,7 +2373,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
 		return 0;
 	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
-	return !inode_capable(inode, CAP_FOWNER);
+	return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
 }
 
 /*
@@ -2414,11 +2417,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
 		return -EPERM;
 	if (isdir) {
-		if (!d_is_directory(victim) && !d_is_autodir(victim))
+		if (!d_is_dir(victim))
 			return -ENOTDIR;
 		if (IS_ROOT(victim))
 			return -EBUSY;
-	} else if (d_is_directory(victim) || d_is_autodir(victim))
+	} else if (d_is_dir(victim))
 		return -EISDIR;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
@@ -2982,7 +2985,7 @@ retry_lookup:
 finish_lookup:
 	/* we _can_ be in RCU mode here */
 	error = -ENOENT;
-	if (d_is_negative(path->dentry)) {
+	if (!inode || d_is_negative(path->dentry)) {
 		path_to_nameidata(path, nd);
 		goto out;
 	}
@@ -3016,11 +3019,10 @@ finish_open:
 	}
 	audit_inode(name, nd->path.dentry, 0);
 	error = -EISDIR;
-	if ((open_flag & O_CREAT) &&
-	    (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry)))
+	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
 	error = -ENOTDIR;
-	if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry))
+	if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
 		goto out;
 	if (!S_ISREG(nd->inode->i_mode))
 		will_truncate = false;
@@ -3126,7 +3128,8 @@ static int do_tmpfile(int dfd, struct filename *pathname,
 	if (error)
 		goto out2;
 	audit_inode(pathname, nd->path.dentry, 0);
-	error = may_open(&nd->path, op->acc_mode, op->open_flag);
+	/* Don't check for other permissions, the inode was just created */
+	error = may_open(&nd->path, MAY_OPEN, op->open_flag);
 	if (error)
 		goto out2;
 	file->f_path.mnt = nd->path.mnt;
@@ -3744,7 +3747,7 @@ exit1:
 slashes:
 	if (d_is_negative(dentry))
 		error = -ENOENT;
-	else if (d_is_directory(dentry) || d_is_autodir(dentry))
+	else if (d_is_dir(dentry))
 		error = -EISDIR;
 	else
 		error = -ENOTDIR;
@@ -4123,7 +4126,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	       struct inode **delegated_inode)
 {
 	int error;
-	int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry);
+	int is_dir = d_is_dir(old_dentry);
 	const unsigned char *old_name;
 
 	if (old_dentry->d_inode == new_dentry->d_inode)
@@ -4216,7 +4219,7 @@ retry_deleg:
 	if (d_is_negative(old_dentry))
 		goto exit4;
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
-	if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) {
+	if (!d_is_dir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
 			goto exit4;
diff --git a/fs/namespace.c b/fs/namespace.c
index 2ffc5a2905d4..039f3802d70e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -777,6 +777,20 @@ static void attach_mnt(struct mount *mnt,
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
 }
 
+static void attach_shadowed(struct mount *mnt,
+			struct mount *parent,
+			struct mount *shadows)
+{
+	if (shadows) {
+		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
+		list_add(&mnt->mnt_child, &shadows->mnt_child);
+	} else {
+		hlist_add_head_rcu(&mnt->mnt_hash,
+				m_hash(&parent->mnt, mnt->mnt_mountpoint));
+		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	}
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -795,12 +809,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 
 	list_splice(&head, n->list.prev);
 
-	if (shadows)
-		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
-	else
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	attach_shadowed(mnt, parent, shadows);
 	touch_mnt_namespace(n);
 }
 
@@ -885,10 +894,23 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
 	/* Don't allow unprivileged users to change mount flags */
-	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
-		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+	if (flag & CL_UNPRIVILEGED) {
+		mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
+
+		if (mnt->mnt.mnt_flags & MNT_READONLY)
+			mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
+		if (mnt->mnt.mnt_flags & MNT_NODEV)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
+
+		if (mnt->mnt.mnt_flags & MNT_NOSUID)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
+
+		if (mnt->mnt.mnt_flags & MNT_NOEXEC)
+			mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
+	}
 
 	/* Don't allow unprivileged users to reveal what is under a mount */
 	if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire))
@@ -1204,6 +1226,11 @@ static void namespace_unlock(void)
 	head.first->pprev = &head.first;
 	INIT_HLIST_HEAD(&unmounted);
 
+	/* undo decrements we'd done in umount_tree() */
+	hlist_for_each_entry(mnt, &head, mnt_hash)
+		if (mnt->mnt_ex_mountpoint.mnt)
+			mntget(mnt->mnt_ex_mountpoint.mnt);
+
 	up_write(&namespace_sem);
 
 	synchronize_rcu();
@@ -1240,6 +1267,9 @@ void umount_tree(struct mount *mnt, int how)
 		hlist_add_head(&p->mnt_hash, &tmp_list);
 	}
 
+	hlist_for_each_entry(p, &tmp_list, mnt_hash)
+		list_del_init(&p->mnt_child);
+
 	if (how)
 		propagate_umount(&tmp_list);
 
@@ -1250,9 +1280,9 @@ void umount_tree(struct mount *mnt, int how)
 		p->mnt_ns = NULL;
 		if (how < 2)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
-		list_del_init(&p->mnt_child);
 		if (mnt_has_parent(p)) {
 			put_mountpoint(p->mnt_mp);
+			mnt_add_count(p->mnt_parent, -1);
 			/* move the reference to mountpoint into ->mnt_ex_mountpoint */
 			p->mnt_ex_mountpoint.dentry = p->mnt_mountpoint;
 			p->mnt_ex_mountpoint.mnt = &p->mnt_parent->mnt;
@@ -1265,6 +1295,8 @@ void umount_tree(struct mount *mnt, int how)
 	}
 	if (last) {
 		last->mnt_hash.next = unmounted.first;
+		if (unmounted.first)
+			unmounted.first->pprev = &last->mnt_hash.next;
 		unmounted.first = tmp_list.first;
 		unmounted.first->pprev = &unmounted.first;
 	}
@@ -1335,6 +1367,8 @@ static int do_umount(struct mount *mnt, int flags)
 		 * Special case for "unmounting" root ...
 		 * we just try to remount it readonly.
 		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!(sb->s_flags & MS_RDONLY))
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
@@ -1407,6 +1441,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 		goto dput_and_out;
 	if (mnt->mnt.mnt_flags & MNT_LOCKED)
 		goto dput_and_out;
+	retval = -EPERM;
+	if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
+		goto dput_and_out;
 
 	retval = do_umount(mnt, flags);
 dput_and_out:
@@ -1483,6 +1520,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
+			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1504,7 +1542,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			attach_mnt(q, parent, p->mnt_mp);
+			mnt_set_mountpoint(parent, p->mnt_mp, q);
+			if (!list_empty(&parent->mnt_mounts)) {
+				t = list_last_entry(&parent->mnt_mounts,
+					struct mount, mnt_child);
+				if (t->mnt_mp != p->mnt_mp)
+					t = NULL;
+			}
+			attach_shadowed(q, parent, t);
 			unlock_mount_hash();
 		}
 	}
@@ -1661,9 +1706,9 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		if (err)
 			goto out;
 		err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+		lock_mount_hash();
 		if (err)
 			goto out_cleanup_ids;
-		lock_mount_hash();
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
 	} else {
@@ -1690,6 +1735,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	return 0;
 
  out_cleanup_ids:
+	while (!hlist_empty(&tree_list)) {
+		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+		umount_tree(child, 0);
+	}
+	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	return err;
@@ -1882,9 +1932,6 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 	if (readonly_request == __mnt_is_readonly(mnt))
 		return 0;
 
-	if (mnt->mnt_flags & MNT_LOCK_READONLY)
-		return -EPERM;
-
 	if (readonly_request)
 		error = mnt_make_readonly(real_mount(mnt));
 	else
@@ -1910,6 +1957,39 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
+	/* Don't allow changing of locked mnt flags.
+	 *
+	 * No locks need to be held here while testing the various
+	 * MNT_LOCK flags because those flags can never be cleared
+	 * once they are set.
+	 */
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+	    !(mnt_flags & MNT_READONLY)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+	    !(mnt_flags & MNT_NODEV)) {
+		/* Was the nodev implicitly added in mount? */
+		if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
+		    !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
+			mnt_flags |= MNT_NODEV;
+		} else {
+			return -EPERM;
+		}
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
+	    !(mnt_flags & MNT_NOSUID)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
+	    !(mnt_flags & MNT_NOEXEC)) {
+		return -EPERM;
+	}
+	if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+	    ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
+		return -EPERM;
+	}
+
 	err = security_sb_remount(sb, data);
 	if (err)
 		return err;
@@ -1923,7 +2003,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 		err = do_remount_sb(sb, flags, data, 0);
 	if (!err) {
 		lock_mount_hash();
-		mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
+		mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
 		mnt->mnt.mnt_flags = mnt_flags;
 		touch_mnt_namespace(mnt->mnt_ns);
 		unlock_mount_hash();
@@ -2044,7 +2124,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 	struct mount *parent;
 	int err;
 
-	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
+	mnt_flags &= ~MNT_INTERNAL_FLAGS;
 
 	mp = lock_mount(path);
 	if (IS_ERR(mp))
@@ -2108,7 +2188,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 		 */
 		if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
 			flags |= MS_NODEV;
-			mnt_flags |= MNT_NODEV;
+			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
 		}
 	}
 
@@ -2422,6 +2502,14 @@ long do_mount(const char *dev_name, const char *dir_name,
 	if (flags & MS_RDONLY)
 		mnt_flags |= MNT_READONLY;
 
+	/* The default atime for remount is preservation */
+	if ((flags & MS_REMOUNT) &&
+	    ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
+		       MS_STRICTATIME)) == 0)) {
+		mnt_flags &= ~MNT_ATIME_MASK;
+		mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
+	}
+
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
 		   MS_STRICTATIME);
@@ -2754,6 +2842,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* make sure we can reach put_old from new_root */
 	if (!is_path_reachable(old_mnt, old.dentry, &new))
 		goto out4;
+	/* make certain new is below the root */
+	if (!is_path_reachable(new_mnt, new.dentry, &root))
+		goto out4;
 	root_mp->m_count++; /* pin it so it won't go away */
 	lock_mount_hash();
 	detach_mnt(new_mnt, &parent_path);
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 60426ccb3b65..2f970de02b16 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -448,7 +448,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 						result = -EIO;
 					}
 				}
-				result = 0;
 			}
 			mutex_unlock(&server->root_setup_lock);
 
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 56ff823ca82e..65d849bdf77a 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
 	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
 	if (end != NFS_I(inode)->npages) {
 		rcu_read_lock();
-		end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+		end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
 		rcu_read_unlock();
 	}
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5d8ccecf5f5c..3ed1be9aade3 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -109,6 +109,8 @@ again:
 			continue;
 		if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
 			continue;
+		if (!nfs4_valid_open_stateid(state))
+			continue;
 		if (!nfs4_stateid_match(&state->stateid, stateid))
 			continue;
 		get_nfs_open_context(ctx);
@@ -177,7 +179,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *
 {
 	int res = 0;
 
-	res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
+	if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+		res = nfs4_proc_delegreturn(inode,
+				delegation->cred,
+				&delegation->stateid,
+				issync);
 	nfs_free_delegation(delegation);
 	return res;
 }
@@ -364,11 +370,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	int err;
+	int err = 0;
 
 	if (delegation == NULL)
 		return 0;
 	do {
+		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+			break;
 		err = nfs_delegation_claim_opens(inode, &delegation->stateid);
 		if (!issync || err != -EAGAIN)
 			break;
@@ -589,10 +597,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl
 	rcu_read_unlock();
 }
 
+static void nfs_revoke_delegation(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation != NULL) {
+		set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
+		nfs_mark_return_delegation(NFS_SERVER(inode), delegation);
+	}
+	rcu_read_unlock();
+}
+
 void nfs_remove_bad_delegation(struct inode *inode)
 {
 	struct nfs_delegation *delegation;
 
+	nfs_revoke_delegation(inode);
 	delegation = nfs_inode_detach_delegation(inode);
 	if (delegation) {
 		nfs_inode_find_state_and_recover(inode, &delegation->stateid);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9a79c7a99d6d..e02b090ab9da 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -31,6 +31,7 @@ enum {
 	NFS_DELEGATION_RETURN_IF_CLOSED,
 	NFS_DELEGATION_REFERENCED,
 	NFS_DELEGATION_RETURNING,
+	NFS_DELEGATION_REVOKED,
 };
 
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b8797ae6831f..de2543d3c283 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -178,6 +178,7 @@ static void nfs_direct_req_free(struct kref *kref)
 {
 	struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
 
+	nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo);
 	if (dreq->l_ctx != NULL)
 		nfs_put_lock_context(dreq->l_ctx);
 	if (dreq->ctx != NULL)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 360114ae8b82..6659ce545f15 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -592,7 +592,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
 	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
-	int err;
+	int err = 0;
 
 	trace_nfs_getattr_enter(inode);
 	/* Flush out writes to the server in order to update c/mtime.  */
@@ -1555,18 +1555,20 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_version = fattr->change_attr;
 		}
 	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
-		invalid |= save_cache_validity;
+		nfsi->cache_validity |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
 		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 	} else if (server->caps & NFS_CAP_MTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
 		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
 	} else if (server->caps & NFS_CAP_CTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	/* Check if our cached file size is stale */
@@ -1588,7 +1590,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					(long long)new_isize);
 		}
 	} else
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_PAGECACHE
 				| NFS_INO_REVAL_FORCED);
 
@@ -1596,7 +1599,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 		memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
 	else if (server->caps & NFS_CAP_ATIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATIME
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
@@ -1607,7 +1611,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 		}
 	} else if (server->caps & NFS_CAP_MODE)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1618,7 +1623,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_uid = fattr->uid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1629,7 +1635,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_gid = fattr->gid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER_GROUP)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1642,7 +1649,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 		}
 	} else if (server->caps & NFS_CAP_NLINK)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 871d6eda8dba..24c6898159cc 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -129,7 +129,10 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		.rpc_argp	= &args,
 		.rpc_resp	= &fattr,
 	};
-	int status;
+	int status = 0;
+
+	if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL))
+		goto out;
 
 	status = -EOPNOTSUPP;
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
@@ -247,3 +250,46 @@ const struct xattr_handler *nfs3_xattr_handlers[] = {
 	&posix_acl_default_xattr_handler,
 	NULL,
 };
+
+static int
+nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data,
+		size_t size, ssize_t *result)
+{
+	struct posix_acl *acl;
+	char *p = data + *result;
+
+	acl = get_acl(inode, type);
+	if (IS_ERR_OR_NULL(acl))
+		return 0;
+
+	posix_acl_release(acl);
+
+	*result += strlen(name);
+	*result += 1;
+	if (!size)
+		return 0;
+	if (*result > size)
+		return -ERANGE;
+
+	strcpy(p, name);
+	return 0;
+}
+
+ssize_t
+nfs3_listxattr(struct dentry *dentry, char *data, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	ssize_t result = 0;
+	int error;
+
+	error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS,
+			POSIX_ACL_XATTR_ACCESS, data, size, &result);
+	if (error)
+		return error;
+
+	error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT,
+			POSIX_ACL_XATTR_DEFAULT, data, size, &result);
+	if (error)
+		return error;
+	return result;
+}
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index a462ef0fb5d6..8a18b4a0a4ee 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -926,7 +926,7 @@ static const struct inode_operations nfs3_dir_inode_operations = {
 	.getattr	= nfs_getattr,
 	.setattr	= nfs_setattr,
 #ifdef CONFIG_NFS_V3_ACL
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs3_listxattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
 	.removexattr	= generic_removexattr,
@@ -940,7 +940,7 @@ static const struct inode_operations nfs3_file_inode_operations = {
 	.getattr	= nfs_getattr,
 	.setattr	= nfs_setattr,
 #ifdef CONFIG_NFS_V3_ACL
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs3_listxattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
 	.removexattr	= generic_removexattr,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 0e46d3d1b6cc..1abe4f55dea2 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -482,6 +482,16 @@ int nfs40_walk_client_list(struct nfs_client *new,
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
 		/* If "pos" isn't marked ready, we can't trust the
 		 * remaining fields in "pos" */
 		if (pos->cl_cons_state > NFS_CS_READY) {
@@ -501,15 +511,6 @@ int nfs40_walk_client_list(struct nfs_client *new,
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
 
-		if (pos->rpc_ops != new->rpc_ops)
-			continue;
-
-		if (pos->cl_proto != new->cl_proto)
-			continue;
-
-		if (pos->cl_minorversion != new->cl_minorversion)
-			continue;
-
 		if (pos->cl_clientid != new->cl_clientid)
 			continue;
 
@@ -615,6 +616,16 @@ int nfs41_walk_client_list(struct nfs_client *new,
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
 		/* If "pos" isn't marked ready, we can't trust the
 		 * remaining fields in "pos", especially the client
 		 * ID and serverowner fields.  Wait for CREATE_SESSION
@@ -640,15 +651,6 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		if (pos->cl_cons_state != NFS_CS_READY)
 			continue;
 
-		if (pos->rpc_ops != new->rpc_ops)
-			continue;
-
-		if (pos->cl_proto != new->cl_proto)
-			continue;
-
-		if (pos->cl_minorversion != new->cl_minorversion)
-			continue;
-
 		if (!nfs4_match_clientids(pos, new))
 			continue;
 
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index b9a35c05b60f..5e992fc51e61 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -1330,7 +1330,7 @@ filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
 	struct nfs4_filelayout *flo;
 
 	flo = kzalloc(sizeof(*flo), gfp_flags);
-	return &flo->generic_hdr;
+	return flo != NULL ? &flo->generic_hdr : NULL;
 }
 
 static void
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 450bfedbe2f4..58258ad50d5f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1068,6 +1068,7 @@ static void nfs4_opendata_free(struct kref *kref)
 	dput(p->dentry);
 	nfs_sb_deactive(sb);
 	nfs_fattr_free_names(&p->f_attr);
+	kfree(p->f_attr.mdsthreshold);
 	kfree(p);
 }
 
@@ -1586,7 +1587,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 			nfs_inode_find_state_and_recover(state->inode,
 					stateid);
 			nfs4_schedule_stateid_recovery(server, state);
-			return 0;
+			return -EAGAIN;
 		case -NFS4ERR_DELAY:
 		case -NFS4ERR_GRACE:
 			set_bit(NFS_DELEGATED_STATE, &state->flags);
@@ -2033,46 +2034,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
 	return ret;
 }
 
+static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+{
+	nfs_remove_bad_delegation(state->inode);
+	write_seqlock(&state->seqlock);
+	nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+	write_sequnlock(&state->seqlock);
+	clear_bit(NFS_DELEGATED_STATE, &state->flags);
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+	if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+		nfs_finish_clear_delegation_stateid(state);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	/* NFSv4.0 doesn't allow for delegation recovery on open expire */
+	nfs40_clear_delegation_stateid(state);
+	return nfs4_open_expired(sp, state);
+}
+
 #if defined(CONFIG_NFS_V4_1)
-static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
+static void nfs41_check_delegation_stateid(struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
-	nfs4_stateid *stateid = &state->stateid;
+	nfs4_stateid stateid;
 	struct nfs_delegation *delegation;
-	struct rpc_cred *cred = NULL;
-	int status = -NFS4ERR_BAD_STATEID;
-
-	/* If a state reset has been done, test_stateid is unneeded */
-	if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
-		return;
+	struct rpc_cred *cred;
+	int status;
 
 	/* Get the delegation credential for use by test/free_stateid */
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(state->inode)->delegation);
-	if (delegation != NULL &&
-	    nfs4_stateid_match(&delegation->stateid, stateid)) {
-		cred = get_rpccred(delegation->cred);
-		rcu_read_unlock();
-		status = nfs41_test_stateid(server, stateid, cred);
-		trace_nfs4_test_delegation_stateid(state, NULL, status);
-	} else
+	if (delegation == NULL) {
 		rcu_read_unlock();
+		return;
+	}
+
+	nfs4_stateid_copy(&stateid, &delegation->stateid);
+	cred = get_rpccred(delegation->cred);
+	rcu_read_unlock();
+	status = nfs41_test_stateid(server, &stateid, cred);
+	trace_nfs4_test_delegation_stateid(state, NULL, status);
 
 	if (status != NFS_OK) {
 		/* Free the stateid unless the server explicitly
 		 * informs us the stateid is unrecognized. */
 		if (status != -NFS4ERR_BAD_STATEID)
-			nfs41_free_stateid(server, stateid, cred);
-		nfs_remove_bad_delegation(state->inode);
-
-		write_seqlock(&state->seqlock);
-		nfs4_stateid_copy(&state->stateid, &state->open_stateid);
-		write_sequnlock(&state->seqlock);
-		clear_bit(NFS_DELEGATED_STATE, &state->flags);
+			nfs41_free_stateid(server, &stateid, cred);
+		nfs_finish_clear_delegation_stateid(state);
 	}
 
-	if (cred != NULL)
-		put_rpccred(cred);
+	put_rpccred(cred);
 }
 
 /**
@@ -2116,7 +2131,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st
 {
 	int status;
 
-	nfs41_clear_delegation_stateid(state);
+	nfs41_check_delegation_stateid(state);
 	status = nfs41_check_open_stateid(state);
 	if (status != NFS_OK)
 		status = nfs4_open_expired(sp, state);
@@ -2244,10 +2259,12 @@ static int _nfs4_do_open(struct inode *dir,
 		}
 	}
 
-	if (ctx_th && server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) {
-		opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc();
-		if (!opendata->f_attr.mdsthreshold)
-			goto err_free_label;
+	if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) {
+		if (!opendata->f_attr.mdsthreshold) {
+			opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc();
+			if (!opendata->f_attr.mdsthreshold)
+				goto err_free_label;
+		}
 		opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0];
 	}
 	if (dentry->d_inode != NULL)
@@ -2275,11 +2292,10 @@ static int _nfs4_do_open(struct inode *dir,
 	if (opendata->file_created)
 		*opened |= FILE_CREATED;
 
-	if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server))
+	if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) {
 		*ctx_th = opendata->f_attr.mdsthreshold;
-	else
-		kfree(opendata->f_attr.mdsthreshold);
-	opendata->f_attr.mdsthreshold = NULL;
+		opendata->f_attr.mdsthreshold = NULL;
+	}
 
 	nfs4_label_free(olabel);
 
@@ -2289,7 +2305,6 @@ static int _nfs4_do_open(struct inode *dir,
 err_free_label:
 	nfs4_label_free(olabel);
 err_opendata_put:
-	kfree(opendata->f_attr.mdsthreshold);
 	nfs4_opendata_put(opendata);
 err_put_state_owner:
 	nfs4_put_state_owner(sp);
@@ -2545,6 +2560,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
 	struct inode *inode = calldata->inode;
+	bool is_rdonly, is_wronly, is_rdwr;
 	int call_close = 0;
 
 	dprintk("%s: begin!\n", __func__);
@@ -2552,21 +2568,27 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		goto out_wait;
 
 	task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
-	calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
 	spin_lock(&state->owner->so_lock);
+	is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
+	is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
+	is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
 	/* Calculate the change in open mode */
+	calldata->arg.fmode = 0;
 	if (state->n_rdwr == 0) {
-		if (state->n_rdonly == 0) {
-			call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
-			calldata->arg.fmode &= ~FMODE_READ;
-		}
-		if (state->n_wronly == 0) {
-			call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
-			calldata->arg.fmode &= ~FMODE_WRITE;
-		}
-	}
+		if (state->n_rdonly == 0)
+			call_close |= is_rdonly;
+		else if (is_rdonly)
+			calldata->arg.fmode |= FMODE_READ;
+		if (state->n_wronly == 0)
+			call_close |= is_wronly;
+		else if (is_wronly)
+			calldata->arg.fmode |= FMODE_WRITE;
+	} else if (is_rdwr)
+		calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
+
+	if (calldata->arg.fmode == 0)
+		call_close |= is_rdwr;
+
 	if (!nfs4_valid_open_stateid(state))
 		call_close = 0;
 	spin_unlock(&state->owner->so_lock);
@@ -7234,7 +7256,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
 	int ret = 0;
 
 	if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
-		return 0;
+		return -EAGAIN;
 	task = _nfs41_proc_sequence(clp, cred, false);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
@@ -7567,6 +7589,9 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 
 	dprintk("--> %s\n", __func__);
 
+	/* nfs4_layoutget_release calls pnfs_put_layout_hdr */
+	pnfs_get_layout_hdr(NFS_I(inode)->layout);
+
 	lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
 	if (!lgp->args.layout.pages) {
 		nfs4_layoutget_release(lgp);
@@ -7579,9 +7604,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 	lgp->res.seq_res.sr_slot = NULL;
 	nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
 
-	/* nfs4_layoutget_release calls pnfs_put_layout_hdr */
-	pnfs_get_layout_hdr(NFS_I(inode)->layout);
-
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return ERR_CAST(task);
@@ -8247,7 +8269,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
 	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
 	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
-	.recover_open	= nfs4_open_expired,
+	.recover_open	= nfs40_open_expired,
 	.recover_lock	= nfs4_lock_expired,
 	.establish_clid = nfs4_init_clientid,
 };
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 1720d32ffa54..e1ba58c3d1ad 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work)
 			}
 			nfs_expire_all_delegations(clp);
 		} else {
+			int ret;
+
 			/* Queue an asynchronous RENEW. */
-			ops->sched_state_renewal(clp, cred, renew_flags);
+			ret = ops->sched_state_renewal(clp, cred, renew_flags);
 			put_rpccred(cred);
-			goto out_exp;
+			switch (ret) {
+			default:
+				goto out_exp;
+			case -EAGAIN:
+			case -ENOMEM:
+				break;
+			}
 		}
 	} else {
 		dprintk("%s: failed to call renewd. Reason: lease not expired \n",
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0deb32105ccf..b4f177f1d405 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1456,7 +1456,7 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 	 * server that doesn't support a grace period.
 	 */
 	spin_lock(&sp->so_lock);
-	write_seqcount_begin(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
 	list_for_each_entry(state, &sp->so_states, open_states) {
 		if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1519,13 +1519,13 @@ restart:
 		spin_lock(&sp->so_lock);
 		goto restart;
 	}
-	write_seqcount_end(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 	return 0;
 out_err:
 	nfs4_put_open_state(state);
 	spin_lock(&sp->so_lock);
-	write_seqcount_end(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 	return status;
 }
@@ -1732,7 +1732,8 @@ restart:
 			if (status < 0) {
 				set_bit(ops->owner_flag_bit, &sp->so_flags);
 				nfs4_put_state_owner(sp);
-				return nfs4_recovery_handle_error(clp, status);
+				status = nfs4_recovery_handle_error(clp, status);
+				return (status != 0) ? status : -EAGAIN;
 			}
 
 			nfs4_put_state_owner(sp);
@@ -1741,7 +1742,7 @@ restart:
 		spin_unlock(&clp->cl_lock);
 	}
 	rcu_read_unlock();
-	return status;
+	return 0;
 }
 
 static int nfs4_check_lease(struct nfs_client *clp)
@@ -1788,7 +1789,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 		break;
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-		nfs4_state_clear_reclaim_reboot(clp);
 		nfs4_state_start_reclaim_reboot(clp);
 		break;
 	case -NFS4ERR_CLID_INUSE:
@@ -2370,6 +2370,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			status = nfs4_check_lease(clp);
 			if (status < 0)
 				goto out_error;
+			continue;
 		}
 
 		if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) {
@@ -2391,14 +2392,11 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim reboot";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->reboot_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
-				continue;
-			nfs4_state_end_reclaim_reboot(clp);
-			if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;
+			nfs4_state_end_reclaim_reboot(clp);
 		}
 
 		/* Now recover expired state... */
@@ -2406,9 +2404,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 2ffebf2081ce..27d7f2742592 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -113,7 +113,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c)
 		if (atomic_read(&c->io_count) == 0)
 			break;
 		ret = nfs_wait_bit_killable(&c->flags);
-	} while (atomic_read(&c->io_count) != 0);
+	} while (atomic_read(&c->io_count) != 0 && !ret);
 	finish_wait(wq, &q.wait);
 	return ret;
 }
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 910ed906eb82..05c3a6e6518d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2246,6 +2246,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen;
 	data->version = nfsvers;
 	data->minorversion = nfss->nfs_client->cl_minorversion;
+	data->net = current->nsproxy->net_ns;
 	memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
 		data->nfs_server.addrlen);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 9a3b6a4cd6b9..aaa16b31e21e 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -913,12 +913,14 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 
 	if (nfs_have_delegated_attributes(inode))
 		goto out;
-	if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+	if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
 		return false;
 	smp_rmb();
 	if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
 		return false;
 out:
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		return false;
 	return PageUptodate(page) != 0;
 }
 
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index d190e33d0ec2..dea8c60954ba 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -402,8 +402,10 @@ sort_pacl(struct posix_acl *pacl)
 	 * by uid/gid. */
 	int i, j;
 
-	if (pacl->a_count <= 4)
-		return; /* no users or groups */
+	/* no users or groups */
+	if (!pacl || pacl->a_count <= 4)
+		return;
+
 	i = 1;
 	while (pacl->a_entries[i].e_tag == ACL_USER)
 		i++;
@@ -530,13 +532,12 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
 
 	/*
 	 * ACLs with no ACEs are treated differently in the inheritable
-	 * and effective cases: when there are no inheritable ACEs, we
-	 * set a zero-length default posix acl:
+	 * and effective cases: when there are no inheritable ACEs,
+	 * calls ->set_acl with a NULL ACL structure.
 	 */
-	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) {
-		pacl = posix_acl_alloc(0, GFP_KERNEL);
-		return pacl ? pacl : ERR_PTR(-ENOMEM);
-	}
+	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT))
+		return NULL;
+
 	/*
 	 * When there are no effective ACEs, the following will end
 	 * up setting a 3-element effective posix ACL with all
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7f05cd140de3..f42bbe5fbc0a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -637,9 +637,11 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
 
 static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
+	int maxtime = max_cb_time(clp->net);
 	struct rpc_timeout	timeparms = {
-		.to_initval	= max_cb_time(clp->net),
+		.to_initval	= maxtime,
 		.to_retries	= 0,
+		.to_maxval	= maxtime,
 	};
 	struct rpc_create_args args = {
 		.net		= clp->net,
@@ -670,7 +672,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		clp->cl_cb_session = ses;
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
-		args.protocol = XPRT_TRANSPORT_BC_TCP;
+		args.protocol = conn->cb_xprt->xpt_class->xcl_ident |
+				XPRT_TRANSPORT_BC;
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
@@ -781,8 +784,12 @@ static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
 {
 	if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
 		rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
-		dprintk("%s slot is busy\n", __func__);
-		return false;
+		/* Race breaker */
+		if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+			dprintk("%s slot is busy\n", __func__);
+			return false;
+		}
+		rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
 	}
 	return true;
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 82189b208af3..86f5d3e474bf 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -618,15 +618,6 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	switch (create->cr_type) {
 	case NF4LNK:
-		/* ugh! we have to null-terminate the linktext, or
-		 * vfs_symlink() will choke.  it is always safe to
-		 * null-terminate by brute force, since at worst we
-		 * will overwrite the first byte of the create namelen
-		 * in the XDR buffer, which has already been extracted
-		 * during XDR decode.
-		 */
-		create->cr_linkname[create->cr_linklen] = 0;
-
 		status = nfsd_symlink(rqstp, &cstate->current_fh,
 				      create->cr_name, create->cr_namelen,
 				      create->cr_linkname, create->cr_linklen,
@@ -1252,7 +1243,8 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
 	 */
 	if (argp->opcnt == resp->opcnt)
 		return false;
-
+	if (next->opnum == OP_ILLEGAL)
+		return false;
 	nextd = OPDESC(next);
 	/*
 	 * Rest of 2.6.3.1.1: certain operations will return WRONGSEC
@@ -1359,6 +1351,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 		/* If op is non-idempotent */
 		if (opdesc->op_flags & OP_MODIFIES_SOMETHING) {
 			plen = opdesc->op_rsize_bop(rqstp, op);
+			/*
+			 * If there's still another operation, make sure
+			 * we'll have space to at least encode an error:
+			 */
+			if (resp->opcnt < args->opcnt)
+				plen += COMPOUND_ERR_SLACK_SPACE;
 			op->status = nfsd4_check_resp_size(resp, plen);
 		}
 
@@ -1523,7 +1521,8 @@ static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *o
 
 static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
-	return (op_encode_hdr_size + 2 + 1024) * sizeof(__be32);
+	return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
+								sizeof(__be32);
 }
 
 static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d5d070fbeb35..daa53da1d286 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1078,6 +1078,18 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 		return NULL;
 	}
 	clp->cl_name.len = name.len;
+	INIT_LIST_HEAD(&clp->cl_sessions);
+	idr_init(&clp->cl_stateids);
+	atomic_set(&clp->cl_refcount, 0);
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
+	INIT_LIST_HEAD(&clp->cl_idhash);
+	INIT_LIST_HEAD(&clp->cl_openowners);
+	INIT_LIST_HEAD(&clp->cl_delegations);
+	INIT_LIST_HEAD(&clp->cl_lru);
+	INIT_LIST_HEAD(&clp->cl_callbacks);
+	INIT_LIST_HEAD(&clp->cl_revoked);
+	spin_lock_init(&clp->cl_lock);
+	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
 }
 
@@ -1095,6 +1107,7 @@ free_client(struct nfs4_client *clp)
 		WARN_ON_ONCE(atomic_read(&ses->se_ref));
 		free_session(ses);
 	}
+	rpc_destroy_wait_queue(&clp->cl_cb_waitq);
 	free_svc_cred(&clp->cl_cred);
 	kfree(clp->cl_name.data);
 	idr_destroy(&clp->cl_stateids);
@@ -1196,15 +1209,14 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source)
 	return 0;
 }
 
-static long long
+static int
 compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2)
 {
-	long long res;
-
-	res = o1->len - o2->len;
-	if (res)
-		return res;
-	return (long long)memcmp(o1->data, o2->data, o1->len);
+	if (o1->len < o2->len)
+		return -1;
+	if (o1->len > o2->len)
+		return 1;
+	return memcmp(o1->data, o2->data, o1->len);
 }
 
 static int same_name(const char *n1, const char *n2)
@@ -1347,7 +1359,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 	if (clp == NULL)
 		return NULL;
 
-	INIT_LIST_HEAD(&clp->cl_sessions);
 	ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
 	if (ret) {
 		spin_lock(&nn->client_lock);
@@ -1355,20 +1366,9 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 		spin_unlock(&nn->client_lock);
 		return NULL;
 	}
-	idr_init(&clp->cl_stateids);
-	atomic_set(&clp->cl_refcount, 0);
-	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
-	INIT_LIST_HEAD(&clp->cl_idhash);
-	INIT_LIST_HEAD(&clp->cl_openowners);
-	INIT_LIST_HEAD(&clp->cl_delegations);
-	INIT_LIST_HEAD(&clp->cl_lru);
-	INIT_LIST_HEAD(&clp->cl_callbacks);
-	INIT_LIST_HEAD(&clp->cl_revoked);
-	spin_lock_init(&clp->cl_lock);
 	nfsd4_init_callback(&clp->cl_cb_null);
 	clp->cl_time = get_seconds();
 	clear_bit(0, &clp->cl_cb_slot_busy);
-	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	copy_verf(clp, verf);
 	rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
 	gen_confirm(clp);
@@ -1400,7 +1400,7 @@ add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root)
 static struct nfs4_client *
 find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root)
 {
-	long long cmp;
+	int cmp;
 	struct rb_node *node = root->rb_node;
 	struct nfs4_client *clp;
 
@@ -3713,9 +3713,16 @@ out:
 static __be32
 nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-	if (check_for_locks(stp->st_file, lockowner(stp->st_stateowner)))
+	struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
+
+	if (check_for_locks(stp->st_file, lo))
 		return nfserr_locks_held;
-	release_lock_stateid(stp);
+	/*
+	 * Currently there's a 1-1 lock stateid<->lockowner
+	 * correspondance, and we have to delete the lockowner when we
+	 * delete the lock stateid:
+	 */
+	release_lockowner(lo);
 	return nfs_ok;
 }
 
@@ -4155,6 +4162,10 @@ static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, c
 
 	if (!same_owner_str(&lo->lo_owner, owner, clid))
 		return false;
+	if (list_empty(&lo->lo_owner.so_stateids)) {
+		WARN_ON_ONCE(1);
+		return false;
+	}
 	lst = list_first_entry(&lo->lo_owner.so_stateids,
 			       struct nfs4_ol_stateid, st_perstateowner);
 	return lst->st_file->fi_inode == inode;
@@ -5062,7 +5073,6 @@ nfs4_state_destroy_net(struct net *net)
 	int i;
 	struct nfs4_client *clp = NULL;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	struct rb_node *node, *tmp;
 
 	for (i = 0; i < CLIENT_HASH_SIZE; i++) {
 		while (!list_empty(&nn->conf_id_hashtbl[i])) {
@@ -5071,13 +5081,11 @@ nfs4_state_destroy_net(struct net *net)
 		}
 	}
 
-	node = rb_first(&nn->unconf_name_tree);
-	while (node != NULL) {
-		tmp = node;
-		node = rb_next(tmp);
-		clp = rb_entry(tmp, struct nfs4_client, cl_namenode);
-		rb_erase(tmp, &nn->unconf_name_tree);
-		destroy_client(clp);
+	for (i = 0; i < CLIENT_HASH_SIZE; i++) {
+		while (!list_empty(&nn->unconf_id_hashtbl[i])) {
+			clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash);
+			destroy_client(clp);
+		}
 	}
 
 	kfree(nn->sessionid_hashtbl);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 63f2395c57ed..dd1afa38f2ae 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -602,7 +602,18 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 		READ_BUF(4);
 		READ32(create->cr_linklen);
 		READ_BUF(create->cr_linklen);
-		SAVEMEM(create->cr_linkname, create->cr_linklen);
+		/*
+		 * The VFS will want a null-terminated string, and
+		 * null-terminating in place isn't safe since this might
+		 * end on a page boundary:
+		 */
+		create->cr_linkname =
+				kmalloc(create->cr_linklen + 1, GFP_KERNEL);
+		if (!create->cr_linkname)
+			return nfserr_jukebox;
+		memcpy(create->cr_linkname, p, create->cr_linklen);
+		create->cr_linkname[create->cr_linklen] = '\0';
+		defer_free(argp, kfree, create->cr_linkname);
 		break;
 	case NF4BLK:
 	case NF4CHR:
@@ -1798,6 +1809,9 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components,
 		}
 		else
 			end++;
+		if (found_esc)
+			end = next;
+
 		str = end;
 	}
 	*pp = p;
@@ -2096,8 +2110,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 	err = vfs_getattr(&path, &stat);
 	if (err)
 		goto out_nfserr;
-	if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
-			FATTR4_WORD0_MAXNAME)) ||
+	if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+			FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
 	    (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
 		       FATTR4_WORD1_SPACE_TOTAL))) {
 		err = vfs_statfs(&path, &statfs);
@@ -2483,6 +2497,8 @@ out_acl:
 			goto out;
 	}
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
+		if ((buflen -= 16) < 0)
+			goto out_resource;
 		WRITE32(3);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
 		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
@@ -2499,8 +2515,10 @@ out:
 		security_release_secctx(context, contextlen);
 #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
 	kfree(acl);
-	if (tempfh)
+	if (tempfh) {
 		fh_put(tempfh);
+		kfree(tempfh);
+	}
 	return status;
 out_nfserr:
 	status = nfserrno(err);
@@ -3471,6 +3489,9 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	struct nfsd4_test_stateid_id *stateid, *next;
 	__be32 *p;
 
+	if (nfserr)
+		return nfserr;
+
 	RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
 	*p++ = htonl(test_stateid->ts_num_ids);
 
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index f8f060ffbf4f..6040da8830ff 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp)
 	hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits));
 }
 
-static inline bool
-nfsd_cache_entry_expired(struct svc_cacherep *rp)
-{
-	return rp->c_state != RC_INPROG &&
-	       time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
-}
-
 /*
  * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
  * Also prune the oldest ones when the total exceeds the max number of entries.
@@ -242,8 +235,14 @@ prune_cache_entries(void)
 	long freed = 0;
 
 	list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
-		if (!nfsd_cache_entry_expired(rp) &&
-		    num_drc_entries <= max_drc_entries)
+		/*
+		 * Don't free entries attached to calls that are still
+		 * in-progress, but do keep scanning the list.
+		 */
+		if (rp->c_state == RC_INPROG)
+			continue;
+		if (num_drc_entries <= max_drc_entries &&
+		    time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
 			break;
 		nfsd_reply_cache_free_locked(rp);
 		freed++;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 7f555179bf81..f34d9de802ab 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -699,6 +699,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net)
 	if (err != 0 || fd < 0)
 		return -EINVAL;
 
+	if (svc_alien_sock(net, fd)) {
+		printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__);
+		return -EINVAL;
+	}
+
 	err = nfsd_create_serv(net);
 	if (err != 0)
 		return err;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 30f34ab02137..f417fef17118 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -282,7 +282,7 @@ void		nfsd_lockd_shutdown(void);
  * reason.
  */
 #define	COMPOUND_SLACK_SPACE		140    /* OP_GETFH */
-#define COMPOUND_ERR_SLACK_SPACE	12     /* OP_SETATTR */
+#define COMPOUND_ERR_SLACK_SPACE	16     /* OP_SETATTR */
 
 #define NFSD_LAUNDROMAT_MINTIMEOUT      1   /* seconds */
 
@@ -328,12 +328,15 @@ void		nfsd_lockd_shutdown(void);
 	(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
-	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SECURITY_LABEL)
+#define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
 #else
-#define NFSD4_2_SUPPORTED_ATTRS_WORD2 0
+#define NFSD4_2_SECURITY_ATTRS		0
 #endif
 
+#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
+	NFSD4_2_SECURITY_ATTRS)
+
 static inline u32 nfsd_suppattrs0(u32 minorversion)
 {
 	return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 9a4a5f9e7468..c34e45d1539b 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -221,7 +221,8 @@ static int nfsd_startup_generic(int nrservs)
 	 */
 	ret = nfsd_racache_init(2*nrservs);
 	if (ret)
-		return ret;
+		goto dec_users;
+
 	ret = nfs4_state_start();
 	if (ret)
 		goto out_racache;
@@ -229,6 +230,8 @@ static int nfsd_startup_generic(int nrservs)
 
 out_racache:
 	nfsd_racache_shutdown();
+dec_users:
+	nfsd_users--;
 	return ret;
 }
 
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index b17d93214d01..9c769a47ac5a 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -152,7 +152,7 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
 	type = (stat->mode & S_IFMT);
 
 	*p++ = htonl(nfs_ftypes[type >> 12]);
-	*p++ = htonl((u32) (stat->mode & S_IALLUGO));
+	*p++ = htonl((u32) stat->mode);
 	*p++ = htonl((u32) stat->nlink);
 	*p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
 	*p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 6d7be3f80356..eea5ad188984 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -404,6 +404,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	umode_t		ftype = 0;
 	__be32		err;
 	int		host_err;
+	bool		get_write_count;
 	int		size_change = 0;
 
 	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
@@ -411,10 +412,18 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	if (iap->ia_valid & ATTR_SIZE)
 		ftype = S_IFREG;
 
+	/* Callers that do fh_verify should do the fh_want_write: */
+	get_write_count = !fhp->fh_dentry;
+
 	/* Get inode */
 	err = fh_verify(rqstp, fhp, ftype, accmode);
 	if (err)
 		goto out;
+	if (get_write_count) {
+		host_err = fh_want_write(fhp);
+		if (host_err)
+			return nfserrno(host_err);
+	}
 
 	dentry = fhp->fh_dentry;
 	inode = dentry->d_inode;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 7e350c562e0e..09480c53fd74 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -24,6 +24,7 @@
 #include <linux/buffer_head.h>
 #include <linux/gfp.h>
 #include <linux/mpage.h>
+#include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/aio.h>
 #include "nilfs.h"
@@ -48,6 +49,8 @@ struct nilfs_iget_args {
 	int for_gc;
 };
 
+static int nilfs_iget_test(struct inode *inode, void *opaque);
+
 void nilfs_inode_add_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
@@ -219,10 +222,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
 
 static int nilfs_set_page_dirty(struct page *page)
 {
+	struct inode *inode = page->mapping->host;
 	int ret = __set_page_dirty_nobuffers(page);
 
 	if (page_has_buffers(page)) {
-		struct inode *inode = page->mapping->host;
 		unsigned nr_dirty = 0;
 		struct buffer_head *bh, *head;
 
@@ -245,6 +248,10 @@ static int nilfs_set_page_dirty(struct page *page)
 
 		if (nr_dirty)
 			nilfs_set_file_dirty(inode, nr_dirty);
+	} else if (ret) {
+		unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+		nilfs_set_file_dirty(inode, nr_dirty);
 	}
 	return ret;
 }
@@ -342,6 +349,17 @@ const struct address_space_operations nilfs_aops = {
 	.is_partially_uptodate  = block_is_partially_uptodate,
 };
 
+static int nilfs_insert_inode_locked(struct inode *inode,
+				     struct nilfs_root *root,
+				     unsigned long ino)
+{
+	struct nilfs_iget_args args = {
+		.ino = ino, .root = root, .cno = 0, .for_gc = 0
+	};
+
+	return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
+}
+
 struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 {
 	struct super_block *sb = dir->i_sb;
@@ -377,7 +395,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		err = nilfs_bmap_read(ii->i_bmap, NULL);
 		if (err < 0)
-			goto failed_bmap;
+			goto failed_after_creation;
 
 		set_bit(NILFS_I_BMAP, &ii->i_state);
 		/* No lock is needed; iget() ensures it. */
@@ -393,21 +411,24 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
 	spin_lock(&nilfs->ns_next_gen_lock);
 	inode->i_generation = nilfs->ns_next_generation++;
 	spin_unlock(&nilfs->ns_next_gen_lock);
-	insert_inode_hash(inode);
+	if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
+		err = -EIO;
+		goto failed_after_creation;
+	}
 
 	err = nilfs_init_acl(inode, dir);
 	if (unlikely(err))
-		goto failed_acl; /* never occur. When supporting
+		goto failed_after_creation; /* never occur. When supporting
 				    nilfs_init_acl(), proper cancellation of
 				    above jobs should be considered */
 
 	return inode;
 
- failed_acl:
- failed_bmap:
+ failed_after_creation:
 	clear_nlink(inode);
+	unlock_new_inode(inode);
 	iput(inode);  /* raw_inode will be deleted through
-			 generic_delete_inode() */
+			 nilfs_evict_inode() */
 	goto failed;
 
  failed_ifile_create_inode:
@@ -455,8 +476,8 @@ int nilfs_read_inode_common(struct inode *inode,
 	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
 	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
 	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
-	if (inode->i_nlink == 0 && inode->i_mode == 0)
-		return -EINVAL; /* this inode is deleted */
+	if (inode->i_nlink == 0)
+		return -ESTALE; /* this inode is deleted */
 
 	inode->i_blocks = le64_to_cpu(raw_inode->i_blocks);
 	ii->i_flags = le32_to_cpu(raw_inode->i_flags);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 9de78f08989e..0f84b257932c 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -51,9 +51,11 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
 	int err = nilfs_add_link(dentry, inode);
 	if (!err) {
 		d_instantiate(dentry, inode);
+		unlock_new_inode(inode);
 		return 0;
 	}
 	inode_dec_link_count(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	return err;
 }
@@ -182,6 +184,7 @@ out:
 out_fail:
 	drop_nlink(inode);
 	nilfs_mark_inode_dirty(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	goto out;
 }
@@ -201,11 +204,15 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir,
 	inode_inc_link_count(inode);
 	ihold(inode);
 
-	err = nilfs_add_nondir(dentry, inode);
-	if (!err)
+	err = nilfs_add_link(dentry, inode);
+	if (!err) {
+		d_instantiate(dentry, inode);
 		err = nilfs_transaction_commit(dir->i_sb);
-	else
+	} else {
+		inode_dec_link_count(inode);
+		iput(inode);
 		nilfs_transaction_abort(dir->i_sb);
+	}
 
 	return err;
 }
@@ -243,6 +250,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	nilfs_mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
 out:
 	if (!err)
 		err = nilfs_transaction_commit(dir->i_sb);
@@ -255,6 +263,7 @@ out_fail:
 	drop_nlink(inode);
 	drop_nlink(inode);
 	nilfs_mark_inode_dirty(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 out_dir:
 	drop_nlink(dir);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 287a22c04149..de6323eb0113 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -71,7 +71,7 @@ static int create_fd(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	client_fd = get_unused_fd();
+	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
 	if (client_fd < 0)
 		return client_fd;
 
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 238a5930cb3c..9d7e2b9659cb 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -42,7 +42,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
 {
 	struct {
 		struct file_handle handle;
-		u8 pad[64];
+		u8 pad[MAX_HANDLE_SZ];
 	} f;
 	int size, ret, i;
 
@@ -50,7 +50,7 @@ static int show_mark_fhandle(struct seq_file *m, struct inode *inode)
 	size = f.handle.handle_bytes >> 2;
 
 	ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0);
-	if ((ret == 255) || (ret == -ENOSPC)) {
+	if ((ret == FILEID_INVALID) || (ret < 0)) {
 		WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
 		return 0;
 	}
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index aeb44e879c51..bb6ee06118ca 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -899,7 +899,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 	}
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
@@ -920,7 +920,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 		page_cache_release(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
 
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -2045,11 +2049,19 @@ out_write_size:
 	di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
+	 * lock, or it will cause a deadlock since journal commit threads holds
+	 * this lock and will ask for the page lock when flushing the data.
+	 * put it here to preserve the unlock order.
+	 */
+	ocfs2_unlock_pages(wc);
+
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
-	ocfs2_free_write_ctxt(wc);
+	brelse(wc->w_di_bh);
+	kfree(wc);
 
 	return copied;
 }
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 5b704c63a103..1edcb141f639 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -90,7 +90,6 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		 * information for this bh as it's not marked locally
 		 * uptodate. */
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}
 
@@ -420,7 +419,6 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 
 	if (!buffer_uptodate(bh)) {
 		ret = -EIO;
-		put_bh(bh);
 		mlog_errno(ret);
 	}
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index af3f7aa73e13..1be3398c96f6 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -650,12 +650,9 @@ void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm,
 	clear_bit(bit, res->refmap);
 }
 
-
-void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
 				   struct dlm_lock_resource *res)
 {
-	assert_spin_locked(&res->spinlock);
-
 	res->inflight_locks++;
 
 	mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name,
@@ -663,6 +660,13 @@ void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
 	     __builtin_return_address(0));
 }
 
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+				   struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&res->spinlock);
+	__dlm_lockres_grab_inflight_ref(dlm, res);
+}
+
 void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
 				   struct dlm_lock_resource *res)
 {
@@ -852,10 +856,8 @@ lookup:
 	/* finally add the lockres to its hash bucket */
 	__dlm_insert_lockres(dlm, res);
 
-	/* Grab inflight ref to pin the resource */
-	spin_lock(&res->spinlock);
-	dlm_lockres_grab_inflight_ref(dlm, res);
-	spin_unlock(&res->spinlock);
+	/* since this lockres is new it doesn't not require the spinlock */
+	__dlm_lockres_grab_inflight_ref(dlm, res);
 
 	/* get an extra ref on the mle in case this is a BLOCK
 	 * if so, the creator of the BLOCK may try to put the last
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 7035af09cc03..fe29f7978f81 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -537,7 +537,10 @@ master_here:
 		/* success!  see if any other nodes need recovery */
 		mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
 		     dlm->name, dlm->reco.dead_node, dlm->node_num);
-		dlm_reset_recovery(dlm);
+		spin_lock(&dlm->spinlock);
+		__dlm_reset_recovery(dlm);
+		dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+		spin_unlock(&dlm->spinlock);
 	}
 	dlm_end_recovery(dlm);
 
@@ -695,6 +698,14 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 		if (all_nodes_done) {
 			int ret;
 
+			/* Set this flag on recovery master to avoid
+			 * a new recovery for another dead node start
+			 * before the recovery is not done. That may
+			 * cause recovery hung.*/
+			spin_lock(&dlm->spinlock);
+			dlm->reco.state |= DLM_RECO_STATE_FINALIZE;
+			spin_unlock(&dlm->spinlock);
+
 			/* all nodes are now in DLM_RECO_NODE_DATA_DONE state
 	 		 * just send a finalize message to everyone and
 	 		 * clean up */
@@ -1750,13 +1761,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 				     struct dlm_migratable_lockres *mres)
 {
 	struct dlm_migratable_lock *ml;
-	struct list_head *queue;
+	struct list_head *queue, *iter;
 	struct list_head *tmpq = NULL;
 	struct dlm_lock *newlock = NULL;
 	struct dlm_lockstatus *lksb = NULL;
 	int ret = 0;
 	int i, j, bad;
-	struct dlm_lock *lock = NULL;
+	struct dlm_lock *lock;
 	u8 from = O2NM_MAX_NODES;
 	unsigned int added = 0;
 	__be64 c;
@@ -1791,14 +1802,16 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			/* MIGRATION ONLY! */
 			BUG_ON(!(mres->flags & DLM_MRES_MIGRATION));
 
+			lock = NULL;
 			spin_lock(&res->spinlock);
 			for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
 				tmpq = dlm_list_idx_to_ptr(res, j);
-				list_for_each_entry(lock, tmpq, list) {
-					if (lock->ml.cookie != ml->cookie)
-						lock = NULL;
-					else
+				list_for_each(iter, tmpq) {
+					lock = list_entry(iter,
+						  struct dlm_lock, list);
+					if (lock->ml.cookie == ml->cookie)
 						break;
+					lock = NULL;
 				}
 				if (lock)
 					break;
@@ -2882,8 +2895,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data,
 				BUG();
 			}
 			dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+			__dlm_reset_recovery(dlm);
 			spin_unlock(&dlm->spinlock);
-			dlm_reset_recovery(dlm);
 			dlm_kick_recovery_thread(dlm);
 			break;
 		default:
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3683643f3f0e..b2427623dd6c 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -94,6 +94,14 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     struct inode *inode,
 				     const char *symname);
 
+static int ocfs2_double_lock(struct ocfs2_super *osb,
+			     struct buffer_head **bh1,
+			     struct inode *inode1,
+			     struct buffer_head **bh2,
+			     struct inode *inode2,
+			     int rename);
+
+static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
 
@@ -450,7 +458,6 @@ leave:
 
 	brelse(new_fe_bh);
 	brelse(parent_fe_bh);
-	kfree(si.name);
 	kfree(si.value);
 
 	ocfs2_free_dir_lookup_result(&lookup);
@@ -657,8 +664,10 @@ static int ocfs2_link(struct dentry *old_dentry,
 {
 	handle_t *handle;
 	struct inode *inode = old_dentry->d_inode;
+	struct inode *old_dir = old_dentry->d_parent->d_inode;
 	int err;
 	struct buffer_head *fe_bh = NULL;
+	struct buffer_head *old_dir_bh = NULL;
 	struct buffer_head *parent_fe_bh = NULL;
 	struct ocfs2_dinode *fe = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
@@ -675,19 +684,33 @@ static int ocfs2_link(struct dentry *old_dentry,
 
 	dquot_initialize(dir);
 
-	err = ocfs2_inode_lock_nested(dir, &parent_fe_bh, 1, OI_LS_PARENT);
+	err = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
+			&parent_fe_bh, dir, 0);
 	if (err < 0) {
 		if (err != -ENOENT)
 			mlog_errno(err);
 		return err;
 	}
 
+	/* make sure both dirs have bhs
+	 * get an extra ref on old_dir_bh if old==new */
+	if (!parent_fe_bh) {
+		if (old_dir_bh) {
+			parent_fe_bh = old_dir_bh;
+			get_bh(parent_fe_bh);
+		} else {
+			mlog(ML_ERROR, "%s: no old_dir_bh!\n", osb->uuid_str);
+			err = -EIO;
+			goto out;
+		}
+	}
+
 	if (!dir->i_nlink) {
 		err = -ENOENT;
 		goto out;
 	}
 
-	err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+	err = ocfs2_lookup_ino_from_name(old_dir, old_dentry->d_name.name,
 			old_dentry->d_name.len, &old_de_ino);
 	if (err) {
 		err = -ENOENT;
@@ -780,10 +803,11 @@ out_unlock_inode:
 	ocfs2_inode_unlock(inode, 1);
 
 out:
-	ocfs2_inode_unlock(dir, 1);
+	ocfs2_double_unlock(old_dir, dir);
 
 	brelse(fe_bh);
 	brelse(parent_fe_bh);
+	brelse(old_dir_bh);
 
 	ocfs2_free_dir_lookup_result(&lookup);
 
@@ -992,14 +1016,15 @@ leave:
 }
 
 /*
- * The only place this should be used is rename!
+ * The only place this should be used is rename and link!
  * if they have the same id, then the 1st one is the only one locked.
  */
 static int ocfs2_double_lock(struct ocfs2_super *osb,
 			     struct buffer_head **bh1,
 			     struct inode *inode1,
 			     struct buffer_head **bh2,
-			     struct inode *inode2)
+			     struct inode *inode2,
+			     int rename)
 {
 	int status;
 	struct ocfs2_inode_info *oi1 = OCFS2_I(inode1);
@@ -1029,7 +1054,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 		}
 		/* lock id2 */
 		status = ocfs2_inode_lock_nested(inode2, bh2, 1,
-						 OI_LS_RENAME1);
+				rename == 1 ? OI_LS_RENAME1 : OI_LS_PARENT);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
@@ -1038,7 +1063,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	}
 
 	/* lock id1 */
-	status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_RENAME2);
+	status = ocfs2_inode_lock_nested(inode1, bh1, 1,
+			rename == 1 ?  OI_LS_RENAME2 : OI_LS_PARENT);
 	if (status < 0) {
 		/*
 		 * An error return must mean that no cluster locks
@@ -1138,7 +1164,7 @@ static int ocfs2_rename(struct inode *old_dir,
 
 	/* if old and new are the same, this'll just do one lock. */
 	status = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
-				   &new_dir_bh, new_dir);
+				   &new_dir_bh, new_dir, 1);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -1855,7 +1881,6 @@ bail:
 
 	brelse(new_fe_bh);
 	brelse(parent_fe_bh);
-	kfree(si.name);
 	kfree(si.value);
 	ocfs2_free_dir_lookup_result(&lookup);
 	if (inode_ac)
diff --git a/fs/open.c b/fs/open.c
index b9ed8b25c108..2ed7325f713e 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -641,23 +641,12 @@ out:
 static inline int __get_file_write_access(struct inode *inode,
 					  struct vfsmount *mnt)
 {
-	int error;
-	error = get_write_access(inode);
+	int error = get_write_access(inode);
 	if (error)
 		return error;
-	/*
-	 * Do not take mount writer counts on
-	 * special files since no writes to
-	 * the mount itself will occur.
-	 */
-	if (!special_file(inode->i_mode)) {
-		/*
-		 * Balanced in __fput()
-		 */
-		error = __mnt_want_write(mnt);
-		if (error)
-			put_write_access(inode);
-	}
+	error = __mnt_want_write(mnt);
+	if (error)
+		put_write_access(inode);
 	return error;
 }
 
@@ -690,12 +679,11 @@ static int do_dentry_open(struct file *f,
 
 	path_get(&f->f_path);
 	inode = f->f_inode = f->f_path.dentry->d_inode;
-	if (f->f_mode & FMODE_WRITE) {
+	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
 		error = __get_file_write_access(inode, f->f_path.mnt);
 		if (error)
 			goto cleanup_file;
-		if (!special_file(inode->i_mode))
-			file_take_write(f);
+		file_take_write(f);
 	}
 
 	f->f_mapping = inode->i_mapping;
@@ -742,7 +730,6 @@ static int do_dentry_open(struct file *f,
 cleanup_all:
 	fops_put(f->f_op);
 	if (f->f_mode & FMODE_WRITE) {
-		put_write_access(inode);
 		if (!special_file(inode->i_mode)) {
 			/*
 			 * We don't consider this a real
@@ -750,6 +737,7 @@ cleanup_all:
 			 * because it all happenend right
 			 * here, so just reset the state.
 			 */
+			put_write_access(inode);
 			file_reset_write(f);
 			__mnt_drop_write(f->f_path.mnt);
 		}
diff --git a/fs/pnode.c b/fs/pnode.c
index 88396df725b4..b7f831089500 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -164,46 +164,94 @@ static struct mount *propagation_next(struct mount *m,
 	}
 }
 
-/*
- * return the source mount to be used for cloning
- *
- * @dest 	the current destination mount
- * @last_dest  	the last seen destination mount
- * @last_src  	the last seen source mount
- * @type	return CL_SLAVE if the new mount has to be
- * 		cloned as a slave.
- */
-static struct mount *get_source(struct mount *dest,
-				struct mount *last_dest,
-				struct mount *last_src,
-				int *type)
+static struct mount *next_group(struct mount *m, struct mount *origin)
 {
-	struct mount *p_last_src = NULL;
-	struct mount *p_last_dest = NULL;
-
-	while (last_dest != dest->mnt_master) {
-		p_last_dest = last_dest;
-		p_last_src = last_src;
-		last_dest = last_dest->mnt_master;
-		last_src = last_src->mnt_master;
+	while (1) {
+		while (1) {
+			struct mount *next;
+			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+				return first_slave(m);
+			next = next_peer(m);
+			if (m->mnt_group_id == origin->mnt_group_id) {
+				if (next == origin)
+					return NULL;
+			} else if (m->mnt_slave.next != &next->mnt_slave)
+				break;
+			m = next;
+		}
+		/* m is the last peer */
+		while (1) {
+			struct mount *master = m->mnt_master;
+			if (m->mnt_slave.next != &master->mnt_slave_list)
+				return next_slave(m);
+			m = next_peer(master);
+			if (master->mnt_group_id == origin->mnt_group_id)
+				break;
+			if (master->mnt_slave.next == &m->mnt_slave)
+				break;
+			m = master;
+		}
+		if (m == origin)
+			return NULL;
 	}
+}
 
-	if (p_last_dest) {
-		do {
-			p_last_dest = next_peer(p_last_dest);
-		} while (IS_MNT_NEW(p_last_dest));
-		/* is that a peer of the earlier? */
-		if (dest == p_last_dest) {
-			*type = CL_MAKE_SHARED;
-			return p_last_src;
+/* all accesses are serialized by namespace_sem */
+static struct user_namespace *user_ns;
+static struct mount *last_dest, *last_source, *dest_master;
+static struct mountpoint *mp;
+static struct hlist_head *list;
+
+static int propagate_one(struct mount *m)
+{
+	struct mount *child;
+	int type;
+	/* skip ones added by this propagate_mnt() */
+	if (IS_MNT_NEW(m))
+		return 0;
+	/* skip if mountpoint isn't covered by it */
+	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
+		return 0;
+	if (m->mnt_group_id == last_dest->mnt_group_id) {
+		type = CL_MAKE_SHARED;
+	} else {
+		struct mount *n, *p;
+		for (n = m; ; n = p) {
+			p = n->mnt_master;
+			if (p == dest_master || IS_MNT_MARKED(p)) {
+				while (last_dest->mnt_master != p) {
+					last_source = last_source->mnt_master;
+					last_dest = last_source->mnt_parent;
+				}
+				if (n->mnt_group_id != last_dest->mnt_group_id) {
+					last_source = last_source->mnt_master;
+					last_dest = last_source->mnt_parent;
+				}
+				break;
+			}
 		}
+		type = CL_SLAVE;
+		/* beginning of peer group among the slaves? */
+		if (IS_MNT_SHARED(m))
+			type |= CL_MAKE_SHARED;
 	}
-	/* slave of the earlier, then */
-	*type = CL_SLAVE;
-	/* beginning of peer group among the slaves? */
-	if (IS_MNT_SHARED(dest))
-		*type |= CL_MAKE_SHARED;
-	return last_src;
+
+	/* Notice when we are propagating across user namespaces */
+	if (m->mnt_ns->user_ns != user_ns)
+		type |= CL_UNPRIVILEGED;
+	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
+	if (IS_ERR(child))
+		return PTR_ERR(child);
+	mnt_set_mountpoint(m, mp, child);
+	last_dest = m;
+	last_source = child;
+	if (m->mnt_master != dest_master) {
+		read_seqlock_excl(&mount_lock);
+		SET_MNT_MARK(m->mnt_master);
+		read_sequnlock_excl(&mount_lock);
+	}
+	hlist_add_head(&child->mnt_hash, list);
+	return 0;
 }
 
 /*
@@ -222,56 +270,48 @@ static struct mount *get_source(struct mount *dest,
 int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 		    struct mount *source_mnt, struct hlist_head *tree_list)
 {
-	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
-	struct mount *m, *child;
+	struct mount *m, *n;
 	int ret = 0;
-	struct mount *prev_dest_mnt = dest_mnt;
-	struct mount *prev_src_mnt  = source_mnt;
-	HLIST_HEAD(tmp_list);
-
-	for (m = propagation_next(dest_mnt, dest_mnt); m;
-			m = propagation_next(m, dest_mnt)) {
-		int type;
-		struct mount *source;
-
-		if (IS_MNT_NEW(m))
-			continue;
-
-		source =  get_source(m, prev_dest_mnt, prev_src_mnt, &type);
-
-		/* Notice when we are propagating across user namespaces */
-		if (m->mnt_ns->user_ns != user_ns)
-			type |= CL_UNPRIVILEGED;
-
-		child = copy_tree(source, source->mnt.mnt_root, type);
-		if (IS_ERR(child)) {
-			ret = PTR_ERR(child);
-			tmp_list = *tree_list;
-			tmp_list.first->pprev = &tmp_list.first;
-			INIT_HLIST_HEAD(tree_list);
+
+	/*
+	 * we don't want to bother passing tons of arguments to
+	 * propagate_one(); everything is serialized by namespace_sem,
+	 * so globals will do just fine.
+	 */
+	user_ns = current->nsproxy->mnt_ns->user_ns;
+	last_dest = dest_mnt;
+	last_source = source_mnt;
+	mp = dest_mp;
+	list = tree_list;
+	dest_master = dest_mnt->mnt_master;
+
+	/* all peers of dest_mnt, except dest_mnt itself */
+	for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
+		ret = propagate_one(n);
+		if (ret)
 			goto out;
-		}
+	}
 
-		if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) {
-			mnt_set_mountpoint(m, dest_mp, child);
-			hlist_add_head(&child->mnt_hash, tree_list);
-		} else {
-			/*
-			 * This can happen if the parent mount was bind mounted
-			 * on some subdirectory of a shared/slave mount.
-			 */
-			hlist_add_head(&child->mnt_hash, &tmp_list);
-		}
-		prev_dest_mnt = m;
-		prev_src_mnt  = child;
+	/* all slave groups */
+	for (m = next_group(dest_mnt, dest_mnt); m;
+			m = next_group(m, dest_mnt)) {
+		/* everything in that slave group */
+		n = m;
+		do {
+			ret = propagate_one(n);
+			if (ret)
+				goto out;
+			n = next_peer(n);
+		} while (n != m);
 	}
 out:
-	lock_mount_hash();
-	while (!hlist_empty(&tmp_list)) {
-		child = hlist_entry(tmp_list.first, struct mount, mnt_hash);
-		umount_tree(child, 0);
+	read_seqlock_excl(&mount_lock);
+	hlist_for_each_entry(n, tree_list, mnt_hash) {
+		m = n->mnt_parent;
+		if (m->mnt_master != dest_mnt->mnt_master)
+			CLEAR_MNT_MARK(m->mnt_master);
 	}
-	unlock_mount_hash();
+	read_sequnlock_excl(&mount_lock);
 	return ret;
 }
 
@@ -341,6 +381,7 @@ static void __propagate_umount(struct mount *mnt)
 		 * other children
 		 */
 		if (child && list_empty(&child->mnt_mounts)) {
+			list_del_init(&child->mnt_child);
 			hlist_del_init_rcu(&child->mnt_hash);
 			hlist_add_before_rcu(&child->mnt_hash, &mnt->mnt_hash);
 		}
diff --git a/fs/pnode.h b/fs/pnode.h
index fc28a27fa892..4a246358b031 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -16,6 +16,9 @@
 #define IS_MNT_NEW(m)  (!(m)->mnt_ns)
 #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
 #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
+#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
+#define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
+#define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
 
 #define CL_EXPIRE    		0x01
 #define CL_SLAVE     		0x02
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 11c54fd51e16..0855f772cd41 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -246,6 +246,12 @@ posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p)
 	umode_t mode = 0;
 	int not_equiv = 0;
 
+	/*
+	 * A null ACL can always be presented as mode bits.
+	 */
+	if (!acl)
+		return 0;
+
 	FOREACH_ACL_ENTRY(pa, acl, pe) {
 		switch (pa->e_tag) {
 			case ACL_USER_OBJ:
@@ -723,7 +729,7 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
 		   void *buffer, size_t size)
 {
 	posix_acl_xattr_header *ext_acl = (posix_acl_xattr_header *)buffer;
-	posix_acl_xattr_entry *ext_entry = ext_acl->a_entries;
+	posix_acl_xattr_entry *ext_entry;
 	int real_size, n;
 
 	real_size = posix_acl_xattr_size(acl->a_count);
@@ -731,7 +737,8 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
 		return real_size;
 	if (real_size > size)
 		return -ERANGE;
-	
+
+	ext_entry = ext_acl->a_entries;
 	ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
 
 	for (n=0; n < acl->a_count; n++, ext_entry++) {
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 656e401794de..baf3464bbce0 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -297,15 +297,11 @@ static void render_cap_t(struct seq_file *m, const char *header,
 	seq_puts(m, header);
 	CAP_FOR_EACH_U32(__capi) {
 		seq_printf(m, "%08x",
-			   a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
+			   a->cap[CAP_LAST_U32 - __capi]);
 	}
 	seq_putc(m, '\n');
 }
 
-/* Remove non-existent capabilities */
-#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \
-				CAP_TO_MASK(CAP_LAST_CAP + 1) - 1)
-
 static inline void task_cap(struct seq_file *m, struct task_struct *p)
 {
 	const struct cred *cred;
@@ -319,11 +315,6 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p)
 	cap_bset	= cred->cap_bset;
 	rcu_read_unlock();
 
-	NORM_CAPS(cap_inheritable);
-	NORM_CAPS(cap_permitted);
-	NORM_CAPS(cap_effective);
-	NORM_CAPS(cap_bset);
-
 	render_cap_t(m, "CapInh:\t", &cap_inheritable);
 	render_cap_t(m, "CapPrm:\t", &cap_permitted);
 	render_cap_t(m, "CapEff:\t", &cap_effective);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b9760628e1fd..489ba8caafc0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2555,6 +2555,57 @@ static const struct file_operations proc_projid_map_operations = {
 	.llseek		= seq_lseek,
 	.release	= proc_id_map_release,
 };
+
+static int proc_setgroups_open(struct inode *inode, struct file *file)
+{
+	struct user_namespace *ns = NULL;
+	struct task_struct *task;
+	int ret;
+
+	ret = -ESRCH;
+	task = get_proc_task(inode);
+	if (task) {
+		rcu_read_lock();
+		ns = get_user_ns(task_cred_xxx(task, user_ns));
+		rcu_read_unlock();
+		put_task_struct(task);
+	}
+	if (!ns)
+		goto err;
+
+	if (file->f_mode & FMODE_WRITE) {
+		ret = -EACCES;
+		if (!ns_capable(ns, CAP_SYS_ADMIN))
+			goto err_put_ns;
+	}
+
+	ret = single_open(file, &proc_setgroups_show, ns);
+	if (ret)
+		goto err_put_ns;
+
+	return 0;
+err_put_ns:
+	put_user_ns(ns);
+err:
+	return ret;
+}
+
+static int proc_setgroups_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	int ret = single_release(inode, file);
+	put_user_ns(ns);
+	return ret;
+}
+
+static const struct file_operations proc_setgroups_operations = {
+	.open		= proc_setgroups_open,
+	.write		= proc_setgroups_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_setgroups_release,
+};
 #endif /* CONFIG_USER_NS */
 
 static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
@@ -2663,6 +2714,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	REG("timers",	  S_IRUGO, proc_timers_operations),
@@ -2998,6 +3050,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("uid_map",    S_IRUGO|S_IWUSR, proc_uid_map_operations),
 	REG("gid_map",    S_IRUGO|S_IWUSR, proc_gid_map_operations),
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
 };
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index fb52b548080d..c4b2646b6d7c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/hugetlb.h>
 #include <linux/huge_mm.h>
 #include <linux/mount.h>
@@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	/*
 	 * We remember last_addr rather than next_addr to hit with
-	 * mmap_cache most of the time. We have zero last_addr at
+	 * vmacache most of the time. We have zero last_addr at
 	 * the beginning and also after lseek. We will have -1 last_addr
 	 * after the end of the vmas.
 	 */
@@ -1350,7 +1351,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
 	struct numa_maps *md;
 	struct page *page;
 
-	if (pte_none(*pte))
+	if (!pte_present(*pte))
 		return 0;
 
 	page = pte_page(*pte);
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 12823845d324..14120a3c6195 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -319,10 +319,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 						compressed ? ".enc.z" : "");
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		sprintf(name, "console-%s", psname);
+		sprintf(name, "console-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_FTRACE:
-		sprintf(name, "ftrace-%s", psname);
+		sprintf(name, "ftrace-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_MCE:
 		sprintf(name, "mce-%s-%lld", psname, id);
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index fa8cef2cca3a..e7d95f959333 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -61,6 +61,11 @@ module_param(mem_size, ulong, 0400);
 MODULE_PARM_DESC(mem_size,
 		"size of reserved RAM used to store oops/panic logs");
 
+static unsigned int mem_type;
+module_param(mem_type, uint, 0600);
+MODULE_PARM_DESC(mem_type,
+		"set to 1 to try to use unbuffered memory (default 0)");
+
 static int dump_oops = 1;
 module_param(dump_oops, int, 0600);
 MODULE_PARM_DESC(dump_oops,
@@ -79,6 +84,7 @@ struct ramoops_context {
 	struct persistent_ram_zone *fprz;
 	phys_addr_t phys_addr;
 	unsigned long size;
+	unsigned int memtype;
 	size_t record_size;
 	size_t console_size;
 	size_t ftrace_size;
@@ -353,7 +359,8 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
 		size_t sz = cxt->record_size;
 
 		cxt->przs[i] = persistent_ram_new(*paddr, sz, 0,
-						  &cxt->ecc_info);
+						  &cxt->ecc_info,
+						  cxt->memtype);
 		if (IS_ERR(cxt->przs[i])) {
 			err = PTR_ERR(cxt->przs[i]);
 			dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n",
@@ -383,7 +390,7 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
 		return -ENOMEM;
 	}
 
-	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info);
+	*prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype);
 	if (IS_ERR(*prz)) {
 		int err = PTR_ERR(*prz);
 
@@ -431,6 +438,7 @@ static int ramoops_probe(struct platform_device *pdev)
 	cxt->dump_read_cnt = 0;
 	cxt->size = pdata->mem_size;
 	cxt->phys_addr = pdata->mem_address;
+	cxt->memtype = pdata->mem_type;
 	cxt->record_size = pdata->record_size;
 	cxt->console_size = pdata->console_size;
 	cxt->ftrace_size = pdata->ftrace_size;
@@ -561,6 +569,7 @@ static void ramoops_register_dummy(void)
 
 	dummy_data->mem_size = mem_size;
 	dummy_data->mem_address = mem_address;
+	dummy_data->mem_type = 0;
 	dummy_data->record_size = record_size;
 	dummy_data->console_size = ramoops_console_size;
 	dummy_data->ftrace_size = ramoops_ftrace_size;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index de272d426763..bda61a759b68 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -380,7 +380,8 @@ void persistent_ram_zap(struct persistent_ram_zone *prz)
 	persistent_ram_update_header_ecc(prz);
 }
 
-static void *persistent_ram_vmap(phys_addr_t start, size_t size)
+static void *persistent_ram_vmap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
 	struct page **pages;
 	phys_addr_t page_start;
@@ -392,7 +393,10 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	page_start = start - offset_in_page(start);
 	page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE);
 
-	prot = pgprot_noncached(PAGE_KERNEL);
+	if (memtype)
+		prot = pgprot_noncached(PAGE_KERNEL);
+	else
+		prot = pgprot_writecombine(PAGE_KERNEL);
 
 	pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL);
 	if (!pages) {
@@ -411,8 +415,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size)
 	return vaddr;
 }
 
-static void *persistent_ram_iomap(phys_addr_t start, size_t size)
+static void *persistent_ram_iomap(phys_addr_t start, size_t size,
+		unsigned int memtype)
 {
+	void *va;
+
 	if (!request_mem_region(start, size, "persistent_ram")) {
 		pr_err("request mem region (0x%llx@0x%llx) failed\n",
 			(unsigned long long)size, (unsigned long long)start);
@@ -422,19 +429,24 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size)
 	buffer_start_add = buffer_start_add_locked;
 	buffer_size_add = buffer_size_add_locked;
 
-	return ioremap(start, size);
+	if (memtype)
+		va = ioremap(start, size);
+	else
+		va = ioremap_wc(start, size);
+
+	return va;
 }
 
 static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
-		struct persistent_ram_zone *prz)
+		struct persistent_ram_zone *prz, int memtype)
 {
 	prz->paddr = start;
 	prz->size = size;
 
 	if (pfn_valid(start >> PAGE_SHIFT))
-		prz->vaddr = persistent_ram_vmap(start, size);
+		prz->vaddr = persistent_ram_vmap(start, size, memtype);
 	else
-		prz->vaddr = persistent_ram_iomap(start, size);
+		prz->vaddr = persistent_ram_iomap(start, size, memtype);
 
 	if (!prz->vaddr) {
 		pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__,
@@ -502,7 +514,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz)
 }
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info)
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype)
 {
 	struct persistent_ram_zone *prz;
 	int ret = -ENOMEM;
@@ -513,7 +526,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 		goto err;
 	}
 
-	ret = persistent_ram_buffer_map(start, size, prz);
+	ret = persistent_ram_buffer_map(start, size, prz, memtype);
 	if (ret)
 		goto err;
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index cfc8dcc16043..89da95700c69 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -637,7 +637,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
 			dqstats_inc(DQST_LOOKUPS);
 			err = sb->dq_op->write_dquot(dquot);
 			if (!ret && err)
-				err = ret;
+				ret = err;
 			dqput(dquot);
 			spin_lock(&dq_list_lock);
 		}
@@ -702,6 +702,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	struct dquot *dquot;
 	unsigned long freed = 0;
 
+	spin_lock(&dq_list_lock);
 	head = free_dquots.prev;
 	while (head != &free_dquots && sc->nr_to_scan) {
 		dquot = list_entry(head, struct dquot, dq_free);
@@ -713,6 +714,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		freed++;
 		head = free_dquots.prev;
 	}
+	spin_unlock(&dq_list_lock);
 	return freed;
 }
 
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 1fd2051109a3..af677353a3f5 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -125,6 +125,7 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 				int d_reclen;
 				char *d_name;
 				ino_t d_ino;
+				loff_t cur_pos = deh_offset(deh);
 
 				if (!de_visible(deh))
 					/* it is hidden entry */
@@ -196,8 +197,9 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 				if (local_buf != small_buf) {
 					kfree(local_buf);
 				}
-				// next entry should be looked for with such offset
-				next_pos = deh_offset(deh) + 1;
+
+				/* deh_offset(deh) may be invalid now. */
+				next_pos = cur_pos + 1;
 
 				if (item_moved(&tmp_ih, &path_to_entry)) {
 					set_cpu_key_k_offset(&pos_key,
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ad62bdbb451e..1e4cf9d73130 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3220,8 +3220,14 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	    attr->ia_size != i_size_read(inode)) {
 		error = inode_newsize_ok(inode, attr->ia_size);
 		if (!error) {
+			/*
+			 * Could race against reiserfs_file_release
+			 * if called from NFS, so take tailpack mutex.
+			 */
+			mutex_lock(&REISERFS_I(inode)->tailpack);
 			truncate_setsize(inode, attr->ia_size);
-			reiserfs_vfs_truncate_file(inode);
+			reiserfs_truncate_file(inode, 1);
+			mutex_unlock(&REISERFS_I(inode)->tailpack);
 		}
 	}
 
diff --git a/fs/super.c b/fs/super.c
index 80d5cf2ca765..440ef51cd696 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -81,6 +81,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
 	dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
 	total_objects = dentries + inodes + fs_objects + 1;
+	if (!total_objects)
+		total_objects = 1;
 
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
@@ -112,9 +114,14 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 
 	sb = container_of(shrink, struct super_block, s_shrink);
 
-	if (!grab_super_passive(sb))
-		return 0;
-
+	/*
+	 * Don't call grab_super_passive as it is a potential
+	 * scalability bottleneck. The counts could get updated
+	 * between super_cache_count and super_cache_scan anyway.
+	 * Call to super_cache_count with shrinker_rwsem held
+	 * ensures the safety of call to list_lru_count_node() and
+	 * s_op->nr_cached_objects().
+	 */
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		total_objects = sb->s_op->nr_cached_objects(sb,
 						 sc->nid);
@@ -125,7 +132,6 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 						 sc->nid);
 
 	total_objects = vfs_pressure_ratio(total_objects);
-	drop_super(sb);
 	return total_objects;
 }
 
@@ -276,10 +282,8 @@ void deactivate_locked_super(struct super_block *s)
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
 		cleancache_invalidate_fs(s);
-		fs->kill_sb(s);
-
-		/* caches are now gone, we can safely kill the shrinker now */
 		unregister_shrinker(&s->s_shrink);
+		fs->kill_sb(s);
 
 		put_filesystem(fs);
 		put_super(s);
@@ -802,7 +806,10 @@ void emergency_remount(void)
 
 static DEFINE_IDA(unnamed_dev_ida);
 static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */
-static int unnamed_dev_start = 0; /* don't bother trying below it */
+/* Many userspace utilities consider an FSID of 0 invalid.
+ * Always return at least 1 from get_anon_bdev.
+ */
+static int unnamed_dev_start = 1;
 
 int get_anon_bdev(dev_t *p)
 {
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 810cf6e613e5..5fd2bf18e27d 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -47,12 +47,13 @@ static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
 	ssize_t count;
 	char *buf;
 
-	/* acquire buffer and ensure that it's >= PAGE_SIZE */
+	/* acquire buffer and ensure that it's >= PAGE_SIZE and clear */
 	count = seq_get_buf(sf, &buf);
 	if (count < PAGE_SIZE) {
 		seq_commit(sf, -1);
 		return 0;
 	}
+	memset(buf, 0, PAGE_SIZE);
 
 	/*
 	 * Invoke show().  Control may reach here via seq file lseek even
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index ff8229340cd5..26b69b2d4a45 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -166,15 +166,10 @@ static int do_commit(struct ubifs_info *c)
 	err = ubifs_orphan_end_commit(c);
 	if (err)
 		goto out;
-	old_ltail_lnum = c->ltail_lnum;
-	err = ubifs_log_end_commit(c, new_ltail_lnum);
-	if (err)
-		goto out;
 	err = dbg_check_old_index(c, &zroot);
 	if (err)
 		goto out;
 
-	mutex_lock(&c->mst_mutex);
 	c->mst_node->cmt_no      = cpu_to_le64(c->cmt_no);
 	c->mst_node->log_lnum    = cpu_to_le32(new_ltail_lnum);
 	c->mst_node->root_lnum   = cpu_to_le32(zroot.lnum);
@@ -203,8 +198,9 @@ static int do_commit(struct ubifs_info *c)
 		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
 	else
 		c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS);
-	err = ubifs_write_master(c);
-	mutex_unlock(&c->mst_mutex);
+
+	old_ltail_lnum = c->ltail_lnum;
+	err = ubifs_log_end_commit(c, new_ltail_lnum);
 	if (err)
 		goto out;
 
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 123c79b7261e..b56eb6275744 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1525,8 +1525,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
 	}
 
 	wait_for_stable_page(page);
-	unlock_page(page);
-	return 0;
+	return VM_FAULT_LOCKED;
 
 out_unlock:
 	unlock_page(page);
diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c
index a902c5919e42..8d59de86dc9a 100644
--- a/fs/ubifs/log.c
+++ b/fs/ubifs/log.c
@@ -106,10 +106,14 @@ static inline long long empty_log_bytes(const struct ubifs_info *c)
 	h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs;
 	t = (long long)c->ltail_lnum * c->leb_size;
 
-	if (h >= t)
+	if (h > t)
 		return c->log_bytes - h + t;
-	else
+	else if (h != t)
 		return t - h;
+	else if (c->lhead_lnum != c->ltail_lnum)
+		return 0;
+	else
+		return c->log_bytes;
 }
 
 /**
@@ -447,9 +451,9 @@ out:
  * @ltail_lnum: new log tail LEB number
  *
  * This function is called on when the commit operation was finished. It
- * moves log tail to new position and unmaps LEBs which contain obsolete data.
- * Returns zero in case of success and a negative error code in case of
- * failure.
+ * moves log tail to new position and updates the master node so that it stores
+ * the new log tail LEB number. Returns zero in case of success and a negative
+ * error code in case of failure.
  */
 int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum)
 {
@@ -477,7 +481,12 @@ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum)
 	spin_unlock(&c->buds_lock);
 
 	err = dbg_check_bud_bytes(c);
+	if (err)
+		goto out;
 
+	err = ubifs_write_master(c);
+
+out:
 	mutex_unlock(&c->log_mutex);
 	return err;
 }
diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c
index ab83ace9910a..1a4bb9e8b3b8 100644
--- a/fs/ubifs/master.c
+++ b/fs/ubifs/master.c
@@ -352,10 +352,9 @@ int ubifs_read_master(struct ubifs_info *c)
  * ubifs_write_master - write master node.
  * @c: UBIFS file-system description object
  *
- * This function writes the master node. The caller has to take the
- * @c->mst_mutex lock before calling this function. Returns zero in case of
- * success and a negative error code in case of failure. The master node is
- * written twice to enable recovery.
+ * This function writes the master node. Returns zero in case of success and a
+ * negative error code in case of failure. The master node is written twice to
+ * enable recovery.
  */
 int ubifs_write_master(struct ubifs_info *c)
 {
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index f35135e28e96..9a9fb94a41c6 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -128,7 +128,6 @@ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention)
 			freed = ubifs_destroy_tnc_subtree(znode);
 			atomic_long_sub(freed, &ubifs_clean_zn_cnt);
 			atomic_long_sub(freed, &c->clean_zn_cnt);
-			ubifs_assert(atomic_long_read(&c->clean_zn_cnt) >= 0);
 			total_freed += freed;
 			znode = zprev;
 		}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 5ded8490c0c6..94d9a64287b7 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1957,7 +1957,6 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
 		mutex_init(&c->lp_mutex);
 		mutex_init(&c->tnc_mutex);
 		mutex_init(&c->log_mutex);
-		mutex_init(&c->mst_mutex);
 		mutex_init(&c->umount_mutex);
 		mutex_init(&c->bu_mutex);
 		mutex_init(&c->write_reserve_mutex);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index e8c8cfe1435c..7ab9c710c749 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1042,7 +1042,6 @@ struct ubifs_debug_info;
  *
  * @mst_node: master node
  * @mst_offs: offset of valid master node
- * @mst_mutex: protects the master node area, @mst_node, and @mst_offs
  *
  * @max_bu_buf_len: maximum bulk-read buffer length
  * @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu
@@ -1282,7 +1281,6 @@ struct ubifs_info {
 
 	struct ubifs_mst_node *mst_node;
 	int mst_offs;
-	struct mutex mst_mutex;
 
 	int max_bu_buf_len;
 	struct mutex bu_mutex;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 982ce05c87ed..287cd5f23421 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1271,13 +1271,22 @@ update_time:
 	return 0;
 }
 
+/*
+ * Maximum length of linked list formed by ICB hierarchy. The chosen number is
+ * arbitrary - just that we hopefully don't limit any real use of rewritten
+ * inode on write-once media but avoid looping for too long on corrupted media.
+ */
+#define UDF_MAX_ICB_NESTING 1024
+
 static void __udf_read_inode(struct inode *inode)
 {
 	struct buffer_head *bh = NULL;
 	struct fileEntry *fe;
 	uint16_t ident;
 	struct udf_inode_info *iinfo = UDF_I(inode);
+	unsigned int indirections = 0;
 
+reread:
 	/*
 	 * Set defaults, but the inode is still incomplete!
 	 * Note: get_new_inode() sets the following on a new inode:
@@ -1314,28 +1323,26 @@ static void __udf_read_inode(struct inode *inode)
 		ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1,
 					&ident);
 		if (ident == TAG_IDENT_IE && ibh) {
-			struct buffer_head *nbh = NULL;
 			struct kernel_lb_addr loc;
 			struct indirectEntry *ie;
 
 			ie = (struct indirectEntry *)ibh->b_data;
 			loc = lelb_to_cpu(ie->indirectICB.extLocation);
 
-			if (ie->indirectICB.extLength &&
-				(nbh = udf_read_ptagged(inode->i_sb, &loc, 0,
-							&ident))) {
-				if (ident == TAG_IDENT_FE ||
-					ident == TAG_IDENT_EFE) {
-					memcpy(&iinfo->i_location,
-						&loc,
-						sizeof(struct kernel_lb_addr));
-					brelse(bh);
-					brelse(ibh);
-					brelse(nbh);
-					__udf_read_inode(inode);
+			if (ie->indirectICB.extLength) {
+				brelse(bh);
+				brelse(ibh);
+				memcpy(&iinfo->i_location, &loc,
+				       sizeof(struct kernel_lb_addr));
+				if (++indirections > UDF_MAX_ICB_NESTING) {
+					udf_err(inode->i_sb,
+						"too many ICBs in ICB hierarchy"
+						" (max %d supported)\n",
+						UDF_MAX_ICB_NESTING);
+					make_bad_inode(inode);
 					return;
 				}
-				brelse(nbh);
+				goto reread;
 			}
 		}
 		brelse(ibh);
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index d7c6dbe4194b..d89f324bc387 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -80,11 +80,17 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct buffer_head *bh = NULL;
 	unsigned char *symlink;
-	int err = -EIO;
+	int err;
 	unsigned char *p = kmap(page);
 	struct udf_inode_info *iinfo;
 	uint32_t pos;
 
+	/* We don't support symlinks longer than one block */
+	if (inode->i_size > inode->i_sb->s_blocksize) {
+		err = -ENAMETOOLONG;
+		goto out_unmap;
+	}
+
 	iinfo = UDF_I(inode);
 	pos = udf_block_map(inode, 0);
 
@@ -94,8 +100,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	} else {
 		bh = sb_bread(inode->i_sb, pos);
 
-		if (!bh)
-			goto out;
+		if (!bh) {
+			err = -EIO;
+			goto out_unlock_inode;
+		}
 
 		symlink = bh->b_data;
 	}
@@ -109,9 +117,10 @@ static int udf_symlink_filler(struct file *file, struct page *page)
 	unlock_page(page);
 	return 0;
 
-out:
+out_unlock_inode:
 	up_read(&iinfo->i_data_sem);
 	SetPageError(page);
+out_unmap:
 	kunmap(page);
 	unlock_page(page);
 	return err;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index db2cfb067d0b..0461fbe405b7 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -434,10 +434,22 @@ xfs_start_page_writeback(
 {
 	ASSERT(PageLocked(page));
 	ASSERT(!PageWriteback(page));
-	if (clear_dirty)
+
+	/*
+	 * if the page was not fully cleaned, we need to ensure that the higher
+	 * layers come back to it correctly. That means we need to keep the page
+	 * dirty, and for WB_SYNC_ALL writeback we need to ensure the
+	 * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to
+	 * write this page in this writeback sweep will be made.
+	 */
+	if (clear_dirty) {
 		clear_page_dirty_for_io(page);
-	set_page_writeback(page);
+		set_page_writeback(page);
+	} else
+		set_page_writeback_keepwrite(page);
+
 	unlock_page(page);
+
 	/* If no buffers on the page are to be written, finish it here */
 	if (!buffers)
 		end_page_writeback(page);
@@ -1660,11 +1672,72 @@ xfs_vm_readpages(
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
+/*
+ * This is basically a copy of __set_page_dirty_buffers() with one
+ * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
+ * dirty, we'll never be able to clean them because we don't write buffers
+ * beyond EOF, and that means we can't invalidate pages that span EOF
+ * that have been marked dirty. Further, the dirty state can leak into
+ * the file interior if the file is extended, resulting in all sorts of
+ * bad things happening as the state does not match the underlying data.
+ *
+ * XXX: this really indicates that bufferheads in XFS need to die. Warts like
+ * this only exist because of bufferheads and how the generic code manages them.
+ */
+STATIC int
+xfs_vm_set_page_dirty(
+	struct page		*page)
+{
+	struct address_space	*mapping = page->mapping;
+	struct inode		*inode = mapping->host;
+	loff_t			end_offset;
+	loff_t			offset;
+	int			newly_dirty;
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	end_offset = i_size_read(inode);
+	offset = page_offset(page);
+
+	spin_lock(&mapping->private_lock);
+	if (page_has_buffers(page)) {
+		struct buffer_head *head = page_buffers(page);
+		struct buffer_head *bh = head;
+
+		do {
+			if (offset < end_offset)
+				set_buffer_dirty(bh);
+			bh = bh->b_this_page;
+			offset += 1 << inode->i_blkbits;
+		} while (bh != head);
+	}
+	newly_dirty = !TestSetPageDirty(page);
+	spin_unlock(&mapping->private_lock);
+
+	if (newly_dirty) {
+		/* sigh - __set_page_dirty() is static, so copy it here, too */
+		unsigned long flags;
+
+		spin_lock_irqsave(&mapping->tree_lock, flags);
+		if (page->mapping) {	/* Race with truncate? */
+			WARN_ON_ONCE(!PageUptodate(page));
+			account_page_dirtied(page, mapping);
+			radix_tree_tag_set(&mapping->page_tree,
+					page_index(page), PAGECACHE_TAG_DIRTY);
+		}
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	}
+	return newly_dirty;
+}
+
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,
 	.writepage		= xfs_vm_writepage,
 	.writepages		= xfs_vm_writepages,
+	.set_page_dirty		= xfs_vm_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
 	.write_begin		= xfs_vm_write_begin,
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 796272a2e129..e69d57be866b 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1295,7 +1295,7 @@ xfs_da3_fixhashpath(
 		node = blk->bp->b_addr;
 		dp->d_ops->node_hdr_from_disk(&nodehdr, node);
 		btree = dp->d_ops->node_tree_p(node);
-		if (be32_to_cpu(btree->hashval) == lasthash)
+		if (be32_to_cpu(btree[blk->index].hashval) == lasthash)
 			break;
 		blk->hashval = lasthash;
 		btree[blk->index].hashval = cpu_to_be32(lasthash);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 7aeb4c895b32..95f94483c3d7 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1011,7 +1011,8 @@ xfs_qm_dqflush(
 	 * Get the buffer containing the on-disk dquot
 	 */
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
-				   mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL);
+				   mp->m_quotainfo->qi_dqchunklen, 0, &bp,
+				   &xfs_dquot_buf_ops);
 	if (error)
 		goto out_unlock;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 64b48eade91d..f50def6018a9 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -302,7 +302,16 @@ xfs_file_aio_read(
 				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
 				return ret;
 			}
-			truncate_pagecache_range(VFS_I(ip), pos, -1);
+
+			/*
+			 * Invalidate whole pages. This can return an error if
+			 * we fail to invalidate a page, but this should never
+			 * happen on XFS. Warn if it does fail.
+			 */
+			ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+						pos >> PAGE_CACHE_SHIFT, -1);
+			WARN_ON_ONCE(ret);
+			ret = 0;
 		}
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
 	}
@@ -683,7 +692,15 @@ xfs_file_dio_aio_write(
 						    pos, -1);
 		if (ret)
 			goto out;
-		truncate_pagecache_range(VFS_I(ip), pos, -1);
+		/*
+		 * Invalidate whole pages. This can return an error if
+		 * we fail to invalidate a page, but this should never
+		 * happen on XFS. Warn if it does fail.
+		 */
+		ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+						pos >> PAGE_CACHE_SHIFT, -1);
+		WARN_ON_ONCE(ret);
+		ret = 0;
 	}
 
 	/*
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index bcfe61202115..78e62cc471c5 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1241,7 +1241,7 @@ xfs_ioctl_setattr(
 		 * cleared upon successful return from chown()
 		 */
 		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
-		    !inode_capable(VFS_I(ip), CAP_FSETID))
+		    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
 			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
 
 		/*
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index b0f4ef77fa70..bf9781e9fd92 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -24,7 +24,8 @@ struct xfs_log_vec {
 	struct xfs_log_iovec	*lv_iovecp;	/* iovec array */
 	struct xfs_log_item	*lv_item;	/* owner */
 	char			*lv_buf;	/* formatted buffer */
-	int			lv_buf_len;	/* size of formatted buffer */
+	int			lv_bytes;	/* accounted space in buffer */
+	int			lv_buf_len;	/* aligned size of buffer */
 	int			lv_size;	/* size of allocated lv */
 };
 
@@ -52,15 +53,21 @@ xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
 	return vec->i_addr;
 }
 
+/*
+ * We need to make sure the next buffer is naturally aligned for the biggest
+ * basic data type we put into it.  We already accounted for this padding when
+ * sizing the buffer.
+ *
+ * However, this padding does not get written into the log, and hence we have to
+ * track the space used by the log vectors separately to prevent log space hangs
+ * due to inaccurate accounting (i.e. a leak) of the used log space through the
+ * CIL context ticket.
+ */
 static inline void
 xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len)
 {
-	/*
-	 * We need to make sure the next buffer is naturally aligned for the
-	 * biggest basic data type we put into it.  We already accounted for
-	 * this when sizing the buffer.
-	 */
 	lv->lv_buf_len += round_up(len, sizeof(uint64_t));
+	lv->lv_bytes += len;
 	vec->i_len = len;
 }
 
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 4ef6fdbced78..bcfbaae4702c 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -97,7 +97,7 @@ xfs_cil_prepare_item(
 {
 	/* Account for the new LV being passed in */
 	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) {
-		*diff_len += lv->lv_buf_len;
+		*diff_len += lv->lv_bytes;
 		*diff_iovecs += lv->lv_niovecs;
 	}
 
@@ -111,7 +111,7 @@ xfs_cil_prepare_item(
 	else if (old_lv != lv) {
 		ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);
 
-		*diff_len -= old_lv->lv_buf_len;
+		*diff_len -= old_lv->lv_bytes;
 		*diff_iovecs -= old_lv->lv_niovecs;
 		kmem_free(old_lv);
 	}
@@ -239,7 +239,7 @@ xlog_cil_insert_format_items(
 			 * that the space reservation accounting is correct.
 			 */
 			*diff_iovecs -= lv->lv_niovecs;
-			*diff_len -= lv->lv_buf_len;
+			*diff_len -= lv->lv_bytes;
 		} else {
 			/* allocate new data chunk */
 			lv = kmem_zalloc(buf_size, KM_SLEEP|KM_NOFS);
@@ -259,6 +259,7 @@ xlog_cil_insert_format_items(
 
 		/* The allocated data region lies beyond the iovec region */
 		lv->lv_buf_len = 0;
+		lv->lv_bytes = 0;
 		lv->lv_buf = (char *)lv + buf_size - nbytes;
 		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index bce53ac81096..eb26418814fe 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2125,6 +2125,17 @@ xlog_recover_validate_buf_type(
 	__uint16_t		magic16;
 	__uint16_t		magicda;
 
+	/*
+	 * We can only do post recovery validation on items on CRC enabled
+	 * fielsystems as we need to know when the buffer was written to be able
+	 * to determine if we should have replayed the item. If we replay old
+	 * metadata over a newer buffer, then it will enter a temporarily
+	 * inconsistent state resulting in verification failures. Hence for now
+	 * just avoid the verification stage for non-crc filesystems
+	 */
+	if (!xfs_sb_version_hascrc(&mp->m_sb))
+		return;
+
 	magic32 = be32_to_cpu(*(__be32 *)bp->b_addr);
 	magic16 = be16_to_cpu(*(__be16*)bp->b_addr);
 	magicda = be16_to_cpu(info->magic);
@@ -2160,8 +2171,6 @@ xlog_recover_validate_buf_type(
 		bp->b_ops = &xfs_agf_buf_ops;
 		break;
 	case XFS_BLFT_AGFL_BUF:
-		if (!xfs_sb_version_hascrc(&mp->m_sb))
-			break;
 		if (magic32 != XFS_AGFL_MAGIC) {
 			xfs_warn(mp, "Bad AGFL block magic!");
 			ASSERT(0);
@@ -2194,10 +2203,6 @@ xlog_recover_validate_buf_type(
 #endif
 		break;
 	case XFS_BLFT_DINO_BUF:
-		/*
-		 * we get here with inode allocation buffers, not buffers that
-		 * track unlinked list changes.
-		 */
 		if (magic16 != XFS_DINODE_MAGIC) {
 			xfs_warn(mp, "Bad INODE block magic!");
 			ASSERT(0);
@@ -2277,8 +2282,6 @@ xlog_recover_validate_buf_type(
 		bp->b_ops = &xfs_attr3_leaf_buf_ops;
 		break;
 	case XFS_BLFT_ATTR_RMT_BUF:
-		if (!xfs_sb_version_hascrc(&mp->m_sb))
-			break;
 		if (magic32 != XFS_ATTR3_RMT_MAGIC) {
 			xfs_warn(mp, "Bad attr remote magic!");
 			ASSERT(0);
@@ -2385,16 +2388,7 @@ xlog_recover_do_reg_buffer(
 	/* Shouldn't be any more regions */
 	ASSERT(i == item->ri_total);
 
-	/*
-	 * We can only do post recovery validation on items on CRC enabled
-	 * fielsystems as we need to know when the buffer was written to be able
-	 * to determine if we should have replayed the item. If we replay old
-	 * metadata over a newer buffer, then it will enter a temporarily
-	 * inconsistent state resulting in verification failures. Hence for now
-	 * just avoid the verification stage for non-crc filesystems
-	 */
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		xlog_recover_validate_buf_type(mp, bp, buf_f);
+	xlog_recover_validate_buf_type(mp, bp, buf_f);
 }
 
 /*
@@ -2502,12 +2496,29 @@ xlog_recover_buffer_pass2(
 	}
 
 	/*
-	 * recover the buffer only if we get an LSN from it and it's less than
+	 * Recover the buffer only if we get an LSN from it and it's less than
 	 * the lsn of the transaction we are replaying.
+	 *
+	 * Note that we have to be extremely careful of readahead here.
+	 * Readahead does not attach verfiers to the buffers so if we don't
+	 * actually do any replay after readahead because of the LSN we found
+	 * in the buffer if more recent than that current transaction then we
+	 * need to attach the verifier directly. Failure to do so can lead to
+	 * future recovery actions (e.g. EFI and unlinked list recovery) can
+	 * operate on the buffers and they won't get the verifier attached. This
+	 * can lead to blocks on disk having the correct content but a stale
+	 * CRC.
+	 *
+	 * It is safe to assume these clean buffers are currently up to date.
+	 * If the buffer is dirtied by a later transaction being replayed, then
+	 * the verifier will be reset to match whatever recover turns that
+	 * buffer into.
 	 */
 	lsn = xlog_recover_get_buf_lsn(mp, bp);
-	if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0)
+	if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
+		xlog_recover_validate_buf_type(mp, bp, buf_f);
 		goto out_release;
+	}
 
 	if (buf_f->blf_flags & XFS_BLF_INODE_BUF) {
 		error = xlog_recover_do_inode_buffer(mp, item, bp, buf_f);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index f96c05669a9e..0eaaa2d296f0 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -320,8 +320,18 @@ reread:
 	/*
 	 * Initialize the mount structure from the superblock.
 	 */
-	xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));
-	xfs_sb_quota_from_disk(&mp->m_sb);
+	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
+
+	/*
+	 * If we haven't validated the superblock, do so now before we try
+	 * to check the sector size and reread the superblock appropriately.
+	 */
+	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
+		if (loud)
+			xfs_warn(mp, "Invalid superblock magic number");
+		error = EINVAL;
+		goto release_buf;
+	}
 
 	/*
 	 * We must be able to do sector-sized and sector-aligned IO.
@@ -334,11 +344,11 @@ reread:
 		goto release_buf;
 	}
 
-	/*
-	 * Re-read the superblock so the buffer is correctly sized,
-	 * and properly verified.
-	 */
 	if (buf_ops == NULL) {
+		/*
+		 * Re-read the superblock so the buffer is correctly sized,
+		 * and properly verified.
+		 */
 		xfs_buf_relse(bp);
 		sector_size = sbp->sb_sectsize;
 		buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 348e4d2ed6e6..6d7d1de13403 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1176,6 +1176,12 @@ xfs_qm_dqiter_bufs(
 		if (error)
 			break;
 
+		/*
+		 * A corrupt buffer might not have a verifier attached, so
+		 * make sure we have the correct one attached before writeback
+		 * occurs.
+		 */
+		bp->b_ops = &xfs_dquot_buf_ops;
 		xfs_qm_reset_dqcounts(mp, bp, firstid, type);
 		xfs_buf_delwri_queue(bp, buffer_list);
 		xfs_buf_relse(bp);
@@ -1261,7 +1267,7 @@ xfs_qm_dqiterate(
 					xfs_buf_readahead(mp->m_ddev_targp,
 					       XFS_FSB_TO_DADDR(mp, rablkno),
 					       mp->m_quotainfo->qi_dqchunklen,
-					       NULL);
+					       &xfs_dquot_buf_ops);
 					rablkno++;
 				}
 			}
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index 1e116794bb66..4afd393846d3 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -397,10 +397,11 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp)
 	}
 }
 
-void
-xfs_sb_from_disk(
+static void
+__xfs_sb_from_disk(
 	struct xfs_sb	*to,
-	xfs_dsb_t	*from)
+	xfs_dsb_t	*from,
+	bool		convert_xquota)
 {
 	to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
 	to->sb_blocksize = be32_to_cpu(from->sb_blocksize);
@@ -456,6 +457,17 @@ xfs_sb_from_disk(
 	to->sb_pad = 0;
 	to->sb_pquotino = be64_to_cpu(from->sb_pquotino);
 	to->sb_lsn = be64_to_cpu(from->sb_lsn);
+	/* Convert on-disk flags to in-memory flags? */
+	if (convert_xquota)
+		xfs_sb_quota_from_disk(to);
+}
+
+void
+xfs_sb_from_disk(
+	struct xfs_sb	*to,
+	xfs_dsb_t	*from)
+{
+	__xfs_sb_from_disk(to, from, true);
 }
 
 static inline void
@@ -571,7 +583,11 @@ xfs_sb_verify(
 	struct xfs_mount *mp = bp->b_target->bt_mount;
 	struct xfs_sb	sb;
 
-	xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp));
+	/*
+	 * Use call variant which doesn't convert quota flags from disk
+	 * format, because xfs_mount_validate_sb checks the on-disk flags.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
 
 	/*
 	 * Only check the in progress field for the primary superblock as
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 8256eb4ad057..ac46782c10d3 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -118,6 +118,7 @@ struct acpi_device;
 struct acpi_hotplug_profile {
 	struct kobject kobj;
 	int (*scan_dependent)(struct acpi_device *adev);
+	void (*notify_online)(struct acpi_device *adev);
 	bool enabled:1;
 	bool demand_offline:1;
 };
@@ -228,7 +229,6 @@ struct acpi_device_pnp {
 	acpi_device_name device_name;	/* Driver-determined */
 	acpi_device_class device_class;	/*        "          */
 	union acpi_object *str_obj;	/* unicode string for _STR method */
-	unsigned long sun;		/* _SUN */
 };
 
 #define acpi_device_bid(d)	((d)->pnp.bus_id)
diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
new file mode 100644
index 000000000000..a5de55c04fb2
--- /dev/null
+++ b/include/asm-generic/early_ioremap.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_EARLY_IOREMAP_H_
+#define _ASM_EARLY_IOREMAP_H_
+
+#include <linux/types.h>
+
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ */
+extern void __iomem *early_ioremap(resource_size_t phys_addr,
+				   unsigned long size);
+extern void *early_memremap(resource_size_t phys_addr,
+			    unsigned long size);
+extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void early_memunmap(void *addr, unsigned long size);
+
+/*
+ * Weak function called by early_ioremap_reset(). It does nothing, but
+ * architectures may provide their own version to do any needed cleanups.
+ */
+extern void early_ioremap_shutdown(void);
+
+#if defined(CONFIG_GENERIC_EARLY_IOREMAP) && defined(CONFIG_MMU)
+/* Arch-specific initialization */
+extern void early_ioremap_init(void);
+
+/* Generic initialization called by architecture code */
+extern void early_ioremap_setup(void);
+
+/*
+ * Called as last step in paging_init() so library can act
+ * accordingly for subsequent map/unmap requests.
+ */
+extern void early_ioremap_reset(void);
+
+#else
+static inline void early_ioremap_init(void) { }
+static inline void early_ioremap_setup(void) { }
+static inline void early_ioremap_reset(void) { }
+#endif
+
+#endif /* _ASM_EARLY_IOREMAP_H_ */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 34c7bdc06014..38a743705cc6 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -680,24 +680,35 @@ static inline int pmd_numa(pmd_t pmd)
 #ifndef pte_mknonnuma
 static inline pte_t pte_mknonnuma(pte_t pte)
 {
-	pte = pte_clear_flags(pte, _PAGE_NUMA);
-	return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
+	pteval_t val = pte_val(pte);
+
+	val &= ~_PAGE_NUMA;
+	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
+	return __pte(val);
 }
 #endif
 
 #ifndef pmd_mknonnuma
 static inline pmd_t pmd_mknonnuma(pmd_t pmd)
 {
-	pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
-	return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
+	pmdval_t val = pmd_val(pmd);
+
+	val &= ~_PAGE_NUMA;
+	val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
+
+	return __pmd(val);
 }
 #endif
 
 #ifndef pte_mknuma
 static inline pte_t pte_mknuma(pte_t pte)
 {
-	pte = pte_set_flags(pte, _PAGE_NUMA);
-	return pte_clear_flags(pte, _PAGE_PRESENT);
+	pteval_t val = pte_val(pte);
+
+	val &= ~_PAGE_PRESENT;
+	val |= _PAGE_NUMA;
+
+	return __pte(val);
 }
 #endif
 
@@ -716,8 +727,12 @@ static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
 #ifndef pmd_mknuma
 static inline pmd_t pmd_mknuma(pmd_t pmd)
 {
-	pmd = pmd_set_flags(pmd, _PAGE_NUMA);
-	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+	pmdval_t val = pmd_val(pmd);
+
+	val &= ~_PAGE_PRESENT;
+	val |= _PAGE_NUMA;
+
+	return __pmd(val);
 }
 #endif
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index bc2121fa9132..f10f64fcc815 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -167,6 +167,16 @@
 #define CLK_OF_TABLES()
 #endif
 
+#ifdef CONFIG_OF_RESERVED_MEM
+#define RESERVEDMEM_OF_TABLES()				\
+	. = ALIGN(8);					\
+	VMLINUX_SYMBOL(__reservedmem_of_table) = .;	\
+	*(__reservedmem_of_table)			\
+	*(__reservedmem_of_table_end)
+#else
+#define RESERVEDMEM_OF_TABLES()
+#endif
+
 #define KERNEL_DTB()							\
 	STRUCT_ALIGN();							\
 	VMLINUX_SYMBOL(__dtb_start) = .;				\
@@ -490,6 +500,7 @@
 	TRACE_SYSCALLS()						\
 	MEM_DISCARD(init.rodata)					\
 	CLK_OF_TABLES()							\
+	RESERVEDMEM_OF_TABLES()						\
 	CLKSRC_OF_TABLES()						\
 	KERNEL_DTB()							\
 	IRQCHIP_OF_MATCH_TABLE()
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index d3909effd725..94f9ea8abcae 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -50,11 +50,7 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 }
 
 #ifndef zero_bytemask
-#ifdef CONFIG_64BIT
-#define zero_bytemask(mask)	(~0ul << fls64(mask))
-#else
-#define zero_bytemask(mask)	(~0ul << fls(mask))
-#endif /* CONFIG_64BIT */
-#endif /* zero_bytemask */
+#define zero_bytemask(mask) (~1ul << __fls(mask))
+#endif
 
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index e73c19e90e38..016c2f110f63 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -100,9 +100,12 @@ struct blkcipher_walk {
 	void *page;
 	u8 *buffer;
 	u8 *iv;
+	unsigned int ivsize;
 
 	int flags;
-	unsigned int blocksize;
+	unsigned int walk_blocksize;
+	unsigned int cipher_blocksize;
+	unsigned int alignmask;
 };
 
 struct ablkcipher_walk {
@@ -192,6 +195,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      struct blkcipher_walk *walk,
 			      unsigned int blocksize);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize);
 
 int ablkcipher_walk_done(struct ablkcipher_request *req,
 			 struct ablkcipher_walk *walk, int err);
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 49376aec2fbb..ca52de5a5c97 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -17,6 +17,7 @@
 	{0x1002, 0x1315, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x1316, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x1317, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x1318, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -73,7 +74,6 @@
 	{0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
-	{0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
@@ -164,8 +164,11 @@
 	{0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6604, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6605, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6608, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
@@ -175,6 +178,8 @@
 	{0x1002, 0x6631, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6640, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6641, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6646, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6650, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6651, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
@@ -297,6 +302,7 @@
 	{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x682C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h
index 8c1603b10665..433528ab5161 100644
--- a/include/dt-bindings/clock/tegra124-car.h
+++ b/include/dt-bindings/clock/tegra124-car.h
@@ -29,7 +29,7 @@
 /* 10 (register bit affects spdif_in and spdif_out) */
 #define TEGRA124_CLK_I2S1 11
 #define TEGRA124_CLK_I2C1 12
-#define TEGRA124_CLK_NDFLASH 13
+/* 13 */
 #define TEGRA124_CLK_SDMMC1 14
 #define TEGRA124_CLK_SDMMC4 15
 /* 16 */
@@ -83,7 +83,7 @@
 
 /* 64 */
 #define TEGRA124_CLK_UARTD 65
-#define TEGRA124_CLK_UARTE 66
+/* 66 */
 #define TEGRA124_CLK_I2C3 67
 #define TEGRA124_CLK_SBC4 68
 #define TEGRA124_CLK_SDMMC3 69
@@ -97,7 +97,7 @@
 #define TEGRA124_CLK_TRACE 77
 #define TEGRA124_CLK_SOC_THERM 78
 #define TEGRA124_CLK_DTV 79
-#define TEGRA124_CLK_NDSPEED 80
+/* 80 */
 #define TEGRA124_CLK_I2CSLOW 81
 #define TEGRA124_CLK_DSIB 82
 #define TEGRA124_CLK_TSEC 83
diff --git a/include/dt-bindings/pinctrl/dra.h b/include/dt-bindings/pinctrl/dra.h
index 002a2855c046..7448edff4723 100644
--- a/include/dt-bindings/pinctrl/dra.h
+++ b/include/dt-bindings/pinctrl/dra.h
@@ -30,7 +30,8 @@
 #define MUX_MODE14	0xe
 #define MUX_MODE15	0xf
 
-#define PULL_ENA		(1 << 16)
+#define PULL_ENA		(0 << 16)
+#define PULL_DIS		(1 << 16)
 #define PULL_UP			(1 << 17)
 #define INPUT_EN		(1 << 18)
 #define SLEWCONTROL		(1 << 19)
@@ -38,10 +39,10 @@
 #define WAKEUP_EVENT		(1 << 25)
 
 /* Active pin states */
-#define PIN_OUTPUT		0
-#define PIN_OUTPUT_PULLUP	(PIN_OUTPUT | PULL_ENA | PULL_UP)
-#define PIN_OUTPUT_PULLDOWN	(PIN_OUTPUT | PULL_ENA)
-#define PIN_INPUT		INPUT_EN
+#define PIN_OUTPUT		(0 | PULL_DIS)
+#define PIN_OUTPUT_PULLUP	(PULL_UP)
+#define PIN_OUTPUT_PULLDOWN	(0)
+#define PIN_INPUT		(INPUT_EN | PULL_DIS)
 #define PIN_INPUT_SLEW		(INPUT_EN | SLEWCONTROL)
 #define PIN_INPUT_PULLUP	(PULL_ENA | INPUT_EN | PULL_UP)
 #define PIN_INPUT_PULLDOWN	(PULL_ENA | INPUT_EN)
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 6d9aeddc09bf..ad9db6045b2f 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -67,6 +67,10 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
+
+u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
+int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
+
 #else
 static inline int kvm_timer_hyp_init(void)
 {
@@ -84,6 +88,16 @@ static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
 static inline void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) {}
+
+static inline int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
+{
+	return 0;
+}
+
+static inline u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index f27000f55a83..2f2aac8448a4 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -24,26 +24,26 @@
 #include <linux/irqreturn.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
-#include <linux/irqchip/arm-gic.h>
 
-#define VGIC_NR_IRQS		256
+#define VGIC_NR_IRQS_LEGACY	256
 #define VGIC_NR_SGIS		16
 #define VGIC_NR_PPIS		16
 #define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_NR_SHARED_IRQS	(VGIC_NR_IRQS - VGIC_NR_PRIVATE_IRQS)
-#define VGIC_MAX_CPUS		KVM_MAX_VCPUS
-#define VGIC_MAX_LRS		(1 << 6)
+
+#define VGIC_V2_MAX_LRS		(1 << 6)
+#define VGIC_V3_MAX_LRS		16
+#define VGIC_MAX_IRQS		1024
 
 /* Sanity checks... */
-#if (VGIC_MAX_CPUS > 8)
+#if (KVM_MAX_VCPUS > 8)
 #error	Invalid number of CPU interfaces
 #endif
 
-#if (VGIC_NR_IRQS & 31)
+#if (VGIC_NR_IRQS_LEGACY & 31)
 #error "VGIC_NR_IRQS must be a multiple of 32"
 #endif
 
-#if (VGIC_NR_IRQS > 1024)
+#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS)
 #error "VGIC_NR_IRQS must be <= 1024"
 #endif
 
@@ -53,26 +53,96 @@
  * - a bunch of shared interrupts (SPI)
  */
 struct vgic_bitmap {
-	union {
-		u32 reg[VGIC_NR_PRIVATE_IRQS / 32];
-		DECLARE_BITMAP(reg_ul, VGIC_NR_PRIVATE_IRQS);
-	} percpu[VGIC_MAX_CPUS];
-	union {
-		u32 reg[VGIC_NR_SHARED_IRQS / 32];
-		DECLARE_BITMAP(reg_ul, VGIC_NR_SHARED_IRQS);
-	} shared;
+	/*
+	 * - One UL per VCPU for private interrupts (assumes UL is at
+	 *   least 32 bits)
+	 * - As many UL as necessary for shared interrupts.
+	 *
+	 * The private interrupts are accessed via the "private"
+	 * field, one UL per vcpu (the state for vcpu n is in
+	 * private[n]). The shared interrupts are accessed via the
+	 * "shared" pointer (IRQn state is at bit n-32 in the bitmap).
+	 */
+	unsigned long *private;
+	unsigned long *shared;
 };
 
 struct vgic_bytemap {
-	u32 percpu[VGIC_MAX_CPUS][VGIC_NR_PRIVATE_IRQS / 4];
-	u32 shared[VGIC_NR_SHARED_IRQS  / 4];
+	/*
+	 * - 8 u32 per VCPU for private interrupts
+	 * - As many u32 as necessary for shared interrupts.
+	 *
+	 * The private interrupts are accessed via the "private"
+	 * field, (the state for vcpu n is in private[n*8] to
+	 * private[n*8 + 7]). The shared interrupts are accessed via
+	 * the "shared" pointer (IRQn state is at byte (n-32)%4 of the
+	 * shared[(n-32)/4] word).
+	 */
+	u32 *private;
+	u32 *shared;
+};
+
+struct kvm_vcpu;
+
+enum vgic_type {
+	VGIC_V2,		/* Good ol' GICv2 */
+	VGIC_V3,		/* New fancy GICv3 */
+};
+
+#define LR_STATE_PENDING	(1 << 0)
+#define LR_STATE_ACTIVE		(1 << 1)
+#define LR_STATE_MASK		(3 << 0)
+#define LR_EOI_INT		(1 << 2)
+
+struct vgic_lr {
+	u16	irq;
+	u8	source;
+	u8	state;
+};
+
+struct vgic_vmcr {
+	u32	ctlr;
+	u32	abpr;
+	u32	bpr;
+	u32	pmr;
+};
+
+struct vgic_ops {
+	struct vgic_lr	(*get_lr)(const struct kvm_vcpu *, int);
+	void	(*set_lr)(struct kvm_vcpu *, int, struct vgic_lr);
+	void	(*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr);
+	u64	(*get_elrsr)(const struct kvm_vcpu *vcpu);
+	u64	(*get_eisr)(const struct kvm_vcpu *vcpu);
+	u32	(*get_interrupt_status)(const struct kvm_vcpu *vcpu);
+	void	(*enable_underflow)(struct kvm_vcpu *vcpu);
+	void	(*disable_underflow)(struct kvm_vcpu *vcpu);
+	void	(*get_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+	void	(*set_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+	void	(*enable)(struct kvm_vcpu *vcpu);
+};
+
+struct vgic_params {
+	/* vgic type */
+	enum vgic_type	type;
+	/* Physical address of vgic virtual cpu interface */
+	phys_addr_t	vcpu_base;
+	/* Number of list registers */
+	u32		nr_lr;
+	/* Interrupt number */
+	unsigned int	maint_irq;
+	/* Virtual control interface base address */
+	void __iomem	*vctrl_base;
 };
 
 struct vgic_dist {
 #ifdef CONFIG_KVM_ARM_VGIC
 	spinlock_t		lock;
+	bool			in_kernel;
 	bool			ready;
 
+	int			nr_cpus;
+	int			nr_irqs;
+
 	/* Virtual control interface mapping */
 	void __iomem		*vctrl_base;
 
@@ -86,11 +156,25 @@ struct vgic_dist {
 	/* Interrupt enabled (one bit per IRQ) */
 	struct vgic_bitmap	irq_enabled;
 
-	/* Interrupt 'pin' level */
-	struct vgic_bitmap	irq_state;
+	/* Level-triggered interrupt external input is asserted */
+	struct vgic_bitmap	irq_level;
+
+	/*
+	 * Interrupt state is pending on the distributor
+	 */
+	struct vgic_bitmap	irq_pending;
 
-	/* Level-triggered interrupt in progress */
-	struct vgic_bitmap	irq_active;
+	/*
+	 * Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered
+	 * interrupts.  Essentially holds the state of the flip-flop in
+	 * Figure 4-10 on page 4-101 in ARM IHI 0048B.b.
+	 * Once set, it is only cleared for level-triggered interrupts on
+	 * guest ACKs (when we queue it) or writes to GICD_ICPENDRn.
+	 */
+	struct vgic_bitmap	irq_soft_pend;
+
+	/* Level-triggered interrupt queued on VCPU interface */
+	struct vgic_bitmap	irq_queued;
 
 	/* Interrupt priority. Not used yet. */
 	struct vgic_bytemap	irq_priority;
@@ -98,46 +182,90 @@ struct vgic_dist {
 	/* Level/edge triggered */
 	struct vgic_bitmap	irq_cfg;
 
-	/* Source CPU per SGI and target CPU */
-	u8			irq_sgi_sources[VGIC_MAX_CPUS][VGIC_NR_SGIS];
-
-	/* Target CPU for each IRQ */
-	u8			irq_spi_cpu[VGIC_NR_SHARED_IRQS];
-	struct vgic_bitmap	irq_spi_target[VGIC_MAX_CPUS];
+	/*
+	 * Source CPU per SGI and target CPU:
+	 *
+	 * Each byte represent a SGI observable on a VCPU, each bit of
+	 * this byte indicating if the corresponding VCPU has
+	 * generated this interrupt. This is a GICv2 feature only.
+	 *
+	 * For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are
+	 * the SGIs observable on VCPUn.
+	 */
+	u8			*irq_sgi_sources;
+
+	/*
+	 * Target CPU for each SPI:
+	 *
+	 * Array of available SPI, each byte indicating the target
+	 * VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32].
+	 */
+	u8			*irq_spi_cpu;
+
+	/*
+	 * Reverse lookup of irq_spi_cpu for faster compute pending:
+	 *
+	 * Array of bitmaps, one per VCPU, describing if IRQn is
+	 * routed to a particular VCPU.
+	 */
+	struct vgic_bitmap	*irq_spi_target;
 
 	/* Bitmap indicating which CPU has something pending */
-	unsigned long		irq_pending_on_cpu;
+	unsigned long		*irq_pending_on_cpu;
+#endif
+};
+
+struct vgic_v2_cpu_if {
+	u32		vgic_hcr;
+	u32		vgic_vmcr;
+	u32		vgic_misr;	/* Saved only */
+	u32		vgic_eisr[2];	/* Saved only */
+	u32		vgic_elrsr[2];	/* Saved only */
+	u32		vgic_apr;
+	u32		vgic_lr[VGIC_V2_MAX_LRS];
+};
+
+struct vgic_v3_cpu_if {
+#ifdef CONFIG_ARM_GIC_V3
+	u32		vgic_hcr;
+	u32		vgic_vmcr;
+	u32		vgic_misr;	/* Saved only */
+	u32		vgic_eisr;	/* Saved only */
+	u32		vgic_elrsr;	/* Saved only */
+	u32		vgic_ap0r[4];
+	u32		vgic_ap1r[4];
+	u64		vgic_lr[VGIC_V3_MAX_LRS];
 #endif
 };
 
 struct vgic_cpu {
 #ifdef CONFIG_KVM_ARM_VGIC
 	/* per IRQ to LR mapping */
-	u8		vgic_irq_lr_map[VGIC_NR_IRQS];
+	u8		*vgic_irq_lr_map;
 
 	/* Pending interrupts on this VCPU */
 	DECLARE_BITMAP(	pending_percpu, VGIC_NR_PRIVATE_IRQS);
-	DECLARE_BITMAP(	pending_shared, VGIC_NR_SHARED_IRQS);
+	unsigned long	*pending_shared;
 
 	/* Bitmap of used/free list registers */
-	DECLARE_BITMAP(	lr_used, VGIC_MAX_LRS);
+	DECLARE_BITMAP(	lr_used, VGIC_V2_MAX_LRS);
 
 	/* Number of list registers on this CPU */
 	int		nr_lr;
 
 	/* CPU vif control registers for world switch */
-	u32		vgic_hcr;
-	u32		vgic_vmcr;
-	u32		vgic_misr;	/* Saved only */
-	u32		vgic_eisr[2];	/* Saved only */
-	u32		vgic_elrsr[2];	/* Saved only */
-	u32		vgic_apr;
-	u32		vgic_lr[VGIC_MAX_LRS];
+	union {
+		struct vgic_v2_cpu_if	vgic_v2;
+		struct vgic_v3_cpu_if	vgic_v3;
+	};
 #endif
 };
 
 #define LR_EMPTY	0xff
 
+#define INT_STATUS_EOI		(1 << 0)
+#define INT_STATUS_UNDERFLOW	(1 << 1)
+
 struct kvm;
 struct kvm_vcpu;
 struct kvm_run;
@@ -148,7 +276,8 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
 int kvm_vgic_init(struct kvm *kvm);
 int kvm_vgic_create(struct kvm *kvm);
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_vgic_destroy(struct kvm *kvm);
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
@@ -157,9 +286,25 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
 bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		      struct kvm_exit_mmio *mmio);
 
-#define irqchip_in_kernel(k)	(!!((k)->arch.vgic.vctrl_base))
+#define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
 #define vgic_initialized(k)	((k)->arch.vgic.ready)
 
+int vgic_v2_probe(struct device_node *vgic_node,
+		  const struct vgic_ops **ops,
+		  const struct vgic_params **params);
+#ifdef CONFIG_ARM_GIC_V3
+int vgic_v3_probe(struct device_node *vgic_node,
+		  const struct vgic_ops **ops,
+		  const struct vgic_params **params);
+#else
+static inline int vgic_v3_probe(struct device_node *vgic_node,
+				const struct vgic_ops **ops,
+				const struct vgic_params **params)
+{
+	return -ENODEV;
+}
+#endif
+
 #else
 static inline int kvm_vgic_hyp_init(void)
 {
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1151a1dcfe41..cd80aa80d03e 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -37,6 +37,7 @@
 
 #include <linux/list.h>
 #include <linux/mod_devicetable.h>
+#include <linux/dynamic_debug.h>
 
 #include <acpi/acpi.h>
 #include <acpi/acpi_bus.h>
@@ -590,6 +591,14 @@ static inline __printf(3, 4) void
 acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {}
 #endif	/* !CONFIG_ACPI */
 
+#if defined(CONFIG_ACPI) && defined(CONFIG_DYNAMIC_DEBUG)
+__printf(3, 4)
+void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const char *fmt, ...);
+#else
+#define __acpi_handle_debug(descriptor, handle, fmt, ...)		\
+	acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__);
+#endif
+
 /*
  * acpi_handle_<level>: Print message with ACPI prefix and object path
  *
@@ -611,11 +620,19 @@ acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {}
 #define acpi_handle_info(handle, fmt, ...)				\
 	acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__)
 
-/* REVISIT: Support CONFIG_DYNAMIC_DEBUG when necessary */
-#if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(DEBUG)
 #define acpi_handle_debug(handle, fmt, ...)				\
 	acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__)
 #else
+#if defined(CONFIG_DYNAMIC_DEBUG)
+#define acpi_handle_debug(handle, fmt, ...)				\
+do {									\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT))		\
+		__acpi_handle_debug(&descriptor, handle, pr_fmt(fmt),	\
+				##__VA_ARGS__);				\
+} while (0)
+#else
 #define acpi_handle_debug(handle, fmt, ...)				\
 ({									\
 	if (0)								\
@@ -623,5 +640,6 @@ acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {}
 	0;								\
 })
 #endif
+#endif
 
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 63b5eff0a80f..c814346ba93c 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -23,6 +23,7 @@
 
 #define AMBA_NR_IRQS	9
 #define AMBA_CID	0xb105f00d
+#define CORESIGHT_CID	0xb105900d
 
 struct clk;
 
diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h
index e82e3ee2c54a..4a53250f970e 100644
--- a/include/linux/amba/clcd.h
+++ b/include/linux/amba/clcd.h
@@ -243,6 +243,9 @@ static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs)
 			val |= CNTL_BGR;
 	}
 
+	/* Reset the current colour depth */
+	val &= ~CNTL_LCDBPP16_444;
+
 	switch (var->bits_per_pixel) {
 	case 1:
 		val |= CNTL_LCDBPP1;
@@ -264,14 +267,15 @@ static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs)
 		 */
 		if (amba_part(fb->dev) == 0x110 ||
 		    var->green.length == 5)
-			val |= CNTL_LCDBPP16;
+			val |= CNTL_LCDBPP16 | CNTL_BGR;
 		else if (var->green.length == 6)
-			val |= CNTL_LCDBPP16_565;
+			val |= CNTL_LCDBPP16_565 | CNTL_BGR;
 		else
-			val |= CNTL_LCDBPP16_444;
+			val |= CNTL_LCDBPP16_444 | CNTL_BGR;
 		break;
 	case 32:
 		val |= CNTL_LCDBPP24;
+		val &= ~CNTL_BGR;
 		break;
 	}
 
diff --git a/include/linux/arm-hdlcd.h b/include/linux/arm-hdlcd.h
new file mode 100644
index 000000000000..939f3a81d56b
--- /dev/null
+++ b/include/linux/arm-hdlcd.h
@@ -0,0 +1,122 @@
+/*
+ * include/linux/arm-hdlcd.h
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ *  ARM HDLCD Controller register definition
+ */
+
+#include <linux/fb.h>
+#include <linux/completion.h>
+
+/* register offsets */
+#define HDLCD_REG_VERSION		0x0000	/* ro */
+#define HDLCD_REG_INT_RAWSTAT		0x0010	/* rw */
+#define HDLCD_REG_INT_CLEAR		0x0014	/* wo */
+#define HDLCD_REG_INT_MASK		0x0018	/* rw */
+#define HDLCD_REG_INT_STATUS		0x001c	/* ro */
+#define HDLCD_REG_USER_OUT		0x0020	/* rw */
+#define HDLCD_REG_FB_BASE		0x0100	/* rw */
+#define HDLCD_REG_FB_LINE_LENGTH	0x0104	/* rw */
+#define HDLCD_REG_FB_LINE_COUNT		0x0108	/* rw */
+#define HDLCD_REG_FB_LINE_PITCH		0x010c	/* rw */
+#define HDLCD_REG_BUS_OPTIONS		0x0110	/* rw */
+#define HDLCD_REG_V_SYNC		0x0200	/* rw */
+#define HDLCD_REG_V_BACK_PORCH		0x0204	/* rw */
+#define HDLCD_REG_V_DATA		0x0208	/* rw */
+#define HDLCD_REG_V_FRONT_PORCH		0x020c	/* rw */
+#define HDLCD_REG_H_SYNC		0x0210	/* rw */
+#define HDLCD_REG_H_BACK_PORCH		0x0214	/* rw */
+#define HDLCD_REG_H_DATA		0x0218	/* rw */
+#define HDLCD_REG_H_FRONT_PORCH		0x021c	/* rw */
+#define HDLCD_REG_POLARITIES		0x0220	/* rw */
+#define HDLCD_REG_COMMAND		0x0230	/* rw */
+#define HDLCD_REG_PIXEL_FORMAT		0x0240	/* rw */
+#define HDLCD_REG_BLUE_SELECT		0x0244	/* rw */
+#define HDLCD_REG_GREEN_SELECT		0x0248	/* rw */
+#define HDLCD_REG_RED_SELECT		0x024c	/* rw */
+
+/* version */
+#define HDLCD_PRODUCT_ID		0x1CDC0000
+#define HDLCD_PRODUCT_MASK		0xFFFF0000
+#define HDLCD_VERSION_MAJOR_MASK	0x0000FF00
+#define HDLCD_VERSION_MINOR_MASK	0x000000FF
+
+/* interrupts */
+#define HDLCD_INTERRUPT_DMA_END		(1 << 0)
+#define HDLCD_INTERRUPT_BUS_ERROR	(1 << 1)
+#define HDLCD_INTERRUPT_VSYNC		(1 << 2)
+#define HDLCD_INTERRUPT_UNDERRUN	(1 << 3)
+
+/* polarity */
+#define HDLCD_POLARITY_VSYNC		(1 << 0)
+#define HDLCD_POLARITY_HSYNC		(1 << 1)
+#define HDLCD_POLARITY_DATAEN		(1 << 2)
+#define HDLCD_POLARITY_DATA		(1 << 3)
+#define HDLCD_POLARITY_PIXELCLK		(1 << 4)
+
+/* commands */
+#define HDLCD_COMMAND_DISABLE		(0 << 0)
+#define HDLCD_COMMAND_ENABLE		(1 << 0)
+
+/* pixel format */
+#define HDLCD_PIXEL_FMT_LITTLE_ENDIAN	(0 << 31)
+#define HDLCD_PIXEL_FMT_BIG_ENDIAN	(1 << 31)
+#define HDLCD_BYTES_PER_PIXEL_MASK	(3 << 3)
+
+/* bus options */
+#define HDLCD_BUS_BURST_MASK		0x01f
+#define HDLCD_BUS_MAX_OUTSTAND		0xf00
+#define HDLCD_BUS_BURST_NONE		(0 << 0)
+#define HDLCD_BUS_BURST_1		(1 << 0)
+#define HDLCD_BUS_BURST_2		(1 << 1)
+#define HDLCD_BUS_BURST_4		(1 << 2)
+#define HDLCD_BUS_BURST_8		(1 << 3)
+#define HDLCD_BUS_BURST_16		(1 << 4)
+
+/* Max resolution supported is 4096x4096, 8 bit per color component,
+   8 bit alpha, but we are going to choose the usual hardware default
+   (2048x2048, 32 bpp) and enable double buffering */
+#define HDLCD_MAX_XRES			2048
+#define HDLCD_MAX_YRES			2048
+#define HDLCD_MAX_FRAMEBUFFER_SIZE	(HDLCD_MAX_XRES * HDLCD_MAX_YRES << 2)
+
+#define HDLCD_MEM_BASE			(CONFIG_PAGE_OFFSET - 0x1000000)
+
+#define NR_PALETTE	256
+
+/* OEMs using HDLCD may wish to enable these settings if
+ * display disruption is apparent and you suspect HDLCD
+ * access to RAM may be starved.
+ */
+/* Turn HDLCD default color red instead of black so
+ * that it's easy to see pixel clock data underruns
+ * (compared to other visual disruption)
+ */
+//#define HDLCD_RED_DEFAULT_COLOUR
+/* Add a counter in the IRQ handler to count buffer underruns
+ * and /proc/hdlcd_underrun to read the counter
+ */
+//#define HDLCD_COUNT_BUFFERUNDERRUNS
+/* Restrict height to 1x screen size
+ *
+ */
+//#define HDLCD_NO_VIRTUAL_SCREEN
+
+#ifdef CONFIG_ANDROID
+#define HDLCD_NO_VIRTUAL_SCREEN
+#endif
+
+struct hdlcd_device {
+	struct fb_info		fb;
+	struct device		*dev;
+	struct clk		*clk;
+	void __iomem		*base;
+	int			irq;
+	struct completion	vsync_completion;
+	unsigned char		*edid;
+};
diff --git a/include/linux/audit.h b/include/linux/audit.h
index ec1464df4c60..419b7d7d7a7f 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -47,6 +47,7 @@ struct sk_buff;
 
 struct audit_krule {
 	int			vers_ops;
+	u32			pflags;
 	u32			flags;
 	u32			listnr;
 	u32			action;
@@ -64,6 +65,9 @@ struct audit_krule {
 	u64			prio;
 };
 
+/* Flag to indicate legacy AUDIT_LOGINUID unset usage */
+#define AUDIT_LOGINUID_LEGACY		0x1
+
 struct audit_field {
 	u32				type;
 	u32				val;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 24819001f5c8..e488e9459a93 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -95,7 +95,7 @@ struct backing_dev_info {
 	unsigned int max_ratio, max_prop_frac;
 
 	struct bdi_writeback wb;  /* default writeback info for this bdi */
-	spinlock_t wb_lock;	  /* protects work_list */
+	spinlock_t wb_lock;	  /* protects work_list & wb.dwork scheduling */
 
 	struct list_head work_list;
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5a4d39b4686b..5aa372a7380c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -216,9 +216,9 @@ static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter,
 }
 
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
-	for ((iter) = start;						\
-	     (bvl) = bvec_iter_bvec((bio_vec), (iter)),			\
-		(iter).bi_size;						\
+	for (iter = (start);						\
+	     (iter).bi_size &&						\
+		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
 	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
 
 
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index be5fd38bd5a0..5d858e02997f 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -18,8 +18,11 @@
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
-#define GENMASK(h, l)		(((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
-#define GENMASK_ULL(h, l)	(((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))
+#define GENMASK(h, l) \
+	(((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4afa4f8f6090..a693c6d29328 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1232,10 +1232,9 @@ static inline int queue_alignment_offset(struct request_queue *q)
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = (sector << 9) & (granularity - 1);
+	unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
 
-	return (granularity + lim->alignment_offset - alignment)
-		& (granularity - 1);
+	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
 
 static inline int bdev_alignment_offset(struct block_device *bdev)
diff --git a/include/linux/capability.h b/include/linux/capability.h
index a6ee1f9a5018..aa93e5ef594c 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -78,8 +78,11 @@ extern const kernel_cap_t __cap_init_eff_set;
 # error Fix up hand-coded capability macro initializers
 #else /* HAND-CODED capability initializers */
 
+#define CAP_LAST_U32			((_KERNEL_CAPABILITY_U32S) - 1)
+#define CAP_LAST_U32_VALID_MASK		(CAP_TO_MASK(CAP_LAST_CAP + 1) -1)
+
 # define CAP_EMPTY_SET    ((kernel_cap_t){{ 0, 0 }})
-# define CAP_FULL_SET     ((kernel_cap_t){{ ~0, ~0 }})
+# define CAP_FULL_SET     ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }})
 # define CAP_FS_SET       ((kernel_cap_t){{ CAP_FS_MASK_B0 \
 				    | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
 				    CAP_FS_MASK_B1 } })
@@ -210,7 +213,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t,
 				      struct user_namespace *ns, int cap);
 extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
-extern bool inode_capable(const struct inode *inode, int cap);
+extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 
 /* audit system wants to get cap info from files as well */
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 939533da93a7..2045a128c987 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -304,6 +304,8 @@ struct clk_div_table {
  *   of this register, and mask of divider bits are in higher 16-bit of this
  *   register.  While setting the divider bits, higher 16-bit should also be
  *   updated to indicate changing divider bits.
+ * CLK_DIVIDER_ROUND_CLOSEST - Makes the best calculated divider to be rounded
+ *	to the closest integer instead of the up one.
  */
 struct clk_divider {
 	struct clk_hw	hw;
@@ -319,6 +321,7 @@ struct clk_divider {
 #define CLK_DIVIDER_POWER_OF_TWO	BIT(1)
 #define CLK_DIVIDER_ALLOW_ZERO		BIT(2)
 #define CLK_DIVIDER_HIWORD_MASK		BIT(3)
+#define CLK_DIVIDER_ROUND_CLOSEST	BIT(4)
 
 extern const struct clk_ops clk_divider_ops;
 struct clk *clk_register_divider(struct device *dev, const char *name,
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 67301a405712..879065d8d208 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -289,7 +289,7 @@ extern struct clocksource* clocksource_get_next(void);
 extern void clocksource_change_rating(struct clocksource *cs, int rating);
 extern void clocksource_suspend(void);
 extern void clocksource_resume(void);
-extern struct clocksource * __init __weak clocksource_default_clock(void);
+extern struct clocksource * __init clocksource_default_clock(void);
 extern void clocksource_mark_unstable(struct clocksource *cs);
 
 extern u64
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 7e1c76e3cd68..01e3132820da 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			bool sync, bool *contended);
+			enum migrate_mode mode, bool *contended);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
@@ -91,7 +91,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended)
+			enum migrate_mode mode, bool *contended)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h
new file mode 100644
index 000000000000..cdd1cc202d51
--- /dev/null
+++ b/include/linux/compiler-gcc5.h
@@ -0,0 +1,66 @@
+#ifndef __LINUX_COMPILER_H
+#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead."
+#endif
+
+#define __used				__attribute__((__used__))
+#define __must_check			__attribute__((warn_unused_result))
+#define __compiler_offsetof(a, b)	__builtin_offsetof(a, b)
+
+/* Mark functions as cold. gcc will assume any path leading to a call
+   to them will be unlikely.  This means a lot of manual unlikely()s
+   are unnecessary now for any paths leading to the usual suspects
+   like BUG(), printk(), panic() etc. [but let's keep them for now for
+   older compilers]
+
+   Early snapshots of gcc 4.3 don't support this and we can't detect this
+   in the preprocessor, but we can live with this because they're unreleased.
+   Maketime probing would be overkill here.
+
+   gcc also has a __attribute__((__hot__)) to move hot functions into
+   a special section, but I don't see any sense in this right now in
+   the kernel context */
+#define __cold			__attribute__((__cold__))
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#ifndef __CHECKER__
+# define __compiletime_warning(message) __attribute__((warning(message)))
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* __CHECKER__ */
+
+/*
+ * Mark a position in code as unreachable.  This can be used to
+ * suppress control flow warnings after asm blocks that transfer
+ * control elsewhere.
+ *
+ * Early snapshots of gcc 4.5 don't support this and we can't detect
+ * this in the preprocessor, but we can live with this because they're
+ * unreleased.  Really, we need to have autoconf for the kernel.
+ */
+#define unreachable() __builtin_unreachable()
+
+/* Mark a function definition as prohibited from being cloned. */
+#define __noclone	__attribute__((__noclone__))
+
+/*
+ * Tell the optimizer that something else uses this function or variable.
+ */
+#define __visible __attribute__((externally_visible))
+
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
+
+#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
new file mode 100644
index 000000000000..bdde4199c74a
--- /dev/null
+++ b/include/linux/coresight.h
@@ -0,0 +1,263 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_CORESIGHT_H
+#define _LINUX_CORESIGHT_H
+
+#include <linux/device.h>
+
+/* Peripheral id registers (0xFD0-0xFEC) */
+#define CORESIGHT_PERIPHIDR4	0xfd0
+#define CORESIGHT_PERIPHIDR5	0xfd4
+#define CORESIGHT_PERIPHIDR6	0xfd8
+#define CORESIGHT_PERIPHIDR7	0xfdC
+#define CORESIGHT_PERIPHIDR0	0xfe0
+#define CORESIGHT_PERIPHIDR1	0xfe4
+#define CORESIGHT_PERIPHIDR2	0xfe8
+#define CORESIGHT_PERIPHIDR3	0xfeC
+/* Component id registers (0xFF0-0xFFC) */
+#define CORESIGHT_COMPIDR0	0xff0
+#define CORESIGHT_COMPIDR1	0xff4
+#define CORESIGHT_COMPIDR2	0xff8
+#define CORESIGHT_COMPIDR3	0xffC
+
+#define ETM_ARCH_V3_3		0x23
+#define ETM_ARCH_V3_5		0x25
+#define PFT_ARCH_V1_0		0x30
+#define PFT_ARCH_V1_1		0x31
+
+#define CORESIGHT_UNLOCK	0xc5acce55
+
+extern struct bus_type coresight_bustype;
+
+enum coresight_dev_type {
+	CORESIGHT_DEV_TYPE_NONE,
+	CORESIGHT_DEV_TYPE_SINK,
+	CORESIGHT_DEV_TYPE_LINK,
+	CORESIGHT_DEV_TYPE_LINKSINK,
+	CORESIGHT_DEV_TYPE_SOURCE,
+};
+
+enum coresight_dev_subtype_sink {
+	CORESIGHT_DEV_SUBTYPE_SINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_SINK_PORT,
+	CORESIGHT_DEV_SUBTYPE_SINK_BUFFER,
+};
+
+enum coresight_dev_subtype_link {
+	CORESIGHT_DEV_SUBTYPE_LINK_NONE,
+	CORESIGHT_DEV_SUBTYPE_LINK_MERG,
+	CORESIGHT_DEV_SUBTYPE_LINK_SPLIT,
+	CORESIGHT_DEV_SUBTYPE_LINK_FIFO,
+};
+
+enum coresight_dev_subtype_source {
+	CORESIGHT_DEV_SUBTYPE_SOURCE_NONE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+};
+
+/**
+ * struct coresight_dev_subtype - further characterisation of a type
+ * @sink_subtype:	type of sink this component is, as defined
+			by @coresight_dev_subtype_sink.
+ * @link_subtype:	type of link this component is, as defined
+			by @coresight_dev_subtype_link.
+ * @source_subtype:	type of source this component is, as defined
+			by @coresight_dev_subtype_source.
+ */
+struct coresight_dev_subtype {
+	enum coresight_dev_subtype_sink sink_subtype;
+	enum coresight_dev_subtype_link link_subtype;
+	enum coresight_dev_subtype_source source_subtype;
+};
+
+/**
+ * struct coresight_platform_data - data harvested from the DT specification
+ * @cpu:	the CPU a source belongs to. Only applicable for ETM/PTMs.
+ * @name:	name of the component as shown under sysfs.
+ * @nr_inport:	number of input ports for this component.
+ * @outports:	list of remote enpoint port number.
+ * @child_names:name of all child components connected to this device.
+ * @child_ports:child component port number the current component is
+		connected  to.
+ * @nr_outport:	number of output ports for this component.
+ * @clk:	The clock this component is associated to.
+ */
+struct coresight_platform_data {
+	int cpu;
+	const char *name;
+	int nr_inport;
+	int *outports;
+	const char **child_names;
+	int *child_ports;
+	int nr_outport;
+	struct clk *clk;
+};
+
+/**
+ * struct coresight_desc - description of a component required from drivers
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @pdata:	platform data collected from DT.
+ * @dev:	The device entity associated to this component.
+ * @groups	:operations specific to this component. These will end up
+		in the component's sysfs sub-directory.
+ */
+struct coresight_desc {
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct coresight_platform_data *pdata;
+	struct device *dev;
+	const struct attribute_group **groups;
+};
+
+/**
+ * struct coresight_connection - representation of a single connection
+ * @ref_count:	keeping count a port' references.
+ * @outport:	a connection's output port number.
+ * @chid_name:	remote component's name.
+ * @child_port:	remote component's port number @output is connected to.
+ * @child_dev:	a @coresight_device representation of the component
+		connected to @outport.
+ */
+struct coresight_connection {
+	int outport;
+	const char *child_name;
+	int child_port;
+	struct coresight_device *child_dev;
+};
+
+/**
+ * struct coresight_device - representation of a device as used by the framework
+ * @nr_inport:	number of input port associated to this component.
+ * @nr_outport:	number of output port associated to this component.
+ * @type:	as defined by @coresight_dev_type.
+ * @subtype:	as defined by @coresight_dev_subtype.
+ * @ops:	generic operations for this component, as defined
+		by @coresight_ops.
+ * @dev:	The device entity associated to this component.
+ * @refcnt:	keep track of what is in use.
+ * @path_link:	link of current component into the path being enabled.
+ * @orphan:	true if the component has connections that haven't been linked.
+ * @enable:	'true' if component is currently part of an active path.
+ * @activated:	'true' only if a _sink_ has been activated.  A sink can be
+		activated but not yet enabled.  Enabling for a _sink_
+		happens when a source has been selected for that it.
+ */
+struct coresight_device {
+	struct coresight_connection *conns;
+	int nr_inport;
+	int nr_outport;
+	enum coresight_dev_type type;
+	struct coresight_dev_subtype subtype;
+	const struct coresight_ops *ops;
+	struct device dev;
+	atomic_t *refcnt;
+	struct list_head path_link;
+	bool orphan;
+	bool enable;	/* true only if configured as part of a path */
+	bool activated;	/* true only if a sink is part of a path */
+};
+
+#define to_coresight_device(d) container_of(d, struct coresight_device, dev)
+
+#define source_ops(csdev)	csdev->ops->source_ops
+#define sink_ops(csdev)		csdev->ops->sink_ops
+#define link_ops(csdev)		csdev->ops->link_ops
+
+#define CORESIGHT_DEBUGFS_ENTRY(__name, __entry_name,			\
+				 __mode, __get, __set, __fmt)		\
+DEFINE_SIMPLE_ATTRIBUTE(__name ## _ops, __get, __set, __fmt);		\
+static const struct coresight_ops_entry __name ## _entry = {		\
+	.name = __entry_name,						\
+	.mode = __mode,							\
+	.ops  = &__name ## _ops						\
+}
+
+/**
+ * struct coresight_ops_sink - basic operations for a sink
+ * Operations available for sinks
+ * @enable:	enables the sink.
+ * @disable:	disables the sink.
+ */
+struct coresight_ops_sink {
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+/**
+ * struct coresight_ops_link - basic operations for a link
+ * Operations available for links.
+ * @enable:	enables flow between iport and oport.
+ * @disable:	disables flow between iport and oport.
+ */
+struct coresight_ops_link {
+	int (*enable)(struct coresight_device *csdev, int iport, int oport);
+	void (*disable)(struct coresight_device *csdev, int iport, int oport);
+};
+
+/**
+ * struct coresight_ops_source - basic operations for a source
+ * Operations available for sources.
+ * @trace_id:	returns the value of the component's trace ID as known
+		to the HW.
+ * @enable:	enables tracing from a source.
+ * @disable:	disables tracing for a source.
+ */
+struct coresight_ops_source {
+	int (*trace_id)(struct coresight_device *csdev);
+	int (*enable)(struct coresight_device *csdev);
+	void (*disable)(struct coresight_device *csdev);
+};
+
+struct coresight_ops {
+	const struct coresight_ops_sink *sink_ops;
+	const struct coresight_ops_link *link_ops;
+	const struct coresight_ops_source *source_ops;
+};
+
+#ifdef CONFIG_CORESIGHT
+extern struct coresight_device *
+coresight_register(struct coresight_desc *desc);
+extern void coresight_unregister(struct coresight_device *csdev);
+extern int coresight_enable(struct coresight_device *csdev);
+extern void coresight_disable(struct coresight_device *csdev);
+extern int coresight_is_bit_set(u32 val, int position, int value);
+extern int coresight_timeout(void __iomem *addr, u32 offset,
+			     int position, int value);
+#ifdef CONFIG_OF
+extern struct coresight_platform_data *of_get_coresight_platform_data(
+				struct device *dev, struct device_node *node);
+#endif
+#else
+static inline struct coresight_device *
+coresight_register(struct coresight_desc *desc) { return NULL; }
+static inline void coresight_unregister(struct coresight_device *csdev) {}
+static inline int
+coresight_enable(struct coresight_device *csdev) { return -ENOSYS; }
+static inline void coresight_disable(struct coresight_device *csdev) {}
+static inline int coresight_is_bit_set(u32 val, int position, int value)
+					 { return 0; }
+static inline int coresight_timeout(void __iomem *addr, u32 offset,
+				     int position, int value) { return 1; }
+#ifdef CONFIG_OF
+static inline struct coresight_platform_data *of_get_coresight_platform_data(
+	struct device *dev, struct device_node *node) { return NULL; }
+#endif
+#endif
+
+#endif
diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h
new file mode 100644
index 000000000000..c4d4eb8ac9fe
--- /dev/null
+++ b/include/linux/cpufeature.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_CPUFEATURE_H
+#define __LINUX_CPUFEATURE_H
+
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+
+#include <linux/mod_devicetable.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Macros imported from <asm/cpufeature.h>:
+ * - cpu_feature(x)		ordinal value of feature called 'x'
+ * - cpu_have_feature(u32 n)	whether feature #n is available
+ * - MAX_CPU_FEATURES		upper bound for feature ordinal values
+ * Optional:
+ * - CPU_FEATURE_TYPEFMT	format string fragment for printing the cpu type
+ * - CPU_FEATURE_TYPEVAL	set of values matching the format string above
+ */
+
+#ifndef CPU_FEATURE_TYPEFMT
+#define CPU_FEATURE_TYPEFMT	"%s"
+#endif
+
+#ifndef CPU_FEATURE_TYPEVAL
+#define CPU_FEATURE_TYPEVAL	ELF_PLATFORM
+#endif
+
+/*
+ * Use module_cpu_feature_match(feature, module_init_function) to
+ * declare that
+ * a) the module shall be probed upon discovery of CPU feature 'feature'
+ *    (typically at boot time using udev)
+ * b) the module must not be loaded if CPU feature 'feature' is not present
+ *    (not even by manual insmod).
+ *
+ * For a list of legal values for 'feature', please consult the file
+ * 'asm/cpufeature.h' of your favorite architecture.
+ */
+#define module_cpu_feature_match(x, __init)			\
+static struct cpu_feature const cpu_feature_match_ ## x[] =	\
+	{ { .feature = cpu_feature(x) }, { } };			\
+MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x);		\
+								\
+static int cpu_feature_match_ ## x ## _init(void)		\
+{								\
+	if (!cpu_have_feature(cpu_feature(x)))			\
+		return -ENODEV;					\
+	return __init();					\
+}								\
+module_init(cpu_feature_match_ ## x ## _init)
+
+#endif
+#endif
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 3fe661fe96d1..b19d3dc2e651 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -87,25 +87,26 @@ extern void rebuild_sched_domains(void);
 extern void cpuset_print_task_mems_allowed(struct task_struct *p);
 
 /*
- * get_mems_allowed is required when making decisions involving mems_allowed
- * such as during page allocation. mems_allowed can be updated in parallel
- * and depending on the new value an operation can fail potentially causing
- * process failure. A retry loop with get_mems_allowed and put_mems_allowed
- * prevents these artificial failures.
+ * read_mems_allowed_begin is required when making decisions involving
+ * mems_allowed such as during page allocation. mems_allowed can be updated in
+ * parallel and depending on the new value an operation can fail potentially
+ * causing process failure. A retry loop with read_mems_allowed_begin and
+ * read_mems_allowed_retry prevents these artificial failures.
  */
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
 /*
- * If this returns false, the operation that took place after get_mems_allowed
- * may have failed. It is up to the caller to retry the operation if
+ * If this returns true, the operation that took place after
+ * read_mems_allowed_begin may have failed artificially due to a concurrent
+ * update of mems_allowed. It is up to the caller to retry the operation if
  * appropriate.
  */
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return !read_seqcount_retry(&current->mems_allowed_seq, seq);
+	return read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
 static inline void set_mems_allowed(nodemask_t nodemask)
@@ -225,14 +226,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 {
 }
 
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return 0;
 }
 
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return true;
+	return false;
 }
 
 #endif /* !CONFIG_CPUSETS */
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 7032518f8542..60023e5d3169 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -14,14 +14,13 @@
 extern unsigned long long elfcorehdr_addr;
 extern unsigned long long elfcorehdr_size;
 
-extern int __weak elfcorehdr_alloc(unsigned long long *addr,
-				   unsigned long long *size);
-extern void __weak elfcorehdr_free(unsigned long long addr);
-extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos);
-extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
-extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
-					 unsigned long from, unsigned long pfn,
-					 unsigned long size, pgprot_t prot);
+extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size);
+extern void elfcorehdr_free(unsigned long long addr);
+extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos);
+extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+extern int remap_oldmem_pfn_range(struct vm_area_struct *vma,
+				  unsigned long from, unsigned long pfn,
+				  unsigned long size, pgprot_t prot);
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 04421e825365..6c58dd7cb9ac 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -68,6 +68,7 @@ extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
 extern int set_groups(struct cred *, struct group_info *);
 extern int groups_search(const struct group_info *, kgid_t);
+extern bool may_setgroups(void);
 
 /* access the groups "array" with this macro */
 #define GROUP_AT(gi, i) \
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index bf72e9ac6de0..3b50cac7ccb3 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -429,7 +429,7 @@ static inline unsigned __d_entry_type(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_ENTRY_TYPE;
 }
 
-static inline bool d_is_directory(const struct dentry *dentry)
+static inline bool d_can_lookup(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE;
 }
@@ -439,6 +439,11 @@ static inline bool d_is_autodir(const struct dentry *dentry)
 	return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE;
 }
 
+static inline bool d_is_dir(const struct dentry *dentry)
+{
+	return d_can_lookup(dentry) || d_is_autodir(dentry);
+}
+
 static inline bool d_is_symlink(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index c5c92d59e531..0a5f55272672 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -433,6 +433,7 @@ typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
 typedef void (*dma_async_tx_callback)(void *dma_async_param);
 
 struct dmaengine_unmap_data {
+	u8 map_cnt;
 	u8 to_cnt;
 	u8 from_cnt;
 	u8 bidi_cnt;
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f4233b195dab..92d0597b7bba 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -524,6 +524,7 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
+extern void ftrace_module_init(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
@@ -533,6 +534,7 @@ static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) {}
 static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	return -EINVAL;
@@ -603,25 +605,27 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 }
 
-#ifndef HAVE_ARCH_CALLER_ADDR
+/* All archs should have this, but we define it for consistency */
+#ifndef ftrace_return_address0
+# define ftrace_return_address0 __builtin_return_address(0)
+#endif
+
+/* Archs may use other ways for ADDR1 and beyond */
+#ifndef ftrace_return_address
 # ifdef CONFIG_FRAME_POINTER
-#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#  define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-#  define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
-#  define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
-#  define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
-#  define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
-#  define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
+#  define ftrace_return_address(n) __builtin_return_address(n)
 # else
-#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#  define CALLER_ADDR1 0UL
-#  define CALLER_ADDR2 0UL
-#  define CALLER_ADDR3 0UL
-#  define CALLER_ADDR4 0UL
-#  define CALLER_ADDR5 0UL
-#  define CALLER_ADDR6 0UL
+#  define ftrace_return_address(n) 0UL
 # endif
-#endif /* ifndef HAVE_ARCH_CALLER_ADDR */
+#endif
+
+#define CALLER_ADDR0 ((unsigned long)ftrace_return_address0)
+#define CALLER_ADDR1 ((unsigned long)ftrace_return_address(1))
+#define CALLER_ADDR2 ((unsigned long)ftrace_return_address(2))
+#define CALLER_ADDR3 ((unsigned long)ftrace_return_address(3))
+#define CALLER_ADDR4 ((unsigned long)ftrace_return_address(4))
+#define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
+#define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
 
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
diff --git a/include/linux/futex.h b/include/linux/futex.h
index b0d95cac826e..6435f46d6e13 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -55,7 +55,11 @@ union futex_key {
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
 extern void exit_pi_state_list(struct task_struct *curr);
+#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
+#define futex_cmpxchg_enabled 1
+#else
 extern int futex_cmpxchg_enabled;
+#endif
 #else
 static inline void exit_robust_list(struct task_struct *curr)
 {
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 31b9d299ef6c..00c88fccd162 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -286,6 +286,7 @@ struct hid_item {
 #define HID_QUIRK_HIDINPUT_FORCE		0x00000080
 #define HID_QUIRK_NO_EMPTY_INPUT		0x00000100
 #define HID_QUIRK_NO_INIT_INPUT_REPORTS		0x00000200
+#define HID_QUIRK_ALWAYS_POLL			0x00000400
 #define HID_QUIRK_SKIP_OUTPUT_REPORTS		0x00010000
 #define HID_QUIRK_FULLSPEED_INTERVAL		0x10000000
 #define HID_QUIRK_NO_INIT_REPORTS		0x20000000
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8c43cc469d78..42b05c4c53e5 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -382,15 +382,13 @@ static inline pgoff_t basepage_index(struct page *page)
 
 extern void dissolve_free_huge_pages(unsigned long start_pfn,
 				     unsigned long end_pfn);
-int pmd_huge_support(void);
-/*
- * Currently hugepage migration is enabled only for pmd-based hugepage.
- * This function will be updated when hugepage migration is more widely
- * supported.
- */
 static inline int hugepage_migration_support(struct hstate *h)
 {
-	return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+	return huge_page_shift(h) == PMD_SHIFT;
+#else
+	return 0;
+#endif
 }
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
@@ -402,6 +400,16 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 	return &mm->page_table_lock;
 }
 
+static inline bool hugepages_supported(void)
+{
+	/*
+	 * Some platform decide whether they support huge pages at boot
+	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
+	 * there is no such support
+	 */
+	return HPAGE_SHIFT != 0;
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
@@ -430,7 +438,6 @@ static inline pgoff_t basepage_index(struct page *page)
 	return page->index;
 }
 #define dissolve_free_huge_pages(s, e)	do {} while (0)
-#define pmd_huge_support()	0
 #define hugepage_migration_support(h)	0
 
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 344883dce584..6088058a3e00 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -464,15 +464,17 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi,
  * 0 . 13 (Windows Server 2008)
  * 1 . 1  (Windows 7)
  * 2 . 4  (Windows 8)
+ * 3 . 0  (Windows 8 R2)
  */
 
 #define VERSION_WS2008  ((0 << 16) | (13))
 #define VERSION_WIN7    ((1 << 16) | (1))
 #define VERSION_WIN8    ((2 << 16) | (4))
+#define VERSION_WIN8_1    ((3 << 16) | (0))
 
 #define VERSION_INVAL -1
 
-#define VERSION_CURRENT VERSION_WIN8
+#define VERSION_CURRENT VERSION_WIN8_1
 
 /* Make maximum size of pipe payload of 16K */
 #define MAX_PIPE_DATA_PAYLOAD		(sizeof(u8) * 16384)
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 7c8b20b120ea..a9a53b12397b 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -56,6 +56,7 @@ struct macvlan_dev {
 	int			numqueues;
 	netdev_features_t	tap_features;
 	int			minor;
+	int			nest_level;
 };
 
 static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index a899dc24be15..a6aa970758a2 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -194,6 +194,7 @@ struct team {
 	bool user_carrier_enabled;
 	bool queue_override_enabled;
 	struct list_head *qom_lists; /* array of queue override mapping lists */
+	bool port_mtu_change_allowed;
 	struct {
 		unsigned int count;
 		unsigned int interval; /* in ms */
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index bbedfb56bd66..2abe67bd4df8 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -73,7 +73,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
 /* found in socket.c */
 extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
 
-static inline int is_vlan_dev(struct net_device *dev)
+static inline bool is_vlan_dev(struct net_device *dev)
 {
         return dev->priv_flags & IFF_802_1Q_VLAN;
 }
@@ -158,6 +158,7 @@ struct vlan_dev_priv {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll				*netpoll;
 #endif
+	unsigned int				nest_level;
 };
 
 static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
@@ -185,7 +186,6 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio)
 }
 
 extern bool vlan_do_receive(struct sk_buff **skb);
-extern struct sk_buff *vlan_untag(struct sk_buff *skb);
 
 extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid);
 extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid);
@@ -227,11 +227,6 @@ static inline bool vlan_do_receive(struct sk_buff **skb)
 	return false;
 }
 
-static inline struct sk_buff *vlan_untag(struct sk_buff *skb)
-{
-	return skb;
-}
-
 static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid)
 {
 	return 0;
diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h
index 8bbd7bc1043d..03fa332ad2a8 100644
--- a/include/linux/iio/events.h
+++ b/include/linux/iio/events.h
@@ -72,7 +72,7 @@ struct iio_event_data {
 
 #define IIO_EVENT_CODE_EXTRACT_TYPE(mask) ((mask >> 56) & 0xFF)
 
-#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0xCF)
+#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0x7F)
 
 #define IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(mask) ((mask >> 32) & 0xFF)
 
diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h
index 369cf2cd5144..68f46cd5d514 100644
--- a/include/linux/iio/trigger.h
+++ b/include/linux/iio/trigger.h
@@ -84,10 +84,12 @@ static inline void iio_trigger_put(struct iio_trigger *trig)
 	put_device(&trig->dev);
 }
 
-static inline void iio_trigger_get(struct iio_trigger *trig)
+static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig)
 {
 	get_device(&trig->dev);
 	__module_get(trig->ops->owner);
+
+	return trig;
 }
 
 /**
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 0068708161ff..0a21fbefdfbe 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -242,7 +242,7 @@ static inline void in_dev_put(struct in_device *idev)
 static __inline__ __be32 inet_make_mask(int logmask)
 {
 	if (logmask)
-		return htonl(~((1<<(32-logmask))-1));
+		return htonl(~((1U<<(32-logmask))-1));
 	return 0;
 }
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a2678d35b5a2..203c43d3e1b8 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -202,7 +202,40 @@ static inline int check_wakeup_irqs(void) { return 0; }
 
 extern cpumask_var_t irq_default_affinity;
 
-extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+/* Internal implementation. Use the helpers below */
+extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
+			      bool force);
+
+/**
+ * irq_set_affinity - Set the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @mask:	cpumask
+ *
+ * Fails if cpumask does not contain an online CPU
+ */
+static inline int
+irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, false);
+}
+
+/**
+ * irq_force_affinity - Force the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @mask:	cpumask
+ *
+ * Same as irq_set_affinity, but without checking the mask against
+ * online cpus.
+ *
+ * Solely for low level cpu hotplug code, where we need to make per
+ * cpu interrupts affine before the cpu becomes online.
+ */
+static inline int
+irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, true);
+}
+
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
@@ -238,6 +271,11 @@ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
 	return -EINVAL;
 }
 
+static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return 0;
+}
+
 static inline int irq_can_set_affinity(unsigned int irq)
 {
 	return 0;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 7dc10036eff5..ef1ac9feff56 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -385,7 +385,8 @@ extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
 extern void irq_cpu_online(void);
 extern void irq_cpu_offline(void);
-extern int __irq_set_affinity_locked(struct irq_data *data,  const struct cpumask *cpumask);
+extern int irq_set_affinity_locked(struct irq_data *data,
+				   const struct cpumask *cpumask, bool force);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void irq_move_irq(struct irq_data *data);
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
new file mode 100644
index 000000000000..03a4ea37ba86
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H
+#define __LINUX_IRQCHIP_ARM_GIC_V3_H
+
+#include <asm/sysreg.h>
+
+/*
+ * Distributor registers. We assume we're running non-secure, with ARE
+ * being set. Secure-only and non-ARE registers are not described.
+ */
+#define GICD_CTLR			0x0000
+#define GICD_TYPER			0x0004
+#define GICD_IIDR			0x0008
+#define GICD_STATUSR			0x0010
+#define GICD_SETSPI_NSR			0x0040
+#define GICD_CLRSPI_NSR			0x0048
+#define GICD_SETSPI_SR			0x0050
+#define GICD_CLRSPI_SR			0x0058
+#define GICD_SEIR			0x0068
+#define GICD_ISENABLER			0x0100
+#define GICD_ICENABLER			0x0180
+#define GICD_ISPENDR			0x0200
+#define GICD_ICPENDR			0x0280
+#define GICD_ISACTIVER			0x0300
+#define GICD_ICACTIVER			0x0380
+#define GICD_IPRIORITYR			0x0400
+#define GICD_ICFGR			0x0C00
+#define GICD_IROUTER			0x6000
+#define GICD_PIDR2			0xFFE8
+
+#define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_ARE_NS		(1U << 4)
+#define GICD_CTLR_ENABLE_G1A		(1U << 1)
+#define GICD_CTLR_ENABLE_G1		(1U << 0)
+
+#define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
+#define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
+
+#define GIC_PIDR2_ARCH_MASK		0xf0
+#define GIC_PIDR2_ARCH_GICv3		0x30
+#define GIC_PIDR2_ARCH_GICv4		0x40
+
+/*
+ * Re-Distributor registers, offsets from RD_base
+ */
+#define GICR_CTLR			GICD_CTLR
+#define GICR_IIDR			0x0004
+#define GICR_TYPER			0x0008
+#define GICR_STATUSR			GICD_STATUSR
+#define GICR_WAKER			0x0014
+#define GICR_SETLPIR			0x0040
+#define GICR_CLRLPIR			0x0048
+#define GICR_SEIR			GICD_SEIR
+#define GICR_PROPBASER			0x0070
+#define GICR_PENDBASER			0x0078
+#define GICR_INVLPIR			0x00A0
+#define GICR_INVALLR			0x00B0
+#define GICR_SYNCR			0x00C0
+#define GICR_MOVLPIR			0x0100
+#define GICR_MOVALLR			0x0110
+#define GICR_PIDR2			GICD_PIDR2
+
+#define GICR_WAKER_ProcessorSleep	(1U << 1)
+#define GICR_WAKER_ChildrenAsleep	(1U << 2)
+
+/*
+ * Re-Distributor registers, offsets from SGI_base
+ */
+#define GICR_ISENABLER0			GICD_ISENABLER
+#define GICR_ICENABLER0			GICD_ICENABLER
+#define GICR_ISPENDR0			GICD_ISPENDR
+#define GICR_ICPENDR0			GICD_ICPENDR
+#define GICR_ISACTIVER0			GICD_ISACTIVER
+#define GICR_ICACTIVER0			GICD_ICACTIVER
+#define GICR_IPRIORITYR0		GICD_IPRIORITYR
+#define GICR_ICFGR0			GICD_ICFGR
+
+#define GICR_TYPER_VLPIS		(1U << 1)
+#define GICR_TYPER_LAST			(1U << 4)
+
+/*
+ * CPU interface registers
+ */
+#define ICC_CTLR_EL1_EOImode_drop_dir	(0U << 1)
+#define ICC_CTLR_EL1_EOImode_drop	(1U << 1)
+#define ICC_SRE_EL1_SRE			(1U << 0)
+
+/*
+ * Hypervisor interface registers (SRE only)
+ */
+#define ICH_LR_VIRTUAL_ID_MASK		((1UL << 32) - 1)
+
+#define ICH_LR_EOI			(1UL << 41)
+#define ICH_LR_GROUP			(1UL << 60)
+#define ICH_LR_STATE			(3UL << 62)
+#define ICH_LR_PENDING_BIT		(1UL << 62)
+#define ICH_LR_ACTIVE_BIT		(1UL << 63)
+
+#define ICH_MISR_EOI			(1 << 0)
+#define ICH_MISR_U			(1 << 1)
+
+#define ICH_HCR_EN			(1 << 0)
+#define ICH_HCR_UIE			(1 << 1)
+
+#define ICH_VMCR_CTLR_SHIFT		0
+#define ICH_VMCR_CTLR_MASK		(0x21f << ICH_VMCR_CTLR_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT		18
+#define ICH_VMCR_BPR1_MASK		(7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT		21
+#define ICH_VMCR_BPR0_MASK		(7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT		24
+#define ICH_VMCR_PMR_MASK		(0xffUL << ICH_VMCR_PMR_SHIFT)
+
+#define ICC_EOIR1_EL1			sys_reg(3, 0, 12, 12, 1)
+#define ICC_IAR1_EL1			sys_reg(3, 0, 12, 12, 0)
+#define ICC_SGI1R_EL1			sys_reg(3, 0, 12, 11, 5)
+#define ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
+#define ICC_CTLR_EL1			sys_reg(3, 0, 12, 12, 4)
+#define ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
+#define ICC_GRPEN1_EL1			sys_reg(3, 0, 12, 12, 7)
+
+#define ICC_IAR1_EL1_SPURIOUS		0x3ff
+
+#define ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
+
+#define ICC_SRE_EL2_SRE			(1 << 0)
+#define ICC_SRE_EL2_ENABLE		(1 << 3)
+
+/*
+ * System register definitions
+ */
+#define ICH_VSEIR_EL2			sys_reg(3, 4, 12, 9, 4)
+#define ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
+#define ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
+#define ICH_MISR_EL2			sys_reg(3, 4, 12, 11, 2)
+#define ICH_EISR_EL2			sys_reg(3, 4, 12, 11, 3)
+#define ICH_ELSR_EL2			sys_reg(3, 4, 12, 11, 5)
+#define ICH_VMCR_EL2			sys_reg(3, 4, 12, 11, 7)
+
+#define __LR0_EL2(x)			sys_reg(3, 4, 12, 12, x)
+#define __LR8_EL2(x)			sys_reg(3, 4, 12, 13, x)
+
+#define ICH_LR0_EL2			__LR0_EL2(0)
+#define ICH_LR1_EL2			__LR0_EL2(1)
+#define ICH_LR2_EL2			__LR0_EL2(2)
+#define ICH_LR3_EL2			__LR0_EL2(3)
+#define ICH_LR4_EL2			__LR0_EL2(4)
+#define ICH_LR5_EL2			__LR0_EL2(5)
+#define ICH_LR6_EL2			__LR0_EL2(6)
+#define ICH_LR7_EL2			__LR0_EL2(7)
+#define ICH_LR8_EL2			__LR8_EL2(0)
+#define ICH_LR9_EL2			__LR8_EL2(1)
+#define ICH_LR10_EL2			__LR8_EL2(2)
+#define ICH_LR11_EL2			__LR8_EL2(3)
+#define ICH_LR12_EL2			__LR8_EL2(4)
+#define ICH_LR13_EL2			__LR8_EL2(5)
+#define ICH_LR14_EL2			__LR8_EL2(6)
+#define ICH_LR15_EL2			__LR8_EL2(7)
+
+#define __AP0Rx_EL2(x)			sys_reg(3, 4, 12, 8, x)
+#define ICH_AP0R0_EL2			__AP0Rx_EL2(0)
+#define ICH_AP0R1_EL2			__AP0Rx_EL2(1)
+#define ICH_AP0R2_EL2			__AP0Rx_EL2(2)
+#define ICH_AP0R3_EL2			__AP0Rx_EL2(3)
+
+#define __AP1Rx_EL2(x)			sys_reg(3, 4, 12, 9, x)
+#define ICH_AP1R0_EL2			__AP1Rx_EL2(0)
+#define ICH_AP1R1_EL2			__AP1Rx_EL2(1)
+#define ICH_AP1R2_EL2			__AP1Rx_EL2(2)
+#define ICH_AP1R3_EL2			__AP1Rx_EL2(3)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+static inline void gic_write_eoir(u64 irq)
+{
+	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq));
+	isb();
+}
+
+#endif
+
+#endif
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 0ceb389dba6c..45e2d8c15bd2 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -21,6 +21,8 @@
 #define GIC_CPU_ACTIVEPRIO		0xd0
 #define GIC_CPU_IDENT			0xfc
 
+#define GICC_IAR_INT_ID_MASK		0x3ff
+
 #define GIC_DIST_CTRL			0x000
 #define GIC_DIST_CTR			0x004
 #define GIC_DIST_IGROUP			0x080
@@ -93,6 +95,11 @@ int gic_get_cpu_id(unsigned int cpu);
 void gic_migrate_target(unsigned int new_cpu_id);
 unsigned long gic_get_sgir_physaddr(void);
 
+extern const struct irq_domain_ops *gic_routable_irq_domain_ops;
+static inline void __init register_routable_domain_ops
+					(const struct irq_domain_ops *ops)
+{
+	gic_routable_irq_domain_ops = ops;
+}
 #endif /* __ASSEMBLY */
-
 #endif
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 26e2661d3935..472c021a2d4f 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -27,6 +27,8 @@ struct irq_desc;
  * @irq_count:		stats field to detect stalled irqs
  * @last_unhandled:	aging timer for unhandled count
  * @irqs_unhandled:	stats field for spurious unhandled interrupts
+ * @threads_handled:	stats field for deferred spurious detection of threaded handlers
+ * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers
  * @lock:		locking for SMP
  * @affinity_hint:	hint to user space for preferred irq affinity
  * @affinity_notify:	context for notification of affinity changes
@@ -52,6 +54,8 @@ struct irq_desc {
 	unsigned int		irq_count;	/* For detecting broken IRQs */
 	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
 	unsigned int		irqs_unhandled;
+	atomic_t		threads_handled;
+	int			threads_handled_last;
 	raw_spinlock_t		lock;
 	struct cpumask		*percpu_enabled;
 #ifdef CONFIG_SMP
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d5b50a19463c..0dae71e9971c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -159,7 +159,11 @@ typedef struct journal_header_s
  * journal_block_tag (in the descriptor).  The other h_chksum* fields are
  * not used.
  *
- * Checksum v1 and v2 are mutually exclusive features.
+ * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
+ * journal_block_tag3_t to store a full 32-bit checksum.  Everything else
+ * is the same as v2.
+ *
+ * Checksum v1, v2, and v3 are mutually exclusive features.
  */
 struct commit_header {
 	__be32		h_magic;
@@ -179,6 +183,14 @@ struct commit_header {
  * raw struct shouldn't be used for pointer math or sizeof() - use
  * journal_tag_bytes(journal) instead to compute this.
  */
+typedef struct journal_block_tag3_s
+{
+	__be32		t_blocknr;	/* The on-disk block number */
+	__be32		t_flags;	/* See below */
+	__be32		t_blocknr_high; /* most-significant high 32bits. */
+	__be32		t_checksum;	/* crc32c(uuid+seq+block) */
+} journal_block_tag3_t;
+
 typedef struct journal_block_tag_s
 {
 	__be32		t_blocknr;	/* The on-disk block number */
@@ -187,9 +199,6 @@ typedef struct journal_block_tag_s
 	__be32		t_blocknr_high; /* most-significant high 32bits. */
 } journal_block_tag_t;
 
-#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
-#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t))
-
 /* Tail of descriptor block, for checksumming */
 struct jbd2_journal_block_tail {
 	__be32		t_checksum;	/* crc32c(uuid+descr_block) */
@@ -284,6 +293,7 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_64BIT		0x00000002
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
+#define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
 
 /* Features known to this kernel version: */
 #define JBD2_KNOWN_COMPAT_FEATURES	JBD2_FEATURE_COMPAT_CHECKSUM
@@ -291,7 +301,8 @@ typedef struct journal_superblock_s
 #define JBD2_KNOWN_INCOMPAT_FEATURES	(JBD2_FEATURE_INCOMPAT_REVOKE | \
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V2)
+					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
+					JBD2_FEATURE_INCOMPAT_CSUM_V3)
 
 #ifdef __KERNEL__
 
@@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y)
 extern int jbd2_journal_blocks_per_page(struct inode *inode);
 extern size_t journal_tag_bytes(journal_t *journal);
 
+static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
+{
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) ||
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return 1;
+
+	return 0;
+}
+
 /*
  * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
  * transaction control blocks.
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 1f44466c1e9d..c367cbdf73ab 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -258,23 +258,11 @@ extern unsigned long preset_lpj;
 #define SEC_JIFFIE_SC (32 - SHIFT_HZ)
 #endif
 #define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29)
-#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19)
 #define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\
                                 TICK_NSEC -1) / (u64)TICK_NSEC))
 
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
-#define USEC_CONVERSION  \
-                    ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\
-                                        TICK_NSEC -1) / (u64)TICK_NSEC))
-/*
- * USEC_ROUND is used in the timeval to jiffie conversion.  See there
- * for more details.  It is the scaled resolution rounding value.  Note
- * that it is a 64-bit value.  Since, when it is applied, we are already
- * in jiffies (albit scaled), it is nothing but the bits we will shift
- * off.
- */
-#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1)
 /*
  * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index 6b06d378f3df..e465bb15912d 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -283,7 +283,7 @@ struct kgdb_io {
 
 extern struct kgdb_arch		arch_kgdb_ops;
 
-extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs);
+extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs);
 
 #ifdef CONFIG_SERIAL_KGDB_NMI
 extern int kgdb_register_nmi_console(void);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b8e9a43e501a..55d75a7cba73 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -138,8 +138,6 @@ static inline bool is_error_page(struct page *page)
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
 
-struct kvm;
-struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
 extern spinlock_t kvm_lock;
@@ -192,7 +190,7 @@ struct kvm_async_pf {
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
 void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 		       struct kvm_arch_async_pf *arch);
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
@@ -313,25 +311,6 @@ struct kvm_kernel_irq_routing_entry {
 	struct hlist_node link;
 };
 
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-
-struct kvm_irq_routing_table {
-	int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
-	struct kvm_kernel_irq_routing_entry *rt_entries;
-	u32 nr_rt_entries;
-	/*
-	 * Array indexed by gsi. Each entry contains list of irq chips
-	 * the gsi is connected to.
-	 */
-	struct hlist_head map[0];
-};
-
-#else
-
-struct kvm_irq_routing_table {};
-
-#endif
-
 #ifndef KVM_PRIVATE_MEM_SLOTS
 #define KVM_PRIVATE_MEM_SLOTS 0
 #endif
@@ -358,6 +337,7 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots *memslots;
 	struct srcu_struct srcu;
+	struct srcu_struct irq_srcu;
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
 	u32 bsp_vcpu_id;
 #endif
@@ -388,11 +368,12 @@ struct kvm {
 	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	/*
-	 * Update side is protected by irq_lock and,
-	 * if configured, irqfds.lock.
+	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
 	struct hlist_head mask_notifier_list;
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
@@ -442,7 +423,7 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 int __must_check vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
 #else
@@ -531,6 +512,8 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
+				      bool *writable);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 void kvm_set_page_accessed(struct page *page);
@@ -589,7 +572,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
 int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
-int kvm_dev_ioctl_check_extension(long ext);
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 
 int kvm_get_dirty_log(struct kvm *kvm,
 			struct kvm_dirty_log *log, int *is_dirty);
@@ -627,6 +610,8 @@ void kvm_arch_exit(void);
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
+
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
@@ -635,8 +620,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
-int kvm_arch_hardware_enable(void *garbage);
-void kvm_arch_hardware_disable(void *garbage);
+int kvm_arch_hardware_enable(void);
+void kvm_arch_hardware_disable(void);
 int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
@@ -739,6 +724,10 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 			     bool mask);
 
+int kvm_irq_map_gsi(struct kvm *kvm,
+		    struct kvm_kernel_irq_routing_entry *entries, int gsi);
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
+
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 		bool line_status);
 int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
@@ -868,6 +857,13 @@ static inline hpa_t pfn_to_hpa(pfn_t pfn)
 	return (hpa_t)pfn << PAGE_SHIFT;
 }
 
+static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
+{
+	unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+
+	return kvm_is_error_hva(hva);
+}
+
 static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
 {
 	set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
@@ -918,28 +914,27 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *entries,
 			unsigned nr,
 			unsigned flags);
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
-			  struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue);
 void kvm_free_irq_routing(struct kvm *kvm);
 
-int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
-
 #else
 
 static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 #endif
 
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
 #ifdef CONFIG_HAVE_KVM_EVENTFD
 
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
+#ifdef CONFIG_HAVE_KVM_IRQFD
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
-void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
+void kvm_irq_routing_update(struct kvm *);
 #else
 static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 {
@@ -961,10 +956,8 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 static inline void kvm_irqfd_release(struct kvm *kvm) {}
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm,
-					  struct kvm_irq_routing_table *irq_rt)
+static inline void kvm_irq_routing_update(struct kvm *kvm)
 {
-	rcu_assign_pointer(kvm->irq_routing, irq_rt);
 }
 #endif
 
@@ -1025,8 +1018,6 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 
 extern bool kvm_rebooting;
 
-struct kvm_device_ops;
-
 struct kvm_device {
 	struct kvm_device_ops *ops;
 	struct kvm *kvm;
@@ -1059,11 +1050,11 @@ struct kvm_device_ops {
 void kvm_device_get(struct kvm_device *dev);
 void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
-extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index b0bcce0ddc95..b606bb689a3e 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -17,6 +17,20 @@
 #ifndef __KVM_TYPES_H__
 #define __KVM_TYPES_H__
 
+struct kvm;
+struct kvm_async_pf;
+struct kvm_device_ops;
+struct kvm_interrupt;
+struct kvm_irq_routing_table;
+struct kvm_memory_slot;
+struct kvm_one_reg;
+struct kvm_run;
+struct kvm_userspace_memory_region;
+struct kvm_vcpu;
+struct kvm_vcpu_init;
+
+enum kvm_mr_change;
+
 #include <asm/types.h>
 
 /*
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bec6dbe939a0..e13b3aef0b0c 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -593,6 +593,7 @@ struct ata_host {
 	struct device 		*dev;
 	void __iomem * const	*iomap;
 	unsigned int		n_ports;
+	unsigned int		n_tags;			/* nr of NCQ tags */
 	void			*private_data;
 	struct ata_port_operations *ops;
 	unsigned long		flags;
@@ -822,6 +823,7 @@ struct ata_port {
 	unsigned long		qc_allocated;
 	unsigned int		qc_active;
 	int			nr_active_links; /* #links with active qcs */
+	unsigned int		last_tag;	/* track next tag hw expects */
 
 	struct ata_link		link;		/* host default link */
 	struct ata_link		*slave_link;	/* see ata_slave_link_init() */
diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h
new file mode 100644
index 000000000000..307d9cab2026
--- /dev/null
+++ b/include/linux/mailbox_client.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ * Author: Jassi Brar <jassisinghbrar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MAILBOX_CLIENT_H
+#define __MAILBOX_CLIENT_H
+
+#include <linux/of.h>
+#include <linux/device.h>
+
+struct mbox_chan;
+
+/**
+ * struct mbox_client - User of a mailbox
+ * @dev:		The client device
+ * @tx_block:		If the mbox_send_message should block until data is
+ *			transmitted.
+ * @tx_tout:		Max block period in ms before TX is assumed failure
+ * @knows_txdone:	If the client could run the TX state machine. Usually
+ *			if the client receives some ACK packet for transmission.
+ *			Unused if the controller already has TX_Done/RTR IRQ.
+ * @rx_callback:	Atomic callback to provide client the data received
+ * @tx_done:		Atomic callback to tell client of data transmission
+ */
+struct mbox_client {
+	struct device *dev;
+	bool tx_block;
+	unsigned long tx_tout;
+	bool knows_txdone;
+
+	void (*rx_callback)(struct mbox_client *cl, void *mssg);
+	void (*tx_done)(struct mbox_client *cl, void *mssg, int r);
+};
+
+struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index);
+int mbox_send_message(struct mbox_chan *chan, void *mssg);
+void mbox_client_txdone(struct mbox_chan *chan, int r); /* atomic */
+bool mbox_client_peek_data(struct mbox_chan *chan); /* atomic */
+void mbox_free_channel(struct mbox_chan *chan); /* may sleep */
+
+#endif /* __MAILBOX_CLIENT_H */
diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h
new file mode 100644
index 000000000000..d4cf96f07cfc
--- /dev/null
+++ b/include/linux/mailbox_controller.h
@@ -0,0 +1,133 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MAILBOX_CONTROLLER_H
+#define __MAILBOX_CONTROLLER_H
+
+#include <linux/of.h>
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/device.h>
+#include <linux/completion.h>
+
+struct mbox_chan;
+
+/**
+ * struct mbox_chan_ops - methods to control mailbox channels
+ * @send_data:	The API asks the MBOX controller driver, in atomic
+ *		context try to transmit a message on the bus. Returns 0 if
+ *		data is accepted for transmission, -EBUSY while rejecting
+ *		if the remote hasn't yet read the last data sent. Actual
+ *		transmission of data is reported by the controller via
+ *		mbox_chan_txdone (if it has some TX ACK irq). It must not
+ *		sleep.
+ * @startup:	Called when a client requests the chan. The controller
+ *		could ask clients for additional parameters of communication
+ *		to be provided via client's chan_data. This call may
+ *		block. After this call the Controller must forward any
+ *		data received on the chan by calling mbox_chan_received_data.
+ *		The controller may do stuff that need to sleep.
+ * @shutdown:	Called when a client relinquishes control of a chan.
+ *		This call may block too. The controller must not forward
+ *		any received data anymore.
+ *		The controller may do stuff that need to sleep.
+ * @last_tx_done: If the controller sets 'txdone_poll', the API calls
+ *		  this to poll status of last TX. The controller must
+ *		  give priority to IRQ method over polling and never
+ *		  set both txdone_poll and txdone_irq. Only in polling
+ *		  mode 'send_data' is expected to return -EBUSY.
+ *		  The controller may do stuff that need to sleep/block.
+ *		  Used only if txdone_poll:=true && txdone_irq:=false
+ * @peek_data: Atomic check for any received data. Return true if controller
+ *		  has some data to push to the client. False otherwise.
+ */
+struct mbox_chan_ops {
+	int (*send_data)(struct mbox_chan *chan, void *data);
+	int (*startup)(struct mbox_chan *chan);
+	void (*shutdown)(struct mbox_chan *chan);
+	bool (*last_tx_done)(struct mbox_chan *chan);
+	bool (*peek_data)(struct mbox_chan *chan);
+};
+
+/**
+ * struct mbox_controller - Controller of a class of communication channels
+ * @dev:		Device backing this controller
+ * @ops:		Operators that work on each communication chan
+ * @chans:		Array of channels
+ * @num_chans:		Number of channels in the 'chans' array.
+ * @txdone_irq:		Indicates if the controller can report to API when
+ *			the last transmitted data was read by the remote.
+ *			Eg, if it has some TX ACK irq.
+ * @txdone_poll:	If the controller can read but not report the TX
+ *			done. Ex, some register shows the TX status but
+ *			no interrupt rises. Ignored if 'txdone_irq' is set.
+ * @txpoll_period:	If 'txdone_poll' is in effect, the API polls for
+ *			last TX's status after these many millisecs
+ * @of_xlate:		Controller driver specific mapping of channel via DT
+ * @poll:		API private. Used to poll for TXDONE on all channels.
+ * @node:		API private. To hook into list of controllers.
+ */
+struct mbox_controller {
+	struct device *dev;
+	struct mbox_chan_ops *ops;
+	struct mbox_chan *chans;
+	int num_chans;
+	bool txdone_irq;
+	bool txdone_poll;
+	unsigned txpoll_period;
+	struct mbox_chan *(*of_xlate)(struct mbox_controller *mbox,
+				      const struct of_phandle_args *sp);
+	/* Internal to API */
+	struct timer_list poll;
+	struct list_head node;
+};
+
+/*
+ * The length of circular buffer for queuing messages from a client.
+ * 'msg_count' tracks the number of buffered messages while 'msg_free'
+ * is the index where the next message would be buffered.
+ * We shouldn't need it too big because every transfer is interrupt
+ * triggered and if we have lots of data to transfer, the interrupt
+ * latencies are going to be the bottleneck, not the buffer length.
+ * Besides, mbox_send_message could be called from atomic context and
+ * the client could also queue another message from the notifier 'tx_done'
+ * of the last transfer done.
+ * REVISIT: If too many platforms see the "Try increasing MBOX_TX_QUEUE_LEN"
+ * print, it needs to be taken from config option or somesuch.
+ */
+#define MBOX_TX_QUEUE_LEN	20
+
+/**
+ * struct mbox_chan - s/w representation of a communication chan
+ * @mbox:		Pointer to the parent/provider of this channel
+ * @txdone_method:	Way to detect TXDone chosen by the API
+ * @cl:			Pointer to the current owner of this channel
+ * @tx_complete:	Transmission completion
+ * @active_req:		Currently active request hook
+ * @msg_count:		No. of mssg currently queued
+ * @msg_free:		Index of next available mssg slot
+ * @msg_data:		Hook for data packet
+ * @lock:		Serialise access to the channel
+ * @con_priv:		Hook for controller driver to attach private data
+ */
+struct mbox_chan {
+	struct mbox_controller *mbox;
+	unsigned txdone_method;
+	struct mbox_client *cl;
+	struct completion tx_complete;
+	void *active_req;
+	unsigned msg_count, msg_free;
+	void *msg_data[MBOX_TX_QUEUE_LEN];
+	spinlock_t lock; /* Serialise access to the channel */
+	void *con_priv;
+};
+
+int mbox_controller_register(struct mbox_controller *mbox); /* can sleep */
+void mbox_controller_unregister(struct mbox_controller *mbox); /* can sleep */
+void mbox_chan_received_data(struct mbox_chan *chan, void *data); /* atomic */
+void mbox_chan_txdone(struct mbox_chan *chan, int r); /* atomic */
+
+#endif /* __MAILBOX_CONTROLLER_H */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index bb7384e3c3d8..8b8d8d12348e 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -35,7 +35,7 @@ struct memory_block {
 };
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
-unsigned long __weak memory_block_size_bytes(void);
+unsigned long memory_block_size_bytes(void);
 
 /* These states are exposed to userspace as text strings in sysfs */
 #define	MEM_ONLINE		(1<<0) /* exposed to userspace */
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5f1ea756aace..5bba088bd239 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -176,6 +176,12 @@ static inline int vma_migratable(struct vm_area_struct *vma)
 {
 	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
 		return 0;
+
+#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+	if (vma->vm_flags & VM_HUGETLB)
+		return 0;
+#endif
+
 	/*
 	 * Migration allocates pages in the highest zone. If we cannot
 	 * do so then migration (at least from node to node) is not
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 84a31ad0b791..a2901c414664 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -5,7 +5,9 @@
 #include <linux/mempolicy.h>
 #include <linux/migrate_mode.h>
 
-typedef struct page *new_page_t(struct page *, unsigned long private, int **);
+typedef struct page *new_page_t(struct page *page, unsigned long private,
+				int **reason);
+typedef void free_page_t(struct page *page, unsigned long private);
 
 /*
  * Return values from addresss_space_operations.migratepage():
@@ -38,7 +40,7 @@ enum migrate_reason {
 extern void putback_movable_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
-extern int migrate_pages(struct list_head *l, new_page_t x,
+extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 		unsigned long private, enum migrate_mode mode, int reason);
 
 extern int migrate_prep(void);
@@ -56,8 +58,9 @@ extern int migrate_page_move_mapping(struct address_space *mapping,
 #else
 
 static inline void putback_movable_pages(struct list_head *l) {}
-static inline int migrate_pages(struct list_head *l, new_page_t x,
-		unsigned long private, enum migrate_mode mode, int reason)
+static inline int migrate_pages(struct list_head *l, new_page_t new,
+		free_page_t free, unsigned long private, enum migrate_mode mode,
+		int reason)
 	{ return -ENOSYS; }
 
 static inline int migrate_prep(void) { return -ENOSYS; }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c1b7414c7bef..46b8ab56b9db 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1041,6 +1041,14 @@ extern void show_free_areas(unsigned int flags);
 extern bool skip_free_areas_node(unsigned int flags, int nid);
 
 int shmem_zero_setup(struct vm_area_struct *);
+#ifdef CONFIG_SHMEM
+bool shmem_mapping(struct address_space *mapping);
+#else
+static inline bool shmem_mapping(struct address_space *mapping)
+{
+	return false;
+}
+#endif
 
 extern int can_do_mlock(void);
 extern int user_shm_lock(size_t, struct user_struct *);
@@ -1123,6 +1131,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 
 extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
 int generic_error_remove_page(struct address_space *mapping, struct page *page);
@@ -1847,9 +1856,6 @@ void page_cache_async_readahead(struct address_space *mapping,
 				unsigned long size);
 
 unsigned long max_sane_readahead(unsigned long nr);
-unsigned long ra_submit(struct file_ra_state *ra,
-			struct address_space *mapping,
-			struct file *filp);
 
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
@@ -1860,7 +1866,7 @@ extern int expand_downwards(struct vm_area_struct *vma,
 #if VM_GROWSUP
 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
 #else
-  #define expand_upwards(vma, address) do { } while (0)
+  #define expand_upwards(vma, address) (0)
 #endif
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 290901a8c1de..2b58d192ea24 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -342,9 +342,9 @@ struct mm_rss_stat {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct * mmap;		/* list of VMAs */
+	struct vm_area_struct *mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
-	struct vm_area_struct * mmap_cache;	/* last find_vma result */
+	u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9b61b9bf81ac..18843532a0c9 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -75,9 +75,13 @@ enum {
 
 extern int page_group_by_mobility_disabled;
 
+#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
+#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)
+
 static inline int get_pageblock_migratetype(struct page *page)
 {
-	return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end);
+	BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2);
+	return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK);
 }
 
 struct free_area {
@@ -357,9 +361,10 @@ struct zone {
 	/* Set to true when the PG_migrate_skip bits should be cleared */
 	bool			compact_blockskip_flush;
 
-	/* pfns where compaction scanners should start */
+	/* pfn where compaction free scanner should start */
 	unsigned long		compact_cached_free_pfn;
-	unsigned long		compact_cached_migrate_pfn;
+	/* pfn where async and sync compaction migration scanner should start */
+	unsigned long		compact_cached_migrate_pfn[2];
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 45e921401b06..f2ac87c613a5 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -564,6 +564,15 @@ struct x86_cpu_id {
 #define X86_MODEL_ANY  0
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
 
+/*
+ * Generic table type for matching CPU features.
+ * @feature:	the bit number of the feature (0 - 65535)
+ */
+
+struct cpu_feature {
+	__u16	feature;
+};
+
 #define IPACK_ANY_FORMAT 0xff
 #define IPACK_ANY_ID (~0)
 struct ipack_device_id {
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 371d346fa270..b0c1e6574e7f 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -42,15 +42,25 @@ struct mnt_namespace;
  * flag, consider how it interacts with shared mounts.
  */
 #define MNT_SHARED_MASK	(MNT_UNBINDABLE)
-#define MNT_PROPAGATION_MASK	(MNT_SHARED | MNT_UNBINDABLE)
+#define MNT_USER_SETTABLE_MASK  (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \
+				 | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \
+				 | MNT_READONLY)
+#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
 
+#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED)
 
 #define MNT_INTERNAL	0x4000
 
+#define MNT_LOCK_ATIME		0x040000
+#define MNT_LOCK_NOEXEC		0x080000
+#define MNT_LOCK_NOSUID		0x100000
+#define MNT_LOCK_NODEV		0x200000
 #define MNT_LOCK_READONLY	0x400000
 #define MNT_LOCKED		0x800000
 #define MNT_DOOMED		0x1000000
 #define MNT_SYNC_UMOUNT		0x2000000
+#define MNT_MARKED		0x4000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
diff --git a/include/linux/net.h b/include/linux/net.h
index 94734a6259a4..17d83393afcc 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -248,24 +248,17 @@ do {								\
 bool __net_get_random_once(void *buf, int nbytes, bool *done,
 			   struct static_key *done_key);
 
-#ifdef HAVE_JUMP_LABEL
-#define ___NET_RANDOM_STATIC_KEY_INIT ((struct static_key) \
-		{ .enabled = ATOMIC_INIT(0), .entries = (void *)1 })
-#else /* !HAVE_JUMP_LABEL */
-#define ___NET_RANDOM_STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
-#endif /* HAVE_JUMP_LABEL */
-
 #define net_get_random_once(buf, nbytes)				\
 	({								\
 		bool ___ret = false;					\
 		static bool ___done = false;				\
-		static struct static_key ___done_key =			\
-			___NET_RANDOM_STATIC_KEY_INIT;			\
-		if (!static_key_true(&___done_key))			\
+		static struct static_key ___once_key =			\
+			STATIC_KEY_INIT_TRUE;				\
+		if (static_key_true(&___once_key))			\
 			___ret = __net_get_random_once(buf,		\
 						       nbytes,		\
 						       &___done,	\
-						       &___done_key);	\
+						       &___once_key);	\
 		___ret;							\
 	})
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index daafd9561cbc..911718fa92ed 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1145,6 +1145,7 @@ struct net_device_ops {
 	netdev_tx_t		(*ndo_dfwd_start_xmit) (struct sk_buff *skb,
 							struct net_device *dev,
 							void *priv);
+	int			(*ndo_get_lock_subclass)(struct net_device *dev);
 };
 
 /*
@@ -2861,7 +2862,12 @@ static inline void netif_addr_lock(struct net_device *dev)
 
 static inline void netif_addr_lock_nested(struct net_device *dev)
 {
-	spin_lock_nested(&dev->addr_list_lock, SINGLE_DEPTH_NESTING);
+	int subclass = SINGLE_DEPTH_NESTING;
+
+	if (dev->netdev_ops->ndo_get_lock_subclass)
+		subclass = dev->netdev_ops->ndo_get_lock_subclass(dev);
+
+	spin_lock_nested(&dev->addr_list_lock, subclass);
 }
 
 static inline void netif_addr_lock_bh(struct net_device *dev)
@@ -2988,6 +2994,14 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 	     priv; \
 	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
 
+void *netdev_lower_get_next(struct net_device *dev,
+				struct list_head **iter);
+#define netdev_for_each_lower_dev(dev, ldev, iter) \
+	for (iter = &(dev)->adj_list.lower, \
+	     ldev = netdev_lower_get_next(dev, &(iter)); \
+	     ldev; \
+	     ldev = netdev_lower_get_next(dev, &(iter)))
+
 void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
@@ -3003,6 +3017,8 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
+int dev_get_nest_level(struct net_device *dev,
+		       bool (*type_check)(struct net_device *dev));
 int skb_checksum_help(struct sk_buff *skb);
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 				  netdev_features_t features, bool tx_path);
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index aad8eeaf416d..034cda789a15 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -16,9 +16,10 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb)
 }
 
 enum netlink_skb_flags {
-	NETLINK_SKB_MMAPED	= 0x1,		/* Packet data is mmaped */
-	NETLINK_SKB_TX		= 0x2,		/* Packet was sent by userspace */
-	NETLINK_SKB_DELIVERED	= 0x4,		/* Packet was delivered */
+	NETLINK_SKB_MMAPED	= 0x1,	/* Packet data is mmaped */
+	NETLINK_SKB_TX		= 0x2,	/* Packet was sent by userspace */
+	NETLINK_SKB_DELIVERED	= 0x4,	/* Packet was delivered */
+	NETLINK_SKB_DST		= 0x8,	/* Dst set in sendto or sendmsg */
 };
 
 struct netlink_skb_parms {
@@ -169,4 +170,11 @@ struct netlink_tap {
 extern int netlink_add_tap(struct netlink_tap *nt);
 extern int netlink_remove_tap(struct netlink_tap *nt);
 
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			  struct user_namespace *ns, int cap);
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *ns, int cap);
+bool netlink_capable(const struct sk_buff *skb, int cap);
+bool netlink_net_capable(const struct sk_buff *skb, int cap);
+
 #endif	/* __LINUX_NETLINK_H */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 5624e4e2763c..53988cb3c05a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1247,11 +1247,22 @@ struct nfs41_free_stateid_res {
 	unsigned int			status;
 };
 
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+	kfree(cinfo->buckets);
+}
+
 #else
 
 struct pnfs_ds_commit_info {
 };
 
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_page;
diff --git a/include/linux/of.h b/include/linux/of.h
index 435cb995904d..3f8144dadaef 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -215,14 +215,12 @@ extern int of_property_read_u64(const struct device_node *np,
 extern int of_property_read_string(struct device_node *np,
 				   const char *propname,
 				   const char **out_string);
-extern int of_property_read_string_index(struct device_node *np,
-					 const char *propname,
-					 int index, const char **output);
 extern int of_property_match_string(struct device_node *np,
 				    const char *propname,
 				    const char *string);
-extern int of_property_count_strings(struct device_node *np,
-				     const char *propname);
+extern int of_property_read_string_helper(struct device_node *np,
+					      const char *propname,
+					      const char **out_strs, size_t sz, int index);
 extern int of_device_is_compatible(const struct device_node *device,
 				   const char *);
 extern int of_device_is_available(const struct device_node *device);
@@ -422,15 +420,9 @@ static inline int of_property_read_string(struct device_node *np,
 	return -ENOSYS;
 }
 
-static inline int of_property_read_string_index(struct device_node *np,
-						const char *propname, int index,
-						const char **out_string)
-{
-	return -ENOSYS;
-}
-
-static inline int of_property_count_strings(struct device_node *np,
-					    const char *propname)
+static inline int of_property_read_string_helper(struct device_node *np,
+						 const char *propname,
+						 const char **out_strs, size_t sz, int index)
 {
 	return -ENOSYS;
 }
@@ -536,6 +528,70 @@ static inline struct device_node *of_find_matching_node(
 }
 
 /**
+ * of_property_read_string_array() - Read an array of strings from a multiple
+ * strings property.
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @out_strs:	output array of string pointers.
+ * @sz:		number of array elements to read.
+ *
+ * Search for a property in a device tree node and retrieve a list of
+ * terminated string values (pointer to data, not a copy) in that property.
+ *
+ * If @out_strs is NULL, the number of strings in the property is returned.
+ */
+static inline int of_property_read_string_array(struct device_node *np,
+						const char *propname, const char **out_strs,
+						size_t sz)
+{
+	return of_property_read_string_helper(np, propname, out_strs, sz, 0);
+}
+
+/**
+ * of_property_count_strings() - Find and return the number of strings from a
+ * multiple strings property.
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device tree node and retrieve the number of null
+ * terminated string contain in it. Returns the number of strings on
+ * success, -EINVAL if the property does not exist, -ENODATA if property
+ * does not have a value, and -EILSEQ if the string is not null-terminated
+ * within the length of the property data.
+ */
+static inline int of_property_count_strings(struct device_node *np,
+					    const char *propname)
+{
+	return of_property_read_string_helper(np, propname, NULL, 0, 0);
+}
+
+/**
+ * of_property_read_string_index() - Find and read a string from a multiple
+ * strings property.
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @index:	index of the string in the list of strings
+ * @out_string:	pointer to null terminated return string, modified only if
+ *		return value is 0.
+ *
+ * Search for a property in a device tree node and retrieve a null
+ * terminated string value (pointer to data, not a copy) in the list of strings
+ * contained in that property.
+ * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if
+ * property does not have a value, and -EILSEQ if the string is not
+ * null-terminated within the length of the property data.
+ *
+ * The out_string pointer is modified only if a valid string can be decoded.
+ */
+static inline int of_property_read_string_index(struct device_node *np,
+						const char *propname,
+						int index, const char **output)
+{
+	int rc = of_property_read_string_helper(np, propname, output, 1, index);
+	return rc < 0 ? rc : 0;
+}
+
+/**
  * of_property_read_bool - Findfrom a property
  * @np:		device node from which the property value is to be read.
  * @propname:	name of the property to be searched.
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 2b77058a7335..5f5b83461a81 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -66,7 +66,7 @@ extern char *of_fdt_get_string(struct boot_param_header *blob, u32 offset);
 extern void *of_fdt_get_property(struct boot_param_header *blob,
 				 unsigned long node,
 				 const char *name,
-				 unsigned long *size);
+				 int *size);
 extern int of_fdt_is_compatible(struct boot_param_header *blob,
 				unsigned long node,
 				const char *compat);
@@ -81,26 +81,25 @@ extern int __initdata dt_root_size_cells;
 extern struct boot_param_header *initial_boot_params;
 
 /* For scanning the flat device-tree at boot time */
-extern char *find_flat_dt_string(u32 offset);
 extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname,
 				     int depth, void *data),
 			   void *data);
-extern void *of_get_flat_dt_prop(unsigned long node, const char *name,
-				 unsigned long *size);
+extern const void *of_get_flat_dt_prop(unsigned long node, const char *name,
+				       int *size);
 extern int of_flat_dt_is_compatible(unsigned long node, const char *name);
 extern int of_flat_dt_match(unsigned long node, const char *const *matches);
 extern unsigned long of_get_flat_dt_root(void);
-extern int of_scan_flat_dt_by_path(const char *path,
-	int (*it)(unsigned long node, const char *name, int depth, void *data),
-	void *data);
 
 extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
 extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
 				     int depth, void *data);
+extern void early_init_fdt_scan_reserved_mem(void);
 extern void early_init_dt_add_memory_arch(u64 base, u64 size);
+extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+					     bool no_map);
 extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align);
-extern u64 dt_mem_next_cell(int s, __be32 **cellp);
+extern u64 dt_mem_next_cell(int s, const __be32 **cellp);
 
 /* Early flat tree scan hooks */
 extern int early_init_dt_scan_root(unsigned long node, const char *uname,
@@ -118,6 +117,7 @@ extern void unflatten_and_copy_device_tree(void);
 extern void early_init_devtree(void *);
 extern void early_get_first_memblock_info(void *, phys_addr_t *);
 #else /* CONFIG_OF_FLATTREE */
+static inline void early_init_fdt_scan_reserved_mem(void) {}
 static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
 static inline void unflatten_device_tree(void) {}
 static inline void unflatten_and_copy_device_tree(void) {}
diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
new file mode 100644
index 000000000000..56e0507a0d58
--- /dev/null
+++ b/include/linux/of_graph.h
@@ -0,0 +1,65 @@
+/*
+ * OF graph binding parsing helpers
+ *
+ * Copyright (C) 2012 - 2013 Samsung Electronics Co., Ltd.
+ * Author: Sylwester Nawrocki <s.nawrocki@samsung.com>
+ *
+ * Copyright (C) 2012 Renesas Electronics Corp.
+ * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_OF_GRAPH_H
+#define __LINUX_OF_GRAPH_H
+
+/**
+ * struct of_endpoint - the OF graph endpoint data structure
+ * @port: identifier (value of reg property) of a port this endpoint belongs to
+ * @id: identifier (value of reg property) of this endpoint
+ * @local_node: pointer to device_node of this endpoint
+ */
+struct of_endpoint {
+	unsigned int port;
+	unsigned int id;
+	const struct device_node *local_node;
+};
+
+#ifdef CONFIG_OF
+int of_graph_parse_endpoint(const struct device_node *node,
+				struct of_endpoint *endpoint);
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+					struct device_node *previous);
+struct device_node *of_graph_get_remote_port_parent(
+					const struct device_node *node);
+struct device_node *of_graph_get_remote_port(const struct device_node *node);
+#else
+
+static inline int of_graph_parse_endpoint(const struct device_node *node,
+					struct of_endpoint *endpoint)
+{
+	return -ENOSYS;
+}
+static inline struct device_node *of_graph_get_next_endpoint(
+					const struct device_node *parent,
+					struct device_node *previous)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port_parent(
+					const struct device_node *node)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port(
+					const struct device_node *node)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_OF */
+
+#endif /* __LINUX_OF_GRAPH_H */
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 3f23b4472c31..6404253d810d 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -44,11 +44,16 @@ extern void of_irq_init(const struct of_device_id *matches);
 
 #ifdef CONFIG_OF_IRQ
 extern int of_irq_count(struct device_node *dev);
+extern int of_irq_get(struct device_node *dev, int index);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
 	return 0;
 }
+static inline int of_irq_get(struct device_node *dev, int index)
+{
+	return 0;
+}
 #endif
 
 #if defined(CONFIG_OF)
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
new file mode 100644
index 000000000000..9b1fbb7f29fc
--- /dev/null
+++ b/include/linux/of_reserved_mem.h
@@ -0,0 +1,53 @@
+#ifndef __OF_RESERVED_MEM_H
+#define __OF_RESERVED_MEM_H
+
+struct device;
+struct of_phandle_args;
+struct reserved_mem_ops;
+
+struct reserved_mem {
+	const char			*name;
+	unsigned long			fdt_node;
+	const struct reserved_mem_ops	*ops;
+	phys_addr_t			base;
+	phys_addr_t			size;
+	void				*priv;
+};
+
+struct reserved_mem_ops {
+	void	(*device_init)(struct reserved_mem *rmem,
+			       struct device *dev);
+	void	(*device_release)(struct reserved_mem *rmem,
+				  struct device *dev);
+};
+
+typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem,
+				      unsigned long node, const char *uname);
+
+#ifdef CONFIG_OF_RESERVED_MEM
+void fdt_init_reserved_mem(void);
+void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+			       phys_addr_t base, phys_addr_t size);
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
+	static const struct of_device_id __reservedmem_of_table_##name	\
+		__used __section(__reservedmem_of_table)		\
+		 = { .compatible = compat,				\
+		     .data = (init == (reservedmem_of_init_fn)NULL) ?	\
+				init : init }
+
+#else
+static inline void fdt_init_reserved_mem(void) { }
+static inline void fdt_reserved_mem_save_node(unsigned long node,
+		const char *uname, phys_addr_t base, phys_addr_t size) { }
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
+	static const struct of_device_id __reservedmem_of_table_##name	\
+		__attribute__((unused))					\
+		 = { .compatible = compat,				\
+		     .data = (init == (reservedmem_of_init_fn)NULL) ?	\
+				init : init }
+
+#endif
+
+#endif /* __OF_RESERVED_MEM_H */
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 4cd62677feb9..17f0949bd822 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -50,6 +50,9 @@ static inline bool oom_task_origin(const struct task_struct *p)
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
+
+extern int oom_kills_count(void);
+extern void note_oom_kill(void);
 extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			     unsigned int points, unsigned long totalpages,
 			     struct mem_cgroup *memcg, nodemask_t *nodemask,
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index d1fe1a761047..ca71a1d347a0 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -317,13 +317,23 @@ CLEARPAGEFLAG(Uptodate, uptodate)
 extern void cancel_dirty_page(struct page *page, unsigned int account_size);
 
 int test_clear_page_writeback(struct page *page);
-int test_set_page_writeback(struct page *page);
+int __test_set_page_writeback(struct page *page, bool keep_write);
+
+#define test_set_page_writeback(page)			\
+	__test_set_page_writeback(page, false)
+#define test_set_page_writeback_keepwrite(page)	\
+	__test_set_page_writeback(page, true)
 
 static inline void set_page_writeback(struct page *page)
 {
 	test_set_page_writeback(page);
 }
 
+static inline void set_page_writeback_keepwrite(struct page *page)
+{
+	test_set_page_writeback_keepwrite(page);
+}
+
 #ifdef CONFIG_PAGEFLAGS_EXTENDED
 /*
  * System with lots of page flags available. This allows separate
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 2ee8cd2466b5..c08730c10c7a 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -30,9 +30,12 @@ enum pageblock_bits {
 	PB_migrate,
 	PB_migrate_end = PB_migrate + 3 - 1,
 			/* 3 bits required for migrate types */
-#ifdef CONFIG_COMPACTION
 	PB_migrate_skip,/* If set the block is skipped by compaction */
-#endif /* CONFIG_COMPACTION */
+
+	/*
+	 * Assume the bits will always align on a word. If this assumption
+	 * changes then get/set pageblock needs updating.
+	 */
 	NR_PAGEBLOCK_BITS
 };
 
@@ -62,11 +65,33 @@ extern int pageblock_order;
 /* Forward declaration */
 struct page;
 
+unsigned long get_pageblock_flags_mask(struct page *page,
+				unsigned long end_bitidx,
+				unsigned long mask);
+void set_pageblock_flags_mask(struct page *page,
+				unsigned long flags,
+				unsigned long end_bitidx,
+				unsigned long mask);
+
 /* Declarations for getting and setting flags. See mm/page_alloc.c */
-unsigned long get_pageblock_flags_group(struct page *page,
-					int start_bitidx, int end_bitidx);
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
-					int start_bitidx, int end_bitidx);
+static inline unsigned long get_pageblock_flags_group(struct page *page,
+					int start_bitidx, int end_bitidx)
+{
+	unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
+	unsigned long mask = (1 << nr_flag_bits) - 1;
+
+	return get_pageblock_flags_mask(page, end_bitidx, mask);
+}
+
+static inline void set_pageblock_flags_group(struct page *page,
+					unsigned long flags,
+					int start_bitidx, int end_bitidx)
+{
+	unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
+	unsigned long mask = (1 << nr_flag_bits) - 1;
+
+	set_pageblock_flags_mask(page, flags, end_bitidx, mask);
+}
 
 #ifdef CONFIG_COMPACTION
 #define get_pageblock_skip(page) \
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 1710d1b060ba..09c1b03867d9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -243,12 +243,20 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x)
 
 typedef int filler_t(void *, struct page *);
 
-extern struct page * find_get_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_lock_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_or_create_page(struct address_space *mapping,
-				pgoff_t index, gfp_t gfp_mask);
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_or_create_page(struct address_space *mapping, pgoff_t index,
+				 gfp_t gfp_mask);
+unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
+			  unsigned int nr_entries, struct page **entries,
+			  pgoff_t *indices);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 			unsigned int nr_pages, struct page **pages);
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
@@ -270,8 +278,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping,
 
 extern struct page * grab_cache_page_nowait(struct address_space *mapping,
 				pgoff_t index);
-extern struct page * read_cache_page_async(struct address_space *mapping,
-				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page(struct address_space *mapping,
 				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page_gfp(struct address_space *mapping,
@@ -279,14 +285,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping,
 extern int read_cache_pages(struct address_space *mapping,
 		struct list_head *pages, filler_t *filler, void *data);
 
-static inline struct page *read_mapping_page_async(
-				struct address_space *mapping,
-				pgoff_t index, void *data)
-{
-	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
-	return read_cache_page_async(mapping, index, filler, data);
-}
-
 static inline struct page *read_mapping_page(struct address_space *mapping,
 				pgoff_t index, void *data)
 {
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index e4dbfab37729..b45d391b4540 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -22,6 +22,11 @@ struct pagevec {
 
 void __pagevec_release(struct pagevec *pvec);
 void __pagevec_lru_add(struct pagevec *pvec);
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_entries,
+				pgoff_t *indices);
+void pagevec_remove_exceptionals(struct pagevec *pvec);
 unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t start, unsigned nr_pages);
 unsigned pagevec_lookup_tag(struct pagevec *pvec,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 33aa2caf0f0c..0e5e16c6f7f1 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -324,6 +324,7 @@ struct pci_dev {
 	unsigned int	is_added:1;
 	unsigned int	is_busmaster:1; /* device is busmaster */
 	unsigned int	no_msi:1;	/* device may not use msi */
+	unsigned int	no_64bit_msi:1; /* device may only use 32-bit MSIs */
 	unsigned int	block_cfg_access:1;	/* config space access is blocked */
 	unsigned int	broken_parity_status:1;	/* Device generates false positive parity */
 	unsigned int	irq_reroute_variant:2;	/* device needs IRQ rerouting variant */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 97fbecdd7a40..057c1d8c77e5 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2551,6 +2551,7 @@
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0	0x0823
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1	0x0824
 #define PCI_DEVICE_ID_INTEL_MRST_SD2	0x084F
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB	0x095E
 #define PCI_DEVICE_ID_INTEL_I960	0x0960
 #define PCI_DEVICE_ID_INTEL_I960RM	0x0962
 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB	0x0c60
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 95961f0bf62d..0afb48fd449d 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -110,7 +110,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
 	pcpu_count = ACCESS_ONCE(ref->pcpu_count);
 
 	if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR))
-		__this_cpu_inc(*pcpu_count);
+		this_cpu_inc(*pcpu_count);
 	else
 		atomic_inc(&ref->count);
 
@@ -139,7 +139,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 	pcpu_count = ACCESS_ONCE(ref->pcpu_count);
 
 	if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) {
-		__this_cpu_inc(*pcpu_count);
+		this_cpu_inc(*pcpu_count);
 		ret = true;
 	}
 
@@ -164,7 +164,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
 	pcpu_count = ACCESS_ONCE(ref->pcpu_count);
 
 	if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR))
-		__this_cpu_dec(*pcpu_count);
+		this_cpu_dec(*pcpu_count);
 	else if (unlikely(atomic_dec_and_test(&ref->count)))
 		ref->release(ref);
 
diff --git a/include/linux/mailbox.h b/include/linux/pl320-ipc.h
index 5161f63ec1c8..5161f63ec1c8 100644
--- a/include/linux/mailbox.h
+++ b/include/linux/pl320-ipc.h
diff --git a/include/linux/plist.h b/include/linux/plist.h
index aa0fb390bd29..8b6c970cff6c 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -98,6 +98,13 @@ struct plist_node {
 }
 
 /**
+ * PLIST_HEAD - declare and init plist_head
+ * @head:	name for struct plist_head variable
+ */
+#define PLIST_HEAD(head) \
+	struct plist_head head = PLIST_HEAD_INIT(head)
+
+/**
  * PLIST_NODE_INIT - static struct plist_node initializer
  * @node:	struct plist_node variable name
  * @__prio:	initial node priority
@@ -134,6 +141,8 @@ static inline void plist_node_init(struct plist_node *node, int prio)
 extern void plist_add(struct plist_node *node, struct plist_head *head);
 extern void plist_del(struct plist_node *node, struct plist_head *head);
 
+extern void plist_requeue(struct plist_node *node, struct plist_head *head);
+
 /**
  * plist_for_each - iterate over the plist
  * @pos:	the type * to use as a loop counter
@@ -143,6 +152,16 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 	 list_for_each_entry(pos, &(head)->node_list, node_list)
 
 /**
+ * plist_for_each_continue - continue iteration over the plist
+ * @pos:	the type * to use as a loop cursor
+ * @head:	the head for your list
+ *
+ * Continue to iterate over plist, continuing after the current position.
+ */
+#define plist_for_each_continue(pos, head)	\
+	 list_for_each_entry_continue(pos, &(head)->node_list, node_list)
+
+/**
  * plist_for_each_safe - iterate safely over a plist of given type
  * @pos:	the type * to use as a loop counter
  * @n:	another type * to use as temporary storage
@@ -163,6 +182,18 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 	 list_for_each_entry(pos, &(head)->node_list, mem.node_list)
 
 /**
+ * plist_for_each_entry_continue - continue iteration over list of given type
+ * @pos:	the type * to use as a loop cursor
+ * @head:	the head for your list
+ * @m:		the name of the list_struct within the struct
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define plist_for_each_entry_continue(pos, head, m)	\
+	list_for_each_entry_continue(pos, &(head)->node_list, m.node_list)
+
+/**
  * plist_for_each_entry_safe - iterate safely over list of given type
  * @pos:	the type * to use as a loop counter
  * @n:		another type * to use as temporary storage
@@ -229,6 +260,20 @@ static inline int plist_node_empty(const struct plist_node *node)
 #endif
 
 /**
+ * plist_next - get the next entry in list
+ * @pos:	the type * to cursor
+ */
+#define plist_next(pos) \
+	list_next_entry(pos, node_list)
+
+/**
+ * plist_prev - get the prev entry in list
+ * @pos:	the type * to cursor
+ */
+#define plist_prev(pos) \
+	list_prev_entry(pos, node_list)
+
+/**
  * plist_first - return the first node (and thus, highest priority)
  * @head:	the &struct plist_head pointer
  *
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 8c6583a53a06..ea05bc207c93 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -596,6 +596,7 @@ extern int dev_pm_put_subsys_data(struct device *dev);
  */
 struct dev_pm_domain {
 	struct dev_pm_ops	ops;
+	void (*detach)(struct device *dev, bool power_off);
 };
 
 /*
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 7c1d252b20c0..66cfa1a39d81 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -310,4 +310,56 @@ static inline void pm_genpd_syscore_poweron(struct device *dev)
 	pm_genpd_syscore_switch(dev, false);
 }
 
+/* OF PM domain providers */
+struct of_device_id;
+
+struct genpd_onecell_data {
+	struct generic_pm_domain **domains;
+	unsigned int num_domains;
+};
+
+typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
+						void *data);
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data);
+void of_genpd_del_provider(struct device_node *np);
+
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data);
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data);
+
+int genpd_dev_pm_attach(struct device *dev);
+#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
+static inline int __of_genpd_add_provider(struct device_node *np,
+					genpd_xlate_t xlate, void *data)
+{
+	return 0;
+}
+static inline void of_genpd_del_provider(struct device_node *np) {}
+
+#define __of_genpd_xlate_simple		NULL
+#define __of_genpd_xlate_onecell	NULL
+
+static inline int genpd_dev_pm_attach(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
+
+static inline int of_genpd_add_provider_simple(struct device_node *np,
+					struct generic_pm_domain *genpd)
+{
+	return __of_genpd_add_provider(np, __of_genpd_xlate_simple, genpd);
+}
+static inline int of_genpd_add_provider_onecell(struct device_node *np,
+					struct genpd_onecell_data *data)
+{
+	return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data);
+}
+
 #endif /* _LINUX_PM_DOMAIN_H */
diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h
index 07e7945a1ff2..e97fc656a058 100644
--- a/include/linux/power/charger-manager.h
+++ b/include/linux/power/charger-manager.h
@@ -253,9 +253,6 @@ struct charger_manager {
 	struct device *dev;
 	struct charger_desc *desc;
 
-	struct power_supply *fuel_gauge;
-	struct power_supply **charger_stat;
-
 #ifdef CONFIG_THERMAL
 	struct thermal_zone_device *tzd_batt;
 #endif
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index de83b4eb1642..1841b58cf173 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -15,6 +15,8 @@
  */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
+#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+
 #include <asm/preempt.h>
 
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
diff --git a/include/linux/printk.h b/include/linux/printk.h
index fa47e2708c01..cbf094f993f4 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -132,9 +132,9 @@ asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
 
 /*
- * Special printk facility for scheduler use only, _DO_NOT_USE_ !
+ * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
  */
-__printf(1, 2) __cold int printk_sched(const char *fmt, ...);
+__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
 
 /*
  * Please don't use printk_ratelimit(), because it shares ratelimiting state
@@ -169,7 +169,7 @@ int printk(const char *s, ...)
 	return 0;
 }
 static inline __printf(1, 2) __cold
-int printk_sched(const char *s, ...)
+int printk_deferred(const char *s, ...)
 {
 	return 0;
 }
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 9974975d40db..4af3fdc85b01 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -53,7 +53,8 @@ struct persistent_ram_zone {
 };
 
 struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
-			u32 sig, struct persistent_ram_ecc_info *ecc_info);
+			u32 sig, struct persistent_ram_ecc_info *ecc_info,
+			unsigned int memtype);
 void persistent_ram_free(struct persistent_ram_zone *prz);
 void persistent_ram_zap(struct persistent_ram_zone *prz);
 
@@ -76,6 +77,7 @@ ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz,
 struct ramoops_platform_data {
 	unsigned long	mem_size;
 	unsigned long	mem_address;
+	unsigned int	mem_type;
 	unsigned long	record_size;
 	unsigned long	console_size;
 	unsigned long	ftrace_size;
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 07d0df6bf768..cc79eff4a1ad 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -5,6 +5,7 @@
 #include <linux/sched.h>		/* For struct task_struct.  */
 #include <linux/err.h>			/* for IS_ERR_VALUE */
 #include <linux/bug.h>			/* For BUG_ON.  */
+#include <linux/pid_namespace.h>	/* For task_active_pid_ns.  */
 #include <uapi/linux/ptrace.h>
 
 /*
@@ -129,6 +130,37 @@ static inline void ptrace_event(int event, unsigned long message)
 }
 
 /**
+ * ptrace_event_pid - possibly stop for a ptrace event notification
+ * @event:	%PTRACE_EVENT_* value to report
+ * @pid:	process identifier for %PTRACE_GETEVENTMSG to return
+ *
+ * Check whether @event is enabled and, if so, report @event and @pid
+ * to the ptrace parent.  @pid is reported as the pid_t seen from the
+ * the ptrace parent's pid namespace.
+ *
+ * Called without locks.
+ */
+static inline void ptrace_event_pid(int event, struct pid *pid)
+{
+	/*
+	 * FIXME: There's a potential race if a ptracer in a different pid
+	 * namespace than parent attaches between computing message below and
+	 * when we acquire tasklist_lock in ptrace_stop().  If this happens,
+	 * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG.
+	 */
+	unsigned long message = 0;
+	struct pid_namespace *ns;
+
+	rcu_read_lock();
+	ns = task_active_pid_ns(rcu_dereference(current->parent));
+	if (ns)
+		message = pid_nr_ns(pid, ns);
+	rcu_read_unlock();
+
+	ptrace_event(event, message);
+}
+
+/**
  * ptrace_init_task - initialize ptrace state for a new child
  * @child:		new child task
  * @ptrace:		true if child should be ptrace'd by parent's tracer
@@ -302,6 +334,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
  * calling arch_ptrace_stop() when it would be superfluous.  For example,
  * if the thread has not been back to user mode since the last stop, the
  * thread state might indicate that nothing needs to be done.
+ *
+ * This is guaranteed to be invoked once before a task stops for ptrace and
+ * may include arch-specific operations necessary prior to a ptrace stop.
  */
 #define arch_ptrace_stop_needed(code, info)	(0)
 #endif
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 403940787be1..e8be53ecfc45 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -219,6 +219,7 @@ static inline void radix_tree_replace_slot(void **pslot, void *item)
 int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
+void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
@@ -226,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root,
 			void ***results, unsigned long *indices,
 			unsigned long first_index, unsigned int max_items);
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index d69cf637a15a..49a4d6f59108 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu);
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu);
 int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table);
 
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 8e3e66ac0a52..953937ea5233 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -4,6 +4,7 @@
 
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
+#include <linux/wait.h>
 #include <uapi/linux/rtnetlink.h>
 
 extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
@@ -22,6 +23,10 @@ extern void rtnl_lock(void);
 extern void rtnl_unlock(void);
 extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
+
+extern wait_queue_head_t netdev_unregistering_wq;
+extern struct mutex net_mutex;
+
 #ifdef CONFIG_PROVE_LOCKING
 extern int lockdep_rtnl_is_held(void);
 #else
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a781dec1cd0b..218b058060f1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -59,6 +59,10 @@ struct sched_param {
 
 #define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
 
+#define VMACACHE_BITS 2
+#define VMACACHE_SIZE (1U << VMACACHE_BITS)
+#define VMACACHE_MASK (VMACACHE_SIZE - 1)
+
 /*
  * Extended scheduling parameters data structure.
  *
@@ -1228,6 +1232,9 @@ struct task_struct {
 #ifdef CONFIG_COMPAT_BRK
 	unsigned brk_randomized:1;
 #endif
+	/* per-thread vma caching */
+	u32 vmacache_seqnum;
+	struct vm_area_struct *vmacache[VMACACHE_SIZE];
 #if defined(SPLIT_RSS_COUNTING)
 	struct task_rss_stat	rss_stat;
 #endif
@@ -1688,6 +1695,24 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 }
 
 
+static int pid_alive(const struct task_struct *p);
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
 					struct pid_namespace *ns)
 {
@@ -1727,7 +1752,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
  *
  * Return: 1 if the process is alive. 0 otherwise.
  */
-static inline int pid_alive(struct task_struct *p)
+static inline int pid_alive(const struct task_struct *p)
 {
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }
@@ -1851,11 +1876,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
 static inline gfp_t memalloc_noio_flags(gfp_t flags)
 {
 	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-		flags &= ~__GFP_IO;
+		flags &= ~(__GFP_IO | __GFP_FS);
 	return flags;
 }
 
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 535f158977b9..8cf350325dc6 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -164,8 +164,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
 static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = ACCESS_ONCE(s->sequence);
-
-	seqcount_lockdep_reader_access(s);
 	smp_rmb();
 	return ret & ~1;
 }
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index f729be981da0..7a15b5b24c0b 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -285,6 +285,22 @@ static inline int uart_poll_timeout(struct uart_port *port)
 /*
  * Console helpers.
  */
+struct earlycon_device {
+	struct console *con;
+	struct uart_port port;
+	char options[16];		/* e.g., 115200n8 */
+	unsigned int baud;
+};
+int setup_earlycon(char *buf, const char *match,
+		   int (*setup)(struct earlycon_device *, const char *));
+
+#define EARLYCON_DECLARE(name, func) \
+static int __init name ## _setup_earlycon(char *buf) \
+{ \
+	return setup_earlycon(buf, __stringify(name), func); \
+} \
+early_param("earlycon", name ## _setup_earlycon);
+
 struct uart_port *uart_get_console(struct uart_port *ports, int nr,
 				   struct console *c);
 void uart_parse_options(char *options, int *baud, int *parity, int *bits,
diff --git a/include/linux/serio.h b/include/linux/serio.h
index 36aac733840a..9f779c7a2da4 100644
--- a/include/linux/serio.h
+++ b/include/linux/serio.h
@@ -23,6 +23,7 @@ struct serio {
 
 	char name[32];
 	char phys[32];
+	char firmware_id[128];
 
 	bool manual_bind;
 
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 9d55438bc4ad..4d1771c2d29f 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -51,6 +51,7 @@ extern struct file *shmem_kernel_file_setup(const char *name, loff_t size,
 					    unsigned long flags);
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern bool shmem_mapping(struct address_space *mapping);
 extern void shmem_unlock_mapping(struct address_space *mapping);
 extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 15ede6a823a6..ad8f85908a56 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2458,6 +2458,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
 void skb_scrub_packet(struct sk_buff *skb, bool xnet);
 unsigned int skb_gso_transport_seglen(const struct sk_buff *skb);
 struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
+struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
 
 struct skb_checksum_ops {
 	__wsum (*update)(const void *mem, int len, __wsum wsum);
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 54f91d35e5fd..46cca4c06848 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -23,7 +23,7 @@ int sock_diag_check_cookie(void *sk, __u32 *cookie);
 void sock_diag_save_cookie(void *sk, __u32 *cookie);
 
 int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr);
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 			     struct sk_buff *skb, int attrtype);
 
 #endif
diff --git a/include/linux/string.h b/include/linux/string.h
index ac889c5ea11b..0ed878d0465c 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -129,7 +129,7 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4);
 #endif
 
 extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
-			const void *from, size_t available);
+				       const void *from, size_t available);
 
 /**
  * strstarts - does @str start with @prefix?
@@ -141,7 +141,8 @@ static inline bool strstarts(const char *str, const char *prefix)
 	return strncmp(str, prefix, strlen(prefix)) == 0;
 }
 
-extern size_t memweight(const void *ptr, size_t bytes);
+size_t memweight(const void *ptr, size_t bytes);
+void memzero_explicit(void *s, size_t count);
 
 /**
  * kbasename - return the last part of a pathname.
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index b05963f09ebf..f5bfb1a80abe 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -32,6 +32,7 @@ struct svc_xprt_class {
 	struct svc_xprt_ops	*xcl_ops;
 	struct list_head	xcl_list;
 	u32			xcl_max_payload;
+	int			xcl_ident;
 };
 
 /*
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 62fd1b756e99..947009ed5996 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -56,6 +56,7 @@ int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
 void		svc_drop(struct svc_rqst *);
 void		svc_sock_update_bufs(struct svc_serv *serv);
+bool		svc_alien_sock(struct net *net, int fd);
 int		svc_addsock(struct svc_serv *serv, const int fd,
 					char *name_return, const size_t len);
 void		svc_init_xprt_sock(void);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 8097b9df6773..51009d280ac7 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -340,6 +340,7 @@ int			xs_swapper(struct rpc_xprt *xprt, int enable);
 #define XPRT_CONNECTION_ABORT	(7)
 #define XPRT_CONNECTION_CLOSE	(8)
 #define XPRT_CONGESTED		(9)
+#define XPRT_CONNECTION_REUSE	(10)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 46ba0c6c219f..789324976801 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -214,8 +214,9 @@ struct percpu_cluster {
 struct swap_info_struct {
 	unsigned long	flags;		/* SWP_USED etc: see above */
 	signed short	prio;		/* swap priority of this type */
+	struct plist_node list;		/* entry in swap_active_head */
+	struct plist_node avail_list;	/* entry in swap_avail_head */
 	signed char	type;		/* strange name for an index */
-	signed char	next;		/* next type on the swap list */
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
 	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
@@ -255,11 +256,6 @@ struct swap_info_struct {
 	struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */
 };
 
-struct swap_list_t {
-	int head;	/* head of priority-ordered swapfile list */
-	int next;	/* swapfile to be used next */
-};
-
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
 extern unsigned long totalreserve_pages;
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index e282624e8c10..388293a91e8c 100644
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -6,7 +6,7 @@
  * want to expose them to the dozens of source files that include swap.h
  */
 extern spinlock_t swap_lock;
-extern struct swap_list_t swap_list;
+extern struct plist_head swap_active_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
 
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index fddbe2023a5d..a629e4b23217 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -118,8 +118,6 @@ static inline __deprecated void set_need_resched(void)
 	 */
 }
 
-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
-
 #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
 /*
  * An arch can define its own version of set_restore_sigmask() to get the
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index fff1d0976f80..8350c538b486 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -39,6 +39,9 @@ struct tpm_class_ops {
 	int (*send) (struct tpm_chip *chip, u8 *buf, size_t len);
 	void (*cancel) (struct tpm_chip *chip);
 	u8 (*status) (struct tpm_chip *chip);
+	bool (*update_timeouts)(struct tpm_chip *chip,
+				unsigned long *timeout_cap);
+
 };
 
 #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE)
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 90b4fdc8a61f..b90b5c221ff0 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -208,7 +208,7 @@ struct tty_port {
 	wait_queue_head_t	delta_msr_wait;	/* Modem status change */
 	unsigned long		flags;		/* TTY flags ASY_*/
 	unsigned char		console:1,	/* port is a console */
-				low_latency:1;	/* direct buffer flush */
+				low_latency:1;	/* optional: tune for latency */
 	struct mutex		mutex;		/* Locking */
 	struct mutex		buf_mutex;	/* Buffer alloc lock */
 	unsigned char		*xmit_buf;	/* Optional buffer */
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 52f944dfe2fd..8b96ae2a38fe 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -30,4 +30,10 @@
    descriptor */
 #define USB_QUIRK_DELAY_INIT		0x00000040
 
+/* device generates spurious wakeup, ignore remote wakeup capability */
+#define USB_QUIRK_IGNORE_REMOTE_WAKEUP	0x00000200
+
+/* device can't handle device_qualifier descriptor requests */
+#define USB_QUIRK_DEVICE_QUALIFIER	0x00000100
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/usb/xhci_pdriver.h b/include/linux/usb/xhci_pdriver.h
new file mode 100644
index 000000000000..376654b5b0f7
--- /dev/null
+++ b/include/linux/usb/xhci_pdriver.h
@@ -0,0 +1,27 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#ifndef __USB_CORE_XHCI_PDRIVER_H
+#define __USB_CORE_XHCI_PDRIVER_H
+
+/**
+ * struct usb_xhci_pdata - platform_data for generic xhci platform driver
+ *
+ * @usb3_lpm_capable:	determines if this xhci platform supports USB3
+ *			LPM capability
+ *
+ */
+struct usb_xhci_pdata {
+	unsigned	usb3_lpm_capable:1;
+};
+
+#endif /* __USB_CORE_XHCI_PDRIVER_H */
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 4836ba3c1cd8..e92abf9e796f 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -17,6 +17,10 @@ struct uid_gid_map {	/* 64 bytes -- 1 cache line */
 	} extent[UID_GID_MAP_MAX_EXTENTS];
 };
 
+#define USERNS_SETGROUPS_ALLOWED 1UL
+
+#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
+
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -27,6 +31,7 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+	unsigned long		flags;
 
 	/* Register of per-UID persistent keyrings for this namespace */
 #ifdef CONFIG_PERSISTENT_KEYRINGS
@@ -63,6 +68,9 @@ extern struct seq_operations proc_projid_seq_operations;
 extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
+extern int proc_setgroups_show(struct seq_file *m, void *v);
+extern bool userns_may_setgroups(const struct user_namespace *ns);
 #else
 
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
@@ -87,6 +95,10 @@ static inline void put_user_ns(struct user_namespace *ns)
 {
 }
 
+static inline bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	return true;
+}
 #endif
 
 #endif /* _LINUX_USER_H */
diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h
index 502073a53dd3..b483abd34493 100644
--- a/include/linux/vga_switcheroo.h
+++ b/include/linux/vga_switcheroo.h
@@ -64,6 +64,7 @@ int vga_switcheroo_get_client_state(struct pci_dev *dev);
 void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic);
 
 int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain);
+void vga_switcheroo_fini_domain_pm_ops(struct device *dev);
 int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain);
 #else
 
@@ -82,6 +83,7 @@ static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return
 static inline void vga_switcheroo_set_dynamic_switch(struct pci_dev *pdev, enum vga_switcheroo_state dynamic) {}
 
 static inline int vga_switcheroo_init_domain_pm_ops(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; }
+static inline void vga_switcheroo_fini_domain_pm_ops(struct device *dev) {}
 static inline int vga_switcheroo_init_domain_pm_optimus_hdmi_audio(struct device *dev, struct dev_pm_domain *domain) { return -EINVAL; }
 
 #endif
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
new file mode 100644
index 000000000000..c3fa0fd43949
--- /dev/null
+++ b/include/linux/vmacache.h
@@ -0,0 +1,38 @@
+#ifndef __LINUX_VMACACHE_H
+#define __LINUX_VMACACHE_H
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+/*
+ * Hash based on the page number. Provides a good hit rate for
+ * workloads with good locality and those with random accesses as well.
+ */
+#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK)
+
+static inline void vmacache_flush(struct task_struct *tsk)
+{
+	memset(tsk->vmacache, 0, sizeof(tsk->vmacache));
+}
+
+extern void vmacache_flush_all(struct mm_struct *mm);
+extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
+extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
+						    unsigned long addr);
+
+#ifndef CONFIG_MMU
+extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long end);
+#endif
+
+static inline void vmacache_invalidate(struct mm_struct *mm)
+{
+	mm->vmacache_seqnum++;
+
+	/* deal with overflows */
+	if (unlikely(mm->vmacache_seqnum == 0))
+		vmacache_flush_all(mm);
+}
+
+#endif /* __LINUX_VMACACHE_H */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 704f4f652d0a..6c62cfa25f1a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -452,7 +452,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
 			1, (name))
 #define create_singlethread_workqueue(name)				\
-	alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, (name))
+	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index bef53ce555d2..b10682cb138c 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -329,6 +329,9 @@ struct v4l2_fh;
  * @retry_start_streaming: start_streaming() was called, but there were not enough
  *		buffers queued. If set, then retry calling start_streaming when
  *		queuing a new buffer.
+ * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for
+ *		buffers. Only set for capture queues if qbuf has not yet been
+ *		called since poll() needs to return POLLERR in that situation.
  * @fileio:	file io emulator internal data, used only if emulator is active
  */
 struct vb2_queue {
@@ -362,6 +365,7 @@ struct vb2_queue {
 
 	unsigned int			streaming:1;
 	unsigned int			retry_start_streaming:1;
+	unsigned int			waiting_for_buffers:1;
 
 	struct vb2_fileio_data		*fileio;
 };
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 7d64d3609ec9..428277869400 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -155,7 +155,11 @@ struct vsock_transport {
 
 /**** CORE ****/
 
-int vsock_core_init(const struct vsock_transport *t);
+int __vsock_core_init(const struct vsock_transport *t, struct module *owner);
+static inline int vsock_core_init(const struct vsock_transport *t)
+{
+	return __vsock_core_init(t, THIS_MODULE);
+}
 void vsock_core_exit(void);
 
 /**** UTILS ****/
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b1f84b05c67e..37123eb1f093 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3637,6 +3637,18 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy);
 void cfg80211_sched_scan_stopped(struct wiphy *wiphy);
 
 /**
+ * cfg80211_sched_scan_stopped_rtnl - notify that the scheduled scan has stopped
+ *
+ * @wiphy: the wiphy on which the scheduled scan stopped
+ *
+ * The driver can call this function to inform cfg80211 that the
+ * scheduled scan had to be stopped, for whatever reason.  The driver
+ * is then called back via the sched_scan_stop operation when done.
+ * This function should be called with rtnl locked.
+ */
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy);
+
+/**
  * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame
  *
  * @wiphy: the wiphy reporting the BSS
diff --git a/include/net/dst.h b/include/net/dst.h
index 77eb53fabfb0..909032821c37 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -466,6 +466,7 @@ void dst_init(void);
 /* Flags for xfrm_lookup flags argument. */
 enum {
 	XFRM_LOOKUP_ICMP = 1 << 0,
+	XFRM_LOOKUP_QUEUE = 1 << 1,
 };
 
 struct flowi;
@@ -476,7 +477,16 @@ static inline struct dst_entry *xfrm_lookup(struct net *net,
 					    int flags)
 {
 	return dst_orig;
-} 
+}
+
+static inline struct dst_entry *xfrm_lookup_route(struct net *net,
+						  struct dst_entry *dst_orig,
+						  const struct flowi *fl,
+						  struct sock *sk,
+						  int flags)
+{
+	return dst_orig;
+}
 
 static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
 {
@@ -488,6 +498,10 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 			      const struct flowi *fl, struct sock *sk,
 			      int flags);
 
+struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
+				    const struct flowi *fl, struct sock *sk,
+				    int flags);
+
 /* skb attached with this dst needs transformation if dst->xfrm is valid */
 static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
 {
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c55aeed41ace..cf9272807788 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -62,6 +62,7 @@ struct inet_connection_sock_af_ops {
 	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
 	int	    (*bind_conflict)(const struct sock *sk,
 				     const struct inet_bind_bucket *tb, bool relax);
+	void	    (*mtu_reduced)(struct sock *sk);
 };
 
 /** inet_connection_sock - INET connection oriented sock
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 6efe73c79c52..823ec7bb9c67 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -41,14 +41,13 @@ struct inet_peer {
 		struct rcu_head     gc_rcu;
 	};
 	/*
-	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count
+	 * Once inet_peer is queued for deletion (refcnt == -1), following field
+	 * is not available: rid
 	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
 			atomic_t			rid;		/* Frag reception counter */
-			atomic_t			ip_id_count;	/* IP ID for the next packet */
 		};
 		struct rcu_head         rcu;
 		struct inet_peer	*gc_next;
@@ -165,7 +164,7 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 void inetpeer_invalidate_tree(struct inet_peer_base *);
 
 /*
- * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
+ * temporary check to make sure we dont access rid, tcp_ts,
  * tcp_ts_stamp if no refcount is taken on inet_peer
  */
 static inline void inet_peer_refcheck(const struct inet_peer *p)
@@ -173,20 +172,4 @@ static inline void inet_peer_refcheck(const struct inet_peer *p)
 	WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
 }
 
-
-/* can be called with or without local BH being disabled */
-static inline int inet_getid(struct inet_peer *p, int more)
-{
-	int old, new;
-	more++;
-	inet_peer_refcheck(p);
-	do {
-		old = atomic_read(&p->ip_id_count);
-		new = old + more;
-		if (!new)
-			new = 1;
-	} while (atomic_cmpxchg(&p->ip_id_count, old, new) != old);
-	return new;
-}
-
 #endif /* _NET_INETPEER_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index 23be0fd37937..937f19681426 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -297,9 +297,10 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
 	}
 }
 
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
+u32 ip_idents_reserve(u32 hash, int segs);
+void __ip_select_ident(struct iphdr *iph, int segs);
 
-static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
+static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
@@ -309,24 +310,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s
 		 * does not change, they drop every other packet in
 		 * a TCP stream using header compression.
 		 */
-		iph->id = (sk && inet_sk(sk)->inet_daddr) ?
-					htons(inet_sk(sk)->inet_id++) : 0;
-	} else
-		__ip_select_ident(iph, dst, 0);
-}
-
-static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more)
-{
-	struct iphdr *iph = ip_hdr(skb);
-
-	if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
 		if (sk && inet_sk(sk)->inet_daddr) {
 			iph->id = htons(inet_sk(sk)->inet_id);
-			inet_sk(sk)->inet_id += 1 + more;
-		} else
+			inet_sk(sk)->inet_id += segs;
+		} else {
 			iph->id = 0;
-	} else
-		__ip_select_ident(iph, dst, more);
+		}
+	} else {
+		__ip_select_ident(iph, segs);
+	}
+}
+
+static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk)
+{
+	ip_select_ident_segs(skb, sk, 1);
 }
 
 /*
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 017badb1aec7..2e74c6cfa612 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -32,6 +32,11 @@ struct route_info {
 #define RT6_LOOKUP_F_SRCPREF_PUBLIC	0x00000010
 #define RT6_LOOKUP_F_SRCPREF_COA	0x00000020
 
+/* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
+ * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
+ */
+#define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr))
+
 /*
  * rt6_srcprefs2flags() and rt6_flags2srcprefs() translate
  * between IPV6_ADDR_PREFERENCES socket option values
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index e77c10405d51..7b9ec5837496 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -40,6 +40,7 @@ struct ip_tunnel_prl_entry {
 
 struct ip_tunnel_dst {
 	struct dst_entry __rcu 		*dst;
+	__be32				 saddr;
 };
 
 struct ip_tunnel {
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4f541f11ce63..a60948d7bcea 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -660,7 +660,7 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
+void ipv6_proxy_select_ident(struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
 
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 956b175523ff..55d15049ab2f 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -47,8 +47,8 @@ enum nf_ct_ext_id {
 /* Extensions: optional stuff which isn't permanently in struct. */
 struct nf_ct_ext {
 	struct rcu_head rcu;
-	u8 offset[NF_CT_EXT_NUM];
-	u8 len;
+	u16 offset[NF_CT_EXT_NUM];
+	u16 len;
 	char data[0];
 };
 
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index cf2b7ae2b9d8..a75fc8e27cd6 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -13,6 +13,16 @@ struct nft_cmp_fast_expr {
 	u8			len;
 };
 
+/* Calculate the mask for the nft_cmp_fast expression. On big endian the
+ * mask needs to include the *upper* bytes when interpreting that data as
+ * something smaller than the full u32, therefore a cpu_to_le32 is done.
+ */
+static inline u32 nft_cmp_fast_mask(unsigned int len)
+{
+	return cpu_to_le32(~0U >> (FIELD_SIZEOF(struct nft_cmp_fast_expr,
+						data) * BITS_PER_BYTE - len));
+}
+
 extern const struct nft_expr_ops nft_cmp_fast_ops;
 
 int nft_cmp_module_init(void);
diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index b07cdc9fa454..f103f30122a1 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -160,7 +160,7 @@ struct ieee80211_reg_rule {
 struct ieee80211_regdomain {
 	struct rcu_head rcu_head;
 	u32 n_reg_rules;
-	char alpha2[2];
+	char alpha2[3];
 	enum nl80211_dfs_regions dfs_region;
 	struct ieee80211_reg_rule reg_rules[];
 };
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 4b7cd695e431..cfcbc3f627bd 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -115,7 +115,7 @@ typedef enum {
  * analysis of the state functions, but in reality just taken from
  * thin air in the hopes othat we don't trigger a kernel panic.
  */
-#define SCTP_MAX_NUM_COMMANDS 14
+#define SCTP_MAX_NUM_COMMANDS 20
 
 typedef union {
 	__s32 i32;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index a3353f45ef94..ba41e01ebc54 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -433,6 +433,11 @@ static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_associat
 	asoc->pmtu_pending = 0;
 }
 
+static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
+{
+	return !list_empty(&chunk->list);
+}
+
 /* Walk through a list of TLV parameters.  Don't trust the
  * individual parameter lengths and instead depend on
  * the chunk length to indicate when to stop.  Make sure
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 7f4eeb340a54..72a31db47ded 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -248,9 +248,9 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *,
 					      int, __be16);
 struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc,
 					     union sctp_addr *addr);
-int sctp_verify_asconf(const struct sctp_association *asoc,
-		       struct sctp_paramhdr *param_hdr, void *chunk_end,
-		       struct sctp_paramhdr **errp);
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+			struct sctp_chunk *chunk, bool addr_param_needed,
+			struct sctp_paramhdr **errp);
 struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 				       struct sctp_chunk *asconf);
 int sctp_process_asconf_ack(struct sctp_association *asoc,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 6ee76c804893..0dfcc92600e8 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1241,6 +1241,7 @@ struct sctp_endpoint {
 	/* SCTP-AUTH: endpoint shared keys */
 	struct list_head endpoint_shared_keys;
 	__u16 active_key_id;
+	__u8  auth_enable;
 };
 
 /* Recover the outter endpoint structure. */
@@ -1269,7 +1270,8 @@ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *,
 int sctp_has_association(struct net *net, const union sctp_addr *laddr,
 			 const union sctp_addr *paddr);
 
-int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
+int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
+		     const struct sctp_association *asoc,
 		     sctp_cid_t, sctp_init_chunk_t *peer_init,
 		     struct sctp_chunk *chunk, struct sctp_chunk **err_chunk);
 int sctp_process_init(struct sctp_association *, struct sctp_chunk *chunk,
@@ -1653,6 +1655,17 @@ struct sctp_association {
 	/* This is the last advertised value of rwnd over a SACK chunk. */
 	__u32 a_rwnd;
 
+	/* Number of bytes by which the rwnd has slopped.  The rwnd is allowed
+	 * to slop over a maximum of the association's frag_point.
+	 */
+	__u32 rwnd_over;
+
+	/* Keeps treack of rwnd pressure.  This happens when we have
+	 * a window, but not recevie buffer (i.e small packets).  This one
+	 * is releases slowly (1 PMTU at a time ).
+	 */
+	__u32 rwnd_press;
+
 	/* This is the sndbuf size in use for the association.
 	 * This corresponds to the sndbuf size for the association,
 	 * as specified in the sk->sndbuf.
@@ -1881,7 +1894,8 @@ void sctp_assoc_update(struct sctp_association *old,
 __u32 sctp_association_get_next_tsn(struct sctp_association *);
 
 void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
-void sctp_assoc_rwnd_update(struct sctp_association *, bool);
+void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
+void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
 void sctp_assoc_set_primary(struct sctp_association *,
 			    struct sctp_transport *);
 void sctp_assoc_del_nonprimary_peers(struct sctp_association *,
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index f257486f17be..3f36d45b714a 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,8 +3,6 @@
 
 #include <linux/types.h>
 
-__u32 secure_ip_id(__be32 daddr);
-__u32 secure_ipv6_id(const __be32 daddr[4]);
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
diff --git a/include/net/sock.h b/include/net/sock.h
index b9586a137cad..f66b2b19a6e4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -969,7 +969,6 @@ struct proto {
 						struct sk_buff *skb);
 
 	void		(*release_cb)(struct sock *sk);
-	void		(*mtu_reduced)(struct sock *sk);
 
 	/* Keeping track of sk's, looking them up, and port selection methods. */
 	void			(*hash)(struct sock *sk);
@@ -1755,8 +1754,8 @@ sk_dst_get(struct sock *sk)
 
 	rcu_read_lock();
 	dst = rcu_dereference(sk->sk_dst_cache);
-	if (dst)
-		dst_hold(dst);
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
 	rcu_read_unlock();
 	return dst;
 }
@@ -1793,9 +1792,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 static inline void
 sk_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_set(sk, dst);
-	spin_unlock(&sk->sk_dst_lock);
+	struct dst_entry *old_dst;
+
+	sk_tx_queue_clear(sk);
+	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+	dst_release(old_dst);
 }
 
 static inline void
@@ -1807,9 +1808,7 @@ __sk_dst_reset(struct sock *sk)
 static inline void
 sk_dst_reset(struct sock *sk)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_reset(sk);
-	spin_unlock(&sk->sk_dst_lock);
+	sk_dst_set(sk, NULL);
 }
 
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
@@ -2278,6 +2277,11 @@ int sock_get_timestampns(struct sock *, struct timespec __user *);
 int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
 		       int type);
 
+bool sk_ns_capable(const struct sock *sk,
+		   struct user_namespace *user_ns, int cap);
+bool sk_capable(const struct sock *sk, int cap);
+bool sk_net_capable(const struct sock *sk, int cap);
+
 /*
  *	Enable debug/info messages
  */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 743accec6c76..1f0d8479e15f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -453,6 +453,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
  */
 
 void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
+void tcp_v4_mtu_reduced(struct sock *sk);
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_create_openreq_child(struct sock *sk,
 				      struct request_sock *req,
@@ -720,8 +721,10 @@ struct tcp_skb_cb {
 #define TCPCB_SACKED_RETRANS	0x02	/* SKB retransmitted		*/
 #define TCPCB_LOST		0x04	/* SKB is lost			*/
 #define TCPCB_TAGBITS		0x07	/* All tag bits			*/
+#define TCPCB_REPAIRED		0x10	/* SKB repaired (no skb_mstamp)	*/
 #define TCPCB_EVER_RETRANS	0x80	/* Ever retransmitted frame	*/
-#define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
+#define TCPCB_RETRANS		(TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \
+				TCPCB_REPAIRED)
 
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
 	/* 1 byte hole */
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index f29e3a27c2cc..0e3ff30647d5 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -601,5 +601,4 @@ struct ib_cm_sidr_rep_param {
 int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
 			struct ib_cm_sidr_rep_param *param);
 
-int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac);
 #endif /* IB_CM_H */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index d65fbec2533d..409fafb63f63 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -149,6 +149,7 @@ struct scsi_device {
 	unsigned skip_ms_page_8:1;	/* do not use MODE SENSE page 0x08 */
 	unsigned skip_ms_page_3f:1;	/* do not use MODE SENSE page 0x3f */
 	unsigned skip_vpd_pages:1;	/* do not read VPD pages */
+	unsigned try_vpd_pages:1;	/* attempt to read VPD pages */
 	unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */
 	unsigned no_start_on_add:1;	/* do not issue start on add */
 	unsigned allow_restart:1; /* issue START_UNIT in error handler */
@@ -257,7 +258,7 @@ struct scsi_target {
 	struct list_head	siblings;
 	struct list_head	devices;
 	struct device		dev;
-	unsigned int		reap_ref; /* protected by the host lock */
+	struct kref		reap_ref; /* last put renders target invisible */
 	unsigned int		channel;
 	unsigned int		id; /* target id ... replace
 				     * scsi_device.id eventually */
@@ -284,7 +285,6 @@ struct scsi_target {
 #define SCSI_DEFAULT_TARGET_BLOCKED	3
 
 	char			scsi_level;
-	struct execute_work	ew;
 	enum scsi_target_state	state;
 	void 			*hostdata; /* available to low-level driver */
 	unsigned long		starget_data[0]; /* for the transport */
diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h
index 447d2d7466fc..183eaab7c380 100644
--- a/include/scsi/scsi_devinfo.h
+++ b/include/scsi/scsi_devinfo.h
@@ -32,4 +32,9 @@
 #define BLIST_ATTACH_PQ3	0x1000000 /* Scan: Attach to PQ3 devices */
 #define BLIST_NO_DIF		0x2000000 /* Disable T10 PI (DIF) */
 #define BLIST_SKIP_VPD_PAGES	0x4000000 /* Ignore SBC-3 VPD pages */
+#define BLIST_SCSI3LUN		0x8000000 /* Scan more than 256 LUNs
+					     for sequential scan */
+#define BLIST_TRY_VPD_PAGES	0x10000000 /* Attempt to read VPD pages */
+#define BLIST_NO_RSOC		0x20000000 /* don't try to issue RSOC */
+
 #endif
diff --git a/include/sound/core.h b/include/sound/core.h
index 2a14f1f02d4f..d6bc9616058b 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -121,6 +121,8 @@ struct snd_card {
 	int user_ctl_count;		/* count of all user controls */
 	struct list_head controls;	/* all controls for this card */
 	struct list_head ctl_files;	/* active control files */
+	struct mutex user_ctl_lock;	/* protects user controls against
+					   concurrent access */
 
 	struct snd_info_entry *proc_root;	/* root for soundcard specific files */
 	struct snd_info_entry *proc_id;	/* the card id */
diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h
index 2883a7a6f9f3..98f2ade0266e 100644
--- a/include/sound/soc-dpcm.h
+++ b/include/sound/soc-dpcm.h
@@ -102,6 +102,8 @@ struct snd_soc_dpcm_runtime {
 	/* state and update */
 	enum snd_soc_dpcm_update runtime_update;
 	enum snd_soc_dpcm_state state;
+
+	int trigger_pending; /* trigger cmd + 1 if pending, 0 if not */
 };
 
 /* can this BE stop and free */
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index 4483fadfa68d..d1fb912740f3 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -68,7 +68,8 @@ extern void iscsit_build_nopin_rsp(struct iscsi_cmd *, struct iscsi_conn *,
 extern void iscsit_build_task_mgt_rsp(struct iscsi_cmd *, struct iscsi_conn *,
 				struct iscsi_tm_rsp *);
 extern int iscsit_build_text_rsp(struct iscsi_cmd *, struct iscsi_conn *,
-				struct iscsi_text_rsp *);
+				struct iscsi_text_rsp *,
+				enum iscsit_transport_type);
 extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *,
 				struct iscsi_reject *);
 extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *,
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 7020e33e742e..f5915b39386a 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -59,6 +59,7 @@ int	transport_subsystem_register(struct se_subsystem_api *);
 void	transport_subsystem_release(struct se_subsystem_api *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
+void	target_complete_cmd_with_length(struct se_cmd *, u8, int);
 
 sense_reason_t	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 sense_reason_t	spc_emulate_report_luns(struct se_cmd *cmd);
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index e76ae19a8d6f..e8a5eca1dbe5 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -132,6 +132,7 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * block_rq_complete - block IO operation completed by device driver
  * @q: queue containing the block operation request
  * @rq: block operations request
+ * @nr_bytes: number of completed bytes
  *
  * The block_rq_complete tracepoint event indicates that some portion
  * of operation request has been completed by the device driver.  If
@@ -139,11 +140,37 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
  * do for the request. If @rq->bio is non-NULL then there is
  * additional work required to complete the request.
  */
-DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+TRACE_EVENT(block_rq_complete,
 
-	TP_PROTO(struct request_queue *q, struct request *rq),
+	TP_PROTO(struct request_queue *q, struct request *rq,
+		 unsigned int nr_bytes),
 
-	TP_ARGS(q, rq)
+	TP_ARGS(q, rq, nr_bytes),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_rq_pos(rq);
+		__entry->nr_sector = nr_bytes >> 9;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
 );
 
 DECLARE_EVENT_CLASS(block_rq,
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 06f544ef2f6f..c6814b917bdf 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -5,6 +5,7 @@
 #define _TRACE_COMPACTION_H
 
 #include <linux/types.h>
+#include <linux/list.h>
 #include <linux/tracepoint.h>
 #include <trace/events/gfpflags.h>
 
@@ -47,10 +48,11 @@ DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages,
 
 TRACE_EVENT(mm_compaction_migratepages,
 
-	TP_PROTO(unsigned long nr_migrated,
-		unsigned long nr_failed),
+	TP_PROTO(unsigned long nr_all,
+		int migrate_rc,
+		struct list_head *migratepages),
 
-	TP_ARGS(nr_migrated, nr_failed),
+	TP_ARGS(nr_all, migrate_rc, migratepages),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, nr_migrated)
@@ -58,7 +60,22 @@ TRACE_EVENT(mm_compaction_migratepages,
 	),
 
 	TP_fast_assign(
-		__entry->nr_migrated = nr_migrated;
+		unsigned long nr_failed = 0;
+		struct list_head *page_lru;
+
+		/*
+		 * migrate_pages() returns either a non-negative number
+		 * with the number of pages that failed migration, or an
+		 * error code, in which case we need to count the remaining
+		 * pages manually
+		 */
+		if (migrate_rc >= 0)
+			nr_failed = migrate_rc;
+		else
+			list_for_each(page_lru, migratepages)
+				nr_failed++;
+
+		__entry->nr_migrated = nr_all - nr_failed;
 		__entry->nr_failed = nr_failed;
 	),
 
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 131a0bda7aec..908925ace776 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -37,7 +37,7 @@ TRACE_EVENT(kvm_userspace_exit,
 		  __entry->errno < 0 ? -__entry->errno : __entry->reason)
 );
 
-#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+#if defined(CONFIG_HAVE_KVM_IRQFD)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
 	TP_ARGS(gsi, level, irq_source_id),
@@ -57,7 +57,7 @@ TRACE_EVENT(kvm_set_irq,
 	TP_printk("gsi %u level %d source %d",
 		  __entry->gsi, __entry->level, __entry->irq_source_id)
 );
-#endif
+#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
 
 #if defined(__KVM_HAVE_IOAPIC)
 #define kvm_deliver_mode		\
@@ -124,7 +124,7 @@ TRACE_EVENT(kvm_msi_set_irq,
 
 #endif /* defined(__KVM_HAVE_IOAPIC) */
 
-#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+#if defined(CONFIG_HAVE_KVM_IRQFD)
 
 TRACE_EVENT(kvm_ack_irq,
 	TP_PROTO(unsigned int irqchip, unsigned int pin),
@@ -149,7 +149,7 @@ TRACE_EVENT(kvm_ack_irq,
 #endif
 );
 
-#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
 
 
 
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 161932737416..ca298c7157ae 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -78,7 +78,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) - __this_cpu_read(mod->refptr->decs);
 		__assign_str(name, mod->name);
 	),
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 67e1bbf83695..dc7bb01f580f 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	/*
 	 * For all intents and purposes a preempted task is a running task.
 	 */
-	if (task_preempt_count(p) & PREEMPT_ACTIVE)
+	if (preempt_count() & PREEMPT_ACTIVE)
 		state = TASK_RUNNING | TASK_STATE_MAX;
 #endif
 
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index fed853f3d7aa..9674145e2f6a 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -4,6 +4,7 @@
 #include <linux/tracepoint.h>
 #include <linux/unistd.h>
 #include <linux/ftrace_event.h>
+#include <linux/thread_info.h>
 
 #include <asm/ptrace.h>
 
@@ -32,4 +33,18 @@ struct syscall_metadata {
 	struct ftrace_event_call *exit_event;
 };
 
+#if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+	else
+		clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+}
+#else
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+}
+#endif
+
 #endif /* _TRACE_SYSCALL_H */
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index 5e1ab552cbed..c28de1afd684 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -114,7 +114,6 @@ struct drm_tegra_submit {
 	__u32 num_waitchks;
 	__u32 waitchk_mask;
 	__u32 timeout;
-	__u32 pad;
 	__u64 syncpts;
 	__u64 cmdbufs;
 	__u64 relocs;
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 87792a5fee3b..33b739522840 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -29,7 +29,7 @@
 #define __VMWGFX_DRM_H__
 
 #ifndef __KERNEL__
-#include <drm.h>
+#include <drm/drm.h>
 #endif
 
 #define DRM_VMW_MAX_SURFACE_FACES 6
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 3ce25b5d75a9..3da5dfed2629 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -316,6 +316,7 @@ header-y += ppp-ioctl.h
 header-y += ppp_defs.h
 header-y += pps.h
 header-y += prctl.h
+header-y += psci.h
 header-y += ptp_clock.h
 header-y += ptrace.h
 header-y += qnx4_fs.h
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index bd24470d24a2..f4849525519c 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -164,6 +164,7 @@ struct input_keymap_entry {
 #define INPUT_PROP_DIRECT		0x01	/* direct input devices */
 #define INPUT_PROP_BUTTONPAD		0x02	/* has button(s) under pad */
 #define INPUT_PROP_SEMI_MT		0x03	/* touch rectangle only */
+#define INPUT_PROP_TOPBUTTONPAD		0x04	/* softbuttons at top of pad */
 
 #define INPUT_PROP_MAX			0x1f
 #define INPUT_PROP_CNT			(INPUT_PROP_MAX + 1)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 932d7f2637d6..cbc65ee211a4 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -171,6 +171,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_WATCHDOG         21
 #define KVM_EXIT_S390_TSCH        22
 #define KVM_EXIT_EPR              23
+#define KVM_EXIT_SYSTEM_EVENT     24
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -301,6 +302,13 @@ struct kvm_run {
 		struct {
 			__u32 epr;
 		} epr;
+		/* KVM_EXIT_SYSTEM_EVENT */
+		struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN       1
+#define KVM_SYSTEM_EVENT_RESET          2
+			__u32 type;
+			__u64 flags;
+		} system_event;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -391,8 +399,9 @@ struct kvm_vapic_addr {
 	__u64 vapic_addr;
 };
 
-/* for KVM_SET_MPSTATE */
+/* for KVM_SET_MP_STATE */
 
+/* not all states are valid on all architectures */
 #define KVM_MP_STATE_RUNNABLE          0
 #define KVM_MP_STATE_UNINITIALIZED     1
 #define KVM_MP_STATE_INIT_RECEIVED     2
@@ -573,9 +582,7 @@ struct kvm_ppc_smmu_info {
 #endif
 /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
-#ifdef __KVM_HAVE_USER_NMI
 #define KVM_CAP_USER_NMI 22
-#endif
 #ifdef __KVM_HAVE_GUEST_DEBUG
 #define KVM_CAP_SET_GUEST_DEBUG 23
 #endif
@@ -657,9 +664,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_GET_SMMU_INFO 78
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
-#ifdef __KVM_HAVE_READONLY_MEM
 #define KVM_CAP_READONLY_MEM 81
-#endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 #define KVM_CAP_PPC_HTAB_FD 84
@@ -675,6 +680,8 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_SPAPR_MULTITCE 94
 #define KVM_CAP_EXT_EMUL_CPUID 95
 #define KVM_CAP_HYPERV_TIME 96
+#define KVM_CAP_ARM_PSCI_0_2 102
+#define KVM_CAP_CHECK_EXTENSION_VM 105
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -847,14 +854,25 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#define KVM_DEV_TYPE_FSL_MPIC_20	1
-#define KVM_DEV_TYPE_FSL_MPIC_42	2
-#define KVM_DEV_TYPE_XICS		3
-#define KVM_DEV_TYPE_VFIO		4
 #define  KVM_DEV_VFIO_GROUP			1
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
-#define KVM_DEV_TYPE_ARM_VGIC_V2	5
+
+enum kvm_device_type {
+	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20	KVM_DEV_TYPE_FSL_MPIC_20
+	KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42	KVM_DEV_TYPE_FSL_MPIC_42
+	KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS		KVM_DEV_TYPE_XICS
+	KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO		KVM_DEV_TYPE_VFIO
+	KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2	KVM_DEV_TYPE_ARM_VGIC_V2
+	KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
+	KVM_DEV_TYPE_MAX,
+};
 
 /*
  * ioctls for VM fds
@@ -992,7 +1010,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_S390_INITIAL_RESET    _IO(KVMIO,   0x97)
 #define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
 #define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
-/* Available with KVM_CAP_NMI */
+/* Available with KVM_CAP_USER_NMI */
 #define KVM_NMI                   _IO(KVMIO,   0x9a)
 /* Available with KVM_CAP_SET_GUEST_DEBUG */
 #define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index 335e8a7cad39..c140620dad92 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -85,6 +85,12 @@
 
 #endif /* _NETINET_IN_H */
 
+/* Definitions for xattr.h */
+#if defined(_SYS_XATTR_H)
+#define __UAPI_DEF_XATTR		0
+#else
+#define __UAPI_DEF_XATTR		1
+#endif
 
 /* If we did not see any headers from any supported C libraries,
  * or we are being included in the kernel, then define everything
@@ -98,6 +104,9 @@
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
 
+/* Definitions for xattr.h */
+#define __UAPI_DEF_XATTR		1
+
 #endif /* __GLIBC__ */
 
 #endif /* _UAPI_LIBC_COMPAT_H */
diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h
index 5dda450eb55b..2ec9fbcd06f9 100644
--- a/include/uapi/linux/netfilter/xt_bpf.h
+++ b/include/uapi/linux/netfilter/xt_bpf.h
@@ -6,6 +6,8 @@
 
 #define XT_BPF_MAX_NUM_INSTR	64
 
+struct sk_filter;
+
 struct xt_bpf_info {
 	__u16 bpf_program_num_elem;
 	struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR];
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
new file mode 100644
index 000000000000..310d83e0a91b
--- /dev/null
+++ b/include/uapi/linux/psci.h
@@ -0,0 +1,90 @@
+/*
+ * ARM Power State and Coordination Interface (PSCI) header
+ *
+ * This header holds common PSCI defines and macros shared
+ * by: ARM kernel, ARM64 kernel, KVM ARM/ARM64 and user space.
+ *
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Anup Patel <anup.patel@linaro.org>
+ */
+
+#ifndef _UAPI_LINUX_PSCI_H
+#define _UAPI_LINUX_PSCI_H
+
+/*
+ * PSCI v0.1 interface
+ *
+ * The PSCI v0.1 function numbers are implementation defined.
+ *
+ * Only PSCI return values such as: SUCCESS, NOT_SUPPORTED,
+ * INVALID_PARAMS, and DENIED defined below are applicable
+ * to PSCI v0.1.
+ */
+
+/* PSCI v0.2 interface */
+#define PSCI_0_2_FN_BASE			0x84000000
+#define PSCI_0_2_FN(n)				(PSCI_0_2_FN_BASE + (n))
+#define PSCI_0_2_64BIT				0x40000000
+#define PSCI_0_2_FN64_BASE			\
+					(PSCI_0_2_FN_BASE + PSCI_0_2_64BIT)
+#define PSCI_0_2_FN64(n)			(PSCI_0_2_FN64_BASE + (n))
+
+#define PSCI_0_2_FN_PSCI_VERSION		PSCI_0_2_FN(0)
+#define PSCI_0_2_FN_CPU_SUSPEND			PSCI_0_2_FN(1)
+#define PSCI_0_2_FN_CPU_OFF			PSCI_0_2_FN(2)
+#define PSCI_0_2_FN_CPU_ON			PSCI_0_2_FN(3)
+#define PSCI_0_2_FN_AFFINITY_INFO		PSCI_0_2_FN(4)
+#define PSCI_0_2_FN_MIGRATE			PSCI_0_2_FN(5)
+#define PSCI_0_2_FN_MIGRATE_INFO_TYPE		PSCI_0_2_FN(6)
+#define PSCI_0_2_FN_MIGRATE_INFO_UP_CPU		PSCI_0_2_FN(7)
+#define PSCI_0_2_FN_SYSTEM_OFF			PSCI_0_2_FN(8)
+#define PSCI_0_2_FN_SYSTEM_RESET		PSCI_0_2_FN(9)
+
+#define PSCI_0_2_FN64_CPU_SUSPEND		PSCI_0_2_FN64(1)
+#define PSCI_0_2_FN64_CPU_ON			PSCI_0_2_FN64(3)
+#define PSCI_0_2_FN64_AFFINITY_INFO		PSCI_0_2_FN64(4)
+#define PSCI_0_2_FN64_MIGRATE			PSCI_0_2_FN64(5)
+#define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU	PSCI_0_2_FN64(7)
+
+/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
+#define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
+#define PSCI_0_2_POWER_STATE_ID_SHIFT		0
+#define PSCI_0_2_POWER_STATE_TYPE_SHIFT		16
+#define PSCI_0_2_POWER_STATE_TYPE_MASK		\
+				(0x1 << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+#define PSCI_0_2_POWER_STATE_AFFL_SHIFT		24
+#define PSCI_0_2_POWER_STATE_AFFL_MASK		\
+				(0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+
+/* PSCI v0.2 affinity level state returned by AFFINITY_INFO */
+#define PSCI_0_2_AFFINITY_LEVEL_ON		0
+#define PSCI_0_2_AFFINITY_LEVEL_OFF		1
+#define PSCI_0_2_AFFINITY_LEVEL_ON_PENDING	2
+
+/* PSCI v0.2 multicore support in Trusted OS returned by MIGRATE_INFO_TYPE */
+#define PSCI_0_2_TOS_UP_MIGRATE			0
+#define PSCI_0_2_TOS_UP_NO_MIGRATE		1
+#define PSCI_0_2_TOS_MP				2
+
+/* PSCI version decoding (independent of PSCI version) */
+#define PSCI_VERSION_MAJOR_SHIFT		16
+#define PSCI_VERSION_MINOR_MASK			\
+		((1U << PSCI_VERSION_MAJOR_SHIFT) - 1)
+#define PSCI_VERSION_MAJOR_MASK			~PSCI_VERSION_MINOR_MASK
+#define PSCI_VERSION_MAJOR(ver)			\
+		(((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
+#define PSCI_VERSION_MINOR(ver)			\
+		((ver) & PSCI_VERSION_MINOR_MASK)
+
+/* PSCI return values (inclusive of all PSCI versions) */
+#define PSCI_RET_SUCCESS			0
+#define PSCI_RET_NOT_SUPPORTED			-1
+#define PSCI_RET_INVALID_PARAMS			-2
+#define PSCI_RET_DENIED				-3
+#define PSCI_RET_ALREADY_ON			-4
+#define PSCI_RET_ON_PENDING			-5
+#define PSCI_RET_INTERNAL_FAILURE		-6
+#define PSCI_RET_NOT_PRESENT			-7
+#define PSCI_RET_DISABLED			-8
+
+#endif /* _UAPI_LINUX_PSCI_H */
diff --git a/include/uapi/linux/usb/Kbuild b/include/uapi/linux/usb/Kbuild
index 6cb4ea826834..4cc4d6e7e523 100644
--- a/include/uapi/linux/usb/Kbuild
+++ b/include/uapi/linux/usb/Kbuild
@@ -1,6 +1,7 @@
 # UAPI Header export list
 header-y += audio.h
 header-y += cdc.h
+header-y += cdc-wdm.h
 header-y += ch11.h
 header-y += ch9.h
 header-y += functionfs.h
diff --git a/include/uapi/linux/usb/cdc-wdm.h b/include/uapi/linux/usb/cdc-wdm.h
index f03134feebd6..0dc132e75030 100644
--- a/include/uapi/linux/usb/cdc-wdm.h
+++ b/include/uapi/linux/usb/cdc-wdm.h
@@ -9,6 +9,8 @@
 #ifndef _UAPI__LINUX_USB_CDC_WDM_H
 #define _UAPI__LINUX_USB_CDC_WDM_H
 
+#include <linux/types.h>
+
 /*
  * This IOCTL is used to retrieve the wMaxCommand for the device,
  * defining the message limit for both reading and writing.
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index d6b01283f85c..f279394aafb0 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -32,12 +32,13 @@ struct usb_endpoint_descriptor_no_audio {
  * All numbers must be in little endian order.
  */
 
+/* Legacy format, deprecated as of 3.14. */
 struct usb_functionfs_descs_head {
 	__le32 magic;
 	__le32 length;
 	__le32 fs_count;
 	__le32 hs_count;
-} __attribute__((packed));
+} __attribute__((packed, deprecated));
 
 /*
  * Descriptors format:
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 6ae7bbe988cc..fe94bb90582e 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -1059,14 +1059,14 @@ struct v4l2_bt_timings {
 
 /* A few useful defines to calculate the total blanking and frame sizes */
 #define V4L2_DV_BT_BLANKING_WIDTH(bt) \
-	(bt->hfrontporch + bt->hsync + bt->hbackporch)
+	((bt)->hfrontporch + (bt)->hsync + (bt)->hbackporch)
 #define V4L2_DV_BT_FRAME_WIDTH(bt) \
-	(bt->width + V4L2_DV_BT_BLANKING_WIDTH(bt))
+	((bt)->width + V4L2_DV_BT_BLANKING_WIDTH(bt))
 #define V4L2_DV_BT_BLANKING_HEIGHT(bt) \
-	(bt->vfrontporch + bt->vsync + bt->vbackporch + \
-	 bt->il_vfrontporch + bt->il_vsync + bt->il_vbackporch)
+	((bt)->vfrontporch + (bt)->vsync + (bt)->vbackporch + \
+	 (bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch)
 #define V4L2_DV_BT_FRAME_HEIGHT(bt) \
-	(bt->height + V4L2_DV_BT_BLANKING_HEIGHT(bt))
+	((bt)->height + V4L2_DV_BT_BLANKING_HEIGHT(bt))
 
 /** struct v4l2_dv_timings - DV timings
  * @type:	the type of the timings
diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h
index 40bbc04b6f81..1590c49cae57 100644
--- a/include/uapi/linux/xattr.h
+++ b/include/uapi/linux/xattr.h
@@ -7,11 +7,18 @@
   Copyright (c) 2001-2002 Silicon Graphics, Inc.  All Rights Reserved.
   Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
 */
+
+#include <linux/libc-compat.h>
+
 #ifndef _UAPI_LINUX_XATTR_H
 #define _UAPI_LINUX_XATTR_H
 
+#if __UAPI_DEF_XATTR
+#define __USE_KERNEL_XATTR_DEFS
+
 #define XATTR_CREATE	0x1	/* set value, fail if attr already exists */
 #define XATTR_REPLACE	0x2	/* set value, fail if attr does not exist */
+#endif
 
 /* Namespaces */
 #define XATTR_OS2_PREFIX "os2."
diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h
index 99b80abf360a..3066718eb120 100644
--- a/include/uapi/rdma/rdma_user_cm.h
+++ b/include/uapi/rdma/rdma_user_cm.h
@@ -34,6 +34,7 @@
 #define RDMA_USER_CM_H
 
 #include <linux/types.h>
+#include <linux/socket.h>
 #include <linux/in6.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_user_sa.h>
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index 5759810e1c1b..21eed488783f 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -80,7 +80,7 @@ struct snd_compr_tstamp {
 struct snd_compr_avail {
 	__u64 avail;
 	struct snd_compr_tstamp tstamp;
-};
+} __attribute__((packed));
 
 enum snd_compr_direction {
 	SND_COMPRESS_PLAYBACK = 0,
diff --git a/init/Kconfig b/init/Kconfig
index 009a797dd242..8b9521a2d2c1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1387,6 +1387,14 @@ config FUTEX
 	  support for "fast userspace mutexes".  The resulting kernel may not
 	  run glibc-based applications correctly.
 
+config HAVE_FUTEX_CMPXCHG
+	bool
+	depends on FUTEX
+	help
+	  Architectures should select this if futex_atomic_cmpxchg_inatomic()
+	  is implemented and always working. This removes a couple of runtime
+	  checks.
+
 config EPOLL
 	bool "Enable eventpoll support" if EXPERT
 	default y
@@ -1614,6 +1622,18 @@ config MMAP_ALLOW_UNINITIALIZED
 
 	  See Documentation/nommu-mmap.txt for more information.
 
+config SYSTEM_TRUSTED_KEYRING
+	bool "Provide system-wide ring of trusted keys"
+	depends on KEYS
+	help
+	  Provide a system keyring to which trusted keys can be added.  Keys in
+	  the keyring are considered to be trusted.  Keys may be added at will
+	  by the kernel from compiled-in data and from hardware key stores, but
+	  userspace may only add extra keys if those keys can be verified by
+	  keys already in the keyring.
+
+	  Keys in this keyring are used by module signature checking.
+
 config PROFILING
 	bool "Profiling support"
 	help
@@ -1649,18 +1669,6 @@ config BASE_SMALL
 	default 0 if BASE_FULL
 	default 1 if !BASE_FULL
 
-config SYSTEM_TRUSTED_KEYRING
-	bool "Provide system-wide ring of trusted keys"
-	depends on KEYS
-	help
-	  Provide a system keyring to which trusted keys can be added.  Keys in
-	  the keyring are considered to be trusted.  Keys may be added at will
-	  by the kernel from compiled-in data and from hardware key stores, but
-	  userspace may only add extra keys if those keys can be verified by
-	  keys already in the keyring.
-
-	  Keys in this keyring are used by module signature checking.
-
 menuconfig MODULES
 	bool "Enable loadable module support"
 	option modules
diff --git a/init/main.c b/init/main.c
index 9c7fd4c9249f..58c132d7de4b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -617,6 +617,10 @@ asmlinkage void __init start_kernel(void)
 	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
+#ifdef CONFIG_X86_ESPFIX64
+	/* Should be run before the first non-init thread is created */
+	init_espfix_bsp();
+#endif
 	thread_info_cache_init();
 	cred_init();
 	fork_init(totalram_pages);
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 17028648cfeb..cadddc8388f3 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -123,7 +123,6 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
-	size_t lenp_bef = *lenp;
 	int oldval;
 	int rc;
 
@@ -133,7 +132,7 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
 
 	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 
-	if (write && !rc && lenp_bef == *lenp) {
+	if (write && !rc) {
 		int newval = *((int *)(ipc_table.data));
 		/*
 		 * The file "auto_msgmni" has correctly been set.
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index d2b32ac27a39..ecee67a00f5f 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -220,6 +220,9 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE
 
 endif
 
+config ARCH_SUPPORTS_ATOMIC_RMW
+	bool
+
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES
+	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
diff --git a/kernel/audit.c b/kernel/audit.c
index 95a20f3f52f1..b45b2daa9f92 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -639,13 +639,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
 	case AUDIT_TTY_SET:
 	case AUDIT_TRIM:
 	case AUDIT_MAKE_EQUIV:
-		if (!capable(CAP_AUDIT_CONTROL))
+		if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
 			err = -EPERM;
 		break;
 	case AUDIT_USER:
 	case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
-		if (!capable(CAP_AUDIT_WRITE))
+		if (!netlink_capable(skb, CAP_AUDIT_WRITE))
 			err = -EPERM;
 		break;
 	default:  /* bad msg */
@@ -687,7 +687,7 @@ static int audit_get_feature(struct sk_buff *skb)
 
 	seq = nlmsg_hdr(skb)->nlmsg_seq;
 
-	audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
+	audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af));
 
 	return 0;
 }
@@ -702,7 +702,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
 	audit_log_task_info(ab, current);
-	audit_log_format(ab, "feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
+	audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
 			 audit_feature_names[which], !!old_feature, !!new_feature,
 			 !!old_lock, !!new_lock, res);
 	audit_log_end(ab);
@@ -1628,7 +1628,7 @@ void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
 	audit_log_format(ab, " %s=", prefix);
 	CAP_FOR_EACH_U32(i) {
 		audit_log_format(ab, "%08x",
-				 cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
+				 cap->cap[CAP_LAST_U32 - i]);
 	}
 }
 
@@ -1829,10 +1829,10 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
 	spin_unlock_irq(&tsk->sighand->siglock);
 
 	audit_log_format(ab,
-			 " ppid=%ld pid=%d auid=%u uid=%u gid=%u"
+			 " ppid=%d pid=%d auid=%u uid=%u gid=%u"
 			 " euid=%u suid=%u fsuid=%u"
 			 " egid=%u sgid=%u fsgid=%u tty=%s ses=%u",
-			 sys_getppid(),
+			 task_ppid_nr(tsk),
 			 tsk->pid,
 			 from_kuid(&init_user_ns, audit_get_loginuid(tsk)),
 			 from_kuid(&init_user_ns, cred->uid),
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 135944a7b28a..a79db03990db 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,6 +154,7 @@ static struct audit_chunk *alloc_chunk(int count)
 		chunk->owners[i].index = i;
 	}
 	fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+	chunk->mark.mask = FS_IN_IGNORED;
 	return chunk;
 }
 
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 92062fd6cc8c..598c1dcf26dd 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -429,6 +429,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) {
 			f->type = AUDIT_LOGINUID_SET;
 			f->val = 0;
+			entry->rule.pflags |= AUDIT_LOGINUID_LEGACY;
 		}
 
 		err = audit_field_valid(entry, f);
@@ -604,6 +605,13 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 			data->buflen += data->values[i] =
 				audit_pack_string(&bufp, krule->filterkey);
 			break;
+		case AUDIT_LOGINUID_SET:
+			if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) {
+				data->fields[i] = AUDIT_LOGINUID;
+				data->values[i] = AUDIT_UID_UNSET;
+				break;
+			}
+			/* fallthrough if set */
 		default:
 			data->values[i] = f->val;
 		}
@@ -620,6 +628,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b)
 	int i;
 
 	if (a->flags != b->flags ||
+	    a->pflags != b->pflags ||
 	    a->listnr != b->listnr ||
 	    a->action != b->action ||
 	    a->field_count != b->field_count)
@@ -738,6 +747,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old)
 	new = &entry->rule;
 	new->vers_ops = old->vers_ops;
 	new->flags = old->flags;
+	new->pflags = old->pflags;
 	new->listnr = old->listnr;
 	new->action = old->action;
 	for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 7aef2f4b6c64..619b58d3fcdf 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -459,7 +459,7 @@ static int audit_filter_rules(struct task_struct *tsk,
 		case AUDIT_PPID:
 			if (ctx) {
 				if (!ctx->ppid)
-					ctx->ppid = sys_getppid();
+					ctx->ppid = task_ppid_nr(tsk);
 				result = audit_comparator(ctx->ppid, f->op, f->val);
 			}
 			break;
@@ -720,6 +720,22 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
 	return AUDIT_BUILD_CONTEXT;
 }
 
+static int audit_in_mask(const struct audit_krule *rule, unsigned long val)
+{
+	int word, bit;
+
+	if (val > 0xffffffff)
+		return false;
+
+	word = AUDIT_WORD(val);
+	if (word >= AUDIT_BITMASK_SIZE)
+		return false;
+
+	bit = AUDIT_BIT(val);
+
+	return rule->mask[word] & bit;
+}
+
 /* At syscall entry and exit time, this filter is called if the
  * audit_state is not low enough that auditing cannot take place, but is
  * also not high enough that we already know we have to write an audit
@@ -737,11 +753,8 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 
 	rcu_read_lock();
 	if (!list_empty(list)) {
-		int word = AUDIT_WORD(ctx->major);
-		int bit  = AUDIT_BIT(ctx->major);
-
 		list_for_each_entry_rcu(e, list, list) {
-			if ((e->rule.mask[word] & bit) == bit &&
+			if (audit_in_mask(&e->rule, ctx->major) &&
 			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
 					       &state, false)) {
 				rcu_read_unlock();
@@ -761,20 +774,16 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 static int audit_filter_inode_name(struct task_struct *tsk,
 				   struct audit_names *n,
 				   struct audit_context *ctx) {
-	int word, bit;
 	int h = audit_hash_ino((u32)n->ino);
 	struct list_head *list = &audit_inode_hash[h];
 	struct audit_entry *e;
 	enum audit_state state;
 
-	word = AUDIT_WORD(ctx->major);
-	bit  = AUDIT_BIT(ctx->major);
-
 	if (list_empty(list))
 		return 0;
 
 	list_for_each_entry_rcu(e, list, list) {
-		if ((e->rule.mask[word] & bit) == bit &&
+		if (audit_in_mask(&e->rule, ctx->major) &&
 		    audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) {
 			ctx->current_state = state;
 			return 1;
@@ -1982,7 +1991,7 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
 	if (!ab)
 		return;
 	audit_log_format(ab, "pid=%d uid=%u"
-			 " old-auid=%u new-auid=%u old-ses=%u new-ses=%u"
+			 " old-auid=%u auid=%u old-ses=%u ses=%u"
 			 " res=%d",
 			 current->pid, uid,
 			 oldloginuid, loginuid, oldsessionid, sessionid,
diff --git a/kernel/capability.c b/kernel/capability.c
index 34019c57888d..00adb2193d01 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -268,6 +268,10 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
 		i++;
 	}
 
+	effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
@@ -433,23 +437,19 @@ bool capable(int cap)
 EXPORT_SYMBOL(capable);
 
 /**
- * inode_capable - Check superior capability over inode
+ * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
  * @inode: The inode in question
  * @cap: The capability in question
  *
- * Return true if the current task has the given superior capability
- * targeted at it's own user namespace and that the given inode is owned
- * by the current user namespace or a child namespace.
- *
- * Currently we check to see if an inode is owned by the current
- * user namespace by seeing if the inode's owner maps into the
- * current user namespace.
- *
+ * Return true if the current task has the given capability targeted at
+ * its own user namespace and that the given inode's uid and gid are
+ * mapped into the current user namespace.
  */
-bool inode_capable(const struct inode *inode, int cap)
+bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
 {
 	struct user_namespace *ns = current_user_ns();
 
-	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
+	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) &&
+		kgid_has_mapping(ns, inode->i_gid);
 }
-EXPORT_SYMBOL(inode_capable);
+EXPORT_SYMBOL(capable_wrt_inode_uidgid);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 0c753ddd223b..550e2050d778 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3663,7 +3663,6 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 
 	l = cgroup_pidlist_find_create(cgrp, type);
 	if (!l) {
-		mutex_unlock(&cgrp->pidlist_mutex);
 		pidlist_free(array);
 		return -ENOMEM;
 	}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index deff2e693766..9a1ba77d6a50 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -692,10 +692,12 @@ void set_cpu_present(unsigned int cpu, bool present)
 
 void set_cpu_online(unsigned int cpu, bool online)
 {
-	if (online)
+	if (online) {
 		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
-	else
+		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+	} else {
 		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+	}
 }
 
 void set_cpu_active(unsigned int cpu, bool active)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e6b1b66afe52..15b3ea693225 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1022,7 +1022,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	task_lock(tsk);
 	/*
 	 * Determine if a loop is necessary if another thread is doing
-	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * read_mems_allowed_begin().  If at least one node remains unchanged and
 	 * tsk does not have a mempolicy, then an empty nodemask will not be
 	 * possible when mems_allowed is larger than a word.
 	 */
@@ -1236,7 +1236,13 @@ done:
 
 int current_cpuset_is_being_rebound(void)
 {
-	return task_cs(current) == cpuset_being_rebound;
+	int ret;
+
+	rcu_read_lock();
+	ret = task_cs(current) == cpuset_being_rebound;
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 334b3980ffc1..8865caec45fb 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -49,6 +49,7 @@
 #include <linux/pid.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/rcupdate.h>
 
 #include <asm/cacheflush.h>
@@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
 	if (!CACHE_FLUSH_IS_SAFE)
 		return;
 
-	if (current->mm && current->mm->mmap_cache) {
-		flush_cache_range(current->mm->mmap_cache,
-				  addr, addr + BREAK_INSTR_SIZE);
+	if (current->mm) {
+		int i;
+
+		for (i = 0; i < VMACACHE_SIZE; i++) {
+			if (!current->vmacache[i])
+				continue;
+			flush_cache_range(current->vmacache[i],
+					  addr, addr + BREAK_INSTR_SIZE);
+		}
 	}
+
 	/* Force flush instruction cache if it was outside the mm */
 	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fa0b2d4ad83c..69cffb46db17 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -39,6 +39,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/mm_types.h>
 #include <linux/cgroup.h>
+#include <linux/compat.h>
 
 #include "internal.h"
 
@@ -1439,6 +1440,11 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
+struct remove_event {
+	struct perf_event *event;
+	bool detach_group;
+};
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1447,12 +1453,15 @@ group_sched_out(struct perf_event *group_event,
  */
 static int __perf_remove_from_context(void *info)
 {
-	struct perf_event *event = info;
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	raw_spin_lock(&ctx->lock);
 	event_sched_out(event, cpuctx, ctx);
+	if (re->detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
 		ctx->is_active = 0;
@@ -1477,10 +1486,14 @@ static int __perf_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
+	struct remove_event re = {
+		.event = event,
+		.detach_group = detach_group,
+	};
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -1489,12 +1502,12 @@ static void perf_remove_from_context(struct perf_event *event)
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, event);
+		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
 	}
 
 retry:
-	if (!task_function_call(task, __perf_remove_from_context, event))
+	if (!task_function_call(task, __perf_remove_from_context, &re))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -1504,6 +1517,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -1511,6 +1529,8 @@ retry:
 	 * Since the task isn't running, its safe to remove the event, us
 	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
+	if (detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
@@ -1943,6 +1963,11 @@ retry:
 	 */
 	if (ctx->is_active) {
 		raw_spin_unlock_irq(&ctx->lock);
+		/*
+		 * Reload the task pointer, it might have been changed by
+		 * a concurrent perf_event_context_sched_out().
+		 */
+		task = ctx->task;
 		goto retry;
 	}
 
@@ -2297,7 +2322,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	next_parent = rcu_dereference(next_ctx->parent_ctx);
 
 	/* If neither context have a parent context; they cannot be clones. */
-	if (!parent && !next_parent)
+	if (!parent || !next_parent)
 		goto unlock;
 
 	if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
@@ -3279,10 +3304,7 @@ int perf_event_release_kernel(struct perf_event *event)
 	 *     to trigger the AB-BA case.
 	 */
 	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	raw_spin_lock_irq(&ctx->lock);
-	perf_group_detach(event);
-	raw_spin_unlock_irq(&ctx->lock);
-	perf_remove_from_context(event);
+	perf_remove_from_context(event, true);
 	mutex_unlock(&ctx->mutex);
 
 	free_event(event);
@@ -3672,6 +3694,26 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return 0;
 }
 
+#ifdef CONFIG_COMPAT
+static long perf_compat_ioctl(struct file *file, unsigned int cmd,
+				unsigned long arg)
+{
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
+	case _IOC_NR(PERF_EVENT_IOC_ID):
+		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
+		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
+			cmd &= ~IOCSIZE_MASK;
+			cmd |= sizeof(void *) << IOCSIZE_SHIFT;
+		}
+		break;
+	}
+	return perf_ioctl(file, cmd, arg);
+}
+#else
+# define perf_compat_ioctl NULL
+#endif
+
 int perf_event_task_enable(void)
 {
 	struct perf_event *event;
@@ -4164,7 +4206,7 @@ static const struct file_operations perf_fops = {
 	.read			= perf_read,
 	.poll			= perf_poll,
 	.unlocked_ioctl		= perf_ioctl,
-	.compat_ioctl		= perf_ioctl,
+	.compat_ioctl		= perf_compat_ioctl,
 	.mmap			= perf_mmap,
 	.fasync			= perf_fasync,
 };
@@ -5406,6 +5448,9 @@ struct swevent_htable {
 
 	/* Recursion avoidance in each contexts */
 	int				recursion[PERF_NR_CONTEXTS];
+
+	/* Keeps track of cpu being initialized/exited */
+	bool				online;
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -5652,8 +5697,14 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	hwc->state = !(flags & PERF_EF_START);
 
 	head = find_swevent_head(swhash, event);
-	if (WARN_ON_ONCE(!head))
+	if (!head) {
+		/*
+		 * We can race with cpu hotplug code. Do not
+		 * WARN if the cpu just got unplugged.
+		 */
+		WARN_ON_ONCE(swhash->online);
 		return -EINVAL;
+	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
 
@@ -7016,6 +7067,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;
+	} else {
+		if (attr.sample_period & (1ULL << 63))
+			return -EINVAL;
 	}
 
 	/*
@@ -7163,7 +7217,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader, false);
 
 		/*
 		 * Removing from the context ends up with disabled
@@ -7173,7 +7227,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_remove_from_context(sibling);
+			perf_remove_from_context(sibling, false);
 			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
@@ -7186,11 +7240,11 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (move_group) {
 		synchronize_rcu();
-		perf_install_in_context(ctx, group_leader, event->cpu);
+		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_install_in_context(ctx, sibling, event->cpu);
+			perf_install_in_context(ctx, sibling, sibling->cpu);
 			get_ctx(ctx);
 		}
 	}
@@ -7303,7 +7357,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	mutex_lock(&src_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
-		perf_remove_from_context(event);
+		perf_remove_from_context(event, false);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
 		list_add(&event->migrate_entry, &events);
@@ -7365,13 +7419,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	if (child_event->parent) {
-		raw_spin_lock_irq(&child_ctx->lock);
-		perf_group_detach(child_event);
-		raw_spin_unlock_irq(&child_ctx->lock);
-	}
-
-	perf_remove_from_context(child_event);
+	perf_remove_from_context(child_event, !!child_event->parent);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7809,8 +7857,10 @@ int perf_event_init_task(struct task_struct *child)
 
 	for_each_task_context_nr(ctxn) {
 		ret = perf_event_init_context(child, ctxn);
-		if (ret)
+		if (ret) {
+			perf_event_free_task(child);
 			return ret;
+		}
 	}
 
 	return 0;
@@ -7833,6 +7883,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = true;
 	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
@@ -7855,14 +7906,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
+	struct remove_event re = { .detach_group = false };
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
-		__perf_remove_from_context(event);
+	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+		__perf_remove_from_context(&re);
 	rcu_read_unlock();
 }
 
@@ -7890,6 +7941,7 @@ static void perf_event_exit_cpu(int cpu)
 	perf_event_exit_cpu_context(cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = false;
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
 }
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 307d87c0991a..1139b228befc 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1621,7 +1621,6 @@ bool uprobe_deny_signal(void)
 		if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
 			utask->state = UTASK_SSTEP_TRAPPED;
 			set_tsk_thread_flag(t, TIF_UPROBE);
-			set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
 		}
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 1e77fc645317..81b3d6789ee8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -560,9 +560,6 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	if (p->exit_state == EXIT_DEAD)
-		return;
 	/*
 	 * If this is a threaded reparent there is no need to
 	 * notify anyone anything has happened.
@@ -570,9 +567,19 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/* We don't want people slaying init.  */
+	/*
+	 * We don't want people slaying init.
+	 *
+	 * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
+	 * can change ->exit_state to EXIT_ZOMBIE. If this is the final
+	 * state, do_notify_parent() was already called and ->exit_signal
+	 * doesn't matter.
+	 */
 	p->exit_signal = SIGCHLD;
 
+	if (p->exit_state == EXIT_DEAD)
+		return;
+
 	/* If it has exited notify the new parent about this child's death. */
 	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
@@ -784,6 +791,8 @@ void do_exit(long code)
 	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
+	if (group_dead)
+		disassociate_ctty(1);
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	check_stack_usage();
@@ -799,13 +808,9 @@ void do_exit(long code)
 
 	cgroup_exit(tsk, 1);
 
-	if (group_dead)
-		disassociate_ctty(1);
-
 	module_put(task_thread_info(tsk)->exec_domain->module);
 
 	proc_exit_connector(tsk);
-
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
diff --git a/kernel/fork.c b/kernel/fork.c
index a17621c6cd42..e2c685396295 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,6 +28,8 @@
 #include <linux/mman.h>
 #include <linux/mmu_notifier.h>
 #include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -363,7 +365,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	mm->locked_vm = 0;
 	mm->mmap = NULL;
-	mm->mmap_cache = NULL;
+	mm->vmacache_seqnum = 0;
 	mm->map_count = 0;
 	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
@@ -876,6 +878,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	if (!oldmm)
 		return 0;
 
+	/* initialize the new vmacache entries */
+	vmacache_flush(tsk);
+
 	if (clone_flags & CLONE_VM) {
 		atomic_inc(&oldmm->mm_users);
 		mm = oldmm;
@@ -1323,7 +1328,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_policy;
 	retval = audit_alloc(p);
 	if (retval)
-		goto bad_fork_cleanup_policy;
+		goto bad_fork_cleanup_perf;
 	/* copy all the process information */
 	retval = copy_semundo(clone_flags, p);
 	if (retval)
@@ -1484,7 +1489,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
+	syscall_tracepoint_update(p);
 	write_unlock_irq(&tasklist_lock);
+
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	if (clone_flags & CLONE_THREAD)
@@ -1520,8 +1527,9 @@ bad_fork_cleanup_semundo:
 	exit_sem(p);
 bad_fork_cleanup_audit:
 	audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
 	perf_event_free_task(p);
+bad_fork_cleanup_policy:
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
@@ -1604,10 +1612,12 @@ long do_fork(unsigned long clone_flags,
 	 */
 	if (!IS_ERR(p)) {
 		struct completion vfork;
+		struct pid *pid;
 
 		trace_sched_process_fork(current, p);
 
-		nr = task_pid_vnr(p);
+		pid = get_task_pid(p, PIDTYPE_PID);
+		nr = pid_vnr(pid);
 
 		if (clone_flags & CLONE_PARENT_SETTID)
 			put_user(nr, parent_tidptr);
@@ -1622,12 +1632,14 @@ long do_fork(unsigned long clone_flags,
 
 		/* forking complete and child started to run, tell ptracer */
 		if (unlikely(trace))
-			ptrace_event(trace, nr);
+			ptrace_event_pid(trace, pid);
 
 		if (clone_flags & CLONE_VFORK) {
 			if (!wait_for_vfork_done(p, &vfork))
-				ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+				ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
 		}
+
+		put_pid(pid);
 	} else {
 		nr = PTR_ERR(p);
 	}
diff --git a/kernel/freezer.c b/kernel/freezer.c
index aa6a8aadb911..8f9279b9c6d7 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -42,6 +42,9 @@ bool freezing_slow_path(struct task_struct *p)
 	if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK))
 		return false;
 
+	if (test_thread_flag(TIF_MEMDIE))
+		return false;
+
 	if (pm_nosig_freezing || cgroup_freezing(p))
 		return true;
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 08ec814ad9d2..fda2950f2ce4 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -157,7 +157,9 @@
  * enqueue.
  */
 
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 int __read_mostly futex_cmpxchg_enabled;
+#endif
 
 /*
  * Futex flags used to encode options to functions and preserve them across
@@ -327,6 +329,8 @@ static void get_futex_key_refs(union futex_key *key)
 	case FUT_OFF_MMSHARED:
 		futex_get_mm(key); /* implies MB (B) */
 		break;
+	default:
+		smp_mb(); /* explicit MB (B) */
 	}
 }
 
@@ -727,6 +731,55 @@ void exit_pi_state_list(struct task_struct *curr)
 	raw_spin_unlock_irq(&curr->pi_lock);
 }
 
+/*
+ * We need to check the following states:
+ *
+ *      Waiter | pi_state | pi->owner | uTID      | uODIED | ?
+ *
+ * [1]  NULL   | ---      | ---       | 0         | 0/1    | Valid
+ * [2]  NULL   | ---      | ---       | >0        | 0/1    | Valid
+ *
+ * [3]  Found  | NULL     | --        | Any       | 0/1    | Invalid
+ *
+ * [4]  Found  | Found    | NULL      | 0         | 1      | Valid
+ * [5]  Found  | Found    | NULL      | >0        | 1      | Invalid
+ *
+ * [6]  Found  | Found    | task      | 0         | 1      | Valid
+ *
+ * [7]  Found  | Found    | NULL      | Any       | 0      | Invalid
+ *
+ * [8]  Found  | Found    | task      | ==taskTID | 0/1    | Valid
+ * [9]  Found  | Found    | task      | 0         | 0      | Invalid
+ * [10] Found  | Found    | task      | !=taskTID | 0/1    | Invalid
+ *
+ * [1]	Indicates that the kernel can acquire the futex atomically. We
+ *	came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
+ *
+ * [2]	Valid, if TID does not belong to a kernel thread. If no matching
+ *      thread is found then it indicates that the owner TID has died.
+ *
+ * [3]	Invalid. The waiter is queued on a non PI futex
+ *
+ * [4]	Valid state after exit_robust_list(), which sets the user space
+ *	value to FUTEX_WAITERS | FUTEX_OWNER_DIED.
+ *
+ * [5]	The user space value got manipulated between exit_robust_list()
+ *	and exit_pi_state_list()
+ *
+ * [6]	Valid state after exit_pi_state_list() which sets the new owner in
+ *	the pi_state but cannot access the user space value.
+ *
+ * [7]	pi_state->owner can only be NULL when the OWNER_DIED bit is set.
+ *
+ * [8]	Owner and user space value match
+ *
+ * [9]	There is no transient state which sets the user space TID to 0
+ *	except exit_robust_list(), but this is indicated by the
+ *	FUTEX_OWNER_DIED bit. See [4]
+ *
+ * [10] There is no transient state which leaves owner and user space
+ *	TID out of sync.
+ */
 static int
 lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 		union futex_key *key, struct futex_pi_state **ps)
@@ -739,12 +792,13 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex(&this->key, key)) {
 			/*
-			 * Another waiter already exists - bump up
-			 * the refcount and return its pi_state:
+			 * Sanity check the waiter before increasing
+			 * the refcount and attaching to it.
 			 */
 			pi_state = this->pi_state;
 			/*
-			 * Userspace might have messed up non-PI and PI futexes
+			 * Userspace might have messed up non-PI and
+			 * PI futexes [3]
 			 */
 			if (unlikely(!pi_state))
 				return -EINVAL;
@@ -752,34 +806,70 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 			WARN_ON(!atomic_read(&pi_state->refcount));
 
 			/*
-			 * When pi_state->owner is NULL then the owner died
-			 * and another waiter is on the fly. pi_state->owner
-			 * is fixed up by the task which acquires
-			 * pi_state->rt_mutex.
-			 *
-			 * We do not check for pid == 0 which can happen when
-			 * the owner died and robust_list_exit() cleared the
-			 * TID.
+			 * Handle the owner died case:
 			 */
-			if (pid && pi_state->owner) {
+			if (uval & FUTEX_OWNER_DIED) {
+				/*
+				 * exit_pi_state_list sets owner to NULL and
+				 * wakes the topmost waiter. The task which
+				 * acquires the pi_state->rt_mutex will fixup
+				 * owner.
+				 */
+				if (!pi_state->owner) {
+					/*
+					 * No pi state owner, but the user
+					 * space TID is not 0. Inconsistent
+					 * state. [5]
+					 */
+					if (pid)
+						return -EINVAL;
+					/*
+					 * Take a ref on the state and
+					 * return. [4]
+					 */
+					goto out_state;
+				}
+
+				/*
+				 * If TID is 0, then either the dying owner
+				 * has not yet executed exit_pi_state_list()
+				 * or some waiter acquired the rtmutex in the
+				 * pi state, but did not yet fixup the TID in
+				 * user space.
+				 *
+				 * Take a ref on the state and return. [6]
+				 */
+				if (!pid)
+					goto out_state;
+			} else {
 				/*
-				 * Bail out if user space manipulated the
-				 * futex value.
+				 * If the owner died bit is not set,
+				 * then the pi_state must have an
+				 * owner. [7]
 				 */
-				if (pid != task_pid_vnr(pi_state->owner))
+				if (!pi_state->owner)
 					return -EINVAL;
 			}
 
+			/*
+			 * Bail out if user space manipulated the
+			 * futex value. If pi state exists then the
+			 * owner TID must be the same as the user
+			 * space TID. [9/10]
+			 */
+			if (pid != task_pid_vnr(pi_state->owner))
+				return -EINVAL;
+
+		out_state:
 			atomic_inc(&pi_state->refcount);
 			*ps = pi_state;
-
 			return 0;
 		}
 	}
 
 	/*
 	 * We are the first waiter - try to look up the real owner and attach
-	 * the new pi_state to it, but bail out when TID = 0
+	 * the new pi_state to it, but bail out when TID = 0 [1]
 	 */
 	if (!pid)
 		return -ESRCH;
@@ -787,6 +877,11 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	if (!p)
 		return -ESRCH;
 
+	if (!p->mm) {
+		put_task_struct(p);
+		return -EPERM;
+	}
+
 	/*
 	 * We need to look at the task state flags to figure out,
 	 * whether the task is exiting. To protect against the do_exit
@@ -807,6 +902,9 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 		return ret;
 	}
 
+	/*
+	 * No existing pi state. First waiter. [2]
+	 */
 	pi_state = alloc_pi_state();
 
 	/*
@@ -878,10 +976,18 @@ retry:
 		return -EDEADLK;
 
 	/*
-	 * Surprise - we got the lock. Just return to userspace:
+	 * Surprise - we got the lock, but we do not trust user space at all.
 	 */
-	if (unlikely(!curval))
-		return 1;
+	if (unlikely(!curval)) {
+		/*
+		 * We verify whether there is kernel state for this
+		 * futex. If not, we can safely assume, that the 0 ->
+		 * TID transition is correct. If state exists, we do
+		 * not bother to fixup the user space state as it was
+		 * corrupted already.
+		 */
+		return futex_top_waiter(hb, key) ? -EINVAL : 1;
+	}
 
 	uval = curval;
 
@@ -1012,6 +1118,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	struct task_struct *new_owner;
 	struct futex_pi_state *pi_state = this->pi_state;
 	u32 uninitialized_var(curval), newval;
+	int ret = 0;
 
 	if (!pi_state)
 		return -EINVAL;
@@ -1035,23 +1142,19 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 		new_owner = this->task;
 
 	/*
-	 * We pass it to the next owner. (The WAITERS bit is always
-	 * kept enabled while there is PI state around. We must also
-	 * preserve the owner died bit.)
+	 * We pass it to the next owner. The WAITERS bit is always
+	 * kept enabled while there is PI state around. We cleanup the
+	 * owner died bit, because we are the owner.
 	 */
-	if (!(uval & FUTEX_OWNER_DIED)) {
-		int ret = 0;
-
-		newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
+	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
-			ret = -EFAULT;
-		else if (curval != uval)
-			ret = -EINVAL;
-		if (ret) {
-			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
-			return ret;
-		}
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+		ret = -EFAULT;
+	else if (curval != uval)
+		ret = -EINVAL;
+	if (ret) {
+		raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+		return ret;
 	}
 
 	raw_spin_lock_irq(&pi_state->owner->pi_lock);
@@ -1331,7 +1434,7 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  *
  * Return:
  *  0 - failed to acquire the lock atomically;
- *  1 - acquired the lock;
+ * >0 - acquired the lock, return value is vpid of the top_waiter
  * <0 - error
  */
 static int futex_proxy_trylock_atomic(u32 __user *pifutex,
@@ -1342,7 +1445,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 {
 	struct futex_q *top_waiter = NULL;
 	u32 curval;
-	int ret;
+	int ret, vpid;
 
 	if (get_futex_value_locked(&curval, pifutex))
 		return -EFAULT;
@@ -1370,11 +1473,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	 * the contended case or if set_waiters is 1.  The pi_state is returned
 	 * in ps in contended cases.
 	 */
+	vpid = task_pid_vnr(top_waiter->task);
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
 				   set_waiters);
-	if (ret == 1)
+	if (ret == 1) {
 		requeue_pi_wake_futex(top_waiter, key2, hb2);
-
+		return vpid;
+	}
 	return ret;
 }
 
@@ -1405,10 +1510,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
-	u32 curval2;
 
 	if (requeue_pi) {
 		/*
+		 * Requeue PI only works on two distinct uaddrs. This
+		 * check is only valid for private futexes. See below.
+		 */
+		if (uaddr1 == uaddr2)
+			return -EINVAL;
+
+		/*
 		 * requeue_pi requires a pi_state, try to allocate it now
 		 * without any locks in case it fails.
 		 */
@@ -1446,10 +1557,20 @@ retry:
 	if (unlikely(ret != 0))
 		goto out_put_key1;
 
+	/*
+	 * The check above which compares uaddrs is not sufficient for
+	 * shared futexes. We need to compare the keys:
+	 */
+	if (requeue_pi && match_futex(&key1, &key2)) {
+		ret = -EINVAL;
+		goto out_put_keys;
+	}
+
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
 
 retry_private:
+	hb_waiters_inc(hb2);
 	double_lock_hb(hb1, hb2);
 
 	if (likely(cmpval != NULL)) {
@@ -1459,6 +1580,7 @@ retry_private:
 
 		if (unlikely(ret)) {
 			double_unlock_hb(hb1, hb2);
+			hb_waiters_dec(hb2);
 
 			ret = get_user(curval, uaddr1);
 			if (ret)
@@ -1491,16 +1613,25 @@ retry_private:
 		 * At this point the top_waiter has either taken uaddr2 or is
 		 * waiting on it.  If the former, then the pi_state will not
 		 * exist yet, look it up one more time to ensure we have a
-		 * reference to it.
+		 * reference to it. If the lock was taken, ret contains the
+		 * vpid of the top waiter task.
 		 */
-		if (ret == 1) {
+		if (ret > 0) {
 			WARN_ON(pi_state);
 			drop_count++;
 			task_count++;
-			ret = get_futex_value_locked(&curval2, uaddr2);
-			if (!ret)
-				ret = lookup_pi_state(curval2, hb2, &key2,
-						      &pi_state);
+			/*
+			 * If we acquired the lock, then the user
+			 * space value of uaddr2 should be vpid. It
+			 * cannot be changed by the top waiter as it
+			 * is blocked on hb2 lock if it tries to do
+			 * so. If something fiddled with it behind our
+			 * back the pi state lookup might unearth
+			 * it. So we rather use the known value than
+			 * rereading and handing potential crap to
+			 * lookup_pi_state.
+			 */
+			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
 		}
 
 		switch (ret) {
@@ -1508,6 +1639,7 @@ retry_private:
 			break;
 		case -EFAULT:
 			double_unlock_hb(hb1, hb2);
+			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
 			ret = fault_in_user_writeable(uaddr2);
@@ -1517,6 +1649,7 @@ retry_private:
 		case -EAGAIN:
 			/* The owner was exiting, try again. */
 			double_unlock_hb(hb1, hb2);
+			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
 			cond_resched();
@@ -1592,6 +1725,7 @@ retry_private:
 
 out_unlock:
 	double_unlock_hb(hb1, hb2);
+	hb_waiters_dec(hb2);
 
 	/*
 	 * drop_futex_key_refs() must be called outside the spinlocks. During
@@ -2280,9 +2414,10 @@ retry:
 	/*
 	 * To avoid races, try to do the TID -> 0 atomic transition
 	 * again. If it succeeds then we can return without waking
-	 * anyone else up:
+	 * anyone else up. We only try this if neither the waiters nor
+	 * the owner died bit are set.
 	 */
-	if (!(uval & FUTEX_OWNER_DIED) &&
+	if (!(uval & ~FUTEX_TID_MASK) &&
 	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
 		goto pi_faulted;
 	/*
@@ -2312,11 +2447,9 @@ retry:
 	/*
 	 * No waiters - kernel unlocks the futex:
 	 */
-	if (!(uval & FUTEX_OWNER_DIED)) {
-		ret = unlock_futex_pi(uaddr, uval);
-		if (ret == -EFAULT)
-			goto pi_faulted;
-	}
+	ret = unlock_futex_pi(uaddr, uval);
+	if (ret == -EFAULT)
+		goto pi_faulted;
 
 out_unlock:
 	spin_unlock(&hb->lock);
@@ -2478,6 +2611,16 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	if (ret)
 		goto out_key2;
 
+	/*
+	 * The check above which compares uaddrs is not sufficient for
+	 * shared futexes. We need to compare the keys:
+	 */
+	if (match_futex(&q.key, &key2)) {
+		queue_unlock(hb);
+		ret = -EINVAL;
+		goto out_put_keys;
+	}
+
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
 	futex_wait_queue_me(hb, &q, to);
 
@@ -2875,9 +3018,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
 }
 
-static int __init futex_init(void)
+static void __init futex_detect_cmpxchg(void)
 {
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
 	u32 curval;
+
+	/*
+	 * This will fail and we want it. Some arch implementations do
+	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
+	 * functionality. We want to know that before we call in any
+	 * of the complex code paths. Also we want to prevent
+	 * registration of robust lists in that case. NULL is
+	 * guaranteed to fault and we get -EFAULT on functional
+	 * implementation, the non-functional ones will return
+	 * -ENOSYS.
+	 */
+	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
+		futex_cmpxchg_enabled = 1;
+#endif
+}
+
+static int __init futex_init(void)
+{
 	unsigned int futex_shift;
 	unsigned long i;
 
@@ -2893,18 +3055,8 @@ static int __init futex_init(void)
 					       &futex_shift, NULL,
 					       futex_hashsize, futex_hashsize);
 	futex_hashsize = 1UL << futex_shift;
-	/*
-	 * This will fail and we want it. Some arch implementations do
-	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
-	 * functionality. We want to know that before we call in any
-	 * of the complex code paths. Also we want to prevent
-	 * registration of robust lists in that case. NULL is
-	 * guaranteed to fault and we get -EFAULT on functional
-	 * implementation, the non-functional ones will return
-	 * -ENOSYS.
-	 */
-	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
-		futex_cmpxchg_enabled = 1;
+
+	futex_detect_cmpxchg();
 
 	for (i = 0; i < futex_hashsize; i++) {
 		atomic_set(&futex_queues[i].waiters, 0);
diff --git a/kernel/groups.c b/kernel/groups.c
index 90cf1c38c8ea..67b4ba30475f 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/user_namespace.h>
 #include <asm/uaccess.h>
 
 /* init to 2 - one for init_task, one to ensure it is never freed */
@@ -223,6 +224,14 @@ out:
 	return i;
 }
 
+bool may_setgroups(void)
+{
+	struct user_namespace *user_ns = current_user_ns();
+
+	return ns_capable(user_ns, CAP_SETGID) &&
+		userns_may_setgroups(user_ns);
+}
+
 /*
  *	SMP: Our groups are copy-on-write. We can set them safely
  *	without another task interfering.
@@ -233,7 +242,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!ns_capable(current_user_ns(), CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 09094361dce5..04d03745fb98 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -247,6 +247,11 @@ again:
 			goto again;
 		}
 		timer->base = new_base;
+	} else {
+		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+			cpu = this_cpu;
+			goto again;
+		}
 	}
 	return new_base;
 }
@@ -582,6 +587,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
 	cpu_base->expires_next.tv64 = expires_next.tv64;
 
+	/*
+	 * If a hang was detected in the last timer interrupt then we
+	 * leave the hang delay active in the hardware. We want the
+	 * system to make progress. That also prevents the following
+	 * scenario:
+	 * T1 expires 50ms from now
+	 * T2 expires 5s from now
+	 *
+	 * T1 is removed, so this code is called and would reprogram
+	 * the hardware to 5s from now. Any hrtimer_start after that
+	 * will not reprogram the hardware due to hang_detected being
+	 * set. So we'd effectivly block all timers until the T2 event
+	 * fires.
+	 */
+	if (cpu_base->hang_detected)
+		return;
+
 	if (cpu_base->expires_next.tv64 != KTIME_MAX)
 		tick_program_event(cpu_base->expires_next, 1);
 }
@@ -981,11 +1003,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	ret = remove_hrtimer(timer, base);
 
-	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
 	if (mode & HRTIMER_MODE_REL) {
-		tim = ktime_add_safe(tim, new_base->get_time());
+		tim = ktime_add_safe(tim, base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
 		 * to signal that they simply return xtime in
@@ -1000,6 +1019,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
+	/* Switch the timer base, if necessary: */
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d3bf660cb57f..ebb8a9e937fa 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -150,7 +150,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	int ret;
 
-	ret = chip->irq_set_affinity(data, mask, false);
+	ret = chip->irq_set_affinity(data, mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 		cpumask_copy(data->affinity, mask);
@@ -162,7 +162,8 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
-int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
+int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
+			    bool force)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	struct irq_desc *desc = irq_data_to_desc(data);
@@ -172,7 +173,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 		return -EINVAL;
 
 	if (irq_can_move_pcntxt(data)) {
-		ret = irq_do_set_affinity(data, mask, false);
+		ret = irq_do_set_affinity(data, mask, force);
 	} else {
 		irqd_set_move_pending(data);
 		irq_copy_pending(desc, mask);
@@ -187,13 +188,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 	return ret;
 }
 
-/**
- *	irq_set_affinity - Set the irq affinity of a given irq
- *	@irq:		Interrupt to set affinity
- *	@mask:		cpumask
- *
- */
-int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
+int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -203,7 +198,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret =  __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask);
+	ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return ret;
 }
@@ -861,8 +856,8 @@ static int irq_thread(void *data)
 		irq_thread_check_affinity(desc, action);
 
 		action_ret = handler_fn(desc, action);
-		if (!noirqdebug)
-			note_interrupt(action->irq, desc, action_ret);
+		if (action_ret == IRQ_HANDLED)
+			atomic_inc(&desc->threads_handled);
 
 		wake_threads_waitq(desc);
 	}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index a1d8cc63b56e..e2514b0e439e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -270,6 +270,8 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc,
 	return action && (action->flags & IRQF_IRQPOLL);
 }
 
+#define SPURIOUS_DEFERRED	0x80000000
+
 void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		    irqreturn_t action_ret)
 {
@@ -277,15 +279,111 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 	    irq_settings_is_polled(desc))
 		return;
 
-	/* we get here again via the threaded handler */
-	if (action_ret == IRQ_WAKE_THREAD)
-		return;
-
 	if (bad_action_ret(action_ret)) {
 		report_bad_irq(irq, desc, action_ret);
 		return;
 	}
 
+	/*
+	 * We cannot call note_interrupt from the threaded handler
+	 * because we need to look at the compound of all handlers
+	 * (primary and threaded). Aside of that in the threaded
+	 * shared case we have no serialization against an incoming
+	 * hardware interrupt while we are dealing with a threaded
+	 * result.
+	 *
+	 * So in case a thread is woken, we just note the fact and
+	 * defer the analysis to the next hardware interrupt.
+	 *
+	 * The threaded handlers store whether they sucessfully
+	 * handled an interrupt and we check whether that number
+	 * changed versus the last invocation.
+	 *
+	 * We could handle all interrupts with the delayed by one
+	 * mechanism, but for the non forced threaded case we'd just
+	 * add pointless overhead to the straight hardirq interrupts
+	 * for the sake of a few lines less code.
+	 */
+	if (action_ret & IRQ_WAKE_THREAD) {
+		/*
+		 * There is a thread woken. Check whether one of the
+		 * shared primary handlers returned IRQ_HANDLED. If
+		 * not we defer the spurious detection to the next
+		 * interrupt.
+		 */
+		if (action_ret == IRQ_WAKE_THREAD) {
+			int handled;
+			/*
+			 * We use bit 31 of thread_handled_last to
+			 * denote the deferred spurious detection
+			 * active. No locking necessary as
+			 * thread_handled_last is only accessed here
+			 * and we have the guarantee that hard
+			 * interrupts are not reentrant.
+			 */
+			if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) {
+				desc->threads_handled_last |= SPURIOUS_DEFERRED;
+				return;
+			}
+			/*
+			 * Check whether one of the threaded handlers
+			 * returned IRQ_HANDLED since the last
+			 * interrupt happened.
+			 *
+			 * For simplicity we just set bit 31, as it is
+			 * set in threads_handled_last as well. So we
+			 * avoid extra masking. And we really do not
+			 * care about the high bits of the handled
+			 * count. We just care about the count being
+			 * different than the one we saw before.
+			 */
+			handled = atomic_read(&desc->threads_handled);
+			handled |= SPURIOUS_DEFERRED;
+			if (handled != desc->threads_handled_last) {
+				action_ret = IRQ_HANDLED;
+				/*
+				 * Note: We keep the SPURIOUS_DEFERRED
+				 * bit set. We are handling the
+				 * previous invocation right now.
+				 * Keep it for the current one, so the
+				 * next hardware interrupt will
+				 * account for it.
+				 */
+				desc->threads_handled_last = handled;
+			} else {
+				/*
+				 * None of the threaded handlers felt
+				 * responsible for the last interrupt
+				 *
+				 * We keep the SPURIOUS_DEFERRED bit
+				 * set in threads_handled_last as we
+				 * need to account for the current
+				 * interrupt as well.
+				 */
+				action_ret = IRQ_NONE;
+			}
+		} else {
+			/*
+			 * One of the primary handlers returned
+			 * IRQ_HANDLED. So we don't care about the
+			 * threaded handlers on the same line. Clear
+			 * the deferred detection bit.
+			 *
+			 * In theory we could/should check whether the
+			 * deferred bit is set and take the result of
+			 * the previous run into account here as
+			 * well. But it's really not worth the
+			 * trouble. If every other interrupt is
+			 * handled we never trigger the spurious
+			 * detector. And if this is just the one out
+			 * of 100k unhandled ones which is handled
+			 * then we merily delay the spurious detection
+			 * by one hard interrupt. Not a real problem.
+			 */
+			desc->threads_handled_last &= ~SPURIOUS_DEFERRED;
+		}
+	}
+
 	if (unlikely(action_ret == IRQ_NONE)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index e30ac0fe61c3..0aa69ea1d8fd 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -44,11 +44,12 @@ static long kptr_obfuscate(long v, int type)
  */
 static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
 {
-	long ret;
+	long t1, t2;
 
-	ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+	t1 = kptr_obfuscate((long)v1, type);
+	t2 = kptr_obfuscate((long)v2, type);
 
-	return (ret < 0) | ((ret > 0) << 1);
+	return (t1 < t2) | ((t1 > t2) << 1);
 }
 
 /* The caller must have pinned the task */
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 60bafbed06ab..18ff0b91d6d2 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1682,6 +1682,14 @@ int kernel_kexec(void)
 		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
 		migrate_to_reboot_cpu();
+
+		/*
+		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
+		 * no further code needs to use CPU hotplug (which is true in
+		 * the reboot case). However, the kexec path depends on using
+		 * CPU hotplug again; so re-enable it here.
+		 */
+		cpu_hotplug_enable();
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
 	}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b5ae3ee860a9..f6249f9ab33e 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -262,7 +262,7 @@ static void create_kthread(struct kthread_create_info *create)
  * kthread_stop() has been called).  The return value should be zero
  * or a negative error number; it will be passed to kthread_stop().
  *
- * Returns a task_struct or ERR_PTR(-ENOMEM).
+ * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR).
  */
 struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 					   void *data, int node,
@@ -298,7 +298,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 		 * that thread.
 		 */
 		if (xchg(&create->done, NULL))
-			return ERR_PTR(-ENOMEM);
+			return ERR_PTR(-EINTR);
 		/*
 		 * kthreadd (or new kernel thread) will call complete()
 		 * shortly.
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 14193d596d78..ab29b6a22669 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -31,3 +31,8 @@ static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
 {
 	return (waiter != NULL);
 }
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2e960a2bab81..1ce0f6c6eb01 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -83,6 +83,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 		owner = *p;
 	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
 }
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	struct task_struct *owner = rt_mutex_owner(lock);
+
+	clear_rt_mutex_waiters(lock);
+	raw_spin_unlock(&lock->wait_lock);
+	/*
+	 * If a new waiter comes in between the unlock and the cmpxchg
+	 * we have two situations:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 * cmpxchg(p, owner, 0) == owner
+	 *					mark_rt_mutex_waiters(lock);
+	 *					acquire(lock);
+	 * or:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					mark_rt_mutex_waiters(lock);
+	 *
+	 * cmpxchg(p, owner, 0) != owner
+	 *					enqueue_waiter();
+	 *					unlock(wait_lock);
+	 * lock(wait_lock);
+	 * wake waiter();
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					acquire(lock);
+	 */
+	return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
 #else
 # define rt_mutex_cmpxchg(l,c,n)	(0)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -90,6 +131,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 	lock->owner = (struct task_struct *)
 			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
 }
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	lock->owner = NULL;
+	raw_spin_unlock(&lock->wait_lock);
+	return true;
+}
 #endif
 
 static inline int
@@ -248,27 +300,36 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
  */
 int max_lock_depth = 1024;
 
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
 /*
  * Adjust the priority chain. Also used for deadlock detection.
  * Decreases task's usage by one - may thus free the task.
  *
- * @task: the task owning the mutex (owner) for which a chain walk is probably
- *	  needed
+ * @task:	the task owning the mutex (owner) for which a chain walk is
+ *		probably needed
  * @deadlock_detect: do we have to carry out deadlock detection?
- * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck
- * 	       things for a task that has just got its priority adjusted, and
- *	       is waiting on a mutex)
+ * @orig_lock:	the mutex (can be NULL if we are walking the chain to recheck
+ *		things for a task that has just got its priority adjusted, and
+ *		is waiting on a mutex)
+ * @next_lock:	the mutex on which the owner of @orig_lock was blocked before
+ *		we dropped its pi_lock. Is never dereferenced, only used for
+ *		comparison to detect lock chain changes.
  * @orig_waiter: rt_mutex_waiter struct for the task that has just donated
- *		 its priority to the mutex owner (can be NULL in the case
- *		 depicted above or if the top waiter is gone away and we are
- *		 actually deboosting the owner)
- * @top_task: the current top waiter
+ *		its priority to the mutex owner (can be NULL in the case
+ *		depicted above or if the top waiter is gone away and we are
+ *		actually deboosting the owner)
+ * @top_task:	the current top waiter
  *
  * Returns 0 or -EDEADLK.
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 				      int deadlock_detect,
 				      struct rt_mutex *orig_lock,
+				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
@@ -302,7 +363,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		}
 		put_task_struct(task);
 
-		return deadlock_detect ? -EDEADLK : 0;
+		return -EDEADLK;
 	}
  retry:
 	/*
@@ -327,13 +388,32 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto out_unlock_pi;
 
 	/*
+	 * We dropped all locks after taking a refcount on @task, so
+	 * the task might have moved on in the lock chain or even left
+	 * the chain completely and blocks now on an unrelated lock or
+	 * on @orig_lock.
+	 *
+	 * We stored the lock on which @task was blocked in @next_lock,
+	 * so we can detect the chain change.
+	 */
+	if (next_lock != waiter->lock)
+		goto out_unlock_pi;
+
+	/*
 	 * Drop out, when the task has no waiters. Note,
 	 * top_waiter can be NULL, when we are in the deboosting
 	 * mode!
 	 */
-	if (top_waiter && (!task_has_pi_waiters(task) ||
-			   top_waiter != task_top_pi_waiter(task)))
-		goto out_unlock_pi;
+	if (top_waiter) {
+		if (!task_has_pi_waiters(task))
+			goto out_unlock_pi;
+		/*
+		 * If deadlock detection is off, we stop here if we
+		 * are not the top pi waiter of the task.
+		 */
+		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
+			goto out_unlock_pi;
+	}
 
 	/*
 	 * When deadlock detection is off then we check, if further
@@ -349,11 +429,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto retry;
 	}
 
-	/* Deadlock detection */
+	/*
+	 * Deadlock detection. If the lock is the same as the original
+	 * lock which caused us to walk the lock chain or if the
+	 * current lock is owned by the task which initiated the chain
+	 * walk, we detected a deadlock.
+	 */
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
 		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
-		ret = deadlock_detect ? -EDEADLK : 0;
+		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
@@ -398,11 +483,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		__rt_mutex_adjust_prio(task);
 	}
 
+	/*
+	 * Check whether the task which owns the current lock is pi
+	 * blocked itself. If yes we store a pointer to the lock for
+	 * the lock chain change detection above. After we dropped
+	 * task->pi_lock next_lock cannot be dereferenced anymore.
+	 */
+	next_lock = task_blocked_on_lock(task);
+
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	top_waiter = rt_mutex_top_waiter(lock);
 	raw_spin_unlock(&lock->wait_lock);
 
+	/*
+	 * We reached the end of the lock chain. Stop right here. No
+	 * point to go back just to figure that out.
+	 */
+	if (!next_lock)
+		goto out_put_task;
+
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -512,8 +612,21 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
-	unsigned long flags;
+	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
+	unsigned long flags;
+
+	/*
+	 * Early deadlock detection. We really don't want the task to
+	 * enqueue on itself just to untangle the mess later. It's not
+	 * only an optimization. We drop the locks, so another waiter
+	 * can come in before the chain walk detects the deadlock. So
+	 * the other will detect the deadlock and return -EDEADLOCK,
+	 * which is wrong, as the other waiter is not in a deadlock
+	 * situation.
+	 */
+	if (owner == task)
+		return -EDEADLK;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 	__rt_mutex_adjust_prio(task);
@@ -533,20 +646,28 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	if (!owner)
 		return 0;
 
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+	} else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
 		chain_walk = 1;
+	}
+
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
 
-	if (!chain_walk)
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	/*
+	 * Even if full deadlock detection is on, if the owner is not
+	 * blocked itself, we can avoid finding this out in the chain
+	 * walk.
+	 */
+	if (!chain_walk || !next_lock)
 		return 0;
 
 	/*
@@ -558,8 +679,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 task);
+	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -569,7 +690,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and wake it up.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * wake it up.
  *
  * Called with lock->wait_lock held.
  */
@@ -590,10 +712,23 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 */
 	rt_mutex_dequeue_pi(current, waiter);
 
-	rt_mutex_set_owner(lock, NULL);
+	/*
+	 * As we are waking up the top waiter, and the waiter stays
+	 * queued on the lock until it gets the lock, this lock
+	 * obviously has waiters. Just set the bit here and this has
+	 * the added benefit of forcing all new tasks into the
+	 * slow path making sure no task of lower priority than
+	 * the top waiter can steal this lock.
+	 */
+	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
+	/*
+	 * It's safe to dereference waiter as it cannot go away as
+	 * long as we hold lock->wait_lock. The waiter task needs to
+	 * acquire it in order to dequeue the waiter.
+	 */
 	wake_up_process(waiter->task);
 }
 
@@ -608,8 +743,8 @@ static void remove_waiter(struct rt_mutex *lock,
 {
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;
-	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	rt_mutex_dequeue(lock, waiter);
@@ -633,13 +768,13 @@ static void remove_waiter(struct rt_mutex *lock,
 		}
 		__rt_mutex_adjust_prio(owner);
 
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
+		/* Store the lock on which owner is blocked or NULL */
+		next_lock = task_blocked_on_lock(owner);
 
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
-	if (!chain_walk)
+	if (!next_lock)
 		return;
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
@@ -647,7 +782,7 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -660,6 +795,7 @@ static void remove_waiter(struct rt_mutex *lock,
 void rt_mutex_adjust_pi(struct task_struct *task)
 {
 	struct rt_mutex_waiter *waiter;
+	struct rt_mutex *next_lock;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -670,12 +806,13 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
-
+	next_lock = waiter->lock;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
-	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+
+	rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
 }
 
 /**
@@ -727,6 +864,26 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	return ret;
 }
 
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+				     struct rt_mutex_waiter *w)
+{
+	/*
+	 * If the result is not -EDEADLOCK or the caller requested
+	 * deadlock detection, nothing to do here.
+	 */
+	if (res != -EDEADLOCK || detect_deadlock)
+		return;
+
+	/*
+	 * Yell lowdly and stop the task right here.
+	 */
+	rt_mutex_print_deadlock(w);
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+}
+
 /*
  * Slow path lock function:
  */
@@ -766,8 +923,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(ret))
+	if (unlikely(ret)) {
 		remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+	}
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -823,12 +982,49 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
 
 	rt_mutex_deadlock_account_unlock(current);
 
-	if (!rt_mutex_has_waiters(lock)) {
-		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
-		return;
+	/*
+	 * We must be careful here if the fast path is enabled. If we
+	 * have no waiters queued we cannot set owner to NULL here
+	 * because of:
+	 *
+	 * foo->lock->owner = NULL;
+	 *			rtmutex_lock(foo->lock);   <- fast path
+	 *			free = atomic_dec_and_test(foo->refcnt);
+	 *			rtmutex_unlock(foo->lock); <- fast path
+	 *			if (free)
+	 *				kfree(foo);
+	 * raw_spin_unlock(foo->lock->wait_lock);
+	 *
+	 * So for the fastpath enabled kernel:
+	 *
+	 * Nothing can set the waiters bit as long as we hold
+	 * lock->wait_lock. So we do the following sequence:
+	 *
+	 *	owner = rt_mutex_owner(lock);
+	 *	clear_rt_mutex_waiters(lock);
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 *	if (cmpxchg(&lock->owner, owner, 0) == owner)
+	 *		return;
+	 *	goto retry;
+	 *
+	 * The fastpath disabled variant is simple as all access to
+	 * lock->owner is serialized by lock->wait_lock:
+	 *
+	 *	lock->owner = NULL;
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 */
+	while (!rt_mutex_has_waiters(lock)) {
+		/* Drops lock->wait_lock ! */
+		if (unlock_rt_mutex_safe(lock) == true)
+			return;
+		/* Relock the rtmutex and try again */
+		raw_spin_lock(&lock->wait_lock);
 	}
 
+	/*
+	 * The wakeup next waiter path does not suffer from the above
+	 * race. See the comments there.
+	 */
 	wakeup_next_waiter(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
@@ -1076,7 +1272,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		return 1;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index a1a1dd06421d..f6a1f3c133b1 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -24,3 +24,8 @@
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
 #define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	WARN(1, "rtmutex deadlock detected\n");
+}
diff --git a/kernel/module.c b/kernel/module.c
index d24fcf29cb64..1d679a6c942f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -815,9 +815,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
-	if (!(flags & O_NONBLOCK))
-		pr_warn("waiting module removal not supported: please upgrade\n");
-
 	if (mutex_lock_interruptible(&module_mutex) != 0)
 		return -EINTR;
 
@@ -1844,7 +1841,9 @@ static void free_module(struct module *mod)
 
 	/* We leave it in list to prevent duplicate loads, but make sure
 	 * that noone uses it while it's being deconstructed. */
+	mutex_lock(&module_mutex);
 	mod->state = MODULE_STATE_UNFORMED;
+	mutex_unlock(&module_mutex);
 
 	/* Remove dynamic debug info */
 	ddebug_remove_module(mod->name);
@@ -3265,6 +3264,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	dynamic_debug_setup(info->debug, info->num_debug);
 
+	/* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
+	ftrace_module_init(mod);
+
 	/* Finally it's fully formed, ready to start executing. */
 	err = complete_formation(mod, info);
 	if (err)
diff --git a/kernel/pid.c b/kernel/pid.c
index 9b9a26698144..82430c858d69 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -341,6 +341,8 @@ out:
 
 out_unlock:
 	spin_unlock_irq(&pidmap_lock);
+	put_pid_ns(ns);
+
 out_free:
 	while (++i <= ns->level)
 		free_pidmap(pid->numbers + i);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 06c62de9c711..db95d8eb761b 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -318,7 +318,9 @@ static void *pidns_get(struct task_struct *task)
 	struct pid_namespace *ns;
 
 	rcu_read_lock();
-	ns = get_pid_ns(task_active_pid_ns(task));
+	ns = task_active_pid_ns(task);
+	if (ns)
+		get_pid_ns(ns);
 	rcu_read_unlock();
 
 	return ns;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 424c2d4265c9..77e6b83c0431 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -634,6 +634,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 			goto out;
 		}
 	} else {
+		memset(&event.sigev_value, 0, sizeof(event.sigev_value));
 		event.sigev_notify = SIGEV_SIGNAL;
 		event.sigev_signo = SIGALRM;
 		event.sigev_value.sival_int = new_timer->it_id;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 2fac9cc79b3d..45aa98ee5a70 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -306,6 +306,10 @@ config PM_GENERIC_DOMAINS_RUNTIME
 	def_bool y
 	depends on PM_RUNTIME && PM_GENERIC_DOMAINS
 
+config PM_GENERIC_DOMAINS_OF
+	def_bool y
+	depends on PM_GENERIC_DOMAINS && OF && !ARCH_EXYNOS
+
 config CPU_PM
 	bool
 	depends on SUSPEND || CPU_IDLE
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 37170d4dd9a6..126586a31408 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -492,8 +492,14 @@ int hibernation_restore(int platform_mode)
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
-		dpm_resume_end(PMSG_RECOVER);
+		/*
+		 * The above should either succeed and jump to the new kernel,
+		 * or return with an error. Otherwise things are just
+		 * undefined, so let's be paranoid.
+		 */
+		BUG_ON(!error);
 	}
+	dpm_resume_end(PMSG_RECOVER);
 	pm_restore_gfp_mask();
 	ftrace_start();
 	resume_console();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 1d1bf630e6e9..3ae41cdd804a 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -293,12 +293,12 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 {
 	char *s = buf;
 #ifdef CONFIG_SUSPEND
-	int i;
+	suspend_state_t i;
+
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (pm_states[i].state)
+			s += sprintf(s,"%s ", pm_states[i].label);
 
-	for (i = 0; i < PM_SUSPEND_MAX; i++) {
-		if (pm_states[i] && valid_state(i))
-			s += sprintf(s,"%s ", pm_states[i]);
-	}
 #endif
 #ifdef CONFIG_HIBERNATION
 	s += sprintf(s, "%s\n", "disk");
@@ -314,7 +314,7 @@ static suspend_state_t decode_state(const char *buf, size_t n)
 {
 #ifdef CONFIG_SUSPEND
 	suspend_state_t state = PM_SUSPEND_MIN;
-	const char * const *s;
+	struct pm_sleep_state *s;
 #endif
 	char *p;
 	int len;
@@ -328,8 +328,9 @@ static suspend_state_t decode_state(const char *buf, size_t n)
 
 #ifdef CONFIG_SUSPEND
 	for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++)
-		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
-			return state;
+		if (s->state && len == strlen(s->label)
+		    && !strncmp(buf, s->label, len))
+			return s->state;
 #endif
 
 	return PM_SUSPEND_ON;
@@ -447,8 +448,8 @@ static ssize_t autosleep_show(struct kobject *kobj,
 
 #ifdef CONFIG_SUSPEND
 	if (state < PM_SUSPEND_MAX)
-		return sprintf(buf, "%s\n", valid_state(state) ?
-						pm_states[state] : "error");
+		return sprintf(buf, "%s\n", pm_states[state].state ?
+					pm_states[state].label : "error");
 #endif
 #ifdef CONFIG_HIBERNATION
 	return sprintf(buf, "disk\n");
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7d4b7ffb3c1d..f770cad3666c 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -175,17 +175,20 @@ extern void swsusp_show_speed(struct timeval *, struct timeval *,
 				unsigned int, char *);
 
 #ifdef CONFIG_SUSPEND
+struct pm_sleep_state {
+	const char *label;
+	suspend_state_t state;
+};
+
 /* kernel/power/suspend.c */
-extern const char *const pm_states[];
+extern struct pm_sleep_state pm_states[];
 
-extern bool valid_state(suspend_state_t state);
 extern int suspend_devices_and_enter(suspend_state_t state);
 #else /* !CONFIG_SUSPEND */
 static inline int suspend_devices_and_enter(suspend_state_t state)
 {
 	return -ENOSYS;
 }
-static inline bool valid_state(suspend_state_t state) { return false; }
 #endif /* !CONFIG_SUSPEND */
 
 #ifdef CONFIG_PM_TEST_SUSPEND
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 06ec8869dbf1..f1fe7ec110bb 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -107,6 +107,28 @@ static int try_to_freeze_tasks(bool user_only)
 	return todo ? -EBUSY : 0;
 }
 
+/*
+ * Returns true if all freezable tasks (except for current) are frozen already
+ */
+static bool check_frozen_processes(void)
+{
+	struct task_struct *g, *p;
+	bool ret = true;
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
+		if (p != current && !freezer_should_skip(p) &&
+		    !frozen(p)) {
+			ret = false;
+			goto done;
+		}
+	}
+done:
+	read_unlock(&tasklist_lock);
+
+	return ret;
+}
+
 /**
  * freeze_processes - Signal user space processes to enter the refrigerator.
  * The current thread will not be frozen.  The same process that calls
@@ -117,6 +139,7 @@ static int try_to_freeze_tasks(bool user_only)
 int freeze_processes(void)
 {
 	int error;
+	int oom_kills_saved;
 
 	error = __usermodehelper_disable(UMH_FREEZING);
 	if (error)
@@ -130,12 +153,27 @@ int freeze_processes(void)
 
 	printk("Freezing user space processes ... ");
 	pm_freezing = true;
+	oom_kills_saved = oom_kills_count();
 	error = try_to_freeze_tasks(true);
 	if (!error) {
-		printk("done.");
 		__usermodehelper_set_disable_depth(UMH_DISABLED);
 		oom_killer_disable();
+
+		/*
+		 * There might have been an OOM kill while we were
+		 * freezing tasks and the killed task might be still
+		 * on the way out so we have to double check for race.
+		 */
+		if (oom_kills_count() != oom_kills_saved &&
+				!check_frozen_processes()) {
+			__usermodehelper_set_disable_depth(UMH_ENABLED);
+			printk("OOM in progress.");
+			error = -EBUSY;
+			goto done;
+		}
+		printk("done.");
 	}
+done:
 	printk("\n");
 	BUG_ON(in_atomic());
 
@@ -184,6 +222,7 @@ void thaw_processes(void)
 
 	printk("Restarting tasks ... ");
 
+	__usermodehelper_set_disable_depth(UMH_FREEZING);
 	thaw_workqueues();
 
 	read_lock(&tasklist_lock);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 62ee437b5c7e..5455d5c3c149 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -29,10 +29,10 @@
 
 #include "power.h"
 
-const char *const pm_states[PM_SUSPEND_MAX] = {
-	[PM_SUSPEND_FREEZE]	= "freeze",
-	[PM_SUSPEND_STANDBY]	= "standby",
-	[PM_SUSPEND_MEM]	= "mem",
+struct pm_sleep_state pm_states[PM_SUSPEND_MAX] = {
+	[PM_SUSPEND_FREEZE] = { .label = "freeze", .state = PM_SUSPEND_FREEZE },
+	[PM_SUSPEND_STANDBY] = { .label = "standby", },
+	[PM_SUSPEND_MEM] = { .label = "mem", },
 };
 
 static const struct platform_suspend_ops *suspend_ops;
@@ -62,42 +62,34 @@ void freeze_wake(void)
 }
 EXPORT_SYMBOL_GPL(freeze_wake);
 
+static bool valid_state(suspend_state_t state)
+{
+	/*
+	 * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level
+	 * support and need to be valid to the low level
+	 * implementation, no valid callback implies that none are valid.
+	 */
+	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
+}
+
 /**
  * suspend_set_ops - Set the global suspend method table.
  * @ops: Suspend operations to use.
  */
 void suspend_set_ops(const struct platform_suspend_ops *ops)
 {
+	suspend_state_t i;
+
 	lock_system_sleep();
+
 	suspend_ops = ops;
+	for (i = PM_SUSPEND_STANDBY; i <= PM_SUSPEND_MEM; i++)
+		pm_states[i].state = valid_state(i) ? i : 0;
+
 	unlock_system_sleep();
 }
 EXPORT_SYMBOL_GPL(suspend_set_ops);
 
-bool valid_state(suspend_state_t state)
-{
-	if (state == PM_SUSPEND_FREEZE) {
-#ifdef CONFIG_PM_DEBUG
-		if (pm_test_level != TEST_NONE &&
-		    pm_test_level != TEST_FREEZER &&
-		    pm_test_level != TEST_DEVICES &&
-		    pm_test_level != TEST_PLATFORM) {
-			printk(KERN_WARNING "Unsupported pm_test mode for "
-					"freeze state, please choose "
-					"none/freezer/devices/platform.\n");
-			return false;
-		}
-#endif
-			return true;
-	}
-	/*
-	 * PM_SUSPEND_STANDBY and PM_SUSPEND_MEMORY states need lowlevel
-	 * support and need to be valid to the lowlevel
-	 * implementation, no valid callback implies that none are valid.
-	 */
-	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
-}
-
 /**
  * suspend_valid_only_mem - Generic memory-only valid callback.
  *
@@ -324,9 +316,17 @@ static int enter_state(suspend_state_t state)
 {
 	int error;
 
-	if (!valid_state(state))
-		return -ENODEV;
-
+	if (state == PM_SUSPEND_FREEZE) {
+#ifdef CONFIG_PM_DEBUG
+		if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
+			pr_warning("PM: Unsupported test mode for freeze state,"
+				   "please choose none/freezer/devices/platform.\n");
+			return -EAGAIN;
+		}
+#endif
+	} else if (!valid_state(state)) {
+		return -EINVAL;
+	}
 	if (!mutex_trylock(&pm_mutex))
 		return -EBUSY;
 
@@ -337,7 +337,7 @@ static int enter_state(suspend_state_t state)
 	sys_sync();
 	printk("done.\n");
 
-	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label);
 	error = suspend_prepare(state);
 	if (error)
 		goto Unlock;
@@ -345,7 +345,7 @@ static int enter_state(suspend_state_t state)
 	if (suspend_test(TEST_FREEZER))
 		goto Finish;
 
-	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	pr_debug("PM: Entering %s sleep\n", pm_states[state].label);
 	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
 	pm_restore_gfp_mask();
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 9b2a1d58558d..269b097e78ea 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -92,13 +92,13 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 	}
 
 	if (state == PM_SUSPEND_MEM) {
-		printk(info_test, pm_states[state]);
+		printk(info_test, pm_states[state].label);
 		status = pm_suspend(state);
 		if (status == -ENODEV)
 			state = PM_SUSPEND_STANDBY;
 	}
 	if (state == PM_SUSPEND_STANDBY) {
-		printk(info_test, pm_states[state]);
+		printk(info_test, pm_states[state].label);
 		status = pm_suspend(state);
 	}
 	if (status < 0)
@@ -136,18 +136,16 @@ static char warn_bad_state[] __initdata =
 
 static int __init setup_test_suspend(char *value)
 {
-	unsigned i;
+	suspend_state_t i;
 
 	/* "=mem" ==> "mem" */
 	value++;
-	for (i = 0; i < PM_SUSPEND_MAX; i++) {
-		if (!pm_states[i])
-			continue;
-		if (strcmp(pm_states[i], value) != 0)
-			continue;
-		test_state = (__force suspend_state_t) i;
-		return 0;
-	}
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (!strcmp(pm_states[i].label, value)) {
+			test_state = pm_states[i].state;
+			return 0;
+		}
+
 	printk(warn_bad_state, value);
 	return 0;
 }
@@ -164,8 +162,8 @@ static int __init test_suspend(void)
 	/* PM is initialized by now; is that state testable? */
 	if (test_state == PM_SUSPEND_ON)
 		goto done;
-	if (!valid_state(test_state)) {
-		printk(warn_bad_state, pm_states[test_state]);
+	if (!pm_states[test_state].state) {
+		printk(warn_bad_state, pm_states[test_state].label);
 		goto done;
 	}
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 4dae9cbe9259..8c086e6049b9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2468,7 +2468,7 @@ void wake_up_klogd(void)
 	preempt_enable();
 }
 
-int printk_sched(const char *fmt, ...)
+int printk_deferred(const char *fmt, ...)
 {
 	unsigned long flags;
 	va_list args;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b3d116cd072d..6705d947ef14 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1228,6 +1228,22 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 }
 
 /*
+ * Awaken the grace-period kthread for the specified flavor of RCU.
+ * Don't do a self-awaken, and don't bother awakening when there is
+ * nothing for the grace-period kthread to do (as in several CPUs
+ * raced to awaken, and we lost), and finally don't try to awaken
+ * a kthread that has not yet been created.
+ */
+static void rcu_gp_kthread_wake(struct rcu_state *rsp)
+{
+	if (current == rsp->gp_kthread ||
+	    !ACCESS_ONCE(rsp->gp_flags) ||
+	    !rsp->gp_kthread)
+		return;
+	wake_up(&rsp->gp_wq);
+}
+
+/*
  * If there is room, assign a ->completed number to any callbacks on
  * this CPU that have not already been assigned.  Also accelerate any
  * callbacks that were previously assigned a ->completed number that has
@@ -1670,7 +1686,7 @@ static void rsp_wakeup(struct irq_work *work)
 	struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work);
 
 	/* Wake up rcu_gp_kthread() to start the grace period. */
-	wake_up(&rsp->gp_wq);
+	rcu_gp_kthread_wake(rsp);
 }
 
 /*
@@ -1746,7 +1762,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
-	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
+	rcu_gp_kthread_wake(rsp);
 }
 
 /*
@@ -2322,7 +2338,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	}
 	rsp->gp_flags |= RCU_GP_FLAG_FQS;
 	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
-	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
+	rcu_gp_kthread_wake(rsp);
 }
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f5c6635b806c..9a3f3c4e1f5a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1322,7 +1322,7 @@ out:
 		 * leave kernel.
 		 */
 		if (p->mm && printk_ratelimit()) {
-			printk_sched("process %d (%s) no longer affine to cpu%d\n",
+			printk_deferred("process %d (%s) no longer affine to cpu%d\n",
 					task_pid_nr(p), p->comm, cpu);
 		}
 	}
@@ -1895,6 +1895,8 @@ unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_SMP
 inline struct dl_bw *dl_bw_of(int i)
 {
+	rcu_lockdep_assert(rcu_read_lock_sched_held(),
+			   "sched RCU must be held");
 	return &cpu_rq(i)->rd->dl_bw;
 }
 
@@ -1903,6 +1905,8 @@ static inline int dl_bw_cpus(int i)
 	struct root_domain *rd = cpu_rq(i)->rd;
 	int cpus = 0;
 
+	rcu_lockdep_assert(rcu_read_lock_sched_held(),
+			   "sched RCU must be held");
 	for_each_cpu_and(i, rd->span, cpu_active_mask)
 		cpus++;
 
@@ -3242,17 +3246,40 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
  * greater than deadline. Furthermore, we have to be sure that
- * user parameters are above the internal resolution (1us); we
- * check sched_runtime only since it is always the smaller one.
+ * user parameters are above the internal resolution of 1us (we
+ * check sched_runtime only since it is always the smaller one) and
+ * below 2^63 ns (we have to check both sched_deadline and
+ * sched_period, as the latter can be zero).
  */
 static bool
 __checkparam_dl(const struct sched_attr *attr)
 {
-	return attr && attr->sched_deadline != 0 &&
-		(attr->sched_period == 0 ||
-		(s64)(attr->sched_period   - attr->sched_deadline) >= 0) &&
-		(s64)(attr->sched_deadline - attr->sched_runtime ) >= 0  &&
-		attr->sched_runtime >= (2 << (DL_SCALE - 1));
+	/* deadline != 0 */
+	if (attr->sched_deadline == 0)
+		return false;
+
+	/*
+	 * Since we truncate DL_SCALE bits, make sure we're at least
+	 * that big.
+	 */
+	if (attr->sched_runtime < (1ULL << DL_SCALE))
+		return false;
+
+	/*
+	 * Since we use the MSB for wrap-around and sign issues, make
+	 * sure it's not set (mind that period can be equal to zero).
+	 */
+	if (attr->sched_deadline & (1ULL << 63) ||
+	    attr->sched_period & (1ULL << 63))
+		return false;
+
+	/* runtime <= deadline <= period (if period != 0) */
+	if ((attr->sched_period != 0 &&
+	     attr->sched_period < attr->sched_deadline) ||
+	    attr->sched_deadline < attr->sched_runtime)
+		return false;
+
+	return true;
 }
 
 /*
@@ -3488,9 +3515,10 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
 	};
 
 	/*
-	 * Fixup the legacy SCHED_RESET_ON_FORK hack
+	 * Fixup the legacy SCHED_RESET_ON_FORK hack, except if
+	 * the policy=-1 was passed by sched_setparam().
 	 */
-	if (policy & SCHED_RESET_ON_FORK) {
+	if ((policy != -1) && (policy & SCHED_RESET_ON_FORK)) {
 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
 		policy &= ~SCHED_RESET_ON_FORK;
 		attr.sched_policy = policy;
@@ -3680,8 +3708,12 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	if (!uattr || pid < 0 || flags)
 		return -EINVAL;
 
-	if (sched_copy_attr(uattr, &attr))
-		return -EFAULT;
+	retval = sched_copy_attr(uattr, &attr);
+	if (retval)
+		return retval;
+
+	if ((int)attr.sched_policy < 0)
+		return -EINVAL;
 
 	rcu_read_lock();
 	retval = -ESRCH;
@@ -3731,7 +3763,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
  */
 SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 {
-	struct sched_param lp;
+	struct sched_param lp = { .sched_priority = 0 };
 	struct task_struct *p;
 	int retval;
 
@@ -3748,11 +3780,8 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	if (retval)
 		goto out_unlock;
 
-	if (task_has_dl_policy(p)) {
-		retval = -EINVAL;
-		goto out_unlock;
-	}
-	lp.sched_priority = p->rt_priority;
+	if (task_has_rt_policy(p))
+		lp.sched_priority = p->rt_priority;
 	rcu_read_unlock();
 
 	/*
@@ -3912,13 +3941,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	 * root_domain.
 	 */
 #ifdef CONFIG_SMP
-	if (task_has_dl_policy(p)) {
-		const struct cpumask *span = task_rq(p)->rd->span;
-
-		if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
+	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
+		rcu_read_lock();
+		if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
 			retval = -EBUSY;
+			rcu_read_unlock();
 			goto out_unlock;
 		}
+		rcu_read_unlock();
 	}
 #endif
 again:
@@ -5051,7 +5081,6 @@ static int sched_cpu_active(struct notifier_block *nfb,
 				      unsigned long action, void *hcpu)
 {
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
 	case CPU_DOWN_FAILED:
 		set_cpu_active((long)hcpu, true);
 		return NOTIFY_OK;
@@ -7434,6 +7463,8 @@ static int sched_dl_global_constraints(void)
 	int cpu, ret = 0;
 	unsigned long flags;
 
+	rcu_read_lock();
+
 	/*
 	 * Here we want to check the bandwidth not being set to some
 	 * value smaller than the currently allocated bandwidth in
@@ -7455,6 +7486,8 @@ static int sched_dl_global_constraints(void)
 			break;
 	}
 
+	rcu_read_unlock();
+
 	return ret;
 }
 
@@ -7470,6 +7503,7 @@ static void sched_dl_do_global(void)
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
+	rcu_read_lock();
 	/*
 	 * FIXME: As above...
 	 */
@@ -7480,6 +7514,7 @@ static void sched_dl_do_global(void)
 		dl_b->bw = new_bw;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	}
+	rcu_read_unlock();
 }
 
 static int sched_rt_global_validate(void)
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b9bb42b2d47..ab001b5d5048 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -210,7 +210,5 @@ int cpudl_init(struct cpudl *cp)
  */
 void cpudl_cleanup(struct cpudl *cp)
 {
-	/*
-	 * nothing to do for the moment
-	 */
+	free_cpumask_var(cp->free_cpus);
 }
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 8b836b376d91..3031bac8aa3e 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -70,8 +70,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 	int idx = 0;
 	int task_pri = convert_prio(p->prio);
 
-	if (task_pri >= MAX_RT_PRIO)
-		return 0;
+	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
 		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 99947919e30b..cfe2f268afaa 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -326,50 +326,50 @@ out:
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq)
+					 struct rq *rq, int ticks)
 {
-	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+	u64 cputime = (__force u64) cputime_one_jiffy;
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
 	if (steal_account_process_tick())
 		return;
 
+	cputime *= ticks;
+	scaled *= ticks;
+
 	if (irqtime_account_hi_update()) {
-		cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_IRQ] += cputime;
 	} else if (irqtime_account_si_update()) {
-		cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_SOFTIRQ] += cputime;
 	} else if (this_cpu_ksoftirqd() == p) {
 		/*
 		 * ksoftirqd time do not get accounted in cpu_softirq_time.
 		 * So, we have to handle it separately here.
 		 * Also, p->stime needs to be updated for ksoftirqd.
 		 */
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SOFTIRQ);
+		__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
-		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_user_time(p, cputime, scaled);
 	} else if (p == rq->idle) {
-		account_idle_time(cputime_one_jiffy);
+		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
-		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_guest_time(p, cputime, scaled);
 	} else {
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SYSTEM);
+		__account_system_time(p, cputime, scaled,	CPUTIME_SYSTEM);
 	}
 }
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	int i;
 	struct rq *rq = this_rq();
 
-	for (i = 0; i < ticks; i++)
-		irqtime_account_process_tick(current, 0, rq);
+	irqtime_account_process_tick(current, 0, rq, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) {}
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq) {}
+						struct rq *rq, int nr_ticks) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
@@ -458,7 +458,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 
 	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq);
+		irqtime_account_process_tick(p, user_tick, rq, 1);
 		return;
 	}
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6e79b3faa4cd..8d3c5ddfdfdd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -329,7 +329,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 
 		if (!lag_once) {
 			lag_once = true;
-			printk_sched("sched: DL replenish lagged to much\n");
+			printk_deferred("sched: DL replenish lagged to much\n");
 		}
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
@@ -490,9 +490,17 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 						     struct sched_dl_entity,
 						     dl_timer);
 	struct task_struct *p = dl_task_of(dl_se);
-	struct rq *rq = task_rq(p);
+	struct rq *rq;
+again:
+	rq = task_rq(p);
 	raw_spin_lock(&rq->lock);
 
+	if (rq != task_rq(p)) {
+		/* Task was moved, retrying. */
+		raw_spin_unlock(&rq->lock);
+		goto again;
+	}
+
 	/*
 	 * We need to take care of a possible races here. In fact, the
 	 * task might have changed its scheduling policy to something
@@ -542,24 +550,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 static
 int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 {
-	int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
-	int rorun = dl_se->runtime <= 0;
-
-	if (!rorun && !dmiss)
-		return 0;
-
-	/*
-	 * If we are beyond our current deadline and we are still
-	 * executing, then we have already used some of the runtime of
-	 * the next instance. Thus, if we do not account that, we are
-	 * stealing bandwidth from the system at each deadline miss!
-	 */
-	if (dmiss) {
-		dl_se->runtime = rorun ? dl_se->runtime : 0;
-		dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
-	}
-
-	return 1;
+	return (dl_se->runtime <= 0);
 }
 
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
@@ -798,10 +789,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
-		replenish_dl_entity(dl_se, pi_se);
-	else
+	if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
 		update_dl_entity(dl_se, pi_se);
+	else if (flags & ENQUEUE_REPLENISH)
+		replenish_dl_entity(dl_se, pi_se);
 
 	__enqueue_dl_entity(dl_se);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index dd52e7ffb10e..183e8e5c38ba 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -608,7 +608,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
-			do_div(avg_atom, nr_switches);
+			avg_atom = div64_ul(avg_atom, nr_switches);
 		else
 			avg_atom = -1LL;
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1999021042c7..27b8e836307f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -837,7 +837,7 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 
 			if (!once) {
 				once = true;
-				printk_sched("sched: RT throttling activated\n");
+				printk_deferred("sched: RT throttling activated\n");
 			}
 		} else {
 			/*
diff --git a/kernel/smp.c b/kernel/smp.c
index ffee35bef179..ff87d4479558 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -617,7 +617,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 			if (cond_func(cpu, info)) {
 				ret = smp_call_function_single(cpu, func,
 								info, wait);
-				WARN_ON_ONCE(!ret);
+				WARN_ON_ONCE(ret);
 			}
 		preempt_enable();
 	}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 49e13e1f8fe6..c1b26e176aa6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -139,11 +139,15 @@ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
-static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
 
+/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
+#ifdef CONFIG_DETECT_HUNG_TASK
+static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
+#endif
+
 #ifdef CONFIG_INOTIFY_USER
 #include <linux/inotify.h>
 #endif
@@ -995,6 +999,7 @@ static struct ctl_table kern_table[] = {
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
 		.proc_handler	= proc_dohung_task_timeout_secs,
+		.extra2		= &hung_task_timeout_max,
 	},
 	{
 		.procname	= "hung_task_warnings",
@@ -1318,7 +1323,7 @@ static struct ctl_table vm_table[] = {
 		.maxlen		= sizeof(percpu_pagelist_fraction),
 		.mode		= 0644,
 		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
-		.extra1		= &min_percpu_pagelist_fract,
+		.extra1		= &zero,
 	},
 #ifdef CONFIG_MMU
 	{
diff --git a/kernel/time.c b/kernel/time.c
index 7c7964c33ae7..3c49ab45f822 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -496,17 +496,20 @@ EXPORT_SYMBOL(usecs_to_jiffies);
  * that a remainder subtract here would not do the right thing as the
  * resolution values don't fall on second boundries.  I.e. the line:
  * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
  *
  * Rather, we just shift the bits off the right.
  *
  * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
  * value to a scaled second value.
  */
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
 {
-	unsigned long sec = value->tv_sec;
-	long nsec = value->tv_nsec + TICK_NSEC - 1;
+	nsec = nsec + TICK_NSEC - 1;
 
 	if (sec >= MAX_SEC_IN_JIFFIES){
 		sec = MAX_SEC_IN_JIFFIES;
@@ -517,6 +520,13 @@ timespec_to_jiffies(const struct timespec *value)
 		 (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
 
 }
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+	return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
 EXPORT_SYMBOL(timespec_to_jiffies);
 
 void
@@ -533,31 +543,27 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
 }
 EXPORT_SYMBOL(jiffies_to_timespec);
 
-/* Same for "timeval"
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
  *
- * Well, almost.  The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part.  Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
  */
 unsigned long
 timeval_to_jiffies(const struct timeval *value)
 {
-	unsigned long sec = value->tv_sec;
-	long usec = value->tv_usec;
-
-	if (sec >= MAX_SEC_IN_JIFFIES){
-		sec = MAX_SEC_IN_JIFFIES;
-		usec = 0;
-	}
-	return (((u64)sec * SEC_CONVERSION) +
-		(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
-		 (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+	return __timespec_to_jiffies(value->tv_sec,
+				     value->tv_usec * NSEC_PER_USEC);
 }
 EXPORT_SYMBOL(timeval_to_jiffies);
 
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 88c9c65a430d..cd45a0727a16 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -464,18 +464,26 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid)
 static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 							ktime_t now)
 {
+	unsigned long flags;
 	struct k_itimer *ptr = container_of(alarm, struct k_itimer,
 						it.alarm.alarmtimer);
-	if (posix_timer_event(ptr, 0) != 0)
-		ptr->it_overrun++;
+	enum alarmtimer_restart result = ALARMTIMER_NORESTART;
+
+	spin_lock_irqsave(&ptr->it_lock, flags);
+	if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) {
+		if (posix_timer_event(ptr, 0) != 0)
+			ptr->it_overrun++;
+	}
 
 	/* Re-add periodic timers */
 	if (ptr->it.alarm.interval.tv64) {
 		ptr->it_overrun += alarm_forward(alarm, now,
 						ptr->it.alarm.interval);
-		return ALARMTIMER_RESTART;
+		result = ALARMTIMER_RESTART;
 	}
-	return ALARMTIMER_NORESTART;
+	spin_unlock_irqrestore(&ptr->it_lock, flags);
+
+	return result;
 }
 
 /**
@@ -541,18 +549,22 @@ static int alarm_timer_create(struct k_itimer *new_timer)
  * @new_timer: k_itimer pointer
  * @cur_setting: itimerspec data to fill
  *
- * Copies the itimerspec data out from the k_itimer
+ * Copies out the current itimerspec data
  */
 static void alarm_timer_get(struct k_itimer *timr,
 				struct itimerspec *cur_setting)
 {
-	memset(cur_setting, 0, sizeof(struct itimerspec));
+	ktime_t relative_expiry_time =
+		alarm_expires_remaining(&(timr->it.alarm.alarmtimer));
 
-	cur_setting->it_interval =
-			ktime_to_timespec(timr->it.alarm.interval);
-	cur_setting->it_value =
-		ktime_to_timespec(timr->it.alarm.alarmtimer.node.expires);
-	return;
+	if (ktime_to_ns(relative_expiry_time) > 0) {
+		cur_setting->it_value = ktime_to_timespec(relative_expiry_time);
+	} else {
+		cur_setting->it_value.tv_sec = 0;
+		cur_setting->it_value.tv_nsec = 0;
+	}
+
+	cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval);
 }
 
 /**
@@ -585,9 +597,14 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 				struct itimerspec *new_setting,
 				struct itimerspec *old_setting)
 {
+	ktime_t exp;
+
 	if (!rtcdev)
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (old_setting)
 		alarm_timer_get(timr, old_setting);
 
@@ -597,8 +614,16 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 
 	/* start the timer */
 	timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
-	alarm_start(&timr->it.alarm.alarmtimer,
-			timespec_to_ktime(new_setting->it_value));
+	exp = timespec_to_ktime(new_setting->it_value);
+	/* Convert (if necessary) to absolute time */
+	if (flags != TIMER_ABSTIME) {
+		ktime_t now;
+
+		now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
+		exp = ktime_add(now, exp);
+	}
+
+	alarm_start(&timr->it.alarm.alarmtimer, exp);
 	return 0;
 }
 
@@ -730,6 +755,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	if (!alarmtimer_get_rtcdev())
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (!capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 086ad6043bcb..60ba1af801c3 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -146,7 +146,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 {
 	/* Nothing to do if we already reached the limit */
 	if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
-		printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n");
+		printk_deferred(KERN_WARNING
+				"CE: Reprogramming failure. Giving up\n");
 		dev->next_event.tv64 = KTIME_MAX;
 		return -ETIME;
 	}
@@ -159,9 +160,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
 		dev->min_delta_ns = MIN_DELTA_LIMIT;
 
-	printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
-	       dev->name ? dev->name : "?",
-	       (unsigned long long) dev->min_delta_ns);
+	printk_deferred(KERN_WARNING
+			"CE: %s increased min_delta_ns to %llu nsec\n",
+			dev->name ? dev->name : "?",
+			(unsigned long long) dev->min_delta_ns);
 	return 0;
 }
 
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 4d23dc4d8139..313a662911b1 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -204,7 +204,8 @@ void __init sched_clock_postinit(void)
 
 static int sched_clock_suspend(void)
 {
-	sched_clock_poll(&sched_clock_timer);
+	update_sched_clock();
+	hrtimer_cancel(&sched_clock_timer);
 	cd.suspended = true;
 	return 0;
 }
@@ -212,6 +213,7 @@ static int sched_clock_suspend(void)
 static void sched_clock_resume(void)
 {
 	cd.epoch_cyc = read_sched_clock();
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
 	cd.suspended = false;
 }
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 20b2fe37d105..0de9d7f5045c 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -276,7 +276,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
 bool tick_check_replacement(struct clock_event_device *curdev,
 			    struct clock_event_device *newdev)
 {
-	if (tick_check_percpu(curdev, newdev, smp_processor_id()))
+	if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
 		return false;
 
 	return tick_check_preferred(curdev, newdev);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 9f8af69c67ec..6558b7ac112d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -84,6 +84,9 @@ static void tick_do_update_jiffies64(ktime_t now)
 
 		/* Keep the tick_next_period variable up to date */
 		tick_next_period = ktime_add(last_jiffies_update, tick_period);
+	} else {
+		write_sequnlock(&jiffies_lock);
+		return;
 	}
 	write_sequnlock(&jiffies_lock);
 	update_wall_time();
@@ -967,7 +970,7 @@ static void tick_nohz_switch_to_nohz(void)
 	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t next;
 
-	if (!tick_nohz_active)
+	if (!tick_nohz_enabled)
 		return;
 
 	local_irq_disable();
diff --git a/kernel/timer.c b/kernel/timer.c
index accfd241b9e5..38f0d40fca13 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -822,7 +822,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 
 	bit = find_last_bit(&mask, BITS_PER_LONG);
 
-	mask = (1 << bit) - 1;
+	mask = (1UL << bit) - 1;
 
 	expires_limit = expires_limit & ~(mask);
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b418cb0d7242..4f3a3c03eadb 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -702,6 +702,7 @@ void blk_trace_shutdown(struct request_queue *q)
  * blk_add_trace_rq - Add a trace for a request oriented action
  * @q:		queue the io is for
  * @rq:		the source request
+ * @nr_bytes:	number of completed bytes
  * @what:	the action
  *
  * Description:
@@ -709,7 +710,7 @@ void blk_trace_shutdown(struct request_queue *q)
  *
  **/
 static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-			     u32 what)
+			     unsigned int nr_bytes, u32 what)
 {
 	struct blk_trace *bt = q->blk_trace;
 
@@ -718,11 +719,11 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+		__blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
 				what, rq->errors, rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
 				rq->cmd_flags, what, rq->errors, 0, NULL);
 	}
 }
@@ -730,33 +731,34 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 static void blk_add_trace_rq_abort(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
 }
 
 static void blk_add_trace_rq_insert(void *ignore,
 				    struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
 }
 
 static void blk_add_trace_rq_issue(void *ignore,
 				   struct request_queue *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
 }
 
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+	blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
 }
 
 static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
-				      struct request *rq)
+				      struct request *rq,
+				      unsigned int nr_bytes)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+	blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
 }
 
 /**
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index cd7f76d1eb86..e3be87edde33 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -331,12 +331,12 @@ static void update_ftrace_function(void)
 		func = ftrace_ops_list_func;
 	}
 
+	update_function_graph_func();
+
 	/* If there's no change, then do nothing more here */
 	if (ftrace_trace_function == func)
 		return;
 
-	update_function_graph_func();
-
 	/*
 	 * If we are using the list function, it doesn't care
 	 * about the function_trace_ops.
@@ -4315,16 +4315,11 @@ static void ftrace_init_module(struct module *mod,
 	ftrace_process_locs(mod, start, end);
 }
 
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
+void ftrace_module_init(struct module *mod)
 {
-	struct module *mod = data;
-
-	if (val == MODULE_STATE_COMING)
-		ftrace_init_module(mod, mod->ftrace_callsites,
-				   mod->ftrace_callsites +
-				   mod->num_ftrace_callsites);
-	return 0;
+	ftrace_init_module(mod, mod->ftrace_callsites,
+			   mod->ftrace_callsites +
+			   mod->num_ftrace_callsites);
 }
 
 static int ftrace_module_notify_exit(struct notifier_block *self,
@@ -4338,11 +4333,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 	return 0;
 }
 #else
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
-{
-	return 0;
-}
 static int ftrace_module_notify_exit(struct notifier_block *self,
 				     unsigned long val, void *data)
 {
@@ -4350,11 +4340,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_enter_nb = {
-	.notifier_call = ftrace_module_notify_enter,
-	.priority = INT_MAX,	/* Run before anything that can use kprobes */
-};
-
 struct notifier_block ftrace_module_exit_nb = {
 	.notifier_call = ftrace_module_notify_exit,
 	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
@@ -4391,10 +4376,6 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_enter_nb);
-	if (ret)
-		pr_warning("Failed to register trace ftrace module enter notifier\n");
-
 	ret = register_module_notifier(&ftrace_module_exit_nb);
 	if (ret)
 		pr_warning("Failed to register trace ftrace module exit notifier\n");
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index fc4da2d97f9b..774a0807fe81 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -543,7 +543,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
  * as data is added to any of the @buffer's cpu buffers. Otherwise
  * it will wait for data to be added to a specific cpu buffer.
  */
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
@@ -557,6 +557,8 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			return -ENODEV;
 		cpu_buffer = buffer->buffers[cpu];
 		work = &cpu_buffer->irq_work;
 	}
@@ -591,6 +593,7 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 		schedule();
 
 	finish_wait(&work->waiters, &wait);
+	return 0;
 }
 
 /**
@@ -613,10 +616,6 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct rb_irq_work *work;
 
-	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
-	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
-		return POLLIN | POLLRDNORM;
-
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
@@ -627,8 +626,22 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 		work = &cpu_buffer->irq_work;
 	}
 
-	work->waiters_pending = true;
 	poll_wait(filp, &work->waiters, poll_table);
+	work->waiters_pending = true;
+	/*
+	 * There's a tight race between setting the waiters_pending and
+	 * checking if the ring buffer is empty.  Once the waiters_pending bit
+	 * is set, the next event will wake the task up, but we can get stuck
+	 * if there's only a single event in.
+	 *
+	 * FIXME: Ideally, we need a memory barrier on the writer side as well,
+	 * but adding a memory barrier to all events will cause too much of a
+	 * performance hit in the fast path.  We only need a memory barrier when
+	 * the buffer goes from empty to having content.  But as this race is
+	 * extremely small, and it's not a problem if another event comes in, we
+	 * will fix it later.
+	 */
+	smp_mb();
 
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
@@ -1982,7 +1995,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
 
 /**
  * rb_update_event - update event type and data
- * @event: the even to update
+ * @event: the event to update
  * @type: the type of event
  * @length: the size of the event field in the ring buffer
  *
@@ -3355,21 +3368,16 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
 	/* Iterator usage is expected to have record disabled */
-	if (list_empty(&cpu_buffer->reader_page->list)) {
-		iter->head_page = rb_set_head_page(cpu_buffer);
-		if (unlikely(!iter->head_page))
-			return;
-		iter->head = iter->head_page->read;
-	} else {
-		iter->head_page = cpu_buffer->reader_page;
-		iter->head = cpu_buffer->reader_page->read;
-	}
+	iter->head_page = cpu_buffer->reader_page;
+	iter->head = cpu_buffer->reader_page->read;
+
+	iter->cache_reader_page = iter->head_page;
+	iter->cache_read = cpu_buffer->read;
+
 	if (iter->head)
 		iter->read_stamp = cpu_buffer->read_stamp;
 	else
 		iter->read_stamp = iter->head_page->page->time_stamp;
-	iter->cache_reader_page = cpu_buffer->reader_page;
-	iter->cache_read = cpu_buffer->read;
 }
 
 /**
@@ -3762,12 +3770,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 		return NULL;
 
 	/*
-	 * We repeat when a time extend is encountered.
-	 * Since the time extend is always attached to a data event,
-	 * we should never loop more than once.
-	 * (We never hit the following condition more than twice).
+	 * We repeat when a time extend is encountered or we hit
+	 * the end of the page. Since the time extend is always attached
+	 * to a data event, we should never loop more than three times.
+	 * Once for going to next page, once on time extend, and
+	 * finally once to get the event.
+	 * (We never hit the following condition more than thrice).
 	 */
-	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3))
 		return NULL;
 
 	if (rb_per_cpu_empty(cpu_buffer))
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 24c1f2382557..71136720ffa1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -454,6 +454,12 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	struct print_entry *entry;
 	unsigned long irq_flags;
 	int alloc;
+	int pc;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -463,7 +469,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -480,6 +486,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 		entry->buf[size] = '\0';
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return size;
 }
@@ -497,6 +504,12 @@ int __trace_bputs(unsigned long ip, const char *str)
 	struct bputs_entry *entry;
 	unsigned long irq_flags;
 	int size = sizeof(struct bputs_entry);
+	int pc;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -504,7 +517,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -513,6 +526,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	entry->str			= str;
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return 1;
 }
@@ -797,7 +811,7 @@ static struct {
 	{ trace_clock_local,	"local",	1 },
 	{ trace_clock_global,	"global",	1 },
 	{ trace_clock_counter,	"counter",	0 },
-	{ trace_clock_jiffies,	"uptime",	1 },
+	{ trace_clock_jiffies,	"uptime",	0 },
 	{ trace_clock,		"perf",		1 },
 	ARCH_TRACE_CLOCKS
 };
@@ -1091,13 +1105,13 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static void default_wait_pipe(struct trace_iterator *iter)
+static int default_wait_pipe(struct trace_iterator *iter)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
-		return;
+		return 0;
 
-	ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+	return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
 }
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1355,7 +1369,6 @@ void tracing_start(void)
 
 	arch_spin_unlock(&ftrace_max_lock);
 
-	ftrace_start();
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
 }
@@ -1402,7 +1415,6 @@ void tracing_stop(void)
 	struct ring_buffer *buffer;
 	unsigned long flags;
 
-	ftrace_stop();
 	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
 	if (global_trace.stop_count++)
 		goto out;
@@ -1449,12 +1461,12 @@ static void tracing_stop_tr(struct trace_array *tr)
 
 void trace_stop_cmdline_recording(void);
 
-static void trace_save_cmdline(struct task_struct *tsk)
+static int trace_save_cmdline(struct task_struct *tsk)
 {
 	unsigned pid, idx;
 
 	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return;
+		return 0;
 
 	/*
 	 * It's not the end of the world if we don't get
@@ -1463,7 +1475,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	 * so if we miss here, then better luck next time.
 	 */
 	if (!arch_spin_trylock(&trace_cmdline_lock))
-		return;
+		return 0;
 
 	idx = map_pid_to_cmdline[tsk->pid];
 	if (idx == NO_CMDLINE_MAP) {
@@ -1488,6 +1500,8 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
 
 	arch_spin_unlock(&trace_cmdline_lock);
+
+	return 1;
 }
 
 void trace_find_cmdline(int pid, char comm[])
@@ -1529,9 +1543,8 @@ void tracing_record_cmdline(struct task_struct *tsk)
 	if (!__this_cpu_read(trace_cmdline_save))
 		return;
 
-	__this_cpu_write(trace_cmdline_save, false);
-
-	trace_save_cmdline(tsk);
+	if (trace_save_cmdline(tsk))
+		__this_cpu_write(trace_cmdline_save, false);
 }
 
 void
@@ -4161,17 +4174,19 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
  *
  *     Anyway, this is really very primitive wakeup.
  */
-void poll_wait_pipe(struct trace_iterator *iter)
+int poll_wait_pipe(struct trace_iterator *iter)
 {
 	set_current_state(TASK_INTERRUPTIBLE);
 	/* sleep for 100 msecs, and try again. */
 	schedule_timeout(HZ / 10);
+	return 0;
 }
 
 /* Must be called with trace_types_lock mutex held. */
 static int tracing_wait_pipe(struct file *filp)
 {
 	struct trace_iterator *iter = filp->private_data;
+	int ret;
 
 	while (trace_empty(iter)) {
 
@@ -4181,10 +4196,13 @@ static int tracing_wait_pipe(struct file *filp)
 
 		mutex_unlock(&iter->mutex);
 
-		iter->trace->wait_pipe(iter);
+		ret = iter->trace->wait_pipe(iter);
 
 		mutex_lock(&iter->mutex);
 
+		if (ret)
+			return ret;
+
 		if (signal_pending(current))
 			return -EINTR;
 
@@ -5112,8 +5130,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 				goto out_unlock;
 			}
 			mutex_unlock(&trace_types_lock);
-			iter->trace->wait_pipe(iter);
+			ret = iter->trace->wait_pipe(iter);
 			mutex_lock(&trace_types_lock);
+			if (ret) {
+				size = ret;
+				goto out_unlock;
+			}
 			if (signal_pending(current)) {
 				size = -EINTR;
 				goto out_unlock;
@@ -5325,8 +5347,10 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			goto out;
 		}
 		mutex_unlock(&trace_types_lock);
-		iter->trace->wait_pipe(iter);
+		ret = iter->trace->wait_pipe(iter);
 		mutex_lock(&trace_types_lock);
+		if (ret)
+			goto out;
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			goto out;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 02b592f2d4b7..c8bd809cbd1c 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -336,7 +336,7 @@ struct tracer {
 	void			(*stop)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
 	void			(*pipe_open)(struct trace_iterator *iter);
-	void			(*wait_pipe)(struct trace_iterator *iter);
+	int			(*wait_pipe)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
 	void			(*pipe_close)(struct trace_iterator *iter);
 	ssize_t			(*read)(struct trace_iterator *iter,
@@ -552,7 +552,7 @@ void trace_init_global_iter(struct trace_iterator *iter);
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
-void poll_wait_pipe(struct trace_iterator *iter);
+int poll_wait_pipe(struct trace_iterator *iter);
 
 void tracing_sched_switch_trace(struct trace_array *tr,
 				struct task_struct *prev,
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 26dc348332b7..57b67b1f24d1 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -59,13 +59,14 @@ u64 notrace trace_clock(void)
 
 /*
  * trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ * Note that this use of jiffies_64 is not completely safe on
+ * 32-bit systems. But the window is tiny, and the effect if
+ * we are affected is that we will have an obviously bogus
+ * timestamp on a trace event - i.e. not life threatening.
  */
 u64 notrace trace_clock_jiffies(void)
 {
-	u64 jiffy = jiffies - INITIAL_JIFFIES;
-
-	/* Return nsecs */
-	return (u64)jiffies_to_usecs(jiffy) * 1000ULL;
+	return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES);
 }
 
 /*
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7b16d40bd64d..e4c4efc4ba0d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -439,6 +439,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file)
 
 	list_del(&file->list);
 	remove_subsystem(file->system);
+	free_event_filter(file->filter);
 	kmem_cache_free(file_cachep, file);
 }
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 8efbb69b04f0..6d6a789e579e 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec)
 			data->ops->func(data);
 			continue;
 		}
-		filter = rcu_dereference(data->filter);
+		filter = rcu_dereference_sched(data->filter);
 		if (filter && !filter_match_preds(filter, rec))
 			continue;
 		if (data->cmd_ops->post_trigger) {
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 759d5e004517..7e3cd7aaec83 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -313,7 +313,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
@@ -360,7 +360,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	int syscall_nr;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
@@ -567,7 +567,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
 		return;
@@ -641,7 +641,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
-	if (syscall_nr < 0)
+	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
 		return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 79e52d93860b..bd0c9b133b54 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -728,9 +728,15 @@ static int uprobe_buffer_enable(void)
 
 static void uprobe_buffer_disable(void)
 {
+	int cpu;
+
 	BUG_ON(!mutex_is_locked(&event_mutex));
 
 	if (--uprobe_buffer_refcnt == 0) {
+		for_each_possible_cpu(cpu)
+			free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer,
+							     cpu)->buf);
+
 		free_percpu(uprobe_cpu_buffer);
 		uprobe_cpu_buffer = NULL;
 	}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 031cc5655a51..63630aef3bd3 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -641,6 +641,9 @@ static int tracepoint_module_coming(struct module *mod)
 	struct tp_module *tp_mod, *iter;
 	int ret = 0;
 
+	if (!mod->num_tracepoints)
+		return 0;
+
 	/*
 	 * We skip modules that taint the kernel, especially those with different
 	 * module headers (for forced load), to make sure we don't cause a crash.
@@ -684,6 +687,9 @@ static int tracepoint_module_going(struct module *mod)
 {
 	struct tp_module *pos;
 
+	if (!mod->num_tracepoints)
+		return 0;
+
 	mutex_lock(&tracepoints_mutex);
 	tracepoint_update_probe_range(mod->tracepoints_ptrs,
 		mod->tracepoints_ptrs + mod->num_tracepoints);
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 602e5bbbceff..d58cc4d8f0d1 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -176,7 +176,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!ns_capable(current_user_ns(), CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;
diff --git a/kernel/user.c b/kernel/user.c
index c006131beb77..c2bbb50f5a90 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,7 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.flags = USERNS_INIT_FLAGS,
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	.persistent_keyring_register_sem =
 	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index dd06439b9c84..153971e4798a 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -24,6 +24,7 @@
 #include <linux/fs_struct.h>
 
 static struct kmem_cache *user_ns_cachep __read_mostly;
+static DEFINE_MUTEX(userns_state_mutex);
 
 static bool new_idmap_permitted(const struct file *file,
 				struct user_namespace *ns, int cap_setid,
@@ -99,6 +100,11 @@ int create_user_ns(struct cred *new)
 	ns->owner = owner;
 	ns->group = group;
 
+	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
+	mutex_lock(&userns_state_mutex);
+	ns->flags = parent_ns->flags;
+	mutex_unlock(&userns_state_mutex);
+
 	set_cred_user_ns(new, ns);
 
 #ifdef CONFIG_PERSISTENT_KEYRINGS
@@ -152,7 +158,7 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
 
 	/* Find the matching extent */
 	extents = map->nr_extents;
-	smp_read_barrier_depends();
+	smp_rmb();
 	for (idx = 0; idx < extents; idx++) {
 		first = map->extent[idx].first;
 		last = first + map->extent[idx].count - 1;
@@ -176,7 +182,7 @@ static u32 map_id_down(struct uid_gid_map *map, u32 id)
 
 	/* Find the matching extent */
 	extents = map->nr_extents;
-	smp_read_barrier_depends();
+	smp_rmb();
 	for (idx = 0; idx < extents; idx++) {
 		first = map->extent[idx].first;
 		last = first + map->extent[idx].count - 1;
@@ -199,7 +205,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id)
 
 	/* Find the matching extent */
 	extents = map->nr_extents;
-	smp_read_barrier_depends();
+	smp_rmb();
 	for (idx = 0; idx < extents; idx++) {
 		first = map->extent[idx].lower_first;
 		last = first + map->extent[idx].count - 1;
@@ -581,9 +587,6 @@ static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent
 	return false;
 }
 
-
-static DEFINE_MUTEX(id_map_mutex);
-
 static ssize_t map_write(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos,
 			 int cap_setid,
@@ -600,7 +603,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	ssize_t ret = -EINVAL;
 
 	/*
-	 * The id_map_mutex serializes all writes to any given map.
+	 * The userns_state_mutex serializes all writes to any given map.
 	 *
 	 * Any map is only ever written once.
 	 *
@@ -615,11 +618,10 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	 * were written before the count of the extents.
 	 *
 	 * To achieve this smp_wmb() is used on guarantee the write
-	 * order and smp_read_barrier_depends() is guaranteed that we
-	 * don't have crazy architectures returning stale data.
-	 *
+	 * order and smp_rmb() is guaranteed that we don't have crazy
+	 * architectures returning stale data.
 	 */
-	mutex_lock(&id_map_mutex);
+	mutex_lock(&userns_state_mutex);
 
 	ret = -EPERM;
 	/* Only allow one successful write to the map */
@@ -746,7 +748,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	*ppos = count;
 	ret = count;
 out:
-	mutex_unlock(&id_map_mutex);
+	mutex_unlock(&userns_state_mutex);
 	if (page)
 		free_page(page);
 	return ret;
@@ -805,17 +807,21 @@ static bool new_idmap_permitted(const struct file *file,
 				struct user_namespace *ns, int cap_setid,
 				struct uid_gid_map *new_map)
 {
-	/* Allow mapping to your own filesystem ids */
-	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) {
+	const struct cred *cred = file->f_cred;
+	/* Don't allow mappings that would allow anything that wouldn't
+	 * be allowed without the establishment of unprivileged mappings.
+	 */
+	if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
+	    uid_eq(ns->owner, cred->euid)) {
 		u32 id = new_map->extent[0].lower_first;
 		if (cap_setid == CAP_SETUID) {
 			kuid_t uid = make_kuid(ns->parent, id);
-			if (uid_eq(uid, file->f_cred->fsuid))
+			if (uid_eq(uid, cred->euid))
 				return true;
-		}
-		else if (cap_setid == CAP_SETGID) {
+		} else if (cap_setid == CAP_SETGID) {
 			kgid_t gid = make_kgid(ns->parent, id);
-			if (gid_eq(gid, file->f_cred->fsgid))
+			if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
+			    gid_eq(gid, cred->egid))
 				return true;
 		}
 	}
@@ -835,6 +841,100 @@ static bool new_idmap_permitted(const struct file *file,
 	return false;
 }
 
+int proc_setgroups_show(struct seq_file *seq, void *v)
+{
+	struct user_namespace *ns = seq->private;
+	unsigned long userns_flags = ACCESS_ONCE(ns->flags);
+
+	seq_printf(seq, "%s\n",
+		   (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
+		   "allow" : "deny");
+	return 0;
+}
+
+ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct seq_file *seq = file->private_data;
+	struct user_namespace *ns = seq->private;
+	char kbuf[8], *pos;
+	bool setgroups_allowed;
+	ssize_t ret;
+
+	/* Only allow a very narrow range of strings to be written */
+	ret = -EINVAL;
+	if ((*ppos != 0) || (count >= sizeof(kbuf)))
+		goto out;
+
+	/* What was written? */
+	ret = -EFAULT;
+	if (copy_from_user(kbuf, buf, count))
+		goto out;
+	kbuf[count] = '\0';
+	pos = kbuf;
+
+	/* What is being requested? */
+	ret = -EINVAL;
+	if (strncmp(pos, "allow", 5) == 0) {
+		pos += 5;
+		setgroups_allowed = true;
+	}
+	else if (strncmp(pos, "deny", 4) == 0) {
+		pos += 4;
+		setgroups_allowed = false;
+	}
+	else
+		goto out;
+
+	/* Verify there is not trailing junk on the line */
+	pos = skip_spaces(pos);
+	if (*pos != '\0')
+		goto out;
+
+	ret = -EPERM;
+	mutex_lock(&userns_state_mutex);
+	if (setgroups_allowed) {
+		/* Enabling setgroups after setgroups has been disabled
+		 * is not allowed.
+		 */
+		if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
+			goto out_unlock;
+	} else {
+		/* Permanently disabling setgroups after setgroups has
+		 * been enabled by writing the gid_map is not allowed.
+		 */
+		if (ns->gid_map.nr_extents != 0)
+			goto out_unlock;
+		ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
+	}
+	mutex_unlock(&userns_state_mutex);
+
+	/* Report a successful write */
+	*ppos = count;
+	ret = count;
+out:
+	return ret;
+out_unlock:
+	mutex_unlock(&userns_state_mutex);
+	goto out;
+}
+
+bool userns_may_setgroups(const struct user_namespace *ns)
+{
+	bool allowed;
+
+	mutex_lock(&userns_state_mutex);
+	/* It is not safe to use setgroups until a gid mapping in
+	 * the user namespace has been established.
+	 */
+	allowed = ns->gid_map.nr_extents != 0;
+	/* Is setgroups allowed? */
+	allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
+	mutex_unlock(&userns_state_mutex);
+
+	return allowed;
+}
+
 static void *userns_get(struct task_struct *task)
 {
 	struct user_namespace *user_ns;
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 4431610f049a..c9b6f01bf853 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -524,10 +524,8 @@ static void update_timers_all_cpus(void)
 	int cpu;
 
 	get_online_cpus();
-	preempt_disable();
 	for_each_online_cpu(cpu)
 		update_timers(cpu);
-	preempt_enable();
 	put_online_cpus();
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 193e977a10ea..b4defdecec8a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1909,6 +1909,12 @@ static void send_mayday(struct work_struct *work)
 
 	/* mayday mayday mayday */
 	if (list_empty(&pwq->mayday_node)) {
+		/*
+		 * If @pwq is for an unbound wq, its base ref may be put at
+		 * any time due to an attribute change.  Pin @pwq until the
+		 * rescuer is done with it.
+		 */
+		get_pwq(pwq);
 		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
 	}
@@ -2391,6 +2397,7 @@ static int rescuer_thread(void *__rescuer)
 	struct worker *rescuer = __rescuer;
 	struct workqueue_struct *wq = rescuer->rescue_wq;
 	struct list_head *scheduled = &rescuer->scheduled;
+	bool should_stop;
 
 	set_user_nice(current, RESCUER_NICE_LEVEL);
 
@@ -2402,11 +2409,15 @@ static int rescuer_thread(void *__rescuer)
 repeat:
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	if (kthread_should_stop()) {
-		__set_current_state(TASK_RUNNING);
-		rescuer->task->flags &= ~PF_WQ_WORKER;
-		return 0;
-	}
+	/*
+	 * By the time the rescuer is requested to stop, the workqueue
+	 * shouldn't have any work pending, but @wq->maydays may still have
+	 * pwq(s) queued.  This can happen by non-rescuer workers consuming
+	 * all the work items before the rescuer got to them.  Go through
+	 * @wq->maydays processing before acting on should_stop so that the
+	 * list is always empty on exit.
+	 */
+	should_stop = kthread_should_stop();
 
 	/* see whether any pwq is asking for help */
 	spin_lock_irq(&wq_mayday_lock);
@@ -2438,6 +2449,12 @@ repeat:
 		process_scheduled_works(rescuer);
 
 		/*
+		 * Put the reference grabbed by send_mayday().  @pool won't
+		 * go away while we're holding its lock.
+		 */
+		put_pwq(pwq);
+
+		/*
 		 * Leave this pool.  If keep_working() is %true, notify a
 		 * regular worker; otherwise, we end up with 0 concurrency
 		 * and stalling the execution.
@@ -2452,6 +2469,12 @@ repeat:
 
 	spin_unlock_irq(&wq_mayday_lock);
 
+	if (should_stop) {
+		__set_current_state(TASK_RUNNING);
+		rescuer->task->flags &= ~PF_WQ_WORKER;
+		return 0;
+	}
+
 	/* rescuers should never participate in concurrency management */
 	WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
 	schedule();
@@ -3392,6 +3415,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 		}
 	}
 
+	dev_set_uevent_suppress(&wq_dev->dev, false);
 	kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
 	return 0;
 }
@@ -4093,7 +4117,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	if (!pwq) {
 		pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
 			   wq->name);
-		goto out_unlock;
+		mutex_lock(&wq->mutex);
+		goto use_dfl_pwq;
 	}
 
 	/*
@@ -5002,7 +5027,7 @@ static void __init wq_numa_init(void)
 	BUG_ON(!tbl);
 
 	for_each_node(node)
-		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
+		BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
 				node_online(node) ? node : NUMA_NO_NODE));
 
 	for_each_possible_cpu(cpu) {
diff --git a/lib/Makefile b/lib/Makefile
index 48140e3ba73f..befe5554a34f 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -147,7 +147,8 @@ obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o
 
 obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
 
-libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o
+libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
+	       fdt_empty_tree.o
 $(foreach file, $(libfdt_files), \
 	$(eval CFLAGS_$(file) = -I$(src)/../scripts/dtc/libfdt))
 lib-$(CONFIG_LIBFDT) += $(libfdt_files)
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index c0b1007011e1..2404d03e251a 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -1723,11 +1723,13 @@ ascend_old_tree:
 		shortcut = assoc_array_ptr_to_shortcut(ptr);
 		slot = shortcut->parent_slot;
 		cursor = shortcut->back_pointer;
+		if (!cursor)
+			goto gc_complete;
 	} else {
 		slot = node->parent_slot;
 		cursor = ptr;
 	}
-	BUG_ON(!ptr);
+	BUG_ON(!cursor);
 	node = assoc_array_ptr_to_node(cursor);
 	slot++;
 	goto continue_node;
@@ -1735,7 +1737,7 @@ ascend_old_tree:
 gc_complete:
 	edit->set[0].to = new_root;
 	assoc_array_apply_edit(edit);
-	edit->array->nr_leaves_on_tree = nr_leaves_on_tree;
+	array->nr_leaves_on_tree = nr_leaves_on_tree;
 	return 0;
 
 enomem:
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 06f7e4fe8d2d..e5c4ebe586ba 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -131,7 +131,9 @@ void __bitmap_shift_right(unsigned long *dst,
 		lower = src[off + k];
 		if (left && off + k == lim - 1)
 			lower &= mask;
-		dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem;
+		dst[k] = lower >> rem;
+		if (rem)
+			dst[k] |= upper << (BITS_PER_LONG - rem);
 		if (left && k == lim - 1)
 			dst[k] &= mask;
 	}
@@ -172,7 +174,9 @@ void __bitmap_shift_left(unsigned long *dst,
 		upper = src[k];
 		if (left && k == lim - 1)
 			upper &= (1UL << left) - 1;
-		dst[k + off] = lower  >> (BITS_PER_LONG - rem) | upper << rem;
+		dst[k + off] = upper << rem;
+		if (rem)
+			dst[k + off] |= lower >> (BITS_PER_LONG - rem);
 		if (left && k + off == lim - 1)
 			dst[k + off] &= (1UL << left) - 1;
 	}
diff --git a/lib/btree.c b/lib/btree.c
index f9a484676cb6..4264871ea1a0 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -198,6 +198,7 @@ EXPORT_SYMBOL_GPL(btree_init);
 
 void btree_destroy(struct btree_head *head)
 {
+	mempool_free(head->node, head->mempool);
 	mempool_destroy(head->mempool);
 	head->mempool = NULL;
 }
diff --git a/lib/fdt_empty_tree.c b/lib/fdt_empty_tree.c
new file mode 100644
index 000000000000..5d30c58150ad
--- /dev/null
+++ b/lib/fdt_empty_tree.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_empty_tree.c"
diff --git a/lib/idr.c b/lib/idr.c
index bfe4db4e165f..674c30bc2ed0 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -250,7 +250,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa,
 			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
 
 			/* if already at the top layer, we need to grow */
-			if (id >= 1 << (idp->layers * IDR_BITS)) {
+			if (id > idr_max(idp->layers)) {
 				*starting_id = id;
 				return -EAGAIN;
 			}
@@ -827,12 +827,10 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 	if (!p)
 		return ERR_PTR(-EINVAL);
 
-	n = (p->layer+1) * IDR_BITS;
-
-	if (id >= (1 << n))
+	if (id > idr_max(p->layer + 1))
 		return ERR_PTR(-EINVAL);
 
-	n -= IDR_BITS;
+	n = p->layer * IDR_BITS;
 	while ((n > 0) && p) {
 		p = p->ary[(id >> n) & IDR_MASK];
 		n -= IDR_BITS;
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index df6839e3ce08..7a85967060a5 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -72,6 +72,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 			len = *ip++;
 			for (; len == 255; length += 255)
 				len = *ip++;
+			if (unlikely(length > (size_t)(length + len)))
+				goto _output_error;
 			length += len;
 		}
 
@@ -106,6 +108,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 		if (length == ML_MASK) {
 			for (; *ip == 255; length += 255)
 				ip++;
+			if (unlikely(length > (size_t)(length + *ip)))
+				goto _output_error;
 			length += *ip++;
 		}
 
@@ -155,7 +159,7 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 
 	/* write overflow error detected */
 _output_error:
-	return (int) (-(((char *)ip) - source));
+	return -1;
 }
 
 static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
@@ -188,6 +192,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 			int s = 255;
 			while ((ip < iend) && (s == 255)) {
 				s = *ip++;
+				if (unlikely(length > (size_t)(length + s)))
+					goto _output_error;
 				length += s;
 			}
 		}
@@ -228,6 +234,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 		if (length == ML_MASK) {
 			while (ip < iend) {
 				int s = *ip++;
+				if (unlikely(length > (size_t)(length + s)))
+					goto _output_error;
 				length += s;
 				if (s == 255)
 					continue;
@@ -280,7 +288,7 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 
 	/* write overflow error detected */
 _output_error:
-	return (int) (-(((char *) ip) - source));
+	return -1;
 }
 
 int lz4_decompress(const unsigned char *src, size_t *src_len,
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 569985d522d5..a1c387f6afba 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -25,6 +25,16 @@
 #define NEED_OP(x)      if (!HAVE_OP(x)) goto output_overrun
 #define TEST_LB(m_pos)  if ((m_pos) < out) goto lookbehind_overrun
 
+/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base
+ * count without overflowing an integer. The multiply will overflow when
+ * multiplying 255 by more than MAXINT/255. The sum will overflow earlier
+ * depending on the base count. Since the base count is taken from a u8
+ * and a few bits, it is safe to assume that it will always be lower than
+ * or equal to 2*255, thus we can always prevent any overflow by accepting
+ * two less 255 steps. See Documentation/lzo.txt for more information.
+ */
+#define MAX_255_COUNT      ((((size_t)~0) / 255) - 2)
+
 int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 			  unsigned char *out, size_t *out_len)
 {
@@ -55,12 +65,19 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 		if (t < 16) {
 			if (likely(state == 0)) {
 				if (unlikely(t == 0)) {
+					size_t offset;
+					const unsigned char *ip_last = ip;
+
 					while (unlikely(*ip == 0)) {
-						t += 255;
 						ip++;
 						NEED_IP(1);
 					}
-					t += 15 + *ip++;
+					offset = ip - ip_last;
+					if (unlikely(offset > MAX_255_COUNT))
+						return LZO_E_ERROR;
+
+					offset = (offset << 8) - offset;
+					t += offset + 15 + *ip++;
 				}
 				t += 3;
 copy_literal_run:
@@ -116,12 +133,19 @@ copy_literal_run:
 		} else if (t >= 32) {
 			t = (t & 31) + (3 - 1);
 			if (unlikely(t == 2)) {
+				size_t offset;
+				const unsigned char *ip_last = ip;
+
 				while (unlikely(*ip == 0)) {
-					t += 255;
 					ip++;
 					NEED_IP(1);
 				}
-				t += 31 + *ip++;
+				offset = ip - ip_last;
+				if (unlikely(offset > MAX_255_COUNT))
+					return LZO_E_ERROR;
+
+				offset = (offset << 8) - offset;
+				t += offset + 31 + *ip++;
 				NEED_IP(2);
 			}
 			m_pos = op - 1;
@@ -134,12 +158,19 @@ copy_literal_run:
 			m_pos -= (t & 8) << 11;
 			t = (t & 7) + (3 - 1);
 			if (unlikely(t == 2)) {
+				size_t offset;
+				const unsigned char *ip_last = ip;
+
 				while (unlikely(*ip == 0)) {
-					t += 255;
 					ip++;
 					NEED_IP(1);
 				}
-				t += 7 + *ip++;
+				offset = ip - ip_last;
+				if (unlikely(offset > MAX_255_COUNT))
+					return LZO_E_ERROR;
+
+				offset = (offset << 8) - offset;
+				t += offset + 7 + *ip++;
 				NEED_IP(2);
 			}
 			next = get_unaligned_le16(ip);
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 18eca7809b08..10ad042d01be 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -201,8 +201,8 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
 	}
 
 	if (unlikely(rem > 0))
-		printk(KERN_WARNING "netlink: %d bytes leftover after parsing "
-		       "attributes.\n", rem);
+		pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
+				    rem, current->comm);
 
 	err = 0;
 errout:
@@ -303,9 +303,15 @@ int nla_memcmp(const struct nlattr *nla, const void *data,
  */
 int nla_strcmp(const struct nlattr *nla, const char *str)
 {
-	int len = strlen(str) + 1;
-	int d = nla_len(nla) - len;
+	int len = strlen(str);
+	char *buf = nla_data(nla);
+	int attrlen = nla_len(nla);
+	int d;
 
+	if (attrlen > 0 && buf[attrlen - 1] == '\0')
+		attrlen--;
+
+	d = attrlen - len;
 	if (d == 0)
 		d = memcmp(nla_data(nla), str, len);
 
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 8280a5dd1727..7dd33577b905 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -169,7 +169,7 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
 	struct percpu_counter *fbc;
 
 	compute_batch_value();
-	if (action != CPU_DEAD)
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
 
 	cpu = (unsigned long)hcpu;
diff --git a/lib/plist.c b/lib/plist.c
index 1ebc95f7a46f..0f2084d30798 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -134,6 +134,46 @@ void plist_del(struct plist_node *node, struct plist_head *head)
 	plist_check_head(head);
 }
 
+/**
+ * plist_requeue - Requeue @node at end of same-prio entries.
+ *
+ * This is essentially an optimized plist_del() followed by
+ * plist_add().  It moves an entry already in the plist to
+ * after any other same-priority entries.
+ *
+ * @node:	&struct plist_node pointer - entry to be moved
+ * @head:	&struct plist_head pointer - list head
+ */
+void plist_requeue(struct plist_node *node, struct plist_head *head)
+{
+	struct plist_node *iter;
+	struct list_head *node_next = &head->node_list;
+
+	plist_check_head(head);
+	BUG_ON(plist_head_empty(head));
+	BUG_ON(plist_node_empty(node));
+
+	if (node == plist_last(head))
+		return;
+
+	iter = plist_next(node);
+
+	if (node->prio != iter->prio)
+		return;
+
+	plist_del(node, head);
+
+	plist_for_each_continue(iter, head) {
+		if (node->prio != iter->prio) {
+			node_next = &iter->node_list;
+			break;
+		}
+	}
+	list_add_tail(&node->node_list, node_next);
+
+	plist_check_head(head);
+}
+
 #ifdef CONFIG_DEBUG_PI_LIST
 #include <linux/sched.h>
 #include <linux/module.h>
@@ -170,6 +210,14 @@ static void __init plist_test_check(int nr_expect)
 	BUG_ON(prio_pos->prio_list.next != &first->prio_list);
 }
 
+static void __init plist_test_requeue(struct plist_node *node)
+{
+	plist_requeue(node, &test_head);
+
+	if (node != plist_last(&test_head))
+		BUG_ON(node->prio == plist_next(node)->prio);
+}
+
 static int  __init plist_test(void)
 {
 	int nr_expect = 0, i, loop;
@@ -193,6 +241,10 @@ static int  __init plist_test(void)
 			nr_expect--;
 		}
 		plist_test_check(nr_expect);
+		if (!plist_node_empty(test_node + i)) {
+			plist_test_requeue(test_node + i);
+			plist_test_check(nr_expect);
+		}
 	}
 
 	for (i = 0; i < ARRAY_SIZE(test_node); i++) {
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index bd4a8dfdf0b8..7e30d2a7f346 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -946,81 +946,6 @@ next:
 }
 EXPORT_SYMBOL(radix_tree_range_tag_if_tagged);
 
-
-/**
- *	radix_tree_next_hole    -    find the next hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest
- *	indexed hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'return - index >= max_scan'
- *	will be true). In rare cases of index wrap-around, 0 will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 5, then subsequently a hole is created at index 10,
- *	radix_tree_next_hole covering both indexes may return 10 if called
- *	under rcu_read_lock.
- */
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index++;
-		if (index == 0)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_next_hole);
-
-/**
- *	radix_tree_prev_hole    -    find the prev hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search backwards in the range [max(index-max_scan+1, 0), index]
- *	for the first hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'index - return >= max_scan'
- *	will be true). In rare cases of wrap-around, ULONG_MAX will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 10, then subsequently a hole is created at index 5,
- *	radix_tree_prev_hole covering both indexes may return 5 if called under
- *	rcu_read_lock.
- */
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				   unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index--;
-		if (index == ULONG_MAX)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_prev_hole);
-
 /**
  *	radix_tree_gang_lookup - perform multiple lookup on a radix tree
  *	@root:		radix tree root
@@ -1337,15 +1262,18 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
 }
 
 /**
- *	radix_tree_delete    -    delete an item from a radix tree
+ *	radix_tree_delete_item    -    delete an item from a radix tree
  *	@root:		radix tree root
  *	@index:		index key
+ *	@item:		expected item
  *
- *	Remove the item at @index from the radix tree rooted at @root.
+ *	Remove @item at @index from the radix tree rooted at @root.
  *
- *	Returns the address of the deleted item, or NULL if it was not present.
+ *	Returns the address of the deleted item, or NULL if it was not present
+ *	or the entry at the given @index was not @item.
  */
-void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+void *radix_tree_delete_item(struct radix_tree_root *root,
+			     unsigned long index, void *item)
 {
 	struct radix_tree_node *node = NULL;
 	struct radix_tree_node *slot = NULL;
@@ -1380,6 +1308,11 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 	if (slot == NULL)
 		goto out;
 
+	if (item && slot != item) {
+		slot = NULL;
+		goto out;
+	}
+
 	/*
 	 * Clear all tags associated with the item to be deleted.
 	 * This way of doing it would be inefficient, but seldom is any set.
@@ -1424,6 +1357,21 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 out:
 	return slot;
 }
+EXPORT_SYMBOL(radix_tree_delete_item);
+
+/**
+ *	radix_tree_delete    -    delete an item from a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *
+ *	Remove the item at @index from the radix tree rooted at @root.
+ *
+ *	Returns the address of the deleted item, or NULL if it was not present.
+ */
+void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+{
+	return radix_tree_delete_item(root, index, NULL);
+}
 EXPORT_SYMBOL(radix_tree_delete);
 
 /**
diff --git a/lib/string.c b/lib/string.c
index e5878de4f101..43d0781daf47 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -586,6 +586,22 @@ void *memset(void *s, int c, size_t count)
 EXPORT_SYMBOL(memset);
 #endif
 
+/**
+ * memzero_explicit - Fill a region of memory (e.g. sensitive
+ *		      keying data) with 0s.
+ * @s: Pointer to the start of the area.
+ * @count: The size of the area.
+ *
+ * memzero_explicit() doesn't need an arch-specific version as
+ * it just invokes the one of memset() implicitly.
+ */
+void memzero_explicit(void *s, size_t count)
+{
+	memset(s, 0, count);
+	OPTIMIZER_HIDE_VAR(s);
+}
+EXPORT_SYMBOL(memzero_explicit);
+
 #ifndef __HAVE_ARCH_MEMCPY
 /**
  * memcpy - Copy one area of memory to another
diff --git a/linaro/configs/android.conf b/linaro/configs/android.conf
new file mode 100644
index 000000000000..e4fd1ad19028
--- /dev/null
+++ b/linaro/configs/android.conf
@@ -0,0 +1,42 @@
+CONFIG_IPV6=y
+# CONFIG_IPV6_SIT is not set
+CONFIG_PANIC_TIMEOUT=0
+CONFIG_HAS_WAKELOCK=y
+CONFIG_WAKELOCK=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DM_CRYPT=y
+CONFIG_POWER_SUPPLY=y
+CONFIG_ANDROID_PARANOID_NETWORK=y
+CONFIG_NET_ACTIVITY_STATS=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+CONFIG_USB_G_ANDROID=y
+CONFIG_SWITCH=y
+CONFIG_STAGING=y
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_LOGGER=y
+CONFIG_ANDROID_TIMED_OUTPUT=y
+CONFIG_ANDROID_TIMED_GPIO=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ANDROID_INTF_ALARM_DEV=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_FUSE_FS=y
+CONFIG_CPU_FREQ_GOV_INTERACTIVE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE=y
+CONFIG_ION=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SW_SYNC_USER=y
+CONFIG_ION_TEST=y
+CONFIG_ION_DUMMY=y
+CONFIG_ADF=y
+CONFIG_ADF_FBDEV=y
+CONFIG_ADF_MEMBLOCK=y
+CONFIG_DMA_SHARED_BUFFER=y
+CONFIG_TUN=y
diff --git a/linaro/configs/arndale.conf b/linaro/configs/arndale.conf
new file mode 100644
index 000000000000..109052f2f6ec
--- /dev/null
+++ b/linaro/configs/arndale.conf
@@ -0,0 +1,66 @@
+CONFIG_KALLSYMS_ALL=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_ARCH_EXYNOS=y
+CONFIG_S3C_LOWLEVEL_UART_PORT=2
+CONFIG_ARCH_EXYNOS5=y
+# CONFIG_EXYNOS_ATAGS is not set
+CONFIG_MACH_EXYNOS4_DT=y
+CONFIG_VMSPLIT_2G=y
+CONFIG_NR_CPUS=2
+CONFIG_HIGHMEM=y
+# CONFIG_COMPACTION is not set
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
+CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init= mem=256M"
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_PM_RUNTIME=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_SATA_EXYNOS=y
+CONFIG_AX88796=y
+CONFIG_AX88796_93CX6=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_SAMSUNG=y
+CONFIG_SERIAL_SAMSUNG_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C=y
+CONFIG_I2C_S3C2410=y
+CONFIG_THERMAL=y
+CONFIG_CPU_THERMAL=y
+CONFIG_EXYNOS_THERMAL=y
+CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_S5M8767=y
+CONFIG_DRM=y
+CONFIG_DRM_LOAD_EDID_FIRMWARE=y
+CONFIG_DRM_EXYNOS=y
+CONFIG_DRM_EXYNOS_DMABUF=y
+CONFIG_DRM_EXYNOS_HDMI=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+CONFIG_MMC_DW_EXYNOS=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_S3C=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_INFO=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_DEBUG_USER=y
+CONFIG_TUN=y
diff --git a/linaro/configs/big-LITTLE-IKS.conf b/linaro/configs/big-LITTLE-IKS.conf
new file mode 100644
index 000000000000..b067fde86eaa
--- /dev/null
+++ b/linaro/configs/big-LITTLE-IKS.conf
@@ -0,0 +1,5 @@
+CONFIG_BIG_LITTLE=y
+CONFIG_BL_SWITCHER=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM_VEXPRESS_BL_CPUFREQ=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
diff --git a/linaro/configs/bigendian.conf b/linaro/configs/bigendian.conf
new file mode 100644
index 000000000000..6a1020299e85
--- /dev/null
+++ b/linaro/configs/bigendian.conf
@@ -0,0 +1,4 @@
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_CPU_ENDIAN_BE8=y
+# CONFIG_VIRTUALIZATION is not set
+# CONFIG_MMC_DW_IDMAC is not set
diff --git a/linaro/configs/debug.conf b/linaro/configs/debug.conf
new file mode 100644
index 000000000000..36980566b2d8
--- /dev/null
+++ b/linaro/configs/debug.conf
@@ -0,0 +1 @@
+CONFIG_PROVE_LOCKING=y
diff --git a/linaro/configs/distribution.conf b/linaro/configs/distribution.conf
new file mode 100644
index 000000000000..729b9b8979e4
--- /dev/null
+++ b/linaro/configs/distribution.conf
@@ -0,0 +1,49 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_CGROUPS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=32768
+CONFIG_SECCOMP=y
+CONFIG_CC_STACKPROTECTOR=y
+CONFIG_SYN_COOKIES=y
+CONFIG_IPV6=y
+CONFIG_NETLABEL=y
+CONFIG_BRIDGE_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NETFILTER_XT_CONNMARK=m
+CONFIG_NETFILTER_XT_MARK=m
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_NAT_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_NAT_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+CONFIG_BRIDGE=m
+CONFIG_TUN=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=65536
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+# CONFIG_DEVKMEM is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_SECURITY=y
+CONFIG_LSM_MMAP_MIN_ADDR=0
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SMACK=y
+CONFIG_SECURITY_APPARMOR=y
+CONFIG_DEFAULT_SECURITY_APPARMOR=y
+CONFIG_HUGETLBFS=y
+CONFIG_HUGETLB_PAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y
diff --git a/linaro/configs/highbank.conf b/linaro/configs/highbank.conf
new file mode 100644
index 000000000000..bf0f3c14b0d0
--- /dev/null
+++ b/linaro/configs/highbank.conf
@@ -0,0 +1,40 @@
+CONFIG_EXPERIMENTAL=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_ARCH_HIGHBANK=y
+CONFIG_ARM_ERRATA_754322=y
+CONFIG_SMP=y
+CONFIG_SCHED_MC=y
+CONFIG_AEABI=y
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_CPU_IDLE=y
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_NET=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_SATA_HIGHBANK=y
+CONFIG_NETDEVICES=y
+CONFIG_NET_CALXEDA_XGMAC=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_IPMI_HANDLER=y
+CONFIG_IPMI_SI=y
+CONFIG_I2C=y
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_SPI=y
+CONFIG_SPI_PL022=y
+CONFIG_GPIO_PL061=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_HIGHBANK_MC=y
+CONFIG_EDAC_HIGHBANK_L2=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_DMADEVICES=y
+CONFIG_PL330_DMA=y
diff --git a/linaro/configs/kvm-guest.conf b/linaro/configs/kvm-guest.conf
new file mode 100644
index 000000000000..00e84a3ba1ec
--- /dev/null
+++ b/linaro/configs/kvm-guest.conf
@@ -0,0 +1,11 @@
+CONFIG_BALLOON_COMPACTION=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_NET=y
+CONFIG_HVC_DRIVER=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_VIRTUALIZATION=y
+# CONFIG_THUMB2_KERNEL is not set
diff --git a/linaro/configs/kvm-host.conf b/linaro/configs/kvm-host.conf
new file mode 100644
index 000000000000..21a40e031372
--- /dev/null
+++ b/linaro/configs/kvm-host.conf
@@ -0,0 +1,11 @@
+CONFIG_VIRTUALIZATION=y
+CONFIG_ARM_LPAE=y
+CONFIG_ARM_VIRT_EXT=y
+CONFIG_HAVE_KVM_IRQCHIP=y
+CONFIG_KVM_ARM_HOST=y
+CONFIG_KVM_ARM_MAX_VCPUS=4
+CONFIG_KVM_ARM_TIMER=y
+CONFIG_KVM_ARM_VGIC=y
+CONFIG_KVM_MMIO=y
+CONFIG_KVM=y
+CONFIG_BLK_DEV_NBD=m
diff --git a/linaro/configs/linaro-base.conf b/linaro/configs/linaro-base.conf
new file mode 100644
index 000000000000..15f6ea784f63
--- /dev/null
+++ b/linaro/configs/linaro-base.conf
@@ -0,0 +1,120 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_HOTPLUG=y
+CONFIG_PERF_EVENTS=y
+CONFIG_SLAB=y
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_SMP=y
+CONFIG_SCHED_MC=y
+CONFIG_SCHED_SMT=y
+CONFIG_THUMB2_KERNEL=y
+CONFIG_AEABI=y
+# CONFIG_OABI_COMPAT is not set
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPU_IDLE=y
+CONFIG_BINFMT_MISC=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_INET_LRO is not set
+CONFIG_NETFILTER=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_CONNECTOR=y
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_OOPS=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_NAND=y
+CONFIG_NETDEVICES=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_BTRFS_FS=y
+CONFIG_QUOTA=y
+CONFIG_QFMT_V2=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_ECRYPT_FS=y
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_SUMMARY=y
+CONFIG_JFFS2_FS_XATTR=y
+CONFIG_JFFS2_COMPRESSION_OPTIONS=y
+CONFIG_JFFS2_LZO=y
+CONFIG_JFFS2_RUBIN=y
+CONFIG_CRAMFS=y
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V2 is not set
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_PRINTK_TIME=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_KEYS=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+CONFIG_CRC_CCITT=y
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=y
+CONFIG_CRC7=y
+CONFIG_HW_PERF_EVENTS=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_JUMP_LABEL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_KGDB=y
+CONFIG_KGDB_TESTS=y
+CONFIG_OF_IDLE_STATES=y
+CONFIG_FTRACE=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_STACK_TRACER=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_MAILBOX=y
+CONFIG_AUDIT=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_LSM_MMAP_MIN_ADDR=4096
+CONFIG_SECURITY_SELINUX=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DEBUG_INFO=y
+CONFIG_FANOTIFY=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_RCU_TORTURE_TEST_RUNNABLE=n
diff --git a/linaro/configs/omap4.conf b/linaro/configs/omap4.conf
new file mode 100644
index 000000000000..d0a2b808ff12
--- /dev/null
+++ b/linaro/configs/omap4.conf
@@ -0,0 +1,196 @@
+CONFIG_EXPERT=y
+CONFIG_KPROBES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_GPIO_PCA953X=y
+CONFIG_OMAP_RESET_CLOCKS=y
+CONFIG_OMAP_MUX_DEBUG=y
+CONFIG_ARCH_OMAP3=y
+CONFIG_ARCH_OMAP4=y
+CONFIG_ARCH_OMAP2PLUS=y
+CONFIG_SOC_OMAP5=y
+# CONFIG_ARCH_OMAP2 is not set
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_ARM_THUMBEE=y
+CONFIG_ARM_ERRATA_411920=y
+CONFIG_NR_CPUS=2
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_CMDLINE="root=/dev/mmcblk0p2 rootwait console=ttyO2,115200"
+CONFIG_KEXEC=y
+CONFIG_PM_DEBUG=y
+CONFIG_CAN=m
+CONFIG_CAN_C_CAN=m
+CONFIG_CAN_C_CAN_PLATFORM=m
+CONFIG_BT=m
+CONFIG_BT_HCIUART=m
+CONFIG_BT_HCIUART_H4=y
+CONFIG_BT_HCIUART_BCSP=y
+CONFIG_BT_HCIUART_LL=y
+CONFIG_BT_HCIBCM203X=m
+CONFIG_BT_HCIBPA10X=m
+CONFIG_CFG80211=m
+CONFIG_MAC80211=m
+CONFIG_MAC80211_RC_PID=y
+CONFIG_MAC80211_RC_DEFAULT_PID=y
+CONFIG_CMA=y
+CONFIG_MTD_NAND_OMAP2=y
+CONFIG_MTD_ONENAND=y
+CONFIG_MTD_ONENAND_VERIFY_WRITE=y
+CONFIG_MTD_ONENAND_OMAP2=y
+CONFIG_MTD_UBI=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_SENSORS_TSL2550=m
+CONFIG_SENSORS_LIS3_I2C=m
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_SCAN_ASYNC=y
+CONFIG_KS8851=y
+CONFIG_KS8851_MLL=y
+CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
+CONFIG_TI_CPSW=y
+CONFIG_SMSC_PHY=y
+CONFIG_USB_USBNET=y
+CONFIG_USB_NET_SMSC95XX=y
+CONFIG_USB_ALI_M5632=y
+CONFIG_USB_AN2720=y
+CONFIG_USB_EPSON2888=y
+CONFIG_USB_KC2190=y
+CONFIG_LIBERTAS=m
+CONFIG_LIBERTAS_USB=m
+CONFIG_LIBERTAS_SDIO=m
+CONFIG_LIBERTAS_DEBUG=y
+CONFIG_INPUT_JOYDEV=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_MATRIX=m
+CONFIG_KEYBOARD_TWL4030=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=y
+CONFIG_INPUT_TWL4030_PWRBUTTON=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_SERIAL_OMAP=y
+CONFIG_SERIAL_OMAP_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_SPI=y
+CONFIG_SPI_OMAP24XX=y
+CONFIG_PINCTRL_SINGLE=y
+CONFIG_DEBUG_GPIO=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_TWL4030=y
+CONFIG_W1=y
+CONFIG_SENSORS_LM75=m
+CONFIG_WATCHDOG=y
+CONFIG_OMAP_WATCHDOG=y
+CONFIG_TWL4030_WATCHDOG=y
+CONFIG_MFD_TPS65217=y
+CONFIG_MFD_TPS65910=y
+CONFIG_TWL6040_CORE=y
+CONFIG_REGULATOR_TPS65023=y
+CONFIG_REGULATOR_TPS6507X=y
+CONFIG_REGULATOR_TPS65217=y
+CONFIG_REGULATOR_TPS65910=y
+CONFIG_REGULATOR_TWL4030=y
+CONFIG_FB=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_OMAP2_DSS=m
+CONFIG_OMAP2_DSS_RFBI=y
+CONFIG_OMAP2_DSS_SDI=y
+CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP2=m
+CONFIG_PANEL_GENERIC_DPI=m
+CONFIG_PANEL_TFP410=m
+CONFIG_PANEL_SHARP_LS037V7DW01=m
+CONFIG_PANEL_NEC_NL8048HL11_01B=m
+CONFIG_PANEL_TAAL=m
+CONFIG_PANEL_TPO_TD043MTEA1=m
+CONFIG_PANEL_ACX565AKM=m
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LCD_CLASS_DEVICE=y
+CONFIG_LCD_PLATFORM=y
+CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
+CONFIG_FONTS=y
+CONFIG_FONT_8x8=y
+CONFIG_FONT_8x16=y
+CONFIG_LOGO=y
+CONFIG_SOUND=m
+CONFIG_SND=m
+CONFIG_SND_VERBOSE_PRINTK=y
+CONFIG_SND_DEBUG=y
+CONFIG_SND_USB_AUDIO=m
+CONFIG_SND_SOC=m
+CONFIG_SND_OMAP_SOC=m
+CONFIG_SND_OMAP_SOC_OMAP_TWL4030=m
+CONFIG_SND_OMAP_SOC_OMAP_ABE_TWL6040=m
+CONFIG_SND_OMAP_SOC_OMAP3_PANDORA=m
+CONFIG_USB=y
+CONFIG_USB_DEBUG=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_WDM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_TEST=y
+CONFIG_USB_PHY=y
+CONFIG_NOP_USB_XCEIV=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_GADGET_DEBUG=y
+CONFIG_USB_GADGET_DEBUG_FILES=y
+CONFIG_USB_GADGET_DEBUG_FS=y
+CONFIG_USB_ZERO=m
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_SDIO_UART=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_MMC_OMAP=y
+CONFIG_MMC_OMAP_HS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_ONESHOT=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_BACKLIGHT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_LEDS_TRIGGER_GPIO=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_TWL92330=y
+CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_OMAP=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_OMAP=y
+# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_UBIFS_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_LIBCRC32C=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/preempt-rt.conf b/linaro/configs/preempt-rt.conf
new file mode 100644
index 000000000000..98e036d75442
--- /dev/null
+++ b/linaro/configs/preempt-rt.conf
@@ -0,0 +1,4 @@
+CONFIG_PREEMPT=y
+CONFIG_PREEMPT_RT_FULL=y
+CONFIG_SLUB=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/ubuntu-minimal.conf b/linaro/configs/ubuntu-minimal.conf
new file mode 120000
index 000000000000..794e82f3bc17
--- /dev/null
+++ b/linaro/configs/ubuntu-minimal.conf
@@ -0,0 +1 @@
+distribution.conf
\ No newline at end of file
diff --git a/linaro/configs/vexpress-tuning.conf b/linaro/configs/vexpress-tuning.conf
new file mode 100644
index 000000000000..adea6cc66ded
--- /dev/null
+++ b/linaro/configs/vexpress-tuning.conf
@@ -0,0 +1 @@
+# CONFIG_PROVE_LOCKING is not set
diff --git a/linaro/configs/vexpress.conf b/linaro/configs/vexpress.conf
new file mode 100644
index 000000000000..0f02f3abd96f
--- /dev/null
+++ b/linaro/configs/vexpress.conf
@@ -0,0 +1,64 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_HAVE_ARM_ARCH_TIMER=y
+CONFIG_NR_CPUS=8
+CONFIG_HIGHMEM=y
+CONFIG_HIGHPTE=y
+CONFIG_ARM_PSCI=y
+CONFIG_MCPM=y
+CONFIG_ARCH_VEXPRESS_DCSCB=y
+CONFIG_ARCH_VEXPRESS_TC2_PM=y
+CONFIG_ARM_BIG_LITTLE_CPUIDLE=y
+CONFIG_BIG_LITTLE=y
+CONFIG_ARM_VEXPRESS_SPC_CPUFREQ=y
+CONFIG_PM_OPP=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+CONFIG_CMDLINE="console=ttyAMA0,38400n8 root=/dev/mmcblk0p2 rootwait mmci.fmax=4000000"
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SMSC911X=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FB_ARMHDLCD=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_ARMAACI=y
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VEXPRESS_CONFIG=y
+CONFIG_SENSORS_VEXPRESS=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_VEXPRESS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
diff --git a/linaro/configs/vexpress64.conf b/linaro/configs/vexpress64.conf
new file mode 100644
index 000000000000..cb5d0162c0fa
--- /dev/null
+++ b/linaro/configs/vexpress64.conf
@@ -0,0 +1,56 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_COMPAT=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+# CONFIG_SERIO_I8042 is not set
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_CMA=y
+CONFIG_DMA_CMA=y
+CONFIG_COMMON_CLK_SCPI=y
+CONFIG_SMSC911X=y
+CONFIG_I2C=y
+CONFIG_ARM_MHU_MBOX=y
+CONFIG_ARM_SCPI_PROTOCOL=y
+CONFIG_USB_HIDDEV=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB=y
+CONFIG_USB_ULPI=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_SYNOPSYS=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_PHY=y
+CONFIG_USB_ISP1301=y
+CONFIG_PM_OPP=y
+CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM64_CPUIDLE=y
+CONFIG_ARM64_CRYPTO=y
diff --git a/linaro/configs/xen.conf b/linaro/configs/xen.conf
new file mode 100644
index 000000000000..d24fabbea076
--- /dev/null
+++ b/linaro/configs/xen.conf
@@ -0,0 +1,7 @@
+CONFIG_XEN=y
+CONFIG_XEN_NETDEV_FRONTEND=y
+CONFIG_XEN_NETDEV_BACKEND=y
+CONFIG_XEN_BLKDEV_FRONTEND=y
+CONFIG_XEN_BLKDEV_BACKEND=y
+CONFIG_XENFS=y
+CONFIG_XEN_COMPAT_XENFS=y
diff --git a/mm/Kconfig b/mm/Kconfig
index 2888024e0b0a..57c124ee4118 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -263,6 +263,9 @@ config MIGRATION
 	  pages as migration can relocate pages to satisfy a huge page
 	  allocation instead of reclaiming.
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	boolean
+
 config PHYS_ADDR_T_64BIT
 	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
 
@@ -577,3 +580,21 @@ config PGTABLE_MAPPING
 
 	  You can check speed with zsmalloc benchmark:
 	  https://github.com/spartacus06/zsmapbench
+
+config MAX_STACK_SIZE_MB
+	int "Maximum user stack size for 32-bit processes (MB)"
+	default 80
+	range 8 256 if METAG
+	range 8 2048
+	depends on STACK_GROWSUP && (!64BIT || COMPAT)
+	help
+	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
+	  user processes when the stack grows upwards (currently only on parisc
+	  and metag arch). The stack will be located at the highest memory
+	  address minus the given value, unless the RLIMIT_STACK hard limit is
+	  changed to a smaller value in which case that is used.
+
+	  A sane initial value is 80 MB.
+
+config GENERIC_EARLY_IOREMAP
+	bool
diff --git a/mm/Makefile b/mm/Makefile
index 310c90a09264..3c21f087037d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,7 +16,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o balloon_compaction.o \
+			   compaction.o balloon_compaction.o vmacache.o \
 			   interval_tree.o list_lru.o $(mmu-y)
 
 obj-y += init-mm.o
@@ -61,3 +61,4 @@ obj-$(CONFIG_CLEANCACHE) += cleancache.o
 obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
 obj-$(CONFIG_ZBUD)	+= zbud.o
 obj-$(CONFIG_ZSMALLOC)	+= zsmalloc.o
+obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index ce682f7a4f29..09d9591b7708 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -288,13 +288,19 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
  * Note, we wouldn't bother setting up the timer, but this function is on the
  * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
  * by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
  */
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
 {
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -307,9 +313,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	spin_unlock_bh(&bdi_lock);
 
 	synchronize_rcu_expedited();
-
-	/* bdi_list is now unused, clear it to mark @bdi dying */
-	INIT_LIST_HEAD(&bdi->bdi_list);
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -360,6 +363,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 */
 	bdi_remove_from_list(bdi);
 
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	clear_bit(BDI_registered, &bdi->state);
+	spin_unlock_bh(&bdi->wb_lock);
+
 	/*
 	 * Drain work list and shutdown the delayed_work.  At this point,
 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
diff --git a/mm/compaction.c b/mm/compaction.c
index 918577595ea8..4229fc22a477 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long pfn;
 
-	zone->compact_cached_migrate_pfn = start_pfn;
+	zone->compact_cached_migrate_pfn[0] = start_pfn;
+	zone->compact_cached_migrate_pfn[1] = start_pfn;
 	zone->compact_cached_free_pfn = end_pfn;
 	zone->compact_blockskip_flush = false;
 
@@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat)
  */
 static void update_pageblock_skip(struct compact_control *cc,
 			struct page *page, unsigned long nr_isolated,
-			bool migrate_scanner)
+			bool set_unsuitable, bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
+	unsigned long pfn;
 
 	if (cc->ignore_skip_hint)
 		return;
@@ -141,20 +143,32 @@ static void update_pageblock_skip(struct compact_control *cc,
 	if (!page)
 		return;
 
-	if (!nr_isolated) {
-		unsigned long pfn = page_to_pfn(page);
+	if (nr_isolated)
+		return;
+
+	/*
+	 * Only skip pageblocks when all forms of compaction will be known to
+	 * fail in the near future.
+	 */
+	if (set_unsuitable)
 		set_pageblock_skip(page);
 
-		/* Update where compaction should restart */
-		if (migrate_scanner) {
-			if (!cc->finished_update_migrate &&
-			    pfn > zone->compact_cached_migrate_pfn)
-				zone->compact_cached_migrate_pfn = pfn;
-		} else {
-			if (!cc->finished_update_free &&
-			    pfn < zone->compact_cached_free_pfn)
-				zone->compact_cached_free_pfn = pfn;
-		}
+	pfn = page_to_pfn(page);
+
+	/* Update where async and sync compaction should restart */
+	if (migrate_scanner) {
+		if (cc->finished_update_migrate)
+			return;
+		if (pfn > zone->compact_cached_migrate_pfn[0])
+			zone->compact_cached_migrate_pfn[0] = pfn;
+		if (cc->mode != MIGRATE_ASYNC &&
+		    pfn > zone->compact_cached_migrate_pfn[1])
+			zone->compact_cached_migrate_pfn[1] = pfn;
+	} else {
+		if (cc->finished_update_free)
+			return;
+		if (pfn < zone->compact_cached_free_pfn)
+			zone->compact_cached_free_pfn = pfn;
 	}
 }
 #else
@@ -166,7 +180,7 @@ static inline bool isolation_suitable(struct compact_control *cc,
 
 static void update_pageblock_skip(struct compact_control *cc,
 			struct page *page, unsigned long nr_isolated,
-			bool migrate_scanner)
+			bool set_unsuitable, bool migrate_scanner)
 {
 }
 #endif /* CONFIG_COMPACTION */
@@ -195,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
 		}
 
 		/* async aborts if taking too long or contended */
-		if (!cc->sync) {
+		if (cc->mode == MIGRATE_ASYNC) {
 			cc->contended = true;
 			return false;
 		}
@@ -208,30 +222,39 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
 	return true;
 }
 
-static inline bool compact_trylock_irqsave(spinlock_t *lock,
-			unsigned long *flags, struct compact_control *cc)
+/*
+ * Aside from avoiding lock contention, compaction also periodically checks
+ * need_resched() and either schedules in sync compaction or aborts async
+ * compaction. This is similar to what compact_checklock_irqsave() does, but
+ * is used where no lock is concerned.
+ *
+ * Returns false when no scheduling was needed, or sync compaction scheduled.
+ * Returns true when async compaction should abort.
+ */
+static inline bool compact_should_abort(struct compact_control *cc)
 {
-	return compact_checklock_irqsave(lock, flags, false, cc);
+	/* async compaction aborts if contended */
+	if (need_resched()) {
+		if (cc->mode == MIGRATE_ASYNC) {
+			cc->contended = true;
+			return true;
+		}
+
+		cond_resched();
+	}
+
+	return false;
 }
 
 /* Returns true if the page is within a block suitable for migration to */
 static bool suitable_migration_target(struct page *page)
 {
-	int migratetype = get_pageblock_migratetype(page);
-
-	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
-	if (migratetype == MIGRATE_RESERVE)
-		return false;
-
-	if (is_migrate_isolate(migratetype))
-		return false;
-
-	/* If the page is a large free page, then allow migration */
+	/* If the page is a large free page, then disallow migration */
 	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return true;
+		return false;
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
-	if (migrate_async_suitable(migratetype))
+	if (migrate_async_suitable(get_pageblock_migratetype(page)))
 		return true;
 
 	/* Otherwise skip the block */
@@ -253,6 +276,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	struct page *cursor, *valid_page = NULL;
 	unsigned long flags;
 	bool locked = false;
+	bool checked_pageblock = false;
 
 	cursor = pfn_to_page(blockpfn);
 
@@ -284,8 +308,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 			break;
 
 		/* Recheck this is a suitable migration target under lock */
-		if (!strict && !suitable_migration_target(page))
-			break;
+		if (!strict && !checked_pageblock) {
+			/*
+			 * We need to check suitability of pageblock only once
+			 * and this isolate_freepages_block() is called with
+			 * pageblock range, so just check once is sufficient.
+			 */
+			checked_pageblock = true;
+			if (!suitable_migration_target(page))
+				break;
+		}
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
@@ -329,7 +361,8 @@ isolate_fail:
 
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, total_isolated, false);
+		update_pageblock_skip(cc, valid_page, total_isolated, true,
+				      false);
 
 	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
 	if (total_isolated)
@@ -460,12 +493,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
-	isolate_mode_t mode = 0;
 	struct lruvec *lruvec;
 	unsigned long flags;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
-	bool skipped_async_unsuitable = false;
+	bool set_unsuitable = true;
+	const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ?
+					ISOLATE_ASYNC_MIGRATE : 0) |
+				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -474,7 +509,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	 */
 	while (unlikely(too_many_isolated(zone))) {
 		/* async migration should just abort */
-		if (!cc->sync)
+		if (cc->mode == MIGRATE_ASYNC)
 			return 0;
 
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -483,11 +518,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			return 0;
 	}
 
+	if (compact_should_abort(cc))
+		return 0;
+
 	/* Time to isolate some pages for migration */
-	cond_resched();
 	for (; low_pfn < end_pfn; low_pfn++) {
 		/* give a chance to irqs before checking need_resched() */
-		if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) {
+		if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
 			if (should_release_lock(&zone->lru_lock)) {
 				spin_unlock_irqrestore(&zone->lru_lock, flags);
 				locked = false;
@@ -526,8 +563,25 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 		/* If isolation recently failed, do not retry */
 		pageblock_nr = low_pfn >> pageblock_order;
-		if (!isolation_suitable(cc, page))
-			goto next_pageblock;
+		if (last_pageblock_nr != pageblock_nr) {
+			int mt;
+
+			last_pageblock_nr = pageblock_nr;
+			if (!isolation_suitable(cc, page))
+				goto next_pageblock;
+
+			/*
+			 * For async migration, also only scan in MOVABLE
+			 * blocks. Async migration is optimistic to see if
+			 * the minimum amount of work satisfies the allocation
+			 */
+			mt = get_pageblock_migratetype(page);
+			if (cc->mode == MIGRATE_ASYNC &&
+			    !migrate_async_suitable(mt)) {
+				set_unsuitable = false;
+				goto next_pageblock;
+			}
+		}
 
 		/*
 		 * Skip if free. page_order cannot be used without zone->lock
@@ -537,18 +591,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 
 		/*
-		 * For async migration, also only scan in MOVABLE blocks. Async
-		 * migration is optimistic to see if the minimum amount of work
-		 * satisfies the allocation
-		 */
-		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
-		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
-			cc->finished_update_migrate = true;
-			skipped_async_unsuitable = true;
-			goto next_pageblock;
-		}
-
-		/*
 		 * Check may be lockless but that's ok as we recheck later.
 		 * It's possible to migrate LRU pages and balloon pages
 		 * Skip any other type of page
@@ -557,11 +599,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			if (unlikely(balloon_page_movable(page))) {
 				if (locked && balloon_page_isolate(page)) {
 					/* Successfully isolated */
-					cc->finished_update_migrate = true;
-					list_add(&page->lru, migratelist);
-					cc->nr_migratepages++;
-					nr_isolated++;
-					goto check_compact_cluster;
+					goto isolate_success;
 				}
 			}
 			continue;
@@ -584,6 +622,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
+		/*
+		 * Migration will fail if an anonymous page is pinned in memory,
+		 * so avoid taking lru_lock and isolating it unnecessarily in an
+		 * admittedly racy check.
+		 */
+		if (!page_mapping(page) &&
+		    page_count(page) > page_mapcount(page))
+			continue;
+
 		/* Check if it is ok to still hold the lock */
 		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
 								locked, cc);
@@ -598,12 +645,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
-		if (!cc->sync)
-			mode |= ISOLATE_ASYNC_MIGRATE;
-
-		if (unevictable)
-			mode |= ISOLATE_UNEVICTABLE;
-
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 
 		/* Try isolate the page */
@@ -613,13 +654,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
 
 		/* Successfully isolated */
-		cc->finished_update_migrate = true;
 		del_page_from_lru_list(page, lruvec, page_lru(page));
+
+isolate_success:
+		cc->finished_update_migrate = true;
 		list_add(&page->lru, migratelist);
 		cc->nr_migratepages++;
 		nr_isolated++;
 
-check_compact_cluster:
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
 			++low_pfn;
@@ -630,7 +672,6 @@ check_compact_cluster:
 
 next_pageblock:
 		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
-		last_pageblock_nr = pageblock_nr;
 	}
 
 	acct_isolated(zone, locked, cc);
@@ -641,11 +682,10 @@ next_pageblock:
 	/*
 	 * Update the pageblock-skip information and cached scanner pfn,
 	 * if the whole pageblock was scanned without isolating any page.
-	 * This is not done when pageblock was skipped due to being unsuitable
-	 * for async compaction, so that eventual sync compaction can try.
 	 */
-	if (low_pfn == end_pfn && !skipped_async_unsuitable)
-		update_pageblock_skip(cc, valid_page, nr_isolated, true);
+	if (low_pfn == end_pfn)
+		update_pageblock_skip(cc, valid_page, nr_isolated,
+				      set_unsuitable, true);
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
@@ -666,44 +706,48 @@ static void isolate_freepages(struct zone *zone,
 				struct compact_control *cc)
 {
 	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+	unsigned long block_start_pfn;	/* start of current pageblock */
+	unsigned long block_end_pfn;	/* end of current pageblock */
+	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
 	/*
 	 * Initialise the free scanner. The starting point is where we last
-	 * scanned from (or the end of the zone if starting). The low point
-	 * is the end of the pageblock the migration scanner is using.
+	 * successfully isolated from, zone-cached value, or the end of the
+	 * zone when isolating for the first time. We need this aligned to
+	 * the pageblock boundary, because we do
+	 * block_start_pfn -= pageblock_nr_pages in the for loop.
+	 * For ending point, take care when isolating in last pageblock of a
+	 * a zone which ends in the middle of a pageblock.
+	 * The low boundary is the end of the pageblock the migration scanner
+	 * is using.
 	 */
-	pfn = cc->free_pfn;
+	block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+	block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
+						zone_end_pfn(zone));
 	low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
 
 	/*
-	 * Take care that if the migration scanner is at the end of the zone
-	 * that the free scanner does not accidentally move to the next zone
-	 * in the next isolation cycle.
-	 */
-	high_pfn = min(low_pfn, pfn);
-
-	z_end_pfn = zone_end_pfn(zone);
-
-	/*
 	 * Isolate free pages until enough are available to migrate the
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
-					pfn -= pageblock_nr_pages) {
+	for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
+				block_end_pfn = block_start_pfn,
+				block_start_pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
 
 		/*
 		 * This can iterate a massively long zone without finding any
 		 * suitable migration targets, so periodically check if we need
-		 * to schedule.
+		 * to schedule, or even abort async compaction.
 		 */
-		cond_resched();
+		if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
+						&& compact_should_abort(cc))
+			break;
 
-		if (!pfn_valid(pfn))
+		if (!pfn_valid(block_start_pfn))
 			continue;
 
 		/*
@@ -713,7 +757,7 @@ static void isolate_freepages(struct zone *zone,
 		 * i.e. it's possible that all pages within a zones range of
 		 * pages do not belong to a single zone.
 		 */
-		page = pfn_to_page(pfn);
+		page = pfn_to_page(block_start_pfn);
 		if (page_zone(page) != zone)
 			continue;
 
@@ -726,29 +770,26 @@ static void isolate_freepages(struct zone *zone,
 			continue;
 
 		/* Found a block suitable for isolating free pages from */
-		isolated = 0;
+		cc->free_pfn = block_start_pfn;
+		isolated = isolate_freepages_block(cc, block_start_pfn,
+					block_end_pfn, freelist, false);
+		nr_freepages += isolated;
 
 		/*
-		 * As pfn may not start aligned, pfn+pageblock_nr_page
-		 * may cross a MAX_ORDER_NR_PAGES boundary and miss
-		 * a pfn_valid check. Ensure isolate_freepages_block()
-		 * only scans within a pageblock
+		 * Set a flag that we successfully isolated in this pageblock.
+		 * In the next loop iteration, zone->compact_cached_free_pfn
+		 * will not be updated and thus it will effectively contain the
+		 * highest pageblock we isolated pages from.
 		 */
-		end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
-		end_pfn = min(end_pfn, z_end_pfn);
-		isolated = isolate_freepages_block(cc, pfn, end_pfn,
-						   freelist, false);
-		nr_freepages += isolated;
+		if (isolated)
+			cc->finished_update_free = true;
 
 		/*
-		 * Record the highest PFN we isolated pages from. When next
-		 * looking for free pages, the search will restart here as
-		 * page migration may have returned some pages to the allocator
+		 * isolate_freepages_block() might have aborted due to async
+		 * compaction being contended
 		 */
-		if (isolated) {
-			cc->finished_update_free = true;
-			high_pfn = max(high_pfn, pfn);
-		}
+		if (cc->contended)
+			break;
 	}
 
 	/* split_free_page does not map the pages */
@@ -758,10 +799,9 @@ static void isolate_freepages(struct zone *zone,
 	 * If we crossed the migrate scanner, we want to keep it that way
 	 * so that compact_finished() may detect this
 	 */
-	if (pfn < low_pfn)
-		cc->free_pfn = max(pfn, zone->zone_start_pfn);
-	else
-		cc->free_pfn = high_pfn;
+	if (block_start_pfn < low_pfn)
+		cc->free_pfn = cc->migrate_pfn;
+
 	cc->nr_freepages = nr_freepages;
 }
 
@@ -776,9 +816,13 @@ static struct page *compaction_alloc(struct page *migratepage,
 	struct compact_control *cc = (struct compact_control *)data;
 	struct page *freepage;
 
-	/* Isolate free pages if necessary */
+	/*
+	 * Isolate free pages if necessary, and if we are not aborting due to
+	 * contention.
+	 */
 	if (list_empty(&cc->freepages)) {
-		isolate_freepages(cc->zone, cc);
+		if (!cc->contended)
+			isolate_freepages(cc->zone, cc);
 
 		if (list_empty(&cc->freepages))
 			return NULL;
@@ -792,23 +836,16 @@ static struct page *compaction_alloc(struct page *migratepage,
 }
 
 /*
- * We cannot control nr_migratepages and nr_freepages fully when migration is
- * running as migrate_pages() has no knowledge of compact_control. When
- * migration is complete, we count the number of pages on the lists by hand.
+ * This is a migrate-callback that "frees" freepages back to the isolated
+ * freelist.  All pages on the freelist are from the same zone, so there is no
+ * special handling needed for NUMA.
  */
-static void update_nr_listpages(struct compact_control *cc)
+static void compaction_free(struct page *page, unsigned long data)
 {
-	int nr_migratepages = 0;
-	int nr_freepages = 0;
-	struct page *page;
-
-	list_for_each_entry(page, &cc->migratepages, lru)
-		nr_migratepages++;
-	list_for_each_entry(page, &cc->freepages, lru)
-		nr_freepages++;
+	struct compact_control *cc = (struct compact_control *)data;
 
-	cc->nr_migratepages = nr_migratepages;
-	cc->nr_freepages = nr_freepages;
+	list_add(&page->lru, &cc->freepages);
+	cc->nr_freepages++;
 }
 
 /* possible outcome of isolate_migratepages */
@@ -855,13 +892,14 @@ static int compact_finished(struct zone *zone,
 	unsigned int order;
 	unsigned long watermark;
 
-	if (fatal_signal_pending(current))
+	if (cc->contended || fatal_signal_pending(current))
 		return COMPACT_PARTIAL;
 
 	/* Compaction run completes if the migrate and free scanner meet */
 	if (cc->free_pfn <= cc->migrate_pfn) {
 		/* Let the next compaction start anew. */
-		zone->compact_cached_migrate_pfn = zone->zone_start_pfn;
+		zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
+		zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
 		zone->compact_cached_free_pfn = zone_end_pfn(zone);
 
 		/*
@@ -961,6 +999,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	int ret;
 	unsigned long start_pfn = zone->zone_start_pfn;
 	unsigned long end_pfn = zone_end_pfn(zone);
+	const bool sync = cc->mode != MIGRATE_ASYNC;
 
 	ret = compaction_suitable(zone, cc->order);
 	switch (ret) {
@@ -986,7 +1025,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	 * information on where the scanners should start but check that it
 	 * is initialised by ensuring the values are within zone boundaries.
 	 */
-	cc->migrate_pfn = zone->compact_cached_migrate_pfn;
+	cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
 	cc->free_pfn = zone->compact_cached_free_pfn;
 	if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
 		cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
@@ -994,7 +1033,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	}
 	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
 		cc->migrate_pfn = start_pfn;
-		zone->compact_cached_migrate_pfn = cc->migrate_pfn;
+		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
+		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
 	}
 
 	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn);
@@ -1002,7 +1042,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	migrate_prep_local();
 
 	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
-		unsigned long nr_migrate, nr_remaining;
 		int err;
 
 		switch (isolate_migratepages(zone, cc)) {
@@ -1017,21 +1056,20 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			;
 		}
 
-		nr_migrate = cc->nr_migratepages;
+		if (!cc->nr_migratepages)
+			continue;
+
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
-				(unsigned long)cc,
-				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
+				compaction_free, (unsigned long)cc, cc->mode,
 				MR_COMPACTION);
-		update_nr_listpages(cc);
-		nr_remaining = cc->nr_migratepages;
 
-		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
-						nr_remaining);
+		trace_mm_compaction_migratepages(cc->nr_migratepages, err,
+							&cc->migratepages);
 
-		/* Release isolated pages not migrated */
+		/* All pages were either migrated or will be released */
+		cc->nr_migratepages = 0;
 		if (err) {
 			putback_movable_pages(&cc->migratepages);
-			cc->nr_migratepages = 0;
 			/*
 			 * migrate_pages() may return -ENOMEM when scanners meet
 			 * and we want compact_finished() to detect it
@@ -1053,9 +1091,8 @@ out:
 	return ret;
 }
 
-static unsigned long compact_zone_order(struct zone *zone,
-				 int order, gfp_t gfp_mask,
-				 bool sync, bool *contended)
+static unsigned long compact_zone_order(struct zone *zone, int order,
+		gfp_t gfp_mask, enum migrate_mode mode, bool *contended)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1064,7 +1101,7 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.order = order,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
-		.sync = sync,
+		.mode = mode,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1086,7 +1123,7 @@ int sysctl_extfrag_threshold = 500;
  * @order: The order of the current allocation
  * @gfp_mask: The GFP mask of the current allocation
  * @nodemask: The allowed nodes to allocate from
- * @sync: Whether migration is synchronous or not
+ * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that is true if compaction was aborted due to lock contention
  * @page: Optionally capture a free page of the requested order during compaction
  *
@@ -1094,7 +1131,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended)
+			enum migrate_mode mode, bool *contended)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1119,7 +1156,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 								nodemask) {
 		int status;
 
-		status = compact_zone_order(zone, order, gfp_mask, sync,
+		status = compact_zone_order(zone, order, gfp_mask, mode,
 						contended);
 		rc = max(status, rc);
 
@@ -1158,9 +1195,6 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 			if (zone_watermark_ok(zone, cc->order,
 						low_wmark_pages(zone), 0, 0))
 				compaction_defer_reset(zone, cc->order, false);
-			/* Currently async compaction is never deferred. */
-			else if (cc->sync)
-				defer_compaction(zone, cc->order);
 		}
 
 		VM_BUG_ON(!list_empty(&cc->freepages));
@@ -1172,7 +1206,7 @@ void compact_pgdat(pg_data_t *pgdat, int order)
 {
 	struct compact_control cc = {
 		.order = order,
-		.sync = false,
+		.mode = MIGRATE_ASYNC,
 	};
 
 	if (!order)
@@ -1185,7 +1219,8 @@ static void compact_node(int nid)
 {
 	struct compact_control cc = {
 		.order = -1,
-		.sync = true,
+		.mode = MIGRATE_SYNC,
+		.ignore_skip_hint = true,
 	};
 
 	__compact_pgdat(NODE_DATA(nid), &cc);
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
new file mode 100644
index 000000000000..e10ccd299d66
--- /dev/null
+++ b/mm/early_ioremap.c
@@ -0,0 +1,245 @@
+/*
+ * Provide common bits of early_ioremap() support for architectures needing
+ * temporary mappings during boot before ioremap() is available.
+ *
+ * This is mostly a direct copy of the x86 early_ioremap implementation.
+ *
+ * (C) Copyright 1995 1996, 2014 Linus Torvalds
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <asm/fixmap.h>
+
+#ifdef CONFIG_MMU
+static int early_ioremap_debug __initdata;
+
+static int __init early_ioremap_debug_setup(char *str)
+{
+	early_ioremap_debug = 1;
+
+	return 0;
+}
+early_param("early_ioremap_debug", early_ioremap_debug_setup);
+
+static int after_paging_init __initdata;
+
+void __init __weak early_ioremap_shutdown(void)
+{
+}
+
+void __init early_ioremap_reset(void)
+{
+	early_ioremap_shutdown();
+	after_paging_init = 1;
+}
+
+/*
+ * Generally, ioremap() is available after paging_init() has been called.
+ * Architectures wanting to allow early_ioremap after paging_init() can
+ * define __late_set_fixmap and __late_clear_fixmap to do the right thing.
+ */
+#ifndef __late_set_fixmap
+static inline void __init __late_set_fixmap(enum fixed_addresses idx,
+					    phys_addr_t phys, pgprot_t prot)
+{
+	BUG();
+}
+#endif
+
+#ifndef __late_clear_fixmap
+static inline void __init __late_clear_fixmap(enum fixed_addresses idx)
+{
+	BUG();
+}
+#endif
+
+static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
+
+void __init early_ioremap_setup(void)
+{
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		if (WARN_ON(prev_map[i]))
+			break;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);
+}
+
+static int __init check_early_ioremap_leak(void)
+{
+	int count = 0;
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+		if (prev_map[i])
+			count++;
+
+	if (WARN(count, KERN_WARNING
+		 "Debug warning: early ioremap leak of %d areas detected.\n"
+		 "please boot with early_ioremap_debug and report the dmesg.\n",
+		 count))
+		return 1;
+	return 0;
+}
+late_initcall(check_early_ioremap_leak);
+
+static void __init __iomem *
+__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
+{
+	unsigned long offset;
+	resource_size_t last_addr;
+	unsigned int nrpages;
+	enum fixed_addresses idx;
+	int i, slot;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (!prev_map[i]) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n",
+		 __func__, (u64)phys_addr, size))
+		return NULL;
+
+	/* Don't allow wraparound or zero size */
+	last_addr = phys_addr + size - 1;
+	if (WARN_ON(!size || last_addr < phys_addr))
+		return NULL;
+
+	prev_size[slot] = size;
+	/*
+	 * Mappings have to be page-aligned
+	 */
+	offset = phys_addr & ~PAGE_MASK;
+	phys_addr &= PAGE_MASK;
+	size = PAGE_ALIGN(last_addr + 1) - phys_addr;
+
+	/*
+	 * Mappings have to fit in the FIX_BTMAP area.
+	 */
+	nrpages = size >> PAGE_SHIFT;
+	if (WARN_ON(nrpages > NR_FIX_BTMAPS))
+		return NULL;
+
+	/*
+	 * Ok, go for it..
+	 */
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+	while (nrpages > 0) {
+		if (after_paging_init)
+			__late_set_fixmap(idx, phys_addr, prot);
+		else
+			__early_set_fixmap(idx, phys_addr, prot);
+		phys_addr += PAGE_SIZE;
+		--idx;
+		--nrpages;
+	}
+	WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n",
+	     __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]);
+
+	prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
+	return prev_map[slot];
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+	unsigned long virt_addr;
+	unsigned long offset;
+	unsigned int nrpages;
+	enum fixed_addresses idx;
+	int i, slot;
+
+	slot = -1;
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i] == addr) {
+			slot = i;
+			break;
+		}
+	}
+
+	if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n",
+		 addr, size))
+		return;
+
+	if (WARN(prev_size[slot] != size,
+		 "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n",
+		 addr, size, slot, prev_size[slot]))
+		return;
+
+	WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n",
+	     addr, size, slot);
+
+	virt_addr = (unsigned long)addr;
+	if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)))
+		return;
+
+	offset = virt_addr & ~PAGE_MASK;
+	nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT;
+
+	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+	while (nrpages > 0) {
+		if (after_paging_init)
+			__late_clear_fixmap(idx);
+		else
+			__early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR);
+		--idx;
+		--nrpages;
+	}
+	prev_map[slot] = NULL;
+}
+
+/* Remap an IO device */
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+	return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO);
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (__force void *)__early_ioremap(phys_addr, size,
+					       FIXMAP_PAGE_NORMAL);
+}
+#else /* CONFIG_MMU */
+
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (__force void __iomem *)phys_addr;
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+	return (void *)phys_addr;
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+}
+
+#endif /* CONFIG_MMU */
+
+
+void __init early_memunmap(void *addr, unsigned long size)
+{
+	early_iounmap((__force void __iomem *)addr, size);
+}
diff --git a/mm/filemap.c b/mm/filemap.c
index 7a13f6ac5421..bdaa21555abe 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -192,9 +192,11 @@ static int filemap_check_errors(struct address_space *mapping)
 {
 	int ret = 0;
 	/* Check for outstanding write errors */
-	if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
+	if (test_bit(AS_ENOSPC, &mapping->flags) &&
+	    test_and_clear_bit(AS_ENOSPC, &mapping->flags))
 		ret = -ENOSPC;
-	if (test_and_clear_bit(AS_EIO, &mapping->flags))
+	if (test_bit(AS_EIO, &mapping->flags) &&
+	    test_and_clear_bit(AS_EIO, &mapping->flags))
 		ret = -EIO;
 	return ret;
 }
@@ -446,6 +448,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
+static int page_cache_tree_insert(struct address_space *mapping,
+				  struct page *page)
+{
+	void **slot;
+	int error;
+
+	slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
+	if (slot) {
+		void *p;
+
+		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+		if (!radix_tree_exceptional_entry(p))
+			return -EEXIST;
+		radix_tree_replace_slot(slot, page);
+		mapping->nrpages++;
+		return 0;
+	}
+	error = radix_tree_insert(&mapping->page_tree, page->index, page);
+	if (!error)
+		mapping->nrpages++;
+	return error;
+}
+
 /**
  * add_to_page_cache_locked - add a locked page to the pagecache
  * @page:	page to add
@@ -480,11 +505,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 	page->index = offset;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = radix_tree_insert(&mapping->page_tree, offset, page);
+	error = page_cache_tree_insert(mapping, page);
 	radix_tree_preload_end();
 	if (unlikely(error))
 		goto err_insert;
-	mapping->nrpages++;
 	__inc_zone_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
 	trace_mm_filemap_add_to_page_cache(page);
@@ -520,10 +544,10 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	if (cpuset_do_page_mem_spread()) {
 		unsigned int cpuset_mems_cookie;
 		do {
-			cpuset_mems_cookie = get_mems_allowed();
+			cpuset_mems_cookie = read_mems_allowed_begin();
 			n = cpuset_mem_spread_node();
 			page = alloc_pages_exact_node(n, gfp, 0);
-		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
 
 		return page;
 	}
@@ -686,14 +710,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 }
 
 /**
- * find_get_page - find and get a page reference
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
+			break;
+		index++;
+		if (index == 0)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
+ * page_cache_prev_hole - find the prev hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search backwards in the range [max(index-max_scan+1, 0), index] for
+ * the first hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'index - return >=
+ * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
+ * will be returned.
+ *
+ * page_cache_prev_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 10, then subsequently a hole is created at
+ * index 5, page_cache_prev_hole covering both indexes may return 5 if
+ * called under rcu_read_lock.
+ */
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
+			break;
+		index--;
+		if (index == ULONG_MAX)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_prev_hole);
+
+/**
+ * find_get_entry - find and get a page cache entry
  * @mapping: the address_space to search
- * @offset: the page index
+ * @offset: the page cache index
  *
- * Is there a pagecache struct page at the given (mapping, offset) tuple?
- * If yes, increment its refcount and return it; if no, return NULL.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
  */
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
 {
 	void **pagep;
 	struct page *page;
@@ -734,24 +845,50 @@ out:
 
 	return page;
 }
-EXPORT_SYMBOL(find_get_page);
+EXPORT_SYMBOL(find_get_entry);
 
 /**
- * find_lock_page - locate, pin and lock a pagecache page
+ * find_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * Locates the desired pagecache page, locks it, increments its reference
- * count and returns its address.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
  *
- * Returns zero if the page was not present. find_lock_page() may sleep.
+ * Otherwise, %NULL is returned.
  */
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_get_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
+EXPORT_SYMBOL(find_get_page);
+
+/**
+ * find_lock_entry - locate, pin and lock a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_entry() may sleep.
+ */
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
 {
 	struct page *page;
 
 repeat:
-	page = find_get_page(mapping, offset);
+	page = find_get_entry(mapping, offset);
 	if (page && !radix_tree_exception(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
@@ -764,6 +901,29 @@ repeat:
 	}
 	return page;
 }
+EXPORT_SYMBOL(find_lock_entry);
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_page() may sleep.
+ */
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_lock_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
 EXPORT_SYMBOL(find_lock_page);
 
 /**
@@ -772,16 +932,18 @@ EXPORT_SYMBOL(find_lock_page);
  * @index: the page's index into the mapping
  * @gfp_mask: page allocation mode
  *
- * Locates a page in the pagecache.  If the page is not present, a new page
- * is allocated using @gfp_mask and is added to the pagecache and to the VM's
- * LRU list.  The returned page is locked and has its reference count
- * incremented.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the page is not present, a new page is allocated using @gfp_mask
+ * and added to the page cache and the VM's LRU list.  The page is
+ * returned locked and with an increased refcount.
  *
- * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
- * allocation!
+ * On memory exhaustion, %NULL is returned.
  *
- * find_or_create_page() returns the desired page's address, or zero on
- * memory exhaustion.
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an
+ * atomic allocation!
  */
 struct page *find_or_create_page(struct address_space *mapping,
 		pgoff_t index, gfp_t gfp_mask)
@@ -814,6 +976,76 @@ repeat:
 EXPORT_SYMBOL(find_or_create_page);
 
 /**
+ * find_get_entries - gang pagecache lookup
+ * @mapping:	The address_space to search
+ * @start:	The starting page cache index
+ * @nr_entries:	The maximum number of entries
+ * @entries:	Where the resulting entries are placed
+ * @indices:	The cache indices corresponding to the entries in @entries
+ *
+ * find_get_entries() will search for and return a group of up to
+ * @nr_entries entries in the mapping.  The entries are placed at
+ * @entries.  find_get_entries() takes a reference against any actual
+ * pages it returns.
+ *
+ * The search returns a group of mapping-contiguous page cache entries
+ * with ascending indexes.  There may be holes in the indices due to
+ * not-present pages.
+ *
+ * Any shadow entries of evicted pages are included in the returned
+ * array.
+ *
+ * find_get_entries() returns the number of pages and shadow entries
+ * which were found.
+ */
+unsigned find_get_entries(struct address_space *mapping,
+			  pgoff_t start, unsigned int nr_entries,
+			  struct page **entries, pgoff_t *indices)
+{
+	void **slot;
+	unsigned int ret = 0;
+	struct radix_tree_iter iter;
+
+	if (!nr_entries)
+		return 0;
+
+	rcu_read_lock();
+restart:
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		struct page *page;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				goto restart;
+			/*
+			 * Otherwise, we must be storing a swap entry
+			 * here as an exceptional entry: so return it
+			 * without attempting to raise page count.
+			 */
+			goto export;
+		}
+		if (!page_cache_get_speculative(page))
+			goto repeat;
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			page_cache_release(page);
+			goto repeat;
+		}
+export:
+		indices[ret] = iter.index;
+		entries[ret] = page;
+		if (++ret == nr_entries)
+			break;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
  * find_get_pages - gang pagecache lookup
  * @mapping:	The address_space to search
  * @start:	The starting page index
@@ -1795,6 +2027,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
 EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
+static struct page *wait_on_page_read(struct page *page)
+{
+	if (!IS_ERR(page)) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page)) {
+			page_cache_release(page);
+			page = ERR_PTR(-EIO);
+		}
+	}
+	return page;
+}
+
 static struct page *__read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
@@ -1821,6 +2065,8 @@ repeat:
 		if (err < 0) {
 			page_cache_release(page);
 			page = ERR_PTR(err);
+		} else {
+			page = wait_on_page_read(page);
 		}
 	}
 	return page;
@@ -1857,6 +2103,10 @@ retry:
 	if (err < 0) {
 		page_cache_release(page);
 		return ERR_PTR(err);
+	} else {
+		page = wait_on_page_read(page);
+		if (IS_ERR(page))
+			return page;
 	}
 out:
 	mark_page_accessed(page);
@@ -1864,40 +2114,25 @@ out:
 }
 
 /**
- * read_cache_page_async - read into page cache, fill it if needed
+ * read_cache_page - read into page cache, fill it if needed
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
  * @data:	first arg to filler(data, page) function, often left as NULL
  *
- * Same as read_cache_page, but don't wait for page to become unlocked
- * after submitting it to the filler.
- *
  * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page but don't wait for it to become unlocked.
+ * not set, try to fill the page and wait for it to become unlocked.
  *
  * If the page does not get brought uptodate, return -EIO.
  */
-struct page *read_cache_page_async(struct address_space *mapping,
+struct page *read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
 }
-EXPORT_SYMBOL(read_cache_page_async);
-
-static struct page *wait_on_page_read(struct page *page)
-{
-	if (!IS_ERR(page)) {
-		wait_on_page_locked(page);
-		if (!PageUptodate(page)) {
-			page_cache_release(page);
-			page = ERR_PTR(-EIO);
-		}
-	}
-	return page;
-}
+EXPORT_SYMBOL(read_cache_page);
 
 /**
  * read_cache_page_gfp - read into page cache, using specified page allocation flags.
@@ -1916,31 +2151,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 {
 	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
 
-	return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp));
+	return do_read_cache_page(mapping, index, filler, NULL, gfp);
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page then wait for it to become unlocked.
- *
- * If the page does not get brought uptodate, return -EIO.
- */
-struct page *read_cache_page(struct address_space *mapping,
-				pgoff_t index,
-				int (*filler)(void *, struct page *),
-				void *data)
-{
-	return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
-}
-EXPORT_SYMBOL(read_cache_page);
-
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
@@ -1974,7 +2188,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 	char *kaddr;
 	size_t copied;
 
-	BUG_ON(!in_atomic());
 	kaddr = kmap_atomic(page);
 	if (likely(i->nr_segs == 1)) {
 		int left;
@@ -2348,9 +2561,7 @@ again:
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		mark_page_accessed(page);
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 1b24bdcb3197..f2a3571c6e22 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -244,8 +244,10 @@ int __frontswap_store(struct page *page)
 		  the (older) page from frontswap
 		 */
 		inc_frontswap_failed_stores();
-		if (dup)
+		if (dup) {
 			__frontswap_clear(sis, offset);
+			frontswap_ops->invalidate_page(type, offset);
+		}
 	}
 	if (frontswap_writethrough_enabled)
 		/* report failure so swap also writes to swap device */
@@ -327,15 +329,12 @@ EXPORT_SYMBOL(__frontswap_invalidate_area);
 
 static unsigned long __frontswap_curr_pages(void)
 {
-	int type;
 	unsigned long totalpages = 0;
 	struct swap_info_struct *si = NULL;
 
 	assert_spin_locked(&swap_lock);
-	for (type = swap_list.head; type >= 0; type = si->next) {
-		si = swap_info[type];
+	plist_for_each_entry(si, &swap_active_head, list)
 		totalpages += atomic_read(&si->frontswap_pages);
-	}
 	return totalpages;
 }
 
@@ -347,11 +346,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
 	int si_frontswap_pages;
 	unsigned long total_pages_to_unuse = total;
 	unsigned long pages = 0, pages_to_unuse = 0;
-	int type;
 
 	assert_spin_locked(&swap_lock);
-	for (type = swap_list.head; type >= 0; type = si->next) {
-		si = swap_info[type];
+	plist_for_each_entry(si, &swap_active_head, list) {
 		si_frontswap_pages = atomic_read(&si->frontswap_pages);
 		if (total_pages_to_unuse < si_frontswap_pages) {
 			pages = pages_to_unuse = total_pages_to_unuse;
@@ -366,7 +363,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
 		}
 		vm_unacct_memory(pages);
 		*unused = pages_to_unuse;
-		*swapid = type;
+		*swapid = si->type;
 		ret = 0;
 		break;
 	}
@@ -413,7 +410,7 @@ void frontswap_shrink(unsigned long target_pages)
 	/*
 	 * we don't want to hold swap_lock while doing a very
 	 * lengthy try_to_unuse, but swap_list may change
-	 * so restart scan from swap_list.head each time
+	 * so restart scan from swap_active_head each time
 	 */
 	spin_lock(&swap_lock);
 	ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1546655a2d78..331faa5c0d5e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -199,7 +199,7 @@ retry:
 	preempt_disable();
 	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
 		preempt_enable();
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		goto retry;
 	}
 
@@ -231,7 +231,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		return HPAGE_PMD_NR;
 	}
 
@@ -1611,16 +1611,23 @@ pmd_t *page_check_address_pmd(struct page *page,
 			      enum page_check_address_pmd_flag flag,
 			      spinlock_t **ptl)
 {
+	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 
 	if (address & ~HPAGE_PMD_MASK)
 		return NULL;
 
-	pmd = mm_find_pmd(mm, address);
-	if (!pmd)
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
 		return NULL;
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		return NULL;
+	pmd = pmd_offset(pud, address);
+
 	*ptl = pmd_lock(mm, pmd);
-	if (pmd_none(*pmd))
+	if (!pmd_present(*pmd))
 		goto unlock;
 	if (pmd_page(*pmd) != page)
 		goto unlock;
@@ -1812,21 +1819,24 @@ static int __split_huge_page_map(struct page *page,
 	if (pmd) {
 		pgtable = pgtable_trans_huge_withdraw(mm, pmd);
 		pmd_populate(mm, &_pmd, pgtable);
+		if (pmd_write(*pmd))
+			BUG_ON(page_mapcount(page) != 1);
 
 		haddr = address;
 		for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
 			pte_t *pte, entry;
 			BUG_ON(PageCompound(page+i));
+			/*
+			 * Note that pmd_numa is not transferred deliberately
+			 * to avoid any possibility that pte_numa leaks to
+			 * a PROT_NONE VMA by accident.
+			 */
 			entry = mk_pte(page + i, vma->vm_page_prot);
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 			if (!pmd_write(*pmd))
 				entry = pte_wrprotect(entry);
-			else
-				BUG_ON(page_mapcount(page) != 1);
 			if (!pmd_young(*pmd))
 				entry = pte_mkold(entry);
-			if (pmd_numa(*pmd))
-				entry = pte_mknuma(entry);
 			pte = pte_offset_map(&_pmd, haddr);
 			BUG_ON(!pte_none(*pte));
 			set_pte_at(mm, haddr, pte, entry);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c01cb9fedb18..67d0c175efcf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -540,7 +540,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 		goto err;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask(h), &mpol, &nodemask);
 
@@ -562,7 +562,7 @@ retry_cpuset:
 	}
 
 	mpol_cond_put(mpol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 
@@ -1134,6 +1134,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	while (nr_pages--) {
 		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 }
 
@@ -1509,6 +1510,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	while (min_count < persistent_huge_pages(h)) {
 		if (!free_pool_huge_page(h, nodes_allowed, 0))
 			break;
+		cond_resched_lock(&hugetlb_lock);
 	}
 	while (count < persistent_huge_pages(h)) {
 		if (!adjust_pool_surplus(h, nodes_allowed, 1))
@@ -2069,6 +2071,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	unsigned long tmp;
 	int ret;
 
+	if (!hugepages_supported())
+		return -ENOTSUPP;
+
 	tmp = h->max_huge_pages;
 
 	if (write && h->order >= MAX_ORDER)
@@ -2122,6 +2127,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	unsigned long tmp;
 	int ret;
 
+	if (!hugepages_supported())
+		return -ENOTSUPP;
+
 	tmp = h->nr_overcommit_huge_pages;
 
 	if (write && h->order >= MAX_ORDER)
@@ -2147,6 +2155,8 @@ out:
 void hugetlb_report_meminfo(struct seq_file *m)
 {
 	struct hstate *h = &default_hstate;
+	if (!hugepages_supported())
+		return;
 	seq_printf(m,
 			"HugePages_Total:   %5lu\n"
 			"HugePages_Free:    %5lu\n"
@@ -2163,6 +2173,8 @@ void hugetlb_report_meminfo(struct seq_file *m)
 int hugetlb_report_node_meminfo(int nid, char *buf)
 {
 	struct hstate *h = &default_hstate;
+	if (!hugepages_supported())
+		return 0;
 	return sprintf(buf,
 		"Node %d HugePages_Total: %5u\n"
 		"Node %d HugePages_Free:  %5u\n"
@@ -2177,6 +2189,9 @@ void hugetlb_show_meminfo(void)
 	struct hstate *h;
 	int nid;
 
+	if (!hugepages_supported())
+		return;
+
 	for_each_node_state(nid, N_MEMORY)
 		for_each_hstate(h)
 			pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
@@ -2336,6 +2351,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 		update_mmu_cache(vma, address, ptep);
 }
 
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_migration_entry(swp))
+		return 1;
+	else
+		return 0;
+}
+
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
+		return 1;
+	else
+		return 0;
+}
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
@@ -2375,7 +2415,24 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
-		if (!huge_pte_none(huge_ptep_get(src_pte))) {
+		entry = huge_ptep_get(src_pte);
+		if (huge_pte_none(entry)) { /* skip none entry */
+			;
+		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
+				    is_hugetlb_entry_hwpoisoned(entry))) {
+			swp_entry_t swp_entry = pte_to_swp_entry(entry);
+
+			if (is_write_migration_entry(swp_entry) && cow) {
+				/*
+				 * COW mappings require pages in both
+				 * parent and child to be set to read.
+				 */
+				make_migration_entry_read(&swp_entry);
+				entry = swp_entry_to_pte(swp_entry);
+				set_huge_pte_at(src, addr, src_pte, entry);
+			}
+			set_huge_pte_at(dst, addr, dst_pte, entry);
+		} else {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 			entry = huge_ptep_get(src_pte);
@@ -2394,32 +2451,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	return ret;
 }
 
-static int is_hugetlb_entry_migration(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
 void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			    unsigned long start, unsigned long end,
 			    struct page *ref_page)
diff --git a/mm/internal.h b/mm/internal.h
index 29e1e761f9eb..1a8a0d4b687a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -11,6 +11,7 @@
 #ifndef __MM_INTERNAL_H
 #define __MM_INTERNAL_H
 
+#include <linux/fs.h>
 #include <linux/mm.h>
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
@@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v)
 	atomic_set(&page->_count, v);
 }
 
+extern int __do_page_cache_readahead(struct address_space *mapping,
+		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+		unsigned long lookahead_size);
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static inline unsigned long ra_submit(struct file_ra_state *ra,
+		struct address_space *mapping, struct file *filp)
+{
+	return __do_page_cache_readahead(mapping, filp,
+					ra->start, ra->size, ra->async_size);
+}
+
 /*
  * Turn a non-refcounted page (->_count == 0) into refcounted with
  * a count of one.
@@ -119,7 +134,7 @@ struct compact_control {
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
-	bool sync;			/* Synchronous migration */
+	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
 	bool finished_update_free;	/* True when the zone cached pfns are
 					 * no longer being updated
@@ -129,7 +144,10 @@ struct compact_control {
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
-	bool contended;			/* True if a lock was contended */
+	bool contended;			/* True if a lock was contended, or
+					 * need_resched() true during async
+					 * compaction
+					 */
 };
 
 unsigned long
@@ -370,5 +388,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
 #define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
+#define ALLOC_FAIR		0x100 /* fair zone allocation */
 
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/madvise.c b/mm/madvise.c
index 539eeb96b323..a402f8fdc68e 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 	for (; start < end; start += PAGE_SIZE) {
 		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
-		page = find_get_page(mapping, index);
+		page = find_get_entry(mapping, index);
 		if (!radix_tree_exceptional_entry(page)) {
 			if (page)
 				page_cache_release(page);
diff --git a/mm/memblock.c b/mm/memblock.c
index 39a31e7f0045..0739dc1b4095 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -183,8 +183,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
 					phys_addr_t end, int nid)
 {
-	int ret;
-	phys_addr_t kernel_end;
+	phys_addr_t kernel_end, ret;
 
 	/* pump up @end */
 	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5b6b0039f725..b58d4fbe6c48 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -292,6 +292,9 @@ struct mem_cgroup {
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
+	/* css_online() has been completed */
+	int initialized;
+
 	/*
 	 * the counter to account for mem+swap usage.
 	 */
@@ -1127,9 +1130,21 @@ skip_node:
 	 * skipping css reference should be safe.
 	 */
 	if (next_css) {
-		if ((next_css == &root->css) ||
-		    ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
-			return mem_cgroup_from_css(next_css);
+		struct mem_cgroup *memcg = mem_cgroup_from_css(next_css);
+
+		if (next_css == &root->css)
+			return memcg;
+
+		if (css_tryget(next_css)) {
+			/*
+			 * Make sure the memcg is initialized:
+			 * mem_cgroup_css_online() orders the the
+			 * initialization against setting the flag.
+			 */
+			if (smp_load_acquire(&memcg->initialized))
+				return memcg;
+			css_put(next_css);
+		}
 
 		prev_css = next_css;
 		goto skip_node;
@@ -5670,8 +5685,12 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup_eventfd_list *ev;
 
+	spin_lock(&memcg_oom_lock);
+
 	list_for_each_entry(ev, &memcg->oom_notify, list)
 		eventfd_signal(ev->eventfd, 1);
+
+	spin_unlock(&memcg_oom_lock);
 	return 0;
 }
 
@@ -6534,6 +6553,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
+	int ret;
 
 	if (css->cgroup->id > MEM_CGROUP_ID_MAX)
 		return -ENOSPC;
@@ -6570,7 +6590,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	}
 	mutex_unlock(&memcg_create_mutex);
 
-	return memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	ret = memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure the memcg is initialized: mem_cgroup_iter()
+	 * orders reading memcg->initialized against its callers
+	 * reading the memcg members.
+	 */
+	smp_store_release(&memcg->initialized, 1);
+
+	return 0;
 }
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 90002ea43638..a98c7fce470a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
 #endif
 	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
 
-	if ((flags & MF_ACTION_REQUIRED) && t == current) {
+	if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
 		si.si_code = BUS_MCEERR_AR;
-		ret = force_sig_info(SIGBUS, &si, t);
+		ret = force_sig_info(SIGBUS, &si, current);
 	} else {
 		/*
 		 * Don't use force here, it's convenient if the signal
@@ -384,20 +384,51 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 	}
 }
 
-static int task_early_kill(struct task_struct *tsk)
+/*
+ * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO)
+ * on behalf of the thread group. Return task_struct of the (first found)
+ * dedicated thread if found, and return NULL otherwise.
+ *
+ * We already hold read_lock(&tasklist_lock) in the caller, so we don't
+ * have to call rcu_read_lock/unlock() in this function.
+ */
+static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
 {
+	struct task_struct *t;
+
+	for_each_thread(tsk, t)
+		if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY))
+			return t;
+	return NULL;
+}
+
+/*
+ * Determine whether a given process is "early kill" process which expects
+ * to be signaled when some page under the process is hwpoisoned.
+ * Return task_struct of the dedicated thread (main thread unless explicitly
+ * specified) if the process is "early kill," and otherwise returns NULL.
+ */
+static struct task_struct *task_early_kill(struct task_struct *tsk,
+					   int force_early)
+{
+	struct task_struct *t;
 	if (!tsk->mm)
-		return 0;
-	if (tsk->flags & PF_MCE_PROCESS)
-		return !!(tsk->flags & PF_MCE_EARLY);
-	return sysctl_memory_failure_early_kill;
+		return NULL;
+	if (force_early)
+		return tsk;
+	t = find_early_kill_thread(tsk);
+	if (t)
+		return t;
+	if (sysctl_memory_failure_early_kill)
+		return tsk;
+	return NULL;
 }
 
 /*
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -412,16 +443,17 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
+		struct task_struct *t = task_early_kill(tsk, force_early);
 
-		if (!task_early_kill(tsk))
+		if (!t)
 			continue;
 		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
 					       pgoff, pgoff) {
 			vma = vmac->vma;
 			if (!page_mapped_in_vma(page, vma))
 				continue;
-			if (vma->vm_mm == tsk->mm)
-				add_to_kill(tsk, page, vma, to_kill, tkc);
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, vma, to_kill, tkc);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -432,7 +464,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -442,10 +474,10 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+		struct task_struct *t = task_early_kill(tsk, force_early);
 
-		if (!task_early_kill(tsk))
+		if (!t)
 			continue;
-
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
 				      pgoff) {
 			/*
@@ -455,8 +487,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * Assume applications who requested early kill want
 			 * to be informed of all such data corruptions.
 			 */
-			if (vma->vm_mm == tsk->mm)
-				add_to_kill(tsk, page, vma, to_kill, tkc);
+			if (vma->vm_mm == t->mm)
+				add_to_kill(t, page, vma, to_kill, tkc);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -469,7 +501,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
  * First preallocate one tokill structure outside the spin locks,
  * so that we can kill at least one process reasonably reliable.
  */
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+				int force_early)
 {
 	struct to_kill *tk;
 
@@ -480,9 +513,9 @@ static void collect_procs(struct page *page, struct list_head *tokill)
 	if (!tk)
 		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk);
+		collect_procs_anon(page, tokill, &tk, force_early);
 	else
-		collect_procs_file(page, tokill, &tk);
+		collect_procs_file(page, tokill, &tk, force_early);
 	kfree(tk);
 }
 
@@ -967,7 +1000,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(ppage, &tokill);
+		collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED);
 
 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
@@ -1085,15 +1118,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			return 0;
 		} else if (PageHuge(hpage)) {
 			/*
-			 * Check "just unpoisoned", "filter hit", and
-			 * "race with other subpage."
+			 * Check "filter hit" and "race with other subpage."
 			 */
 			lock_page(hpage);
-			if (!PageHWPoison(hpage)
-			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
-			    || (p != hpage && TestSetPageHWPoison(hpage))) {
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-				return 0;
+			if (PageHWPoison(hpage)) {
+				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+				    || (p != hpage && TestSetPageHWPoison(hpage))) {
+					atomic_long_sub(nr_pages, &num_poisoned_pages);
+					unlock_page(hpage);
+					return 0;
+				}
 			}
 			set_page_hwpoison_huge_page(hpage);
 			res = dequeue_hwpoisoned_huge_page(hpage);
@@ -1156,6 +1190,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
+		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		put_page(hpage);
 		res = 0;
 		goto out;
 	}
@@ -1504,7 +1540,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 
 	/* Keep page count to indicate a given hugepage is isolated. */
 	list_move(&hpage->lru, &pagelist);
-	ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+	ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 				MIGRATE_SYNC, MR_MEMORY_FAILURE);
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
@@ -1585,7 +1621,7 @@ static int __soft_offline_page(struct page *page, int flags)
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
-		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
 			if (!list_empty(&pagelist)) {
diff --git a/mm/memory.c b/mm/memory.c
index 22dfa617bddb..fcc849d1eb5a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -117,6 +117,8 @@ __setup("norandmaps", disable_randmaps);
 unsigned long zero_pfn __read_mostly;
 unsigned long highest_memmap_pfn __read_mostly;
 
+EXPORT_SYMBOL(zero_pfn);
+
 /*
  * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
  */
@@ -808,20 +810,20 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		if (!pte_file(pte)) {
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
-			if (swap_duplicate(entry) < 0)
-				return entry.val;
-
-			/* make sure dst_mm is on swapoff's mmlist. */
-			if (unlikely(list_empty(&dst_mm->mmlist))) {
-				spin_lock(&mmlist_lock);
-				if (list_empty(&dst_mm->mmlist))
-					list_add(&dst_mm->mmlist,
-						 &src_mm->mmlist);
-				spin_unlock(&mmlist_lock);
-			}
-			if (likely(!non_swap_entry(entry)))
+			if (likely(!non_swap_entry(entry))) {
+				if (swap_duplicate(entry) < 0)
+					return entry.val;
+
+				/* make sure dst_mm is on swapoff's mmlist. */
+				if (unlikely(list_empty(&dst_mm->mmlist))) {
+					spin_lock(&mmlist_lock);
+					if (list_empty(&dst_mm->mmlist))
+						list_add(&dst_mm->mmlist,
+							 &src_mm->mmlist);
+					spin_unlock(&mmlist_lock);
+				}
 				rss[MM_SWAPENTS]++;
-			else if (is_migration_entry(entry)) {
+			} else if (is_migration_entry(entry)) {
 				page = migration_entry_to_page(entry);
 
 				if (PageAnon(page))
@@ -1120,7 +1122,7 @@ again:
 						addr) != page->index) {
 				pte_t ptfile = pgoff_to_pte(page->index);
 				if (pte_soft_dirty(ptent))
-					pte_file_mksoft_dirty(ptfile);
+					ptfile = pte_file_mksoft_dirty(ptfile);
 				set_pte_at(mm, addr, pte, ptfile);
 			}
 			if (PageAnon(page))
@@ -1929,12 +1931,17 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long address, unsigned int fault_flags)
 {
 	struct vm_area_struct *vma;
+	vm_flags_t vm_flags;
 	int ret;
 
 	vma = find_extend_vma(mm, address);
 	if (!vma || address < vma->vm_start)
 		return -EFAULT;
 
+	vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
+	if (!(vm_flags & vma->vm_flags))
+		return -EFAULT;
+
 	ret = handle_mm_fault(mm, vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
 		if (ret & VM_FAULT_OOM)
@@ -3199,7 +3206,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (prev && prev->vm_end == address)
 			return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
 
-		expand_downwards(vma, address - PAGE_SIZE);
+		return expand_downwards(vma, address - PAGE_SIZE);
 	}
 	if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
 		struct vm_area_struct *next = vma->vm_next;
@@ -3208,7 +3215,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo
 		if (next && next->vm_start == address + PAGE_SIZE)
 			return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
 
-		expand_upwards(vma, address + PAGE_SIZE);
+		return expand_upwards(vma, address + PAGE_SIZE);
 	}
 	return 0;
 }
@@ -3751,9 +3758,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 	}
 
-	/* THP should already have been handled */
-	BUG_ON(pmd_numa(*pmd));
-
 	/*
 	 * Use __pte_alloc instead of pte_alloc_map, because we can't
 	 * run pte_offset_map on the pmd, if an huge pmd could
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a650db29606f..f6f23833de44 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1332,7 +1332,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		 * alloc_migrate_target should be improooooved!!
 		 * migrate_pages returns # of failed pages.
 		 */
-		ret = migrate_pages(&source, alloc_migrate_target, 0,
+		ret = migrate_pages(&source, alloc_migrate_target, NULL, 0,
 					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
 		if (ret)
 			putback_movable_pages(&source);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ae3c8f3595d4..e8fff0fa1202 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -526,9 +526,13 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma,
 	int nid;
 	struct page *page;
 	spinlock_t *ptl;
+	pte_t entry;
 
 	ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd);
-	page = pte_page(huge_ptep_get((pte_t *)pmd));
+	entry = huge_ptep_get((pte_t *)pmd);
+	if (!pte_present(entry))
+		goto unlock;
+	page = pte_page(entry);
 	nid = page_to_nid(page);
 	if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
 		goto unlock;
@@ -649,19 +653,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
  * @nodes and @flags,) it's isolated and queued to the pagelist which is
  * passed via @private.)
  */
-static struct vm_area_struct *
+static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		const nodemask_t *nodes, unsigned long flags, void *private)
 {
-	int err;
-	struct vm_area_struct *first, *vma, *prev;
-
+	int err = 0;
+	struct vm_area_struct *vma, *prev;
 
-	first = find_vma(mm, start);
-	if (!first)
-		return ERR_PTR(-EFAULT);
+	vma = find_vma(mm, start);
+	if (!vma)
+		return -EFAULT;
 	prev = NULL;
-	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+	for (; vma && vma->vm_start < end; vma = vma->vm_next) {
 		unsigned long endvma = vma->vm_end;
 
 		if (endvma > end)
@@ -671,9 +674,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
 			if (!vma->vm_next && vma->vm_end < end)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 			if (prev && prev->vm_end < vma->vm_start)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 		}
 
 		if (flags & MPOL_MF_LAZY) {
@@ -687,15 +690,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 			err = queue_pages_pgd_range(vma, start, endvma, nodes,
 						flags, private);
-			if (err) {
-				first = ERR_PTR(err);
+			if (err)
 				break;
-			}
 		}
 next:
 		prev = vma;
 	}
-	return first;
+	return err;
 }
 
 /*
@@ -1059,7 +1060,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 			flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, new_node_page, dest,
+		err = migrate_pages(&pagelist, new_node_page, NULL, dest,
 					MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_movable_pages(&pagelist);
@@ -1180,16 +1181,17 @@ out:
 
 /*
  * Allocate a new page for page migration based on vma policy.
- * Start assuming that page is mapped by vma pointed to by @private.
+ * Start by assuming the page is mapped by the same vma as contains @start.
  * Search forward from there, if not.  N.B., this assumes that the
  * list of pages handed to migrate_pages()--which is how we get here--
  * is in virtual address order.
  */
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
-	struct vm_area_struct *vma = (struct vm_area_struct *)private;
+	struct vm_area_struct *vma;
 	unsigned long uninitialized_var(address);
 
+	vma = find_vma(current->mm, start);
 	while (vma) {
 		address = page_address_in_vma(page, vma);
 		if (address != -EFAULT)
@@ -1219,7 +1221,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	return -ENOSYS;
 }
 
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
 	return NULL;
 }
@@ -1229,7 +1231,6 @@ static long do_mbind(unsigned long start, unsigned long len,
 		     unsigned short mode, unsigned short mode_flags,
 		     nodemask_t *nmask, unsigned long flags)
 {
-	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	struct mempolicy *new;
 	unsigned long end;
@@ -1295,11 +1296,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (err)
 		goto mpol_out;
 
-	vma = queue_pages_range(mm, start, end, nmask,
+	err = queue_pages_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
-
-	err = PTR_ERR(vma);	/* maybe ... */
-	if (!IS_ERR(vma))
+	if (!err)
 		err = mbind_range(mm, start, end, new);
 
 	if (!err) {
@@ -1307,9 +1306,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
-			nr_failed = migrate_pages(&pagelist, new_vma_page,
-					(unsigned long)vma,
-					MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
+			nr_failed = migrate_pages(&pagelist, new_page, NULL,
+				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_movable_pages(&pagelist);
 		}
@@ -1899,7 +1897,7 @@ int node_random(const nodemask_t *maskp)
  * If the effective policy is 'BIND, returns a pointer to the mempolicy's
  * @nodemask for filtering the zonelist.
  *
- * Must be protected by get_mems_allowed()
+ * Must be protected by read_mems_allowed_begin()
  */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 				gfp_t gfp_flags, struct mempolicy **mpol,
@@ -2063,7 +2061,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 retry_cpuset:
 	pol = get_vma_policy(current, vma, addr);
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
@@ -2071,7 +2069,7 @@ retry_cpuset:
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 			goto retry_cpuset;
 
 		return page;
@@ -2081,7 +2079,7 @@ retry_cpuset:
 				      policy_nodemask(gfp, pol));
 	if (unlikely(mpol_needs_cond_ref(pol)))
 		__mpol_put(pol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 }
@@ -2115,7 +2113,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		pol = &default_policy;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/*
 	 * No reference counting needed for current->mempolicy
@@ -2128,7 +2126,7 @@ retry_cpuset:
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	return page;
@@ -2172,7 +2170,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 	} else
 		*new = *old;
 
-	rcu_read_lock();
 	if (current_cpuset_is_being_rebound()) {
 		nodemask_t mems = cpuset_mems_allowed(current);
 		if (new->flags & MPOL_F_REBINDING)
@@ -2180,7 +2177,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 		else
 			mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
 	}
-	rcu_read_unlock();
 	atomic_set(&new->refcnt, 1);
 	return new;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index bed48809e5d0..3acac4a62c4b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -148,8 +148,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (pte_swp_soft_dirty(*ptep))
 		pte = pte_mksoft_dirty(pte);
+
+	/* Recheck VMA as permissions can change since migration started  */
 	if (is_write_migration_entry(entry))
-		pte = pte_mkwrite(pte);
+		pte = maybe_mkwrite(pte, vma);
+
 #ifdef CONFIG_HUGETLB_PAGE
 	if (PageHuge(new)) {
 		pte = pte_mkhuge(pte);
@@ -938,8 +941,9 @@ out:
  * Obtain the lock on page, remove all ptes and migrate the page
  * to the newly allocated page in newpage.
  */
-static int unmap_and_move(new_page_t get_new_page, unsigned long private,
-			struct page *page, int force, enum migrate_mode mode)
+static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page,
+			unsigned long private, struct page *page, int force,
+			enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -983,11 +987,18 @@ out:
 				page_is_file_cache(page));
 		putback_lru_page(page);
 	}
+
 	/*
-	 * Move the new page to the LRU. If migration was not successful
-	 * then this will free the page.
+	 * If migration was not successful and there's a freeing callback, use
+	 * it.  Otherwise, putback_lru_page() will drop the reference grabbed
+	 * during isolation.
 	 */
-	putback_lru_page(newpage);
+	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
+		ClearPageSwapBacked(newpage);
+		put_new_page(newpage, private);
+	} else
+		putback_lru_page(newpage);
+
 	if (result) {
 		if (rc)
 			*result = rc;
@@ -1016,8 +1027,9 @@ out:
  * will wait in the page fault for migration to complete.
  */
 static int unmap_and_move_huge_page(new_page_t get_new_page,
-				unsigned long private, struct page *hpage,
-				int force, enum migrate_mode mode)
+				free_page_t put_new_page, unsigned long private,
+				struct page *hpage, int force,
+				enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -1056,20 +1068,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	if (!page_mapped(hpage))
 		rc = move_to_new_page(new_hpage, hpage, 1, mode);
 
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		remove_migration_ptes(hpage, hpage);
 
 	if (anon_vma)
 		put_anon_vma(anon_vma);
 
-	if (!rc)
+	if (rc == MIGRATEPAGE_SUCCESS)
 		hugetlb_cgroup_migrate(hpage, new_hpage);
 
 	unlock_page(hpage);
 out:
 	if (rc != -EAGAIN)
 		putback_active_hugepage(hpage);
-	put_page(new_hpage);
+
+	/*
+	 * If migration was not successful and there's a freeing callback, use
+	 * it.  Otherwise, put_page() will drop the reference grabbed during
+	 * isolation.
+	 */
+	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
+		put_new_page(new_hpage, private);
+	else
+		put_page(new_hpage);
+
 	if (result) {
 		if (rc)
 			*result = rc;
@@ -1086,6 +1108,8 @@ out:
  * @from:		The list of pages to be migrated.
  * @get_new_page:	The function used to allocate free pages to be used
  *			as the target of the page migration.
+ * @put_new_page:	The function used to free target pages if migration
+ *			fails, or NULL if no special handling is necessary.
  * @private:		Private data to be passed on to get_new_page()
  * @mode:		The migration mode that specifies the constraints for
  *			page migration, if any.
@@ -1099,7 +1123,8 @@ out:
  * Returns the number of pages that were not migrated, or an error code.
  */
 int migrate_pages(struct list_head *from, new_page_t get_new_page,
-		unsigned long private, enum migrate_mode mode, int reason)
+		free_page_t put_new_page, unsigned long private,
+		enum migrate_mode mode, int reason)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -1121,10 +1146,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 
 			if (PageHuge(page))
 				rc = unmap_and_move_huge_page(get_new_page,
-						private, page, pass > 2, mode);
+						put_new_page, private, page,
+						pass > 2, mode);
 			else
-				rc = unmap_and_move(get_new_page, private,
-						page, pass > 2, mode);
+				rc = unmap_and_move(get_new_page, put_new_page,
+						private, page, pass > 2, mode);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -1273,7 +1299,7 @@ set_status:
 
 	err = 0;
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, new_page_node,
+		err = migrate_pages(&pagelist, new_page_node, NULL,
 				(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_movable_pages(&pagelist);
@@ -1729,7 +1755,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 
 	list_add(&page->lru, &migratepages);
 	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
-				     node, MIGRATE_ASYNC, MR_NUMA_MISPLACED);
+				     NULL, node, MIGRATE_ASYNC,
+				     MR_NUMA_MISPLACED);
 	if (nr_remaining) {
 		if (!list_empty(&migratepages)) {
 			list_del(&page->lru);
diff --git a/mm/mincore.c b/mm/mincore.c
index 101623378fbf..725c80961048 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-	page = find_get_page(mapping, pgoff);
 #ifdef CONFIG_SWAP
-	/* shmem/tmpfs may return swap: account for swapcache page too. */
-	if (radix_tree_exceptional_entry(page)) {
-		swp_entry_t swap = radix_to_swp_entry(page);
-		page = find_get_page(swap_address_space(swap), swap.val);
-	}
+	if (shmem_mapping(mapping)) {
+		page = find_get_entry(mapping, pgoff);
+		/*
+		 * shmem/tmpfs may return swap: account for swapcache
+		 * page too.
+		 */
+		if (radix_tree_exceptional_entry(page)) {
+			swp_entry_t swp = radix_to_swp_entry(page);
+			page = find_get_page(swap_address_space(swp), swp.val);
+		}
+	} else
+		page = find_get_page(mapping, pgoff);
+#else
+	page = find_get_page(mapping, pgoff);
 #endif
 	if (page) {
 		present = PageUptodate(page);
diff --git a/mm/mlock.c b/mm/mlock.c
index 4e1a68162285..b1eb53634005 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -79,6 +79,7 @@ void clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {
@@ -174,6 +175,7 @@ unsigned int munlock_vma_page(struct page *page)
 	unsigned int nr_pages;
 	struct zone *zone = page_zone(page);
 
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	/*
diff --git a/mm/mmap.c b/mm/mmap.c
index 20ff0c33274c..085bcd890ad2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/shm.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
@@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 	prev->vm_next = next = vma->vm_next;
 	if (next)
 		next->vm_prev = prev;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = prev;
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
@@ -743,8 +745,11 @@ again:			remove_next = 1 + (end > next->vm_end);
 		 * shrinking vma had, to cover any anon pages imported.
 		 */
 		if (exporter && exporter->anon_vma && !importer->anon_vma) {
-			if (anon_vma_clone(importer, exporter))
-				return -ENOMEM;
+			int error;
+
+			error = anon_vma_clone(importer, exporter);
+			if (error)
+				return error;
 			importer->anon_vma = exporter->anon_vma;
 		}
 	}
@@ -1989,34 +1994,33 @@ EXPORT_SYMBOL(get_unmapped_area);
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct *vma = NULL;
+	struct rb_node *rb_node;
+	struct vm_area_struct *vma;
 
 	/* Check the cache first. */
-	/* (Cache hit rate is typically around 35%.) */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
-		struct rb_node *rb_node;
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
+		return vma;
 
-		rb_node = mm->mm_rb.rb_node;
-		vma = NULL;
+	rb_node = mm->mm_rb.rb_node;
+	vma = NULL;
 
-		while (rb_node) {
-			struct vm_area_struct *vma_tmp;
-
-			vma_tmp = rb_entry(rb_node,
-					   struct vm_area_struct, vm_rb);
-
-			if (vma_tmp->vm_end > addr) {
-				vma = vma_tmp;
-				if (vma_tmp->vm_start <= addr)
-					break;
-				rb_node = rb_node->rb_left;
-			} else
-				rb_node = rb_node->rb_right;
-		}
-		if (vma)
-			mm->mmap_cache = vma;
+	while (rb_node) {
+		struct vm_area_struct *tmp;
+
+		tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);
+
+		if (tmp->vm_end > addr) {
+			vma = tmp;
+			if (tmp->vm_start <= addr)
+				break;
+			rb_node = rb_node->rb_left;
+		} else
+			rb_node = rb_node->rb_right;
 	}
+
+	if (vma)
+		vmacache_update(addr, vma);
 	return vma;
 }
 
@@ -2054,14 +2058,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
-	unsigned long new_start;
+	unsigned long new_start, actual_size;
 
 	/* address space limit tests */
 	if (!may_expand_vm(mm, grow))
 		return -ENOMEM;
 
 	/* Stack limit test */
-	if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+	actual_size = size;
+	if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
+		actual_size -= PAGE_SIZE;
+	if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
 		return -ENOMEM;
 
 	/* mlock limit tests */
@@ -2388,7 +2395,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else
 		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
-	mm->mmap_cache = NULL;		/* Kill the cache. */
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
@@ -2425,7 +2434,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	if (err)
 		goto out_free_vma;
 
-	if (anon_vma_clone(new, vma))
+	err = anon_vma_clone(new, vma);
+	if (err)
 		goto out_free_mpol;
 
 	if (new->vm_file)
diff --git a/mm/mremap.c b/mm/mremap.c
index 0843feb66f3d..05f1180e9f21 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			break;
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
-			if (extent == HPAGE_PMD_SIZE)
+			if (extent == HPAGE_PMD_SIZE) {
+				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				/* See comment in move_ptes() */
+				if (need_rmap_locks)
+					anon_vma_lock_write(vma->anon_vma);
 				err = move_huge_pmd(vma, new_vma, old_addr,
 						    new_addr, old_end,
 						    old_pmd, new_pmd);
+				if (need_rmap_locks)
+					anon_vma_unlock_write(vma->anon_vma);
+			}
 			if (err > 0) {
 				need_flush = true;
 				continue;
diff --git a/mm/nommu.c b/mm/nommu.c
index 8740213b1647..3ee4f74fbfbe 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -15,6 +15,7 @@
 
 #include <linux/export.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
 #include <linux/file.h>
@@ -768,16 +769,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
  */
 static void delete_vma_from_mm(struct vm_area_struct *vma)
 {
+	int i;
 	struct address_space *mapping;
 	struct mm_struct *mm = vma->vm_mm;
+	struct task_struct *curr = current;
 
 	kenter("%p", vma);
 
 	protect_vma(vma, 0);
 
 	mm->map_count--;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = NULL;
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		/* if the vma is cached, invalidate the entire cache */
+		if (curr->vmacache[i] == vma) {
+			vmacache_invalidate(curr->mm);
+			break;
+		}
+	}
 
 	/* remove the VMA from the mapping */
 	if (vma->vm_file) {
@@ -825,8 +833,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;
 
 	/* check the cache first */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -835,7 +843,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end > addr) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
@@ -874,8 +882,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 	unsigned long end = addr + len;
 
 	/* check the cache first */
-	vma = mm->mmap_cache;
-	if (vma && vma->vm_start == addr && vma->vm_end == end)
+	vma = vmacache_find_exact(mm, addr, end);
+	if (vma)
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -886,7 +894,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end == end) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3291e82d4352..171c00f2e495 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -406,6 +406,23 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 		dump_tasks(memcg, nodemask);
 }
 
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+	return atomic_read(&oom_kills);
+}
+
+void note_oom_kill(void)
+{
+	atomic_inc(&oom_kills);
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7106cb1aca8e..9f45f87a5859 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -593,14 +593,14 @@ unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
  * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
  *     => fast response on large errors; small oscillation near setpoint
  */
-static inline long long pos_ratio_polynom(unsigned long setpoint,
+static long long pos_ratio_polynom(unsigned long setpoint,
 					  unsigned long dirty,
 					  unsigned long limit)
 {
 	long long pos_ratio;
 	long x;
 
-	x = div_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
+	x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT,
 		    limit - setpoint + 1);
 	pos_ratio = x;
 	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
@@ -842,7 +842,7 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
 	x_intercept = bdi_setpoint + span;
 
 	if (bdi_dirty < x_intercept - span / 4) {
-		pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty),
+		pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
 				    x_intercept - bdi_setpoint + 1);
 	} else
 		pos_ratio /= 4;
@@ -1324,9 +1324,9 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi,
 	*bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 
 	if (bdi_bg_thresh)
-		*bdi_bg_thresh = div_u64((u64)*bdi_thresh *
-					 background_thresh,
-					 dirty_thresh);
+		*bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh *
+							background_thresh,
+							dirty_thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
@@ -2398,7 +2398,7 @@ int test_clear_page_writeback(struct page *page)
 	return ret;
 }
 
-int test_set_page_writeback(struct page *page)
+int __test_set_page_writeback(struct page *page, bool keep_write)
 {
 	struct address_space *mapping = page_mapping(page);
 	int ret;
@@ -2423,9 +2423,10 @@ int test_set_page_writeback(struct page *page)
 			radix_tree_tag_clear(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);
-		radix_tree_tag_clear(&mapping->page_tree,
-				     page_index(page),
-				     PAGECACHE_TAG_TOWRITE);
+		if (!keep_write)
+			radix_tree_tag_clear(&mapping->page_tree,
+						page_index(page),
+						PAGECACHE_TAG_TOWRITE);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	} else {
 		ret = TestSetPageWriteback(page);
@@ -2436,7 +2437,7 @@ int test_set_page_writeback(struct page *page)
 	return ret;
 
 }
-EXPORT_SYMBOL(test_set_page_writeback);
+EXPORT_SYMBOL(__test_set_page_writeback);
 
 /*
  * Return true if any of the pages in the mapping are marked with the
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3bac76ae4b30..4b258297cc7c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
 
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
+#define MIN_PERCPU_PAGELIST_FRACTION	(8)
 
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
@@ -798,9 +799,21 @@ void __init init_cma_reserved_pageblock(struct page *page)
 		set_page_count(p, 0);
 	} while (++p, --i);
 
-	set_page_refcounted(page);
 	set_pageblock_migratetype(page, MIGRATE_CMA);
-	__free_pages(page, pageblock_order);
+
+	if (pageblock_order >= MAX_ORDER) {
+		i = pageblock_nr_pages;
+		p = page;
+		do {
+			set_page_refcounted(p);
+			__free_pages(p, MAX_ORDER - 1);
+			p += MAX_ORDER_NR_PAGES;
+		} while (i -= MAX_ORDER_NR_PAGES);
+	} else {
+		set_page_refcounted(page);
+		__free_pages(page, pageblock_order);
+	}
+
 	adjust_managed_page_count(page, pageblock_nr_pages);
 }
 #endif
@@ -930,6 +943,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		rmv_page_order(page);
 		area->nr_free--;
 		expand(zone, page, order, current_order, area, migratetype);
+		set_freepage_migratetype(page, migratetype);
 		return page;
 	}
 
@@ -1056,7 +1070,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 
 	/*
 	 * When borrowing from MIGRATE_CMA, we need to release the excess
-	 * buddy pages to CMA itself.
+	 * buddy pages to CMA itself. We also ensure the freepage_migratetype
+	 * is set to CMA so it is returned to the correct freelist in case
+	 * the page ends up being not actually allocated from the pcp lists.
 	 */
 	if (is_migrate_cma(fallback_type))
 		return fallback_type;
@@ -1124,6 +1140,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 
 			expand(zone, page, order, current_order, area,
 			       new_type);
+			/* The freepage_migratetype may differ from pageblock's
+			 * migratetype depending on the decisions in
+			 * try_to_steal_freepages. This is OK as long as it does
+			 * not differ for MIGRATE_CMA type.
+			 */
+			set_freepage_migratetype(page, new_type);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
 				start_migratetype, migratetype, new_type);
@@ -1174,7 +1196,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
 			int migratetype, int cold)
 {
-	int mt = migratetype, i;
+	int i;
 
 	spin_lock(&zone->lock);
 	for (i = 0; i < count; ++i) {
@@ -1195,14 +1217,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			list_add(&page->lru, list);
 		else
 			list_add_tail(&page->lru, list);
-		if (IS_ENABLED(CONFIG_CMA)) {
-			mt = get_pageblock_migratetype(page);
-			if (!is_migrate_cma(mt) && !is_migrate_isolate(mt))
-				mt = migratetype;
-		}
-		set_freepage_migratetype(page, mt);
 		list = &page->lru;
-		if (is_migrate_cma(mt))
+		if (is_migrate_cma(get_freepage_migratetype(page)))
 			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
 					      -(1 << order));
 	}
@@ -1238,15 +1254,6 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 	}
 	local_irq_restore(flags);
 }
-static bool gfp_thisnode_allocation(gfp_t gfp_mask)
-{
-	return (gfp_mask & GFP_THISNODE) == GFP_THISNODE;
-}
-#else
-static bool gfp_thisnode_allocation(gfp_t gfp_mask)
-{
-	return false;
-}
 #endif
 
 /*
@@ -1580,15 +1587,10 @@ again:
 		if (!page)
 			goto failed;
 		__mod_zone_freepage_state(zone, -(1 << order),
-					  get_pageblock_migratetype(page));
+					  get_freepage_migratetype(page));
 	}
 
-	/*
-	 * NOTE: GFP_THISNODE allocations do not partake in the kswapd
-	 * aging protocol, so they can't be fair.
-	 */
-	if (!gfp_thisnode_allocation(gfp_flags))
-		__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1870,7 +1872,7 @@ static void __paginginit init_zone_allows_reclaim(int nid)
 {
 	int i;
 
-	for_each_online_node(i)
+	for_each_node_state(i, N_MEMORY)
 		if (node_distance(nid, i) <= RECLAIM_DISTANCE)
 			node_set(i, NODE_DATA(nid)->reclaim_nodes);
 		else
@@ -1954,23 +1956,12 @@ zonelist_scan:
 		 * zone size to ensure fair page aging.  The zone a
 		 * page was allocated in should have no effect on the
 		 * time the page has in memory before being reclaimed.
-		 *
-		 * Try to stay in local zones in the fastpath.  If
-		 * that fails, the slowpath is entered, which will do
-		 * another pass starting with the local zones, but
-		 * ultimately fall back to remote zones that do not
-		 * partake in the fairness round-robin cycle of this
-		 * zonelist.
-		 *
-		 * NOTE: GFP_THISNODE allocations do not partake in
-		 * the kswapd aging protocol, so they can't be fair.
 		 */
-		if ((alloc_flags & ALLOC_WMARK_LOW) &&
-		    !gfp_thisnode_allocation(gfp_mask)) {
-			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
-				continue;
+		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
 				continue;
+			if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0)
+				continue;
 		}
 		/*
 		 * When allocating a page cache page for writing, we
@@ -2208,6 +2199,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 
 	/*
+	 * PM-freezer should be notified that there might be an OOM killer on
+	 * its way to kill and wake somebody up. This is too early and we might
+	 * end up not killing anything but false positives are acceptable.
+	 * See freeze_processes.
+	 */
+	note_oom_kill();
+
+	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
 	 * we're still under heavy pressure.
@@ -2250,7 +2249,7 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, bool sync_migration,
+	int migratetype, enum migrate_mode mode,
 	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
@@ -2264,7 +2263,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
-						nodemask, sync_migration,
+						nodemask, mode,
 						contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 
@@ -2297,7 +2296,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * As async compaction considers a subset of pageblocks, only
 		 * defer if the failure was a sync compaction failure.
 		 */
-		if (sync_migration)
+		if (mode != MIGRATE_ASYNC)
 			defer_compaction(preferred_zone, order);
 
 		cond_resched();
@@ -2310,9 +2309,8 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, bool sync_migration,
-	bool *contended_compaction, bool *deferred_compaction,
-	unsigned long *did_some_progress)
+	int migratetype, enum migrate_mode mode, bool *contended_compaction,
+	bool *deferred_compaction, unsigned long *did_some_progress)
 {
 	return NULL;
 }
@@ -2408,37 +2406,45 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 	return page;
 }
 
-static void prepare_slowpath(gfp_t gfp_mask, unsigned int order,
-			     struct zonelist *zonelist,
-			     enum zone_type high_zoneidx,
-			     struct zone *preferred_zone)
+static void reset_alloc_batches(struct zonelist *zonelist,
+				enum zone_type high_zoneidx,
+				struct zone *preferred_zone)
 {
 	struct zoneref *z;
 	struct zone *zone;
 
 	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		if (!(gfp_mask & __GFP_NO_KSWAPD))
-			wakeup_kswapd(zone, order, zone_idx(preferred_zone));
 		/*
 		 * Only reset the batches of zones that were actually
-		 * considered in the fast path, we don't want to
-		 * thrash fairness information for zones that are not
+		 * considered in the fairness pass, we don't want to
+		 * trash fairness information for zones that are not
 		 * actually part of this zonelist's round-robin cycle.
 		 */
 		if (!zone_local(preferred_zone, zone))
 			continue;
 		mod_zone_page_state(zone, NR_ALLOC_BATCH,
-				    high_wmark_pages(zone) -
-				    low_wmark_pages(zone) -
-				    zone_page_state(zone, NR_ALLOC_BATCH));
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
 	}
 }
 
+static void wake_all_kswapds(unsigned int order,
+			     struct zonelist *zonelist,
+			     enum zone_type high_zoneidx,
+			     struct zone *preferred_zone)
+{
+	struct zoneref *z;
+	struct zone *zone;
+
+	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+		wakeup_kswapd(zone, order, zone_idx(preferred_zone));
+}
+
 static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
 	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
 
 	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
 	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2447,20 +2453,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * The caller may dip into page reserves a bit more if the caller
 	 * cannot run direct reclaim, or if the caller has realtime scheduling
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
 	 */
 	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
-	if (!wait) {
+	if (atomic) {
 		/*
-		 * Not worth trying to allocate harder for
-		 * __GFP_NOMEMALLOC even if it can't schedule.
+		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+		 * if it can't schedule.
 		 */
-		if  (!(gfp_mask & __GFP_NOMEMALLOC))
+		if (!(gfp_mask & __GFP_NOMEMALLOC))
 			alloc_flags |= ALLOC_HARDER;
 		/*
-		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+		 * comment for __cpuset_node_allowed_softwall().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
@@ -2499,7 +2505,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	int alloc_flags;
 	unsigned long pages_reclaimed = 0;
 	unsigned long did_some_progress;
-	bool sync_migration = false;
+	enum migrate_mode migration_mode = MIGRATE_ASYNC;
 	bool deferred_compaction = false;
 	bool contended_compaction = false;
 
@@ -2522,12 +2528,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (gfp_thisnode_allocation(gfp_mask))
+	if (IS_ENABLED(CONFIG_NUMA) &&
+	    (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
 restart:
-	prepare_slowpath(gfp_mask, order, zonelist,
-			 high_zoneidx, preferred_zone);
+	if (!(gfp_mask & __GFP_NO_KSWAPD))
+		wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -2592,17 +2599,15 @@ rebalance:
 	 * Try direct compaction. The first pass is asynchronous. Subsequent
 	 * attempts after direct reclaim are synchronous
 	 */
-	page = __alloc_pages_direct_compact(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask,
-					alloc_flags, preferred_zone,
-					migratetype, sync_migration,
-					&contended_compaction,
+	page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
+					high_zoneidx, nodemask, alloc_flags,
+					preferred_zone, migratetype,
+					migration_mode, &contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 	if (page)
 		goto got_pg;
-	sync_migration = true;
+	migration_mode = MIGRATE_SYNC_LIGHT;
 
 	/*
 	 * If compaction is deferred for high-order allocations, it is because
@@ -2677,12 +2682,10 @@ rebalance:
 		 * direct reclaim and reclaim/compaction depends on compaction
 		 * being called after reclaim so call directly if necessary
 		 */
-		page = __alloc_pages_direct_compact(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask,
-					alloc_flags, preferred_zone,
-					migratetype, sync_migration,
-					&contended_compaction,
+		page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
+					high_zoneidx, nodemask, alloc_flags,
+					preferred_zone, migratetype,
+					migration_mode, &contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 		if (page)
@@ -2711,7 +2714,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
-	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
+	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
 	struct mem_cgroup *memcg = NULL;
 
 	gfp_mask &= gfp_allowed_mask;
@@ -2739,7 +2742,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
@@ -2752,12 +2755,29 @@ retry_cpuset:
 	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
+retry:
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, alloc_flags,
 			preferred_zone, migratetype);
 	if (unlikely(!page)) {
 		/*
+		 * The first pass makes sure allocations are spread
+		 * fairly within the local node.  However, the local
+		 * node might have free pages left after the fairness
+		 * batches are exhausted, and remote zones haven't
+		 * even been considered yet.  Try once more without
+		 * fairness, and include remote zones now, before
+		 * entering the slowpath and waking kswapd: prefer
+		 * spilling to a remote zone over swapping locally.
+		 */
+		if (alloc_flags & ALLOC_FAIR) {
+			reset_alloc_batches(zonelist, high_zoneidx,
+					    preferred_zone);
+			alloc_flags &= ~ALLOC_FAIR;
+			goto retry;
+		}
+		/*
 		 * Runtime PM, block IO and its error handling path
 		 * can deadlock because I/O on the device might not
 		 * complete.
@@ -2777,7 +2797,7 @@ out:
 	 * the mask is being updated. If a page allocation is about to fail,
 	 * check if the cpuset changed during allocation and if so, retry.
 	 */
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	memcg_kmem_commit_charge(page, memcg, order);
@@ -3045,9 +3065,9 @@ bool skip_free_areas_node(unsigned int flags, int nid)
 		goto out;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		ret = !node_isset(nid, cpuset_current_mems_allowed);
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 out:
 	return ret;
 }
@@ -4105,7 +4125,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
 #endif
 
-static int __meminit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
 {
 #ifdef CONFIG_MMU
 	int batch;
@@ -4221,8 +4241,8 @@ static void pageset_set_high(struct per_cpu_pageset *p,
 	pageset_update(&p->pcp, high, batch);
 }
 
-static void __meminit pageset_set_high_and_batch(struct zone *zone,
-		struct per_cpu_pageset *pcp)
+static void pageset_set_high_and_batch(struct zone *zone,
+				       struct per_cpu_pageset *pcp)
 {
 	if (percpu_pagelist_fraction)
 		pageset_set_high(pcp,
@@ -4919,7 +4939,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
-	init_zone_allows_reclaim(nid);
+	if (node_state(nid, N_MEMORY))
+		init_zone_allows_reclaim(nid);
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 #endif
@@ -5647,9 +5668,8 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 
 		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
-				      high_wmark_pages(zone) -
-				      low_wmark_pages(zone) -
-				      zone_page_state(zone, NR_ALLOC_BATCH));
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
 
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
@@ -5847,23 +5867,38 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
-	unsigned int cpu;
+	int old_percpu_pagelist_fraction;
 	int ret;
 
+	mutex_lock(&pcp_batch_high_lock);
+	old_percpu_pagelist_fraction = percpu_pagelist_fraction;
+
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
-	if (!write || (ret < 0))
-		return ret;
+	if (!write || ret < 0)
+		goto out;
+
+	/* Sanity checking to avoid pcp imbalance */
+	if (percpu_pagelist_fraction &&
+	    percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
+		percpu_pagelist_fraction = old_percpu_pagelist_fraction;
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* No change? */
+	if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
+		goto out;
 
-	mutex_lock(&pcp_batch_high_lock);
 	for_each_populated_zone(zone) {
-		unsigned long  high;
-		high = zone->managed_pages / percpu_pagelist_fraction;
+		unsigned int cpu;
+
 		for_each_possible_cpu(cpu)
-			pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
-					 high);
+			pageset_set_high_and_batch(zone,
+					per_cpu_ptr(zone->pageset, cpu));
 	}
+out:
 	mutex_unlock(&pcp_batch_high_lock);
-	return 0;
+	return ret;
 }
 
 int hashdist = HASHDIST_DEFAULT;
@@ -6006,53 +6041,65 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
  * @end_bitidx: The last bit of interest
  * returns pageblock_bits flags
  */
-unsigned long get_pageblock_flags_group(struct page *page,
-					int start_bitidx, int end_bitidx)
+unsigned long get_pageblock_flags_mask(struct page *page,
+					unsigned long end_bitidx,
+					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx;
-	unsigned long flags = 0;
-	unsigned long value = 1;
+	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long word;
 
 	zone = page_zone(page);
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
+	word_bitidx = bitidx / BITS_PER_LONG;
+	bitidx &= (BITS_PER_LONG-1);
 
-	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
-		if (test_bit(bitidx + start_bitidx, bitmap))
-			flags |= value;
-
-	return flags;
+	word = bitmap[word_bitidx];
+	bitidx += end_bitidx;
+	return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
 }
 
 /**
- * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @start_bitidx: The first bit of interest
  * @end_bitidx: The last bit of interest
  * @flags: The flags to set
  */
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
-					int start_bitidx, int end_bitidx)
+void set_pageblock_flags_mask(struct page *page, unsigned long flags,
+					unsigned long end_bitidx,
+					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx;
-	unsigned long value = 1;
+	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long old_word, word;
+
+	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
 
 	zone = page_zone(page);
 	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
+	word_bitidx = bitidx / BITS_PER_LONG;
+	bitidx &= (BITS_PER_LONG-1);
+
 	VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page);
 
-	for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
-		if (flags & value)
-			__set_bit(bitidx + start_bitidx, bitmap);
-		else
-			__clear_bit(bitidx + start_bitidx, bitmap);
+	bitidx += end_bitidx;
+	mask <<= (BITS_PER_LONG - bitidx - 1);
+	flags <<= (BITS_PER_LONG - bitidx - 1);
+
+	word = ACCESS_ONCE(bitmap[word_bitidx]);
+	for (;;) {
+		old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
+		if (word == old_word)
+			break;
+		word = old_word;
+	}
 }
 
 /*
@@ -6212,7 +6259,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 		cc->nr_migratepages -= nr_reclaimed;
 
 		ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
-				    0, MIGRATE_SYNC, MR_CMA);
+				    NULL, 0, cc->mode, MR_CMA);
 	}
 	if (ret < 0) {
 		putback_movable_pages(&cc->migratepages);
@@ -6251,7 +6298,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.nr_migratepages = 0,
 		.order = -1,
 		.zone = page_zone(pfn_to_page(start)),
-		.sync = true,
+		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index cfd162882c00..0e9a319d5f8d 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -171,6 +171,7 @@ static void free_page_cgroup(void *addr)
 			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
+		kmemleak_free(addr);
 		free_pages_exact(addr, table_size);
 	}
 }
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 3707c71ae4cd..51108165f829 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			    int page_start, int page_end)
 {
 	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
-	unsigned int cpu;
+	unsigned int cpu, tcpu;
 	int i;
 
 	for_each_possible_cpu(cpu) {
@@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
 
 			*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
-			if (!*pagep) {
-				pcpu_free_pages(chunk, pages, populated,
-						page_start, page_end);
-				return -ENOMEM;
-			}
+			if (!*pagep)
+				goto err;
 		}
 	}
 	return 0;
+
+err:
+	while (--i >= page_start)
+		__free_page(pages[pcpu_page_idx(cpu, i)]);
+
+	for_each_possible_cpu(tcpu) {
+		if (tcpu == cpu)
+			break;
+		for (i = page_start; i < page_end; i++)
+			__free_page(pages[pcpu_page_idx(tcpu, i)]);
+	}
+	return -ENOMEM;
 }
 
 /**
@@ -263,6 +272,7 @@ err:
 		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
 				   page_end - page_start);
 	}
+	pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
 	return err;
 }
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 036cfe07050f..a2a54a85f691 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -612,7 +612,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
 						sizeof(chunk->map[0]));
 	if (!chunk->map) {
-		kfree(chunk);
+		pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 		return NULL;
 	}
 
diff --git a/mm/readahead.c b/mm/readahead.c
index 0de2360d65f3..0ca36a7770b1 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,9 +8,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/fs.h>
 #include <linux/gfp.h>
-#include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
@@ -20,6 +18,8 @@
 #include <linux/syscalls.h>
 #include <linux/file.h>
 
+#include "internal.h"
+
 /*
  * Initialise a struct file's readahead state.  Assumes that the caller has
  * memset *ra to zero.
@@ -149,8 +149,7 @@ out:
  *
  * Returns the number of pages requested, or the maximum amount of I/O allowed.
  */
-static int
-__do_page_cache_readahead(struct address_space *mapping, struct file *filp,
+int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 			pgoff_t offset, unsigned long nr_to_read,
 			unsigned long lookahead_size)
 {
@@ -179,7 +178,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, page_offset);
 		rcu_read_unlock();
-		if (page)
+		if (page && !radix_tree_exceptional_entry(page))
 			continue;
 
 		page = page_cache_alloc_readahead(mapping);
@@ -233,28 +232,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	return 0;
 }
 
+#define MAX_READAHEAD   ((512*4096)/PAGE_CACHE_SIZE)
 /*
  * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
  * sensible upper limit.
  */
 unsigned long max_sane_readahead(unsigned long nr)
 {
-	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE)
-		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
-}
-
-/*
- * Submit IO for the read-ahead request in file_ra_state.
- */
-unsigned long ra_submit(struct file_ra_state *ra,
-		       struct address_space *mapping, struct file *filp)
-{
-	int actual;
-
-	actual = __do_page_cache_readahead(mapping, filp,
-					ra->start, ra->size, ra->async_size);
-
-	return actual;
+	return min(nr, MAX_READAHEAD);
 }
 
 /*
@@ -347,7 +332,7 @@ static pgoff_t count_history_pages(struct address_space *mapping,
 	pgoff_t head;
 
 	rcu_read_lock();
-	head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+	head = page_cache_prev_hole(mapping, offset - 1, max);
 	rcu_read_unlock();
 
 	return offset - 1 - head;
@@ -427,7 +412,7 @@ ondemand_readahead(struct address_space *mapping,
 		pgoff_t start;
 
 		rcu_read_lock();
-		start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
+		start = page_cache_next_hole(mapping, offset + 1, max);
 		rcu_read_unlock();
 
 		if (!start || start - offset > max)
diff --git a/mm/rmap.c b/mm/rmap.c
index 8fc049f9a5a6..cab982084e2b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma)
 	 * LOCK should suffice since the actual taking of the lock must
 	 * happen _before_ what follows.
 	 */
+	might_sleep();
 	if (rwsem_is_locked(&anon_vma->root->rwsem)) {
 		anon_vma_lock_write(anon_vma);
 		anon_vma_unlock_write(anon_vma);
@@ -273,6 +274,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 {
 	struct anon_vma_chain *avc;
 	struct anon_vma *anon_vma;
+	int error;
 
 	/* Don't bother if the parent process has no anon_vma here. */
 	if (!pvma->anon_vma)
@@ -282,8 +284,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
 	 * First, attach the new VMA to the parent VMA's anon_vmas,
 	 * so rmap can find non-COWed pages in child processes.
 	 */
-	if (anon_vma_clone(vma, pvma))
-		return -ENOMEM;
+	error = anon_vma_clone(vma, pvma);
+	if (error)
+		return error;
 
 	/* Then add our own anon_vma. */
 	anon_vma = anon_vma_alloc();
@@ -426,8 +429,9 @@ struct anon_vma *page_get_anon_vma(struct page *page)
 	 * above cannot corrupt).
 	 */
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
+		return NULL;
 	}
 out:
 	rcu_read_unlock();
@@ -477,9 +481,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page)
 	}
 
 	if (!page_mapped(page)) {
+		rcu_read_unlock();
 		put_anon_vma(anon_vma);
-		anon_vma = NULL;
-		goto out;
+		return NULL;
 	}
 
 	/* we pinned the anon_vma, its safe to sleep */
@@ -1322,9 +1326,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}
 
@@ -1544,10 +1558,9 @@ void __put_anon_vma(struct anon_vma *anon_vma)
 {
 	struct anon_vma *root = anon_vma->root;
 
+	anon_vma_free(anon_vma);
 	if (root != anon_vma && atomic_dec_and_test(&root->refcount))
 		anon_vma_free(root);
-
-	anon_vma_free(anon_vma);
 }
 
 static struct anon_vma *rmap_walk_anon_lock(struct page *page,
diff --git a/mm/shmem.c b/mm/shmem.c
index 1f18c9d0d93e..0f1447563f17 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -80,11 +80,12 @@ static struct vfsmount *shm_mnt;
 #define SHORT_SYMLINK_LEN 128
 
 /*
- * shmem_fallocate and shmem_writepage communicate via inode->i_private
- * (with i_mutex making sure that it has only one user at a time):
- * we would prefer not to enlarge the shmem inode just for that.
+ * shmem_fallocate communicates with shmem_fault or shmem_writepage via
+ * inode->i_private (with i_mutex making sure that it has only one user at
+ * a time): we would prefer not to enlarge the shmem inode just for that.
  */
 struct shmem_falloc {
+	wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
 	pgoff_t start;		/* start of range currently being fallocated */
 	pgoff_t next;		/* the next page offset to be fallocated */
 	pgoff_t nr_falloced;	/* how many new pages have been fallocated */
@@ -242,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
 			pgoff_t index, void *expected, void *replacement)
 {
 	void **pslot;
-	void *item = NULL;
+	void *item;
 
 	VM_BUG_ON(!expected);
+	VM_BUG_ON(!replacement);
 	pslot = radix_tree_lookup_slot(&mapping->page_tree, index);
-	if (pslot)
-		item = radix_tree_deref_slot_protected(pslot,
-							&mapping->tree_lock);
+	if (!pslot)
+		return -ENOENT;
+	item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock);
 	if (item != expected)
 		return -ENOENT;
-	if (replacement)
-		radix_tree_replace_slot(pslot, replacement);
-	else
-		radix_tree_delete(&mapping->page_tree, index);
+	radix_tree_replace_slot(pslot, replacement);
 	return 0;
 }
 
@@ -331,84 +330,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
 }
 
 /*
- * Like find_get_pages, but collecting swap entries as well as pages.
- */
-static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
-					pgoff_t start, unsigned int nr_pages,
-					struct page **pages, pgoff_t *indices)
-{
-	void **slot;
-	unsigned int ret = 0;
-	struct radix_tree_iter iter;
-
-	if (!nr_pages)
-		return 0;
-
-	rcu_read_lock();
-restart:
-	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
-		struct page *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
-			continue;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page))
-				goto restart;
-			/*
-			 * Otherwise, we must be storing a swap entry
-			 * here as an exceptional entry: so return it
-			 * without attempting to raise page count.
-			 */
-			goto export;
-		}
-		if (!page_cache_get_speculative(page))
-			goto repeat;
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			page_cache_release(page);
-			goto repeat;
-		}
-export:
-		indices[ret] = iter.index;
-		pages[ret] = page;
-		if (++ret == nr_pages)
-			break;
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
-/*
  * Remove swap entry from radix tree, free the swap and its page cache.
  */
 static int shmem_free_swap(struct address_space *mapping,
 			   pgoff_t index, void *radswap)
 {
-	int error;
+	void *old;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = shmem_radix_tree_replace(mapping, index, radswap, NULL);
+	old = radix_tree_delete_item(&mapping->page_tree, index, radswap);
 	spin_unlock_irq(&mapping->tree_lock);
-	if (!error)
-		free_swap_and_cache(radix_to_swp_entry(radswap));
-	return error;
-}
-
-/*
- * Pagevec may contain swap entries, so shuffle up pages before releasing.
- */
-static void shmem_deswap_pagevec(struct pagevec *pvec)
-{
-	int i, j;
-
-	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-		if (!radix_tree_exceptional_entry(page))
-			pvec->pages[j++] = page;
-	}
-	pvec->nr = j;
+	if (old != radswap)
+		return -ENOENT;
+	free_swap_and_cache(radix_to_swp_entry(radswap));
+	return 0;
 }
 
 /*
@@ -429,12 +364,12 @@ void shmem_unlock_mapping(struct address_space *mapping)
 		 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
 		 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
 		 */
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-					PAGEVEC_SIZE, pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+					   PAGEVEC_SIZE, pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		index = indices[pvec.nr - 1] + 1;
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		check_move_unevictable_pages(pvec.pages, pvec.nr);
 		pagevec_release(&pvec);
 		cond_resched();
@@ -466,9 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	pagevec_init(&pvec, 0);
 	index = start;
 	while (index < end) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		mem_cgroup_uncharge_start();
@@ -497,7 +432,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -533,22 +468,20 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		return;
 
 	index = start;
-	for ( ; ; ) {
+	while (index < end) {
 		cond_resched();
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+
+		pvec.nr = find_get_entries(mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+				pvec.pages, indices);
 		if (!pvec.nr) {
-			if (index == start || unfalloc)
+			/* If all gone or hole-punch or unfalloc, we're done */
+			if (index == start || end != -1)
 				break;
+			/* But if truncating, restart to make sure all gone */
 			index = start;
 			continue;
 		}
-		if ((index == start || unfalloc) && indices[0] >= end) {
-			shmem_deswap_pagevec(&pvec);
-			pagevec_release(&pvec);
-			break;
-		}
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
@@ -560,8 +493,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (radix_tree_exceptional_entry(page)) {
 				if (unfalloc)
 					continue;
-				nr_swaps_freed += !shmem_free_swap(mapping,
-								index, page);
+				if (shmem_free_swap(mapping, index, page)) {
+					/* Swap was replaced by page: retry */
+					index--;
+					break;
+				}
+				nr_swaps_freed++;
 				continue;
 			}
 
@@ -570,11 +507,16 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 				if (page->mapping == mapping) {
 					VM_BUG_ON_PAGE(PageWriteback(page), page);
 					truncate_inode_page(mapping, page);
+				} else {
+					/* Page was replaced by swap: retry */
+					unlock_page(page);
+					index--;
+					break;
 				}
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -824,6 +766,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 			spin_lock(&inode->i_lock);
 			shmem_falloc = inode->i_private;
 			if (shmem_falloc &&
+			    !shmem_falloc->waitq &&
 			    index >= shmem_falloc->start &&
 			    index < shmem_falloc->next)
 				shmem_falloc->nr_unswapped++;
@@ -1080,7 +1023,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		return -EFBIG;
 repeat:
 	swap.val = 0;
-	page = find_lock_page(mapping, index);
+	page = find_lock_entry(mapping, index);
 	if (radix_tree_exceptional_entry(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
@@ -1298,6 +1241,64 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	int error;
 	int ret = VM_FAULT_LOCKED;
 
+	/*
+	 * Trinity finds that probing a hole which tmpfs is punching can
+	 * prevent the hole-punch from ever completing: which in turn
+	 * locks writers out with its hold on i_mutex.  So refrain from
+	 * faulting pages into the hole while it's being punched.  Although
+	 * shmem_undo_range() does remove the additions, it may be unable to
+	 * keep up, as each new page needs its own unmap_mapping_range() call,
+	 * and the i_mmap tree grows ever slower to scan if new vmas are added.
+	 *
+	 * It does not matter if we sometimes reach this check just before the
+	 * hole-punch begins, so that one fault then races with the punch:
+	 * we just need to make racing faults a rare case.
+	 *
+	 * The implementation below would be much simpler if we just used a
+	 * standard mutex or completion: but we cannot take i_mutex in fault,
+	 * and bloating every shmem inode for this unlikely case would be sad.
+	 */
+	if (unlikely(inode->i_private)) {
+		struct shmem_falloc *shmem_falloc;
+
+		spin_lock(&inode->i_lock);
+		shmem_falloc = inode->i_private;
+		if (shmem_falloc &&
+		    shmem_falloc->waitq &&
+		    vmf->pgoff >= shmem_falloc->start &&
+		    vmf->pgoff < shmem_falloc->next) {
+			wait_queue_head_t *shmem_falloc_waitq;
+			DEFINE_WAIT(shmem_fault_wait);
+
+			ret = VM_FAULT_NOPAGE;
+			if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+			   !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				/* It's polite to up mmap_sem if we can */
+				up_read(&vma->vm_mm->mmap_sem);
+				ret = VM_FAULT_RETRY;
+			}
+
+			shmem_falloc_waitq = shmem_falloc->waitq;
+			prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
+					TASK_UNINTERRUPTIBLE);
+			spin_unlock(&inode->i_lock);
+			schedule();
+
+			/*
+			 * shmem_falloc_waitq points into the shmem_fallocate()
+			 * stack of the hole-punching task: shmem_falloc_waitq
+			 * is usually invalid by the time we reach here, but
+			 * finish_wait() does not dereference it in that case;
+			 * though i_lock needed lest racing with wake_up_all().
+			 */
+			spin_lock(&inode->i_lock);
+			finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
+			spin_unlock(&inode->i_lock);
+			return ret;
+		}
+		spin_unlock(&inode->i_lock);
+	}
+
 	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
@@ -1417,6 +1418,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	return inode;
 }
 
+bool shmem_mapping(struct address_space *mapping)
+{
+	return mapping->backing_dev_info == &shmem_backing_dev_info;
+}
+
 #ifdef CONFIG_TMPFS
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
@@ -1729,7 +1735,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 	pagevec_init(&pvec, 0);
 	pvec.nr = 1;		/* start small: we may be there already */
 	while (!done) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+		pvec.nr = find_get_entries(mapping, index,
 					pvec.nr, pvec.pages, indices);
 		if (!pvec.nr) {
 			if (whence == SEEK_DATA)
@@ -1756,7 +1762,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				break;
 			}
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		pvec.nr = PAGEVEC_SIZE;
 		cond_resched();
@@ -1817,12 +1823,25 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		struct address_space *mapping = file->f_mapping;
 		loff_t unmap_start = round_up(offset, PAGE_SIZE);
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
+
+		shmem_falloc.waitq = &shmem_falloc_waitq;
+		shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+		shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
+		spin_lock(&inode->i_lock);
+		inode->i_private = &shmem_falloc;
+		spin_unlock(&inode->i_lock);
 
 		if ((u64)unmap_end > (u64)unmap_start)
 			unmap_mapping_range(mapping, unmap_start,
 					    1 + unmap_end - unmap_start, 0);
 		shmem_truncate_range(inode, offset, offset + len - 1);
 		/* No need to unmap again: hole-punching leaves COWed pages */
+
+		spin_lock(&inode->i_lock);
+		inode->i_private = NULL;
+		wake_up_all(&shmem_falloc_waitq);
+		spin_unlock(&inode->i_lock);
 		error = 0;
 		goto out;
 	}
@@ -1840,6 +1859,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		goto out;
 	}
 
+	shmem_falloc.waitq = NULL;
 	shmem_falloc.start = start;
 	shmem_falloc.next  = start;
 	shmem_falloc.nr_falloced = 0;
@@ -2063,8 +2083,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct
 
 	if (new_dentry->d_inode) {
 		(void) shmem_unlink(new_dir, new_dentry);
-		if (they_are_dirs)
+		if (they_are_dirs) {
+			drop_nlink(new_dentry->d_inode);
 			drop_nlink(old_dir);
+		}
 	} else if (they_are_dirs) {
 		drop_nlink(old_dir);
 		inc_nlink(new_dir);
diff --git a/mm/slab.c b/mm/slab.c
index b264214c77ea..0b1c2a58559d 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -375,6 +375,39 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 
 #endif
 
+#define OBJECT_FREE (0)
+#define OBJECT_ACTIVE (1)
+
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+
+static void set_obj_status(struct page *page, int idx, int val)
+{
+	int freelist_size;
+	char *status;
+	struct kmem_cache *cachep = page->slab_cache;
+
+	freelist_size = cachep->num * sizeof(unsigned int);
+	status = (char *)page->freelist + freelist_size;
+	status[idx] = val;
+}
+
+static inline unsigned int get_obj_status(struct page *page, int idx)
+{
+	int freelist_size;
+	char *status;
+	struct kmem_cache *cachep = page->slab_cache;
+
+	freelist_size = cachep->num * sizeof(unsigned int);
+	status = (char *)page->freelist + freelist_size;
+
+	return status[idx];
+}
+
+#else
+static inline void set_obj_status(struct page *page, int idx, int val) {}
+
+#endif
+
 /*
  * Do not go above this order unless 0 objects fit into the slab or
  * overridden on the command line.
@@ -565,9 +598,18 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 	return cachep->array[smp_processor_id()];
 }
 
-static size_t slab_mgmt_size(size_t nr_objs, size_t align)
+static size_t calculate_freelist_size(int nr_objs, size_t align)
 {
-	return ALIGN(nr_objs * sizeof(unsigned int), align);
+	size_t freelist_size;
+
+	freelist_size = nr_objs * sizeof(unsigned int);
+	if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
+		freelist_size += nr_objs * sizeof(char);
+
+	if (align)
+		freelist_size = ALIGN(freelist_size, align);
+
+	return freelist_size;
 }
 
 /*
@@ -600,6 +642,10 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 		nr_objs = slab_size / buffer_size;
 
 	} else {
+		int extra_space = 0;
+
+		if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
+			extra_space = sizeof(char);
 		/*
 		 * Ignore padding for the initial guess. The padding
 		 * is at most @align-1 bytes, and @buffer_size is at
@@ -608,17 +654,18 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 		 * into the memory allocation when taking the padding
 		 * into account.
 		 */
-		nr_objs = (slab_size) / (buffer_size + sizeof(unsigned int));
+		nr_objs = (slab_size) /
+			(buffer_size + sizeof(unsigned int) + extra_space);
 
 		/*
 		 * This calculated number will be either the right
 		 * amount, or one greater than what we want.
 		 */
-		if (slab_mgmt_size(nr_objs, align) + nr_objs*buffer_size
-		       > slab_size)
+		if (calculate_freelist_size(nr_objs, align) >
+			slab_size - nr_objs * buffer_size)
 			nr_objs--;
 
-		mgmt_size = slab_mgmt_size(nr_objs, align);
+		mgmt_size = calculate_freelist_size(nr_objs, align);
 	}
 	*num = nr_objs;
 	*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
@@ -2011,13 +2058,16 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 			continue;
 
 		if (flags & CFLGS_OFF_SLAB) {
+			size_t freelist_size_per_obj = sizeof(unsigned int);
 			/*
 			 * Max number of objs-per-slab for caches which
 			 * use off-slab slabs. Needed to avoid a possible
 			 * looping condition in cache_grow().
 			 */
+			if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
+				freelist_size_per_obj += sizeof(char);
 			offslab_limit = size;
-			offslab_limit /= sizeof(unsigned int);
+			offslab_limit /= freelist_size_per_obj;
 
  			if (num > offslab_limit)
 				break;
@@ -2139,7 +2189,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 int
 __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 {
-	size_t left_over, freelist_size, ralign;
+	size_t left_over, freelist_size;
+	size_t ralign = BYTES_PER_WORD;
 	gfp_t gfp;
 	int err;
 	size_t size = cachep->size;
@@ -2172,14 +2223,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 		size &= ~(BYTES_PER_WORD - 1);
 	}
 
-	/*
-	 * Redzoning and user store require word alignment or possibly larger.
-	 * Note this will be overridden by architecture or caller mandated
-	 * alignment if either is greater than BYTES_PER_WORD.
-	 */
-	if (flags & SLAB_STORE_USER)
-		ralign = BYTES_PER_WORD;
-
 	if (flags & SLAB_RED_ZONE) {
 		ralign = REDZONE_ALIGN;
 		/* If redzoning, ensure that the second redzone is suitably
@@ -2258,8 +2301,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (!cachep->num)
 		return -E2BIG;
 
-	freelist_size =
-		ALIGN(cachep->num * sizeof(unsigned int), cachep->align);
+	freelist_size = calculate_freelist_size(cachep->num, cachep->align);
 
 	/*
 	 * If the slab has been placed off-slab, and we have enough space then
@@ -2272,7 +2314,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 
 	if (flags & CFLGS_OFF_SLAB) {
 		/* really off slab. No need for manual alignment */
-		freelist_size = cachep->num * sizeof(unsigned int);
+		freelist_size = calculate_freelist_size(cachep->num, 0);
 
 #ifdef CONFIG_PAGE_POISONING
 		/* If we're going to use the generic kernel_map_pages()
@@ -2589,6 +2631,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 		if (cachep->ctor)
 			cachep->ctor(objp);
 #endif
+		set_obj_status(page, i, OBJECT_FREE);
 		slab_freelist(page)[i] = i;
 	}
 }
@@ -2797,6 +2840,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	BUG_ON(objnr >= cachep->num);
 	BUG_ON(objp != index_to_obj(cachep, page, objnr));
 
+	set_obj_status(page, objnr, OBJECT_FREE);
 	if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
 		if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
@@ -2930,6 +2974,8 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
 static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 				gfp_t flags, void *objp, unsigned long caller)
 {
+	struct page *page;
+
 	if (!objp)
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
@@ -2960,6 +3006,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
 		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
 	}
+
+	page = virt_to_head_page(objp);
+	set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE);
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON)
 		cachep->ctor(objp);
@@ -3073,7 +3122,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = node_zonelist(slab_node(), flags);
 
 retry:
@@ -3131,7 +3180,7 @@ retry:
 		}
 	}
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+	if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return obj;
 }
@@ -4201,21 +4250,12 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c,
 						struct page *page)
 {
 	void *p;
-	int i, j;
+	int i;
 
 	if (n[0] == n[1])
 		return;
 	for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
-		bool active = true;
-
-		for (j = page->active; j < c->num; j++) {
-			/* Skip freed item */
-			if (slab_freelist(page)[j] == i) {
-				active = false;
-				break;
-			}
-		}
-		if (!active)
+		if (get_obj_status(page, i) != OBJECT_ACTIVE)
 			continue;
 
 		if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 1ec3c619ba04..f149e6724411 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -56,7 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			continue;
 		}
 
-#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON)
+#if !defined(CONFIG_SLUB)
 		/*
 		 * For simplicity, we won't check this in the list of memcg
 		 * caches. We have control over memcg naming, and if there
diff --git a/mm/slub.c b/mm/slub.c
index 25f14ad8f817..7611f148ee81 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1684,7 +1684,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 		return NULL;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		zonelist = node_zonelist(slab_node(), flags);
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 			struct kmem_cache_node *n;
@@ -1696,19 +1696,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 				object = get_partial_node(s, n, c, flags);
 				if (object) {
 					/*
-					 * Return the object even if
-					 * put_mems_allowed indicated that
-					 * the cpuset mems_allowed was
-					 * updated in parallel. It's a
-					 * harmless race between the alloc
-					 * and the cpuset update.
+					 * Don't check read_mems_allowed_retry()
+					 * here - if mems_allowed was updated in
+					 * parallel, that was a harmless race
+					 * between allocation and the cpuset
+					 * update
 					 */
-					put_mems_allowed(cpuset_mems_cookie);
 					return object;
 				}
 			}
 		}
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 #endif
 	return NULL;
 }
diff --git a/mm/swap.c b/mm/swap.c
index 0092097b3f4c..c8048d71c642 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -948,6 +948,57 @@ void __pagevec_lru_add(struct pagevec *pvec)
 EXPORT_SYMBOL(__pagevec_lru_add);
 
 /**
+ * pagevec_lookup_entries - gang pagecache lookup
+ * @pvec:	Where the resulting entries are placed
+ * @mapping:	The address_space to search
+ * @start:	The starting entry index
+ * @nr_entries:	The maximum number of entries
+ * @indices:	The cache indices corresponding to the entries in @pvec
+ *
+ * pagevec_lookup_entries() will search for and return a group of up
+ * to @nr_entries pages and shadow entries in the mapping.  All
+ * entries are placed in @pvec.  pagevec_lookup_entries() takes a
+ * reference against actual pages in @pvec.
+ *
+ * The search returns a group of mapping-contiguous entries with
+ * ascending indexes.  There may be holes in the indices due to
+ * not-present entries.
+ *
+ * pagevec_lookup_entries() returns the number of entries which were
+ * found.
+ */
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_pages,
+				pgoff_t *indices)
+{
+	pvec->nr = find_get_entries(mapping, start, nr_pages,
+				    pvec->pages, indices);
+	return pagevec_count(pvec);
+}
+
+/**
+ * pagevec_remove_exceptionals - pagevec exceptionals pruning
+ * @pvec:	The pagevec to prune
+ *
+ * pagevec_lookup_entries() fills both pages and exceptional radix
+ * tree entries into the pagevec.  This function prunes all
+ * exceptionals from @pvec without leaving holes, so that it can be
+ * passed on to page-only pagevec operations.
+ */
+void pagevec_remove_exceptionals(struct pagevec *pvec)
+{
+	int i, j;
+
+	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+		if (!radix_tree_exceptional_entry(page))
+			pvec->pages[j++] = page;
+	}
+	pvec->nr = j;
+}
+
+/**
  * pagevec_lookup - gang pagecache lookup
  * @pvec:	Where the resulting pages are placed
  * @mapping:	The address_space to search
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4a7f7e6992b6..beeeef8a1b2d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -51,14 +51,32 @@ atomic_long_t nr_swap_pages;
 /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */
 long total_swap_pages;
 static int least_priority;
-static atomic_t highest_priority_index = ATOMIC_INIT(-1);
 
 static const char Bad_file[] = "Bad swap file entry ";
 static const char Unused_file[] = "Unused swap file entry ";
 static const char Bad_offset[] = "Bad swap offset entry ";
 static const char Unused_offset[] = "Unused swap offset entry ";
 
-struct swap_list_t swap_list = {-1, -1};
+/*
+ * all active swap_info_structs
+ * protected with swap_lock, and ordered by priority.
+ */
+PLIST_HEAD(swap_active_head);
+
+/*
+ * all available (active, not full) swap_info_structs
+ * protected with swap_avail_lock, ordered by priority.
+ * This is used by get_swap_page() instead of swap_active_head
+ * because swap_active_head includes all swap_info_structs,
+ * but get_swap_page() doesn't need to look at full ones.
+ * This uses its own lock instead of swap_lock because when a
+ * swap_info_struct changes between not-full/full, it needs to
+ * add/remove itself to/from this list, but the swap_info_struct->lock
+ * is held and the locking order requires swap_lock to be taken
+ * before any swap_info_struct->lock.
+ */
+static PLIST_HEAD(swap_avail_head);
+static DEFINE_SPINLOCK(swap_avail_lock);
 
 struct swap_info_struct *swap_info[MAX_SWAPFILES];
 
@@ -591,6 +609,9 @@ checks:
 	if (si->inuse_pages == si->pages) {
 		si->lowest_bit = si->max;
 		si->highest_bit = 0;
+		spin_lock(&swap_avail_lock);
+		plist_del(&si->avail_list, &swap_avail_head);
+		spin_unlock(&swap_avail_lock);
 	}
 	si->swap_map[offset] = usage;
 	inc_cluster_info_page(si, si->cluster_info, offset);
@@ -640,71 +661,65 @@ no_page:
 
 swp_entry_t get_swap_page(void)
 {
-	struct swap_info_struct *si;
+	struct swap_info_struct *si, *next;
 	pgoff_t offset;
-	int type, next;
-	int wrapped = 0;
-	int hp_index;
 
-	spin_lock(&swap_lock);
 	if (atomic_long_read(&nr_swap_pages) <= 0)
 		goto noswap;
 	atomic_long_dec(&nr_swap_pages);
 
-	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
-		hp_index = atomic_xchg(&highest_priority_index, -1);
-		/*
-		 * highest_priority_index records current highest priority swap
-		 * type which just frees swap entries. If its priority is
-		 * higher than that of swap_list.next swap type, we use it.  It
-		 * isn't protected by swap_lock, so it can be an invalid value
-		 * if the corresponding swap type is swapoff. We double check
-		 * the flags here. It's even possible the swap type is swapoff
-		 * and swapon again and its priority is changed. In such rare
-		 * case, low prority swap type might be used, but eventually
-		 * high priority swap will be used after several rounds of
-		 * swap.
-		 */
-		if (hp_index != -1 && hp_index != type &&
-		    swap_info[type]->prio < swap_info[hp_index]->prio &&
-		    (swap_info[hp_index]->flags & SWP_WRITEOK)) {
-			type = hp_index;
-			swap_list.next = type;
-		}
-
-		si = swap_info[type];
-		next = si->next;
-		if (next < 0 ||
-		    (!wrapped && si->prio != swap_info[next]->prio)) {
-			next = swap_list.head;
-			wrapped++;
-		}
+	spin_lock(&swap_avail_lock);
 
+start_over:
+	plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) {
+		/* requeue si to after same-priority siblings */
+		plist_requeue(&si->avail_list, &swap_avail_head);
+		spin_unlock(&swap_avail_lock);
 		spin_lock(&si->lock);
-		if (!si->highest_bit) {
+		if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {
+			spin_lock(&swap_avail_lock);
+			if (plist_node_empty(&si->avail_list)) {
+				spin_unlock(&si->lock);
+				goto nextsi;
+			}
+			WARN(!si->highest_bit,
+			     "swap_info %d in list but !highest_bit\n",
+			     si->type);
+			WARN(!(si->flags & SWP_WRITEOK),
+			     "swap_info %d in list but !SWP_WRITEOK\n",
+			     si->type);
+			plist_del(&si->avail_list, &swap_avail_head);
 			spin_unlock(&si->lock);
-			continue;
+			goto nextsi;
 		}
-		if (!(si->flags & SWP_WRITEOK)) {
-			spin_unlock(&si->lock);
-			continue;
-		}
-
-		swap_list.next = next;
 
-		spin_unlock(&swap_lock);
 		/* This is called for allocating swap entry for cache */
 		offset = scan_swap_map(si, SWAP_HAS_CACHE);
 		spin_unlock(&si->lock);
 		if (offset)
-			return swp_entry(type, offset);
-		spin_lock(&swap_lock);
-		next = swap_list.next;
+			return swp_entry(si->type, offset);
+		pr_debug("scan_swap_map of si %d failed to find offset\n",
+		       si->type);
+		spin_lock(&swap_avail_lock);
+nextsi:
+		/*
+		 * if we got here, it's likely that si was almost full before,
+		 * and since scan_swap_map() can drop the si->lock, multiple
+		 * callers probably all tried to get a page from the same si
+		 * and it filled up before we could get one; or, the si filled
+		 * up between us dropping swap_avail_lock and taking si->lock.
+		 * Since we dropped the swap_avail_lock, the swap_avail_head
+		 * list may have been modified; so if next is still in the
+		 * swap_avail_head list then try it, otherwise start over.
+		 */
+		if (plist_node_empty(&next->avail_list))
+			goto start_over;
 	}
 
+	spin_unlock(&swap_avail_lock);
+
 	atomic_long_inc(&nr_swap_pages);
 noswap:
-	spin_unlock(&swap_lock);
 	return (swp_entry_t) {0};
 }
 
@@ -766,27 +781,6 @@ out:
 	return NULL;
 }
 
-/*
- * This swap type frees swap entry, check if it is the highest priority swap
- * type which just frees swap entry. get_swap_page() uses
- * highest_priority_index to search highest priority swap type. The
- * swap_info_struct.lock can't protect us if there are multiple swap types
- * active, so we use atomic_cmpxchg.
- */
-static void set_highest_priority_index(int type)
-{
-	int old_hp_index, new_hp_index;
-
-	do {
-		old_hp_index = atomic_read(&highest_priority_index);
-		if (old_hp_index != -1 &&
-			swap_info[old_hp_index]->prio >= swap_info[type]->prio)
-			break;
-		new_hp_index = type;
-	} while (atomic_cmpxchg(&highest_priority_index,
-		old_hp_index, new_hp_index) != old_hp_index);
-}
-
 static unsigned char swap_entry_free(struct swap_info_struct *p,
 				     swp_entry_t entry, unsigned char usage)
 {
@@ -828,9 +822,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 		dec_cluster_info_page(p, p->cluster_info, offset);
 		if (offset < p->lowest_bit)
 			p->lowest_bit = offset;
-		if (offset > p->highest_bit)
+		if (offset > p->highest_bit) {
+			bool was_full = !p->highest_bit;
 			p->highest_bit = offset;
-		set_highest_priority_index(p->type);
+			if (was_full && (p->flags & SWP_WRITEOK)) {
+				spin_lock(&swap_avail_lock);
+				WARN_ON(!plist_node_empty(&p->avail_list));
+				if (plist_node_empty(&p->avail_list))
+					plist_add(&p->avail_list,
+						  &swap_avail_head);
+				spin_unlock(&swap_avail_lock);
+			}
+		}
 		atomic_long_inc(&nr_swap_pages);
 		p->inuse_pages--;
 		frontswap_invalidate_page(p->type, offset);
@@ -1765,30 +1768,37 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				struct swap_cluster_info *cluster_info)
 {
-	int i, prev;
-
 	if (prio >= 0)
 		p->prio = prio;
 	else
 		p->prio = --least_priority;
+	/*
+	 * the plist prio is negated because plist ordering is
+	 * low-to-high, while swap ordering is high-to-low
+	 */
+	p->list.prio = -p->prio;
+	p->avail_list.prio = -p->prio;
 	p->swap_map = swap_map;
 	p->cluster_info = cluster_info;
 	p->flags |= SWP_WRITEOK;
 	atomic_long_add(p->pages, &nr_swap_pages);
 	total_swap_pages += p->pages;
 
-	/* insert swap space into swap_list: */
-	prev = -1;
-	for (i = swap_list.head; i >= 0; i = swap_info[i]->next) {
-		if (p->prio >= swap_info[i]->prio)
-			break;
-		prev = i;
-	}
-	p->next = i;
-	if (prev < 0)
-		swap_list.head = swap_list.next = p->type;
-	else
-		swap_info[prev]->next = p->type;
+	assert_spin_locked(&swap_lock);
+	/*
+	 * both lists are plists, and thus priority ordered.
+	 * swap_active_head needs to be priority ordered for swapoff(),
+	 * which on removal of any swap_info_struct with an auto-assigned
+	 * (i.e. negative) priority increments the auto-assigned priority
+	 * of any lower-priority swap_info_structs.
+	 * swap_avail_head needs to be priority ordered for get_swap_page(),
+	 * which allocates swap pages from the highest available priority
+	 * swap_info_struct.
+	 */
+	plist_add(&p->list, &swap_active_head);
+	spin_lock(&swap_avail_lock);
+	plist_add(&p->avail_list, &swap_avail_head);
+	spin_unlock(&swap_avail_lock);
 }
 
 static void enable_swap_info(struct swap_info_struct *p, int prio,
@@ -1823,8 +1833,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct address_space *mapping;
 	struct inode *inode;
 	struct filename *pathname;
-	int i, type, prev;
-	int err;
+	int err, found = 0;
 	unsigned int old_block_size;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -1842,17 +1851,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		goto out;
 
 	mapping = victim->f_mapping;
-	prev = -1;
 	spin_lock(&swap_lock);
-	for (type = swap_list.head; type >= 0; type = swap_info[type]->next) {
-		p = swap_info[type];
+	plist_for_each_entry(p, &swap_active_head, list) {
 		if (p->flags & SWP_WRITEOK) {
-			if (p->swap_file->f_mapping == mapping)
+			if (p->swap_file->f_mapping == mapping) {
+				found = 1;
 				break;
+			}
 		}
-		prev = type;
 	}
-	if (type < 0) {
+	if (!found) {
 		err = -EINVAL;
 		spin_unlock(&swap_lock);
 		goto out_dput;
@@ -1864,20 +1872,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		spin_unlock(&swap_lock);
 		goto out_dput;
 	}
-	if (prev < 0)
-		swap_list.head = p->next;
-	else
-		swap_info[prev]->next = p->next;
-	if (type == swap_list.next) {
-		/* just pick something that's safe... */
-		swap_list.next = swap_list.head;
-	}
+	spin_lock(&swap_avail_lock);
+	plist_del(&p->avail_list, &swap_avail_head);
+	spin_unlock(&swap_avail_lock);
 	spin_lock(&p->lock);
 	if (p->prio < 0) {
-		for (i = p->next; i >= 0; i = swap_info[i]->next)
-			swap_info[i]->prio = p->prio--;
+		struct swap_info_struct *si = p;
+
+		plist_for_each_entry_continue(si, &swap_active_head, list) {
+			si->prio++;
+			si->list.prio--;
+			si->avail_list.prio--;
+		}
 		least_priority++;
 	}
+	plist_del(&p->list, &swap_active_head);
 	atomic_long_sub(p->pages, &nr_swap_pages);
 	total_swap_pages -= p->pages;
 	p->flags &= ~SWP_WRITEOK;
@@ -1885,7 +1894,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	spin_unlock(&swap_lock);
 
 	set_current_oom_origin();
-	err = try_to_unuse(type, false, 0); /* force all pages to be unused */
+	err = try_to_unuse(p->type, false, 0); /* force unuse all pages */
 	clear_current_oom_origin();
 
 	if (err) {
@@ -1926,7 +1935,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	frontswap_map = frontswap_map_get(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
-	frontswap_invalidate_area(type);
+	frontswap_invalidate_area(p->type);
 	frontswap_map_set(p, NULL);
 	mutex_unlock(&swapon_mutex);
 	free_percpu(p->percpu_cluster);
@@ -1935,7 +1944,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	vfree(cluster_info);
 	vfree(frontswap_map);
 	/* Destroy swap account information */
-	swap_cgroup_swapoff(type);
+	swap_cgroup_swapoff(p->type);
 
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
@@ -2142,8 +2151,9 @@ static struct swap_info_struct *alloc_swap_info(void)
 		 */
 	}
 	INIT_LIST_HEAD(&p->first_swap_extent.list);
+	plist_node_init(&p->list, 0);
+	plist_node_init(&p->avail_list, 0);
 	p->flags = SWP_USED;
-	p->next = -1;
 	spin_unlock(&swap_lock);
 	spin_lock_init(&p->lock);
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 353b683afd6e..827ad8d2b5cd 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -20,8 +20,25 @@
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
+static void clear_exceptional_entry(struct address_space *mapping,
+				    pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	radix_tree_delete_item(&mapping->page_tree, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+}
 
 /**
  * do_invalidatepage - invalidate part or all of a page
@@ -208,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	unsigned int	partial_start;	/* inclusive */
 	unsigned int	partial_end;	/* exclusive */
 	struct pagevec	pvec;
+	pgoff_t		indices[PAGEVEC_SIZE];
 	pgoff_t		index;
 	int		i;
 
@@ -238,17 +256,23 @@ void truncate_inode_pages_range(struct address_space *mapping,
 
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index < end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -259,6 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -307,14 +332,16 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		if (!pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+		if (!pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 			if (index == start)
 				break;
 			index = start;
 			continue;
 		}
-		if (index == start && pvec.pages[0]->index >= end) {
+		if (index == start && indices[0] >= end) {
+			pagevec_remove_exceptionals(&pvec);
 			pagevec_release(&pvec);
 			break;
 		}
@@ -323,16 +350,22 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			wait_on_page_writeback(page);
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -375,6 +408,7 @@ EXPORT_SYMBOL(truncate_inode_pages);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index = start;
 	unsigned long ret;
@@ -390,17 +424,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	 */
 
 	pagevec_init(&pvec, 0);
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -414,6 +454,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 				deactivate_page(page);
 			count += ret;
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -481,6 +522,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page)
 int invalidate_inode_pages2_range(struct address_space *mapping,
 				  pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index;
 	int i;
@@ -491,17 +533,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 	cleancache_invalidate_inode(mapping);
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			if (page->mapping != mapping) {
@@ -539,6 +587,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				ret = ret2;
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -613,12 +662,67 @@ EXPORT_SYMBOL(truncate_pagecache);
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
+	loff_t oldsize = inode->i_size;
+
 	i_size_write(inode, newsize);
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
 	truncate_pagecache(inode, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
 
 /**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
  * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
  * @inode: inode
  * @lstart: offset of beginning of hole
diff --git a/mm/util.c b/mm/util.c
index a24aa22f2473..c1010cb7ca0c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -275,17 +275,14 @@ pid_t vm_is_stack(struct task_struct *task,
 
 	if (in_group) {
 		struct task_struct *t;
-		rcu_read_lock();
-		if (!pid_alive(task))
-			goto done;
 
-		t = task;
-		do {
+		rcu_read_lock();
+		for_each_thread(task, t) {
 			if (vm_is_stack_for_task(t, vma)) {
 				ret = t->pid;
 				goto done;
 			}
-		} while_each_thread(task, t);
+		}
 done:
 		rcu_read_unlock();
 	}
diff --git a/mm/vmacache.c b/mm/vmacache.c
new file mode 100644
index 000000000000..1037a3bab505
--- /dev/null
+++ b/mm/vmacache.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) 2014 Davidlohr Bueso.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
+
+/*
+ * Flush vma caches for threads that share a given mm.
+ *
+ * The operation is safe because the caller holds the mmap_sem
+ * exclusively and other threads accessing the vma cache will
+ * have mmap_sem held at least for read, so no extra locking
+ * is required to maintain the vma cache.
+ */
+void vmacache_flush_all(struct mm_struct *mm)
+{
+	struct task_struct *g, *p;
+
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		/*
+		 * Only flush the vmacache pointers as the
+		 * mm seqnum is already set and curr's will
+		 * be set upon invalidation when the next
+		 * lookup is done.
+		 */
+		if (mm == p->mm)
+			vmacache_flush(p);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * This task may be accessing a foreign mm via (for example)
+ * get_user_pages()->find_vma().  The vmacache is task-local and this
+ * task's vmacache pertains to a different mm (ie, its own).  There is
+ * nothing we can do here.
+ *
+ * Also handle the case where a kernel thread has adopted this mm via use_mm().
+ * That kernel thread's vmacache is not applicable to this mm.
+ */
+static bool vmacache_valid_mm(struct mm_struct *mm)
+{
+	return current->mm == mm && !(current->flags & PF_KTHREAD);
+}
+
+void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
+{
+	if (vmacache_valid_mm(newvma->vm_mm))
+		current->vmacache[VMACACHE_HASH(addr)] = newvma;
+}
+
+static bool vmacache_valid(struct mm_struct *mm)
+{
+	struct task_struct *curr;
+
+	if (!vmacache_valid_mm(mm))
+		return false;
+
+	curr = current;
+	if (mm->vmacache_seqnum != curr->vmacache_seqnum) {
+		/*
+		 * First attempt will always be invalid, initialize
+		 * the new cache for this task here.
+		 */
+		curr->vmacache_seqnum = mm->vmacache_seqnum;
+		vmacache_flush(curr);
+		return false;
+	}
+	return true;
+}
+
+struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (!vma)
+			continue;
+		if (WARN_ON_ONCE(vma->vm_mm != mm))
+			break;
+		if (vma->vm_start <= addr && vma->vm_end > addr)
+			return vma;
+	}
+
+	return NULL;
+}
+
+#ifndef CONFIG_MMU
+struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+					   unsigned long start,
+					   unsigned long end)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start == start && vma->vm_end == end)
+			return vma;
+	}
+
+	return NULL;
+}
+#endif
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index d4042e75f7c7..c5afd573d7da 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -165,6 +165,7 @@ static void vmpressure_work_fn(struct work_struct *work)
 	unsigned long scanned;
 	unsigned long reclaimed;
 
+	spin_lock(&vmpr->sr_lock);
 	/*
 	 * Several contexts might be calling vmpressure(), so it is
 	 * possible that the work was rescheduled again before the old
@@ -173,11 +174,12 @@ static void vmpressure_work_fn(struct work_struct *work)
 	 * here. No need for any locks here since we don't care if
 	 * vmpr->reclaimed is in sync.
 	 */
-	if (!vmpr->scanned)
+	scanned = vmpr->scanned;
+	if (!scanned) {
+		spin_unlock(&vmpr->sr_lock);
 		return;
+	}
 
-	spin_lock(&vmpr->sr_lock);
-	scanned = vmpr->scanned;
 	reclaimed = vmpr->reclaimed;
 	vmpr->scanned = 0;
 	vmpr->reclaimed = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a9c74b409681..be6a689a71a6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -224,15 +224,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	unsigned long freed = 0;
 	unsigned long long delta;
 	long total_scan;
-	long max_pass;
+	long freeable;
 	long nr;
 	long new_nr;
 	int nid = shrinkctl->nid;
 	long batch_size = shrinker->batch ? shrinker->batch
 					  : SHRINK_BATCH;
 
-	max_pass = shrinker->count_objects(shrinker, shrinkctl);
-	if (max_pass == 0)
+	freeable = shrinker->count_objects(shrinker, shrinkctl);
+	if (freeable == 0)
 		return 0;
 
 	/*
@@ -244,14 +244,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 
 	total_scan = nr;
 	delta = (4 * nr_pages_scanned) / shrinker->seeks;
-	delta *= max_pass;
+	delta *= freeable;
 	do_div(delta, lru_pages + 1);
 	total_scan += delta;
 	if (total_scan < 0) {
 		printk(KERN_ERR
 		"shrink_slab: %pF negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
-		total_scan = max_pass;
+		total_scan = freeable;
 	}
 
 	/*
@@ -260,26 +260,26 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	 * shrinkers to return -1 all the time. This results in a large
 	 * nr being built up so when a shrink that can do some work
 	 * comes along it empties the entire cache due to nr >>>
-	 * max_pass.  This is bad for sustaining a working set in
+	 * freeable. This is bad for sustaining a working set in
 	 * memory.
 	 *
 	 * Hence only allow the shrinker to scan the entire cache when
 	 * a large delta change is calculated directly.
 	 */
-	if (delta < max_pass / 4)
-		total_scan = min(total_scan, max_pass / 2);
+	if (delta < freeable / 4)
+		total_scan = min(total_scan, freeable / 2);
 
 	/*
 	 * Avoid risking looping forever due to too large nr value:
 	 * never try to free more than twice the estimate number of
 	 * freeable entries.
 	 */
-	if (total_scan > max_pass * 2)
-		total_scan = max_pass * 2;
+	if (total_scan > freeable * 2)
+		total_scan = freeable * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
 				nr_pages_scanned, lru_pages,
-				max_pass, delta, total_scan);
+				freeable, delta, total_scan);
 
 	/*
 	 * Normally, we should not scan less than batch_size objects in one
@@ -292,12 +292,12 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	 *
 	 * We detect the "tight on memory" situations by looking at the total
 	 * number of objects we want to scan (total_scan). If it is greater
-	 * than the total number of objects on slab (max_pass), we must be
+	 * than the total number of objects on slab (freeable), we must be
 	 * scanning at high prio and therefore should try to reclaim as much as
 	 * possible.
 	 */
 	while (total_scan >= batch_size ||
-	       total_scan >= max_pass) {
+	       total_scan >= freeable) {
 		unsigned long ret;
 		unsigned long nr_to_scan = min(batch_size, total_scan);
 
@@ -1144,7 +1144,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 			TTU_UNMAP|TTU_IGNORE_ACCESS,
 			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
 	list_splice(&clean_pages, page_list);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
+	mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
 	return ret;
 }
 
@@ -1540,19 +1540,18 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * If dirty pages are scanned that are not queued for IO, it
 		 * implies that flushers are not keeping up. In this case, flag
 		 * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
-		 * pages from reclaim context. It will forcibly stall in the
-		 * next check.
+		 * pages from reclaim context.
 		 */
 		if (nr_unqueued_dirty == nr_taken)
 			zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
 
 		/*
-		 * In addition, if kswapd scans pages marked marked for
-		 * immediate reclaim and under writeback (nr_immediate), it
-		 * implies that pages are cycling through the LRU faster than
+		 * If kswapd scans pages marked marked for immediate
+		 * reclaim and under writeback (nr_immediate), it implies
+		 * that pages are cycling through the LRU faster than
 		 * they are written so also forcibly stall.
 		 */
-		if (nr_unqueued_dirty == nr_taken || nr_immediate)
+		if (nr_immediate)
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
@@ -2019,13 +2018,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct blk_plug plug;
-	bool scan_adjusted = false;
+	bool scan_adjusted;
 
 	get_scan_count(lruvec, sc, nr);
 
 	/* Record the original scan target for proportional adjustments later */
 	memcpy(targets, nr, sizeof(nr));
 
+	/*
+	 * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
+	 * event that can occur when there is little memory pressure e.g.
+	 * multiple streaming readers/writers. Hence, we do not abort scanning
+	 * when the requested number of pages are reclaimed when scanning at
+	 * DEF_PRIORITY on the assumption that the fact we are direct
+	 * reclaiming implies that kswapd is not keeping up and it is best to
+	 * do a batch of work at once. For memcg reclaim one check is made to
+	 * abort proportional reclaim if either the file or anon lru has already
+	 * dropped to zero at the first pass.
+	 */
+	scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
+			 sc->priority == DEF_PRIORITY);
+
 	blk_start_plug(&plug);
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
@@ -2046,17 +2059,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 			continue;
 
 		/*
-		 * For global direct reclaim, reclaim only the number of pages
-		 * requested. Less care is taken to scan proportionally as it
-		 * is more important to minimise direct reclaim stall latency
-		 * than it is to properly age the LRU lists.
-		 */
-		if (global_reclaim(sc) && !current_is_kswapd())
-			break;
-
-		/*
 		 * For kswapd and memcg, reclaim at least the number of pages
-		 * requested. Ensure that the anon and file LRUs shrink
+		 * requested. Ensure that the anon and file LRUs are scanned
 		 * proportionally what was requested by get_scan_count(). We
 		 * stop reclaiming one LRU and reduce the amount scanning
 		 * proportional to the original scan target.
@@ -2064,6 +2068,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
 		nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
 
+		/*
+		 * It's just vindictive to attack the larger once the smaller
+		 * has gone to zero.  And given the way we stop scanning the
+		 * smaller below, this makes sure that we only make one nudge
+		 * towards proportionality once we've got nr_to_reclaim.
+		 */
+		if (!nr_file || !nr_anon)
+			break;
+
 		if (nr_file > nr_anon) {
 			unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
 						targets[LRU_ACTIVE_ANON] + 1;
@@ -2425,8 +2438,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			unsigned long lru_pages = 0;
 
 			nodes_clear(shrink->nodes_to_scan);
-			for_each_zone_zonelist(zone, z, zonelist,
-					gfp_zone(sc->gfp_mask)) {
+			for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_zone(sc->gfp_mask), sc->nodemask) {
 				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 					continue;
 
@@ -2502,10 +2515,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
+		if (!populated_zone(zone))
+			continue;
+
 		pfmemalloc_reserve += min_wmark_pages(zone);
 		free_pages += zone_page_state(zone, NR_FREE_PAGES);
 	}
 
+	/* If there are no reserves (unexpected config) then do not throttle */
+	if (!pfmemalloc_reserve)
+		return true;
+
 	wmark_ok = free_pages > pfmemalloc_reserve / 2;
 
 	/* kswapd must be awake if processes are being throttled */
@@ -2530,9 +2550,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 					nodemask_t *nodemask)
 {
+	struct zoneref *z;
 	struct zone *zone;
-	int high_zoneidx = gfp_zone(gfp_mask);
-	pg_data_t *pgdat;
+	pg_data_t *pgdat = NULL;
 
 	/*
 	 * Kernel threads should not be throttled as they may be indirectly
@@ -2551,10 +2571,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	if (fatal_signal_pending(current))
 		goto out;
 
-	/* Check if the pfmemalloc reserves are ok */
-	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
-	pgdat = zone->zone_pgdat;
-	if (pfmemalloc_watermark_ok(pgdat))
+	/*
+	 * Check if the pfmemalloc reserves are ok by finding the first node
+	 * with a usable ZONE_NORMAL or lower zone. The expectation is that
+	 * GFP_KERNEL will be required for allocating network buffers when
+	 * swapping over the network so ZONE_HIGHMEM is unusable.
+	 *
+	 * Throttling is based on the first usable node and throttled processes
+	 * wait on a queue until kswapd makes progress and wakes them. There
+	 * is an affinity then between processes waking up and where reclaim
+	 * progress has been made assuming the process wakes on the same node.
+	 * More importantly, processes running on remote nodes will not compete
+	 * for remote pfmemalloc reserves and processes on different nodes
+	 * should make reasonable progress.
+	 */
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_mask, nodemask) {
+		if (zone_idx(zone) > ZONE_NORMAL)
+			continue;
+
+		/* Throttle based on the first usable node */
+		pgdat = zone->zone_pgdat;
+		if (pfmemalloc_watermark_ok(pgdat))
+			goto out;
+		break;
+	}
+
+	/* If no zone was usable by the allocation flags then do not throttle */
+	if (!pgdat)
 		goto out;
 
 	/* Account for the throttling */
@@ -2816,18 +2860,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 		return false;
 
 	/*
-	 * There is a potential race between when kswapd checks its watermarks
-	 * and a process gets throttled. There is also a potential race if
-	 * processes get throttled, kswapd wakes, a large process exits therby
-	 * balancing the zones that causes kswapd to miss a wakeup. If kswapd
-	 * is going to sleep, no process should be sleeping on pfmemalloc_wait
-	 * so wake them now if necessary. If necessary, processes will wake
-	 * kswapd and get throttled again
+	 * The throttled processes are normally woken up in balance_pgdat() as
+	 * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+	 * race between when kswapd checks the watermarks and a process gets
+	 * throttled. There is also a potential race if processes get
+	 * throttled, kswapd wakes, a large process exits thereby balancing the
+	 * zones, which causes kswapd to exit balance_pgdat() before reaching
+	 * the wake up checks. If kswapd is going to sleep, no process should
+	 * be sleeping on pfmemalloc_wait, so wake them now if necessary. If
+	 * the wake up is premature, processes will wake kswapd and get
+	 * throttled again. The difference from wake ups in balance_pgdat() is
+	 * that here we are under prepare_to_wait().
 	 */
-	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
-		wake_up(&pgdat->pfmemalloc_wait);
-		return false;
-	}
+	if (waitqueue_active(&pgdat->pfmemalloc_wait))
+		wake_up_all(&pgdat->pfmemalloc_wait);
 
 	return pgdat_balanced(pgdat, order, classzone_idx);
 }
@@ -3285,7 +3331,10 @@ static int kswapd(void *p)
 		}
 	}
 
+	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
 	current->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+
 	return 0;
 }
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 175273f38cb1..44ebd5c2cd4a 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
+	vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out_uninit_mvrp;
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 6ee48aac776f..5d56e05d83dd 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -106,56 +106,6 @@ u16 vlan_dev_vlan_id(const struct net_device *dev)
 }
 EXPORT_SYMBOL(vlan_dev_vlan_id);
 
-static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
-{
-	if (skb_cow(skb, skb_headroom(skb)) < 0)
-		return NULL;
-	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
-	skb->mac_header += VLAN_HLEN;
-	return skb;
-}
-
-struct sk_buff *vlan_untag(struct sk_buff *skb)
-{
-	struct vlan_hdr *vhdr;
-	u16 vlan_tci;
-
-	if (unlikely(vlan_tx_tag_present(skb))) {
-		/* vlan_tci is already set-up so leave this for another time */
-		return skb;
-	}
-
-	skb = skb_share_check(skb, GFP_ATOMIC);
-	if (unlikely(!skb))
-		goto err_free;
-
-	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
-		goto err_free;
-
-	vhdr = (struct vlan_hdr *) skb->data;
-	vlan_tci = ntohs(vhdr->h_vlan_TCI);
-	__vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci);
-
-	skb_pull_rcsum(skb, VLAN_HLEN);
-	vlan_set_encap_proto(skb, vhdr);
-
-	skb = vlan_reorder_header(skb);
-	if (unlikely(!skb))
-		goto err_free;
-
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb_reset_mac_len(skb);
-
-	return skb;
-
-err_free:
-	kfree_skb(skb);
-	return NULL;
-}
-EXPORT_SYMBOL(vlan_untag);
-
-
 /*
  * vlan info and vid list
  */
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 27bfe2f8e2de..1f26a1b8c576 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -524,6 +524,11 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
 	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
 }
 
+static int vlan_dev_get_lock_subclass(struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->nest_level;
+}
+
 static const struct header_ops vlan_header_ops = {
 	.create	 = vlan_dev_hard_header,
 	.rebuild = vlan_dev_rebuild_header,
@@ -559,7 +564,7 @@ static const struct net_device_ops vlan_netdev_ops;
 static int vlan_dev_init(struct net_device *dev)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
-	int subclass = 0, i;
+	int i;
 
 	netif_carrier_off(dev);
 
@@ -608,10 +613,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-	if (is_vlan_dev(real_dev))
-		subclass = 1;
-
-	vlan_dev_set_lockdep_class(dev, subclass);
+	vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
 
 	vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
 	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
@@ -633,8 +635,6 @@ static void vlan_dev_uninit(struct net_device *dev)
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	int i;
 
-	free_percpu(vlan->vlan_pcpu_stats);
-	vlan->vlan_pcpu_stats = NULL;
 	for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) {
 		while ((pm = vlan->egress_priority_map[i]) != NULL) {
 			vlan->egress_priority_map[i] = pm->next;
@@ -791,8 +791,18 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
+	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
 };
 
+static void vlan_dev_free(struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+
+	free_percpu(vlan->vlan_pcpu_stats);
+	vlan->vlan_pcpu_stats = NULL;
+	free_netdev(dev);
+}
+
 void vlan_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -802,7 +812,7 @@ void vlan_setup(struct net_device *dev)
 	dev->tx_queue_len	= 0;
 
 	dev->netdev_ops		= &vlan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->destructor		= vlan_dev_free;
 	dev->ethtool_ops	= &vlan_ethtool_ops;
 
 	memset(dev->broadcast, 0, ETH_ALEN);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 02806c6b2ff3..0c769cc65f25 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1489,8 +1489,6 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 
 	/* Queue packet (standard) */
-	skb->sk = sock;
-
 	if (sock_queue_rcv_skb(sock, skb) < 0)
 		goto drop;
 
@@ -1644,7 +1642,6 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	if (!skb)
 		goto out;
 
-	skb->sk = sk;
 	skb_reserve(skb, ddp_dl->header_length);
 	skb_reserve(skb, dev->hard_header_len);
 	skb->dev = dev;
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 8323bced8e5b..d074d06ce094 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -1545,6 +1545,8 @@ out_neigh:
 	if ((orig_neigh_node) && (!is_single_hop_neigh))
 		batadv_orig_node_free_ref(orig_neigh_node);
 out:
+	if (router_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_ifinfo);
 	if (router)
 		batadv_neigh_node_free_ref(router);
 	if (router_router)
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index edee50411892..bd8219a7dddf 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -940,8 +940,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 		 * additional DAT answer may trigger kernel warnings about
 		 * a packet coming from the wrong port.
 		 */
-		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr,
-					BATADV_NO_FLAGS)) {
+		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) {
 			ret = true;
 			goto out;
 		}
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 88df9b1d552d..c46387a46535 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -128,6 +128,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
 {
 	struct batadv_frag_table_entry *chain;
 	struct batadv_frag_list_entry *frag_entry_new = NULL, *frag_entry_curr;
+	struct batadv_frag_list_entry *frag_entry_last = NULL;
 	struct batadv_frag_packet *frag_packet;
 	uint8_t bucket;
 	uint16_t seqno, hdr_size = sizeof(struct batadv_frag_packet);
@@ -180,11 +181,14 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
 			ret = true;
 			goto out;
 		}
+
+		/* store current entry because it could be the last in list */
+		frag_entry_last = frag_entry_curr;
 	}
 
-	/* Reached the end of the list, so insert after 'frag_entry_curr'. */
-	if (likely(frag_entry_curr)) {
-		hlist_add_after(&frag_entry_curr->list, &frag_entry_new->list);
+	/* Reached the end of the list, so insert after 'frag_entry_last'. */
+	if (likely(frag_entry_last)) {
+		hlist_add_after(&frag_entry_last->list, &frag_entry_new->list);
 		chain->size += skb->len - hdr_size;
 		chain->timestamp = jiffies;
 		ret = true;
@@ -418,12 +422,13 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			     struct batadv_neigh_node *neigh_node)
 {
 	struct batadv_priv *bat_priv;
-	struct batadv_hard_iface *primary_if;
+	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_frag_packet frag_header;
 	struct sk_buff *skb_fragment;
 	unsigned mtu = neigh_node->if_incoming->net_dev->mtu;
 	unsigned header_size = sizeof(frag_header);
 	unsigned max_fragment_size, max_packet_size;
+	bool ret = false;
 
 	/* To avoid merge and refragmentation at next-hops we never send
 	 * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
@@ -483,7 +488,11 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			   skb->len + ETH_HLEN);
 	batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
 
-	return true;
+	ret = true;
+
 out_err:
-	return false;
+	if (primary_if)
+		batadv_hardif_free_ref(primary_if);
+
+	return ret;
 }
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 55cf2260d295..36b9ae61f5e8 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -42,8 +42,10 @@
 
 static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node)
 {
-	if (atomic_dec_and_test(&gw_node->refcount))
+	if (atomic_dec_and_test(&gw_node->refcount)) {
+		batadv_orig_node_free_ref(gw_node->orig_node);
 		kfree_rcu(gw_node, rcu);
+	}
 }
 
 static struct batadv_gw_node *
@@ -408,9 +410,14 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv,
 	if (gateway->bandwidth_down == 0)
 		return;
 
+	if (!atomic_inc_not_zero(&orig_node->refcount))
+		return;
+
 	gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC);
-	if (!gw_node)
+	if (!gw_node) {
+		batadv_orig_node_free_ref(orig_node);
 		return;
+	}
 
 	INIT_HLIST_NODE(&gw_node->list);
 	gw_node->orig_node = orig_node;
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index b851cc580853..fbda6b54baff 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -83,7 +83,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 		return true;
 
 	/* no more parents..stop recursion */
-	if (net_dev->iflink == net_dev->ifindex)
+	if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex)
 		return false;
 
 	/* recurse over the parent device */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 853941629dc1..abf612d7d0ae 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -500,12 +500,17 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
 static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 {
 	struct batadv_orig_ifinfo *orig_ifinfo;
+	struct batadv_neigh_node *router;
 
 	orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
 
 	if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
 		batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
 
+	/* this is the last reference to this object */
+	router = rcu_dereference_protected(orig_ifinfo->router, true);
+	if (router)
+		batadv_neigh_node_free_ref_now(router);
 	kfree(orig_ifinfo);
 }
 
@@ -697,6 +702,47 @@ free_orig_node:
 }
 
 /**
+ * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor
+ * @bat_priv: the bat priv with all the soft interface information
+ * @neigh: orig node which is to be checked
+ */
+static void
+batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
+			  struct batadv_neigh_node *neigh)
+{
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
+	struct batadv_hard_iface *if_outgoing;
+	struct hlist_node *node_tmp;
+
+	spin_lock_bh(&neigh->ifinfo_lock);
+
+	/* for all ifinfo objects for this neighinator */
+	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
+				  &neigh->ifinfo_list, list) {
+		if_outgoing = neigh_ifinfo->if_outgoing;
+
+		/* always keep the default interface */
+		if (if_outgoing == BATADV_IF_DEFAULT)
+			continue;
+
+		/* don't purge if the interface is not (going) down */
+		if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
+		    (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
+		    (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+			continue;
+
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "neighbor/ifinfo purge: neighbor %pM, iface: %s\n",
+			   neigh->addr, if_outgoing->net_dev->name);
+
+		hlist_del_rcu(&neigh_ifinfo->list);
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+	}
+
+	spin_unlock_bh(&neigh->ifinfo_lock);
+}
+
+/**
  * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator
  * @bat_priv: the bat priv with all the soft interface information
  * @orig_node: orig node which is to be checked
@@ -795,6 +841,11 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
 
 			hlist_del_rcu(&neigh_node->list);
 			batadv_neigh_node_free_ref(neigh_node);
+		} else {
+			/* only necessary if not the whole neighbor is to be
+			 * deleted, but some interface has been removed.
+			 */
+			batadv_purge_neigh_ifinfo(bat_priv, neigh_node);
 		}
 	}
 
@@ -852,7 +903,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 {
 	struct batadv_neigh_node *best_neigh_node;
 	struct batadv_hard_iface *hard_iface;
-	bool changed;
+	bool changed_ifinfo, changed_neigh;
 
 	if (batadv_has_timed_out(orig_node->last_seen,
 				 2 * BATADV_PURGE_TIMEOUT)) {
@@ -862,10 +913,10 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 			   jiffies_to_msecs(orig_node->last_seen));
 		return true;
 	}
-	changed = batadv_purge_orig_ifinfo(bat_priv, orig_node);
-	changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node);
+	changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node);
+	changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node);
 
-	if (!changed)
+	if (!changed_ifinfo && !changed_neigh)
 		return false;
 
 	/* first for NULL ... */
@@ -1023,7 +1074,8 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
 	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface);
 
 out:
-	batadv_hardif_free_ref(hard_iface);
+	if (hard_iface)
+		batadv_hardif_free_ref(hard_iface);
 	return 0;
 }
 
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index adb3ea04adaa..d906016f3c6b 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -420,12 +420,18 @@ static int conn_send(struct l2cap_conn *conn,
 	return 0;
 }
 
-static void get_dest_bdaddr(struct in6_addr *ip6_daddr,
-			    bdaddr_t *addr, u8 *addr_type)
+static u8 get_addr_type_from_eui64(u8 byte)
 {
-	u8 *eui64;
+	/* Is universal(0) or local(1) bit,  */
+	if (byte & 0x02)
+		return ADDR_LE_DEV_RANDOM;
 
-	eui64 = ip6_daddr->s6_addr + 8;
+	return ADDR_LE_DEV_PUBLIC;
+}
+
+static void copy_to_bdaddr(struct in6_addr *ip6_daddr, bdaddr_t *addr)
+{
+	u8 *eui64 = ip6_daddr->s6_addr + 8;
 
 	addr->b[0] = eui64[7];
 	addr->b[1] = eui64[6];
@@ -433,16 +439,19 @@ static void get_dest_bdaddr(struct in6_addr *ip6_daddr,
 	addr->b[3] = eui64[2];
 	addr->b[4] = eui64[1];
 	addr->b[5] = eui64[0];
+}
 
-	addr->b[5] ^= 2;
+static void convert_dest_bdaddr(struct in6_addr *ip6_daddr,
+				bdaddr_t *addr, u8 *addr_type)
+{
+	copy_to_bdaddr(ip6_daddr, addr);
 
-	/* Set universal/local bit to 0 */
-	if (addr->b[5] & 1) {
-		addr->b[5] &= ~1;
-		*addr_type = ADDR_LE_DEV_PUBLIC;
-	} else {
-		*addr_type = ADDR_LE_DEV_RANDOM;
-	}
+	/* We need to toggle the U/L bit that we got from IPv6 address
+	 * so that we get the proper address and type of the BD address.
+	 */
+	addr->b[5] ^= 0x02;
+
+	*addr_type = get_addr_type_from_eui64(addr->b[5]);
 }
 
 static int header_create(struct sk_buff *skb, struct net_device *netdev,
@@ -473,9 +482,11 @@ static int header_create(struct sk_buff *skb, struct net_device *netdev,
 		/* Get destination BT device from skb.
 		 * If there is no such peer then discard the packet.
 		 */
-		get_dest_bdaddr(&hdr->daddr, &addr, &addr_type);
+		convert_dest_bdaddr(&hdr->daddr, &addr, &addr_type);
 
-		BT_DBG("dest addr %pMR type %d", &addr, addr_type);
+		BT_DBG("dest addr %pMR type %s IP %pI6c", &addr,
+		       addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM",
+		       &hdr->daddr);
 
 		read_lock_irqsave(&devices_lock, flags);
 		peer = peer_lookup_ba(dev, &addr, addr_type);
@@ -556,7 +567,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	} else {
 		unsigned long flags;
 
-		get_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type);
+		convert_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type);
 		eui64_addr = lowpan_cb(skb)->addr.s6_addr + 8;
 		dev = lowpan_dev(netdev);
 
@@ -564,8 +575,10 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 		peer = peer_lookup_ba(dev, &addr, addr_type);
 		read_unlock_irqrestore(&devices_lock, flags);
 
-		BT_DBG("xmit from %s to %pMR (%pI6c) peer %p", netdev->name,
-		       &addr, &lowpan_cb(skb)->addr, peer);
+		BT_DBG("xmit %s to %pMR type %s IP %pI6c peer %p",
+		       netdev->name, &addr,
+		       addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM",
+		       &lowpan_cb(skb)->addr, peer);
 
 		if (peer && peer->conn)
 			err = send_pkt(peer->conn, netdev->dev_addr,
@@ -620,13 +633,13 @@ static void set_addr(u8 *eui, u8 *addr, u8 addr_type)
 	eui[6] = addr[1];
 	eui[7] = addr[0];
 
-	eui[0] ^= 2;
-
-	/* Universal/local bit set, RFC 4291 */
+	/* Universal/local bit set, BT 6lowpan draft ch. 3.2.1 */
 	if (addr_type == ADDR_LE_DEV_PUBLIC)
-		eui[0] |= 1;
+		eui[0] &= ~0x02;
 	else
-		eui[0] &= ~1;
+		eui[0] |= 0x02;
+
+	BT_DBG("type %d addr %*phC", addr_type, 8, eui);
 }
 
 static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr,
@@ -634,7 +647,6 @@ static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr,
 {
 	netdev->addr_assign_type = NET_ADDR_PERM;
 	set_addr(netdev->dev_addr, addr->b, addr_type);
-	netdev->dev_addr[0] ^= 2;
 }
 
 static void ifup(struct net_device *netdev)
@@ -684,13 +696,6 @@ static int add_peer_conn(struct l2cap_conn *conn, struct lowpan_dev *dev)
 
 	memcpy(&peer->eui64_addr, (u8 *)&peer->peer_addr.s6_addr + 8,
 	       EUI64_ADDR_LEN);
-	peer->eui64_addr[0] ^= 2; /* second bit-flip (Universe/Local)
-				   * is done according RFC2464
-				   */
-
-	raw_dump_inline(__func__, "peer IPv6 address",
-			(unsigned char *)&peer->peer_addr, 16);
-	raw_dump_inline(__func__, "peer EUI64 address", peer->eui64_addr, 8);
 
 	write_lock_irqsave(&devices_lock, flags);
 	INIT_LIST_HEAD(&peer->list);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index ba5366c320da..1c6e950b9ae7 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -752,14 +752,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 	if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
 		struct hci_cp_auth_requested cp;
 
-		/* encrypt must be pending if auth is also pending */
-		set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-
 		cp.handle = cpu_to_le16(conn->handle);
 		hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
 			     sizeof(cp), &cp);
-		if (conn->key_type != 0xff)
+
+		/* If we're already encrypted set the REAUTH_PEND flag,
+		 * otherwise set the ENCRYPT_PEND.
+		 */
+		if (conn->link_mode & HCI_LM_ENCRYPT)
 			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
+		else
+			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 	}
 
 	return 0;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 5f812455a450..2e8c5765e5ea 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -48,6 +48,10 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb)
 	smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */
 	wake_up_bit(&hdev->flags, HCI_INQUIRY);
 
+	hci_dev_lock(hdev);
+	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	hci_dev_unlock(hdev);
+
 	hci_conn_check_pending(hdev);
 }
 
@@ -3006,6 +3010,12 @@ static void hci_key_refresh_complete_evt(struct hci_dev *hdev,
 	if (!conn)
 		goto unlock;
 
+	/* For BR/EDR the necessary steps are taken through the
+	 * auth_complete event.
+	 */
+	if (conn->type != LE_LINK)
+		goto unlock;
+
 	if (!ev->status)
 		conn->sec_level = conn->pending_sec_level;
 
@@ -3171,8 +3181,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 
 		/* If we're not the initiators request authorization to
 		 * proceed from user space (mgmt_user_confirm with
-		 * confirm_hint set to 1). */
-		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
+		 * confirm_hint set to 1). The exception is if neither
+		 * side had MITM in which case we do auto-accept.
+		 */
+		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) &&
+		    (loc_mitm || rem_mitm)) {
 			BT_DBG("Confirming auto-accept as acceptor");
 			confirm_hint = 1;
 			goto confirm;
@@ -3593,7 +3606,13 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp);
 
-	if (ltk->type & HCI_SMP_STK) {
+	/* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a
+	 * temporary key used to encrypt a connection following
+	 * pairing. It is used during the Encrypted Session Setup to
+	 * distribute the keys. Later, security can be re-established
+	 * using a distributed LTK.
+	 */
+	if (ltk->type == HCI_SMP_STK_SLAVE) {
 		list_del(&ltk->list);
 		kfree(ltk);
 	}
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index b0ad2c752d73..0007c9e9853a 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2608,12 +2608,8 @@ static int l2cap_segment_le_sdu(struct l2cap_chan *chan,
 
 	BT_DBG("chan %p, msg %p, len %zu", chan, msg, len);
 
-	pdu_len = chan->conn->mtu - L2CAP_HDR_SIZE;
-
-	pdu_len = min_t(size_t, pdu_len, chan->remote_mps);
-
 	sdu_len = len;
-	pdu_len -= L2CAP_SDULEN_SIZE;
+	pdu_len = chan->remote_mps - L2CAP_SDULEN_SIZE;
 
 	while (len > 0) {
 		if (len <= pdu_len)
@@ -7471,9 +7467,9 @@ int __init l2cap_init(void)
 	l2cap_debugfs = debugfs_create_file("l2cap", 0444, bt_debugfs,
 					    NULL, &l2cap_debugfs_fops);
 
-	debugfs_create_u16("l2cap_le_max_credits", 0466, bt_debugfs,
+	debugfs_create_u16("l2cap_le_max_credits", 0644, bt_debugfs,
 			   &le_max_credits);
-	debugfs_create_u16("l2cap_le_default_mps", 0466, bt_debugfs,
+	debugfs_create_u16("l2cap_le_default_mps", 0644, bt_debugfs,
 			   &le_default_mps);
 
 	bt_6lowpan_init();
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index d58f76bcebd1..06a7a769737f 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -778,11 +778,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 
 		/*change security for LE channels */
 		if (chan->scid == L2CAP_CID_ATT) {
-			if (!conn->hcon->out) {
-				err = -EINVAL;
-				break;
-			}
-
 			if (smp_conn_security(conn->hcon, sec.level))
 				break;
 			sk->sk_state = BT_CONFIG;
@@ -1117,7 +1112,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how)
 		l2cap_chan_close(chan, 0);
 		lock_sock(sk);
 
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+		    !(current->flags & PF_EXITING))
 			err = bt_sock_wait_state(sk, BT_CLOSED,
 						 sk->sk_lingertime);
 	}
@@ -1181,13 +1177,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
 	/* Check for backlog size */
 	if (sk_acceptq_is_full(parent)) {
 		BT_DBG("backlog full %d", parent->sk_ack_backlog);
+		release_sock(parent);
 		return NULL;
 	}
 
 	sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
 			      GFP_ATOMIC);
-	if (!sk)
+	if (!sk) {
+		release_sock(parent);
 		return NULL;
+        }
 
 	bt_sock_reclassify_lock(sk, BTPROTO_L2CAP);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index a03ca3ca91bf..f1ac2a754acc 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2826,8 +2826,13 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 	}
 
 	if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) {
-		/* Continue with pairing via SMP */
+		/* Continue with pairing via SMP. The hdev lock must be
+		 * released as SMP may try to recquire it for crypto
+		 * purposes.
+		 */
+		hci_dev_unlock(hdev);
 		err = smp_user_confirm_reply(conn, mgmt_op, passkey);
+		hci_dev_lock(hdev);
 
 		if (!err)
 			err = cmd_complete(sk, hdev->id, mgmt_op,
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index facd8a79c038..b08865111024 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -1859,10 +1859,13 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s)
 	/* Get data directly from socket receive queue without copying it. */
 	while ((skb = skb_dequeue(&sk->sk_receive_queue))) {
 		skb_orphan(skb);
-		if (!skb_linearize(skb))
+		if (!skb_linearize(skb)) {
 			s = rfcomm_recv_frame(s, skb);
-		else
+			if (!s)
+				break;
+		} else {
 			kfree_skb(skb);
+		}
 	}
 
 	if (s && (sk->sk_state == BT_CLOSED))
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 3c2d3e4aa2f5..a0050de6f1f1 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -898,7 +898,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how)
 		sk->sk_shutdown = SHUTDOWN_MASK;
 		__rfcomm_sock_close(sk);
 
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+		    !(current->flags & PF_EXITING))
 			err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
 	}
 	release_sock(sk);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 24fa3964b3c8..316dd4e0af39 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -909,7 +909,8 @@ static int sco_sock_shutdown(struct socket *sock, int how)
 		sco_sock_clear_timer(sk);
 		__sco_sock_close(sk);
 
-		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+		if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+		    !(current->flags & PF_EXITING))
 			err = bt_sock_wait_state(sk, BT_CLOSED,
 						 sk->sk_lingertime);
 	}
@@ -929,7 +930,8 @@ static int sco_sock_release(struct socket *sock)
 
 	sco_sock_close(sk);
 
-	if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) {
+	if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+	    !(current->flags & PF_EXITING)) {
 		lock_sock(sk);
 		err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
 		release_sock(sk);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index d0cca3c65f01..04d6348fd530 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -73,7 +73,7 @@ int br_handle_frame_finish(struct sk_buff *skb)
 		goto drop;
 
 	if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
-		goto drop;
+		goto out;
 
 	/* insert into forwarding database after filtering to avoid spoofing */
 	br = p->br;
@@ -147,8 +147,8 @@ static int br_handle_local_finish(struct sk_buff *skb)
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	u16 vid = 0;
 
-	br_vlan_get_tag(skb, &vid);
-	if (p->flags & BR_LEARNING)
+	/* check if vlan is allowed, to avoid spoofing */
+	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
 		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
 	return 0;	 /* process further */
 }
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e74b6d530cb6..e8844d975b32 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -445,6 +445,20 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_bridge *br = netdev_priv(dev);
+
+	if (tb[IFLA_ADDRESS]) {
+		spin_lock_bh(&br->lock);
+		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+		spin_unlock_bh(&br->lock);
+	}
+
+	return register_netdevice(dev);
+}
+
 static size_t br_get_link_af_size(const struct net_device *dev)
 {
 	struct net_port_vlans *pv;
@@ -473,6 +487,7 @@ struct rtnl_link_ops br_link_ops __read_mostly = {
 	.priv_size	= sizeof(struct net_bridge),
 	.setup		= br_dev_setup,
 	.validate	= br_validate,
+	.newlink	= br_dev_newlink,
 	.dellink	= br_dev_delete,
 };
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 3ba11bc99b65..4acfc3eef56a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -302,6 +302,9 @@ struct br_input_skb_cb {
 	int igmp;
 	int mrouters_only;
 #endif
+#ifdef CONFIG_BRIDGE_VLAN_FILTERING
+	bool vlan_filtered;
+#endif
 };
 
 #define BR_INPUT_SKB_CB(__skb)	((struct br_input_skb_cb *)(__skb)->cb)
@@ -581,6 +584,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 			struct sk_buff *skb, u16 *vid);
 bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
 		       const struct sk_buff *skb);
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_port_vlans *v,
 			       struct sk_buff *skb);
@@ -648,6 +652,12 @@ static inline bool br_allowed_egress(struct net_bridge *br,
 	return true;
 }
 
+static inline bool br_should_learn(struct net_bridge_port *p,
+				   struct sk_buff *skb, u16 *vid)
+{
+	return true;
+}
+
 static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
 					     const struct net_port_vlans *v,
 					     struct sk_buff *skb)
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index f23c74b3a953..e1bd2539f9dc 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -125,7 +125,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
 {
 	u16 vid;
 
-	if (!br->vlan_enabled)
+	/* If this packet was not filtered at input, let it pass */
+	if (!BR_INPUT_SKB_CB(skb)->vlan_filtered)
 		goto out;
 
 	/* Vlan filter table must be configured at this point.  The
@@ -163,14 +164,18 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	/* If VLAN filtering is disabled on the bridge, all packets are
 	 * permitted.
 	 */
-	if (!br->vlan_enabled)
+	if (!br->vlan_enabled) {
+		BR_INPUT_SKB_CB(skb)->vlan_filtered = false;
 		return true;
+	}
 
 	/* If there are no vlan in the permitted list, all packets are
 	 * rejected.
 	 */
 	if (!v)
-		return false;
+		goto drop;
+
+	BR_INPUT_SKB_CB(skb)->vlan_filtered = true;
 
 	/* If vlan tx offload is disabled on bridge device and frame was
 	 * sent from vlan device on the bridge device, it does not have
@@ -179,7 +184,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	if (unlikely(!vlan_tx_tag_present(skb) &&
 		     (skb->protocol == htons(ETH_P_8021Q) ||
 		      skb->protocol == htons(ETH_P_8021AD)))) {
-		skb = vlan_untag(skb);
+		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
 			return false;
 	}
@@ -193,7 +198,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		 * vlan untagged or priority-tagged traffic belongs to.
 		 */
 		if (pvid == VLAN_N_VID)
-			return false;
+			goto drop;
 
 		/* PVID is set on this port.  Any untagged or priority-tagged
 		 * ingress frame is considered to belong to this vlan.
@@ -216,7 +221,8 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	/* Frame had a valid vlan tag.  See if vlan is allowed */
 	if (test_bit(*vid, v->vlan_bitmap))
 		return true;
-
+drop:
+	kfree_skb(skb);
 	return false;
 }
 
@@ -227,7 +233,8 @@ bool br_allowed_egress(struct net_bridge *br,
 {
 	u16 vid;
 
-	if (!br->vlan_enabled)
+	/* If this packet was not filtered at input, let it pass */
+	if (!BR_INPUT_SKB_CB(skb)->vlan_filtered)
 		return true;
 
 	if (!v)
@@ -240,6 +247,35 @@ bool br_allowed_egress(struct net_bridge *br,
 	return false;
 }
 
+/* Called under RCU */
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
+{
+	struct net_bridge *br = p->br;
+	struct net_port_vlans *v;
+
+	/* If filtering was disabled at input, let it pass. */
+	if (!br->vlan_enabled)
+		return true;
+
+	v = rcu_dereference(p->vlan_info);
+	if (!v)
+		return false;
+
+	br_vlan_get_tag(skb, vid);
+	if (!*vid) {
+		*vid = br_get_pvid(v);
+		if (*vid == VLAN_N_VID)
+			return false;
+
+		return true;
+	}
+
+	if (test_bit(*vid, v->vlan_bitmap))
+		return true;
+
+	return false;
+}
+
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
  */
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 0e474b13463b..1059ed3bc255 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1044,10 +1044,9 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
 	if (repl->num_counters &&
 	   copy_to_user(repl->counters, counterstmp,
 	   repl->num_counters * sizeof(struct ebt_counter))) {
-		ret = -EFAULT;
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("ebtables: counters copy to user failed while replacing table\n");
 	}
-	else
-		ret = 0;
 
 	/* decrease module count and free resources */
 	EBT_ENTRY_ITERATE(table->entries, table->entries_size,
diff --git a/net/can/gw.c b/net/can/gw.c
index ac31891967da..050a2110d43f 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -804,7 +804,7 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh)
 	u8 limhops = 0;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))
@@ -893,7 +893,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh)
 	u8 limhops = 0;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 96238ba95f2b..de6662b14e1f 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -13,8 +13,6 @@
 #include "auth_x.h"
 #include "auth_x_protocol.h"
 
-#define TEMP_TICKET_BUF_LEN	256
-
 static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed);
 
 static int ceph_x_is_authenticated(struct ceph_auth_client *ac)
@@ -64,7 +62,7 @@ static int ceph_x_encrypt(struct ceph_crypto_key *secret,
 }
 
 static int ceph_x_decrypt(struct ceph_crypto_key *secret,
-			  void **p, void *end, void *obuf, size_t olen)
+			  void **p, void *end, void **obuf, size_t olen)
 {
 	struct ceph_x_encrypt_header head;
 	size_t head_len = sizeof(head);
@@ -75,8 +73,14 @@ static int ceph_x_decrypt(struct ceph_crypto_key *secret,
 		return -EINVAL;
 
 	dout("ceph_x_decrypt len %d\n", len);
-	ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen,
-			    *p, len);
+	if (*obuf == NULL) {
+		*obuf = kmalloc(len, GFP_NOFS);
+		if (!*obuf)
+			return -ENOMEM;
+		olen = len;
+	}
+
+	ret = ceph_decrypt2(secret, &head, &head_len, *obuf, &olen, *p, len);
 	if (ret)
 		return ret;
 	if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC)
@@ -129,139 +133,120 @@ static void remove_ticket_handler(struct ceph_auth_client *ac,
 	kfree(th);
 }
 
-static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
-				    struct ceph_crypto_key *secret,
-				    void *buf, void *end)
+static int process_one_ticket(struct ceph_auth_client *ac,
+			      struct ceph_crypto_key *secret,
+			      void **p, void *end)
 {
 	struct ceph_x_info *xi = ac->private;
-	int num;
-	void *p = buf;
+	int type;
+	u8 tkt_struct_v, blob_struct_v;
+	struct ceph_x_ticket_handler *th;
+	void *dbuf = NULL;
+	void *dp, *dend;
+	int dlen;
+	char is_enc;
+	struct timespec validity;
+	struct ceph_crypto_key old_key;
+	void *ticket_buf = NULL;
+	void *tp, *tpend;
+	struct ceph_timespec new_validity;
+	struct ceph_crypto_key new_session_key;
+	struct ceph_buffer *new_ticket_blob;
+	unsigned long new_expires, new_renew_after;
+	u64 new_secret_id;
 	int ret;
-	char *dbuf;
-	char *ticket_buf;
-	u8 reply_struct_v;
 
-	dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
-	if (!dbuf)
-		return -ENOMEM;
+	ceph_decode_need(p, end, sizeof(u32) + 1, bad);
 
-	ret = -ENOMEM;
-	ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
-	if (!ticket_buf)
-		goto out_dbuf;
+	type = ceph_decode_32(p);
+	dout(" ticket type %d %s\n", type, ceph_entity_type_name(type));
 
-	ceph_decode_need(&p, end, 1 + sizeof(u32), bad);
-	reply_struct_v = ceph_decode_8(&p);
-	if (reply_struct_v != 1)
+	tkt_struct_v = ceph_decode_8(p);
+	if (tkt_struct_v != 1)
 		goto bad;
-	num = ceph_decode_32(&p);
-	dout("%d tickets\n", num);
-	while (num--) {
-		int type;
-		u8 tkt_struct_v, blob_struct_v;
-		struct ceph_x_ticket_handler *th;
-		void *dp, *dend;
-		int dlen;
-		char is_enc;
-		struct timespec validity;
-		struct ceph_crypto_key old_key;
-		void *tp, *tpend;
-		struct ceph_timespec new_validity;
-		struct ceph_crypto_key new_session_key;
-		struct ceph_buffer *new_ticket_blob;
-		unsigned long new_expires, new_renew_after;
-		u64 new_secret_id;
-
-		ceph_decode_need(&p, end, sizeof(u32) + 1, bad);
-
-		type = ceph_decode_32(&p);
-		dout(" ticket type %d %s\n", type, ceph_entity_type_name(type));
-
-		tkt_struct_v = ceph_decode_8(&p);
-		if (tkt_struct_v != 1)
-			goto bad;
-
-		th = get_ticket_handler(ac, type);
-		if (IS_ERR(th)) {
-			ret = PTR_ERR(th);
-			goto out;
-		}
 
-		/* blob for me */
-		dlen = ceph_x_decrypt(secret, &p, end, dbuf,
-				      TEMP_TICKET_BUF_LEN);
-		if (dlen <= 0) {
-			ret = dlen;
-			goto out;
-		}
-		dout(" decrypted %d bytes\n", dlen);
-		dend = dbuf + dlen;
-		dp = dbuf;
+	th = get_ticket_handler(ac, type);
+	if (IS_ERR(th)) {
+		ret = PTR_ERR(th);
+		goto out;
+	}
 
-		tkt_struct_v = ceph_decode_8(&dp);
-		if (tkt_struct_v != 1)
-			goto bad;
+	/* blob for me */
+	dlen = ceph_x_decrypt(secret, p, end, &dbuf, 0);
+	if (dlen <= 0) {
+		ret = dlen;
+		goto out;
+	}
+	dout(" decrypted %d bytes\n", dlen);
+	dp = dbuf;
+	dend = dp + dlen;
 
-		memcpy(&old_key, &th->session_key, sizeof(old_key));
-		ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
-		if (ret)
-			goto out;
+	tkt_struct_v = ceph_decode_8(&dp);
+	if (tkt_struct_v != 1)
+		goto bad;
 
-		ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
-		ceph_decode_timespec(&validity, &new_validity);
-		new_expires = get_seconds() + validity.tv_sec;
-		new_renew_after = new_expires - (validity.tv_sec / 4);
-		dout(" expires=%lu renew_after=%lu\n", new_expires,
-		     new_renew_after);
+	memcpy(&old_key, &th->session_key, sizeof(old_key));
+	ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
+	if (ret)
+		goto out;
 
-		/* ticket blob for service */
-		ceph_decode_8_safe(&p, end, is_enc, bad);
-		tp = ticket_buf;
-		if (is_enc) {
-			/* encrypted */
-			dout(" encrypted ticket\n");
-			dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf,
-					      TEMP_TICKET_BUF_LEN);
-			if (dlen < 0) {
-				ret = dlen;
-				goto out;
-			}
-			dlen = ceph_decode_32(&tp);
-		} else {
-			/* unencrypted */
-			ceph_decode_32_safe(&p, end, dlen, bad);
-			ceph_decode_need(&p, end, dlen, bad);
-			ceph_decode_copy(&p, ticket_buf, dlen);
+	ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
+	ceph_decode_timespec(&validity, &new_validity);
+	new_expires = get_seconds() + validity.tv_sec;
+	new_renew_after = new_expires - (validity.tv_sec / 4);
+	dout(" expires=%lu renew_after=%lu\n", new_expires,
+	     new_renew_after);
+
+	/* ticket blob for service */
+	ceph_decode_8_safe(p, end, is_enc, bad);
+	if (is_enc) {
+		/* encrypted */
+		dout(" encrypted ticket\n");
+		dlen = ceph_x_decrypt(&old_key, p, end, &ticket_buf, 0);
+		if (dlen < 0) {
+			ret = dlen;
+			goto out;
 		}
-		tpend = tp + dlen;
-		dout(" ticket blob is %d bytes\n", dlen);
-		ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad);
-		blob_struct_v = ceph_decode_8(&tp);
-		new_secret_id = ceph_decode_64(&tp);
-		ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend);
-		if (ret)
+		tp = ticket_buf;
+		dlen = ceph_decode_32(&tp);
+	} else {
+		/* unencrypted */
+		ceph_decode_32_safe(p, end, dlen, bad);
+		ticket_buf = kmalloc(dlen, GFP_NOFS);
+		if (!ticket_buf) {
+			ret = -ENOMEM;
 			goto out;
-
-		/* all is well, update our ticket */
-		ceph_crypto_key_destroy(&th->session_key);
-		if (th->ticket_blob)
-			ceph_buffer_put(th->ticket_blob);
-		th->session_key = new_session_key;
-		th->ticket_blob = new_ticket_blob;
-		th->validity = new_validity;
-		th->secret_id = new_secret_id;
-		th->expires = new_expires;
-		th->renew_after = new_renew_after;
-		dout(" got ticket service %d (%s) secret_id %lld len %d\n",
-		     type, ceph_entity_type_name(type), th->secret_id,
-		     (int)th->ticket_blob->vec.iov_len);
-		xi->have_keys |= th->service;
+		}
+		tp = ticket_buf;
+		ceph_decode_need(p, end, dlen, bad);
+		ceph_decode_copy(p, ticket_buf, dlen);
 	}
+	tpend = tp + dlen;
+	dout(" ticket blob is %d bytes\n", dlen);
+	ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad);
+	blob_struct_v = ceph_decode_8(&tp);
+	new_secret_id = ceph_decode_64(&tp);
+	ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend);
+	if (ret)
+		goto out;
+
+	/* all is well, update our ticket */
+	ceph_crypto_key_destroy(&th->session_key);
+	if (th->ticket_blob)
+		ceph_buffer_put(th->ticket_blob);
+	th->session_key = new_session_key;
+	th->ticket_blob = new_ticket_blob;
+	th->validity = new_validity;
+	th->secret_id = new_secret_id;
+	th->expires = new_expires;
+	th->renew_after = new_renew_after;
+	dout(" got ticket service %d (%s) secret_id %lld len %d\n",
+	     type, ceph_entity_type_name(type), th->secret_id,
+	     (int)th->ticket_blob->vec.iov_len);
+	xi->have_keys |= th->service;
 
-	ret = 0;
 out:
 	kfree(ticket_buf);
-out_dbuf:
 	kfree(dbuf);
 	return ret;
 
@@ -270,6 +255,34 @@ bad:
 	goto out;
 }
 
+static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
+				    struct ceph_crypto_key *secret,
+				    void *buf, void *end)
+{
+	void *p = buf;
+	u8 reply_struct_v;
+	u32 num;
+	int ret;
+
+	ceph_decode_8_safe(&p, end, reply_struct_v, bad);
+	if (reply_struct_v != 1)
+		return -EINVAL;
+
+	ceph_decode_32_safe(&p, end, num, bad);
+	dout("%d tickets\n", num);
+
+	while (num--) {
+		ret = process_one_ticket(ac, secret, &p, end);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+
+bad:
+	return -EINVAL;
+}
+
 static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 				   struct ceph_x_ticket_handler *th,
 				   struct ceph_x_authorizer *au)
@@ -583,13 +596,14 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
 	struct ceph_x_ticket_handler *th;
 	int ret = 0;
 	struct ceph_x_authorize_reply reply;
+	void *preply = &reply;
 	void *p = au->reply_buf;
 	void *end = p + sizeof(au->reply_buf);
 
 	th = get_ticket_handler(ac, au->service);
 	if (IS_ERR(th))
 		return PTR_ERR(th);
-	ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply));
+	ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply));
 	if (ret < 0)
 		return ret;
 	if (ret != sizeof(reply))
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index b703790b4e44..074bb2a5e675 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -292,8 +292,8 @@ static int is_out(const struct crush_map *map,
  * @outpos: our position in that vector
  * @tries: number of attempts to make
  * @recurse_tries: number of attempts to have recursive chooseleaf make
- * @local_tries: localized retries
- * @local_fallback_tries: localized fallback retries
+ * @local_retries: localized retries
+ * @local_fallback_retries: localized fallback retries
  * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose)
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
  */
@@ -304,8 +304,8 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       int *out, int outpos,
 			       unsigned int tries,
 			       unsigned int recurse_tries,
-			       unsigned int local_tries,
-			       unsigned int local_fallback_tries,
+			       unsigned int local_retries,
+			       unsigned int local_fallback_retries,
 			       int recurse_to_leaf,
 			       int *out2)
 {
@@ -344,9 +344,9 @@ static int crush_choose_firstn(const struct crush_map *map,
 					reject = 1;
 					goto reject;
 				}
-				if (local_fallback_tries > 0 &&
+				if (local_fallback_retries > 0 &&
 				    flocal >= (in->size>>1) &&
-				    flocal > local_fallback_tries)
+				    flocal > local_fallback_retries)
 					item = bucket_perm_choose(in, x, r);
 				else
 					item = crush_bucket_choose(in, x, r);
@@ -393,8 +393,8 @@ static int crush_choose_firstn(const struct crush_map *map,
 							 x, outpos+1, 0,
 							 out2, outpos,
 							 recurse_tries, 0,
-							 local_tries,
-							 local_fallback_tries,
+							 local_retries,
+							 local_fallback_retries,
 							 0,
 							 NULL) <= outpos)
 							/* didn't get leaf */
@@ -420,14 +420,14 @@ reject:
 					ftotal++;
 					flocal++;
 
-					if (collide && flocal <= local_tries)
+					if (collide && flocal <= local_retries)
 						/* retry locally a few times */
 						retry_bucket = 1;
-					else if (local_fallback_tries > 0 &&
-						 flocal <= in->size + local_fallback_tries)
+					else if (local_fallback_retries > 0 &&
+						 flocal <= in->size + local_fallback_retries)
 						/* exhaustive bucket search */
 						retry_bucket = 1;
-					else if (ftotal <= tries)
+					else if (ftotal < tries)
 						/* then retry descent */
 						retry_descent = 1;
 					else
@@ -640,10 +640,18 @@ int crush_do_rule(const struct crush_map *map,
 	__u32 step;
 	int i, j;
 	int numrep;
-	int choose_tries = map->choose_total_tries;
-	int choose_local_tries = map->choose_local_tries;
-	int choose_local_fallback_tries = map->choose_local_fallback_tries;
+	/*
+	 * the original choose_total_tries value was off by one (it
+	 * counted "retries" and not "tries").  add one.
+	 */
+	int choose_tries = map->choose_total_tries + 1;
 	int choose_leaf_tries = 0;
+	/*
+	 * the local tries values were counted as "retries", though,
+	 * and need no adjustment
+	 */
+	int choose_local_retries = map->choose_local_tries;
+	int choose_local_fallback_retries = map->choose_local_fallback_tries;
 
 	if ((__u32)ruleno >= map->max_rules) {
 		dprintk(" bad ruleno %d\n", ruleno);
@@ -677,12 +685,12 @@ int crush_do_rule(const struct crush_map *map,
 
 		case CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES:
 			if (curstep->arg1 > 0)
-				choose_local_tries = curstep->arg1;
+				choose_local_retries = curstep->arg1;
 			break;
 
 		case CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES:
 			if (curstep->arg1 > 0)
-				choose_local_fallback_tries = curstep->arg1;
+				choose_local_fallback_retries = curstep->arg1;
 			break;
 
 		case CRUSH_RULE_CHOOSELEAF_FIRSTN:
@@ -734,8 +742,8 @@ int crush_do_rule(const struct crush_map *map,
 						o+osize, j,
 						choose_tries,
 						recurse_tries,
-						choose_local_tries,
-						choose_local_fallback_tries,
+						choose_local_retries,
+						choose_local_fallback_retries,
 						recurse_to_leaf,
 						c+osize);
 				} else {
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 6e7a236525b6..06f19b9e159a 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -89,11 +89,82 @@ static struct crypto_blkcipher *ceph_crypto_alloc_cipher(void)
 
 static const u8 *aes_iv = (u8 *)CEPH_AES_IV;
 
+/*
+ * Should be used for buffers allocated with ceph_kvmalloc().
+ * Currently these are encrypt out-buffer (ceph_buffer) and decrypt
+ * in-buffer (msg front).
+ *
+ * Dispose of @sgt with teardown_sgtable().
+ *
+ * @prealloc_sg is to avoid memory allocation inside sg_alloc_table()
+ * in cases where a single sg is sufficient.  No attempt to reduce the
+ * number of sgs by squeezing physically contiguous pages together is
+ * made though, for simplicity.
+ */
+static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg,
+			 const void *buf, unsigned int buf_len)
+{
+	struct scatterlist *sg;
+	const bool is_vmalloc = is_vmalloc_addr(buf);
+	unsigned int off = offset_in_page(buf);
+	unsigned int chunk_cnt = 1;
+	unsigned int chunk_len = PAGE_ALIGN(off + buf_len);
+	int i;
+	int ret;
+
+	if (buf_len == 0) {
+		memset(sgt, 0, sizeof(*sgt));
+		return -EINVAL;
+	}
+
+	if (is_vmalloc) {
+		chunk_cnt = chunk_len >> PAGE_SHIFT;
+		chunk_len = PAGE_SIZE;
+	}
+
+	if (chunk_cnt > 1) {
+		ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS);
+		if (ret)
+			return ret;
+	} else {
+		WARN_ON(chunk_cnt != 1);
+		sg_init_table(prealloc_sg, 1);
+		sgt->sgl = prealloc_sg;
+		sgt->nents = sgt->orig_nents = 1;
+	}
+
+	for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) {
+		struct page *page;
+		unsigned int len = min(chunk_len - off, buf_len);
+
+		if (is_vmalloc)
+			page = vmalloc_to_page(buf);
+		else
+			page = virt_to_page(buf);
+
+		sg_set_page(sg, page, len, off);
+
+		off = 0;
+		buf += len;
+		buf_len -= len;
+	}
+	WARN_ON(buf_len != 0);
+
+	return 0;
+}
+
+static void teardown_sgtable(struct sg_table *sgt)
+{
+	if (sgt->orig_nents > 1)
+		sg_free_table(sgt);
+}
+
 static int ceph_aes_encrypt(const void *key, int key_len,
 			    void *dst, size_t *dst_len,
 			    const void *src, size_t src_len)
 {
-	struct scatterlist sg_in[2], sg_out[1];
+	struct scatterlist sg_in[2], prealloc_sg;
+	struct sg_table sg_out;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
 	int ret;
@@ -109,16 +180,18 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 
 	*dst_len = src_len + zero_padding;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	sg_init_table(sg_in, 2);
 	sg_set_buf(&sg_in[0], src, src_len);
 	sg_set_buf(&sg_in[1], pad, zero_padding);
-	sg_init_table(sg_out, 1);
-	sg_set_buf(sg_out, dst, *dst_len);
+	ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+	if (ret)
+		goto out_tfm;
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
+
 	/*
 	print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
 		       key, key_len, 1);
@@ -127,16 +200,22 @@ static int ceph_aes_encrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
 			pad, zero_padding, 1);
 	*/
-	ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+	ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
 				     src_len + zero_padding);
-	crypto_free_blkcipher(tfm);
-	if (ret < 0)
+	if (ret < 0) {
 		pr_err("ceph_aes_crypt failed %d\n", ret);
+		goto out_sg;
+	}
 	/*
 	print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
 		       dst, *dst_len, 1);
 	*/
-	return 0;
+
+out_sg:
+	teardown_sgtable(&sg_out);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
@@ -144,7 +223,8 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 			     const void *src1, size_t src1_len,
 			     const void *src2, size_t src2_len)
 {
-	struct scatterlist sg_in[3], sg_out[1];
+	struct scatterlist sg_in[3], prealloc_sg;
+	struct sg_table sg_out;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
 	int ret;
@@ -160,17 +240,19 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 
 	*dst_len = src1_len + src2_len + zero_padding;
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	sg_init_table(sg_in, 3);
 	sg_set_buf(&sg_in[0], src1, src1_len);
 	sg_set_buf(&sg_in[1], src2, src2_len);
 	sg_set_buf(&sg_in[2], pad, zero_padding);
-	sg_init_table(sg_out, 1);
-	sg_set_buf(sg_out, dst, *dst_len);
+	ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+	if (ret)
+		goto out_tfm;
+
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
+
 	/*
 	print_hex_dump(KERN_ERR, "enc  key: ", DUMP_PREFIX_NONE, 16, 1,
 		       key, key_len, 1);
@@ -181,23 +263,30 @@ static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
 	print_hex_dump(KERN_ERR, "enc  pad: ", DUMP_PREFIX_NONE, 16, 1,
 			pad, zero_padding, 1);
 	*/
-	ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+	ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
 				     src1_len + src2_len + zero_padding);
-	crypto_free_blkcipher(tfm);
-	if (ret < 0)
+	if (ret < 0) {
 		pr_err("ceph_aes_crypt2 failed %d\n", ret);
+		goto out_sg;
+	}
 	/*
 	print_hex_dump(KERN_ERR, "enc  out: ", DUMP_PREFIX_NONE, 16, 1,
 		       dst, *dst_len, 1);
 	*/
-	return 0;
+
+out_sg:
+	teardown_sgtable(&sg_out);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 static int ceph_aes_decrypt(const void *key, int key_len,
 			    void *dst, size_t *dst_len,
 			    const void *src, size_t src_len)
 {
-	struct scatterlist sg_in[1], sg_out[2];
+	struct sg_table sg_in;
+	struct scatterlist sg_out[2], prealloc_sg;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm };
 	char pad[16];
@@ -209,16 +298,16 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
-	crypto_blkcipher_setkey((void *)tfm, key, key_len);
-	sg_init_table(sg_in, 1);
 	sg_init_table(sg_out, 2);
-	sg_set_buf(sg_in, src, src_len);
 	sg_set_buf(&sg_out[0], dst, *dst_len);
 	sg_set_buf(&sg_out[1], pad, sizeof(pad));
+	ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+	if (ret)
+		goto out_tfm;
 
+	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
 
 	/*
@@ -227,12 +316,10 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec  in: ", DUMP_PREFIX_NONE, 16, 1,
 		       src, src_len, 1);
 	*/
-
-	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
-	crypto_free_blkcipher(tfm);
+	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
 	if (ret < 0) {
 		pr_err("ceph_aes_decrypt failed %d\n", ret);
-		return ret;
+		goto out_sg;
 	}
 
 	if (src_len <= *dst_len)
@@ -250,7 +337,12 @@ static int ceph_aes_decrypt(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1,
 		       dst, *dst_len, 1);
 	*/
-	return 0;
+
+out_sg:
+	teardown_sgtable(&sg_in);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 static int ceph_aes_decrypt2(const void *key, int key_len,
@@ -258,7 +350,8 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 			     void *dst2, size_t *dst2_len,
 			     const void *src, size_t src_len)
 {
-	struct scatterlist sg_in[1], sg_out[3];
+	struct sg_table sg_in;
+	struct scatterlist sg_out[3], prealloc_sg;
 	struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
 	struct blkcipher_desc desc = { .tfm = tfm };
 	char pad[16];
@@ -270,17 +363,17 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
-	sg_init_table(sg_in, 1);
-	sg_set_buf(sg_in, src, src_len);
 	sg_init_table(sg_out, 3);
 	sg_set_buf(&sg_out[0], dst1, *dst1_len);
 	sg_set_buf(&sg_out[1], dst2, *dst2_len);
 	sg_set_buf(&sg_out[2], pad, sizeof(pad));
+	ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+	if (ret)
+		goto out_tfm;
 
 	crypto_blkcipher_setkey((void *)tfm, key, key_len);
 	iv = crypto_blkcipher_crt(tfm)->iv;
 	ivsize = crypto_blkcipher_ivsize(tfm);
-
 	memcpy(iv, aes_iv, ivsize);
 
 	/*
@@ -289,12 +382,10 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 	print_hex_dump(KERN_ERR, "dec   in: ", DUMP_PREFIX_NONE, 16, 1,
 		       src, src_len, 1);
 	*/
-
-	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
-	crypto_free_blkcipher(tfm);
+	ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
 	if (ret < 0) {
 		pr_err("ceph_aes_decrypt failed %d\n", ret);
-		return ret;
+		goto out_sg;
 	}
 
 	if (src_len <= *dst1_len)
@@ -324,7 +415,11 @@ static int ceph_aes_decrypt2(const void *key, int key_len,
 		       dst2, *dst2_len, 1);
 	*/
 
-	return 0;
+out_sg:
+	teardown_sgtable(&sg_in);
+out_tfm:
+	crypto_free_blkcipher(tfm);
+	return ret;
 }
 
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 30efc5c18622..2e87eecec8f6 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -291,7 +291,11 @@ int ceph_msgr_init(void)
 	if (ceph_msgr_slab_init())
 		return -ENOMEM;
 
-	ceph_msgr_wq = alloc_workqueue("ceph-msgr", 0, 0);
+	/*
+	 * The number of active work items is limited by the number of
+	 * connections, so leave @max_active at default.
+	 */
+	ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_MEM_RECLAIM, 0);
 	if (ceph_msgr_wq)
 		return 0;
 
@@ -557,7 +561,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
 		     int offset, size_t size, bool more)
 {
 	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
@@ -570,6 +574,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	return ret;
 }
 
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+		     int offset, size_t size, bool more)
+{
+	int ret;
+	struct kvec iov;
+
+	/* sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fallback to sendmsg if that's the case */
+	if (page_count(page) >= 1)
+		return __ceph_tcp_sendpage(sock, page, offset, size, more);
+
+	iov.iov_base = kmap(page) + offset;
+	iov.iov_len = size;
+	ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
+	kunmap(page);
+
+	return ret;
+}
 
 /*
  * Shutdown/close the socket for the given connection.
@@ -882,7 +904,7 @@ static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor,
 	BUG_ON(page_count > (int)USHRT_MAX);
 	cursor->page_count = (unsigned short)page_count;
 	BUG_ON(length > SIZE_MAX - cursor->page_offset);
-	cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE;
+	cursor->last_piece = cursor->page_offset + cursor->resid <= PAGE_SIZE;
 }
 
 static struct page *
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 2ac9ef35110b..dbcbf5a4707f 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1041,7 +1041,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	if (!m) {
 		pr_info("alloc_msg unknown type %d\n", type);
 		*skip = 1;
+	} else if (front_len > m->front_alloc_len) {
+		pr_warning("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n",
+			   front_len, m->front_alloc_len,
+			   (unsigned int)con->peer_name.type,
+			   le64_to_cpu(con->peer_name.num));
+		ceph_msg_put(m);
+		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
 	}
+
 	return m;
 }
 
diff --git a/net/compat.c b/net/compat.c
index f50161fb812e..cbc1a2a26587 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -85,7 +85,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 {
 	int tot_len;
 
-	if (kern_msg->msg_namelen) {
+	if (kern_msg->msg_name && kern_msg->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			int err = move_addr_to_kernel(kern_msg->msg_name,
 						      kern_msg->msg_namelen,
@@ -93,10 +93,11 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 			if (err < 0)
 				return err;
 		}
-		if (kern_msg->msg_name)
-			kern_msg->msg_name = kern_address;
-	} else
+		kern_msg->msg_name = kern_address;
+	} else {
 		kern_msg->msg_name = NULL;
+		kern_msg->msg_namelen = 0;
+	}
 
 	tot_len = iov_from_user_compat_to_kern(kern_iov,
 					  (struct compat_iovec __user *)kern_msg->msg_iov,
diff --git a/net/core/dev.c b/net/core/dev.c
index 45fa2f11f84d..3ed11a555834 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -148,6 +148,9 @@ struct list_head ptype_all __read_mostly;	/* Taps */
 static struct list_head offload_base __read_mostly;
 
 static int netif_rx_internal(struct sk_buff *skb);
+static int call_netdevice_notifiers_info(unsigned long val,
+					 struct net_device *dev,
+					 struct netdev_notifier_info *info);
 
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -1207,7 +1210,11 @@ EXPORT_SYMBOL(netdev_features_change);
 void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
-		call_netdevice_notifiers(NETDEV_CHANGE, dev);
+		struct netdev_notifier_change_info change_info;
+
+		change_info.flags_changed = 0;
+		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+					      &change_info.info);
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
 }
@@ -2289,7 +2296,7 @@ EXPORT_SYMBOL(skb_checksum_help);
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
 	__be16 type = skb->protocol;
-	int vlan_depth = ETH_HLEN;
+	int vlan_depth = skb->mac_len;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
 	if (type == htons(ETH_P_TEB)) {
@@ -3547,7 +3554,7 @@ another_round:
 
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
-		skb = vlan_untag(skb);
+		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
 			goto unlock;
 	}
@@ -3944,6 +3951,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	}
 	NAPI_GRO_CB(skb)->count = 1;
 	NAPI_GRO_CB(skb)->age = jiffies;
+	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
@@ -4050,6 +4058,9 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+	skb->encapsulation = 0;
+	skb_shinfo(skb)->gso_type = 0;
+	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 
 	napi->skb = skb;
 }
@@ -4605,6 +4616,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
 
 /**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ *                         list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+
+	return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
+/**
  * netdev_lower_get_first_private_rcu - Get the first ->private from the
  *				       lower neighbour list, RCU
  *				       variant
@@ -5054,6 +5091,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
+
+int dev_get_nest_level(struct net_device *dev,
+		       bool (*type_check)(struct net_device *dev))
+{
+	struct net_device *lower = NULL;
+	struct list_head *iter;
+	int max_nest = -1;
+	int nest;
+
+	ASSERT_RTNL();
+
+	netdev_for_each_lower_dev(dev, lower, iter) {
+		nest = dev_get_nest_level(lower, type_check);
+		if (max_nest < nest)
+			max_nest = nest;
+	}
+
+	if (type_check(dev))
+		max_nest++;
+
+	return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -5523,7 +5584,7 @@ static int dev_new_index(struct net *net)
 
 /* Delayed registration/unregisteration */
 static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
 {
@@ -6496,6 +6557,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue);
 /**
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -6505,6 +6569,7 @@ void unregister_netdevice_many(struct list_head *head)
 		rollback_registered_many(head);
 		list_for_each_entry(dev, head, unreg_list)
 			net_set_todo(dev);
+		list_del(head);
 	}
 }
 EXPORT_SYMBOL(unregister_netdevice_many);
@@ -6960,7 +7025,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 		}
 	}
 	unregister_netdevice_many(&dev_kill_list);
-	list_del(&dev_kill_list);
 	rtnl_unlock();
 }
 
diff --git a/net/core/dst.c b/net/core/dst.c
index ca4231ec7347..15b6792e6ebb 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -267,6 +267,15 @@ again:
 }
 EXPORT_SYMBOL(dst_destroy);
 
+static void dst_destroy_rcu(struct rcu_head *head)
+{
+	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+
+	dst = dst_destroy(dst);
+	if (dst)
+		__dst_free(dst);
+}
+
 void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
@@ -274,11 +283,8 @@ void dst_release(struct dst_entry *dst)
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
-			dst = dst_destroy(dst);
-			if (dst)
-				__dst_free(dst);
-		}
+		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
 EXPORT_SYMBOL(dst_release);
diff --git a/net/core/filter.c b/net/core/filter.c
index ad30d626a5bd..ebce437678fc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -355,6 +355,8 @@ load_b:
 
 			if (skb_is_nonlinear(skb))
 				return 0;
+			if (skb->len < sizeof(struct nlattr))
+				return 0;
 			if (A > skb->len - sizeof(struct nlattr))
 				return 0;
 
@@ -371,11 +373,13 @@ load_b:
 
 			if (skb_is_nonlinear(skb))
 				return 0;
+			if (skb->len < sizeof(struct nlattr))
+				return 0;
 			if (A > skb->len - sizeof(struct nlattr))
 				return 0;
 
 			nla = (struct nlattr *)&skb->data[A];
-			if (nla->nla_len > A - skb->len)
+			if (nla->nla_len > skb->len - A)
 				return 0;
 
 			nla = nla_find_nested(nla, X);
diff --git a/net/core/iovec.c b/net/core/iovec.c
index b61869429f4c..26dc0062652f 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 {
 	int size, ct, err;
 
-	if (m->msg_namelen) {
+	if (m->msg_name && m->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			void __user *namep;
 			namep = (void __user __force *) m->msg_name;
@@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 			if (err < 0)
 				return err;
 		}
-		if (m->msg_name)
-			m->msg_name = address;
+		m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
+		m->msg_namelen = 0;
 	}
 
 	size = m->msg_iovlen * sizeof(struct iovec);
@@ -107,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend);
 int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
 			int offset, int len)
 {
+	/* No data? Done! */
+	if (len == 0)
+		return 0;
+
 	/* Skip over the finished iovecs */
 	while (offset >= iov->iov_len) {
 		offset -= iov->iov_len;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e16129019c66..7d95f69635c6 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1247,8 +1247,8 @@ void __neigh_set_probe_once(struct neighbour *neigh)
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
-	neigh->nud_state = NUD_PROBE;
-	atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+	neigh->nud_state = NUD_INCOMPLETE;
+	atomic_set(&neigh->probes, neigh_max_probes(neigh));
 	neigh_add_timer(neigh,
 			jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 81d3a9a08453..7c8ffd974961 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -24,7 +24,7 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index df9e6b1a9759..723fa7da8025 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -788,7 +788,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 	}
 
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
-		skb = vlan_untag(skb);
+		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
 			goto out;
 	}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 120eecc0f5a4..46175866851e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
 }
 EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
 
+/* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace.
+ */
+static void rtnl_lock_unregistering_all(void)
+{
+	struct net *net;
+	bool unregistering;
+	DEFINE_WAIT(wait);
+
+	for (;;) {
+		prepare_to_wait(&netdev_unregistering_wq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		unregistering = false;
+		rtnl_lock();
+		for_each_net(net) {
+			if (net->dev_unreg_count > 0) {
+				unregistering = true;
+				break;
+			}
+		}
+		if (!unregistering)
+			break;
+		__rtnl_unlock();
+		schedule();
+	}
+	finish_wait(&netdev_unregistering_wq, &wait);
+}
+
 /**
  * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
  * @ops: struct rtnl_link_ops * to unregister
  */
 void rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
-	rtnl_lock();
+	/* Close the race with cleanup_net() */
+	mutex_lock(&net_mutex);
+	rtnl_lock_unregistering_all();
 	__rtnl_link_unregister(ops);
 	rtnl_unlock();
+	mutex_unlock(&net_mutex);
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 
@@ -768,13 +799,15 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 			(nla_total_size(sizeof(struct ifla_vf_mac)) +
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
 			 nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_spoofchk)));
+			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
+			 nla_total_size(sizeof(struct ifla_vf_link_state)));
 		return size;
 	} else
 		return 0;
 }
 
-static size_t rtnl_port_size(const struct net_device *dev)
+static size_t rtnl_port_size(const struct net_device *dev,
+			     u32 ext_filter_mask)
 {
 	size_t port_size = nla_total_size(4)		/* PORT_VF */
 		+ nla_total_size(PORT_PROFILE_MAX)	/* PORT_PROFILE */
@@ -790,7 +823,8 @@ static size_t rtnl_port_size(const struct net_device *dev)
 	size_t port_self_size = nla_total_size(sizeof(struct nlattr))
 		+ port_size;
 
-	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+	    !(ext_filter_mask & RTEXT_FILTER_VF))
 		return 0;
 	if (dev_num_vf(dev->dev.parent))
 		return port_self_size + vf_ports_size +
@@ -825,7 +859,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
-	       + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+	       + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
 	       + rtnl_link_get_size(dev) /* IFLA_LINKINFO */
 	       + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
 	       + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
@@ -887,11 +921,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
+static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
+			  u32 ext_filter_mask)
 {
 	int err;
 
-	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+	if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+	    !(ext_filter_mask & RTEXT_FILTER_VF))
 		return 0;
 
 	err = rtnl_port_self_fill(skb, dev);
@@ -1076,7 +1112,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		nla_nest_end(skb, vfinfo);
 	}
 
-	if (rtnl_port_fill(skb, dev))
+	if (rtnl_port_fill(skb, dev, ext_filter_mask))
 		goto nla_put_failure;
 
 	if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) {
@@ -1130,6 +1166,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct hlist_head *head;
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
+	int err;
+	int hdrlen;
 
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
@@ -1137,8 +1175,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	/* A hack to preserve kernel<->userspace interface.
+	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+	 * what iproute2 < v3.9.0 used.
+	 * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+	 * attribute, its netlink message is shorter than struct ifinfomsg.
+	 */
+	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1150,11 +1197,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		hlist_for_each_entry_rcu(dev, head, index_hlist) {
 			if (idx < s_idx)
 				goto cont;
-			if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
-					     NETLINK_CB(cb->skb).portid,
-					     cb->nlh->nlmsg_seq, 0,
-					     NLM_F_MULTI,
-					     ext_filter_mask) <= 0)
+			err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+					       NETLINK_CB(cb->skb).portid,
+					       cb->nlh->nlmsg_seq, 0,
+					       NLM_F_MULTI,
+					       ext_filter_mask);
+			/* If we ran out of room on the first message,
+			 * we're in trouble
+			 */
+			WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
+
+			if (err <= 0)
 				goto out;
 
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -1386,7 +1439,8 @@ static int do_set_master(struct net_device *dev, int ifindex)
 	return 0;
 }
 
-static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
+static int do_setlink(const struct sk_buff *skb,
+		      struct net_device *dev, struct ifinfomsg *ifm,
 		      struct nlattr **tb, char *ifname, int modified)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -1398,7 +1452,8 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
 			err = PTR_ERR(net);
 			goto errout;
 		}
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+		if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+			put_net(net);
 			err = -EPERM;
 			goto errout;
 		}
@@ -1652,7 +1707,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (err < 0)
 		goto errout;
 
-	err = do_setlink(dev, ifm, tb, ifname, 0);
+	err = do_setlink(skb, dev, ifm, tb, ifname, 0);
 errout:
 	return err;
 }
@@ -1692,7 +1747,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ops->dellink(dev, &list_kill);
 	unregister_netdevice_many(&list_kill);
-	list_del(&list_kill);
 	return 0;
 }
 
@@ -1769,7 +1823,8 @@ err:
 }
 EXPORT_SYMBOL(rtnl_create_link);
 
-static int rtnl_group_changelink(struct net *net, int group,
+static int rtnl_group_changelink(const struct sk_buff *skb,
+		struct net *net, int group,
 		struct ifinfomsg *ifm,
 		struct nlattr **tb)
 {
@@ -1778,7 +1833,7 @@ static int rtnl_group_changelink(struct net *net, int group,
 
 	for_each_netdev(net, dev) {
 		if (dev->group == group) {
-			err = do_setlink(dev, ifm, tb, NULL, 0);
+			err = do_setlink(skb, dev, ifm, tb, NULL, 0);
 			if (err < 0)
 				return err;
 		}
@@ -1920,12 +1975,12 @@ replay:
 				modified = 1;
 			}
 
-			return do_setlink(dev, ifm, tb, ifname, modified);
+			return do_setlink(skb, dev, ifm, tb, ifname, modified);
 		}
 
 		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
 			if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
-				return rtnl_group_changelink(net,
+				return rtnl_group_changelink(skb, net,
 						nla_get_u32(tb[IFLA_GROUP]),
 						ifm, tb);
 			return -ENODEV;
@@ -2042,9 +2097,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
+	int hdrlen;
+
+	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
@@ -2312,7 +2371,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err = -EINVAL;
 	__u8 *addr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2764,7 +2823,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	sz_idx = type>>2;
 	kind = type&3;
 
-	if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 897da56f3aff..ba71212f0251 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
-	u32 hash[MD5_DIGEST_WORDS];
-
-	net_secret_init();
-	hash[0] = (__force __u32) daddr;
-	hash[1] = net_secret[13];
-	hash[2] = net_secret[14];
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
-	__u32 hash[4];
-
-	net_secret_init();
-	memcpy(hash, daddr, 16);
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
 
 __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 				 __be16 sport, __be16 dport)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 90b96a11b974..baf6fc457df9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -62,6 +62,7 @@
 #include <linux/scatterlist.h>
 #include <linux/errqueue.h>
 #include <linux/prefetch.h>
+#include <linux/if_vlan.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
@@ -2881,12 +2882,13 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	int pos;
 	int dummy;
 
+	__skb_push(head_skb, doffset);
 	proto = skb_network_protocol(head_skb, &dummy);
 	if (unlikely(!proto))
 		return ERR_PTR(-EINVAL);
 
 	csum = !!can_checksum_protocol(features, proto);
-	__skb_push(head_skb, doffset);
+
 	headroom = skb_headroom(head_skb);
 	pos = skb_headlen(head_skb);
 
@@ -2967,9 +2969,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		tail = nskb;
 
 		__copy_skb_header(nskb, head_skb);
-		nskb->mac_len = head_skb->mac_len;
 
 		skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom);
+		skb_reset_mac_len(nskb);
 
 		skb_copy_from_linear_data_offset(head_skb, -tnl_hlen,
 						 nskb->data - tnl_hlen,
@@ -3076,7 +3078,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
 
-	lp = NAPI_GRO_CB(p)->last ?: p;
+	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
 	if (headlen <= offset) {
@@ -3138,6 +3140,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 		NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
 		goto done;
 	}
+	/* switch back to head shinfo */
+	pinfo = skb_shinfo(p);
+
 	if (pinfo->frag_list)
 		goto merge;
 	if (skb_gro_len(p) != pinfo->gso_size)
@@ -3192,7 +3197,7 @@ merge:
 
 	__skb_pull(skb, offset);
 
-	if (!NAPI_GRO_CB(p)->last)
+	if (NAPI_GRO_CB(p)->last == p)
 		skb_shinfo(p)->frag_list = skb;
 	else
 		NAPI_GRO_CB(p)->last->next = skb;
@@ -3951,12 +3956,66 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet);
 unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
 {
 	const struct skb_shared_info *shinfo = skb_shinfo(skb);
-	unsigned int hdr_len;
 
 	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
-		hdr_len = tcp_hdrlen(skb);
-	else
-		hdr_len = sizeof(struct udphdr);
-	return hdr_len + shinfo->gso_size;
+		return tcp_hdrlen(skb) + shinfo->gso_size;
+
+	/* UFO sets gso_size to the size of the fragmentation
+	 * payload, i.e. the size of the L4 (UDP) header is already
+	 * accounted for.
+	 */
+	return shinfo->gso_size;
 }
 EXPORT_SYMBOL_GPL(skb_gso_transport_seglen);
+
+static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
+{
+	if (skb_cow(skb, skb_headroom(skb)) < 0) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
+	skb->mac_header += VLAN_HLEN;
+	return skb;
+}
+
+struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
+{
+	struct vlan_hdr *vhdr;
+	u16 vlan_tci;
+
+	if (unlikely(vlan_tx_tag_present(skb))) {
+		/* vlan_tci is already set-up so leave this for another time */
+		return skb;
+	}
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		goto err_free;
+
+	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+		goto err_free;
+
+	vhdr = (struct vlan_hdr *)skb->data;
+	vlan_tci = ntohs(vhdr->h_vlan_TCI);
+	__vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci);
+
+	skb_pull_rcsum(skb, VLAN_HLEN);
+	vlan_set_encap_proto(skb, vhdr);
+
+	skb = skb_reorder_vlan_header(skb);
+	if (unlikely(!skb))
+		goto err_free;
+
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_reset_mac_len(skb);
+
+	return skb;
+
+err_free:
+	kfree_skb(skb);
+	return NULL;
+}
+EXPORT_SYMBOL(skb_vlan_untag);
diff --git a/net/core/sock.c b/net/core/sock.c
index c0fc6bdad1e3..c8069561bdb7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -145,6 +145,55 @@
 static DEFINE_MUTEX(proto_list_mutex);
 static LIST_HEAD(proto_list);
 
+/**
+ * sk_ns_capable - General socket capability test
+ * @sk: Socket to use a capability on or through
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in the user
+ * namespace @user_ns.
+ */
+bool sk_ns_capable(const struct sock *sk,
+		   struct user_namespace *user_ns, int cap)
+{
+	return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(sk_ns_capable);
+
+/**
+ * sk_capable - Socket global capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The global capbility to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in all user
+ * namespaces.
+ */
+bool sk_capable(const struct sock *sk, int cap)
+{
+	return sk_ns_capable(sk, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(sk_capable);
+
+/**
+ * sk_net_capable - Network namespace socket capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socke was created
+ * and the current process has the capability @cap over the network namespace
+ * the socket is a member of.
+ */
+bool sk_net_capable(const struct sock *sk, int cap)
+{
+	return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(sk_net_capable);
+
+
 #ifdef CONFIG_MEMCG_KMEM
 int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a0e9cf6379de..c38e7a2b5a8e 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 }
 EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
 
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 			     struct sk_buff *skb, int attrtype)
 {
 	struct nlattr *attr;
@@ -57,7 +57,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
 	unsigned int len;
 	int err = 0;
 
-	if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
+	if (!may_report_filterinfo) {
 		nla_reserve(skb, attrtype, 0);
 		return 0;
 	}
diff --git a/net/core/utils.c b/net/core/utils.c
index 2f737bf90b3f..eed34338736c 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w)
 {
 	struct __net_random_once_work *work =
 		container_of(w, struct __net_random_once_work, work);
-	if (!static_key_enabled(work->key))
-		static_key_slow_inc(work->key);
+	BUG_ON(!static_key_enabled(work->key));
+	static_key_slow_dec(work->key);
 	kfree(work);
 }
 
@@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key)
 }
 
 bool __net_get_random_once(void *buf, int nbytes, bool *done,
-			   struct static_key *done_key)
+			   struct static_key *once_key)
 {
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
@@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
 	*done = true;
 	spin_unlock_irqrestore(&lock, flags);
 
-	__net_random_once_disable_jump(done_key);
+	__net_random_once_disable_jump(once_key);
 
 	return true;
 }
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 553644402670..f8b98d89c285 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1669,7 +1669,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlmsghdr *reply_nlh = NULL;
 	const struct reply_func *fn;
 
-	if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN))
+	if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index a603823a3e27..3b726f31c64c 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -574,7 +574,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct dn_ifaddr __rcu **ifap;
 	int err = -EINVAL;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
@@ -618,7 +618,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct dn_ifaddr *ifa;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 57dc159245ec..d332aefb0846 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
@@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index e83015cecfa7..e4d9560a910b 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_skb(struct sk_buff *skb)
 	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
 		return;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		RCV_SKB_FAIL(-EPERM);
 
 	/* Eventually we might send routing messages too */
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index e7b6d53eef88..f005cc760535 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -149,7 +149,9 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	if (!*_result)
 		goto put;
 
-	memcpy(*_result, upayload->data, len + 1);
+	memcpy(*_result, upayload->data, len);
+	(*_result)[len] = '\0';
+
 	if (_expiry)
 		*_expiry = rkey->expiry;
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 19ab78aca547..07bd8edef417 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1434,6 +1434,9 @@ static int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
+	if (skb->encapsulation)
+		skb_set_inner_network_header(skb, nhoff);
+
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
 
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 8b5134c582f1..a3095fdefbed 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -86,18 +86,26 @@ out:
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
 
+/* Because UDP xmit path can manipulate sk_dst_cache without holding
+ * socket lock, we need to use sk_dst_set() here,
+ * even if we own the socket lock.
+ */
 void ip4_datagram_release_cb(struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ip_options_rcu *inet_opt;
 	__be32 daddr = inet->inet_daddr;
+	struct dst_entry *dst;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
-		return;
-
 	rcu_read_lock();
+
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
+		rcu_read_unlock();
+		return;
+	}
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
@@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk)
 				   inet->inet_saddr, inet->inet_dport,
 				   inet->inet_sport, sk->sk_protocol,
 				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
-	if (!IS_ERR(rt))
-		__sk_dst_set(sk, &rt->dst);
+
+	dst = !IS_ERR(rt) ? &rt->dst : NULL;
+	sk_dst_set(sk, dst);
+
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index f2e15738534d..8f7bd56955b0 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -62,6 +62,10 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res)
 	else
 		res->tclassid = 0;
 #endif
+
+	if (err == -ESRCH)
+		err = -ENETUNREACH;
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(__fib_lookup);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b53f0bf84dca..017fa5e17594 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -535,7 +535,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
 			return 1;
 
 		attrlen = rtnh_attrlen(rtnh);
-		if (attrlen < 0) {
+		if (attrlen > 0) {
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
@@ -820,13 +820,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
+	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
-	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
 	fi->fib_protocol = cfg->fc_protocol;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index f1d32280cb54..278836f1a5ad 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -50,7 +50,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 
 	greh = (struct gre_base_hdr *)skb_transport_header(skb);
 
-	ghl = skb_inner_network_header(skb) - skb_transport_header(skb);
+	ghl = skb_inner_mac_header(skb) - skb_transport_header(skb);
 	if (unlikely(ghl < sizeof(*greh)))
 		goto out;
 
@@ -255,6 +255,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
 	int err = -ENOENT;
 	__be16 type;
 
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type = SKB_GSO_GRE;
+
 	type = greh->protocol;
 	if (greh->flags & GRE_KEY)
 		grehlen += GRE_HEADER_SECTION;
@@ -268,6 +271,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
 		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
 
 	rcu_read_unlock();
+
+	skb_set_inner_mac_header(skb, nhoff + grehlen);
+
 	return err;
 }
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 0134663fdbce..1e4aa8354f93 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -732,8 +732,6 @@ static void icmp_unreach(struct sk_buff *skb)
 				/* fall through */
 			case 0:
 				info = ntohs(icmph->un.frag.mtu);
-				if (!info)
-					goto out;
 			}
 			break;
 		case ICMP_SR_FAILED:
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 97e4d1655d26..0ffcd4d64e0a 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	pip->saddr    = fl4.saddr;
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&pip[1])[0] = IPOPT_RA;
 	((u8 *)&pip[1])[1] = 4;
 	((u8 *)&pip[1])[2] = 0;
@@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	iph->daddr    = dst;
 	iph->saddr    = fl4.saddr;
 	iph->protocol = IPPROTO_IGMP;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&iph[1])[0] = IPOPT_RA;
 	((u8 *)&iph[1])[1] = 4;
 	((u8 *)&iph[1])[2] = 0;
@@ -1952,6 +1952,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 	rtnl_lock();
 	in_dev = ip_mc_find_dev(net, imr);
+	if (!in_dev) {
+		ret = -ENODEV;
+		goto out;
+	}
 	ifindex = imr->imr_ifindex;
 	for (imlp = &inet->mc_list;
 	     (iml = rtnl_dereference(*imlp)) != NULL;
@@ -1969,16 +1973,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 		*imlp = iml->next_rcu;
 
-		if (in_dev)
-			ip_mc_dec_group(in_dev, group);
+		ip_mc_dec_group(in_dev, group);
 		rtnl_unlock();
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
 		kfree_rcu(iml, rcu);
 		return 0;
 	}
-	if (!in_dev)
-		ret = -ENODEV;
+out:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 48f424465112..bf2cb4a4714b 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -26,20 +26,7 @@
  *  Theory of operations.
  *  We keep one entry for each peer IP address.  The nodes contains long-living
  *  information about the peer which doesn't depend on routes.
- *  At this moment this information consists only of ID field for the next
- *  outgoing IP packet.  This field is incremented with each packet as encoded
- *  in inet_getid() function (include/net/inetpeer.h).
- *  At the moment of writing this notes identifier of IP packets is generated
- *  to be unpredictable using this code only for packets subjected
- *  (actually or potentially) to defragmentation.  I.e. DF packets less than
- *  PMTU in size when local fragmentation is disabled use a constant ID and do
- *  not use this code (see ip_select_ident() in include/net/ip.h).
  *
- *  Route cache entries hold references to our nodes.
- *  New cache entries get references via lookup by destination IP address in
- *  the avl tree.  The reference is grabbed only when it's needed i.e. only
- *  when we try to output IP packet which needs an unpredictable ID (see
- *  __ip_select_ident() in net/ipv4/route.c).
  *  Nodes are removed only when reference counter goes to 0.
  *  When it's happened the node may be removed when a sufficient amount of
  *  time has been passed since its last use.  The less-recently-used entry can
@@ -62,7 +49,6 @@
  *		refcnt: atomically against modifications on other CPU;
  *		   usually under some other lock to prevent node disappearing
  *		daddr: unchangeable
- *		ip_id_count: atomic value (no lock needed)
  */
 
 static struct kmem_cache *peer_cachep __read_mostly;
@@ -497,10 +483,6 @@ relookup:
 		p->daddr = *daddr;
 		atomic_set(&p->refcnt, 1);
 		atomic_set(&p->rid, 0);
-		atomic_set(&p->ip_id_count,
-				(daddr->family == AF_INET) ?
-					secure_ip_id(daddr->addr.a4) :
-					secure_ipv6_id(daddr->addr.a6));
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
 		/* 60*HZ is arbitrary, but chosen enough high so that the first
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index f3869c186d97..1c6bd4359cbd 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -42,12 +42,12 @@
 static bool ip_may_fragment(const struct sk_buff *skb)
 {
 	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
-	       !skb->local_df;
+		skb->local_df;
 }
 
 static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 {
-	if (skb->len <= mtu || skb->local_df)
+	if (skb->len <= mtu)
 		return false;
 
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index ec4f762efda5..94213c891565 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -463,6 +463,7 @@ static const struct net_device_ops ipgre_netdev_ops = {
 static void ipgre_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &ipgre_netdev_ops;
+	dev->type		= ARPHRD_IPGRE;
 	ip_tunnel_setup(dev, ipgre_net_id);
 }
 
@@ -501,7 +502,6 @@ static int ipgre_tunnel_init(struct net_device *dev)
 	memcpy(dev->dev_addr, &iph->saddr, 4);
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->type		= ARPHRD_IPGRE;
 	dev->flags		= IFF_NOARP;
 	dev->priv_flags		&= ~IFF_XMIT_DST_RELEASE;
 	dev->addr_len		= 4;
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index f4ab72e19af9..96f90b89df32 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -288,6 +288,10 @@ int ip_options_compile(struct net *net,
 			optptr++;
 			continue;
 		}
+		if (unlikely(l < 2)) {
+			pp_ptr = optptr;
+			goto error;
+		}
 		optlen = optptr[1];
 		if (optlen < 2 || optlen > l) {
 			pp_ptr = optptr;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 73c6b63bba74..844323b6cfb9 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -386,8 +386,7 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_more(skb, &rt->dst, sk,
-			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
@@ -1338,7 +1337,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
@@ -1488,6 +1487,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	struct sk_buff *nskb;
 	struct sock *sk;
 	struct inet_sock *inet;
+	int err;
 
 	if (ip_options_echo(&replyopts.opt.opt, skb))
 		return;
@@ -1526,8 +1526,13 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 	sock_net_set(sk, net);
 	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
-	ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
-		       &ipc, &rt, MSG_DONTWAIT);
+	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
+			     len, 0, &ipc, &rt, MSG_DONTWAIT);
+	if (unlikely(err)) {
+		ip_flush_pending_frames(sk);
+		goto out;
+	}
+
 	nskb = skb_peek(&sk->sk_write_queue);
 	if (nskb) {
 		if (arg->csumoffset >= 0)
@@ -1539,7 +1544,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
-
+out:
 	put_cpu_var(unicast_sock);
 
 	ip_rt_put(rt);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index a82a22d8f77f..0a4af0920af3 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -69,28 +69,25 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote)
 }
 
 static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
-			     struct dst_entry *dst)
+			     struct dst_entry *dst, __be32 saddr)
 {
 	struct dst_entry *old_dst;
 
-	if (dst) {
-		if (dst->flags & DST_NOCACHE)
-			dst = NULL;
-		else
-			dst_clone(dst);
-	}
+	dst_clone(dst);
 	old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
 	dst_release(old_dst);
+	idst->saddr = saddr;
 }
 
-static void tunnel_dst_set(struct ip_tunnel *t, struct dst_entry *dst)
+static void tunnel_dst_set(struct ip_tunnel *t,
+			   struct dst_entry *dst, __be32 saddr)
 {
-	__tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst);
+	__tunnel_dst_set(this_cpu_ptr(t->dst_cache), dst, saddr);
 }
 
 static void tunnel_dst_reset(struct ip_tunnel *t)
 {
-	tunnel_dst_set(t, NULL);
+	tunnel_dst_set(t, NULL, 0);
 }
 
 void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
@@ -98,23 +95,29 @@ void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
 	int i;
 
 	for_each_possible_cpu(i)
-		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
+		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL, 0);
 }
 EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
 
-static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
+static struct rtable *tunnel_rtable_get(struct ip_tunnel *t,
+					u32 cookie, __be32 *saddr)
 {
+	struct ip_tunnel_dst *idst;
 	struct dst_entry *dst;
 
 	rcu_read_lock();
-	dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
+	idst = this_cpu_ptr(t->dst_cache);
+	dst = rcu_dereference(idst->dst);
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
 	if (dst) {
-		if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
-			rcu_read_unlock();
+		if (!dst->obsolete || dst->ops->check(dst, cookie)) {
+			*saddr = idst->saddr;
+		} else {
 			tunnel_dst_reset(t);
-			return NULL;
+			dst_release(dst);
+			dst = NULL;
 		}
-		dst_hold(dst);
 	}
 	rcu_read_unlock();
 	return (struct rtable *)dst;
@@ -173,6 +176,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (remote != t->parms.iph.daddr ||
+		    t->parms.iph.saddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -189,10 +193,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	head = &itn->tunnels[hash];
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if ((local != t->parms.iph.saddr &&
-		     (local != t->parms.iph.daddr ||
-		      !ipv4_is_multicast(local))) ||
-		    !(t->dev->flags & IFF_UP))
+		if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
+		    (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
+			continue;
+
+		if (!(t->dev->flags & IFF_UP))
 			continue;
 
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
@@ -209,6 +214,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (t->parms.i_key != key ||
+		    t->parms.iph.saddr != 0 ||
+		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -362,7 +369,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		if (!IS_ERR(rt)) {
 			tdev = rt->dst.dev;
-			tunnel_dst_set(tunnel, &rt->dst);
+			tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
 			ip_rt_put(rt);
 		}
 		if (dev->type != ARPHRD_ETHER)
@@ -438,6 +445,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		tunnel->i_seqno = ntohl(tpi->seq) + 1;
 	}
 
+	skb_reset_network_header(skb);
+
 	err = IP_ECN_decapsulate(iph, skb);
 	if (unlikely(err)) {
 		if (log_ecn_error)
@@ -534,9 +543,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int err;
-	bool connected = true;
+	bool connected;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+	connected = (tunnel->parms.iph.daddr != 0);
 
 	dst = tnl_params->daddr;
 	if (dst == 0) {
@@ -603,7 +613,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
 			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
 
-	rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL;
+	rt = connected ? tunnel_rtable_get(tunnel, 0, &fl4.saddr) : NULL;
 
 	if (!rt) {
 		rt = ip_route_output_key(tunnel->net, &fl4);
@@ -613,7 +623,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 		}
 		if (connected)
-			tunnel_dst_set(tunnel, &rt->dst);
+			tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
 	}
 
 	if (rt->dst.dev == dev) {
@@ -872,6 +882,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 	}
 	rtnl_unlock();
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 8d69626f2206..791a419f0699 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -74,7 +74,7 @@ int iptunnel_xmit(struct rtable *rt, struct sk_buff *skb,
 	iph->daddr	=	dst;
 	iph->saddr	=	src;
 	iph->ttl	=	ttl;
-	__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
 
 	err = ip_local_out(skb);
 	if (unlikely(net_xmit_eval(err)))
@@ -91,11 +91,12 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto)
 	skb_pull_rcsum(skb, hdr_len);
 
 	if (inner_proto == htons(ETH_P_TEB)) {
-		struct ethhdr *eh = (struct ethhdr *)skb->data;
+		struct ethhdr *eh;
 
 		if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
 			return -ENOMEM;
 
+		eh = (struct ethhdr *)skb->data;
 		if (likely(ntohs(eh->h_proto) >= ETH_P_802_3_MIN))
 			skb->protocol = eh->h_proto;
 		else
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 48eafae51769..b0a9cb4bbfdb 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -207,6 +207,7 @@ static const struct net_device_ops vti_netdev_ops = {
 static void vti_tunnel_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &vti_netdev_ops;
+	dev->type		= ARPHRD_TUNNEL;
 	ip_tunnel_setup(dev, vti_net_id);
 }
 
@@ -218,7 +219,6 @@ static int vti_tunnel_init(struct net_device *dev)
 	memcpy(dev->dev_addr, &iph->saddr, 4);
 	memcpy(dev->broadcast, &iph->daddr, 4);
 
-	dev->type		= ARPHRD_TUNNEL;
 	dev->hard_header_len	= LL_MAX_HEADER + sizeof(struct iphdr);
 	dev->mtu		= ETH_DATA_LEN;
 	dev->flags		= IFF_NOARP;
@@ -369,6 +369,7 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
 	.validate	= vti_tunnel_validate,
 	.newlink	= vti_newlink,
 	.changelink	= vti_changelink,
+	.dellink        = ip_tunnel_dellink,
 	.get_size	= vti_get_size,
 	.fill_info	= vti_fill_info,
 };
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 812b18351462..62eaa005e146 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+				 t->parms.link, 0, IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
@@ -486,4 +486,5 @@ static void __exit ipip_fini(void)
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ipip");
 MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 28863570dd60..1149fc2290e2 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1663,7 +1663,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
 	iph->protocol	=	IPPROTO_IPIP;
 	iph->ihl	=	5;
 	iph->tot_len	=	htons(skb->len);
-	ip_select_ident(skb, skb_dst(skb), NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 59da7cde0724..f95b6f93814b 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1044,8 +1044,10 @@ static int __do_replace(struct net *net, const char *name,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 718dfbd30cbe..99e810f84671 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1231,8 +1231,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 12e13bd82b5b..f40f321b41fc 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,7 +22,6 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-/* Returns new sk_buff, or NULL */
 static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 {
 	int err;
@@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 	err = ip_defrag(skb, user);
 	local_bh_enable();
 
-	if (!err)
+	if (!err) {
 		ip_send_check(ip_hdr(skb));
+		skb->local_df = 1;
+	}
 
 	return err;
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2d11c094296e..0d33f947a87f 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -217,6 +217,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 					     &ipv6_hdr(skb)->daddr))
 				continue;
 #endif
+		} else {
+			continue;
 		}
 
 		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
@@ -252,26 +254,33 @@ int ping_init_sock(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
 	kgid_t group = current_egid();
-	struct group_info *group_info = get_current_groups();
-	int i, j, count = group_info->ngroups;
+	struct group_info *group_info;
+	int i, j, count;
 	kgid_t low, high;
+	int ret = 0;
 
 	inet_get_ping_group_range_net(net, &low, &high);
 	if (gid_lte(low, group) && gid_lte(group, high))
 		return 0;
 
+	group_info = get_current_groups();
+	count = group_info->ngroups;
 	for (i = 0; i < group_info->nblocks; i++) {
 		int cp_count = min_t(int, NGROUPS_PER_BLOCK, count);
 		for (j = 0; j < cp_count; j++) {
 			kgid_t gid = group_info->blocks[i][j];
 			if (gid_lte(low, gid) && gid_lte(gid, high))
-				return 0;
+				goto out_release_group;
 		}
 
 		count -= cp_count;
 	}
 
-	return -EACCES;
+	ret = -EACCES;
+
+out_release_group:
+	put_group_info(group_info);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(ping_init_sock);
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index c04518f4850a..11c8d81fdc59 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		iph->check   = 0;
 		iph->tot_len = htons(length);
 		if (!iph->id)
-			ip_select_ident(skb, &rt->dst, NULL);
+			ip_select_ident(skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 4c011ec69ed4..487bb6252520 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -89,6 +89,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/jhash.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -462,39 +463,45 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 	return neigh_create(&arp_tbl, pkey, dev);
 }
 
-/*
- * Peer allocation may fail only in serious out-of-memory conditions.  However
- * we still can generate some output.
- * Random ID selection looks a bit dangerous because we have no chances to
- * select ID being unique in a reasonable period of time.
- * But broken packet identifier may be better than no packet at all.
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+	atomic_t	id;
+	u32		stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
  */
-static void ip_select_fb_ident(struct iphdr *iph)
+u32 ip_idents_reserve(u32 hash, int segs)
 {
-	static DEFINE_SPINLOCK(ip_fb_id_lock);
-	static u32 ip_fallback_id;
-	u32 salt;
+	struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+	u32 old = ACCESS_ONCE(bucket->stamp32);
+	u32 now = (u32)jiffies;
+	u32 delta = 0;
 
-	spin_lock_bh(&ip_fb_id_lock);
-	salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
-	iph->id = htons(salt & 0xFFFF);
-	ip_fallback_id = salt;
-	spin_unlock_bh(&ip_fb_id_lock);
+	if (old != now && cmpxchg(&bucket->stamp32, old, now) == old)
+		delta = prandom_u32_max(now - old);
+
+	return atomic_add_return(segs + delta, &bucket->id) - segs;
 }
+EXPORT_SYMBOL(ip_idents_reserve);
 
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
+void __ip_select_ident(struct iphdr *iph, int segs)
 {
-	struct net *net = dev_net(dst->dev);
-	struct inet_peer *peer;
+	static u32 ip_idents_hashrnd __read_mostly;
+	u32 hash, id;
 
-	peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
-	if (peer) {
-		iph->id = htons(inet_getid(peer, more));
-		inet_putpeer(peer);
-		return;
-	}
+	net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
 
-	ip_select_fb_ident(iph);
+	hash = jhash_3words((__force u32)iph->daddr,
+			    (__force u32)iph->saddr,
+			    iph->protocol,
+			    ip_idents_hashrnd);
+	id = ip_idents_reserve(hash, segs);
+	iph->id = htons(id);
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
@@ -1029,7 +1036,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
-	struct dst_entry *dst;
+	struct dst_entry *odst = NULL;
 	bool new = false;
 
 	bh_lock_sock(sk);
@@ -1037,16 +1044,17 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	if (!ip_sk_accept_pmtu(sk))
 		goto out;
 
-	rt = (struct rtable *) __sk_dst_get(sk);
+	odst = sk_dst_get(sk);
 
-	if (sock_owned_by_user(sk) || !rt) {
+	if (sock_owned_by_user(sk) || !odst) {
 		__ipv4_sk_update_pmtu(skb, sk, mtu);
 		goto out;
 	}
 
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
 
-	if (!__sk_dst_check(sk, 0)) {
+	rt = (struct rtable *)odst;
+	if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
 		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt))
 			goto out;
@@ -1056,8 +1064,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 
 	__ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
 
-	dst = dst_check(&rt->dst, 0);
-	if (!dst) {
+	if (!dst_check(&rt->dst, 0)) {
 		if (new)
 			dst_release(&rt->dst);
 
@@ -1069,10 +1076,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	}
 
 	if (new)
-		__sk_dst_set(sk, &rt->dst);
+		sk_dst_set(sk, &rt->dst);
 
 out:
 	bh_unlock_sock(sk);
+	dst_release(odst);
 }
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 
@@ -1526,7 +1534,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct in_device *out_dev;
 	unsigned int flags = 0;
 	bool do_cache;
-	u32 itag;
+	u32 itag = 0;
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
@@ -2260,9 +2268,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 		return rt;
 
 	if (flp4->flowi4_proto)
-		rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
-						   flowi4_to_flowi(flp4),
-						   sk, 0);
+		rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst,
+							flowi4_to_flowi(flp4),
+							sk, 0);
 
 	return rt;
 }
@@ -2364,7 +2372,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 			}
 		} else
 #endif
-			if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+			if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
 				goto nla_put_failure;
 	}
 
@@ -2717,6 +2725,12 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
+	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
+	if (!ip_idents)
+		panic("IP: failed to allocate ip_idents\n");
+
+	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 97c8f5620c43..29d240b87af1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1108,7 +1108,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (unlikely(tp->repair)) {
 		if (tp->repair_queue == TCP_RECV_QUEUE) {
 			copied = tcp_send_rcvq(sk, msg, size);
-			goto out;
+			goto out_nopush;
 		}
 
 		err = -EINVAL;
@@ -1175,13 +1175,6 @@ new_segment:
 					goto wait_for_memory;
 
 				/*
-				 * All packets are restored as if they have
-				 * already been sent.
-				 */
-				if (tp->repair)
-					TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
-				/*
 				 * Check whether we can use HW checksum.
 				 */
 				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
@@ -1190,6 +1183,13 @@ new_segment:
 				skb_entail(sk, skb);
 				copy = size_goal;
 				max = size_goal;
+
+				/* All packets are restored as if they have
+				 * already been sent. skb_mstamp isn't set to
+				 * avoid wrong rtt estimation.
+				 */
+				if (tp->repair)
+					TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
 			}
 
 			/* Try to append data to the end of skb. */
@@ -1282,6 +1282,7 @@ wait_for_memory:
 out:
 	if (copied)
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+out_nopush:
 	release_sock(sk);
 	return copied + copied_syn;
 
@@ -2953,61 +2954,42 @@ EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
 #ifdef CONFIG_TCP_MD5SIG
-static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly;
+static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool);
 static DEFINE_MUTEX(tcp_md5sig_mutex);
-
-static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu);
-
-		if (p->md5_desc.tfm)
-			crypto_free_hash(p->md5_desc.tfm);
-	}
-	free_percpu(pool);
-}
+static bool tcp_md5sig_pool_populated = false;
 
 static void __tcp_alloc_md5sig_pool(void)
 {
 	int cpu;
-	struct tcp_md5sig_pool __percpu *pool;
-
-	pool = alloc_percpu(struct tcp_md5sig_pool);
-	if (!pool)
-		return;
 
 	for_each_possible_cpu(cpu) {
-		struct crypto_hash *hash;
-
-		hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-		if (IS_ERR_OR_NULL(hash))
-			goto out_free;
+		if (!per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm) {
+			struct crypto_hash *hash;
 
-		per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
+			hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
+			if (IS_ERR_OR_NULL(hash))
+				return;
+			per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash;
+		}
 	}
-	/* before setting tcp_md5sig_pool, we must commit all writes
-	 * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool()
+	/* before setting tcp_md5sig_pool_populated, we must commit all writes
+	 * to memory. See smp_rmb() in tcp_get_md5sig_pool()
 	 */
 	smp_wmb();
-	tcp_md5sig_pool = pool;
-	return;
-out_free:
-	__tcp_free_md5sig_pool(pool);
+	tcp_md5sig_pool_populated = true;
 }
 
 bool tcp_alloc_md5sig_pool(void)
 {
-	if (unlikely(!tcp_md5sig_pool)) {
+	if (unlikely(!tcp_md5sig_pool_populated)) {
 		mutex_lock(&tcp_md5sig_mutex);
 
-		if (!tcp_md5sig_pool)
+		if (!tcp_md5sig_pool_populated)
 			__tcp_alloc_md5sig_pool();
 
 		mutex_unlock(&tcp_md5sig_mutex);
 	}
-	return tcp_md5sig_pool != NULL;
+	return tcp_md5sig_pool_populated;
 }
 EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
 
@@ -3021,13 +3003,13 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
  */
 struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 {
-	struct tcp_md5sig_pool __percpu *p;
-
 	local_bh_disable();
-	p = ACCESS_ONCE(tcp_md5sig_pool);
-	if (p)
-		return __this_cpu_ptr(p);
 
+	if (tcp_md5sig_pool_populated) {
+		/* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */
+		smp_rmb();
+		return this_cpu_ptr(&tcp_md5sig_pool);
+	}
 	local_bh_enable();
 	return NULL;
 }
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 828e4c3ffbaf..121a9a22dc98 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -409,7 +409,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 		ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
 		ratio += cnt;
 
-		ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
+		ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
 	}
 
 	/* Some calls are for duplicates without timetamps */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eeaac399420d..22917918fa80 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1113,7 +1113,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
 	}
 
 	/* D-SACK for already forgotten data... Do dumb counting. */
-	if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+	if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
 	    !after(end_seq_0, prior_snd_una) &&
 	    after(end_seq_0, tp->undo_marker))
 		tp->undo_retrans--;
@@ -1169,7 +1169,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 			unsigned int new_len = (pkt_len / mss) * mss;
 			if (!in_sack && new_len < pkt_len) {
 				new_len += mss;
-				if (new_len > skb->len)
+				if (new_len >= skb->len)
 					return 0;
 			}
 			pkt_len = new_len;
@@ -1193,7 +1193,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
 
 	/* Account D-SACK for retransmitted packet. */
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
-		if (tp->undo_marker && tp->undo_retrans &&
+		if (tp->undo_marker && tp->undo_retrans > 0 &&
 		    after(end_seq, tp->undo_marker))
 			tp->undo_retrans--;
 		if (sacked & TCPCB_SACKED_ACKED)
@@ -1894,7 +1894,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp)
 	tp->lost_out = 0;
 
 	tp->undo_marker = 0;
-	tp->undo_retrans = 0;
+	tp->undo_retrans = -1;
 }
 
 void tcp_clear_retrans(struct tcp_sock *tp)
@@ -2663,7 +2663,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 
 	tp->prior_ssthresh = 0;
 	tp->undo_marker = tp->snd_una;
-	tp->undo_retrans = tp->retrans_out;
+	tp->undo_retrans = tp->retrans_out ? : -1;
 
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
 		if (!ece_ack)
@@ -2678,18 +2678,16 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
  */
 static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 {
-	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
-		if (flag & FLAG_ORIG_SACK_ACKED) {
-			/* Step 3.b. A timeout is spurious if not all data are
-			 * lost, i.e., never-retransmitted data are (s)acked.
-			 */
-			tcp_try_undo_loss(sk, true);
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
 			return;
-		}
+
 		if (after(tp->snd_nxt, tp->high_seq) &&
 		    (flag & FLAG_DATA_SACKED || is_dupack)) {
 			tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
@@ -2705,12 +2703,9 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
 
 	if (recovered) {
 		/* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
-		icsk->icsk_retransmits = 0;
 		tcp_try_undo_recovery(sk);
 		return;
 	}
-	if (flag & FLAG_DATA_ACKED)
-		icsk->icsk_retransmits = 0;
 	if (tcp_is_reno(tp)) {
 		/* A Reno DUPACK means new data in F-RTO step 2.b above are
 		 * delivered. Lower inflight to clock out (re)tranmissions.
@@ -3399,8 +3394,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
 
-	if (after(ack, prior_snd_una))
+	if (after(ack, prior_snd_una)) {
 		flag |= FLAG_SND_UNA_ADVANCED;
+		icsk->icsk_retransmits = 0;
+	}
 
 	prior_fackets = tp->fackets_out;
 	prior_in_flight = tcp_packets_in_flight(tp);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1e4eac779f51..a782d5be132e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -269,7 +269,7 @@ EXPORT_SYMBOL(tcp_v4_connect);
  * It can be called through tcp_release_cb() if socket was owned by user
  * at the time tcp_v4_err() was called to handle ICMP message.
  */
-static void tcp_v4_mtu_reduced(struct sock *sk)
+void tcp_v4_mtu_reduced(struct sock *sk)
 {
 	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
@@ -300,6 +300,7 @@ static void tcp_v4_mtu_reduced(struct sock *sk)
 		tcp_simple_retransmit(sk);
 	} /* else let the usual retransmit timer handle it */
 }
+EXPORT_SYMBOL(tcp_v4_mtu_reduced);
 
 static void do_redirect(struct sk_buff *skb, struct sock *sk)
 {
@@ -2117,6 +2118,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.compat_setsockopt = compat_ip_setsockopt,
 	.compat_getsockopt = compat_ip_getsockopt,
 #endif
+	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
 EXPORT_SYMBOL(ipv4_specific);
 
@@ -2736,7 +2738,6 @@ struct proto tcp_prot = {
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v4_do_rcv,
 	.release_cb		= tcp_release_cb,
-	.mtu_reduced		= tcp_v4_mtu_reduced,
 	.hash			= inet_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index b92b81718ca4..c25953a386d0 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -310,7 +310,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 
 	th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr,
 				  iph->daddr, 0);
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 
 	return tcp_gro_complete(skb);
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 17a11e65e57f..91b98e5a17aa 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -787,7 +787,7 @@ void tcp_release_cb(struct sock *sk)
 		__sock_put(sk);
 	}
 	if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
-		sk->sk_prot->mtu_reduced(sk);
+		inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
 		__sock_put(sk);
 	}
 }
@@ -1876,8 +1876,11 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
 		BUG_ON(!tso_segs);
 
-		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE)
+		if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
+			/* "when" is used as a start point for the retransmit timer */
+			TCP_SKB_CB(skb)->when = tcp_time_stamp;
 			goto repair; /* Skip network transmission */
+		}
 
 		cwnd_quota = tcp_cwnd_test(tp, skb);
 		if (!cwnd_quota) {
@@ -2066,9 +2069,7 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
 		goto rearm_timer;
 
-	/* Probe with zero data doesn't trigger fast recovery. */
-	if (skb->len > 0)
-		err = __tcp_retransmit_skb(sk, skb);
+	err = __tcp_retransmit_skb(sk, skb);
 
 	/* Record snd_nxt for loss detection. */
 	if (likely(!err))
@@ -2448,8 +2449,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (!tp->retrans_stamp)
 			tp->retrans_stamp = TCP_SKB_CB(skb)->when;
 
-		tp->undo_retrans += tcp_skb_pcount(skb);
-
 		/* snd_nxt is stored to detect loss of retransmitted segment,
 		 * see tcp_input.c tcp_sacktag_write_queue().
 		 */
@@ -2457,6 +2456,10 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	} else {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
+
+	if (tp->undo_retrans < 0)
+		tp->undo_retrans = 0;
+	tp->undo_retrans += tcp_skb_pcount(skb);
 	return err;
 }
 
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 06cae62bf208..6b1a5fd60598 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -219,7 +219,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 			 * This is:
 			 *     (actual rate in segments) * baseRTT
 			 */
-			target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt;
+			target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT;
+			do_div(target_cwnd, rtt);
 
 			/* Calculate the difference between the window we had,
 			 * and the window we would like to have. This quantity
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 326475a94865..603ad498e18a 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -145,7 +145,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 
 		rtt = veno->minrtt;
 
-		target_cwnd = (tp->snd_cwnd * veno->basertt);
+		target_cwnd = (u64)tp->snd_cwnd * veno->basertt;
 		target_cwnd <<= V_PARAM_SHIFT;
 		do_div(target_cwnd, rtt);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 77bd16fa9f34..b25e852625d8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1833,6 +1833,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
 	struct udp_hslot *hslot = &udp_table.hash[slot];
 
+	/* Do not bother scanning a too big list */
+	if (hslot->count > 10)
+		return NULL;
+
 	rcu_read_lock();
 begin:
 	count = 0;
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 31b18152528f..1f564a1487a3 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -117,12 +117,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
 		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
-	ip_select_ident(skb, dst->child, NULL);
 
 	top_iph->ttl = ip4_dst_hoplimit(dst->child);
 
 	top_iph->saddr = x->props.saddr.a4;
 	top_iph->daddr = x->id.daddr.a4;
+	ip_select_ident(skb, NULL);
 
 	return 0;
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6c7fa0853fc7..3f0ec063d7f8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1684,14 +1684,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 	addrconf_mod_dad_work(ifp, 0);
 }
 
-/* Join to solicited addr multicast group. */
-
+/* Join to solicited addr multicast group.
+ * caller must hold RTNL */
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
-	ASSERT_RTNL();
-
 	if (dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1699,12 +1697,11 @@ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr)
 	ipv6_dev_mc_inc(dev, &maddr);
 }
 
+/* caller must hold RTNL */
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct in6_addr maddr;
 
-	ASSERT_RTNL();
-
 	if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP))
 		return;
 
@@ -1712,12 +1709,11 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 	__ipv6_dev_mc_dec(idev, &maddr);
 }
 
+/* caller must hold RTNL */
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
 
-	ASSERT_RTNL();
-
 	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
@@ -1726,12 +1722,11 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 	ipv6_dev_ac_inc(ifp->idev->dev, &addr);
 }
 
+/* caller must hold RTNL */
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
 
-	ASSERT_RTNL();
-
 	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 210183244689..ff2de7d9d8e6 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -77,6 +77,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	pac->acl_next = NULL;
 	pac->acl_addr = *addr;
 
+	rtnl_lock();
 	rcu_read_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
@@ -137,6 +138,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 error:
 	rcu_read_unlock();
+	rtnl_unlock();
 	if (pac)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 	return err;
@@ -171,11 +173,13 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	spin_unlock_bh(&ipv6_sk_ac_lock);
 
+	rtnl_lock();
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, pac->acl_ifindex);
 	if (dev)
 		ipv6_dev_ac_dec(dev, &pac->acl_addr);
 	rcu_read_unlock();
+	rtnl_unlock();
 
 	sock_kfree_s(sk, pac, sizeof(*pac));
 	return 0;
@@ -198,6 +202,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 	spin_unlock_bh(&ipv6_sk_ac_lock);
 
 	prev_index = 0;
+	rtnl_lock();
 	rcu_read_lock();
 	while (pac) {
 		struct ipv6_ac_socklist *next = pac->acl_next;
@@ -212,6 +217,7 @@ void ipv6_sock_ac_close(struct sock *sk)
 		pac = next;
 	}
 	rcu_read_unlock();
+	rtnl_unlock();
 }
 
 static void aca_put(struct ifacaddr6 *ac)
@@ -233,6 +239,8 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
 	struct rt6_info *rt;
 	int err;
 
+	ASSERT_RTNL();
+
 	idev = in6_dev_get(dev);
 
 	if (idev == NULL)
@@ -302,6 +310,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct ifacaddr6 *aca, *prev_aca;
 
+	ASSERT_RTNL();
+
 	write_lock_bh(&idev->lock);
 	prev_aca = NULL;
 	for (aca = idev->ac_list; aca; aca = aca->aca_next) {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index f2610e157660..7b326529e6a2 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -520,7 +520,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 			      np->tclass, NULL, &fl6, (struct rt6_info *)dst,
 			      MSG_DONTWAIT, np->dontfrag);
 	if (err) {
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 075602fc6b6a..1e55f5eba185 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1418,7 +1418,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 
 				if (w->skip) {
 					w->skip--;
-					continue;
+					goto skip;
 				}
 
 				err = w->func(w);
@@ -1428,6 +1428,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 				w->count++;
 				continue;
 			}
+skip:
 			w->state = FWS_U;
 		case FWS_U:
 			if (fn == w->root)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f3ffb43f59c0..4a230b18dfe3 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -508,11 +508,11 @@ static int ip6gre_rcv(struct sk_buff *skb)
 
 		skb->protocol = gre_proto;
 		/* WCCP version 1 and 2 protocol decoding.
-		 * - Change protocol to IP
+		 * - Change protocol to IPv6
 		 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
 		 */
 		if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
-			skb->protocol = htons(ETH_P_IP);
+			skb->protocol = htons(ETH_P_IPV6);
 			if ((*(h + offset) & 0xF0) != 0x40)
 				offset += 4;
 		}
@@ -787,7 +787,7 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_IPIP;
+	fl6.flowi6_proto = IPPROTO_GRE;
 
 	dsfield = ipv4_get_dsfield(iph);
 
@@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 		encap_limit = t->parms.encap_limit;
 
 	memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
-	fl6.flowi6_proto = IPPROTO_IPV6;
+	fl6.flowi6_proto = IPPROTO_GRE;
 
 	dsfield = ipv6_get_dsfield(ipv6h);
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
@@ -962,8 +962,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 	else
 		dev->flags &= ~IFF_POINTOPOINT;
 
-	dev->iflink = p->link;
-
 	/* Precalculate GRE options length */
 	if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
 		if (t->parms.o_flags&GRE_CSUM)
@@ -1273,6 +1271,7 @@ static int ip6gre_tunnel_init(struct net_device *dev)
 		u64_stats_init(&ip6gre_tunnel_stats->syncp);
 	}
 
+	dev->iflink = tunnel->parms.link;
 
 	return 0;
 }
@@ -1474,6 +1473,8 @@ static int ip6gre_tap_init(struct net_device *dev)
 		u64_stats_init(&ip6gre_tap_stats->syncp);
 	}
 
+	dev->iflink = tunnel->parms.link;
+
 	return 0;
 }
 
@@ -1566,6 +1567,15 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 	return 0;
 }
 
+static void ip6gre_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+	if (dev != ign->fb_tunnel_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static size_t ip6gre_get_size(const struct net_device *dev)
 {
 	return
@@ -1643,6 +1653,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
 	.validate	= ip6gre_tunnel_validate,
 	.newlink	= ip6gre_newlink,
 	.changelink	= ip6gre_changelink,
+	.dellink	= ip6gre_dellink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
 };
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 59f95affceb0..b2f091566f88 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -196,7 +196,6 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	unsigned int off;
 	u16 flush = 1;
 	int proto;
-	__wsum csum;
 
 	off = skb_gro_offset(skb);
 	hlen = off + sizeof(*iph);
@@ -264,13 +263,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	NAPI_GRO_CB(skb)->flush |= flush;
 
-	csum = skb->csum;
-	skb_postpull_rcsum(skb, iph, skb_network_header_len(skb));
+	skb_gro_postpull_rcsum(skb, iph, nlen);
 
 	pp = ops->callbacks.gro_receive(head, skb);
 
-	skb->csum = csum;
-
 out_unlock:
 	rcu_read_unlock();
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 64d6073731d3..12f7ef0f243a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -344,12 +344,16 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 
 static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 {
-	if (skb->len <= mtu || skb->local_df)
+	if (skb->len <= mtu)
 		return false;
 
+	/* ipv6 conntrack defrag sets max_frag_size + local_df */
 	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
 		return true;
 
+	if (skb->local_df)
+		return false;
+
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
 		return false;
 
@@ -533,6 +537,20 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 hash, id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+	id = ip_idents_reserve(hash, 1);
+	fhdr->identification = htonl(id);
+}
+
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
@@ -990,7 +1008,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (final_dst)
 		fl6->daddr = *final_dst;
 
-	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow);
 
@@ -1022,7 +1040,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (final_dst)
 		fl6->daddr = *final_dst;
 
-	return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
+	return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
 }
 EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow);
 
@@ -1225,7 +1243,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		unsigned int maxnonfragsize, headersize;
 
 		headersize = sizeof(struct ipv6hdr) +
-			     (opt ? opt->tot_len : 0) +
+			     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
 			     (dst_allfrag(&rt->dst) ?
 			      sizeof(struct frag_hdr) : 0) +
 			     rt->rt6i_nfheader_len;
@@ -1566,8 +1584,8 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (proto == IPPROTO_ICMPV6) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
 	err = ip6_local_out(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5db8d310f9c0..657639d39f70 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -61,6 +61,7 @@
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ip6tnl");
 MODULE_ALIAS_NETDEV("ip6tnl0");
 
 #ifdef IP6_TNL_DEBUG
@@ -271,9 +272,6 @@ static int ip6_tnl_create2(struct net_device *dev)
 	int err;
 
 	t = netdev_priv(dev);
-	err = ip6_tnl_dev_init(dev);
-	if (err < 0)
-		goto out;
 
 	err = register_netdevice(dev);
 	if (err < 0)
@@ -1455,6 +1453,7 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
 
 
 static const struct net_device_ops ip6_tnl_netdev_ops = {
+	.ndo_init	= ip6_tnl_dev_init,
 	.ndo_uninit	= ip6_tnl_dev_uninit,
 	.ndo_start_xmit = ip6_tnl_xmit,
 	.ndo_do_ioctl	= ip6_tnl_ioctl,
@@ -1546,16 +1545,10 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = dev_net(dev);
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
-	int err = ip6_tnl_dev_init_gen(dev);
-
-	if (err)
-		return err;
 
 	t->parms.proto = IPPROTO_IPV6;
 	dev_hold(dev);
 
-	ip6_tnl_link_config(t);
-
 	rcu_assign_pointer(ip6n->tnls_wc[0], t);
 	return 0;
 }
@@ -1564,7 +1557,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[])
 {
 	u8 proto;
 
-	if (!data)
+	if (!data || !data[IFLA_IPTUN_PROTO])
 		return 0;
 
 	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 2d19272b8cee..28456c9a1847 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -172,10 +172,6 @@ static int vti6_tnl_create2(struct net_device *dev)
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
 	int err;
 
-	err = vti6_dev_init(dev);
-	if (err < 0)
-		goto out;
-
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
@@ -693,6 +689,7 @@ static int vti6_change_mtu(struct net_device *dev, int new_mtu)
 }
 
 static const struct net_device_ops vti6_netdev_ops = {
+	.ndo_init	= vti6_dev_init,
 	.ndo_uninit	= vti6_dev_uninit,
 	.ndo_start_xmit = vti6_tnl_xmit,
 	.ndo_do_ioctl	= vti6_ioctl,
@@ -772,16 +769,10 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct net *net = dev_net(dev);
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
-	int err = vti6_dev_init_gen(dev);
-
-	if (err)
-		return err;
 
 	t->parms.proto = IPPROTO_IPV6;
 	dev_hold(dev);
 
-	vti6_link_config(t);
-
 	rcu_assign_pointer(ip6n->tnls_wc[0], t);
 	return 0;
 }
@@ -834,6 +825,15 @@ static int vti6_newlink(struct net *src_net, struct net_device *dev,
 	return vti6_tnl_create2(dev);
 }
 
+static void vti6_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct net *net = dev_net(dev);
+	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+
+	if (dev != ip6n->fb_tnl_dev)
+		unregister_netdevice_queue(dev, head);
+}
+
 static int vti6_changelink(struct net_device *dev, struct nlattr *tb[],
 			   struct nlattr *data[])
 {
@@ -909,6 +909,7 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.setup		= vti6_dev_setup,
 	.validate	= vti6_validate,
 	.newlink	= vti6_newlink,
+	.dellink	= vti6_dellink,
 	.changelink	= vti6_changelink,
 	.get_size	= vti6_get_size,
 	.fill_info	= vti6_fill_info,
@@ -954,6 +955,7 @@ static int __net_init vti6_init_net(struct net *net)
 	if (!ip6n->fb_tnl_dev)
 		goto err_alloc_dev;
 	dev_net_set(ip6n->fb_tnl_dev, net);
+	ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops;
 
 	err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index e1e47350784b..761e4586ab5f 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -172,6 +172,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	mc_lst->next = NULL;
 	mc_lst->addr = *addr;
 
+	rtnl_lock();
 	rcu_read_lock();
 	if (ifindex == 0) {
 		struct rt6_info *rt;
@@ -185,6 +186,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	if (dev == NULL) {
 		rcu_read_unlock();
+		rtnl_unlock();
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return -ENODEV;
 	}
@@ -202,6 +204,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	if (err) {
 		rcu_read_unlock();
+		rtnl_unlock();
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
 		return err;
 	}
@@ -212,6 +215,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	spin_unlock(&ipv6_sk_mc_lock);
 
 	rcu_read_unlock();
+	rtnl_unlock();
 
 	return 0;
 }
@@ -229,6 +233,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	if (!ipv6_addr_is_multicast(addr))
 		return -EINVAL;
 
+	rtnl_lock();
 	spin_lock(&ipv6_sk_mc_lock);
 	for (lnk = &np->ipv6_mc_list;
 	     (mc_lst = rcu_dereference_protected(*lnk,
@@ -252,12 +257,15 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			} else
 				(void) ip6_mc_leave_src(sk, mc_lst, NULL);
 			rcu_read_unlock();
+			rtnl_unlock();
+
 			atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
 			kfree_rcu(mc_lst, rcu);
 			return 0;
 		}
 	}
 	spin_unlock(&ipv6_sk_mc_lock);
+	rtnl_unlock();
 
 	return -EADDRNOTAVAIL;
 }
@@ -302,6 +310,7 @@ void ipv6_sock_mc_close(struct sock *sk)
 	if (!rcu_access_pointer(np->ipv6_mc_list))
 		return;
 
+	rtnl_lock();
 	spin_lock(&ipv6_sk_mc_lock);
 	while ((mc_lst = rcu_dereference_protected(np->ipv6_mc_list,
 				lockdep_is_held(&ipv6_sk_mc_lock))) != NULL) {
@@ -328,6 +337,7 @@ void ipv6_sock_mc_close(struct sock *sk)
 		spin_lock(&ipv6_sk_mc_lock);
 	}
 	spin_unlock(&ipv6_sk_mc_lock);
+	rtnl_unlock();
 }
 
 int ip6_mc_source(int add, int omode, struct sock *sk,
@@ -845,6 +855,8 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 	struct ifmcaddr6 *mc;
 	struct inet6_dev *idev;
 
+	ASSERT_RTNL();
+
 	/* we need to take a reference on idev */
 	idev = in6_dev_get(dev);
 
@@ -916,6 +928,8 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 {
 	struct ifmcaddr6 *ma, **map;
 
+	ASSERT_RTNL();
+
 	write_lock_bh(&idev->lock);
 	for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) {
 		if (ipv6_addr_equal(&ma->mca_addr, addr)) {
@@ -1620,11 +1634,12 @@ static void mld_sendpack(struct sk_buff *skb)
 		      dst_output);
 out:
 	if (!err) {
-		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
-		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-	} else
-		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+	} else {
+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+	}
 
 	rcu_read_unlock();
 	return;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 95f3f1da0d7f..d38e6a8d8b9f 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb)
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};
+	int err;
 
 	dst = ip6_route_output(net, skb->sk, &fl6);
-	if (dst->error) {
+	err = dst->error;
+	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
 		dst_release(dst);
-		return dst->error;
+		return err;
 	}
 
 	/* Drop old route. */
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 710238f58aa9..e080fbbbc0e5 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1241,8 +1241,10 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
 
 	xt_free_table_info(oldinfo);
 	if (copy_to_user(counters_ptr, counters,
-			 sizeof(struct xt_counters) * num_counters) != 0)
-		ret = -EFAULT;
+			 sizeof(struct xt_counters) * num_counters) != 0) {
+		/* Silent error, can't fail, new table is already in place */
+		net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n");
+	}
 	vfree(counters);
 	xt_table_unlock(t);
 	return ret;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 827f795209cf..ae4a06be14df 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -3,38 +3,43 @@
  * not configured or static.  These functions are needed by GSO/GRO implementation.
  */
 #include <linux/export.h>
+#include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/addrconf.h>
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+/* This function exists only for tap drivers that must support broken
+ * clients requesting UFO without specifying an IPv6 fragment ID.
+ *
+ * This is similar to ipv6_select_ident() but we use an independent hash
+ * seed to limit information leakage.
+ *
+ * The network header must be set before calling this.
+ */
+void ipv6_proxy_select_ident(struct sk_buff *skb)
 {
-	static atomic_t ipv6_fragmentation_id;
-	int old, new;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (rt && !(rt->dst.flags & DST_NOPEER)) {
-		struct inet_peer *peer;
-		struct net *net;
-
-		net = dev_net(rt->dst.dev);
-		peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-		if (peer) {
-			fhdr->identification = htonl(inet_getid(peer, 0));
-			inet_putpeer(peer);
-			return;
-		}
-	}
-#endif
-	do {
-		old = atomic_read(&ipv6_fragmentation_id);
-		new = old + 1;
-		if (!new)
-			new = 1;
-	} while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old);
-	fhdr->identification = htonl(new);
+	static u32 ip6_proxy_idents_hashrnd __read_mostly;
+	struct in6_addr buf[2];
+	struct in6_addr *addrs;
+	u32 hash, id;
+
+	addrs = skb_header_pointer(skb,
+				   skb_network_offset(skb) +
+				   offsetof(struct ipv6hdr, saddr),
+				   sizeof(buf), buf);
+	if (!addrs)
+		return;
+
+	net_get_random_once(&ip6_proxy_idents_hashrnd,
+			    sizeof(ip6_proxy_idents_hashrnd));
+
+	hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd);
+	hash = __ipv6_addr_jhash(&addrs[0], hash);
+
+	id = ip_idents_reserve(hash, 1);
+	skb_shinfo(skb)->ip6_frag_id = htonl(id);
 }
-EXPORT_SYMBOL(ipv6_select_ident);
+EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 587bbdcb22b4..bda74291c3e0 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -182,8 +182,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			      MSG_DONTWAIT, np->dontfrag);
 
 	if (err) {
-		ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
-				   ICMP6_MIB_OUTERRORS);
+		ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
+				ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
 		err = icmpv6_push_pending_frames(sk, &fl6,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fba54a407bb2..7cc1102e298c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1342,7 +1342,7 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
 	if (mtu)
-		return mtu;
+		goto out;
 
 	mtu = IPV6_MIN_MTU;
 
@@ -1352,7 +1352,8 @@ static unsigned int ip6_mtu(const struct dst_entry *dst)
 		mtu = idev->cnf.mtu6;
 	rcu_read_unlock();
 
-	return mtu;
+out:
+	return min_t(unsigned int, mtu, IP6_MAX_MTU);
 }
 
 static struct dst_entry *icmp6_dst_gc_list;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index b4d74c86586c..317b6dbf3190 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -101,19 +101,19 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
 		if (remote == t->parms.iph.daddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
 	for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
 		if (local == t->parms.iph.saddr &&
-		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+		    (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
@@ -195,10 +195,8 @@ static int ipip6_tunnel_create(struct net_device *dev)
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 	int err;
 
-	err = ipip6_tunnel_init(dev);
-	if (err < 0)
-		goto out;
-	ipip6_tunnel_clone_6rd(dev, sitn);
+	memcpy(dev->dev_addr, &t->parms.iph.saddr, 4);
+	memcpy(dev->broadcast, &t->parms.iph.daddr, 4);
 
 	if ((__force u16)t->parms.i_flags & SIT_ISATAP)
 		dev->priv_flags |= IFF_ISATAP;
@@ -207,7 +205,8 @@ static int ipip6_tunnel_create(struct net_device *dev)
 	if (err < 0)
 		goto out;
 
-	strcpy(t->parms.name, dev->name);
+	ipip6_tunnel_clone_6rd(dev, sitn);
+
 	dev->rtnl_link_ops = &sit_link_ops;
 
 	dev_hold(dev);
@@ -560,12 +559,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
@@ -1321,6 +1320,7 @@ static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
 }
 
 static const struct net_device_ops ipip6_netdev_ops = {
+	.ndo_init	= ipip6_tunnel_init,
 	.ndo_uninit	= ipip6_tunnel_uninit,
 	.ndo_start_xmit	= sit_tunnel_xmit,
 	.ndo_do_ioctl	= ipip6_tunnel_ioctl,
@@ -1367,9 +1367,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
-
-	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
-	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
+	strcpy(tunnel->parms.name, dev->name);
 
 	ipip6_tunnel_bind_dev(dev);
 	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
@@ -1401,7 +1399,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
-	strcpy(tunnel->parms.name, dev->name);
 
 	iph->version		= 4;
 	iph->protocol		= IPPROTO_IPV6;
@@ -1850,4 +1847,5 @@ xfrm_tunnel_failed:
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 889079b2ea85..a4f890dd223a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1668,6 +1668,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific = {
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
 #endif
+	.mtu_reduced	   = tcp_v6_mtu_reduced,
 };
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1699,6 +1700,7 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
 	.compat_setsockopt = compat_ipv6_setsockopt,
 	.compat_getsockopt = compat_ipv6_getsockopt,
 #endif
+	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1935,7 +1937,6 @@ struct proto tcpv6_prot = {
 	.sendpage		= tcp_sendpage,
 	.backlog_rcv		= tcp_v6_do_rcv,
 	.release_cb		= tcp_release_cb,
-	.mtu_reduced		= tcp_v6_mtu_reduced,
 	.hash			= tcp_v6_hash,
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 0d78132ff18a..01b0ff9a0c2c 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 	if (NAPI_GRO_CB(skb)->flush)
 		goto skip_csum;
 
-	wsum = skb->csum;
+	wsum = NAPI_GRO_CB(skb)->csum;
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_NONE:
@@ -73,7 +73,7 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 
 	th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr,
 				  &iph->daddr, 0);
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
 
 	return tcp_gro_complete(skb);
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1e586d92260e..20b63d2ab70f 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -716,15 +716,15 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 				if (inet->inet_dport != rmt_port)
 					continue;
 			}
-			if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
-			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
+			if (!ipv6_addr_any(&s->sk_v6_daddr) &&
+			    !ipv6_addr_equal(&s->sk_v6_daddr, rmt_addr))
 				continue;
 
 			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
 				continue;
 
-			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-				if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
+			if (!ipv6_addr_any(&s->sk_v6_rcv_saddr)) {
+				if (!ipv6_addr_equal(&s->sk_v6_rcv_saddr, loc_addr))
 					continue;
 			}
 			if (!inet6_mc_check(s, loc_addr, rmt_addr))
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 00b2a6d1c009..d65aea21ce81 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1763,6 +1763,7 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	struct ipxhdr *ipx = NULL;
 	struct sk_buff *skb;
 	int copied, rc;
+	bool locked = true;
 
 	lock_sock(sk);
 	/* put the autobinding in */
@@ -1789,6 +1790,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sock_flag(sk, SOCK_ZAPPED))
 		goto out;
 
+	release_sock(sk);
+	locked = false;
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &rc);
 	if (!skb)
@@ -1822,7 +1825,8 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock,
 out_free:
 	skb_free_datagram(sk, skb);
 out:
-	release_sock(sk);
+	if (locked)
+		release_sock(sk);
 	return rc;
 }
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index c4b7218058b6..1465363a452b 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1829,7 +1829,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
 		spin_lock_irqsave(&list->lock, flags);
 
 		while (list_skb != (struct sk_buff *)list) {
-			if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
+			if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
 				this = list_skb;
 				break;
 			}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 5990919356a5..da8d067d6107 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -756,9 +756,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	session->deref = pppol2tp_session_sock_put;
 
 	/* If PMTU discovery was enabled, use the MTU that was discovered */
-	dst = sk_dst_get(sk);
+	dst = sk_dst_get(tunnel->sock);
 	if (dst != NULL) {
-		u32 pmtu = dst_mtu(__sk_dst_get(sk));
+		u32 pmtu = dst_mtu(dst);
+
 		if (pmtu != 0)
 			session->mtu = session->mru = pmtu -
 				PPPOL2TP_HEADER_OVERHEAD;
@@ -1368,7 +1369,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 	int err;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
@@ -1494,7 +1495,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname,
 	struct pppol2tp_session *ps;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (get_user(len, optlen))
 		return -EFAULT;
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index 7c7df475a401..f056f9ed97fb 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -54,6 +54,9 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 
 	memset(&aead_req, 0, sizeof(aead_req));
 
+	if (data_len == 0)
+		return -EINVAL;
+
 	sg_init_one(&pt, data, data_len);
 	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
 	sg_init_table(ct, 2);
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index ebf80f3abd83..653ce5d9e6e0 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read(
 	ssize_t ret = -EINVAL;
 
 	read_lock(&dev_base_lock);
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*format)(sdata, buf, sizeof(buf));
+	ret = (*format)(sdata, buf, sizeof(buf));
 	read_unlock(&dev_base_lock);
 
 	if (ret >= 0)
@@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write(
 
 	ret = -ENODEV;
 	rtnl_lock();
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*write)(sdata, buf, count);
+	ret = (*write)(sdata, buf, count);
 	rtnl_unlock();
 
 	return ret;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 2796a198728f..3f076b9c9308 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -815,7 +815,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	memset(&params, 0, sizeof(params));
 	memset(&csa_ie, 0, sizeof(csa_ie));
-	err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon,
+	err = ieee80211_parse_ch_switch_ie(sdata, elems,
 					   ifibss->chandef.chan->band,
 					   sta_flags, ifibss->bssid, &csa_ie);
 	/* can't switch to destination channel, fail */
@@ -1655,6 +1655,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	sdata->u.ibss.control_port = params->control_port;
 	sdata->u.ibss.userspace_handles_dfs = params->userspace_handles_dfs;
 	sdata->u.ibss.basic_rates = params->basic_rates;
+	sdata->u.ibss.last_scan_completed = jiffies;
 
 	/* fix basic_rates if channel does not support these rates */
 	rate_flags = ieee80211_chandef_rate_flags(&params->chandef);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 5e44e3179e02..bf7a1bbb975f 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -317,6 +317,7 @@ struct ieee80211_roc_work {
 
 	bool started, abort, hw_begun, notified;
 	bool to_be_freed;
+	bool on_channel;
 
 	unsigned long hw_start_time;
 
@@ -1385,6 +1386,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata,
 				  __le16 fc, bool acked);
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata);
 
 /* IBSS code */
@@ -1567,7 +1569,6 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
  * ieee80211_parse_ch_switch_ie - parses channel switch IEs
  * @sdata: the sdata of the interface which has received the frame
  * @elems: parsed 802.11 elements received with the frame
- * @beacon: indicates if the frame was a beacon or probe response
  * @current_band: indicates the current band
  * @sta_flags: contains information about own capabilities and restrictions
  *	to decide which channel switch announcements can be accepted. Only the
@@ -1581,7 +1582,7 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
  * Return: 0 on success, <0 on error and >0 if there is nothing to parse.
  */
 int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
-				 struct ieee802_11_elems *elems, bool beacon,
+				 struct ieee802_11_elems *elems,
 				 enum ieee80211_band current_band,
 				 u32 sta_flags, u8 *bssid,
 				 struct ieee80211_csa_ie *csa_ie);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index ce1c44370610..06f5de4e4fbb 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -760,10 +760,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	int i, flushed;
 	struct ps_data *ps;
 	struct cfg80211_chan_def chandef;
+	bool cancel_scan;
 
 	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
 
-	if (rcu_access_pointer(local->scan_sdata) == sdata)
+	cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata;
+	if (cancel_scan)
 		ieee80211_scan_cancel(local);
 
 	/*
@@ -973,6 +975,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_recalc_ps(local, -1);
 
+	if (cancel_scan)
+		flush_delayed_work(&local->scan_work);
+
 	if (local->open_count == 0) {
 		ieee80211_stop_device(local);
 
@@ -1761,7 +1766,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)
 	}
 	mutex_unlock(&local->iflist_mtx);
 	unregister_netdevice_many(&unreg_list);
-	list_del(&unreg_list);
 
 	list_for_each_entry_safe(sdata, tmp, &wdev_list, list) {
 		list_del(&sdata->list);
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 6ff65a1ebaa9..d78b37a5d951 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -652,7 +652,7 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 	int i;
 
 	mutex_lock(&local->key_mtx);
-	for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
+	for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) {
 		key = key_mtx_dereference(local, sta->gtk[i]);
 		if (!key)
 			continue;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index d767cfb9b45f..c7a7a86afdb8 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -148,6 +148,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local)
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 		if (!rcu_access_pointer(sdata->vif.chanctx_conf))
 			continue;
+		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+			continue;
 		power = min(power, sdata->vif.bss_conf.txpower);
 	}
 	rcu_read_unlock();
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 5b919cab1de0..3d52d1d68431 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -885,7 +885,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 
 	memset(&params, 0, sizeof(params));
 	memset(&csa_ie, 0, sizeof(csa_ie));
-	err = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, band,
+	err = ieee80211_parse_ch_switch_ie(sdata, elems, band,
 					   sta_flags, sdata->vif.addr,
 					   &csa_ie);
 	if (err < 0)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 245dce969b31..c9535a976b56 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1001,7 +1001,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 
 	current_band = cbss->channel->band;
 	memset(&csa_ie, 0, sizeof(csa_ie));
-	res = ieee80211_parse_ch_switch_ie(sdata, elems, beacon, current_band,
+	res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band,
 					   ifmgd->flags,
 					   ifmgd->associated->bssid, &csa_ie);
 	if (res	< 0)
@@ -1086,7 +1086,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		ieee80211_queue_work(&local->hw, &ifmgd->chswitch_work);
 	else
 		mod_timer(&ifmgd->chswitch_timer,
-			  TU_TO_EXP_TIME(csa_ie.count * cbss->beacon_interval));
+			  TU_TO_EXP_TIME((csa_ie.count - 1) *
+					 cbss->beacon_interval));
 }
 
 static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
@@ -2708,8 +2709,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 	bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems,
 					channel);
 	if (bss) {
-		ieee80211_rx_bss_put(local, bss);
 		sdata->vif.bss_conf.beacon_rate = bss->beacon_rate;
+		ieee80211_rx_bss_put(local, bss);
 	}
 }
 
@@ -3504,6 +3505,38 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata)
 }
 
 #ifdef CONFIG_PM
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
+
+	sdata_lock(sdata);
+
+	if (ifmgd->auth_data || ifmgd->assoc_data) {
+		const u8 *bssid = ifmgd->auth_data ?
+				ifmgd->auth_data->bss->bssid :
+				ifmgd->assoc_data->bss->bssid;
+
+		/*
+		 * If we are trying to authenticate / associate while suspending,
+		 * cfg80211 won't know and won't actually abort those attempts,
+		 * thus we need to do that ourselves.
+		 */
+		ieee80211_send_deauth_disassoc(sdata, bssid,
+					       IEEE80211_STYPE_DEAUTH,
+					       WLAN_REASON_DEAUTH_LEAVING,
+					       false, frame_buf);
+		if (ifmgd->assoc_data)
+			ieee80211_destroy_assoc_data(sdata, false);
+		if (ifmgd->auth_data)
+			ieee80211_destroy_auth_data(sdata, false);
+		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
+				      IEEE80211_DEAUTH_FRAME_LEN);
+	}
+
+	sdata_unlock(sdata);
+}
+
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -4208,8 +4241,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	rcu_read_unlock();
 
 	if (bss->wmm_used && bss->uapsd_supported &&
-	    (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) &&
-	    sdata->wmm_acm != 0xff) {
+	    (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) {
 		assoc_data->uapsd = true;
 		ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED;
 	} else {
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 0c2a29484c07..7a17decd27f9 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		container_of(work, struct ieee80211_roc_work, work.work);
 	struct ieee80211_sub_if_data *sdata = roc->sdata;
 	struct ieee80211_local *local = sdata->local;
-	bool started;
+	bool started, on_channel;
 
 	mutex_lock(&local->mtx);
 
@@ -354,13 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 	if (!roc->started) {
 		struct ieee80211_roc_work *dep;
 
-		/* start this ROC */
+		WARN_ON(local->use_chanctx);
+
+		/* If actually operating on the desired channel (with at least
+		 * 20 MHz channel width) don't stop all the operations but still
+		 * treat it as though the ROC operation started properly, so
+		 * other ROC operations won't interfere with this one.
+		 */
+		roc->on_channel = roc->chan == local->_oper_chandef.chan &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_10;
 
-		/* switch channel etc */
+		/* start this ROC */
 		ieee80211_recalc_idle(local);
 
-		local->tmp_channel = roc->chan;
-		ieee80211_hw_config(local, 0);
+		if (!roc->on_channel) {
+			ieee80211_offchannel_stop_vifs(local);
+
+			local->tmp_channel = roc->chan;
+			ieee80211_hw_config(local, 0);
+		}
 
 		/* tell userspace or send frame */
 		ieee80211_handle_roc_started(roc);
@@ -379,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work)
  finish:
 		list_del(&roc->list);
 		started = roc->started;
+		on_channel = roc->on_channel;
 		ieee80211_roc_notify_destroy(roc, !roc->abort);
 
-		if (started) {
+		if (started && !on_channel) {
 			ieee80211_flush_queues(local, NULL);
 
 			local->tmp_channel = NULL;
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index af64fb8e8add..d478b880a0af 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -100,10 +100,18 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 
 	/* remove all interfaces that were created in the driver */
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata) ||
-		    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-		    sdata->vif.type == NL80211_IFTYPE_MONITOR)
+		if (!ieee80211_sdata_running(sdata))
 			continue;
+		switch (sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+		case NL80211_IFTYPE_MONITOR:
+			continue;
+		case NL80211_IFTYPE_STATION:
+			ieee80211_mgd_quiesce(sdata);
+			break;
+		default:
+			break;
+		}
 
 		drv_remove_interface(local, sdata);
 	}
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 22b223f13c9f..74350c3863b8 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -462,7 +462,7 @@ static void rate_fixup_ratelist(struct ieee80211_vif *vif,
 	 */
 	if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) {
 		u32 basic_rates = vif->bss_conf.basic_rates;
-		s8 baserate = basic_rates ? ffs(basic_rates - 1) : 0;
+		s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0;
 
 		rate = &sband->bitrates[rates[0].idx];
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3e57f96c9666..1e4dc4ed5e0d 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1679,11 +1679,14 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	sc = le16_to_cpu(hdr->seq_ctrl);
 	frag = sc & IEEE80211_SCTL_FRAG;
 
-	if (likely((!ieee80211_has_morefrags(fc) && frag == 0) ||
-		   is_multicast_ether_addr(hdr->addr1))) {
-		/* not fragmented */
-		goto out;
+	if (is_multicast_ether_addr(hdr->addr1)) {
+		rx->local->dot11MulticastReceivedFrameCount++;
+		goto out_no_led;
 	}
+
+	if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
+		goto out;
+
 	I802_DEBUG_INC(rx->local->rx_handlers_fragments);
 
 	if (skb_linearize(rx->skb))
@@ -1774,12 +1777,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	status->rx_flags |= IEEE80211_RX_FRAGMENTED;
 
  out:
+	ieee80211_led_rx(rx->local);
+ out_no_led:
 	if (rx->sta)
 		rx->sta->rx_packets++;
-	if (is_multicast_ether_addr(hdr->addr1))
-		rx->local->dot11MulticastReceivedFrameCount++;
-	else
-		ieee80211_led_rx(rx->local);
 	return RX_CONTINUE;
 }
 
diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c
index 6ab009070084..efeba56c913b 100644
--- a/net/mac80211/spectmgmt.c
+++ b/net/mac80211/spectmgmt.c
@@ -22,7 +22,7 @@
 #include "wme.h"
 
 int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
-				 struct ieee802_11_elems *elems, bool beacon,
+				 struct ieee802_11_elems *elems,
 				 enum ieee80211_band current_band,
 				 u32 sta_flags, u8 *bssid,
 				 struct ieee80211_csa_ie *csa_ie)
@@ -91,19 +91,13 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
 		return -EINVAL;
 	}
 
-	if (!beacon && sec_chan_offs) {
+	if (sec_chan_offs) {
 		secondary_channel_offset = sec_chan_offs->sec_chan_offs;
-	} else if (beacon && ht_oper) {
-		secondary_channel_offset =
-			ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET;
 	} else if (!(sta_flags & IEEE80211_STA_DISABLE_HT)) {
-		/* If it's not a beacon, HT is enabled and the IE not present,
-		 * it's 20 MHz, 802.11-2012 8.5.2.6:
-		 *	This element [the Secondary Channel Offset Element] is
-		 *	present when switching to a 40 MHz channel. It may be
-		 *	present when switching to a 20 MHz channel (in which
-		 *	case the secondary channel offset is set to SCN).
-		 */
+		/* If the secondary channel offset IE is not present,
+		 * we can't know what's the post-CSA offset, so the
+		 * best we can do is use 20MHz.
+		*/
 		secondary_channel_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE;
 	}
 
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 137a192e64bc..bedaeecdab97 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -240,6 +240,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 4080c615636f..e5a7ac2f3687 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -414,6 +414,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx)
 	if (ieee80211_has_order(hdr->frame_control))
 		return TX_CONTINUE;
 
+	if (ieee80211_is_probe_req(hdr->frame_control))
+		return TX_CONTINUE;
+
 	if (tx->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)
 		info->hw_queue = tx->sdata->vif.cab_queue;
 
@@ -464,6 +467,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 {
 	struct sta_info *sta = tx->sta;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
 	struct ieee80211_local *local = tx->local;
 
 	if (unlikely(!sta))
@@ -474,6 +478,15 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		     !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) {
 		int ac = skb_get_queue_mapping(tx->skb);
 
+		/* only deauth, disassoc and action are bufferable MMPDUs */
+		if (ieee80211_is_mgmt(hdr->frame_control) &&
+		    !ieee80211_is_deauth(hdr->frame_control) &&
+		    !ieee80211_is_disassoc(hdr->frame_control) &&
+		    !ieee80211_is_action(hdr->frame_control)) {
+			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
+			return TX_CONTINUE;
+		}
+
 		ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n",
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
@@ -532,22 +545,8 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 static ieee80211_tx_result debug_noinline
 ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
-
 	if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
 		return TX_CONTINUE;
-
-	/* only deauth, disassoc and action are bufferable MMPDUs */
-	if (ieee80211_is_mgmt(hdr->frame_control) &&
-	    !ieee80211_is_deauth(hdr->frame_control) &&
-	    !ieee80211_is_disassoc(hdr->frame_control) &&
-	    !ieee80211_is_action(hdr->frame_control)) {
-		if (tx->flags & IEEE80211_TX_UNICAST)
-			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
-		return TX_CONTINUE;
-	}
-
 	if (tx->flags & IEEE80211_TX_UNICAST)
 		return ieee80211_tx_h_unicast_ps_buf(tx);
 	else
@@ -2909,7 +2908,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 				cpu_to_le16(IEEE80211_FCTL_MOREDATA);
 		}
 
-		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+		if (sdata->vif.type == NL80211_IFTYPE_AP)
 			sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
 		if (!ieee80211_tx_prepare(sdata, &tx, skb))
 			break;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index b8700d417a9c..642762518213 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1754,7 +1754,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	mutex_unlock(&local->mtx);
 
 	if (sched_scan_stopped)
-		cfg80211_sched_scan_stopped(local->hw.wiphy);
+		cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
 
 	/*
 	 * If this is for hw restart things are still running.
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index de770ec39e51..cf9937743abb 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -636,7 +636,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index)
 	struct ip_set *set;
 	struct ip_set_net *inst = ip_set_pernet(net);
 
-	if (index > inst->ip_set_max)
+	if (index >= inst->ip_set_max)
 		return IPSET_INVALID_ID;
 
 	nfnl_lock(NFNL_SUBSYS_IPSET);
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a8eb0a89326a..610e19c0e13f 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data)
 			ip_vs_control_del(cp);
 
 		if (cp->flags & IP_VS_CONN_F_NFCT) {
-			ip_vs_conn_drop_conntrack(cp);
 			/* Do not access conntracks during subsys cleanup
 			 * because nf_conntrack_find_get can not be used after
 			 * conntrack cleanup for the net.
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 4f26ee46b51f..27d3f40de3cd 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1392,15 +1392,19 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 
 	if (ipip) {
 		__be32 info = ic->un.gateway;
+		__u8 type = ic->type;
+		__u8 code = ic->code;
 
 		/* Update the MTU */
 		if (ic->type == ICMP_DEST_UNREACH &&
 		    ic->code == ICMP_FRAG_NEEDED) {
 			struct ip_vs_dest *dest = cp->dest;
 			u32 mtu = ntohs(ic->un.frag.mtu);
+			__be16 frag_off = cih->frag_off;
 
 			/* Strip outer IP and ICMP, go to IPIP header */
-			__skb_pull(skb, ihl + sizeof(_icmph));
+			if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
+				goto ignore_ipip;
 			offset2 -= ihl + sizeof(_icmph);
 			skb_reset_network_header(skb);
 			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
@@ -1408,7 +1412,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 			ipv4_update_pmtu(skb, dev_net(skb->dev),
 					 mtu, 0, 0, 0, 0);
 			/* Client uses PMTUD? */
-			if (!(cih->frag_off & htons(IP_DF)))
+			if (!(frag_off & htons(IP_DF)))
 				goto ignore_ipip;
 			/* Prefer the resulting PMTU */
 			if (dest) {
@@ -1427,12 +1431,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
 		/* Strip outer IP, ICMP and IPIP, go to IP header of
 		 * original request.
 		 */
-		__skb_pull(skb, offset2);
+		if (pskb_pull(skb, offset2) == NULL)
+			goto ignore_ipip;
 		skb_reset_network_header(skb);
 		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
 			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
-			ic->type, ic->code, ntohl(info));
-		icmp_send(skb, ic->type, ic->code, info);
+			type, code, ntohl(info));
+		icmp_send(skb, type, code, info);
 		/* ICMP can be shorter but anyways, account it */
 		ip_vs_out_stats(cp, skb);
 
@@ -1901,7 +1906,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 	{
 		.hook		= ip_vs_local_reply6,
 		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
+		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_OUT,
 		.priority	= NF_IP6_PRI_NAT_DST + 1,
 	},
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c47444e4cf8c..1692e7534759 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->daddr		=	cp->daddr.ip;
 	iph->saddr		=	saddr;
 	iph->ttl		=	old_iph->ttl;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
 	skb->local_df = 1;
@@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->nexthdr		=	IPPROTO_IPV6;
 	iph->payload_len	=	old_iph->payload_len;
 	be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
-	iph->priority		=	old_iph->priority;
 	memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
+	ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph));
 	iph->daddr = cp->daddr.in6;
 	iph->saddr = saddr;
 	iph->hop_limit		=	old_iph->hop_limit;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 52ca952b802c..23247a0d2b69 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -517,6 +517,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 	return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (nf_nat_proto_remove(ct, data))
+		return 1;
+
+	if (!nat || !nat->ct)
+		return 0;
+
+	/* This netns is being destroyed, and conntrack has nat null binding.
+	 * Remove it from bysource hash, as the table will be freed soon.
+	 *
+	 * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+	 * will delete entry from already-freed table.
+	 */
+	if (!del_timer(&ct->timeout))
+		return 1;
+
+	spin_lock_bh(&nf_nat_lock);
+	hlist_del_rcu(&nat->bysource);
+	ct->status &= ~IPS_NAT_DONE_MASK;
+	nat->ct = NULL;
+	spin_unlock_bh(&nf_nat_lock);
+
+	add_timer(&ct->timeout);
+
+	/* don't delete conntrack.  Although that would make things a lot
+	 * simpler, we'd end up flushing all conntracks on nat rmmod.
+	 */
+	return 0;
+}
+
 static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
 {
 	struct nf_nat_proto_clean clean = {
@@ -787,7 +820,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	struct nf_nat_proto_clean clean = {};
 
-	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0);
+	nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index adce01e8bb57..c68e5e0628df 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1934,7 +1934,8 @@ static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const
 
 static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
 	[NFTA_SET_TABLE]		= { .type = NLA_STRING },
-	[NFTA_SET_NAME]			= { .type = NLA_STRING },
+	[NFTA_SET_NAME]			= { .type = NLA_STRING,
+					    .len = IFNAMSIZ - 1 },
 	[NFTA_SET_FLAGS]		= { .type = NLA_U32 },
 	[NFTA_SET_KEY_TYPE]		= { .type = NLA_U32 },
 	[NFTA_SET_KEY_LEN]		= { .type = NLA_U32 },
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 90998a6ff8b9..804105391b9a 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -25,9 +25,8 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 			      struct nft_data data[NFT_REG_MAX + 1])
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
-	u32 mask;
+	u32 mask = nft_cmp_fast_mask(priv->len);
 
-	mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - priv->len);
 	if ((data[priv->sreg].data[0] & mask) == priv->data)
 		return;
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 046aa13b4fea..bf8a108b46e2 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -248,15 +248,15 @@ replay:
 #endif
 		{
 			nfnl_unlock(subsys_id);
-			kfree_skb(nskb);
-			return netlink_ack(skb, nlh, -EOPNOTSUPP);
+			netlink_ack(skb, nlh, -EOPNOTSUPP);
+			return kfree_skb(nskb);
 		}
 	}
 
 	if (!ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
-		kfree_skb(nskb);
-		return netlink_ack(skb, nlh, -EOPNOTSUPP);
+		netlink_ack(skb, nlh, -EOPNOTSUPP);
+		return kfree_skb(skb);
 	}
 
 	while (skb->len >= nlmsg_total_size(0)) {
@@ -367,7 +367,7 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 	    skb->len < nlh->nlmsg_len)
 		return;
 
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN)) {
 		netlink_ack(skb, nlh, -EPERM);
 		return;
 	}
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index a155d19a225e..6ff12a191400 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -45,7 +45,8 @@
 #define NFULNL_NLBUFSIZ_DEFAULT	NLMSG_GOODSIZE
 #define NFULNL_TIMEOUT_DEFAULT 	100	/* every second */
 #define NFULNL_QTHRESH_DEFAULT 	100	/* 100 packets */
-#define NFULNL_COPY_RANGE_MAX	0xFFFF	/* max packet size is limited by 16-bit struct nfattr nfa_len field */
+/* max packet size is limited by 16-bit struct nfattr nfa_len field */
+#define NFULNL_COPY_RANGE_MAX	(0xFFFF - NLA_HDRLEN)
 
 #define PRINTR(x, args...)	do { if (net_ratelimit()) \
 				     printk(x, ## args); } while (0);
@@ -255,6 +256,8 @@ nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode,
 
 	case NFULNL_COPY_PACKET:
 		inst->copy_mode = mode;
+		if (range == 0)
+			range = NFULNL_COPY_RANGE_MAX;
 		inst->copy_range = min_t(unsigned int,
 					 range, NFULNL_COPY_RANGE_MAX);
 		break;
@@ -346,26 +349,25 @@ nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size,
 	return skb;
 }
 
-static int
+static void
 __nfulnl_send(struct nfulnl_instance *inst)
 {
-	int status = -1;
-
 	if (inst->qlen > 1) {
 		struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0,
 						 NLMSG_DONE,
 						 sizeof(struct nfgenmsg),
 						 0);
-		if (!nlh)
+		if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n",
+			      inst->skb->len, skb_tailroom(inst->skb))) {
+			kfree_skb(inst->skb);
 			goto out;
+		}
 	}
-	status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
-				   MSG_DONTWAIT);
-
+	nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
+			  MSG_DONTWAIT);
+out:
 	inst->qlen = 0;
 	inst->skb = NULL;
-out:
-	return status;
 }
 
 static void
@@ -652,7 +654,8 @@ nfulnl_log_packet(struct net *net,
 		+ nla_total_size(sizeof(u_int32_t))	/* gid */
 		+ nla_total_size(plen)			/* prefix */
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_hw))
-		+ nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp));
+		+ nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp))
+		+ nla_total_size(sizeof(struct nfgenmsg));	/* NLMSG_DONE */
 
 	if (in && skb_mac_header_was_set(skb)) {
 		size +=   nla_total_size(skb->dev->hard_header_len)
@@ -681,8 +684,7 @@ nfulnl_log_packet(struct net *net,
 		break;
 
 	case NFULNL_COPY_PACKET:
-		if (inst->copy_range == 0
-		    || inst->copy_range > skb->len)
+		if (inst->copy_range > skb->len)
 			data_len = skb->len;
 		else
 			data_len = inst->copy_range;
@@ -695,8 +697,7 @@ nfulnl_log_packet(struct net *net,
 		goto unlock_and_release;
 	}
 
-	if (inst->skb &&
-	    size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) {
+	if (inst->skb && size > skb_tailroom(inst->skb)) {
 		/* either the queue len is too high or we don't have
 		 * enough room in the skb left. flush to userspace. */
 		__nfulnl_flush(inst);
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 954925db414d..e2b3f51c81f1 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -128,7 +128,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 	BUG_ON(err < 0);
 	desc.len *= BITS_PER_BYTE;
 
-	mask = ~0U >> (sizeof(priv->data) * BITS_PER_BYTE - desc.len);
+	mask = nft_cmp_fast_mask(desc.len);
 	priv->data = data.data[0] & mask;
 	priv->len  = desc.len;
 	return 0;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 82cb8236f8a1..ad979612238a 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -678,7 +678,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	family = ctx->afi->family;
 
 	/* Re-use the existing target if it's already loaded. */
-	list_for_each_entry(nft_target, &nft_match_list, head) {
+	list_for_each_entry(nft_target, &nft_target_list, head) {
 		struct xt_target *target = nft_target->ops.data;
 
 		if (strcmp(target->name, tg_name) == 0 &&
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index 9a8e77e7f8d4..ef5c75a5b200 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -31,7 +31,7 @@ static int cgroup_mt_check(const struct xt_mtchk_param *par)
 	if (info->invert & ~1)
 		return -EINVAL;
 
-	return info->id ? 0 : -EINVAL;
+	return 0;
 }
 
 static bool
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index a3910fc2122b..47dc6836830a 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -104,7 +104,7 @@ struct xt_hashlimit_htable {
 	spinlock_t lock;		/* lock for list_head */
 	u_int32_t rnd;			/* random seed for hash */
 	unsigned int count;		/* number entries in table */
-	struct timer_list timer;	/* timer for gc */
+	struct delayed_work gc_work;
 
 	/* seq_file stuff */
 	struct proc_dir_entry *pde;
@@ -213,7 +213,7 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent)
 	call_rcu_bh(&ent->rcu, dsthash_free_rcu);
 	ht->count--;
 }
-static void htable_gc(unsigned long htlong);
+static void htable_gc(struct work_struct *work);
 
 static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo,
 			 u_int8_t family)
@@ -273,9 +273,9 @@ static int htable_create(struct net *net, struct xt_hashlimit_mtinfo1 *minfo,
 	}
 	hinfo->net = net;
 
-	setup_timer(&hinfo->timer, htable_gc, (unsigned long)hinfo);
-	hinfo->timer.expires = jiffies + msecs_to_jiffies(hinfo->cfg.gc_interval);
-	add_timer(&hinfo->timer);
+	INIT_DEFERRABLE_WORK(&hinfo->gc_work, htable_gc);
+	queue_delayed_work(system_power_efficient_wq, &hinfo->gc_work,
+			   msecs_to_jiffies(hinfo->cfg.gc_interval));
 
 	hlist_add_head(&hinfo->node, &hashlimit_net->htables);
 
@@ -300,29 +300,30 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht,
 {
 	unsigned int i;
 
-	/* lock hash table and iterate over it */
-	spin_lock_bh(&ht->lock);
 	for (i = 0; i < ht->cfg.size; i++) {
 		struct dsthash_ent *dh;
 		struct hlist_node *n;
+
+		spin_lock_bh(&ht->lock);
 		hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) {
 			if ((*select)(ht, dh))
 				dsthash_free(ht, dh);
 		}
+		spin_unlock_bh(&ht->lock);
+		cond_resched();
 	}
-	spin_unlock_bh(&ht->lock);
 }
 
-/* hash table garbage collector, run by timer */
-static void htable_gc(unsigned long htlong)
+static void htable_gc(struct work_struct *work)
 {
-	struct xt_hashlimit_htable *ht = (struct xt_hashlimit_htable *)htlong;
+	struct xt_hashlimit_htable *ht;
+
+	ht = container_of(work, struct xt_hashlimit_htable, gc_work.work);
 
 	htable_selective_cleanup(ht, select_gc);
 
-	/* re-add the timer accordingly */
-	ht->timer.expires = jiffies + msecs_to_jiffies(ht->cfg.gc_interval);
-	add_timer(&ht->timer);
+	queue_delayed_work(system_power_efficient_wq,
+			   &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval));
 }
 
 static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo)
@@ -341,7 +342,7 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo)
 
 static void htable_destroy(struct xt_hashlimit_htable *hinfo)
 {
-	del_timer_sync(&hinfo->timer);
+	cancel_delayed_work_sync(&hinfo->gc_work);
 	htable_remove_proc_entry(hinfo);
 	htable_selective_cleanup(hinfo, select_all);
 	kfree(hinfo->name);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 04748ab649c2..7c177bc43806 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -205,7 +205,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 		nskb->protocol = htons((u16) sk->sk_protocol);
 		nskb->pkt_type = netlink_is_kernel(sk) ?
 				 PACKET_KERNEL : PACKET_USER;
-
+		skb_reset_network_header(nskb);
 		ret = dev_queue_xmit(nskb);
 		if (unlikely(ret > 0))
 			ret = net_xmit_errno(ret);
@@ -636,7 +636,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
 		while (nlk->cb_running && netlink_dump_space(nlk)) {
 			err = netlink_dump(sk);
 			if (err < 0) {
-				sk->sk_err = err;
+				sk->sk_err = -err;
 				sk->sk_error_report(sk);
 				break;
 			}
@@ -707,7 +707,7 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 	 * after validation, the socket and the ring may only be used by a
 	 * single process, otherwise we fall back to copying.
 	 */
-	if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 ||
+	if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 ||
 	    atomic_read(&nlk->mapped) > 1)
 		excl = false;
 
@@ -1360,7 +1360,74 @@ retry:
 	return err;
 }
 
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			struct user_namespace *user_ns, int cap)
+{
+	return ((nsp->flags & NETLINK_SKB_DST) ||
+		file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *user_ns, int cap)
+{
+	return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
 {
 	return (nl_table[sock->sk->sk_protocol].flags & flag) ||
 		ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1428,7 +1495,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 
 	/* Only superuser is allowed to listen multicasts */
 	if (nladdr->nl_groups) {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
@@ -1490,7 +1557,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	if ((nladdr->nl_groups || nladdr->nl_pid) &&
-	    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
@@ -2096,7 +2163,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
@@ -2228,6 +2295,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2247,8 +2315,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		dst_group = ffs(addr->nl_groups);
 		err =  -EPERM;
 		if ((dst_group || dst_portid) &&
-		    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
+		netlink_skb_flags |= NETLINK_SKB_DST;
 	} else {
 		dst_portid = nlk->dst_portid;
 		dst_group = nlk->dst_group;
@@ -2278,6 +2347,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
 	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
@@ -2378,7 +2448,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
-			sk->sk_err = ret;
+			sk->sk_err = -ret;
 			sk->sk_error_report(sk);
 		}
 	}
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index b1dcdb932a86..a3ba3ca0ff92 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -561,7 +561,7 @@ static int genl_family_rcv_msg(struct genl_family *family,
 		return -EOPNOTSUPP;
 
 	if ((ops->flags & GENL_ADMIN_PERM) &&
-	    !capable(CAP_NET_ADMIN))
+	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) {
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 2c77e7b1a913..600c7646b3d3 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -42,6 +42,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 static int make_writable(struct sk_buff *skb, int write_len)
 {
+	if (!pskb_may_pull(skb, write_len))
+		return -ENOMEM;
+
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
 
@@ -70,6 +73,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 
 	vlan_set_encap_proto(skb, vhdr);
 	skb->mac_header += VLAN_HLEN;
+	if (skb_network_offset(skb) < ETH_HLEN)
+		skb_set_network_header(skb, ETH_HLEN);
 	skb_reset_mac_len(skb);
 
 	return 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 48a6a93db296..48b181797d7b 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -635,6 +635,7 @@ static void init_prb_bdqc(struct packet_sock *po,
 	p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
 	p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
 
+	p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
 	prb_init_ft_ops(p1, req_u);
 	prb_setup_retire_blk_timer(po, tx_ring);
 	prb_open_block(p1, pbd);
@@ -1946,6 +1947,18 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 			if ((int)snaplen < 0)
 				snaplen = 0;
 		}
+	} else if (unlikely(macoff + snaplen >
+			    GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
+		u32 nval;
+
+		nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff;
+		pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n",
+			    snaplen, nval, macoff);
+		snaplen = nval;
+		if (unlikely((int)snaplen < 0)) {
+			snaplen = 0;
+			macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+		}
 	}
 	spin_lock(&sk->sk_receive_queue.lock);
 	h.raw = packet_current_rx_frame(po, skb,
@@ -3779,6 +3792,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		if (unlikely(req->tp_block_size & (PAGE_SIZE - 1)))
 			goto out;
+		if (po->tp_version >= TPACKET_V3 &&
+		    (int)(req->tp_block_size -
+			  BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
 			goto out;
diff --git a/net/packet/diag.c b/net/packet/diag.c
index 533ce4ff108a..92f2c7107eec 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -128,6 +128,7 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb)
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			struct packet_diag_req *req,
+			bool may_report_filterinfo,
 			struct user_namespace *user_ns,
 			u32 portid, u32 seq, u32 flags, int sk_ino)
 {
@@ -172,7 +173,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 		goto out_nlmsg_trim;
 
 	if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
-	    sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER))
+	    sock_diag_put_filterinfo(may_report_filterinfo, sk, skb,
+				     PACKET_DIAG_FILTER))
 		goto out_nlmsg_trim;
 
 	return nlmsg_end(skb, nlh);
@@ -188,9 +190,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	struct packet_diag_req *req;
 	struct net *net;
 	struct sock *sk;
+	bool may_report_filterinfo;
 
 	net = sock_net(skb->sk);
 	req = nlmsg_data(cb->nlh);
+	may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
 
 	mutex_lock(&net->packet.sklist_lock);
 	sk_for_each(sk, &net->packet.sklist) {
@@ -200,6 +204,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 			goto next;
 
 		if (sk_diag_fill(sk, skb, req,
+				 may_report_filterinfo,
 				 sk_user_ns(NETLINK_CB(cb->skb).sk),
 				 NETLINK_CB(cb->skb).portid,
 				 cb->nlh->nlmsg_seq, NLM_F_MULTI,
diff --git a/net/packet/internal.h b/net/packet/internal.h
index eb9580a6b25f..cdddf6a30399 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -29,6 +29,7 @@ struct tpacket_kbdq_core {
 	char		*pkblk_start;
 	char		*pkblk_end;
 	int		kblk_size;
+	unsigned int	max_frame_len;
 	unsigned int	knum_blocks;
 	uint64_t	knxt_seq_num;
 	char		*prev;
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index dc15f4300808..b64151ade6b3 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 	u8 pnaddr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();
@@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	int err;
 	u8 dst;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();
diff --git a/net/rds/iw.c b/net/rds/iw.c
index 7826d46baa70..589935661d66 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support IB devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_RNIC)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 72bdc7166345..3b2265523552 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -908,7 +908,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
 	int ret = 0, ovr = 0;
 
-	if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 29a30a14c315..bdbdb1a7920a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -134,7 +134,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	int err;
 	int tp_created = 0;
 
-	if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index eed8404443d8..f435a88d899a 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -188,6 +188,12 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
 	[TCA_TCINDEX_CLASSID]		= { .type = NLA_U32 },
 };
 
+static void tcindex_filter_result_init(struct tcindex_filter_result *r)
+{
+	memset(r, 0, sizeof(*r));
+	tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+}
+
 static int
 tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  u32 handle, struct tcindex_data *p,
@@ -207,15 +213,11 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		return err;
 
 	memcpy(&cp, p, sizeof(cp));
-	memset(&new_filter_result, 0, sizeof(new_filter_result));
-	tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+	tcindex_filter_result_init(&new_filter_result);
 
+	tcindex_filter_result_init(&cr);
 	if (old_r)
-		memcpy(&cr, r, sizeof(cr));
-	else {
-		memset(&cr, 0, sizeof(cr));
-		tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-	}
+		cr.res = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -267,9 +269,14 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	err = -ENOMEM;
 	if (!cp.perfect && !cp.h) {
 		if (valid_perfect_hash(&cp)) {
+			int i;
+
 			cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL);
 			if (!cp.perfect)
 				goto errout;
+			for (i = 0; i < cp.hash; i++)
+				tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT,
+					      TCA_TCINDEX_POLICE);
 			balloc = 1;
 		} else {
 			cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL);
@@ -295,14 +302,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	tcf_exts_change(tp, &cr.exts, &e);
+	if (old_r)
+		tcf_exts_change(tp, &r->exts, &e);
+	else
+		tcf_exts_change(tp, &cr.exts, &e);
 
 	tcf_tree_lock(tp);
 	if (old_r && old_r != r)
-		memset(old_r, 0, sizeof(*old_r));
+		tcindex_filter_result_init(old_r);
 
 	memcpy(p, &cp, sizeof(cp));
-	memcpy(r, &cr, sizeof(cr));
+	r->res = cr.res;
 
 	if (r == &new_filter_result) {
 		struct tcindex_filter **fp;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index a07d55e75698..98532cfa7823 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1084,7 +1084,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *p = NULL;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1151,7 +1151,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *q, *p;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -1491,7 +1491,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 qid;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 647680b1c625..039977830783 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -553,11 +553,6 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	if (err < 0)
 		return err;
 
-	sch_tree_lock(sch);
-
-	if (tb[TCA_HHF_BACKLOG_LIMIT])
-		sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]);
-
 	if (tb[TCA_HHF_QUANTUM])
 		new_quantum = nla_get_u32(tb[TCA_HHF_QUANTUM]);
 
@@ -567,6 +562,12 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt)
 	non_hh_quantum = (u64)new_quantum * new_hhf_non_hh_weight;
 	if (non_hh_quantum > INT_MAX)
 		return -EINVAL;
+
+	sch_tree_lock(sch);
+
+	if (tb[TCA_HHF_BACKLOG_LIMIT])
+		sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]);
+
 	q->quantum = new_quantum;
 	q->hhf_non_hh_weight = new_hhf_non_hh_weight;
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index ee13d28d39d1..d477d476714d 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -330,7 +330,7 @@ void sctp_association_free(struct sctp_association *asoc)
 	/* Only real associations count against the endpoint, so
 	 * don't bother for if this is a temporary association.
 	 */
-	if (!asoc->temp) {
+	if (!list_empty(&asoc->asocs)) {
 		list_del(&asoc->asocs);
 
 		/* Decrement the backlog value for a TCP-style listening
@@ -1151,6 +1151,7 @@ void sctp_assoc_update(struct sctp_association *asoc,
 	asoc->c = new->c;
 	asoc->peer.rwnd = new->peer.rwnd;
 	asoc->peer.sack_needed = new->peer.sack_needed;
+	asoc->peer.auth_capable = new->peer.auth_capable;
 	asoc->peer.i = new->peer.i;
 	sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
 			 asoc->peer.i.initial_tsn, GFP_ATOMIC);
@@ -1396,35 +1397,44 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc)
 	return false;
 }
 
-/* Update asoc's rwnd for the approximated state in the buffer,
- * and check whether SACK needs to be sent.
- */
-void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
+/* Increase asoc's rwnd by len and send any window update SACK if needed. */
+void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
 {
-	int rx_count;
 	struct sctp_chunk *sack;
 	struct timer_list *timer;
 
-	if (asoc->ep->rcvbuf_policy)
-		rx_count = atomic_read(&asoc->rmem_alloc);
-	else
-		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+	if (asoc->rwnd_over) {
+		if (asoc->rwnd_over >= len) {
+			asoc->rwnd_over -= len;
+		} else {
+			asoc->rwnd += (len - asoc->rwnd_over);
+			asoc->rwnd_over = 0;
+		}
+	} else {
+		asoc->rwnd += len;
+	}
 
-	if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
-		asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
-	else
-		asoc->rwnd = 0;
+	/* If we had window pressure, start recovering it
+	 * once our rwnd had reached the accumulated pressure
+	 * threshold.  The idea is to recover slowly, but up
+	 * to the initial advertised window.
+	 */
+	if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
+		int change = min(asoc->pathmtu, asoc->rwnd_press);
+		asoc->rwnd += change;
+		asoc->rwnd_press -= change;
+	}
 
-	pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n",
-		 __func__, asoc, asoc->rwnd, rx_count,
-		 asoc->base.sk->sk_rcvbuf);
+	pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n",
+		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
+		 asoc->a_rwnd);
 
 	/* Send a window update SACK if the rwnd has increased by at least the
 	 * minimum of the association's PMTU and half of the receive buffer.
 	 * The algorithm used is similar to the one described in
 	 * Section 4.2.3.3 of RFC 1122.
 	 */
-	if (update_peer && sctp_peer_needs_update(asoc)) {
+	if (sctp_peer_needs_update(asoc)) {
 		asoc->a_rwnd = asoc->rwnd;
 
 		pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u "
@@ -1446,6 +1456,45 @@ void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
 	}
 }
 
+/* Decrease asoc's rwnd by len. */
+void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
+{
+	int rx_count;
+	int over = 0;
+
+	if (unlikely(!asoc->rwnd || asoc->rwnd_over))
+		pr_debug("%s: association:%p has asoc->rwnd:%u, "
+			 "asoc->rwnd_over:%u!\n", __func__, asoc,
+			 asoc->rwnd, asoc->rwnd_over);
+
+	if (asoc->ep->rcvbuf_policy)
+		rx_count = atomic_read(&asoc->rmem_alloc);
+	else
+		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+
+	/* If we've reached or overflowed our receive buffer, announce
+	 * a 0 rwnd if rwnd would still be positive.  Store the
+	 * the potential pressure overflow so that the window can be restored
+	 * back to original value.
+	 */
+	if (rx_count >= asoc->base.sk->sk_rcvbuf)
+		over = 1;
+
+	if (asoc->rwnd >= len) {
+		asoc->rwnd -= len;
+		if (over) {
+			asoc->rwnd_press += asoc->rwnd;
+			asoc->rwnd = 0;
+		}
+	} else {
+		asoc->rwnd_over = len - asoc->rwnd;
+		asoc->rwnd = 0;
+	}
+
+	pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n",
+		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
+		 asoc->rwnd_press);
+}
 
 /* Build the bind address list for the association based on info from the
  * local endpoint and the remote peer.
@@ -1578,6 +1627,8 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 	 * ack chunk whose serial number matches that of the request.
 	 */
 	list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) {
+		if (sctp_chunk_pending(ack))
+			continue;
 		if (ack->subh.addip_hdr->serial == serial) {
 			sctp_chunk_hold(ack);
 			return ack;
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 683c7d1b1306..fb7976aee61c 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -386,14 +386,13 @@ nomem:
  */
 int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
 {
-	struct net *net = sock_net(asoc->base.sk);
 	struct sctp_auth_bytes	*secret;
 	struct sctp_shared_key *ep_key;
 
 	/* If we don't support AUTH, or peer is not capable
 	 * we don't need to do anything.
 	 */
-	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+	if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
 		return 0;
 
 	/* If the key_id is non-zero and we couldn't find an
@@ -440,16 +439,16 @@ struct sctp_shared_key *sctp_auth_get_shkey(
  */
 int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
 {
-	struct net *net = sock_net(ep->base.sk);
 	struct crypto_hash *tfm = NULL;
 	__u16   id;
 
-	/* if the transforms are already allocted, we are done */
-	if (!net->sctp.auth_enable) {
+	/* If AUTH extension is disabled, we are done */
+	if (!ep->auth_enable) {
 		ep->auth_hmacs = NULL;
 		return 0;
 	}
 
+	/* If the transforms are already allocated, we are done */
 	if (ep->auth_hmacs)
 		return 0;
 
@@ -665,12 +664,10 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param)
 /* Check if peer requested that this chunk is authenticated */
 int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 {
-	struct net  *net;
 	if (!asoc)
 		return 0;
 
-	net = sock_net(asoc->base.sk);
-	if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+	if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
 		return 0;
 
 	return __sctp_auth_cid(chunk, asoc->peer.peer_chunks);
@@ -679,12 +676,10 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 /* Check if we requested that peer authenticate this chunk. */
 int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
 {
-	struct net *net;
 	if (!asoc)
 		return 0;
 
-	net = sock_net(asoc->base.sk);
-	if (!net->sctp.auth_enable)
+	if (!asoc->ep->auth_enable)
 		return 0;
 
 	return __sctp_auth_cid(chunk,
@@ -867,8 +862,6 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
 		list_add(&cur_key->key_list, sh_keys);
 
 	cur_key->key = key;
-	sctp_auth_key_hold(key);
-
 	return 0;
 nomem:
 	if (!replace)
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 8e5fdea05216..3d9f429858dc 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -68,7 +68,8 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 	if (!ep->digest)
 		return NULL;
 
-	if (net->sctp.auth_enable) {
+	ep->auth_enable = net->sctp.auth_enable;
+	if (ep->auth_enable) {
 		/* Allocate space for HMACS and CHUNKS authentication
 		 * variables.  There are arrays that we encode directly
 		 * into parameters to make the rest of the operations easier.
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 4de12afa13d4..7e8a16c77039 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -140,18 +140,9 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 		} else {
 			/* Nothing to do. Next chunk in the packet, please. */
 			ch = (sctp_chunkhdr_t *) chunk->chunk_end;
-
 			/* Force chunk->skb->data to chunk->chunk_end.  */
-			skb_pull(chunk->skb,
-				 chunk->chunk_end - chunk->skb->data);
-
-			/* Verify that we have at least chunk headers
-			 * worth of buffer left.
-			 */
-			if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) {
-				sctp_chunk_free(chunk);
-				chunk = queue->in_progress = NULL;
-			}
+			skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data);
+			/* We are guaranteed to pull a SCTP header. */
 		}
 	}
 
@@ -187,24 +178,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 	skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
 	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
 
-	if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) {
+	if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) <
+	    skb_tail_pointer(chunk->skb)) {
 		/* This is not a singleton */
 		chunk->singleton = 0;
 	} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
-		/* RFC 2960, Section 6.10  Bundling
-		 *
-		 * Partial chunks MUST NOT be placed in an SCTP packet.
-		 * If the receiver detects a partial chunk, it MUST drop
-		 * the chunk.
-		 *
-		 * Since the end of the chunk is past the end of our buffer
-		 * (which contains the whole packet, we can freely discard
-		 * the whole packet.
-		 */
-		sctp_chunk_free(chunk);
-		chunk = queue->in_progress = NULL;
-
-		return NULL;
+		/* Discard inside state machine. */
+		chunk->pdiscard = 1;
+		chunk->chunk_end = skb_tail_pointer(chunk->skb);
 	} else {
 		/* We are at the end of the packet, so mark the chunk
 		 * in case we need to send a SACK.
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 0f4d15fc2627..740ca5f7add0 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -401,12 +401,12 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	sk = chunk->skb->sk;
 
 	/* Allocate the new skb.  */
-	nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC);
+	nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC);
 	if (!nskb)
 		goto nomem;
 
 	/* Make sure the outbound skb has enough header room reserved. */
-	skb_reserve(nskb, packet->overhead + LL_MAX_HEADER);
+	skb_reserve(nskb, packet->overhead + MAX_HEADER);
 
 	/* Set the owning socket so that we know where to get the
 	 * destination IP address.
@@ -599,7 +599,7 @@ out:
 	return err;
 no_route:
 	kfree_skb(nskb);
-	IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+	IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
 
 	/* FIXME: Returning the 'err' will effect all the associations
 	 * associated with a socket, although only one of the paths of the
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 4e1d0fcb028e..a62a215dd22e 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -491,8 +491,13 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 			continue;
 		if ((laddr->state == SCTP_ADDR_SRC) &&
 		    (AF_INET == laddr->a.sa.sa_family)) {
-			fl4->saddr = laddr->a.v4.sin_addr.s_addr;
 			fl4->fl4_sport = laddr->a.v4.sin_port;
+			flowi4_update_output(fl4,
+					     asoc->base.sk->sk_bound_dev_if,
+					     RT_CONN_FLAGS(asoc->base.sk),
+					     daddr->v4.sin_addr.s_addr,
+					     laddr->a.v4.sin_addr.s_addr);
+
 			rt = ip_route_output_key(sock_net(sk), fl4);
 			if (!IS_ERR(rt)) {
 				dst = &rt->dst;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 3a1767ef3201..43abb643f3a1 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -219,6 +219,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 			     gfp_t gfp, int vparam_len)
 {
 	struct net *net = sock_net(asoc->base.sk);
+	struct sctp_endpoint *ep = asoc->ep;
 	sctp_inithdr_t init;
 	union sctp_params addrs;
 	size_t chunksize;
@@ -278,7 +279,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	chunksize += vparam_len;
 
 	/* Account for AUTH related parameters */
-	if (net->sctp.auth_enable) {
+	if (ep->auth_enable) {
 		/* Add random parameter length*/
 		chunksize += sizeof(asoc->c.auth_random);
 
@@ -363,7 +364,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
 	}
 
 	/* Add SCTP-AUTH chunks to the parameter list */
-	if (net->sctp.auth_enable) {
+	if (ep->auth_enable) {
 		sctp_addto_chunk(retval, sizeof(asoc->c.auth_random),
 				 asoc->c.auth_random);
 		if (auth_hmacs)
@@ -2010,7 +2011,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc,
 			/* if the peer reports AUTH, assume that he
 			 * supports AUTH.
 			 */
-			if (net->sctp.auth_enable)
+			if (asoc->ep->auth_enable)
 				asoc->peer.auth_capable = 1;
 			break;
 		case SCTP_CID_ASCONF:
@@ -2102,6 +2103,7 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc,
  * 	SCTP_IERROR_NO_ERROR - continue with the chunk
  */
 static sctp_ierror_t sctp_verify_param(struct net *net,
+					const struct sctp_endpoint *ep,
 					const struct sctp_association *asoc,
 					union sctp_params param,
 					sctp_cid_t cid,
@@ -2152,7 +2154,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		goto fallthrough;
 
 	case SCTP_PARAM_RANDOM:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		/* SCTP-AUTH: Secion 6.1
@@ -2169,7 +2171,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		break;
 
 	case SCTP_PARAM_CHUNKS:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		/* SCTP-AUTH: Section 3.2
@@ -2185,7 +2187,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net,
 		break;
 
 	case SCTP_PARAM_HMAC_ALGO:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fallthrough;
 
 		hmacs = (struct sctp_hmac_algo_param *)param.p;
@@ -2220,10 +2222,9 @@ fallthrough:
 }
 
 /* Verify the INIT packet before we process it.  */
-int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
-		     sctp_cid_t cid,
-		     sctp_init_chunk_t *peer_init,
-		     struct sctp_chunk *chunk,
+int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
+		     const struct sctp_association *asoc, sctp_cid_t cid,
+		     sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk,
 		     struct sctp_chunk **errp)
 {
 	union sctp_params param;
@@ -2264,8 +2265,8 @@ int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
 
 	/* Verify all the variable length parameters */
 	sctp_walk_params(param, peer_init, init_hdr.params) {
-
-		result = sctp_verify_param(net, asoc, param, cid, chunk, errp);
+		result = sctp_verify_param(net, ep, asoc, param, cid,
+					   chunk, errp);
 		switch (result) {
 		case SCTP_IERROR_ABORT:
 		case SCTP_IERROR_NOMEM:
@@ -2497,6 +2498,7 @@ static int sctp_process_param(struct sctp_association *asoc,
 	struct sctp_af *af;
 	union sctp_addr_param *addr_param;
 	struct sctp_transport *t;
+	struct sctp_endpoint *ep = asoc->ep;
 
 	/* We maintain all INIT parameters in network byte order all the
 	 * time.  This allows us to not worry about whether the parameters
@@ -2607,6 +2609,9 @@ do_addr_param:
 		addr_param = param.v + sizeof(sctp_addip_param_t);
 
 		af = sctp_get_af_specific(param_type2af(param.p->type));
+		if (af == NULL)
+			break;
+
 		af->from_addr_param(&addr, addr_param,
 				    htons(asoc->peer.port), 0);
 
@@ -2636,7 +2641,7 @@ do_addr_param:
 		goto fall_through;
 
 	case SCTP_PARAM_RANDOM:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		/* Save peer's random parameter */
@@ -2649,7 +2654,7 @@ do_addr_param:
 		break;
 
 	case SCTP_PARAM_HMAC_ALGO:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		/* Save peer's HMAC list */
@@ -2665,7 +2670,7 @@ do_addr_param:
 		break;
 
 	case SCTP_PARAM_CHUNKS:
-		if (!net->sctp.auth_enable)
+		if (!ep->auth_enable)
 			goto fall_through;
 
 		asoc->peer.peer_chunks = kmemdup(param.p,
@@ -3108,50 +3113,63 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
 	return SCTP_ERROR_NO_ERROR;
 }
 
-/* Verify the ASCONF packet before we process it.  */
-int sctp_verify_asconf(const struct sctp_association *asoc,
-		       struct sctp_paramhdr *param_hdr, void *chunk_end,
-		       struct sctp_paramhdr **errp) {
-	sctp_addip_param_t *asconf_param;
+/* Verify the ASCONF packet before we process it. */
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+			struct sctp_chunk *chunk, bool addr_param_needed,
+			struct sctp_paramhdr **errp)
+{
+	sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr;
 	union sctp_params param;
-	int length, plen;
+	bool addr_param_seen = false;
 
-	param.v = (sctp_paramhdr_t *) param_hdr;
-	while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) {
-		length = ntohs(param.p->length);
-		*errp = param.p;
-
-		if (param.v > chunk_end - length ||
-		    length < sizeof(sctp_paramhdr_t))
-			return 0;
+	sctp_walk_params(param, addip, addip_hdr.params) {
+		size_t length = ntohs(param.p->length);
 
+		*errp = param.p;
 		switch (param.p->type) {
+		case SCTP_PARAM_ERR_CAUSE:
+			break;
+		case SCTP_PARAM_IPV4_ADDRESS:
+			if (length != sizeof(sctp_ipv4addr_param_t))
+				return false;
+			addr_param_seen = true;
+			break;
+		case SCTP_PARAM_IPV6_ADDRESS:
+			if (length != sizeof(sctp_ipv6addr_param_t))
+				return false;
+			addr_param_seen = true;
+			break;
 		case SCTP_PARAM_ADD_IP:
 		case SCTP_PARAM_DEL_IP:
 		case SCTP_PARAM_SET_PRIMARY:
-			asconf_param = (sctp_addip_param_t *)param.v;
-			plen = ntohs(asconf_param->param_hdr.length);
-			if (plen < sizeof(sctp_addip_param_t) +
-			    sizeof(sctp_paramhdr_t))
-				return 0;
+			/* In ASCONF chunks, these need to be first. */
+			if (addr_param_needed && !addr_param_seen)
+				return false;
+			length = ntohs(param.addip->param_hdr.length);
+			if (length < sizeof(sctp_addip_param_t) +
+				     sizeof(sctp_paramhdr_t))
+				return false;
 			break;
 		case SCTP_PARAM_SUCCESS_REPORT:
 		case SCTP_PARAM_ADAPTATION_LAYER_IND:
 			if (length != sizeof(sctp_addip_param_t))
-				return 0;
-
+				return false;
 			break;
 		default:
-			break;
+			/* This is unkown to us, reject! */
+			return false;
 		}
-
-		param.v += WORD_ROUND(length);
 	}
 
-	if (param.v != chunk_end)
-		return 0;
+	/* Remaining sanity checks. */
+	if (addr_param_needed && !addr_param_seen)
+		return false;
+	if (!addr_param_needed && addr_param_seen)
+		return false;
+	if (param.v != chunk->chunk_end)
+		return false;
 
-	return 1;
+	return true;
 }
 
 /* Process an incoming ASCONF chunk with the next expected serial no. and
@@ -3160,16 +3178,17 @@ int sctp_verify_asconf(const struct sctp_association *asoc,
 struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 				       struct sctp_chunk *asconf)
 {
+	sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr;
+	bool all_param_pass = true;
+	union sctp_params param;
 	sctp_addiphdr_t		*hdr;
 	union sctp_addr_param	*addr_param;
 	sctp_addip_param_t	*asconf_param;
 	struct sctp_chunk	*asconf_ack;
-
 	__be16	err_code;
 	int	length = 0;
 	int	chunk_len;
 	__u32	serial;
-	int	all_param_pass = 1;
 
 	chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t);
 	hdr = (sctp_addiphdr_t *)asconf->skb->data;
@@ -3197,9 +3216,14 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 		goto done;
 
 	/* Process the TLVs contained within the ASCONF chunk. */
-	while (chunk_len > 0) {
+	sctp_walk_params(param, addip, addip_hdr.params) {
+		/* Skip preceeding address parameters. */
+		if (param.p->type == SCTP_PARAM_IPV4_ADDRESS ||
+		    param.p->type == SCTP_PARAM_IPV6_ADDRESS)
+			continue;
+
 		err_code = sctp_process_asconf_param(asoc, asconf,
-						     asconf_param);
+						     param.addip);
 		/* ADDIP 4.1 A7)
 		 * If an error response is received for a TLV parameter,
 		 * all TLVs with no response before the failed TLV are
@@ -3207,28 +3231,20 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
 		 * the failed response are considered unsuccessful unless
 		 * a specific success indication is present for the parameter.
 		 */
-		if (SCTP_ERROR_NO_ERROR != err_code)
-			all_param_pass = 0;
-
+		if (err_code != SCTP_ERROR_NO_ERROR)
+			all_param_pass = false;
 		if (!all_param_pass)
-			sctp_add_asconf_response(asconf_ack,
-						 asconf_param->crr_id, err_code,
-						 asconf_param);
+			sctp_add_asconf_response(asconf_ack, param.addip->crr_id,
+						 err_code, param.addip);
 
 		/* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add
 		 * an IP address sends an 'Out of Resource' in its response, it
 		 * MUST also fail any subsequent add or delete requests bundled
 		 * in the ASCONF.
 		 */
-		if (SCTP_ERROR_RSRC_LOW == err_code)
+		if (err_code == SCTP_ERROR_RSRC_LOW)
 			goto done;
-
-		/* Move to the next ASCONF param. */
-		length = ntohs(asconf_param->param_hdr.length);
-		asconf_param = (void *)asconf_param + length;
-		chunk_len -= length;
 	}
-
 done:
 	asoc->peer.addip_serial++;
 
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 5d6883ff00c3..fef2acdf4a2e 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -496,11 +496,10 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands,
 
 	/* If the transport error count is greater than the pf_retrans
 	 * threshold, and less than pathmaxrtx, and if the current state
-	 * is not SCTP_UNCONFIRMED, then mark this transport as Partially
-	 * Failed, see SCTP Quick Failover Draft, section 5.1
+	 * is SCTP_ACTIVE, then mark this transport as Partially Failed,
+	 * see SCTP Quick Failover Draft, section 5.1
 	 */
-	if ((transport->state != SCTP_PF) &&
-	   (transport->state != SCTP_UNCONFIRMED) &&
+	if ((transport->state == SCTP_ACTIVE) &&
 	   (asoc->pf_retrans < transport->pathmaxrxt) &&
 	   (transport->error_count > asoc->pf_retrans)) {
 
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 01e002430c85..3e287a3fa03b 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -170,6 +170,9 @@ sctp_chunk_length_valid(struct sctp_chunk *chunk,
 {
 	__u16 chunk_length = ntohs(chunk->chunk_hdr->length);
 
+	/* Previously already marked? */
+	if (unlikely(chunk->pdiscard))
+		return 0;
 	if (unlikely(chunk_length < required_length))
 		return 0;
 
@@ -357,7 +360,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net,
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 		/* This chunk contains fatal error. It is to be discarded.
@@ -524,7 +527,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net,
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 
@@ -1430,7 +1433,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init(
 
 	/* Verify the INIT chunk before processing it. */
 	err_chunk = NULL;
-	if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+	if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
 			      (sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
 			      &err_chunk)) {
 		/* This chunk contains fatal error. It is to be discarded.
@@ -1775,9 +1778,22 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net,
 	/* Update the content of current association. */
 	sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
 	sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
-	sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
-			SCTP_STATE(SCTP_STATE_ESTABLISHED));
-	sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+	if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+	    (sctp_sstate(asoc->base.sk, CLOSING) ||
+	     sock_flag(asoc->base.sk, SOCK_DEAD))) {
+		/* if were currently in SHUTDOWN_PENDING, but the socket
+		 * has been closed by user, don't transition to ESTABLISHED.
+		 * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+		 */
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+		return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
+						     SCTP_ST_CHUNK(0), NULL,
+						     commands);
+	} else {
+		sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
+				SCTP_STATE(SCTP_STATE_ESTABLISHED));
+		sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+	}
 	return SCTP_DISPOSITION_CONSUME;
 
 nomem_ev:
@@ -3578,9 +3594,7 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
 	struct sctp_chunk	*asconf_ack = NULL;
 	struct sctp_paramhdr	*err_param = NULL;
 	sctp_addiphdr_t		*hdr;
-	union sctp_addr_param	*addr_param;
 	__u32			serial;
-	int			length;
 
 	if (!sctp_vtag_verify(chunk, asoc)) {
 		sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG,
@@ -3605,17 +3619,8 @@ sctp_disposition_t sctp_sf_do_asconf(struct net *net,
 	hdr = (sctp_addiphdr_t *)chunk->skb->data;
 	serial = ntohl(hdr->serial);
 
-	addr_param = (union sctp_addr_param *)hdr->params;
-	length = ntohs(addr_param->p.length);
-	if (length < sizeof(sctp_paramhdr_t))
-		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
-			   (void *)addr_param, commands);
-
 	/* Verify the ASCONF chunk before processing it. */
-	if (!sctp_verify_asconf(asoc,
-			    (sctp_paramhdr_t *)((void *)addr_param + length),
-			    (void *)chunk->chunk_end,
-			    &err_param))
+	if (!sctp_verify_asconf(asoc, chunk, true, &err_param))
 		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
 						  (void *)err_param, commands);
 
@@ -3732,10 +3737,7 @@ sctp_disposition_t sctp_sf_do_asconf_ack(struct net *net,
 	rcvd_serial = ntohl(addip_hdr->serial);
 
 	/* Verify the ASCONF-ACK chunk before processing it. */
-	if (!sctp_verify_asconf(asoc,
-	    (sctp_paramhdr_t *)addip_hdr->params,
-	    (void *)asconf_ack->chunk_end,
-	    &err_param))
+	if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param))
 		return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
 			   (void *)err_param, commands);
 
@@ -6178,7 +6180,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	 * PMTU.  In cases, such as loopback, this might be a rather
 	 * large spill over.
 	 */
-	if ((!chunk->data_accepted) && (!asoc->rwnd ||
+	if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over ||
 	    (datalen > asoc->rwnd + asoc->frag_point))) {
 
 		/* If this is the next TSN, consider reneging to make
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 981aaf8b6ace..604a6acdf92e 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2115,6 +2115,12 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
 		sctp_skb_pull(skb, copied);
 		skb_queue_head(&sk->sk_receive_queue, skb);
 
+		/* When only partial message is copied to the user, increase
+		 * rwnd by that amount. If all the data in the skb is read,
+		 * rwnd is updated when the event is freed.
+		 */
+		if (!sctp_ulpevent_is_notification(event))
+			sctp_assoc_rwnd_increase(event->asoc, copied);
 		goto out;
 	} else if ((event->msg_flags & MSG_NOTIFICATION) ||
 		   (event->msg_flags & MSG_EOR))
@@ -3315,10 +3321,10 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunk val;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authchunk))
@@ -3335,7 +3341,7 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk,
 	}
 
 	/* add this chunk id to the endpoint */
-	return sctp_auth_ep_add_chunkid(sctp_sk(sk)->ep, val.sauth_chunk);
+	return sctp_auth_ep_add_chunkid(ep, val.sauth_chunk);
 }
 
 /*
@@ -3348,12 +3354,12 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_hmacalgo *hmacs;
 	u32 idents;
 	int err;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen < sizeof(struct sctp_hmacalgo))
@@ -3370,7 +3376,7 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk,
 		goto out;
 	}
 
-	err = sctp_auth_ep_set_hmacs(sctp_sk(sk)->ep, hmacs);
+	err = sctp_auth_ep_set_hmacs(ep, hmacs);
 out:
 	kfree(hmacs);
 	return err;
@@ -3386,12 +3392,12 @@ static int sctp_setsockopt_auth_key(struct sock *sk,
 				    char __user *optval,
 				    unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkey *authkey;
 	struct sctp_association *asoc;
 	int ret;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen <= sizeof(struct sctp_authkey))
@@ -3412,7 +3418,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk,
 		goto out;
 	}
 
-	ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey);
+	ret = sctp_auth_set_key(ep, asoc, authkey);
 out:
 	kzfree(authkey);
 	return ret;
@@ -3428,11 +3434,11 @@ static int sctp_setsockopt_active_key(struct sock *sk,
 				      char __user *optval,
 				      unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authkeyid))
@@ -3444,8 +3450,7 @@ static int sctp_setsockopt_active_key(struct sock *sk,
 	if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
 		return -EINVAL;
 
-	return sctp_auth_set_active_key(sctp_sk(sk)->ep, asoc,
-					val.scact_keynumber);
+	return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber);
 }
 
 /*
@@ -3457,11 +3462,11 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 				   char __user *optval,
 				   unsigned int optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (optlen != sizeof(struct sctp_authkeyid))
@@ -3473,8 +3478,7 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 	if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
 		return -EINVAL;
 
-	return sctp_auth_del_key_id(sctp_sk(sk)->ep, asoc,
-				    val.scact_keynumber);
+	return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber);
 
 }
 
@@ -5381,16 +5385,16 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len,
 static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_hmacalgo  __user *p = (void __user *)optval;
 	struct sctp_hmac_algo_param *hmacs;
 	__u16 data_len = 0;
 	u32 num_idents;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
-	hmacs = sctp_sk(sk)->ep->auth_hmacs_list;
+	hmacs = ep->auth_hmacs_list;
 	data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t);
 
 	if (len < sizeof(struct sctp_hmacalgo) + data_len)
@@ -5411,11 +5415,11 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
 static int sctp_getsockopt_active_key(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authkeyid val;
 	struct sctp_association *asoc;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authkeyid))
@@ -5430,7 +5434,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len,
 	if (asoc)
 		val.scact_keynumber = asoc->active_key_id;
 	else
-		val.scact_keynumber = sctp_sk(sk)->ep->active_key_id;
+		val.scact_keynumber = ep->active_key_id;
 
 	len = sizeof(struct sctp_authkeyid);
 	if (put_user(len, optlen))
@@ -5444,7 +5448,7 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len,
 static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunks __user *p = (void __user *)optval;
 	struct sctp_authchunks val;
 	struct sctp_association *asoc;
@@ -5452,7 +5456,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
 	u32    num_chunks = 0;
 	char __user *to;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authchunks))
@@ -5489,7 +5493,7 @@ num:
 static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 				    char __user *optval, int __user *optlen)
 {
-	struct net *net = sock_net(sk);
+	struct sctp_endpoint *ep = sctp_sk(sk)->ep;
 	struct sctp_authchunks __user *p = (void __user *)optval;
 	struct sctp_authchunks val;
 	struct sctp_association *asoc;
@@ -5497,7 +5501,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 	u32    num_chunks = 0;
 	char __user *to;
 
-	if (!net->sctp.auth_enable)
+	if (!ep->auth_enable)
 		return -EACCES;
 
 	if (len < sizeof(struct sctp_authchunks))
@@ -5514,7 +5518,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
 	if (asoc)
 		ch = (struct sctp_chunks_param *)asoc->c.auth_chunks;
 	else
-		ch = sctp_sk(sk)->ep->auth_chunk_list;
+		ch = ep->auth_chunk_list;
 
 	if (!ch)
 		goto num;
@@ -6593,6 +6597,46 @@ static void __sctp_write_space(struct sctp_association *asoc)
 	}
 }
 
+static void sctp_wake_up_waiters(struct sock *sk,
+				 struct sctp_association *asoc)
+{
+	struct sctp_association *tmp = asoc;
+
+	/* We do accounting for the sndbuf space per association,
+	 * so we only need to wake our own association.
+	 */
+	if (asoc->ep->sndbuf_policy)
+		return __sctp_write_space(asoc);
+
+	/* If association goes down and is just flushing its
+	 * outq, then just normally notify others.
+	 */
+	if (asoc->base.dead)
+		return sctp_write_space(sk);
+
+	/* Accounting for the sndbuf space is per socket, so we
+	 * need to wake up others, try to be fair and in case of
+	 * other associations, let them have a go first instead
+	 * of just doing a sctp_write_space() call.
+	 *
+	 * Note that we reach sctp_wake_up_waiters() only when
+	 * associations free up queued chunks, thus we are under
+	 * lock and the list of associations on a socket is
+	 * guaranteed not to change.
+	 */
+	for (tmp = list_next_entry(tmp, asocs); 1;
+	     tmp = list_next_entry(tmp, asocs)) {
+		/* Manually skip the head element. */
+		if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs))
+			continue;
+		/* Wake up association. */
+		__sctp_write_space(tmp);
+		/* We've reached the end. */
+		if (tmp == asoc)
+			break;
+	}
+}
+
 /* Do accounting for the sndbuf space.
  * Decrement the used sndbuf space of the corresponding association by the
  * data size which was just transmitted(freed).
@@ -6620,7 +6664,7 @@ static void sctp_wfree(struct sk_buff *skb)
 	sk_mem_uncharge(sk, skb->truesize);
 
 	sock_wfree(skb);
-	__sctp_write_space(asoc);
+	sctp_wake_up_waiters(sk, asoc);
 
 	sctp_association_put(asoc);
 }
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 35c8923b5554..dfa532f00d88 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -64,6 +64,9 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos);
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos);
 
 static struct ctl_table sctp_table[] = {
 	{
@@ -266,7 +269,7 @@ static struct ctl_table sctp_net_table[] = {
 		.data		= &init_net.sctp.auth_enable,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_sctp_do_auth,
 	},
 	{
 		.procname	= "addr_scope_policy",
@@ -304,41 +307,40 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 				loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
-	char tmp[8];
 	struct ctl_table tbl;
-	int ret;
-	int changed = 0;
+	bool changed = false;
 	char *none = "none";
+	char tmp[8];
+	int ret;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
 
 	if (write) {
 		tbl.data = tmp;
-		tbl.maxlen = 8;
+		tbl.maxlen = sizeof(tmp);
 	} else {
 		tbl.data = net->sctp.sctp_hmac_alg ? : none;
 		tbl.maxlen = strlen(tbl.data);
 	}
-		ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
 
-	if (write) {
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
 #ifdef CONFIG_CRYPTO_MD5
 		if (!strncmp(tmp, "md5", 3)) {
 			net->sctp.sctp_hmac_alg = "md5";
-			changed = 1;
+			changed = true;
 		}
 #endif
 #ifdef CONFIG_CRYPTO_SHA1
 		if (!strncmp(tmp, "sha1", 4)) {
 			net->sctp.sctp_hmac_alg = "sha1";
-			changed = 1;
+			changed = true;
 		}
 #endif
 		if (!strncmp(tmp, "none", 4)) {
 			net->sctp.sctp_hmac_alg = NULL;
-			changed = 1;
+			changed = true;
 		}
-
 		if (!changed)
 			ret = -EINVAL;
 	}
@@ -351,11 +353,10 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 				loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
-	int new_value;
-	struct ctl_table tbl;
 	unsigned int min = *(unsigned int *) ctl->extra1;
 	unsigned int max = *(unsigned int *) ctl->extra2;
-	int ret;
+	struct ctl_table tbl;
+	int ret, new_value;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
 	tbl.maxlen = sizeof(unsigned int);
@@ -364,12 +365,15 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 		tbl.data = &new_value;
 	else
 		tbl.data = &net->sctp.rto_min;
+
 	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
-	if (write) {
-		if (ret || new_value > max || new_value < min)
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
 			return -EINVAL;
+
 		net->sctp.rto_min = new_value;
 	}
+
 	return ret;
 }
 
@@ -378,11 +382,10 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 				loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
-	int new_value;
-	struct ctl_table tbl;
 	unsigned int min = *(unsigned int *) ctl->extra1;
 	unsigned int max = *(unsigned int *) ctl->extra2;
-	int ret;
+	struct ctl_table tbl;
+	int ret, new_value;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
 	tbl.maxlen = sizeof(unsigned int);
@@ -391,12 +394,45 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 		tbl.data = &new_value;
 	else
 		tbl.data = &net->sctp.rto_max;
+
 	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
-	if (write) {
-		if (ret || new_value > max || new_value < min)
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
 			return -EINVAL;
+
 		net->sctp.rto_max = new_value;
 	}
+
+	return ret;
+}
+
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+			     void __user *buffer, size_t *lenp,
+			     loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct ctl_table tbl;
+	int new_value, ret;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.auth_enable;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		struct sock *sk = net->sctp.ctl_sock;
+
+		net->sctp.auth_enable = new_value;
+		/* Update the value in the control socket */
+		lock_sock(sk);
+		sctp_sk(sk)->ep->auth_enable = new_value;
+		release_sock(sk);
+	}
+
 	return ret;
 }
 
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 8d198ae03606..b6842fdb53d4 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -366,9 +366,10 @@ fail:
  * specification [SCTP] and any extensions for a list of possible
  * error formats.
  */
-struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
-	const struct sctp_association *asoc, struct sctp_chunk *chunk,
-	__u16 flags, gfp_t gfp)
+struct sctp_ulpevent *
+sctp_ulpevent_make_remote_error(const struct sctp_association *asoc,
+				struct sctp_chunk *chunk, __u16 flags,
+				gfp_t gfp)
 {
 	struct sctp_ulpevent *event;
 	struct sctp_remote_error *sre;
@@ -387,8 +388,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	/* Copy the skb to a new skb with room for us to prepend
 	 * notification with.
 	 */
-	skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error),
-			      0, gfp);
+	skb = skb_copy_expand(chunk->skb, sizeof(*sre), 0, gfp);
 
 	/* Pull off the rest of the cause TLV from the chunk.  */
 	skb_pull(chunk->skb, elen);
@@ -399,62 +399,21 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	event = sctp_skb2event(skb);
 	sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
 
-	sre = (struct sctp_remote_error *)
-		skb_push(skb, sizeof(struct sctp_remote_error));
+	sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre));
 
 	/* Trim the buffer to the right length.  */
-	skb_trim(skb, sizeof(struct sctp_remote_error) + elen);
+	skb_trim(skb, sizeof(*sre) + elen);
 
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_type:
-	 *   It should be SCTP_REMOTE_ERROR.
-	 */
+	/* RFC6458, Section 6.1.3. SCTP_REMOTE_ERROR */
+	memset(sre, 0, sizeof(*sre));
 	sre->sre_type = SCTP_REMOTE_ERROR;
-
-	/*
-	 * Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_flags: 16 bits (unsigned integer)
-	 *   Currently unused.
-	 */
 	sre->sre_flags = 0;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_length: sizeof (__u32)
-	 *
-	 * This field is the total length of the notification data,
-	 * including the notification header.
-	 */
 	sre->sre_length = skb->len;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_error: 16 bits (unsigned integer)
-	 * This value represents one of the Operational Error causes defined in
-	 * the SCTP specification, in network byte order.
-	 */
 	sre->sre_error = cause;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association id field, holds the identifier for the association.
-	 * All notifications for a given association have the same association
-	 * identifier.  For TCP style socket, this field is ignored.
-	 */
 	sctp_ulpevent_set_owner(event, asoc);
 	sre->sre_assoc_id = sctp_assoc2id(asoc);
 
 	return event;
-
 fail:
 	return NULL;
 }
@@ -899,7 +858,9 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event)
 	return notification->sn_header.sn_type;
 }
 
-/* Copy out the sndrcvinfo into a msghdr.  */
+/* RFC6458, Section 5.3.2. SCTP Header Information Structure
+ * (SCTP_SNDRCV, DEPRECATED)
+ */
 void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 				   struct msghdr *msghdr)
 {
@@ -908,74 +869,21 @@ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 	if (sctp_ulpevent_is_notification(event))
 		return;
 
-	/* Sockets API Extensions for SCTP
-	 * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV)
-	 *
-	 * sinfo_stream: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() the SCTP stack places the message's stream number in
-	 * this value.
-	*/
+	memset(&sinfo, 0, sizeof(sinfo));
 	sinfo.sinfo_stream = event->stream;
-	/* sinfo_ssn: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() this value contains the stream sequence number that
-	 * the remote endpoint placed in the DATA chunk.  For fragmented
-	 * messages this is the same number for all deliveries of the message
-	 * (if more than one recvmsg() is needed to read the message).
-	 */
 	sinfo.sinfo_ssn = event->ssn;
-	/* sinfo_ppid: 32 bits (unsigned integer)
-	 *
-	 * In recvmsg() this value is
-	 * the same information that was passed by the upper layer in the peer
-	 * application.  Please note that byte order issues are NOT accounted
-	 * for and this information is passed opaquely by the SCTP stack from
-	 * one end to the other.
-	 */
 	sinfo.sinfo_ppid = event->ppid;
-	/* sinfo_flags: 16 bits (unsigned integer)
-	 *
-	 * This field may contain any of the following flags and is composed of
-	 * a bitwise OR of these values.
-	 *
-	 * recvmsg() flags:
-	 *
-	 * SCTP_UNORDERED - This flag is present when the message was sent
-	 *                 non-ordered.
-	 */
 	sinfo.sinfo_flags = event->flags;
-	/* sinfo_tsn: 32 bit (unsigned integer)
-	 *
-	 * For the receiving side, this field holds a TSN that was
-	 * assigned to one of the SCTP Data Chunks.
-	 */
 	sinfo.sinfo_tsn = event->tsn;
-	/* sinfo_cumtsn: 32 bit (unsigned integer)
-	 *
-	 * This field will hold the current cumulative TSN as
-	 * known by the underlying SCTP layer.  Note this field is
-	 * ignored when sending and only valid for a receive
-	 * operation when sinfo_flags are set to SCTP_UNORDERED.
-	 */
 	sinfo.sinfo_cumtsn = event->cumtsn;
-	/* sinfo_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association handle field, sinfo_assoc_id, holds the identifier
-	 * for the association announced in the COMMUNICATION_UP notification.
-	 * All notifications for a given association have the same identifier.
-	 * Ignored for one-to-one style sockets.
-	 */
 	sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc);
-
-	/* context value that is set via SCTP_CONTEXT socket option. */
+	/* Context value that is set via SCTP_CONTEXT socket option. */
 	sinfo.sinfo_context = event->asoc->default_rcv_context;
-
 	/* These fields are not used while receiving. */
 	sinfo.sinfo_timetolive = 0;
 
 	put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV,
-		 sizeof(struct sctp_sndrcvinfo), (void *)&sinfo);
+		 sizeof(sinfo), &sinfo);
 }
 
 /* Do accounting for bytes received and hold a reference to the association
@@ -989,7 +897,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event,
 	skb = sctp_event2skb(event);
 	/* Set the owner and charge rwnd for bytes received.  */
 	sctp_ulpevent_set_owner(event, asoc);
-	sctp_assoc_rwnd_update(asoc, false);
+	sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb));
 
 	if (!skb->data_len)
 		return;
@@ -1011,7 +919,6 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
 {
 	struct sk_buff *skb, *frag;
 	unsigned int	len;
-	struct sctp_association *asoc;
 
 	/* Current stack structures assume that the rcv buffer is
 	 * per socket.   For UDP style sockets this is not true as
@@ -1036,11 +943,8 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
 	}
 
 done:
-	asoc = event->asoc;
-	sctp_association_hold(asoc);
+	sctp_assoc_rwnd_increase(event->asoc, len);
 	sctp_ulpevent_release_owner(event);
-	sctp_assoc_rwnd_update(asoc, true);
-	sctp_association_put(asoc);
 }
 
 static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event)
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 0edada973434..5ff8b87c3d04 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -533,6 +533,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 
 	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
 		clnt->cl_autobind = 1;
+	if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT)
+		clnt->cl_noretranstimeo = 1;
 	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
 		clnt->cl_discrtry = 1;
 	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
@@ -571,6 +573,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
 	/* Turn off autobind on clones */
 	new->cl_autobind = 0;
 	new->cl_softrtry = clnt->cl_softrtry;
+	new->cl_noretranstimeo = clnt->cl_noretranstimeo;
 	new->cl_discrtry = clnt->cl_discrtry;
 	new->cl_chatty = clnt->cl_chatty;
 	return new;
@@ -1798,21 +1801,19 @@ call_connect_status(struct rpc_task *task)
 	trace_rpc_connect_status(task, status);
 	task->tk_status = 0;
 	switch (status) {
-		/* if soft mounted, test if we've timed out */
-	case -ETIMEDOUT:
-		task->tk_action = call_timeout;
-		return;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -ENETUNREACH:
 	case -EHOSTUNREACH:
-		/* retry with existing socket, after a delay */
-		rpc_delay(task, 3*HZ);
 		if (RPC_IS_SOFTCONN(task))
 			break;
+		/* retry with existing socket, after a delay */
+		rpc_delay(task, 3*HZ);
 	case -EAGAIN:
-		task->tk_action = call_bind;
+		/* Check for timeouts before looping back to call_bind */
+	case -ETIMEDOUT:
+		task->tk_action = call_timeout;
 		return;
 	case 0:
 		clnt->cl_stats->netreconn++;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 06c6ff0cb911..a4acaf2bcf18 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -730,6 +730,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt)
 			svc_add_new_temp_xprt(serv, newxpt);
+		else
+			module_put(xprt->xpt_class->xcl_owner);
 	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b6e59f0a9475..5e8fe777772b 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -685,6 +685,7 @@ static struct svc_xprt_class svc_udp_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_udp_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
+	.xcl_ident = XPRT_TRANSPORT_UDP,
 };
 
 static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
@@ -1279,6 +1280,7 @@ static struct svc_xprt_class svc_tcp_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_tcp_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_ident = XPRT_TRANSPORT_TCP,
 };
 
 void svc_init_xprt_sock(void)
@@ -1397,6 +1399,22 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	return svsk;
 }
 
+bool svc_alien_sock(struct net *net, int fd)
+{
+	int err;
+	struct socket *sock = sockfd_lookup(fd, &err);
+	bool ret = false;
+
+	if (!sock)
+		goto out;
+	if (sock_net(sock->sk) != net)
+		ret = true;
+	sockfd_put(sock);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(svc_alien_sock);
+
 /**
  * svc_addsock - add a listener socket to an RPC service
  * @serv: pointer to RPC service to which to add a new listener
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 7d4df99f761f..03ac88431984 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1316,7 +1316,7 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
 		}
 	}
 	spin_unlock(&xprt_list_lock);
-	printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident);
+	dprintk("RPC: transport (%d) not supported\n", args->ident);
 	return ERR_PTR(-EIO);
 
 found:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 62e4f9bcc387..ed36cb52cd86 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -89,6 +89,7 @@ struct svc_xprt_class svc_rdma_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_rdma_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_ident = XPRT_TRANSPORT_RDMA,
 };
 
 struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 0addefca8e77..41c2f9d7a148 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -842,6 +842,8 @@ static void xs_error_report(struct sock *sk)
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
 			xprt, -err);
 	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+	if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state))
+		goto out;
 	xprt_wake_pending_tasks(xprt, err);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -2251,7 +2253,9 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 		abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
 				&xprt->state);
 		/* "close" the socket, preserving the local port */
+		set_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 		xs_tcp_reuse_connection(transport);
+		clear_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 
 		if (abort_and_exit)
 			goto out_eagain;
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index bf860d9e75af..3ca45bf5029f 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -537,6 +537,7 @@ receive:
 
 		buf = node->bclink.deferred_head;
 		node->bclink.deferred_head = buf->next;
+		buf->next = NULL;
 		node->bclink.deferred_size--;
 		goto receive;
 	}
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 3aaf73de9e2d..ad844d365340 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 	int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
 	u16 cmd;
 
-	if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN)))
+	if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN)))
 		cmd = TIPC_CMD_NOT_NET_ADMIN;
 	else
 		cmd = req_userhdr->cmd;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 5adfd94c5b85..85d232bed87d 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1925,9 +1925,23 @@ static struct miscdevice vsock_device = {
 	.fops		= &vsock_device_ops,
 };
 
-static int __vsock_core_init(void)
+int __vsock_core_init(const struct vsock_transport *t, struct module *owner)
 {
-	int err;
+	int err = mutex_lock_interruptible(&vsock_register_mutex);
+
+	if (err)
+		return err;
+
+	if (transport) {
+		err = -EBUSY;
+		goto err_busy;
+	}
+
+	/* Transport must be the owner of the protocol so that it can't
+	 * unload while there are open sockets.
+	 */
+	vsock_proto.owner = owner;
+	transport = t;
 
 	vsock_init_tables();
 
@@ -1951,36 +1965,19 @@ static int __vsock_core_init(void)
 		goto err_unregister_proto;
 	}
 
+	mutex_unlock(&vsock_register_mutex);
 	return 0;
 
 err_unregister_proto:
 	proto_unregister(&vsock_proto);
 err_misc_deregister:
 	misc_deregister(&vsock_device);
-	return err;
-}
-
-int vsock_core_init(const struct vsock_transport *t)
-{
-	int retval = mutex_lock_interruptible(&vsock_register_mutex);
-	if (retval)
-		return retval;
-
-	if (transport) {
-		retval = -EBUSY;
-		goto out;
-	}
-
-	transport = t;
-	retval = __vsock_core_init();
-	if (retval)
-		transport = NULL;
-
-out:
+	transport = NULL;
+err_busy:
 	mutex_unlock(&vsock_register_mutex);
-	return retval;
+	return err;
 }
-EXPORT_SYMBOL_GPL(vsock_core_init);
+EXPORT_SYMBOL_GPL(__vsock_core_init);
 
 void vsock_core_exit(void)
 {
@@ -2000,5 +1997,5 @@ EXPORT_SYMBOL_GPL(vsock_core_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Socket Family");
-MODULE_VERSION("1.0.0.0-k");
+MODULE_VERSION("1.0.1.0-k");
 MODULE_LICENSE("GPL v2");
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 4fe2e6e2bc76..df33156ecd2d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1450,18 +1450,17 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		}
 		CMD(start_p2p_device, START_P2P_DEVICE);
 		CMD(set_mcast_rate, SET_MCAST_RATE);
+#ifdef CONFIG_NL80211_TESTMODE
+		CMD(testmode_cmd, TESTMODE);
+#endif
 		if (state->split) {
 			CMD(crit_proto_start, CRIT_PROTOCOL_START);
 			CMD(crit_proto_stop, CRIT_PROTOCOL_STOP);
 			if (dev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
 				CMD(channel_switch, CHANNEL_SWITCH);
+			CMD(set_qos_map, SET_QOS_MAP);
 		}
-		CMD(set_qos_map, SET_QOS_MAP);
-
-#ifdef CONFIG_NL80211_TESTMODE
-		CMD(testmode_cmd, TESTMODE);
-#endif
-
+		/* add into the if now */
 #undef CMD
 
 		if (dev->ops->connect || dev->ops->auth) {
@@ -6797,6 +6796,9 @@ void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp)
 	struct nlattr *data = ((void **)skb->cb)[2];
 	enum nl80211_multicast_groups mcgrp = NL80211_MCGRP_TESTMODE;
 
+	/* clear CB data for netlink core to own from now on */
+	memset(skb->cb, 0, sizeof(skb->cb));
+
 	nla_nest_end(skb, data);
 	genlmsg_end(skb, hdr);
 
@@ -9076,6 +9078,9 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb)
 	void *hdr = ((void **)skb->cb)[1];
 	struct nlattr *data = ((void **)skb->cb)[2];
 
+	/* clear CB data for netlink core to own from now on */
+	memset(skb->cb, 0, sizeof(skb->cb));
+
 	if (WARN_ON(!rdev->cur_cmd_info)) {
 		kfree_skb(skb);
 		return -EINVAL;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index f0541370e68e..338794ea44d1 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1683,17 +1683,9 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 	struct wiphy *wiphy = NULL;
 	enum reg_request_treatment treatment;
 
-	if (WARN_ON(!reg_request->alpha2))
-		return;
-
 	if (reg_request->wiphy_idx != WIPHY_IDX_INVALID)
 		wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx);
 
-	if (reg_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && !wiphy) {
-		kfree(reg_request);
-		return;
-	}
-
 	switch (reg_request->initiator) {
 	case NL80211_REGDOM_SET_BY_CORE:
 		reg_process_hint_core(reg_request);
@@ -1706,20 +1698,29 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 		schedule_delayed_work(&reg_timeout, msecs_to_jiffies(3142));
 		return;
 	case NL80211_REGDOM_SET_BY_DRIVER:
+		if (!wiphy)
+			goto out_free;
 		treatment = reg_process_hint_driver(wiphy, reg_request);
 		break;
 	case NL80211_REGDOM_SET_BY_COUNTRY_IE:
+		if (!wiphy)
+			goto out_free;
 		treatment = reg_process_hint_country_ie(wiphy, reg_request);
 		break;
 	default:
 		WARN(1, "invalid initiator %d\n", reg_request->initiator);
-		return;
+		goto out_free;
 	}
 
 	/* This is required so that the orig_* parameters are saved */
 	if (treatment == REG_REQ_ALREADY_SET && wiphy &&
 	    wiphy->regulatory_flags & REGULATORY_STRICT_REG)
 		wiphy_update_regulatory(wiphy, reg_request->initiator);
+
+	return;
+
+out_free:
+	kfree(reg_request);
 }
 
 /*
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d1ed4aebbbb7..38d6dd553770 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -284,14 +284,22 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_results);
 
-void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
 
+	ASSERT_RTNL();
+
 	trace_cfg80211_sched_scan_stopped(wiphy);
 
-	rtnl_lock();
 	__cfg80211_stop_sched_scan(rdev, true);
+}
+EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl);
+
+void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+{
+	rtnl_lock();
+	cfg80211_sched_scan_stopped_rtnl(wiphy);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_stopped);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index f04d4c32e96e..760722f9126b 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -235,7 +235,6 @@ void cfg80211_conn_work(struct work_struct *work)
 					NULL, 0, NULL, 0,
 					WLAN_STATUS_UNSPECIFIED_FAILURE,
 					false, NULL);
-			cfg80211_sme_free(wdev);
 		}
 		wdev_unlock(wdev);
 	}
@@ -649,6 +648,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			cfg80211_unhold_bss(bss_from_pub(bss));
 			cfg80211_put_bss(wdev->wiphy, bss);
 		}
+		cfg80211_sme_free(wdev);
 		return;
 	}
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index fbcc23edee54..b89eb3990f0a 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2068,7 +2068,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure,
 		MAC_ASSIGN(addr, addr);
 		__entry->key_type = key_type;
 		__entry->key_id = key_id;
-		memcpy(__entry->tsc, tsc, 6);
+		if (tsc)
+			memcpy(__entry->tsc, tsc, 6);
 	),
 	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm",
 		  NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 1d5c7bf29938..59cf325f2772 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -41,6 +41,11 @@
 
 static struct dst_entry *xfrm_policy_sk_bundles;
 
+struct xfrm_flo {
+	struct dst_entry *dst_orig;
+	u8 flags;
+};
+
 static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
 static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO]
 						__read_mostly;
@@ -1889,13 +1894,14 @@ static int xdst_queue_output(struct sk_buff *skb)
 }
 
 static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
-						 struct dst_entry *dst,
+						 struct xfrm_flo *xflo,
 						 const struct flowi *fl,
 						 int num_xfrms,
 						 u16 family)
 {
 	int err;
 	struct net_device *dev;
+	struct dst_entry *dst;
 	struct dst_entry *dst1;
 	struct xfrm_dst *xdst;
 
@@ -1903,9 +1909,12 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
 	if (IS_ERR(xdst))
 		return xdst;
 
-	if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0)
+	if (!(xflo->flags & XFRM_LOOKUP_QUEUE) ||
+	    net->xfrm.sysctl_larval_drop ||
+	    num_xfrms <= 0)
 		return xdst;
 
+	dst = xflo->dst_orig;
 	dst1 = &xdst->u.dst;
 	dst_hold(dst);
 	xdst->route = dst;
@@ -1947,7 +1956,7 @@ static struct flow_cache_object *
 xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 		   struct flow_cache_object *oldflo, void *ctx)
 {
-	struct dst_entry *dst_orig = (struct dst_entry *)ctx;
+	struct xfrm_flo *xflo = (struct xfrm_flo *)ctx;
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	struct xfrm_dst *xdst, *new_xdst;
 	int num_pols = 0, num_xfrms = 0, i, err, pol_dead;
@@ -1988,7 +1997,8 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 			goto make_dummy_bundle;
 	}
 
-	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig);
+	new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
+						  xflo->dst_orig);
 	if (IS_ERR(new_xdst)) {
 		err = PTR_ERR(new_xdst);
 		if (err != -EAGAIN)
@@ -2022,7 +2032,7 @@ make_dummy_bundle:
 	/* We found policies, but there's no bundles to instantiate:
 	 * either because the policy blocks, has no transformations or
 	 * we could not build template (no xfrm_states).*/
-	xdst = xfrm_create_dummy_bundle(net, dst_orig, fl, num_xfrms, family);
+	xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family);
 	if (IS_ERR(xdst)) {
 		xfrm_pols_put(pols, num_pols);
 		return ERR_CAST(xdst);
@@ -2121,13 +2131,18 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 	}
 
 	if (xdst == NULL) {
+		struct xfrm_flo xflo;
+
+		xflo.dst_orig = dst_orig;
+		xflo.flags = flags;
+
 		/* To accelerate a bit...  */
 		if ((dst_orig->flags & DST_NOXFRM) ||
 		    !net->xfrm.policy_count[XFRM_POLICY_OUT])
 			goto nopol;
 
 		flo = flow_cache_lookup(net, fl, family, dir,
-					xfrm_bundle_lookup, dst_orig);
+					xfrm_bundle_lookup, &xflo);
 		if (flo == NULL)
 			goto nopol;
 		if (IS_ERR(flo)) {
@@ -2155,7 +2170,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
 
-			return make_blackhole(net, family, dst_orig);
+			return ERR_PTR(-EREMOTE);
 		}
 
 		err = -EAGAIN;
@@ -2212,6 +2227,23 @@ dropdst:
 }
 EXPORT_SYMBOL(xfrm_lookup);
 
+/* Callers of xfrm_lookup_route() must ensure a call to dst_output().
+ * Otherwise we may send out blackholed packets.
+ */
+struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
+				    const struct flowi *fl,
+				    struct sock *sk, int flags)
+{
+	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
+					    flags | XFRM_LOOKUP_QUEUE);
+
+	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
+		return make_blackhole(net, dst_orig->ops->family, dst_orig);
+
+	return dst;
+}
+EXPORT_SYMBOL(xfrm_lookup_route);
+
 static inline int
 xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl)
 {
@@ -2477,7 +2509,7 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 
 	skb_dst_force(skb);
 
-	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, 0);
+	dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE);
 	if (IS_ERR(dst)) {
 		res = 0;
 		dst = NULL;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 2f7ddc3a59b4..3bea4ddc699d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -176,9 +176,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AEAD]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
 		    attrs[XFRMA_ALG_COMP]	||
-		    attrs[XFRMA_TFCPAD]		||
-		    (ntohl(p->id.spi) >= 0x10000))
-
+		    attrs[XFRMA_TFCPAD])
 			goto out;
 		break;
 
@@ -206,7 +204,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AUTH]	||
 		    attrs[XFRMA_ALG_AUTH_TRUNC]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
-		    attrs[XFRMA_TFCPAD])
+		    attrs[XFRMA_TFCPAD]		||
+		    (ntohl(p->id.spi) >= 0x10000))
 			goto out;
 		break;
 
@@ -2350,7 +2349,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	link = &xfrm_dispatch[type];
 
 	/* All operations require privileges, even GET */
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 79c059e70860..5ce9d7d3c7b3 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -153,6 +153,7 @@ dtc_cpp_flags  = -Wp,-MD,$(depfile).pre.tmp -nostdinc                    \
 		 -I$(srctree)/arch/$(SRCARCH)/boot/dts                   \
 		 -I$(srctree)/arch/$(SRCARCH)/boot/dts/include           \
 		 -I$(srctree)/drivers/of/testcase-data                   \
+		 -I$(srctree)/include                                    \
 		 -undef -D__DTS__
 
 # Finds the multi-part object the current object will be linked into
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index da058da413e7..2438cc351952 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1753,7 +1753,7 @@ sub dump_struct($$) {
 	# strip kmemcheck_bitfield_{begin,end}.*;
 	$members =~ s/kmemcheck_bitfield_.*?;//gos;
 	# strip attributes
-	$members =~ s/__aligned\s*\(.+\)//gos;
+	$members =~ s/__aligned\s*\([^;]*\)//gos;
 
 	create_parameterlist($members, ';', $file);
 	check_sections($file, $declaration_name, "struct", $sectcheck, $struct_actual, $nested);
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index bb5d115ca671..f282516acc7b 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -174,6 +174,9 @@ int main(void)
 	DEVID_FIELD(x86_cpu_id, model);
 	DEVID_FIELD(x86_cpu_id, vendor);
 
+	DEVID(cpu_feature);
+	DEVID_FIELD(cpu_feature, feature);
+
 	DEVID(mei_cl_device_id);
 	DEVID_FIELD(mei_cl_device_id, name);
 
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 25e5cb0aaef6..506146e5f4a8 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1135,6 +1135,16 @@ static int do_x86cpu_entry(const char *filename, void *symval,
 }
 ADD_TO_DEVTABLE("x86cpu", x86_cpu_id, do_x86cpu_entry);
 
+/* LOOKS like cpu:type:*:feature:*FEAT* */
+static int do_cpu_entry(const char *filename, void *symval, char *alias)
+{
+	DEF_FIELD(symval, cpu_feature, feature);
+
+	sprintf(alias, "cpu:type:*:feature:*%04X*", feature);
+	return 1;
+}
+ADD_TO_DEVTABLE("cpu", cpu_feature, do_cpu_entry);
+
 /* Looks like: mei:S */
 static int do_mei_entry(const char *filename, void *symval,
 			char *alias)
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index f46e4dd0558d..152d4d25ab7c 100644
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -155,11 +155,11 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then
 			for module in $(find lib/modules/ -name *.ko); do
 				mkdir -p $(dirname $dbg_dir/usr/lib/debug/$module)
 				# only keep debug symbols in the debug file
-				objcopy --only-keep-debug $module $dbg_dir/usr/lib/debug/$module
+				$OBJCOPY --only-keep-debug $module $dbg_dir/usr/lib/debug/$module
 				# strip original module from debug symbols
-				objcopy --strip-debug $module
+				$OBJCOPY --strip-debug $module
 				# then add a link to those
-				objcopy --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module
+				$OBJCOPY --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module
 			done
 		)
 	fi
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 9c22317778eb..e11aa4a156d2 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -40,6 +40,11 @@
 #define R_METAG_NONE                     3
 #endif
 
+#ifndef EM_AARCH64
+#define EM_AARCH64	183
+#define R_AARCH64_ABS64	257
+#endif
+
 static int fd_map;	/* File descriptor for file being modified. */
 static int mmap_failed; /* Boolean flag. */
 static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
@@ -347,6 +352,8 @@ do_file(char const *const fname)
 	case EM_ARM:	 reltype = R_ARM_ABS32;
 			 altmcount = "__gnu_mcount_nc";
 			 break;
+	case EM_AARCH64:
+			 reltype = R_AARCH64_ABS64; gpfx = '_'; break;
 	case EM_IA_64:	 reltype = R_IA64_IMM64;   gpfx = '_'; break;
 	case EM_METAG:	 reltype = R_METAG_ADDR32;
 			 altmcount = "_mcount_wrapper";
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 9d1421e63ff8..49b582a225b0 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -163,11 +163,11 @@ static int mcount_adjust = 0;
 
 static int MIPS_is_fake_mcount(Elf_Rel const *rp)
 {
-	static Elf_Addr old_r_offset;
+	static Elf_Addr old_r_offset = ~(Elf_Addr)0;
 	Elf_Addr current_r_offset = _w(rp->r_offset);
 	int is_fake;
 
-	is_fake = old_r_offset &&
+	is_fake = (old_r_offset != ~(Elf_Addr)0) &&
 		(current_r_offset - old_r_offset == MIPS_FAKEMCOUNT_OFFSET);
 	old_r_offset = current_r_offset;
 
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 91280b82da08..397b6b84e8c5 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -279,6 +279,11 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_ARM_(CALL|PC24|THM_CALL)" .
 			"\\s+(__gnu_mcount_nc|mcount)\$";
 
+} elsif ($arch eq "arm64") {
+    $alignment = 3;
+    $section_type = '%progbits';
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_AARCH64_CALL26\\s+_mcount\$";
+    $type = ".quad";
 } elsif ($arch eq "ia64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
     $type = "data8";
diff --git a/security/commoncap.c b/security/commoncap.c
index b9d613e0ef14..963dc5981661 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -421,6 +421,9 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data
 		cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable);
 	}
 
+	cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
 	return 0;
 }
 
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index d3b6d2cd3a06..6e4e6eb732fe 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -308,57 +308,139 @@ static int devcgroup_seq_show(struct seq_file *m, void *v)
 }
 
 /**
- * may_access - verifies if a new exception is part of what is allowed
- *		by a dev cgroup based on the default policy +
- *		exceptions. This is used to make sure a child cgroup
- *		won't have more privileges than its parent or to
- *		verify if a certain access is allowed.
- * @dev_cgroup: dev cgroup to be tested against
- * @refex: new exception
- * @behavior: behavior of the exception
+ * match_exception	- iterates the exception list trying to match a rule
+ * 			  based on type, major, minor and access type. It is
+ * 			  considered a match if an exception is found that
+ * 			  will contain the entire range of provided parameters.
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * returns: true in case it matches an exception completely
  */
-static bool may_access(struct dev_cgroup *dev_cgroup,
-		       struct dev_exception_item *refex,
-		       enum devcg_behavior behavior)
+static bool match_exception(struct list_head *exceptions, short type,
+			    u32 major, u32 minor, short access)
 {
 	struct dev_exception_item *ex;
-	bool match = false;
 
-	rcu_lockdep_assert(rcu_read_lock_held() ||
-			   lockdep_is_held(&devcgroup_mutex),
-			   "device_cgroup::may_access() called without proper synchronization");
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+			continue;
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+			continue;
+		if (ex->major != ~0 && ex->major != major)
+			continue;
+		if (ex->minor != ~0 && ex->minor != minor)
+			continue;
+		/* provided access cannot have more than the exception rule */
+		if (access & (~ex->access))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * match_exception_partial - iterates the exception list trying to match a rule
+ * 			     based on type, major, minor and access type. It is
+ * 			     considered a match if an exception's range is
+ * 			     found to contain *any* of the devices specified by
+ * 			     provided parameters. This is used to make sure no
+ * 			     extra access is being granted that is forbidden by
+ * 			     any of the exception list.
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * returns: true in case the provided range mat matches an exception completely
+ */
+static bool match_exception_partial(struct list_head *exceptions, short type,
+				    u32 major, u32 minor, short access)
+{
+	struct dev_exception_item *ex;
 
-	list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) {
-		if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
 			continue;
-		if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
 			continue;
-		if (ex->major != ~0 && ex->major != refex->major)
+		/*
+		 * We must be sure that both the exception and the provided
+		 * range aren't masking all devices
+		 */
+		if (ex->major != ~0 && major != ~0 && ex->major != major)
 			continue;
-		if (ex->minor != ~0 && ex->minor != refex->minor)
+		if (ex->minor != ~0 && minor != ~0 && ex->minor != minor)
 			continue;
-		if (refex->access & (~ex->access))
+		/*
+		 * In order to make sure the provided range isn't matching
+		 * an exception, all its access bits shouldn't match the
+		 * exception's access bits
+		 */
+		if (!(access & ex->access))
 			continue;
-		match = true;
-		break;
+		return true;
 	}
+	return false;
+}
+
+/**
+ * verify_new_ex - verifies if a new exception is part of what is allowed
+ *		   by a dev cgroup based on the default policy +
+ *		   exceptions. This is used to make sure a child cgroup
+ *		   won't have more privileges than its parent
+ * @dev_cgroup: dev cgroup to be tested against
+ * @refex: new exception
+ * @behavior: behavior of the exception's dev_cgroup
+ */
+static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
+		          struct dev_exception_item *refex,
+		          enum devcg_behavior behavior)
+{
+	bool match = false;
+
+	rcu_lockdep_assert(rcu_read_lock_held() ||
+			   lockdep_is_held(&devcgroup_mutex),
+			   "device_cgroup:verify_new_ex called without proper synchronization");
 
 	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
 		if (behavior == DEVCG_DEFAULT_ALLOW) {
-			/* the exception will deny access to certain devices */
+			/*
+			 * new exception in the child doesn't matter, only
+			 * adding extra restrictions
+			 */
 			return true;
 		} else {
-			/* the exception will allow access to certain devices */
+			/*
+			 * new exception in the child will add more devices
+			 * that can be acessed, so it can't match any of
+			 * parent's exceptions, even slightly
+			 */
+			match = match_exception_partial(&dev_cgroup->exceptions,
+							refex->type,
+							refex->major,
+							refex->minor,
+							refex->access);
+
 			if (match)
-				/*
-				 * a new exception allowing access shouldn't
-				 * match an parent's exception
-				 */
 				return false;
 			return true;
 		}
 	} else {
-		/* only behavior == DEVCG_DEFAULT_DENY allowed here */
+		/*
+		 * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore
+		 * the new exception will add access to more devices and must
+		 * be contained completely in an parent's exception to be
+		 * allowed
+		 */
+		match = match_exception(&dev_cgroup->exceptions, refex->type,
+					refex->major, refex->minor,
+					refex->access);
+
 		if (match)
 			/* parent has an exception that matches the proposed */
 			return true;
@@ -380,7 +462,38 @@ static int parent_has_perm(struct dev_cgroup *childcg,
 
 	if (!parent)
 		return 1;
-	return may_access(parent, ex, childcg->behavior);
+	return verify_new_ex(parent, ex, childcg->behavior);
+}
+
+/**
+ * parent_allows_removal - verify if it's ok to remove an exception
+ * @childcg: child cgroup from where the exception will be removed
+ * @ex: exception being removed
+ *
+ * When removing an exception in cgroups with default ALLOW policy, it must
+ * be checked if removing it will give the child cgroup more access than the
+ * parent.
+ *
+ * Return: true if it's ok to remove exception, false otherwise
+ */
+static bool parent_allows_removal(struct dev_cgroup *childcg,
+				  struct dev_exception_item *ex)
+{
+	struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css));
+
+	if (!parent)
+		return true;
+
+	/* It's always allowed to remove access to devices */
+	if (childcg->behavior == DEVCG_DEFAULT_DENY)
+		return true;
+
+	/*
+	 * Make sure you're not removing part or a whole exception existing in
+	 * the parent cgroup
+	 */
+	return !match_exception_partial(&parent->exceptions, ex->type,
+					ex->major, ex->minor, ex->access);
 }
 
 /**
@@ -618,17 +731,21 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 
 	switch (filetype) {
 	case DEVCG_ALLOW:
-		if (!parent_has_perm(devcgroup, &ex))
-			return -EPERM;
 		/*
 		 * If the default policy is to allow by default, try to remove
 		 * an matching exception instead. And be silent about it: we
 		 * don't want to break compatibility
 		 */
 		if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+			/* Check if the parent allows removing it first */
+			if (!parent_allows_removal(devcgroup, &ex))
+				return -EPERM;
 			dev_exception_rm(devcgroup, &ex);
-			return 0;
+			break;
 		}
+
+		if (!parent_has_perm(devcgroup, &ex))
+			return -EPERM;
 		rc = dev_exception_add(devcgroup, &ex);
 		break;
 	case DEVCG_DENY:
@@ -708,18 +825,18 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor,
 				        short access)
 {
 	struct dev_cgroup *dev_cgroup;
-	struct dev_exception_item ex;
-	int rc;
-
-	memset(&ex, 0, sizeof(ex));
-	ex.type = type;
-	ex.major = major;
-	ex.minor = minor;
-	ex.access = access;
+	bool rc;
 
 	rcu_read_lock();
 	dev_cgroup = task_devcgroup(current);
-	rc = may_access(dev_cgroup, &ex, dev_cgroup->behavior);
+	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW)
+		/* Can't match any of the exceptions, even partially */
+		rc = !match_exception_partial(&dev_cgroup->exceptions,
+					      type, major, minor, access);
+	else
+		/* Need to match completely one exception to be allowed */
+		rc = match_exception(&dev_cgroup->exceptions, type, major,
+				     minor, access);
 	rcu_read_unlock();
 
 	if (!rc)
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 336b3ddfe63f..7e71e066198f 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -269,6 +269,13 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name,
 		goto out;
 	}
 	evm_status = evm_verify_current_integrity(dentry);
+	if (evm_status == INTEGRITY_NOXATTRS) {
+		struct integrity_iint_cache *iint;
+
+		iint = integrity_iint_find(dentry->d_inode);
+		if (iint && (iint->flags & IMA_NEW_FILE))
+			return 0;
+	}
 out:
 	if (evm_status != INTEGRITY_PASS)
 		integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode,
@@ -285,12 +292,23 @@ out:
  * @xattr_value: pointer to the new extended attribute value
  * @xattr_value_len: pointer to the new extended attribute value length
  *
- * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that
- * the current value is valid.
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
  */
 int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
+		if (!xattr_value_len)
+			return -EINVAL;
+		if (xattr_data->type != EVM_IMA_XATTR_DIGSIG)
+			return -EPERM;
+	}
 	return evm_protect_xattr(dentry, xattr_name, xattr_value,
 				 xattr_value_len);
 }
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 0356e1d437ca..f79fa8be203c 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -27,7 +27,7 @@
 #include "../integrity.h"
 
 enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
-		     IMA_SHOW_ASCII };
+		     IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII };
 enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 
 /* digest size for IMA, fits SHA1 or MD5 */
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index c38bbce8c6a6..025824af08e0 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -199,6 +199,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 			    struct evm_ima_xattr_data **xattr_value,
 			    int *xattr_len)
 {
+	const char *audit_cause = "failed";
 	struct inode *inode = file_inode(file);
 	const char *filename = file->f_dentry->d_name.name;
 	int result = 0;
@@ -213,6 +214,12 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	if (!(iint->flags & IMA_COLLECTED)) {
 		u64 i_version = file_inode(file)->i_version;
 
+		if (file->f_flags & O_DIRECT) {
+			audit_cause = "failed(directio)";
+			result = -EACCES;
+			goto out;
+		}
+
 		/* use default hash algorithm */
 		hash.hdr.algo = ima_hash_algo;
 
@@ -233,9 +240,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 				result = -ENOMEM;
 		}
 	}
+out:
 	if (result)
 		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
-				    filename, "collect_data", "failed",
+				    filename, "collect_data", audit_cause,
 				    result, 0);
 	return result;
 }
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 734e9468aca0..6df1b2527d02 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -194,8 +194,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			goto out;
 
 		cause = "missing-hash";
-		status =
-		    (inode->i_size == 0) ? INTEGRITY_PASS : INTEGRITY_NOLABEL;
+		status = INTEGRITY_NOLABEL;
+		if (inode->i_size == 0) {
+			iint->flags |= IMA_NEW_FILE;
+			status = INTEGRITY_PASS;
+		}
 		goto out;
 	}
 
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index fdf60def52e9..b5c126fe0bd9 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -25,6 +25,36 @@
 
 static struct crypto_shash *ima_shash_tfm;
 
+/**
+ * ima_kernel_read - read file content
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+static int ima_kernel_read(struct file *file, loff_t offset,
+			   char *addr, unsigned long count)
+{
+	mm_segment_t old_fs;
+	char __user *buf = addr;
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!file->f_op->read && !file->f_op->aio_read)
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, &offset);
+	else
+		ret = do_sync_read(file, buf, count, &offset);
+	set_fs(old_fs);
+	return ret;
+}
+
 int ima_init_crypto(void)
 {
 	long rc;
@@ -98,7 +128,7 @@ static int ima_calc_file_hash_tfm(struct file *file,
 	while (offset < i_size) {
 		int rbuf_len;
 
-		rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE);
+		rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE);
 		if (rbuf_len < 0) {
 			rc = rbuf_len;
 			break;
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index db01125926bd..468a3ba3c539 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -160,6 +160,8 @@ static int ima_measurements_show(struct seq_file *m, void *v)
 
 		if (is_ima_template && strcmp(field->field_id, "d") == 0)
 			show = IMA_SHOW_BINARY_NO_FIELD_LEN;
+		if (is_ima_template && strcmp(field->field_id, "n") == 0)
+			show = IMA_SHOW_BINARY_OLD_STRING_FMT;
 		field->field_show(m, show, &e->template_data[i]);
 	}
 	return 0;
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 149ee1119f87..9f70efd08058 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -131,11 +131,13 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint,
 		return;
 
 	mutex_lock(&inode->i_mutex);
-	if (atomic_read(&inode->i_writecount) == 1 &&
-	    iint->version != inode->i_version) {
-		iint->flags &= ~IMA_DONE_MASK;
-		if (iint->flags & IMA_APPRAISE)
-			ima_update_xattr(iint, file);
+	if (atomic_read(&inode->i_writecount) == 1) {
+		if ((iint->version != inode->i_version) ||
+		    (iint->flags & IMA_NEW_FILE)) {
+			iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
+			if (iint->flags & IMA_APPRAISE)
+				ima_update_xattr(iint, file);
+		}
 	}
 	mutex_unlock(&inode->i_mutex);
 }
@@ -217,8 +219,11 @@ static int process_measurement(struct file *file, const char *filename,
 		xattr_ptr = &xattr_value;
 
 	rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
-	if (rc != 0)
+	if (rc != 0) {
+		if (file->f_flags & O_DIRECT)
+			rc = (iint->flags & IMA_PERMIT_DIRECTIO) ? 0 : -EACCES;
 		goto out_digsig;
+	}
 
 	pathname = !filename ? ima_d_path(&file->f_path, &pathbuf) : filename;
 	if (!pathname)
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index a9c3d3cd1990..085c4964be99 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -351,7 +351,7 @@ enum {
 	Opt_obj_user, Opt_obj_role, Opt_obj_type,
 	Opt_subj_user, Opt_subj_role, Opt_subj_type,
 	Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner,
-	Opt_appraise_type, Opt_fsuuid
+	Opt_appraise_type, Opt_fsuuid, Opt_permit_directio
 };
 
 static match_table_t policy_tokens = {
@@ -373,6 +373,7 @@ static match_table_t policy_tokens = {
 	{Opt_uid, "uid=%s"},
 	{Opt_fowner, "fowner=%s"},
 	{Opt_appraise_type, "appraise_type=%s"},
+	{Opt_permit_directio, "permit_directio"},
 	{Opt_err, NULL}
 };
 
@@ -621,6 +622,9 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 			else
 				result = -EINVAL;
 			break;
+		case Opt_permit_directio:
+			entry->flags |= IMA_PERMIT_DIRECTIO;
+			break;
 		case Opt_err:
 			ima_log_string(ab, "UNKNOWN", p);
 			result = -EINVAL;
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
index 1683bbf289a4..e8592e7bfc21 100644
--- a/security/integrity/ima/ima_template_lib.c
+++ b/security/integrity/ima/ima_template_lib.c
@@ -109,13 +109,16 @@ static void ima_show_template_data_binary(struct seq_file *m,
 					  enum data_formats datafmt,
 					  struct ima_field_data *field_data)
 {
+	u32 len = (show == IMA_SHOW_BINARY_OLD_STRING_FMT) ?
+	    strlen(field_data->data) : field_data->len;
+
 	if (show != IMA_SHOW_BINARY_NO_FIELD_LEN)
-		ima_putc(m, &field_data->len, sizeof(u32));
+		ima_putc(m, &len, sizeof(len));
 
-	if (!field_data->len)
+	if (!len)
 		return;
 
-	ima_putc(m, field_data->data, field_data->len);
+	ima_putc(m, field_data->data, len);
 }
 
 static void ima_show_template_field_data(struct seq_file *m,
@@ -129,6 +132,7 @@ static void ima_show_template_field_data(struct seq_file *m,
 		break;
 	case IMA_SHOW_BINARY:
 	case IMA_SHOW_BINARY_NO_FIELD_LEN:
+	case IMA_SHOW_BINARY_OLD_STRING_FMT:
 		ima_show_template_data_binary(m, show, datafmt, field_data);
 		break;
 	default:
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 2fb5e53e927f..2f8715d77a5a 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -30,6 +30,8 @@
 #define IMA_ACTION_FLAGS	0xff000000
 #define IMA_DIGSIG		0x01000000
 #define IMA_DIGSIG_REQUIRED	0x02000000
+#define IMA_PERMIT_DIRECTIO	0x04000000
+#define IMA_NEW_FILE		0x08000000
 
 #define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
 				 IMA_APPRAISE_SUBMASK)
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 9e1e005c7596..c4c8df4b214d 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -1018,10 +1018,13 @@ static int __init init_encrypted(void)
 	ret = encrypted_shash_alloc();
 	if (ret < 0)
 		return ret;
+	ret = aes_get_sizes();
+	if (ret < 0)
+		goto out;
 	ret = register_key_type(&key_type_encrypted);
 	if (ret < 0)
 		goto out;
-	return aes_get_sizes();
+	return 0;
 out:
 	encrypted_shash_release();
 	return ret;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b332e2cc0954..47b5c69e4605 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -470,6 +470,7 @@ next_inode:
 				list_entry(sbsec->isec_head.next,
 					   struct inode_security_struct, list);
 		struct inode *inode = isec->inode;
+		list_del_init(&isec->list);
 		spin_unlock(&sbsec->isec_lock);
 		inode = igrab(inode);
 		if (inode) {
@@ -478,7 +479,6 @@ next_inode:
 			iput(inode);
 		}
 		spin_lock(&sbsec->isec_lock);
-		list_del_init(&isec->list);
 		goto next_inode;
 	}
 	spin_unlock(&sbsec->isec_lock);
@@ -1418,15 +1418,33 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 		isec->sid = sbsec->sid;
 
 		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
-			if (opt_dentry) {
-				isec->sclass = inode_mode_to_security_class(inode->i_mode);
-				rc = selinux_proc_get_sid(opt_dentry,
-							  isec->sclass,
-							  &sid);
-				if (rc)
-					goto out_unlock;
-				isec->sid = sid;
-			}
+			/* We must have a dentry to determine the label on
+			 * procfs inodes */
+			if (opt_dentry)
+				/* Called from d_instantiate or
+				 * d_splice_alias. */
+				dentry = dget(opt_dentry);
+			else
+				/* Called from selinux_complete_init, try to
+				 * find a dentry. */
+				dentry = d_find_alias(inode);
+			/*
+			 * This can be hit on boot when a file is accessed
+			 * before the policy is loaded.  When we load policy we
+			 * may find inodes that have no dentry on the
+			 * sbsec->isec_head list.  No reason to complain as
+			 * these will get fixed up the next time we go through
+			 * inode_doinit() with a dentry, before these inodes
+			 * could be used again by userspace.
+			 */
+			if (!dentry)
+				goto out_unlock;
+			isec->sclass = inode_mode_to_security_class(inode->i_mode);
+			rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+			dput(dentry);
+			if (rc)
+				goto out_unlock;
+			isec->sid = sid;
 		}
 		break;
 	}
diff --git a/sound/core/control.c b/sound/core/control.c
index d8aa206e8bde..98a29b26c5f4 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -289,6 +289,10 @@ static bool snd_ctl_remove_numid_conflict(struct snd_card *card,
 {
 	struct snd_kcontrol *kctl;
 
+	/* Make sure that the ids assigned to the control do not wrap around */
+	if (card->last_numid >= UINT_MAX - count)
+		card->last_numid = 0;
+
 	list_for_each_entry(kctl, &card->controls, list) {
 		if (kctl->id.numid < card->last_numid + 1 + count &&
 		    kctl->id.numid + kctl->count > card->last_numid + 1) {
@@ -331,6 +335,7 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 {
 	struct snd_ctl_elem_id id;
 	unsigned int idx;
+	unsigned int count;
 	int err = -EINVAL;
 
 	if (! kcontrol)
@@ -338,6 +343,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	if (snd_BUG_ON(!card || !kcontrol->info))
 		goto error;
 	id = kcontrol->id;
+	if (id.index > UINT_MAX - kcontrol->count)
+		goto error;
+
 	down_write(&card->controls_rwsem);
 	if (snd_ctl_find_id(card, &id)) {
 		up_write(&card->controls_rwsem);
@@ -359,8 +367,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -389,6 +398,7 @@ int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol,
 		    bool add_on_replace)
 {
 	struct snd_ctl_elem_id id;
+	unsigned int count;
 	unsigned int idx;
 	struct snd_kcontrol *old;
 	int ret;
@@ -424,8 +434,9 @@ add:
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -898,9 +909,9 @@ static int snd_ctl_elem_write(struct snd_card *card, struct snd_ctl_file *file,
 			result = kctl->put(kctl, control);
 		}
 		if (result > 0) {
+			struct snd_ctl_elem_id id = control->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
-				       &control->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id);
 			return 0;
 		}
 	}
@@ -992,6 +1003,7 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file,
 
 struct user_element {
 	struct snd_ctl_elem_info info;
+	struct snd_card *card;
 	void *elem_data;		/* element data */
 	unsigned long elem_data_size;	/* size of element data in bytes */
 	void *tlv_data;			/* TLV data */
@@ -1035,7 +1047,9 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol,
 {
 	struct user_element *ue = kcontrol->private_data;
 
+	mutex_lock(&ue->card->user_ctl_lock);
 	memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return 0;
 }
 
@@ -1044,10 +1058,12 @@ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol,
 {
 	int change;
 	struct user_element *ue = kcontrol->private_data;
-	
+
+	mutex_lock(&ue->card->user_ctl_lock);
 	change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0;
 	if (change)
 		memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return change;
 }
 
@@ -1067,19 +1083,32 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol,
 		new_data = memdup_user(tlv, size);
 		if (IS_ERR(new_data))
 			return PTR_ERR(new_data);
+		mutex_lock(&ue->card->user_ctl_lock);
 		change = ue->tlv_data_size != size;
 		if (!change)
 			change = memcmp(ue->tlv_data, new_data, size);
 		kfree(ue->tlv_data);
 		ue->tlv_data = new_data;
 		ue->tlv_data_size = size;
+		mutex_unlock(&ue->card->user_ctl_lock);
 	} else {
-		if (! ue->tlv_data_size || ! ue->tlv_data)
-			return -ENXIO;
-		if (size < ue->tlv_data_size)
-			return -ENOSPC;
+		int ret = 0;
+
+		mutex_lock(&ue->card->user_ctl_lock);
+		if (!ue->tlv_data_size || !ue->tlv_data) {
+			ret = -ENXIO;
+			goto err_unlock;
+		}
+		if (size < ue->tlv_data_size) {
+			ret = -ENOSPC;
+			goto err_unlock;
+		}
 		if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size))
-			return -EFAULT;
+			ret = -EFAULT;
+err_unlock:
+		mutex_unlock(&ue->card->user_ctl_lock);
+		if (ret)
+			return ret;
 	}
 	return change;
 }
@@ -1137,8 +1166,6 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	struct user_element *ue;
 	int idx, err;
 
-	if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS)
-		return -ENOMEM;
 	if (info->count < 1)
 		return -EINVAL;
 	access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE :
@@ -1147,21 +1174,16 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 				 SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE));
 	info->id.numid = 0;
 	memset(&kctl, 0, sizeof(kctl));
-	down_write(&card->controls_rwsem);
-	_kctl = snd_ctl_find_id(card, &info->id);
-	err = 0;
-	if (_kctl) {
-		if (replace)
-			err = snd_ctl_remove(card, _kctl);
-		else
-			err = -EBUSY;
-	} else {
-		if (replace)
-			err = -ENOENT;
+
+	if (replace) {
+		err = snd_ctl_remove_user_ctl(file, &info->id);
+		if (err)
+			return err;
 	}
-	up_write(&card->controls_rwsem);
-	if (err < 0)
-		return err;
+
+	if (card->user_ctl_count >= MAX_USER_CONTROLS)
+		return -ENOMEM;
+
 	memcpy(&kctl.id, &info->id, sizeof(info->id));
 	kctl.count = info->owner ? info->owner : 1;
 	access |= SNDRV_CTL_ELEM_ACCESS_USER;
@@ -1211,6 +1233,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL);
 	if (ue == NULL)
 		return -ENOMEM;
+	ue->card = card;
 	ue->info = *info;
 	ue->info.access = 0;
 	ue->elem_data = (char *)ue + sizeof(*ue);
@@ -1322,8 +1345,9 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file,
 		}
 		err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv);
 		if (err > 0) {
+			struct snd_ctl_elem_id id = kctl->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id);
 			return 0;
 		}
 	} else {
diff --git a/sound/core/info.c b/sound/core/info.c
index e79baa11b60e..08070e1eefeb 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -679,7 +679,7 @@ int snd_info_card_free(struct snd_card *card)
  * snd_info_get_line - read one line from the procfs buffer
  * @buffer: the procfs buffer
  * @line: the buffer to store
- * @len: the max. buffer size - 1
+ * @len: the max. buffer size
  *
  * Reads one line from the buffer and stores the string.
  *
@@ -699,7 +699,7 @@ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len)
 			buffer->stop = 1;
 		if (c == '\n')
 			break;
-		if (len) {
+		if (len > 1) {
 			len--;
 			*line++ = c;
 		}
diff --git a/sound/core/init.c b/sound/core/init.c
index 0d42fcda0de2..39c25167add8 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -218,6 +218,7 @@ int snd_card_create(int idx, const char *xid,
 	INIT_LIST_HEAD(&card->devices);
 	init_rwsem(&card->controls_rwsem);
 	rwlock_init(&card->ctl_files_rwlock);
+	mutex_init(&card->user_ctl_lock);
 	INIT_LIST_HEAD(&card->controls);
 	INIT_LIST_HEAD(&card->ctl_files);
 	spin_lock_init(&card->files_lock);
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index af49721ba0e3..c4ac3c1e19af 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -206,6 +206,8 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream,
 	if (err < 0)
 		return err;
 
+	if (clear_user(src, sizeof(*src)))
+		return -EFAULT;
 	if (put_user(status.state, &src->state) ||
 	    compat_put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) ||
 	    compat_put_timespec(&status.tstamp, &src->tstamp) ||
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index a2104671f51d..e1ef106c8a6f 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1783,14 +1783,16 @@ static int snd_pcm_lib_ioctl_fifo_size(struct snd_pcm_substream *substream,
 {
 	struct snd_pcm_hw_params *params = arg;
 	snd_pcm_format_t format;
-	int channels, width;
+	int channels;
+	ssize_t frame_size;
 
 	params->fifo_size = substream->runtime->hw.fifo_size;
 	if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_FIFO_IN_FRAMES)) {
 		format = params_format(params);
 		channels = params_channels(params);
-		width = snd_pcm_format_physical_width(format);
-		params->fifo_size /= width * channels;
+		frame_size = snd_pcm_format_size(format, channels);
+		if (frame_size > 0)
+			params->fifo_size /= (unsigned)frame_size;
 	}
 	return 0;
 }
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 01a5e05ede95..566b0f69d628 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -3189,7 +3189,7 @@ static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = {
 
 #ifndef ARCH_HAS_DMA_MMAP_COHERENT
 /* This should be defined / handled globally! */
-#ifdef CONFIG_ARM
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
 #define ARCH_HAS_DMA_MMAP_COHERENT
 #endif
 #endif
diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig
index 8756c8e32922..46e563046bfb 100644
--- a/sound/pci/Kconfig
+++ b/sound/pci/Kconfig
@@ -859,8 +859,8 @@ config SND_VIRTUOSO
 	select SND_JACK if INPUT=y || INPUT=SND
 	help
 	  Say Y here to include support for sound cards based on the
-	  Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS,
-	  Essence ST (Deluxe), and Essence STX.
+	  Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX,
+	  Essence ST (Deluxe), and Essence STX (II).
 	  Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental;
 	  for the Xense, missing.
 
diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c
index cae36597aa71..0a34b5f1c475 100644
--- a/sound/pci/emu10k1/emu10k1_callback.c
+++ b/sound/pci/emu10k1/emu10k1_callback.c
@@ -85,6 +85,8 @@ snd_emu10k1_ops_setup(struct snd_emux *emux)
  * get more voice for pcm
  *
  * terminate most inactive voice and give it as a pcm voice.
+ *
+ * voice_lock is already held.
  */
 int
 snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
@@ -92,12 +94,10 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
 	struct snd_emux *emu;
 	struct snd_emux_voice *vp;
 	struct best_voice best[V_END];
-	unsigned long flags;
 	int i;
 
 	emu = hw->synth;
 
-	spin_lock_irqsave(&emu->voice_lock, flags);
 	lookup_voices(emu, hw, best, 1); /* no OFF voices */
 	for (i = 0; i < V_END; i++) {
 		if (best[i].voice >= 0) {
@@ -113,11 +113,9 @@ snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
 			vp->emu->num_voices--;
 			vp->ch = -1;
 			vp->state = SNDRV_EMUX_ST_OFF;
-			spin_unlock_irqrestore(&emu->voice_lock, flags);
 			return ch;
 		}
 	}
-	spin_unlock_irqrestore(&emu->voice_lock, flags);
 
 	/* not found */
 	return -ENOMEM;
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index dafcf82139e2..f6e5c4ed03ed 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -338,8 +338,10 @@ int snd_hda_get_sub_nodes(struct hda_codec *codec, hda_nid_t nid,
 	unsigned int parm;
 
 	parm = snd_hda_param_read(codec, nid, AC_PAR_NODE_COUNT);
-	if (parm == -1)
+	if (parm == -1) {
+		*start_id = 0;
 		return 0;
+	}
 	*start_id = (parm >> 16) & 0x7fff;
 	return (int)(parm & 0x7fff);
 }
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index e354ab1ec20f..103e85a13f35 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -297,9 +297,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define ULI_NUM_CAPTURE		5
 #define ULI_NUM_PLAYBACK	6
 
-/* ATI HDMI may have up to 8 playbacks and 0 capture */
+/* ATI HDMI has 1 playback and 0 capture */
 #define ATIHDMI_NUM_CAPTURE	0
-#define ATIHDMI_NUM_PLAYBACK	8
+#define ATIHDMI_NUM_PLAYBACK	1
 
 /* TERA has 4 playback and 3 capture */
 #define TERA_NUM_CAPTURE	3
@@ -2930,7 +2930,7 @@ static int azx_suspend(struct device *dev)
 	struct azx *chip = card->private_data;
 	struct azx_pcm *p;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
@@ -2961,7 +2961,7 @@ static int azx_resume(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip = card->private_data;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
@@ -2996,7 +2996,7 @@ static int azx_runtime_suspend(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip = card->private_data;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	if (!(chip->driver_caps & AZX_DCAPS_PM_RUNTIME))
@@ -3022,7 +3022,7 @@ static int azx_runtime_resume(struct device *dev)
 	struct hda_codec *codec;
 	int status;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	if (!(chip->driver_caps & AZX_DCAPS_PM_RUNTIME))
@@ -3057,7 +3057,7 @@ static int azx_runtime_idle(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip = card->private_data;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	if (!power_save_controller ||
@@ -3988,6 +3988,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	/* Lynx Point */
 	{ PCI_DEVICE(0x8086, 0x8c20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	/* 9 Series */
+	{ PCI_DEVICE(0x8086, 0x8ca0),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* Wellsburg */
 	{ PCI_DEVICE(0x8086, 0x8d20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
@@ -4024,6 +4027,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	/* BayTrail */
 	{ PCI_DEVICE(0x8086, 0x0f04),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH_NOPM },
+	/* Braswell */
+	{ PCI_DEVICE(0x8086, 0x2284),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* ICH */
 	{ PCI_DEVICE(0x8086, 0x2668),
 	  .driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC |
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 8ed0bcc01386..1a05efa08d96 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -333,6 +333,8 @@ static const struct hda_fixup ad1986a_fixups[] = {
 
 static const struct snd_pci_quirk ad1986a_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x30af, "HP B2800", AD1986A_FIXUP_LAPTOP_IMIC),
+	SND_PCI_QUIRK(0x1043, 0x1443, "ASUS Z99He", AD1986A_FIXUP_EAPD),
+	SND_PCI_QUIRK(0x1043, 0x1447, "ASUS A8JN", AD1986A_FIXUP_EAPD),
 	SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8100, "ASUS P5", AD1986A_FIXUP_3STACK),
 	SND_PCI_QUIRK_MASK(0x1043, 0xff00, 0x8200, "ASUS M2", AD1986A_FIXUP_3STACK),
 	SND_PCI_QUIRK(0x10de, 0xcb84, "ASUS A8N-VM", AD1986A_FIXUP_3STACK),
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 46ecdbb9053f..d5843da4ae19 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -4379,6 +4379,9 @@ static void ca0132_download_dsp(struct hda_codec *codec)
 	return; /* NOP */
 #endif
 
+	if (spec->dsp_state == DSP_DOWNLOAD_FAILED)
+		return; /* don't retry failures */
+
 	chipio_enable_clocks(codec);
 	spec->dsp_state = DSP_DOWNLOADING;
 	if (!ca0132_download_dsp_images(codec))
@@ -4555,7 +4558,8 @@ static int ca0132_init(struct hda_codec *codec)
 	struct auto_pin_cfg *cfg = &spec->autocfg;
 	int i;
 
-	spec->dsp_state = DSP_DOWNLOAD_INIT;
+	if (spec->dsp_state != DSP_DOWNLOAD_FAILED)
+		spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->curr_chip_addx = INVALID_CHIP_ADDRESS;
 
 	snd_hda_power_up(codec);
@@ -4666,6 +4670,7 @@ static int patch_ca0132(struct hda_codec *codec)
 	codec->spec = spec;
 	spec->codec = codec;
 
+	spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->num_mixers = 1;
 	spec->mixers[0] = ca0132_mixer;
 
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index bcf91bea3317..ffc19464b978 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -3237,6 +3237,7 @@ enum {
 	CXT_FIXUP_HEADPHONE_MIC_PIN,
 	CXT_FIXUP_HEADPHONE_MIC,
 	CXT_FIXUP_GPIO1,
+	CXT_FIXUP_ASPIRE_DMIC,
 	CXT_FIXUP_THINKPAD_ACPI,
 };
 
@@ -3397,6 +3398,12 @@ static const struct hda_fixup cxt_fixups[] = {
 			{ }
 		},
 	},
+	[CXT_FIXUP_ASPIRE_DMIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = cxt_fixup_stereo_dmic,
+		.chained = true,
+		.chain_id = CXT_FIXUP_GPIO1,
+	},
 	[CXT_FIXUP_THINKPAD_ACPI] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = hda_fixup_thinkpad_acpi,
@@ -3410,7 +3417,7 @@ static const struct snd_pci_quirk cxt5051_fixups[] = {
 
 static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC),
-	SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_GPIO1),
+	SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 5ef95034d041..611110a3f1a4 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1062,6 +1062,7 @@ static void hdmi_pin_setup_infoframe(struct hda_codec *codec,
 {
 	union audio_infoframe ai;
 
+	memset(&ai, 0, sizeof(ai));
 	if (conn_type == 0) { /* HDMI */
 		struct hdmi_audio_infoframe *hdmi_ai = &ai.hdmi;
 
@@ -1123,8 +1124,10 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 					    AMP_OUT_UNMUTE);
 
 	eld = &per_pin->sink_eld;
-	if (!eld->monitor_present)
+	if (!eld->monitor_present) {
+		hdmi_set_channel_count(codec, per_pin->cvt_nid, channels);
 		return;
+	}
 
 	if (!non_pcm && per_pin->chmap_set)
 		ca = hdmi_manual_channel_allocation(channels, per_pin->chmap);
@@ -1554,19 +1557,22 @@ static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
 		}
 	}
 
-	if (pin_eld->eld_valid && !eld->eld_valid) {
-		update_eld = true;
+	if (pin_eld->eld_valid != eld->eld_valid)
 		eld_changed = true;
-	}
+
+	if (pin_eld->eld_valid && !eld->eld_valid)
+		update_eld = true;
+
 	if (update_eld) {
 		bool old_eld_valid = pin_eld->eld_valid;
 		pin_eld->eld_valid = eld->eld_valid;
-		eld_changed = pin_eld->eld_size != eld->eld_size ||
+		if (pin_eld->eld_size != eld->eld_size ||
 			      memcmp(pin_eld->eld_buffer, eld->eld_buffer,
-				     eld->eld_size) != 0;
-		if (eld_changed)
+				     eld->eld_size) != 0) {
 			memcpy(pin_eld->eld_buffer, eld->eld_buffer,
 			       eld->eld_size);
+			eld_changed = true;
+		}
 		pin_eld->eld_size = eld->eld_size;
 		pin_eld->info = eld->info;
 
@@ -2163,7 +2169,7 @@ static int generic_hdmi_resume(struct hda_codec *codec)
 	struct hdmi_spec *spec = codec->spec;
 	int pin_idx;
 
-	generic_hdmi_init(codec);
+	codec->patch_ops.init(codec);
 	snd_hda_codec_resume_amp(codec);
 	snd_hda_codec_resume_cache(codec);
 
@@ -3311,6 +3317,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = {
 { .id = 0x80862808, .name = "Broadwell HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x80862880, .name = "CedarTrail HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x80862882, .name = "Valleyview2 HDMI",	.patch = patch_generic_hdmi },
+{ .id = 0x80862883, .name = "Braswell HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x808629fb, .name = "Crestline HDMI",	.patch = patch_generic_hdmi },
 {} /* terminator */
 };
@@ -3367,6 +3374,7 @@ MODULE_ALIAS("snd-hda-codec-id:80862807");
 MODULE_ALIAS("snd-hda-codec-id:80862808");
 MODULE_ALIAS("snd-hda-codec-id:80862880");
 MODULE_ALIAS("snd-hda-codec-id:80862882");
+MODULE_ALIAS("snd-hda-codec-id:80862883");
 MODULE_ALIAS("snd-hda-codec-id:808629fb");
 
 MODULE_LICENSE("GPL");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 8d0a84436674..910f2dbe1b24 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -180,6 +180,8 @@ static void alc_fix_pll(struct hda_codec *codec)
 			    spec->pll_coef_idx);
 	val = snd_hda_codec_read(codec, spec->pll_nid, 0,
 				 AC_VERB_GET_PROC_COEF, 0);
+	if (val == -1)
+		return;
 	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX,
 			    spec->pll_coef_idx);
 	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF,
@@ -325,6 +327,7 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type)
 		case 0x10ec0885:
 		case 0x10ec0887:
 		/*case 0x10ec0889:*/ /* this causes an SPDIF problem */
+		case 0x10ec0900:
 			alc889_coef_init(codec);
 			break;
 		case 0x10ec0888:
@@ -993,6 +996,7 @@ static int alc_codec_rename_from_preset(struct hda_codec *codec)
 
 static const struct snd_pci_quirk beep_white_list[] = {
 	SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1),
+	SND_PCI_QUIRK(0x1043, 0x115d, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x829f, "ASUS", 1),
 	SND_PCI_QUIRK(0x1043, 0x8376, "EeePC", 1),
 	SND_PCI_QUIRK(0x1043, 0x83ce, "EeePC", 1),
@@ -1645,12 +1649,10 @@ static const struct hda_fixup alc260_fixups[] = {
 	[ALC260_FIXUP_COEF] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
-			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x07 },
-			{ 0x20, AC_VERB_SET_PROC_COEF,  0x3040 },
+			{ 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 },
+			{ 0x1a, AC_VERB_SET_PROC_COEF,  0x3040 },
 			{ }
 		},
-		.chained = true,
-		.chain_id = ALC260_FIXUP_HP_PIN_0F,
 	},
 	[ALC260_FIXUP_GPIO1] = {
 		.type = HDA_FIXUP_VERBS,
@@ -1665,8 +1667,8 @@ static const struct hda_fixup alc260_fixups[] = {
 	[ALC260_FIXUP_REPLACER] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
-			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x07 },
-			{ 0x20, AC_VERB_SET_PROC_COEF,  0x3050 },
+			{ 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 },
+			{ 0x1a, AC_VERB_SET_PROC_COEF,  0x3050 },
 			{ }
 		},
 		.chained = true,
@@ -2329,6 +2331,7 @@ static int patch_alc882(struct hda_codec *codec)
 	switch (codec->vendor_id) {
 	case 0x10ec0882:
 	case 0x10ec0885:
+	case 0x10ec0900:
 		break;
 	default:
 		/* ALC883 and variants */
@@ -2766,6 +2769,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up)
 {
 	int val = alc_read_coef_idx(codec, 0x04);
+	if (val == -1)
+		return;
 	if (power_up)
 		val |= 1 << 11;
 	else
@@ -2786,6 +2791,89 @@ static void alc269_shutup(struct hda_codec *codec)
 	snd_hda_shutup_pins(codec);
 }
 
+static void alc283_restore_default_value(struct hda_codec *codec)
+{
+	int val;
+
+	/* Power Down Control */
+	alc_write_coef_idx(codec, 0x03, 0x0002);
+	/* FIFO and filter clock */
+	alc_write_coef_idx(codec, 0x05, 0x0700);
+	/* DMIC control */
+	alc_write_coef_idx(codec, 0x07, 0x0200);
+	/* Analog clock */
+	val = alc_read_coef_idx(codec, 0x06);
+	alc_write_coef_idx(codec, 0x06, (val & ~0x00f0) | 0x0);
+	/* JD */
+	val = alc_read_coef_idx(codec, 0x08);
+	alc_write_coef_idx(codec, 0x08, (val & ~0xfffc) | 0x0c2c);
+	/* JD offset1 */
+	alc_write_coef_idx(codec, 0x0a, 0xcccc);
+	/* JD offset2 */
+	alc_write_coef_idx(codec, 0x0b, 0xcccc);
+	/* LDO1/2/3, DAC/ADC */
+	alc_write_coef_idx(codec, 0x0e, 0x6fc0);
+	/* JD */
+	val = alc_read_coef_idx(codec, 0x0f);
+	alc_write_coef_idx(codec, 0x0f, (val & ~0xf800) | 0x1000);
+	/* Capless */
+	val = alc_read_coef_idx(codec, 0x10);
+	alc_write_coef_idx(codec, 0x10, (val & ~0xfc00) | 0x0c00);
+	/* Class D test 4 */
+	alc_write_coef_idx(codec, 0x3a, 0x0);
+	/* IO power down directly */
+	val = alc_read_coef_idx(codec, 0x0c);
+	alc_write_coef_idx(codec, 0x0c, (val & ~0xfe00) | 0x0);
+	/* ANC */
+	alc_write_coef_idx(codec, 0x22, 0xa0c0);
+	/* AGC MUX */
+	val = alc_read_coefex_idx(codec, 0x53, 0x01);
+	alc_write_coefex_idx(codec, 0x53, 0x01, (val & ~0x000f) | 0x0008);
+	/* DAC simple content protection */
+	val = alc_read_coef_idx(codec, 0x1d);
+	alc_write_coef_idx(codec, 0x1d, (val & ~0x00e0) | 0x0);
+	/* ADC simple content protection */
+	val = alc_read_coef_idx(codec, 0x1f);
+	alc_write_coef_idx(codec, 0x1f, (val & ~0x00e0) | 0x0);
+	/* DAC ADC Zero Detection */
+	alc_write_coef_idx(codec, 0x21, 0x8804);
+	/* PLL */
+	alc_write_coef_idx(codec, 0x2e, 0x2902);
+	/* capless control 2 */
+	alc_write_coef_idx(codec, 0x33, 0xa080);
+	/* capless control 3 */
+	alc_write_coef_idx(codec, 0x34, 0x3400);
+	/* capless control 4 */
+	alc_write_coef_idx(codec, 0x35, 0x2f3e);
+	/* capless control 5 */
+	alc_write_coef_idx(codec, 0x36, 0x0);
+	/* class D test 2 */
+	val = alc_read_coef_idx(codec, 0x38);
+	alc_write_coef_idx(codec, 0x38, (val & ~0x0fff) | 0x0900);
+	/* class D test 3 */
+	alc_write_coef_idx(codec, 0x39, 0x110a);
+	/* class D test 5 */
+	val = alc_read_coef_idx(codec, 0x3b);
+	alc_write_coef_idx(codec, 0x3b, (val & ~0x00f8) | 0x00d8);
+	/* class D test 6 */
+	alc_write_coef_idx(codec, 0x3c, 0x0014);
+	/* classD OCP */
+	alc_write_coef_idx(codec, 0x3d, 0xc2ba);
+	/* classD pure DC test */
+	val = alc_read_coef_idx(codec, 0x42);
+	alc_write_coef_idx(codec, 0x42, (val & ~0x0f80) | 0x0);
+	/* test mode */
+	alc_write_coef_idx(codec, 0x49, 0x0);
+	/* Class D DC enable */
+	val = alc_read_coef_idx(codec, 0x40);
+	alc_write_coef_idx(codec, 0x40, (val & ~0xf800) | 0x9800);
+	/* DC offset */
+	val = alc_read_coef_idx(codec, 0x42);
+	alc_write_coef_idx(codec, 0x42, (val & ~0xf000) | 0x2000);
+	/* Class D amp control */
+	alc_write_coef_idx(codec, 0x37, 0xfc06);
+}
+
 static void alc283_init(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -2793,6 +2881,8 @@ static void alc283_init(struct hda_codec *codec)
 	bool hp_pin_sense;
 	int val;
 
+	alc283_restore_default_value(codec);
+
 	if (!hp_pin)
 		return;
 	hp_pin_sense = snd_hda_jack_detect(codec, hp_pin);
@@ -2836,6 +2926,9 @@ static void alc283_shutup(struct hda_codec *codec)
 
 	alc_write_coef_idx(codec, 0x43, 0x9004);
 
+	/*depop hp during suspend*/
+	alc_write_coef_idx(codec, 0x06, 0x2100);
+
 	snd_hda_codec_write(codec, hp_pin, 0,
 			    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
 
@@ -2980,6 +3073,15 @@ static int alc269_resume(struct hda_codec *codec)
 	snd_hda_codec_resume_cache(codec);
 	alc_inv_dmic_sync(codec, true);
 	hda_call_check_power_status(codec, 0x01);
+
+	/* on some machine, the BIOS will clear the codec gpio data when enter
+	 * suspend, and won't restore the data after resume, so we restore it
+	 * in the driver.
+	 */
+	if (spec->gpio_led)
+		snd_hda_codec_write(codec, codec->afg, 0, AC_VERB_SET_GPIO_DATA,
+			    spec->gpio_led);
+
 	if (spec->has_alc5505_dsp)
 		alc5505_dsp_resume(codec);
 
@@ -3126,8 +3228,9 @@ static void alc269_fixup_mic_mute_hook(void *private_data, int enabled)
 
 	if (spec->mute_led_polarity)
 		enabled = !enabled;
-	pinval = AC_PINCTL_IN_EN |
-		(enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80);
+	pinval = snd_hda_codec_get_pin_target(codec, spec->mute_led_nid);
+	pinval &= ~AC_PINCTL_VREFEN;
+	pinval |= enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80;
 	if (spec->mute_led_nid)
 		snd_hda_set_pin_ctl_cache(codec, spec->mute_led_nid, pinval);
 }
@@ -3847,6 +3950,7 @@ enum {
 	ALC269_FIXUP_HEADSET_MIC,
 	ALC269_FIXUP_QUANTA_MUTE,
 	ALC269_FIXUP_LIFEBOOK,
+	ALC269_FIXUP_LIFEBOOK_EXTMIC,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,
@@ -3974,6 +4078,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_QUANTA_MUTE
 	},
+	[ALC269_FIXUP_LIFEBOOK_EXTMIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1903c }, /* headset mic, with jack detect */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4319,6 +4430,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x061f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0629, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x062c, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x062e, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0632, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x063e, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
@@ -4339,14 +4453,26 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
 	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x2191, "HP Touchsmart 14", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2192, "HP Touchsmart 15", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2210, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2211, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2212, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2214, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -4386,6 +4512,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2334, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4408,6 +4538,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
 	SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
@@ -4423,6 +4554,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
@@ -4522,27 +4654,30 @@ static void alc269_fill_coef(struct hda_codec *codec)
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x017) {
 		val = alc_read_coef_idx(codec, 0x04);
 		/* Power up output pin */
-		alc_write_coef_idx(codec, 0x04, val | (1<<11));
+		if (val != -1)
+			alc_write_coef_idx(codec, 0x04, val | (1<<11));
 	}
 
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x018) {
 		val = alc_read_coef_idx(codec, 0xd);
-		if ((val & 0x0c00) >> 10 != 0x1) {
+		if (val != -1 && (val & 0x0c00) >> 10 != 0x1) {
 			/* Capless ramp up clock control */
 			alc_write_coef_idx(codec, 0xd, val | (1<<10));
 		}
 		val = alc_read_coef_idx(codec, 0x17);
-		if ((val & 0x01c0) >> 6 != 0x4) {
+		if (val != -1 && (val & 0x01c0) >> 6 != 0x4) {
 			/* Class D power on reset */
 			alc_write_coef_idx(codec, 0x17, val | (1<<7));
 		}
 	}
 
 	val = alc_read_coef_idx(codec, 0xd); /* Class D */
-	alc_write_coef_idx(codec, 0xd, val | (1<<14));
+	if (val != -1)
+		alc_write_coef_idx(codec, 0xd, val | (1<<14));
 
 	val = alc_read_coef_idx(codec, 0x4); /* HP */
-	alc_write_coef_idx(codec, 0x4, val | (1<<11));
+	if (val != -1)
+		alc_write_coef_idx(codec, 0x4, val | (1<<11));
 }
 
 /*
@@ -4618,6 +4753,7 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->codec_variant = ALC269_TYPE_ALC285;
 		break;
 	case 0x10ec0286:
+	case 0x10ec0288:
 		spec->codec_variant = ALC269_TYPE_ALC286;
 		break;
 	case 0x10ec0255:
@@ -5184,6 +5320,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0626, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0628, "Dell", ALC668_FIXUP_AUTO_MUTE),
 	SND_PCI_QUIRK(0x1028, 0x064e, "Dell", ALC668_FIXUP_AUTO_MUTE),
+	SND_PCI_QUIRK(0x1028, 0x0696, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0698, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
 	SND_PCI_QUIRK(0x1043, 0x11cd, "Asus N550", ALC662_FIXUP_BASS_1A_CHMAP),
 	SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_BASS_CHMAP),
@@ -5424,6 +5562,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0284, .name = "ALC284", .patch = patch_alc269 },
 	{ .id = 0x10ec0285, .name = "ALC285", .patch = patch_alc269 },
 	{ .id = 0x10ec0286, .name = "ALC286", .patch = patch_alc269 },
+	{ .id = 0x10ec0288, .name = "ALC288", .patch = patch_alc269 },
 	{ .id = 0x10ec0290, .name = "ALC290", .patch = patch_alc269 },
 	{ .id = 0x10ec0292, .name = "ALC292", .patch = patch_alc269 },
 	{ .id = 0x10ec0293, .name = "ALC293", .patch = patch_alc269 },
@@ -5444,6 +5583,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 },
 	{ .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 },
 	{ .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 },
+	{ .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 },
 	{ .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 },
 	{ .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 },
 	{ .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 },
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 3bc29c9b2529..12f28d7e0fdc 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -84,6 +84,7 @@ enum {
 	STAC_DELL_EQ,
 	STAC_ALIENWARE_M17X,
 	STAC_92HD89XX_HP_FRONT_JACK,
+	STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK,
 	STAC_92HD73XX_MODELS
 };
 
@@ -558,8 +559,8 @@ static void stac_init_power_map(struct hda_codec *codec)
 		if (snd_hda_jack_tbl_get(codec, nid))
 			continue;
 		if (def_conf == AC_JACK_PORT_COMPLEX &&
-		    !(spec->vref_mute_led_nid == nid ||
-		      is_jack_detectable(codec, nid))) {
+		    spec->vref_mute_led_nid != nid &&
+		    is_jack_detectable(codec, nid)) {
 			snd_hda_jack_detect_enable_callback(codec, nid,
 							    STAC_PWR_EVENT,
 							    jack_update_power);
@@ -592,9 +593,9 @@ static void stac_store_hints(struct hda_codec *codec)
 			spec->gpio_mask;
 	}
 	if (get_int_hint(codec, "gpio_dir", &spec->gpio_dir))
-		spec->gpio_mask &= spec->gpio_mask;
-	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
 		spec->gpio_dir &= spec->gpio_mask;
+	if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
+		spec->gpio_data &= spec->gpio_mask;
 	if (get_int_hint(codec, "eapd_mask", &spec->eapd_mask))
 		spec->eapd_mask &= spec->gpio_mask;
 	if (get_int_hint(codec, "gpio_mute", &spec->gpio_mute))
@@ -1803,6 +1804,11 @@ static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = {
 	{}
 };
 
+static const struct hda_pintbl stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs[] = {
+	{ 0x0e, 0x400000f0 },
+	{}
+};
+
 static void stac92hd73xx_fixup_ref(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
@@ -1925,6 +1931,10 @@ static const struct hda_fixup stac92hd73xx_fixups[] = {
 	[STAC_92HD89XX_HP_FRONT_JACK] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = stac92hd89xx_hp_front_jack_pin_configs,
+	},
+	[STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs,
 	}
 };
 
@@ -1985,6 +1995,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = {
 		      "Alienware M17x", STAC_ALIENWARE_M17X),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
 		      "Alienware M17x R3", STAC_DELL_EQ),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1927,
+				"HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
 				"unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
 	{} /* terminator */
@@ -4200,11 +4212,18 @@ static int stac_parse_auto_config(struct hda_codec *codec)
 			return err;
 	}
 
-	stac_init_power_map(codec);
-
 	return 0;
 }
 
+static int stac_build_controls(struct hda_codec *codec)
+{
+	int err = snd_hda_gen_build_controls(codec);
+
+	if (err < 0)
+		return err;
+	stac_init_power_map(codec);
+	return 0;
+}
 
 static int stac_init(struct hda_codec *codec)
 {
@@ -4316,7 +4335,7 @@ static int stac_suspend(struct hda_codec *codec)
 #endif /* CONFIG_PM */
 
 static const struct hda_codec_ops stac_patch_ops = {
-	.build_controls = snd_hda_gen_build_controls,
+	.build_controls = stac_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = stac_init,
 	.free = stac_free,
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index 28ec872e54c0..b6e278fe8f67 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -685,9 +685,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pointer(struct snd_pcm_substream *
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_PBK_CTRL) & 1))
 		return 0;
 	ptr = runtime->buffer_size - inw(ice->ddma_port + 4);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substream *substream)
@@ -704,9 +705,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substrea
 		addr = ICE1712_DSC_ADDR0;
 	ptr = snd_ice1712_ds_read(ice, substream->number * 2, addr) -
 		ice->playback_con_virt_addr[substream->number];
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *substream)
@@ -717,9 +719,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *s
 	if (!(snd_ice1712_read(ice, ICE1712_IREG_CAP_CTRL) & 1))
 		return 0;
 	ptr = inl(ICEREG(ice, CONCAP_ADDR)) - ice->capture_con_virt_addr;
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback = {
@@ -1113,9 +1116,10 @@ static snd_pcm_uframes_t snd_ice1712_playback_pro_pointer(struct snd_pcm_substre
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_PLAYBACK_START))
 		return 0;
 	ptr = ice->playback_pro_size - (inw(ICEMT(ice, PLAYBACK_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substream *substream)
@@ -1126,9 +1130,10 @@ static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substrea
 	if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_CAPTURE_START_SHADOW))
 		return 0;
 	ptr = ice->capture_pro_size - (inw(ICEMT(ice, CAPTURE_SIZE)) << 2);
+	ptr = bytes_to_frames(substream->runtime, ptr);
 	if (ptr == substream->runtime->buffer_size)
 		ptr = 0;
-	return bytes_to_frames(substream->runtime, ptr);
+	return ptr;
 }
 
 static const struct snd_pcm_hardware snd_ice1712_playback_pro = {
diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c
index 64b9fda5f04a..dbbbacfd535e 100644
--- a/sound/pci/oxygen/virtuoso.c
+++ b/sound/pci/oxygen/virtuoso.c
@@ -53,6 +53,7 @@ static DEFINE_PCI_DEVICE_TABLE(xonar_ids) = {
 	{ OXYGEN_PCI_SUBID(0x1043, 0x835e) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x838e) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x8522) },
+	{ OXYGEN_PCI_SUBID(0x1043, 0x85f4) },
 	{ OXYGEN_PCI_SUBID_BROKEN_EEPROM },
 	{ }
 };
diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c
index c8c7f2c9b355..e02605931669 100644
--- a/sound/pci/oxygen/xonar_pcm179x.c
+++ b/sound/pci/oxygen/xonar_pcm179x.c
@@ -100,8 +100,8 @@
  */
 
 /*
- * Xonar Essence ST (Deluxe)/STX
- * -----------------------------
+ * Xonar Essence ST (Deluxe)/STX (II)
+ * ----------------------------------
  *
  * CMI8788:
  *
@@ -1138,6 +1138,14 @@ int get_xonar_pcm179x_model(struct oxygen *chip,
 		chip->model.resume = xonar_stx_resume;
 		chip->model.set_dac_params = set_pcm1796_params;
 		break;
+	case 0x85f4:
+		chip->model = model_xonar_st;
+		/* TODO: daughterboard support */
+		chip->model.shortname = "Xonar STX II";
+		chip->model.init = xonar_stx_init;
+		chip->model.resume = xonar_stx_resume;
+		chip->model.set_dac_params = set_pcm1796_params;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/sound/soc/blackfin/bf5xx-i2s-pcm.c b/sound/soc/blackfin/bf5xx-i2s-pcm.c
index a3881c4381c9..bcf591373a7a 100644
--- a/sound/soc/blackfin/bf5xx-i2s-pcm.c
+++ b/sound/soc/blackfin/bf5xx-i2s-pcm.c
@@ -290,19 +290,19 @@ static int bf5xx_pcm_silence(struct snd_pcm_substream *substream,
 	unsigned int sample_size = runtime->sample_bits / 8;
 	void *buf = runtime->dma_area;
 	struct bf5xx_i2s_pcm_data *dma_data;
-	unsigned int offset, size;
+	unsigned int offset, samples;
 
 	dma_data = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);
 
 	if (dma_data->tdm_mode) {
 		offset = pos * 8 * sample_size;
-		size = count * 8 * sample_size;
+		samples = count * 8;
 	} else {
 		offset = frames_to_bytes(runtime, pos);
-		size = frames_to_bytes(runtime, count);
+		samples = count * runtime->channels;
 	}
 
-	snd_pcm_format_set_silence(runtime->format, buf + offset, size);
+	snd_pcm_format_set_silence(runtime->format, buf + offset, samples);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/adau1701.c b/sound/soc/codecs/adau1701.c
index d71c59cf7bdd..370b742117ef 100644
--- a/sound/soc/codecs/adau1701.c
+++ b/sound/soc/codecs/adau1701.c
@@ -230,8 +230,10 @@ static int adau1701_reg_read(void *context, unsigned int reg,
 
 	*value = 0;
 
-	for (i = 0; i < size; i++)
-		*value |= recv_buf[i] << (i * 8);
+	for (i = 0; i < size; i++) {
+		*value <<= 8;
+		*value |= recv_buf[i];
+	}
 
 	return 0;
 }
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index 6e9ea8379a91..7a272fa90b39 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -124,9 +124,8 @@ static int cs42l51_set_chan_mix(struct snd_kcontrol *kcontrol,
 
 static const DECLARE_TLV_DB_SCALE(adc_pcm_tlv, -5150, 50, 0);
 static const DECLARE_TLV_DB_SCALE(tone_tlv, -1050, 150, 0);
-/* This is a lie. after -102 db, it stays at -102 */
-/* maybe a range would be better */
-static const DECLARE_TLV_DB_SCALE(aout_tlv, -11550, 50, 0);
+
+static const DECLARE_TLV_DB_SCALE(aout_tlv, -10200, 50, 0);
 
 static const DECLARE_TLV_DB_SCALE(boost_tlv, 1600, 1600, 0);
 static const char *chan_mix[] = {
@@ -141,7 +140,7 @@ static const struct soc_enum cs42l51_chan_mix =
 static const struct snd_kcontrol_new cs42l51_snd_controls[] = {
 	SOC_DOUBLE_R_SX_TLV("PCM Playback Volume",
 			CS42L51_PCMA_VOL, CS42L51_PCMB_VOL,
-			6, 0x19, 0x7F, adc_pcm_tlv),
+			0, 0x19, 0x7F, adc_pcm_tlv),
 	SOC_DOUBLE_R("PCM Playback Switch",
 			CS42L51_PCMA_VOL, CS42L51_PCMB_VOL, 7, 1, 1),
 	SOC_DOUBLE_R_SX_TLV("Analog Playback Volume",
@@ -149,7 +148,7 @@ static const struct snd_kcontrol_new cs42l51_snd_controls[] = {
 			0, 0x34, 0xE4, aout_tlv),
 	SOC_DOUBLE_R_SX_TLV("ADC Mixer Volume",
 			CS42L51_ADCA_VOL, CS42L51_ADCB_VOL,
-			6, 0x19, 0x7F, adc_pcm_tlv),
+			0, 0x19, 0x7F, adc_pcm_tlv),
 	SOC_DOUBLE_R("ADC Mixer Switch",
 			CS42L51_ADCA_VOL, CS42L51_ADCB_VOL, 7, 1, 1),
 	SOC_SINGLE("Playback Deemphasis Switch", CS42L51_DAC_CTL, 3, 1, 0),
diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c
index 0bac6d5a4ac8..1102ced9b20e 100644
--- a/sound/soc/codecs/cs42l52.c
+++ b/sound/soc/codecs/cs42l52.c
@@ -347,7 +347,7 @@ static const char * const right_swap_text[] = {
 static const unsigned int swap_values[] = { 0, 1, 3 };
 
 static const struct soc_enum adca_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 3,
 			      ARRAY_SIZE(left_swap_text),
 			      left_swap_text,
 			      swap_values);
@@ -356,7 +356,7 @@ static const struct snd_kcontrol_new adca_mixer =
 	SOC_DAPM_ENUM("Route", adca_swap_enum);
 
 static const struct soc_enum pcma_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 3,
 			      ARRAY_SIZE(left_swap_text),
 			      left_swap_text,
 			      swap_values);
@@ -365,7 +365,7 @@ static const struct snd_kcontrol_new pcma_mixer =
 	SOC_DAPM_ENUM("Route", pcma_swap_enum);
 
 static const struct soc_enum adcb_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 3,
 			      ARRAY_SIZE(right_swap_text),
 			      right_swap_text,
 			      swap_values);
@@ -374,7 +374,7 @@ static const struct snd_kcontrol_new adcb_mixer =
 	SOC_DAPM_ENUM("Route", adcb_swap_enum);
 
 static const struct soc_enum pcmb_swap_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 3,
 			      ARRAY_SIZE(right_swap_text),
 			      right_swap_text,
 			      swap_values);
diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c
index 549d5d6a3fef..7b95f7cbc515 100644
--- a/sound/soc/codecs/cs42l73.c
+++ b/sound/soc/codecs/cs42l73.c
@@ -319,7 +319,7 @@ static const char * const cs42l73_mono_mix_texts[] = {
 static const unsigned int cs42l73_mono_mix_values[] = { 0, 1, 2 };
 
 static const struct soc_enum spk_asp_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 1,
+	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 3,
 			      ARRAY_SIZE(cs42l73_mono_mix_texts),
 			      cs42l73_mono_mix_texts,
 			      cs42l73_mono_mix_values);
@@ -337,7 +337,7 @@ static const struct snd_kcontrol_new spk_xsp_mixer =
 	SOC_DAPM_ENUM("Route", spk_xsp_enum);
 
 static const struct soc_enum esl_asp_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 5,
+	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 3,
 			      ARRAY_SIZE(cs42l73_mono_mix_texts),
 			      cs42l73_mono_mix_texts,
 			      cs42l73_mono_mix_values);
@@ -346,7 +346,7 @@ static const struct snd_kcontrol_new esl_asp_mixer =
 	SOC_DAPM_ENUM("Route", esl_asp_enum);
 
 static const struct soc_enum esl_xsp_enum =
-	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 7,
+	SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 3,
 			      ARRAY_SIZE(cs42l73_mono_mix_texts),
 			      cs42l73_mono_mix_texts,
 			      cs42l73_mono_mix_values);
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 9f714ea86613..9dd260f9dd06 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -255,6 +255,7 @@ static struct reg_default max98090_reg[] = {
 static bool max98090_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
+	case M98090_REG_SOFTWARE_RESET:
 	case M98090_REG_DEVICE_STATUS:
 	case M98090_REG_JACK_STATUS:
 	case M98090_REG_REVISION_ID:
@@ -1377,8 +1378,8 @@ static const struct snd_soc_dapm_route max98090_dapm_routes[] = {
 	{"STENL Mux", "Sidetone Left", "DMICL"},
 	{"STENR Mux", "Sidetone Right", "ADCR"},
 	{"STENR Mux", "Sidetone Right", "DMICR"},
-	{"DACL", "NULL", "STENL Mux"},
-	{"DACR", "NULL", "STENL Mux"},
+	{"DACL", NULL, "STENL Mux"},
+	{"DACR", NULL, "STENL Mux"},
 
 	{"AIFINL", NULL, "SHDN"},
 	{"AIFINR", NULL, "SHDN"},
@@ -2249,7 +2250,7 @@ static int max98090_probe(struct snd_soc_codec *codec)
 	/* Register for interrupts */
 	dev_dbg(codec->dev, "irq = %d\n", max98090->irq);
 
-	ret = request_threaded_irq(max98090->irq, NULL,
+	ret = devm_request_threaded_irq(codec->dev, max98090->irq, NULL,
 		max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 		"max98090_interrupt", codec);
 	if (ret < 0) {
@@ -2360,6 +2361,8 @@ static int max98090_runtime_resume(struct device *dev)
 
 	regcache_cache_only(max98090->regmap, false);
 
+	max98090_reset(max98090);
+
 	regcache_sync(max98090->regmap);
 
 	return 0;
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index 886924934aa5..5cb515b08a32 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2071,6 +2071,7 @@ static struct snd_soc_codec_driver soc_codec_dev_rt5640 = {
 static const struct regmap_config rt5640_regmap = {
 	.reg_bits = 8,
 	.val_bits = 16,
+	.use_single_rw = true,
 
 	.max_register = RT5640_VENDOR_ID2 + 1 + (ARRAY_SIZE(rt5640_ranges) *
 					       RT5640_PR_SPACING),
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 0fcbe90f3ef2..12528e9ac4c2 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1369,8 +1369,7 @@ static int sgtl5000_probe(struct snd_soc_codec *codec)
 
 	/* enable small pop, introduce 400ms delay in turning off */
 	snd_soc_update_bits(codec, SGTL5000_CHIP_REF_CTRL,
-				SGTL5000_SMALL_POP,
-				SGTL5000_SMALL_POP);
+				SGTL5000_SMALL_POP, 1);
 
 	/* disable short cut detector */
 	snd_soc_write(codec, SGTL5000_CHIP_SHORT_CTRL, 0);
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index 2f8c88931f69..bd7a344bf8c5 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -275,7 +275,7 @@
 #define SGTL5000_BIAS_CTRL_MASK			0x000e
 #define SGTL5000_BIAS_CTRL_SHIFT		1
 #define SGTL5000_BIAS_CTRL_WIDTH		3
-#define SGTL5000_SMALL_POP			0x0001
+#define SGTL5000_SMALL_POP			0
 
 /*
  * SGTL5000_CHIP_MIC_CTRL
diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c
index 4068f2491232..bb3878c9625f 100644
--- a/sound/soc/codecs/sigmadsp.c
+++ b/sound/soc/codecs/sigmadsp.c
@@ -176,6 +176,13 @@ static int _process_sigma_firmware(struct device *dev,
 		goto done;
 	}
 
+	if (ssfw_head->version != 1) {
+		dev_err(dev,
+			"Failed to load firmware: Invalid version %d. Supported firmware versions: 1\n",
+			ssfw_head->version);
+		goto done;
+	}
+
 	crc = crc32(0, fw->data + sizeof(*ssfw_head),
 			fw->size - sizeof(*ssfw_head));
 	pr_debug("%s: crc=%x\n", __func__, crc);
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index 470fbfb4b386..fd53d37e1181 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -169,7 +169,7 @@ static int snd_soc_dapm_put_volsw_aic3x(struct snd_kcontrol *kcontrol,
 	mask <<= shift;
 	val <<= shift;
 
-	change = snd_soc_test_bits(codec, val, mask, reg);
+	change = snd_soc_test_bits(codec, reg, mask, val);
 	if (change) {
 		update.kcontrol = kcontrol;
 		update.reg = reg;
@@ -1121,6 +1121,7 @@ static int aic3x_regulator_event(struct notifier_block *nb,
 static int aic3x_set_power(struct snd_soc_codec *codec, int power)
 {
 	struct aic3x_priv *aic3x = snd_soc_codec_get_drvdata(codec);
+	unsigned int pll_c, pll_d;
 	int ret;
 
 	if (power) {
@@ -1138,6 +1139,18 @@ static int aic3x_set_power(struct snd_soc_codec *codec, int power)
 		/* Sync reg_cache with the hardware */
 		regcache_cache_only(aic3x->regmap, false);
 		regcache_sync(aic3x->regmap);
+
+		/* Rewrite paired PLL D registers in case cached sync skipped
+		 * writing one of them and thus caused other one also not
+		 * being written
+		 */
+		pll_c = snd_soc_read(codec, AIC3X_PLL_PROGC_REG);
+		pll_d = snd_soc_read(codec, AIC3X_PLL_PROGD_REG);
+		if (pll_c == aic3x_reg[AIC3X_PLL_PROGC_REG].def ||
+			pll_d == aic3x_reg[AIC3X_PLL_PROGD_REG].def) {
+			snd_soc_write(codec, AIC3X_PLL_PROGC_REG, pll_c);
+			snd_soc_write(codec, AIC3X_PLL_PROGD_REG, pll_d);
+		}
 	} else {
 		/*
 		 * Do soft reset to this codec instance in order to clear
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 97db3b45b411..799348e9cdd0 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -154,6 +154,7 @@ static struct reg_default wm8962_reg[] = {
 	{ 40, 0x0000 },   /* R40    - SPKOUTL volume */
 	{ 41, 0x0000 },   /* R41    - SPKOUTR volume */
 
+	{ 49, 0x0010 },   /* R49    - Class D Control 1 */
 	{ 51, 0x0003 },   /* R51    - Class D Control 2 */
 
 	{ 56, 0x0506 },   /* R56    - Clocking 4 */
@@ -795,7 +796,6 @@ static bool wm8962_volatile_register(struct device *dev, unsigned int reg)
 	case WM8962_ALC2:
 	case WM8962_THERMAL_SHUTDOWN_STATUS:
 	case WM8962_ADDITIONAL_CONTROL_4:
-	case WM8962_CLASS_D_CONTROL_1:
 	case WM8962_DC_SERVO_6:
 	case WM8962_INTERRUPT_STATUS_1:
 	case WM8962_INTERRUPT_STATUS_2:
@@ -2922,13 +2922,22 @@ static int wm8962_set_fll(struct snd_soc_codec *codec, int fll_id, int source,
 static int wm8962_mute(struct snd_soc_dai *dai, int mute)
 {
 	struct snd_soc_codec *codec = dai->codec;
-	int val;
+	int val, ret;
 
 	if (mute)
-		val = WM8962_DAC_MUTE;
+		val = WM8962_DAC_MUTE | WM8962_DAC_MUTE_ALT;
 	else
 		val = 0;
 
+	/**
+	 * The DAC mute bit is mirrored in two registers, update both to keep
+	 * the register cache consistent.
+	 */
+	ret = snd_soc_update_bits(codec, WM8962_CLASS_D_CONTROL_1,
+				  WM8962_DAC_MUTE_ALT, val);
+	if (ret < 0)
+		return ret;
+
 	return snd_soc_update_bits(codec, WM8962_ADC_DAC_CONTROL_1,
 				   WM8962_DAC_MUTE, val);
 }
diff --git a/sound/soc/codecs/wm8962.h b/sound/soc/codecs/wm8962.h
index a1a5d5294c19..910aafd09d21 100644
--- a/sound/soc/codecs/wm8962.h
+++ b/sound/soc/codecs/wm8962.h
@@ -1954,6 +1954,10 @@
 #define WM8962_SPKOUTL_ENA_MASK                 0x0040  /* SPKOUTL_ENA */
 #define WM8962_SPKOUTL_ENA_SHIFT                     6  /* SPKOUTL_ENA */
 #define WM8962_SPKOUTL_ENA_WIDTH                     1  /* SPKOUTL_ENA */
+#define WM8962_DAC_MUTE_ALT                     0x0010  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_MASK                0x0010  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_SHIFT                    4  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_WIDTH                    1  /* DAC_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE                 0x0002  /* SPKOUTL_PGA_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE_MASK            0x0002  /* SPKOUTL_PGA_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE_SHIFT                1  /* SPKOUTL_PGA_MUTE */
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index adb72063d44e..d98e52f647d2 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -3497,6 +3497,7 @@ static irqreturn_t wm8994_mic_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+/* Should be called with accdet_lock held */
 static void wm1811_micd_stop(struct snd_soc_codec *codec)
 {
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
@@ -3504,14 +3505,10 @@ static void wm1811_micd_stop(struct snd_soc_codec *codec)
 	if (!wm8994->jackdet)
 		return;
 
-	mutex_lock(&wm8994->accdet_lock);
-
 	snd_soc_update_bits(codec, WM8958_MIC_DETECT_1, WM8958_MICD_ENA, 0);
 
 	wm1811_jackdet_set_mode(codec, WM1811_JACKDET_MODE_JACK);
 
-	mutex_unlock(&wm8994->accdet_lock);
-
 	if (wm8994->wm8994->pdata.jd_ext_cap)
 		snd_soc_dapm_disable_pin(&codec->dapm,
 					 "MICBIAS2");
@@ -3552,10 +3549,10 @@ static void wm8958_open_circuit_work(struct work_struct *work)
 						  open_circuit_work.work);
 	struct device *dev = wm8994->wm8994->dev;
 
-	wm1811_micd_stop(wm8994->hubs.codec);
-
 	mutex_lock(&wm8994->accdet_lock);
 
+	wm1811_micd_stop(wm8994->hubs.codec);
+
 	dev_dbg(dev, "Reporting open circuit\n");
 
 	wm8994->jack_mic = false;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 444626fcab40..0502e3f17412 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1341,6 +1341,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
 			  file, blocks, pos - firmware->size);
 
 out_fw:
+	regmap_async_complete(regmap);
 	release_firmware(firmware);
 	wm_adsp_buf_free(&buf_list);
 out:
@@ -1745,3 +1746,5 @@ int wm_adsp2_init(struct wm_adsp *adsp, bool dvfs)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_init);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 670afa29e30d..7350ebbae642 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -418,8 +418,17 @@ static int davinci_config_channel_size(struct davinci_mcasp *mcasp,
 {
 	u32 fmt;
 	u32 tx_rotate = (word_length / 4) & 0x7;
-	u32 rx_rotate = (32 - word_length) / 4;
 	u32 mask = (1ULL << word_length) - 1;
+	/*
+	 * For captured data we should not rotate, inversion and masking is
+	 * enoguh to get the data to the right position:
+	 * Format	  data from bus		after reverse (XRBUF)
+	 * S16_LE:	|LSB|MSB|xxx|xxx|	|xxx|xxx|MSB|LSB|
+	 * S24_3LE:	|LSB|DAT|MSB|xxx|	|xxx|MSB|DAT|LSB|
+	 * S24_LE:	|LSB|DAT|MSB|xxx|	|xxx|MSB|DAT|LSB|
+	 * S32_LE:	|LSB|DAT|DAT|MSB|	|MSB|DAT|DAT|LSB|
+	 */
+	u32 rx_rotate = 0;
 
 	/*
 	 * if s BCLK-to-LRCLK ratio has been configured via the set_clkdiv()
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index 25c31f1655f6..2f6357578616 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -263,6 +263,19 @@ static void dw_i2s_shutdown(struct snd_pcm_substream *substream,
 	snd_soc_dai_set_dma_data(dai, substream, NULL);
 }
 
+static int dw_i2s_prepare(struct snd_pcm_substream *substream,
+			  struct snd_soc_dai *dai)
+{
+	struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		i2s_write_reg(dev->i2s_base, TXFFR, 1);
+	else
+		i2s_write_reg(dev->i2s_base, RXFFR, 1);
+
+	return 0;
+}
+
 static int dw_i2s_trigger(struct snd_pcm_substream *substream,
 		int cmd, struct snd_soc_dai *dai)
 {
@@ -294,6 +307,7 @@ static struct snd_soc_dai_ops dw_i2s_dai_ops = {
 	.startup	= dw_i2s_startup,
 	.shutdown	= dw_i2s_shutdown,
 	.hw_params	= dw_i2s_hw_params,
+	.prepare	= dw_i2s_prepare,
 	.trigger	= dw_i2s_trigger,
 };
 
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index a3119a00d8fa..6c6b35e471c8 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -725,7 +725,8 @@ static int pxa_ssp_probe(struct snd_soc_dai *dai)
 		ssp_handle = of_parse_phandle(dev->of_node, "port", 0);
 		if (!ssp_handle) {
 			dev_err(dev, "unable to get 'port' phandle\n");
-			return -ENODEV;
+			ret = -ENODEV;
+			goto err_priv;
 		}
 
 		priv->ssp = pxa_ssp_request_of(ssp_handle, "SoC audio");
@@ -766,9 +767,7 @@ static int pxa_ssp_remove(struct snd_soc_dai *dai)
 			  SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_64000 |	\
 			  SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000)
 
-#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
-			    SNDRV_PCM_FMTBIT_S24_LE |	\
-			    SNDRV_PCM_FMTBIT_S32_LE)
+#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE)
 
 static const struct snd_soc_dai_ops pxa_ssp_dai_ops = {
 	.startup	= pxa_ssp_startup,
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 0a9b44c940ce..5dae66002a11 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -915,11 +915,9 @@ static int i2s_suspend(struct snd_soc_dai *dai)
 {
 	struct i2s_dai *i2s = to_info(dai);
 
-	if (dai->active) {
-		i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
-		i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
-		i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);
-	}
+	i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
+	i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
+	i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);
 
 	return 0;
 }
@@ -928,11 +926,9 @@ static int i2s_resume(struct snd_soc_dai *dai)
 {
 	struct i2s_dai *i2s = to_info(dai);
 
-	if (dai->active) {
-		writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
-		writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
-		writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);
-	}
+	writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
+	writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
+	writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);
 
 	return 0;
 }
diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index 1967f44e7cd4..9d0c59ce6de8 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -1785,8 +1785,7 @@ static const struct snd_soc_dai_ops fsi_dai_ops = {
 static struct snd_pcm_hardware fsi_pcm_hardware = {
 	.info =		SNDRV_PCM_INFO_INTERLEAVED	|
 			SNDRV_PCM_INFO_MMAP		|
-			SNDRV_PCM_INFO_MMAP_VALID	|
-			SNDRV_PCM_INFO_PAUSE,
+			SNDRV_PCM_INFO_MMAP_VALID,
 	.buffer_bytes_max	= 64 * 1024,
 	.period_bytes_min	= 32,
 	.period_bytes_max	= 8192,
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 743de5e3b1e1..37fcd93ed1fd 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -626,8 +626,7 @@ static void rsnd_dai_remove(struct platform_device *pdev,
 static struct snd_pcm_hardware rsnd_pcm_hardware = {
 	.info =		SNDRV_PCM_INFO_INTERLEAVED	|
 			SNDRV_PCM_INFO_MMAP		|
-			SNDRV_PCM_INFO_MMAP_VALID	|
-			SNDRV_PCM_INFO_PAUSE,
+			SNDRV_PCM_INFO_MMAP_VALID,
 	.buffer_bytes_max	= 64 * 1024,
 	.period_bytes_min	= 32,
 	.period_bytes_max	= 8192,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index b9dc6acbba8c..e4da224d7253 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -251,7 +251,6 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 static void dapm_kcontrol_free(struct snd_kcontrol *kctl)
 {
 	struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl);
-	kfree(data->widget);
 	kfree(data->wlist);
 	kfree(data);
 }
@@ -690,9 +689,9 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w,
 	int shared;
 	struct snd_kcontrol *kcontrol;
 	bool wname_in_long_name, kcname_in_long_name;
-	char *long_name;
+	char *long_name = NULL;
 	const char *name;
-	int ret;
+	int ret = 0;
 
 	if (dapm->codec)
 		prefix = dapm->codec->name_prefix;
@@ -757,15 +756,17 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w,
 
 		kcontrol = snd_soc_cnew(&w->kcontrol_news[kci], NULL, name,
 					prefix);
-		kfree(long_name);
-		if (!kcontrol)
-			return -ENOMEM;
+		if (!kcontrol) {
+			ret = -ENOMEM;
+			goto exit_free;
+		}
+
 		kcontrol->private_free = dapm_kcontrol_free;
 
 		ret = dapm_kcontrol_data_alloc(w, kcontrol);
 		if (ret) {
 			snd_ctl_free_one(kcontrol);
-			return ret;
+			goto exit_free;
 		}
 
 		ret = snd_ctl_add(card, kcontrol);
@@ -773,17 +774,18 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w,
 			dev_err(dapm->dev,
 				"ASoC: failed to add widget %s dapm kcontrol %s: %d\n",
 				w->name, name, ret);
-			return ret;
+			goto exit_free;
 		}
 	}
 
 	ret = dapm_kcontrol_add_widget(kcontrol, w);
-	if (ret)
-		return ret;
+	if (ret == 0)
+		w->kcontrols[kci] = kcontrol;
 
-	w->kcontrols[kci] = kcontrol;
+exit_free:
+	kfree(long_name);
 
-	return 0;
+	return ret;
 }
 
 /* create new dapm mixer control */
@@ -2889,22 +2891,19 @@ int snd_soc_dapm_put_volsw(struct snd_kcontrol *kcontrol,
 	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 
 	change = dapm_kcontrol_set_value(kcontrol, val);
-
-	if (reg != SND_SOC_NOPM) {
-		mask = mask << shift;
-		val = val << shift;
-
-		change = snd_soc_test_bits(codec, reg, mask, val);
-	}
-
 	if (change) {
 		if (reg != SND_SOC_NOPM) {
-			update.kcontrol = kcontrol;
-			update.reg = reg;
-			update.mask = mask;
-			update.val = val;
+			mask = mask << shift;
+			val = val << shift;
+
+			if (snd_soc_test_bits(codec, reg, mask, val)) {
+				update.kcontrol = kcontrol;
+				update.reg = reg;
+				update.mask = mask;
+				update.val = val;
+				card->update = &update;
+			}
 
-			card->update = &update;
 		}
 
 		ret = soc_dapm_mixer_update_power(card, kcontrol, connect);
@@ -3650,8 +3649,11 @@ void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card)
 		cpu_dai = rtd->cpu_dai;
 		codec_dai = rtd->codec_dai;
 
-		/* dynamic FE links have no fixed DAI mapping */
-		if (rtd->dai_link->dynamic)
+		/*
+		 * dynamic FE links have no fixed DAI mapping.
+		 * CODEC<->CODEC links have no direct connection.
+		 */
+		if (rtd->dai_link->dynamic || rtd->dai_link->params)
 			continue;
 
 		/* there is no point in connecting BE DAI links with dummies */
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 28522bd03b8e..e28704e1274a 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1258,13 +1258,36 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
 		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture);
 }
 
+static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd);
+
+/* Set FE's runtime_update state; the state is protected via PCM stream lock
+ * for avoiding the race with trigger callback.
+ * If the state is unset and a trigger is pending while the previous operation,
+ * process the pending trigger action here.
+ */
+static void dpcm_set_fe_update_state(struct snd_soc_pcm_runtime *fe,
+				     int stream, enum snd_soc_dpcm_update state)
+{
+	struct snd_pcm_substream *substream =
+		snd_soc_dpcm_get_substream(fe, stream);
+
+	snd_pcm_stream_lock_irq(substream);
+	if (state == SND_SOC_DPCM_UPDATE_NO && fe->dpcm[stream].trigger_pending) {
+		dpcm_fe_dai_do_trigger(substream,
+				       fe->dpcm[stream].trigger_pending - 1);
+		fe->dpcm[stream].trigger_pending = 0;
+	}
+	fe->dpcm[stream].runtime_update = state;
+	snd_pcm_stream_unlock_irq(substream);
+}
+
 static int dpcm_fe_dai_startup(struct snd_pcm_substream *fe_substream)
 {
 	struct snd_soc_pcm_runtime *fe = fe_substream->private_data;
 	struct snd_pcm_runtime *runtime = fe_substream->runtime;
 	int stream = fe_substream->stream, ret = 0;
 
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE);
 
 	ret = dpcm_be_dai_startup(fe, fe_substream->stream);
 	if (ret < 0) {
@@ -1286,13 +1309,13 @@ static int dpcm_fe_dai_startup(struct snd_pcm_substream *fe_substream)
 	dpcm_set_fe_runtime(fe_substream);
 	snd_pcm_limit_hw_rates(runtime);
 
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 	return 0;
 
 unwind:
 	dpcm_be_dai_startup_unwind(fe, fe_substream->stream);
 be_err:
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 	return ret;
 }
 
@@ -1339,7 +1362,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream)
 	struct snd_soc_pcm_runtime *fe = substream->private_data;
 	int stream = substream->stream;
 
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE);
 
 	/* shutdown the BEs */
 	dpcm_be_dai_shutdown(fe, substream->stream);
@@ -1353,7 +1376,7 @@ static int dpcm_fe_dai_shutdown(struct snd_pcm_substream *substream)
 	dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP);
 
 	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE;
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 	return 0;
 }
 
@@ -1401,7 +1424,7 @@ static int dpcm_fe_dai_hw_free(struct snd_pcm_substream *substream)
 	int err, stream = substream->stream;
 
 	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE);
 
 	dev_dbg(fe->dev, "ASoC: hw_free FE %s\n", fe->dai_link->name);
 
@@ -1416,7 +1439,7 @@ static int dpcm_fe_dai_hw_free(struct snd_pcm_substream *substream)
 	err = dpcm_be_dai_hw_free(fe, stream);
 
 	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_HW_FREE;
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 
 	mutex_unlock(&fe->card->mutex);
 	return 0;
@@ -1509,7 +1532,7 @@ static int dpcm_fe_dai_hw_params(struct snd_pcm_substream *substream,
 	int ret, stream = substream->stream;
 
 	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE);
 
 	memcpy(&fe->dpcm[substream->stream].hw_params, params,
 			sizeof(struct snd_pcm_hw_params));
@@ -1532,7 +1555,7 @@ static int dpcm_fe_dai_hw_params(struct snd_pcm_substream *substream,
 		fe->dpcm[stream].state = SND_SOC_DPCM_STATE_HW_PARAMS;
 
 out:
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 	mutex_unlock(&fe->card->mutex);
 	return ret;
 }
@@ -1646,7 +1669,7 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
 }
 EXPORT_SYMBOL_GPL(dpcm_be_dai_trigger);
 
-static int dpcm_fe_dai_trigger(struct snd_pcm_substream *substream, int cmd)
+static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	struct snd_soc_pcm_runtime *fe = substream->private_data;
 	int stream = substream->stream, ret;
@@ -1720,6 +1743,23 @@ out:
 	return ret;
 }
 
+static int dpcm_fe_dai_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	struct snd_soc_pcm_runtime *fe = substream->private_data;
+	int stream = substream->stream;
+
+	/* if FE's runtime_update is already set, we're in race;
+	 * process this trigger later at exit
+	 */
+	if (fe->dpcm[stream].runtime_update != SND_SOC_DPCM_UPDATE_NO) {
+		fe->dpcm[stream].trigger_pending = cmd + 1;
+		return 0; /* delayed, assuming it's successful */
+	}
+
+	/* we're alone, let's trigger */
+	return dpcm_fe_dai_do_trigger(substream, cmd);
+}
+
 int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
@@ -1763,7 +1803,7 @@ static int dpcm_fe_dai_prepare(struct snd_pcm_substream *substream)
 
 	dev_dbg(fe->dev, "ASoC: prepare FE %s\n", fe->dai_link->name);
 
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_FE);
 
 	/* there is no point preparing this FE if there are no BEs */
 	if (list_empty(&fe->dpcm[stream].be_clients)) {
@@ -1790,7 +1830,7 @@ static int dpcm_fe_dai_prepare(struct snd_pcm_substream *substream)
 	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE;
 
 out:
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 	mutex_unlock(&fe->card->mutex);
 
 	return ret;
@@ -1937,11 +1977,11 @@ static int dpcm_run_new_update(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	int ret;
 
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_BE;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_BE);
 	ret = dpcm_run_update_startup(fe, stream);
 	if (ret < 0)
 		dev_err(fe->dev, "ASoC: failed to startup some BEs\n");
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 
 	return ret;
 }
@@ -1950,11 +1990,11 @@ static int dpcm_run_old_update(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	int ret;
 
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_BE;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_BE);
 	ret = dpcm_run_update_shutdown(fe, stream);
 	if (ret < 0)
 		dev_err(fe->dev, "ASoC: failed to shutdown some BEs\n");
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+	dpcm_set_fe_update_state(fe, stream, SND_SOC_DPCM_UPDATE_NO);
 
 	return ret;
 }
@@ -1989,7 +2029,6 @@ int soc_dpcm_runtime_update(struct snd_soc_card *card)
 
 		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
 		if (paths < 0) {
-			dpcm_path_put(&list);
 			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
 					fe->dai_link->name,  "playback");
 			mutex_unlock(&card->mutex);
@@ -2012,6 +2051,7 @@ int soc_dpcm_runtime_update(struct snd_soc_card *card)
 			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
 		}
 
+		dpcm_path_put(&list);
 capture:
 		/* skip if FE doesn't have capture capability */
 		if (!fe->cpu_dai->driver->capture.channels_min)
@@ -2019,7 +2059,6 @@ capture:
 
 		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
 		if (paths < 0) {
-			dpcm_path_put(&list);
 			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
 					fe->dai_link->name,  "capture");
 			mutex_unlock(&card->mutex);
@@ -2084,7 +2123,6 @@ static int dpcm_fe_dai_open(struct snd_pcm_substream *fe_substream)
 	fe->dpcm[stream].runtime = fe_substream->runtime;
 
 	if (dpcm_path_get(fe, stream, &list) <= 0) {
-		dpcm_path_put(&list);
 		dev_dbg(fe->dev, "ASoC: %s no valid %s route\n",
 			fe->dai_link->name, stream ? "capture" : "playback");
 	}
diff --git a/sound/usb/card.c b/sound/usb/card.c
index d979050e6a6a..ab433a02dbf1 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -304,6 +304,11 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif)
 
 static int snd_usb_audio_free(struct snd_usb_audio *chip)
 {
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &chip->ep_list)
+		snd_usb_endpoint_free(p);
+
 	mutex_destroy(&chip->mutex);
 	kfree(chip);
 	return 0;
@@ -580,27 +585,30 @@ static void snd_usb_audio_disconnect(struct usb_device *dev,
 				     struct snd_usb_audio *chip)
 {
 	struct snd_card *card;
-	struct list_head *p, *n;
+	struct list_head *p;
+	bool was_shutdown;
 
 	if (chip == (void *)-1L)
 		return;
 
 	card = chip->card;
 	down_write(&chip->shutdown_rwsem);
+	was_shutdown = chip->shutdown;
 	chip->shutdown = 1;
 	up_write(&chip->shutdown_rwsem);
 
 	mutex_lock(&register_mutex);
-	chip->num_interfaces--;
-	if (chip->num_interfaces <= 0) {
+	if (!was_shutdown) {
+		struct snd_usb_endpoint *ep;
+
 		snd_card_disconnect(card);
 		/* release the pcm resources */
 		list_for_each(p, &chip->pcm_list) {
 			snd_usb_stream_disconnect(p);
 		}
 		/* release the endpoint resources */
-		list_for_each_safe(p, n, &chip->ep_list) {
-			snd_usb_endpoint_free(p);
+		list_for_each_entry(ep, &chip->ep_list, list) {
+			snd_usb_endpoint_release(ep);
 		}
 		/* release the midi resources */
 		list_for_each(p, &chip->midi_list) {
@@ -610,6 +618,10 @@ static void snd_usb_audio_disconnect(struct usb_device *dev,
 		list_for_each(p, &chip->mixer_list) {
 			snd_usb_mixer_disconnect(p);
 		}
+	}
+
+	chip->num_interfaces--;
+	if (chip->num_interfaces <= 0) {
 		usb_chip[chip->index] = NULL;
 		mutex_unlock(&register_mutex);
 		snd_card_free_when_closed(card);
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 9867ab866857..97acb906acc2 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -92,6 +92,7 @@ struct snd_usb_endpoint {
 	unsigned int curframesize;      /* current packet size in frames (for capture) */
 	unsigned int syncmaxsize;	/* sync endpoint packet size */
 	unsigned int fill_max:1;	/* fill max packet size always */
+	unsigned int udh01_fb_quirk:1;	/* corrupted feedback data */
 	unsigned int datainterval;      /* log_2 of data packet interval */
 	unsigned int syncinterval;	/* P for adaptive mode, 0 otherwise */
 	unsigned char silence_value;
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 83aabea259d7..105ece3c14e3 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -469,6 +469,10 @@ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip,
 			ep->syncinterval = 3;
 
 		ep->syncmaxsize = le16_to_cpu(get_endpoint(alts, 1)->wMaxPacketSize);
+
+		if (chip->usb_id == USB_ID(0x0644, 0x8038) /* TEAC UD-H01 */ &&
+		    ep->syncmaxsize == 4)
+			ep->udh01_fb_quirk = 1;
 	}
 
 	list_add_tail(&ep->list, &chip->ep_list);
@@ -977,19 +981,30 @@ void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep)
 }
 
 /**
+ * snd_usb_endpoint_release: Tear down an snd_usb_endpoint
+ *
+ * @ep: the endpoint to release
+ *
+ * This function does not care for the endpoint's use count but will tear
+ * down all the streaming URBs immediately.
+ */
+void snd_usb_endpoint_release(struct snd_usb_endpoint *ep)
+{
+	release_urbs(ep, 1);
+}
+
+/**
  * snd_usb_endpoint_free: Free the resources of an snd_usb_endpoint
  *
  * @ep: the list header of the endpoint to free
  *
- * This function does not care for the endpoint's use count but will tear
- * down all the streaming URBs immediately and free all resources.
+ * This free all resources of the given ep.
  */
 void snd_usb_endpoint_free(struct list_head *head)
 {
 	struct snd_usb_endpoint *ep;
 
 	ep = list_entry(head, struct snd_usb_endpoint, list);
-	release_urbs(ep, 1);
 	kfree(ep);
 }
 
@@ -1099,7 +1114,16 @@ void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep,
 	if (f == 0)
 		return;
 
-	if (unlikely(ep->freqshift == INT_MIN)) {
+	if (unlikely(sender->udh01_fb_quirk)) {
+		/*
+		 * The TEAC UD-H01 firmware sometimes changes the feedback value
+		 * by +/- 0x1.0000.
+		 */
+		if (f < ep->freqn - 0x8000)
+			f += 0x10000;
+		else if (f > ep->freqn + 0x8000)
+			f -= 0x10000;
+	} else if (unlikely(ep->freqshift == INT_MIN)) {
 		/*
 		 * The first time we see a feedback value, determine its format
 		 * by shifting it left or right until it matches the nominal
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 1c7e8ee48abc..e61ee5c356a3 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -23,6 +23,7 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep);
 int  snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep);
+void snd_usb_endpoint_release(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_free(struct list_head *head);
 
 int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep);
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index b901f468b67a..c7aa71ee775b 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -364,6 +364,8 @@ static void snd_usbmidi_error_timer(unsigned long data)
 		if (in && in->error_resubmit) {
 			in->error_resubmit = 0;
 			for (j = 0; j < INPUT_URBS; ++j) {
+				if (atomic_read(&in->urbs[j]->use_count))
+					continue;
 				in->urbs[j]->dev = umidi->dev;
 				snd_usbmidi_submit_urb(in->urbs[j], GFP_ATOMIC);
 			}
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index d1d72ff50347..621bc9ebb55e 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -328,8 +328,11 @@ static struct usbmix_name_map gamecom780_map[] = {
 	{}
 };
 
-static const struct usbmix_name_map kef_x300a_map[] = {
-	{ 10, NULL }, /* firmware locks up (?) when we try to access this FU */
+/* some (all?) SCMS USB3318 devices are affected by a firmware lock up
+ * when anything attempts to access FU 10 (control)
+ */
+static const struct usbmix_name_map scms_usb3318_map[] = {
+	{ 10, NULL },
 	{ 0 }
 };
 
@@ -425,8 +428,14 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.map = ebox44_map,
 	},
 	{
+		/* KEF X300A */
 		.id = USB_ID(0x27ac, 0x1000),
-		.map = kef_x300a_map,
+		.map = scms_usb3318_map,
+	},
+	{
+		/* Arcam rPAC */
+		.id = USB_ID(0x25c4, 0x0003),
+		.map = scms_usb3318_map,
 	},
 	{ 0 } /* terminator */
 };
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index f4b12c216f1c..5a723df670b4 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -885,6 +885,11 @@ static int snd_ftu_eff_switch_put(struct snd_kcontrol *kctl,
 	return changed;
 }
 
+static void kctl_private_value_free(struct snd_kcontrol *kctl)
+{
+	kfree((void *)kctl->private_value);
+}
+
 static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer,
 	int validx, int bUnitID)
 {
@@ -919,6 +924,7 @@ static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer,
 		return -ENOMEM;
 	}
 
+	kctl->private_free = kctl_private_value_free;
 	err = snd_ctl_add(mixer->chip->card, kctl);
 	if (err < 0)
 		return err;
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index ca3256d6fde3..ede4b92710aa 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1488,7 +1488,8 @@ static void retire_playback_urb(struct snd_usb_substream *subs,
 	 * on two reads of a counter updated every ms.
 	 */
 	if (abs(est_delay - subs->last_delay) * 1000 > runtime->rate * 2)
-		snd_printk(KERN_DEBUG "delay: estimated %d, actual %d\n",
+		dev_dbg_ratelimited(&subs->dev->dev,
+			"delay: estimated %d, actual %d\n",
 			est_delay, subs->last_delay);
 
 	if (!subs->running) {
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index f652b10ce905..c657752a420c 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -385,6 +385,36 @@ YAMAHA_DEVICE(0x105d, NULL),
 	}
 },
 {
+	USB_DEVICE(0x0499, 0x1509),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		/* .vendor_name = "Yamaha", */
+		/* .product_name = "Steinberg UR22", */
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_MIDI_YAMAHA
+			},
+			{
+				.ifnum = 4,
+				.type = QUIRK_IGNORE_INTERFACE
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
 	USB_DEVICE(0x0499, 0x150a),
 	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
 		/* .vendor_name = "Yamaha", */
@@ -1581,6 +1611,35 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 	}
 },
 {
+	/* BOSS ME-25 */
+	USB_DEVICE(0x0582, 0x0113),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = & (const struct snd_usb_midi_endpoint_info) {
+					.out_cables = 0x0001,
+					.in_cables  = 0x0001
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
 	/* only 44.1 kHz works at the moment */
 	USB_DEVICE(0x0582, 0x0120),
 	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 89730707614c..827d40441ec7 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -666,7 +666,7 @@ static int snd_usb_gamecon780_boot_quirk(struct usb_device *dev)
 	/* set the initial volume and don't change; other values are either
 	 * too loud or silent due to firmware bug (bko#65251)
 	 */
-	u8 buf[2] = { 0x74, 0xdc };
+	u8 buf[2] = { 0x74, 0xe3 };
 	return snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR,
 			USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT,
 			UAC_FU_VOLUME << 8, 9 << 8, buf, 2);
@@ -1142,6 +1142,20 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
 		mdelay(20);
+
+	/* Marantz/Denon devices with USB DAC functionality need a delay
+	 * after each class compliant request
+	 */
+	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x154e) &&
+	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+
+		switch (le16_to_cpu(dev->descriptor.idProduct)) {
+		case 0x3005: /* Marantz HD-DAC1 */
+		case 0x3006: /* Marantz SA-14S1 */
+			mdelay(20);
+			break;
+		}
+	}
 }
 
 /*
diff --git a/tools/gator/daemon/Android.mk b/tools/gator/daemon/Android.mk
new file mode 100644
index 000000000000..970ac6946150
--- /dev/null
+++ b/tools/gator/daemon/Android.mk
@@ -0,0 +1,76 @@
+LOCAL_PATH := $(call my-dir)
+include $(CLEAR_VARS)
+
+XML_H := $(shell cd $(LOCAL_PATH) && make events_xml.h defaults_xml.h)
+
+LOCAL_SRC_FILES := \
+	AnnotateListener.cpp \
+	Buffer.cpp \
+	CCNDriver.cpp \
+	CPUFreqDriver.cpp \
+	CapturedXML.cpp \
+	Child.cpp \
+	Command.cpp \
+	ConfigurationXML.cpp \
+	DiskIODriver.cpp \
+	Driver.cpp \
+	DriverSource.cpp \
+	DynBuf.cpp \
+	EventsXML.cpp \
+	ExternalSource.cpp \
+	FSDriver.cpp \
+	Fifo.cpp \
+	FtraceDriver.cpp \
+	FtraceSource.cpp \
+	HwmonDriver.cpp \
+	KMod.cpp \
+	LocalCapture.cpp \
+	Logging.cpp \
+	main.cpp \
+	MaliVideoDriver.cpp \
+	MemInfoDriver.cpp\
+	Monitor.cpp \
+	NetDriver.cpp \
+	OlySocket.cpp \
+	OlyUtility.cpp \
+	PerfBuffer.cpp \
+	PerfDriver.cpp \
+	PerfGroup.cpp \
+	PerfSource.cpp \
+	Proc.cpp \
+	Sender.cpp \
+	SessionData.cpp \
+	SessionXML.cpp \
+	Setup.cpp \
+	Source.cpp \
+	StreamlineSetup.cpp \
+	UEvent.cpp \
+	UserSpaceSource.cpp \
+	libsensors/access.c \
+	libsensors/conf-lex.c \
+	libsensors/conf-parse.c \
+	libsensors/data.c \
+	libsensors/error.c \
+	libsensors/general.c \
+	libsensors/init.c \
+	libsensors/sysfs.c \
+	mxml/mxml-attr.c \
+	mxml/mxml-entity.c \
+	mxml/mxml-file.c \
+	mxml/mxml-get.c \
+	mxml/mxml-index.c \
+	mxml/mxml-node.c \
+	mxml/mxml-private.c \
+	mxml/mxml-search.c \
+	mxml/mxml-set.c \
+	mxml/mxml-string.c
+
+LOCAL_CFLAGS += -Wall -O3 -fno-exceptions -pthread -DETCDIR=\"/etc\" -Ilibsensors -fPIE
+LOCAL_LDFLAGS += -fPIE -pie
+
+LOCAL_C_INCLUDES := $(LOCAL_PATH)
+
+LOCAL_MODULE := gatord
+LOCAL_MODULE_TAGS := optional
+
+include $(BUILD_EXECUTABLE)
diff --git a/tools/gator/daemon/AnnotateListener.cpp b/tools/gator/daemon/AnnotateListener.cpp
new file mode 100644
index 000000000000..50110b4dc84c
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.cpp
@@ -0,0 +1,69 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "AnnotateListener.h"
+
+#include <unistd.h>
+
+#include "OlySocket.h"
+
+struct AnnotateClient {
+	AnnotateClient *next;
+	int fd;
+};
+
+AnnotateListener::AnnotateListener() : mClients(NULL), mSock(NULL) {
+}
+
+AnnotateListener::~AnnotateListener() {
+	close();
+	delete mSock;
+}
+
+void AnnotateListener::setup() {
+	mSock = new OlyServerSocket(8082);
+}
+
+int AnnotateListener::getFd() {
+	return mSock->getFd();
+}
+
+void AnnotateListener::handle() {
+	AnnotateClient *const client = new AnnotateClient();
+	client->fd = mSock->acceptConnection();
+	client->next = mClients;
+	mClients = client;
+}
+
+void AnnotateListener::close() {
+	mSock->closeServerSocket();
+	while (mClients != NULL) {
+		::close(mClients->fd);
+		AnnotateClient *next = mClients->next;
+		delete mClients;
+		mClients = next;
+	}
+}
+
+void AnnotateListener::signal() {
+	const char ch = 0;
+	AnnotateClient **ptr = &mClients;
+	AnnotateClient *client = mClients;
+	while (client != NULL) {
+		if (write(client->fd, &ch, sizeof(ch)) != 1) {
+			::close(client->fd);
+			AnnotateClient *next = client->next;
+			delete client;
+			*ptr = next;
+			client = next;
+			continue;
+		}
+		ptr = &client->next;
+		client = client->next;
+	}
+}
diff --git a/tools/gator/daemon/AnnotateListener.h b/tools/gator/daemon/AnnotateListener.h
new file mode 100644
index 000000000000..cdefef12db22
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+class AnnotateClient;
+class OlyServerSocket;
+
+class AnnotateListener {
+public:
+	AnnotateListener();
+	~AnnotateListener();
+
+	void setup();
+	int getFd();
+
+	void handle();
+	void close();
+	void signal();
+
+private:
+	AnnotateClient *mClients;
+	OlyServerSocket *mSock;
+
+	// Intentionally unimplemented
+	AnnotateListener(const AnnotateListener &);
+	AnnotateListener &operator=(const AnnotateListener &);
+};
diff --git a/tools/gator/daemon/Application.mk b/tools/gator/daemon/Application.mk
new file mode 100644
index 000000000000..3ada471cac19
--- /dev/null
+++ b/tools/gator/daemon/Application.mk
@@ -0,0 +1,3 @@
+APP_PLATFORM := android-8
+# Replace armeabi-v7a with arm64-v8a to build an arm64 gatord or with armeabi to build an ARM11 gatord
+APP_ABI := armeabi-v7a
diff --git a/tools/gator/daemon/Buffer.cpp b/tools/gator/daemon/Buffer.cpp
new file mode 100644
index 000000000000..8fa628015069
--- /dev/null
+++ b/tools/gator/daemon/Buffer.cpp
@@ -0,0 +1,428 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Buffer.h"
+
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+#define mask (mSize - 1)
+
+enum {
+	CODE_PEA         = 1,
+	CODE_KEYS        = 2,
+	CODE_FORMAT      = 3,
+	CODE_MAPS        = 4,
+	CODE_COMM        = 5,
+	CODE_KEYS_OLD    = 6,
+	CODE_ONLINE_CPU  = 7,
+	CODE_OFFLINE_CPU = 8,
+	CODE_KALLSYMS    = 9,
+};
+
+// Summary Frame Messages
+enum {
+	MESSAGE_SUMMARY = 1,
+	MESSAGE_CORE_NAME = 3,
+};
+
+// From gator_marshaling.c
+#define NEWLINE_CANARY \
+	/* Unix */ \
+	"1\n" \
+	/* Windows */ \
+	"2\r\n" \
+	/* Mac OS */ \
+	"3\r" \
+	/* RISC OS */ \
+	"4\n\r" \
+	/* Add another character so the length isn't 0x0a bytes */ \
+	"5"
+
+Buffer::Buffer(const int32_t core, const int32_t buftype, const int size, sem_t *const readerSem) : mBuf(new char[size]), mReaderSem(readerSem), mCommitTime(gSessionData->mLiveRate), mSize(size), mReadPos(0), mWritePos(0), mCommitPos(0), mAvailable(true), mIsDone(false), mCore(core), mBufType(buftype) {
+	if ((mSize & mask) != 0) {
+		logg->logError(__FILE__, __LINE__, "Buffer size is not a power of 2");
+		handleException();
+	}
+	sem_init(&mWriterSem, 0, 0);
+	frame();
+}
+
+Buffer::~Buffer() {
+	delete [] mBuf;
+	sem_destroy(&mWriterSem);
+}
+
+void Buffer::write(Sender *const sender) {
+	if (!commitReady()) {
+		return;
+	}
+
+	// commit and read are updated by the writer, only read them once
+	int commitPos = mCommitPos;
+	int readPos = mReadPos;
+
+	// determine the size of two halves
+	int length1 = commitPos - readPos;
+	char *buffer1 = mBuf + readPos;
+	int length2 = 0;
+	char *buffer2 = mBuf;
+	if (length1 < 0) {
+		length1 = mSize - readPos;
+		length2 = commitPos;
+	}
+
+	logg->logMessage("Sending data length1: %i length2: %i", length1, length2);
+
+	// start, middle or end
+	if (length1 > 0) {
+		sender->writeData(buffer1, length1, RESPONSE_APC_DATA);
+	}
+
+	// possible wrap around
+	if (length2 > 0) {
+		sender->writeData(buffer2, length2, RESPONSE_APC_DATA);
+	}
+
+	mReadPos = commitPos;
+
+	// send a notification that space is available
+	sem_post(&mWriterSem);
+}
+
+bool Buffer::commitReady() const {
+	return mCommitPos != mReadPos;
+}
+
+int Buffer::bytesAvailable() const {
+	int filled = mWritePos - mReadPos;
+	if (filled < 0) {
+		filled += mSize;
+	}
+
+	int remaining = mSize - filled;
+
+	if (mAvailable) {
+		// Give some extra room; also allows space to insert the overflow error packet
+		remaining -= 200;
+	} else {
+		// Hysteresis, prevents multiple overflow messages
+		remaining -= 2000;
+	}
+
+	return remaining;
+}
+
+bool Buffer::checkSpace(const int bytes) {
+	const int remaining = bytesAvailable();
+
+	if (remaining < bytes) {
+		mAvailable = false;
+	} else {
+		mAvailable = true;
+	}
+
+	return mAvailable;
+}
+
+int Buffer::contiguousSpaceAvailable() const {
+	int remaining = bytesAvailable();
+	int contiguous = mSize - mWritePos;
+	if (remaining < contiguous) {
+		return remaining;
+	} else {
+		return contiguous;
+	}
+}
+
+void Buffer::commit(const uint64_t time) {
+	// post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload
+	const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+	int length = mWritePos - mCommitPos;
+	if (length < 0) {
+		length += mSize;
+	}
+	length = length - typeLength - sizeof(int32_t);
+	for (size_t byte = 0; byte < sizeof(int32_t); byte++) {
+		mBuf[(mCommitPos + typeLength + byte) & mask] = (length >> byte * 8) & 0xFF;
+	}
+
+	logg->logMessage("Committing data mReadPos: %i mWritePos: %i mCommitPos: %i", mReadPos, mWritePos, mCommitPos);
+	mCommitPos = mWritePos;
+
+	if (gSessionData->mLiveRate > 0) {
+		while (time > mCommitTime) {
+			mCommitTime += gSessionData->mLiveRate;
+		}
+	}
+
+	if (!mIsDone) {
+		frame();
+	}
+
+	// send a notification that data is ready
+	sem_post(mReaderSem);
+}
+
+void Buffer::check(const uint64_t time) {
+	int filled = mWritePos - mCommitPos;
+	if (filled < 0) {
+		filled += mSize;
+	}
+	if (filled >= ((mSize * 3) / 4) || (gSessionData->mLiveRate > 0 && time >= mCommitTime)) {
+		commit(time);
+	}
+}
+
+void Buffer::packInt(char *const buf, const int size, int &writePos, int32_t x) {
+	int packedBytes = 0;
+	int more = true;
+	while (more) {
+		// low order 7 bits of x
+		char b = x & 0x7f;
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+			more = false;
+		} else {
+			b |= 0x80;
+		}
+
+		buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+		packedBytes++;
+	}
+
+	writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt(int32_t x) {
+	packInt(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::packInt64(char *const buf, const int size, int &writePos, int64_t x) {
+	int packedBytes = 0;
+	int more = true;
+	while (more) {
+		// low order 7 bits of x
+		char b = x & 0x7f;
+		x >>= 7;
+
+		if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+			more = false;
+		} else {
+			b |= 0x80;
+		}
+
+		buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+		packedBytes++;
+	}
+
+	writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt64(int64_t x) {
+	packInt64(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::writeBytes(const void *const data, size_t count) {
+	size_t i;
+	for (i = 0; i < count; ++i) {
+		mBuf[(mWritePos + i) & mask] = static_cast<const char *>(data)[i];
+	}
+
+	mWritePos = (mWritePos + i) & mask;
+}
+
+void Buffer::writeString(const char *const str) {
+	const int len = strlen(str);
+	packInt(len);
+	writeBytes(str, len);
+}
+
+void Buffer::frame() {
+	if (!gSessionData->mLocalCapture) {
+		packInt(RESPONSE_APC_DATA);
+	}
+	// Reserve space for the length
+	mWritePos += sizeof(int32_t);
+	packInt(mBufType);
+	if ((mBufType == FRAME_BLOCK_COUNTER) || (mBufType == FRAME_PERF_ATTRS) || (mBufType == FRAME_PERF)) {
+		packInt(mCore);
+	}
+}
+
+void Buffer::summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname) {
+	packInt(MESSAGE_SUMMARY);
+	writeString(NEWLINE_CANARY);
+	packInt64(timestamp);
+	packInt64(uptime);
+	packInt64(monotonicDelta);
+	writeString("uname");
+	writeString(uname);
+	writeString("");
+	check(currTime);
+}
+
+void Buffer::coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name) {
+	if (checkSpace(3 * MAXSIZE_PACK32 + 0x100)) {
+		packInt(MESSAGE_CORE_NAME);
+		packInt(core);
+		packInt(cpuid);
+		writeString(name);
+	}
+	check(currTime);
+}
+
+bool Buffer::eventHeader(const uint64_t curr_time) {
+	bool retval = false;
+	if (checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		// key of zero indicates a timestamp
+		packInt(0);
+		packInt64(curr_time);
+		retval = true;
+	}
+
+	return retval;
+}
+
+bool Buffer::eventTid(const int tid) {
+	bool retval = false;
+	if (checkSpace(2 * MAXSIZE_PACK32)) {
+		// key of 1 indicates a tid
+		packInt(1);
+		packInt(tid);
+		retval = true;
+	}
+
+	return retval;
+}
+
+void Buffer::event(const int key, const int32_t value) {
+	if (checkSpace(2 * MAXSIZE_PACK32)) {
+		packInt(key);
+		packInt(value);
+	}
+}
+
+void Buffer::event64(const int key, const int64_t value) {
+	if (checkSpace(MAXSIZE_PACK64 + MAXSIZE_PACK32)) {
+		packInt(key);
+		packInt64(value);
+	}
+}
+
+void Buffer::pea(const uint64_t currTime, const struct perf_event_attr *const pea, int key) {
+	while (!checkSpace(2 * MAXSIZE_PACK32 + pea->size)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_PEA);
+	writeBytes(pea, pea->size);
+	packInt(key);
+	check(currTime);
+}
+
+void Buffer::keys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys) {
+	while (!checkSpace(2 * MAXSIZE_PACK32 + count * (MAXSIZE_PACK32 + MAXSIZE_PACK64))) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KEYS);
+	packInt(count);
+	for (int i = 0; i < count; ++i) {
+		packInt64(ids[i]);
+		packInt(keys[i]);
+	}
+	check(currTime);
+}
+
+void Buffer::keysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf) {
+	while (!checkSpace((2 + keyCount) * MAXSIZE_PACK32 + bytes)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KEYS_OLD);
+	packInt(keyCount);
+	for (int i = 0; i < keyCount; ++i) {
+		packInt(keys[i]);
+	}
+	writeBytes(buf, bytes);
+	check(currTime);
+}
+
+void Buffer::format(const uint64_t currTime, const int length, const char *const format) {
+	while (!checkSpace(MAXSIZE_PACK32 + length + 1)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_FORMAT);
+	writeBytes(format, length + 1);
+	check(currTime);
+}
+
+void Buffer::maps(const uint64_t currTime, const int pid, const int tid, const char *const maps) {
+	const int mapsLen = strlen(maps) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + mapsLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_MAPS);
+	packInt(pid);
+	packInt(tid);
+	writeBytes(maps, mapsLen);
+	check(currTime);
+}
+
+void Buffer::comm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm) {
+	const int imageLen = strlen(image) + 1;
+	const int commLen = strlen(comm) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + imageLen + commLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_COMM);
+	packInt(pid);
+	packInt(tid);
+	writeBytes(image, imageLen);
+	writeBytes(comm, commLen);
+	check(currTime);
+}
+
+void Buffer::onlineCPU(const uint64_t currTime, const uint64_t time, const int cpu) {
+	while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_ONLINE_CPU);
+	packInt64(time);
+	packInt(cpu);
+	check(currTime);
+}
+
+void Buffer::offlineCPU(const uint64_t currTime, const uint64_t time, const int cpu) {
+	while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_OFFLINE_CPU);
+	packInt64(time);
+	packInt(cpu);
+	check(currTime);
+}
+
+void Buffer::kallsyms(const uint64_t currTime, const char *const kallsyms) {
+	const int kallsymsLen = strlen(kallsyms) + 1;
+	while (!checkSpace(3 * MAXSIZE_PACK32 + kallsymsLen)) {
+		sem_wait(&mWriterSem);
+	}
+	packInt(CODE_KALLSYMS);
+	writeBytes(kallsyms, kallsymsLen);
+	check(currTime);
+}
+
+void Buffer::setDone() {
+	mIsDone = true;
+	commit(0);
+}
+
+bool Buffer::isDone() const {
+	return mIsDone && mReadPos == mCommitPos && mCommitPos == mWritePos;
+}
diff --git a/tools/gator/daemon/Buffer.h b/tools/gator/daemon/Buffer.h
new file mode 100644
index 000000000000..6cffd8e39a36
--- /dev/null
+++ b/tools/gator/daemon/Buffer.h
@@ -0,0 +1,106 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef BUFFER_H
+#define BUFFER_H
+
+#include <stdint.h>
+#include <semaphore.h>
+
+#include "k/perf_event.h"
+
+class Sender;
+
+enum {
+	FRAME_SUMMARY       =  1,
+	FRAME_BLOCK_COUNTER =  5,
+	FRAME_EXTERNAL      = 10,
+	FRAME_PERF_ATTRS    = 11,
+	FRAME_PERF          = 12,
+};
+
+class Buffer {
+public:
+	static const size_t MAXSIZE_PACK32 = 5;
+	static const size_t MAXSIZE_PACK64 = 10;
+
+	Buffer(int32_t core, int32_t buftype, const int size, sem_t *const readerSem);
+	~Buffer();
+
+	void write(Sender *sender);
+
+	int bytesAvailable() const;
+	int contiguousSpaceAvailable() const;
+	void commit(const uint64_t time);
+	void check(const uint64_t time);
+
+	// Summary messages
+	void summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname);
+	void coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name);
+
+	// Block Counter messages
+	bool eventHeader(uint64_t curr_time);
+	bool eventTid(int tid);
+	void event(int key, int32_t value);
+	void event64(int key, int64_t value);
+
+	// Perf Attrs messages
+	void pea(const uint64_t currTime, const struct perf_event_attr *const pea, int key);
+	void keys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys);
+	void keysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf);
+	void format(const uint64_t currTime, const int length, const char *const format);
+	void maps(const uint64_t currTime, const int pid, const int tid, const char *const maps);
+	void comm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm);
+	void onlineCPU(const uint64_t currTime, const uint64_t time, const int cpu);
+	void offlineCPU(const uint64_t currTime, const uint64_t time, const int cpu);
+	void kallsyms(const uint64_t currTime, const char *const kallsyms);
+
+	void setDone();
+	bool isDone() const;
+
+	// Prefer a new member to using these functions if possible
+	char *getWritePos() { return mBuf + mWritePos; }
+	void advanceWrite(int bytes) { mWritePos = (mWritePos + bytes) & /*mask*/(mSize - 1); }
+	static void packInt(char *const buf, const int size, int &writePos, int32_t x);
+	void packInt(int32_t x);
+	static void packInt64(char *const buf, const int size, int &writePos, int64_t x);
+	void packInt64(int64_t x);
+	void writeBytes(const void *const data, size_t count);
+	void writeString(const char *const str);
+
+	static void writeLEInt(unsigned char *buf, int v) {
+		buf[0] = (v >> 0) & 0xFF;
+		buf[1] = (v >> 8) & 0xFF;
+		buf[2] = (v >> 16) & 0xFF;
+		buf[3] = (v >> 24) & 0xFF;
+	}
+
+private:
+	void frame();
+	bool commitReady() const;
+	bool checkSpace(int bytes);
+
+	char *const mBuf;
+	sem_t *const mReaderSem;
+	uint64_t mCommitTime;
+	sem_t mWriterSem;
+	const int mSize;
+	int mReadPos;
+	int mWritePos;
+	int mCommitPos;
+	bool mAvailable;
+	bool mIsDone;
+	const int32_t mCore;
+	const int32_t mBufType;
+
+	// Intentionally unimplemented
+	Buffer(const Buffer &);
+	Buffer &operator=(const Buffer &);
+};
+
+#endif // BUFFER_H
diff --git a/tools/gator/daemon/CCNDriver.cpp b/tools/gator/daemon/CCNDriver.cpp
new file mode 100644
index 000000000000..dd1a2b133842
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.cpp
@@ -0,0 +1,295 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CCNDriver.h"
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "k/perf_event.h"
+
+#include "Config.h"
+#include "DriverSource.h"
+#include "Logging.h"
+
+static const char TAG_CATEGORY[] = "category";
+static const char TAG_COUNTER_SET[] = "counter_set";
+static const char TAG_EVENT[] = "event";
+static const char TAG_OPTION[] = "option";
+static const char TAG_OPTION_SET[] = "option_set";
+
+static const char ATTR_AVERAGE_SELECTION[] = "average_selection";
+static const char ATTR_COUNTER[] = "counter";
+static const char ATTR_COUNTER_SET[] = "counter_set";
+static const char ATTR_COUNT[] = "count";
+static const char ATTR_DESCRIPTION[] = "description";
+static const char ATTR_DISPLAY[] = "display";
+static const char ATTR_EVENT[] = "event";
+static const char ATTR_EVENT_DELTA[] = "event_delta";
+static const char ATTR_NAME[] = "name";
+static const char ATTR_OPTION_SET[] = "option_set";
+static const char ATTR_TITLE[] = "title";
+static const char ATTR_UNITS[] = "units";
+
+static const char XP_REGION[] = "XP_Region";
+static const char HNF_REGION[] = "HN-F_Region";
+static const char RNI_REGION[] = "RN-I_Region";
+static const char SBAS_REGION[] = "SBAS_Region";
+static const char CCN_5XX[] = "CCN-5xx";
+#define ARM_CCN_5XX "ARM_CCN_5XX_"
+
+static const char *const VC_TYPES[] = { "REQ", "RSP", "SNP", "DAT" };
+static const char *const XP_EVENT_NAMES[] = { NULL, "H-bit", "S-bit", "P-Cnt", "TknV" };
+static const char *const XP_EVENT_DESCRIPTIONS[] = { NULL, "Set H-bit, signaled when this XP sets the H-bit.", "Set S-bit, signaled when this XP sets the S-bit.", "Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC.", "No TknV, signaled when this XP transmits a valid packet." };
+static const char *const HNF_EVENT_NAMES[] = { NULL, "Cache Miss", "L3 SF Cache Access", "Cache Fill", "POCQ Retry", "POCQ Reqs Recvd", "SF Hit", "SF Evictions", "Snoops Sent", "Snoops Broadcast", "L3 Eviction", "L3 Fill Invalid Way", "MC Retries", "MC Reqs", "QOS HH Retry" };
+static const char *const HNF_EVENT_DESCRIPTIONS[] = { NULL, "Counts the total cache misses. This is the first time lookup result, and is high priority.", "Counts the number of cache accesses. This is the first time access, and is high priority.", "Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache.", "Counts the number of requests that have been retried.", "Counts the number of requests received by HN.", "Counts the number of snoop filter hits.", "Counts the number of snoop filter evictions. Cache invalidations are initiated.", "Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops.", "Counts the number of snoop broadcasts sent.", "Counts the number of L3 evictions.", "Counts the number of L3 fills to an invalid way.", "Counts the number of transactions retried by the memory controller.", "Counts the number of requests to the memory controller.", "Counts the number of times a highest-priority QoS class was retried at the HN-F." };
+static const char *const RNI_EVENT_NAMES[] = { NULL, "S0 RDataBeats", "S1 RDataBeats", "S2 RDataBeats", "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const RNI_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", "S1 RDataBeats.", "S2 RDataBeats.", "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+static const char *const SBAS_EVENT_NAMES[] = { NULL, "S0 RDataBeats", NULL, NULL, "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const SBAS_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", NULL, NULL, "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+
+// This class is used only to poll for CCN-5xx configuration and emit events XML for it. All other operations are handled by PerfDriver
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+}
+
+static unsigned int getConfig(unsigned int node, unsigned int type, unsigned int event, unsigned int port, unsigned int vc) {
+  return
+    ((node  & 0xff) <<  0) |
+    ((type  & 0xff) <<  8) |
+    ((event & 0xff) << 16) |
+    ((port  & 0x03) << 24) |
+    ((vc    & 0x07) << 26) |
+    0;
+}
+
+static bool perfPoll(struct perf_event_attr *const pea) {
+	int fd = sys_perf_event_open(pea, -1, 0, -1, 0);
+	if (fd < 0) {
+		return false;
+	}
+	close(fd);
+	return true;
+}
+
+CCNDriver::CCNDriver() : mNodeTypes(NULL), mXpCount(0) {
+}
+
+CCNDriver::~CCNDriver() {
+	delete mNodeTypes;
+}
+
+bool CCNDriver::claimCounter(const Counter &) const {
+	// Handled by PerfDriver
+	return false;
+}
+
+void CCNDriver::resetCounters() {
+	// Handled by PerfDriver
+}
+
+void CCNDriver::setupCounter(Counter &) {
+	// Handled by PerfDriver
+}
+
+void CCNDriver::readEvents(mxml_node_t *const) {
+	struct stat st;
+	if (stat("/sys/bus/event_source/devices/ccn", &st) != 0) {
+		// Not found
+		return;
+	}
+
+	int type;
+	if (DriverSource::readIntDriver("/sys/bus/event_source/devices/ccn/type", &type) != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to read CCN-5xx type");
+		handleException();
+	}
+
+	// Detect number of xps
+	struct perf_event_attr pea;
+	memset(&pea, 0, sizeof(pea));
+	pea.type = type;
+	pea.size = sizeof(pea);
+
+	mXpCount = 1;
+	while (true) {
+		pea.config = getConfig(0, 0x08, 1, 0, 1) | mXpCount;
+		if (!perfPoll(&pea)) {
+			break;
+		}
+		mXpCount *= 2;
+	};
+	{
+		int lower = mXpCount/2 + 1;
+		while (lower < mXpCount) {
+			int mid = (lower + mXpCount)/2;
+			pea.config = getConfig(0, 0x08, 1, 0, 1) | mid;
+			if (perfPoll(&pea)) {
+				lower = mid + 1;
+			} else {
+				mXpCount = mid;
+			}
+		}
+	}
+
+	mNodeTypes = new NodeType[2*mXpCount];
+
+	// Detect node types
+	for (int i = 0; i < 2*mXpCount; ++i) {
+		pea.config = getConfig(0, 0x04, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_HNF;
+			continue;
+		}
+
+		pea.config = getConfig(0, 0x16, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_RNI;
+			continue;
+		}
+
+		pea.config = getConfig(0, 0x10, 1, 0, 0) | i;
+		if (perfPoll(&pea)) {
+			mNodeTypes[i] = NT_SBAS;
+			continue;
+		}
+
+		mNodeTypes[i] = NT_UNKNOWN;
+	}
+}
+
+int CCNDriver::writeCounters(mxml_node_t *const) const {
+	// Handled by PerfDriver
+	return 0;
+}
+
+void CCNDriver::writeEvents(mxml_node_t *const root) const {
+	mxml_node_t *const counter_set = mxmlNewElement(root, TAG_COUNTER_SET);
+	mxmlElementSetAttr(counter_set, ATTR_NAME, ARM_CCN_5XX "cnt");
+	mxmlElementSetAttr(counter_set, ATTR_COUNT, "8");
+
+	mxml_node_t *const category = mxmlNewElement(root, TAG_CATEGORY);
+	mxmlElementSetAttr(category, ATTR_NAME, CCN_5XX);
+	mxmlElementSetAttr(category, TAG_COUNTER_SET, ARM_CCN_5XX "cnt");
+
+	mxml_node_t *const clock_event = mxmlNewElement(category, TAG_EVENT);
+	mxmlElementSetAttr(clock_event, ATTR_COUNTER, ARM_CCN_5XX "ccnt");
+	mxmlElementSetAttr(clock_event, ATTR_EVENT, "0xff00");
+	mxmlElementSetAttr(clock_event, ATTR_TITLE, "CCN-5xx Clock");
+	mxmlElementSetAttr(clock_event, ATTR_NAME, "Cycles");
+	mxmlElementSetAttr(clock_event, ATTR_DISPLAY, "hertz");
+	mxmlElementSetAttr(clock_event, ATTR_UNITS, "Hz");
+	mxmlElementSetAttr(clock_event, ATTR_AVERAGE_SELECTION, "yes");
+	mxmlElementSetAttr(clock_event, ATTR_DESCRIPTION, "The number of core clock cycles");
+
+	mxml_node_t *const xp_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(xp_option_set, ATTR_NAME, XP_REGION);
+
+	for (int i = 0; i < mXpCount; ++i) {
+		mxml_node_t *const option = mxmlNewElement(xp_option_set, TAG_OPTION);
+		mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+		mxmlElementSetAttrf(option, ATTR_NAME, "XP %i", i);
+		mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Crosspoint %i", i);
+	}
+
+	for (int vc = 0; vc < ARRAY_LENGTH(VC_TYPES); ++vc) {
+		if (VC_TYPES[vc] == NULL) {
+			continue;
+		}
+		for (int bus = 0; bus < 2; ++bus) {
+			for (int eventId = 0; eventId < ARRAY_LENGTH(XP_EVENT_NAMES); ++eventId) {
+				if (XP_EVENT_NAMES[eventId] == NULL) {
+					continue;
+				}
+				mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+				mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x08, eventId, bus, vc));
+				mxmlElementSetAttr(event, ATTR_OPTION_SET, XP_REGION);
+				mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+				mxmlElementSetAttrf(event, ATTR_NAME, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_NAMES[eventId]);
+				mxmlElementSetAttrf(event, ATTR_DESCRIPTION, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_DESCRIPTIONS[eventId]);
+			}
+		}
+	}
+
+	mxml_node_t *const hnf_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(hnf_option_set, ATTR_NAME, HNF_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(HNF_EVENT_NAMES); ++eventId) {
+		if (HNF_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x04, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, HNF_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, HNF_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, HNF_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	mxml_node_t *const rni_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(rni_option_set, ATTR_NAME, RNI_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(RNI_EVENT_NAMES); ++eventId) {
+		if (RNI_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x16, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, RNI_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, RNI_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, RNI_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	mxml_node_t *const sbas_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+	mxmlElementSetAttr(sbas_option_set, ATTR_NAME, SBAS_REGION);
+
+	for (int eventId = 0; eventId < ARRAY_LENGTH(SBAS_EVENT_NAMES); ++eventId) {
+		if (SBAS_EVENT_NAMES[eventId] == NULL) {
+			continue;
+		}
+		mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+		mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x10, eventId, 0, 0));
+		mxmlElementSetAttr(event, ATTR_OPTION_SET, SBAS_REGION);
+		mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+		mxmlElementSetAttr(event, ATTR_NAME, SBAS_EVENT_NAMES[eventId]);
+		mxmlElementSetAttr(event, ATTR_DESCRIPTION, SBAS_EVENT_DESCRIPTIONS[eventId]);
+	}
+
+	for (int i = 0; i < 2*mXpCount; ++i) {
+		switch (mNodeTypes[i]) {
+		case NT_HNF: {
+			mxml_node_t *const option = mxmlNewElement(hnf_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "HN-F %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Fully-coherent Home Node %i", i);
+			break;
+		}
+		case NT_RNI: {
+			mxml_node_t *const option = mxmlNewElement(rni_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "RN-I %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "I/O-coherent Requesting Node %i", i);
+			break;
+		}
+		case NT_SBAS: {
+			mxml_node_t *const option = mxmlNewElement(sbas_option_set, TAG_OPTION);
+			mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+			mxmlElementSetAttrf(option, ATTR_NAME, "SBAS %i", i);
+			mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "ACE master to CHI protocol bridge %i", i);
+			break;
+		}
+		default:
+			continue;
+		}
+	}
+}
diff --git a/tools/gator/daemon/CCNDriver.h b/tools/gator/daemon/CCNDriver.h
new file mode 100644
index 000000000000..fb4c717e969a
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.h
@@ -0,0 +1,43 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CCNDRIVER_H
+#define CCNDRIVER_H
+
+#include "Driver.h"
+
+class CCNDriver : public Driver {
+public:
+	CCNDriver();
+	~CCNDriver();
+
+	bool claimCounter(const Counter &counter) const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+
+	void readEvents(mxml_node_t *const);
+	int writeCounters(mxml_node_t *const root) const;
+	void writeEvents(mxml_node_t *const) const;
+
+private:
+	enum NodeType {
+		NT_UNKNOWN,
+		NT_HNF,
+		NT_RNI,
+		NT_SBAS,
+	};
+
+	NodeType *mNodeTypes;
+	int mXpCount;
+
+	// Intentionally unimplemented
+	CCNDriver(const CCNDriver &);
+	CCNDriver &operator=(const CCNDriver &);
+};
+
+#endif // CCNDRIVER_H
diff --git a/tools/gator/daemon/CPUFreqDriver.cpp b/tools/gator/daemon/CPUFreqDriver.cpp
new file mode 100644
index 000000000000..41f9d6f2b3f4
--- /dev/null
+++ b/tools/gator/daemon/CPUFreqDriver.cpp
@@ -0,0 +1,58 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CPUFreqDriver.h"
+
+#include "Buffer.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+CPUFreqDriver::CPUFreqDriver() : mPrev() {
+}
+
+CPUFreqDriver::~CPUFreqDriver() {
+}
+
+void CPUFreqDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new DriverCounter(getCounters(), strdup("Linux_power_cpu_freq")));
+}
+
+void CPUFreqDriver::read(Buffer *const buffer) {
+	char buf[64];
+	const DriverCounter *const counter = getCounters();
+	if ((counter == NULL) || !counter->isEnabled()) {
+		return;
+	}
+
+	const int key = getCounters()->getKey();
+	bool resetCores = false;
+	for (int i = 0; i < gSessionData->mCores; ++i) {
+		snprintf(buf, sizeof(buf), "/sys/devices/system/cpu/cpu%i/cpufreq/cpuinfo_cur_freq", i);
+		int64_t freq;
+		if (DriverSource::readInt64Driver(buf, &freq) != 0) {
+			freq = 0;
+		}
+		if (mPrev[i] != freq) {
+			mPrev[i] = freq;
+			// Change cores
+			buffer->event64(2, i);
+			resetCores = true;
+			buffer->event64(key, 1000*freq);
+		}
+	}
+	if (resetCores) {
+		// Revert cores, UserSpaceSource is all on core 0
+		buffer->event64(2, 0);
+	}
+}
diff --git a/tools/gator/daemon/CPUFreqDriver.h b/tools/gator/daemon/CPUFreqDriver.h
new file mode 100644
index 000000000000..ad8c9aaa9e7d
--- /dev/null
+++ b/tools/gator/daemon/CPUFreqDriver.h
@@ -0,0 +1,34 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CPUFREQDRIVER_H
+#define CPUFREQDRIVER_H
+
+#include "Config.h"
+#include "Driver.h"
+
+class CPUFreqDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	CPUFreqDriver();
+	~CPUFreqDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void read(Buffer *const buffer);
+
+private:
+	int64_t mPrev[NR_CPUS];
+
+	// Intentionally unimplemented
+	CPUFreqDriver(const CPUFreqDriver &);
+	CPUFreqDriver &operator=(const CPUFreqDriver &);
+};
+
+#endif // CPUFREQDRIVER_H
diff --git a/tools/gator/daemon/CapturedXML.cpp b/tools/gator/daemon/CapturedXML.cpp
new file mode 100644
index 000000000000..0b5802c893bb
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.cpp
@@ -0,0 +1,145 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CapturedXML.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <dirent.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+
+CapturedXML::CapturedXML() {
+}
+
+CapturedXML::~CapturedXML() {
+}
+
+mxml_node_t* CapturedXML::getTree(bool includeTime) {
+	mxml_node_t *xml;
+	mxml_node_t *captured;
+	mxml_node_t *target;
+	int x;
+
+	xml = mxmlNewXML("1.0");
+
+	captured = mxmlNewElement(xml, "captured");
+	mxmlElementSetAttr(captured, "version", "1");
+	if (gSessionData->perf.isSetup()) {
+		mxmlElementSetAttr(captured, "type", "Perf");
+		mxmlElementSetAttr(captured, "perf_beta", "yes");
+	}
+	mxmlElementSetAttrf(captured, "protocol", "%d", PROTOCOL_VERSION);
+	if (includeTime) { // Send the following only after the capture is complete
+		if (time(NULL) > 1267000000) { // If the time is reasonable (after Feb 23, 2010)
+			mxmlElementSetAttrf(captured, "created", "%lu", time(NULL)); // Valid until the year 2038
+		}
+	}
+
+	target = mxmlNewElement(captured, "target");
+	mxmlElementSetAttr(target, "name", gSessionData->mCoreName);
+	mxmlElementSetAttrf(target, "sample_rate", "%d", gSessionData->mSampleRate);
+	mxmlElementSetAttrf(target, "cores", "%d", gSessionData->mCores);
+	mxmlElementSetAttrf(target, "cpuid", "0x%x", gSessionData->mMaxCpuId);
+
+	if (!gSessionData->mOneShot && (gSessionData->mSampleRate > 0)) {
+		mxmlElementSetAttr(target, "supports_live", "yes");
+	}
+
+	if (gSessionData->mLocalCapture) {
+		mxmlElementSetAttr(target, "local_capture", "yes");
+	}
+
+	mxml_node_t *counters = NULL;
+	for (x = 0; x < MAX_PERFORMANCE_COUNTERS; x++) {
+		const Counter & counter = gSessionData->mCounters[x];
+		if (counter.isEnabled()) {
+			if (counters == NULL) {
+				counters = mxmlNewElement(captured, "counters");
+			}
+			mxml_node_t *const node = mxmlNewElement(counters, "counter");
+			mxmlElementSetAttrf(node, "key", "0x%x", counter.getKey());
+			mxmlElementSetAttr(node, "type", counter.getType());
+			if (counter.getEvent() != -1) {
+				mxmlElementSetAttrf(node, "event", "0x%x", counter.getEvent());
+			}
+			if (counter.getCount() > 0) {
+				mxmlElementSetAttrf(node, "count", "%d", counter.getCount());
+			}
+			if (counter.getCores() > 0) {
+				mxmlElementSetAttrf(node, "cores", "%d", counter.getCores());
+			}
+		}
+	}
+
+	return xml;
+}
+
+char* CapturedXML::getXML(bool includeTime) {
+	char* xml_string;
+	mxml_node_t *xml = getTree(includeTime);
+	xml_string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	mxmlDelete(xml);
+	return xml_string;
+}
+
+void CapturedXML::write(char* path) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/captured.xml", path);
+
+	char* xml = getXML(true);
+	if (util->writeToDisk(file, xml) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	free(xml);
+}
+
+// whitespace callback utility function used with mini-xml
+const char * mxmlWhitespaceCB(mxml_node_t *node, int loc) {
+	const char *name;
+
+	name = mxmlGetElement(node);
+
+	if (loc == MXML_WS_BEFORE_OPEN) {
+		// Single indentation
+		if (!strcmp(name, "target") || !strcmp(name, "counters"))
+			return "\n  ";
+
+		// Double indentation
+		if (!strcmp(name, "counter"))
+			return "\n    ";
+
+		// Avoid a carriage return on the first line of the xml file
+		if (!strncmp(name, "?xml", 4))
+			return NULL;
+
+		// Default - no indentation
+		return "\n";
+	}
+
+	if (loc == MXML_WS_BEFORE_CLOSE) {
+		// No indentation
+		if (!strcmp(name, "captured"))
+			return "\n";
+
+		// Single indentation
+		if (!strcmp(name, "counters"))
+			return "\n  ";
+
+		// Default - no carriage return
+		return NULL;
+	}
+
+	return NULL;
+}
diff --git a/tools/gator/daemon/CapturedXML.h b/tools/gator/daemon/CapturedXML.h
new file mode 100644
index 000000000000..b704f6e53bb5
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CAPTURED_XML_H__
+#define __CAPTURED_XML_H__
+
+#include "mxml/mxml.h"
+
+class CapturedXML {
+public:
+	CapturedXML();
+	~CapturedXML();
+	char* getXML(bool includeTime); // the string should be freed by the caller
+	void write(char* path);
+private:
+	mxml_node_t* getTree(bool includeTime);
+};
+
+const char * mxmlWhitespaceCB(mxml_node_t *node, int where);
+
+#endif //__CAPTURED_XML_H__
diff --git a/tools/gator/daemon/Child.cpp b/tools/gator/daemon/Child.cpp
new file mode 100644
index 000000000000..6b5bbb3bf6af
--- /dev/null
+++ b/tools/gator/daemon/Child.cpp
@@ -0,0 +1,392 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Child.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+#include "CapturedXML.h"
+#include "Command.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "DriverSource.h"
+#include "ExternalSource.h"
+#include "FtraceSource.h"
+#include "LocalCapture.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "PerfSource.h"
+#include "Sender.h"
+#include "SessionData.h"
+#include "StreamlineSetup.h"
+#include "UserSpaceSource.h"
+
+static sem_t haltPipeline, senderThreadStarted, startProfile, senderSem; // Shared by Child and spawned threads
+static Source *primarySource = NULL;
+static Source *externalSource = NULL;
+static Source *userSpaceSource = NULL;
+static Source *ftraceSource = NULL;
+static Sender* sender = NULL;        // Shared by Child.cpp and spawned threads
+Child* child = NULL;                 // shared by Child.cpp and main.cpp
+
+extern void cleanUp();
+void handleException() {
+	if (child && child->numExceptions++ > 0) {
+		// it is possible one of the below functions itself can cause an exception, thus allow only one exception
+		logg->logMessage("Received multiple exceptions, terminating the child");
+		exit(1);
+	}
+	fprintf(stderr, "%s", logg->getLastError());
+
+	if (child && child->socket) {
+		if (sender) {
+			// send the error, regardless of the command sent by Streamline
+			sender->writeData(logg->getLastError(), strlen(logg->getLastError()), RESPONSE_ERROR);
+
+			// cannot close the socket before Streamline issues the command, so wait for the command before exiting
+			if (gSessionData->mWaitingOnCommand) {
+				char discard;
+				child->socket->receiveNBytes(&discard, 1);
+			}
+
+			// Ensure all data is flushed
+			child->socket->shutdownConnection();
+
+			// this indirectly calls close socket which will ensure the data has been sent
+			delete sender;
+		}
+	}
+
+	if (gSessionData->mLocalCapture)
+		cleanUp();
+
+	exit(1);
+}
+
+// CTRL C Signal Handler for child process
+static void child_handler(int signum) {
+	static bool beenHere = false;
+	if (beenHere == true) {
+		logg->logMessage("Gator is being forced to shut down.");
+		exit(1);
+	}
+	beenHere = true;
+	logg->logMessage("Gator is shutting down.");
+	if (signum == SIGALRM || !primarySource) {
+		exit(1);
+	} else {
+		child->endSession();
+		alarm(5); // Safety net in case endSession does not complete within 5 seconds
+	}
+}
+
+static void *durationThread(void *) {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-duration", 0, 0, 0);
+	sem_wait(&startProfile);
+	if (gSessionData->mSessionIsActive) {
+		// Time out after duration seconds
+		// Add a second for host-side filtering
+		sleep(gSessionData->mDuration + 1);
+		if (gSessionData->mSessionIsActive) {
+			logg->logMessage("Duration expired.");
+			child->endSession();
+		}
+	}
+	logg->logMessage("Exit duration thread");
+	return 0;
+}
+
+static void *stopThread(void *) {
+	OlySocket* socket = child->socket;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-stopper", 0, 0, 0);
+	while (gSessionData->mSessionIsActive) {
+		// This thread will stall until the APC_STOP or PING command is received over the socket or the socket is disconnected
+		unsigned char header[5];
+		const int result = socket->receiveNBytes((char*)&header, sizeof(header));
+		const char type = header[0];
+		const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+		if (result == -1) {
+			child->endSession();
+		} else if (result > 0) {
+			if ((type != COMMAND_APC_STOP) && (type != COMMAND_PING)) {
+				logg->logMessage("INVESTIGATE: Received unknown command type %d", type);
+			} else {
+				// verify a length of zero
+				if (length == 0) {
+					if (type == COMMAND_APC_STOP) {
+						logg->logMessage("Stop command received.");
+						child->endSession();
+					} else {
+						// Ping is used to make sure gator is alive and requires an ACK as the response
+						logg->logMessage("Ping command received.");
+						sender->writeData(NULL, 0, RESPONSE_ACK);
+					}
+				} else {
+					logg->logMessage("INVESTIGATE: Received stop command but with length = %d", length);
+				}
+			}
+		}
+	}
+
+	logg->logMessage("Exit stop thread");
+	return 0;
+}
+
+static void *senderThread(void *) {
+	char end_sequence[] = {RESPONSE_APC_DATA, 0, 0, 0, 0};
+
+	sem_post(&senderThreadStarted);
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-sender", 0, 0, 0);
+	sem_wait(&haltPipeline);
+
+	while (!primarySource->isDone() ||
+	       !externalSource->isDone() ||
+	       (userSpaceSource != NULL && !userSpaceSource->isDone()) ||
+	       (ftraceSource != NULL && !ftraceSource->isDone())) {
+		sem_wait(&senderSem);
+
+		primarySource->write(sender);
+		externalSource->write(sender);
+		if (userSpaceSource != NULL) {
+			userSpaceSource->write(sender);
+		}
+		if (ftraceSource != NULL) {
+			ftraceSource->write(sender);
+		}
+	}
+
+	// write end-of-capture sequence
+	if (!gSessionData->mLocalCapture) {
+		sender->writeData(end_sequence, sizeof(end_sequence), RESPONSE_APC_DATA);
+	}
+
+	logg->logMessage("Exit sender thread");
+	return 0;
+}
+
+Child::Child() {
+	initialization();
+	gSessionData->mLocalCapture = true;
+}
+
+Child::Child(OlySocket* sock, int conn) {
+	initialization();
+	socket = sock;
+	mNumConnections = conn;
+}
+
+Child::~Child() {
+}
+
+void Child::initialization() {
+	// Set up different handlers for signals
+	gSessionData->mSessionIsActive = true;
+	signal(SIGINT, child_handler);
+	signal(SIGTERM, child_handler);
+	signal(SIGABRT, child_handler);
+	signal(SIGALRM, child_handler);
+	socket = NULL;
+	numExceptions = 0;
+	mNumConnections = 0;
+
+	// Initialize semaphores
+	sem_init(&senderThreadStarted, 0, 0);
+	sem_init(&startProfile, 0, 0);
+	sem_init(&senderSem, 0, 0);
+}
+
+void Child::endSession() {
+	gSessionData->mSessionIsActive = false;
+	primarySource->interrupt();
+	externalSource->interrupt();
+	if (userSpaceSource != NULL) {
+		userSpaceSource->interrupt();
+	}
+	if (ftraceSource != NULL) {
+		ftraceSource->interrupt();
+	}
+	sem_post(&haltPipeline);
+}
+
+void Child::run() {
+	LocalCapture* localCapture = NULL;
+	pthread_t durationThreadID, stopThreadID, senderThreadID;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-child", 0, 0, 0);
+
+	// Disable line wrapping when generating xml files; carriage returns and indentation to be added manually
+	mxmlSetWrapMargin(0);
+
+	// Instantiate the Sender - must be done first, after which error messages can be sent
+	sender = new Sender(socket);
+
+	if (mNumConnections > 1) {
+		logg->logError(__FILE__, __LINE__, "Session already in progress");
+		handleException();
+	}
+
+	// Populate gSessionData with the configuration
+	{ ConfigurationXML configuration; }
+
+	// Set up the driver; must be done after gSessionData->mPerfCounterType[] is populated
+	if (!gSessionData->perf.isSetup()) {
+		primarySource = new DriverSource(&senderSem, &startProfile);
+	} else {
+		primarySource = new PerfSource(&senderSem, &startProfile);
+	}
+
+	// Initialize all drivers
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		driver->resetCounters();
+	}
+
+	// Set up counters using the associated driver's setup function
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		Counter & counter = gSessionData->mCounters[i];
+		if (counter.isEnabled()) {
+			counter.getDriver()->setupCounter(counter);
+		}
+	}
+
+	// Start up and parse session xml
+	if (socket) {
+		// Respond to Streamline requests
+		StreamlineSetup ss(socket);
+	} else {
+		char* xmlString;
+		xmlString = util->readFromDisk(gSessionData->mSessionXMLPath);
+		if (xmlString == 0) {
+			logg->logError(__FILE__, __LINE__, "Unable to read session xml file: %s", gSessionData->mSessionXMLPath);
+			handleException();
+		}
+		gSessionData->parseSessionXML(xmlString);
+		localCapture = new LocalCapture();
+		localCapture->createAPCDirectory(gSessionData->mTargetPath);
+		localCapture->copyImages(gSessionData->mImages);
+		localCapture->write(xmlString);
+		sender->createDataFile(gSessionData->mAPCDir);
+		free(xmlString);
+	}
+
+	if (gSessionData->kmod.isMaliCapture() && (gSessionData->mSampleRate == 0)) {
+		logg->logError(__FILE__, __LINE__, "Mali counters are not supported with Sample Rate: None.");
+		handleException();
+	}
+
+	// Must be after session XML is parsed
+	if (!primarySource->prepare()) {
+		if (gSessionData->perf.isSetup()) {
+			logg->logError(__FILE__, __LINE__, "Unable to prepare gator driver for capture");
+		} else {
+			logg->logError(__FILE__, __LINE__, "Unable to communicate with the perf API, please ensure that CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER are enabled. Please refer to README_Streamline.txt for more information.");
+		}
+		handleException();
+	}
+
+	// Sender thread shall be halted until it is signaled for one shot mode
+	sem_init(&haltPipeline, 0, gSessionData->mOneShot ? 0 : 2);
+
+	// Must be initialized before senderThread is started as senderThread checks externalSource
+	externalSource = new ExternalSource(&senderSem);
+	if (!externalSource->prepare()) {
+		logg->logError(__FILE__, __LINE__, "Unable to prepare external source for capture");
+		handleException();
+	}
+	externalSource->start();
+
+	// Create the duration, stop, and sender threads
+	bool thread_creation_success = true;
+	if (gSessionData->mDuration > 0 && pthread_create(&durationThreadID, NULL, durationThread, NULL)) {
+		thread_creation_success = false;
+	} else if (socket && pthread_create(&stopThreadID, NULL, stopThread, NULL)) {
+		thread_creation_success = false;
+	} else if (pthread_create(&senderThreadID, NULL, senderThread, NULL)) {
+		thread_creation_success = false;
+	}
+
+	bool startUSSource = false;
+	for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+		if (gSessionData->usDrivers[i]->countersEnabled()) {
+			startUSSource = true;
+		}
+	}
+	if (startUSSource) {
+		userSpaceSource = new UserSpaceSource(&senderSem);
+		if (!userSpaceSource->prepare()) {
+			logg->logError(__FILE__, __LINE__, "Unable to prepare userspace source for capture");
+			handleException();
+		}
+		userSpaceSource->start();
+	}
+
+	if (gSessionData->ftraceDriver.countersEnabled()) {
+		ftraceSource = new FtraceSource(&senderSem);
+		if (!ftraceSource->prepare()) {
+			logg->logError(__FILE__, __LINE__, "Unable to prepare userspace source for capture");
+			handleException();
+		}
+		ftraceSource->start();
+	}
+
+	if (gSessionData->mAllowCommands && (gSessionData->mCaptureCommand != NULL)) {
+		pthread_t thread;
+		if (pthread_create(&thread, NULL, commandThread, NULL)) {
+			thread_creation_success = false;
+		}
+	}
+
+	if (!thread_creation_success) {
+		logg->logError(__FILE__, __LINE__, "Failed to create gator threads");
+		handleException();
+	}
+
+	// Wait until thread has started
+	sem_wait(&senderThreadStarted);
+
+	// Start profiling
+	primarySource->run();
+
+	if (ftraceSource != NULL) {
+		ftraceSource->join();
+	}
+	if (userSpaceSource != NULL) {
+		userSpaceSource->join();
+	}
+	externalSource->join();
+
+	// Wait for the other threads to exit
+	pthread_join(senderThreadID, NULL);
+
+	// Shutting down the connection should break the stop thread which is stalling on the socket recv() function
+	if (socket) {
+		logg->logMessage("Waiting on stop thread");
+		socket->shutdownConnection();
+		pthread_join(stopThreadID, NULL);
+	}
+
+	// Write the captured xml file
+	if (gSessionData->mLocalCapture) {
+		CapturedXML capturedXML;
+		capturedXML.write(gSessionData->mAPCDir);
+	}
+
+	logg->logMessage("Profiling ended.");
+
+	delete ftraceSource;
+	delete userSpaceSource;
+	delete externalSource;
+	delete primarySource;
+	delete sender;
+	delete localCapture;
+}
diff --git a/tools/gator/daemon/Child.h b/tools/gator/daemon/Child.h
new file mode 100644
index 000000000000..cc78202ceb5c
--- /dev/null
+++ b/tools/gator/daemon/Child.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CHILD_H__
+#define __CHILD_H__
+
+class OlySocket;
+
+class Child {
+public:
+	Child();
+	Child(OlySocket* sock, int numConnections);
+	~Child();
+	void run();
+	OlySocket *socket;
+	void endSession();
+	int numExceptions;
+private:
+	int mNumConnections;
+
+	void initialization();
+
+	// Intentionally unimplemented
+	Child(const Child &);
+	Child &operator=(const Child &);
+};
+
+#endif //__CHILD_H__
diff --git a/tools/gator/daemon/Command.cpp b/tools/gator/daemon/Command.cpp
new file mode 100644
index 000000000000..28d73cf5a905
--- /dev/null
+++ b/tools/gator/daemon/Command.cpp
@@ -0,0 +1,172 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Command.h"
+
+#include <fcntl.h>
+#include <pwd.h>
+#include <stdio.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+static int getUid(const char *const name, char *const shPath, const char *const tmpDir) {
+	// Lookups may fail when using a different libc or a statically compiled executable
+	char gatorTemp[32];
+	snprintf(gatorTemp, sizeof(gatorTemp), "%s/gator_temp", tmpDir);
+
+	const int fd = open(gatorTemp, 600, O_CREAT | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+	close(fd);
+
+	char cmd[128];
+	snprintf(cmd, sizeof(cmd), "chown %s %s || rm %s", name, gatorTemp, gatorTemp);
+
+	const int pid = fork();
+	if (pid < 0) {
+		logg->logError(__FILE__, __LINE__, "fork failed");
+		handleException();
+	}
+	if (pid == 0) {
+		char cargv1[] = "-c";
+		char *cargv[] = {
+			shPath,
+			cargv1,
+			cmd,
+			NULL,
+		};
+
+		execv(cargv[0], cargv);
+		exit(-1);
+	}
+	while ((waitpid(pid, NULL, 0) < 0) && (errno == EINTR));
+
+	struct stat st;
+	int result = -1;
+	if (stat(gatorTemp, &st) == 0) {
+		result = st.st_uid;
+	}
+	unlink(gatorTemp);
+	return result;
+}
+
+static int getUid(const char *const name) {
+	// Look up the username
+	struct passwd *const user = getpwnam(name);
+	if (user != NULL) {
+		return user->pw_uid;
+	}
+
+
+	// Are we on Linux
+	char cargv0l[] = "/bin/sh";
+	if ((access(cargv0l, X_OK) == 0) && (access("/tmp", W_OK) == 0)) {
+		return getUid(name, cargv0l, "/tmp");
+	}
+
+	// Are we on android
+	char cargv0a[] = "/system/bin/sh";
+	if ((access(cargv0a, X_OK) == 0) && (access("/data", W_OK) == 0)) {
+		return getUid(name, cargv0a, "/data");
+	}
+
+	return -1;
+}
+
+void *commandThread(void *) {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-command", 0, 0, 0);
+
+	const char *const name = gSessionData->mCaptureUser == NULL ? "nobody" : gSessionData->mCaptureUser;
+	const int uid = getUid(name);
+	if (uid < 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to lookup the user %s, please double check that the user exists", name);
+		handleException();
+	}
+
+	sleep(3);
+
+	char buf[128];
+	int pipefd[2];
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError(__FILE__, __LINE__, "pipe failed");
+		handleException();
+	}
+
+	const int pid = fork();
+	if (pid < 0) {
+		logg->logError(__FILE__, __LINE__, "fork failed");
+		handleException();
+	}
+	if (pid == 0) {
+		char cargv0l[] = "/bin/sh";
+		char cargv0a[] = "/system/bin/sh";
+		char cargv1[] = "-c";
+		char *cargv[] = {
+			cargv0l,
+			cargv1,
+			gSessionData->mCaptureCommand,
+			NULL,
+		};
+
+		buf[0] = '\0';
+		close(pipefd[0]);
+
+		// Gator runs at a high priority, reset the priority to the default
+		if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+			snprintf(buf, sizeof(buf), "setpriority failed");
+			goto fail_exit;
+		}
+
+		if (setuid(uid) != 0) {
+			snprintf(buf, sizeof(buf), "setuid failed");
+			goto fail_exit;
+		}
+
+		{
+			const char *const path = gSessionData->mCaptureWorkingDir == NULL ? "/" : gSessionData->mCaptureWorkingDir;
+			if (chdir(path) != 0) {
+				snprintf(buf, sizeof(buf), "Unable to cd to %s, please verify the directory exists and is accessable to %s", path, name);
+				goto fail_exit;
+			}
+		}
+
+		execv(cargv[0], cargv);
+		cargv[0] = cargv0a;
+		execv(cargv[0], cargv);
+		snprintf(buf, sizeof(buf), "execv failed");
+
+	fail_exit:
+		if (buf[0] != '\0') {
+			const ssize_t bytes = write(pipefd[1], buf, sizeof(buf));
+			// Can't do anything if this fails
+			(void)bytes;
+		}
+
+		exit(-1);
+	}
+
+	close(pipefd[1]);
+	const ssize_t bytes = read(pipefd[0], buf, sizeof(buf));
+	if (bytes > 0) {
+		logg->logError(__FILE__, __LINE__, buf);
+		handleException();
+	}
+	close(pipefd[0]);
+
+	return NULL;
+}
diff --git a/tools/gator/daemon/Command.h b/tools/gator/daemon/Command.h
new file mode 100644
index 000000000000..17244b7aaebc
--- /dev/null
+++ b/tools/gator/daemon/Command.h
@@ -0,0 +1,14 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COMMAND_H
+#define COMMAND_H
+
+void *commandThread(void *);
+
+#endif // COMMAND_H
diff --git a/tools/gator/daemon/Config.h b/tools/gator/daemon/Config.h
new file mode 100644
index 000000000000..bee383a1c797
--- /dev/null
+++ b/tools/gator/daemon/Config.h
@@ -0,0 +1,28 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CONFIG_H
+#define CONFIG_H
+
+#define ARRAY_LENGTH(A) static_cast<int>(sizeof(A)/sizeof((A)[0]))
+#define ACCESS_ONCE(x) (*(volatile typeof(x)*)&(x))
+
+#define MAX_PERFORMANCE_COUNTERS 50
+#define NR_CPUS 32
+
+template<typename T>
+static inline T min(const T a, const T b) {
+	return (a < b ? a : b);
+}
+
+template<typename T>
+static inline T max(const T a, const T b) {
+	return (a > b ? a : b);
+}
+
+#endif // CONFIG_H
diff --git a/tools/gator/daemon/ConfigurationXML.cpp b/tools/gator/daemon/ConfigurationXML.cpp
new file mode 100644
index 000000000000..6590dd389196
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.cpp
@@ -0,0 +1,217 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ConfigurationXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <dirent.h>
+
+#include "Driver.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char* ATTR_COUNTER            = "counter";
+static const char* ATTR_REVISION           = "revision";
+static const char* ATTR_EVENT              = "event";
+static const char* ATTR_COUNT              = "count";
+static const char* ATTR_CORES              = "cores";
+
+ConfigurationXML::ConfigurationXML() {
+	const char * configuration_xml;
+	unsigned int configuration_xml_len;
+	getDefaultConfigurationXml(configuration_xml, configuration_xml_len);
+
+	char path[PATH_MAX];
+
+	getPath(path);
+	mConfigurationXML = util->readFromDisk(path);
+
+	for (int retryCount = 0; retryCount < 2; ++retryCount) {
+		if (mConfigurationXML == NULL) {
+			logg->logMessage("Unable to locate configuration.xml, using default in binary");
+			// null-terminate configuration_xml
+			mConfigurationXML = (char*)malloc(configuration_xml_len + 1);
+			memcpy(mConfigurationXML, (const void*)configuration_xml, configuration_xml_len);
+			mConfigurationXML[configuration_xml_len] = 0;
+		}
+
+		int ret = parse(mConfigurationXML);
+		if (ret == 1) {
+			remove();
+
+			// Free the current configuration and reload
+			free((void*)mConfigurationXML);
+			mConfigurationXML = NULL;
+			continue;
+		}
+
+		break;
+	}
+
+	validate();
+}
+
+ConfigurationXML::~ConfigurationXML() {
+	if (mConfigurationXML) {
+		free((void*)mConfigurationXML);
+	}
+}
+
+int ConfigurationXML::parse(const char* configurationXML) {
+	mxml_node_t *tree, *node;
+	int ret;
+
+	// clear counter overflow
+	gSessionData->mCounterOverflow = 0;
+	gSessionData->mIsEBS = false;
+	mIndex = 0;
+
+	// disable all counters prior to parsing the configuration xml
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		gSessionData->mCounters[i].setEnabled(false);
+	}
+
+	tree = mxmlLoadString(NULL, configurationXML, MXML_NO_CALLBACK);
+
+	node = mxmlGetFirstChild(tree);
+	while (node && mxmlGetType(node) != MXML_ELEMENT)
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+
+	ret = configurationsTag(node);
+
+	node = mxmlGetFirstChild(node);
+	while (node) {
+		if (mxmlGetType(node) != MXML_ELEMENT) {
+			node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+			continue;
+		}
+		configurationTag(node);
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+	}
+
+	mxmlDelete(tree);
+
+	return ret;
+}
+
+void ConfigurationXML::validate(void) {
+	for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+		const Counter & counter = gSessionData->mCounters[i];
+		if (counter.isEnabled()) {
+			if (strcmp(counter.getType(), "") == 0) {
+				logg->logError(__FILE__, __LINE__, "Invalid required attribute in configuration.xml:\n  counter=\"%s\"\n  event=%d\n", counter.getType(), counter.getEvent());
+				handleException();
+			}
+
+			// iterate through the remaining enabled performance counters
+			for (int j = i + 1; j < MAX_PERFORMANCE_COUNTERS; j++) {
+				const Counter & counter2 = gSessionData->mCounters[j];
+				if (counter2.isEnabled()) {
+					// check if the types are the same
+					if (strcmp(counter.getType(), counter2.getType()) == 0) {
+						logg->logError(__FILE__, __LINE__, "Duplicate performance counter type in configuration.xml: %s", counter.getType());
+						handleException();
+					}
+				}
+			}
+		}
+	}
+}
+
+#define CONFIGURATION_REVISION 3
+int ConfigurationXML::configurationsTag(mxml_node_t *node) {
+	const char* revision_string;
+
+	revision_string = mxmlElementGetAttr(node, ATTR_REVISION);
+	if (!revision_string) {
+		return 1; //revision issue;
+	}
+
+	int revision = strtol(revision_string, NULL, 10);
+	if (revision < CONFIGURATION_REVISION) {
+		return 1; // revision issue
+	}
+
+	// A revision >= CONFIGURATION_REVISION is okay
+	// Greater than can occur when Streamline is newer than gator
+
+	return 0;
+}
+
+void ConfigurationXML::configurationTag(mxml_node_t *node) {
+	// handle all other performance counters
+	if (mIndex >= MAX_PERFORMANCE_COUNTERS) {
+		mIndex++;
+		gSessionData->mCounterOverflow = mIndex;
+		return;
+	}
+
+	// read attributes
+	Counter & counter = gSessionData->mCounters[mIndex];
+	counter.clear();
+	if (mxmlElementGetAttr(node, ATTR_COUNTER)) counter.setType(mxmlElementGetAttr(node, ATTR_COUNTER));
+	if (mxmlElementGetAttr(node, ATTR_EVENT)) counter.setEvent(strtol(mxmlElementGetAttr(node, ATTR_EVENT), NULL, 16));
+	if (mxmlElementGetAttr(node, ATTR_COUNT)) counter.setCount(strtol(mxmlElementGetAttr(node, ATTR_COUNT), NULL, 10));
+	if (mxmlElementGetAttr(node, ATTR_CORES)) counter.setCores(strtol(mxmlElementGetAttr(node, ATTR_CORES), NULL, 10));
+	if (counter.getCount() > 0) {
+		gSessionData->mIsEBS = true;
+	}
+	counter.setEnabled(true);
+
+	// Associate a driver with each counter
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		if (driver->claimCounter(counter)) {
+			if (counter.getDriver() != NULL) {
+				logg->logError(__FILE__, __LINE__, "More than one driver has claimed %s:%i", counter.getType(), counter.getEvent());
+				handleException();
+			}
+			counter.setDriver(driver);
+		}
+	}
+
+	// If no driver is associated with the counter, disable it
+	if (counter.getDriver() == NULL) {
+		logg->logMessage("No driver has claimed %s:%i", counter.getType(), counter.getEvent());
+		counter.setEnabled(false);
+	}
+
+	if (counter.isEnabled()) {
+		// update counter index
+		mIndex++;
+	}
+}
+
+void ConfigurationXML::getDefaultConfigurationXml(const char * & xml, unsigned int & len) {
+#include "defaults_xml.h" // defines and initializes char defaults_xml[] and int defaults_xml_len
+	xml = (const char *)defaults_xml;
+	len = defaults_xml_len;
+}
+
+void ConfigurationXML::getPath(char* path) {
+	if (gSessionData->mConfigurationXMLPath) {
+		strncpy(path, gSessionData->mConfigurationXMLPath, PATH_MAX);
+	} else {
+		if (util->getApplicationFullPath(path, PATH_MAX) != 0) {
+			logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+		}
+		strncat(path, "configuration.xml", PATH_MAX - strlen(path) - 1);
+	}
+}
+
+void ConfigurationXML::remove() {
+	char path[PATH_MAX];
+	getPath(path);
+
+	if (::remove(path) != 0) {
+		logg->logError(__FILE__, __LINE__, "Invalid configuration.xml file detected and unable to delete it. To resolve, delete configuration.xml on disk");
+		handleException();
+	}
+	logg->logMessage("Invalid configuration.xml file detected and removed");
+}
diff --git a/tools/gator/daemon/ConfigurationXML.h b/tools/gator/daemon/ConfigurationXML.h
new file mode 100644
index 000000000000..efa415e508b6
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTERS_H
+#define COUNTERS_H
+
+#include "mxml/mxml.h"
+
+class ConfigurationXML {
+public:
+	static void getDefaultConfigurationXml(const char * & xml, unsigned int & len);
+	static void getPath(char* path);
+	static void remove();
+
+	ConfigurationXML();
+	~ConfigurationXML();
+	const char* getConfigurationXML() {return mConfigurationXML;}
+	void validate(void);
+
+private:
+	char* mConfigurationXML;
+	int mIndex;
+
+	int parse(const char* xmlFile);
+	int configurationsTag(mxml_node_t *node);
+	void configurationTag(mxml_node_t *node);
+
+	// Intentionally unimplemented
+	ConfigurationXML(const ConfigurationXML &);
+	ConfigurationXML &operator=(const ConfigurationXML &);
+};
+
+#endif // COUNTERS_H
diff --git a/tools/gator/daemon/Counter.h b/tools/gator/daemon/Counter.h
new file mode 100644
index 000000000000..5202aa046362
--- /dev/null
+++ b/tools/gator/daemon/Counter.h
@@ -0,0 +1,65 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTER_H
+#define COUNTER_H
+
+#include <string.h>
+
+class Driver;
+
+class Counter {
+public:
+	static const size_t MAX_STRING_LEN = 80;
+	static const size_t MAX_DESCRIPTION_LEN = 400;
+
+	Counter () {
+		clear();
+	}
+
+	void clear () {
+		mType[0] = '\0';
+		mEnabled = false;
+		mEvent = -1;
+		mCount = 0;
+		mCores = -1;
+		mKey = 0;
+		mDriver = NULL;
+	}
+
+	void setType(const char *const type) { strncpy(mType, type, sizeof(mType)); mType[sizeof(mType) - 1] = '\0'; }
+	void setEnabled(const bool enabled) { mEnabled = enabled; }
+	void setEvent(const int event) { mEvent = event; }
+	void setCount(const int count) { mCount = count; }
+	void setCores(const int cores) { mCores = cores; }
+	void setKey(const int key) { mKey = key; }
+	void setDriver(Driver *const driver) { mDriver = driver; }
+
+	const char *getType() const { return mType;}
+	bool isEnabled() const { return mEnabled; }
+	int getEvent() const { return mEvent; }
+	int getCount() const { return mCount; }
+	int getCores() const { return mCores; }
+	int getKey() const { return mKey; }
+	Driver *getDriver() const { return mDriver; }
+
+private:
+	// Intentionally unimplemented
+	Counter(const Counter &);
+	Counter & operator=(const Counter &);
+
+	char mType[MAX_STRING_LEN];
+	bool mEnabled;
+	int mEvent;
+	int mCount;
+	int mCores;
+	int mKey;
+	Driver *mDriver;
+};
+
+#endif // COUNTER_H
diff --git a/tools/gator/daemon/DiskIODriver.cpp b/tools/gator/daemon/DiskIODriver.cpp
new file mode 100644
index 000000000000..5deb0f375f3a
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.cpp
@@ -0,0 +1,125 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DiskIODriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class DiskIOCounter : public DriverCounter {
+public:
+	DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~DiskIOCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+	int64_t mPrev;
+
+	// Intentionally unimplemented
+	DiskIOCounter(const DiskIOCounter &);
+	DiskIOCounter &operator=(const DiskIOCounter &);
+};
+
+DiskIOCounter::DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+DiskIOCounter::~DiskIOCounter() {
+}
+
+int64_t DiskIOCounter::read() {
+	int64_t result = *mValue - mPrev;
+	mPrev = *mValue;
+	// Kernel assumes a sector is 512 bytes
+	return result << 9;
+}
+
+DiskIODriver::DiskIODriver() : mBuf(), mReadBytes(0), mWriteBytes(0) {
+}
+
+DiskIODriver::~DiskIODriver() {
+}
+
+void DiskIODriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_rd"), &mReadBytes));
+	setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_wr"), &mWriteBytes));
+}
+
+void DiskIODriver::doRead() {
+	if (!countersEnabled()) {
+		return;
+	}
+
+	if (!mBuf.read("/proc/diskstats")) {
+		logg->logError(__FILE__, __LINE__, "Unable to read /proc/diskstats");
+		handleException();
+	}
+
+	mReadBytes = 0;
+	mWriteBytes = 0;
+
+	char *lastName = NULL;
+	int lastNameLen = -1;
+	char *start = mBuf.getBuf();
+	while (*start != '\0') {
+		char *end = strchr(start, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+
+		int nameStart = -1;
+		int nameEnd = -1;
+		int64_t readBytes = -1;
+		int64_t writeBytes = -1;
+		const int count = sscanf(start, "%*d %*d %n%*s%n %*u %*u %" SCNu64 " %*u %*u %*u %" SCNu64, &nameStart, &nameEnd, &readBytes, &writeBytes);
+		if (count != 2) {
+			logg->logError(__FILE__, __LINE__, "Unable to parse /proc/diskstats");
+			handleException();
+		}
+
+		// Skip partitions which are identified if the name is a substring of the last non-partition
+		if ((lastName == NULL) || (strncmp(lastName, start + nameStart, lastNameLen) != 0)) {
+			lastName = start + nameStart;
+			lastNameLen = nameEnd - nameStart;
+			mReadBytes += readBytes;
+			mWriteBytes += writeBytes;
+		}
+
+		if (end == NULL) {
+			break;
+		}
+		start = end + 1;
+	}
+}
+
+void DiskIODriver::start() {
+	doRead();
+	// Initialize previous values
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
+
+void DiskIODriver::read(Buffer *const buffer) {
+	doRead();
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/DiskIODriver.h b/tools/gator/daemon/DiskIODriver.h
new file mode 100644
index 000000000000..d0db18c77d04
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DISKIODRIVER_H
+#define DISKIODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class DiskIODriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	DiskIODriver();
+	~DiskIODriver();
+
+	void readEvents(mxml_node_t *const root);
+	void start();
+	void read(Buffer *const buffer);
+
+private:
+	void doRead();
+
+	DynBuf mBuf;
+	int64_t mReadBytes;
+	int64_t mWriteBytes;
+
+	// Intentionally unimplemented
+	DiskIODriver(const DiskIODriver &);
+	DiskIODriver &operator=(const DiskIODriver &);
+};
+
+#endif // DISKIODRIVER_H
diff --git a/tools/gator/daemon/Driver.cpp b/tools/gator/daemon/Driver.cpp
new file mode 100644
index 000000000000..275da31c7a0d
--- /dev/null
+++ b/tools/gator/daemon/Driver.cpp
@@ -0,0 +1,96 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Driver.h"
+
+#include "Buffer.h"
+#include "SessionData.h"
+
+DriverCounter::DriverCounter(DriverCounter *const next, const char *const name) : mNext(next), mName(name), mKey(getEventKey()), mEnabled(false) {
+}
+
+DriverCounter::~DriverCounter() {
+	delete mName;
+}
+
+Driver *Driver::head = NULL;
+
+Driver::Driver() : next(head) {
+	head = this;
+}
+
+SimpleDriver::~SimpleDriver() {
+	DriverCounter *counters = mCounters;
+	while (counters != NULL) {
+		DriverCounter *counter = counters;
+		counters = counter->getNext();
+		delete counter;
+	}
+}
+
+DriverCounter *SimpleDriver::findCounter(const Counter &counter) const {
+	for (DriverCounter *driverCounter = mCounters; driverCounter != NULL; driverCounter = driverCounter->getNext()) {
+		if (strcmp(driverCounter->getName(), counter.getType()) == 0) {
+			return driverCounter;
+		}
+	}
+
+	return NULL;
+}
+
+bool SimpleDriver::claimCounter(const Counter &counter) const {
+	return findCounter(counter) != NULL;
+}
+
+bool SimpleDriver::countersEnabled() const {
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		if (counter->isEnabled()) {
+			return true;
+		}
+	}
+	return false;
+}
+
+void SimpleDriver::resetCounters() {
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		counter->setEnabled(false);
+	}
+}
+
+void SimpleDriver::setupCounter(Counter &counter) {
+	DriverCounter *const driverCounter = findCounter(counter);
+	if (driverCounter == NULL) {
+		counter.setEnabled(false);
+		return;
+	}
+	driverCounter->setEnabled(true);
+	counter.setKey(driverCounter->getKey());
+}
+
+int SimpleDriver::writeCounters(mxml_node_t *root) const {
+	int count = 0;
+	for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+		mxml_node_t *node = mxmlNewElement(root, "counter");
+		mxmlElementSetAttr(node, "name", counter->getName());
+		++count;
+	}
+
+	return count;
+}
+
+PolledDriver::~PolledDriver() {
+}
+
+void PolledDriver::read(Buffer *const buffer) {
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		buffer->event64(counter->getKey(), counter->read());
+	}
+}
diff --git a/tools/gator/daemon/Driver.h b/tools/gator/daemon/Driver.h
new file mode 100644
index 000000000000..72870e3dbca1
--- /dev/null
+++ b/tools/gator/daemon/Driver.h
@@ -0,0 +1,118 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVER_H
+#define DRIVER_H
+
+#include <stdint.h>
+
+#include "mxml/mxml.h"
+
+class Buffer;
+class Counter;
+
+class DriverCounter {
+public:
+	DriverCounter(DriverCounter *const next, const char *const name);
+	virtual ~DriverCounter();
+
+	DriverCounter *getNext() const { return mNext; }
+	const char *getName() const { return mName; }
+	int getKey() const { return mKey; }
+	bool isEnabled() const { return mEnabled; }
+	void setEnabled(const bool enabled) { mEnabled = enabled; }
+	virtual int64_t read() { return -1; }
+
+private:
+	DriverCounter *const mNext;
+	const char *const mName;
+	const int mKey;
+	bool mEnabled;
+
+	// Intentionally unimplemented
+	DriverCounter(const DriverCounter &);
+	DriverCounter &operator=(const DriverCounter &);
+};
+
+class Driver {
+public:
+	static Driver *getHead() { return head; }
+
+	virtual ~Driver() {}
+
+	// Returns true if this driver can manage the counter
+	virtual bool claimCounter(const Counter &counter) const = 0;
+	// Clears and disables all counters
+	virtual void resetCounters() = 0;
+	// Enables and prepares the counter for capture
+	virtual void setupCounter(Counter &counter) = 0;
+
+	// Performs any actions needed for setup or based on eventsXML
+	virtual void readEvents(mxml_node_t *const) {}
+	// Emits available counters
+	virtual int writeCounters(mxml_node_t *const root) const = 0;
+	// Emits possible dynamically generated events/counters
+	virtual void writeEvents(mxml_node_t *const) const {}
+
+	Driver *getNext() const { return next; }
+
+protected:
+	Driver();
+
+private:
+	static Driver *head;
+	Driver *next;
+
+	// Intentionally unimplemented
+	Driver(const Driver &);
+	Driver &operator=(const Driver &);
+};
+
+class SimpleDriver : public Driver {
+public:
+	virtual ~SimpleDriver();
+
+	bool claimCounter(const Counter &counter) const;
+	bool countersEnabled() const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+	int writeCounters(mxml_node_t *root) const;
+
+protected:
+	SimpleDriver() : mCounters(NULL) {}
+
+	DriverCounter *getCounters() const { return mCounters; }
+	void setCounters(DriverCounter *const counter) { mCounters = counter; }
+
+	DriverCounter *findCounter(const Counter &counter) const;
+
+private:
+	DriverCounter *mCounters;
+
+	// Intentionally unimplemented
+	SimpleDriver(const SimpleDriver &);
+	SimpleDriver &operator=(const SimpleDriver &);
+};
+
+class PolledDriver : public SimpleDriver {
+public:
+	virtual ~PolledDriver();
+
+	virtual void start() {}
+	virtual void read(Buffer *const buffer);
+
+protected:
+	PolledDriver() {}
+
+private:
+	// Intentionally unimplemented
+	PolledDriver(const PolledDriver &);
+	PolledDriver &operator=(const PolledDriver &);
+};
+
+#endif // DRIVER_H
diff --git a/tools/gator/daemon/DriverSource.cpp b/tools/gator/daemon/DriverSource.cpp
new file mode 100644
index 000000000000..7f299b646952
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.cpp
@@ -0,0 +1,322 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DriverSource.h"
+
+#include <fcntl.h>
+#include <inttypes.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Child.h"
+#include "DynBuf.h"
+#include "Fifo.h"
+#include "Logging.h"
+#include "Proc.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+DriverSource::DriverSource(sem_t *senderSem, sem_t *startProfile) : mBuffer(NULL), mFifo(NULL), mSenderSem(senderSem), mStartProfile(startProfile), mBufferSize(0), mBufferFD(0), mLength(1) {
+	int driver_version = 0;
+
+	mBuffer = new Buffer(0, FRAME_PERF_ATTRS, 4*1024*1024, senderSem);
+	if (readIntDriver("/dev/gator/version", &driver_version) == -1) {
+		logg->logError(__FILE__, __LINE__, "Error reading gator driver version");
+		handleException();
+	}
+
+	// Verify the driver version matches the daemon version
+	if (driver_version != PROTOCOL_VERSION) {
+		if ((driver_version > PROTOCOL_DEV) || (PROTOCOL_VERSION > PROTOCOL_DEV)) {
+			// One of the mismatched versions is development version
+			logg->logError(__FILE__, __LINE__,
+				"DEVELOPMENT BUILD MISMATCH: gator driver version \"%d\" is not in sync with gator daemon version \"%d\".\n"
+				">> The following must be synchronized from engineering repository:\n"
+				">> * gator driver\n"
+				">> * gator daemon\n"
+				">> * Streamline", driver_version, PROTOCOL_VERSION);
+			handleException();
+		} else {
+			// Release version mismatch
+			logg->logError(__FILE__, __LINE__,
+				"gator driver version \"%d\" is different than gator daemon version \"%d\".\n"
+				">> Please upgrade the driver and daemon to the latest versions.", driver_version, PROTOCOL_VERSION);
+			handleException();
+		}
+	}
+
+	int enable = -1;
+	if (readIntDriver("/dev/gator/enable", &enable) != 0 || enable != 0) {
+		logg->logError(__FILE__, __LINE__, "Driver already enabled, possibly a session is already in progress.");
+		handleException();
+	}
+
+	readIntDriver("/dev/gator/cpu_cores", &gSessionData->mCores);
+	if (gSessionData->mCores == 0) {
+		gSessionData->mCores = 1;
+	}
+
+	if (readIntDriver("/dev/gator/buffer_size", &mBufferSize) || mBufferSize <= 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to read the driver buffer size");
+		handleException();
+	}
+}
+
+DriverSource::~DriverSource() {
+	delete mFifo;
+
+	// Write zero for safety, as a zero should have already been written
+	writeDriver("/dev/gator/enable", "0");
+
+	// Calls event_buffer_release in the driver
+	if (mBufferFD) {
+		close(mBufferFD);
+	}
+}
+
+bool DriverSource::prepare() {
+	// Create user-space buffers, add 5 to the size to account for the 1-byte type and 4-byte length
+	logg->logMessage("Created %d MB collector buffer with a %d-byte ragged end", gSessionData->mTotalBufferSize, mBufferSize);
+	mFifo = new Fifo(mBufferSize + 5, gSessionData->mTotalBufferSize*1024*1024, mSenderSem);
+
+	return true;
+}
+
+void DriverSource::bootstrapThread() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+	DynBuf printb;
+	DynBuf b1;
+	DynBuf b2;
+	const uint64_t currTime = getTime();
+
+	if (!readProcComms(currTime, mBuffer, &printb, &b1, &b2)) {
+		logg->logError(__FILE__, __LINE__, "readProcComms failed");
+		handleException();
+	}
+
+	mBuffer->commit(currTime);
+	mBuffer->setDone();
+}
+
+void *DriverSource::bootstrapThreadStatic(void *arg) {
+	static_cast<DriverSource *>(arg)->bootstrapThread();
+	return NULL;
+}
+
+void DriverSource::run() {
+	// Get the initial pointer to the collect buffer
+	char *collectBuffer = mFifo->start();
+	int bytesCollected = 0;
+
+	logg->logMessage("********** Profiling started **********");
+
+	// Set the maximum backtrace depth
+	if (writeReadDriver("/dev/gator/backtrace_depth", &gSessionData->mBacktraceDepth)) {
+		logg->logError(__FILE__, __LINE__, "Unable to set the driver backtrace depth");
+		handleException();
+	}
+
+	// open the buffer which calls userspace_buffer_open() in the driver
+	mBufferFD = open("/dev/gator/buffer", O_RDONLY | O_CLOEXEC);
+	if (mBufferFD < 0) {
+		logg->logError(__FILE__, __LINE__, "The gator driver did not set up properly. Please view the linux console or dmesg log for more information on the failure.");
+		handleException();
+	}
+
+	// set the tick rate of the profiling timer
+	if (writeReadDriver("/dev/gator/tick", &gSessionData->mSampleRate) != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to set the driver tick");
+		handleException();
+	}
+
+	// notify the kernel of the response type
+	int response_type = gSessionData->mLocalCapture ? 0 : RESPONSE_APC_DATA;
+	if (writeDriver("/dev/gator/response_type", response_type)) {
+		logg->logError(__FILE__, __LINE__, "Unable to write the response type");
+		handleException();
+	}
+
+	// Set the live rate
+	if (writeReadDriver("/dev/gator/live_rate", &gSessionData->mLiveRate)) {
+		logg->logError(__FILE__, __LINE__, "Unable to set the driver live rate");
+		handleException();
+	}
+
+	logg->logMessage("Start the driver");
+
+	// This command makes the driver start profiling by calling gator_op_start() in the driver
+	if (writeDriver("/dev/gator/enable", "1") != 0) {
+		logg->logError(__FILE__, __LINE__, "The gator driver did not start properly. Please view the linux console or dmesg log for more information on the failure.");
+		handleException();
+	}
+
+	lseek(mBufferFD, 0, SEEK_SET);
+
+	sem_post(mStartProfile);
+
+	pthread_t bootstrapThreadID;
+	if (pthread_create(&bootstrapThreadID, NULL, bootstrapThreadStatic, this) != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to start the gator_bootstrap thread");
+		handleException();
+	}
+
+	// Collect Data
+	do {
+		// This command will stall until data is received from the driver
+		// Calls event_buffer_read in the driver
+		errno = 0;
+		bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+
+		// If read() returned due to an interrupt signal, re-read to obtain the last bit of collected data
+		if (bytesCollected == -1 && errno == EINTR) {
+			bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+		}
+
+		// return the total bytes written
+		logg->logMessage("Driver read of %d bytes", bytesCollected);
+
+		// In one shot mode, stop collection once all the buffers are filled
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+			if (bytesCollected == -1 || mFifo->willFill(bytesCollected)) {
+				logg->logMessage("One shot");
+				child->endSession();
+			}
+		}
+		collectBuffer = mFifo->write(bytesCollected);
+	} while (bytesCollected > 0);
+
+	logg->logMessage("Exit collect data loop");
+
+	pthread_join(bootstrapThreadID, NULL);
+}
+
+void DriverSource::interrupt() {
+	// This command should cause the read() function in collect() to return and stop the driver from profiling
+	if (writeDriver("/dev/gator/enable", "0") != 0) {
+		logg->logMessage("Stopping kernel failed");
+	}
+}
+
+bool DriverSource::isDone() {
+	return mLength <= 0 && (mBuffer == NULL || mBuffer->isDone());
+}
+
+void DriverSource::write(Sender *sender) {
+	char *data = mFifo->read(&mLength);
+	if (data != NULL) {
+		sender->writeData(data, mLength, RESPONSE_APC_DATA);
+		mFifo->release();
+		// Assume the summary packet is in the first block received from the driver
+		gSessionData->mSentSummary = true;
+	}
+	if (mBuffer != NULL && !mBuffer->isDone()) {
+		mBuffer->write(sender);
+		if (mBuffer->isDone()) {
+			Buffer *buf = mBuffer;
+			mBuffer = NULL;
+			delete buf;
+		}
+	}
+}
+
+int DriverSource::readIntDriver(const char *fullpath, int *value) {
+	char data[40]; // Sufficiently large to hold any integer
+	const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+
+	const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+	close(fd);
+	if (bytes < 0) {
+		return -1;
+	}
+	data[bytes] = '\0';
+
+	char *endptr;
+	errno = 0;
+	*value = strtol(data, &endptr, 10);
+	if (errno != 0 || *endptr != '\n') {
+		logg->logMessage("Invalid value in file %s", fullpath);
+		return -1;
+	}
+
+	return 0;
+}
+
+int DriverSource::readInt64Driver(const char *fullpath, int64_t *value) {
+	char data[40]; // Sufficiently large to hold any integer
+	const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+
+	const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+	close(fd);
+	if (bytes < 0) {
+		return -1;
+	}
+	data[bytes] = '\0';
+
+	char *endptr;
+	errno = 0;
+	*value = strtoll(data, &endptr, 10);
+	if (errno != 0 || (*endptr != '\n' && *endptr != '\0')) {
+		logg->logMessage("Invalid value in file %s", fullpath);
+		return -1;
+	}
+
+	return 0;
+}
+
+int DriverSource::writeDriver(const char *fullpath, const char *data) {
+	int fd = open(fullpath, O_WRONLY | O_CLOEXEC);
+	if (fd < 0) {
+		return -1;
+	}
+	if (::write(fd, data, strlen(data)) < 0) {
+		close(fd);
+		logg->logMessage("Opened but could not write to %s", fullpath);
+		return -1;
+	}
+	close(fd);
+	return 0;
+}
+
+int DriverSource::writeDriver(const char *path, int value) {
+	char data[40]; // Sufficiently large to hold any integer
+	snprintf(data, sizeof(data), "%d", value);
+	return writeDriver(path, data);
+}
+
+int DriverSource::writeDriver(const char *path, int64_t value) {
+	char data[40]; // Sufficiently large to hold any integer
+	snprintf(data, sizeof(data), "%" PRIi64, value);
+	return writeDriver(path, data);
+}
+
+int DriverSource::writeReadDriver(const char *path, int *value) {
+	if (writeDriver(path, *value) || readIntDriver(path, value)) {
+		return -1;
+	}
+	return 0;
+}
+
+int DriverSource::writeReadDriver(const char *path, int64_t *value) {
+	if (writeDriver(path, *value) || readInt64Driver(path, value)) {
+		return -1;
+	}
+	return 0;
+}
diff --git a/tools/gator/daemon/DriverSource.h b/tools/gator/daemon/DriverSource.h
new file mode 100644
index 000000000000..ec27b0815bbf
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.h
@@ -0,0 +1,57 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVERSOURCE_H
+#define DRIVERSOURCE_H
+
+#include <semaphore.h>
+#include <stdint.h>
+
+#include "Source.h"
+
+class Buffer;
+class Fifo;
+
+class DriverSource : public Source {
+public:
+	DriverSource(sem_t *senderSem, sem_t *startProfile);
+	~DriverSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+	static int readIntDriver(const char *fullpath, int *value);
+	static int readInt64Driver(const char *fullpath, int64_t *value);
+	static int writeDriver(const char *fullpath, const char *data);
+	static int writeDriver(const char *path, int value);
+	static int writeDriver(const char *path, int64_t value);
+	static int writeReadDriver(const char *path, int *value);
+	static int writeReadDriver(const char *path, int64_t *value);
+
+private:
+	static void *bootstrapThreadStatic(void *arg);
+	void bootstrapThread();
+
+	Buffer *mBuffer;
+	Fifo *mFifo;
+	sem_t *const mSenderSem;
+	sem_t *const mStartProfile;
+	int mBufferSize;
+	int mBufferFD;
+	int mLength;
+
+	// Intentionally unimplemented
+	DriverSource(const DriverSource &);
+	DriverSource &operator=(const DriverSource &);
+};
+
+#endif // DRIVERSOURCE_H
diff --git a/tools/gator/daemon/DynBuf.cpp b/tools/gator/daemon/DynBuf.cpp
new file mode 100644
index 000000000000..df20713ad63c
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.cpp
@@ -0,0 +1,139 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "DynBuf.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+// Pick an aggressive size as buffer is primarily used for disk IO
+#define MIN_BUFFER_FREE (1 << 12)
+
+int DynBuf::resize(const size_t minCapacity) {
+	size_t scaledCapacity = 2 * capacity;
+	if (scaledCapacity < minCapacity) {
+		scaledCapacity = minCapacity;
+	}
+	if (scaledCapacity < 2 * MIN_BUFFER_FREE) {
+		scaledCapacity = 2 * MIN_BUFFER_FREE;
+	}
+	capacity = scaledCapacity;
+
+	buf = static_cast<char *>(realloc(buf, capacity));
+	if (buf == NULL) {
+		return -errno;
+	}
+
+	return 0;
+}
+
+bool DynBuf::read(const char *const path) {
+	int result = false;
+
+	const int fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		logg->logMessage("%s(%s:%i): open failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	length = 0;
+
+	for (;;) {
+		const size_t minCapacity = length + MIN_BUFFER_FREE + 1;
+		if (capacity < minCapacity) {
+			if (resize(minCapacity) != 0) {
+				logg->logMessage("%s(%s:%i): DynBuf::resize failed", __FUNCTION__, __FILE__, __LINE__);
+				goto fail;
+			}
+		}
+
+		const ssize_t bytes = ::read(fd, buf + length, capacity - length - 1);
+		if (bytes < 0) {
+			logg->logMessage("%s(%s:%i): read failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		} else if (bytes == 0) {
+			break;
+		}
+		length += bytes;
+	}
+
+	buf[length] = '\0';
+	result = true;
+
+ fail:
+	close(fd);
+
+	return result;
+}
+
+int DynBuf::readlink(const char *const path) {
+	ssize_t bytes = MIN_BUFFER_FREE;
+
+	for (;;) {
+		if (static_cast<size_t>(bytes) >= capacity) {
+			const int err = resize(2 * bytes);
+			if (err != 0) {
+				return err;
+			}
+		}
+		bytes = ::readlink(path, buf, capacity);
+		if (bytes < 0) {
+			return -errno;
+		} else if (static_cast<size_t>(bytes) < capacity) {
+			break;
+		}
+	}
+
+	length = bytes;
+	buf[bytes] = '\0';
+
+	return 0;
+}
+
+bool DynBuf::printf(const char *format, ...) {
+	va_list ap;
+
+	if (capacity <= 0) {
+		if (resize(2 * MIN_BUFFER_FREE) != 0) {
+			logg->logMessage("%s(%s:%i): DynBuf::resize failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	va_start(ap, format);
+	int bytes = vsnprintf(buf, capacity, format, ap);
+	va_end(ap);
+	if (bytes < 0) {
+		logg->logMessage("%s(%s:%i): fsnprintf failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	if (static_cast<size_t>(bytes) > capacity) {
+		if (resize(bytes + 1) != 0) {
+			logg->logMessage("%s(%s:%i): DynBuf::resize failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+
+		va_start(ap, format);
+		bytes = vsnprintf(buf, capacity, format, ap);
+		va_end(ap);
+		if (bytes < 0) {
+			logg->logMessage("%s(%s:%i): fsnprintf failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	length = bytes;
+
+	return true;
+}
diff --git a/tools/gator/daemon/DynBuf.h b/tools/gator/daemon/DynBuf.h
new file mode 100644
index 000000000000..2f4554ab2e49
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.h
@@ -0,0 +1,52 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DYNBUF_H
+#define DYNBUF_H
+
+#include <stdlib.h>
+
+class DynBuf {
+public:
+	DynBuf() : capacity(0), length(0), buf(NULL) {}
+	~DynBuf() {
+		reset();
+	}
+
+	inline void reset() {
+		capacity = 0;
+		length = 0;
+		if (buf != NULL) {
+			free(buf);
+			buf = NULL;
+		}
+	}
+
+	bool read(const char *const path);
+	// On error instead of printing the error and returning false, this returns -errno
+	int readlink(const char *const path);
+	__attribute__ ((format(printf, 2, 3)))
+	bool printf(const char *format, ...);
+
+	size_t getLength() const { return length; }
+	const char *getBuf() const { return buf; }
+	char *getBuf() { return buf; }
+
+private:
+	int resize(const size_t minCapacity);
+
+	size_t capacity;
+	size_t length;
+	char *buf;
+
+	// Intentionally undefined
+	DynBuf(const DynBuf &);
+	DynBuf &operator=(const DynBuf &);
+};
+
+#endif // DYNBUF_H
diff --git a/tools/gator/daemon/EventsXML.cpp b/tools/gator/daemon/EventsXML.cpp
new file mode 100644
index 000000000000..d905bbabe988
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.cpp
@@ -0,0 +1,76 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "EventsXML.h"
+
+#include "CapturedXML.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+mxml_node_t *EventsXML::getTree() {
+#include "events_xml.h" // defines and initializes char events_xml[] and int events_xml_len
+	char path[PATH_MAX];
+	mxml_node_t *xml;
+	FILE *fl;
+
+	// Avoid unused variable warning
+	(void)events_xml_len;
+
+	// Load the provided or default events xml
+	if (gSessionData->mEventsXMLPath) {
+		strncpy(path, gSessionData->mEventsXMLPath, PATH_MAX);
+	} else {
+		util->getApplicationFullPath(path, PATH_MAX);
+		strncat(path, "events.xml", PATH_MAX - strlen(path) - 1);
+	}
+	fl = fopen(path, "r");
+	if (fl) {
+		xml = mxmlLoadFile(NULL, fl, MXML_NO_CALLBACK);
+		fclose(fl);
+	} else {
+		logg->logMessage("Unable to locate events.xml, using default");
+		xml = mxmlLoadString(NULL, (const char *)events_xml, MXML_NO_CALLBACK);
+	}
+
+	return xml;
+}
+
+char *EventsXML::getXML() {
+	mxml_node_t *xml = getTree();
+
+	// Add dynamic events from the drivers
+	mxml_node_t *events = mxmlFindElement(xml, xml, "events", NULL, NULL, MXML_DESCEND);
+	if (!events) {
+		logg->logError(__FILE__, __LINE__, "Unable to find <events> node in the events.xml");
+		handleException();
+	}
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		driver->writeEvents(events);
+	}
+
+	char *string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	mxmlDelete(xml);
+
+	return string;
+}
+
+void EventsXML::write(const char *path) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/events.xml", path);
+
+	char *buf = getXML();
+	if (util->writeToDisk(file, buf) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	free(buf);
+}
diff --git a/tools/gator/daemon/EventsXML.h b/tools/gator/daemon/EventsXML.h
new file mode 100644
index 000000000000..ff7a02fd3c78
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.h
@@ -0,0 +1,21 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EVENTS_XML
+#define EVENTS_XML
+
+#include "mxml/mxml.h"
+
+class EventsXML {
+public:
+	mxml_node_t *getTree();
+	char *getXML();
+	void write(const char* path);
+};
+
+#endif // EVENTS_XML
diff --git a/tools/gator/daemon/ExternalSource.cpp b/tools/gator/daemon/ExternalSource.cpp
new file mode 100644
index 000000000000..8f5e6b684c53
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.cpp
@@ -0,0 +1,260 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ExternalSource.h"
+
+#include <fcntl.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+static const char MALI_VIDEO[] = "\0mali-video";
+static const char MALI_VIDEO_STARTUP[] = "\0mali-video-startup";
+static const char MALI_VIDEO_V1[] = "MALI_VIDEO 1\n";
+static const char MALI_GRAPHICS[] = "\0mali_thirdparty_server";
+static const char MALI_GRAPHICS_STARTUP[] = "\0mali_thirdparty_client";
+static const char MALI_GRAPHICS_V1[] = "MALI_GRAPHICS 1\n";
+
+static bool setNonblock(const int fd) {
+	int flags;
+
+	flags = fcntl(fd, F_GETFL);
+	if (flags < 0) {
+		logg->logMessage("fcntl getfl failed");
+		return false;
+	}
+
+	if (fcntl(fd, F_SETFL, flags | O_NONBLOCK) != 0) {
+		logg->logMessage("fcntl setfl failed");
+		return false;
+	}
+
+	return true;
+}
+
+ExternalSource::ExternalSource(sem_t *senderSem) : mBuffer(0, FRAME_EXTERNAL, 128*1024, senderSem), mMonitor(), mMveStartupUds(MALI_VIDEO_STARTUP, sizeof(MALI_VIDEO_STARTUP)), mMaliStartupUds(MALI_GRAPHICS_STARTUP, sizeof(MALI_GRAPHICS_STARTUP)), mAnnotate(8083), mInterruptFd(-1), mMaliUds(-1), mMveUds(-1) {
+	sem_init(&mBufferSem, 0, 0);
+}
+
+ExternalSource::~ExternalSource() {
+}
+
+void ExternalSource::waitFor(const int bytes) {
+	while (mBuffer.bytesAvailable() <= bytes) {
+		sem_wait(&mBufferSem);
+	}
+}
+
+void ExternalSource::configureConnection(const int fd, const char *const handshake, size_t size) {
+	if (!setNonblock(fd)) {
+		logg->logError(__FILE__, __LINE__, "Unable to set nonblock on fh");
+		handleException();
+	}
+
+	if (!mMonitor.add(fd)) {
+		logg->logError(__FILE__, __LINE__, "Unable to add fh to monitor");
+		handleException();
+	}
+
+	// Write the handshake to the circular buffer
+	waitFor(Buffer::MAXSIZE_PACK32 + size - 1);
+	mBuffer.packInt(fd);
+	mBuffer.writeBytes(handshake, size - 1);
+	mBuffer.commit(1);
+}
+
+bool ExternalSource::connectMali() {
+	mMaliUds = OlySocket::connect(MALI_GRAPHICS, sizeof(MALI_GRAPHICS));
+	if (mMaliUds < 0) {
+		return false;
+	}
+
+	configureConnection(mMaliUds, MALI_GRAPHICS_V1, sizeof(MALI_GRAPHICS_V1));
+
+	return true;
+}
+
+bool ExternalSource::connectMve() {
+	if (!gSessionData->maliVideo.countersEnabled()) {
+		return true;
+	}
+
+	mMveUds = OlySocket::connect(MALI_VIDEO, sizeof(MALI_VIDEO));
+	if (mMveUds < 0) {
+		return false;
+	}
+
+	if (!gSessionData->maliVideo.start(mMveUds)) {
+		return false;
+	}
+
+	configureConnection(mMveUds, MALI_VIDEO_V1, sizeof(MALI_VIDEO_V1));
+
+	return true;
+}
+
+bool ExternalSource::prepare() {
+	if (!mMonitor.init() ||
+			!setNonblock(mMveStartupUds.getFd()) || !mMonitor.add(mMveStartupUds.getFd()) ||
+			!setNonblock(mMaliStartupUds.getFd()) || !mMonitor.add(mMaliStartupUds.getFd()) ||
+			!setNonblock(mAnnotate.getFd()) || !mMonitor.add(mAnnotate.getFd()) ||
+			false) {
+		return false;
+	}
+
+	connectMali();
+	connectMve();
+
+	return true;
+}
+
+void ExternalSource::run() {
+	int pipefd[2];
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-external", 0, 0, 0);
+
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError(__FILE__, __LINE__, "pipe failed");
+		handleException();
+	}
+	mInterruptFd = pipefd[1];
+
+	if (!mMonitor.add(pipefd[0])) {
+		logg->logError(__FILE__, __LINE__, "Monitor::add failed");
+		handleException();
+	}
+
+	// Notify annotate clients to retry connecting to gatord
+	gSessionData->annotateListener.signal();
+
+	while (gSessionData->mSessionIsActive) {
+		struct epoll_event events[16];
+		// Clear any pending sem posts
+		while (sem_trywait(&mBufferSem) == 0);
+		int ready = mMonitor.wait(events, ARRAY_LENGTH(events), -1);
+		if (ready < 0) {
+			logg->logError(__FILE__, __LINE__, "Monitor::wait failed");
+			handleException();
+		}
+
+		const uint64_t currTime = getTime();
+
+		for (int i = 0; i < ready; ++i) {
+			const int fd = events[i].data.fd;
+			if (fd == mMveStartupUds.getFd()) {
+				// Mali Video Engine says it's alive
+				int client = mMveStartupUds.acceptConnection();
+				// Don't read from this connection, establish a new connection to Mali-V500
+				close(client);
+				if (!connectMve()) {
+					logg->logError(__FILE__, __LINE__, "Unable to configure incoming Mali video connection");
+					handleException();
+				}
+			} else if (fd == mMaliStartupUds.getFd()) {
+				// Mali Graphics says it's alive
+				int client = mMaliStartupUds.acceptConnection();
+				// Don't read from this connection, establish a new connection to Mali Graphics
+				close(client);
+				if (!connectMali()) {
+					logg->logError(__FILE__, __LINE__, "Unable to configure incoming Mali graphics connection");
+					handleException();
+				}
+			} else if (fd == mAnnotate.getFd()) {
+				int client = mAnnotate.acceptConnection();
+				if (!setNonblock(client) || !mMonitor.add(client)) {
+					logg->logError(__FILE__, __LINE__, "Unable to set socket options on incoming annotation connection");
+					handleException();
+				}
+			} else if (fd == pipefd[0]) {
+				// Means interrupt has been called and mSessionIsActive should be reread
+			} else {
+				/* This can result in some starvation if there are multiple
+				 * threads which are annotating heavily, but it is not
+				 * recommended that threads annotate that much as it can also
+				 * starve out the gator data.
+				 */
+				while (gSessionData->mSessionIsActive) {
+					// Wait until there is enough room for the fd, two headers and two ints
+					waitFor(7*Buffer::MAXSIZE_PACK32 + 2*sizeof(uint32_t));
+					mBuffer.packInt(fd);
+					const int contiguous = mBuffer.contiguousSpaceAvailable();
+					const int bytes = read(fd, mBuffer.getWritePos(), contiguous);
+					if (bytes < 0) {
+						if (errno == EAGAIN) {
+							// Nothing left to read
+							mBuffer.commit(currTime);
+							break;
+						}
+						// Something else failed, close the socket
+						mBuffer.commit(currTime);
+						mBuffer.packInt(-1);
+						mBuffer.packInt(fd);
+						mBuffer.commit(currTime);
+						close(fd);
+						break;
+					} else if (bytes == 0) {
+						// The other side is closed
+						mBuffer.commit(currTime);
+						mBuffer.packInt(-1);
+						mBuffer.packInt(fd);
+						mBuffer.commit(currTime);
+						close(fd);
+						break;
+					}
+
+					mBuffer.advanceWrite(bytes);
+					mBuffer.commit(currTime);
+
+					// Short reads also mean nothing is left to read
+					if (bytes < contiguous) {
+						break;
+					}
+				}
+			}
+		}
+	}
+
+	mBuffer.setDone();
+
+	if (mMveUds >= 0) {
+		gSessionData->maliVideo.stop(mMveUds);
+	}
+
+	mInterruptFd = -1;
+	close(pipefd[0]);
+	close(pipefd[1]);
+}
+
+void ExternalSource::interrupt() {
+	if (mInterruptFd >= 0) {
+		int8_t c = 0;
+		// Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+		if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+			logg->logError(__FILE__, __LINE__, "write failed");
+			handleException();
+		}
+	}
+}
+
+bool ExternalSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void ExternalSource::write(Sender *sender) {
+	// Don't send external data until the summary packet is sent so that monotonic delta is available
+	if (!gSessionData->mSentSummary) {
+		return;
+	}
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+		sem_post(&mBufferSem);
+	}
+}
diff --git a/tools/gator/daemon/ExternalSource.h b/tools/gator/daemon/ExternalSource.h
new file mode 100644
index 000000000000..919e75e8a41a
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.h
@@ -0,0 +1,53 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EXTERNALSOURCE_H
+#define EXTERNALSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "Source.h"
+
+// Counters from external sources like graphics drivers and annotations
+class ExternalSource : public Source {
+public:
+	ExternalSource(sem_t *senderSem);
+	~ExternalSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	void waitFor(const int bytes);
+	void configureConnection(const int fd, const char *const handshake, size_t size);
+	bool connectMali();
+	bool connectMve();
+
+	sem_t mBufferSem;
+	Buffer mBuffer;
+	Monitor mMonitor;
+	OlyServerSocket mMveStartupUds;
+	OlyServerSocket mMaliStartupUds;
+	OlyServerSocket mAnnotate;
+	int mInterruptFd;
+	int mMaliUds;
+	int mMveUds;
+
+	// Intentionally unimplemented
+	ExternalSource(const ExternalSource &);
+	ExternalSource &operator=(const ExternalSource &);
+};
+
+#endif // EXTERNALSOURCE_H
diff --git a/tools/gator/daemon/FSDriver.cpp b/tools/gator/daemon/FSDriver.cpp
new file mode 100644
index 000000000000..dd8eb804dc99
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.cpp
@@ -0,0 +1,158 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FSDriver.h"
+
+#include <fcntl.h>
+#include <regex.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "DriverSource.h"
+#include "Logging.h"
+
+class FSCounter : public DriverCounter {
+public:
+	FSCounter(DriverCounter *next, char *name, char *path, const char *regex);
+	~FSCounter();
+
+	const char *getPath() const { return mPath; }
+
+	int64_t read();
+
+private:
+	char *const mPath;
+	regex_t mReg;
+	bool mUseRegex;
+
+	// Intentionally unimplemented
+	FSCounter(const FSCounter &);
+	FSCounter &operator=(const FSCounter &);
+};
+
+FSCounter::FSCounter(DriverCounter *next, char *name, char *path, const char *regex) : DriverCounter(next, name), mPath(path), mUseRegex(regex != NULL) {
+	if (mUseRegex) {
+		int result = regcomp(&mReg, regex, REG_EXTENDED);
+		if (result != 0) {
+			char buf[128];
+			regerror(result, &mReg, buf, sizeof(buf));
+			logg->logError(__FILE__, __LINE__, "Invalid regex '%s': %s", regex, buf);
+			handleException();
+		}
+	}
+}
+
+FSCounter::~FSCounter() {
+	free(mPath);
+	if (mUseRegex) {
+		regfree(&mReg);
+	}
+}
+
+int64_t FSCounter::read() {
+	int64_t value;
+	if (mUseRegex) {
+		char buf[4096];
+		size_t pos = 0;
+		const int fd = open(mPath, O_RDONLY | O_CLOEXEC);
+		if (fd < 0) {
+			goto fail;
+		}
+		while (pos < sizeof(buf) - 1) {
+			const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+			if (bytes < 0) {
+				goto fail;
+			} else if (bytes == 0) {
+				break;
+			}
+			pos += bytes;
+		}
+		close(fd);
+		buf[pos] = '\0';
+
+		regmatch_t match[2];
+		int result = regexec(&mReg, buf, 2, match, 0);
+		if (result != 0) {
+			regerror(result, &mReg, buf, sizeof(buf));
+			logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", mPath, buf);
+			handleException();
+		}
+
+		if (match[1].rm_so < 0) {
+			logg->logError(__FILE__, __LINE__, "Parsing %s failed", mPath);
+			handleException();
+		}
+
+		errno = 0;
+		value = strtoll(buf + match[1].rm_so, NULL, 0);
+		if (errno != 0) {
+			logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", mPath, strerror(errno));
+			handleException();
+		}
+	} else {
+		if (DriverSource::readInt64Driver(mPath, &value) != 0) {
+			goto fail;
+		}
+	}
+	return value;
+
+ fail:
+	logg->logError(__FILE__, __LINE__, "Unable to read %s", mPath);
+	handleException();
+}
+
+FSDriver::FSDriver() {
+}
+
+FSDriver::~FSDriver() {
+}
+
+void FSDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (counter[0] == '/') {
+			logg->logError(__FILE__, __LINE__, "Old style filesystem counter (%s) detected, please create a new unique counter value and move the filename into the path attribute, see events-Filesystem.xml for examples", counter);
+			handleException();
+		}
+
+		if (strncmp(counter, "filesystem_", 11) != 0) {
+			continue;
+		}
+
+		const char *path = mxmlElementGetAttr(node, "path");
+		if (path == NULL) {
+			logg->logError(__FILE__, __LINE__, "The filesystem counter %s is missing the required path attribute", counter);
+			handleException();
+		}
+		const char *regex = mxmlElementGetAttr(node, "regex");
+		setCounters(new FSCounter(getCounters(), strdup(counter), strdup(path), regex));
+	}
+}
+
+int FSDriver::writeCounters(mxml_node_t *root) const {
+	int count = 0;
+	for (FSCounter *counter = static_cast<FSCounter *>(getCounters()); counter != NULL; counter = static_cast<FSCounter *>(counter->getNext())) {
+		if (access(counter->getPath(), R_OK) == 0) {
+			mxml_node_t *node = mxmlNewElement(root, "counter");
+			mxmlElementSetAttr(node, "name", counter->getName());
+			++count;
+		}
+	}
+
+	return count;
+}
diff --git a/tools/gator/daemon/FSDriver.h b/tools/gator/daemon/FSDriver.h
new file mode 100644
index 000000000000..a7dc8b4df9dd
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.h
@@ -0,0 +1,29 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FSDRIVER_H
+#define FSDRIVER_H
+
+#include "Driver.h"
+
+class FSDriver : public PolledDriver {
+public:
+	FSDriver();
+	~FSDriver();
+
+	void readEvents(mxml_node_t *const xml);
+
+	int writeCounters(mxml_node_t *root) const;
+
+private:
+	// Intentionally unimplemented
+	FSDriver(const FSDriver &);
+	FSDriver &operator=(const FSDriver &);
+};
+
+#endif // FSDRIVER_H
diff --git a/tools/gator/daemon/Fifo.cpp b/tools/gator/daemon/Fifo.cpp
new file mode 100644
index 000000000000..41275fd287b8
--- /dev/null
+++ b/tools/gator/daemon/Fifo.cpp
@@ -0,0 +1,127 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Fifo.h"
+
+#include <stdlib.h>
+
+#include "Logging.h"
+
+// bufferSize is the amount of data to be filled
+// singleBufferSize is the maximum size that may be filled during a single write
+// (bufferSize + singleBufferSize) will be allocated
+Fifo::Fifo(int singleBufferSize, int bufferSize, sem_t* readerSem) {
+  mWrite = mRead = mReadCommit = mRaggedEnd = 0;
+  mWrapThreshold = bufferSize;
+  mSingleBufferSize = singleBufferSize;
+  mReaderSem = readerSem;
+  mBuffer = (char*)malloc(bufferSize + singleBufferSize);
+  mEnd = false;
+
+  if (mBuffer == NULL) {
+    logg->logError(__FILE__, __LINE__, "failed to allocate %d bytes", bufferSize + singleBufferSize);
+    handleException();
+  }
+
+  if (sem_init(&mWaitForSpaceSem, 0, 0)) {
+    logg->logError(__FILE__, __LINE__, "sem_init() failed");
+    handleException();
+  }
+}
+
+Fifo::~Fifo() {
+  free(mBuffer);
+  sem_destroy(&mWaitForSpaceSem);
+}
+
+int Fifo::numBytesFilled() const {
+  return mWrite - mRead + mRaggedEnd;
+}
+
+char* Fifo::start() const {
+  return mBuffer;
+}
+
+bool Fifo::isEmpty() const {
+  return mRead == mWrite && mRaggedEnd == 0;
+}
+
+bool Fifo::isFull() const {
+  return willFill(0);
+}
+
+// Determines if the buffer will fill assuming 'additional' bytes will be added to the buffer
+// 'full' means there is less than singleBufferSize bytes available contiguously; it does not mean there are zero bytes available
+bool Fifo::willFill(int additional) const {
+  if (mWrite > mRead) {
+    if (numBytesFilled() + additional < mWrapThreshold) {
+      return false;
+    }
+  } else {
+    if (numBytesFilled() + additional < mWrapThreshold - mSingleBufferSize) {
+      return false;
+    }
+  }
+  return true;
+}
+
+// This function will stall until contiguous singleBufferSize bytes are available
+char* Fifo::write(int length) {
+  if (length <= 0) {
+    length = 0;
+    mEnd = true;
+  }
+
+  // update the write pointer
+  mWrite += length;
+
+  // handle the wrap-around
+  if (mWrite >= mWrapThreshold) {
+    mRaggedEnd = mWrite;
+    mWrite = 0;
+  }
+
+  // send a notification that data is ready
+  sem_post(mReaderSem);
+
+  // wait for space
+  while (isFull()) {
+    sem_wait(&mWaitForSpaceSem);
+  }
+
+  return &mBuffer[mWrite];
+}
+
+void Fifo::release() {
+  // update the read pointer now that the data has been handled
+  mRead = mReadCommit;
+
+  // handle the wrap-around
+  if (mRead >= mWrapThreshold) {
+    mRaggedEnd = mRead = mReadCommit = 0;
+  }
+
+  // send a notification that data is free (space is available)
+  sem_post(&mWaitForSpaceSem);
+}
+
+// This function will return null if no data is available
+char* Fifo::read(int *const length) {
+  // wait for data
+  if (isEmpty() && !mEnd) {
+    return NULL;
+  }
+
+  // obtain the length
+  do {
+    mReadCommit = mRaggedEnd ? mRaggedEnd : mWrite;
+    *length = mReadCommit - mRead;
+  } while (*length < 0); // plugs race condition without using semaphores
+
+  return &mBuffer[mRead];
+}
diff --git a/tools/gator/daemon/Fifo.h b/tools/gator/daemon/Fifo.h
new file mode 100644
index 000000000000..21c8d8580391
--- /dev/null
+++ b/tools/gator/daemon/Fifo.h
@@ -0,0 +1,48 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __FIFO_H__
+#define __FIFO_H__
+
+#ifdef WIN32
+#include <windows.h>
+#define sem_t HANDLE
+#define sem_init(sem, pshared, value) ((*(sem) = CreateSemaphore(NULL, value, LONG_MAX, NULL)) == NULL)
+#define sem_wait(sem) WaitForSingleObject(*(sem), INFINITE)
+#define sem_post(sem) ReleaseSemaphore(*(sem), 1, NULL)
+#define sem_destroy(sem) CloseHandle(*(sem))
+#else
+#include <semaphore.h>
+#endif
+
+class Fifo {
+public:
+  Fifo(int singleBufferSize, int totalBufferSize, sem_t* readerSem);
+  ~Fifo();
+  int numBytesFilled() const;
+  bool isEmpty() const;
+  bool isFull() const;
+  bool willFill(int additional) const;
+  char* start() const;
+  char* write(int length);
+  void release();
+  char* read(int *const length);
+
+private:
+  int mSingleBufferSize, mWrite, mRead, mReadCommit, mRaggedEnd, mWrapThreshold;
+  sem_t mWaitForSpaceSem;
+  sem_t* mReaderSem;
+  char* mBuffer;
+  bool mEnd;
+
+  // Intentionally unimplemented
+  Fifo(const Fifo &);
+  Fifo &operator=(const Fifo &);
+};
+
+#endif //__FIFO_H__
diff --git a/tools/gator/daemon/FtraceDriver.cpp b/tools/gator/daemon/FtraceDriver.cpp
new file mode 100644
index 000000000000..b156f1c0b8b4
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.cpp
@@ -0,0 +1,118 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FtraceDriver.h"
+
+#include <regex.h>
+
+#include "Logging.h"
+
+class FtraceCounter : public DriverCounter {
+public:
+	FtraceCounter(DriverCounter *next, char *name, const char *regex);
+	~FtraceCounter();
+
+	int read(const char *const line, int64_t *values);
+
+private:
+	regex_t reg;
+
+	// Intentionally unimplemented
+	FtraceCounter(const FtraceCounter &);
+	FtraceCounter &operator=(const FtraceCounter &);
+};
+
+FtraceCounter::FtraceCounter(DriverCounter *next, char *name, const char *regex) : DriverCounter(next, name) {
+	int result = regcomp(&reg, regex, REG_EXTENDED);
+	if (result != 0) {
+		char buf[128];
+		regerror(result, &reg, buf, sizeof(buf));
+		logg->logError(__FILE__, __LINE__, "Invalid regex '%s': %s", regex, buf);
+		handleException();
+	}
+}
+
+FtraceCounter::~FtraceCounter() {
+	regfree(&reg);
+}
+
+int FtraceCounter::read(const char *const line, int64_t *values) {
+	regmatch_t match[2];
+	int result = regexec(&reg, line, 2, match, 0);
+	if (result != 0) {
+		// No match
+		return 0;
+	}
+
+	if (match[1].rm_so < 0) {
+		logg->logError(__FILE__, __LINE__, "Parsing %s failed", getName());
+		handleException();
+	}
+
+	errno = 0;
+	int64_t value = strtoll(line + match[1].rm_so, NULL, 0);
+	if (errno != 0) {
+		logg->logError(__FILE__, __LINE__, "Parsing %s failed: %s", getName(), strerror(errno));
+		handleException();
+	}
+
+	values[0] = getKey();
+	values[1] = value;
+
+	return 1;
+}
+
+FtraceDriver::FtraceDriver() : mValues(NULL) {
+}
+
+FtraceDriver::~FtraceDriver() {
+	delete [] mValues;
+}
+
+void FtraceDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	int count = 0;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			continue;
+		}
+
+		if (strncmp(counter, "ftrace_", 7) != 0) {
+			continue;
+		}
+
+		const char *regex = mxmlElementGetAttr(node, "regex");
+		if (regex == NULL) {
+			logg->logError(__FILE__, __LINE__, "The regex counter %s is missing the required regex attribute", counter);
+			handleException();
+		}
+		setCounters(new FtraceCounter(getCounters(), strdup(counter), regex));
+		++count;
+	}
+
+	mValues = new int64_t[2*count];
+}
+
+int FtraceDriver::read(const char *line, int64_t **buf) {
+	int count = 0;
+
+	for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		count += counter->read(line, mValues + 2*count);
+	}
+
+	*buf = mValues;
+	return count;
+}
diff --git a/tools/gator/daemon/FtraceDriver.h b/tools/gator/daemon/FtraceDriver.h
new file mode 100644
index 000000000000..5f958bec672c
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FTRACEDRIVER_H
+#define FTRACEDRIVER_H
+
+#include "Driver.h"
+
+class FtraceDriver : public SimpleDriver {
+public:
+	FtraceDriver();
+	~FtraceDriver();
+
+	void readEvents(mxml_node_t *const xml);
+
+	int read(const char *line, int64_t **buf);
+
+private:
+	int64_t *mValues;
+
+	// Intentionally unimplemented
+	FtraceDriver(const FtraceDriver &);
+	FtraceDriver &operator=(const FtraceDriver &);
+};
+
+#endif // FTRACEDRIVER_H
diff --git a/tools/gator/daemon/FtraceSource.cpp b/tools/gator/daemon/FtraceSource.cpp
new file mode 100644
index 000000000000..521633357417
--- /dev/null
+++ b/tools/gator/daemon/FtraceSource.cpp
@@ -0,0 +1,158 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FtraceSource.h"
+
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+static void handler(int signum)
+{
+	(void)signum;
+};
+
+FtraceSource::FtraceSource(sem_t *senderSem) : mFtraceFh(NULL), mBuffer(0, FRAME_BLOCK_COUNTER, 128*1024, senderSem), mTid(-1), mTracingOn(0) {
+}
+
+FtraceSource::~FtraceSource() {
+}
+
+bool FtraceSource::prepare() {
+	{
+		struct sigaction act;
+		act.sa_handler = handler;
+		act.sa_flags = (int)SA_RESETHAND;
+		if (sigaction(SIGUSR1, &act, NULL) != 0) {
+			logg->logError(__FILE__, __LINE__, "sigaction failed: %s\n", strerror(errno));
+			handleException();
+		}
+	}
+
+	if (DriverSource::readIntDriver("/sys/kernel/debug/tracing/tracing_on", &mTracingOn)) {
+		logg->logError(__FILE__, __LINE__, "Unable to read if ftrace is enabled");
+		handleException();
+	}
+
+	if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "0") != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to turn ftrace off before truncating the buffer");
+		handleException();
+	}
+
+	{
+		int fd;
+		fd = open("/sys/kernel/debug/tracing/trace", O_WRONLY | O_TRUNC | O_CLOEXEC, 0666);
+		if (fd < 0) {
+			logg->logError(__FILE__, __LINE__, "Unable truncate ftrace buffer: %s", strerror(errno));
+			handleException();
+		}
+		close(fd);
+	}
+
+	if (DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "perf") != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to switch ftrace to the perf clock, please ensure you are running Linux 3.10 or later");
+		handleException();
+	}
+
+	mFtraceFh = fopen_cloexec("/sys/kernel/debug/tracing/trace_pipe", "rb");
+	if (mFtraceFh == NULL) {
+		logg->logError(__FILE__, __LINE__, "Unable to open trace_pipe");
+		handleException();
+	}
+
+	return true;
+}
+
+void FtraceSource::run() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-ftrace", 0, 0, 0);
+	mTid = syscall(__NR_gettid);
+
+	if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "1") != 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to turn ftrace on");
+		handleException();
+	}
+
+	while (gSessionData->mSessionIsActive) {
+		char buf[1<<12];
+
+		if (fgets(buf, sizeof(buf), mFtraceFh) == NULL) {
+			if (errno == EINTR) {
+				// Interrupted by interrupt - likely user request to terminate
+				break;
+			}
+			logg->logError(__FILE__, __LINE__, "Unable read trace data: %s", strerror(errno));
+			handleException();
+		}
+
+		const uint64_t currTime = getTime();
+
+		char *const colon = strstr(buf, ": ");
+		if (colon == NULL) {
+			logg->logError(__FILE__, __LINE__, "Unable find colon: %s", buf);
+			handleException();
+		}
+		*colon = '\0';
+
+		char *const space = strrchr(buf, ' ');
+		if (space == NULL) {
+			logg->logError(__FILE__, __LINE__, "Unable find space: %s", buf);
+			handleException();
+		}
+		*colon = ':';
+
+		int64_t *data = NULL;
+		int count = gSessionData->ftraceDriver.read(colon + 2, &data);
+		if (count > 0) {
+			errno = 0;
+			const long long time = strtod(space, NULL) * 1000000000;
+			if (errno != 0) {
+				logg->logError(__FILE__, __LINE__, "Unable to parse time: %s", strerror(errno));
+				handleException();
+			}
+			mBuffer.event64(-1, time);
+
+			for (int i = 0; i < count; ++i) {
+				mBuffer.event64(data[2*i + 0], data[2*i + 1]);
+			}
+
+			mBuffer.check(currTime);
+		}
+
+	}
+
+	mBuffer.setDone();
+
+	DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", mTracingOn);
+	fclose(mFtraceFh);
+	DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "local");
+}
+
+void FtraceSource::interrupt() {
+	// Closing the underlying file handle does not result in the read on the ftrace file handle to return, so send a signal to the thread
+	syscall(__NR_tgkill, getpid(), mTid, SIGUSR1);
+}
+
+bool FtraceSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void FtraceSource::write(Sender *sender) {
+	// Don't send ftrace data until the summary packet is sent so that monotonic delta is available
+	if (!gSessionData->mSentSummary) {
+		return;
+	}
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+	}
+}
diff --git a/tools/gator/daemon/FtraceSource.h b/tools/gator/daemon/FtraceSource.h
new file mode 100644
index 000000000000..2391b881494e
--- /dev/null
+++ b/tools/gator/daemon/FtraceSource.h
@@ -0,0 +1,43 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FTRACESOURCE_H
+#define FTRACESOURCE_H
+
+#include <semaphore.h>
+#include <stdio.h>
+
+#include "Buffer.h"
+#include "Source.h"
+
+class FtraceSource : public Source {
+public:
+	FtraceSource(sem_t *senderSem);
+	~FtraceSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	void waitFor(const int bytes);
+
+	FILE *mFtraceFh;
+	Buffer mBuffer;
+	int mTid;
+	int mTracingOn;
+
+	// Intentionally unimplemented
+	FtraceSource(const FtraceSource &);
+	FtraceSource &operator=(const FtraceSource &);
+};
+
+#endif // FTRACESOURCE_H
diff --git a/tools/gator/daemon/HwmonDriver.cpp b/tools/gator/daemon/HwmonDriver.cpp
new file mode 100644
index 000000000000..9d161ae5ac56
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.cpp
@@ -0,0 +1,245 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "HwmonDriver.h"
+
+#include "libsensors/sensors.h"
+
+#include "Logging.h"
+
+// feature->type to input map
+static sensors_subfeature_type getInput(const sensors_feature_type type) {
+	switch (type) {
+	case SENSORS_FEATURE_IN: return SENSORS_SUBFEATURE_IN_INPUT;
+	case SENSORS_FEATURE_FAN: return SENSORS_SUBFEATURE_FAN_INPUT;
+	case SENSORS_FEATURE_TEMP: return SENSORS_SUBFEATURE_TEMP_INPUT;
+	case SENSORS_FEATURE_POWER: return SENSORS_SUBFEATURE_POWER_INPUT;
+	case SENSORS_FEATURE_ENERGY: return SENSORS_SUBFEATURE_ENERGY_INPUT;
+	case SENSORS_FEATURE_CURR: return SENSORS_SUBFEATURE_CURR_INPUT;
+	case SENSORS_FEATURE_HUMIDITY: return SENSORS_SUBFEATURE_HUMIDITY_INPUT;
+	default:
+		logg->logError(__FILE__, __LINE__, "Unsupported hwmon feature %i", type);
+		handleException();
+	}
+};
+
+class HwmonCounter : public DriverCounter {
+public:
+	HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature);
+	~HwmonCounter();
+
+	const char *getLabel() const { return label; }
+	const char *getTitle() const { return title; }
+	bool isDuplicate() const { return duplicate; }
+	const char *getDisplay() const { return display; }
+	const char *getCounterClass() const { return counter_class; }
+	const char *getUnit() const { return unit; }
+	int getModifier() const { return modifier; }
+
+	int64_t read();
+
+private:
+	void init(const sensors_chip_name *chip, const sensors_feature *feature);
+
+	const sensors_chip_name *chip;
+	const sensors_feature *feature;
+	char *label;
+	const char *title;
+	const char *display;
+	const char *counter_class;
+	const char *unit;
+	double previous_value;
+	int modifier;
+	int monotonic: 1,
+		duplicate : 1;
+
+	// Intentionally unimplemented
+	HwmonCounter(const HwmonCounter &);
+	HwmonCounter &operator=(const HwmonCounter &);
+};
+
+HwmonCounter::HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature) : DriverCounter(next, name), chip(chip), feature(feature), duplicate(false) {
+	label = sensors_get_label(chip, feature);
+
+	switch (feature->type) {
+	case SENSORS_FEATURE_IN:
+		title = "Voltage";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "V";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_FAN:
+		title = "Fan";
+		display = "average";
+		counter_class = "absolute";
+		unit = "RPM";
+		modifier = 1;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_TEMP:
+		title = "Temperature";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "°C";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_POWER:
+		title = "Power";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "W";
+		modifier = 1000000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_ENERGY:
+		title = "Energy";
+		display = "accumulate";
+		counter_class = "delta";
+		unit = "J";
+		modifier = 1000000;
+		monotonic = true;
+		break;
+	case SENSORS_FEATURE_CURR:
+		title = "Current";
+		display = "maximum";
+		counter_class = "absolute";
+		unit = "A";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	case SENSORS_FEATURE_HUMIDITY:
+		title = "Humidity";
+		display = "average";
+		counter_class = "absolute";
+		unit = "%";
+		modifier = 1000;
+		monotonic = false;
+		break;
+	default:
+		logg->logError(__FILE__, __LINE__, "Unsupported hwmon feature %i", feature->type);
+		handleException();
+	}
+
+	for (HwmonCounter * counter = static_cast<HwmonCounter *>(next); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+		if (strcmp(label, counter->getLabel()) == 0 && strcmp(title, counter->getTitle()) == 0) {
+			duplicate = true;
+			counter->duplicate = true;
+			break;
+		}
+	}
+}
+
+HwmonCounter::~HwmonCounter() {
+	free((void *)label);
+}
+
+int64_t HwmonCounter::read() {
+	double value;
+	double result;
+	const sensors_subfeature *subfeature;
+
+	// Keep in sync with the read check in HwmonDriver::readEvents
+	subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type));
+	if (!subfeature) {
+		logg->logError(__FILE__, __LINE__, "No input value for hwmon sensor %s", label);
+		handleException();
+	}
+
+	if (sensors_get_value(chip, subfeature->number, &value) != 0) {
+		logg->logError(__FILE__, __LINE__, "Can't get input value for hwmon sensor %s", label);
+		handleException();
+	}
+
+	result = (monotonic ? value - previous_value : value);
+	previous_value = value;
+
+	return result;
+}
+
+HwmonDriver::HwmonDriver() {
+}
+
+HwmonDriver::~HwmonDriver() {
+	sensors_cleanup();
+}
+
+void HwmonDriver::readEvents(mxml_node_t *const) {
+	int err = sensors_init(NULL);
+	if (err) {
+		logg->logMessage("Failed to initialize libsensors! (%d)", err);
+		return;
+	}
+	sensors_sysfs_no_scaling = 1;
+
+	int chip_nr = 0;
+	const sensors_chip_name *chip;
+	while ((chip = sensors_get_detected_chips(NULL, &chip_nr))) {
+		int feature_nr = 0;
+		const sensors_feature *feature;
+		while ((feature = sensors_get_features(chip, &feature_nr))) {
+			// Keep in sync with HwmonCounter::read
+			// Can this counter be read?
+			double value;
+			const sensors_subfeature *const subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type));
+			if ((subfeature == NULL) || (sensors_get_value(chip, subfeature->number, &value) != 0)) {
+				continue;
+			}
+
+			// Get the name of the counter
+			int len = sensors_snprintf_chip_name(NULL, 0, chip) + 1;
+			char *chip_name = new char[len];
+			sensors_snprintf_chip_name(chip_name, len, chip);
+			len = snprintf(NULL, 0, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number) + 1;
+			char *const name = new char[len];
+			snprintf(name, len, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number);
+			delete [] chip_name;
+
+			setCounters(new HwmonCounter(getCounters(), name, chip, feature));
+		}
+	}
+}
+
+void HwmonDriver::writeEvents(mxml_node_t *root) const {
+	root = mxmlNewElement(root, "category");
+	mxmlElementSetAttr(root, "name", "hwmon");
+
+	char buf[1024];
+	for (HwmonCounter *counter = static_cast<HwmonCounter *>(getCounters()); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+		mxml_node_t *node = mxmlNewElement(root, "event");
+		mxmlElementSetAttr(node, "counter", counter->getName());
+		mxmlElementSetAttr(node, "title", counter->getTitle());
+		if (counter->isDuplicate()) {
+			mxmlElementSetAttrf(node, "name", "%s (0x%x)", counter->getLabel(), counter->getKey());
+		} else {
+			mxmlElementSetAttr(node, "name", counter->getLabel());
+		}
+		mxmlElementSetAttr(node, "display", counter->getDisplay());
+		mxmlElementSetAttr(node, "class", counter->getCounterClass());
+		mxmlElementSetAttr(node, "units", counter->getUnit());
+		if (counter->getModifier() != 1) {
+			mxmlElementSetAttrf(node, "modifier", "%d", counter->getModifier());
+		}
+		if (strcmp(counter->getDisplay(), "average") == 0 || strcmp(counter->getDisplay(), "maximum") == 0) {
+			mxmlElementSetAttr(node, "average_selection", "yes");
+		}
+		snprintf(buf, sizeof(buf), "libsensors %s sensor %s (%s)", counter->getTitle(), counter->getLabel(), counter->getName());
+		mxmlElementSetAttr(node, "description", buf);
+	}
+}
+
+void HwmonDriver::start() {
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
diff --git a/tools/gator/daemon/HwmonDriver.h b/tools/gator/daemon/HwmonDriver.h
new file mode 100644
index 000000000000..f28d825e3b7b
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef HWMONDRIVER_H
+#define HWMONDRIVER_H
+
+#include "Driver.h"
+
+class HwmonDriver : public PolledDriver {
+public:
+	HwmonDriver();
+	~HwmonDriver();
+
+	void readEvents(mxml_node_t *const root);
+
+	void writeEvents(mxml_node_t *root) const;
+
+	void start();
+
+private:
+	// Intentionally unimplemented
+	HwmonDriver(const HwmonDriver &);
+	HwmonDriver &operator=(const HwmonDriver &);
+};
+
+#endif // HWMONDRIVER_H
diff --git a/tools/gator/daemon/KMod.cpp b/tools/gator/daemon/KMod.cpp
new file mode 100644
index 000000000000..fe9dc6a7e4f7
--- /dev/null
+++ b/tools/gator/daemon/KMod.cpp
@@ -0,0 +1,119 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "KMod.h"
+
+#include <sys/types.h>
+#include <dirent.h>
+#include <unistd.h>
+
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// Claim all the counters in /dev/gator/events
+bool KMod::claimCounter(const Counter &counter) const {
+	char text[128];
+	snprintf(text, sizeof(text), "/dev/gator/events/%s", counter.getType());
+	return access(text, F_OK) == 0;
+}
+
+void KMod::resetCounters() {
+	char base[128];
+	char text[128];
+
+	// Initialize all perf counters in the driver, i.e. set enabled to zero
+	struct dirent *ent;
+	DIR* dir = opendir("/dev/gator/events");
+	if (dir) {
+		while ((ent = readdir(dir)) != NULL) {
+			// skip hidden files, current dir, and parent dir
+			if (ent->d_name[0] == '.')
+				continue;
+			snprintf(base, sizeof(base), "/dev/gator/events/%s", ent->d_name);
+			snprintf(text, sizeof(text), "%s/enabled", base);
+			DriverSource::writeDriver(text, 0);
+			snprintf(text, sizeof(text), "%s/count", base);
+			DriverSource::writeDriver(text, 0);
+		}
+		closedir(dir);
+	}
+}
+
+static const char ARM_MALI_MIDGARD[] = "ARM_Mali-Midgard_";
+static const char ARM_MALI_T[] = "ARM_Mali-T";
+
+void KMod::setupCounter(Counter &counter) {
+	char base[128];
+	char text[128];
+	snprintf(base, sizeof(base), "/dev/gator/events/%s", counter.getType());
+
+	if ((strncmp(counter.getType(), ARM_MALI_MIDGARD, sizeof(ARM_MALI_MIDGARD) - 1) == 0 ||
+	     strncmp(counter.getType(), ARM_MALI_T, sizeof(ARM_MALI_T) - 1) == 0)) {
+		mIsMaliCapture = true;
+	}
+
+	snprintf(text, sizeof(text), "%s/enabled", base);
+	int enabled = true;
+	if (DriverSource::writeReadDriver(text, &enabled) || !enabled) {
+		counter.setEnabled(false);
+		return;
+	}
+
+	int value = 0;
+	snprintf(text, sizeof(text), "%s/key", base);
+	DriverSource::readIntDriver(text, &value);
+	counter.setKey(value);
+
+	snprintf(text, sizeof(text), "%s/cores", base);
+	if (DriverSource::readIntDriver(text, &value) == 0) {
+		counter.setCores(value);
+	}
+
+	snprintf(text, sizeof(text), "%s/event", base);
+	DriverSource::writeDriver(text, counter.getEvent());
+	snprintf(text, sizeof(text), "%s/count", base);
+	if (access(text, F_OK) == 0) {
+		int count = counter.getCount();
+		if (DriverSource::writeReadDriver(text, &count) && counter.getCount() > 0) {
+			logg->logError(__FILE__, __LINE__, "Cannot enable EBS for %s:%i with a count of %d\n", counter.getType(), counter.getEvent(), counter.getCount());
+			handleException();
+		}
+		counter.setCount(count);
+	} else if (counter.getCount() > 0) {
+		ConfigurationXML::remove();
+		logg->logError(__FILE__, __LINE__, "Event Based Sampling is only supported with kernel versions 3.0.0 and higher with CONFIG_PERF_EVENTS=y, and CONFIG_HW_PERF_EVENTS=y. The invalid configuration.xml has been removed.\n");
+		handleException();
+	}
+}
+
+int KMod::writeCounters(mxml_node_t *root) const {
+	struct dirent *ent;
+	mxml_node_t *counter;
+
+	// counters.xml is simply a file listing of /dev/gator/events
+	DIR* dir = opendir("/dev/gator/events");
+	if (dir == NULL) {
+		return 0;
+	}
+
+	int count = 0;
+	while ((ent = readdir(dir)) != NULL) {
+		// skip hidden files, current dir, and parent dir
+		if (ent->d_name[0] == '.')
+			continue;
+		counter = mxmlNewElement(root, "counter");
+		mxmlElementSetAttr(counter, "name", ent->d_name);
+		++count;
+	}
+	closedir(dir);
+
+	return count;
+}
diff --git a/tools/gator/daemon/KMod.h b/tools/gator/daemon/KMod.h
new file mode 100644
index 000000000000..900a60e87d24
--- /dev/null
+++ b/tools/gator/daemon/KMod.h
@@ -0,0 +1,32 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef KMOD_H
+#define KMOD_H
+
+#include "Driver.h"
+
+// Driver for the gator kernel module
+class KMod : public Driver {
+public:
+	KMod() : mIsMaliCapture(false) {}
+	~KMod() {}
+
+	bool claimCounter(const Counter &counter) const;
+	void resetCounters();
+	void setupCounter(Counter &counter);
+
+	int writeCounters(mxml_node_t *root) const;
+
+	bool isMaliCapture() const { return mIsMaliCapture; }
+
+private:
+	bool mIsMaliCapture;
+};
+
+#endif // KMOD_H
diff --git a/tools/gator/daemon/LocalCapture.cpp b/tools/gator/daemon/LocalCapture.cpp
new file mode 100644
index 000000000000..d2a4b799d7ac
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.cpp
@@ -0,0 +1,131 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "LocalCapture.h"
+
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "EventsXML.h"
+
+LocalCapture::LocalCapture() {}
+
+LocalCapture::~LocalCapture() {}
+
+void LocalCapture::createAPCDirectory(char* target_path) {
+	gSessionData->mAPCDir = createUniqueDirectory(target_path, ".apc");
+	if ((removeDirAndAllContents(gSessionData->mAPCDir) != 0 || mkdir(gSessionData->mAPCDir, S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH) != 0)) {
+		logg->logError(__FILE__, __LINE__, "Unable to create directory %s", gSessionData->mAPCDir);
+		handleException();
+	}
+}
+
+void LocalCapture::write(char* string) {
+	char file[PATH_MAX];
+
+	// Set full path
+	snprintf(file, PATH_MAX, "%s/session.xml", gSessionData->mAPCDir);
+
+	// Write the file
+	if (util->writeToDisk(file, string) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify the path.", file);
+		handleException();
+	}
+
+	// Write events XML
+	EventsXML eventsXML;
+	eventsXML.write(gSessionData->mAPCDir);
+}
+
+char* LocalCapture::createUniqueDirectory(const char* initialPath, const char* ending) {
+	char* output;
+	char path[PATH_MAX];
+
+	// Ensure the path is an absolute path, i.e. starts with a slash
+	if (initialPath == 0 || strlen(initialPath) == 0) {
+		logg->logError(__FILE__, __LINE__, "Missing -o command line option required for a local capture.");
+		handleException();
+	} else if (initialPath[0] != '/') {
+		if (getcwd(path, PATH_MAX) == 0) {
+			logg->logMessage("Unable to retrieve the current working directory");
+		}
+		strncat(path, "/", PATH_MAX - strlen(path) - 1);
+		strncat(path, initialPath, PATH_MAX - strlen(path) - 1);
+	} else {
+		strncpy(path, initialPath, PATH_MAX);
+		path[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+
+	// Add ending if it is not already there
+	if (strcmp(&path[strlen(path) - strlen(ending)], ending) != 0) {
+		strncat(path, ending, PATH_MAX - strlen(path) - 1);
+	}
+
+	output = strdup(path);
+
+	return output;
+}
+
+int LocalCapture::removeDirAndAllContents(char* path) {
+	int error = 0;
+	struct stat mFileInfo;
+	// Does the path exist?
+	if (stat(path, &mFileInfo) == 0) {
+		// Is it a directory?
+		if (mFileInfo.st_mode & S_IFDIR) {
+			DIR * dir = opendir(path);
+			dirent* entry = readdir(dir);
+			while (entry) {
+				if (strcmp(entry->d_name, ".") != 0 && strcmp(entry->d_name, "..") != 0) {
+					char* newpath = (char*)malloc(strlen(path) + strlen(entry->d_name) + 2);
+					sprintf(newpath, "%s/%s", path, entry->d_name);
+					error = removeDirAndAllContents(newpath);
+					free(newpath);
+					if (error) {
+						break;
+					}
+				}
+				entry = readdir(dir);
+			}
+			closedir(dir);
+			if (error == 0) {
+				error = rmdir(path);
+			}
+		} else {
+			error = remove(path);
+		}
+	}
+	return error;
+}
+
+void LocalCapture::copyImages(ImageLinkList* ptr) {
+	char dstfilename[PATH_MAX];
+
+	while (ptr) {
+		strncpy(dstfilename, gSessionData->mAPCDir, PATH_MAX);
+		dstfilename[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+		if (gSessionData->mAPCDir[strlen(gSessionData->mAPCDir) - 1] != '/') {
+			strncat(dstfilename, "/", PATH_MAX - strlen(dstfilename) - 1);
+		}
+		strncat(dstfilename, util->getFilePart(ptr->path), PATH_MAX - strlen(dstfilename) - 1);
+		if (util->copyFile(ptr->path, dstfilename)) {
+			logg->logMessage("copied file %s to %s", ptr->path, dstfilename);
+		} else {
+			logg->logMessage("copy of file %s to %s failed", ptr->path, dstfilename);
+		}
+
+		ptr = ptr->next;
+	}
+}
diff --git a/tools/gator/daemon/LocalCapture.h b/tools/gator/daemon/LocalCapture.h
new file mode 100644
index 000000000000..25d281f8328b
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOCAL_CAPTURE_H__
+#define __LOCAL_CAPTURE_H__
+
+struct ImageLinkList;
+
+class LocalCapture {
+public:
+	LocalCapture();
+	~LocalCapture();
+	void write(char* string);
+	void copyImages(ImageLinkList* ptr);
+	void createAPCDirectory(char* target_path);
+private:
+	char* createUniqueDirectory(const char* path, const char* ending);
+	int removeDirAndAllContents(char* path);
+};
+
+#endif //__LOCAL_CAPTURE_H__
diff --git a/tools/gator/daemon/Logging.cpp b/tools/gator/daemon/Logging.cpp
new file mode 100644
index 000000000000..41ffa1a45151
--- /dev/null
+++ b/tools/gator/daemon/Logging.cpp
@@ -0,0 +1,78 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Logging.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+
+#ifdef WIN32
+#define MUTEX_INIT()    mLoggingMutex = CreateMutex(NULL, false, NULL);
+#define MUTEX_LOCK()    WaitForSingleObject(mLoggingMutex, 0xFFFFFFFF);
+#define MUTEX_UNLOCK()  ReleaseMutex(mLoggingMutex);
+#define snprintf _snprintf
+#else
+#include <pthread.h>
+#define MUTEX_INIT()    pthread_mutex_init(&mLoggingMutex, NULL)
+#define MUTEX_LOCK()    pthread_mutex_lock(&mLoggingMutex)
+#define MUTEX_UNLOCK()  pthread_mutex_unlock(&mLoggingMutex)
+#endif
+
+// Global thread-safe logging
+Logging* logg = NULL;
+
+Logging::Logging(bool debug) {
+	mDebug = debug;
+	MUTEX_INIT();
+
+	strcpy(mErrBuf, "Unknown Error");
+	strcpy(mLogBuf, "Unknown Message");
+}
+
+Logging::~Logging() {
+}
+
+void Logging::logError(const char* file, int line, const char* fmt, ...) {
+	va_list args;
+
+	MUTEX_LOCK();
+	if (mDebug) {
+		snprintf(mErrBuf, sizeof(mErrBuf), "ERROR[%s:%d]: ", file, line);
+	} else {
+		mErrBuf[0] = 0;
+	}
+
+	va_start(args, fmt);
+	vsnprintf(mErrBuf + strlen(mErrBuf), sizeof(mErrBuf) - 2 - strlen(mErrBuf), fmt, args); //  subtract 2 for \n and \0
+	va_end(args);
+
+	if (strlen(mErrBuf) > 0) {
+		strcat(mErrBuf, "\n");
+	}
+	MUTEX_UNLOCK();
+}
+
+void Logging::logMessage(const char* fmt, ...) {
+	if (mDebug) {
+		va_list args;
+
+		MUTEX_LOCK();
+		strcpy(mLogBuf, "INFO: ");
+
+		va_start(args, fmt);
+		vsnprintf(mLogBuf + strlen(mLogBuf), sizeof(mLogBuf) - 2 - strlen(mLogBuf), fmt, args); //  subtract 2 for \n and \0
+		va_end(args);
+		strcat(mLogBuf, "\n");
+
+		fprintf(stdout, "%s", mLogBuf);
+		fflush(stdout);
+		MUTEX_UNLOCK();
+	}
+}
diff --git a/tools/gator/daemon/Logging.h b/tools/gator/daemon/Logging.h
new file mode 100644
index 000000000000..09e93ff13f7a
--- /dev/null
+++ b/tools/gator/daemon/Logging.h
@@ -0,0 +1,36 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOGGING_H__
+#define __LOGGING_H__
+
+#include <pthread.h>
+
+#define DRIVER_ERROR "\n Driver issue:\n  >> gator.ko must be built against the current kernel version & configuration\n  >> gator.ko should be co-located with gatord in the same directory\n  >>   OR insmod gator.ko prior to launching gatord"
+
+class Logging {
+public:
+	Logging(bool debug);
+	~Logging();
+	void logError(const char* file, int line, const char* fmt, ...);
+	void logMessage(const char* fmt, ...);
+	char* getLastError() {return mErrBuf;}
+	char* getLastMessage() {return mLogBuf;}
+
+private:
+	char mErrBuf[4096]; // Arbitrarily large buffer to hold a string
+	char mLogBuf[4096]; // Arbitrarily large buffer to hold a string
+	bool mDebug;
+	pthread_mutex_t mLoggingMutex;
+};
+
+extern Logging* logg;
+
+extern void handleException() __attribute__ ((noreturn));
+
+#endif //__LOGGING_H__
diff --git a/tools/gator/daemon/Makefile b/tools/gator/daemon/Makefile
new file mode 100644
index 000000000000..27531b438b63
--- /dev/null
+++ b/tools/gator/daemon/Makefile
@@ -0,0 +1,22 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/arm-linux-gnueabihf-
+# NOTE: This toolchain uses the hardfloat abi by default. For non-hardfloat
+# targets run 'make SOFTFLOAT=1 SYSROOT=/path/to/sysroot', see
+# README_Streamline.txt for more details
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+ifeq ($(SOFTFLOAT),1)
+	CPPFLAGS += -marm -mthumb-interwork -march=armv4t -mfloat-abi=soft
+	LDFLAGS += -marm -march=armv4t -mfloat-abi=soft
+endif
+ifneq ($(SYSROOT),)
+	LDFLAGS += --sysroot=$(SYSROOT)
+endif
+
+include common.mk
diff --git a/tools/gator/daemon/Makefile_aarch64 b/tools/gator/daemon/Makefile_aarch64
new file mode 100644
index 000000000000..efd1fa002182
--- /dev/null
+++ b/tools/gator/daemon/Makefile_aarch64
@@ -0,0 +1,12 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+# make -f Makefile_aarch64
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/aarch64-linux-gnu-
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+include common.mk
diff --git a/tools/gator/daemon/MaliVideoDriver.cpp b/tools/gator/daemon/MaliVideoDriver.cpp
new file mode 100644
index 000000000000..5eef2643ab15
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.cpp
@@ -0,0 +1,191 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MaliVideoDriver.h"
+
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Counter.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// From instr/src/mve_instr_comm_protocol.h
+typedef enum mve_instr_configuration_type {
+	MVE_INSTR_RAW         = 1 << 0,
+	MVE_INSTR_COUNTERS    = 1 << 1,
+	MVE_INSTR_EVENTS      = 1 << 2,
+	MVE_INSTR_ACTIVITIES  = 1 << 3,
+
+	// Raw always pushed regardless
+	MVE_INSTR_PULL        = 1 << 12,
+	// Raw always unpacked regardless
+	MVE_INSTR_PACKED_COMM = 1 << 13,
+	// Don’t send ACKt response
+	MVE_INSTR_NO_AUTO_ACK   = 1 << 14,
+} mve_instr_configuration_type_t;
+
+static const char COUNTER[] = "ARM_Mali-V500_cnt";
+static const char EVENT[] = "ARM_Mali-V500_evn";
+static const char ACTIVITY[] = "ARM_Mali-V500_act";
+
+class MaliVideoCounter : public DriverCounter {
+public:
+	MaliVideoCounter(DriverCounter *next, const char *name, const MaliVideoCounterType type, const int id) : DriverCounter(next, name), mType(type), mId(id) {
+	}
+
+	~MaliVideoCounter() {
+	}
+
+	MaliVideoCounterType getType() const { return mType; }
+	int getId() const { return mId; }
+
+private:
+	const MaliVideoCounterType mType;
+	// Mali Video id
+	const int mId;
+};
+
+MaliVideoDriver::MaliVideoDriver() {
+}
+
+MaliVideoDriver::~MaliVideoDriver() {
+}
+
+void MaliVideoDriver::readEvents(mxml_node_t *const xml) {
+	mxml_node_t *node = xml;
+	while (true) {
+		node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+		if (node == NULL) {
+			break;
+		}
+		const char *counter = mxmlElementGetAttr(node, "counter");
+		if (counter == NULL) {
+			// Ignore
+		} else if (strncmp(counter, COUNTER, sizeof(COUNTER) - 1) == 0) {
+			const int i = strtol(counter + sizeof(COUNTER) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_COUNTER, i));
+		} else if (strncmp(counter, EVENT, sizeof(EVENT) - 1) == 0) {
+			const int i = strtol(counter + sizeof(EVENT) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_EVENT, i));
+		} else if (strncmp(counter, ACTIVITY, sizeof(ACTIVITY) - 1) == 0) {
+			const int i = strtol(counter + sizeof(ACTIVITY) - 1, NULL, 10);
+			setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_ACTIVITY, i));
+		}
+	}
+}
+
+int MaliVideoDriver::writeCounters(mxml_node_t *root) const {
+	if (access("/dev/mv500", F_OK) != 0) {
+		return 0;
+	}
+
+	return super::writeCounters(root);
+}
+
+void MaliVideoDriver::marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos) {
+	// size
+	int numEnabled = 0;
+	for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() == type)) {
+			++numEnabled;
+		}
+	}
+	Buffer::packInt(buf, bufsize, pos, numEnabled*sizeof(uint32_t));
+	for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() == type)) {
+			Buffer::packInt(buf, bufsize, pos, counter->getId());
+		}
+	}
+}
+
+static bool writeAll(const int mveUds, const char *const buf, const int pos) {
+	int written = 0;
+	while (written < pos) {
+		size_t bytes = ::write(mveUds, buf + written, pos - written);
+		if (bytes <= 0) {
+			logg->logMessage("%s(%s:%i): write failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+		written += bytes;
+	}
+
+	return true;
+}
+
+bool MaliVideoDriver::start(const int mveUds) {
+	char buf[256];
+	int pos = 0;
+
+	// code - MVE_INSTR_STARTUP
+	buf[pos++] = 'C';
+	buf[pos++] = 'L';
+	buf[pos++] = 'N';
+	buf[pos++] = 'T';
+	// size
+	Buffer::packInt(buf, sizeof(buf), pos, sizeof(uint32_t));
+	// client_version_number
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+
+	// code - MVE_INSTR_CONFIGURE
+	buf[pos++] = 'C';
+	buf[pos++] = 'N';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	// size
+	Buffer::packInt(buf, sizeof(buf), pos, 5*sizeof(uint32_t));
+	// configuration
+	Buffer::packInt(buf, sizeof(buf), pos, MVE_INSTR_COUNTERS | MVE_INSTR_EVENTS | MVE_INSTR_ACTIVITIES | MVE_INSTR_PACKED_COMM);
+	// communication_protocol_version
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+	// data_protocol_version
+	Buffer::packInt(buf, sizeof(buf), pos, 1);
+	// sample_rate - convert samples/second to ms/sample
+	Buffer::packInt(buf, sizeof(buf), pos, 1000/gSessionData->mSampleRate);
+	// live_rate - convert ns/flush to ms/flush
+	Buffer::packInt(buf, sizeof(buf), pos, gSessionData->mLiveRate/1000000);
+
+	// code - MVE_INSTR_ENABLE_COUNTERS
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'c';
+	marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos);
+
+	// code - MVE_INSTR_ENABLE_EVENTS
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'e';
+	marshalEnable(MVCT_EVENT, buf, sizeof(buf), pos);
+
+	// code - MVE_INSTR_ENABLE_ACTIVITIES
+	buf[pos++] = 'C';
+	buf[pos++] = 'F';
+	buf[pos++] = 'G';
+	buf[pos++] = 'a';
+	marshalEnable(MVCT_ACTIVITY, buf, sizeof(buf), pos);
+
+	return writeAll(mveUds, buf, pos);
+}
+
+void MaliVideoDriver::stop(const int mveUds) {
+	char buf[8];
+	int pos = 0;
+
+	// code - MVE_INSTR_STOP
+	buf[pos++] = 'S';
+	buf[pos++] = 'T';
+	buf[pos++] = 'O';
+	buf[pos++] = 'P';
+	marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos);
+
+	writeAll(mveUds, buf, pos);
+
+	close(mveUds);
+}
diff --git a/tools/gator/daemon/MaliVideoDriver.h b/tools/gator/daemon/MaliVideoDriver.h
new file mode 100644
index 000000000000..204a57a447ac
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.h
@@ -0,0 +1,45 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MALIVIDEODRIVER_H
+#define MALIVIDEODRIVER_H
+
+#include "Driver.h"
+
+class MaliVideoCounter;
+
+enum MaliVideoCounterType {
+	MVCT_COUNTER,
+	MVCT_EVENT,
+	MVCT_ACTIVITY,
+};
+
+class MaliVideoDriver : public SimpleDriver {
+private:
+	typedef SimpleDriver super;
+
+public:
+	MaliVideoDriver();
+	~MaliVideoDriver();
+
+	void readEvents(mxml_node_t *const root);
+
+	int writeCounters(mxml_node_t *root) const;
+
+	bool start(const int mveUds);
+	void stop(const int mveUds);
+
+private:
+	void marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos);
+
+	// Intentionally unimplemented
+	MaliVideoDriver(const MaliVideoDriver &);
+	MaliVideoDriver &operator=(const MaliVideoDriver &);
+};
+
+#endif // MALIVIDEODRIVER_H
diff --git a/tools/gator/daemon/MemInfoDriver.cpp b/tools/gator/daemon/MemInfoDriver.cpp
new file mode 100644
index 000000000000..cce15c16fcdc
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.cpp
@@ -0,0 +1,93 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MemInfoDriver.h"
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class MemInfoCounter : public DriverCounter {
+public:
+	MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~MemInfoCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+
+	// Intentionally unimplemented
+	MemInfoCounter(const MemInfoCounter &);
+	MemInfoCounter &operator=(const MemInfoCounter &);
+};
+
+MemInfoCounter::MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value) {
+}
+
+MemInfoCounter::~MemInfoCounter() {
+}
+
+int64_t MemInfoCounter::read() {
+	return *mValue;
+}
+
+MemInfoDriver::MemInfoDriver() : mBuf(), mMemUsed(0), mMemFree(0), mBuffers(0) {
+}
+
+MemInfoDriver::~MemInfoDriver() {
+}
+
+void MemInfoDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memused2"), &mMemUsed));
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memfree"), &mMemFree));
+	setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_bufferram"), &mBuffers));
+}
+
+void MemInfoDriver::read(Buffer *const buffer) {
+	if (!countersEnabled()) {
+		return;
+	}
+
+	if (!mBuf.read("/proc/meminfo")) {
+		logg->logError(__FILE__, __LINE__, "Failed to read /proc/meminfo");
+		handleException();
+	}
+
+	char *key = mBuf.getBuf();
+	char *colon;
+	int64_t memTotal = 0;
+	while ((colon = strchr(key, ':')) != NULL) {
+		char *end = strchr(colon + 1, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+		*colon = '\0';
+
+		if (strcmp(key, "MemTotal") == 0) {
+			memTotal = strtoll(colon + 1, NULL, 10) << 10;
+		} else if (strcmp(key, "MemFree") == 0) {
+			mMemFree = strtoll(colon + 1, NULL, 10) << 10;
+		} else if (strcmp(key, "Buffers") == 0) {
+			mBuffers = strtoll(colon + 1, NULL, 10) << 10;
+		}
+
+		if (end == NULL) {
+			break;
+		}
+		key = end + 1;
+	}
+
+	mMemUsed = memTotal - mMemFree;
+
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/MemInfoDriver.h b/tools/gator/daemon/MemInfoDriver.h
new file mode 100644
index 000000000000..eb1b0417f309
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.h
@@ -0,0 +1,37 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MEMINFODRIVER_H
+#define MEMINFODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class MemInfoDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	MemInfoDriver();
+	~MemInfoDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void read(Buffer *const buffer);
+
+private:
+	DynBuf mBuf;
+	int64_t mMemUsed;
+	int64_t mMemFree;
+	int64_t mBuffers;
+
+	// Intentionally unimplemented
+	MemInfoDriver(const MemInfoDriver &);
+	MemInfoDriver &operator=(const MemInfoDriver &);
+};
+
+#endif // MEMINFODRIVER_H
diff --git a/tools/gator/daemon/Monitor.cpp b/tools/gator/daemon/Monitor.cpp
new file mode 100644
index 000000000000..74f22ee29fec
--- /dev/null
+++ b/tools/gator/daemon/Monitor.cpp
@@ -0,0 +1,82 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Monitor.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+Monitor::Monitor() : mFd(-1) {
+}
+
+Monitor::~Monitor() {
+	if (mFd >= 0) {
+		::close(mFd);
+	}
+}
+
+void Monitor::close() {
+	if (mFd >= 0) {
+		::close(mFd);
+		mFd = -1;
+	}
+}
+
+bool Monitor::init() {
+#ifdef EPOLL_CLOEXEC
+	mFd = epoll_create1(EPOLL_CLOEXEC);
+#else
+	mFd = epoll_create(16);
+#endif
+	if (mFd < 0) {
+		logg->logMessage("%s(%s:%i): epoll_create1 failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+#ifndef EPOLL_CLOEXEC
+  int fdf = fcntl(mFd, F_GETFD);
+  if ((fdf == -1) || (fcntl(mFd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		logg->logMessage("%s(%s:%i): fcntl failed", __FUNCTION__, __FILE__, __LINE__);
+    ::close(mFd);
+    return -1;
+  }
+#endif
+
+	return true;
+}
+
+bool Monitor::add(const int fd) {
+	struct epoll_event event;
+	memset(&event, 0, sizeof(event));
+	event.data.fd = fd;
+	event.events = EPOLLIN;
+	if (epoll_ctl(mFd, EPOLL_CTL_ADD, fd, &event) != 0) {
+		logg->logMessage("%s(%s:%i): epoll_ctl failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	return true;
+}
+
+int Monitor::wait(struct epoll_event *const events, int maxevents, int timeout) {
+	int result = epoll_wait(mFd, events, maxevents, timeout);
+	if (result < 0) {
+		// Ignore if the call was interrupted as this will happen when SIGINT is received
+		if (errno == EINTR) {
+			result = 0;
+		} else {
+			logg->logMessage("%s(%s:%i): epoll_wait failed", __FUNCTION__, __FILE__, __LINE__);
+		}
+	}
+
+	return result;
+}
diff --git a/tools/gator/daemon/Monitor.h b/tools/gator/daemon/Monitor.h
new file mode 100644
index 000000000000..7194e0e4ca50
--- /dev/null
+++ b/tools/gator/daemon/Monitor.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MONITOR_H
+#define MONITOR_H
+
+#include <sys/epoll.h>
+
+class Monitor {
+public:
+	Monitor();
+	~Monitor();
+
+	void close();
+	bool init();
+	bool add(const int fd);
+	int wait(struct epoll_event *const events, int maxevents, int timeout);
+
+private:
+
+	int mFd;
+
+	// Intentionally unimplemented
+	Monitor(const Monitor &);
+	Monitor &operator=(const Monitor &);
+};
+
+#endif // MONITOR_H
diff --git a/tools/gator/daemon/NetDriver.cpp b/tools/gator/daemon/NetDriver.cpp
new file mode 100644
index 000000000000..e75c0695779a
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.cpp
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "NetDriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class NetCounter : public DriverCounter {
+public:
+	NetCounter(DriverCounter *next, char *const name, int64_t *const value);
+	~NetCounter();
+
+	int64_t read();
+
+private:
+	int64_t *const mValue;
+	int64_t mPrev;
+
+	// Intentionally unimplemented
+	NetCounter(const NetCounter &);
+	NetCounter &operator=(const NetCounter &);
+};
+
+NetCounter::NetCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+NetCounter::~NetCounter() {
+}
+
+int64_t NetCounter::read() {
+	int64_t result = *mValue - mPrev;
+	mPrev = *mValue;
+	return result;
+}
+
+NetDriver::NetDriver() : mBuf(), mReceiveBytes(0), mTransmitBytes(0) {
+}
+
+NetDriver::~NetDriver() {
+}
+
+void NetDriver::readEvents(mxml_node_t *const) {
+	// Only for use with perf
+	if (!gSessionData->perf.isSetup()) {
+		return;
+	}
+
+	setCounters(new NetCounter(getCounters(), strdup("Linux_net_rx"), &mReceiveBytes));
+	setCounters(new NetCounter(getCounters(), strdup("Linux_net_tx"), &mTransmitBytes));
+}
+
+bool NetDriver::doRead() {
+	if (!countersEnabled()) {
+		return true;
+	}
+
+	if (!mBuf.read("/proc/net/dev")) {
+		return false;
+	}
+
+	// Skip the header
+	char *key;
+	if (((key = strchr(mBuf.getBuf(), '\n')) == NULL) ||
+			((key = strchr(key + 1, '\n')) == NULL)) {
+		return false;
+	}
+	key = key + 1;
+
+	mReceiveBytes = 0;
+	mTransmitBytes = 0;
+
+	char *colon;
+	while ((colon = strchr(key, ':')) != NULL) {
+		char *end = strchr(colon + 1, '\n');
+		if (end != NULL) {
+			*end = '\0';
+		}
+		*colon = '\0';
+
+		int64_t receiveBytes;
+		int64_t transmitBytes;
+		const int count = sscanf(colon + 1, " %" SCNu64 " %*u %*u %*u %*u %*u %*u %*u %" SCNu64, &receiveBytes, &transmitBytes);
+		if (count != 2) {
+			return false;
+		}
+		mReceiveBytes += receiveBytes;
+		mTransmitBytes += transmitBytes;
+
+		if (end == NULL) {
+			break;
+		}
+		key = end + 1;
+	}
+
+	return true;
+}
+
+void NetDriver::start() {
+	if (!doRead()) {
+		logg->logError(__FILE__, __LINE__, "Unable to read network stats");
+		handleException();
+	}
+	// Initialize previous values
+	for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+		if (!counter->isEnabled()) {
+			continue;
+		}
+		counter->read();
+	}
+}
+
+void NetDriver::read(Buffer *const buffer) {
+	if (!doRead()) {
+		logg->logError(__FILE__, __LINE__, "Unable to read network stats");
+		handleException();
+	}
+	super::read(buffer);
+}
diff --git a/tools/gator/daemon/NetDriver.h b/tools/gator/daemon/NetDriver.h
new file mode 100644
index 000000000000..50ff850bfc6d
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef NETDRIVER_H
+#define NETDRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class NetDriver : public PolledDriver {
+private:
+	typedef PolledDriver super;
+
+public:
+	NetDriver();
+	~NetDriver();
+
+	void readEvents(mxml_node_t *const root);
+	void start();
+	void read(Buffer *const buffer);
+
+private:
+	bool doRead();
+
+	DynBuf mBuf;
+	int64_t mReceiveBytes;
+	int64_t mTransmitBytes;
+
+	// Intentionally unimplemented
+	NetDriver(const NetDriver &);
+	NetDriver &operator=(const NetDriver &);
+};
+
+#endif // NETDRIVER_H
diff --git a/tools/gator/daemon/OlySocket.cpp b/tools/gator/daemon/OlySocket.cpp
new file mode 100644
index 000000000000..aa0ce4929916
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.cpp
@@ -0,0 +1,324 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlySocket.h"
+
+#include <stdio.h>
+#include <string.h>
+#ifdef WIN32
+#include <Winsock2.h>
+#include <ws2tcpip.h>
+#else
+#include <netinet/in.h>
+#include <sys/un.h>
+#include <unistd.h>
+#include <netdb.h>
+#include <fcntl.h>
+#endif
+
+#include "Logging.h"
+
+#ifdef WIN32
+#define CLOSE_SOCKET(x) closesocket(x)
+#define SHUTDOWN_RX_TX SD_BOTH
+#define snprintf       _snprintf
+#else
+#define CLOSE_SOCKET(x) close(x)
+#define SHUTDOWN_RX_TX SHUT_RDWR
+#endif
+
+int socket_cloexec(int domain, int type, int protocol) {
+#ifdef SOCK_CLOEXEC
+  return socket(domain, type | SOCK_CLOEXEC, protocol);
+#else
+  int sock = socket(domain, type, protocol);
+#ifdef FD_CLOEXEC
+  if (sock < 0) {
+    return -1;
+  }
+  int fdf = fcntl(sock, F_GETFD);
+  if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+    close(sock);
+    return -1;
+  }
+#endif
+  return sock;
+#endif
+}
+
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen) {
+  int sock;
+#ifdef SOCK_CLOEXEC
+  sock = accept4(sockfd, addr, addrlen, SOCK_CLOEXEC);
+  if (sock >= 0) {
+    return sock;
+  }
+  // accept4 with SOCK_CLOEXEC may not work on all kernels, so fallback
+#endif
+  sock = accept(sockfd, addr, addrlen);
+#ifdef FD_CLOEXEC
+  if (sock < 0) {
+    return -1;
+  }
+  int fdf = fcntl(sock, F_GETFD);
+  if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+    close(sock);
+    return -1;
+  }
+#endif
+  return sock;
+}
+
+OlyServerSocket::OlyServerSocket(int port) {
+#ifdef WIN32
+  WSADATA wsaData;
+  if (WSAStartup(0x0202, &wsaData) != 0) {
+    logg->logError(__FILE__, __LINE__, "Windows socket initialization failed");
+    handleException();
+  }
+#endif
+
+  createServerSocket(port);
+}
+
+OlySocket::OlySocket(int socketID) : mSocketID(socketID) {
+}
+
+#ifndef WIN32
+
+#define MIN(A, B) ({ \
+  const __typeof__(A) __a = A; \
+  const __typeof__(B) __b = B; \
+  __a > __b ? __b : __a; \
+})
+
+OlyServerSocket::OlyServerSocket(const char* path, const size_t pathSize) {
+  // Create socket
+  mFDServer = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+  if (mFDServer < 0) {
+    logg->logError(__FILE__, __LINE__, "Error creating server socket");
+    handleException();
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_un sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sun_family = AF_UNIX;
+  memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+  sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+  // Bind the socket to an address
+  if (bind(mFDServer, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+    logg->logError(__FILE__, __LINE__, "Binding of server socket failed.");
+    handleException();
+  }
+
+  // Listen for connections on this socket
+  if (listen(mFDServer, 1) < 0) {
+    logg->logError(__FILE__, __LINE__, "Listening of server socket failed");
+    handleException();
+  }
+}
+
+int OlySocket::connect(const char* path, const size_t pathSize) {
+  int fd = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+  if (fd < 0) {
+    return -1;
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_un sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sun_family = AF_UNIX;
+  memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+  sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+  if (::connect(fd, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+    close(fd);
+    return -1;
+  }
+
+  return fd;
+}
+
+#endif
+
+OlySocket::~OlySocket() {
+  if (mSocketID > 0) {
+    CLOSE_SOCKET(mSocketID);
+  }
+}
+
+OlyServerSocket::~OlyServerSocket() {
+  if (mFDServer > 0) {
+    CLOSE_SOCKET(mFDServer);
+  }
+}
+
+void OlySocket::shutdownConnection() {
+  // Shutdown is primarily used to unblock other threads that are blocking on send/receive functions
+  shutdown(mSocketID, SHUTDOWN_RX_TX);
+}
+
+void OlySocket::closeSocket() {
+  // Used for closing an accepted socket but keeping the server socket active
+  if (mSocketID > 0) {
+    CLOSE_SOCKET(mSocketID);
+    mSocketID = -1;
+  }
+}
+
+void OlyServerSocket::closeServerSocket() {
+  if (CLOSE_SOCKET(mFDServer) != 0) {
+    logg->logError(__FILE__, __LINE__, "Failed to close server socket.");
+    handleException();
+  }
+  mFDServer = 0;
+}
+
+void OlyServerSocket::createServerSocket(int port) {
+  int family = AF_INET6;
+
+  // Create socket
+  mFDServer = socket_cloexec(PF_INET6, SOCK_STREAM, IPPROTO_TCP);
+  if (mFDServer < 0) {
+    family = AF_INET;
+    mFDServer = socket_cloexec(PF_INET, SOCK_STREAM, IPPROTO_TCP);
+    if (mFDServer < 0) {
+      logg->logError(__FILE__, __LINE__, "Error creating server socket");
+      handleException();
+    }
+  }
+
+  // Enable address reuse, another solution would be to create the server socket once and only close it when the object exits
+  int on = 1;
+  if (setsockopt(mFDServer, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+    logg->logError(__FILE__, __LINE__, "Setting server socket options failed");
+    handleException();
+  }
+
+  // Create sockaddr_in structure, ensuring non-populated fields are zero
+  struct sockaddr_in6 sockaddr;
+  memset((void*)&sockaddr, 0, sizeof(sockaddr));
+  sockaddr.sin6_family = family;
+  sockaddr.sin6_port = htons(port);
+  sockaddr.sin6_addr = in6addr_any;
+
+  // Bind the socket to an address
+  if (bind(mFDServer, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+    logg->logError(__FILE__, __LINE__, "Binding of server socket failed.\nIs an instance already running?");
+    handleException();
+  }
+
+  // Listen for connections on this socket
+  if (listen(mFDServer, 1) < 0) {
+    logg->logError(__FILE__, __LINE__, "Listening of server socket failed");
+    handleException();
+  }
+}
+
+// mSocketID is always set to the most recently accepted connection
+// The user of this class should maintain the different socket connections, e.g. by forking the process
+int OlyServerSocket::acceptConnection() {
+  int socketID;
+  if (mFDServer <= 0) {
+    logg->logError(__FILE__, __LINE__, "Attempting multiple connections on a single connection server socket or attempting to accept on a client socket");
+    handleException();
+  }
+
+  // Accept a connection, note that this call blocks until a client connects
+  socketID = accept_cloexec(mFDServer, NULL, NULL);
+  if (socketID < 0) {
+    logg->logError(__FILE__, __LINE__, "Socket acceptance failed");
+    handleException();
+  }
+  return socketID;
+}
+
+void OlySocket::send(const char* buffer, int size) {
+  if (size <= 0 || buffer == NULL) {
+    return;
+  }
+
+  while (size > 0) {
+    int n = ::send(mSocketID, buffer, size, 0);
+    if (n < 0) {
+      logg->logError(__FILE__, __LINE__, "Socket send error");
+      handleException();
+    }
+    size -= n;
+    buffer += n;
+  }
+}
+
+// Returns the number of bytes received
+int OlySocket::receive(char* buffer, int size) {
+  if (size <= 0 || buffer == NULL) {
+    return 0;
+  }
+
+  int bytes = recv(mSocketID, buffer, size, 0);
+  if (bytes < 0) {
+    logg->logError(__FILE__, __LINE__, "Socket receive error");
+    handleException();
+  } else if (bytes == 0) {
+    logg->logMessage("Socket disconnected");
+    return -1;
+  }
+  return bytes;
+}
+
+// Receive exactly size bytes of data. Note, this function will block until all bytes are received
+int OlySocket::receiveNBytes(char* buffer, int size) {
+  int bytes = 0;
+  while (size > 0 && buffer != NULL) {
+    bytes = recv(mSocketID, buffer, size, 0);
+    if (bytes < 0) {
+      logg->logError(__FILE__, __LINE__, "Socket receive error");
+      handleException();
+    } else if (bytes == 0) {
+      logg->logMessage("Socket disconnected");
+      return -1;
+    }
+    buffer += bytes;
+    size -= bytes;
+  }
+  return bytes;
+}
+
+// Receive data until a carriage return, line feed, or null is encountered, or the buffer fills
+int OlySocket::receiveString(char* buffer, int size) {
+  int bytes_received = 0;
+  bool found = false;
+
+  if (buffer == 0) {
+    return 0;
+  }
+
+  while (!found && bytes_received < size) {
+    // Receive a single character
+    int bytes = recv(mSocketID, &buffer[bytes_received], 1, 0);
+    if (bytes < 0) {
+      logg->logError(__FILE__, __LINE__, "Socket receive error");
+      handleException();
+    } else if (bytes == 0) {
+      logg->logMessage("Socket disconnected");
+      return -1;
+    }
+
+    // Replace carriage returns and line feeds with zero
+    if (buffer[bytes_received] == '\n' || buffer[bytes_received] == '\r' || buffer[bytes_received] == '\0') {
+      buffer[bytes_received] = '\0';
+      found = true;
+    }
+
+    bytes_received++;
+  }
+
+  return bytes_received;
+}
diff --git a/tools/gator/daemon/OlySocket.h b/tools/gator/daemon/OlySocket.h
new file mode 100644
index 000000000000..6b53b01fc3ee
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.h
@@ -0,0 +1,64 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __OLY_SOCKET_H__
+#define __OLY_SOCKET_H__
+
+#include <stddef.h>
+
+#ifdef WIN32
+typedef socklen_t int;
+#else
+#include <sys/socket.h>
+#endif
+
+class OlySocket {
+public:
+#ifndef WIN32
+  static int connect(const char* path, const size_t pathSize);
+#endif
+
+  OlySocket(int socketID);
+  ~OlySocket();
+
+  void closeSocket();
+  void shutdownConnection();
+  void send(const char* buffer, int size);
+  int receive(char* buffer, int size);
+  int receiveNBytes(char* buffer, int size);
+  int receiveString(char* buffer, int size);
+
+  bool isValid() const { return mSocketID >= 0; }
+
+private:
+  int mSocketID;
+};
+
+class OlyServerSocket {
+public:
+  OlyServerSocket(int port);
+#ifndef WIN32
+  OlyServerSocket(const char* path, const size_t pathSize);
+#endif
+  ~OlyServerSocket();
+
+  int acceptConnection();
+  void closeServerSocket();
+
+  int getFd() { return mFDServer; }
+
+private:
+  int mFDServer;
+
+  void createServerSocket(int port);
+};
+
+int socket_cloexec(int domain, int type, int protocol);
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen);
+
+#endif //__OLY_SOCKET_H__
diff --git a/tools/gator/daemon/OlyUtility.cpp b/tools/gator/daemon/OlyUtility.cpp
new file mode 100644
index 000000000000..45340a27d9fa
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.cpp
@@ -0,0 +1,227 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlyUtility.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+#if defined(WIN32)
+#include <windows.h>
+#elif defined(__linux__)
+#include <unistd.h>
+#elif defined(DARWIN)
+#include <mach-o/dyld.h>
+#endif
+
+OlyUtility* util = NULL;
+
+bool OlyUtility::stringToBool(const char* string, bool defValue) {
+  char value[32];
+
+  if (string == NULL) {
+    return defValue;
+  }
+
+  strncpy(value, string, sizeof(value));
+  if (value[0] == 0) {
+    return defValue;
+  }
+  value[sizeof(value) - 1] = 0; // strncpy does not guarantee a null-terminated string
+
+  // Convert to lowercase
+  int i = 0;
+  while (value[i]) {
+    value[i] = tolower(value[i]);
+    i++;
+  }
+
+  if (strcmp(value, "true") == 0 || strcmp(value, "yes") == 0 || strcmp(value, "1") == 0 || strcmp(value, "on") == 0) {
+    return true;
+  } else if (strcmp(value, "false") == 0 || strcmp(value, "no") == 0 || strcmp(value, "0") == 0 || strcmp(value, "off") == 0) {
+    return false;
+  } else {
+    return defValue;
+  }
+}
+
+void OlyUtility::stringToLower(char* string) {
+  if (string == NULL) {
+    return;
+  }
+
+  while (*string) {
+    *string = tolower(*string);
+    string++;
+  }
+}
+
+// Modifies fullpath with the path part including the trailing path separator
+int OlyUtility::getApplicationFullPath(char* fullpath, int sizeOfPath) {
+  memset(fullpath, 0, sizeOfPath);
+#if defined(WIN32)
+  int length = GetModuleFileName(NULL, fullpath, sizeOfPath);
+#elif defined(__linux__)
+  int length = readlink("/proc/self/exe", fullpath, sizeOfPath);
+#elif defined(DARWIN)
+  uint32_t length_u = (uint32_t)sizeOfPath;
+  int length = sizeOfPath;
+  if (_NSGetExecutablePath(fullpath, &length_u) == 0) {
+    length = strlen(fullpath);
+  }
+#endif
+
+  if (length == sizeOfPath) {
+    return -1;
+  }
+
+  fullpath[length] = 0;
+  getPathPart(fullpath);
+
+  return 0;
+}
+
+char* OlyUtility::readFromDisk(const char* file, unsigned int *size, bool appendNull) {
+  // Open the file
+  FILE* pFile = fopen(file, "rb");
+  if (pFile==NULL) {
+    return NULL;
+  }
+
+  // Obtain file size
+  fseek(pFile , 0 , SEEK_END);
+  unsigned int lSize = ftell(pFile);
+  rewind(pFile);
+
+  // Allocate memory to contain the whole file
+  char* buffer = (char*)malloc(lSize + (int)appendNull);
+  if (buffer == NULL) {
+    fclose(pFile);
+    return NULL;
+  }
+
+  // Copy the file into the buffer
+  if (fread(buffer, 1, lSize, pFile) != lSize) {
+    free(buffer);
+    fclose(pFile);
+    return NULL;
+  }
+
+  // Terminate
+  fclose(pFile);
+
+  if (appendNull) {
+    buffer[lSize] = 0;
+  }
+
+  if (size) {
+    *size = lSize;
+  }
+
+  return buffer;
+}
+
+int OlyUtility::writeToDisk(const char* path, const char* data) {
+  // Open the file
+  FILE* pFile = fopen(path, "wb");
+  if (pFile == NULL) {
+    return -1;
+  }
+
+  // Write the data to disk
+  if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+    fclose(pFile);
+    return -1;
+  }
+
+  // Terminate
+  fclose(pFile);
+  return 0;
+}
+
+int OlyUtility::appendToDisk(const char* path, const char* data) {
+  // Open the file
+  FILE* pFile = fopen(path, "a");
+  if (pFile == NULL) {
+    return -1;
+  }
+
+  // Write the data to disk
+  if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+    fclose(pFile);
+    return -1;
+  }
+
+  // Terminate
+  fclose(pFile);
+  return 0;
+}
+
+/**
+ * Copies the srcFile into dstFile in 1kB chunks.
+ * The dstFile will be overwritten if it exists.
+ * 0 is returned on an error; otherwise 1.
+ */
+#define TRANSFER_SIZE 1024
+int OlyUtility::copyFile(const char* srcFile, const char* dstFile) {
+  char buffer[TRANSFER_SIZE];
+  FILE * f_src = fopen(srcFile,"rb");
+  if (!f_src) {
+    return 0;
+  }
+  FILE * f_dst = fopen(dstFile,"wb");
+  if (!f_dst) {
+    fclose(f_src);
+    return 0;
+  }
+  while (!feof(f_src)) {
+    int num_bytes_read = fread(buffer, 1, TRANSFER_SIZE, f_src);
+    if (num_bytes_read < TRANSFER_SIZE && !feof(f_src)) {
+      fclose(f_src);
+      fclose(f_dst);
+      return 0;
+    }
+    int num_bytes_written = fwrite(buffer, 1, num_bytes_read, f_dst);
+    if (num_bytes_written != num_bytes_read) {
+      fclose(f_src);
+      fclose(f_dst);
+      return 0;
+    }
+  }
+  fclose(f_src);
+  fclose(f_dst);
+  return 1;
+}
+
+const char* OlyUtility::getFilePart(const char* path) {
+  const char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+  // in case path is not a full path
+  if (last_sep == NULL) {
+    return path;
+  }
+
+  return last_sep++;
+}
+
+// getPathPart may modify the contents of path
+// returns the path including the trailing path separator
+char* OlyUtility::getPathPart(char* path) {
+  char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+  // in case path is not a full path
+  if (last_sep == NULL) {
+    return 0;
+  }
+  last_sep++;
+  *last_sep = 0;
+
+  return (path);
+}
diff --git a/tools/gator/daemon/OlyUtility.h b/tools/gator/daemon/OlyUtility.h
new file mode 100644
index 000000000000..1d26beb596fa
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef OLY_UTILITY_H
+#define OLY_UTILITY_H
+
+#include <stddef.h>
+
+#ifdef WIN32
+#define PATH_SEPARATOR '\\'
+#define CAIMAN_PATH_MAX MAX_PATH
+#define snprintf _snprintf
+#else
+#include <limits.h>
+#define PATH_SEPARATOR '/'
+#define CAIMAN_PATH_MAX PATH_MAX
+#endif
+
+class OlyUtility {
+public:
+  OlyUtility() {};
+  ~OlyUtility() {};
+  bool stringToBool(const char* string, bool defValue);
+  void stringToLower(char* string);
+  int getApplicationFullPath(char* path, int sizeOfPath);
+  char* readFromDisk(const char* file, unsigned int *size = NULL, bool appendNull = true);
+  int writeToDisk(const char* path, const char* file);
+  int appendToDisk(const char* path, const char* file);
+  int copyFile(const char* srcFile, const char* dstFile);
+  const char* getFilePart(const char* path);
+  char* getPathPart(char* path);
+private:
+};
+
+extern OlyUtility* util;
+
+#endif // OLY_UTILITY_H
diff --git a/tools/gator/daemon/PerfBuffer.cpp b/tools/gator/daemon/PerfBuffer.cpp
new file mode 100644
index 000000000000..f127c996d43b
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.cpp
@@ -0,0 +1,158 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfBuffer.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+PerfBuffer::PerfBuffer() {
+	for (int cpu = 0; cpu < ARRAY_LENGTH(mBuf); ++cpu) {
+		mBuf[cpu] = MAP_FAILED;
+		mDiscard[cpu] = false;
+		mFds[cpu] = -1;
+	}
+}
+
+PerfBuffer::~PerfBuffer() {
+	for (int cpu = ARRAY_LENGTH(mBuf) - 1; cpu >= 0; --cpu) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+		}
+	}
+}
+
+bool PerfBuffer::useFd(const int cpu, const int fd) {
+	if (mFds[cpu] < 0) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			logg->logMessage("%s(%s:%i): cpu %i already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__, cpu);
+			return false;
+		}
+
+		// The buffer isn't mapped yet
+		mBuf[cpu] = mmap(NULL, gSessionData->mPageSize + BUF_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+		if (mBuf[cpu] == MAP_FAILED) {
+			logg->logMessage("%s(%s:%i): mmap failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+		mFds[cpu] = fd;
+
+		// Check the version
+		struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+		if (pemp->compat_version != 0) {
+			logg->logMessage("%s(%s:%i): Incompatible perf_event_mmap_page compat_version", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	} else {
+		if (mBuf[cpu] == MAP_FAILED) {
+			logg->logMessage("%s(%s:%i): cpu already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+
+		if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, mFds[cpu]) < 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+void PerfBuffer::discard(const int cpu) {
+	if (mBuf[cpu] != MAP_FAILED) {
+		mDiscard[cpu] = true;
+	}
+}
+
+bool PerfBuffer::isEmpty() {
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		if (mBuf[cpu] != MAP_FAILED) {
+			// Take a snapshot of the positions
+			struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+			const __u64 head = pemp->data_head;
+			const __u64 tail = pemp->data_tail;
+
+			if (head != tail) {
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+static void compressAndSend(const int cpu, const __u64 head, __u64 tail, const uint8_t *const b, Sender *const sender) {
+	// Pick a big size but something smaller than the chunkSize in Sender::writeData which is 100k
+	char buf[1<<16];
+	int writePos = 0;
+	const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+
+	while (head > tail) {
+		writePos = 0;
+		if (!gSessionData->mLocalCapture) {
+			buf[writePos++] = RESPONSE_APC_DATA;
+		}
+		// Reserve space for size
+		writePos += sizeof(uint32_t);
+		Buffer::packInt(buf, sizeof(buf), writePos, FRAME_PERF);
+		Buffer::packInt(buf, sizeof(buf), writePos, cpu);
+
+		while (head > tail) {
+			const int count = reinterpret_cast<const struct perf_event_header *>(b + (tail & BUF_MASK))->size/sizeof(uint64_t);
+			// Can this whole message be written as Streamline assumes events are not split between frames
+			if (sizeof(buf) <= writePos + count*Buffer::MAXSIZE_PACK64) {
+				break;
+			}
+			for (int i = 0; i < count; ++i) {
+				// Must account for message size
+				Buffer::packInt64(buf, sizeof(buf), writePos, *reinterpret_cast<const uint64_t *>(b + (tail & BUF_MASK)));
+				tail += sizeof(uint64_t);
+			}
+		}
+
+		// Write size
+		Buffer::writeLEInt(reinterpret_cast<unsigned char *>(buf + typeLength), writePos - typeLength - sizeof(uint32_t));
+		sender->writeData(buf, writePos, RESPONSE_APC_DATA);
+	}
+}
+
+bool PerfBuffer::send(Sender *const sender) {
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		if (mBuf[cpu] == MAP_FAILED) {
+			continue;
+		}
+
+		// Take a snapshot of the positions
+		struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+		const __u64 head = pemp->data_head;
+		const __u64 tail = pemp->data_tail;
+
+		if (head > tail) {
+			const uint8_t *const b = static_cast<uint8_t *>(mBuf[cpu]) + gSessionData->mPageSize;
+			compressAndSend(cpu, head, tail, b, sender);
+
+			// Update tail with the data read
+			pemp->data_tail = head;
+		}
+
+		if (mDiscard[cpu]) {
+			munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+			mBuf[cpu] = MAP_FAILED;
+			mDiscard[cpu] = false;
+			mFds[cpu] = -1;
+			logg->logMessage("%s(%s:%i): Unmaped cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu);
+		}
+	}
+
+	return true;
+}
diff --git a/tools/gator/daemon/PerfBuffer.h b/tools/gator/daemon/PerfBuffer.h
new file mode 100644
index 000000000000..25a10625a9e8
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.h
@@ -0,0 +1,41 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_BUFFER
+#define PERF_BUFFER
+
+#include "Config.h"
+
+#define BUF_SIZE (gSessionData->mTotalBufferSize * 1024 * 1024)
+#define BUF_MASK (BUF_SIZE - 1)
+
+class Sender;
+
+class PerfBuffer {
+public:
+	PerfBuffer();
+	~PerfBuffer();
+
+	bool useFd(const int cpu, const int fd);
+	void discard(const int cpu);
+	bool isEmpty();
+	bool send(Sender *const sender);
+
+private:
+	void *mBuf[NR_CPUS];
+	// After the buffer is flushed it should be unmaped
+	bool mDiscard[NR_CPUS];
+	// fd that corresponds to the mBuf
+	int mFds[NR_CPUS];
+
+	// Intentionally undefined
+	PerfBuffer(const PerfBuffer &);
+	PerfBuffer &operator=(const PerfBuffer &);
+};
+
+#endif // PERF_BUFFER
diff --git a/tools/gator/daemon/PerfDriver.cpp b/tools/gator/daemon/PerfDriver.cpp
new file mode 100644
index 000000000000..ee90284cee41
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.cpp
@@ -0,0 +1,351 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfDriver.h"
+
+#include <dirent.h>
+#include <sys/utsname.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Config.h"
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfGroup.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+#define PERF_DEVICES "/sys/bus/event_source/devices"
+
+#define TYPE_DERIVED ~0U
+
+// From gator.h
+struct gator_cpu {
+	const int cpuid;
+	// Human readable name
+	const char *const core_name;
+	// gatorfs event and Perf PMU name
+	const char *const pmnc_name;
+	const int pmnc_counters;
+};
+
+// From gator_main.c
+static const struct gator_cpu gator_cpus[] = {
+	{ 0xb36, "ARM1136",      "ARM_ARM11",        3 },
+	{ 0xb56, "ARM1156",      "ARM_ARM11",        3 },
+	{ 0xb76, "ARM1176",      "ARM_ARM11",        3 },
+	{ 0xb02, "ARM11MPCore",  "ARM_ARM11MPCore",  3 },
+	{ 0xc05, "Cortex-A5",    "ARMv7_Cortex_A5",  2 },
+	{ 0xc07, "Cortex-A7",    "ARMv7_Cortex_A7",  4 },
+	{ 0xc08, "Cortex-A8",    "ARMv7_Cortex_A8",  4 },
+	{ 0xc09, "Cortex-A9",    "ARMv7_Cortex_A9",  6 },
+	{ 0xc0f, "Cortex-A15",   "ARMv7_Cortex_A15", 6 },
+	{ 0xc0e, "Cortex-A17",   "ARMv7_Cortex_A17", 6 },
+	{ 0x00f, "Scorpion",     "Scorpion",         4 },
+	{ 0x02d, "ScorpionMP",   "ScorpionMP",       4 },
+	{ 0x049, "KraitSIM",     "Krait",            4 },
+	{ 0x04d, "Krait",        "Krait",            4 },
+	{ 0x06f, "Krait S4 Pro", "Krait",            4 },
+	{ 0xd03, "Cortex-A53",   "ARM_Cortex-A53",   6 },
+	{ 0xd07, "Cortex-A57",   "ARM_Cortex-A57",   6 },
+	{ 0xd0f, "AArch64",      "ARM_AArch64",      6 },
+};
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+struct uncore_counter {
+	// Perf PMU name
+	const char *const perfName;
+	// gatorfs event name
+	const char *const gatorName;
+	const int count;
+};
+
+static const struct uncore_counter uncore_counters[] = {
+	{ "CCI_400", "CCI_400", 4 },
+	{ "CCI_400-r1", "CCI_400-r1", 4 },
+	{ "ccn", "ARM_CCN_5XX", 8 },
+};
+
+class PerfCounter : public DriverCounter {
+public:
+	PerfCounter(DriverCounter *next, const char *name, uint32_t type, uint64_t config, bool perCpu) : DriverCounter(next, name), mType(type), mCount(0), mConfig(config), mPerCpu(perCpu) {}
+
+	~PerfCounter() {
+	}
+
+	uint32_t getType() const { return mType; }
+	int getCount() const { return mCount; }
+	void setCount(const int count) { mCount = count; }
+	uint64_t getConfig() const { return mConfig; }
+	void setConfig(const uint64_t config) { mConfig = config; }
+	bool isPerCpu() const { return mPerCpu; }
+
+private:
+	const uint32_t mType;
+	int mCount;
+	uint64_t mConfig;
+	bool mPerCpu;
+};
+
+PerfDriver::PerfDriver() : mIsSetup(false), mLegacySupport(false) {
+}
+
+PerfDriver::~PerfDriver() {
+}
+
+void PerfDriver::addCpuCounters(const char *const counterName, const int type, const int numCounters) {
+	int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+	char *name = new char[len];
+	snprintf(name, len, "%s_ccnt", counterName);
+	setCounters(new PerfCounter(getCounters(), name, type, -1, true));
+
+	for (int j = 0; j < numCounters; ++j) {
+		len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+		name = new char[len];
+		snprintf(name, len, "%s_cnt%d", counterName, j);
+		setCounters(new PerfCounter(getCounters(), name, type, -1, true));
+	}
+}
+
+void PerfDriver::addUncoreCounters(const char *const counterName, const int type, const int numCounters) {
+	int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+	char *name = new char[len];
+	snprintf(name, len, "%s_ccnt", counterName);
+	setCounters(new PerfCounter(getCounters(), name, type, -1, false));
+
+	for (int j = 0; j < numCounters; ++j) {
+		len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+		name = new char[len];
+		snprintf(name, len, "%s_cnt%d", counterName, j);
+		setCounters(new PerfCounter(getCounters(), name, type, -1, false));
+	}
+}
+
+bool PerfDriver::setup() {
+	// Check the kernel version
+	int release[3];
+	if (!getLinuxVersion(release)) {
+		logg->logMessage("%s(%s:%i): getLinuxVersion failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	if (KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 4, 0)) {
+		logg->logMessage("%s(%s:%i): Unsupported kernel version", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	mLegacySupport = KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 12, 0);
+
+	if (access(EVENTS_PATH, R_OK) != 0) {
+		logg->logMessage("%s(%s:%i): " EVENTS_PATH " does not exist, is CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER enabled?", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	// Add supported PMUs
+	bool foundCpu = false;
+	DIR *dir = opendir(PERF_DEVICES);
+	if (dir == NULL) {
+		logg->logMessage("%s(%s:%i): opendif failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(dir)) != NULL) {
+		for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+			const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+			// Do the names match exactly?
+			if (strcasecmp(gator_cpu->pmnc_name, dirent->d_name) != 0 &&
+			    // Do these names match but have the old vs new prefix?
+			    ((strncasecmp(dirent->d_name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) != 0 ||
+			      strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) != 0 ||
+			      strcasecmp(dirent->d_name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) != 0))) {
+				continue;
+			}
+
+			int type;
+			char buf[256];
+			snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+			if (DriverSource::readIntDriver(buf, &type) != 0) {
+				continue;
+			}
+
+			foundCpu = true;
+			logg->logMessage("Adding cpu counters for %s", gator_cpu->pmnc_name);
+			addCpuCounters(gator_cpu->pmnc_name, type, gator_cpu->pmnc_counters);
+		}
+
+		for (int i = 0; i < ARRAY_LENGTH(uncore_counters); ++i) {
+			if (strcmp(dirent->d_name, uncore_counters[i].perfName) != 0) {
+				continue;
+			}
+
+			int type;
+			char buf[256];
+			snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+			if (DriverSource::readIntDriver(buf, &type) != 0) {
+				continue;
+			}
+
+			logg->logMessage("Adding uncore counters for %s", uncore_counters[i].gatorName);
+			addUncoreCounters(uncore_counters[i].gatorName, type, uncore_counters[i].count);
+		}
+	}
+	closedir(dir);
+
+	if (!foundCpu) {
+		// If no cpu was found based on pmu names, try by cpuid
+		for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+			if (gSessionData->mMaxCpuId != gator_cpus[i].cpuid) {
+				continue;
+			}
+
+			foundCpu = true;
+			logg->logMessage("Adding cpu counters (based on cpuid) for %s", gator_cpus[i].pmnc_name);
+			addCpuCounters(gator_cpus[i].pmnc_name, PERF_TYPE_RAW, gator_cpus[i].pmnc_counters);
+		}
+	}
+
+	/*
+	if (!foundCpu) {
+		// If all else fails, use the perf architected counters
+		// 9 because that's how many are in events-Perf-Hardware.xml - assume they can all be enabled at once
+		addCpuCounters("Perf_Hardware", PERF_TYPE_HARDWARE, 9);
+	}
+	*/
+
+	// Add supported software counters
+	long long id;
+	DynBuf printb;
+
+	id = getTracepointId("irq/softirq_exit", &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_irq_softirq", PERF_TYPE_TRACEPOINT, id, true));
+	}
+
+	id = getTracepointId("irq/irq_handler_exit", &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_irq_irq", PERF_TYPE_TRACEPOINT, id, true));
+	}
+
+	id = getTracepointId(SCHED_SWITCH, &printb);
+	if (id >= 0) {
+		setCounters(new PerfCounter(getCounters(), "Linux_sched_switch", PERF_TYPE_TRACEPOINT, id, true));
+	}
+
+	setCounters(new PerfCounter(getCounters(), "Linux_cpu_wait_contention", TYPE_DERIVED, -1, false));
+
+	//Linux_cpu_wait_io
+
+	mIsSetup = true;
+	return true;
+}
+
+bool PerfDriver::summary(Buffer *const buffer) {
+	struct utsname utsname;
+	if (uname(&utsname) != 0) {
+		logg->logMessage("%s(%s:%i): uname failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	char buf[512];
+	snprintf(buf, sizeof(buf), "%s %s %s %s %s GNU/Linux", utsname.sysname, utsname.nodename, utsname.release, utsname.version, utsname.machine);
+
+	struct timespec ts;
+	if (clock_gettime(CLOCK_REALTIME, &ts) != 0) {
+		logg->logMessage("%s(%s:%i): clock_gettime failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	const int64_t timestamp = (int64_t)ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+	const uint64_t monotonicStarted = getTime();
+	gSessionData->mMonotonicStarted = monotonicStarted;
+
+	buffer->summary(monotonicStarted, timestamp, monotonicStarted, monotonicStarted, buf);
+
+	for (int i = 0; i < gSessionData->mCores; ++i) {
+		coreName(monotonicStarted, buffer, i);
+	}
+	buffer->commit(monotonicStarted);
+
+	return true;
+}
+
+void PerfDriver::coreName(const uint32_t startTime, Buffer *const buffer, const int cpu) {
+	// Don't send information on a cpu we know nothing about
+	if (gSessionData->mCpuIds[cpu] == -1) {
+		return;
+	}
+
+	int j;
+	for (j = 0; j < ARRAY_LENGTH(gator_cpus); ++j) {
+		if (gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) {
+			break;
+		}
+	}
+	if (gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) {
+		buffer->coreName(startTime, cpu, gSessionData->mCpuIds[cpu], gator_cpus[j].core_name);
+	} else {
+		char buf[32];
+		if (gSessionData->mCpuIds[cpu] == -1) {
+			snprintf(buf, sizeof(buf), "Unknown");
+		} else {
+			snprintf(buf, sizeof(buf), "Unknown (0x%.3x)", gSessionData->mCpuIds[cpu]);
+		}
+		buffer->coreName(startTime, cpu, gSessionData->mCpuIds[cpu], buf);
+	}
+}
+
+void PerfDriver::setupCounter(Counter &counter) {
+	PerfCounter *const perfCounter = static_cast<PerfCounter *>(findCounter(counter));
+	if (perfCounter == NULL) {
+		counter.setEnabled(false);
+		return;
+	}
+
+	// Don't use the config from counters XML if it's not set, ex: software counters
+	if (counter.getEvent() != -1) {
+		perfCounter->setConfig(counter.getEvent());
+	}
+	perfCounter->setCount(counter.getCount());
+	perfCounter->setEnabled(true);
+	counter.setKey(perfCounter->getKey());
+}
+
+bool PerfDriver::enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const {
+	for (PerfCounter *counter = static_cast<PerfCounter *>(getCounters()); counter != NULL; counter = static_cast<PerfCounter *>(counter->getNext())) {
+		if (counter->isEnabled() && (counter->getType() != TYPE_DERIVED)) {
+			if (!group->add(currTime, buffer, counter->getKey(), counter->getType(), counter->getConfig(), counter->getCount(), counter->getCount() > 0 ? PERF_SAMPLE_TID | PERF_SAMPLE_IP : 0, counter->isPerCpu() ? PERF_GROUP_PER_CPU : 0)) {
+				logg->logMessage("%s(%s:%i): PerfGroup::add failed", __FUNCTION__, __FILE__, __LINE__);
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
+long long PerfDriver::getTracepointId(const char *const name, DynBuf *const printb) {
+	if (!printb->printf(EVENTS_PATH "/%s/id", name)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return -1;
+	}
+
+	int64_t result;
+	if (DriverSource::readInt64Driver(printb->getBuf(), &result) != 0) {
+		logg->logMessage("%s(%s:%i): DriverSource::readInt64Driver failed", __FUNCTION__, __FILE__, __LINE__);
+		return -1;
+	}
+
+	return result;
+}
diff --git a/tools/gator/daemon/PerfDriver.h b/tools/gator/daemon/PerfDriver.h
new file mode 100644
index 000000000000..846203a9e18b
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.h
@@ -0,0 +1,57 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFDRIVER_H
+#define PERFDRIVER_H
+
+#include <stdint.h>
+
+#include "Driver.h"
+
+// If debugfs is not mounted at /sys/kernel/debug, update DEBUGFS_PATH
+#define DEBUGFS_PATH "/sys/kernel/debug"
+#define EVENTS_PATH DEBUGFS_PATH "/tracing/events"
+
+#define SCHED_SWITCH "sched/sched_switch"
+#define CPU_IDLE "power/cpu_idle"
+
+class Buffer;
+class DynBuf;
+class PerfGroup;
+
+class PerfDriver : public SimpleDriver {
+public:
+	PerfDriver();
+	~PerfDriver();
+
+	bool getLegacySupport() const { return mLegacySupport; }
+
+	bool setup();
+	bool summary(Buffer *const buffer);
+	void coreName(const uint32_t startTime, Buffer *const buffer, const int cpu);
+	bool isSetup() const { return mIsSetup; }
+
+	void setupCounter(Counter &counter);
+
+	bool enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const;
+
+	static long long getTracepointId(const char *const name, DynBuf *const printb);
+
+private:
+	void addCpuCounters(const char *const counterName, const int type, const int numCounters);
+	void addUncoreCounters(const char *const counterName, const int type, const int numCounters);
+
+	bool mIsSetup;
+	bool mLegacySupport;
+
+	// Intentionally undefined
+	PerfDriver(const PerfDriver &);
+	PerfDriver &operator=(const PerfDriver &);
+};
+
+#endif // PERFDRIVER_H
diff --git a/tools/gator/daemon/PerfGroup.cpp b/tools/gator/daemon/PerfGroup.cpp
new file mode 100644
index 000000000000..4fd960a9058c
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.cpp
@@ -0,0 +1,244 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfGroup.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "SessionData.h"
+
+#define DEFAULT_PEA_ARGS(pea, additionalSampleType) \
+	pea.size = sizeof(pea); \
+	/* Emit time, read_format below, group leader id, and raw tracepoint info */ \
+	pea.sample_type = (gSessionData->perf.getLegacySupport() \
+										 ? PERF_SAMPLE_TID | PERF_SAMPLE_IP | PERF_SAMPLE_TIME | PERF_SAMPLE_READ | PERF_SAMPLE_ID \
+										 : PERF_SAMPLE_TIME | PERF_SAMPLE_READ | PERF_SAMPLE_IDENTIFIER ) | additionalSampleType; \
+	/* Emit emit value in group format */ \
+	pea.read_format = PERF_FORMAT_ID | PERF_FORMAT_GROUP; \
+	/* start out disabled */ \
+	pea.disabled = 1; \
+	/* have a sampling interrupt happen when we cross the wakeup_watermark boundary */ \
+	pea.watermark = 1; \
+	/* Be conservative in flush size as only one buffer set is monitored */ \
+	pea.wakeup_watermark = BUF_SIZE / 2
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+	int fd = syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+	if (fd < 0) {
+		return -1;
+	}
+	int fdf = fcntl(fd, F_GETFD);
+	if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		close(fd);
+		return -1;
+	}
+	return fd;
+}
+
+PerfGroup::PerfGroup(PerfBuffer *const pb) : mPb(pb) {
+	memset(&mAttrs, 0, sizeof(mAttrs));
+	memset(&mPerCpu, 0, sizeof(mPerCpu));
+	memset(&mKeys, -1, sizeof(mKeys));
+	memset(&mFds, -1, sizeof(mFds));
+}
+
+PerfGroup::~PerfGroup() {
+	for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+		if (mFds[pos] >= 0) {
+			close(mFds[pos]);
+		}
+	}
+}
+
+bool PerfGroup::add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) {
+	int i;
+	for (i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			break;
+		}
+	}
+
+	if (i >= ARRAY_LENGTH(mKeys)) {
+		logg->logMessage("%s(%s:%i): Too many counters", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	DEFAULT_PEA_ARGS(mAttrs[i], sampleType);
+	mAttrs[i].type = type;
+	mAttrs[i].config = config;
+	mAttrs[i].sample_period = sample;
+	// always be on the CPU but only a group leader can be pinned
+	mAttrs[i].pinned = (i == 0 ? 1 : 0);
+	mAttrs[i].mmap = (flags & PERF_GROUP_MMAP ? 1 : 0);
+	mAttrs[i].comm = (flags & PERF_GROUP_COMM ? 1 : 0);
+	mAttrs[i].freq = (flags & PERF_GROUP_FREQ ? 1 : 0);
+	mAttrs[i].task = (flags & PERF_GROUP_TASK ? 1 : 0);
+	mAttrs[i].sample_id_all = (flags & PERF_GROUP_SAMPLE_ID_ALL ? 1 : 0);
+	mPerCpu[i] = (flags & PERF_GROUP_PER_CPU);
+
+	mKeys[i] = key;
+
+	buffer->pea(currTime, &mAttrs[i], key);
+
+	return true;
+}
+
+int PerfGroup::prepareCPU(const int cpu, Monitor *const monitor) {
+	logg->logMessage("%s(%s:%i): Onlining cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu);
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			continue;
+		}
+
+		if ((cpu != 0) && !mPerCpu[i]) {
+			continue;
+		}
+
+		const int offset = i * gSessionData->mCores;
+		if (mFds[cpu + offset] >= 0) {
+			logg->logMessage("%s(%s:%i): cpu already online or not correctly cleaned up", __FUNCTION__, __FILE__, __LINE__);
+			return PG_FAILURE;
+		}
+
+		logg->logMessage("%s(%s:%i): perf_event_open cpu: %i type: %lli config: %lli sample: %lli sample_type: 0x%llx pinned: %i mmap: %i comm: %i freq: %i task: %i sample_id_all: %i", __FUNCTION__, __FILE__, __LINE__, cpu, (long long)mAttrs[i].type, (long long)mAttrs[i].config, (long long)mAttrs[i].sample_period, (long long)mAttrs[i].sample_type, mAttrs[i].pinned, mAttrs[i].mmap, mAttrs[i].comm, mAttrs[i].freq, mAttrs[i].task, mAttrs[i].sample_id_all);
+		mFds[cpu + offset] = sys_perf_event_open(&mAttrs[i], -1, cpu, i == 0 ? -1 : mFds[cpu], i == 0 ? 0 : PERF_FLAG_FD_OUTPUT);
+		if (mFds[cpu + offset] < 0) {
+			logg->logMessage("%s(%s:%i): failed %s", __FUNCTION__, __FILE__, __LINE__, strerror(errno));
+			if (errno == ENODEV) {
+				return PG_CPU_OFFLINE;
+			}
+			continue;
+		}
+
+		if (!mPb->useFd(cpu, mFds[cpu + offset])) {
+			logg->logMessage("%s(%s:%i): PerfBuffer::useFd failed", __FUNCTION__, __FILE__, __LINE__);
+			return PG_FAILURE;
+		}
+
+
+		if (!monitor->add(mFds[cpu + offset])) {
+		  logg->logMessage("%s(%s:%i): Monitor::add failed", __FUNCTION__, __FILE__, __LINE__);
+		  return PG_FAILURE;
+		}
+	}
+
+	return PG_SUCCESS;
+}
+
+int PerfGroup::onlineCPU(const uint64_t currTime, const int cpu, const bool start, Buffer *const buffer) {
+	__u64 ids[ARRAY_LENGTH(mKeys)];
+	int coreKeys[ARRAY_LENGTH(mKeys)];
+	int idCount = 0;
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		const int fd = mFds[cpu + i * gSessionData->mCores];
+		if (fd < 0) {
+			continue;
+		}
+
+		coreKeys[idCount] = mKeys[i];
+		if (!gSessionData->perf.getLegacySupport() && ioctl(fd, PERF_EVENT_IOC_ID, &ids[idCount]) != 0 &&
+				// Workaround for running 32-bit gatord on 64-bit systems, kernel patch in the works
+				ioctl(fd, (PERF_EVENT_IOC_ID & ~IOCSIZE_MASK) | (8 << _IOC_SIZESHIFT), &ids[idCount]) != 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			return 0;
+		}
+		++idCount;
+	}
+
+	if (!gSessionData->perf.getLegacySupport()) {
+		buffer->keys(currTime, idCount, ids, coreKeys);
+	} else {
+		char buf[1024];
+		ssize_t bytes = read(mFds[cpu], buf, sizeof(buf));
+		if (bytes < 0) {
+			logg->logMessage("read failed");
+			return 0;
+		}
+		buffer->keysOld(currTime, idCount, coreKeys, bytes, buf);
+	}
+
+	if (start) {
+		for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+			int offset = i * gSessionData->mCores + cpu;
+			if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+				logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+				return 0;
+			}
+		}
+	}
+
+	if (idCount == 0) {
+		logg->logMessage("%s(%s:%i): no events came online", __FUNCTION__, __FILE__, __LINE__);
+	}
+
+	return idCount;
+}
+
+bool PerfGroup::offlineCPU(const int cpu) {
+	logg->logMessage("%s(%s:%i): Offlining cpu %i", __FUNCTION__, __FILE__, __LINE__, cpu);
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		int offset = i * gSessionData->mCores + cpu;
+		if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_DISABLE, 0) < 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+	}
+
+	// Mark the buffer so that it will be released next time it's read
+	mPb->discard(cpu);
+
+	for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+		if (mKeys[i] < 0) {
+			continue;
+		}
+
+		int offset = i * gSessionData->mCores + cpu;
+		if (mFds[offset] >= 0) {
+			close(mFds[offset]);
+			mFds[offset] = -1;
+		}
+	}
+
+	return true;
+}
+
+bool PerfGroup::start() {
+	for (int pos = 0; pos < ARRAY_LENGTH(mFds); ++pos) {
+		if (mFds[pos] >= 0 && ioctl(mFds[pos], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+			logg->logMessage("%s(%s:%i): ioctl failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+	}
+
+	return true;
+
+ fail:
+	stop();
+
+	return false;
+}
+
+void PerfGroup::stop() {
+	for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+		if (mFds[pos] >= 0) {
+			ioctl(mFds[pos], PERF_EVENT_IOC_DISABLE, 0);
+		}
+	}
+}
diff --git a/tools/gator/daemon/PerfGroup.h b/tools/gator/daemon/PerfGroup.h
new file mode 100644
index 000000000000..f7b3d725bac7
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.h
@@ -0,0 +1,65 @@
+ /**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_GROUP
+#define PERF_GROUP
+
+#include <stdint.h>
+
+// Use a snapshot of perf_event.h as it may be more recent than what is on the target and if not newer features won't be supported anyways
+#include "k/perf_event.h"
+
+#include "Config.h"
+
+class Buffer;
+class Monitor;
+class PerfBuffer;
+
+enum PerfGroupFlags {
+	PERF_GROUP_MMAP          = 1 << 0,
+	PERF_GROUP_COMM          = 1 << 1,
+	PERF_GROUP_FREQ          = 1 << 2,
+	PERF_GROUP_TASK          = 1 << 3,
+	PERF_GROUP_SAMPLE_ID_ALL = 1 << 4,
+	PERF_GROUP_PER_CPU       = 1 << 5,
+};
+
+enum {
+	PG_SUCCESS = 0,
+	PG_FAILURE,
+	PG_CPU_OFFLINE,
+};
+
+class PerfGroup {
+public:
+	PerfGroup(PerfBuffer *const pb);
+	~PerfGroup();
+
+	bool add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags);
+	// Safe to call concurrently
+	int prepareCPU(const int cpu, Monitor *const monitor);
+	// Not safe to call concurrently. Returns the number of events enabled
+	int onlineCPU(const uint64_t currTime, const int cpu, const bool start, Buffer *const buffer);
+	bool offlineCPU(int cpu);
+	bool start();
+	void stop();
+
+private:
+	// +1 for the group leader
+	struct perf_event_attr mAttrs[MAX_PERFORMANCE_COUNTERS + 1];
+	bool mPerCpu[MAX_PERFORMANCE_COUNTERS + 1];
+	int mKeys[MAX_PERFORMANCE_COUNTERS + 1];
+	int mFds[NR_CPUS * (MAX_PERFORMANCE_COUNTERS + 1)];
+	PerfBuffer *const mPb;
+
+	// Intentionally undefined
+	PerfGroup(const PerfGroup &);
+	PerfGroup &operator=(const PerfGroup &);
+};
+
+#endif // PERF_GROUP
diff --git a/tools/gator/daemon/PerfSource.cpp b/tools/gator/daemon/PerfSource.cpp
new file mode 100644
index 000000000000..193b7789a290
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.cpp
@@ -0,0 +1,449 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfSource.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfDriver.h"
+#include "Proc.h"
+#include "SessionData.h"
+
+#ifndef SCHED_RESET_ON_FORK
+#define SCHED_RESET_ON_FORK 0x40000000
+#endif
+
+extern Child *child;
+
+static bool sendTracepointFormat(const uint64_t currTime, Buffer *const buffer, const char *const name, DynBuf *const printb, DynBuf *const b) {
+	if (!printb->printf(EVENTS_PATH "/%s/format", name)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	if (!b->read(printb->getBuf())) {
+		logg->logMessage("%s(%s:%i): DynBuf::read failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	buffer->format(currTime, b->getLength(), b->getBuf());
+
+	return true;
+}
+
+static void *syncFunc(void *arg)
+{
+	struct timespec ts;
+	int64_t nextTime = gSessionData->mMonotonicStarted;
+	int err;
+	(void)arg;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-sync", 0, 0, 0);
+
+	// Mask all signals so that this thread will not be woken up
+	{
+		sigset_t set;
+		if (sigfillset(&set) != 0) {
+			logg->logError(__FILE__, __LINE__, "sigfillset failed");
+			handleException();
+		}
+		if ((err = pthread_sigmask(SIG_SETMASK, &set, NULL)) != 0) {
+			logg->logError(__FILE__, __LINE__, "pthread_sigmask failed");
+			handleException();
+		}
+	}
+
+	for (;;) {
+		if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+			logg->logError(__FILE__, __LINE__, "clock_gettime failed");
+			handleException();
+		}
+		const int64_t currTime = ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+		// Wake up once a second
+		nextTime += NS_PER_S;
+
+		// Always sleep more than 1 ms, hopefully things will line up better next time
+		const int64_t sleepTime = max(nextTime - currTime, (int64_t)(NS_PER_MS + 1));
+		ts.tv_sec = sleepTime/NS_PER_S;
+		ts.tv_nsec = sleepTime % NS_PER_S;
+
+		err = nanosleep(&ts, NULL);
+		if (err != 0) {
+			fprintf(stderr, "clock_nanosleep failed: %s\n", strerror(err));
+			return NULL;
+		}
+	}
+
+	return NULL;
+}
+
+static long getMaxCoreNum() {
+	DIR *dir = opendir("/sys/devices/system/cpu");
+	if (dir == NULL) {
+		logg->logError(__FILE__, __LINE__, "Unable to determine the number of cores on the target, opendir failed");
+		handleException();
+	}
+
+	long maxCoreNum = -1;
+	struct dirent *dirent;
+	while ((dirent = readdir(dir)) != NULL) {
+		if (strncmp(dirent->d_name, "cpu", 3) == 0) {
+			char *endptr;
+			errno = 0;
+			long coreNum = strtol(dirent->d_name + 3, &endptr, 10);
+			if ((errno == 0) && (*endptr == '\0') && (coreNum >= maxCoreNum)) {
+				maxCoreNum = coreNum + 1;
+			}
+		}
+	}
+	closedir(dir);
+
+	if (maxCoreNum < 1) {
+		logg->logError(__FILE__, __LINE__, "Unable to determine the number of cores on the target, no cpu# directories found");
+		handleException();
+	}
+
+	if (maxCoreNum >= NR_CPUS) {
+		logg->logError(__FILE__, __LINE__, "Too many cores on the target, please increase NR_CPUS in Config.h");
+		handleException();
+	}
+
+	return maxCoreNum;
+}
+
+PerfSource::PerfSource(sem_t *senderSem, sem_t *startProfile) : mSummary(0, FRAME_SUMMARY, 1024, senderSem), mBuffer(0, FRAME_PERF_ATTRS, 1024*1024, senderSem), mCountersBuf(), mCountersGroup(&mCountersBuf), mIdleGroup(&mCountersBuf), mMonitor(), mUEvent(), mSenderSem(senderSem), mStartProfile(startProfile), mInterruptFd(-1), mIsDone(false) {
+	long l = sysconf(_SC_PAGE_SIZE);
+	if (l < 0) {
+		logg->logError(__FILE__, __LINE__, "Unable to obtain the page size");
+		handleException();
+	}
+	gSessionData->mPageSize = static_cast<int>(l);
+	gSessionData->mCores = static_cast<int>(getMaxCoreNum());
+}
+
+PerfSource::~PerfSource() {
+}
+
+bool PerfSource::prepare() {
+	DynBuf printb;
+	DynBuf b1;
+	long long schedSwitchId;
+	long long cpuIdleId;
+
+	const uint64_t currTime = getTime();
+
+	// Reread cpuinfo since cores may have changed since startup
+	gSessionData->readCpuInfo();
+
+	if (0
+			|| !mMonitor.init()
+			|| !mUEvent.init()
+			|| !mMonitor.add(mUEvent.getFd())
+
+			|| (schedSwitchId = PerfDriver::getTracepointId(SCHED_SWITCH, &printb)) < 0
+			|| !sendTracepointFormat(currTime, &mBuffer, SCHED_SWITCH, &printb, &b1)
+
+			|| (cpuIdleId = PerfDriver::getTracepointId(CPU_IDLE, &printb)) < 0
+			|| !sendTracepointFormat(currTime, &mBuffer, CPU_IDLE, &printb, &b1)
+
+			// Only want RAW but not IP on sched_switch and don't want TID on SAMPLE_ID
+			|| !mCountersGroup.add(currTime, &mBuffer, 100/**/, PERF_TYPE_TRACEPOINT, schedSwitchId, 1, PERF_SAMPLE_RAW, PERF_GROUP_MMAP | PERF_GROUP_COMM | PERF_GROUP_TASK | PERF_GROUP_SAMPLE_ID_ALL | PERF_GROUP_PER_CPU)
+			|| !mIdleGroup.add(currTime, &mBuffer, 101/**/, PERF_TYPE_TRACEPOINT, cpuIdleId, 1, PERF_SAMPLE_RAW, PERF_GROUP_PER_CPU)
+
+			// Only want TID and IP but not RAW on timer
+			|| (gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS && !mCountersGroup.add(currTime, &mBuffer, 102/**/, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, 1000000000UL / gSessionData->mSampleRate, PERF_SAMPLE_TID | PERF_SAMPLE_IP, PERF_GROUP_PER_CPU))
+
+			|| !gSessionData->perf.enable(currTime, &mCountersGroup, &mBuffer)
+			|| 0) {
+		logg->logMessage("%s(%s:%i): perf setup failed, are you running Linux 3.4 or later?", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		const int result = mCountersGroup.prepareCPU(cpu, &mMonitor);
+		if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) {
+			logg->logError(__FILE__, __LINE__, "PerfGroup::prepareCPU on mCountersGroup failed");
+			handleException();
+		}
+	}
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		const int result = mIdleGroup.prepareCPU(cpu, &mMonitor);
+		if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) {
+			logg->logError(__FILE__, __LINE__, "PerfGroup::prepareCPU on mIdleGroup failed");
+			handleException();
+		}
+	}
+
+	int numEvents = 0;
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		numEvents += mCountersGroup.onlineCPU(currTime, cpu, false, &mBuffer);
+	}
+	for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+		numEvents += mIdleGroup.onlineCPU(currTime, cpu, false, &mBuffer);
+	}
+	if (numEvents <= 0) {
+		logg->logMessage("%s(%s:%i): PerfGroup::onlineCPU failed on all cores", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	// Send the summary right before the start so that the monotonic delta is close to the start time
+	if (!gSessionData->perf.summary(&mSummary)) {
+	  logg->logError(__FILE__, __LINE__, "PerfDriver::summary failed", __FUNCTION__, __FILE__, __LINE__);
+	  handleException();
+	}
+
+	// Start the timer thread to used to sync perf and monotonic raw times
+	pthread_t syncThread;
+	if (pthread_create(&syncThread, NULL, syncFunc, NULL)) {
+	  logg->logError(__FILE__, __LINE__, "pthread_create failed", __FUNCTION__, __FILE__, __LINE__);
+	  handleException();
+	}
+	struct sched_param param;
+	param.sched_priority = sched_get_priority_max(SCHED_FIFO);
+	if (pthread_setschedparam(syncThread, SCHED_FIFO | SCHED_RESET_ON_FORK, &param) != 0) {
+	  logg->logError(__FILE__, __LINE__, "pthread_setschedparam failed");
+	  handleException();
+	}
+
+	mBuffer.commit(currTime);
+
+	return true;
+}
+
+struct ProcThreadArgs {
+	Buffer *mBuffer;
+	uint64_t mCurrTime;
+	bool mIsDone;
+};
+
+void *procFunc(void *arg) {
+	DynBuf printb;
+	DynBuf b;
+	const ProcThreadArgs *const args = (ProcThreadArgs *)arg;
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+	// Gator runs at a high priority, reset the priority to the default
+	if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+		logg->logError(__FILE__, __LINE__, "setpriority failed");
+		handleException();
+	}
+
+	if (!readProcMaps(args->mCurrTime, args->mBuffer, &printb, &b)) {
+		logg->logError(__FILE__, __LINE__, "readProcMaps failed");
+		handleException();
+	}
+	args->mBuffer->commit(args->mCurrTime);
+
+	if (!readKallsyms(args->mCurrTime, args->mBuffer, &args->mIsDone)) {
+		logg->logError(__FILE__, __LINE__, "readKallsyms failed");
+		handleException();
+	}
+	args->mBuffer->commit(args->mCurrTime);
+
+	return NULL;
+}
+
+static const char CPU_DEVPATH[] = "/devices/system/cpu/cpu";
+
+void PerfSource::run() {
+	int pipefd[2];
+	pthread_t procThread;
+	ProcThreadArgs procThreadArgs;
+
+	{
+		DynBuf printb;
+		DynBuf b1;
+		DynBuf b2;
+
+		const uint64_t currTime = getTime();
+
+		// Start events before reading proc to avoid race conditions
+		if (!mCountersGroup.start() || !mIdleGroup.start()) {
+			logg->logError(__FILE__, __LINE__, "PerfGroup::start failed", __FUNCTION__, __FILE__, __LINE__);
+			handleException();
+		}
+
+		if (!readProcComms(currTime, &mBuffer, &printb, &b1, &b2)) {
+			logg->logError(__FILE__, __LINE__, "readProcComms failed");
+			handleException();
+		}
+		mBuffer.commit(currTime);
+
+		// Postpone reading kallsyms as on android adb gets too backed up and data is lost
+		procThreadArgs.mBuffer = &mBuffer;
+		procThreadArgs.mCurrTime = currTime;
+		procThreadArgs.mIsDone = false;
+		if (pthread_create(&procThread, NULL, procFunc, &procThreadArgs)) {
+			logg->logError(__FILE__, __LINE__, "pthread_create failed", __FUNCTION__, __FILE__, __LINE__);
+			handleException();
+		}
+	}
+
+	if (pipe_cloexec(pipefd) != 0) {
+		logg->logError(__FILE__, __LINE__, "pipe failed");
+		handleException();
+	}
+	mInterruptFd = pipefd[1];
+
+	if (!mMonitor.add(pipefd[0])) {
+		logg->logError(__FILE__, __LINE__, "Monitor::add failed");
+		handleException();
+	}
+
+	int timeout = -1;
+	if (gSessionData->mLiveRate > 0) {
+		timeout = gSessionData->mLiveRate/NS_PER_MS;
+	}
+
+	sem_post(mStartProfile);
+
+	while (gSessionData->mSessionIsActive) {
+		// +1 for uevents, +1 for pipe
+		struct epoll_event events[NR_CPUS + 2];
+		int ready = mMonitor.wait(events, ARRAY_LENGTH(events), timeout);
+		if (ready < 0) {
+			logg->logError(__FILE__, __LINE__, "Monitor::wait failed");
+			handleException();
+		}
+		const uint64_t currTime = getTime();
+
+		for (int i = 0; i < ready; ++i) {
+			if (events[i].data.fd == mUEvent.getFd()) {
+				if (!handleUEvent(currTime)) {
+					logg->logError(__FILE__, __LINE__, "PerfSource::handleUEvent failed");
+					handleException();
+				}
+				break;
+			}
+		}
+
+		// send a notification that data is ready
+		sem_post(mSenderSem);
+
+		// In one shot mode, stop collection once all the buffers are filled
+		// Assume timeout == 0 in this case
+		if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+			logg->logMessage("%s(%s:%i): One shot", __FUNCTION__, __FILE__, __LINE__);
+			child->endSession();
+		}
+	}
+
+	procThreadArgs.mIsDone = true;
+	pthread_join(procThread, NULL);
+	mIdleGroup.stop();
+	mCountersGroup.stop();
+	mBuffer.setDone();
+	mIsDone = true;
+
+	// send a notification that data is ready
+	sem_post(mSenderSem);
+
+	mInterruptFd = -1;
+	close(pipefd[0]);
+	close(pipefd[1]);
+}
+
+bool PerfSource::handleUEvent(const uint64_t currTime) {
+	UEventResult result;
+	if (!mUEvent.read(&result)) {
+		logg->logMessage("%s(%s:%i): UEvent::Read failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	if (strcmp(result.mSubsystem, "cpu") == 0) {
+		if (strncmp(result.mDevPath, CPU_DEVPATH, sizeof(CPU_DEVPATH) - 1) != 0) {
+			logg->logMessage("%s(%s:%i): Unexpected cpu DEVPATH format", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+		char *endptr;
+		errno = 0;
+		int cpu = strtol(result.mDevPath + sizeof(CPU_DEVPATH) - 1, &endptr, 10);
+		if (errno != 0 || *endptr != '\0') {
+			logg->logMessage("%s(%s:%i): strtol failed", __FUNCTION__, __FILE__, __LINE__);
+			return false;
+		}
+
+		if (cpu >= gSessionData->mCores) {
+			logg->logError(__FILE__, __LINE__, "Only %i cores are expected but core %i reports %s", gSessionData->mCores, cpu, result.mAction);
+			handleException();
+		}
+
+		if (strcmp(result.mAction, "online") == 0) {
+			mBuffer.onlineCPU(currTime, currTime - gSessionData->mMonotonicStarted, cpu);
+			// Only call onlineCPU if prepareCPU succeeded
+			bool result = false;
+			int err = mCountersGroup.prepareCPU(cpu, &mMonitor);
+			if (err == PG_CPU_OFFLINE) {
+				result = true;
+			} else if (err == PG_SUCCESS) {
+				if (mCountersGroup.onlineCPU(currTime, cpu, true, &mBuffer)) {
+					err = mIdleGroup.prepareCPU(cpu, &mMonitor);
+					if (err == PG_CPU_OFFLINE) {
+						result = true;
+					} else if (err == PG_SUCCESS) {
+						if (mIdleGroup.onlineCPU(currTime, cpu, true, &mBuffer)) {
+							result = true;
+						}
+					}
+				}
+			}
+			mBuffer.commit(currTime);
+
+			gSessionData->readCpuInfo();
+			gSessionData->perf.coreName(currTime, &mSummary, cpu);
+			mSummary.commit(currTime);
+			return result;
+		} else if (strcmp(result.mAction, "offline") == 0) {
+			const bool result = mCountersGroup.offlineCPU(cpu) && mIdleGroup.offlineCPU(cpu);
+			mBuffer.offlineCPU(currTime, currTime - gSessionData->mMonotonicStarted, cpu);
+			return result;
+		}
+	}
+
+	return true;
+}
+
+void PerfSource::interrupt() {
+	if (mInterruptFd >= 0) {
+		int8_t c = 0;
+		// Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+		if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+			logg->logError(__FILE__, __LINE__, "write failed");
+			handleException();
+		}
+	}
+}
+
+bool PerfSource::isDone () {
+	return mBuffer.isDone() && mIsDone && mCountersBuf.isEmpty();
+}
+
+void PerfSource::write (Sender *sender) {
+	if (!mSummary.isDone()) {
+		mSummary.write(sender);
+		gSessionData->mSentSummary = true;
+	}
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+	}
+	if (!mCountersBuf.send(sender)) {
+		logg->logError(__FILE__, __LINE__, "PerfBuffer::send failed");
+		handleException();
+	}
+}
diff --git a/tools/gator/daemon/PerfSource.h b/tools/gator/daemon/PerfSource.h
new file mode 100644
index 000000000000..ce1eafe8e953
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.h
@@ -0,0 +1,55 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFSOURCE_H
+#define PERFSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "PerfGroup.h"
+#include "Source.h"
+#include "UEvent.h"
+
+class Sender;
+
+class PerfSource : public Source {
+public:
+	PerfSource(sem_t *senderSem, sem_t *startProfile);
+	~PerfSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	bool handleUEvent(const uint64_t currTime);
+
+	Buffer mSummary;
+	Buffer mBuffer;
+	PerfBuffer mCountersBuf;
+	PerfGroup mCountersGroup;
+	PerfGroup mIdleGroup;
+	Monitor mMonitor;
+	UEvent mUEvent;
+	sem_t *const mSenderSem;
+	sem_t *const mStartProfile;
+	int mInterruptFd;
+	bool mIsDone;
+
+	// Intentionally undefined
+	PerfSource(const PerfSource &);
+	PerfSource &operator=(const PerfSource &);
+};
+
+#endif // PERFSOURCE_H
diff --git a/tools/gator/daemon/Proc.cpp b/tools/gator/daemon/Proc.cpp
new file mode 100644
index 000000000000..e6b26b1199fa
--- /dev/null
+++ b/tools/gator/daemon/Proc.cpp
@@ -0,0 +1,312 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Proc.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+struct ProcStat {
+	// From linux-dev/include/linux/sched.h
+#define TASK_COMM_LEN 16
+	// TASK_COMM_LEN may grow, so be ready for it to get larger
+	char comm[2*TASK_COMM_LEN];
+	long numThreads;
+};
+
+static bool readProcStat(ProcStat *const ps, const char *const pathname, DynBuf *const b) {
+	if (!b->read(pathname)) {
+		logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the thread exited", __FUNCTION__, __FILE__, __LINE__);
+		// This is not a fatal error - the thread just doesn't exist any more
+		return true;
+	}
+
+	char *comm = strchr(b->getBuf(), '(');
+	if (comm == NULL) {
+		logg->logMessage("%s(%s:%i): parsing stat failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	++comm;
+	char *const str = strrchr(comm, ')');
+	if (str == NULL) {
+		logg->logMessage("%s(%s:%i): parsing stat failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+	*str = '\0';
+	strncpy(ps->comm, comm, sizeof(ps->comm) - 1);
+	ps->comm[sizeof(ps->comm) - 1] = '\0';
+
+	const int count = sscanf(str + 2, " %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %ld", &ps->numThreads);
+	if (count != 1) {
+		logg->logMessage("%s(%s:%i): sscanf failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	return true;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static const char *readProcExe(DynBuf *const printb, const int pid, const int tid, DynBuf *const b) {
+	if (tid == -1 ? !printb->printf("/proc/%i/exe", pid)
+			: !printb->printf("/proc/%i/task/%i/exe", pid, tid)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	const int err = b->readlink(printb->getBuf());
+	const char *image;
+	if (err == 0) {
+		image = strrchr(b->getBuf(), '/');
+		if (image == NULL) {
+			image = b->getBuf();
+		} else {
+			++image;
+		}
+	} else if (err == -ENOENT) {
+		// readlink /proc/[pid]/exe returns ENOENT for kernel threads
+		image = "\0";
+	} else {
+		logg->logMessage("%s(%s:%i): DynBuf::readlink failed", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	// Android apps are run by app_process but the cmdline is changed to reference the actual app name
+	// On 64-bit android app_process can be app_process32 or app_process64
+	if (strncmp(image, APP_PROCESS, sizeof(APP_PROCESS) - 1) != 0) {
+		return image;
+	}
+
+	if (tid == -1 ? !printb->printf("/proc/%i/cmdline", pid)
+			: !printb->printf("/proc/%i/task/%i/cmdline", pid, tid)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	if (!b->read(printb->getBuf())) {
+		logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the thread exited", __FUNCTION__, __FILE__, __LINE__);
+		return NULL;
+	}
+
+	return b->getBuf();
+}
+
+static bool readProcTask(const uint64_t currTime, Buffer *const buffer, const int pid, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+	bool result = false;
+
+	if (!b1->printf("/proc/%i/task", pid)) {
+		logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+		return result;
+	}
+	DIR *task = opendir(b1->getBuf());
+	if (task == NULL) {
+		logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__);
+		// This is not a fatal error - the thread just doesn't exist any more
+		return true;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(task)) != NULL) {
+		char *endptr;
+		const int tid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore task items that are not integers like ., etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/task/%i/stat", pid, tid)) {
+			logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+		ProcStat ps;
+		if (!readProcStat(&ps, printb->getBuf(), b1)) {
+			logg->logMessage("%s(%s:%i): readProcStat failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+
+		const char *const image = readProcExe(printb, pid, tid, b2);
+		if (image == NULL) {
+			logg->logMessage("%s(%s:%i): readImage failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+
+		buffer->comm(currTime, pid, tid, image, ps.comm);
+	}
+
+	result = true;
+
+ fail:
+	closedir(task);
+
+	return result;
+}
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+	bool result = false;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__);
+		return result;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/stat", pid)) {
+			logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+		ProcStat ps;
+		if (!readProcStat(&ps, printb->getBuf(), b1)) {
+			logg->logMessage("%s(%s:%i): readProcStat failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+
+		if (ps.numThreads <= 1) {
+			const char *const image = readProcExe(printb, pid, -1, b1);
+			if (image == NULL) {
+				logg->logMessage("%s(%s:%i): readImage failed", __FUNCTION__, __FILE__, __LINE__);
+				goto fail;
+			}
+
+			buffer->comm(currTime, pid, pid, image, ps.comm);
+		} else {
+			if (!readProcTask(currTime, buffer, pid, printb, b1, b2)) {
+				logg->logMessage("%s(%s:%i): readProcTask failed", __FUNCTION__, __FILE__, __LINE__);
+				goto fail;
+			}
+		}
+	}
+
+	result = true;
+
+ fail:
+	closedir(proc);
+
+	return result;
+}
+
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b) {
+	bool result = false;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logMessage("%s(%s:%i): opendir failed", __FUNCTION__, __FILE__, __LINE__);
+		return result;
+	}
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0') {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/maps", pid)) {
+			logg->logMessage("%s(%s:%i): DynBuf::printf failed", __FUNCTION__, __FILE__, __LINE__);
+			goto fail;
+		}
+		if (!b->read(printb->getBuf())) {
+			logg->logMessage("%s(%s:%i): DynBuf::read failed, likely because the process exited", __FUNCTION__, __FILE__, __LINE__);
+			// This is not a fatal error - the process just doesn't exist any more
+			continue;
+		}
+
+		buffer->maps(currTime, pid, pid, b->getBuf());
+	}
+
+	result = true;
+
+ fail:
+	closedir(proc);
+
+	return result;
+}
+
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone) {
+	int fd = ::open("/proc/kallsyms", O_RDONLY | O_CLOEXEC);
+
+	if (fd < 0) {
+		logg->logMessage("%s(%s:%i): open failed", __FUNCTION__, __FILE__, __LINE__);
+		return true;
+	};
+
+	char buf[1<<12];
+	ssize_t pos = 0;
+	while (gSessionData->mSessionIsActive && !ACCESS_ONCE(*isDone)) {
+		// Assert there is still space in the buffer
+		if (sizeof(buf) - pos - 1 == 0) {
+			logg->logError(__FILE__, __LINE__, "no space left in buffer");
+			handleException();
+		}
+
+		{
+			// -1 to reserve space for \0
+			const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+			if (bytes < 0) {
+				logg->logError(__FILE__, __LINE__, "read failed", __FUNCTION__, __FILE__, __LINE__);
+				handleException();
+			}
+			if (bytes == 0) {
+				// Assert the buffer is empty
+				if (pos != 0) {
+					logg->logError(__FILE__, __LINE__, "buffer not empty on eof");
+					handleException();
+				}
+				break;
+			}
+			pos += bytes;
+		}
+
+		ssize_t newline;
+		// Find the last '\n'
+		for (newline = pos - 1; newline >= 0; --newline) {
+			if (buf[newline] == '\n') {
+				const char was = buf[newline + 1];
+				buf[newline + 1] = '\0';
+				buffer->kallsyms(currTime, buf);
+				// Sleep 3 ms to avoid sending out too much data too quickly
+				usleep(3000);
+				buf[0] = was;
+				// Assert the memory regions do not overlap
+				if (pos - newline >= newline + 1) {
+					logg->logError(__FILE__, __LINE__, "memcpy src and dst overlap");
+					handleException();
+				}
+				if (pos - newline - 2 > 0) {
+					memcpy(buf + 1, buf + newline + 2, pos - newline - 2);
+				}
+				pos -= newline + 1;
+				break;
+			}
+		}
+	}
+
+	close(fd);
+
+	return true;
+}
diff --git a/tools/gator/daemon/Proc.h b/tools/gator/daemon/Proc.h
new file mode 100644
index 000000000000..2a1a7cbc1e99
--- /dev/null
+++ b/tools/gator/daemon/Proc.h
@@ -0,0 +1,21 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PROC_H
+#define PROC_H
+
+#include <stdint.h>
+
+class Buffer;
+class DynBuf;
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2);
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b);
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone);
+
+#endif // PROC_H
diff --git a/tools/gator/daemon/Sender.cpp b/tools/gator/daemon/Sender.cpp
new file mode 100644
index 000000000000..8a54a6678974
--- /dev/null
+++ b/tools/gator/daemon/Sender.cpp
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Sender.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+Sender::Sender(OlySocket* socket) {
+	mDataFile = NULL;
+	mDataSocket = NULL;
+
+	// Set up the socket connection
+	if (socket) {
+		char streamline[64] = {0};
+		mDataSocket = socket;
+
+		// Receive magic sequence - can wait forever
+		// Streamline will send data prior to the magic sequence for legacy support, which should be ignored for v4+
+		while (strcmp("STREAMLINE", streamline) != 0) {
+			if (mDataSocket->receiveString(streamline, sizeof(streamline)) == -1) {
+				logg->logError(__FILE__, __LINE__, "Socket disconnected");
+				handleException();
+			}
+		}
+
+		// Send magic sequence - must be done first, after which error messages can be sent
+		char magic[32];
+		snprintf(magic, 32, "GATOR %i\n", PROTOCOL_VERSION);
+		mDataSocket->send(magic, strlen(magic));
+
+		gSessionData->mWaitingOnCommand = true;
+		logg->logMessage("Completed magic sequence");
+	}
+
+	pthread_mutex_init(&mSendMutex, NULL);
+}
+
+Sender::~Sender() {
+	// Just close it as the client socket is on the stack
+	if (mDataSocket != NULL) {
+		mDataSocket->closeSocket();
+		mDataSocket = NULL;
+	}
+	if (mDataFile != NULL) {
+		fclose(mDataFile);
+	}
+}
+
+void Sender::createDataFile(char* apcDir) {
+	if (apcDir == NULL) {
+		return;
+	}
+
+	mDataFileName = (char*)malloc(strlen(apcDir) + 12);
+	sprintf(mDataFileName, "%s/0000000000", apcDir);
+	mDataFile = fopen_cloexec(mDataFileName, "wb");
+	if (!mDataFile) {
+		logg->logError(__FILE__, __LINE__, "Failed to open binary file: %s", mDataFileName);
+		handleException();
+	}
+}
+
+void Sender::writeData(const char* data, int length, int type) {
+	if (length < 0 || (data == NULL && length > 0)) {
+		return;
+	}
+
+	// Multiple threads call writeData()
+	pthread_mutex_lock(&mSendMutex);
+
+	// Send data over the socket connection
+	if (mDataSocket) {
+		// Start alarm
+		const int alarmDuration = 8;
+		alarm(alarmDuration);
+
+		// Send data over the socket, sending the type and size first
+		logg->logMessage("Sending data with length %d", length);
+		if (type != RESPONSE_APC_DATA) {
+			// type and length already added by the Collector for apc data
+			unsigned char header[5];
+			header[0] = type;
+			Buffer::writeLEInt(header + 1, length);
+			mDataSocket->send((char*)&header, sizeof(header));
+		}
+
+		// 100Kbits/sec * alarmDuration sec / 8 bits/byte
+		const int chunkSize = 100*1000 * alarmDuration / 8;
+		int pos = 0;
+		while (true) {
+			mDataSocket->send((const char*)data + pos, min(length - pos, chunkSize));
+			pos += chunkSize;
+			if (pos >= length) {
+				break;
+			}
+
+			// Reset the alarm
+			alarm(alarmDuration);
+			logg->logMessage("Resetting the alarm");
+		}
+
+		// Stop alarm
+		alarm(0);
+	}
+
+	// Write data to disk as long as it is not meta data
+	if (mDataFile && type == RESPONSE_APC_DATA) {
+		logg->logMessage("Writing data with length %d", length);
+		// Send data to the data file
+		if (fwrite(data, 1, length, mDataFile) != (unsigned int)length) {
+			logg->logError(__FILE__, __LINE__, "Failed writing binary file %s", mDataFileName);
+			handleException();
+		}
+	}
+
+	pthread_mutex_unlock(&mSendMutex);
+}
diff --git a/tools/gator/daemon/Sender.h b/tools/gator/daemon/Sender.h
new file mode 100644
index 000000000000..5aa911713820
--- /dev/null
+++ b/tools/gator/daemon/Sender.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __SENDER_H__
+#define __SENDER_H__
+
+#include <stdio.h>
+#include <pthread.h>
+
+class OlySocket;
+
+enum {
+	RESPONSE_XML = 1,
+	RESPONSE_APC_DATA = 3,
+	RESPONSE_ACK = 4,
+	RESPONSE_NAK = 5,
+	RESPONSE_ERROR = 0xFF
+};
+
+class Sender {
+public:
+	Sender(OlySocket* socket);
+	~Sender();
+	void writeData(const char* data, int length, int type);
+	void createDataFile(char* apcDir);
+private:
+	OlySocket* mDataSocket;
+	FILE* mDataFile;
+	char* mDataFileName;
+	pthread_mutex_t mSendMutex;
+
+	// Intentionally unimplemented
+	Sender(const Sender &);
+	Sender &operator=(const Sender &);
+};
+
+#endif //__SENDER_H__
diff --git a/tools/gator/daemon/SessionData.cpp b/tools/gator/daemon/SessionData.cpp
new file mode 100644
index 000000000000..0e65d7842647
--- /dev/null
+++ b/tools/gator/daemon/SessionData.cpp
@@ -0,0 +1,261 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionData.h"
+
+#include <fcntl.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include "CPUFreqDriver.h"
+#include "DiskIODriver.h"
+#include "FSDriver.h"
+#include "HwmonDriver.h"
+#include "Logging.h"
+#include "MemInfoDriver.h"
+#include "NetDriver.h"
+#include "SessionXML.h"
+
+#define CORE_NAME_UNKNOWN "unknown"
+
+SessionData* gSessionData = NULL;
+
+SessionData::SessionData() {
+	usDrivers[0] = new HwmonDriver();
+	usDrivers[1] = new FSDriver();
+	usDrivers[2] = new MemInfoDriver();
+	usDrivers[3] = new NetDriver();
+	usDrivers[4] = new CPUFreqDriver();
+	usDrivers[5] = new DiskIODriver();
+	initialize();
+}
+
+SessionData::~SessionData() {
+}
+
+void SessionData::initialize() {
+	mWaitingOnCommand = false;
+	mSessionIsActive = false;
+	mLocalCapture = false;
+	mOneShot = false;
+	mSentSummary = false;
+	mAllowCommands = false;
+	const size_t cpuIdSize = sizeof(int)*NR_CPUS;
+	// Share mCpuIds across all instances of gatord
+	mCpuIds = (int *)mmap(NULL, cpuIdSize, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (mCpuIds == MAP_FAILED) {
+		logg->logError(__FILE__, __LINE__, "Unable to mmap shared memory for cpuids");
+		handleException();
+	}
+	memset(mCpuIds, -1, cpuIdSize);
+	strcpy(mCoreName, CORE_NAME_UNKNOWN);
+	readModel();
+	readCpuInfo();
+	mImages = NULL;
+	mConfigurationXMLPath = NULL;
+	mSessionXMLPath = NULL;
+	mEventsXMLPath = NULL;
+	mTargetPath = NULL;
+	mAPCDir = NULL;
+	mCaptureWorkingDir = NULL;
+	mCaptureCommand = NULL;
+	mCaptureUser = NULL;
+	mSampleRate = 0;
+	mLiveRate = 0;
+	mDuration = 0;
+	mMonotonicStarted = -1;
+	mBacktraceDepth = 0;
+	mTotalBufferSize = 0;
+	// sysconf(_SC_NPROCESSORS_CONF) is unreliable on 2.6 Android, get the value from the kernel module
+	mCores = 1;
+	mPageSize = 0;
+}
+
+void SessionData::parseSessionXML(char* xmlString) {
+	SessionXML session(xmlString);
+	session.parse();
+
+	// Set session data values - use prime numbers just below the desired value to reduce the chance of events firing at the same time
+	if (strcmp(session.parameters.sample_rate, "high") == 0) {
+		mSampleRate = 9973; // 10000
+	} else if (strcmp(session.parameters.sample_rate, "normal") == 0) {
+		mSampleRate = 997; // 1000
+	} else if (strcmp(session.parameters.sample_rate, "low") == 0) {
+		mSampleRate = 97; // 100
+	} else if (strcmp(session.parameters.sample_rate, "none") == 0) {
+		mSampleRate = 0;
+	} else {
+		logg->logError(__FILE__, __LINE__, "Invalid sample rate (%s) in session xml.", session.parameters.sample_rate);
+		handleException();
+	}
+	mBacktraceDepth = session.parameters.call_stack_unwinding == true ? 128 : 0;
+
+	// Determine buffer size (in MB) based on buffer mode
+	mOneShot = true;
+	if (strcmp(session.parameters.buffer_mode, "streaming") == 0) {
+		mOneShot = false;
+		mTotalBufferSize = 1;
+	} else if (strcmp(session.parameters.buffer_mode, "small") == 0) {
+		mTotalBufferSize = 1;
+	} else if (strcmp(session.parameters.buffer_mode, "normal") == 0) {
+		mTotalBufferSize = 4;
+	} else if (strcmp(session.parameters.buffer_mode, "large") == 0) {
+		mTotalBufferSize = 16;
+	} else {
+		logg->logError(__FILE__, __LINE__, "Invalid value for buffer mode in session xml.");
+		handleException();
+	}
+
+	// Convert milli- to nanoseconds
+	mLiveRate = session.parameters.live_rate * (int64_t)1000000;
+	if (mLiveRate > 0 && mLocalCapture) {
+		logg->logMessage("Local capture is not compatable with live, disabling live");
+		mLiveRate = 0;
+	}
+
+	if (!mAllowCommands && (mCaptureCommand != NULL)) {
+		logg->logError(__FILE__, __LINE__, "Running a command during a capture is not currently allowed. Please restart gatord with the -a flag.");
+		handleException();
+	}
+}
+
+void SessionData::readModel() {
+	FILE *fh = fopen("/proc/device-tree/model", "rb");
+	if (fh == NULL) {
+		return;
+	}
+
+	char buf[256];
+	if (fgets(buf, sizeof(buf), fh) != NULL) {
+		strcpy(mCoreName, buf);
+	}
+
+	fclose(fh);
+}
+
+void SessionData::readCpuInfo() {
+	char temp[256]; // arbitrarily large amount
+	mMaxCpuId = -1;
+
+	FILE *f = fopen("/proc/cpuinfo", "r");
+	if (f == NULL) {
+		logg->logMessage("Error opening /proc/cpuinfo\n"
+			"The core name in the captured xml file will be 'unknown'.");
+		return;
+	}
+
+	bool foundCoreName = false;
+	int processor = -1;
+	while (fgets(temp, sizeof(temp), f)) {
+		const size_t len = strlen(temp);
+
+		if (len == 1) {
+			// New section, clear the processor. Streamline will not know the cpus if the pre Linux 3.8 format of cpuinfo is encountered but also that no incorrect information will be transmitted.
+			processor = -1;
+			continue;
+		}
+
+		if (len > 0) {
+			// Replace the line feed with a null
+			temp[len - 1] = '\0';
+		}
+
+		const bool foundHardware = strstr(temp, "Hardware") != 0;
+		const bool foundCPUPart = strstr(temp, "CPU part") != 0;
+		const bool foundProcessor = strstr(temp, "processor") != 0;
+		if (foundHardware || foundCPUPart || foundProcessor) {
+			char* position = strchr(temp, ':');
+			if (position == NULL || (unsigned int)(position - temp) + 2 >= strlen(temp)) {
+				logg->logMessage("Unknown format of /proc/cpuinfo\n"
+					"The core name in the captured xml file will be 'unknown'.");
+				return;
+			}
+			position += 2;
+
+			if (foundHardware && (strcmp(mCoreName, CORE_NAME_UNKNOWN) == 0)) {
+				strncpy(mCoreName, position, sizeof(mCoreName));
+				mCoreName[sizeof(mCoreName) - 1] = 0; // strncpy does not guarantee a null-terminated string
+				foundCoreName = true;
+			}
+
+			if (foundCPUPart) {
+				const int cpuId = strtol(position, NULL, 0);
+				// If this does not have the full topology in /proc/cpuinfo, mCpuIds[0] may not have the 1 CPU part emitted - this guarantees it's in mMaxCpuId
+				if (cpuId > mMaxCpuId) {
+					mMaxCpuId = cpuId;
+				}
+				if (processor >= NR_CPUS) {
+					logg->logMessage("Too many processors, please increase NR_CPUS");
+				} else if (processor >= 0) {
+					mCpuIds[processor] = cpuId;
+				}
+			}
+
+			if (foundProcessor) {
+				processor = strtol(position, NULL, 0);
+			}
+		}
+	}
+
+	if (!foundCoreName) {
+		logg->logMessage("Could not determine core name from /proc/cpuinfo\n"
+				 "The core name in the captured xml file will be 'unknown'.");
+	}
+	fclose(f);
+}
+
+uint64_t getTime() {
+	struct timespec ts;
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+		logg->logError(__FILE__, __LINE__, "Failed to get uptime");
+		handleException();
+	}
+	return (NS_PER_S*ts.tv_sec + ts.tv_nsec);
+}
+
+int getEventKey() {
+	// key 0 is reserved as a timestamp
+	// key 1 is reserved as the marker for thread specific counters
+	// key 2 is reserved as the marker for core
+	// Odd keys are assigned by the driver, even keys by the daemon
+	static int key = 4;
+
+	const int ret = key;
+	key += 2;
+	return ret;
+}
+
+int pipe_cloexec(int pipefd[2]) {
+	if (pipe(pipefd) != 0) {
+		return -1;
+	}
+
+	int fdf;
+	if (((fdf = fcntl(pipefd[0], F_GETFD)) == -1) || (fcntl(pipefd[0], F_SETFD, fdf | FD_CLOEXEC) != 0) ||
+			((fdf = fcntl(pipefd[1], F_GETFD)) == -1) || (fcntl(pipefd[1], F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		close(pipefd[0]);
+		close(pipefd[1]);
+		return -1;
+	}
+	return 0;
+}
+
+FILE *fopen_cloexec(const char *path, const char *mode) {
+	FILE *fh = fopen(path, mode);
+	if (fh == NULL) {
+		return NULL;
+	}
+	int fd = fileno(fh);
+	int fdf = fcntl(fd, F_GETFD);
+	if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+		fclose(fh);
+		return NULL;
+	}
+	return fh;
+}
diff --git a/tools/gator/daemon/SessionData.h b/tools/gator/daemon/SessionData.h
new file mode 100644
index 000000000000..ed282af4a869
--- /dev/null
+++ b/tools/gator/daemon/SessionData.h
@@ -0,0 +1,102 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_DATA_H
+#define SESSION_DATA_H
+
+#include <stdint.h>
+
+#include "AnnotateListener.h"
+#include "Config.h"
+#include "Counter.h"
+#include "FtraceDriver.h"
+#include "KMod.h"
+#include "MaliVideoDriver.h"
+#include "PerfDriver.h"
+
+#define PROTOCOL_VERSION 20
+// Differentiates development versions (timestamp) from release versions
+#define PROTOCOL_DEV 1000
+
+#define NS_PER_S 1000000000LL
+#define NS_PER_MS 1000000LL
+#define NS_PER_US 1000LL
+
+struct ImageLinkList {
+	char* path;
+	struct ImageLinkList *next;
+};
+
+class SessionData {
+public:
+	static const size_t MAX_STRING_LEN = 80;
+
+	SessionData();
+	~SessionData();
+	void initialize();
+	void parseSessionXML(char* xmlString);
+	void readModel();
+	void readCpuInfo();
+
+	PolledDriver *usDrivers[6];
+	KMod kmod;
+	PerfDriver perf;
+	MaliVideoDriver maliVideo;
+	FtraceDriver ftraceDriver;
+	AnnotateListener annotateListener;
+
+	char mCoreName[MAX_STRING_LEN];
+	struct ImageLinkList *mImages;
+	char *mConfigurationXMLPath;
+	char *mSessionXMLPath;
+	char *mEventsXMLPath;
+	char *mTargetPath;
+	char *mAPCDir;
+	char *mCaptureWorkingDir;
+	char *mCaptureCommand;
+	char *mCaptureUser;
+
+	bool mWaitingOnCommand;
+	bool mSessionIsActive;
+	bool mLocalCapture;
+	// halt processing of the driver data until profiling is complete or the buffer is filled
+	bool mOneShot;
+	bool mIsEBS;
+	bool mSentSummary;
+	bool mAllowCommands;
+
+	int64_t mMonotonicStarted;
+	int mBacktraceDepth;
+	// number of MB to use for the entire collection buffer
+	int mTotalBufferSize;
+	int mSampleRate;
+	int64_t mLiveRate;
+	int mDuration;
+	int mCores;
+	int mPageSize;
+	int *mCpuIds;
+	int mMaxCpuId;
+
+	// PMU Counters
+	int mCounterOverflow;
+	Counter mCounters[MAX_PERFORMANCE_COUNTERS];
+
+private:
+	// Intentionally unimplemented
+	SessionData(const SessionData &);
+	SessionData &operator=(const SessionData &);
+};
+
+extern SessionData* gSessionData;
+
+uint64_t getTime();
+int getEventKey();
+int pipe_cloexec(int pipefd[2]);
+FILE *fopen_cloexec(const char *path, const char *mode);
+
+#endif // SESSION_DATA_H
diff --git a/tools/gator/daemon/SessionXML.cpp b/tools/gator/daemon/SessionXML.cpp
new file mode 100644
index 000000000000..dea4c8f299ec
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.cpp
@@ -0,0 +1,111 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char *TAG_SESSION = "session";
+static const char *TAG_IMAGE   = "image";
+
+static const char *ATTR_VERSION              = "version";
+static const char *ATTR_CALL_STACK_UNWINDING = "call_stack_unwinding";
+static const char *ATTR_BUFFER_MODE          = "buffer_mode";
+static const char *ATTR_SAMPLE_RATE          = "sample_rate";
+static const char *ATTR_DURATION             = "duration";
+static const char *ATTR_PATH                 = "path";
+static const char *ATTR_LIVE_RATE            = "live_rate";
+static const char *ATTR_CAPTURE_WORKING_DIR  = "capture_working_dir";
+static const char *ATTR_CAPTURE_COMMAND      = "capture_command";
+static const char *ATTR_CAPTURE_USER         = "capture_user";
+
+SessionXML::SessionXML(const char *str) {
+	parameters.buffer_mode[0] = 0;
+	parameters.sample_rate[0] = 0;
+	parameters.call_stack_unwinding = false;
+	parameters.live_rate = 0;
+	mSessionXML = str;
+	logg->logMessage(mSessionXML);
+}
+
+SessionXML::~SessionXML() {
+}
+
+void SessionXML::parse() {
+	mxml_node_t *tree;
+	mxml_node_t *node;
+
+	tree = mxmlLoadString(NULL, mSessionXML, MXML_NO_CALLBACK);
+	node = mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND);
+
+	if (node) {
+		sessionTag(tree, node);
+		mxmlDelete(tree);
+		return;
+	}
+
+	logg->logError(__FILE__, __LINE__, "No session tag found in the session.xml file");
+	handleException();
+}
+
+void SessionXML::sessionTag(mxml_node_t *tree, mxml_node_t *node) {
+	int version = 0;
+	if (mxmlElementGetAttr(node, ATTR_VERSION)) version = strtol(mxmlElementGetAttr(node, ATTR_VERSION), NULL, 10);
+	if (version != 1) {
+		logg->logError(__FILE__, __LINE__, "Invalid session.xml version: %d", version);
+		handleException();
+	}
+
+	// copy to pre-allocated strings
+	if (mxmlElementGetAttr(node, ATTR_BUFFER_MODE)) {
+		strncpy(parameters.buffer_mode, mxmlElementGetAttr(node, ATTR_BUFFER_MODE), sizeof(parameters.buffer_mode));
+		parameters.buffer_mode[sizeof(parameters.buffer_mode) - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+	if (mxmlElementGetAttr(node, ATTR_SAMPLE_RATE)) {
+		strncpy(parameters.sample_rate, mxmlElementGetAttr(node, ATTR_SAMPLE_RATE), sizeof(parameters.sample_rate));
+		parameters.sample_rate[sizeof(parameters.sample_rate) - 1] = 0; // strncpy does not guarantee a null-terminated string
+	}
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR)) gSessionData->mCaptureWorkingDir = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR));
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND)) gSessionData->mCaptureCommand = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND));
+	if (mxmlElementGetAttr(node, ATTR_CAPTURE_USER)) gSessionData->mCaptureUser = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_USER));
+
+	// integers/bools
+	parameters.call_stack_unwinding = util->stringToBool(mxmlElementGetAttr(node, ATTR_CALL_STACK_UNWINDING), false);
+	if (mxmlElementGetAttr(node, ATTR_DURATION)) gSessionData->mDuration = strtol(mxmlElementGetAttr(node, ATTR_DURATION), NULL, 10);
+	if (mxmlElementGetAttr(node, ATTR_LIVE_RATE)) parameters.live_rate = strtol(mxmlElementGetAttr(node, ATTR_LIVE_RATE), NULL, 10);
+
+	// parse subtags
+	node = mxmlGetFirstChild(node);
+	while (node) {
+		if (mxmlGetType(node) != MXML_ELEMENT) {
+			node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+			continue;
+		}
+		if (strcmp(TAG_IMAGE, mxmlGetElement(node)) == 0) {
+			sessionImage(node);
+		}
+		node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+	}
+}
+
+void SessionXML::sessionImage(mxml_node_t *node) {
+	int length = strlen(mxmlElementGetAttr(node, ATTR_PATH));
+	struct ImageLinkList *image;
+
+	image = (struct ImageLinkList *)malloc(sizeof(struct ImageLinkList));
+	image->path = (char*)malloc(length + 1);
+	image->path = strdup(mxmlElementGetAttr(node, ATTR_PATH));
+	image->next = gSessionData->mImages;
+	gSessionData->mImages = image;
+}
diff --git a/tools/gator/daemon/SessionXML.h b/tools/gator/daemon/SessionXML.h
new file mode 100644
index 000000000000..53965749c74b
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_XML_H
+#define SESSION_XML_H
+
+#include "mxml/mxml.h"
+
+struct ImageLinkList;
+
+struct ConfigParameters {
+	// buffer mode, "streaming", "low", "normal", "high" defines oneshot and buffer size
+	char buffer_mode[64];
+	// capture mode, "high", "normal", or "low"
+	char sample_rate[64];
+	// whether stack unwinding is performed
+	bool call_stack_unwinding;
+	int live_rate;
+};
+
+class SessionXML {
+public:
+	SessionXML(const char *str);
+	~SessionXML();
+	void parse();
+	ConfigParameters parameters;
+private:
+	const char *mSessionXML;
+	void sessionTag(mxml_node_t *tree, mxml_node_t *node);
+	void sessionImage(mxml_node_t *node);
+
+	// Intentionally unimplemented
+	SessionXML(const SessionXML &);
+	SessionXML &operator=(const SessionXML &);
+};
+
+#endif // SESSION_XML_H
diff --git a/tools/gator/daemon/Setup.cpp b/tools/gator/daemon/Setup.cpp
new file mode 100644
index 000000000000..d4ce0328c633
--- /dev/null
+++ b/tools/gator/daemon/Setup.cpp
@@ -0,0 +1,232 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Setup.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Config.h"
+#include "DynBuf.h"
+#include "Logging.h"
+
+bool getLinuxVersion(int version[3]) {
+	// Check the kernel version
+	struct utsname utsname;
+	if (uname(&utsname) != 0) {
+		logg->logMessage("%s(%s:%i): uname failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	version[0] = 0;
+	version[1] = 0;
+	version[2] = 0;
+
+	int part = 0;
+	char *ch = utsname.release;
+	while (*ch >= '0' && *ch <= '9' && part < 3) {
+		version[part] = 10*version[part] + *ch - '0';
+
+		++ch;
+		if (*ch == '.') {
+			++part;
+			++ch;
+		}
+	}
+
+	return true;
+}
+
+static int pgrep_gator(DynBuf *const printb) {
+	DynBuf b;
+
+	DIR *proc = opendir("/proc");
+	if (proc == NULL) {
+		logg->logError(__FILE__, __LINE__, "gator: error: opendir failed");
+		handleException();
+	}
+
+	int self = getpid();
+
+	struct dirent *dirent;
+	while ((dirent = readdir(proc)) != NULL) {
+		char *endptr;
+		const int pid = strtol(dirent->d_name, &endptr, 10);
+		if (*endptr != '\0' || (pid == self)) {
+			// Ignore proc items that are not integers like ., cpuinfo, etc...
+			continue;
+		}
+
+		if (!printb->printf("/proc/%i/stat", pid)) {
+			logg->logError(__FILE__, __LINE__, "gator: error: DynBuf::printf failed");
+			handleException();
+		}
+
+		if (!b.read(printb->getBuf())) {
+			// This is not a fatal error - the thread just doesn't exist any more
+			continue;
+		}
+
+		char *comm = strchr(b.getBuf(), '(');
+		if (comm == NULL) {
+			logg->logError(__FILE__, __LINE__, "gator: error: parsing stat begin failed");
+			handleException();
+		}
+		++comm;
+		char *const str = strrchr(comm, ')');
+		if (str == NULL) {
+			logg->logError(__FILE__, __LINE__, "gator: error: parsing stat end failed");
+			handleException();
+		}
+		*str = '\0';
+
+		if (strncmp(comm, "gator", 5) == 0) {
+			// Assume there is only one gator process
+			return pid;
+		}
+	}
+
+	closedir(proc);
+
+	return -1;
+}
+
+int update(const char *const gatorPath) {
+	printf("gator: starting\n");
+
+	int version[3];
+	if (!getLinuxVersion(version)) {
+		logg->logError(__FILE__, __LINE__, "gator: error: getLinuxVersion failed");
+		handleException();
+	}
+
+	if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(2, 6, 32)) {
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline can't automatically setup gator as this kernel version is not supported. Please upgrade the kernel on your device.");
+		handleException();
+	}
+
+	if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(3, 4, 0)) {
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline can't automatically setup gator as gator.ko is required for this version of Linux. Please build gator.ko and gatord and install them on your device.");
+		handleException();
+	}
+
+	if (access("/sys/module/gator", F_OK) == 0) {
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline has detected that the gator kernel module is loaded on your device. Please build an updated version of gator.ko and gatord and install them on your device.");
+		handleException();
+	}
+
+	if (geteuid() != 0) {
+		printf("gator: trying sudo\n");
+		execlp("sudo", "sudo", gatorPath, "-u", NULL);
+		// Streamline will provide the password if needed
+
+		printf("gator: trying su\n");
+		char buf[1<<10];
+		snprintf(buf, sizeof(buf), "%s -u", gatorPath);
+		execlp("su", "su", "-", "-c", buf, NULL);
+		// Streamline will provide the password if needed
+
+		logg->logError(__FILE__, __LINE__, "gator: error: Streamline was unable to sudo to root on your device. Please double check passwords, ensure sudo or su work with this user or try a different username.");
+		handleException();
+	}
+	printf("gator: now root\n");
+
+	// setenforce 0 not needed for userspace gator
+
+	// Kill existing gator
+	DynBuf gatorStatPath;
+	int gator_main = pgrep_gator(&gatorStatPath);
+	if (gator_main > 0) {
+		if (kill(gator_main, SIGTERM) != 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: kill SIGTERM failed");
+			handleException();
+		}
+		for (int i = 0; ; ++i) {
+			if (access(gatorStatPath.getBuf(), F_OK) != 0) {
+				break;
+			}
+			if (i == 5) {
+				if (kill(gator_main, SIGKILL) != 0) {
+					logg->logError(__FILE__, __LINE__, "gator: error: kill SIGKILL failed");
+					handleException();
+				}
+			} else if (i >= 10) {
+				logg->logError(__FILE__, __LINE__, "gator: error: unable to kill running gator");
+				handleException();
+			}
+			sleep(1);
+		}
+	}
+	printf("gator: no gatord running\n");
+
+	rename("gatord", "gatord.old");
+	rename("gator.ko", "gator.ko.old");
+
+	// Rename gatord.YYYYMMDDHHMMSSMMMM to gatord
+	char *newGatorPath = strdup(gatorPath);
+	char *dot = strrchr(newGatorPath, '.');
+	if (dot != NULL) {
+		*dot = '\0';
+		if (rename(gatorPath, newGatorPath) != 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: rename failed");
+			handleException();
+		}
+	}
+
+	// Fork and start gatord (redirect stdout and stderr)
+	int child = fork();
+	if (child < 0) {
+		logg->logError(__FILE__, __LINE__, "gator: error: fork failed");
+		handleException();
+	} else if (child == 0) {
+		int inFd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+		if (inFd < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: open of /dev/null failed");
+			handleException();
+		}
+		int outFd = open("gatord.out", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0600);
+		if (outFd < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: open of gatord.out failed");
+			handleException();
+		}
+		int errFd = open("gatord.err", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0600);
+		if (errFd < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: open of gatord.err failed");
+			handleException();
+		}
+		if (dup2(inFd, STDIN_FILENO) < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stdin failed");
+			handleException();
+		}
+		if (dup2(outFd, STDOUT_FILENO) < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stdout failed");
+			handleException();
+		}
+		if (dup2(errFd, STDERR_FILENO) < 0) {
+			logg->logError(__FILE__, __LINE__, "gator: error: dup2 for stderr failed");
+			handleException();
+		}
+		execlp(newGatorPath, newGatorPath, "-a", NULL);
+		logg->logError(__FILE__, __LINE__, "gator: error: execlp failed");
+		handleException();
+	}
+
+	printf("gator: done\n");
+
+	return 0;
+}
diff --git a/tools/gator/daemon/Setup.h b/tools/gator/daemon/Setup.h
new file mode 100644
index 000000000000..280d61139784
--- /dev/null
+++ b/tools/gator/daemon/Setup.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SETUP_H
+#define SETUP_H
+
+// From include/generated/uapi/linux/version.h
+#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))
+
+bool getLinuxVersion(int version[3]);
+int update(const char *const gatorPath);
+
+#endif // SETUP_H
diff --git a/tools/gator/daemon/Source.cpp b/tools/gator/daemon/Source.cpp
new file mode 100644
index 000000000000..60cf704e599b
--- /dev/null
+++ b/tools/gator/daemon/Source.cpp
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Source.h"
+
+#include "Logging.h"
+
+Source::Source() : mThreadID() {
+}
+
+Source::~Source() {
+}
+
+void Source::start() {
+	if (pthread_create(&mThreadID, NULL, runStatic, this)) {
+		logg->logError(__FILE__, __LINE__, "Failed to create source thread");
+		handleException();
+	}
+}
+
+void Source::join() {
+	pthread_join(mThreadID, NULL);
+}
+
+void *Source::runStatic(void *arg) {
+	static_cast<Source *>(arg)->run();
+	return NULL;
+}
diff --git a/tools/gator/daemon/Source.h b/tools/gator/daemon/Source.h
new file mode 100644
index 000000000000..56ac3d6e94f3
--- /dev/null
+++ b/tools/gator/daemon/Source.h
@@ -0,0 +1,40 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SOURCE_H
+#define SOURCE_H
+
+#include <pthread.h>
+
+class Sender;
+
+class Source {
+public:
+	Source();
+	virtual ~Source();
+
+	virtual bool prepare() = 0;
+	void start();
+	virtual void run() = 0;
+	virtual void interrupt() = 0;
+	void join();
+
+	virtual bool isDone() = 0;
+	virtual void write(Sender *sender) = 0;
+
+private:
+	static void *runStatic(void *arg);
+
+	pthread_t mThreadID;
+
+	// Intentionally undefined
+	Source(const Source &);
+	Source &operator=(const Source &);
+};
+
+#endif // SOURCE_H
diff --git a/tools/gator/daemon/StreamlineSetup.cpp b/tools/gator/daemon/StreamlineSetup.cpp
new file mode 100644
index 000000000000..2b61eaeb290d
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.cpp
@@ -0,0 +1,272 @@
+/**
+ * Copyright (C) ARM Limited 2011-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "StreamlineSetup.h"
+
+#include "Buffer.h"
+#include "CapturedXML.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+static const char* TAG_SESSION = "session";
+static const char* TAG_REQUEST = "request";
+static const char* TAG_CONFIGURATIONS = "configurations";
+
+static const char* ATTR_TYPE           = "type";
+static const char* VALUE_EVENTS        = "events";
+static const char* VALUE_CONFIGURATION = "configuration";
+static const char* VALUE_COUNTERS      = "counters";
+static const char* VALUE_CAPTURED      = "captured";
+static const char* VALUE_DEFAULTS      = "defaults";
+
+StreamlineSetup::StreamlineSetup(OlySocket* s) {
+	bool ready = false;
+	char* data = NULL;
+	int type;
+
+	mSocket = s;
+
+	// Receive commands from Streamline (master)
+	while (!ready) {
+		// receive command over socket
+		gSessionData->mWaitingOnCommand = true;
+		data = readCommand(&type);
+
+		// parse and handle data
+		switch (type) {
+			case COMMAND_REQUEST_XML:
+				handleRequest(data);
+				break;
+			case COMMAND_DELIVER_XML:
+				handleDeliver(data);
+				break;
+			case COMMAND_APC_START:
+				logg->logMessage("Received apc start request");
+				ready = true;
+				break;
+			case COMMAND_APC_STOP:
+				logg->logMessage("Received apc stop request before apc start request");
+				exit(0);
+				break;
+			case COMMAND_DISCONNECT:
+				logg->logMessage("Received disconnect command");
+				exit(0);
+				break;
+			case COMMAND_PING:
+				logg->logMessage("Received ping command");
+				sendData(NULL, 0, RESPONSE_ACK);
+				break;
+			default:
+				logg->logError(__FILE__, __LINE__, "Target error: Unknown command type, %d", type);
+				handleException();
+		}
+
+		free(data);
+	}
+
+	if (gSessionData->mCounterOverflow > 0) {
+		logg->logError(__FILE__, __LINE__, "Only %i performance counters are permitted, %i are selected", MAX_PERFORMANCE_COUNTERS, gSessionData->mCounterOverflow);
+		handleException();
+	}
+}
+
+StreamlineSetup::~StreamlineSetup() {
+}
+
+char* StreamlineSetup::readCommand(int* command) {
+	unsigned char header[5];
+	char* data;
+	int response;
+
+	// receive type and length
+	response = mSocket->receiveNBytes((char*)&header, sizeof(header));
+
+	// After receiving a single byte, we are no longer waiting on a command
+	gSessionData->mWaitingOnCommand = false;
+
+	if (response < 0) {
+		logg->logError(__FILE__, __LINE__, "Target error: Unexpected socket disconnect");
+		handleException();
+	}
+
+	const char type = header[0];
+	const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+
+	// add artificial limit
+	if ((length < 0) || length > 1024 * 1024) {
+		logg->logError(__FILE__, __LINE__, "Target error: Invalid length received, %d", length);
+		handleException();
+	}
+
+	// allocate memory to contain the xml file, size of zero returns a zero size object
+	data = (char*)calloc(length + 1, 1);
+	if (data == NULL) {
+		logg->logError(__FILE__, __LINE__, "Unable to allocate memory for xml");
+		handleException();
+	}
+
+	// receive data
+	response = mSocket->receiveNBytes(data, length);
+	if (response < 0) {
+		logg->logError(__FILE__, __LINE__, "Target error: Unexpected socket disconnect");
+		handleException();
+	}
+
+	// null terminate the data for string parsing
+	if (length > 0) {
+		data[length] = 0;
+	}
+
+	*command = type;
+	return data;
+}
+
+void StreamlineSetup::handleRequest(char* xml) {
+	mxml_node_t *tree, *node;
+	const char * attr = NULL;
+
+	tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+	node = mxmlFindElement(tree, tree, TAG_REQUEST, ATTR_TYPE, NULL, MXML_DESCEND_FIRST);
+	if (node) {
+		attr = mxmlElementGetAttr(node, ATTR_TYPE);
+	}
+	if (attr && strcmp(attr, VALUE_EVENTS) == 0) {
+		sendEvents();
+		logg->logMessage("Sent events xml response");
+	} else if (attr && strcmp(attr, VALUE_CONFIGURATION) == 0) {
+		sendConfiguration();
+		logg->logMessage("Sent configuration xml response");
+	} else if (attr && strcmp(attr, VALUE_COUNTERS) == 0) {
+		sendCounters();
+		logg->logMessage("Sent counters xml response");
+	} else if (attr && strcmp(attr, VALUE_CAPTURED) == 0) {
+		CapturedXML capturedXML;
+		char* capturedText = capturedXML.getXML(false);
+		sendData(capturedText, strlen(capturedText), RESPONSE_XML);
+		free(capturedText);
+		logg->logMessage("Sent captured xml response");
+	} else if (attr && strcmp(attr, VALUE_DEFAULTS) == 0) {
+		sendDefaults();
+		logg->logMessage("Sent default configuration xml response");
+	} else {
+		char error[] = "Unknown request";
+		sendData(error, strlen(error), RESPONSE_NAK);
+		logg->logMessage("Received unknown request:\n%s", xml);
+	}
+
+	mxmlDelete(tree);
+}
+
+void StreamlineSetup::handleDeliver(char* xml) {
+	mxml_node_t *tree;
+
+	// Determine xml type
+	tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+	if (mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND_FIRST)) {
+		// Session XML
+		gSessionData->parseSessionXML(xml);
+		sendData(NULL, 0, RESPONSE_ACK);
+		logg->logMessage("Received session xml");
+	} else if (mxmlFindElement(tree, tree, TAG_CONFIGURATIONS, NULL, NULL, MXML_DESCEND_FIRST)) {
+		// Configuration XML
+		writeConfiguration(xml);
+		sendData(NULL, 0, RESPONSE_ACK);
+		logg->logMessage("Received configuration xml");
+	} else {
+		// Unknown XML
+		logg->logMessage("Received unknown XML delivery type");
+		sendData(NULL, 0, RESPONSE_NAK);
+	}
+
+	mxmlDelete(tree);
+}
+
+void StreamlineSetup::sendData(const char* data, uint32_t length, char type) {
+	unsigned char header[5];
+	header[0] = type;
+	Buffer::writeLEInt(header + 1, length);
+	mSocket->send((char*)&header, sizeof(header));
+	mSocket->send((const char*)data, length);
+}
+
+void StreamlineSetup::sendEvents() {
+	EventsXML eventsXML;
+	char* string = eventsXML.getXML();
+	sendString(string, RESPONSE_XML);
+	free(string);
+}
+
+void StreamlineSetup::sendConfiguration() {
+	ConfigurationXML xml;
+
+	const char* string = xml.getConfigurationXML();
+	sendData(string, strlen(string), RESPONSE_XML);
+}
+
+void StreamlineSetup::sendDefaults() {
+	// Send the config built into the binary
+	const char* xml;
+	unsigned int size;
+	ConfigurationXML::getDefaultConfigurationXml(xml, size);
+
+	// Artificial size restriction
+	if (size > 1024*1024) {
+		logg->logError(__FILE__, __LINE__, "Corrupt default configuration file");
+		handleException();
+	}
+
+	sendData(xml, size, RESPONSE_XML);
+}
+
+void StreamlineSetup::sendCounters() {
+	mxml_node_t *xml;
+	mxml_node_t *counters;
+
+	xml = mxmlNewXML("1.0");
+	counters = mxmlNewElement(xml, "counters");
+	int count = 0;
+	for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+		count += driver->writeCounters(counters);
+	}
+
+	if (count == 0) {
+		logg->logError(__FILE__, __LINE__, "No counters found, this could be because /dev/gator/events can not be read or because perf is not working correctly");
+		handleException();
+	}
+
+	char* string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+	sendString(string, RESPONSE_XML);
+
+	free(string);
+	mxmlDelete(xml);
+}
+
+void StreamlineSetup::writeConfiguration(char* xml) {
+	char path[PATH_MAX];
+
+	ConfigurationXML::getPath(path);
+
+	if (util->writeToDisk(path, xml) < 0) {
+		logg->logError(__FILE__, __LINE__, "Error writing %s\nPlease verify write permissions to this path.", path);
+		handleException();
+	}
+
+	// Re-populate gSessionData with the configuration, as it has now changed
+	{ ConfigurationXML configuration; }
+
+	if (gSessionData->mCounterOverflow > 0) {
+		logg->logError(__FILE__, __LINE__, "Only %i performance counters are permitted, %i are selected", MAX_PERFORMANCE_COUNTERS, gSessionData->mCounterOverflow);
+		handleException();
+	}
+}
diff --git a/tools/gator/daemon/StreamlineSetup.h b/tools/gator/daemon/StreamlineSetup.h
new file mode 100644
index 000000000000..623e14f2b64a
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.h
@@ -0,0 +1,50 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __STREAMLINE_SETUP_H__
+#define __STREAMLINE_SETUP_H__
+
+#include <stdint.h>
+#include <string.h>
+
+class OlySocket;
+
+// Commands from Streamline
+enum {
+	COMMAND_REQUEST_XML = 0,
+	COMMAND_DELIVER_XML = 1,
+	COMMAND_APC_START   = 2,
+	COMMAND_APC_STOP    = 3,
+	COMMAND_DISCONNECT  = 4,
+	COMMAND_PING        = 5
+};
+
+class StreamlineSetup {
+public:
+	StreamlineSetup(OlySocket *socket);
+	~StreamlineSetup();
+private:
+	OlySocket* mSocket;
+
+	char* readCommand(int*);
+	void handleRequest(char* xml);
+	void handleDeliver(char* xml);
+	void sendData(const char* data, uint32_t length, char type);
+	void sendString(const char* string, int type) {sendData(string, strlen(string), type);}
+	void sendEvents();
+	void sendConfiguration();
+	void sendDefaults();
+	void sendCounters();
+	void writeConfiguration(char* xml);
+
+	// Intentionally unimplemented
+	StreamlineSetup(const StreamlineSetup &);
+	StreamlineSetup &operator=(const StreamlineSetup &);
+};
+
+#endif //__STREAMLINE_SETUP_H__
diff --git a/tools/gator/daemon/UEvent.cpp b/tools/gator/daemon/UEvent.cpp
new file mode 100644
index 000000000000..f94a995393e8
--- /dev/null
+++ b/tools/gator/daemon/UEvent.cpp
@@ -0,0 +1,77 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "UEvent.h"
+
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#include <linux/netlink.h>
+
+#include "Logging.h"
+#include "OlySocket.h"
+
+static const char EMPTY[] = "";
+static const char ACTION[] = "ACTION=";
+static const char DEVPATH[] = "DEVPATH=";
+static const char SUBSYSTEM[] = "SUBSYSTEM=";
+
+UEvent::UEvent() : mFd(-1) {
+}
+
+UEvent::~UEvent() {
+	if (mFd >= 0) {
+		close(mFd);
+	}
+}
+
+bool UEvent::init() {
+	mFd = socket_cloexec(PF_NETLINK, SOCK_RAW, NETLINK_KOBJECT_UEVENT);
+	if (mFd < 0) {
+		logg->logMessage("%s(%s:%i): socket failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	struct sockaddr_nl sockaddr;
+	memset(&sockaddr, 0, sizeof(sockaddr));
+	sockaddr.nl_family = AF_NETLINK;
+	sockaddr.nl_groups = 1; // bitmask: (1 << 0) == kernel events, (1 << 1) == udev events
+	sockaddr.nl_pid = 0;
+	if (bind(mFd, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) != 0) {
+		logg->logMessage("%s(%s:%i): bind failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	return true;
+}
+
+bool UEvent::read(UEventResult *const result) {
+	ssize_t bytes = recv(mFd, result->mBuf, sizeof(result->mBuf), 0);
+	if (bytes <= 0) {
+		logg->logMessage("%s(%s:%i): recv failed", __FUNCTION__, __FILE__, __LINE__);
+		return false;
+	}
+
+	result->mAction = EMPTY;
+	result->mDevPath = EMPTY;
+	result->mSubsystem = EMPTY;
+
+	for (int pos = 0; pos < bytes; pos += strlen(result->mBuf + pos) + 1) {
+		char *const str = result->mBuf + pos;
+		if (strncmp(str, ACTION, sizeof(ACTION) - 1) == 0) {
+			result->mAction = str + sizeof(ACTION) - 1;
+		} else if (strncmp(str, DEVPATH, sizeof(DEVPATH) - 1) == 0) {
+			result->mDevPath = str + sizeof(DEVPATH) - 1;
+		} else if (strncmp(str, SUBSYSTEM, sizeof(SUBSYSTEM) - 1) == 0) {
+			result->mSubsystem = str + sizeof(SUBSYSTEM) - 1;
+		}
+	}
+
+	return true;
+}
diff --git a/tools/gator/daemon/UEvent.h b/tools/gator/daemon/UEvent.h
new file mode 100644
index 000000000000..2f7ef2c93f5d
--- /dev/null
+++ b/tools/gator/daemon/UEvent.h
@@ -0,0 +1,36 @@
+/**
+ * Copyright (C) ARM Limited 2013-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef UEVENT_H
+#define UEVENT_H
+
+struct UEventResult {
+	const char *mAction;
+	const char *mDevPath;
+	const char *mSubsystem;
+	char mBuf[1<<13];
+};
+
+class UEvent {
+public:
+	UEvent();
+	~UEvent();
+
+	bool init();
+	bool read(UEventResult *const result);
+	int getFd() const { return mFd; }
+
+private:
+	int mFd;
+
+	// Intentionally undefined
+	UEvent(const UEvent &);
+	UEvent &operator=(const UEvent &);
+};
+
+#endif // UEVENT_H
diff --git a/tools/gator/daemon/UserSpaceSource.cpp b/tools/gator/daemon/UserSpaceSource.cpp
new file mode 100644
index 000000000000..4a9b22f4b555
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.cpp
@@ -0,0 +1,94 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "UserSpaceSource.h"
+
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+UserSpaceSource::UserSpaceSource(sem_t *senderSem) : mBuffer(0, FRAME_BLOCK_COUNTER, gSessionData->mTotalBufferSize*1024*1024, senderSem) {
+}
+
+UserSpaceSource::~UserSpaceSource() {
+}
+
+bool UserSpaceSource::prepare() {
+	return true;
+}
+
+void UserSpaceSource::run() {
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-counters", 0, 0, 0);
+
+	for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+		gSessionData->usDrivers[i]->start();
+	}
+
+	int64_t monotonic_started = 0;
+	while (monotonic_started <= 0) {
+		usleep(10);
+
+		if (gSessionData->perf.isSetup()) {
+			monotonic_started = gSessionData->mMonotonicStarted;
+		} else {
+			if (DriverSource::readInt64Driver("/dev/gator/started", &monotonic_started) == -1) {
+				logg->logError(__FILE__, __LINE__, "Error reading gator driver start time");
+				handleException();
+			}
+			gSessionData->mMonotonicStarted = monotonic_started;
+		}
+	}
+
+	uint64_t next_time = 0;
+	while (gSessionData->mSessionIsActive) {
+		const uint64_t curr_time = getTime() - monotonic_started;
+		// Sample ten times a second ignoring gSessionData->mSampleRate
+		next_time += NS_PER_S/10;//gSessionData->mSampleRate;
+		if (next_time < curr_time) {
+			logg->logMessage("Too slow, curr_time: %lli next_time: %lli", curr_time, next_time);
+			next_time = curr_time;
+		}
+
+		if (mBuffer.eventHeader(curr_time)) {
+			for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+				gSessionData->usDrivers[i]->read(&mBuffer);
+			}
+			// Only check after writing all counters so that time and corresponding counters appear in the same frame
+			mBuffer.check(curr_time);
+		}
+
+		if (mBuffer.bytesAvailable() <= 0) {
+			logg->logMessage("One shot (counters)");
+			child->endSession();
+		}
+
+		usleep((next_time - curr_time)/NS_PER_US);
+	}
+
+	mBuffer.setDone();
+}
+
+void UserSpaceSource::interrupt() {
+	// Do nothing
+}
+
+bool UserSpaceSource::isDone() {
+	return mBuffer.isDone();
+}
+
+void UserSpaceSource::write(Sender *sender) {
+	if (!mBuffer.isDone()) {
+		mBuffer.write(sender);
+	}
+}
diff --git a/tools/gator/daemon/UserSpaceSource.h b/tools/gator/daemon/UserSpaceSource.h
new file mode 100644
index 000000000000..9b3666016dc5
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef USERSPACESOURCE_H
+#define USERSPACESOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Source.h"
+
+// User space counters
+class UserSpaceSource : public Source {
+public:
+	UserSpaceSource(sem_t *senderSem);
+	~UserSpaceSource();
+
+	bool prepare();
+	void run();
+	void interrupt();
+
+	bool isDone();
+	void write(Sender *sender);
+
+private:
+	Buffer mBuffer;
+
+	// Intentionally unimplemented
+	UserSpaceSource(const UserSpaceSource &);
+	UserSpaceSource &operator=(const UserSpaceSource &);
+};
+
+#endif // USERSPACESOURCE_H
diff --git a/tools/gator/daemon/c++.cpp b/tools/gator/daemon/c++.cpp
new file mode 100644
index 000000000000..6041e5e96469
--- /dev/null
+++ b/tools/gator/daemon/c++.cpp
@@ -0,0 +1,40 @@
+/**
+ * Minimal set of C++ functions so that libstdc++ is not required
+ *
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+void operator delete(void *ptr) {
+  if (ptr != NULL) {
+    free(ptr);
+  }
+}
+
+void operator delete[](void *ptr) {
+  operator delete(ptr);
+}
+
+void *operator new(size_t size) {
+  void *ptr = malloc(size == 0 ? 1 : size);
+  if (ptr == NULL) {
+    abort();
+  }
+  return ptr;
+}
+
+void *operator new[](size_t size) {
+  return operator new(size);
+}
+
+extern "C"
+void __cxa_pure_virtual() {
+  printf("pure virtual method called\n");
+  abort();
+}
diff --git a/tools/gator/daemon/common.mk b/tools/gator/daemon/common.mk
new file mode 100644
index 000000000000..769a92e51a35
--- /dev/null
+++ b/tools/gator/daemon/common.mk
@@ -0,0 +1,52 @@
+# -g produces debugging information
+# -O3 maximum optimization
+# -O0 no optimization, used for debugging
+# -Wall enables most warnings
+# -Werror treats warnings as errors
+# -std=c++0x is the planned new c++ standard
+# -std=c++98 is the 1998 c++ standard
+CPPFLAGS += -O3 -Wall -fno-exceptions -pthread -MMD -DETCDIR=\"/etc\" -Ilibsensors
+CXXFLAGS += -fno-rtti -Wextra # -Weffc++
+ifeq ($(WERROR),1)
+	CPPFLAGS += -Werror
+endif
+# -s strips the binary of debug info
+LDFLAGS += -s
+LDLIBS += -lrt -lm -pthread
+TARGET = gatord
+C_SRC = $(wildcard mxml/*.c) $(wildcard libsensors/*.c)
+CXX_SRC = $(wildcard *.cpp)
+
+all: $(TARGET)
+
+events.xml: events_header.xml $(wildcard events-*.xml) events_footer.xml
+	cat $^ > $@
+
+include $(wildcard *.d)
+include $(wildcard mxml/*.d)
+
+EventsXML.cpp: events_xml.h
+ConfigurationXML.cpp: defaults_xml.h
+
+# Don't regenerate conf-lex.c or conf-parse.c
+libsensors/conf-lex.c: ;
+libsensors/conf-parse.c: ;
+
+%_xml.h: %.xml escape
+	./escape $< > $@
+
+%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+%.o: %.cpp
+	$(CXX) $(CXXFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+$(TARGET): $(CXX_SRC:%.cpp=%.o) $(C_SRC:%.c=%.o)
+	$(CC) $(LDFLAGS) $^ $(LDLIBS) -o $@
+
+# Intentionally ignore CC as a native binary is required
+escape: escape.c
+	gcc $^ -o $@
+
+clean:
+	rm -f *.d *.o mxml/*.d mxml/*.o libsensors/*.d libsensors/*.o $(TARGET) escape events.xml events_xml.h defaults_xml.h
diff --git a/tools/gator/daemon/defaults.xml b/tools/gator/daemon/defaults.xml
new file mode 100644
index 000000000000..086eca1e804e
--- /dev/null
+++ b/tools/gator/daemon/defaults.xml
@@ -0,0 +1,84 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configurations revision="3">
+  <configuration counter="ARM_ARM11_ccnt" event="0xff"/>
+  <configuration counter="ARM_ARM11_cnt0" event="0x7"/>
+  <configuration counter="ARM_ARM11_cnt1" event="0xb"/>
+  <configuration counter="ARM_ARM11MPCore_ccnt" event="0xff"/>
+  <configuration counter="ARM_ARM11MPCore_cnt0" event="0x08"/>
+  <configuration counter="ARM_ARM11MPCore_cnt1" event="0x0b"/>
+  <configuration counter="ARMv7_Cortex_A5_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A5_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A5_cnt1" event="0x1"/>
+  <configuration counter="ARMv7_Cortex_A7_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt0" event="0x08"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt1" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A7_cnt2" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A8_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt1" event="0x44"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt2" event="0x43"/>
+  <configuration counter="ARMv7_Cortex_A8_cnt3" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A9_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt0" event="0x68"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt1" event="0x06"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt2" event="0x07"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt3" event="0x03"/>
+  <configuration counter="ARMv7_Cortex_A9_cnt4" event="0x04"/>
+  <configuration counter="ARMv7_Cortex_A15_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt0" event="0x8"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt1" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt2" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A15_cnt3" event="0x19"/>
+  <configuration counter="ARMv7_Cortex_A17_ccnt" event="0xff"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt0" event="0x08"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt1" event="0x16"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt2" event="0x10"/>
+  <configuration counter="ARMv7_Cortex_A17_cnt3" event="0x19"/>
+  <configuration counter="ARM_Cortex-A53_ccnt" event="0x11"/>
+  <configuration counter="ARM_Cortex-A53_cnt0" event="0x8"/>
+  <configuration counter="ARM_Cortex-A53_cnt1" event="0x16"/>
+  <configuration counter="ARM_Cortex-A53_cnt2" event="0x10"/>
+  <configuration counter="ARM_Cortex-A53_cnt3" event="0x19"/>
+  <configuration counter="ARM_Cortex-A57_ccnt" event="0x11"/>
+  <configuration counter="ARM_Cortex-A57_cnt0" event="0x8"/>
+  <configuration counter="ARM_Cortex-A57_cnt1" event="0x16"/>
+  <configuration counter="ARM_Cortex-A57_cnt2" event="0x10"/>
+  <configuration counter="ARM_Cortex-A57_cnt3" event="0x19"/>
+  <configuration counter="Scorpion_ccnt" event="0xff"/>
+  <configuration counter="Scorpion_cnt0" event="0x08"/>
+  <configuration counter="Scorpion_cnt1" event="0x10"/>
+  <configuration counter="ScorpionMP_ccnt" event="0xff"/>
+  <configuration counter="ScorpionMP_cnt0" event="0x08"/>
+  <configuration counter="ScorpionMP_cnt1" event="0x10"/>
+  <configuration counter="Krait_ccnt" event="0xff"/>
+  <configuration counter="Krait_cnt0" event="0x08"/>
+  <configuration counter="Krait_cnt1" event="0x10"/>
+  <configuration counter="Linux_block_rq_wr"/>
+  <configuration counter="Linux_block_rq_rd"/>
+  <configuration counter="Linux_meminfo_memused"/>
+  <configuration counter="Linux_meminfo_memused2"/>
+  <configuration counter="Linux_meminfo_memfree"/>
+  <configuration counter="Linux_power_cpu_freq"/>
+  <configuration counter="ARM_Mali-4xx_fragment"/>
+  <configuration counter="ARM_Mali-4xx_vertex"/>
+  <configuration counter="ARM_Mali-Midgard_fragment" cores="1"/>
+  <configuration counter="ARM_Mali-Midgard_vertex" cores="1"/>
+  <configuration counter="ARM_Mali-Midgard_opencl" cores="1"/>
+  <configuration counter="ARM_Mali-T60x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T60x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T60x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T60x_JS2_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T62x_JS2_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T72x_JS2_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_GPU_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_JS0_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_JS1_ACTIVE"/>
+  <configuration counter="ARM_Mali-T76x_JS2_ACTIVE"/>
+  <configuration counter="L2C-310_cnt0" event="0x1"/>
+</configurations>
diff --git a/tools/gator/daemon/escape.c b/tools/gator/daemon/escape.c
new file mode 100644
index 000000000000..2b0863aaf425
--- /dev/null
+++ b/tools/gator/daemon/escape.c
@@ -0,0 +1,75 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * The Makefile in the daemon folder builds and executes 'escape'
+ * 'escape' creates configuration_xml.h from configuration.xml and events_xml.h from events-*.xml
+ * these genereated xml files are then #included and built as part of the gatord binary
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+static void print_escaped_path(char *path) {
+  if (isdigit(*path)) {
+    printf("__");
+  }
+  for (; *path != '\0'; ++path) {
+    printf("%c", isalnum(*path) ? *path : '_');
+  }
+}
+
+int main(int argc, char *argv[]) {
+  int i;
+  char *path;
+  FILE *in = NULL;
+  int ch;
+  unsigned int len = 0;
+
+  for (i = 1; i < argc && argv[i][0] == '-'; ++i) ;
+  if (i == argc) {
+    fprintf(stderr, "Usage: %s <filename>\n", argv[0]);
+    return EXIT_FAILURE;
+  }
+  path = argv[i];
+
+  errno = 0;
+  if ((in = fopen(path, "r")) == NULL) {
+    fprintf(stderr, "Unable to open '%s': %s\n", path, strerror(errno));
+    return EXIT_FAILURE;
+  }
+
+  printf("static const unsigned char ");
+  print_escaped_path(path);
+  printf("[] = {");
+  for (;;) {
+    ch = fgetc(in);
+    if (len != 0) {
+      printf(",");
+    }
+    if (len % 12 == 0) {
+      printf("\n ");
+    }
+    // Write out a null character after the contents of the file but do not increment len
+    printf(" 0x%.2x", (ch == EOF ? 0 : ch));
+    if (ch == EOF) {
+      break;
+    }
+    ++len;
+  }
+  printf("\n};\nstatic const unsigned int ");
+  print_escaped_path(path);
+  printf("_len = %i;\n", len);
+
+  fclose(in);
+
+  return EXIT_SUCCESS;
+}
diff --git a/tools/gator/daemon/events-ARM11.xml b/tools/gator/daemon/events-ARM11.xml
new file mode 100644
index 000000000000..57e323546314
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11.xml
@@ -0,0 +1,39 @@
+  <counter_set name="ARM_ARM11_cnt" count="3"/>
+  <category name="ARM11" counter_set="ARM_ARM11_cnt" per_cpu="yes">
+    <event counter="ARM_ARM11_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+    <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+    <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+    <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x05" title="Branch" name="Instruction executed" description="Branch instruction executed, branch might or might not have changed program flow"/>
+    <event event="0x06" title="Branch" name="Mispredicted" description="Branch mis-predicted"/>
+    <event event="0x07" title="Instruction" name="Executed" description="Instructions executed"/>
+    <event event="0x09" title="Cache" name="Data access" description="Data cache access, not including Cache operations"/>
+    <event event="0x0a" title="Cache" name="Data all access" description="Data cache access, not including Cache Operations regardless of whether or not the location is cacheable"/>
+    <event event="0x0b" title="Cache" name="Data miss" description="Data cache miss, not including Cache Operations"/>
+    <event event="0x0c" title="Cache" name="Write-back" description="Data cache write-back"/>
+    <event event="0x0d" title="Program Counter" name="SW change" description="Software changed the PC"/>
+    <event event="0x0f" title="Cache " name="TLB miss" description="Main TLB miss (unused on ARM1156)"/>
+    <event event="0x10" title="External" name="Access" description="Explicit external data or peripheral access"/>
+    <event event="0x11" title="Cache" name="Data miss" description="Stall because of Load Store Unit request queue being full"/>
+    <event event="0x12" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of a Data Synchronization Barrier command or Strongly Ordered operation"/>
+    <event event="0x13" title="Disable Interrupts" name="FIQ" description="The number of cycles which FIQ interrupts are disabled (ARM1156 only)"/>
+    <event event="0x14" title="Disable Interrupts" name="IRQ" description="The number of cycles which IRQ interrupts are disabled (ARM1156 only)"/>
+    <event event="0x20" title="ETM" name="ETMEXTOUT[0]" description="ETMEXTOUT[0] signal was asserted for a cycle"/>
+    <event event="0x21" title="ETM" name="ETMEXTOUT[1]" description="ETMEXTOUT[1] signal was asserted for a cycle"/>
+    <event event="0x22" title="ETM" name="ETMEXTOUT[0,1]" description="ETMEXTOUT[0] or ETMEXTOUT[1] was asserted"/>
+    <event event="0x23" title="Procedure" name="Calls" description="Procedure call instruction executed"/>
+    <event event="0x24" title="Procedure" name="Returns" description="Procedure return instruction executed"/>
+    <event event="0x25" title="Procedure" name="Return and predicted" description="Procedure return instruction executed and return address predicted"/>
+    <event event="0x26" title="Procedure" name="Return and mispredicted" description="Procedure return instruction executed and return address predicted incorrectly"/>
+    <event event="0x30" title="Cache" name="Inst tag or parity error" description="Instruction cache Tag or Valid RAM parity error (ARM1156 only)"/>
+    <event event="0x31" title="Cache" name="Inst parity error" description="Instruction cache RAM parity error (ARM1156 only)"/>
+    <event event="0x32" title="Cache" name="Data tag or parity error" description="Data cache Tag or Valid RAM parity error (ARM1156 only)"/>
+    <event event="0x33" title="Cache" name="Data parity error" description="Data cache RAM parity error (ARM1156 only)"/>
+    <event event="0x34" title="ITCM" name="Error" description="ITCM error (ARM1156 only)"/>
+    <event event="0x35" title="DTCM" name="Error" description="DTCM error (ARM1156 only)"/>
+    <event event="0x36" title="Procedure" name="Return address pop" description="Procedure return address popped off the return stack (ARM1156 only)"/>
+    <event event="0x37" title="Procedure" name="Return address misprediction" description="Procedure return address popped off the return stack has been incorrectly predicted by the PFU (ARM1156 only)"/>
+    <event event="0x38" title="Cache" name="Data dirty parity error" description="Data cache Dirty RAM parity error (ARM1156 only)"/>
+  </category>
diff --git a/tools/gator/daemon/events-ARM11MPCore.xml b/tools/gator/daemon/events-ARM11MPCore.xml
new file mode 100644
index 000000000000..2d5c5e199e66
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11MPCore.xml
@@ -0,0 +1,26 @@
+  <counter_set name="ARM_ARM11MPCore_cnt" count="3"/>
+  <category name="ARM11MPCore" counter_set="ARM_ARM11MPCore_cnt" per_cpu="yes">
+    <event counter="ARM_ARM11MPCore_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+    <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+    <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+    <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+    <event event="0x05" title="Branch" name="Instruction executed" description="Branch instructions executed, branch might or might not have changed program flow"/>
+    <event event="0x06" title="Branch" name="Not predicted" description="Branch not predicted"/>
+    <event event="0x07" title="Branch" name="Mispredicted" description="Branch mispredicted"/>
+    <event event="0x08" title="Core" name="Instructions" description="Instructions executed"/>
+    <event event="0x09" title="Core" name="Folded Instructions" description="Folded instructions executed"/>
+    <event event="0x0a" title="Cache" name="Data read access" description="Data cache read access, not including cache operations"/>
+    <event event="0x0b" title="Cache" name="Data read miss" description="Data cache miss, not including Cache Operations"/>
+    <event event="0x0c" title="Cache" name="Data write access" description="Data cache write access"/>
+    <event event="0x0d" title="Cache" name="Data write miss" description="Data cache write miss"/>
+    <event event="0x0e" title="Cache" name="Data line eviction" description="Data cache line eviction, not including cache operations"/>
+    <event event="0x0f" title="Branch" name="PC change w/o mode change" description="Software changed the PC and there is not a mode change"/>
+    <event event="0x10" title="Cache " name="TLB miss" description="Main TLB miss"/>
+    <event event="0x11" title="External" name="External Memory request" description="External memory request (cache refill, noncachable, write-back)"/>
+    <event event="0x12" title="Cache" name="Stall" description="Stall because of Load Store Unit request queue being full"/>
+    <event event="0x13" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of LSU ordering constraints or CP15 operations (Data Synchronization Barrier command) or Strongly Ordered operation"/>
+    <event event="0x14" title="Write Buffer" name="Write Merges" description="Buffered write merged in a store buffer slot"/>
+    <event event="0xFF" title="Core" name="Cycle counter" description="An increment each cycle"/>
+  </category>
diff --git a/tools/gator/daemon/events-CCI-400.xml b/tools/gator/daemon/events-CCI-400.xml
new file mode 100644
index 000000000000..20002efd1543
--- /dev/null
+++ b/tools/gator/daemon/events-CCI-400.xml
@@ -0,0 +1,98 @@
+  <counter_set name="CCI_400_cnt" count="4"/>
+  <category name="CCI-400" counter_set="CCI_400_cnt" per_cpu="no" supports_event_based_sampling="yes">
+    <event counter="CCI_400_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="Slave">
+      <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+      <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+      <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+      <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+      <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+    </option_set>
+    <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+    <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+    <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+    <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+    <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation, CleanInvalid, CleanShared, MakeInvalid"/>
+    <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+    <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+    <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+    <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+    <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+    <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+    <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+    <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+    <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+    <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+    <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+    <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+    <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+    <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+    <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+    <option_set name="Master">
+      <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+      <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+      <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+    </option_set>
+    <event event="0x14" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+    <event event="0x15" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Read request stall cycle because of an address hazard"/>
+    <event event="0x16" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of an ID hazard"/>
+    <event event="0x17" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="Read request stall cycle because the transaction tracker is full. Increase MIx_R_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+    <event event="0x18" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+    <event event="0x19" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+    <event event="0x1a" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase MIx_W_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+  </category>
+  <counter_set name="CCI_400-r1_cnt" count="4"/>
+  <category name="CCI-400" counter_set="CCI_400-r1_cnt" per_cpu="no" supports_event_based_sampling="yes">
+    <event counter="CCI_400-r1_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="Slave">
+      <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+      <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+      <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+      <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+      <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+    </option_set>
+    <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+    <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+    <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+    <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+    <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation"/>
+    <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+    <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+    <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+    <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+    <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+    <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+    <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+    <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+    <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+    <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+    <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+    <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+    <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+    <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+    <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+    <event event="0x14" option_set="Slave" title="CCI-400" name="Read stall: slave hazard" description="Read request stall cycle because of a slave interface ID hazard"/>
+    <option_set name="Master">
+      <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+      <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+      <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+    </option_set>
+    <event event="0x00" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+    <event event="0x01" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Stall cycle because of an address hazard. A read or write invalidation is stalled because of an outstanding transaction to an overlapping address"/>
+    <event event="0x02" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of a master interface ID hazard"/>
+    <event event="0x03" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="A read request with a QoS value in the high priority group is stalled for a cycle because the read transaction queue is full. Increase MIx_R_MAX to avoid this stall"/>
+    <event event="0x04" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+    <event event="0x05" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+    <event event="0x06" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="A write request is stalled for a cycle because the write transaction tracker is full. Increase MIx_W_MAX to avoid this stall"/>
+    <event event="0x07" option_set="Master" title="CCI-400" name="Read Stall: Low Priority" description="A read request with a QoS value in the low priority group is stalled for a cycle because there are no slots available in the read queue for the low priority group"/>
+    <event event="0x08" option_set="Master" title="CCI-400" name="Read Stall: Medium Priority" description="A read request with a QoS value in the medium priority group is stalled for a cycle because there are no slots available in the read queue for the medium priority group"/>
+    <event event="0x09" option_set="Master" title="CCI-400" name="Read Stall: VN0" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+    <event event="0x0a" option_set="Master" title="CCI-400" name="Read Stall: VN1" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+    <event event="0x0b" option_set="Master" title="CCI-400" name="Read Stall: VN2" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+    <event event="0x0c" option_set="Master" title="CCI-400" name="Read Stall: VN3" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN3"/>
+    <event event="0x0d" option_set="Master" title="CCI-400" name="Write Stall: VN0" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+    <event event="0x0e" option_set="Master" title="CCI-400" name="Write Stall: VN1" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+    <event event="0x0f" option_set="Master" title="CCI-400" name="Write Stall: VN2" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+    <event event="0x10" option_set="Master" title="CCI-400" name="Write Stall: VN" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN"/>
+    <event event="0x11" option_set="Master" title="CCI-400" name="WriteUnique or WriteLineUnique Stall" description="A WriteUnique or WriteLineUnique request is stalled for a cycle because of an address hazard"/>
+  </category>
diff --git a/tools/gator/daemon/events-CCN-504.xml b/tools/gator/daemon/events-CCN-504.xml
new file mode 100644
index 000000000000..6ef3e6483717
--- /dev/null
+++ b/tools/gator/daemon/events-CCN-504.xml
@@ -0,0 +1,113 @@
+  <counter_set name="CCN-504_cnt" count="4"/>
+  <category name="CCN-504" counter_set="CCN-504_cnt">
+    <event counter="CCN-504_ccnt" title="CCN-504 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+    <option_set name="XP_Region">
+      <option event_delta="0x400000" name="XP 0" description="Crosspoint 0"/>
+      <option event_delta="0x410000" name="XP 1" description="Crosspoint 1"/>
+      <option event_delta="0x420000" name="XP 2" description="Crosspoint 2"/>
+      <option event_delta="0x430000" name="XP 3" description="Crosspoint 3"/>
+      <option event_delta="0x440000" name="XP 4" description="Crosspoint 4"/>
+      <option event_delta="0x450000" name="XP 5" description="Crosspoint 5"/>
+      <option event_delta="0x460000" name="XP 6" description="Crosspoint 6"/>
+      <option event_delta="0x470000" name="XP 7" description="Crosspoint 7"/>
+      <option event_delta="0x480000" name="XP 8" description="Crosspoint 8"/>
+      <option event_delta="0x490000" name="XP 9" description="Crosspoint 9"/>
+      <option event_delta="0x4A0000" name="XP 10" description="Crosspoint 10"/>
+    </option_set>
+    <event event="0x0801" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: H-bit" description="Bus 0: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0802" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: S-bit" description="Bus 0: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0803" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: P-Cnt" description="Bus 0: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0804" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: TknV" description="Bus 0: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0809" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: H-bit" description="Bus 1: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x080A" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: S-bit" description="Bus 1: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x080B" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: P-Cnt" description="Bus 1: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x080C" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: TknV" description="Bus 1: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0811" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: H-bit" description="Bus 0: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0812" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: S-bit" description="Bus 0: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0813" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: P-Cnt" description="Bus 0: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0814" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: TknV" description="Bus 0: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0819" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: H-bit" description="Bus 1: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x081A" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: S-bit" description="Bus 1: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x081B" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: P-Cnt" description="Bus 1: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x081C" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: TknV" description="Bus 1: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0821" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: H-bit" description="Bus 0: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0822" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: S-bit" description="Bus 0: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0823" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: P-Cnt" description="Bus 0: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0824" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: TknV" description="Bus 0: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0829" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: H-bit" description="Bus 1: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x082A" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: S-bit" description="Bus 1: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x082B" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: P-Cnt" description="Bus 1: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x082C" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: TknV" description="Bus 1: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0831" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: H-bit" description="Bus 0: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0832" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: S-bit" description="Bus 0: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0833" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: P-Cnt" description="Bus 0: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0834" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: TknV" description="Bus 0: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0839" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: H-bit" description="Bus 1: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x083A" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: S-bit" description="Bus 1: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x083B" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: P-Cnt" description="Bus 1: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x083C" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: TknV" description="Bus 1: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0871" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: H-bit" description="Bus 0: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x0872" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: S-bit" description="Bus 0: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x0873" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: P-Cnt" description="Bus 0: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x0874" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: TknV" description="Bus 0: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+    <event event="0x0879" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: H-bit" description="Bus 1: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+    <event event="0x087A" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: S-bit" description="Bus 1: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+    <event event="0x087B" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: P-Cnt" description="Bus 1: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+    <event event="0x087C" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: TknV" description="Bus 1: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+    <option_set name="HN-F_Region">
+      <option event_delta="0x200000" name="HN-F 3" description="Fully-coherent Home Node 3"/>
+      <option event_delta="0x210000" name="HN-F 5" description="Fully-coherent Home Node 5"/>
+      <option event_delta="0x220000" name="HN-F 7" description="Fully-coherent Home Node 7"/>
+      <option event_delta="0x230000" name="HN-F 8" description="Fully-coherent Home Node 8"/>
+      <option event_delta="0x240000" name="HN-F 13" description="Fully-coherent Home Node 13"/>
+      <option event_delta="0x250000" name="HN-F 15" description="Fully-coherent Home Node 15"/>
+      <option event_delta="0x260000" name="HN-F 17" description="Fully-coherent Home Node 17"/>
+      <option event_delta="0x270000" name="HN-F 18" description="Fully-coherent Home Node 18"/>
+    </option_set>
+    <event event="0x0401" option_set="HN-F_Region" title="CCN-504" name="Cache Miss" description="Counts the total cache misses. This is the first time lookup result, and is high priority."/>
+    <event event="0x0402" option_set="HN-F_Region" title="CCN-504" name="L3 SF Cache Access" description="Counts the number of cache accesses. This is the first time access, and is high priority."/>
+    <event event="0x0403" option_set="HN-F_Region" title="CCN-504" name="Cache Fill" description="Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache."/>
+    <event event="0x0404" option_set="HN-F_Region" title="CCN-504" name="POCQ Retry" description="Counts the number of requests that have been retried."/>
+    <event event="0x0405" option_set="HN-F_Region" title="CCN-504" name="POCQ Reqs Recvd" description="Counts the number of requests received by HN."/>
+    <event event="0x0406" option_set="HN-F_Region" title="CCN-504" name="SF Hit" description="Counts the number of snoop filter hits."/>
+    <event event="0x0407" option_set="HN-F_Region" title="CCN-504" name="SF Evictions" description="Counts the number of snoop filter evictions. Cache invalidations are initiated."/>
+    <event event="0x0408" option_set="HN-F_Region" title="CCN-504" name="Snoops Sent" description="Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops."/>
+    <event event="0x0409" option_set="HN-F_Region" title="CCN-504" name="Snoops Broadcast" description="Counts the number of snoop broadcasts sent."/>
+    <event event="0x040A" option_set="HN-F_Region" title="CCN-504" name="L3 Eviction" description="Counts the number of L3 evictions."/>
+    <event event="0x040B" option_set="HN-F_Region" title="CCN-504" name="L3 Fill Invalid Way" description="Counts the number of L3 fills to an invalid way."/>
+    <event event="0x040C" option_set="HN-F_Region" title="CCN-504" name="MC Retries" description="Counts the number of transactions retried by the memory controller."/>
+    <event event="0x040D" option_set="HN-F_Region" title="CCN-504" name="MC Reqs" description="Counts the number of requests to the memory controller."/>
+    <event event="0x040E" option_set="HN-F_Region" title="CCN-504" name="QOS HH Retry" description="Counts the number of times a highest-priority QoS class was retried at the HN-F."/>
+    <option_set name="RN-I_Region">
+      <option event_delta="0x800000" name="RN-I 0" description="I/O-coherent Requesting Node 0"/>
+      <option event_delta="0x820000" name="RN-I 2" description="I/O-coherent Requesting Node 2"/>
+      <option event_delta="0x860000" name="RN-I 6" description="I/O-coherent Requesting Node 6"/>
+      <option event_delta="0x8C0000" name="RN-I 12" description="I/O-coherent Requesting Node 12"/>
+      <option event_delta="0x900000" name="RN-I 16" description="I/O-coherent Requesting Node 16"/>
+      <option event_delta="0x940000" name="RN-I 20" description="I/O-coherent Requesting Node 20"/>
+    </option_set>
+    <event event="0x1601" option_set="RN-I_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+    <event event="0x1602" option_set="RN-I_Region" title="CCN-504" name="S1 RDataBeats" description="S1 RDataBeats."/>
+    <event event="0x1603" option_set="RN-I_Region" title="CCN-504" name="S2 RDataBeats" description="S2 RDataBeats."/>
+    <event event="0x1604" option_set="RN-I_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+    <event event="0x1605" option_set="RN-I_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+    <event event="0x1606" option_set="RN-I_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+    <event event="0x1607" option_set="RN-I_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+    <event event="0x1608" option_set="RN-I_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+    <event event="0x1609" option_set="RN-I_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+    <event event="0x160A" option_set="RN-I_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+    <option_set name="SBAS_Region">
+      <option event_delta="0x810000" name="SBAS 1" description="ACE master to CHI protocol bridge 1"/>
+      <option event_delta="0x890000" name="SBAS 9" description="ACE master to CHI protocol bridge 9"/>
+      <option event_delta="0x8B0000" name="SBAS 11" description="ACE master to CHI protocol bridge 11"/>
+      <option event_delta="0x930000" name="SBAS 19" description="ACE master to CHI protocol bridge 19"/>
+    </option_set>
+    <event event="0x1001" option_set="SBAS_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+    <event event="0x1004" option_set="SBAS_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+    <event event="0x1005" option_set="SBAS_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+    <event event="0x1006" option_set="SBAS_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+    <event event="0x1007" option_set="SBAS_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+    <event event="0x1008" option_set="SBAS_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+    <event event="0x1009" option_set="SBAS_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+    <event event="0x100A" option_set="SBAS_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A15.xml b/tools/gator/daemon/events-Cortex-A15.xml
new file mode 100644
index 000000000000..f50e55d66195
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A15.xml
@@ -0,0 +1,68 @@
+  <counter_set name="ARMv7_Cortex_A15_cnt" count="6"/>
+  <category name="Cortex-A15" counter_set="ARMv7_Cortex_A15_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A15_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Software increment architecturally executed"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus - Access"/>
+    <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Write to translation table base architecturally executed"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus - Cycle"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-Back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-Back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4c" title="TLB" name="L1 data refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4d" title="TLB" name="L1 data refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-Back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-Back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed - LDREX"/>
+    <event event="0x6d" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Instruction speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Instruction speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed - Software change of the PC"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7a" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A17.xml b/tools/gator/daemon/events-Cortex-A17.xml
new file mode 100644
index 000000000000..4dd08c1f203d
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A17.xml
@@ -0,0 +1,86 @@
+  <counter_set name="ARMv7_Cortex_A17_cnt" count="6"/>
+  <category name="Cortex-A17" counter_set="ARMv7_Cortex_A17_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A17_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus - Access"/>
+    <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+    <event event="0x1c" title="Memory" name="Translation table" description="Write to translation table base architecturally executed"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus - Cycle"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-Back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-Back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed - LDREX"/>
+    <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed - STREX fail"/>
+    <event event="0x6f" title="Intrinsic" name="STREX" description="Exclusive instruction speculatively executed - STREX"/>
+    <event event="0x70" title="Instruction" name="Load" description="Instruction speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Instruction speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed - Software change of the PC"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7a" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x8a" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0xc0" title="Instruction" name="Stalled Linefill" description="Instruction side stalled due to a Linefill"/>
+    <event event="0xc1" title="Instruction" name="Stalled Page Table Walk" description="Instruction Side stalled due to a Page Table Walk"/>
+    <event event="0xc2" title="Cache" name="4 Ways Read" description="Number of set of 4 ways read in the instruction cache - Tag RAM"/>
+    <event event="0xc3" title="Cache" name="Ways Read" description="Number of ways read in the instruction cache - Data RAM"/>
+    <event event="0xc4" title="Cache" name="BATC Read" description="Number of ways read in the instruction BTAC RAM"/>
+    <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A17 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data"/>
+    <event event="0xd3" title="Slots" name="Load-Store Unit" description="Duration during which all slots in the Load-Store Unit are busy"/>
+    <event event="0xd8" title="Slots" name="Load-Store Issue Queue" description="Duration during which all slots in the Load-Store Issue queue are busy"/>
+    <event event="0xd9" title="Slots" name="Data Processing Issue Queue" description="Duration during which all slots in the Data Processing issue queue are busy"/>
+    <event event="0xda" title="Slots" name="Data Engine Issue Queue" description="Duration during which all slots in the Data Engine issue queue are busy"/>
+    <event event="0xdb" title="NEON" name="Flush" description="Number of NEON instruction which fail their condition code and lead to a flush of the DE pipe"/>
+    <event event="0xdc" title="Hypervisor" name="Traps" description="Number of Trap to hypervisor"/>
+    <event event="0xde" title="PTM" name="EXTOUT 0" description="PTM EXTOUT 0"/>
+    <event event="0xdf" title="PTM" name="EXTOUT 1" description="PTM EXTOUT 1"/>
+    <event event="0xe0" title="MMU" name="Table Walk" description="Duration during which the MMU handle a Page table walk"/>
+    <event event="0xe1" title="MMU" name="Stage1 Table Walk" description="Duration during which the MMU handle a Stage1 Page table walk"/>
+    <event event="0xe2" title="MMU" name="Stage2 Table Walk" description="Duration during which the MMU handle a Stage2 Page table walk"/>
+    <event event="0xe3" title="MMU" name="LSU Table Walk" description="Duration during which the MMU handle a Page table walk requested by the Load Store Unit"/>
+    <event event="0xe4" title="MMU" name="Instruction Table Walk" description="Duration during which the MMU handle a Page table walk requested by the Instruction side"/>
+    <event event="0xe5" title="MMU" name="Preload Table Walk" description="Duration during which the MMU handle a Page table walk requested by a Preload instruction or Prefetch request"/>
+    <event event="0xe6" title="MMU" name="cp15 Table Walk" description="Duration during which the MMU handle a Page table walk requested by a cp15 operation (maintenance by MVA and VA-to-PA operation)"/>
+    <event event="0xe7" title="Cache" name="L1 PLD TLB refill" description="Level 1 PLD TLB refill"/>
+    <event event="0xe8" title="Cache" name="L1 CP15 TLB refill" description="Level 1 CP15 TLB refill"/>
+    <event event="0xe9" title="Cache" name="L1 TLB flush" description="Level 1 TLB flush"/>
+    <event event="0xea" title="Cache" name="L2 TLB access" description="Level 2 TLB access"/>
+    <event event="0xeb" title="Cache" name="L2 TLB miss" description="Level 2 TLB miss"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A5.xml b/tools/gator/daemon/events-Cortex-A5.xml
new file mode 100644
index 000000000000..d67581d77c08
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A5.xml
@@ -0,0 +1,36 @@
+  <counter_set name="ARMv7_Cortex_A5_cnt" count="2"/>
+  <category name="Cortex-A5" counter_set="ARMv7_Cortex_A5_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A5_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Procedure" name="Return" description="Procedure return, other than exception return, architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="Instruction access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="Data eviction" description="Data cache eviction"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="IRQ exception taken"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="FIQ exception taken"/>
+    <event event="0xC0" title="Memory" name="External request" description="External memory request"/>
+    <event event="0xC1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+    <event event="0xC2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+    <event event="0xC3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+    <event event="0xC4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+    <event event="0xC5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+    <event event="0xC7" title="ETM" name="ETM Ext Out[0]" description="ETM - ETM Ext Out[0]"/>
+    <event event="0xC8" title="ETM" name="ETM Ext Out[1]" description="ETM - ETM Ext Out[1]"/>
+    <event event="0xC9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A53.xml b/tools/gator/daemon/events-Cortex-A53.xml
new file mode 100644
index 000000000000..5ba17907d5ab
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A53.xml
@@ -0,0 +1,87 @@
+  <counter_set name="ARM_Cortex-A53_cnt" count="6"/>
+  <category name="Cortex-A53" counter_set="ARM_Cortex-A53_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARM_Cortex-A53_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1A" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1B" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+    <event event="0x1C" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+    <event event="0x1D" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x1E" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4C" title="Cache" name="L1 data refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4D" title="Cache" name="L1 data refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6A" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6C" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+    <event event="0x6D" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6E" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+    <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7A" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7C" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7D" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7E" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+    <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+    <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+    <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+    <event event="0x8A" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0x8B" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+    <event event="0x8C" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort or SError not taken locally"/>
+    <event event="0x8D" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+    <event event="0x8E" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+    <event event="0x8F" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+    <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load Acquire"/>
+    <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store Release"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A57.xml b/tools/gator/daemon/events-Cortex-A57.xml
new file mode 100644
index 000000000000..fbe96c2d4eb2
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A57.xml
@@ -0,0 +1,87 @@
+  <counter_set name="ARM_Cortex-A57_cnt" count="6"/>
+  <category name="Cortex-A57" counter_set="ARM_Cortex-A57_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARM_Cortex-A57_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+    <event event="0x1A" title="Memory" name="Error" description="Local memory error"/>
+    <event event="0x1B" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+    <event event="0x1C" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+    <event event="0x1D" title="Bus" name="Cycle" description="Bus cycle"/>
+    <event event="0x1E" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+    <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+    <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+    <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+    <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+    <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+    <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+    <event event="0x4C" title="Cache" name="L1 data refill read" description="Level 1 data TLB refill - Read"/>
+    <event event="0x4D" title="Cache" name="L1 data refill write" description="Level 1 data TLB refill - Write"/>
+    <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+    <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+    <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+    <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+    <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+    <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+    <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+    <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+    <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+    <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+    <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+    <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+    <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+    <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+    <event event="0x6A" title="Memory" name="Unaligned" description="Unaligned access"/>
+    <event event="0x6C" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+    <event event="0x6D" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+    <event event="0x6E" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+    <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+    <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+    <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+    <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+    <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+    <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+    <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+    <event event="0x78" title="Instruction" name="Immediate branch" description="Branch speculatively executed - Immediate branch"/>
+    <event event="0x79" title="Instruction" name="Procedure return" description="Branch speculatively executed - Procedure return"/>
+    <event event="0x7A" title="Instruction" name="Indirect branch" description="Branch speculatively executed - Indirect branch"/>
+    <event event="0x7C" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+    <event event="0x7D" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+    <event event="0x7E" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+    <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+    <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+    <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+    <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+    <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+    <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+    <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+    <event event="0x8A" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+    <event event="0x8B" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+    <event event="0x8C" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort or SError not taken locally"/>
+    <event event="0x8D" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+    <event event="0x8E" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+    <event event="0x8F" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+    <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load Acquire"/>
+    <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store Release"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A7.xml b/tools/gator/daemon/events-Cortex-A7.xml
new file mode 100644
index 000000000000..6e078b3cffa3
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A7.xml
@@ -0,0 +1,43 @@
+  <counter_set name="ARMv7_Cortex_A7_cnt" count="4"/>
+  <category name="Cortex-A7" counter_set="ARMv7_Cortex_A7_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A7_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Software increment architecturally executed"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Memory" name="Data Read" description="Data read architecturally executed"/>
+    <event event="0x07" title="Memory" name="Data Write" description="Data write architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+    <event event="0x14" title="Cache" name="L1 inst access" description="Instruction cache access"/>
+    <event event="0x15" title="Cache" name="L1 data eviction" description="Level 1 data cache eviction"/>
+    <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+    <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+    <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+    <event event="0x19" title="Bus" name="Access" description="Bus - Access"/>
+    <event event="0x1d" title="Bus" name="Cycle" description="Bus - Cycle"/>
+    <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+    <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+    <event event="0x86" title="Exception" name="IRQ" description="IRQ exception taken"/>
+    <event event="0x87" title="Exception" name="FIQ" description="FIQ exception taken"/>
+    <event event="0xC0" title="Memory" name="External request" description="External memory request"/>
+    <event event="0xC1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+    <event event="0xC2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+    <event event="0xC3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+    <event event="0xC4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+    <event event="0xC5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+    <event event="0xC7" title="ETM" name="ETM Ext Out[0]" description="ETM - ETM Ext Out[0]"/>
+    <event event="0xC8" title="ETM" name="ETM Ext Out[1]" description="ETM - ETM Ext Out[1]"/>
+    <event event="0xC9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+    <event event="0xCA" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local cluster, rather than accessing the L2 cache or issuing an external read."/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A8.xml b/tools/gator/daemon/events-Cortex-A8.xml
new file mode 100644
index 000000000000..a69e25ab2c34
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A8.xml
@@ -0,0 +1,52 @@
+  <counter_set name="ARMv7_Cortex_A8_cnt" count="4"/>
+  <category name="Cortex-A8" counter_set="ARMv7_Cortex_A8_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A8_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Procedure" name="Return" description="Procedure return, other than exception return, architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x40" title="Cache" name="Write buffer full" description="Any write buffer full cycle"/>
+    <event event="0x41" title="Cache" name="L2 store" description="Any store that is merged in the L2 memory system"/>
+    <event event="0x42" title="Cache" name="Bufferable transaction" description="Any bufferable store transaction from load/store to L2 cache, excluding eviction or cast out data"/>
+    <event event="0x43" title="Cache" name="L2 access" description="Any accesses to the L2 cache"/>
+    <event event="0x44" title="Cache" name="L2 miss" description="Any cacheable miss in the L2 cache"/>
+    <event event="0x45" title="AXI" name="Read" description="The number of AXI read data transfers"/>
+    <event event="0x46" title="AXI" name="Write" description="The number of AXI write data transfers"/>
+    <event event="0x47" title="Memory" name="Replay event" description="Any replay event in the memory system"/>
+    <event event="0x48" title="Memory" name="Unaligned access replay" description="Any unaligned memory access that results in a replay"/>
+    <event event="0x49" title="Cache" name="L1 data hash miss" description="Any L1 data memory access that misses in the cache as a result of the hashing algorithm"/>
+    <event event="0x4a" title="Cache" name="L1 inst hash miss" description="Any L1 instruction memory access that misses in the cache as a result of the hashing algorithm"/>
+    <event event="0x4b" title="Cache" name="L1 page coloring" description="Any L1 data memory access in which a page coloring alias occurs"/>
+    <event event="0x4c" title="NEON" name="L1 cache hit" description="Any NEON access that hits in the L1 data cache"/>
+    <event event="0x4d" title="NEON" name="L1 cache access" description="Any NEON cacheable data accesses for L1 data cache"/>
+    <event event="0x4e" title="NEON" name="L2 cache access" description="Any L2 cache accesses as a result of a NEON memory access"/>
+    <event event="0x4f" title="NEON" name="L2 cache hit" description="Any NEON hit in the L2 cache"/>
+    <event event="0x50" title="Cache" name="L1 inst access" description="Any L1 instruction cache access, excluding CP15 cache accesses"/>
+    <event event="0x51" title="Branch" name="Return stack misprediction" description="Any return stack misprediction because of incorrect target address for a taken return stack pop"/>
+    <event event="0x52" title="Branch" name="Direction misprediction" description="Branch direction misprediction"/>
+    <event event="0x53" title="Branch" name="Taken prediction" description="Any predictable branch that is predicted to be taken"/>
+    <event event="0x54" title="Branch" name="Executed and taken prediction" description="Any predictable branch that is executed and taken"/>
+    <event event="0x55" title="Core" name="Operations issued" description="Number of operations issued, where an operation is either: an instruction or one operation in a sequence of operations that make up a multi-cycle instruction"/>
+    <event event="0x56" title="Core" name="No issue cycles" description="Increment for every cycle that no instructions are available for issue"/>
+    <event event="0x57" title="Core" name="Issue cycles" description="For every cycle, this event counts the number of instructions issued in that cycle. Multi-cycle instructions are only counted once"/>
+    <event event="0x58" title="NEON" name="MRC data wait" description="Number of cycles the processor stalls waiting on MRC data from NEON"/>
+    <event event="0x59" title="NEON" name="Full queue" description="Number of cycles that the processor stalls as a result of a full NEON instruction queue or NEON load queue"/>
+    <event event="0x5a" title="NEON" name="Idle" description="Number of cycles that NEON and integer processors are both not idle"/>
+    <event event="0x70" title="External" name="PMUEXTIN[0]" description="Counts any event from external input source PMUEXTIN[0]"/>
+    <event event="0x71" title="External" name="PMUEXTIN[1]" description="Counts any event from external input source PMUEXTIN[1]"/>
+    <event event="0x72" title="External" name="PMUEXTIN[0,1]" description="Counts any event from both external input sources PMUEXTIN[0] and PMUEXTIN[1]"/>
+  </category>
diff --git a/tools/gator/daemon/events-Cortex-A9.xml b/tools/gator/daemon/events-Cortex-A9.xml
new file mode 100644
index 000000000000..3e7f8289062e
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A9.xml
@@ -0,0 +1,65 @@
+  <counter_set name="ARMv7_Cortex_A9_cnt" count="6"/>
+  <category name="Cortex-A9" counter_set="ARMv7_Cortex_A9_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ARMv7_Cortex_A9_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x40" title="Java" name="Bytecode execute" description="Counts the number of Java bytecodes being decoded, including speculative ones"/>
+    <event event="0x41" title="Java" name="SW bytecode execute" description="Counts the number of software java bytecodes being decoded, including speculative ones"/>
+    <event event="0x42" title="Jazelle" name="Backward branch execute" description="Counts the number of Jazelle taken branches being executed"/>
+    <event event="0x50" title="Cache" name="Coherency miss" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor which also miss in all the other Cortex-A9 processors, meaning that the request is sent to the external memory"/>
+    <event event="0x51" title="Cache" name="Coherency hit" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor which hit in another Cortex-A9 processor, meaning that the linefill data is fetched directly from the relevant Cortex-A9 cache"/>
+    <event event="0x60" title="Cache" name="Inst dependent stall" description="Counts the number of cycles where the processor is ready to accept new instructions, but does not receive any because of the instruction side not being able to provide any and the instruction cache is currently performing at least one linefill"/>
+    <event event="0x61" title="Cache" name="Data dependent stall" description="Counts the number of cycles where the core has some instructions that it cannot issue to any pipeline, and the Load Store unit has at least one pending linefill request, and no pending TLB requests"/>
+    <event event="0x62" title="Cache" name="TLB stall" description="Counts the number of cycles where the processor is stalled waiting for the completion of translation table walks from the main TLB"/>
+    <event event="0x63" title="Intrinsic" name="STREX pass" description="Counts the number of STREX instructions architecturally executed and passed"/>
+    <event event="0x64" title="Intrinsic" name="STREX fail" description="Counts the number of STREX instructions architecturally executed and failed"/>
+    <event event="0x65" title="Cache" name="Data eviction" description="Counts the number of eviction requests because of a linefill in the data cache"/>
+    <event event="0x66" title="Pipeline" name="Issue stage no dispatch" description="Counts the number of cycles where the issue stage does not dispatch any instruction because it is empty or cannot dispatch any instructions"/>
+    <event event="0x67" title="Pipeline" name="Issue stage empty" description="Counts the number of cycles where the issue stage is empty"/>
+    <event event="0x68" title="Instruction" name="Executed" description="Counts the number of instructions going through the Register Renaming stage. This number is an approximate number of the total number of instructions speculatively executed, and even more approximate of the total number of instructions architecturally executed"/>
+    <event event="0x69" title="Cache" name="Data linefills" description="Counts the number of linefills performed on the external AXI bus"/>
+    <event event="0x6A" title="Cache" name="Prefetch linefills" description="Counts the number of data linefills caused by prefetcher requests"/>
+    <event event="0x6B" title="Cache" name="Prefetch hits" description="Counts the number of cache hits in a line that belongs to a stream followed by the prefetcher"/>
+    <event event="0x6E" title="Core" name="Functions" description="Counts the number of procedure returns whose condition codes do not fail, excluding all returns from exception"/>
+    <event event="0x70" title="Instruction" name="Main execution unit" description="Counts the number of instructions being executed in the main execution pipeline of the processor, the multiply pipeline and arithmetic logic unit pipeline"/>
+    <event event="0x71" title="Instruction" name="Second execution unit" description="Counts the number of instructions being executed in the processor second execution pipeline (ALU)"/>
+    <event event="0x72" title="Instruction" name="Load/Store" description="Counts the number of instructions being executed in the Load/Store unit"/>
+    <event event="0x73" title="Instruction" name="Floating point" description="Counts the number of Floating-point instructions going through the Register Rename stage"/>
+    <event event="0x74" title="Instruction" name="NEON" description="Counts the number of NEON instructions going through the Register Rename stage"/>
+    <event event="0x80" title="Stalls" name="PLD" description="Counts the number of cycles where the processor is stalled because PLD slots are all full"/>
+    <event event="0x81" title="Stalls" name="Memory write" description="Counts the number of cycles when the processor is stalled and the data side is stalled too because it is full and executing writes to the external memory"/>
+    <event event="0x82" title="Stalls" name="Inst main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the instruction side"/>
+    <event event="0x83" title="Stalls" name="Data main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the data side"/>
+    <event event="0x84" title="Stalls" name="Inst micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the instruction side"/>
+    <event event="0x85" title="Stalls" name="Data micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the data side"/>
+    <event event="0x86" title="Stalls" name="DMB" description="Counts the number of stall cycles because of the execution of a DMB memory barrier"/>
+    <event event="0x8A" title="Clock" name="Integer core" description="Counts the number of cycles during which the integer core clock is enabled"/>
+    <event event="0x8B" title="Clock" name="Data engine" description="Counts the number of cycles during which the Data Engine clock is enabled"/>
+    <event event="0x8C" title="Clock" name="NEON" description="Counts the number of cycles when the NEON SIMD clock is enabled"/>
+    <event event="0x8D" title="Memory" name="TLB inst allocations" description="Counts the number of TLB allocations because of Instruction requests"/>
+    <event event="0x8E" title="Memory" name="TLB data allocations" description="Counts the number of TLB allocations because of Data requests"/>
+    <event event="0x90" title="Instruction" name="ISB" description="Counts the number of ISB instructions architecturally executed"/>
+    <event event="0x91" title="Instruction" name="DSB" description="Counts the number of DSB instructions architecturally executed"/>
+    <event event="0x92" title="Instruction" name="DMB" description="Counts the number of DMB instructions speculatively executed"/>
+    <event event="0x93" title="External" name="Interrupts" description="Counts the number of external interrupts executed by the processor"/>
+    <event event="0xA0" title="PLE" name="Cache line rq completed" description="Counts the number of PLE cache line requests completed"/>
+    <event event="0xA1" title="PLE" name="Cache line rq skipped" description="Counts the number of PLE cache line requests skipped"/>
+    <event event="0xA2" title="PLE" name="FIFO flush" description="Counts the number of PLE FIFO flush requests"/>
+    <event event="0xA3" title="PLE" name="Request completed" description="Counts the number of PLE FIFO flush completed"/>
+    <event event="0xA4" title="PLE" name="FIFO overflow" description="Counts the number of PLE FIFO flush overflowed"/>
+    <event event="0xA5" title="PLE" name="Request programmed" description="Counts the number of PLE FIFO flush program requests"/>
+  </category>
diff --git a/tools/gator/daemon/events-Filesystem.xml b/tools/gator/daemon/events-Filesystem.xml
new file mode 100644
index 000000000000..9ef61ddac811
--- /dev/null
+++ b/tools/gator/daemon/events-Filesystem.xml
@@ -0,0 +1,11 @@
+  <category name="Filesystem">
+    <!-- counter attribute must start with filesystem_ and be unique -->
+    <!-- regex item in () is the value shown -->
+    <!--
+    <event counter="filesystem_cpu1_online" path="/sys/devices/system/cpu/cpu1/online" title="online" name="cpu 1" class="absolute" description="If cpu 1 is online"/>
+    <event counter="filesystem_loginuid" path="/proc/self/loginuid" title="loginuid" name="loginuid" class="absolute" description="loginuid"/>
+    <event counter="filesystem_gatord_rss" path="/proc/self/stat" title="stat" name="rss" class="absolute" regex="-?[0-9]+ \(.*\) . -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ (-?[0-9]+)" units="pages" description="resident set size"/>
+    <event counter="filesystem_processes" path="/proc/stat" title="proc-stat" name="processes" class="absolute" regex="processes ([0-9]+)" description="Number of processes and threads created"/>
+    <event counter="filesystem_context_switches" path="/proc/stat" title="proc-stat" name="context switches" class="absolute" regex="ctxt ([0-9]+)" description="Number of processes and threads created"/>
+    -->
+  </category>
diff --git a/tools/gator/daemon/events-Krait-architected.xml b/tools/gator/daemon/events-Krait-architected.xml
new file mode 100644
index 000000000000..b8d3bcb48de7
--- /dev/null
+++ b/tools/gator/daemon/events-Krait-architected.xml
@@ -0,0 +1,22 @@
+  <counter_set name="Krait_cnt" count="4"/>
+  <category name="Krait" counter_set="Krait_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Krait_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+  </category>
diff --git a/tools/gator/daemon/events-L2C-310.xml b/tools/gator/daemon/events-L2C-310.xml
new file mode 100644
index 000000000000..923fb90334d0
--- /dev/null
+++ b/tools/gator/daemon/events-L2C-310.xml
@@ -0,0 +1,18 @@
+  <counter_set name="L2C-310_cnt" count="2"/>
+  <category name="L2C-310" counter_set="L2C-310_cnt" per_cpu="no">
+    <event event="0x1" title="L2 Cache" name="CastOUT" description="Eviction, CastOUT, of a line from the L2 cache"/>
+    <event event="0x2" title="L2 Cache" name="Data Read Hit" description="Data read hit in the L2 cache"/>
+    <event event="0x3" title="L2 Cache" name="Data Read Request" description="Data read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x4" title="L2 Cache" name="Data Write Hit" description="Data write hit in the L2 cache"/>
+    <event event="0x5" title="L2 Cache" name="Data Write Request" description="Data write lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x6" title="L2 Cache" name="Data Write-Through Request" description="Data write lookup to the L2 cache with Write-Through attribute. Subsequently results in a hit or miss"/>
+    <event event="0x7" title="L2 Cache" name="Instruction Read Hit" description="Instruction read hit in the L2 cache"/>
+    <event event="0x8" title="L2 Cache" name="Instruction Read Request" description="Instruction read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+    <event event="0x9" title="L2 Cache" name="Write Allocate Miss" description="Allocation into the L2 cache caused by a write, with Write-Allocate attribute, miss"/>
+    <event event="0xa" title="L2 Cache" name="Internal Prefetch Allocate" description="Allocation of a prefetch generated by L2C-310 into the L2 cache"/>
+    <event event="0xb" title="L2 Cache" name="Prefitch Hit" description="Prefetch hint hits in the L2 cache"/>
+    <event event="0xc" title="L2 Cache" name="Prefitch Allocate" description="Prefetch hint allocated into the L2 cache"/>
+    <event event="0xd" title="L2 Cache" name="Speculative Read Received" description="Speculative read received"/>
+    <event event="0xe" title="L2 Cache" name="Speculative Read Confirmed" description="Speculative read confirmed"/>
+    <event event="0xf" title="L2 Cache" name="Prefetch Hint Received" description="Prefetch hint received"/>
+  </category>
diff --git a/tools/gator/daemon/events-Linux.xml b/tools/gator/daemon/events-Linux.xml
new file mode 100644
index 000000000000..62a7018d038f
--- /dev/null
+++ b/tools/gator/daemon/events-Linux.xml
@@ -0,0 +1,17 @@
+  <category name="Linux">
+    <event counter="Linux_irq_softirq" title="Interrupts" name="SoftIRQ" per_cpu="yes" description="Linux SoftIRQ taken"/>
+    <event counter="Linux_irq_irq" title="Interrupts" name="IRQ" per_cpu="yes" description="Linux IRQ taken"/>
+    <event counter="Linux_block_rq_wr" title="Disk I/O" name="Write" units="B" description="Disk I/O Bytes Written"/>
+    <event counter="Linux_block_rq_rd" title="Disk I/O" name="Read" units="B" description="Disk I/O Bytes Read"/>
+    <event counter="Linux_net_rx" title="Network" name="Receive" units="B" description="Receive network traffic, including effect from Streamline"/>
+    <event counter="Linux_net_tx" title="Network" name="Transmit" units="B" description="Transmit network traffic, including effect from Streamline"/>
+    <event counter="Linux_sched_switch" title="Scheduler" name="Switch" per_cpu="yes" description="Context switch events"/>
+    <event counter="Linux_meminfo_memused" title="Memory" name="Used" class="absolute" units="B" proc="yes" description="Total used memory size. Note: a process' used memory includes shared memory that may be counted more than once (equivalent to RES from top). Kernel threads are not filterable."/>
+    <event counter="Linux_meminfo_memused2" title="Memory" name="Used" class="absolute" units="B" description="Total used memory size"/>
+    <event counter="Linux_meminfo_memfree" title="Memory" name="Free" class="absolute" display="minimum" units="B" description="Available memory size"/>
+    <event counter="Linux_meminfo_bufferram" title="Memory" name="Buffer" class="absolute" units="B" description="Memory used by OS disk buffers"/>
+    <event counter="Linux_power_cpu_freq" title="Clock" name="Frequency" per_cpu="yes" class="absolute" units="Hz" series_composition="overlay" average_cores="yes" description="Frequency setting of the CPU"/>
+    <event counter="Linux_cpu_wait_contention" title="CPU Contention" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x003c96fb" description="One or more threads are runnable but waiting due to CPU contention"/>
+    <event counter="Linux_cpu_wait_io" title="CPU I/O" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" modifier="10000" color="0x00b30000" description="One or more threads are blocked on an I/O resource"/>
+    <event counter="Linux_power_cpu" title="CPU Status" name="Activity" class="activity" activity1="Off" activity_color1="0x0000ff00" activity2="WFI" activity_color2="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="CPU Status"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-4xx.xml b/tools/gator/daemon/events-Mali-4xx.xml
new file mode 100644
index 000000000000..0a95dfeb6485
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-4xx.xml
@@ -0,0 +1,245 @@
+  <counter_set name="ARM_Mali-4xx_VP_0_cnt" count="2"/>
+  <counter_set name="ARM_Mali-4xx_SW_cnt" count="0"/>
+  <category name="Mali Vertex Processor" counter_set="ARM_Mali-4xx_VP_0_cnt" per_cpu="no">
+    <event event="0x01" title="Mali-4xx VP" name="Active cycles" description="Number of cycles per frame the MaliGP2 was active."/>
+    <event event="0x02" title="Mali-4xx VP" name="Active cycles, vertex shader" description="Number of cycles per frame the vertex shader unit was active."/>
+    <event event="0x03" title="Mali-4xx VP" name="Active cycles, vertex storer" description="Number of cycles per frame the vertex storer unit was active."/>
+    <event event="0x04" title="Mali-4xx VP" name="Active cycles, vertex loader" description="Number of cycles per frame the vertex loader unit was active."/>
+    <event event="0x05" title="Mali-4xx VP" name="Cycles vertex loader waiting for vertex shader" description="Number of cycles per frame the vertex loader was idle while waiting on the vertex shader."/>
+    <event event="0x06" title="Mali-4xx VP" name="Words read, system bus" description="Total number of 64 bit words read by the GP2 from the system bus per frame."/>
+    <event event="0x07" title="Mali-4xx VP" name="Words written, system bus" description="Total number of 64 bit words written by the GP2 to the system bus per frame."/>
+    <event event="0x08" title="Mali-4xx VP" name="Read bursts, system bus" description="Number of read bursts by the GP2 from the system bus per frame."/>
+    <event event="0x09" title="Mali-4xx VP" name="Write bursts, system bus" description="Number of write bursts from the MaliGP2 to the system bus per frame."/>
+    <event event="0x0a" title="Mali-4xx VP" name="Vertices processed" description="Number of vertices processed by the MaliGP2 per frame."/>
+    <event event="0x0b" title="Mali-4xx VP" name="Vertices fetched" description="Number of vertices fetched by the MaliGP2 per frame."/>
+    <event event="0x0c" title="Mali-4xx VP" name="Primitives fetched" description="Number of graphics primitives fetched by the MaliGP2 per frame."/>
+    <event event="0x0e" title="Mali-4xx VP" name="Primitives culled" description="Number of graphics primitives discarded per frame, because they were seen from the back or were offscreen."/>
+    <event event="0x0f" title="Mali-4xx VP" name="Commands written to tiles" description="Number of commands (8 Bytes, mainly primitives) written by GP2 to the PP input data structure per frame."/>
+    <event event="0x10" title="Mali-4xx VP" name="Memory blocks allocated" description="Number of overflow data blocks needed for outputting the PP input data structure per frame ."/>
+    <event event="0x13" title="Mali-4xx VP" name="Vertex loader cache misses" description="Number of cache misses for the vertex shader's vertex input unit per frame."/>
+    <event event="0x16" title="Mali-4xx VP" name="Active cycles, vertex shader command processor" description="Number of cycles per frame the GP2 vertex shader command processor was active. This includes time waiting for semaphores."/>
+    <event event="0x17" title="Mali-4xx VP" name="Active cycles, PLBU command processor" description="Number of cycles per frame the MaliGP2 PLBU command processor was active. This includes time waiting for semaphores."/>
+    <event event="0x18" title="Mali-4xx VP" name="Active Cycles, PLBU list writer" description="Number of cycles per frame the MaliGP2 PLBU output unit was active. This includes time spent waiting on the bus."/>
+    <event event="0x19" title="Mali-4xx VP" name="Active cycles, PLBU geometry processing" description="Number of cycles per frame the MaliGP2 PLBU was active, excepting final data output. In other words: active cycles through the prepare list commands. This includes time spent waiting on the bus."/>
+    <event event="0x1b" title="Mali-4xx VP" name="Active cycles, PLBU primitive assembly" description="Number of active cycles per frame spent by the MaliGP2 PLBU doing primitive assembly. This does not include scissoring or final output. This includes time spent waiting on the bus."/>
+    <event event="0x1c" title="Mali-4xx VP" name="Active cycles, PLBU vertex fetcher" description="Number of active cycles per frame spent by the MaliGP2 PLBU fetching vertex data. This includes time spent waiting on the bus."/>
+    <event event="0x1e" title="Mali-4xx VP" name="Active cycles, Bounding-box and command generator" description="Number of active cycles per frame spent by the MaliGP2 PLBU setting up bounding boxes and commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+    <event event="0x20" title="Mali-4xx VP" name="Active cycles, Scissor tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over tiles to perform scissoring. This includes time spent waiting on the bus."/>
+    <event event="0x21" title="Mali-4xx VP" name="Active cycles, PLBU tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over the tiles in the bounding box generating commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+  </category>
+  <category name="Mali Fragment Processor" per_cpu="no">
+    <counter_set name="ARM_Mali-4xx_FP_0_cnt" title="Mali-4xx FP0" description="Mali GPU Fragment Processor 0" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_1_cnt" title="Mali-4xx FP1" description="Mali GPU Fragment Processor 1" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_2_cnt" title="Mali-4xx FP2" description="Mali GPU Fragment Processor 2" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_3_cnt" title="Mali-4xx FP3" description="Mali GPU Fragment Processor 3" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_4_cnt" title="Mali-4xx FP4" description="Mali GPU Fragment Processor 4" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_5_cnt" title="Mali-4xx FP5" description="Mali GPU Fragment Processor 5" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_6_cnt" title="Mali-4xx FP6" description="Mali GPU Fragment Processor 6" count="2"/>
+    <counter_set name="ARM_Mali-4xx_FP_7_cnt" title="Mali-4xx FP7" description="Mali GPU Fragment Processor 7" count="2"/>
+    <event event="0x00" title="Mali-4xx FP" name="Active clock cycles" description="Active clock cycles, between polygon start and IRQ."/>
+    <event event="0x02" title="Mali-4xx FP" name="Total bus reads" description="Total number of 64-bit words read from the bus."/>
+    <event event="0x03" title="Mali-4xx FP" name="Total bus writes" description="Total number of 64-bit words written to the bus."/>
+    <event event="0x04" title="Mali-4xx FP" name="Bus read request cycles" description="Number of cycles during which the bus read request signal was HIGH."/>
+    <event event="0x05" title="Mali-4xx FP" name="Bus write request cycles" description="Number of cycles during which the bus write request signal was HIGH."/>
+    <event event="0x06" title="Mali-4xx FP" name="Bus read transactions count" description="Number of read requests accepted by the bus."/>
+    <event event="0x07" title="Mali-4xx FP" name="Bus write transactions" description="Number of write requests accepted by the bus."/>
+    <event event="0x09" title="Mali-4xx FP" name="Tile writeback writes" description="64-bit words written to the bus by the writeback unit."/>
+    <event event="0x0a" title="Mali-4xx FP" name="Store unit writes" description="64-bit words written to the bus by the store unit."/>
+    <event event="0x0d" title="Mali-4xx FP" name="Texture cache uncompressed reads" description="Number of 64-bit words read from the bus into the uncompressed textures cache."/>
+    <event event="0x0e" title="Mali-4xx FP" name="Polygon list reads" description="Number of 64-bit words read from the bus by the polygon list reader."/>
+    <event event="0x0f" title="Mali-4xx FP" name="RSW reads" description="Number of 64-bit words read from the bus into the Render State Word register."/>
+    <event event="0x10" title="Mali-4xx FP" name="Vertex cache reads" description="Number of 64-bit words read from the bus into the vertex cache."/>
+    <event event="0x11" title="Mali-4xx FP" name="Uniform remapping reads" description="Number of 64-bit words read from the bus when reading from the uniform remapping table."/>
+    <event event="0x12" title="Mali-4xx FP" name="Program cache reads" description="Number of 64-bit words read from the bus into the fragment shader program cache."/>
+    <event event="0x13" title="Mali-4xx FP" name="Varying reads" description="Number of 64-bit words containing varyings generated by the vertex processing read from the bus."/>
+    <event event="0x14" title="Mali-4xx FP" name="Texture descriptors reads" description="Number of 64-bit words containing texture descriptors read from the bus."/>
+    <event event="0x15" title="Mali-4xx FP" name="Texture descriptor remapping reads" description="Number of 64-bit words read from the bus when reading from the texture descriptor remapping table."/>
+    <event event="0x17" title="Mali-4xx FP" name="Load unit reads" description="Number of 64-bit words read from the bus by the LOAD sub-instruction."/>
+    <event event="0x18" title="Mali-4xx FP" name="Polygon count" description="Number of triangles read from the polygon list."/>
+    <event event="0x19" title="Mali-4xx FP" name="Pixel rectangle count" description="Number of pixel rectangles read from the polygon list."/>
+    <event event="0x1a" title="Mali-4xx FP" name="Lines count" description="Number of lines read from the polygon list."/>
+    <event event="0x1b" title="Mali-4xx FP" name="Points count" description="Number of points read from the polygon list."/>
+    <event event="0x1c" title="Mali-4xx FP" name="Stall cycles PolygonListReader" description="Number of clock cycles the Polygon List Reader waited for output being collected."/>
+    <event event="0x1d" title="Mali-4xx FP" name="Stall cycles triangle setup" description="Number of clock cycles the TSC waited for input."/>
+    <event event="0x1e" title="Mali-4xx FP" name="Quad rasterized count" description="Number of 2x?2 quads output from rasterizer."/>
+    <event event="0x1f" title="Mali-4xx FP" name="Fragment rasterized count" description="Number of fragment rasterized. Fragments/(Quads*4) gives average actual fragments per quad."/>
+    <event event="0x20" title="Mali-4xx FP" name="Fragment rejected fragment-kill count" description="Number of fragments exiting the fragment shader as killed."/>
+    <event event="0x21" title="Mali-4xx FP" name="Fragment rejected fwd-fragment-kill count" description="Number of fragments killed by forward fragment kill."/>
+    <event event="0x22" title="Mali-4xx FP" name="Fragment passed z/stencil count" description="Number of fragments passing Z and stencil test."/>
+    <event event="0x23" title="Mali-4xx FP" name="Patches rejected early z/stencil count" description="Number of patches rejected by EarlyZ. A patch can be 8x8, 4x4 or 2x2 pixels."/>
+    <event event="0x24" title="Mali-4xx FP" name="Patches evaluated" description="Number of patches evaluated for EarlyZ rejection."/>
+    <event event="0x25" title="Mali-4xx FP" name="Instruction completed count" description="Number of fragment shader instruction words completed. It is a function of pixels processed and the length of the shader programs."/>
+    <event event="0x26" title="Mali-4xx FP" name="Instruction failed rendezvous count" description="Number of fragment shader instructions not completed because of failed Rendezvous."/>
+    <event event="0x27" title="Mali-4xx FP" name="Instruction failed varying-miss count" description="Number of fragment shader instructions not completed because of failed varying operation."/>
+    <event event="0x28" title="Mali-4xx FP" name="Instruction failed texture-miss count" description="Number of fragment shader instructions not completed because of failed texture operation."/>
+    <event event="0x29" title="Mali-4xx FP" name="Instruction failed load-miss count" description="Number of fragment shader instructions not completed because of failed load operation."/>
+    <event event="0x2a" title="Mali-4xx FP" name="Instruction failed tile read-miss count" description="Number of fragment shader instructions not completed because of failed read from the tilebuffer."/>
+    <event event="0x2b" title="Mali-4xx FP" name="Instruction failed store-miss count" description="Number of fragment shader instructions not completed because of failed store operation."/>
+    <event event="0x2c" title="Mali-4xx FP" name="Rendezvous breakage count" description="Number of Rendezvous breakages reported."/>
+    <event event="0x2d" title="Mali-4xx FP" name="Pipeline bubbles cycle count" description="Number of unused cycles in the fragment shader while rendering is active."/>
+    <event event="0x2e" title="Mali-4xx FP" name="Texture mapper multipass count" description="Number of texture operations looped because of more texture passes needed."/>
+    <event event="0x2f" title="Mali-4xx FP" name="Texture mapper cycle count" description="Number of texture operation cycles."/>
+    <event event="0x30" title="Mali-4xx FP" name="Vertex cache hit count" description="Number of times a requested vertex was found in the cache (Number of vertex cache hits)."/>
+    <event event="0x31" title="Mali-4xx FP" name="Vertex cache miss count" description="Number of times a requested vertex was not found in the cache (Number of vertex cache misses)."/>
+    <event event="0x32" title="Mali-4xx FP" name="Varying cache hit count" description="Number of times a requested varying was found in the cache (Number of varying cache hits)."/>
+    <event event="0x33" title="Mali-4xx FP" name="Varying cache miss count" description="Number of times a requested varying was not found in the cache (Number of varying cache misses)."/>
+    <event event="0x34" title="Mali-4xx FP" name="Varying cache conflict miss count" description="Number of times a requested varying was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+    <event event="0x35" title="Mali-4xx FP" name="Texture cache hit count" description="Number of times a requested texel was found in the texture cache (Number of texture cache hits)."/>
+    <event event="0x36" title="Mali-4xx FP" name="Texture cache miss count" description="Number of times a requested texel was not found in the texture cache (Number of texture cache misses)."/>
+    <event event="0x37" title="Mali-4xx FP" name="Texture cache conflict miss count" description="Number of times a requested texel was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+    <event event="0x38" title="Mali-4xx FP" name="Compressed texture cache hit count" description="Number of times a requested item was found in the cache."/>
+    <event event="0x39" title="Mali-4xx FP" name="Compressed texture cache miss count" description="Number of times a requested item was not found in the cache."/>
+    <event event="0x3a" title="Mali-4xx FP" name="Load/Store cache hit count" description="Number of hits in the load/store cache."/>
+    <event event="0x3b" title="Mali-4xx FP" name="Load/Store cache miss count" description="Number of misses in the load/store cache."/>
+    <event event="0x3c" title="Mali-4xx FP" name="Program cache hit count" description="Number of hits in the program cache."/>
+    <event event="0x3d" title="Mali-4xx FP" name="Program cache miss count" description="Number of misses in the program cache."/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_0_cnt" title="Mali-4xx L2" description="Mali GPU L2 Cache Core 0" count="2"/>
+  <category name="Mali-4xx L2" counter_set="ARM_Mali-4xx_L2_0_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_1_cnt" title="Mali-4xx L2 1" description="Mali GPU L2 Cache Core 1" count="2"/>
+  <category name="Mali-4xx L2_1" counter_set="ARM_Mali-4xx_L2_1_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache 1" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache 1" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache 1" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache 1" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache 1" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache 1" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache 1" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache 1" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache 1" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache 1" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache 1" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_L2_2_cnt" title="Mali-4xx L2 2" description="Mali GPU L2 Cache Core 2" count="2"/>
+  <category name="Mali-4xx L2_2" counter_set="ARM_Mali-4xx_L2_2_cnt" per_cpu="no">
+    <event event="0x01" title="Mali L2 Cache 2" name="Total clock cycles" description="Total clock cycles"/>
+    <event event="0x02" title="Mali L2 Cache 2" name="Active clock cycles" description="Active clock cycles"/>
+    <option_set name="All">
+      <option event_delta="0x08" name="Master" description="Master"/>
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <option_set name="Slaves">
+      <option event_delta="0x10" name="All slaves" description="All slaves"/>
+      <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+      <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+      <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+      <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+      <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+    </option_set>
+    <event event="0x00" option_set="All" title="Mali L2 Cache 2" name="Read transactions" description="Read transactions"/>
+    <event event="0x01" option_set="All" title="Mali L2 Cache 2" name="Write transactions" description="Write transactions"/>
+    <event event="0x02" option_set="All" title="Mali L2 Cache 2" name="Words read" description="Words read"/>
+    <event event="0x03" option_set="All" title="Mali L2 Cache 2" name="Words written" description="Words written"/>
+    <event event="0x04" option_set="Slaves" title="Mali L2 Cache 2" name="Read hits" description="Read hits"/>
+    <event event="0x05" option_set="Slaves" title="Mali L2 Cache 2" name="Read misses" description="Read misses"/>
+    <event event="0x06" option_set="Slaves" title="Mali L2 Cache 2" name="Write invalidates" description="Write invalidates"/>
+    <event event="0x07" option_set="Slaves" title="Mali L2 Cache 2" name="Read invalidates" description="Read invalidates"/>
+    <event event="0x08" option_set="Slaves" title="Mali L2 Cache 2" name="Cacheable read transactions" description="Cacheable read transactions"/>
+  </category>
+  <counter_set name="ARM_Mali-4xx_Filmstrip_cnt" count="1"/>
+  <category name="Mali-4xx Filmstrip" counter_set="ARM_Mali-4xx_Filmstrip_cnt" per_cpu="no">
+    <option_set name="fs">
+      <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+      <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+      <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+    </option_set>
+    <event event="0x0400" option_set="fs" title="ARM Mali-4xx" name="Filmstrip" description="Scaled framebuffer"/>
+  </category>
+  <category name="ARM_Mali-4xx_Voltage" per_cpu="no">
+    <event counter="ARM_Mali-4xx_Voltage" title="Mali GPU Voltage" name="Voltage" class="absolute" display="average" average_selection="yes" units="mV" description="GPU core voltage."/>
+  </category>
+  <category name="ARM_Mali-4xx_Frequency" per_cpu="no">
+    <event counter="ARM_Mali-4xx_Frequency" title="Mali GPU Frequency" name="Frequency" display="average" average_selection="yes" units="MHz" description="GPU core frequency."/>
+  </category>
+  <category name="Mali-4xx Activity" counter_set="ARM_Mali-4xx_Activity_cnt">
+    <event counter="ARM_Mali-4xx_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="GPU Fragment Activity"/>
+    <event counter="ARM_Mali-4xx_vertex" title="GPU Vertex" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" description="GPU Vertex Activity"/>
+  </category>
+  <category name="Mali-4xx Software Counters" counter_set="ARM_Mali-4xx_SW_cnt" per_cpu="no">
+    <!-- EGL Counters -->
+    <event counter="ARM_Mali-4xx_SW_0" title="Mali EGL Software Counters" name="Blit Time" description="Time spent blitting the framebuffer from video memory to framebuffer."/>
+    <!-- glDrawElements Counters -->
+    <event counter="ARM_Mali-4xx_SW_1" title="glDrawElements Statistics" name="Calls to glDrawElements" description="Number of calls to glDrawElements."/>
+    <event counter="ARM_Mali-4xx_SW_2" title="glDrawElements Statistics" name="Indices to glDrawElements" description="Number of indices to glDrawElements."/>
+    <event counter="ARM_Mali-4xx_SW_3" title="glDrawElements Statistics" name="Transformed by glDrawElements" description="Number of vertices transformed by glDrawElements."/>
+    <!-- glDrawArrays Counters -->
+    <event counter="ARM_Mali-4xx_SW_4" title="glDrawArrays Statistics" name="Calls to glDrawArrays" description="Number of calls to glDrawArrays."/>
+    <event counter="ARM_Mali-4xx_SW_5" title="glDrawArrays Statistics" name="Transformed by glDrawArrays" description="Number of vertices transformed by glDrawArrays."/>
+    <!-- Draw Call Counters -->
+    <event counter="ARM_Mali-4xx_SW_6" title="Drawcall Statistics" name="Points" description="Number of calls to glDraw* with parameter GL_POINTS."/>
+    <event counter="ARM_Mali-4xx_SW_7" title="Drawcall Statistics" name="Lines" description="Number of calls to glDraw* with parameter GL_LINES."/>
+    <event counter="ARM_Mali-4xx_SW_8" title="Drawcall Statistics" name="Lineloop" description="Number of calls to glDraw* with parameter GL_LINE_LOOP."/>
+    <event counter="ARM_Mali-4xx_SW_9" title="Drawcall Statistics" name="Linestrip" description="Number of calls to glDraw* with parameter GL_LINE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_10" title="Drawcall Statistics" name="Triangles" description="Number of calls to glDraw* with parameter GL_TRIANGLES."/>
+    <event counter="ARM_Mali-4xx_SW_11" title="Drawcall Statistics" name="Trianglestrip" description="Number of calls to glDraw* with parameter GL_TRIANGLE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_12" title="Drawcall Statistics" name="Trianglefan" description="Number of calls to glDraw* with parameter GL_TRIANGLE_FAN."/>
+    <event counter="ARM_Mali-4xx_SW_13" title="Drawcall Statistics" name="Vertex Upload Time (us)" description="Time spent uploading vertex attributes and faceindex data not present in a VBO."/>
+    <event counter="ARM_Mali-4xx_SW_14" title="Drawcall Statistics" name="Uniform Bytes Copied (bytes)" description="Number of bytes copied to Mali memory as a result of uniforms update."/>
+    <!-- Buffer Profiling Counters -->
+    <event counter="ARM_Mali-4xx_SW_15" title="Buffer Profiling" name="Texture Upload Time (ms)" description="Time spent uploading textures."/>
+    <event counter="ARM_Mali-4xx_SW_16" title="Buffer Profiling" name="VBO Upload Time (ms)" description="Time spent uploading vertex buffer objects."/>
+    <event counter="ARM_Mali-4xx_SW_17" title="Buffer Profiling" name="FBO Flushes" description="Number of flushed on framebuffer attachment."/>
+    <!-- OpenGL ES 1.1 Emulation -->
+    <event counter="ARM_Mali-4xx_SW_18" title="Fixed-function Emulation" name="# Vertex Shaders Generated" description="Number of vertex shaders generated."/>
+    <event counter="ARM_Mali-4xx_SW_19" title="Fixed-function Emulation" name="# Fragment Shaders Generated" description="Number of fragment shaders generated."/>
+    <!-- Geometry Statistics -->
+    <event counter="ARM_Mali-4xx_SW_33" title="Geometry Statistics" name="Triangles" description="The total number of triangles passed to GLES per-frame."/>
+    <event counter="ARM_Mali-4xx_SW_34" title="Geometry Statistics" name="Independent Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLES."/>
+    <event counter="ARM_Mali-4xx_SW_35" title="Geometry Statistics" name="Strip Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_36" title="Geometry Statistics" name="Fan Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_FAN."/>
+    <event counter="ARM_Mali-4xx_SW_37" title="Geometry Statistics" name="Lines" description="Number of lines passed to GLES per-frame."/>
+    <event counter="ARM_Mali-4xx_SW_38" title="Geometry Statistics" name="Independent Lines" description="Number of lines passed to GLES using the mode GL_LINES."/>
+    <event counter="ARM_Mali-4xx_SW_39" title="Geometry Statistics" name="Strip Lines" description="Number of lines passed to GLES using the mode GL_LINE_STRIP."/>
+    <event counter="ARM_Mali-4xx_SW_40" title="Geometry Statistics" name="Loop Lines" description="Number of lines passed to GLES using the mode GL_LINE_LOOP."/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard.xml b/tools/gator/daemon/events-Mali-Midgard.xml
new file mode 100644
index 000000000000..b6ab4b88cd2e
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard.xml
@@ -0,0 +1,46 @@
+  <category name="Mali-Midgard Software Counters" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_TOTAL_ALLOC_PAGES" title="Mali Total Alloc Pages" name="Total number of allocated pages" description="Mali total number of allocated pages."/>
+  </category>
+  <category name="Mali-Midgard PM Shader" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_SHADER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 0" description="Mali PM Shader: PM Shader Core 0."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 1" description="Mali PM Shader: PM Shader Core 1."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_2" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 2" description="Mali PM Shader: PM Shader Core 2."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_3" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 3" description="Mali PM Shader: PM Shader Core 3."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_4" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 4" description="Mali PM Shader: PM Shader Core 4."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_5" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 5" description="Mali PM Shader: PM Shader Core 5."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_6" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 6" description="Mali PM Shader: PM Shader Core 6."/>
+    <event counter="ARM_Mali-Midgard_PM_SHADER_7" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 7" description="Mali PM Shader: PM Shader Core 7."/>
+  </category>
+  <category name="Mali-Midgard PM Tiler" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_TILER_0" display="average" average_selection="yes" percentage="yes" title="Mali PM Tiler" name="PM Tiler Core 0" description="Mali PM Tiler: PM Tiler Core 0."/>
+  </category>
+  <category name="Mali-Midgard PM L2" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_PM_L2_0" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 0" description="Mali PM L2: PM L2 Core 0."/>
+    <event counter="ARM_Mali-Midgard_PM_L2_1" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 1" description="Mali PM L2: PM L2 Core 1."/>
+  </category>
+  <category name="Mali-Midgard MMU Address Space" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_MMU_AS_0" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 0" description="Mali MMU Address Space 0 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_1" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 1" description="Mali MMU Address Space 1 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_2" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 2" description="Mali MMU Address Space 2 usage."/>
+    <event counter="ARM_Mali-Midgard_MMU_AS_3" display="average" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 3" description="Mali MMU Address Space 3 usage."/>
+  </category>
+  <category name="Mali-Midgard MMU Page Fault" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_0" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 0" description="Reports the number of newly allocated pages after a MMU page fault in address space 0."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_1" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 1" description="Reports the number of newly allocated pages after a MMU page fault in address space 1."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_2" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 2" description="Reports the number of newly allocated pages after a MMU page fault in address space 2."/>
+    <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_3" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 3" description="Reports the number of newly allocated pages after a MMU page fault in address space 3."/>
+  </category>
+  <counter_set name="ARM_Mali-Midgard_Filmstrip_cnt" count="1"/>
+  <category name="Mali-Midgard Filmstrip" counter_set="ARM_Mali-Midgard_Filmstrip_cnt" per_cpu="no">
+    <option_set name="fs">
+      <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+      <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+      <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+    </option_set>
+    <event event="0x0400" option_set="fs" title="ARM Mali-Midgard" name="Filmstrip" description="Scaled framebuffer"/>
+  </category>
+  <category name="Mali-Midgard Activity" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 0 Activity"/>
+    <event counter="ARM_Mali-Midgard_vertex" title="GPU Vertex-Tiling-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 1 Activity"/>
+    <event counter="ARM_Mali-Midgard_opencl" title="GPU Vertex-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00ef022f" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 2 Activity"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard_hw.xml b/tools/gator/daemon/events-Mali-Midgard_hw.xml
new file mode 100644
index 000000000000..4f3323f197d7
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard_hw.xml
@@ -0,0 +1,91 @@
+  <category name="Mali-Midgard Job Manager" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles the GPU was active"/>
+    <event counter="ARM_Mali-Midgard_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles the GPU had a pending interrupt"/>
+    <event counter="ARM_Mali-Midgard_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) was active"/>
+    <event counter="ARM_Mali-Midgard_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) was active"/>
+    <event counter="ARM_Mali-Midgard_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) was active"/>
+    <event counter="ARM_Mali-Midgard_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-Midgard_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-Midgard_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-Midgard_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-Midgard_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-Midgard_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+  </category>
+  <category name="Mali-Midgard Tiler" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-Midgard_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-Midgard_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-Midgard_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-Midgard_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+    <event counter="ARM_Mali-Midgard_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-Midgard_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-Midgard_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+    <event counter="ARM_Mali-Midgard_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-Midgard_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-Midgard_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-Midgard_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-Midgard_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-Midgard_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-Midgard_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-Midgard_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_1" title="Mali Tiler Commands" name="Prims in 1 command" description="Number of primitives producing 1 command"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_2" title="Mali Tiler Commands" name="Prims in 2 command" description="Number of primitives producing 2 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_3" title="Mali Tiler Commands" name="Prims in 3 command" description="Number of primitives producing 3 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_4" title="Mali Tiler Commands" name="Prims in 4 command" description="Number of primitives producing 4 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_4_7" title="Mali Tiler Commands" name="Prims in 4-7 commands" description="Number of primitives producing 4-7 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_5_7" title="Mali Tiler Commands" name="Prims in 5-7 commands" description="Number of primitives producing 5-7 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_8_15" title="Mali Tiler Commands" name="Prims in 8-15 commands" description="Number of primitives producing 8-15 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_16_63" title="Mali Tiler Commands" name="Prims in 16-63 commands" description="Number of primitives producing 16-63 commands"/>
+    <event counter="ARM_Mali-Midgard_COMMAND_64" title="Mali Tiler Commands" name="Prims in &gt;= 64 commands" description="Number of primitives producing &gt;= 64 commands"/>
+  </category>
+  <category name="Mali-Midgard Shader Core" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles the Tripipe was active"/>
+    <event counter="ARM_Mali-Midgard_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-Midgard_FRAG_CYCLE_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS" title="Mali Core Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-Midgard_FRAG_DUMMY_THREADS" title="Mali Core Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_TASKS" title="Mali Compute Threads" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads started" description="Number of compute threads started"/>
+    <event counter="ARM_Mali-Midgard_COMPUTE_CYCLES_DESC" title="Mali Compute Threads" name="Compute cycles awaiting descriptors" description="Number of compute cycles spent waiting for descriptors"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+    <event counter="ARM_Mali-Midgard_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-Midgard_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+    <event counter="ARM_Mali-Midgard_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+    <event counter="ARM_Mali-Midgard_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-Midgard_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+    <event counter="ARM_Mali-Midgard_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-Midgard_TEX_THREADS" title="Mali Texture Pipe" name="T instruction issues" description="Number of instructions issused to the T-pipe, including restarts"/>
+    <event counter="ARM_Mali-Midgard_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+    <event counter="ARM_Mali-Midgard_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-Midgard_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+  </category>
+  <category name="Mali-Midgard L2 and MMU" per_cpu="no">
+    <event counter="ARM_Mali-Midgard_L2_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-Midgard_L2_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-Midgard_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-Midgard_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-Midgard_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-Midgard_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-Midgard_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-Midgard_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T60x_hw.xml b/tools/gator/daemon/events-Mali-T60x_hw.xml
new file mode 100644
index 000000000000..50797e6492ad
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T60x_hw.xml
@@ -0,0 +1,108 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T60x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T60x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T60x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T60x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T60x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T60x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T60x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T60x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T60x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T60x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T60x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T60x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T60x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T60x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T60x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T60x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T60x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T60x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T60x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T60x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T60x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T60x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T60x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T60x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T60x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T60x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T60x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T60x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T60x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T60x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T60x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T60x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T60x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T60x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T60x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T60x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T60x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T60x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T60x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+    <event counter="ARM_Mali-T60x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+    <event counter="ARM_Mali-T60x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T60x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T62x_hw.xml b/tools/gator/daemon/events-Mali-T62x_hw.xml
new file mode 100644
index 000000000000..6ecc53c2ada1
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T62x_hw.xml
@@ -0,0 +1,109 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T62x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T62x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T62x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T62x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T62x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T62x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T62x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T62x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T62x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T62x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T62x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T62x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T62x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T62x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T62x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T62x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T62x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T62x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T62x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T62x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T62x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T62x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T62x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T62x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T62x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T62x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T62x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T62x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T62x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T62x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T62x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T62x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T62x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T62x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T62x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T62x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T62x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T62x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T62x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T62x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+    <event counter="ARM_Mali-T62x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+    <event counter="ARM_Mali-T62x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T62x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T72x_hw.xml b/tools/gator/daemon/events-Mali-T72x_hw.xml
new file mode 100644
index 000000000000..5587534770c8
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T72x_hw.xml
@@ -0,0 +1,95 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T72x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T72x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T72x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T72x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T72x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T72x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T72x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T72x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T72x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T72x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T72x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T72x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T72x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T72x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T72x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T72x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T72x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T72x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T72x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T72x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T72x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T72x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T72x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T72x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T72x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T72x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T72x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe"/>
+
+    <event counter="ARM_Mali-T72x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T72x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T72x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T72x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+
+    <event counter="ARM_Mali-T72x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T72x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T72x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T72x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T72x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T72x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T72x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T72x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T72x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T72x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+  </category>
diff --git a/tools/gator/daemon/events-Mali-T76x_hw.xml b/tools/gator/daemon/events-Mali-T76x_hw.xml
new file mode 100644
index 000000000000..be74c5a42624
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T76x_hw.xml
@@ -0,0 +1,108 @@
+
+  <category name="Mali Job Manager" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+    <event counter="ARM_Mali-T76x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+    <event counter="ARM_Mali-T76x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+    <event counter="ARM_Mali-T76x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+    <event counter="ARM_Mali-T76x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+    <event counter="ARM_Mali-T76x_JS0_JOBS" title="Mali Job Manager Work" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+    <event counter="ARM_Mali-T76x_JS0_TASKS" title="Mali Job Manager Work" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+    <event counter="ARM_Mali-T76x_JS1_JOBS" title="Mali Job Manager Work" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+    <event counter="ARM_Mali-T76x_JS1_TASKS" title="Mali Job Manager Work" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+    <event counter="ARM_Mali-T76x_JS2_TASKS" title="Mali Job Manager Work" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+    <event counter="ARM_Mali-T76x_JS2_JOBS" title="Mali Job Manager Work" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+  </category>
+
+  <category name="Mali Tiler" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+    <event counter="ARM_Mali-T76x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+    <event counter="ARM_Mali-T76x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+    <event counter="ARM_Mali-T76x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+    <event counter="ARM_Mali-T76x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+    <event counter="ARM_Mali-T76x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+    <event counter="ARM_Mali-T76x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+    <event counter="ARM_Mali-T76x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+    <event counter="ARM_Mali-T76x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+    <event counter="ARM_Mali-T76x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+    <event counter="ARM_Mali-T76x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+  </category>
+
+  <category name="Mali Shader Core" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+    <event counter="ARM_Mali-T76x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+    <event counter="ARM_Mali-T76x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+    <event counter="ARM_Mali-T76x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+    <event counter="ARM_Mali-T76x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+    <event counter="ARM_Mali-T76x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+    <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+    <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+    <event counter="ARM_Mali-T76x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+    <event counter="ARM_Mali-T76x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+    <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+    <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+    <event counter="ARM_Mali-T76x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+    <event counter="ARM_Mali-T76x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+    <event counter="ARM_Mali-T76x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+    <event counter="ARM_Mali-T76x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+    <event counter="ARM_Mali-T76x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+    <event counter="ARM_Mali-T76x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+    <event counter="ARM_Mali-T76x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+    <event counter="ARM_Mali-T76x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+    <event counter="ARM_Mali-T76x_LSC_READ_HITS" title="Mali Load/Store Cache" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_READ_MISSES" title="Mali Load/Store Cache" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_WRITE_HITS" title="Mali Load/Store Cache" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_WRITE_MISSES" title="Mali Load/Store Cache" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_LINE_FETCHES" title="Mali Load/Store Cache" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_DIRTY_LINE" title="Mali Load/Store Cache" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+    <event counter="ARM_Mali-T76x_LSC_SNOOPS" title="Mali Load/Store Cache" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+  </category>
+
+  <category name="Mali L2 Cache" per_cpu="no">
+
+    <event counter="ARM_Mali-T76x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache" name="External write beats" description="Number of external bus write beats"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_READ_BEATS" title="Mali L2 Cache" name="External read beats" description="Number of external bus read beats"/>
+    <event counter="ARM_Mali-T76x_L2_READ_SNOOP" title="Mali L2 Cache" name="Read snoops" description="Number of read transaction snoops"/>
+    <event counter="ARM_Mali-T76x_L2_READ_HIT" title="Mali L2 Cache" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_SNOOP" title="Mali L2 Cache" name="Write snoops" description="Number of write transaction snoops"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_HIT" title="Mali L2 Cache" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_AR_STALL" title="Mali L2 Cache" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_W_STALL" title="Mali L2 Cache" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+    <event counter="ARM_Mali-T76x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+    <event counter="ARM_Mali-T76x_L2_READ_LOOKUP" title="Mali L2 Cache" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+    <event counter="ARM_Mali-T76x_L2_WRITE_LOOKUP" title="Mali L2 Cache" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+  </category>
diff --git a/tools/gator/daemon/events-Mali-V500.xml b/tools/gator/daemon/events-Mali-V500.xml
new file mode 100644
index 000000000000..89bc7f4734df
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-V500.xml
@@ -0,0 +1,30 @@
+  <category name="Mali-V500">
+    <event counter="ARM_Mali-V500_cnt0" title="MVE-V500 Stats" name="Samples" class="absolute" description="The number of times we have taken a sample"/>
+    <event counter="ARM_Mali-V500_cnt1" title="MVE-V500 Input Totals" name="Queued input-buffers" class="absolute" description="The number of input-buffers that has been queued for consumption by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt2" title="MVE-V500 Input Totals" name="Consumed input-buffers" class="absolute" description="The number of input-buffers that has been consumed by the MVE and returned to the application"/>
+    <event counter="ARM_Mali-V500_cnt3" title="MVE-V500 Output Totals" name="Queued output-buffers" class="absolute" description="The number of output-buffers that has been queued for usage by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt4" title="MVE-V500 Output Totals" name="Consumed output-buffers" class="absolute" description="The number of output-buffers that has been consumed by the MVE and returned to the application"/>
+    <event counter="ARM_Mali-V500_cnt5" title="MVE-V500 Stats" name="Created Sessions" class="absolute" description="The number of created sessions throughout the lifetime of the process"/>
+    <event counter="ARM_Mali-V500_cnt6" title="MVE-V500 Sessions" name="Active Sessions" description="The number of currently existing sessions"/>
+    <event counter="ARM_Mali-V500_cnt7" title="MVE-V500 Stats" name="Processed Frames" class="absolute" description="The number of processed frames. A processed frame is one where the encode or decode is complete for that particular frame. Frames can be processed out of order so this is not the same as the number of output-buffers returned"/>
+    <event counter="ARM_Mali-V500_cnt8" title="MVE-V500 Input Totals" name="Input Flushes Requested" class="absolute" description="The number of requested flushes of the input queue"/>
+    <event counter="ARM_Mali-V500_cnt9" title="MVE-V500 Input Totals" name="Input Flushes Complete" class="absolute" description="The number of completed flushes of the input queue"/>
+    <event counter="ARM_Mali-V500_cnt10" title="MVE-V500 Output Totals" name="Output Flushes Requested" class="absolute" description="The number of requested flushes of the output queue"/>
+    <event counter="ARM_Mali-V500_cnt11" title="MVE-V500 Output Totals" name="Output Flushes Complete" class="absolute" description="The number of completed flushes of the output queue"/>
+    <event counter="ARM_Mali-V500_cnt12" title="MVE-V500 Output" name="Queued Output Buffers (current)" description="The number of output-buffers that are currently queued for usage by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt13" title="MVE-V500 Input" name="Queued Input Buffers (current)" description="The number of input-buffers that are currently queued for consumption by the MVE"/>
+    <event counter="ARM_Mali-V500_cnt14" title="MVE-V500 Output" name="Output Queue Flushes" description="The number of pending flushes for the MVE output-queue"/>
+    <event counter="ARM_Mali-V500_cnt15" title="MVE-V500 Input" name="Input Queue Flushes" description="The number of pending flushes for the MVE input-queue"/>
+    <event counter="ARM_Mali-V500_cnt16" title="MVE-V500 Stats" name="Errors encountered" class="absolute" description="The number of errors encountered"/>
+    <event counter="ARM_Mali-V500_cnt17" title="MVE-V500 Bandwidth" name="Bits consumed" class="absolute" description="The number of bits consumed during decode"/>
+    <event counter="ARM_Mali-V500_cnt18" title="MVE-V500 Bandwidth" name="AFBC bandwidth" class="absolute" description="The amount of AFBC-encoded bytes read or written"/>
+    <event counter="ARM_Mali-V500_cnt19" title="MVE-V500 Bandwidth" name="Bandwidth (read)" class="absolute" description="The amount of bytes read over the AXI bus"/>
+    <event counter="ARM_Mali-V500_cnt20" title="MVE-V500 Bandwidth" name="Bandwidth (write)" class="absolute" description="The amount of bytes written over the AXI bus"/>
+    <event counter="ARM_Mali-V500_evn0" title="MVE-V500 Sessions" name="Session created" description="Generated when a session has been created"/>
+    <event counter="ARM_Mali-V500_evn1" title="MVE-V500 Sessions" name="Session destroyed" description="Generated when a session has been destroyed"/>
+    <event counter="ARM_Mali-V500_evn2" title="MVE-V500 Frames" name="Frame Processed" description="Generated when the MVE has finished processing a frame"/>
+    <event counter="ARM_Mali-V500_evn3" title="MVE-V500 Output" name="Output buffer received" description="Generated when an an output buffer is returned to us from the MVE"/>
+    <event counter="ARM_Mali-V500_evn4" title="MVE-V500 Input" name="Input buffer received" description="Generated when we an input buffer is returned to us from the MVE"/>
+    <event counter="ARM_Mali-V500_act0" title="MVE-V500 Parsed" name="Activity" class="activity" activity1="activity" activity_color1="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/>
+    <event counter="ARM_Mali-V500_act1" title="MVE-V500 Piped" name="Activity" class="activity" activity1="activity" activity_color1="0x0000ff00" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/>
+  </category>
diff --git a/tools/gator/daemon/events-Perf-Hardware.xml b/tools/gator/daemon/events-Perf-Hardware.xml
new file mode 100644
index 000000000000..423696f82420
--- /dev/null
+++ b/tools/gator/daemon/events-Perf-Hardware.xml
@@ -0,0 +1,12 @@
+  <counter_set name="Perf_Hardware_cnt" count="6"/>
+  <category name="Perf Hardware" counter_set="Perf_Hardware_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Perf_Hardware_ccnt" event="0" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="1" title="Instruction" name="Executed" description="Instruction executed"/>
+    <event event="2" title="Cache" name="References" description="Cache References"/>
+    <event event="3" title="Cache" name="Misses" description="Cache Misses"/>
+    <event event="4" title="Branch" name="Instructions" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="5" title="Branch" name="Misses" description="Branch mispredicted or not predicted"/>
+    <event event="6" title="Bus" name="Cycles" description="Bus Cycles"/>
+    <event event="7" title="Instruction" name="Stalled Frontend" description="Stalled Frontend Cycles"/>
+    <event event="8" title="Instruction" name="Stalled Backend" description="Stalled Backend Cycles"/>
+  </category>
diff --git a/tools/gator/daemon/events-Scorpion.xml b/tools/gator/daemon/events-Scorpion.xml
new file mode 100644
index 000000000000..fa716fdc4840
--- /dev/null
+++ b/tools/gator/daemon/events-Scorpion.xml
@@ -0,0 +1,107 @@
+  <counter_set name="Scorpion_cnt" count="4"/>
+  <category name="Scorpion" counter_set="Scorpion_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="Scorpion_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+    <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+    <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+    <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+    <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+    <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+    <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+    <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+    <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+    <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+    <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+    <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+    <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+    <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+    <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+    <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+    <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+    <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+    <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+    <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+    <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+    <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+    <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+    <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+    <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+    <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+    <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+    <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+    <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+    <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+    <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+    <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+    <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+    <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+    <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+    <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+    <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+    <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+    <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+    <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+    <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+    <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+    <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+    <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+    <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+    <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+    <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+    <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+    <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+    <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+    <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+    <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+    <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+    <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+    <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+    <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+    <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+    <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+    <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+    <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+    <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+    <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+    <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+    <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+    <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+    <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+    <event event="0x8e" title="Scorpion" name="BANK_AB_HIT" description="L2 hit rates bank A/B hits"/>
+    <event event="0x8f" title="Scorpion" name="BANK_AB_ACCESS" description="L2 hit rates bank A/B accesses"/>
+    <event event="0x90" title="Scorpion" name="BANK_CD_HIT" description="L2 hit rates bank C/D hits"/>
+    <event event="0x91" title="Scorpion" name="BANK_CD_ACCESS" description="L2 hit rates bank C/D accesses"/>
+    <event event="0x92" title="Scorpion" name="BANK_AB_DSIDE_HIT" description="L2 hit rates bank A/B d-side hits"/>
+    <event event="0x93" title="Scorpion" name="BANK_AB_DSIDE_ACCESS" description="L2 hit rates bank A/B d-side accesses"/>
+    <event event="0x94" title="Scorpion" name="BANK_CD_DSIDE_HIT" description="L2 hit rates bank C/D d-side hits"/>
+    <event event="0x95" title="Scorpion" name="BANK_CD_DSIDE_ACCESS" description="L2 hit rates bank C/D d-side accesses"/>
+    <event event="0x96" title="Scorpion" name="BANK_AB_ISIDE_HIT" description="L2 hit rates bank A/B i-side hits"/>
+    <event event="0x97" title="Scorpion" name="BANK_AB_ISIDE_ACCESS" description="L2 hit rates bank A/B i-side accesses"/>
+    <event event="0x98" title="Scorpion" name="BANK_CD_ISIDE_HIT" description="L2 hit rates bank C/D i-side hits"/>
+    <event event="0x99" title="Scorpion" name="BANK_CD_ISIDE_ACCESS" description="L2 hit rates bank C/D i-side accesses"/>
+    <event event="0x9a" title="Scorpion" name="ISIDE_RD_WAIT" description="fills and castouts cycles that i-side RD requests wait on data from bus"/>
+    <event event="0x9b" title="Scorpion" name="DSIDE_RD_WAIT" description="fills and castouts cycles that d-side RD requests wait on data from bus"/>
+    <event event="0x9c" title="Scorpion" name="BANK_BYPASS_WRITE" description="fills and castouts bank bypass writes"/>
+    <event event="0x9d" title="Scorpion" name="BANK_AB_NON_CASTOUT" description="fills and castouts bank A/B non-castout writes to bus"/>
+    <event event="0x9e" title="Scorpion" name="BANK_AB_L2_CASTOUT" description="fills and castouts bank A/B L2 castouts (granules)"/>
+    <event event="0x9f" title="Scorpion" name="BANK_CD_NON_CASTOUT" description="fills and castouts bank C/D non-castout writes to bus"/>
+    <event event="0xa0" title="Scorpion" name="BANK_CD_L2_CASTOUT" description="fills and castouts bank C/D L2 castouts (granules)"/>
+  </category>
diff --git a/tools/gator/daemon/events-ScorpionMP.xml b/tools/gator/daemon/events-ScorpionMP.xml
new file mode 100644
index 000000000000..c648ccefb287
--- /dev/null
+++ b/tools/gator/daemon/events-ScorpionMP.xml
@@ -0,0 +1,90 @@
+  <counter_set name="ScorpionMP_cnt" count="4"/>
+  <category name="ScorpionMP" counter_set="ScorpionMP_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+    <event counter="ScorpionMP_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+    <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+    <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+    <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+    <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+    <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+    <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+    <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+    <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+    <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+    <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+    <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+    <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+    <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+    <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+    <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+    <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+    <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+    <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+    <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+    <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+    <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+    <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+    <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+    <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+    <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+    <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+    <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+    <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+    <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+    <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+    <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+    <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+    <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+    <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+    <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+    <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+    <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+    <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+    <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+    <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+    <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+    <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+    <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+    <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+    <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+    <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+    <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+    <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+    <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+    <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+    <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+    <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+    <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+    <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+    <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+    <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+    <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+    <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+    <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+    <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+    <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+    <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+    <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+    <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+    <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+    <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+    <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+    <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+    <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+    <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+    <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+    <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+    <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+    <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+    <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+    <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+    <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+    <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+    <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+    <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+    <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+    <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+    <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+    <event event="0x8e" title="ScorpionMP" name="NUM_BARRIERS" description="Barriers"/>
+    <event event="0x8f" title="ScorpionMP" name="BARRIER_CYCLES" description="Barrier cycles"/>
+  </category>
diff --git a/tools/gator/daemon/events-ftrace.xml b/tools/gator/daemon/events-ftrace.xml
new file mode 100644
index 000000000000..33ab7aab2196
--- /dev/null
+++ b/tools/gator/daemon/events-ftrace.xml
@@ -0,0 +1,7 @@
+  <category name="Ftrace">
+    <!-- counter attribute must start with ftrace_ and be unique -->
+    <!-- regex item in () is the value shown -->
+    <!--
+    <event counter="ftrace_trace_marker_numbers" title="ftrace" name="trace_marker" class="absolute" regex="([0-9]+)" description="Numbers written to /sys/kernel/debug/tracing/trace_marker, ex: echo 42 > /sys/kernel/debug/tracing/trace_marker"/>
+    -->
+  </category>
diff --git a/tools/gator/daemon/events_footer.xml b/tools/gator/daemon/events_footer.xml
new file mode 100644
index 000000000000..cd2b44665bab
--- /dev/null
+++ b/tools/gator/daemon/events_footer.xml
@@ -0,0 +1 @@
+</events>
diff --git a/tools/gator/daemon/events_header.xml b/tools/gator/daemon/events_header.xml
new file mode 100644
index 000000000000..38ec4c03246e
--- /dev/null
+++ b/tools/gator/daemon/events_header.xml
@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<events>
diff --git a/tools/gator/daemon/k/perf_event.3.12.h b/tools/gator/daemon/k/perf_event.3.12.h
new file mode 100644
index 000000000000..e886c48cadf6
--- /dev/null
+++ b/tools/gator/daemon/k/perf_event.3.12.h
@@ -0,0 +1,792 @@
+/*
+ * Performance events:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_PERF_EVENT_H
+#define _LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
+	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+	PERF_COUNT_HW_CACHE_NODE		= 6,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
+	PERF_COUNT_SW_DUMMY			= 9,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_READ			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
+	PERF_SAMPLE_REGS_USER			= 1U << 12,
+	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
+
+	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
+};
+
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type {
+	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
+
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+	PERF_SAMPLE_REGS_ABI_NONE	= 0,
+	PERF_SAMPLE_REGS_ABI_32		= 1,
+	PERF_SAMPLE_REGS_ABI_64		= 2,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *	{ u64		value;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		id;           } && PERF_FORMAT_ID
+ *	} && !PERF_FORMAT_GROUP
+ *
+ *	{ u64		nr;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		value;
+ *	    { u64	id;           } && PERF_FORMAT_ID
+ *	  }		cntr[nr];
+ *	} && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
+
+	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
+					/* add: sample_stack_user */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ */
+struct perf_event_attr {
+
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+
+	/*
+	 * Size of the attr structure, for fwd/bwd compat.
+	 */
+	__u32			size;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
+				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
+
+				exclude_host   :  1, /* don't count in host   */
+				exclude_guest  :  1, /* don't count in guest  */
+
+				exclude_callchain_kernel : 1, /* exclude kernel callchains */
+				exclude_callchain_user   : 1, /* exclude user callchains */
+				mmap2          :  1, /* include mmap with inode data     */
+
+				__reserved_1   : 40;
+
+	union {
+		__u32		wakeup_events;	  /* wakeup every n events */
+		__u32		wakeup_watermark; /* bytes before wakeup   */
+	};
+
+	__u32			bp_type;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
+	__u64	branch_sample_type; /* enum perf_branch_sample_type */
+
+	/*
+	 * Defines set of user regs to dump on samples.
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_user;
+
+	/*
+	 * Defines size of the user stack to dump on samples.
+	 */
+	__u32	sample_stack_user;
+
+	/* Align to u64. */
+	__u32	__reserved_2;
+};
+
+#define perf_flags(attr)	(*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
+
+enum perf_event_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw events in user-space.
+	 *
+	 *   u32 seq, time_mult, time_shift, idx, width;
+	 *   u64 count, enabled, running;
+	 *   u64 cyc, time_offset;
+	 *   s64 pmc = 0;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *     barrier()
+	 *
+	 *     enabled = pc->time_enabled;
+	 *     running = pc->time_running;
+	 *
+	 *     if (pc->cap_usr_time && enabled != running) {
+	 *       cyc = rdtsc();
+	 *       time_offset = pc->time_offset;
+	 *       time_mult   = pc->time_mult;
+	 *       time_shift  = pc->time_shift;
+	 *     }
+	 *
+	 *     idx = pc->index;
+	 *     count = pc->offset;
+	 *     if (pc->cap_usr_rdpmc && idx) {
+	 *       width = pc->pmc_width;
+	 *       pmc = rdpmc(idx - 1);
+	 *     }
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware event identifier */
+	__s64	offset;			/* add to hardware event value */
+	__u64	time_enabled;		/* time event active */
+	__u64	time_running;		/* time event on cpu */
+	union {
+		__u64	capabilities;
+		struct {
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
+		};
+	};
+
+	/*
+	 * If cap_usr_rdpmc this field provides the bit-width of the value
+	 * read using the rdpmc() or equivalent instruction. This can be used
+	 * to sign extend the result like:
+	 *
+	 *   pmc <<= 64 - width;
+	 *   pmc >>= 64 - width; // signed shift right
+	 *   count += pmc;
+	 */
+	__u16	pmc_width;
+
+	/*
+	 * If cap_usr_time the below fields can be used to compute the time
+	 * delta since time_enabled (in ns) using rdtsc or similar.
+	 *
+	 *   u64 quot, rem;
+	 *   u64 delta;
+	 *
+	 *   quot = (cyc >> time_shift);
+	 *   rem = cyc & ((1 << time_shift) - 1);
+	 *   delta = time_offset + quot * time_mult +
+	 *              ((rem * time_mult) >> time_shift);
+	 *
+	 * Where time_offset,time_mult,time_shift and cyc are read in the
+	 * seqcount loop described above. This delta can then be added to
+	 * enabled and possible running (if idx), improving the scaling:
+	 *
+	 *   enabled += delta;
+	 *   if (idx)
+	 *     running += delta;
+	 *
+	 *   quot = count / running;
+	 *   rem  = count % running;
+	 *   count = quot * enabled + (rem * enabled) / running;
+	 */
+	__u16	time_shift;
+	__u32	time_mult;
+	__u64	time_offset;
+	/*
+	 * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+	 * from sample timestamps.
+	 *
+	 *   time = timestamp - time_zero;
+	 *   quot = time / time_mult;
+	 *   rem  = time % time_mult;
+	 *   cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+	 *
+	 * And vice versa:
+	 *
+	 *   quot = cyc >> time_shift;
+	 *   rem  = cyc & ((1 << time_shift) - 1);
+	 *   timestamp = time_zero + quot * time_mult +
+	 *               ((rem * time_mult) >> time_shift);
+	 */
+	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
+
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u8	__reserved[118*8+4];	/* align to 1k. */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
+	 *
+	 * When the mapping is PROT_WRITE the @data_tail value should be
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
+	 */
+	__u64   data_head;		/* head in the data section */
+	__u64	data_tail;		/* user-space written tail */
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
+#define PERF_RECORD_MISC_KERNEL			(1 << 0)
+#define PERF_RECORD_MISC_USER			(2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+#define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
+
+struct perf_event_header {
+	__u32	type;
+	__u16	misc;
+	__u16	size;
+};
+
+enum perf_event_type {
+
+	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
+	 *
+	 * struct sample_id {
+	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 * 	{ u64			time;     } && PERF_SAMPLE_TIME
+	 * 	{ u64			id;       } && PERF_SAMPLE_ID
+	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
+	 */
+
+	/*
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST			= 2,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				stream_id;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_FORK			= 7,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
+	 *
+	 *	struct read_format		values;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_READ			= 8,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
+	 *
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
+	 *
+	 *	{ u64			nr,
+	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 *	#
+	 *	# The RAW record below is opaque data wrt the ABI
+	 *	#
+	 *	# That is, the ABI doesn't make any promises wrt to
+	 *	# the stability of its content, it may vary depending
+	 *	# on event, hardware, kernel version and phase of
+	 *	# the moon.
+	 *	#
+	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 *	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64                   nr;
+	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *
+	 * 	{ u64			abi; # enum perf_sample_regs_abi
+	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+	 *
+	 * 	{ u64			size;
+	 * 	  char			data[size];
+	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 * };
+	 */
+	PERF_RECORD_SAMPLE			= 9,
+
+	/*
+	 * The MMAP2 records are an augmented version of MMAP, they add
+	 * maj, min, ino numbers to be used to uniquely identify each mapping
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	u32				maj;
+	 *	u32				min;
+	 *	u64				ino;
+	 *	u64				ino_generation;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP2			= 10,
+
+	PERF_RECORD_MAX,			/* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH		127
+
+enum perf_callchain_context {
+	PERF_CONTEXT_HV			= (__u64)-32,
+	PERF_CONTEXT_KERNEL		= (__u64)-128,
+	PERF_CONTEXT_USER		= (__u64)-512,
+
+	PERF_CONTEXT_GUEST		= (__u64)-2048,
+	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
+	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
+
+	PERF_CONTEXT_MAX		= (__u64)-4095,
+};
+
+#define PERF_FLAG_FD_NO_GROUP		(1U << 0)
+#define PERF_FLAG_FD_OUTPUT		(1U << 1)
+#define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */
+
+union perf_mem_data_src {
+	__u64 val;
+	struct {
+		__u64   mem_op:5,	/* type of opcode */
+			mem_lvl:14,	/* memory hierarchy level */
+			mem_snoop:5,	/* snoop mode */
+			mem_lock:2,	/* lock instr */
+			mem_dtlb:7,	/* tlb access */
+			mem_rsvd:31;
+	};
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA		0x01 /* not available */
+#define PERF_MEM_OP_LOAD	0x02 /* load instruction */
+#define PERF_MEM_OP_STORE	0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH	0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT	0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA		0x01  /* not available */
+#define PERF_MEM_LVL_HIT	0x02  /* hit level */
+#define PERF_MEM_LVL_MISS	0x04  /* miss level  */
+#define PERF_MEM_LVL_L1		0x08  /* L1 */
+#define PERF_MEM_LVL_LFB	0x10  /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2		0x20  /* L2 */
+#define PERF_MEM_LVL_L3		0x40  /* L3 */
+#define PERF_MEM_LVL_LOC_RAM	0x80  /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1	0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2	0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1	0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2	0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO		0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT	5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA	0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT	0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS	0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT	19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA	0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT	24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA		0x01 /* not available */
+#define PERF_MEM_TLB_HIT	0x02 /* hit level */
+#define PERF_MEM_TLB_MISS	0x04 /* miss level */
+#define PERF_MEM_TLB_L1		0x08 /* L1 */
+#define PERF_MEM_TLB_L2		0x10 /* L2 */
+#define PERF_MEM_TLB_WK		0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT	26
+
+#define PERF_MEM_S(a, s) \
+	(((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
+ */
+struct perf_branch_entry {
+	__u64	from;
+	__u64	to;
+	__u64	mispred:1,  /* target mispredicted */
+		predicted:1,/* target predicted */
+		in_tx:1,    /* in transaction */
+		abort:1,    /* transaction abort */
+		reserved:60;
+};
+
+#endif /* _LINUX_PERF_EVENT_H */
diff --git a/tools/gator/daemon/k/perf_event.h b/tools/gator/daemon/k/perf_event.h
new file mode 120000
index 000000000000..e5dff8c21ef4
--- /dev/null
+++ b/tools/gator/daemon/k/perf_event.h
@@ -0,0 +1 @@
+perf_event.3.12.h
\ No newline at end of file
diff --git a/tools/gator/daemon/libsensors/COPYING.LGPL b/tools/gator/daemon/libsensors/COPYING.LGPL
new file mode 100644
index 000000000000..4362b49151d7
--- /dev/null
+++ b/tools/gator/daemon/libsensors/COPYING.LGPL
@@ -0,0 +1,502 @@
+                  GNU LESSER GENERAL PUBLIC LICENSE
+                       Version 2.1, February 1999
+
+ Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL.  It also counts
+ as the successor of the GNU Library Public License, version 2, hence
+ the version number 2.1.]
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Lesser General Public License, applies to some
+specially designated software packages--typically libraries--of the
+Free Software Foundation and other authors who decide to use it.  You
+can use it too, but we suggest you first think carefully about whether
+this license or the ordinary General Public License is the better
+strategy to use in any particular case, based on the explanations below.
+
+  When we speak of free software, we are referring to freedom of use,
+not price.  Our General Public Licenses are designed to make sure that
+you have the freedom to distribute copies of free software (and charge
+for this service if you wish); that you receive source code or can get
+it if you want it; that you can change the software and use pieces of
+it in new free programs; and that you are informed that you can do
+these things.
+
+  To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights.  These restrictions translate to certain responsibilities for
+you if you distribute copies of the library or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link other code with the library, you must provide
+complete object files to the recipients, so that they can relink them
+with the library after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  To protect each distributor, we want to make it very clear that
+there is no warranty for the free library.  Also, if the library is
+modified by someone else and passed on, the recipients should know
+that what they have is not the original version, so that the original
+author's reputation will not be affected by problems that might be
+introduced by others.
+
+  Finally, software patents pose a constant threat to the existence of
+any free program.  We wish to make sure that a company cannot
+effectively restrict the users of a free program by obtaining a
+restrictive license from a patent holder.  Therefore, we insist that
+any patent license obtained for a version of the library must be
+consistent with the full freedom of use specified in this license.
+
+  Most GNU software, including some libraries, is covered by the
+ordinary GNU General Public License.  This license, the GNU Lesser
+General Public License, applies to certain designated libraries, and
+is quite different from the ordinary General Public License.  We use
+this license for certain libraries in order to permit linking those
+libraries into non-free programs.
+
+  When a program is linked with a library, whether statically or using
+a shared library, the combination of the two is legally speaking a
+combined work, a derivative of the original library.  The ordinary
+General Public License therefore permits such linking only if the
+entire combination fits its criteria of freedom.  The Lesser General
+Public License permits more lax criteria for linking other code with
+the library.
+
+  We call this license the "Lesser" General Public License because it
+does Less to protect the user's freedom than the ordinary General
+Public License.  It also provides other free software developers Less
+of an advantage over competing non-free programs.  These disadvantages
+are the reason we use the ordinary General Public License for many
+libraries.  However, the Lesser license provides advantages in certain
+special circumstances.
+
+  For example, on rare occasions, there may be a special need to
+encourage the widest possible use of a certain library, so that it becomes
+a de-facto standard.  To achieve this, non-free programs must be
+allowed to use the library.  A more frequent case is that a free
+library does the same job as widely used non-free libraries.  In this
+case, there is little to gain by limiting the free library to free
+software only, so we use the Lesser General Public License.
+
+  In other cases, permission to use a particular library in non-free
+programs enables a greater number of people to use a large body of
+free software.  For example, permission to use the GNU C Library in
+non-free programs enables many more people to use the whole GNU
+operating system, as well as its variant, the GNU/Linux operating
+system.
+
+  Although the Lesser General Public License is Less protective of the
+users' freedom, it does ensure that the user of a program that is
+linked with the Library has the freedom and the wherewithal to run
+that program using a modified version of the Library.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, whereas the latter must
+be combined with the library in order to run.
+
+                  GNU LESSER GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library or other
+program which contains a notice placed by the copyright holder or
+other authorized party saying it may be distributed under the terms of
+this Lesser General Public License (also called "this License").
+Each licensee is addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also combine or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Use a suitable shared library mechanism for linking with the
+    Library.  A suitable mechanism is one that (1) uses at run time a
+    copy of the library already present on the user's computer system,
+    rather than copying library functions into the executable, and (2)
+    will operate properly with a modified version of the library, if
+    the user installs one, as long as the modified version is
+    interface-compatible with the version that the work was made with.
+
+    c) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    d) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    e) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the materials to be distributed need not include anything that is
+normally distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties with
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Lesser General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+                            NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+           How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Lesser General Public License for more details.
+
+    You should have received a copy of the GNU Lesser General Public
+    License along with this library; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/libsensors/access.c b/tools/gator/daemon/libsensors/access.c
new file mode 100644
index 000000000000..8e227e2550db
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.c
@@ -0,0 +1,561 @@
+/*
+    access.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#include "access.h"
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "sysfs.h"
+
+/* We watch the recursion depth for variables only, as an easy way to
+   detect cycles. */
+#define DEPTH_MAX	8
+
+static int sensors_eval_expr(const sensors_chip_features *chip_features,
+			     const sensors_expr *expr,
+			     double val, int depth, double *result);
+
+/* Compare two chips name descriptions, to see whether they could match.
+   Return 0 if it does not match, return 1 if it does match. */
+static int sensors_match_chip(const sensors_chip_name *chip1,
+		       const sensors_chip_name *chip2)
+{
+	if ((chip1->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+	    (chip2->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+	    strcmp(chip1->prefix, chip2->prefix))
+		return 0;
+
+	if ((chip1->bus.type != SENSORS_BUS_TYPE_ANY) &&
+	    (chip2->bus.type != SENSORS_BUS_TYPE_ANY) &&
+	    (chip1->bus.type != chip2->bus.type))
+		return 0;
+
+	if ((chip1->bus.nr != SENSORS_BUS_NR_ANY) &&
+	    (chip2->bus.nr != SENSORS_BUS_NR_ANY) &&
+	    (chip1->bus.nr != chip2->bus.nr))
+		return 0;
+
+	if ((chip1->addr != chip2->addr) &&
+	    (chip1->addr != SENSORS_CHIP_NAME_ADDR_ANY) &&
+	    (chip2->addr != SENSORS_CHIP_NAME_ADDR_ANY))
+		return 0;
+
+	return 1;
+}
+
+/* Returns, one by one, a pointer to all sensor_chip structs of the
+   config file which match with the given chip name. Last should be
+   the value returned by the last call, or NULL if this is the first
+   call. Returns NULL if no more matches are found. Do not modify
+   the struct the return value points to! 
+   Note that this visits the list of chips from last to first. Usually,
+   you want the match that was latest in the config file. */
+static sensors_chip *
+sensors_for_all_config_chips(const sensors_chip_name *name,
+			     const sensors_chip *last)
+{
+	int nr, i;
+	sensors_chip_name_list chips;
+
+	for (nr = last ? last - sensors_config_chips - 1 :
+			 sensors_config_chips_count - 1; nr >= 0; nr--) {
+
+		chips = sensors_config_chips[nr].chips;
+		for (i = 0; i < chips.fits_count; i++) {
+			if (sensors_match_chip(&chips.fits[i], name))
+				return sensors_config_chips + nr;
+		}
+	}
+	return NULL;
+}
+
+/* Look up a chip in the intern chip list, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_chip_features *
+sensors_lookup_chip(const sensors_chip_name *name)
+{
+	int i;
+
+	for (i = 0; i < sensors_proc_chips_count; i++)
+		if (sensors_match_chip(&sensors_proc_chips[i].chip, name))
+			return &sensors_proc_chips[i];
+
+	return NULL;
+}
+
+/* Look up a subfeature of the given chip, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_nr(const sensors_chip_features *chip,
+			     int subfeat_nr)
+{
+	if (subfeat_nr < 0 ||
+	    subfeat_nr >= chip->subfeature_count)
+		return NULL;
+	return chip->subfeature + subfeat_nr;
+}
+
+/* Look up a feature of the given chip, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if
+   not found.*/
+static const sensors_feature *
+sensors_lookup_feature_nr(const sensors_chip_features *chip, int feat_nr)
+{
+	if (feat_nr < 0 ||
+	    feat_nr >= chip->feature_count)
+		return NULL;
+	return chip->feature + feat_nr;
+}
+
+/* Look up a subfeature by name, and return a pointer to it.
+   Do not modify the struct the return value points to! Returns NULL if 
+   not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_name(const sensors_chip_features *chip,
+			       const char *name)
+{
+	int j;
+
+	for (j = 0; j < chip->subfeature_count; j++)
+		if (!strcmp(chip->subfeature[j].name, name))
+			return chip->subfeature + j;
+	return NULL;
+}
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+   one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+   if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip)
+{
+	if ((chip->prefix == SENSORS_CHIP_NAME_PREFIX_ANY) ||
+	    (chip->bus.type == SENSORS_BUS_TYPE_ANY) ||
+	    (chip->bus.nr == SENSORS_BUS_NR_ANY) ||
+	    (chip->addr == SENSORS_CHIP_NAME_ADDR_ANY))
+		return 1;
+	else
+		return 0;
+}
+
+/* Look up the label for a given feature. Note that chip should not
+   contain wildcard values! The returned string is newly allocated (free it
+   yourself). On failure, NULL is returned.
+   If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+			const sensors_feature *feature)
+{
+	char *label;
+	const sensors_chip *chip;
+	char buf[PATH_MAX];
+	FILE *f;
+	int i;
+
+	if (sensors_chip_name_has_wildcards(name))
+		return NULL;
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->labels_count; i++)
+			if (!strcmp(feature->name, chip->labels[i].name)) {
+				label = chip->labels[i].value;
+				goto sensors_get_label_exit;
+			}
+
+	/* No user specified label, check for a _label sysfs file */
+	snprintf(buf, PATH_MAX, "%s/%s_label", name->path, feature->name);
+	
+	if ((f = fopen(buf, "r"))) {
+		i = fread(buf, 1, sizeof(buf), f);
+		fclose(f);
+		if (i > 0) {
+			/* i - 1 to strip the '\n' at the end */
+			buf[i - 1] = 0;
+			label = buf;
+			goto sensors_get_label_exit;
+		}
+	}
+
+	/* No label, return the feature name instead */
+	label = feature->name;
+	
+sensors_get_label_exit:
+	label = strdup(label);
+	if (!label)
+		sensors_fatal_error(__func__, "Allocating label text");
+	return label;
+}
+
+/* Looks up whether a feature should be ignored. Returns
+   1 if it should be ignored, 0 if not. */
+static int sensors_get_ignored(const sensors_chip_name *name,
+			       const sensors_feature *feature)
+{
+	const sensors_chip *chip;
+	int i;
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->ignores_count; i++)
+			if (!strcmp(feature->name, chip->ignores[i].name))
+				return 1;
+	return 0;
+}
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+static int __sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+			       int depth, double *result)
+{
+	const sensors_chip_features *chip_features;
+	const sensors_subfeature *subfeature;
+	const sensors_expr *expr = NULL;
+	double val;
+	int res, i;
+
+	if (depth >= DEPTH_MAX)
+		return -SENSORS_ERR_RECURSION;
+	if (sensors_chip_name_has_wildcards(name))
+		return -SENSORS_ERR_WILDCARDS;
+	if (!(chip_features = sensors_lookup_chip(name)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+							subfeat_nr)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature->flags & SENSORS_MODE_R))
+		return -SENSORS_ERR_ACCESS_R;
+
+	/* Apply compute statement if it exists */
+	if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+		const sensors_feature *feature;
+		const sensors_chip *chip;
+
+		feature = sensors_lookup_feature_nr(chip_features,
+					subfeature->mapping);
+
+		chip = NULL;
+		while (!expr &&
+		       (chip = sensors_for_all_config_chips(name, chip)))
+			for (i = 0; i < chip->computes_count; i++) {
+				if (!strcmp(feature->name,
+					    chip->computes[i].name)) {
+					expr = chip->computes[i].from_proc;
+					break;
+				}
+			}
+	}
+
+	res = sensors_read_sysfs_attr(name, subfeature, &val);
+	if (res)
+		return res;
+	if (!expr)
+		*result = val;
+	else if ((res = sensors_eval_expr(chip_features, expr, val, depth,
+					  result)))
+		return res;
+	return 0;
+}
+
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+		      double *result)
+{
+	return __sensors_get_value(name, subfeat_nr, 0, result);
+}
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+		      double value)
+{
+	const sensors_chip_features *chip_features;
+	const sensors_subfeature *subfeature;
+	const sensors_expr *expr = NULL;
+	int i, res;
+	double to_write;
+
+	if (sensors_chip_name_has_wildcards(name))
+		return -SENSORS_ERR_WILDCARDS;
+	if (!(chip_features = sensors_lookup_chip(name)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+							subfeat_nr)))
+		return -SENSORS_ERR_NO_ENTRY;
+	if (!(subfeature->flags & SENSORS_MODE_W))
+		return -SENSORS_ERR_ACCESS_W;
+
+	/* Apply compute statement if it exists */
+	if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+		const sensors_feature *feature;
+		const sensors_chip *chip;
+
+		feature = sensors_lookup_feature_nr(chip_features,
+					subfeature->mapping);
+
+		chip = NULL;
+		while (!expr &&
+		       (chip = sensors_for_all_config_chips(name, chip)))
+			for (i = 0; i < chip->computes_count; i++) {
+				if (!strcmp(feature->name,
+					    chip->computes[i].name)) {
+					expr = chip->computes[i].to_proc;
+					break;
+				}
+			}
+	}
+
+	to_write = value;
+	if (expr)
+		if ((res = sensors_eval_expr(chip_features, expr,
+					     value, 0, &to_write)))
+			return res;
+	return sensors_write_sysfs_attr(name, subfeature, to_write);
+}
+
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+						    *match, int *nr)
+{
+	const sensors_chip_name *res;
+
+	while (*nr < sensors_proc_chips_count) {
+		res = &sensors_proc_chips[(*nr)++].chip;
+		if (!match || sensors_match_chip(res, match))
+			return res;
+	}
+	return NULL;
+}
+
+const char *sensors_get_adapter_name(const sensors_bus_id *bus)
+{
+	int i;
+
+	/* bus types with a single instance */
+	switch (bus->type) {
+	case SENSORS_BUS_TYPE_ISA:
+		return "ISA adapter";
+	case SENSORS_BUS_TYPE_PCI:
+		return "PCI adapter";
+	/* SPI should not be here, but for now SPI adapters have no name
+	   so we don't have any custom string to return. */
+	case SENSORS_BUS_TYPE_SPI:
+		return "SPI adapter";
+	case SENSORS_BUS_TYPE_VIRTUAL:
+		return "Virtual device";
+	case SENSORS_BUS_TYPE_ACPI:
+		return "ACPI interface";
+	/* HID should probably not be there either, but I don't know if
+	   HID buses have a name nor where to find it. */
+	case SENSORS_BUS_TYPE_HID:
+		return "HID adapter";
+	}
+
+	/* bus types with several instances */
+	for (i = 0; i < sensors_proc_bus_count; i++)
+		if (sensors_proc_bus[i].bus.type == bus->type &&
+		    sensors_proc_bus[i].bus.nr == bus->nr)
+			return sensors_proc_bus[i].adapter;
+	return NULL;
+}
+
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr)
+{
+	const sensors_chip_features *chip;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	while (*nr < chip->feature_count
+	    && sensors_get_ignored(name, &chip->feature[*nr]))
+		(*nr)++;
+	if (*nr >= chip->feature_count)
+		return NULL;
+	return &chip->feature[(*nr)++];
+}
+
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+			const sensors_feature *feature, int *nr)
+{
+	const sensors_chip_features *chip;
+	const sensors_subfeature *subfeature;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	/* Seek directly to the first subfeature */
+	if (*nr < feature->first_subfeature)
+		*nr = feature->first_subfeature;
+
+	if (*nr >= chip->subfeature_count)
+		return NULL;	/* end of list */
+	subfeature = &chip->subfeature[(*nr)++];
+	if (subfeature->mapping == feature->number)
+		return subfeature;
+	return NULL;	/* end of subfeature list */
+}
+
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+		       const sensors_feature *feature,
+		       sensors_subfeature_type type)
+{
+	const sensors_chip_features *chip;
+	int i;
+
+	if (!(chip = sensors_lookup_chip(name)))
+		return NULL;	/* No such chip */
+
+	for (i = feature->first_subfeature; i < chip->subfeature_count &&
+	     chip->subfeature[i].mapping == feature->number; i++) {
+		if (chip->subfeature[i].type == type)
+			return &chip->subfeature[i];
+	}
+	return NULL;	/* No such subfeature */
+}
+
+/* Evaluate an expression */
+int sensors_eval_expr(const sensors_chip_features *chip_features,
+		      const sensors_expr *expr,
+		      double val, int depth, double *result)
+{
+	double res1, res2;
+	int res;
+	const sensors_subfeature *subfeature;
+
+	if (expr->kind == sensors_kind_val) {
+		*result = expr->data.val;
+		return 0;
+	}
+	if (expr->kind == sensors_kind_source) {
+		*result = val;
+		return 0;
+	}
+	if (expr->kind == sensors_kind_var) {
+		if (!(subfeature = sensors_lookup_subfeature_name(chip_features,
+							    expr->data.var)))
+			return -SENSORS_ERR_NO_ENTRY;
+		return __sensors_get_value(&chip_features->chip,
+					   subfeature->number, depth + 1,
+					   result);
+	}
+	if ((res = sensors_eval_expr(chip_features, expr->data.subexpr.sub1,
+				     val, depth, &res1)))
+		return res;
+	if (expr->data.subexpr.sub2 &&
+	    (res = sensors_eval_expr(chip_features, expr->data.subexpr.sub2,
+				     val, depth, &res2)))
+		return res;
+	switch (expr->data.subexpr.op) {
+	case sensors_add:
+		*result = res1 + res2;
+		return 0;
+	case sensors_sub:
+		*result = res1 - res2;
+		return 0;
+	case sensors_multiply:
+		*result = res1 * res2;
+		return 0;
+	case sensors_divide:
+		if (res2 == 0.0)
+			return -SENSORS_ERR_DIV_ZERO;
+		*result = res1 / res2;
+		return 0;
+	case sensors_negate:
+		*result = -res1;
+		return 0;
+	case sensors_exp:
+		*result = exp(res1);
+		return 0;
+	case sensors_log:
+		if (res1 < 0.0)
+			return -SENSORS_ERR_DIV_ZERO;
+		*result = log(res1);
+		return 0;
+	}
+	return 0;
+}
+
+/* Execute all set statements for this particular chip. The chip may not 
+   contain wildcards!  This function will return 0 on success, and <0 on 
+   failure. */
+static int sensors_do_this_chip_sets(const sensors_chip_name *name)
+{
+	const sensors_chip_features *chip_features;
+	sensors_chip *chip;
+	double value;
+	int i;
+	int err = 0, res;
+	const sensors_subfeature *subfeature;
+
+	chip_features = sensors_lookup_chip(name);	/* Can't fail */
+
+	for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+		for (i = 0; i < chip->sets_count; i++) {
+			subfeature = sensors_lookup_subfeature_name(chip_features,
+							chip->sets[i].name);
+			if (!subfeature) {
+				sensors_parse_error_wfn("Unknown feature name",
+						    chip->sets[i].line.filename,
+						    chip->sets[i].line.lineno);
+				err = -SENSORS_ERR_NO_ENTRY;
+				continue;
+			}
+
+			res = sensors_eval_expr(chip_features,
+						chip->sets[i].value, 0,
+						0, &value);
+			if (res) {
+				sensors_parse_error_wfn("Error parsing expression",
+						    chip->sets[i].line.filename,
+						    chip->sets[i].line.lineno);
+				err = res;
+				continue;
+			}
+			if ((res = sensors_set_value(name, subfeature->number,
+						     value))) {
+				sensors_parse_error_wfn("Failed to set value",
+						chip->sets[i].line.filename,
+						chip->sets[i].line.lineno);
+				err = res;
+				continue;
+			}
+		}
+	return err;
+}
+
+/* Execute all set statements for this particular chip. The chip may contain
+   wildcards!  This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name)
+{
+	int nr, this_res;
+	const sensors_chip_name *found_name;
+	int res = 0;
+
+	for (nr = 0; (found_name = sensors_get_detected_chips(name, &nr));) {
+		this_res = sensors_do_this_chip_sets(found_name);
+		if (this_res)
+			res = this_res;
+	}
+	return res;
+}
diff --git a/tools/gator/daemon/libsensors/access.h b/tools/gator/daemon/libsensors/access.h
new file mode 100644
index 000000000000..1d3784340757
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.h
@@ -0,0 +1,33 @@
+/*
+    access.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007        Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ACCESS_H
+#define LIB_SENSORS_ACCESS_H
+
+#include "sensors.h"
+#include "data.h"
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+   one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+   if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip);
+
+#endif /* def LIB_SENSORS_ACCESS_H */
diff --git a/tools/gator/daemon/libsensors/conf-lex.c b/tools/gator/daemon/libsensors/conf-lex.c
new file mode 100644
index 000000000000..a54664b3d77b
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.c
@@ -0,0 +1,2881 @@
+
+#line 3 "<stdout>"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define yy_create_buffer sensors_yy_create_buffer
+#define yy_delete_buffer sensors_yy_delete_buffer
+#define yy_flex_debug sensors_yy_flex_debug
+#define yy_init_buffer sensors_yy_init_buffer
+#define yy_flush_buffer sensors_yy_flush_buffer
+#define yy_load_buffer_state sensors_yy_load_buffer_state
+#define yy_switch_to_buffer sensors_yy_switch_to_buffer
+#define yyin sensors_yyin
+#define yyleng sensors_yyleng
+#define yylex sensors_yylex
+#define yylineno sensors_yylineno
+#define yyout sensors_yyout
+#define yyrestart sensors_yyrestart
+#define yytext sensors_yytext
+#define yywrap sensors_yywrap
+#define yyalloc sensors_yyalloc
+#define yyrealloc sensors_yyrealloc
+#define yyfree sensors_yyfree
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types. 
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! C99 */
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif	/* defined (__STDC__) */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index.  If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition.  This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN (yy_start) = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.  The YYSTATE alias is for lex
+ * compatibility.
+ */
+#define YY_START (((yy_start) - 1) / 2)
+#define YYSTATE YY_START
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". */
+#define YY_NEW_FILE sensors_yyrestart(sensors_yyin  )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k.
+ * Moreover, YY_BUF_SIZE is 2*YY_READ_BUF_SIZE in the general case.
+ * Ditto for the __ia64__ case accordingly.
+ */
+#define YY_BUF_SIZE 32768
+#else
+#define YY_BUF_SIZE 16384
+#endif /* __ia64__ */
+#endif
+
+/* The state buf must be large enough to hold one state per character in the main buffer.
+ */
+#define YY_STATE_BUF_SIZE   ((YY_BUF_SIZE + 2) * sizeof(yy_state_type))
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int sensors_yyleng;
+
+extern FILE *sensors_yyin, *sensors_yyout;
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+    #define YY_LESS_LINENO(n)
+    
+/* Return all but the first "n" matched characters back to the input stream. */
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up sensors_yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		*yy_cp = (yy_hold_char); \
+		YY_RESTORE_YY_MORE_OFFSET \
+		(yy_c_buf_p) = yy_cp = yy_bp + yyless_macro_arg - YY_MORE_ADJ; \
+		YY_DO_BEFORE_ACTION; /* set up sensors_yytext again */ \
+		} \
+	while ( 0 )
+
+#define unput(c) yyunput( c, (yytext_ptr)  )
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+	/* When an EOF's been seen but there's still some text to process
+	 * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+	 * shouldn't try reading from the input source any more.  We might
+	 * still have a bunch of tokens to match, though, because of
+	 * possible backing-up.
+	 *
+	 * When we actually see the EOF, we change the status to "new"
+	 * (via sensors_yyrestart()), so that the user can continue scanning by
+	 * just pointing sensors_yyin at a new input file.
+	 */
+#define YY_BUFFER_EOF_PENDING 2
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+/* Stack of input buffers. */
+static size_t yy_buffer_stack_top = 0; /**< index of top of stack. */
+static size_t yy_buffer_stack_max = 0; /**< capacity of stack. */
+static YY_BUFFER_STATE * yy_buffer_stack = 0; /**< Stack as an array. */
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ *
+ * Returns the top of the stack, or NULL.
+ */
+#define YY_CURRENT_BUFFER ( (yy_buffer_stack) \
+                          ? (yy_buffer_stack)[(yy_buffer_stack_top)] \
+                          : NULL)
+
+/* Same as previous macro, but useful when we know that the buffer stack is not
+ * NULL or when we need an lvalue. For internal use only.
+ */
+#define YY_CURRENT_BUFFER_LVALUE (yy_buffer_stack)[(yy_buffer_stack_top)]
+
+/* yy_hold_char holds the character lost when sensors_yytext is formed. */
+static char yy_hold_char;
+static int yy_n_chars;		/* number of characters read into yy_ch_buf */
+int sensors_yyleng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 0;		/* whether we need to initialize */
+static int yy_start = 0;	/* start state number */
+
+/* Flag which is used to allow sensors_yywrap()'s to do buffer switches
+ * instead of setting up a fresh sensors_yyin.  A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+void sensors_yyrestart (FILE *input_file  );
+void sensors_yy_switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE sensors_yy_create_buffer (FILE *file,int size  );
+void sensors_yy_delete_buffer (YY_BUFFER_STATE b  );
+void sensors_yy_flush_buffer (YY_BUFFER_STATE b  );
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer  );
+void sensors_yypop_buffer_state (void );
+
+static void sensors_yyensure_buffer_stack (void );
+static void sensors_yy_load_buffer_state (void );
+static void sensors_yy_init_buffer (YY_BUFFER_STATE b,FILE *file  );
+
+#define YY_FLUSH_BUFFER sensors_yy_flush_buffer(YY_CURRENT_BUFFER )
+
+YY_BUFFER_STATE sensors_yy_scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE sensors_yy_scan_bytes (yyconst char *bytes,int len  );
+
+void *sensors_yyalloc (yy_size_t  );
+void *sensors_yyrealloc (void *,yy_size_t  );
+void sensors_yyfree (void *  );
+
+#define yy_new_buffer sensors_yy_create_buffer
+
+#define yy_set_interactive(is_interactive) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){ \
+        sensors_yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_is_interactive = is_interactive; \
+	}
+
+#define yy_set_bol(at_bol) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){\
+        sensors_yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_at_bol = at_bol; \
+	}
+
+#define YY_AT_BOL() (YY_CURRENT_BUFFER_LVALUE->yy_at_bol)
+
+/* Begin user sect3 */
+
+#define sensors_yywrap(n) 1
+#define YY_SKIP_YYWRAP
+
+typedef unsigned char YY_CHAR;
+
+FILE *sensors_yyin = (FILE *) 0, *sensors_yyout = (FILE *) 0;
+
+typedef int yy_state_type;
+
+extern int sensors_yylineno;
+
+int sensors_yylineno = 1;
+
+extern char *sensors_yytext;
+#define yytext_ptr sensors_yytext
+static yyconst flex_int16_t yy_nxt[][39] =
+    {
+    {
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+        0,    0,    0,    0,    0,    0,    0,    0,    0
+    },
+
+    {
+        9,   10,   11,   12,   10,   13,   10,   10,   10,   10,
+       10,   10,   10,   10,   10,   10,   10,   10,   10,   10,
+       14,   15,   16,   14,   14,   14,   14,   14,   17,   18,
+       14,   14,   14,   14,   14,   19,   14,   14,   14
+    },
+
+    {
+        9,   10,   11,   12,   10,   13,   10,   10,   10,   10,
+       10,   10,   10,   10,   10,   10,   10,   10,   10,   10,
+
+       14,   15,   16,   14,   14,   14,   14,   14,   17,   18,
+       14,   14,   14,   14,   14,   19,   14,   14,   14
+    },
+
+    {
+        9,   20,   21,   22,   23,   24,   25,   26,   27,   28,
+       29,   30,   31,   32,   33,   34,   35,   36,   37,   38,
+       35,   35,   35,   35,   35,   35,   35,   35,   35,   35,
+       35,   35,   35,   35,   35,   35,   35,   35,   35
+    },
+
+    {
+        9,   20,   21,   22,   23,   24,   25,   26,   27,   28,
+       29,   30,   31,   32,   33,   34,   35,   36,   37,   38,
+       35,   35,   35,   35,   35,   35,   35,   35,   35,   35,
+       35,   35,   35,   35,   35,   35,   35,   35,   35
+
+    },
+
+    {
+        9,   39,   39,   40,   41,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   42,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39
+    },
+
+    {
+        9,   39,   39,   40,   41,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   42,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39,   39,
+       39,   39,   39,   39,   39,   39,   39,   39,   39
+    },
+
+    {
+        9,   43,   43,   44,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43
+    },
+
+    {
+        9,   43,   43,   44,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43,   43,
+       43,   43,   43,   43,   43,   43,   43,   43,   43
+    },
+
+    {
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,
+       -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9,   -9
+
+    },
+
+    {
+        9,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,
+      -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10,  -10
+    },
+
+    {
+        9,  -11,   45,   46,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,
+      -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11,  -11
+    },
+
+    {
+        9,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,
+      -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12,  -12
+    },
+
+    {
+        9,   47,   47,   48,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47
+    },
+
+    {
+        9,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,
+      -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,  -14,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,
+      -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,  -15,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   50,   49
+    },
+
+    {
+        9,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,
+      -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,  -16,
+       49,   49,   49,   49,   49,   49,   49,   51,   49,   49,
+       49,   49,   52,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,
+      -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,  -17,
+
+       49,   49,   49,   49,   49,   49,   53,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,
+      -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,  -18,
+       54,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,
+      -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,  -19,
+       49,   49,   49,   49,   55,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,
+      -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20,  -20
+    },
+
+    {
+        9,  -21,   56,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,
+      -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21,  -21
+    },
+
+    {
+        9,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,
+      -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22,  -22
+    },
+
+    {
+        9,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,
+      -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23,  -23
+    },
+
+    {
+        9,   57,   57,   58,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57
+
+    },
+
+    {
+        9,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,
+      -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25,  -25
+    },
+
+    {
+        9,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,
+      -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26,  -26
+    },
+
+    {
+        9,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,
+      -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27,  -27
+    },
+
+    {
+        9,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,
+      -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28,  -28
+    },
+
+    {
+        9,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,
+      -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29,  -29
+
+    },
+
+    {
+        9,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,
+      -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30,  -30
+    },
+
+    {
+        9,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,   59,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,
+      -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31,  -31
+    },
+
+    {
+        9,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,
+      -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32,  -32
+    },
+
+    {
+        9,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,  -33,
+      -33,  -33,   60,  -33,   61,  -33,   62,  -33,  -33,  -33,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,
+      -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34,  -34
+
+    },
+
+    {
+        9,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,  -35,
+      -35,  -35,  -35,  -35,   62,  -35,   62,  -35,  -35,  -35,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -36,   63,   64,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,
+      -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36,  -36
+    },
+
+    {
+        9,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,
+      -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37,  -37
+    },
+
+    {
+        9,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,
+      -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38,  -38
+    },
+
+    {
+        9,   65,   65,  -39,  -39,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,  -39,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65
+
+    },
+
+    {
+        9,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,
+      -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40,  -40
+    },
+
+    {
+        9,  -41,  -41,  -41,   66,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,
+      -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41,  -41
+    },
+
+    {
+        9,   67,   67,   68,   67,   67,   67,   67,   67,   67,
+       67,   67,   67,   67,   67,   67,   67,   67,   67,   67,
+
+       69,   70,   67,   67,   67,   71,   67,   67,   67,   67,
+       67,   72,   67,   67,   73,   67,   74,   67,   75
+    },
+
+    {
+        9,   76,   76,  -43,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76
+    },
+
+    {
+        9,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,
+      -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44,  -44
+
+    },
+
+    {
+        9,  -45,   45,   46,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,
+      -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45,  -45
+    },
+
+    {
+        9,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,
+      -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46,  -46
+    },
+
+    {
+        9,   47,   47,   48,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+
+       47,   47,   47,   47,   47,   47,   47,   47,   47,   47,
+       47,   47,   47,   47,   47,   47,   47,   47,   47
+    },
+
+    {
+        9,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,
+      -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48,  -48
+    },
+
+    {
+        9,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,
+      -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,  -49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,
+      -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,  -50,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   77,   49,   49,   49
+    },
+
+    {
+        9,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,
+      -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,  -51,
+       49,   49,   49,   49,   49,   49,   49,   49,   78,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,
+      -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,  -52,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       79,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,
+      -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,  -53,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   80,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,
+      -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,  -54,
+       49,   81,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,
+      -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,  -55,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   82,   49,   49
+    },
+
+    {
+        9,  -56,   56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,
+      -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56,  -56
+    },
+
+    {
+        9,   57,   57,   58,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+
+       57,   57,   57,   57,   57,   57,   57,   57,   57,   57,
+       57,   57,   57,   57,   57,   57,   57,   57,   57
+    },
+
+    {
+        9,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,
+      -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58,  -58
+    },
+
+    {
+        9,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,   59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,
+      -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59,  -59
+
+    },
+
+    {
+        9,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,   59,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,
+      -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60,  -60
+    },
+
+    {
+        9,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,  -61,
+      -61,  -61,   60,  -61,   61,  -61,   62,  -61,  -61,  -61,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,  -62,
+      -62,  -62,  -62,  -62,   62,  -62,   62,  -62,  -62,  -62,
+
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62
+    },
+
+    {
+        9,  -63,   63,   64,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,
+      -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63,  -63
+    },
+
+    {
+        9,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,
+      -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64,  -64
+
+    },
+
+    {
+        9,   65,   65,  -65,  -65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,  -65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65,   65,
+       65,   65,   65,   65,   65,   65,   65,   65,   65
+    },
+
+    {
+        9,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,
+      -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66,  -66
+    },
+
+    {
+        9,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,
+      -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67,  -67
+    },
+
+    {
+        9,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,
+      -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68,  -68
+    },
+
+    {
+        9,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,
+      -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69,  -69
+
+    },
+
+    {
+        9,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,
+      -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70,  -70
+    },
+
+    {
+        9,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,
+      -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71,  -71
+    },
+
+    {
+        9,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,
+      -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72,  -72
+    },
+
+    {
+        9,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,
+      -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73,  -73
+    },
+
+    {
+        9,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,
+      -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74,  -74
+
+    },
+
+    {
+        9,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,
+      -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75,  -75
+    },
+
+    {
+        9,   76,   76,  -76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76,   76,
+       76,   76,   76,   76,   76,   76,   76,   76,   76
+    },
+
+    {
+        9,  -77,   83,  -77,  -77,  -77,  -77,  -77,  -77,  -77,
+      -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,  -77,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,
+      -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,  -78,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   84,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,
+      -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,  -79,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   85,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,
+      -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,  -80,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   86,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,
+      -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,  -81,
+       49,   49,   49,   49,   87,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -82,   88,  -82,  -82,  -82,  -82,  -82,  -82,  -82,
+      -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,  -82,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -83,   83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,
+      -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83,  -83
+    },
+
+    {
+        9,  -84,   89,  -84,  -84,  -84,  -84,  -84,  -84,  -84,
+      -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,  -84,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,
+      -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,  -85,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   90,   49
+    },
+
+    {
+        9,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,
+      -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,  -86,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   91,   49,   49,   49,   49
+    },
+
+    {
+        9,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,
+      -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,  -87,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   92,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -88,   88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,
+      -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88,  -88
+    },
+
+    {
+        9,  -89,   89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,
+      -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89,  -89
+
+    },
+
+    {
+        9,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,
+      -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,  -90,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   93,   49,   49
+    },
+
+    {
+        9,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,
+      -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,  -91,
+       49,   49,   49,   49,   94,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -92,   95,  -92,  -92,  -92,  -92,  -92,  -92,  -92,
+      -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,  -92,
+
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,
+      -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,  -93,
+       49,   49,   49,   49,   96,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -94,   97,  -94,  -94,  -94,  -94,  -94,  -94,  -94,
+      -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,  -94,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+
+    },
+
+    {
+        9,  -95,   95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,
+      -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95,  -95
+    },
+
+    {
+        9,  -96,   98,  -96,  -96,  -96,  -96,  -96,  -96,  -96,
+      -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,  -96,
+       49,   49,   49,   49,   49,   49,   49,   49,   49,   49,
+       49,   49,   49,   49,   49,   49,   49,   49,   49
+    },
+
+    {
+        9,  -97,   97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,
+      -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97,  -97
+    },
+
+    {
+        9,  -98,   98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,
+      -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98,  -98
+    },
+
+    } ;
+
+static yy_state_type yy_get_previous_state (void );
+static yy_state_type yy_try_NUL_trans (yy_state_type current_state  );
+static int yy_get_next_buffer (void );
+static void yy_fatal_error (yyconst char msg[]  );
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up sensors_yytext.
+ */
+#define YY_DO_BEFORE_ACTION \
+	(yytext_ptr) = yy_bp; \
+	sensors_yyleng = (size_t) (yy_cp - yy_bp); \
+	(yy_hold_char) = *yy_cp; \
+	*yy_cp = '\0'; \
+	(yy_c_buf_p) = yy_cp;
+
+#define YY_NUM_RULES 50
+#define YY_END_OF_BUFFER 51
+/* This struct is not used in this scanner,
+   but its presence is necessary. */
+struct yy_trans_info
+	{
+	flex_int32_t yy_verify;
+	flex_int32_t yy_nxt;
+	};
+static yyconst flex_int16_t yy_accept[99] =
+    {   0,
+        0,    0,    0,    0,    0,    0,   13,   13,   51,   12,
+        1,    2,    3,   11,   11,   11,   11,   11,   11,   33,
+       15,   16,   31,   18,   25,   26,   23,   21,   27,   22,
+       33,   24,   20,   28,   32,   33,   29,   30,   49,   36,
+       39,   48,   13,   14,    1,    2,    3,    4,   11,   11,
+       11,   11,   11,   11,   11,   15,   18,   19,   20,   34,
+       20,   32,   35,   17,   49,   38,   47,   37,   40,   41,
+       42,   43,   44,   45,   46,   13,    8,   11,   11,   11,
+       11,    6,    8,    9,   11,   11,   11,    6,    9,   11,
+       11,    5,   11,   10,    5,    7,   10,    7
+
+    } ;
+
+static yyconst flex_int32_t yy_ec[256] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    2,    3,
+        2,    2,    2,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    2,    1,    4,    5,    1,    1,    1,    1,    6,
+        7,    8,    9,   10,   11,   12,   13,   14,   14,   14,
+       14,   14,   14,   14,   14,   14,   14,    1,    1,    1,
+        1,    1,    1,   15,   16,   16,   16,   16,   16,   16,
+       16,   16,   16,   16,   16,   16,   16,   16,   16,   16,
+       16,   16,   16,   16,   16,   16,   16,   16,   16,   16,
+        1,   17,    1,   18,   16,   19,   20,   21,   22,   23,
+
+       24,   25,   26,   27,   28,   23,   23,   29,   30,   31,
+       32,   33,   23,   34,   35,   36,   37,   38,   23,   23,
+       23,   23,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1
+    } ;
+
+extern int sensors_yy_flex_debug;
+int sensors_yy_flex_debug = 0;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+#define YY_RESTORE_YY_MORE_OFFSET
+char *sensors_yytext;
+#line 1 "lib/conf-lex.l"
+#line 2 "lib/conf-lex.l"
+/*
+    conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl> 
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+                                             &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+                                         &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+                                                &buffer_count,\
+                                                &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+                                                   &buffer, \
+                                                   &buffer_count,&buffer_max,1)
+
+/* Scanner for configuration files */
+/* All states are exclusive */
+
+
+
+/* Any whitespace-like character */
+/* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+/* Only positive whole numbers are recognized here */
+#line 1255 "<stdout>"
+
+#define INITIAL 0
+#define MIDDLE 1
+#define STRING 2
+#define ERR 3
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+static int yy_init_globals (void );
+
+/* Accessor methods to globals.
+   These are made visible to non-reentrant scanners for convenience. */
+
+int sensors_yylex_destroy (void );
+
+int sensors_yyget_debug (void );
+
+void sensors_yyset_debug (int debug_flag  );
+
+YY_EXTRA_TYPE sensors_yyget_extra (void );
+
+void sensors_yyset_extra (YY_EXTRA_TYPE user_defined  );
+
+FILE *sensors_yyget_in (void );
+
+void sensors_yyset_in  (FILE * in_str  );
+
+FILE *sensors_yyget_out (void );
+
+void sensors_yyset_out  (FILE * out_str  );
+
+int sensors_yyget_leng (void );
+
+char *sensors_yyget_text (void );
+
+int sensors_yyget_lineno (void );
+
+void sensors_yyset_lineno (int line_number  );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int sensors_yywrap (void );
+#else
+extern int sensors_yywrap (void );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#ifdef __cplusplus
+static int yyinput (void );
+#else
+static int input (void );
+#endif
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k */
+#define YY_READ_BUF_SIZE 16384
+#else
+#define YY_READ_BUF_SIZE 8192
+#endif /* __ia64__ */
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO do { if (fwrite( sensors_yytext, sensors_yyleng, 1, sensors_yyout )) {} } while (0)
+#endif
+
+/* Gets input and stuffs it into "buf".  number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_is_interactive ) \
+		{ \
+		int c = '*'; \
+		size_t n; \
+		for ( n = 0; n < max_size && \
+			     (c = getc( sensors_yyin )) != EOF && c != '\n'; ++n ) \
+			buf[n] = (char) c; \
+		if ( c == '\n' ) \
+			buf[n++] = (char) c; \
+		if ( c == EOF && ferror( sensors_yyin ) ) \
+			YY_FATAL_ERROR( "input in flex scanner failed" ); \
+		result = n; \
+		} \
+	else \
+		{ \
+		errno=0; \
+		while ( (result = fread(buf, 1, max_size, sensors_yyin))==0 && ferror(sensors_yyin)) \
+			{ \
+			if( errno != EINTR) \
+				{ \
+				YY_FATAL_ERROR( "input in flex scanner failed" ); \
+				break; \
+				} \
+			errno=0; \
+			clearerr(sensors_yyin); \
+			} \
+		}\
+\
+
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* end tables serialization structures and prototypes */
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int sensors_yylex (void);
+
+#define YY_DECL int sensors_yylex (void)
+#endif /* !YY_DECL */
+
+/* Code executed at the beginning of each rule, after sensors_yytext and sensors_yyleng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+#define YY_RULE_SETUP \
+	YY_USER_ACTION
+
+/** The main scanner function which does all the work.
+ */
+YY_DECL
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp, *yy_bp;
+	register int yy_act;
+    
+#line 80 "lib/conf-lex.l"
+
+
+ /*
+  * STATE: INITIAL
+  */
+
+#line 1450 "<stdout>"
+
+	if ( !(yy_init) )
+		{
+		(yy_init) = 1;
+
+#ifdef YY_USER_INIT
+		YY_USER_INIT;
+#endif
+
+		if ( ! (yy_start) )
+			(yy_start) = 1;	/* first start state */
+
+		if ( ! sensors_yyin )
+			sensors_yyin = stdin;
+
+		if ( ! sensors_yyout )
+			sensors_yyout = stdout;
+
+		if ( ! YY_CURRENT_BUFFER ) {
+			sensors_yyensure_buffer_stack ();
+			YY_CURRENT_BUFFER_LVALUE =
+				sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+		}
+
+		sensors_yy_load_buffer_state( );
+		}
+
+	while ( 1 )		/* loops until end-of-file is reached */
+		{
+		yy_cp = (yy_c_buf_p);
+
+		/* Support of sensors_yytext. */
+		*yy_cp = (yy_hold_char);
+
+		/* yy_bp points to the position in yy_ch_buf of the start of
+		 * the current run.
+		 */
+		yy_bp = yy_cp;
+
+		yy_current_state = (yy_start);
+yy_match:
+		while ( (yy_current_state = yy_nxt[yy_current_state][ yy_ec[YY_SC_TO_UI(*yy_cp)]  ]) > 0 )
+			++yy_cp;
+
+		yy_current_state = -yy_current_state;
+
+yy_find_action:
+		yy_act = yy_accept[yy_current_state];
+
+		YY_DO_BEFORE_ACTION;
+
+do_action:	/* This label is used only to access EOF actions. */
+
+		switch ( yy_act )
+	{ /* beginning of action switch */
+
+case YY_STATE_EOF(INITIAL):
+#line 88 "lib/conf-lex.l"
+{ /* EOF from this state terminates */
+		  return 0;
+		}
+	YY_BREAK
+case 1:
+YY_RULE_SETUP
+#line 92 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+	YY_BREAK
+case 2:
+/* rule 2 can match eol */
+YY_RULE_SETUP
+#line 94 "lib/conf-lex.l"
+{ /* eat a bare newline (possibly preceded by blanks) */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/* comments */
+case 3:
+YY_RULE_SETUP
+#line 100 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+	YY_BREAK
+case 4:
+/* rule 4 can match eol */
+YY_RULE_SETUP
+#line 102 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/*
+  * Keywords must be followed by whitespace - eat that too.
+  * If there isn't trailing whitespace, we still need to
+  * accept it as lexically correct (even though the parser
+  * will reject it anyway.)
+  */
+case 5:
+YY_RULE_SETUP
+#line 113 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return LABEL;
+		}
+	YY_BREAK
+case 6:
+YY_RULE_SETUP
+#line 120 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return SET;
+		}
+	YY_BREAK
+case 7:
+YY_RULE_SETUP
+#line 127 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return COMPUTE;
+		}
+	YY_BREAK
+case 8:
+YY_RULE_SETUP
+#line 134 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return BUS;
+		}
+	YY_BREAK
+case 9:
+YY_RULE_SETUP
+#line 141 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return CHIP;
+		}
+	YY_BREAK
+case 10:
+YY_RULE_SETUP
+#line 148 "lib/conf-lex.l"
+{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return IGNORE;
+		}
+	YY_BREAK
+/* Anything else at the beginning of a line is an error */
+case 11:
+#line 158 "lib/conf-lex.l"
+case 12:
+YY_RULE_SETUP
+#line 158 "lib/conf-lex.l"
+{
+		  BEGIN(ERR);
+		  strcpy(sensors_lex_error,"Invalid keyword");
+		  return ERROR;
+		}
+	YY_BREAK
+
+/*
+  * STATE: ERROR
+  */
+
+case 13:
+YY_RULE_SETUP
+#line 171 "lib/conf-lex.l"
+; /* eat whatever is left on this line */
+	YY_BREAK
+case 14:
+/* rule 14 can match eol */
+YY_RULE_SETUP
+#line 173 "lib/conf-lex.l"
+{
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+
+/*
+  * STATE: MIDDLE
+  */
+
+case 15:
+YY_RULE_SETUP
+#line 186 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+	YY_BREAK
+case 16:
+/* rule 16 can match eol */
+YY_RULE_SETUP
+#line 188 "lib/conf-lex.l"
+{ /* newline here sends EOL token to parser */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+case YY_STATE_EOF(MIDDLE):
+#line 194 "lib/conf-lex.l"
+{ /* EOF here sends EOL token to parser also */
+		  BEGIN(INITIAL);
+		  return EOL;
+		}
+	YY_BREAK
+case 17:
+/* rule 17 can match eol */
+YY_RULE_SETUP
+#line 199 "lib/conf-lex.l"
+{ /* eat an escaped newline with no state change */
+		  sensors_yylineno++;
+		}
+	YY_BREAK
+/* comments */
+case 18:
+YY_RULE_SETUP
+#line 205 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+	YY_BREAK
+case 19:
+/* rule 19 can match eol */
+YY_RULE_SETUP
+#line 207 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+	YY_BREAK
+/* A number */
+case 20:
+YY_RULE_SETUP
+#line 215 "lib/conf-lex.l"
+{
+		  sensors_yylval.value = atof(sensors_yytext);
+		  return FLOAT;
+		}
+	YY_BREAK
+/* Some operators */
+case 21:
+YY_RULE_SETUP
+#line 222 "lib/conf-lex.l"
+return '+';
+	YY_BREAK
+case 22:
+YY_RULE_SETUP
+#line 223 "lib/conf-lex.l"
+return '-';
+	YY_BREAK
+case 23:
+YY_RULE_SETUP
+#line 224 "lib/conf-lex.l"
+return '*';
+	YY_BREAK
+case 24:
+YY_RULE_SETUP
+#line 225 "lib/conf-lex.l"
+return '/';
+	YY_BREAK
+case 25:
+YY_RULE_SETUP
+#line 226 "lib/conf-lex.l"
+return '(';
+	YY_BREAK
+case 26:
+YY_RULE_SETUP
+#line 227 "lib/conf-lex.l"
+return ')';
+	YY_BREAK
+case 27:
+YY_RULE_SETUP
+#line 228 "lib/conf-lex.l"
+return ',';
+	YY_BREAK
+case 28:
+YY_RULE_SETUP
+#line 229 "lib/conf-lex.l"
+return '@';
+	YY_BREAK
+case 29:
+YY_RULE_SETUP
+#line 230 "lib/conf-lex.l"
+return '^';
+	YY_BREAK
+case 30:
+YY_RULE_SETUP
+#line 231 "lib/conf-lex.l"
+return '`';
+	YY_BREAK
+/* Quoted string */
+case 31:
+YY_RULE_SETUP
+#line 235 "lib/conf-lex.l"
+{
+		  buffer_malloc();
+		  BEGIN(STRING);
+		}
+	YY_BREAK
+/* A normal, unquoted identifier */
+case 32:
+YY_RULE_SETUP
+#line 242 "lib/conf-lex.l"
+{
+		  sensors_yylval.name = strdup(sensors_yytext);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  
+		  return NAME;
+		}
+	YY_BREAK
+/* anything else is bogus */
+case 33:
+#line 254 "lib/conf-lex.l"
+case 34:
+#line 255 "lib/conf-lex.l"
+case 35:
+YY_RULE_SETUP
+#line 255 "lib/conf-lex.l"
+{
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+
+/*
+  * STATE: STRING
+  */
+
+/* Oops, newline or EOF while in a string is not good */
+case 36:
+/* rule 36 can match eol */
+#line 270 "lib/conf-lex.l"
+case 37:
+/* rule 37 can match eol */
+YY_RULE_SETUP
+#line 270 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"No matching double quote.");
+		  buffer_free();
+		  yyless(0);
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+case YY_STATE_EOF(STRING):
+#line 280 "lib/conf-lex.l"
+{
+		  strcpy(sensors_lex_error,
+			"Reached end-of-file without a matching double quote.");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return ERROR;
+		}
+	YY_BREAK
+/* At the end */
+case 38:
+YY_RULE_SETUP
+#line 290 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"Quoted strings must be separated by whitespace.");
+		  buffer_free();
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+	YY_BREAK
+case 39:
+YY_RULE_SETUP
+#line 299 "lib/conf-lex.l"
+{
+		  buffer_add_char("\0");
+		  sensors_yylval.name = strdup(buffer);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return NAME;
+		}
+	YY_BREAK
+case 40:
+YY_RULE_SETUP
+#line 310 "lib/conf-lex.l"
+buffer_add_char("\a");
+	YY_BREAK
+case 41:
+YY_RULE_SETUP
+#line 311 "lib/conf-lex.l"
+buffer_add_char("\b");
+	YY_BREAK
+case 42:
+YY_RULE_SETUP
+#line 312 "lib/conf-lex.l"
+buffer_add_char("\f");
+	YY_BREAK
+case 43:
+YY_RULE_SETUP
+#line 313 "lib/conf-lex.l"
+buffer_add_char("\n");
+	YY_BREAK
+case 44:
+YY_RULE_SETUP
+#line 314 "lib/conf-lex.l"
+buffer_add_char("\r");
+	YY_BREAK
+case 45:
+YY_RULE_SETUP
+#line 315 "lib/conf-lex.l"
+buffer_add_char("\t");
+	YY_BREAK
+case 46:
+YY_RULE_SETUP
+#line 316 "lib/conf-lex.l"
+buffer_add_char("\v");
+	YY_BREAK
+/* Other escapes: just copy the character behind the slash */
+case 47:
+YY_RULE_SETUP
+#line 320 "lib/conf-lex.l"
+{
+		  buffer_add_char(&sensors_yytext[1]);
+		}
+	YY_BREAK
+/* Anything else (including a bare '\' which may be followed by EOF) */
+case 48:
+#line 327 "lib/conf-lex.l"
+case 49:
+YY_RULE_SETUP
+#line 327 "lib/conf-lex.l"
+{
+		  buffer_add_string(sensors_yytext);
+		}
+	YY_BREAK
+
+case 50:
+YY_RULE_SETUP
+#line 332 "lib/conf-lex.l"
+YY_FATAL_ERROR( "flex scanner jammed" );
+	YY_BREAK
+#line 1903 "<stdout>"
+			case YY_STATE_EOF(ERR):
+				yyterminate();
+
+	case YY_END_OF_BUFFER:
+		{
+		/* Amount of text matched not including the EOB char. */
+		int yy_amount_of_matched_text = (int) (yy_cp - (yytext_ptr)) - 1;
+
+		/* Undo the effects of YY_DO_BEFORE_ACTION. */
+		*yy_cp = (yy_hold_char);
+		YY_RESTORE_YY_MORE_OFFSET
+
+		if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_NEW )
+			{
+			/* We're scanning a new file or input source.  It's
+			 * possible that this happened because the user
+			 * just pointed sensors_yyin at a new source and called
+			 * sensors_yylex().  If so, then we have to assure
+			 * consistency between YY_CURRENT_BUFFER and our
+			 * globals.  Here is the right place to do so, because
+			 * this is the first action (other than possibly a
+			 * back-up) that will match for the new input source.
+			 */
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+			YY_CURRENT_BUFFER_LVALUE->yy_input_file = sensors_yyin;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status = YY_BUFFER_NORMAL;
+			}
+
+		/* Note that here we test for yy_c_buf_p "<=" to the position
+		 * of the first EOB in the buffer, since yy_c_buf_p will
+		 * already have been incremented past the NUL character
+		 * (since all states make transitions on EOB to the
+		 * end-of-buffer state).  Contrast this with the test
+		 * in input().
+		 */
+		if ( (yy_c_buf_p) <= &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			{ /* This was really a NUL. */
+			yy_state_type yy_next_state;
+
+			(yy_c_buf_p) = (yytext_ptr) + yy_amount_of_matched_text;
+
+			yy_current_state = yy_get_previous_state(  );
+
+			/* Okay, we're now positioned to make the NUL
+			 * transition.  We couldn't have
+			 * yy_get_previous_state() go ahead and do it
+			 * for us because it doesn't know how to deal
+			 * with the possibility of jamming (and we don't
+			 * want to build jamming into it because then it
+			 * will run more slowly).
+			 */
+
+			yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+			yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+
+			if ( yy_next_state )
+				{
+				/* Consume the NUL. */
+				yy_cp = ++(yy_c_buf_p);
+				yy_current_state = yy_next_state;
+				goto yy_match;
+				}
+
+			else
+				{
+				yy_cp = (yy_c_buf_p);
+				goto yy_find_action;
+				}
+			}
+
+		else switch ( yy_get_next_buffer(  ) )
+			{
+			case EOB_ACT_END_OF_FILE:
+				{
+				(yy_did_buffer_switch_on_eof) = 0;
+
+				if ( sensors_yywrap( ) )
+					{
+					/* Note: because we've taken care in
+					 * yy_get_next_buffer() to have set up
+					 * sensors_yytext, we can now set up
+					 * yy_c_buf_p so that if some total
+					 * hoser (like flex itself) wants to
+					 * call the scanner after we return the
+					 * YY_NULL, it'll still work - another
+					 * YY_NULL will get returned.
+					 */
+					(yy_c_buf_p) = (yytext_ptr) + YY_MORE_ADJ;
+
+					yy_act = YY_STATE_EOF(YY_START);
+					goto do_action;
+					}
+
+				else
+					{
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+					}
+				break;
+				}
+
+			case EOB_ACT_CONTINUE_SCAN:
+				(yy_c_buf_p) =
+					(yytext_ptr) + yy_amount_of_matched_text;
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_match;
+
+			case EOB_ACT_LAST_MATCH:
+				(yy_c_buf_p) =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)];
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_find_action;
+			}
+		break;
+		}
+
+	default:
+		YY_FATAL_ERROR(
+			"fatal flex scanner internal error--no action found" );
+	} /* end of action switch */
+		} /* end of scanning one token */
+} /* end of sensors_yylex */
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ *	EOB_ACT_LAST_MATCH -
+ *	EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ *	EOB_ACT_END_OF_FILE - end of file
+ */
+static int yy_get_next_buffer (void)
+{
+    	register char *dest = YY_CURRENT_BUFFER_LVALUE->yy_ch_buf;
+	register char *source = (yytext_ptr);
+	register int number_to_move, i;
+	int ret_val;
+
+	if ( (yy_c_buf_p) > &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] )
+		YY_FATAL_ERROR(
+		"fatal flex scanner internal error--end of buffer missed" );
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_fill_buffer == 0 )
+		{ /* Don't try to fill the buffer, so this is an EOF. */
+		if ( (yy_c_buf_p) - (yytext_ptr) - YY_MORE_ADJ == 1 )
+			{
+			/* We matched a single character, the EOB, so
+			 * treat this as a final EOF.
+			 */
+			return EOB_ACT_END_OF_FILE;
+			}
+
+		else
+			{
+			/* We matched some text prior to the EOB, first
+			 * process it.
+			 */
+			return EOB_ACT_LAST_MATCH;
+			}
+		}
+
+	/* Try to read more data. */
+
+	/* First move last chars to start of buffer. */
+	number_to_move = (int) ((yy_c_buf_p) - (yytext_ptr)) - 1;
+
+	for ( i = 0; i < number_to_move; ++i )
+		*(dest++) = *(source++);
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+		/* don't do the read, it's not guaranteed to return an EOF,
+		 * just force an EOF
+		 */
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars) = 0;
+
+	else
+		{
+			int num_to_read =
+			YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
+
+		while ( num_to_read <= 0 )
+			{ /* Not enough room in the buffer - grow it. */
+
+			/* just a shorter name for the current buffer */
+			YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+
+			int yy_c_buf_p_offset =
+				(int) ((yy_c_buf_p) - b->yy_ch_buf);
+
+			if ( b->yy_is_our_buffer )
+				{
+				int new_size = b->yy_buf_size * 2;
+
+				if ( new_size <= 0 )
+					b->yy_buf_size += b->yy_buf_size / 8;
+				else
+					b->yy_buf_size *= 2;
+
+				b->yy_ch_buf = (char *)
+					/* Include room in for 2 EOB chars. */
+					sensors_yyrealloc((void *) b->yy_ch_buf,b->yy_buf_size + 2  );
+				}
+			else
+				/* Can't grow it, we don't own it. */
+				b->yy_ch_buf = 0;
+
+			if ( ! b->yy_ch_buf )
+				YY_FATAL_ERROR(
+				"fatal error - scanner input buffer overflow" );
+
+			(yy_c_buf_p) = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+			num_to_read = YY_CURRENT_BUFFER_LVALUE->yy_buf_size -
+						number_to_move - 1;
+
+			}
+
+		if ( num_to_read > YY_READ_BUF_SIZE )
+			num_to_read = YY_READ_BUF_SIZE;
+
+		/* Read in more data. */
+		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
+			(yy_n_chars), (size_t) num_to_read );
+
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	if ( (yy_n_chars) == 0 )
+		{
+		if ( number_to_move == YY_MORE_ADJ )
+			{
+			ret_val = EOB_ACT_END_OF_FILE;
+			sensors_yyrestart(sensors_yyin  );
+			}
+
+		else
+			{
+			ret_val = EOB_ACT_LAST_MATCH;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status =
+				YY_BUFFER_EOF_PENDING;
+			}
+		}
+
+	else
+		ret_val = EOB_ACT_CONTINUE_SCAN;
+
+	if ((yy_size_t) ((yy_n_chars) + number_to_move) > YY_CURRENT_BUFFER_LVALUE->yy_buf_size) {
+		/* Extend the array by 50%, plus the number we really need. */
+		yy_size_t new_size = (yy_n_chars) + number_to_move + ((yy_n_chars) >> 1);
+		YY_CURRENT_BUFFER_LVALUE->yy_ch_buf = (char *) sensors_yyrealloc((void *) YY_CURRENT_BUFFER_LVALUE->yy_ch_buf,new_size  );
+		if ( ! YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+			YY_FATAL_ERROR( "out of dynamic memory in yy_get_next_buffer()" );
+	}
+
+	(yy_n_chars) += number_to_move;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] = YY_END_OF_BUFFER_CHAR;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] = YY_END_OF_BUFFER_CHAR;
+
+	(yytext_ptr) = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[0];
+
+	return ret_val;
+}
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+    static yy_state_type yy_get_previous_state (void)
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp;
+    
+	yy_current_state = (yy_start);
+
+	for ( yy_cp = (yytext_ptr) + YY_MORE_ADJ; yy_cp < (yy_c_buf_p); ++yy_cp )
+		{
+		yy_current_state = yy_nxt[yy_current_state][(*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1)];
+		}
+
+	return yy_current_state;
+}
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ *	next_state = yy_try_NUL_trans( current_state );
+ */
+    static yy_state_type yy_try_NUL_trans  (yy_state_type yy_current_state )
+{
+	register int yy_is_jam;
+    
+	yy_current_state = yy_nxt[yy_current_state][1];
+	yy_is_jam = (yy_current_state <= 0);
+
+	return yy_is_jam ? 0 : yy_current_state;
+}
+
+#ifndef YY_NO_INPUT
+#ifdef __cplusplus
+    static int yyinput (void)
+#else
+    static int input  (void)
+#endif
+
+{
+	int c;
+    
+	*(yy_c_buf_p) = (yy_hold_char);
+
+	if ( *(yy_c_buf_p) == YY_END_OF_BUFFER_CHAR )
+		{
+		/* yy_c_buf_p now points to the character we want to return.
+		 * If this occurs *before* the EOB characters, then it's a
+		 * valid NUL; if not, then we've hit the end of the buffer.
+		 */
+		if ( (yy_c_buf_p) < &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			/* This was really a NUL. */
+			*(yy_c_buf_p) = '\0';
+
+		else
+			{ /* need more input */
+			int offset = (yy_c_buf_p) - (yytext_ptr);
+			++(yy_c_buf_p);
+
+			switch ( yy_get_next_buffer(  ) )
+				{
+				case EOB_ACT_LAST_MATCH:
+					/* This happens because yy_g_n_b()
+					 * sees that we've accumulated a
+					 * token and flags that we need to
+					 * try matching the token before
+					 * proceeding.  But for input(),
+					 * there's no matching to consider.
+					 * So convert the EOB_ACT_LAST_MATCH
+					 * to EOB_ACT_END_OF_FILE.
+					 */
+
+					/* Reset buffer status. */
+					sensors_yyrestart(sensors_yyin );
+
+					/*FALLTHROUGH*/
+
+				case EOB_ACT_END_OF_FILE:
+					{
+					if ( sensors_yywrap( ) )
+						return EOF;
+
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+#ifdef __cplusplus
+					return yyinput();
+#else
+					return input();
+#endif
+					}
+
+				case EOB_ACT_CONTINUE_SCAN:
+					(yy_c_buf_p) = (yytext_ptr) + offset;
+					break;
+				}
+			}
+		}
+
+	c = *(unsigned char *) (yy_c_buf_p);	/* cast for 8-bit char's */
+	*(yy_c_buf_p) = '\0';	/* preserve sensors_yytext */
+	(yy_hold_char) = *++(yy_c_buf_p);
+
+	return c;
+}
+#endif	/* ifndef YY_NO_INPUT */
+
+/** Immediately switch to a different input stream.
+ * @param input_file A readable stream.
+ * 
+ * @note This function does not reset the start condition to @c INITIAL .
+ */
+    void sensors_yyrestart  (FILE * input_file )
+{
+    
+	if ( ! YY_CURRENT_BUFFER ){
+        sensors_yyensure_buffer_stack ();
+		YY_CURRENT_BUFFER_LVALUE =
+            sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+	}
+
+	sensors_yy_init_buffer(YY_CURRENT_BUFFER,input_file );
+	sensors_yy_load_buffer_state( );
+}
+
+/** Switch to a different input buffer.
+ * @param new_buffer The new input buffer.
+ * 
+ */
+    void sensors_yy_switch_to_buffer  (YY_BUFFER_STATE  new_buffer )
+{
+    
+	/* TODO. We should be able to replace this entire function body
+	 * with
+	 *		sensors_yypop_buffer_state();
+	 *		sensors_yypush_buffer_state(new_buffer);
+     */
+	sensors_yyensure_buffer_stack ();
+	if ( YY_CURRENT_BUFFER == new_buffer )
+		return;
+
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+	sensors_yy_load_buffer_state( );
+
+	/* We don't actually know whether we did this switch during
+	 * EOF (sensors_yywrap()) processing, but the only time this flag
+	 * is looked at is after sensors_yywrap() is called, so it's safe
+	 * to go ahead and always set it.
+	 */
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+static void sensors_yy_load_buffer_state  (void)
+{
+    	(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+	(yytext_ptr) = (yy_c_buf_p) = YY_CURRENT_BUFFER_LVALUE->yy_buf_pos;
+	sensors_yyin = YY_CURRENT_BUFFER_LVALUE->yy_input_file;
+	(yy_hold_char) = *(yy_c_buf_p);
+}
+
+/** Allocate and initialize an input buffer state.
+ * @param file A readable stream.
+ * @param size The character buffer size in bytes. When in doubt, use @c YY_BUF_SIZE.
+ * 
+ * @return the allocated buffer state.
+ */
+    YY_BUFFER_STATE sensors_yy_create_buffer  (FILE * file, int  size )
+{
+	YY_BUFFER_STATE b;
+    
+	b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+	b->yy_buf_size = size;
+
+	/* yy_ch_buf has to be 2 characters longer than the size given because
+	 * we need to put in 2 end-of-buffer characters.
+	 */
+	b->yy_ch_buf = (char *) sensors_yyalloc(b->yy_buf_size + 2  );
+	if ( ! b->yy_ch_buf )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+	b->yy_is_our_buffer = 1;
+
+	sensors_yy_init_buffer(b,file );
+
+	return b;
+}
+
+/** Destroy the buffer.
+ * @param b a buffer created with sensors_yy_create_buffer()
+ * 
+ */
+    void sensors_yy_delete_buffer (YY_BUFFER_STATE  b )
+{
+    
+	if ( ! b )
+		return;
+
+	if ( b == YY_CURRENT_BUFFER ) /* Not sure if we should pop here. */
+		YY_CURRENT_BUFFER_LVALUE = (YY_BUFFER_STATE) 0;
+
+	if ( b->yy_is_our_buffer )
+		sensors_yyfree((void *) b->yy_ch_buf  );
+
+	sensors_yyfree((void *) b  );
+}
+
+#ifndef __cplusplus
+extern int isatty (int );
+#endif /* __cplusplus */
+    
+/* Initializes or reinitializes a buffer.
+ * This function is sometimes called more than once on the same buffer,
+ * such as during a sensors_yyrestart() or at EOF.
+ */
+    static void sensors_yy_init_buffer  (YY_BUFFER_STATE  b, FILE * file )
+
+{
+	int oerrno = errno;
+    
+	sensors_yy_flush_buffer(b );
+
+	b->yy_input_file = file;
+	b->yy_fill_buffer = 1;
+
+    /* If b is the current buffer, then sensors_yy_init_buffer was _probably_
+     * called from sensors_yyrestart() or through yy_get_next_buffer.
+     * In that case, we don't want to reset the lineno or column.
+     */
+    if (b != YY_CURRENT_BUFFER){
+        b->yy_bs_lineno = 1;
+        b->yy_bs_column = 0;
+    }
+
+        b->yy_is_interactive = file ? (isatty( fileno(file) ) > 0) : 0;
+    
+	errno = oerrno;
+}
+
+/** Discard all buffered characters. On the next scan, YY_INPUT will be called.
+ * @param b the buffer state to be flushed, usually @c YY_CURRENT_BUFFER.
+ * 
+ */
+    void sensors_yy_flush_buffer (YY_BUFFER_STATE  b )
+{
+    	if ( ! b )
+		return;
+
+	b->yy_n_chars = 0;
+
+	/* We always need two end-of-buffer characters.  The first causes
+	 * a transition to the end-of-buffer state.  The second causes
+	 * a jam in that state.
+	 */
+	b->yy_ch_buf[0] = YY_END_OF_BUFFER_CHAR;
+	b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+
+	b->yy_buf_pos = &b->yy_ch_buf[0];
+
+	b->yy_at_bol = 1;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	if ( b == YY_CURRENT_BUFFER )
+		sensors_yy_load_buffer_state( );
+}
+
+/** Pushes the new state onto the stack. The new state becomes
+ *  the current state. This function will allocate the stack
+ *  if necessary.
+ *  @param new_buffer The new state.
+ *  
+ */
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer )
+{
+    	if (new_buffer == NULL)
+		return;
+
+	sensors_yyensure_buffer_stack();
+
+	/* This block is copied from sensors_yy_switch_to_buffer. */
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	/* Only push if top exists. Otherwise, replace top. */
+	if (YY_CURRENT_BUFFER)
+		(yy_buffer_stack_top)++;
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+
+	/* copied from sensors_yy_switch_to_buffer. */
+	sensors_yy_load_buffer_state( );
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+/** Removes and deletes the top of the stack, if present.
+ *  The next element becomes the new top.
+ *  
+ */
+void sensors_yypop_buffer_state (void)
+{
+    	if (!YY_CURRENT_BUFFER)
+		return;
+
+	sensors_yy_delete_buffer(YY_CURRENT_BUFFER );
+	YY_CURRENT_BUFFER_LVALUE = NULL;
+	if ((yy_buffer_stack_top) > 0)
+		--(yy_buffer_stack_top);
+
+	if (YY_CURRENT_BUFFER) {
+		sensors_yy_load_buffer_state( );
+		(yy_did_buffer_switch_on_eof) = 1;
+	}
+}
+
+/* Allocates the stack if it does not exist.
+ *  Guarantees space for at least one push.
+ */
+static void sensors_yyensure_buffer_stack (void)
+{
+	int num_to_alloc;
+    
+	if (!(yy_buffer_stack)) {
+
+		/* First allocation is just for 2 elements, since we don't know if this
+		 * scanner will even need a stack. We use 2 instead of 1 to avoid an
+		 * immediate realloc on the next call.
+         */
+		num_to_alloc = 1;
+		(yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyalloc
+								(num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+								  
+		memset((yy_buffer_stack), 0, num_to_alloc * sizeof(struct yy_buffer_state*));
+				
+		(yy_buffer_stack_max) = num_to_alloc;
+		(yy_buffer_stack_top) = 0;
+		return;
+	}
+
+	if ((yy_buffer_stack_top) >= ((yy_buffer_stack_max)) - 1){
+
+		/* Increase the buffer to prepare for a possible push. */
+		int grow_size = 8 /* arbitrary grow size */;
+
+		num_to_alloc = (yy_buffer_stack_max) + grow_size;
+		(yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyrealloc
+								((yy_buffer_stack),
+								num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		if ( ! (yy_buffer_stack) )
+			YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+
+		/* zero only the new slots.*/
+		memset((yy_buffer_stack) + (yy_buffer_stack_max), 0, grow_size * sizeof(struct yy_buffer_state*));
+		(yy_buffer_stack_max) = num_to_alloc;
+	}
+}
+
+/** Setup the input buffer state to scan directly from a user-specified character buffer.
+ * @param base the character buffer
+ * @param size the size in bytes of the character buffer
+ * 
+ * @return the newly allocated buffer state object. 
+ */
+YY_BUFFER_STATE sensors_yy_scan_buffer  (char * base, yy_size_t  size )
+{
+	YY_BUFFER_STATE b;
+    
+	if ( size < 2 ||
+	     base[size-2] != YY_END_OF_BUFFER_CHAR ||
+	     base[size-1] != YY_END_OF_BUFFER_CHAR )
+		/* They forgot to leave room for the EOB's. */
+		return 0;
+
+	b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_buffer()" );
+
+	b->yy_buf_size = size - 2;	/* "- 2" to take care of EOB's */
+	b->yy_buf_pos = b->yy_ch_buf = base;
+	b->yy_is_our_buffer = 0;
+	b->yy_input_file = 0;
+	b->yy_n_chars = b->yy_buf_size;
+	b->yy_is_interactive = 0;
+	b->yy_at_bol = 1;
+	b->yy_fill_buffer = 0;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	sensors_yy_switch_to_buffer(b  );
+
+	return b;
+}
+
+/** Setup the input buffer state to scan a string. The next call to sensors_yylex() will
+ * scan from a @e copy of @a str.
+ * @param yystr a NUL-terminated string to scan
+ * 
+ * @return the newly allocated buffer state object.
+ * @note If you want to scan bytes that may contain NUL values, then use
+ *       sensors_yy_scan_bytes() instead.
+ */
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char * yystr )
+{
+    
+	return sensors_yy_scan_bytes(yystr,strlen(yystr) );
+}
+
+/** Setup the input buffer state to scan the given bytes. The next call to sensors_yylex() will
+ * scan from a @e copy of @a bytes.
+ * @param yybytes the byte buffer to scan
+ * @param _yybytes_len the number of bytes in the buffer pointed to by @a bytes.
+ * 
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE sensors_yy_scan_bytes  (yyconst char * yybytes, int  _yybytes_len )
+{
+	YY_BUFFER_STATE b;
+	char *buf;
+	yy_size_t n;
+	int i;
+    
+	/* Get memory for full buffer, including space for trailing EOB's. */
+	n = _yybytes_len + 2;
+	buf = (char *) sensors_yyalloc(n  );
+	if ( ! buf )
+		YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_bytes()" );
+
+	for ( i = 0; i < _yybytes_len; ++i )
+		buf[i] = yybytes[i];
+
+	buf[_yybytes_len] = buf[_yybytes_len+1] = YY_END_OF_BUFFER_CHAR;
+
+	b = sensors_yy_scan_buffer(buf,n );
+	if ( ! b )
+		YY_FATAL_ERROR( "bad buffer in sensors_yy_scan_bytes()" );
+
+	/* It's okay to grow etc. this buffer, and we should throw it
+	 * away when we're done.
+	 */
+	b->yy_is_our_buffer = 1;
+
+	return b;
+}
+
+#ifndef YY_EXIT_FAILURE
+#define YY_EXIT_FAILURE 2
+#endif
+
+static void yy_fatal_error (yyconst char* msg )
+{
+    	(void) fprintf( stderr, "%s\n", msg );
+	exit( YY_EXIT_FAILURE );
+}
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up sensors_yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		sensors_yytext[sensors_yyleng] = (yy_hold_char); \
+		(yy_c_buf_p) = sensors_yytext + yyless_macro_arg; \
+		(yy_hold_char) = *(yy_c_buf_p); \
+		*(yy_c_buf_p) = '\0'; \
+		sensors_yyleng = yyless_macro_arg; \
+		} \
+	while ( 0 )
+
+/* Accessor  methods (get/set functions) to struct members. */
+
+/** Get the current line number.
+ * 
+ */
+int sensors_yyget_lineno  (void)
+{
+        
+    return sensors_yylineno;
+}
+
+/** Get the input stream.
+ * 
+ */
+FILE *sensors_yyget_in  (void)
+{
+        return sensors_yyin;
+}
+
+/** Get the output stream.
+ * 
+ */
+FILE *sensors_yyget_out  (void)
+{
+        return sensors_yyout;
+}
+
+/** Get the length of the current token.
+ * 
+ */
+int sensors_yyget_leng  (void)
+{
+        return sensors_yyleng;
+}
+
+/** Get the current token.
+ * 
+ */
+
+char *sensors_yyget_text  (void)
+{
+        return sensors_yytext;
+}
+
+/** Set the current line number.
+ * @param line_number
+ * 
+ */
+void sensors_yyset_lineno (int  line_number )
+{
+    
+    sensors_yylineno = line_number;
+}
+
+/** Set the input stream. This does not discard the current
+ * input buffer.
+ * @param in_str A readable stream.
+ * 
+ * @see sensors_yy_switch_to_buffer
+ */
+void sensors_yyset_in (FILE *  in_str )
+{
+        sensors_yyin = in_str ;
+}
+
+void sensors_yyset_out (FILE *  out_str )
+{
+        sensors_yyout = out_str ;
+}
+
+int sensors_yyget_debug  (void)
+{
+        return sensors_yy_flex_debug;
+}
+
+void sensors_yyset_debug (int  bdebug )
+{
+        sensors_yy_flex_debug = bdebug ;
+}
+
+static int yy_init_globals (void)
+{
+        /* Initialization is the same as for the non-reentrant scanner.
+     * This function is called from sensors_yylex_destroy(), so don't allocate here.
+     */
+
+    (yy_buffer_stack) = 0;
+    (yy_buffer_stack_top) = 0;
+    (yy_buffer_stack_max) = 0;
+    (yy_c_buf_p) = (char *) 0;
+    (yy_init) = 0;
+    (yy_start) = 0;
+
+/* Defined in main.c */
+#ifdef YY_STDINIT
+    sensors_yyin = stdin;
+    sensors_yyout = stdout;
+#else
+    sensors_yyin = (FILE *) 0;
+    sensors_yyout = (FILE *) 0;
+#endif
+
+    /* For future reference: Set errno on error, since we are called by
+     * sensors_yylex_init()
+     */
+    return 0;
+}
+
+/* sensors_yylex_destroy is for both reentrant and non-reentrant scanners. */
+int sensors_yylex_destroy  (void)
+{
+    
+    /* Pop the buffer stack, destroying each element. */
+	while(YY_CURRENT_BUFFER){
+		sensors_yy_delete_buffer(YY_CURRENT_BUFFER  );
+		YY_CURRENT_BUFFER_LVALUE = NULL;
+		sensors_yypop_buffer_state();
+	}
+
+	/* Destroy the stack itself. */
+	sensors_yyfree((yy_buffer_stack) );
+	(yy_buffer_stack) = NULL;
+
+    /* Reset the globals. This is important in a non-reentrant scanner so the next time
+     * sensors_yylex() is called, initialization will occur. */
+    yy_init_globals( );
+
+    return 0;
+}
+
+/*
+ * Internal utility routines.
+ */
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char* s1, yyconst char * s2, int n )
+{
+	register int i;
+	for ( i = 0; i < n; ++i )
+		s1[i] = s2[i];
+}
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * s )
+{
+	register int n;
+	for ( n = 0; s[n]; ++n )
+		;
+
+	return n;
+}
+#endif
+
+void *sensors_yyalloc (yy_size_t  size )
+{
+	return (void *) malloc( size );
+}
+
+void *sensors_yyrealloc  (void * ptr, yy_size_t  size )
+{
+	/* The cast to (char *) in the following accommodates both
+	 * implementations that use char* generic pointers, and those
+	 * that use void* generic pointers.  It works with the latter
+	 * because both ANSI C and C++ allow castless assignment from
+	 * any pointer type to void*, and deal with argument conversions
+	 * as though doing an assignment.
+	 */
+	return (void *) realloc( (char *) ptr, size );
+}
+
+void sensors_yyfree (void * ptr )
+{
+	free( (char *) ptr );	/* see sensors_yyrealloc() for (char *) cast */
+}
+
+#define YYTABLES_NAME "yytables"
+
+#line 332 "lib/conf-lex.l"
+
+
+
+/*
+	Do the buffer handling manually.  This allows us to scan as many
+	config files as we need to, while cleaning up properly after each
+	one.  The "BEGIN(0)" line ensures that we start in the default state,
+	even if e.g. the previous config file was syntactically broken.
+
+	Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+	BEGIN(0);
+	if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+		return -1;
+
+	sensors_yy_switch_to_buffer(scan_buf);
+	sensors_yyfilename = filename;
+	sensors_yylineno = 1;
+	return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+	sensors_yy_delete_buffer(scan_buf);
+	scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, sensors_yylex_destroy() must be called when done with the
+   scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+    (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+				    (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+	sensors_yylex_destroy();
+#endif
+#endif
+}
+
+
diff --git a/tools/gator/daemon/libsensors/conf-lex.l b/tools/gator/daemon/libsensors/conf-lex.l
new file mode 100644
index 000000000000..43ddbd8f5bd5
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.l
@@ -0,0 +1,372 @@
+%{
+/*
+    conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl> 
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+                                             &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+                                         &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+                                                &buffer_count,\
+                                                &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+                                                   &buffer, \
+                                                   &buffer_count,&buffer_max,1)
+
+%}
+
+ /* Scanner for configuration files */
+
+%option nodefault
+%option noyywrap
+%option nounput
+
+ /* All states are exclusive */
+
+%x MIDDLE
+%x STRING
+%x ERR
+
+ /* Any whitespace-like character */
+
+BLANK		[ \f\r\t\v]
+
+IDCHAR		[[:alnum:]_]
+
+ /* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+
+FLOAT   [[:digit:]]*\.?[[:digit:]]+
+
+ /* Only positive whole numbers are recognized here */
+
+NUM	0|([1-9][[:digit:]]*)
+
+
+%%
+
+ /*
+  * STATE: INITIAL
+  */
+
+<INITIAL>{
+
+<<EOF>>		{ /* EOF from this state terminates */
+		  return 0;
+		}
+
+{BLANK}+	; /* eat as many blanks as possible at once */
+
+{BLANK}*\n	{ /* eat a bare newline (possibly preceded by blanks) */
+		  sensors_yylineno++;
+		}
+
+ /* comments */
+
+#.*		; /* eat the rest of the line after comment char */
+
+#.*\n		{ /* eat the rest of the line after comment char */
+		  sensors_yylineno++;
+		}
+
+ /*
+  * Keywords must be followed by whitespace - eat that too.
+  * If there isn't trailing whitespace, we still need to
+  * accept it as lexically correct (even though the parser
+  * will reject it anyway.)
+  */
+
+label{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return LABEL;
+		}
+
+set{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return SET;
+		}
+
+compute{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return COMPUTE;
+		}
+
+bus{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return BUS;
+		}
+
+chip{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return CHIP;
+		}
+
+ignore{BLANK}*	{
+		  sensors_yylval.line.filename = sensors_yyfilename;
+		  sensors_yylval.line.lineno = sensors_yylineno;
+		  BEGIN(MIDDLE);
+		  return IGNORE;
+		}
+
+ /* Anything else at the beginning of a line is an error */
+
+[a-z]+		|
+.		{
+		  BEGIN(ERR);
+		  strcpy(sensors_lex_error,"Invalid keyword");
+		  return ERROR;
+		}
+}
+
+ /*
+  * STATE: ERROR
+  */
+
+<ERR>{
+
+.*		; /* eat whatever is left on this line */
+
+\n		{
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+}
+
+ /*
+  * STATE: MIDDLE
+  */
+
+<MIDDLE>{
+
+{BLANK}+	; /* eat as many blanks as possible at once */
+
+\n		{ /* newline here sends EOL token to parser */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+
+<<EOF>>		{ /* EOF here sends EOL token to parser also */
+		  BEGIN(INITIAL);
+		  return EOL;
+		}
+
+\\{BLANK}*\n	{ /* eat an escaped newline with no state change */
+		  sensors_yylineno++;
+		}
+
+ /* comments */
+
+#.*		; /* eat the rest of the line after comment char */
+
+#.*\n		{ /* eat the rest of the line after comment char */
+		  BEGIN(INITIAL);
+		  sensors_yylineno++;
+		  return EOL;
+		}
+
+ /* A number */
+
+{FLOAT}		{
+		  sensors_yylval.value = atof(sensors_yytext);
+		  return FLOAT;
+		}
+
+ /* Some operators */
+
+"+"		return '+';
+"-"		return '-';
+"*"		return '*';
+"/"		return '/';
+"("		return '(';
+")"		return ')';
+","		return ',';
+"@"		return '@';
+"^"		return '^';
+"`"		return '`';
+
+ /* Quoted string */
+
+\"		{
+		  buffer_malloc();
+		  BEGIN(STRING);
+		}
+
+ /* A normal, unquoted identifier */
+
+{IDCHAR}+	{
+		  sensors_yylval.name = strdup(sensors_yytext);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  
+		  return NAME;
+		}
+
+ /* anything else is bogus */
+
+.		|
+[[:digit:]]*\.	|
+\\{BLANK}*	{
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+}
+
+ /*
+  * STATE: STRING
+  */
+
+<STRING>{
+
+ /* Oops, newline or EOF while in a string is not good */
+
+\n		|
+\\\n		{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"No matching double quote.");
+		  buffer_free();
+		  yyless(0);
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+
+<<EOF>>		{
+		  strcpy(sensors_lex_error,
+			"Reached end-of-file without a matching double quote.");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return ERROR;
+		}
+
+ /* At the end */
+
+\"\"		{
+		  buffer_add_char("\0");
+		  strcpy(sensors_lex_error,
+			"Quoted strings must be separated by whitespace.");
+		  buffer_free();
+		  BEGIN(ERR);
+		  return ERROR;
+		}
+		
+\"		{
+		  buffer_add_char("\0");
+		  sensors_yylval.name = strdup(buffer);
+		  if (! sensors_yylval.name)
+		    sensors_fatal_error("conf-lex.l",
+                                        "Allocating a new string");
+		  buffer_free();
+		  BEGIN(MIDDLE);
+		  return NAME;
+		}
+
+\\a		buffer_add_char("\a");
+\\b		buffer_add_char("\b");
+\\f		buffer_add_char("\f");
+\\n		buffer_add_char("\n");
+\\r		buffer_add_char("\r");
+\\t		buffer_add_char("\t");
+\\v		buffer_add_char("\v");
+
+ /* Other escapes: just copy the character behind the slash */
+
+\\.		{
+		  buffer_add_char(&sensors_yytext[1]);
+		}
+
+ /* Anything else (including a bare '\' which may be followed by EOF) */
+
+\\		|
+[^\\\n\"]+	{
+		  buffer_add_string(sensors_yytext);
+		}
+}
+
+%%
+
+/*
+	Do the buffer handling manually.  This allows us to scan as many
+	config files as we need to, while cleaning up properly after each
+	one.  The "BEGIN(0)" line ensures that we start in the default state,
+	even if e.g. the previous config file was syntactically broken.
+
+	Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+	BEGIN(0);
+	if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+		return -1;
+
+	sensors_yy_switch_to_buffer(scan_buf);
+	sensors_yyfilename = filename;
+	sensors_yylineno = 1;
+	return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+	sensors_yy_delete_buffer(scan_buf);
+	scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, yylex_destroy() must be called when done with the
+   scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+    (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+				    (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+	sensors_yylex_destroy();
+#endif
+#endif
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.c b/tools/gator/daemon/libsensors/conf-parse.c
new file mode 100644
index 000000000000..fb775460a1c3
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.c
@@ -0,0 +1,2042 @@
+/* A Bison parser, made by GNU Bison 2.5.  */
+
+/* Bison implementation for Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+/* C LALR(1) parser skeleton written by Richard Stallman, by
+   simplifying the original so-called "semantic" parser.  */
+
+/* All symbols defined below should begin with yy or YY, to avoid
+   infringing on user name space.  This should be done even for local
+   variables, as they might otherwise be expanded by user macros.
+   There are some unavoidable exceptions within include files to
+   define necessary library symbols; they are noted "INFRINGES ON
+   USER NAME SPACE" below.  */
+
+/* Identify Bison output.  */
+#define YYBISON 1
+
+/* Bison version.  */
+#define YYBISON_VERSION "2.5"
+
+/* Skeleton name.  */
+#define YYSKELETON_NAME "yacc.c"
+
+/* Pure parsers.  */
+#define YYPURE 0
+
+/* Push parsers.  */
+#define YYPUSH 0
+
+/* Pull parsers.  */
+#define YYPULL 1
+
+/* Using locations.  */
+#define YYLSP_NEEDED 0
+
+/* Substitute the variable and function names.  */
+#define yyparse         sensors_yyparse
+#define yylex           sensors_yylex
+#define yyerror         sensors_yyerror
+#define yylval          sensors_yylval
+#define yychar          sensors_yychar
+#define yydebug         sensors_yydebug
+#define yynerrs         sensors_yynerrs
+
+
+/* Copy the first part of user declarations.  */
+
+/* Line 268 of yacc.c  */
+#line 1 "lib/conf-parse.y"
+
+/*
+    conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+                                      &sensors_config_busses,\
+                                      &sensors_config_busses_count,\
+                                      &sensors_config_busses_max,\
+                                      sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+                                        &current_chip->labels,\
+                                        &current_chip->labels_count,\
+                                        &current_chip->labels_max,\
+                                        sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+                                      &current_chip->sets,\
+                                      &current_chip->sets_count,\
+                                      &current_chip->sets_max,\
+                                      sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->computes,\
+                                          &current_chip->computes_count,\
+                                          &current_chip->computes_max,\
+                                          sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->ignores,\
+                                          &current_chip->ignores_count,\
+                                          &current_chip->ignores_max,\
+                                          sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+                                       &sensors_config_chips,\
+                                       &sensors_config_chips_count,\
+                                       &sensors_config_chips_max,\
+                                       sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+                                                  &(list).fits,\
+                                                  &(list).fits_count,\
+                                                  &(list).fits_max, \
+		                                  sizeof(sensors_chip_name));
+
+
+
+/* Line 268 of yacc.c  */
+#line 158 "lib/conf-parse.c"
+
+/* Enabling traces.  */
+#ifndef YYDEBUG
+# define YYDEBUG 0
+#endif
+
+/* Enabling verbose error messages.  */
+#ifdef YYERROR_VERBOSE
+# undef YYERROR_VERBOSE
+# define YYERROR_VERBOSE 1
+#else
+# define YYERROR_VERBOSE 0
+#endif
+
+/* Enabling the token table.  */
+#ifndef YYTOKEN_TABLE
+# define YYTOKEN_TABLE 0
+#endif
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NEG = 258,
+     EOL = 259,
+     BUS = 260,
+     LABEL = 261,
+     SET = 262,
+     CHIP = 263,
+     COMPUTE = 264,
+     IGNORE = 265,
+     FLOAT = 266,
+     NAME = 267,
+     ERROR = 268
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 293 of yacc.c  */
+#line 79 "lib/conf-parse.y"
+
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+
+
+
+/* Line 293 of yacc.c  */
+#line 220 "lib/conf-parse.c"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+
+/* Copy the second part of user declarations.  */
+
+
+/* Line 343 of yacc.c  */
+#line 232 "lib/conf-parse.c"
+
+#ifdef short
+# undef short
+#endif
+
+#ifdef YYTYPE_UINT8
+typedef YYTYPE_UINT8 yytype_uint8;
+#else
+typedef unsigned char yytype_uint8;
+#endif
+
+#ifdef YYTYPE_INT8
+typedef YYTYPE_INT8 yytype_int8;
+#elif (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+typedef signed char yytype_int8;
+#else
+typedef short int yytype_int8;
+#endif
+
+#ifdef YYTYPE_UINT16
+typedef YYTYPE_UINT16 yytype_uint16;
+#else
+typedef unsigned short int yytype_uint16;
+#endif
+
+#ifdef YYTYPE_INT16
+typedef YYTYPE_INT16 yytype_int16;
+#else
+typedef short int yytype_int16;
+#endif
+
+#ifndef YYSIZE_T
+# ifdef __SIZE_TYPE__
+#  define YYSIZE_T __SIZE_TYPE__
+# elif defined size_t
+#  define YYSIZE_T size_t
+# elif ! defined YYSIZE_T && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#  include <stddef.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYSIZE_T size_t
+# else
+#  define YYSIZE_T unsigned int
+# endif
+#endif
+
+#define YYSIZE_MAXIMUM ((YYSIZE_T) -1)
+
+#ifndef YY_
+# if defined YYENABLE_NLS && YYENABLE_NLS
+#  if ENABLE_NLS
+#   include <libintl.h> /* INFRINGES ON USER NAME SPACE */
+#   define YY_(msgid) dgettext ("bison-runtime", msgid)
+#  endif
+# endif
+# ifndef YY_
+#  define YY_(msgid) msgid
+# endif
+#endif
+
+/* Suppress unused-variable warnings by "using" E.  */
+#if ! defined lint || defined __GNUC__
+# define YYUSE(e) ((void) (e))
+#else
+# define YYUSE(e) /* empty */
+#endif
+
+/* Identity function, used to suppress warnings about constant conditions.  */
+#ifndef lint
+# define YYID(n) (n)
+#else
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static int
+YYID (int yyi)
+#else
+static int
+YYID (yyi)
+    int yyi;
+#endif
+{
+  return yyi;
+}
+#endif
+
+#if ! defined yyoverflow || YYERROR_VERBOSE
+
+/* The parser invokes alloca or malloc; define the necessary symbols.  */
+
+# ifdef YYSTACK_USE_ALLOCA
+#  if YYSTACK_USE_ALLOCA
+#   ifdef __GNUC__
+#    define YYSTACK_ALLOC __builtin_alloca
+#   elif defined __BUILTIN_VA_ARG_INCR
+#    include <alloca.h> /* INFRINGES ON USER NAME SPACE */
+#   elif defined _AIX
+#    define YYSTACK_ALLOC __alloca
+#   elif defined _MSC_VER
+#    include <malloc.h> /* INFRINGES ON USER NAME SPACE */
+#    define alloca _alloca
+#   else
+#    define YYSTACK_ALLOC alloca
+#    if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+#     include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#     ifndef EXIT_SUCCESS
+#      define EXIT_SUCCESS 0
+#     endif
+#    endif
+#   endif
+#  endif
+# endif
+
+# ifdef YYSTACK_ALLOC
+   /* Pacify GCC's `empty if-body' warning.  */
+#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (YYID (0))
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+    /* The OS might guarantee only one guard page at the bottom of the stack,
+       and a page size can be as small as 4096 bytes.  So we cannot safely
+       invoke alloca (N) if N exceeds 4096.  Use a slightly smaller number
+       to allow for a few compiler-allocated temporary stack slots.  */
+#   define YYSTACK_ALLOC_MAXIMUM 4032 /* reasonable circa 2006 */
+#  endif
+# else
+#  define YYSTACK_ALLOC YYMALLOC
+#  define YYSTACK_FREE YYFREE
+#  ifndef YYSTACK_ALLOC_MAXIMUM
+#   define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM
+#  endif
+#  if (defined __cplusplus && ! defined EXIT_SUCCESS \
+       && ! ((defined YYMALLOC || defined malloc) \
+	     && (defined YYFREE || defined free)))
+#   include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#   ifndef EXIT_SUCCESS
+#    define EXIT_SUCCESS 0
+#   endif
+#  endif
+#  ifndef YYMALLOC
+#   define YYMALLOC malloc
+#   if ! defined malloc && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+#  ifndef YYFREE
+#   define YYFREE free
+#   if ! defined free && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+void free (void *); /* INFRINGES ON USER NAME SPACE */
+#   endif
+#  endif
+# endif
+#endif /* ! defined yyoverflow || YYERROR_VERBOSE */
+
+
+#if (! defined yyoverflow \
+     && (! defined __cplusplus \
+	 || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
+
+/* A type that is properly aligned for any stack member.  */
+union yyalloc
+{
+  yytype_int16 yyss_alloc;
+  YYSTYPE yyvs_alloc;
+};
+
+/* The size of the maximum gap between one aligned stack and the next.  */
+# define YYSTACK_GAP_MAXIMUM (sizeof (union yyalloc) - 1)
+
+/* The size of an array large to enough to hold all stacks, each with
+   N elements.  */
+# define YYSTACK_BYTES(N) \
+     ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
+      + YYSTACK_GAP_MAXIMUM)
+
+# define YYCOPY_NEEDED 1
+
+/* Relocate STACK from its old location to the new one.  The
+   local variables YYSIZE and YYSTACKSIZE give the old and new number of
+   elements in the stack, and YYPTR gives the new location of the
+   stack.  Advance YYPTR to a properly aligned location for the next
+   stack.  */
+# define YYSTACK_RELOCATE(Stack_alloc, Stack)				\
+    do									\
+      {									\
+	YYSIZE_T yynewbytes;						\
+	YYCOPY (&yyptr->Stack_alloc, Stack, yysize);			\
+	Stack = &yyptr->Stack_alloc;					\
+	yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+	yyptr += yynewbytes / sizeof (*yyptr);				\
+      }									\
+    while (YYID (0))
+
+#endif
+
+#if defined YYCOPY_NEEDED && YYCOPY_NEEDED
+/* Copy COUNT objects from FROM to TO.  The source and destination do
+   not overlap.  */
+# ifndef YYCOPY
+#  if defined __GNUC__ && 1 < __GNUC__
+#   define YYCOPY(To, From, Count) \
+      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#  else
+#   define YYCOPY(To, From, Count)		\
+      do					\
+	{					\
+	  YYSIZE_T yyi;				\
+	  for (yyi = 0; yyi < (Count); yyi++)	\
+	    (To)[yyi] = (From)[yyi];		\
+	}					\
+      while (YYID (0))
+#  endif
+# endif
+#endif /* !YYCOPY_NEEDED */
+
+/* YYFINAL -- State number of the termination state.  */
+#define YYFINAL  2
+/* YYLAST -- Last index in YYTABLE.  */
+#define YYLAST   58
+
+/* YYNTOKENS -- Number of terminals.  */
+#define YYNTOKENS  24
+/* YYNNTS -- Number of nonterminals.  */
+#define YYNNTS  16
+/* YYNRULES -- Number of rules.  */
+#define YYNRULES  34
+/* YYNRULES -- Number of states.  */
+#define YYNSTATES  63
+
+/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
+#define YYUNDEFTOK  2
+#define YYMAXUTOK   268
+
+#define YYTRANSLATE(YYX)						\
+  ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
+
+/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX.  */
+static const yytype_uint8 yytranslate[] =
+{
+       0,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+      22,    23,     5,     4,    10,     3,     2,     6,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,    21,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     8,     2,     9,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     1,     2,     7,    11,
+      12,    13,    14,    15,    16,    17,    18,    19,    20
+};
+
+#if YYDEBUG
+/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
+   YYRHS.  */
+static const yytype_uint8 yyprhs[] =
+{
+       0,     0,     3,     4,     7,    10,    13,    16,    19,    22,
+      25,    28,    32,    36,    40,    46,    49,    52,    54,    57,
+      59,    61,    63,    67,    71,    75,    79,    82,    86,    89,
+      92,    94,    96,    98,   100
+};
+
+/* YYRHS -- A `-1'-separated list of the rules' RHS.  */
+static const yytype_int8 yyrhs[] =
+{
+      25,     0,    -1,    -1,    25,    26,    -1,    27,    11,    -1,
+      28,    11,    -1,    29,    11,    -1,    32,    11,    -1,    30,
+      11,    -1,    31,    11,    -1,     1,    11,    -1,    12,    35,
+      36,    -1,    13,    37,    38,    -1,    14,    37,    34,    -1,
+      16,    37,    34,    10,    34,    -1,    17,    37,    -1,    15,
+      33,    -1,    39,    -1,    33,    39,    -1,    18,    -1,    19,
+      -1,    21,    -1,    34,     4,    34,    -1,    34,     3,    34,
+      -1,    34,     5,    34,    -1,    34,     6,    34,    -1,     3,
+      34,    -1,    22,    34,    23,    -1,     8,    34,    -1,     9,
+      34,    -1,    19,    -1,    19,    -1,    19,    -1,    19,    -1,
+      19,    -1
+};
+
+/* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
+static const yytype_uint16 yyrline[] =
+{
+       0,   119,   119,   120,   123,   124,   125,   126,   127,   128,
+     129,   132,   141,   156,   171,   188,   201,   219,   225,   231,
+     236,   241,   245,   252,   259,   266,   273,   280,   282,   289,
+     298,   308,   312,   316,   320
+};
+#endif
+
+#if YYDEBUG || YYERROR_VERBOSE || YYTOKEN_TABLE
+/* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+   First, the terminals, then, starting at YYNTOKENS, nonterminals.  */
+static const char *const yytname[] =
+{
+  "$end", "error", "$undefined", "'-'", "'+'", "'*'", "'/'", "NEG", "'^'",
+  "'`'", "','", "EOL", "BUS", "LABEL", "SET", "CHIP", "COMPUTE", "IGNORE",
+  "FLOAT", "NAME", "ERROR", "'@'", "'('", "')'", "$accept", "input",
+  "line", "bus_statement", "label_statement", "set_statement",
+  "compute_statement", "ignore_statement", "chip_statement",
+  "chip_name_list", "expression", "bus_id", "adapter_name",
+  "function_name", "string", "chip_name", 0
+};
+#endif
+
+# ifdef YYPRINT
+/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
+   token YYLEX-NUM.  */
+static const yytype_uint16 yytoknum[] =
+{
+       0,   256,   257,    45,    43,    42,    47,   258,    94,    96,
+      44,   259,   260,   261,   262,   263,   264,   265,   266,   267,
+     268,    64,    40,    41
+};
+# endif
+
+/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
+static const yytype_uint8 yyr1[] =
+{
+       0,    24,    25,    25,    26,    26,    26,    26,    26,    26,
+      26,    27,    28,    29,    30,    31,    32,    33,    33,    34,
+      34,    34,    34,    34,    34,    34,    34,    34,    34,    34,
+      35,    36,    37,    38,    39
+};
+
+/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
+static const yytype_uint8 yyr2[] =
+{
+       0,     2,     0,     2,     2,     2,     2,     2,     2,     2,
+       2,     3,     3,     3,     5,     2,     2,     1,     2,     1,
+       1,     1,     3,     3,     3,     3,     2,     3,     2,     2,
+       1,     1,     1,     1,     1
+};
+
+/* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
+   Performed when YYTABLE doesn't specify something else to do.  Zero
+   means the default is an error.  */
+static const yytype_uint8 yydefact[] =
+{
+       2,     0,     1,     0,     0,     0,     0,     0,     0,     0,
+       3,     0,     0,     0,     0,     0,     0,    10,    30,     0,
+      32,     0,     0,    34,    16,    17,     0,    15,     4,     5,
+       6,     8,     9,     7,    31,    11,    33,    12,     0,     0,
+       0,    19,    20,    21,     0,    13,    18,     0,    26,    28,
+      29,     0,     0,     0,     0,     0,     0,    27,    23,    22,
+      24,    25,    14
+};
+
+/* YYDEFGOTO[NTERM-NUM].  */
+static const yytype_int8 yydefgoto[] =
+{
+      -1,     1,    10,    11,    12,    13,    14,    15,    16,    24,
+      45,    19,    35,    21,    37,    25
+};
+
+/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+   STATE-NUM.  */
+#define YYPACT_NINF -27
+static const yytype_int8 yypact[] =
+{
+     -27,    37,   -27,    -4,    -3,     1,     1,     6,     1,     1,
+     -27,     8,    13,    20,    23,    32,    34,   -27,   -27,    29,
+     -27,    39,    14,   -27,     6,   -27,    14,   -27,   -27,   -27,
+     -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,    14,    14,
+      14,   -27,   -27,   -27,    14,    36,   -27,     5,   -27,   -27,
+     -27,    -2,    14,    14,    14,    14,    14,   -27,     0,     0,
+     -27,   -27,    36
+};
+
+/* YYPGOTO[NTERM-NUM].  */
+static const yytype_int8 yypgoto[] =
+{
+     -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,   -27,
+     -26,   -27,   -27,    38,   -27,    31
+};
+
+/* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
+   positive, shift that token.  If negative, reduce the rule which
+   number is the opposite.  If YYTABLE_NINF, syntax error.  */
+#define YYTABLE_NINF -1
+static const yytype_uint8 yytable[] =
+{
+      47,    52,    53,    54,    55,    54,    55,    17,    52,    53,
+      54,    55,    48,    49,    50,    56,    18,    38,    51,    28,
+      20,    57,    39,    40,    29,    23,    58,    59,    60,    61,
+      62,    30,    41,    42,    31,    43,    44,     2,     3,    52,
+      53,    54,    55,    32,    22,    33,    26,    27,    34,     4,
+       5,     6,     7,     8,     9,    46,     0,     0,    36
+};
+
+#define yypact_value_is_default(yystate) \
+  ((yystate) == (-27))
+
+#define yytable_value_is_error(yytable_value) \
+  YYID (0)
+
+static const yytype_int8 yycheck[] =
+{
+      26,     3,     4,     5,     6,     5,     6,    11,     3,     4,
+       5,     6,    38,    39,    40,    10,    19,     3,    44,    11,
+      19,    23,     8,     9,    11,    19,    52,    53,    54,    55,
+      56,    11,    18,    19,    11,    21,    22,     0,     1,     3,
+       4,     5,     6,    11,     6,    11,     8,     9,    19,    12,
+      13,    14,    15,    16,    17,    24,    -1,    -1,    19
+};
+
+/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+   symbol of state STATE-NUM.  */
+static const yytype_uint8 yystos[] =
+{
+       0,    25,     0,     1,    12,    13,    14,    15,    16,    17,
+      26,    27,    28,    29,    30,    31,    32,    11,    19,    35,
+      19,    37,    37,    19,    33,    39,    37,    37,    11,    11,
+      11,    11,    11,    11,    19,    36,    19,    38,     3,     8,
+       9,    18,    19,    21,    22,    34,    39,    34,    34,    34,
+      34,    34,     3,     4,     5,     6,    10,    23,    34,    34,
+      34,    34,    34
+};
+
+#define yyerrok		(yyerrstatus = 0)
+#define yyclearin	(yychar = YYEMPTY)
+#define YYEMPTY		(-2)
+#define YYEOF		0
+
+#define YYACCEPT	goto yyacceptlab
+#define YYABORT		goto yyabortlab
+#define YYERROR		goto yyerrorlab
+
+
+/* Like YYERROR except do call yyerror.  This remains here temporarily
+   to ease the transition to the new meaning of YYERROR, for GCC.
+   Once GCC version 2 has supplanted version 1, this can go.  However,
+   YYFAIL appears to be in use.  Nevertheless, it is formally deprecated
+   in Bison 2.4.2's NEWS entry, where a plan to phase it out is
+   discussed.  */
+
+#define YYFAIL		goto yyerrlab
+#if defined YYFAIL
+  /* This is here to suppress warnings from the GCC cpp's
+     -Wunused-macros.  Normally we don't worry about that warning, but
+     some users do, and we want to make it easy for users to remove
+     YYFAIL uses, which will produce warnings from Bison 2.5.  */
+#endif
+
+#define YYRECOVERING()  (!!yyerrstatus)
+
+#define YYBACKUP(Token, Value)					\
+do								\
+  if (yychar == YYEMPTY && yylen == 1)				\
+    {								\
+      yychar = (Token);						\
+      yylval = (Value);						\
+      YYPOPSTACK (1);						\
+      goto yybackup;						\
+    }								\
+  else								\
+    {								\
+      yyerror (YY_("syntax error: cannot back up")); \
+      YYERROR;							\
+    }								\
+while (YYID (0))
+
+
+#define YYTERROR	1
+#define YYERRCODE	256
+
+
+/* YYLLOC_DEFAULT -- Set CURRENT to span from RHS[1] to RHS[N].
+   If N is 0, then set CURRENT to the empty location which ends
+   the previous symbol: RHS[0] (always defined).  */
+
+#define YYRHSLOC(Rhs, K) ((Rhs)[K])
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N)				\
+    do									\
+      if (YYID (N))                                                    \
+	{								\
+	  (Current).first_line   = YYRHSLOC (Rhs, 1).first_line;	\
+	  (Current).first_column = YYRHSLOC (Rhs, 1).first_column;	\
+	  (Current).last_line    = YYRHSLOC (Rhs, N).last_line;		\
+	  (Current).last_column  = YYRHSLOC (Rhs, N).last_column;	\
+	}								\
+      else								\
+	{								\
+	  (Current).first_line   = (Current).last_line   =		\
+	    YYRHSLOC (Rhs, 0).last_line;				\
+	  (Current).first_column = (Current).last_column =		\
+	    YYRHSLOC (Rhs, 0).last_column;				\
+	}								\
+    while (YYID (0))
+#endif
+
+
+/* This macro is provided for backward compatibility. */
+
+#ifndef YY_LOCATION_PRINT
+# define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+#endif
+
+
+/* YYLEX -- calling `yylex' with the right arguments.  */
+
+#ifdef YYLEX_PARAM
+# define YYLEX yylex (YYLEX_PARAM)
+#else
+# define YYLEX yylex ()
+#endif
+
+/* Enable debugging if requested.  */
+#if YYDEBUG
+
+# ifndef YYFPRINTF
+#  include <stdio.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYFPRINTF fprintf
+# endif
+
+# define YYDPRINTF(Args)			\
+do {						\
+  if (yydebug)					\
+    YYFPRINTF Args;				\
+} while (YYID (0))
+
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)			  \
+do {									  \
+  if (yydebug)								  \
+    {									  \
+      YYFPRINTF (stderr, "%s ", Title);					  \
+      yy_symbol_print (stderr,						  \
+		  Type, Value); \
+      YYFPRINTF (stderr, "\n");						  \
+    }									  \
+} while (YYID (0))
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_value_print (yyoutput, yytype, yyvaluep)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+#endif
+{
+  if (!yyvaluep)
+    return;
+# ifdef YYPRINT
+  if (yytype < YYNTOKENS)
+    YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
+# else
+  YYUSE (yyoutput);
+# endif
+  switch (yytype)
+    {
+      default:
+	break;
+    }
+}
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_print (yyoutput, yytype, yyvaluep)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE const * const yyvaluep;
+#endif
+{
+  if (yytype < YYNTOKENS)
+    YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
+  else
+    YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+
+  yy_symbol_value_print (yyoutput, yytype, yyvaluep);
+  YYFPRINTF (yyoutput, ")");
+}
+
+/*------------------------------------------------------------------.
+| yy_stack_print -- Print the state stack from its BOTTOM up to its |
+| TOP (included).                                                   |
+`------------------------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_stack_print (yytype_int16 *yybottom, yytype_int16 *yytop)
+#else
+static void
+yy_stack_print (yybottom, yytop)
+    yytype_int16 *yybottom;
+    yytype_int16 *yytop;
+#endif
+{
+  YYFPRINTF (stderr, "Stack now");
+  for (; yybottom <= yytop; yybottom++)
+    {
+      int yybot = *yybottom;
+      YYFPRINTF (stderr, " %d", yybot);
+    }
+  YYFPRINTF (stderr, "\n");
+}
+
+# define YY_STACK_PRINT(Bottom, Top)				\
+do {								\
+  if (yydebug)							\
+    yy_stack_print ((Bottom), (Top));				\
+} while (YYID (0))
+
+
+/*------------------------------------------------.
+| Report that the YYRULE is going to be reduced.  |
+`------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yy_reduce_print (YYSTYPE *yyvsp, int yyrule)
+#else
+static void
+yy_reduce_print (yyvsp, yyrule)
+    YYSTYPE *yyvsp;
+    int yyrule;
+#endif
+{
+  int yynrhs = yyr2[yyrule];
+  int yyi;
+  unsigned long int yylno = yyrline[yyrule];
+  YYFPRINTF (stderr, "Reducing stack by rule %d (line %lu):\n",
+	     yyrule - 1, yylno);
+  /* The symbols being reduced.  */
+  for (yyi = 0; yyi < yynrhs; yyi++)
+    {
+      YYFPRINTF (stderr, "   $%d = ", yyi + 1);
+      yy_symbol_print (stderr, yyrhs[yyprhs[yyrule] + yyi],
+		       &(yyvsp[(yyi + 1) - (yynrhs)])
+		       		       );
+      YYFPRINTF (stderr, "\n");
+    }
+}
+
+# define YY_REDUCE_PRINT(Rule)		\
+do {					\
+  if (yydebug)				\
+    yy_reduce_print (yyvsp, Rule); \
+} while (YYID (0))
+
+/* Nonzero means print parse trace.  It is left uninitialized so that
+   multiple parsers can coexist.  */
+int yydebug;
+#else /* !YYDEBUG */
+# define YYDPRINTF(Args)
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)
+# define YY_STACK_PRINT(Bottom, Top)
+# define YY_REDUCE_PRINT(Rule)
+#endif /* !YYDEBUG */
+
+
+/* YYINITDEPTH -- initial size of the parser's stacks.  */
+#ifndef	YYINITDEPTH
+# define YYINITDEPTH 200
+#endif
+
+/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only
+   if the built-in stack extension method is used).
+
+   Do not make this value too large; the results are undefined if
+   YYSTACK_ALLOC_MAXIMUM < YYSTACK_BYTES (YYMAXDEPTH)
+   evaluated with infinite-precision integer arithmetic.  */
+
+#ifndef YYMAXDEPTH
+# define YYMAXDEPTH 10000
+#endif
+
+
+#if YYERROR_VERBOSE
+
+# ifndef yystrlen
+#  if defined __GLIBC__ && defined _STRING_H
+#   define yystrlen strlen
+#  else
+/* Return the length of YYSTR.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static YYSIZE_T
+yystrlen (const char *yystr)
+#else
+static YYSIZE_T
+yystrlen (yystr)
+    const char *yystr;
+#endif
+{
+  YYSIZE_T yylen;
+  for (yylen = 0; yystr[yylen]; yylen++)
+    continue;
+  return yylen;
+}
+#  endif
+# endif
+
+# ifndef yystpcpy
+#  if defined __GLIBC__ && defined _STRING_H && defined _GNU_SOURCE
+#   define yystpcpy stpcpy
+#  else
+/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
+   YYDEST.  */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static char *
+yystpcpy (char *yydest, const char *yysrc)
+#else
+static char *
+yystpcpy (yydest, yysrc)
+    char *yydest;
+    const char *yysrc;
+#endif
+{
+  char *yyd = yydest;
+  const char *yys = yysrc;
+
+  while ((*yyd++ = *yys++) != '\0')
+    continue;
+
+  return yyd - 1;
+}
+#  endif
+# endif
+
+# ifndef yytnamerr
+/* Copy to YYRES the contents of YYSTR after stripping away unnecessary
+   quotes and backslashes, so that it's suitable for yyerror.  The
+   heuristic is that double-quoting is unnecessary unless the string
+   contains an apostrophe, a comma, or backslash (other than
+   backslash-backslash).  YYSTR is taken from yytname.  If YYRES is
+   null, do not copy; instead, return the length of what the result
+   would have been.  */
+static YYSIZE_T
+yytnamerr (char *yyres, const char *yystr)
+{
+  if (*yystr == '"')
+    {
+      YYSIZE_T yyn = 0;
+      char const *yyp = yystr;
+
+      for (;;)
+	switch (*++yyp)
+	  {
+	  case '\'':
+	  case ',':
+	    goto do_not_strip_quotes;
+
+	  case '\\':
+	    if (*++yyp != '\\')
+	      goto do_not_strip_quotes;
+	    /* Fall through.  */
+	  default:
+	    if (yyres)
+	      yyres[yyn] = *yyp;
+	    yyn++;
+	    break;
+
+	  case '"':
+	    if (yyres)
+	      yyres[yyn] = '\0';
+	    return yyn;
+	  }
+    do_not_strip_quotes: ;
+    }
+
+  if (! yyres)
+    return yystrlen (yystr);
+
+  return yystpcpy (yyres, yystr) - yyres;
+}
+# endif
+
+/* Copy into *YYMSG, which is of size *YYMSG_ALLOC, an error message
+   about the unexpected token YYTOKEN for the state stack whose top is
+   YYSSP.
+
+   Return 0 if *YYMSG was successfully written.  Return 1 if *YYMSG is
+   not large enough to hold the message.  In that case, also set
+   *YYMSG_ALLOC to the required number of bytes.  Return 2 if the
+   required number of bytes is too large to store.  */
+static int
+yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
+                yytype_int16 *yyssp, int yytoken)
+{
+  YYSIZE_T yysize0 = yytnamerr (0, yytname[yytoken]);
+  YYSIZE_T yysize = yysize0;
+  YYSIZE_T yysize1;
+  enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
+  /* Internationalized format string. */
+  const char *yyformat = 0;
+  /* Arguments of yyformat. */
+  char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
+  /* Number of reported tokens (one for the "unexpected", one per
+     "expected"). */
+  int yycount = 0;
+
+  /* There are many possibilities here to consider:
+     - Assume YYFAIL is not used.  It's too flawed to consider.  See
+       <http://lists.gnu.org/archive/html/bison-patches/2009-12/msg00024.html>
+       for details.  YYERROR is fine as it does not invoke this
+       function.
+     - If this state is a consistent state with a default action, then
+       the only way this function was invoked is if the default action
+       is an error action.  In that case, don't check for expected
+       tokens because there are none.
+     - The only way there can be no lookahead present (in yychar) is if
+       this state is a consistent state with a default action.  Thus,
+       detecting the absence of a lookahead is sufficient to determine
+       that there is no unexpected or expected token to report.  In that
+       case, just report a simple "syntax error".
+     - Don't assume there isn't a lookahead just because this state is a
+       consistent state with a default action.  There might have been a
+       previous inconsistent state, consistent state with a non-default
+       action, or user semantic action that manipulated yychar.
+     - Of course, the expected token list depends on states to have
+       correct lookahead information, and it depends on the parser not
+       to perform extra reductions after fetching a lookahead from the
+       scanner and before detecting a syntax error.  Thus, state merging
+       (from LALR or IELR) and default reductions corrupt the expected
+       token list.  However, the list is correct for canonical LR with
+       one exception: it will still contain any token that will not be
+       accepted due to an error action in a later state.
+  */
+  if (yytoken != YYEMPTY)
+    {
+      int yyn = yypact[*yyssp];
+      yyarg[yycount++] = yytname[yytoken];
+      if (!yypact_value_is_default (yyn))
+        {
+          /* Start YYX at -YYN if negative to avoid negative indexes in
+             YYCHECK.  In other words, skip the first -YYN actions for
+             this state because they are default actions.  */
+          int yyxbegin = yyn < 0 ? -yyn : 0;
+          /* Stay within bounds of both yycheck and yytname.  */
+          int yychecklim = YYLAST - yyn + 1;
+          int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+          int yyx;
+
+          for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+            if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR
+                && !yytable_value_is_error (yytable[yyx + yyn]))
+              {
+                if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
+                  {
+                    yycount = 1;
+                    yysize = yysize0;
+                    break;
+                  }
+                yyarg[yycount++] = yytname[yyx];
+                yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+                if (! (yysize <= yysize1
+                       && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+                  return 2;
+                yysize = yysize1;
+              }
+        }
+    }
+
+  switch (yycount)
+    {
+# define YYCASE_(N, S)                      \
+      case N:                               \
+        yyformat = S;                       \
+      break
+      YYCASE_(0, YY_("syntax error"));
+      YYCASE_(1, YY_("syntax error, unexpected %s"));
+      YYCASE_(2, YY_("syntax error, unexpected %s, expecting %s"));
+      YYCASE_(3, YY_("syntax error, unexpected %s, expecting %s or %s"));
+      YYCASE_(4, YY_("syntax error, unexpected %s, expecting %s or %s or %s"));
+      YYCASE_(5, YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s"));
+# undef YYCASE_
+    }
+
+  yysize1 = yysize + yystrlen (yyformat);
+  if (! (yysize <= yysize1 && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+    return 2;
+  yysize = yysize1;
+
+  if (*yymsg_alloc < yysize)
+    {
+      *yymsg_alloc = 2 * yysize;
+      if (! (yysize <= *yymsg_alloc
+             && *yymsg_alloc <= YYSTACK_ALLOC_MAXIMUM))
+        *yymsg_alloc = YYSTACK_ALLOC_MAXIMUM;
+      return 1;
+    }
+
+  /* Avoid sprintf, as that infringes on the user's name space.
+     Don't have undefined behavior even if the translation
+     produced a string with the wrong number of "%s"s.  */
+  {
+    char *yyp = *yymsg;
+    int yyi = 0;
+    while ((*yyp = *yyformat) != '\0')
+      if (*yyp == '%' && yyformat[1] == 's' && yyi < yycount)
+        {
+          yyp += yytnamerr (yyp, yyarg[yyi++]);
+          yyformat += 2;
+        }
+      else
+        {
+          yyp++;
+          yyformat++;
+        }
+  }
+  return 0;
+}
+#endif /* YYERROR_VERBOSE */
+
+/*-----------------------------------------------.
+| Release the memory associated to this symbol.  |
+`-----------------------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+static void
+yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep)
+#else
+static void
+yydestruct (yymsg, yytype, yyvaluep)
+    const char *yymsg;
+    int yytype;
+    YYSTYPE *yyvaluep;
+#endif
+{
+  YYUSE (yyvaluep);
+
+  if (!yymsg)
+    yymsg = "Deleting";
+  YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp);
+
+  switch (yytype)
+    {
+
+      default:
+	break;
+    }
+}
+
+
+/* Prevent warnings from -Wmissing-prototypes.  */
+#ifdef YYPARSE_PARAM
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void *YYPARSE_PARAM);
+#else
+int yyparse ();
+#endif
+#else /* ! YYPARSE_PARAM */
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void);
+#else
+int yyparse ();
+#endif
+#endif /* ! YYPARSE_PARAM */
+
+
+/* The lookahead symbol.  */
+int yychar;
+
+/* The semantic value of the lookahead symbol.  */
+YYSTYPE yylval;
+
+/* Number of syntax errors so far.  */
+int yynerrs;
+
+
+/*----------.
+| yyparse.  |
+`----------*/
+
+#ifdef YYPARSE_PARAM
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void *YYPARSE_PARAM)
+#else
+int
+yyparse (YYPARSE_PARAM)
+    void *YYPARSE_PARAM;
+#endif
+#else /* ! YYPARSE_PARAM */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+     || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void)
+#else
+int
+yyparse ()
+
+#endif
+#endif
+{
+    int yystate;
+    /* Number of tokens to shift before error messages enabled.  */
+    int yyerrstatus;
+
+    /* The stacks and their tools:
+       `yyss': related to states.
+       `yyvs': related to semantic values.
+
+       Refer to the stacks thru separate pointers, to allow yyoverflow
+       to reallocate them elsewhere.  */
+
+    /* The state stack.  */
+    yytype_int16 yyssa[YYINITDEPTH];
+    yytype_int16 *yyss;
+    yytype_int16 *yyssp;
+
+    /* The semantic value stack.  */
+    YYSTYPE yyvsa[YYINITDEPTH];
+    YYSTYPE *yyvs;
+    YYSTYPE *yyvsp;
+
+    YYSIZE_T yystacksize;
+
+  int yyn;
+  int yyresult;
+  /* Lookahead token as an internal (translated) token number.  */
+  int yytoken;
+  /* The variables used to return semantic value and location from the
+     action routines.  */
+  YYSTYPE yyval;
+
+#if YYERROR_VERBOSE
+  /* Buffer for error messages, and its allocated size.  */
+  char yymsgbuf[128];
+  char *yymsg = yymsgbuf;
+  YYSIZE_T yymsg_alloc = sizeof yymsgbuf;
+#endif
+
+#define YYPOPSTACK(N)   (yyvsp -= (N), yyssp -= (N))
+
+  /* The number of symbols on the RHS of the reduced rule.
+     Keep to zero when no symbol should be popped.  */
+  int yylen = 0;
+
+  yytoken = 0;
+  yyss = yyssa;
+  yyvs = yyvsa;
+  yystacksize = YYINITDEPTH;
+
+  YYDPRINTF ((stderr, "Starting parse\n"));
+
+  yystate = 0;
+  yyerrstatus = 0;
+  yynerrs = 0;
+  yychar = YYEMPTY; /* Cause a token to be read.  */
+
+  /* Initialize stack pointers.
+     Waste one element of value and location stack
+     so that they stay on the same level as the state stack.
+     The wasted elements are never initialized.  */
+  yyssp = yyss;
+  yyvsp = yyvs;
+
+  goto yysetstate;
+
+/*------------------------------------------------------------.
+| yynewstate -- Push a new state, which is found in yystate.  |
+`------------------------------------------------------------*/
+ yynewstate:
+  /* In all cases, when you get here, the value and location stacks
+     have just been pushed.  So pushing a state here evens the stacks.  */
+  yyssp++;
+
+ yysetstate:
+  *yyssp = yystate;
+
+  if (yyss + yystacksize - 1 <= yyssp)
+    {
+      /* Get the current used size of the three stacks, in elements.  */
+      YYSIZE_T yysize = yyssp - yyss + 1;
+
+#ifdef yyoverflow
+      {
+	/* Give user a chance to reallocate the stack.  Use copies of
+	   these so that the &'s don't force the real ones into
+	   memory.  */
+	YYSTYPE *yyvs1 = yyvs;
+	yytype_int16 *yyss1 = yyss;
+
+	/* Each stack pointer address is followed by the size of the
+	   data in use in that stack, in bytes.  This used to be a
+	   conditional around just the two extra args, but that might
+	   be undefined if yyoverflow is a macro.  */
+	yyoverflow (YY_("memory exhausted"),
+		    &yyss1, yysize * sizeof (*yyssp),
+		    &yyvs1, yysize * sizeof (*yyvsp),
+		    &yystacksize);
+
+	yyss = yyss1;
+	yyvs = yyvs1;
+      }
+#else /* no yyoverflow */
+# ifndef YYSTACK_RELOCATE
+      goto yyexhaustedlab;
+# else
+      /* Extend the stack our own way.  */
+      if (YYMAXDEPTH <= yystacksize)
+	goto yyexhaustedlab;
+      yystacksize *= 2;
+      if (YYMAXDEPTH < yystacksize)
+	yystacksize = YYMAXDEPTH;
+
+      {
+	yytype_int16 *yyss1 = yyss;
+	union yyalloc *yyptr =
+	  (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+	if (! yyptr)
+	  goto yyexhaustedlab;
+	YYSTACK_RELOCATE (yyss_alloc, yyss);
+	YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+#  undef YYSTACK_RELOCATE
+	if (yyss1 != yyssa)
+	  YYSTACK_FREE (yyss1);
+      }
+# endif
+#endif /* no yyoverflow */
+
+      yyssp = yyss + yysize - 1;
+      yyvsp = yyvs + yysize - 1;
+
+      YYDPRINTF ((stderr, "Stack size increased to %lu\n",
+		  (unsigned long int) yystacksize));
+
+      if (yyss + yystacksize - 1 <= yyssp)
+	YYABORT;
+    }
+
+  YYDPRINTF ((stderr, "Entering state %d\n", yystate));
+
+  if (yystate == YYFINAL)
+    YYACCEPT;
+
+  goto yybackup;
+
+/*-----------.
+| yybackup.  |
+`-----------*/
+yybackup:
+
+  /* Do appropriate processing given the current state.  Read a
+     lookahead token if we need one and don't already have one.  */
+
+  /* First try to decide what to do without reference to lookahead token.  */
+  yyn = yypact[yystate];
+  if (yypact_value_is_default (yyn))
+    goto yydefault;
+
+  /* Not known => get a lookahead token if don't already have one.  */
+
+  /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol.  */
+  if (yychar == YYEMPTY)
+    {
+      YYDPRINTF ((stderr, "Reading a token: "));
+      yychar = YYLEX;
+    }
+
+  if (yychar <= YYEOF)
+    {
+      yychar = yytoken = YYEOF;
+      YYDPRINTF ((stderr, "Now at end of input.\n"));
+    }
+  else
+    {
+      yytoken = YYTRANSLATE (yychar);
+      YY_SYMBOL_PRINT ("Next token is", yytoken, &yylval, &yylloc);
+    }
+
+  /* If the proper action on seeing token YYTOKEN is to reduce or to
+     detect an error, take that action.  */
+  yyn += yytoken;
+  if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken)
+    goto yydefault;
+  yyn = yytable[yyn];
+  if (yyn <= 0)
+    {
+      if (yytable_value_is_error (yyn))
+        goto yyerrlab;
+      yyn = -yyn;
+      goto yyreduce;
+    }
+
+  /* Count tokens shifted since error; after three, turn off error
+     status.  */
+  if (yyerrstatus)
+    yyerrstatus--;
+
+  /* Shift the lookahead token.  */
+  YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);
+
+  /* Discard the shifted token.  */
+  yychar = YYEMPTY;
+
+  yystate = yyn;
+  *++yyvsp = yylval;
+
+  goto yynewstate;
+
+
+/*-----------------------------------------------------------.
+| yydefault -- do the default action for the current state.  |
+`-----------------------------------------------------------*/
+yydefault:
+  yyn = yydefact[yystate];
+  if (yyn == 0)
+    goto yyerrlab;
+  goto yyreduce;
+
+
+/*-----------------------------.
+| yyreduce -- Do a reduction.  |
+`-----------------------------*/
+yyreduce:
+  /* yyn is the number of a rule to reduce with.  */
+  yylen = yyr2[yyn];
+
+  /* If YYLEN is nonzero, implement the default value of the action:
+     `$$ = $1'.
+
+     Otherwise, the following line sets YYVAL to garbage.
+     This behavior is undocumented and Bison
+     users should not rely upon it.  Assigning to YYVAL
+     unconditionally makes the parser a bit smaller, and it avoids a
+     GCC warning that YYVAL may be used uninitialized.  */
+  yyval = yyvsp[1-yylen];
+
+
+  YY_REDUCE_PRINT (yyn);
+  switch (yyn)
+    {
+        case 11:
+
+/* Line 1806 of yacc.c  */
+#line 133 "lib/conf-parse.y"
+    { sensors_bus new_el;
+		    new_el.line = (yyvsp[(1) - (3)].line);
+		    new_el.bus = (yyvsp[(2) - (3)].bus);
+                    new_el.adapter = (yyvsp[(3) - (3)].name);
+		    bus_add_el(&new_el);
+		  }
+    break;
+
+  case 12:
+
+/* Line 1806 of yacc.c  */
+#line 142 "lib/conf-parse.y"
+    { sensors_label new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Label statement before first chip statement");
+			      free((yyvsp[(2) - (3)].name));
+			      free((yyvsp[(3) - (3)].name));
+			      YYERROR;
+			    }
+			    new_el.line = (yyvsp[(1) - (3)].line);
+			    new_el.name = (yyvsp[(2) - (3)].name);
+			    new_el.value = (yyvsp[(3) - (3)].name);
+			    label_add_el(&new_el);
+			  }
+    break;
+
+  case 13:
+
+/* Line 1806 of yacc.c  */
+#line 157 "lib/conf-parse.y"
+    { sensors_set new_el;
+		    if (!current_chip) {
+		      sensors_yyerror("Set statement before first chip statement");
+		      free((yyvsp[(2) - (3)].name));
+		      sensors_free_expr((yyvsp[(3) - (3)].expr));
+		      YYERROR;
+		    }
+		    new_el.line = (yyvsp[(1) - (3)].line);
+		    new_el.name = (yyvsp[(2) - (3)].name);
+		    new_el.value = (yyvsp[(3) - (3)].expr);
+		    set_add_el(&new_el);
+		  }
+    break;
+
+  case 14:
+
+/* Line 1806 of yacc.c  */
+#line 172 "lib/conf-parse.y"
+    { sensors_compute new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Compute statement before first chip statement");
+			      free((yyvsp[(2) - (5)].name));
+			      sensors_free_expr((yyvsp[(3) - (5)].expr));
+			      sensors_free_expr((yyvsp[(5) - (5)].expr));
+			      YYERROR;
+			    }
+			    new_el.line = (yyvsp[(1) - (5)].line);
+			    new_el.name = (yyvsp[(2) - (5)].name);
+			    new_el.from_proc = (yyvsp[(3) - (5)].expr);
+			    new_el.to_proc = (yyvsp[(5) - (5)].expr);
+			    compute_add_el(&new_el);
+			  }
+    break;
+
+  case 15:
+
+/* Line 1806 of yacc.c  */
+#line 189 "lib/conf-parse.y"
+    { sensors_ignore new_el;
+			  if (!current_chip) {
+			    sensors_yyerror("Ignore statement before first chip statement");
+			    free((yyvsp[(2) - (2)].name));
+			    YYERROR;
+			  }
+			  new_el.line = (yyvsp[(1) - (2)].line);
+			  new_el.name = (yyvsp[(2) - (2)].name);
+			  ignore_add_el(&new_el);
+			}
+    break;
+
+  case 16:
+
+/* Line 1806 of yacc.c  */
+#line 202 "lib/conf-parse.y"
+    { sensors_chip new_el;
+		    new_el.line = (yyvsp[(1) - (2)].line);
+		    new_el.labels = NULL;
+		    new_el.sets = NULL;
+		    new_el.computes = NULL;
+		    new_el.ignores = NULL;
+		    new_el.labels_count = new_el.labels_max = 0;
+		    new_el.sets_count = new_el.sets_max = 0;
+		    new_el.computes_count = new_el.computes_max = 0;
+		    new_el.ignores_count = new_el.ignores_max = 0;
+		    new_el.chips = (yyvsp[(2) - (2)].chips);
+		    chip_add_el(&new_el);
+		    current_chip = sensors_config_chips + 
+		                   sensors_config_chips_count - 1;
+		  }
+    break;
+
+  case 17:
+
+/* Line 1806 of yacc.c  */
+#line 220 "lib/conf-parse.y"
+    { 
+		    (yyval.chips).fits = NULL;
+		    (yyval.chips).fits_count = (yyval.chips).fits_max = 0;
+		    fits_add_el(&(yyvsp[(1) - (1)].chip),(yyval.chips));
+		  }
+    break;
+
+  case 18:
+
+/* Line 1806 of yacc.c  */
+#line 226 "lib/conf-parse.y"
+    { (yyval.chips) = (yyvsp[(1) - (2)].chips);
+		    fits_add_el(&(yyvsp[(2) - (2)].chip),(yyval.chips));
+		  }
+    break;
+
+  case 19:
+
+/* Line 1806 of yacc.c  */
+#line 232 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->data.val = (yyvsp[(1) - (1)].value); 
+		    (yyval.expr)->kind = sensors_kind_val;
+		  }
+    break;
+
+  case 20:
+
+/* Line 1806 of yacc.c  */
+#line 237 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->data.var = (yyvsp[(1) - (1)].name);
+		    (yyval.expr)->kind = sensors_kind_var;
+		  }
+    break;
+
+  case 21:
+
+/* Line 1806 of yacc.c  */
+#line 242 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr();
+		    (yyval.expr)->kind = sensors_kind_source;
+		  }
+    break;
+
+  case 22:
+
+/* Line 1806 of yacc.c  */
+#line 246 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_add;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 23:
+
+/* Line 1806 of yacc.c  */
+#line 253 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_sub;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 24:
+
+/* Line 1806 of yacc.c  */
+#line 260 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_multiply;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 25:
+
+/* Line 1806 of yacc.c  */
+#line 267 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_divide;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+		  }
+    break;
+
+  case 26:
+
+/* Line 1806 of yacc.c  */
+#line 274 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_negate;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 27:
+
+/* Line 1806 of yacc.c  */
+#line 281 "lib/conf-parse.y"
+    { (yyval.expr) = (yyvsp[(2) - (3)].expr); }
+    break;
+
+  case 28:
+
+/* Line 1806 of yacc.c  */
+#line 283 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_exp;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 29:
+
+/* Line 1806 of yacc.c  */
+#line 290 "lib/conf-parse.y"
+    { (yyval.expr) = malloc_expr(); 
+		    (yyval.expr)->kind = sensors_kind_sub;
+		    (yyval.expr)->data.subexpr.op = sensors_log;
+		    (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+		    (yyval.expr)->data.subexpr.sub2 = NULL;
+		  }
+    break;
+
+  case 30:
+
+/* Line 1806 of yacc.c  */
+#line 299 "lib/conf-parse.y"
+    { int res = sensors_parse_bus_id((yyvsp[(1) - (1)].name),&(yyval.bus));
+		    free((yyvsp[(1) - (1)].name));
+		    if (res) {
+                      sensors_yyerror("Parse error in bus id");
+		      YYERROR;
+                    }
+		  }
+    break;
+
+  case 31:
+
+/* Line 1806 of yacc.c  */
+#line 309 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 32:
+
+/* Line 1806 of yacc.c  */
+#line 313 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 33:
+
+/* Line 1806 of yacc.c  */
+#line 317 "lib/conf-parse.y"
+    { (yyval.name) = (yyvsp[(1) - (1)].name); }
+    break;
+
+  case 34:
+
+/* Line 1806 of yacc.c  */
+#line 321 "lib/conf-parse.y"
+    { int res = sensors_parse_chip_name((yyvsp[(1) - (1)].name),&(yyval.chip)); 
+		    free((yyvsp[(1) - (1)].name));
+		    if (res) {
+		      sensors_yyerror("Parse error in chip name");
+		      YYERROR;
+		    }
+		  }
+    break;
+
+
+
+/* Line 1806 of yacc.c  */
+#line 1793 "lib/conf-parse.c"
+      default: break;
+    }
+  /* User semantic actions sometimes alter yychar, and that requires
+     that yytoken be updated with the new translation.  We take the
+     approach of translating immediately before every use of yytoken.
+     One alternative is translating here after every semantic action,
+     but that translation would be missed if the semantic action invokes
+     YYABORT, YYACCEPT, or YYERROR immediately after altering yychar or
+     if it invokes YYBACKUP.  In the case of YYABORT or YYACCEPT, an
+     incorrect destructor might then be invoked immediately.  In the
+     case of YYERROR or YYBACKUP, subsequent parser actions might lead
+     to an incorrect destructor call or verbose syntax error message
+     before the lookahead is translated.  */
+  YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc);
+
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+
+  *++yyvsp = yyval;
+
+  /* Now `shift' the result of the reduction.  Determine what state
+     that goes to, based on the state we popped back to and the rule
+     number reduced by.  */
+
+  yyn = yyr1[yyn];
+
+  yystate = yypgoto[yyn - YYNTOKENS] + *yyssp;
+  if (0 <= yystate && yystate <= YYLAST && yycheck[yystate] == *yyssp)
+    yystate = yytable[yystate];
+  else
+    yystate = yydefgoto[yyn - YYNTOKENS];
+
+  goto yynewstate;
+
+
+/*------------------------------------.
+| yyerrlab -- here on detecting error |
+`------------------------------------*/
+yyerrlab:
+  /* Make sure we have latest lookahead translation.  See comments at
+     user semantic actions for why this is necessary.  */
+  yytoken = yychar == YYEMPTY ? YYEMPTY : YYTRANSLATE (yychar);
+
+  /* If not already recovering from an error, report this error.  */
+  if (!yyerrstatus)
+    {
+      ++yynerrs;
+#if ! YYERROR_VERBOSE
+      yyerror (YY_("syntax error"));
+#else
+# define YYSYNTAX_ERROR yysyntax_error (&yymsg_alloc, &yymsg, \
+                                        yyssp, yytoken)
+      {
+        char const *yymsgp = YY_("syntax error");
+        int yysyntax_error_status;
+        yysyntax_error_status = YYSYNTAX_ERROR;
+        if (yysyntax_error_status == 0)
+          yymsgp = yymsg;
+        else if (yysyntax_error_status == 1)
+          {
+            if (yymsg != yymsgbuf)
+              YYSTACK_FREE (yymsg);
+            yymsg = (char *) YYSTACK_ALLOC (yymsg_alloc);
+            if (!yymsg)
+              {
+                yymsg = yymsgbuf;
+                yymsg_alloc = sizeof yymsgbuf;
+                yysyntax_error_status = 2;
+              }
+            else
+              {
+                yysyntax_error_status = YYSYNTAX_ERROR;
+                yymsgp = yymsg;
+              }
+          }
+        yyerror (yymsgp);
+        if (yysyntax_error_status == 2)
+          goto yyexhaustedlab;
+      }
+# undef YYSYNTAX_ERROR
+#endif
+    }
+
+
+
+  if (yyerrstatus == 3)
+    {
+      /* If just tried and failed to reuse lookahead token after an
+	 error, discard it.  */
+
+      if (yychar <= YYEOF)
+	{
+	  /* Return failure if at end of input.  */
+	  if (yychar == YYEOF)
+	    YYABORT;
+	}
+      else
+	{
+	  yydestruct ("Error: discarding",
+		      yytoken, &yylval);
+	  yychar = YYEMPTY;
+	}
+    }
+
+  /* Else will try to reuse lookahead token after shifting the error
+     token.  */
+  goto yyerrlab1;
+
+
+/*---------------------------------------------------.
+| yyerrorlab -- error raised explicitly by YYERROR.  |
+`---------------------------------------------------*/
+yyerrorlab:
+
+  /* Pacify compilers like GCC when the user code never invokes
+     YYERROR and the label yyerrorlab therefore never appears in user
+     code.  */
+  if (/*CONSTCOND*/ 0)
+     goto yyerrorlab;
+
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYERROR.  */
+  YYPOPSTACK (yylen);
+  yylen = 0;
+  YY_STACK_PRINT (yyss, yyssp);
+  yystate = *yyssp;
+  goto yyerrlab1;
+
+
+/*-------------------------------------------------------------.
+| yyerrlab1 -- common code for both syntax error and YYERROR.  |
+`-------------------------------------------------------------*/
+yyerrlab1:
+  yyerrstatus = 3;	/* Each real token shifted decrements this.  */
+
+  for (;;)
+    {
+      yyn = yypact[yystate];
+      if (!yypact_value_is_default (yyn))
+	{
+	  yyn += YYTERROR;
+	  if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+	    {
+	      yyn = yytable[yyn];
+	      if (0 < yyn)
+		break;
+	    }
+	}
+
+      /* Pop the current state because it cannot handle the error token.  */
+      if (yyssp == yyss)
+	YYABORT;
+
+
+      yydestruct ("Error: popping",
+		  yystos[yystate], yyvsp);
+      YYPOPSTACK (1);
+      yystate = *yyssp;
+      YY_STACK_PRINT (yyss, yyssp);
+    }
+
+  *++yyvsp = yylval;
+
+
+  /* Shift the error token.  */
+  YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp);
+
+  yystate = yyn;
+  goto yynewstate;
+
+
+/*-------------------------------------.
+| yyacceptlab -- YYACCEPT comes here.  |
+`-------------------------------------*/
+yyacceptlab:
+  yyresult = 0;
+  goto yyreturn;
+
+/*-----------------------------------.
+| yyabortlab -- YYABORT comes here.  |
+`-----------------------------------*/
+yyabortlab:
+  yyresult = 1;
+  goto yyreturn;
+
+#if !defined(yyoverflow) || YYERROR_VERBOSE
+/*-------------------------------------------------.
+| yyexhaustedlab -- memory exhaustion comes here.  |
+`-------------------------------------------------*/
+yyexhaustedlab:
+  yyerror (YY_("memory exhausted"));
+  yyresult = 2;
+  /* Fall through.  */
+#endif
+
+yyreturn:
+  if (yychar != YYEMPTY)
+    {
+      /* Make sure we have latest lookahead translation.  See comments at
+         user semantic actions for why this is necessary.  */
+      yytoken = YYTRANSLATE (yychar);
+      yydestruct ("Cleanup: discarding lookahead",
+                  yytoken, &yylval);
+    }
+  /* Do not reclaim the symbols of the rule which action triggered
+     this YYABORT or YYACCEPT.  */
+  YYPOPSTACK (yylen);
+  YY_STACK_PRINT (yyss, yyssp);
+  while (yyssp != yyss)
+    {
+      yydestruct ("Cleanup: popping",
+		  yystos[*yyssp], yyvsp);
+      YYPOPSTACK (1);
+    }
+#ifndef yyoverflow
+  if (yyss != yyssa)
+    YYSTACK_FREE (yyss);
+#endif
+#if YYERROR_VERBOSE
+  if (yymsg != yymsgbuf)
+    YYSTACK_FREE (yymsg);
+#endif
+  /* Make sure YYID is used.  */
+  return YYID (yyresult);
+}
+
+
+
+/* Line 2067 of yacc.c  */
+#line 330 "lib/conf-parse.y"
+
+
+void sensors_yyerror(const char *err)
+{
+  if (sensors_lex_error[0]) {
+    sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+    sensors_lex_error[0] = '\0';
+  } else
+    sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+  sensors_expr *res = malloc(sizeof(sensors_expr));
+  if (! res)
+    sensors_fatal_error(__func__, "Allocating a new expression");
+  return res;
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.h b/tools/gator/daemon/libsensors/conf-parse.h
new file mode 100644
index 000000000000..89c9c1a0d59f
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.h
@@ -0,0 +1,84 @@
+/* A Bison parser, made by GNU Bison 2.5.  */
+
+/* Bison interface for Yacc-like parsers in C
+   
+      Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+   
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+   
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
+
+/* As a special exception, you may create a larger work that contains
+   part or all of the Bison parser skeleton and distribute that work
+   under terms of your choice, so long as that work isn't itself a
+   parser generator using the skeleton or a modified version thereof
+   as a parser skeleton.  Alternatively, if you modify or redistribute
+   the parser skeleton itself, you may (at your option) remove this
+   special exception, which will cause the skeleton and the resulting
+   Bison output files to be licensed under the GNU General Public
+   License without this special exception.
+   
+   This special exception was added by the Free Software Foundation in
+   version 2.2 of Bison.  */
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NEG = 258,
+     EOL = 259,
+     BUS = 260,
+     LABEL = 261,
+     SET = 262,
+     CHIP = 263,
+     COMPUTE = 264,
+     IGNORE = 265,
+     FLOAT = 266,
+     NAME = 267,
+     ERROR = 268
+   };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 2068 of yacc.c  */
+#line 79 "lib/conf-parse.y"
+
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+
+
+
+/* Line 2068 of yacc.c  */
+#line 76 "lib/conf-parse.h"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+extern YYSTYPE sensors_yylval;
+
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.y b/tools/gator/daemon/libsensors/conf-parse.y
new file mode 100644
index 000000000000..1937f544dc66
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.y
@@ -0,0 +1,347 @@
+%{
+/*
+    conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+                                      &sensors_config_busses,\
+                                      &sensors_config_busses_count,\
+                                      &sensors_config_busses_max,\
+                                      sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+                                        &current_chip->labels,\
+                                        &current_chip->labels_count,\
+                                        &current_chip->labels_max,\
+                                        sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+                                      &current_chip->sets,\
+                                      &current_chip->sets_count,\
+                                      &current_chip->sets_max,\
+                                      sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->computes,\
+                                          &current_chip->computes_count,\
+                                          &current_chip->computes_max,\
+                                          sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+                                          &current_chip->ignores,\
+                                          &current_chip->ignores_count,\
+                                          &current_chip->ignores_max,\
+                                          sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+                                       &sensors_config_chips,\
+                                       &sensors_config_chips_count,\
+                                       &sensors_config_chips_max,\
+                                       sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+                                                  &(list).fits,\
+                                                  &(list).fits_count,\
+                                                  &(list).fits_max, \
+		                                  sizeof(sensors_chip_name));
+
+%}
+
+%union {
+  double value;
+  char *name;
+  void *nothing;
+  sensors_chip_name_list chips;
+  sensors_expr *expr;
+  sensors_bus_id bus;
+  sensors_chip_name chip;
+  sensors_config_line line;
+}  
+
+%left <nothing> '-' '+'
+%left <nothing> '*' '/'
+%left <nothing> NEG
+%right <nothing> '^' '`'
+
+%token <nothing> ','
+%token <nothing> EOL
+%token <line> BUS
+%token <line> LABEL
+%token <line> SET
+%token <line> CHIP
+%token <line> COMPUTE
+%token <line> IGNORE
+%token <value> FLOAT
+%token <name> NAME
+%token <nothing> ERROR
+
+%type <chips> chip_name_list
+%type <expr> expression
+%type <bus> bus_id
+%type <name> adapter_name
+%type <name> function_name
+%type <name> string
+%type <chip> chip_name
+
+%start input
+
+%%
+
+input:	  /* empty */
+	| input line
+;
+
+line:	  bus_statement EOL
+	| label_statement EOL
+	| set_statement EOL
+	| chip_statement EOL
+	| compute_statement EOL
+	| ignore_statement EOL
+	| error	EOL
+;
+
+bus_statement:	  BUS bus_id adapter_name
+		  { sensors_bus new_el;
+		    new_el.line = $1;
+		    new_el.bus = $2;
+                    new_el.adapter = $3;
+		    bus_add_el(&new_el);
+		  }
+;
+
+label_statement:	  LABEL function_name string
+			  { sensors_label new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Label statement before first chip statement");
+			      free($2);
+			      free($3);
+			      YYERROR;
+			    }
+			    new_el.line = $1;
+			    new_el.name = $2;
+			    new_el.value = $3;
+			    label_add_el(&new_el);
+			  }
+;
+
+set_statement:	  SET function_name expression
+		  { sensors_set new_el;
+		    if (!current_chip) {
+		      sensors_yyerror("Set statement before first chip statement");
+		      free($2);
+		      sensors_free_expr($3);
+		      YYERROR;
+		    }
+		    new_el.line = $1;
+		    new_el.name = $2;
+		    new_el.value = $3;
+		    set_add_el(&new_el);
+		  }
+;
+
+compute_statement:	  COMPUTE function_name expression ',' expression
+			  { sensors_compute new_el;
+			    if (!current_chip) {
+			      sensors_yyerror("Compute statement before first chip statement");
+			      free($2);
+			      sensors_free_expr($3);
+			      sensors_free_expr($5);
+			      YYERROR;
+			    }
+			    new_el.line = $1;
+			    new_el.name = $2;
+			    new_el.from_proc = $3;
+			    new_el.to_proc = $5;
+			    compute_add_el(&new_el);
+			  }
+;
+
+ignore_statement:	IGNORE function_name
+			{ sensors_ignore new_el;
+			  if (!current_chip) {
+			    sensors_yyerror("Ignore statement before first chip statement");
+			    free($2);
+			    YYERROR;
+			  }
+			  new_el.line = $1;
+			  new_el.name = $2;
+			  ignore_add_el(&new_el);
+			}
+;
+
+chip_statement:	  CHIP chip_name_list
+		  { sensors_chip new_el;
+		    new_el.line = $1;
+		    new_el.labels = NULL;
+		    new_el.sets = NULL;
+		    new_el.computes = NULL;
+		    new_el.ignores = NULL;
+		    new_el.labels_count = new_el.labels_max = 0;
+		    new_el.sets_count = new_el.sets_max = 0;
+		    new_el.computes_count = new_el.computes_max = 0;
+		    new_el.ignores_count = new_el.ignores_max = 0;
+		    new_el.chips = $2;
+		    chip_add_el(&new_el);
+		    current_chip = sensors_config_chips + 
+		                   sensors_config_chips_count - 1;
+		  }
+;
+
+chip_name_list:	  chip_name
+		  { 
+		    $$.fits = NULL;
+		    $$.fits_count = $$.fits_max = 0;
+		    fits_add_el(&$1,$$);
+		  }
+		| chip_name_list chip_name
+		  { $$ = $1;
+		    fits_add_el(&$2,$$);
+		  }
+;
+	
+expression:	  FLOAT	
+		  { $$ = malloc_expr(); 
+		    $$->data.val = $1; 
+		    $$->kind = sensors_kind_val;
+		  }
+		| NAME
+		  { $$ = malloc_expr(); 
+		    $$->data.var = $1;
+		    $$->kind = sensors_kind_var;
+		  }
+		| '@'
+		  { $$ = malloc_expr();
+		    $$->kind = sensors_kind_source;
+		  }
+		| expression '+' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_add;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '-' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_sub;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '*' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_multiply;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| expression '/' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_divide;
+		    $$->data.subexpr.sub1 = $1;
+		    $$->data.subexpr.sub2 = $3;
+		  }
+		| '-' expression  %prec NEG
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_negate;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+		| '(' expression ')'
+		  { $$ = $2; }
+		| '^' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_exp;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+		| '`' expression
+		  { $$ = malloc_expr(); 
+		    $$->kind = sensors_kind_sub;
+		    $$->data.subexpr.op = sensors_log;
+		    $$->data.subexpr.sub1 = $2;
+		    $$->data.subexpr.sub2 = NULL;
+		  }
+;
+
+bus_id:		  NAME
+		  { int res = sensors_parse_bus_id($1,&$$);
+		    free($1);
+		    if (res) {
+                      sensors_yyerror("Parse error in bus id");
+		      YYERROR;
+                    }
+		  }
+;
+
+adapter_name:	  NAME
+		  { $$ = $1; }
+;
+
+function_name:	  NAME
+		  { $$ = $1; }
+;
+
+string:	  NAME
+	  { $$ = $1; }
+;
+
+chip_name:	  NAME
+		  { int res = sensors_parse_chip_name($1,&$$); 
+		    free($1);
+		    if (res) {
+		      sensors_yyerror("Parse error in chip name");
+		      YYERROR;
+		    }
+		  }
+;
+
+%%
+
+void sensors_yyerror(const char *err)
+{
+  if (sensors_lex_error[0]) {
+    sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+    sensors_lex_error[0] = '\0';
+  } else
+    sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+  sensors_expr *res = malloc(sizeof(sensors_expr));
+  if (! res)
+    sensors_fatal_error(__func__, "Allocating a new expression");
+  return res;
+}
diff --git a/tools/gator/daemon/libsensors/conf.h b/tools/gator/daemon/libsensors/conf.h
new file mode 100644
index 000000000000..b7ce4f7ca833
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf.h
@@ -0,0 +1,34 @@
+/*
+    conf.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_CONF_H
+#define LIB_SENSORS_CONF_H
+
+/* This is defined in conf-lex.l */
+int sensors_yylex(void);
+extern char sensors_lex_error[];
+extern const char *sensors_yyfilename;
+extern int sensors_yylineno;
+extern FILE *sensors_yyin;
+
+/* This is defined in conf-parse.y */
+int sensors_yyparse(void);
+
+#endif /* LIB_SENSORS_CONF_H */
diff --git a/tools/gator/daemon/libsensors/data.c b/tools/gator/daemon/libsensors/data.c
new file mode 100644
index 000000000000..cac9c8dc6eb1
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.c
@@ -0,0 +1,278 @@
+/*
+    data.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to move version.h to the current directory. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "access.h"
+#include "error.h"
+#include "data.h"
+#include "sensors.h"
+#include "version.h"
+
+const char *libsensors_version = LM_VERSION;
+
+char **sensors_config_files = NULL;
+int sensors_config_files_count = 0;
+int sensors_config_files_max = 0;
+
+sensors_chip *sensors_config_chips = NULL;
+int sensors_config_chips_count = 0;
+int sensors_config_chips_subst = 0;
+int sensors_config_chips_max = 0;
+
+sensors_bus *sensors_config_busses = NULL;
+int sensors_config_busses_count = 0;
+int sensors_config_busses_max = 0;
+
+sensors_chip_features *sensors_proc_chips = NULL;
+int sensors_proc_chips_count = 0;
+int sensors_proc_chips_max = 0;
+
+sensors_bus *sensors_proc_bus = NULL;
+int sensors_proc_bus_count = 0;
+int sensors_proc_bus_max = 0;
+
+void sensors_free_chip_name(sensors_chip_name *chip)
+{
+	free(chip->prefix);
+}
+
+/*
+   Parse a chip name to the internal representation. These are valid names:
+
+     lm78-i2c-10-5e		*-i2c-10-5e
+     lm78-i2c-10-*		*-i2c-10-*
+     lm78-i2c-*-5e		*-i2c-*-5e
+     lm78-i2c-*-*		*-i2c-*-*
+     lm78-isa-10dd		*-isa-10dd
+     lm78-isa-*			*-isa-*
+     lm78-*			*-*
+
+   Here 'lm78' can be any prefix. 'i2c' and 'isa' are
+   literal strings, just like all dashes '-' and wildcards '*'. '10' can
+   be any decimal i2c bus number. '5e' can be any hexadecimal i2c device
+   address, and '10dd' any hexadecimal isa address.
+
+   The 'prefix' part in the result is freshly allocated. All old contents
+   of res is overwritten. res itself is not allocated. In case of an error
+   return (ie. != 0), res is undefined, but all allocations are undone.
+*/
+
+int sensors_parse_chip_name(const char *name, sensors_chip_name *res)
+{
+	char *dash;
+
+	/* First, the prefix. It's either "*" or a real chip name. */
+	if (!strncmp(name, "*-", 2)) {
+		res->prefix = SENSORS_CHIP_NAME_PREFIX_ANY;
+		name += 2;
+	} else {
+		if (!(dash = strchr(name, '-')))
+			return -SENSORS_ERR_CHIP_NAME;
+		res->prefix = strndup(name, dash - name);
+		if (!res->prefix)
+			sensors_fatal_error(__func__,
+					    "Allocating name prefix");
+		name = dash + 1;
+	}
+
+	/* Then we have either a sole "*" (all chips with this name) or a bus
+	   type and an address. */
+	if (!strcmp(name, "*")) {
+		res->bus.type = SENSORS_BUS_TYPE_ANY;
+		res->bus.nr = SENSORS_BUS_NR_ANY;
+		res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+		return 0;
+	}
+
+	if (!(dash = strchr(name, '-')))
+		goto ERROR;
+	if (!strncmp(name, "i2c", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_I2C;
+	else if (!strncmp(name, "isa", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_ISA;
+	else if (!strncmp(name, "pci", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_PCI;
+	else if (!strncmp(name, "spi", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_SPI;
+	else if (!strncmp(name, "virtual", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+	else if (!strncmp(name, "acpi", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_ACPI;
+	else if (!strncmp(name, "hid", dash - name))
+		res->bus.type = SENSORS_BUS_TYPE_HID;
+	else
+		goto ERROR;
+	name = dash + 1;
+
+	/* Some bus types (i2c, spi) have an additional bus number.
+	   For these, the next part is either a "*" (any bus of that type)
+	   or a decimal number. */
+	switch (res->bus.type) {
+	case SENSORS_BUS_TYPE_I2C:
+	case SENSORS_BUS_TYPE_SPI:
+	case SENSORS_BUS_TYPE_HID:
+		if (!strncmp(name, "*-", 2)) {
+			res->bus.nr = SENSORS_BUS_NR_ANY;
+			name += 2;
+			break;
+		}
+
+		res->bus.nr = strtoul(name, &dash, 10);
+		if (*name == '\0' || *dash != '-' || res->bus.nr < 0)
+			goto ERROR;
+		name = dash + 1;
+		break;
+	default:
+		res->bus.nr = SENSORS_BUS_NR_ANY;
+	}
+
+	/* Last part is the chip address, or "*" for any address. */
+	if (!strcmp(name, "*")) {
+		res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+	} else {
+		res->addr = strtoul(name, &dash, 16);
+		if (*name == '\0' || *dash != '\0' || res->addr < 0)
+			goto ERROR;
+	}
+
+	return 0;
+
+ERROR:
+	free(res->prefix);
+	return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_snprintf_chip_name(char *str, size_t size,
+			       const sensors_chip_name *chip)
+{
+	if (sensors_chip_name_has_wildcards(chip))
+		return -SENSORS_ERR_WILDCARDS;
+
+	switch (chip->bus.type) {
+	case SENSORS_BUS_TYPE_ISA:
+		return snprintf(str, size, "%s-isa-%04x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_PCI:
+		return snprintf(str, size, "%s-pci-%04x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_I2C:
+		return snprintf(str, size, "%s-i2c-%hd-%02x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	case SENSORS_BUS_TYPE_SPI:
+		return snprintf(str, size, "%s-spi-%hd-%x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	case SENSORS_BUS_TYPE_VIRTUAL:
+		return snprintf(str, size, "%s-virtual-%x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_ACPI:
+		return snprintf(str, size, "%s-acpi-%x", chip->prefix,
+				chip->addr);
+	case SENSORS_BUS_TYPE_HID:
+		return snprintf(str, size, "%s-hid-%hd-%x", chip->prefix,
+				chip->bus.nr, chip->addr);
+	}
+
+	return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus)
+{
+	char *endptr;
+
+	if (strncmp(name, "i2c-", 4)) {
+		return -SENSORS_ERR_BUS_NAME;
+	}
+	name += 4;
+	bus->type = SENSORS_BUS_TYPE_I2C;
+	bus->nr = strtoul(name, &endptr, 10);
+	if (*name == '\0' || *endptr != '\0' || bus->nr < 0)
+		return -SENSORS_ERR_BUS_NAME;
+	return 0;
+}
+
+static int sensors_substitute_chip(sensors_chip_name *name,
+				   const char *filename, int lineno)
+{
+	int i, j;
+	for (i = 0; i < sensors_config_busses_count; i++)
+		if (sensors_config_busses[i].bus.type == name->bus.type &&
+		    sensors_config_busses[i].bus.nr == name->bus.nr)
+			break;
+
+	if (i == sensors_config_busses_count) {
+		sensors_parse_error_wfn("Undeclared bus id referenced",
+					filename, lineno);
+		name->bus.nr = SENSORS_BUS_NR_IGNORE;
+		return -SENSORS_ERR_BUS_NAME;
+	}
+
+	/* Compare the adapter names */
+	for (j = 0; j < sensors_proc_bus_count; j++) {
+		if (!strcmp(sensors_config_busses[i].adapter,
+			    sensors_proc_bus[j].adapter)) {
+			name->bus.nr = sensors_proc_bus[j].bus.nr;
+			return 0;
+		}
+	}
+
+	/* We did not find a matching bus name, simply ignore this chip
+	   config entry. */
+	name->bus.nr = SENSORS_BUS_NR_IGNORE;
+	return 0;
+}
+
+/* Bus substitution is on a per-configuration file basis, so we keep
+   memory (in sensors_config_chips_subst) of which chip entries have been
+   already substituted. */
+int sensors_substitute_busses(void)
+{
+	int err, i, j, lineno;
+	sensors_chip_name_list *chips;
+	const char *filename;
+	int res = 0;
+
+	for (i = sensors_config_chips_subst;
+	     i < sensors_config_chips_count; i++) {
+		filename = sensors_config_chips[i].line.filename;
+		lineno = sensors_config_chips[i].line.lineno;
+		chips = &sensors_config_chips[i].chips;
+		for (j = 0; j < chips->fits_count; j++) {
+			/* We can only substitute if a specific bus number
+			   is given. */
+			if (chips->fits[j].bus.nr == SENSORS_BUS_NR_ANY)
+				continue;
+
+			err = sensors_substitute_chip(&chips->fits[j],
+						      filename, lineno);
+			if (err)
+				res = err;
+		}
+	}
+	sensors_config_chips_subst = sensors_config_chips_count;
+	return res;
+}
diff --git a/tools/gator/daemon/libsensors/data.h b/tools/gator/daemon/libsensors/data.h
new file mode 100644
index 000000000000..4a23eabe1414
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.h
@@ -0,0 +1,184 @@
+/*
+    data.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_DATA_H
+#define LIB_SENSORS_DATA_H
+
+#include "sensors.h"
+#include "general.h"
+
+/* This header file contains all kinds of data structures which are used
+   for the representation of the config file data and the sensors
+   data. */
+
+/* Kinds of expression operators recognized */
+typedef enum sensors_operation {
+	sensors_add, sensors_sub, sensors_multiply, sensors_divide,
+	sensors_negate, sensors_exp, sensors_log,
+} sensors_operation;
+
+/* An expression can have several forms */
+typedef enum sensors_expr_kind {
+	sensors_kind_val, sensors_kind_source, sensors_kind_var,
+	sensors_kind_sub
+} sensors_expr_kind;
+
+/* An expression. It is either a floating point value, a variable name,
+   an operation on subexpressions, or the special value 'sub' } */
+struct sensors_expr;
+
+typedef struct sensors_subexpr {
+	sensors_operation op;
+	struct sensors_expr *sub1;
+	struct sensors_expr *sub2;
+} sensors_subexpr;
+
+typedef struct sensors_expr {
+	sensors_expr_kind kind;
+	union {
+		double val;
+		char *var;
+		sensors_subexpr subexpr;
+	} data;
+} sensors_expr;
+
+/* Config file line reference */
+typedef struct sensors_config_line {
+	const char *filename;
+	int lineno;
+} sensors_config_line;
+
+/* Config file label declaration: a feature name, combined with the label
+   value */
+typedef struct sensors_label {
+	char *name;
+	char *value;
+	sensors_config_line line;
+} sensors_label;
+
+/* Config file set declaration: a subfeature name, combined with an
+   expression */
+typedef struct sensors_set {
+	char *name;
+	sensors_expr *value;
+	sensors_config_line line;
+} sensors_set;
+
+/* Config file compute declaration: a feature name, combined with two
+   expressions */
+typedef struct sensors_compute {
+	char *name;
+	sensors_expr *from_proc;
+	sensors_expr *to_proc;
+	sensors_config_line line;
+} sensors_compute;
+
+/* Config file ignore declaration: a feature name */
+typedef struct sensors_ignore {
+	char *name;
+	sensors_config_line line;
+} sensors_ignore;
+
+/* A list of chip names, used to represent a config file chips declaration */
+typedef struct sensors_chip_name_list {
+	sensors_chip_name *fits;
+	int fits_count;
+	int fits_max;
+} sensors_chip_name_list;
+
+/* A config file chip block */
+typedef struct sensors_chip {
+	sensors_chip_name_list chips;
+	sensors_label *labels;
+	int labels_count;
+	int labels_max;
+	sensors_set *sets;
+	int sets_count;
+	int sets_max;
+	sensors_compute *computes;
+	int computes_count;
+	int computes_max;
+	sensors_ignore *ignores;
+	int ignores_count;
+	int ignores_max;
+	sensors_config_line line;
+} sensors_chip;
+
+/* Config file bus declaration: the bus type and number, combined with adapter
+   name */
+typedef struct sensors_bus {
+	char *adapter;
+	sensors_bus_id bus;
+	sensors_config_line line;
+} sensors_bus;
+
+/* Internal data about all features and subfeatures of a chip */
+typedef struct sensors_chip_features {
+	struct sensors_chip_name chip;
+	struct sensors_feature *feature;
+	struct sensors_subfeature *subfeature;
+	int feature_count;
+	int subfeature_count;
+} sensors_chip_features;
+
+extern char **sensors_config_files;
+extern int sensors_config_files_count;
+extern int sensors_config_files_max;
+
+#define sensors_add_config_files(el) sensors_add_array_el( \
+	(el), &sensors_config_files, &sensors_config_files_count, \
+	&sensors_config_files_max, sizeof(char *))
+
+extern sensors_chip *sensors_config_chips;
+extern int sensors_config_chips_count;
+extern int sensors_config_chips_subst;
+extern int sensors_config_chips_max;
+
+extern sensors_bus *sensors_config_busses;
+extern int sensors_config_busses_count;
+extern int sensors_config_busses_max;
+
+extern sensors_chip_features *sensors_proc_chips;
+extern int sensors_proc_chips_count;
+extern int sensors_proc_chips_max;
+
+#define sensors_add_proc_chips(el) sensors_add_array_el( \
+	(el), &sensors_proc_chips, &sensors_proc_chips_count,\
+	&sensors_proc_chips_max, sizeof(struct sensors_chip_features))
+
+extern sensors_bus *sensors_proc_bus;
+extern int sensors_proc_bus_count;
+extern int sensors_proc_bus_max;
+
+#define sensors_add_proc_bus(el) sensors_add_array_el( \
+	(el), &sensors_proc_bus, &sensors_proc_bus_count,\
+	&sensors_proc_bus_max, sizeof(struct sensors_bus))
+
+/* Substitute configuration bus numbers with real-world bus numbers
+   in the chips lists */
+int sensors_substitute_busses(void);
+
+
+/* Parse a bus id into its components. Returns 0 on success, a value from
+   error.h on failure. */
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus);
+
+#endif /* def LIB_SENSORS_DATA_H */
diff --git a/tools/gator/daemon/libsensors/error.c b/tools/gator/daemon/libsensors/error.c
new file mode 100644
index 000000000000..55bde81295fb
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.c
@@ -0,0 +1,92 @@
+/*
+    error.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <stdio.h>
+#include "error.h"
+#include "general.h"
+
+static void sensors_default_parse_error(const char *err, int lineno);
+static void sensors_default_parse_error_wfn(const char *err,
+					    const char *filename, int lineno);
+static void sensors_default_fatal_error(const char *proc, const char *err);
+
+void (*sensors_parse_error) (const char *err, int lineno) =
+						sensors_default_parse_error;
+void (*sensors_parse_error_wfn) (const char *err, const char *filename,
+				 int lineno) = sensors_default_parse_error_wfn;
+void (*sensors_fatal_error) (const char *proc, const char *err) =
+						sensors_default_fatal_error;
+
+static const char *errorlist[] = {
+	/* Invalid error code    */ "Unknown error",
+	/* SENSORS_ERR_WILDCARDS */ "Wildcard found in chip name",
+	/* SENSORS_ERR_NO_ENTRY  */ "No such subfeature known",
+	/* SENSORS_ERR_ACCESS_R  */ "Can't read",
+	/* SENSORS_ERR_KERNEL    */ "Kernel interface error",
+	/* SENSORS_ERR_DIV_ZERO  */ "Divide by zero",
+	/* SENSORS_ERR_CHIP_NAME */ "Can't parse chip name",
+	/* SENSORS_ERR_BUS_NAME  */ "Can't parse bus name",
+	/* SENSORS_ERR_PARSE     */ "General parse error",
+	/* SENSORS_ERR_ACCESS_W  */ "Can't write",
+	/* SENSORS_ERR_IO        */ "I/O error",
+	/* SENSORS_ERR_RECURSION */ "Evaluation recurses too deep",
+};
+
+const char *sensors_strerror(int errnum)
+{
+	if (errnum < 0)
+		errnum = -errnum;
+	if (errnum >= ARRAY_SIZE(errorlist))
+		errnum = 0;
+	return errorlist[errnum];
+}
+
+void sensors_default_parse_error(const char *err, int lineno)
+{
+	if (lineno)
+		fprintf(stderr, "Error: Line %d: %s\n", lineno, err);
+	else
+		fprintf(stderr, "Error: %s\n", err);
+}
+
+void sensors_default_parse_error_wfn(const char *err,
+				     const char *filename, int lineno)
+{
+	/* If application provided a custom parse error reporting function
+	   but not the variant with the filename, fall back to the original
+	   variant without the filename, for backwards compatibility. */
+	if (sensors_parse_error != sensors_default_parse_error ||
+	    !filename)
+		return sensors_parse_error(err, lineno);
+
+	if (lineno)
+		fprintf(stderr, "Error: File %s, line %d: %s\n", filename,
+			lineno, err);
+	else
+		fprintf(stderr, "Error: File %s: %s\n", filename, err);
+}
+
+void sensors_default_fatal_error(const char *proc, const char *err)
+{
+	fprintf(stderr, "Fatal error in `%s': %s\n", proc, err);
+	exit(1);
+}
diff --git a/tools/gator/daemon/libsensors/error.h b/tools/gator/daemon/libsensors/error.h
new file mode 100644
index 000000000000..37cdc956151d
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.h
@@ -0,0 +1,74 @@
+/*
+    error.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007-2009   Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ERROR_H
+#define LIB_SENSORS_ERROR_H
+
+#define SENSORS_ERR_WILDCARDS	1 /* Wildcard found in chip name */
+#define SENSORS_ERR_NO_ENTRY	2 /* No such subfeature known */
+#define SENSORS_ERR_ACCESS_R	3 /* Can't read */
+#define SENSORS_ERR_KERNEL	4 /* Kernel interface error */
+#define SENSORS_ERR_DIV_ZERO	5 /* Divide by zero */
+#define SENSORS_ERR_CHIP_NAME	6 /* Can't parse chip name */
+#define SENSORS_ERR_BUS_NAME	7 /* Can't parse bus name */
+#define SENSORS_ERR_PARSE	8 /* General parse error */
+#define SENSORS_ERR_ACCESS_W	9 /* Can't write */
+#define SENSORS_ERR_IO		10 /* I/O error */
+#define SENSORS_ERR_RECURSION	11 /* Evaluation recurses too deep */
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+
+/* This function returns a pointer to a string which describes the error.
+   errnum may be negative (the corresponding positive error is returned).
+   You may not modify the result! */
+const char *sensors_strerror(int errnum);
+
+/* These functions are called when a parse error is detected. Give them new
+   values, and your own functions are called instead of the default (which
+   print to stderr). These functions may terminate the program, but they
+   usually output an error and return. The first function is the original
+   one, the second one was added later when support for multiple
+   configuration files was added.
+   The library code now only calls the second function. However, for
+   backwards compatibility, if an application provides a custom handling
+   function for the first function but not the second, then all parse
+   errors will be reported using the first function (that is, the filename
+   is never reported.)
+   Note that filename can be NULL (if filename isn't known) and lineno
+   can be 0 (if the error occurs before the actual parsing starts.) */
+extern void (*sensors_parse_error) (const char *err, int lineno);
+extern void (*sensors_parse_error_wfn) (const char *err,
+					const char *filename, int lineno);
+
+/* This function is called when an immediately fatal error (like no
+   memory left) is detected. Give it a new value, and your own function
+   is called instead of the default (which prints to stderr and ends
+   the program). Never let it return! */
+extern void (*sensors_fatal_error) (const char *proc, const char *err);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/general.c b/tools/gator/daemon/libsensors/general.c
new file mode 100644
index 000000000000..f237e3b59c22
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.c
@@ -0,0 +1,85 @@
+/*
+    general.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#include "error.h"
+#include "general.h"
+#include <errno.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+
+#define A_BUNCH 16
+
+void sensors_malloc_array(void *list, int *num_el, int *max_el, int el_size)
+{
+	void **my_list = (void **)list;
+
+	*my_list = malloc(el_size*A_BUNCH);
+	if (! *my_list)
+		sensors_fatal_error(__func__, "Allocating new elements");
+	*max_el = A_BUNCH;
+	*num_el = 0;
+}
+
+void sensors_free_array(void *list, int *num_el, int *max_el)
+{
+	void **my_list = (void **)list;
+
+	free(*my_list);
+	*my_list = NULL;
+	*num_el = 0;
+	*max_el = 0;
+}
+
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+			  int *max_el, int el_size)
+{
+	int new_max_el;
+	void **my_list = (void *)list;
+	if (*num_el + 1 > *max_el) {
+		new_max_el = *max_el + A_BUNCH;
+		*my_list = realloc(*my_list, new_max_el * el_size);
+		if (! *my_list)
+			sensors_fatal_error(__func__,
+					    "Allocating new elements");
+		*max_el = new_max_el;
+	}
+	memcpy(((char *) *my_list) + *num_el * el_size, el, el_size);
+	(*num_el) ++;
+}
+
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+			   int *num_el, int *max_el, int el_size)
+{
+	int new_max_el;
+	void **my_list = (void *)list;
+	if (*num_el + nr_els > *max_el) {
+		new_max_el = (*max_el + nr_els + A_BUNCH);
+		new_max_el -= new_max_el % A_BUNCH;
+		*my_list = realloc(*my_list, new_max_el * el_size);
+		if (! *my_list)
+			sensors_fatal_error(__func__,
+					    "Allocating new elements");
+		*max_el = new_max_el;
+	}
+	memcpy(((char *)*my_list) + *num_el * el_size, els, el_size * nr_els);
+	*num_el += nr_els;
+}
diff --git a/tools/gator/daemon/libsensors/general.h b/tools/gator/daemon/libsensors/general.h
new file mode 100644
index 000000000000..a3971e02e1b7
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.h
@@ -0,0 +1,39 @@
+/*
+    general.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_GENERAL
+#define LIB_SENSORS_GENERAL
+
+/* These are general purpose functions. They allow you to use variable-
+   length arrays, which are extended automatically. A distinction is
+   made between the current number of elements and the maximum number.
+   You can only add elements at the end. Primitive, but very useful
+   for internal use. */
+void sensors_malloc_array(void *list, int *num_el, int *max_el,
+			  int el_size);
+void sensors_free_array(void *list, int *num_el, int *max_el);
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+			  int *max_el, int el_size);
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+			   int *num_el, int *max_el, int el_size);
+
+#define ARRAY_SIZE(arr)	(int)(sizeof(arr) / sizeof((arr)[0]))
+
+#endif /* LIB_SENSORS_GENERAL */
diff --git a/tools/gator/daemon/libsensors/init.c b/tools/gator/daemon/libsensors/init.c
new file mode 100644
index 000000000000..558046e76c24
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.c
@@ -0,0 +1,341 @@
+/*
+    init.c - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2009  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to cast alphasort to supress a warning as it's prototype is different on android. ***/
+
+/* Needed for scandir() and alphasort() */
+#define _BSD_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <locale.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <dirent.h>
+#include <unistd.h>
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "conf.h"
+#include "sysfs.h"
+#include "scanner.h"
+#include "init.h"
+
+#define DEFAULT_CONFIG_FILE	ETCDIR "/sensors3.conf"
+#define ALT_CONFIG_FILE		ETCDIR "/sensors.conf"
+#define DEFAULT_CONFIG_DIR	ETCDIR "/sensors.d"
+
+/* Wrapper around sensors_yyparse(), which clears the locale so that
+   the decimal numbers are always parsed properly. */
+static int sensors_parse(void)
+{
+	int res;
+	char *locale;
+
+	/* Remember the current locale and clear it */
+	locale = setlocale(LC_ALL, NULL);
+	if (locale) {
+		locale = strdup(locale);
+		if (!locale)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		setlocale(LC_ALL, "C");
+	}
+
+	res = sensors_yyparse();
+
+	/* Restore the old locale */
+	if (locale) {
+		setlocale(LC_ALL, locale);
+		free(locale);
+	}
+
+	return res;
+}
+
+static void free_bus(sensors_bus *bus)
+{
+	free(bus->adapter);
+}
+
+static void free_config_busses(void)
+{
+	int i;
+
+	for (i = 0; i < sensors_config_busses_count; i++)
+		free_bus(&sensors_config_busses[i]);
+	free(sensors_config_busses);
+	sensors_config_busses = NULL;
+	sensors_config_busses_count = sensors_config_busses_max = 0;
+}
+
+static int parse_config(FILE *input, const char *name)
+{
+	int err;
+	char *name_copy;
+
+	if (name) {
+		/* Record configuration file name for error reporting */
+		name_copy = strdup(name);
+		if (!name_copy)
+			sensors_fatal_error(__func__, "Out of memory");
+		sensors_add_config_files(&name_copy);
+	} else
+		name_copy = NULL;
+
+	if (sensors_scanner_init(input, name_copy)) {
+		err = -SENSORS_ERR_PARSE;
+		goto exit_cleanup;
+	}
+	err = sensors_parse();
+	sensors_scanner_exit();
+	if (err) {
+		err = -SENSORS_ERR_PARSE;
+		goto exit_cleanup;
+	}
+
+	err = sensors_substitute_busses();
+
+exit_cleanup:
+	free_config_busses();
+	return err;
+}
+
+static int config_file_filter(const struct dirent *entry)
+{
+	return entry->d_name[0] != '.';		/* Skip hidden files */
+}
+
+static int add_config_from_dir(const char *dir)
+{
+	int count, res, i;
+	struct dirent **namelist;
+
+	count = scandir(dir, &namelist, config_file_filter, (int (*)(const struct dirent **, const struct dirent **))alphasort);
+	if (count < 0) {
+		/* Do not return an error if directory does not exist */
+		if (errno == ENOENT)
+			return 0;
+		
+		sensors_parse_error_wfn(strerror(errno), NULL, 0);
+		return -SENSORS_ERR_PARSE;
+	}
+
+	for (res = 0, i = 0; !res && i < count; i++) {
+		int len;
+		char path[PATH_MAX];
+		FILE *input;
+		struct stat st;
+
+		len = snprintf(path, sizeof(path), "%s/%s", dir,
+			       namelist[i]->d_name);
+		if (len < 0 || len >= (int)sizeof(path)) {
+			res = -SENSORS_ERR_PARSE;
+			continue;
+		}
+
+		/* Only accept regular files */
+		if (stat(path, &st) < 0 || !S_ISREG(st.st_mode))
+			continue;
+
+		input = fopen(path, "r");
+		if (input) {
+			res = parse_config(input, path);
+			fclose(input);
+		} else {
+			res = -SENSORS_ERR_PARSE;
+			sensors_parse_error_wfn(strerror(errno), path, 0);
+		}
+	}
+
+	/* Free memory allocated by scandir() */
+	for (i = 0; i < count; i++)
+		free(namelist[i]);
+	free(namelist);
+
+	return res;
+}
+
+int sensors_init(FILE *input)
+{
+	int res;
+
+	if (!sensors_init_sysfs())
+		return -SENSORS_ERR_KERNEL;
+	if ((res = sensors_read_sysfs_bus()) ||
+	    (res = sensors_read_sysfs_chips()))
+		goto exit_cleanup;
+
+	if (input) {
+		res = parse_config(input, NULL);
+		if (res)
+			goto exit_cleanup;
+	} else {
+		const char* name;
+
+		/* No configuration provided, use default */
+		input = fopen(name = DEFAULT_CONFIG_FILE, "r");
+		if (!input && errno == ENOENT)
+			input = fopen(name = ALT_CONFIG_FILE, "r");
+		if (input) {
+			res = parse_config(input, name);
+			fclose(input);
+			if (res)
+				goto exit_cleanup;
+
+		} else if (errno != ENOENT) {
+			sensors_parse_error_wfn(strerror(errno), name, 0);
+			res = -SENSORS_ERR_PARSE;
+			goto exit_cleanup;
+		}
+
+		/* Also check for files in default directory */
+		res = add_config_from_dir(DEFAULT_CONFIG_DIR);
+		if (res)
+			goto exit_cleanup;
+	}
+
+	return 0;
+
+exit_cleanup:
+	sensors_cleanup();
+	return res;
+}
+
+static void free_chip_name(sensors_chip_name *name)
+{
+	free(name->prefix);
+	free(name->path);
+}
+
+static void free_chip_features(sensors_chip_features *features)
+{
+	int i;
+
+	for (i = 0; i < features->subfeature_count; i++)
+		free(features->subfeature[i].name);
+	free(features->subfeature);
+	for (i = 0; i < features->feature_count; i++)
+		free(features->feature[i].name);
+	free(features->feature);
+}
+
+static void free_label(sensors_label *label)
+{
+	free(label->name);
+	free(label->value);
+}
+
+void sensors_free_expr(sensors_expr *expr)
+{
+	if (expr->kind == sensors_kind_var)
+		free(expr->data.var);
+	else if (expr->kind == sensors_kind_sub) {
+		if (expr->data.subexpr.sub1)
+			sensors_free_expr(expr->data.subexpr.sub1);
+		if (expr->data.subexpr.sub2)
+			sensors_free_expr(expr->data.subexpr.sub2);
+	}
+	free(expr);
+}
+
+static void free_set(sensors_set *set)
+{
+	free(set->name);
+	sensors_free_expr(set->value);
+}
+
+static void free_compute(sensors_compute *compute)
+{
+	free(compute->name);
+	sensors_free_expr(compute->from_proc);
+	sensors_free_expr(compute->to_proc);
+}
+
+static void free_ignore(sensors_ignore *ignore)
+{
+	free(ignore->name);
+}
+
+static void free_chip(sensors_chip *chip)
+{
+	int i;
+
+	for (i = 0; i < chip->chips.fits_count; i++)
+		free_chip_name(&chip->chips.fits[i]);
+	free(chip->chips.fits);
+	chip->chips.fits_count = chip->chips.fits_max = 0;
+
+	for (i = 0; i < chip->labels_count; i++)
+		free_label(&chip->labels[i]);
+	free(chip->labels);
+	chip->labels_count = chip->labels_max = 0;
+
+	for (i = 0; i < chip->sets_count; i++)
+		free_set(&chip->sets[i]);
+	free(chip->sets);
+	chip->sets_count = chip->sets_max = 0;
+
+	for (i = 0; i < chip->computes_count; i++)
+		free_compute(&chip->computes[i]);
+	free(chip->computes);
+	chip->computes_count = chip->computes_max = 0;
+
+	for (i = 0; i < chip->ignores_count; i++)
+		free_ignore(&chip->ignores[i]);
+	free(chip->ignores);
+	chip->ignores_count = chip->ignores_max = 0;
+}
+
+void sensors_cleanup(void)
+{
+	int i;
+
+	for (i = 0; i < sensors_proc_chips_count; i++) {
+		free_chip_name(&sensors_proc_chips[i].chip);
+		free_chip_features(&sensors_proc_chips[i]);
+	}
+	free(sensors_proc_chips);
+	sensors_proc_chips = NULL;
+	sensors_proc_chips_count = sensors_proc_chips_max = 0;
+
+	for (i = 0; i < sensors_config_chips_count; i++)
+		free_chip(&sensors_config_chips[i]);
+	free(sensors_config_chips);
+	sensors_config_chips = NULL;
+	sensors_config_chips_count = sensors_config_chips_max = 0;
+	sensors_config_chips_subst = 0;
+
+	for (i = 0; i < sensors_proc_bus_count; i++)
+		free_bus(&sensors_proc_bus[i]);
+	free(sensors_proc_bus);
+	sensors_proc_bus = NULL;
+	sensors_proc_bus_count = sensors_proc_bus_max = 0;
+
+	for (i = 0; i < sensors_config_files_count; i++)
+		free(sensors_config_files[i]);
+	free(sensors_config_files);
+	sensors_config_files = NULL;
+	sensors_config_files_count = sensors_config_files_max = 0;
+}
diff --git a/tools/gator/daemon/libsensors/init.h b/tools/gator/daemon/libsensors/init.h
new file mode 100644
index 000000000000..47006a62db63
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.h
@@ -0,0 +1,28 @@
+/*
+    init.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (C) 2007  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_INIT_H
+#define LIB_SENSORS_INIT_H
+
+#include "data.h"
+
+void sensors_free_expr(sensors_expr *expr);
+
+#endif /* def LIB_SENSORS_INIT_H */
diff --git a/tools/gator/daemon/libsensors/scanner.h b/tools/gator/daemon/libsensors/scanner.h
new file mode 100644
index 000000000000..4c415167de5c
--- /dev/null
+++ b/tools/gator/daemon/libsensors/scanner.h
@@ -0,0 +1,32 @@
+/*
+    scanner.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 2006 Mark M. Hoffman <mhoffman@lightlink.com>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to fix input defined but not used warning from conf-lex.c. ***/
+
+#ifndef LIB_SENSORS_SCANNER_H
+#define LIB_SENSORS_SCANNER_H
+
+int sensors_scanner_init(FILE *input, const char *filename);
+void sensors_scanner_exit(void);
+
+#define YY_NO_INPUT
+
+#endif
+
diff --git a/tools/gator/daemon/libsensors/sensors.h b/tools/gator/daemon/libsensors/sensors.h
new file mode 100644
index 000000000000..7874d028dc82
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sensors.h
@@ -0,0 +1,311 @@
+/*
+    sensors.h - Part of libsensors, a Linux library for reading sensor data.
+    Copyright (c) 1998, 1999  Frodo Looijaard <frodol@dds.nl>
+    Copyright (C) 2007, 2010  Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to read non-scaled values. ***/
+
+#ifndef LIB_SENSORS_SENSORS_H
+#define LIB_SENSORS_SENSORS_H
+
+#include <stdio.h>
+#include <limits.h>
+
+/* Publicly accessible library functions */
+
+/* libsensors API version define, first digit is the major version (changed
+   when the API + ABI breaks), the third digit is incremented to track small
+   API additions like new flags / enum values. The second digit is for tracking
+   larger additions like new methods. */
+#define SENSORS_API_VERSION		0x432
+
+#define SENSORS_CHIP_NAME_PREFIX_ANY	NULL
+#define SENSORS_CHIP_NAME_ADDR_ANY	(-1)
+
+#define SENSORS_BUS_TYPE_ANY		(-1)
+#define SENSORS_BUS_TYPE_I2C		0
+#define SENSORS_BUS_TYPE_ISA		1
+#define SENSORS_BUS_TYPE_PCI		2
+#define SENSORS_BUS_TYPE_SPI		3
+#define SENSORS_BUS_TYPE_VIRTUAL	4
+#define SENSORS_BUS_TYPE_ACPI		5
+#define SENSORS_BUS_TYPE_HID		6
+#define SENSORS_BUS_NR_ANY		(-1)
+#define SENSORS_BUS_NR_IGNORE		(-2)
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+extern const char *libsensors_version;
+
+extern int sensors_sysfs_no_scaling;
+
+typedef struct sensors_bus_id {
+	short type;
+	short nr;
+} sensors_bus_id;
+
+/* A chip name is encoded in this structure */
+typedef struct sensors_chip_name {
+	char *prefix;
+	sensors_bus_id bus;
+	int addr;
+	char *path;
+} sensors_chip_name;
+
+/* Load the configuration file and the detected chips list. If this
+   returns a value unequal to zero, you are in trouble; you can not
+   assume anything will be initialized properly. If you want to
+   reload the configuration file, call sensors_cleanup() below before
+   calling sensors_init() again. */
+int sensors_init(FILE *input);
+
+/* Clean-up function: You can't access anything after
+   this, until the next sensors_init() call! */
+void sensors_cleanup(void);
+
+/* Parse a chip name to the internal representation. Return 0 on success, <0
+   on error. */
+int sensors_parse_chip_name(const char *orig_name, sensors_chip_name *res);
+
+/* Free memory allocated for the internal representation of a chip name. */
+void sensors_free_chip_name(sensors_chip_name *chip);
+
+/* Print a chip name from its internal representation. Note that chip should
+   not contain wildcard values! Return the number of characters printed on
+   success (same as snprintf), <0 on error. */
+int sensors_snprintf_chip_name(char *str, size_t size,
+			       const sensors_chip_name *chip);
+
+/* This function returns the adapter name of a bus,
+   as used within the sensors_chip_name structure. If it could not be found,
+   it returns NULL */
+const char *sensors_get_adapter_name(const sensors_bus_id *bus);
+
+typedef struct sensors_feature sensors_feature;
+
+/* Look up the label for a given feature. Note that chip should not
+   contain wildcard values! The returned string is newly allocated (free it
+   yourself). On failure, NULL is returned.
+   If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+			const sensors_feature *feature);
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure.  */
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+		      double *value);
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+   contain wildcard values! This function will return 0 on success, and <0
+   on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+		      double value);
+
+/* Execute all set statements for this particular chip. The chip may contain
+   wildcards!  This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name);
+
+/* This function returns all detected chips that match a given chip name,
+   one by one. If no chip name is provided, all detected chips are returned.
+   To start at the beginning of the list, use 0 for nr; NULL is returned if
+   we are at the end of the list. Do not try to change these chip names, as
+   they point to internal structures! */
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+						    *match, int *nr);
+
+/* These defines are used in the flags field of sensors_subfeature */
+#define SENSORS_MODE_R			1
+#define SENSORS_MODE_W			2
+#define SENSORS_COMPUTE_MAPPING		4
+
+typedef enum sensors_feature_type {
+	SENSORS_FEATURE_IN		= 0x00,
+	SENSORS_FEATURE_FAN		= 0x01,
+	SENSORS_FEATURE_TEMP		= 0x02,
+	SENSORS_FEATURE_POWER		= 0x03,
+	SENSORS_FEATURE_ENERGY		= 0x04,
+	SENSORS_FEATURE_CURR		= 0x05,
+	SENSORS_FEATURE_HUMIDITY	= 0x06,
+	SENSORS_FEATURE_MAX_MAIN,
+	SENSORS_FEATURE_VID		= 0x10,
+	SENSORS_FEATURE_INTRUSION	= 0x11,
+	SENSORS_FEATURE_MAX_OTHER,
+	SENSORS_FEATURE_BEEP_ENABLE	= 0x18,
+	SENSORS_FEATURE_UNKNOWN		= INT_MAX,
+} sensors_feature_type;
+
+/* All the sensor types (in, fan, temp, vid) are a multiple of 0x100 apart,
+   and sensor subfeatures which have no compute mapping have bit 7 set. */
+typedef enum sensors_subfeature_type {
+	SENSORS_SUBFEATURE_IN_INPUT = SENSORS_FEATURE_IN << 8,
+	SENSORS_SUBFEATURE_IN_MIN,
+	SENSORS_SUBFEATURE_IN_MAX,
+	SENSORS_SUBFEATURE_IN_LCRIT,
+	SENSORS_SUBFEATURE_IN_CRIT,
+	SENSORS_SUBFEATURE_IN_AVERAGE,
+	SENSORS_SUBFEATURE_IN_LOWEST,
+	SENSORS_SUBFEATURE_IN_HIGHEST,
+	SENSORS_SUBFEATURE_IN_ALARM = (SENSORS_FEATURE_IN << 8) | 0x80,
+	SENSORS_SUBFEATURE_IN_MIN_ALARM,
+	SENSORS_SUBFEATURE_IN_MAX_ALARM,
+	SENSORS_SUBFEATURE_IN_BEEP,
+	SENSORS_SUBFEATURE_IN_LCRIT_ALARM,
+	SENSORS_SUBFEATURE_IN_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_FAN_INPUT = SENSORS_FEATURE_FAN << 8,
+	SENSORS_SUBFEATURE_FAN_MIN,
+	SENSORS_SUBFEATURE_FAN_MAX,
+	SENSORS_SUBFEATURE_FAN_ALARM = (SENSORS_FEATURE_FAN << 8) | 0x80,
+	SENSORS_SUBFEATURE_FAN_FAULT,
+	SENSORS_SUBFEATURE_FAN_DIV,
+	SENSORS_SUBFEATURE_FAN_BEEP,
+	SENSORS_SUBFEATURE_FAN_PULSES,
+	SENSORS_SUBFEATURE_FAN_MIN_ALARM,
+	SENSORS_SUBFEATURE_FAN_MAX_ALARM,
+
+	SENSORS_SUBFEATURE_TEMP_INPUT = SENSORS_FEATURE_TEMP << 8,
+	SENSORS_SUBFEATURE_TEMP_MAX,
+	SENSORS_SUBFEATURE_TEMP_MAX_HYST,
+	SENSORS_SUBFEATURE_TEMP_MIN,
+	SENSORS_SUBFEATURE_TEMP_CRIT,
+	SENSORS_SUBFEATURE_TEMP_CRIT_HYST,
+	SENSORS_SUBFEATURE_TEMP_LCRIT,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST,
+	SENSORS_SUBFEATURE_TEMP_LOWEST,
+	SENSORS_SUBFEATURE_TEMP_HIGHEST,
+	SENSORS_SUBFEATURE_TEMP_ALARM = (SENSORS_FEATURE_TEMP << 8) | 0x80,
+	SENSORS_SUBFEATURE_TEMP_MAX_ALARM,
+	SENSORS_SUBFEATURE_TEMP_MIN_ALARM,
+	SENSORS_SUBFEATURE_TEMP_CRIT_ALARM,
+	SENSORS_SUBFEATURE_TEMP_FAULT,
+	SENSORS_SUBFEATURE_TEMP_TYPE,
+	SENSORS_SUBFEATURE_TEMP_OFFSET,
+	SENSORS_SUBFEATURE_TEMP_BEEP,
+	SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM,
+	SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM,
+
+	SENSORS_SUBFEATURE_POWER_AVERAGE = SENSORS_FEATURE_POWER << 8,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST,
+	SENSORS_SUBFEATURE_POWER_INPUT,
+	SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST,
+	SENSORS_SUBFEATURE_POWER_INPUT_LOWEST,
+	SENSORS_SUBFEATURE_POWER_CAP,
+	SENSORS_SUBFEATURE_POWER_CAP_HYST,
+	SENSORS_SUBFEATURE_POWER_MAX,
+	SENSORS_SUBFEATURE_POWER_CRIT,
+	SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL = (SENSORS_FEATURE_POWER << 8) | 0x80,
+	SENSORS_SUBFEATURE_POWER_ALARM,
+	SENSORS_SUBFEATURE_POWER_CAP_ALARM,
+	SENSORS_SUBFEATURE_POWER_MAX_ALARM,
+	SENSORS_SUBFEATURE_POWER_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_ENERGY_INPUT = SENSORS_FEATURE_ENERGY << 8,
+
+	SENSORS_SUBFEATURE_CURR_INPUT = SENSORS_FEATURE_CURR << 8,
+	SENSORS_SUBFEATURE_CURR_MIN,
+	SENSORS_SUBFEATURE_CURR_MAX,
+	SENSORS_SUBFEATURE_CURR_LCRIT,
+	SENSORS_SUBFEATURE_CURR_CRIT,
+	SENSORS_SUBFEATURE_CURR_AVERAGE,
+	SENSORS_SUBFEATURE_CURR_LOWEST,
+	SENSORS_SUBFEATURE_CURR_HIGHEST,
+	SENSORS_SUBFEATURE_CURR_ALARM = (SENSORS_FEATURE_CURR << 8) | 0x80,
+	SENSORS_SUBFEATURE_CURR_MIN_ALARM,
+	SENSORS_SUBFEATURE_CURR_MAX_ALARM,
+	SENSORS_SUBFEATURE_CURR_BEEP,
+	SENSORS_SUBFEATURE_CURR_LCRIT_ALARM,
+	SENSORS_SUBFEATURE_CURR_CRIT_ALARM,
+
+	SENSORS_SUBFEATURE_HUMIDITY_INPUT = SENSORS_FEATURE_HUMIDITY << 8,
+
+	SENSORS_SUBFEATURE_VID = SENSORS_FEATURE_VID << 8,
+
+	SENSORS_SUBFEATURE_INTRUSION_ALARM = SENSORS_FEATURE_INTRUSION << 8,
+	SENSORS_SUBFEATURE_INTRUSION_BEEP,
+
+	SENSORS_SUBFEATURE_BEEP_ENABLE = SENSORS_FEATURE_BEEP_ENABLE << 8,
+
+	SENSORS_SUBFEATURE_UNKNOWN = INT_MAX,
+} sensors_subfeature_type;
+
+/* Data about a single chip feature (or category leader) */
+struct sensors_feature {
+	char *name;
+	int number;
+	sensors_feature_type type;
+	/* Members below are for libsensors internal use only */
+	int first_subfeature;
+	int padding1;
+};
+
+/* Data about a single chip subfeature:
+   name is the string name used to refer to this subfeature (in config files)
+   number is the internal subfeature number, used in many functions to refer
+     to this subfeature
+   type is the subfeature type
+   mapping is the number of a main feature this subfeature belongs to
+     (for example subfeatures fan1_input, fan1_min, fan1_div and fan1_alarm
+      are mapped to main feature fan1)
+   flags is a bitfield, its value is a combination of SENSORS_MODE_R (readable),
+     SENSORS_MODE_W (writable) and SENSORS_COMPUTE_MAPPING (affected by the
+     computation rules of the main feature) */
+typedef struct sensors_subfeature {
+	char *name;
+	int number;
+	sensors_subfeature_type type;
+	int mapping;
+	unsigned int flags;
+} sensors_subfeature;
+
+/* This returns all main features of a specific chip. nr is an internally
+   used variable. Set it to zero to start at the begin of the list. If no
+   more features are found NULL is returned.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr);
+
+/* This returns all subfeatures of a given main feature. nr is an internally
+   used variable. Set it to zero to start at the begin of the list. If no
+   more features are found NULL is returned.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+			    const sensors_feature *feature, int *nr);
+
+/* This returns the subfeature of the given type for a given main feature,
+   if it exists, NULL otherwise.
+   Do not try to change the returned structure; you will corrupt internal
+   data structures. */
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+		       const sensors_feature *feature,
+		       sensors_subfeature_type type);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/sysfs.c b/tools/gator/daemon/libsensors/sysfs.c
new file mode 100644
index 000000000000..2b494c9975b4
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.c
@@ -0,0 +1,926 @@
+/*
+    sysfs.c - Part of libsensors, a library for reading Linux sensor data
+    Copyright (c) 2005 Mark M. Hoffman <mhoffman@lightlink.com>
+    Copyright (C) 2007-2010 Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to improve performance by substituting calls to fread() with calls to read() and to read non-scaled values. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/vfs.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+#include <errno.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "general.h"
+#include "sysfs.h"
+
+
+/****************************************************************************/
+
+#define ATTR_MAX	128
+#define SYSFS_MAGIC	0x62656572
+
+int sensors_sysfs_no_scaling;
+
+/*
+ * Read an attribute from sysfs
+ * Returns a pointer to a freshly allocated string; free it yourself.
+ * If the file doesn't exist or can't be read, NULL is returned.
+ */
+static char *sysfs_read_attr(const char *device, const char *attr)
+{
+	char path[NAME_MAX];
+	char buf[ATTR_MAX], *p;
+	FILE *f;
+
+	snprintf(path, NAME_MAX, "%s/%s", device, attr);
+
+	if (!(f = fopen(path, "r")))
+		return NULL;
+	p = fgets(buf, ATTR_MAX, f);
+	fclose(f);
+	if (!p)
+		return NULL;
+
+	/* Last byte is a '\n'; chop that off */
+	p = strndup(buf, strlen(buf) - 1);
+	if (!p)
+		sensors_fatal_error(__func__, "Out of memory");
+	return p;
+}
+
+/*
+ * Call an arbitrary function for each class device of the given class
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_classdev(const char *class_name,
+				   int (*func)(const char *, const char *))
+{
+	char path[NAME_MAX];
+	int path_off, ret;
+	DIR *dir;
+	struct dirent *ent;
+
+	path_off = snprintf(path, NAME_MAX, "%s/class/%s",
+			    sensors_sysfs_mount, class_name);
+	if (!(dir = opendir(path)))
+		return errno;
+
+	ret = 0;
+	while (!ret && (ent = readdir(dir))) {
+		if (ent->d_name[0] == '.')	/* skip hidden entries */
+			continue;
+
+		snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+			 ent->d_name);
+		ret = func(path, ent->d_name);
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+/*
+ * Call an arbitrary function for each device of the given bus type
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_busdev(const char *bus_type,
+				 int (*func)(const char *, const char *))
+{
+	char path[NAME_MAX];
+	int path_off, ret;
+	DIR *dir;
+	struct dirent *ent;
+
+	path_off = snprintf(path, NAME_MAX, "%s/bus/%s/devices",
+			    sensors_sysfs_mount, bus_type);
+	if (!(dir = opendir(path)))
+		return errno;
+
+	ret = 0;
+	while (!ret && (ent = readdir(dir))) {
+		if (ent->d_name[0] == '.')	/* skip hidden entries */
+			continue;
+
+		snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+			 ent->d_name);
+		ret = func(path, ent->d_name);
+	}
+
+	closedir(dir);
+	return ret;
+}
+
+/****************************************************************************/
+
+char sensors_sysfs_mount[NAME_MAX];
+
+#define MAX_MAIN_SENSOR_TYPES	(SENSORS_FEATURE_MAX_MAIN - SENSORS_FEATURE_IN)
+#define MAX_OTHER_SENSOR_TYPES	(SENSORS_FEATURE_MAX_OTHER - SENSORS_FEATURE_VID)
+#define MAX_SENSORS_PER_TYPE	24
+/* max_subfeatures is now computed dynamically */
+#define FEATURE_SIZE		(max_subfeatures * 2)
+#define FEATURE_TYPE_SIZE	(MAX_SENSORS_PER_TYPE * FEATURE_SIZE)
+
+/*
+ * Room for all 7 main types (in, fan, temp, power, energy, current, humidity)
+ * and 2 other types (VID, intrusion) with all their subfeatures + misc features
+ */
+#define SUB_OFFSET_OTHER	(MAX_MAIN_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define SUB_OFFSET_MISC		(SUB_OFFSET_OTHER + \
+				 MAX_OTHER_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define ALL_POSSIBLE_SUBFEATURES	(SUB_OFFSET_MISC + 1)
+
+static
+int get_type_scaling(sensors_subfeature_type type)
+{
+	/* Multipliers for subfeatures */
+	switch (type & 0xFF80) {
+	case SENSORS_SUBFEATURE_IN_INPUT:
+	case SENSORS_SUBFEATURE_TEMP_INPUT:
+	case SENSORS_SUBFEATURE_CURR_INPUT:
+	case SENSORS_SUBFEATURE_HUMIDITY_INPUT:
+		return 1000;
+	case SENSORS_SUBFEATURE_FAN_INPUT:
+		return 1;
+	case SENSORS_SUBFEATURE_POWER_AVERAGE:
+	case SENSORS_SUBFEATURE_ENERGY_INPUT:
+		return 1000000;
+	}
+
+	/* Multipliers for second class subfeatures
+	   that need their own multiplier */
+	switch (type) {
+	case SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL:
+	case SENSORS_SUBFEATURE_VID:
+	case SENSORS_SUBFEATURE_TEMP_OFFSET:
+		return 1000;
+	default:
+		return 1;
+	}
+}
+
+static
+char *get_feature_name(sensors_feature_type ftype, char *sfname)
+{
+	char *name, *underscore;
+
+	switch (ftype) {
+	case SENSORS_FEATURE_IN:
+	case SENSORS_FEATURE_FAN:
+	case SENSORS_FEATURE_TEMP:
+	case SENSORS_FEATURE_POWER:
+	case SENSORS_FEATURE_ENERGY:
+	case SENSORS_FEATURE_CURR:
+	case SENSORS_FEATURE_HUMIDITY:
+	case SENSORS_FEATURE_INTRUSION:
+		underscore = strchr(sfname, '_');
+		name = strndup(sfname, underscore - sfname);
+		if (!name)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		break;
+	default:
+		name = strdup(sfname);
+		if (!name)
+			sensors_fatal_error(__func__, "Out of memory");
+	}
+
+	return name;
+}
+
+/* Static mappings for use by sensors_subfeature_get_type() */
+struct subfeature_type_match
+{
+	const char *name;
+	sensors_subfeature_type type;
+};
+
+struct feature_type_match
+{
+	const char *name;
+	const struct subfeature_type_match *submatches;
+};
+
+static const struct subfeature_type_match temp_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_TEMP_INPUT },
+	{ "max", SENSORS_SUBFEATURE_TEMP_MAX },
+	{ "max_hyst", SENSORS_SUBFEATURE_TEMP_MAX_HYST },
+	{ "min", SENSORS_SUBFEATURE_TEMP_MIN },
+	{ "crit", SENSORS_SUBFEATURE_TEMP_CRIT },
+	{ "crit_hyst", SENSORS_SUBFEATURE_TEMP_CRIT_HYST },
+	{ "lcrit", SENSORS_SUBFEATURE_TEMP_LCRIT },
+	{ "emergency", SENSORS_SUBFEATURE_TEMP_EMERGENCY },
+	{ "emergency_hyst", SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST },
+	{ "lowest", SENSORS_SUBFEATURE_TEMP_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_TEMP_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_TEMP_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_TEMP_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_TEMP_MAX_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_TEMP_CRIT_ALARM },
+	{ "emergency_alarm", SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM },
+	{ "fault", SENSORS_SUBFEATURE_TEMP_FAULT },
+	{ "type", SENSORS_SUBFEATURE_TEMP_TYPE },
+	{ "offset", SENSORS_SUBFEATURE_TEMP_OFFSET },
+	{ "beep", SENSORS_SUBFEATURE_TEMP_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match in_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_IN_INPUT },
+	{ "min", SENSORS_SUBFEATURE_IN_MIN },
+	{ "max", SENSORS_SUBFEATURE_IN_MAX },
+	{ "lcrit", SENSORS_SUBFEATURE_IN_LCRIT },
+	{ "crit", SENSORS_SUBFEATURE_IN_CRIT },
+	{ "average", SENSORS_SUBFEATURE_IN_AVERAGE },
+	{ "lowest", SENSORS_SUBFEATURE_IN_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_IN_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_IN_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_IN_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_IN_MAX_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_IN_LCRIT_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_IN_CRIT_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_IN_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match fan_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_FAN_INPUT },
+	{ "min", SENSORS_SUBFEATURE_FAN_MIN },
+	{ "max", SENSORS_SUBFEATURE_FAN_MAX },
+	{ "div", SENSORS_SUBFEATURE_FAN_DIV },
+	{ "pulses", SENSORS_SUBFEATURE_FAN_PULSES },
+	{ "alarm", SENSORS_SUBFEATURE_FAN_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_FAN_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_FAN_MAX_ALARM },
+	{ "fault", SENSORS_SUBFEATURE_FAN_FAULT },
+	{ "beep", SENSORS_SUBFEATURE_FAN_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match power_matches[] = {
+	{ "average", SENSORS_SUBFEATURE_POWER_AVERAGE },
+	{ "average_highest", SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST },
+	{ "average_lowest", SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST },
+	{ "input", SENSORS_SUBFEATURE_POWER_INPUT },
+	{ "input_highest", SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST },
+	{ "input_lowest", SENSORS_SUBFEATURE_POWER_INPUT_LOWEST },
+	{ "cap", SENSORS_SUBFEATURE_POWER_CAP },
+	{ "cap_hyst", SENSORS_SUBFEATURE_POWER_CAP_HYST },
+	{ "cap_alarm", SENSORS_SUBFEATURE_POWER_CAP_ALARM },
+	{ "alarm", SENSORS_SUBFEATURE_POWER_ALARM },
+	{ "max", SENSORS_SUBFEATURE_POWER_MAX },
+	{ "max_alarm", SENSORS_SUBFEATURE_POWER_MAX_ALARM },
+	{ "crit", SENSORS_SUBFEATURE_POWER_CRIT },
+	{ "crit_alarm", SENSORS_SUBFEATURE_POWER_CRIT_ALARM },
+	{ "average_interval", SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match energy_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_ENERGY_INPUT },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match curr_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_CURR_INPUT },
+	{ "min", SENSORS_SUBFEATURE_CURR_MIN },
+	{ "max", SENSORS_SUBFEATURE_CURR_MAX },
+	{ "lcrit", SENSORS_SUBFEATURE_CURR_LCRIT },
+	{ "crit", SENSORS_SUBFEATURE_CURR_CRIT },
+	{ "average", SENSORS_SUBFEATURE_CURR_AVERAGE },
+	{ "lowest", SENSORS_SUBFEATURE_CURR_LOWEST },
+	{ "highest", SENSORS_SUBFEATURE_CURR_HIGHEST },
+	{ "alarm", SENSORS_SUBFEATURE_CURR_ALARM },
+	{ "min_alarm", SENSORS_SUBFEATURE_CURR_MIN_ALARM },
+	{ "max_alarm", SENSORS_SUBFEATURE_CURR_MAX_ALARM },
+	{ "lcrit_alarm", SENSORS_SUBFEATURE_CURR_LCRIT_ALARM },
+	{ "crit_alarm", SENSORS_SUBFEATURE_CURR_CRIT_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_CURR_BEEP },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match humidity_matches[] = {
+	{ "input", SENSORS_SUBFEATURE_HUMIDITY_INPUT },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match cpu_matches[] = {
+	{ "vid", SENSORS_SUBFEATURE_VID },
+	{ NULL, 0 }
+};
+
+static const struct subfeature_type_match intrusion_matches[] = {
+	{ "alarm", SENSORS_SUBFEATURE_INTRUSION_ALARM },
+	{ "beep", SENSORS_SUBFEATURE_INTRUSION_BEEP },
+	{ NULL, 0 }
+};
+static struct feature_type_match matches[] = {
+	{ "temp%d%c", temp_matches },
+	{ "in%d%c", in_matches },
+	{ "fan%d%c", fan_matches },
+	{ "cpu%d%c", cpu_matches },
+	{ "power%d%c", power_matches },
+	{ "curr%d%c", curr_matches },
+	{ "energy%d%c", energy_matches },
+	{ "intrusion%d%c", intrusion_matches },
+	{ "humidity%d%c", humidity_matches },
+};
+
+/* Return the subfeature type and channel number based on the subfeature
+   name */
+static
+sensors_subfeature_type sensors_subfeature_get_type(const char *name, int *nr)
+{
+	char c;
+	int i, count;
+	const struct subfeature_type_match *submatches;
+
+	/* Special case */
+	if (!strcmp(name, "beep_enable")) {
+		*nr = 0;
+		return SENSORS_SUBFEATURE_BEEP_ENABLE;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(matches); i++)
+		if ((count = sscanf(name, matches[i].name, nr, &c)))
+			break;
+
+	if (i == ARRAY_SIZE(matches) || count != 2 || c != '_')
+		return SENSORS_SUBFEATURE_UNKNOWN;  /* no match */
+
+	submatches = matches[i].submatches;
+	name = strchr(name + 3, '_') + 1;
+	for (i = 0; submatches[i].name != NULL; i++)
+		if (!strcmp(name, submatches[i].name))
+			return submatches[i].type;
+
+	return SENSORS_SUBFEATURE_UNKNOWN;
+}
+
+static int sensors_compute_max(void)
+{
+	int i, j, max, offset;
+	const struct subfeature_type_match *submatches;
+	sensors_feature_type ftype;
+
+	max = 0;
+	for (i = 0; i < ARRAY_SIZE(matches); i++) {
+		submatches = matches[i].submatches;
+		for (j = 0; submatches[j].name != NULL; j++) {
+			ftype = submatches[j].type >> 8;
+
+			if (ftype < SENSORS_FEATURE_VID) {
+				offset = submatches[j].type & 0x7F;
+				if (offset >= max)
+					max = offset + 1;
+			} else {
+				offset = submatches[j].type & 0xFF;
+				if (offset >= max * 2)
+					max = ((offset + 1) + 1) / 2;
+			}
+		}
+	}
+
+	return max;
+}
+
+static int sensors_get_attr_mode(const char *device, const char *attr)
+{
+	char path[NAME_MAX];
+	struct stat st;
+	int mode = 0;
+
+	snprintf(path, NAME_MAX, "%s/%s", device, attr);
+	if (!stat(path, &st)) {
+		if (st.st_mode & S_IRUSR)
+			mode |= SENSORS_MODE_R;
+		if (st.st_mode & S_IWUSR)
+			mode |= SENSORS_MODE_W;
+	}
+	return mode;
+}
+
+static int sensors_read_dynamic_chip(sensors_chip_features *chip,
+				     const char *dev_path)
+{
+	int i, fnum = 0, sfnum = 0, prev_slot;
+	static int max_subfeatures;
+	DIR *dir;
+	struct dirent *ent;
+	sensors_subfeature *all_subfeatures;
+	sensors_subfeature *dyn_subfeatures;
+	sensors_feature *dyn_features;
+	sensors_feature_type ftype;
+	sensors_subfeature_type sftype;
+
+	if (!(dir = opendir(dev_path)))
+		return -errno;
+
+	/* Dynamically figure out the max number of subfeatures */
+	if (!max_subfeatures)
+		max_subfeatures = sensors_compute_max();
+
+	/* We use a large sparse table at first to store all found
+	   subfeatures, so that we can store them sorted at type and index
+	   and then later create a dense sorted table. */
+	all_subfeatures = calloc(ALL_POSSIBLE_SUBFEATURES,
+				 sizeof(sensors_subfeature));
+	if (!all_subfeatures)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	while ((ent = readdir(dir))) {
+		char *name;
+		int nr;
+
+		/* Skip directories and symlinks */
+		if (ent->d_type != DT_REG)
+			continue;
+
+		name = ent->d_name;
+
+		sftype = sensors_subfeature_get_type(name, &nr);
+		if (sftype == SENSORS_SUBFEATURE_UNKNOWN)
+			continue;
+		ftype = sftype >> 8;
+
+		/* Adjust the channel number */
+		switch (ftype) {
+		case SENSORS_FEATURE_FAN:
+		case SENSORS_FEATURE_TEMP:
+		case SENSORS_FEATURE_POWER:
+		case SENSORS_FEATURE_ENERGY:
+		case SENSORS_FEATURE_CURR:
+		case SENSORS_FEATURE_HUMIDITY:
+			nr--;
+			break;
+		default:
+			break;
+		}
+
+		if (nr < 0 || nr >= MAX_SENSORS_PER_TYPE) {
+			/* More sensors of one type than MAX_SENSORS_PER_TYPE,
+			   we have to ignore it */
+#ifdef DEBUG
+			sensors_fatal_error(__func__,
+					    "Increase MAX_SENSORS_PER_TYPE!");
+#endif
+			continue;
+		}
+
+		/* "calculate" a place to store the subfeature in our sparse,
+		   sorted table */
+		switch (ftype) {
+		case SENSORS_FEATURE_VID:
+		case SENSORS_FEATURE_INTRUSION:
+			i = SUB_OFFSET_OTHER +
+			    (ftype - SENSORS_FEATURE_VID) * FEATURE_TYPE_SIZE +
+			    nr * FEATURE_SIZE + (sftype & 0xFF);
+			break;
+		case SENSORS_FEATURE_BEEP_ENABLE:
+			i = SUB_OFFSET_MISC +
+			    (ftype - SENSORS_FEATURE_BEEP_ENABLE);
+			break;
+		default:
+			i = ftype * FEATURE_TYPE_SIZE +
+			    nr * FEATURE_SIZE +
+			    ((sftype & 0x80) >> 7) * max_subfeatures +
+			    (sftype & 0x7F);
+		}
+
+		if (all_subfeatures[i].name) {
+#ifdef DEBUG
+			sensors_fatal_error(__func__, "Duplicate subfeature");
+#endif
+			continue;
+		}
+
+		/* fill in the subfeature members */
+		all_subfeatures[i].type = sftype;
+		all_subfeatures[i].name = strdup(name);
+		if (!all_subfeatures[i].name)
+			sensors_fatal_error(__func__, "Out of memory");
+
+		/* Other and misc subfeatures are never scaled */
+		if (sftype < SENSORS_SUBFEATURE_VID && !(sftype & 0x80))
+			all_subfeatures[i].flags |= SENSORS_COMPUTE_MAPPING;
+		all_subfeatures[i].flags |= sensors_get_attr_mode(dev_path, name);
+
+		sfnum++;
+	}
+	closedir(dir);
+
+	if (!sfnum) { /* No subfeature */
+		chip->subfeature = NULL;
+		goto exit_free;
+	}
+
+	/* How many main features? */
+	prev_slot = -1;
+	for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+		if (!all_subfeatures[i].name)
+			continue;
+
+		if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+			fnum++;
+			prev_slot = i / FEATURE_SIZE;
+		}
+	}
+
+	dyn_subfeatures = calloc(sfnum, sizeof(sensors_subfeature));
+	dyn_features = calloc(fnum, sizeof(sensors_feature));
+	if (!dyn_subfeatures || !dyn_features)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	/* Copy from the sparse array to the compact array */
+	sfnum = 0;
+	fnum = -1;
+	prev_slot = -1;
+	for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+		if (!all_subfeatures[i].name)
+			continue;
+
+		/* New main feature? */
+		if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+			ftype = all_subfeatures[i].type >> 8;
+			fnum++;
+			prev_slot = i / FEATURE_SIZE;
+
+			dyn_features[fnum].name = get_feature_name(ftype,
+						all_subfeatures[i].name);
+			dyn_features[fnum].number = fnum;
+			dyn_features[fnum].first_subfeature = sfnum;
+			dyn_features[fnum].type = ftype;
+		}
+
+		dyn_subfeatures[sfnum] = all_subfeatures[i];
+		dyn_subfeatures[sfnum].number = sfnum;
+		/* Back to the feature */
+		dyn_subfeatures[sfnum].mapping = fnum;
+
+		sfnum++;
+	}
+
+	chip->subfeature = dyn_subfeatures;
+	chip->subfeature_count = sfnum;
+	chip->feature = dyn_features;
+	chip->feature_count = ++fnum;
+
+exit_free:
+	free(all_subfeatures);
+	return 0;
+}
+
+/* returns !0 if sysfs filesystem was found, 0 otherwise */
+int sensors_init_sysfs(void)
+{
+	struct statfs statfsbuf;
+
+	snprintf(sensors_sysfs_mount, NAME_MAX, "%s", "/sys");
+	if (statfs(sensors_sysfs_mount, &statfsbuf) < 0
+	 || statfsbuf.f_type != SYSFS_MAGIC)
+		return 0;
+
+	return 1;
+}
+
+/* returns: number of devices added (0 or 1) if successful, <0 otherwise */
+static int sensors_read_one_sysfs_chip(const char *dev_path,
+				       const char *dev_name,
+				       const char *hwmon_path)
+{
+	int domain, bus, slot, fn, vendor, product, id;
+	int err = -SENSORS_ERR_KERNEL;
+	char *bus_attr;
+	char bus_path[NAME_MAX];
+	char linkpath[NAME_MAX];
+	char subsys_path[NAME_MAX], *subsys;
+	int sub_len;
+	sensors_chip_features entry;
+
+	/* ignore any device without name attribute */
+	if (!(entry.chip.prefix = sysfs_read_attr(hwmon_path, "name")))
+		return 0;
+
+	entry.chip.path = strdup(hwmon_path);
+	if (!entry.chip.path)
+		sensors_fatal_error(__func__, "Out of memory");
+
+	if (dev_path == NULL) {
+		/* Virtual device */
+		entry.chip.bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+		entry.chip.bus.nr = 0;
+		/* For now we assume that virtual devices are unique */
+		entry.chip.addr = 0;
+		goto done;
+	}
+
+	/* Find bus type */
+	snprintf(linkpath, NAME_MAX, "%s/subsystem", dev_path);
+	sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+	if (sub_len < 0 && errno == ENOENT) {
+		/* Fallback to "bus" link for kernels <= 2.6.17 */
+		snprintf(linkpath, NAME_MAX, "%s/bus", dev_path);
+		sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+	}
+	if (sub_len < 0) {
+		/* Older kernels (<= 2.6.11) have neither the subsystem
+		   symlink nor the bus symlink */
+		if (errno == ENOENT)
+			subsys = NULL;
+		else
+			goto exit_free;
+	} else {
+		subsys_path[sub_len] = '\0';
+		subsys = strrchr(subsys_path, '/') + 1;
+	}
+
+	if ((!subsys || !strcmp(subsys, "i2c")) &&
+	    sscanf(dev_name, "%hd-%x", &entry.chip.bus.nr,
+		   &entry.chip.addr) == 2) {
+		/* find out if legacy ISA or not */
+		if (entry.chip.bus.nr == 9191) {
+			entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+			entry.chip.bus.nr = 0;
+		} else {
+			entry.chip.bus.type = SENSORS_BUS_TYPE_I2C;
+			snprintf(bus_path, sizeof(bus_path),
+				"%s/class/i2c-adapter/i2c-%d/device",
+				sensors_sysfs_mount, entry.chip.bus.nr);
+
+			if ((bus_attr = sysfs_read_attr(bus_path, "name"))) {
+				if (!strncmp(bus_attr, "ISA ", 4)) {
+					entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+					entry.chip.bus.nr = 0;
+				}
+
+				free(bus_attr);
+			}
+		}
+	} else
+	if ((!subsys || !strcmp(subsys, "spi")) &&
+	    sscanf(dev_name, "spi%hd.%d", &entry.chip.bus.nr,
+		   &entry.chip.addr) == 2) {
+		/* SPI */
+		entry.chip.bus.type = SENSORS_BUS_TYPE_SPI;
+	} else
+	if ((!subsys || !strcmp(subsys, "pci")) &&
+	    sscanf(dev_name, "%x:%x:%x.%x", &domain, &bus, &slot, &fn) == 4) {
+		/* PCI */
+		entry.chip.addr = (domain << 16) + (bus << 8) + (slot << 3) + fn;
+		entry.chip.bus.type = SENSORS_BUS_TYPE_PCI;
+		entry.chip.bus.nr = 0;
+	} else
+	if ((!subsys || !strcmp(subsys, "platform") ||
+			!strcmp(subsys, "of_platform"))) {
+		/* must be new ISA (platform driver) */
+		if (sscanf(dev_name, "%*[a-z0-9_].%d", &entry.chip.addr) != 1)
+			entry.chip.addr = 0;
+		entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+		entry.chip.bus.nr = 0;
+	} else if (subsys && !strcmp(subsys, "acpi")) {
+		entry.chip.bus.type = SENSORS_BUS_TYPE_ACPI;
+		/* For now we assume that acpi devices are unique */
+		entry.chip.bus.nr = 0;
+		entry.chip.addr = 0;
+	} else
+	if (subsys && !strcmp(subsys, "hid") &&
+	    sscanf(dev_name, "%x:%x:%x.%x", &bus, &vendor, &product, &id) == 4) {
+		entry.chip.bus.type = SENSORS_BUS_TYPE_HID;
+		/* As of kernel 2.6.32, the hid device names don't look good */
+		entry.chip.bus.nr = bus;
+		entry.chip.addr = id;
+	} else {
+		/* Ignore unknown device */
+		err = 0;
+		goto exit_free;
+	}
+
+done:
+	if (sensors_read_dynamic_chip(&entry, hwmon_path) < 0)
+		goto exit_free;
+	if (!entry.subfeature) { /* No subfeature, discard chip */
+		err = 0;
+		goto exit_free;
+	}
+	sensors_add_proc_chips(&entry);
+
+	return 1;
+
+exit_free:
+	free(entry.chip.prefix);
+	free(entry.chip.path);
+	return err;
+}
+
+static int sensors_add_hwmon_device_compat(const char *path,
+					   const char *dev_name)
+{
+	int err;
+
+	err = sensors_read_one_sysfs_chip(path, dev_name, path);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_read_sysfs_chips_compat(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_busdev("i2c", sensors_add_hwmon_device_compat);
+	if (ret && ret != ENOENT)
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+static int sensors_add_hwmon_device(const char *path, const char *classdev)
+{
+	char linkpath[NAME_MAX];
+	char device[NAME_MAX], *device_p;
+	int dev_len, err;
+	(void)classdev; /* hide warning */
+
+	snprintf(linkpath, NAME_MAX, "%s/device", path);
+	dev_len = readlink(linkpath, device, NAME_MAX - 1);
+	if (dev_len < 0) {
+		/* No device link? Treat as virtual */
+		err = sensors_read_one_sysfs_chip(NULL, NULL, path);
+	} else {
+		device[dev_len] = '\0';
+		device_p = strrchr(device, '/') + 1;
+
+		/* The attributes we want might be those of the hwmon class
+		   device, or those of the device itself. */
+		err = sensors_read_one_sysfs_chip(linkpath, device_p, path);
+		if (err == 0)
+			err = sensors_read_one_sysfs_chip(linkpath, device_p,
+							  linkpath);
+	}
+	if (err < 0)
+		return err;
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_chips(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_classdev("hwmon", sensors_add_hwmon_device);
+	if (ret == ENOENT) {
+		/* compatibility function for kernel 2.6.n where n <= 13 */
+		return sensors_read_sysfs_chips_compat();
+	}
+
+	if (ret > 0)
+		ret = -SENSORS_ERR_KERNEL;
+	return ret;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_add_i2c_bus(const char *path, const char *classdev)
+{
+	sensors_bus entry;
+
+	if (sscanf(classdev, "i2c-%hd", &entry.bus.nr) != 1 ||
+	    entry.bus.nr == 9191) /* legacy ISA */
+		return 0;
+	entry.bus.type = SENSORS_BUS_TYPE_I2C;
+
+	/* Get the adapter name from the classdev "name" attribute
+	 * (Linux 2.6.20 and later). If it fails, fall back to
+	 * the device "name" attribute (for older kernels). */
+	entry.adapter = sysfs_read_attr(path, "name");
+	if (!entry.adapter)
+		entry.adapter = sysfs_read_attr(path, "device/name");
+	if (entry.adapter)
+		sensors_add_proc_bus(&entry);
+
+	return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_bus(void)
+{
+	int ret;
+
+	ret = sysfs_foreach_classdev("i2c-adapter", sensors_add_i2c_bus);
+	if (ret == ENOENT)
+		ret = sysfs_foreach_busdev("i2c", sensors_add_i2c_bus);
+	if (ret && ret != ENOENT)
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+			    const sensors_subfeature *subfeature,
+			    double *value)
+{
+	char n[NAME_MAX];
+	int f;
+
+	snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+	if ((f = open(n, O_RDONLY)) != -1) {
+		int res, err = 0;
+		char buf[512];
+		int count;
+
+		errno = 0;
+		if ((count = read(f, buf, sizeof(buf) - 1)) == -1) {
+			if (errno == EIO)
+				err = -SENSORS_ERR_IO;
+			else 
+				err = -SENSORS_ERR_ACCESS_R;
+		} else {
+			buf[count] = '\0';
+			errno = 0;
+			res = sscanf(buf, "%lf", value);
+			if (res == EOF && errno == EIO)
+				err = -SENSORS_ERR_IO;
+			else if (res != 1)
+				err = -SENSORS_ERR_ACCESS_R;
+		}
+		res = close(f);
+		if (err)
+			return err;
+
+		if (res != 0) {
+			if (errno == EIO)
+				return -SENSORS_ERR_IO;
+			else 
+				return -SENSORS_ERR_ACCESS_R;
+		}
+		if (!sensors_sysfs_no_scaling)
+			*value /= get_type_scaling(subfeature->type);
+	} else
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
+
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+			     const sensors_subfeature *subfeature,
+			     double value)
+{
+	char n[NAME_MAX];
+	FILE *f;
+
+	snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+	if ((f = fopen(n, "w"))) {
+		int res, err = 0;
+
+		if (!sensors_sysfs_no_scaling)
+			value *= get_type_scaling(subfeature->type);
+		res = fprintf(f, "%d", (int) value);
+		if (res == -EIO)
+			err = -SENSORS_ERR_IO;
+		else if (res < 0)
+			err = -SENSORS_ERR_ACCESS_W;
+		res = fclose(f);
+		if (err)
+			return err;
+
+		if (res == EOF) {
+			if (errno == EIO)
+				return -SENSORS_ERR_IO;
+			else 
+				return -SENSORS_ERR_ACCESS_W;
+		}
+	} else
+		return -SENSORS_ERR_KERNEL;
+
+	return 0;
+}
diff --git a/tools/gator/daemon/libsensors/sysfs.h b/tools/gator/daemon/libsensors/sysfs.h
new file mode 100644
index 000000000000..38584afd028e
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.h
@@ -0,0 +1,43 @@
+/*
+    sysfs.h - part of libsensors, a library for reading Linux sensor data
+    Copyright (C)             Mark M. Hoffman <mhoffman@lightlink.com>
+    Copyright (C) 2007        Jean Delvare <khali@linux-fr.org>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Lesser General Public
+    License as published by the Free Software Foundation; either
+    version 2.1 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+    MA 02110-1301 USA.
+*/
+
+#ifndef SENSORS_LIB_SYSFS_H
+#define SENSORS_LIB_SYSFS_H
+
+extern char sensors_sysfs_mount[];
+
+int sensors_init_sysfs(void);
+
+int sensors_read_sysfs_chips(void);
+
+int sensors_read_sysfs_bus(void);
+
+/* Read a value out of a sysfs attribute file */
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+			    const sensors_subfeature *subfeature,
+			    double *value);
+
+/* Write a value to a sysfs attribute file */
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+			     const sensors_subfeature *subfeature,
+			     double value);
+
+#endif /* !SENSORS_LIB_SYSFS_H */
diff --git a/tools/gator/daemon/libsensors/version.h b/tools/gator/daemon/libsensors/version.h
new file mode 100644
index 000000000000..76ceb08c29d0
--- /dev/null
+++ b/tools/gator/daemon/libsensors/version.h
@@ -0,0 +1 @@
+#define LM_VERSION "3.3.2"
diff --git a/tools/gator/daemon/main.cpp b/tools/gator/daemon/main.cpp
new file mode 100644
index 000000000000..fbce1e15d0d0
--- /dev/null
+++ b/tools/gator/daemon/main.cpp
@@ -0,0 +1,584 @@
+/**
+ * Copyright (C) ARM Limited 2010-2014. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <arpa/inet.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "CCNDriver.h"
+#include "Child.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+extern Child* child;
+static int shutdownFilesystem();
+static pthread_mutex_t numSessions_mutex;
+static OlyServerSocket* sock = NULL;
+static Monitor monitor;
+static int numSessions = 0;
+static bool driverRunningAtStart = false;
+static bool driverMountedAtStart = false;
+
+struct cmdline_t {
+	char *module;
+	int port;
+	bool update;
+};
+
+#define DEFAULT_PORT 8080
+
+void cleanUp() {
+	if (shutdownFilesystem() == -1) {
+		logg->logMessage("Error shutting down gator filesystem");
+	}
+	delete sock;
+	delete util;
+	delete logg;
+}
+
+// CTRL C Signal Handler
+static void handler(int signum) {
+	logg->logMessage("Received signal %d, gator daemon exiting", signum);
+
+	// Case 1: both child and parent receive the signal
+	if (numSessions > 0) {
+		// Arbitrary sleep of 1 second to give time for the child to exit;
+		// if something bad happens, continue the shutdown process regardless
+		sleep(1);
+	}
+
+	// Case 2: only the parent received the signal
+	if (numSessions > 0) {
+		// Kill child threads - the first signal exits gracefully
+		logg->logMessage("Killing process group as %d child was running when signal was received", numSessions);
+		kill(0, SIGINT);
+
+		// Give time for the child to exit
+		sleep(1);
+
+		if (numSessions > 0) {
+			// The second signal force kills the child
+			logg->logMessage("Force kill the child");
+			kill(0, SIGINT);
+			// Again, sleep for 1 second
+			sleep(1);
+
+			if (numSessions > 0) {
+				// Something bad has really happened; the child is not exiting and therefore may hold the /dev/gator resource open
+				printf("Unable to kill the gatord child process, thus gator.ko may still be loaded.\n");
+			}
+		}
+	}
+
+	cleanUp();
+	exit(0);
+}
+
+// Child exit Signal Handler
+static void child_exit(int) {
+	int status;
+	int pid = wait(&status);
+	if (pid != -1) {
+		pthread_mutex_lock(&numSessions_mutex);
+		numSessions--;
+		pthread_mutex_unlock(&numSessions_mutex);
+		logg->logMessage("Child process %d exited with status %d", pid, status);
+	}
+}
+
+static const int UDP_REQ_PORT = 30001;
+
+typedef struct {
+	char rviHeader[8];
+	uint32_t messageID;
+	uint8_t ethernetAddress[8];
+	uint32_t ethernetType;
+	uint32_t dhcp;
+	char dhcpName[40];
+	uint32_t ipAddress;
+	uint32_t defaultGateway;
+	uint32_t subnetMask;
+	uint32_t activeConnections;
+} RVIConfigureInfo;
+
+static const char DST_REQ[] = { 'D', 'S', 'T', '_', 'R', 'E', 'Q', ' ', 0, 0, 0, 0x64 };
+
+class UdpListener {
+public:
+	UdpListener() : mDstAns(), mReq(-1) {}
+
+	void setup(int port) {
+		mReq = udpPort(UDP_REQ_PORT);
+
+		// Format the answer buffer
+		memset(&mDstAns, 0, sizeof(mDstAns));
+		memcpy(mDstAns.rviHeader, "STR_ANS ", sizeof(mDstAns.rviHeader));
+		if (gethostname(mDstAns.dhcpName, sizeof(mDstAns.dhcpName) - 1) != 0) {
+			logg->logError(__FILE__, __LINE__, "gethostname failed");
+			handleException();
+		}
+		// Subvert the defaultGateway field for the port number
+		if (port != DEFAULT_PORT) {
+			mDstAns.defaultGateway = port;
+		}
+		// Subvert the subnetMask field for the protocol version
+		mDstAns.subnetMask = PROTOCOL_VERSION;
+	}
+
+	int getReq() const {
+		return mReq;
+	}
+
+	void handle() {
+		char buf[128];
+		struct sockaddr_in6 sockaddr;
+		socklen_t addrlen;
+		int read;
+		addrlen = sizeof(sockaddr);
+		read = recvfrom(mReq, &buf, sizeof(buf), 0, (struct sockaddr *)&sockaddr, &addrlen);
+		if (read < 0) {
+			logg->logError(__FILE__, __LINE__, "recvfrom failed");
+			handleException();
+		} else if ((read == 12) && (memcmp(buf, DST_REQ, sizeof(DST_REQ)) == 0)) {
+			// Don't care if sendto fails - gatord shouldn't exit because of it and Streamline will retry
+			sendto(mReq, &mDstAns, sizeof(mDstAns), 0, (struct sockaddr *)&sockaddr, addrlen);
+		}
+	}
+
+	void close() {
+		::close(mReq);
+	}
+
+private:
+	int udpPort(int port) {
+		int s;
+		struct sockaddr_in6 sockaddr;
+		int on;
+		int family = AF_INET6;
+
+		s = socket_cloexec(AF_INET6, SOCK_DGRAM, IPPROTO_UDP);
+		if (s == -1) {
+			family = AF_INET;
+			s = socket_cloexec(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+			if (s == -1) {
+				logg->logError(__FILE__, __LINE__, "socket failed");
+				handleException();
+			}
+		}
+
+		on = 1;
+		if (setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+			logg->logError(__FILE__, __LINE__, "setsockopt failed");
+			handleException();
+		}
+
+		memset((void*)&sockaddr, 0, sizeof(sockaddr));
+		sockaddr.sin6_family = family;
+		sockaddr.sin6_port = htons(port);
+		sockaddr.sin6_addr = in6addr_any;
+		if (bind(s, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) < 0) {
+			logg->logError(__FILE__, __LINE__, "socket failed");
+			handleException();
+		}
+
+		return s;
+	}
+
+	RVIConfigureInfo mDstAns;
+	int mReq;
+};
+
+static UdpListener udpListener;
+
+// retval: -1 = failure; 0 = was already mounted; 1 = successfully mounted
+static int mountGatorFS() {
+	// If already mounted,
+	if (access("/dev/gator/buffer", F_OK) == 0) {
+		return 0;
+	}
+
+	// else, mount the filesystem
+	mkdir("/dev/gator", S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
+	if (mount("nodev", "/dev/gator", "gatorfs", 0, NULL) != 0) {
+		return -1;
+	} else {
+		return 1;
+	}
+}
+
+static bool init_module (const char * const location) {
+	bool ret(false);
+	const int fd = open(location, O_RDONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		struct stat st;
+		if (fstat(fd, &st) == 0) {
+			void * const p = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+			if (p != MAP_FAILED) {
+				if (syscall(__NR_init_module, p, (unsigned long)st.st_size, "") == 0) {
+					ret = true;
+				}
+				munmap(p, st.st_size);
+			}
+		}
+		close(fd);
+	}
+
+	return ret;
+}
+
+static bool setupFilesystem(char* module) {
+	if (module) {
+		// unmount and rmmod if the module was specified on the commandline, i.e. ensure that the specified module is indeed running
+		shutdownFilesystem();
+
+		// if still mounted
+		if (access("/dev/gator/buffer", F_OK) == 0) {
+			logg->logError(__FILE__, __LINE__, "Unable to remove the running gator.ko. Manually remove the module or use the running module by not specifying one on the commandline");
+			handleException();
+		}
+	}
+
+	const int retval = mountGatorFS();
+	if (retval == 1) {
+		logg->logMessage("Driver already running at startup");
+		driverRunningAtStart = true;
+	} else if (retval == 0) {
+		logg->logMessage("Driver already mounted at startup");
+		driverRunningAtStart = driverMountedAtStart = true;
+	} else {
+		char command[256]; // arbitrarily large amount
+		char location[256]; // arbitrarily large amount
+
+		if (module) {
+			strncpy(location, module, sizeof(location));
+		} else {
+			// Is the driver co-located in the same directory?
+			if (util->getApplicationFullPath(location, sizeof(location)) != 0) { // allow some buffer space
+				logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+			}
+			strncat(location, "gator.ko", sizeof(location) - strlen(location) - 1);
+		}
+
+		if (access(location, F_OK) == -1) {
+			if (module == NULL) {
+				// The gator kernel is not already loaded and unable to locate gator.ko in the default location
+				return false;
+			} else {
+				// gator location specified on the command line but it was not found
+				logg->logError(__FILE__, __LINE__, "gator module not found at %s", location);
+				handleException();
+			}
+		}
+
+		// Load driver
+		bool success = init_module(location);
+		if (!success) {
+			logg->logMessage("init_module failed, trying insmod");
+			snprintf(command, sizeof(command), "insmod %s >/dev/null 2>&1", location);
+			if (system(command) != 0) {
+				logg->logMessage("Unable to load gator.ko driver with command: %s", command);
+				logg->logError(__FILE__, __LINE__, "Unable to load (insmod) gator.ko driver:\n  >>> gator.ko must be built against the current kernel version & configuration\n  >>> See dmesg for more details");
+				handleException();
+			}
+		}
+
+		if (mountGatorFS() == -1) {
+			logg->logError(__FILE__, __LINE__, "Unable to mount the gator filesystem needed for profiling.");
+			handleException();
+		}
+	}
+
+	return true;
+}
+
+static int shutdownFilesystem() {
+	if (driverMountedAtStart == false) {
+		umount("/dev/gator");
+	}
+	if (driverRunningAtStart == false) {
+		if (syscall(__NR_delete_module, "gator", O_NONBLOCK) != 0) {
+			logg->logMessage("delete_module failed, trying rmmod");
+			if (system("rmmod gator >/dev/null 2>&1") != 0) {
+				return -1;
+			}
+		}
+	}
+
+	return 0; // success
+}
+
+static const char OPTSTRING[] = "hvudap:s:c:e:m:o:";
+
+static bool hasDebugFlag(int argc, char** argv) {
+	int c;
+
+	optind = 1;
+	while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+		if (c == 'd') {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static struct cmdline_t parseCommandLine(int argc, char** argv) {
+	struct cmdline_t cmdline;
+	cmdline.port = DEFAULT_PORT;
+	cmdline.module = NULL;
+	cmdline.update = false;
+	char version_string[256]; // arbitrary length to hold the version information
+	int c;
+
+	// build the version string
+	if (PROTOCOL_VERSION < PROTOCOL_DEV) {
+		snprintf(version_string, sizeof(version_string), "Streamline gatord version %d (DS-5 v5.%d)", PROTOCOL_VERSION, PROTOCOL_VERSION);
+	} else {
+		snprintf(version_string, sizeof(version_string), "Streamline gatord development version %d", PROTOCOL_VERSION);
+	}
+
+	optind = 1;
+	while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+		switch (c) {
+			case 'c':
+				gSessionData->mConfigurationXMLPath = optarg;
+				break;
+			case 'd':
+				// Already handled
+				break;
+			case 'e':
+				gSessionData->mEventsXMLPath = optarg;
+				break;
+			case 'm':
+				cmdline.module = optarg;
+				break;
+			case 'p':
+				cmdline.port = strtol(optarg, NULL, 10);
+				break;
+			case 's':
+				gSessionData->mSessionXMLPath = optarg;
+				break;
+			case 'o':
+				gSessionData->mTargetPath = optarg;
+				break;
+			case 'u':
+				cmdline.update = true;
+				break;
+			case 'a':
+				gSessionData->mAllowCommands = true;
+				break;
+			case 'h':
+			case '?':
+				logg->logError(__FILE__, __LINE__,
+					"%s. All parameters are optional:\n"
+					"-c config_xml   path and filename of the configuration.xml to use\n"
+					"-e events_xml   path and filename of the events.xml to use\n"
+					"-h              this help page\n"
+					"-m module       path and filename of gator.ko\n"
+					"-p port_number  port upon which the server listens; default is 8080\n"
+					"-s session_xml  path and filename of a session.xml used for local capture\n"
+					"-o apc_dir      path and name of the output for a local capture\n"
+					"-v              version information\n"
+					"-d              enable debug messages\n"
+					"-a              allow the user user to provide a command to run at the start of a capture"
+					, version_string);
+				handleException();
+				break;
+			case 'v':
+				logg->logError(__FILE__, __LINE__, version_string);
+				handleException();
+				break;
+		}
+	}
+
+	// Error checking
+	if (cmdline.port != DEFAULT_PORT && gSessionData->mSessionXMLPath != NULL) {
+		logg->logError(__FILE__, __LINE__, "Only a port or a session xml can be specified, not both");
+		handleException();
+	}
+
+	if (gSessionData->mTargetPath != NULL && gSessionData->mSessionXMLPath == NULL) {
+		logg->logError(__FILE__, __LINE__, "Missing -s command line option required for a local capture.");
+		handleException();
+	}
+
+	if (optind < argc) {
+		logg->logError(__FILE__, __LINE__, "Unknown argument: %s. Use '-h' for help.", argv[optind]);
+		handleException();
+	}
+
+	return cmdline;
+}
+
+static void handleClient() {
+	OlySocket client(sock->acceptConnection());
+
+	int pid = fork();
+	if (pid < 0) {
+		// Error
+		logg->logError(__FILE__, __LINE__, "Fork process failed. Please power cycle the target device if this error persists.");
+	} else if (pid == 0) {
+		// Child
+		sock->closeServerSocket();
+		udpListener.close();
+		monitor.close();
+		child = new Child(&client, numSessions + 1);
+		child->run();
+		delete child;
+		exit(0);
+	} else {
+		// Parent
+		client.closeSocket();
+
+		pthread_mutex_lock(&numSessions_mutex);
+		numSessions++;
+		pthread_mutex_unlock(&numSessions_mutex);
+
+		// Maximum number of connections is 2
+		int wait = 0;
+		while (numSessions > 1) {
+			// Throttle until one of the children exits before continuing to accept another socket connection
+			logg->logMessage("%d sessions active!", numSessions);
+			if (wait++ >= 10) { // Wait no more than 10 seconds
+				// Kill last created child
+				kill(pid, SIGALRM);
+				break;
+			}
+			sleep(1);
+		}
+	}
+}
+
+// Gator data flow: collector -> collector fifo -> sender
+int main(int argc, char** argv) {
+	// Ensure proper signal handling by making gatord the process group leader
+	//   e.g. it may not be the group leader when launched as 'sudo gatord'
+	setsid();
+
+  // Set up global thread-safe logging
+	logg = new Logging(hasDebugFlag(argc, argv));
+	// Global data class
+	gSessionData = new SessionData();
+	// Set up global utility class
+	util = new OlyUtility();
+
+	// Initialize drivers
+	new CCNDriver();
+
+	prctl(PR_SET_NAME, (unsigned long)&"gatord-main", 0, 0, 0);
+	pthread_mutex_init(&numSessions_mutex, NULL);
+
+	signal(SIGINT, handler);
+	signal(SIGTERM, handler);
+	signal(SIGABRT, handler);
+
+	// Set to high priority
+	if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), -19) == -1) {
+		logg->logMessage("setpriority() failed");
+	}
+
+	// Parse the command line parameters
+	struct cmdline_t cmdline = parseCommandLine(argc, argv);
+
+	if (cmdline.update) {
+		return update(argv[0]);
+	}
+
+	// Verify root permissions
+	uid_t euid = geteuid();
+	if (euid) {
+		logg->logError(__FILE__, __LINE__, "gatord must be launched with root privileges");
+		handleException();
+	}
+
+	// Call before setting up the SIGCHLD handler, as system() spawns child processes
+	if (!setupFilesystem(cmdline.module)) {
+		logg->logMessage("Unable to setup gatorfs, trying perf");
+		if (!gSessionData->perf.setup()) {
+			logg->logError(__FILE__, __LINE__,
+				       "Unable to locate gator.ko driver:\n"
+				       "  >>> gator.ko should be co-located with gatord in the same directory\n"
+				       "  >>> OR insmod gator.ko prior to launching gatord\n"
+				       "  >>> OR specify the location of gator.ko on the command line\n"
+				       "  >>> OR run Linux 3.4 or later with perf (CONFIG_PERF_EVENTS and CONFIG_HW_PERF_EVENTS) and tracing (CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER) support to collect data via userspace only");
+			handleException();
+		}
+	}
+
+	{
+		EventsXML eventsXML;
+		mxml_node_t *xml = eventsXML.getTree();
+		// Initialize all drivers
+		for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+			driver->readEvents(xml);
+		}
+		mxmlDelete(xml);
+	}
+
+	// Handle child exit codes
+	signal(SIGCHLD, child_exit);
+
+	// Ignore the SIGPIPE signal so that any send to a broken socket will return an error code instead of asserting a signal
+	// Handling the error at the send function call is much easier than trying to do anything intelligent in the sig handler
+	signal(SIGPIPE, SIG_IGN);
+
+	// If the command line argument is a session xml file, no need to open a socket
+	if (gSessionData->mSessionXMLPath) {
+		child = new Child();
+		child->run();
+		delete child;
+	} else {
+		gSessionData->annotateListener.setup();
+		sock = new OlyServerSocket(cmdline.port);
+		udpListener.setup(cmdline.port);
+		if (!monitor.init() ||
+				!monitor.add(sock->getFd()) ||
+				!monitor.add(udpListener.getReq()) ||
+				!monitor.add(gSessionData->annotateListener.getFd()) ||
+				false) {
+			logg->logError(__FILE__, __LINE__, "Monitor setup failed");
+			handleException();
+		}
+		// Forever loop, can be exited via a signal or exception
+		while (1) {
+			struct epoll_event events[2];
+			logg->logMessage("Waiting on connection...");
+			int ready = monitor.wait(events, ARRAY_LENGTH(events), -1);
+			if (ready < 0) {
+				logg->logError(__FILE__, __LINE__, "Monitor::wait failed");
+				handleException();
+			}
+			for (int i = 0; i < ready; ++i) {
+				if (events[i].data.fd == sock->getFd()) {
+					handleClient();
+				} else if (events[i].data.fd == udpListener.getReq()) {
+					udpListener.handle();
+				} else if (events[i].data.fd == gSessionData->annotateListener.getFd()) {
+					gSessionData->annotateListener.handle();
+				}
+			}
+		}
+	}
+
+	cleanUp();
+	return 0;
+}
diff --git a/tools/gator/daemon/mxml/COPYING b/tools/gator/daemon/mxml/COPYING
new file mode 100644
index 000000000000..4d0aa78af224
--- /dev/null
+++ b/tools/gator/daemon/mxml/COPYING
@@ -0,0 +1,507 @@
+			   Mini-XML License
+			  September 18, 2010
+
+
+The Mini-XML library and included programs are provided under the
+terms of the GNU Library General Public License version 2 (LGPL2)
+with the following exceptions:
+
+  1. Static linking of applications to the Mini-XML library
+does not constitute a derivative work and does not require
+the author to provide source code for the application, use
+the shared Mini-XML libraries, or link their applications
+against a user-supplied version of Mini-XML.
+
+If you link the application to a modified version of
+Mini-XML, then the changes to Mini-XML must be provided
+under the terms of the LGPL2 in sections 1, 2, and 4.
+
+  2. You do not have to provide a copy of the Mini-XML license
+with programs that are linked to the Mini-XML library, nor
+do you have to identify the Mini-XML license in your
+program or documentation as required by section 6 of the
+LGPL2.
+
+
+		  GNU LIBRARY GENERAL PUBLIC LICENSE
+			 Version 2, June 1991
+
+	  Copyright (C) 1991 Free Software Foundation, Inc.
+       59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+     Everyone is permitted to copy and distribute verbatim copies
+      of this license document, but changing it is not allowed.
+
+    [This is the first released version of the library GPL.  It is
+   numbered 2 because it goes with version 2 of the ordinary GPL.]
+
+			       Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+  This license, the Library General Public License, applies to some
+specially designated Free Software Foundation software, and to any
+other libraries whose authors decide to use it.  You can use it for
+your libraries, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if
+you distribute copies of the library, or if you modify it.
+
+  For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you.  You must make sure that they, too, receive or can get the source
+code.  If you link a program with the library, you must provide
+complete object files to the recipients so that they can relink them
+with the library, after making changes to the library and recompiling
+it.  And you must show them these terms so they know their rights.
+
+  Our method of protecting your rights has two steps: (1) copyright
+the library, and (2) offer you this license which gives you legal
+permission to copy, distribute and/or modify the library.
+
+  Also, for each distributor's protection, we want to make certain
+that everyone understands that there is no warranty for this free
+library.  If the library is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original
+version, so that any problems introduced by others will not reflect on
+the original authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that companies distributing free
+software will individually obtain patent licenses, thus in effect
+transforming the program into proprietary software.  To prevent this,
+we have made it clear that any patent must be licensed for everyone's
+free use or not licensed at all.
+
+  Most GNU software, including some libraries, is covered by the ordinary
+GNU General Public License, which was designed for utility programs.  This
+license, the GNU Library General Public License, applies to certain
+designated libraries.  This license is quite different from the ordinary
+one; be sure to read it in full, and don't assume that anything in it is
+the same as in the ordinary license.
+
+  The reason we have a separate public license for some libraries is that
+they blur the distinction we usually make between modifying or adding to a
+program and simply using it.  Linking a program with a library, without
+changing the library, is in some sense simply using the library, and is
+analogous to running a utility program or application program.  However, in
+a textual and legal sense, the linked executable is a combined work, a
+derivative of the original library, and the ordinary General Public License
+treats it as such.
+
+  Because of this blurred distinction, using the ordinary General
+Public License for libraries did not effectively promote software
+sharing, because most developers did not use the libraries.  We
+concluded that weaker conditions might promote sharing better.
+
+  However, unrestricted linking of non-free programs would deprive the
+users of those programs of all benefit from the free status of the
+libraries themselves.  This Library General Public License is intended to
+permit developers of non-free programs to use free libraries, while
+preserving your freedom as a user of such programs to change the free
+libraries that are incorporated in them.  (We have not seen how to achieve
+this as regards changes in header files, but we have achieved it as regards
+changes in the actual functions of the Library.)  The hope is that this
+will lead to faster development of free libraries.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.  Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library".  The
+former contains code derived from the library, while the latter only
+works together with the library.
+
+  Note that it is possible for a library to be covered by the ordinary
+General Public License rather than by this special one.
+
+		  GNU LIBRARY GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License Agreement applies to any software library which
+contains a notice placed by the copyright holder or other authorized
+party saying it may be distributed under the terms of this Library
+General Public License (also called "this License").  Each licensee is
+addressed as "you".
+
+  A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+  The "Library", below, refers to any such software library or work
+which has been distributed under these terms.  A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language.  (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+  "Source code" for a work means the preferred form of the work for
+making modifications to it.  For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+  Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it).  Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+  1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+  You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+  2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) The modified work must itself be a software library.
+
+    b) You must cause the files modified to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    c) You must cause the whole of the work to be licensed at no
+    charge to all third parties under the terms of this License.
+
+    d) If a facility in the modified Library refers to a function or a
+    table of data to be supplied by an application program that uses
+    the facility, other than as an argument passed when the facility
+    is invoked, then you must make a good faith effort to ensure that,
+    in the event an application does not supply such function or
+    table, the facility still operates, and performs whatever part of
+    its purpose remains meaningful.
+
+    (For example, a function in a library to compute square roots has
+    a purpose that is entirely well-defined independent of the
+    application.  Therefore, Subsection 2d requires that any
+    application-supplied function or table used by this function must
+    be optional: if the application does not supply it, the square
+    root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library.  To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License.  (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.)  Do not make any other change in
+these notices.
+
+  Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+  This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+  4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+  If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library".  Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+  However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library".  The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+  When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library.  The
+threshold for this to be true is not precisely defined by law.
+
+  If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work.  (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+  Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+  6. As an exception to the Sections above, you may also compile or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+  You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License.  You must supply a copy of this License.  If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License.  Also, you must do one
+of these things:
+
+    a) Accompany the work with the complete corresponding
+    machine-readable source code for the Library including whatever
+    changes were used in the work (which must be distributed under
+    Sections 1 and 2 above); and, if the work is an executable linked
+    with the Library, with the complete machine-readable "work that
+    uses the Library", as object code and/or source code, so that the
+    user can modify the Library and then relink to produce a modified
+    executable containing the modified Library.  (It is understood
+    that the user who changes the contents of definitions files in the
+    Library will not necessarily be able to recompile the application
+    to use the modified definitions.)
+
+    b) Accompany the work with a written offer, valid for at
+    least three years, to give the same user the materials
+    specified in Subsection 6a, above, for a charge no more
+    than the cost of performing this distribution.
+
+    c) If distribution of the work is made by offering access to copy
+    from a designated place, offer equivalent access to copy the above
+    specified materials from the same place.
+
+    d) Verify that the user has already received a copy of these
+    materials or that you have already sent this user a copy.
+
+  For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it.  However, as a special exception,
+the source code distributed need not include anything that is normally
+distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+  It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system.  Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+  7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+    a) Accompany the combined library with a copy of the same work
+    based on the Library, uncombined with any other library
+    facilities.  This must be distributed under the terms of the
+    Sections above.
+
+    b) Give prominent notice with the combined library of the fact
+    that part of it is a work based on the Library, and explaining
+    where to find the accompanying uncombined form of the same work.
+
+  8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License.  Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License.  However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+  9. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Library or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+  10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded.  In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+  13. The Free Software Foundation may publish revised and/or new
+versions of the Library General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation.  If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+  14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission.  For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this.  Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+			    NO WARRANTY
+
+  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+		     END OF TERMS AND CONDITIONS
+
+     Appendix: How to Apply These Terms to Your New Libraries
+
+  If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change.  You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+  To apply these terms, attach the following notices to the library.  It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the library's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Library General Public
+    License as published by the Free Software Foundation; either
+    version 2 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Library General Public License for more details.
+
+    You should have received a copy of the GNU Library General Public
+    License along with this library; if not, write to the Free
+    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the
+  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+  <signature of Ty Coon>, 1 April 1990
+  Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/mxml/config.h b/tools/gator/daemon/mxml/config.h
new file mode 100644
index 000000000000..ad6df1d7debe
--- /dev/null
+++ b/tools/gator/daemon/mxml/config.h
@@ -0,0 +1,96 @@
+/* config.h.  Generated from config.h.in by configure.  */
+/*
+ * "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Configuration file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+#include <ctype.h>
+
+
+/*
+ * Version number...
+ */
+
+#define MXML_VERSION "Mini-XML v2.8"
+
+
+/*
+ * Inline function support...
+ */
+
+#define inline
+
+
+/*
+ * Long long support...
+ */
+
+#define HAVE_LONG_LONG 1
+
+
+/*
+ * Do we have the snprintf() and vsnprintf() functions?
+ */
+
+#define HAVE_SNPRINTF 1
+#define HAVE_VSNPRINTF 1
+
+
+/*
+ * Do we have the strXXX() functions?
+ */
+
+#define HAVE_STRDUP 1
+
+
+/*
+ * Do we have threading support?
+ */
+
+#define HAVE_PTHREAD_H 1
+
+
+/*
+ * Define prototypes for string functions as needed...
+ */
+
+#  ifndef HAVE_STRDUP
+extern char	*_mxml_strdup(const char *);
+#    define strdup _mxml_strdup
+#  endif /* !HAVE_STRDUP */
+
+extern char	*_mxml_strdupf(const char *, ...);
+extern char	*_mxml_vstrdupf(const char *, va_list);
+
+#  ifndef HAVE_SNPRINTF
+extern int	_mxml_snprintf(char *, size_t, const char *, ...);
+#    define snprintf _mxml_snprintf
+#  endif /* !HAVE_SNPRINTF */
+
+#  ifndef HAVE_VSNPRINTF
+extern int	_mxml_vsnprintf(char *, size_t, const char *, va_list);
+#    define vsnprintf _mxml_vsnprintf
+#  endif /* !HAVE_VSNPRINTF */
+
+/*
+ * End of "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-attr.c b/tools/gator/daemon/mxml/mxml-attr.c
new file mode 100644
index 000000000000..8e89cc1474f8
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-attr.c
@@ -0,0 +1,314 @@
+/*
+ * "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Attribute support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static int	mxml_set_attr(mxml_node_t *node, const char *name,
+		              char *value);
+
+
+/*
+ * 'mxmlElementDeleteAttr()' - Delete an attribute.
+ *
+ * @since Mini-XML 2.4@
+ */
+
+void
+mxmlElementDeleteAttr(mxml_node_t *node,/* I - Element */
+                      const char  *name)/* I - Attribute name */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* Cirrent attribute */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementDeleteAttr(node=%p, name=\"%s\")\n",
+          node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return;
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+  {
+#ifdef DEBUG
+    printf("    %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+    if (!strcmp(attr->name, name))
+    {
+     /*
+      * Delete this attribute...
+      */
+
+      free(attr->name);
+      free(attr->value);
+
+      i --;
+      if (i > 0)
+        memmove(attr, attr + 1, i * sizeof(mxml_attr_t));
+
+      node->value.element.num_attrs --;
+
+      if (node->value.element.num_attrs == 0)
+        free(node->value.element.attrs);
+      return;
+    }
+  }
+}
+
+
+/*
+ * 'mxmlElementGetAttr()' - Get an attribute.
+ *
+ * This function returns NULL if the node is not an element or the
+ * named attribute does not exist.
+ */
+
+const char *				/* O - Attribute value or NULL */
+mxmlElementGetAttr(mxml_node_t *node,	/* I - Element node */
+                   const char  *name)	/* I - Name of attribute */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* Cirrent attribute */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementGetAttr(node=%p, name=\"%s\")\n",
+          node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return (NULL);
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+  {
+#ifdef DEBUG
+    printf("    %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+    if (!strcmp(attr->name, name))
+    {
+#ifdef DEBUG
+      printf("    Returning \"%s\"!\n", attr->value);
+#endif /* DEBUG */
+      return (attr->value);
+    }
+  }
+
+ /*
+  * Didn't find attribute, so return NULL...
+  */
+
+#ifdef DEBUG
+  puts("    Returning NULL!\n");
+#endif /* DEBUG */
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlElementSetAttr()' - Set an attribute.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new string value. The string value is copied
+ * into the element node. This function does nothing if the node is
+ * not an element.
+ */
+
+void
+mxmlElementSetAttr(mxml_node_t *node,	/* I - Element node */
+                   const char  *name,	/* I - Name of attribute */
+                   const char  *value)	/* I - Attribute value */
+{
+  char	*valuec;			/* Copy of value */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlElementSetAttr(node=%p, name=\"%s\", value=\"%s\")\n",
+          node, name ? name : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return;
+
+  if (value)
+    valuec = strdup(value);
+  else
+    valuec = NULL;
+
+  if (mxml_set_attr(node, name, valuec))
+    free(valuec);
+}
+
+
+/*
+ * 'mxmlElementSetAttrf()' - Set an attribute with a formatted value.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new formatted string. The formatted string value is
+ * copied into the element node. This function does nothing if the node
+ * is not an element.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlElementSetAttrf(mxml_node_t *node,	/* I - Element node */
+                    const char  *name,	/* I - Name of attribute */
+                    const char  *format,/* I - Printf-style attribute value */
+		    ...)		/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Argument pointer */
+  char		*value;			/* Value */
+
+
+#ifdef DEBUG
+  fprintf(stderr,
+          "mxmlElementSetAttrf(node=%p, name=\"%s\", format=\"%s\", ...)\n",
+          node, name ? name : "(null)", format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name || !format)
+    return;
+
+ /*
+  * Format the value...
+  */
+
+  va_start(ap, format);
+  value = _mxml_vstrdupf(format, ap);
+  va_end(ap);
+
+  if (!value)
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+  else if (mxml_set_attr(node, name, value))
+    free(value);
+}
+
+
+/*
+ * 'mxml_set_attr()' - Set or add an attribute name/value pair.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_set_attr(mxml_node_t *node,	/* I - Element node */
+              const char  *name,	/* I - Attribute name */
+              char        *value)	/* I - Attribute value */
+{
+  int		i;			/* Looping var */
+  mxml_attr_t	*attr;			/* New attribute */
+
+
+ /*
+  * Look for the attribute...
+  */
+
+  for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+       i > 0;
+       i --, attr ++)
+    if (!strcmp(attr->name, name))
+    {
+     /*
+      * Free the old value as needed...
+      */
+
+      if (attr->value)
+        free(attr->value);
+
+      attr->value = value;
+
+      return (0);
+    }
+
+ /*
+  * Add a new attribute...
+  */
+
+  if (node->value.element.num_attrs == 0)
+    attr = malloc(sizeof(mxml_attr_t));
+  else
+    attr = realloc(node->value.element.attrs,
+                   (node->value.element.num_attrs + 1) * sizeof(mxml_attr_t));
+
+  if (!attr)
+  {
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+    return (-1);
+  }
+
+  node->value.element.attrs = attr;
+  attr += node->value.element.num_attrs;
+
+  if ((attr->name = strdup(name)) == NULL)
+  {
+    mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+               name, node->value.element.name);
+    return (-1);
+  }
+
+  attr->value = value;
+
+  node->value.element.num_attrs ++;
+
+  return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-entity.c b/tools/gator/daemon/mxml/mxml-entity.c
new file mode 100644
index 000000000000..0d11df6a70bc
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-entity.c
@@ -0,0 +1,449 @@
+/*
+ * "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Character entity support code for Mini-XML, a small XML-like
+ * file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * 'mxmlEntityAddCallback()' - Add a callback to convert entities to Unicode.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlEntityAddCallback(
+    mxml_entity_cb_t cb)		/* I - Callback function to add */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  if (global->num_entity_cbs < (int)(sizeof(global->entity_cbs) / sizeof(global->entity_cbs[0])))
+  {
+    global->entity_cbs[global->num_entity_cbs] = cb;
+    global->num_entity_cbs ++;
+
+    return (0);
+  }
+  else
+  {
+    mxml_error("Unable to add entity callback!");
+
+    return (-1);
+  }
+}
+
+
+/*
+ * 'mxmlEntityGetName()' - Get the name that corresponds to the character value.
+ *
+ * If val does not need to be represented by a named entity, NULL is returned.
+ */
+
+const char *				/* O - Entity name or NULL */
+mxmlEntityGetName(int val)		/* I - Character value */
+{
+  switch (val)
+  {
+    case '&' :
+        return ("amp");
+
+    case '<' :
+        return ("lt");
+
+    case '>' :
+        return ("gt");
+
+    case '\"' :
+        return ("quot");
+
+    default :
+        return (NULL);
+  }
+}
+
+
+/*
+ * 'mxmlEntityGetValue()' - Get the character corresponding to a named entity.
+ *
+ * The entity name can also be a numeric constant. -1 is returned if the
+ * name is not known.
+ */
+
+int					/* O - Character value or -1 on error */
+mxmlEntityGetValue(const char *name)	/* I - Entity name */
+{
+  int		i;			/* Looping var */
+  int		ch;			/* Character value */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  for (i = 0; i < global->num_entity_cbs; i ++)
+    if ((ch = (global->entity_cbs[i])(name)) >= 0)
+      return (ch);
+
+  return (-1);
+}
+
+
+/*
+ * 'mxmlEntityRemoveCallback()' - Remove a callback.
+ */
+
+void
+mxmlEntityRemoveCallback(
+    mxml_entity_cb_t cb)		/* I - Callback function to remove */
+{
+  int		i;			/* Looping var */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  for (i = 0; i < global->num_entity_cbs; i ++)
+    if (cb == global->entity_cbs[i])
+    {
+     /*
+      * Remove the callback...
+      */
+
+      global->num_entity_cbs --;
+
+      if (i < global->num_entity_cbs)
+        memmove(global->entity_cbs + i, global->entity_cbs + i + 1,
+	        (global->num_entity_cbs - i) * sizeof(global->entity_cbs[0]));
+
+      return;
+    }
+}
+
+
+/*
+ * '_mxml_entity_cb()' - Lookup standard (X)HTML entities.
+ */
+
+int					/* O - Unicode value or -1 */
+_mxml_entity_cb(const char *name)	/* I - Entity name */
+{
+  int	diff,				/* Difference between names */
+	current,			/* Current entity in search */
+	first,				/* First entity in search */
+	last;				/* Last entity in search */
+  static const struct
+  {
+    const char	*name;			/* Entity name */
+    int		val;			/* Character value */
+  }	entities[] =
+  {
+    { "AElig",		198 },
+    { "Aacute",		193 },
+    { "Acirc",		194 },
+    { "Agrave",		192 },
+    { "Alpha",		913 },
+    { "Aring",		197 },
+    { "Atilde",		195 },
+    { "Auml",		196 },
+    { "Beta",		914 },
+    { "Ccedil",		199 },
+    { "Chi",		935 },
+    { "Dagger",		8225 },
+    { "Delta",		916 },
+    { "Dstrok",		208 },
+    { "ETH",		208 },
+    { "Eacute",		201 },
+    { "Ecirc",		202 },
+    { "Egrave",		200 },
+    { "Epsilon",	917 },
+    { "Eta",		919 },
+    { "Euml",		203 },
+    { "Gamma",		915 },
+    { "Iacute",		205 },
+    { "Icirc",		206 },
+    { "Igrave",		204 },
+    { "Iota",		921 },
+    { "Iuml",		207 },
+    { "Kappa",		922 },
+    { "Lambda",		923 },
+    { "Mu",		924 },
+    { "Ntilde",		209 },
+    { "Nu",		925 },
+    { "OElig",		338 },
+    { "Oacute",		211 },
+    { "Ocirc",		212 },
+    { "Ograve",		210 },
+    { "Omega",		937 },
+    { "Omicron",	927 },
+    { "Oslash",		216 },
+    { "Otilde",		213 },
+    { "Ouml",		214 },
+    { "Phi",		934 },
+    { "Pi",		928 },
+    { "Prime",		8243 },
+    { "Psi",		936 },
+    { "Rho",		929 },
+    { "Scaron",		352 },
+    { "Sigma",		931 },
+    { "THORN",		222 },
+    { "Tau",		932 },
+    { "Theta",		920 },
+    { "Uacute",		218 },
+    { "Ucirc",		219 },
+    { "Ugrave",		217 },
+    { "Upsilon",	933 },
+    { "Uuml",		220 },
+    { "Xi",		926 },
+    { "Yacute",		221 },
+    { "Yuml",		376 },
+    { "Zeta",		918 },
+    { "aacute",		225 },
+    { "acirc",		226 },
+    { "acute",		180 },
+    { "aelig",		230 },
+    { "agrave",		224 },
+    { "alefsym",	8501 },
+    { "alpha",		945 },
+    { "amp",		'&' },
+    { "and",		8743 },
+    { "ang",		8736 },
+    { "apos",           '\'' },
+    { "aring",		229 },
+    { "asymp",		8776 },
+    { "atilde",		227 },
+    { "auml",		228 },
+    { "bdquo",		8222 },
+    { "beta",		946 },
+    { "brkbar",		166 },
+    { "brvbar",		166 },
+    { "bull",		8226 },
+    { "cap",		8745 },
+    { "ccedil",		231 },
+    { "cedil",		184 },
+    { "cent",		162 },
+    { "chi",		967 },
+    { "circ",		710 },
+    { "clubs",		9827 },
+    { "cong",		8773 },
+    { "copy",		169 },
+    { "crarr",		8629 },
+    { "cup",		8746 },
+    { "curren",		164 },
+    { "dArr",		8659 },
+    { "dagger",		8224 },
+    { "darr",		8595 },
+    { "deg",		176 },
+    { "delta",		948 },
+    { "diams",		9830 },
+    { "die",		168 },
+    { "divide",		247 },
+    { "eacute",		233 },
+    { "ecirc",		234 },
+    { "egrave",		232 },
+    { "empty",		8709 },
+    { "emsp",		8195 },
+    { "ensp",		8194 },
+    { "epsilon",	949 },
+    { "equiv",		8801 },
+    { "eta",		951 },
+    { "eth",		240 },
+    { "euml",		235 },
+    { "euro",		8364 },
+    { "exist",		8707 },
+    { "fnof",		402 },
+    { "forall",		8704 },
+    { "frac12",		189 },
+    { "frac14",		188 },
+    { "frac34",		190 },
+    { "frasl",		8260 },
+    { "gamma",		947 },
+    { "ge",		8805 },
+    { "gt",		'>' },
+    { "hArr",		8660 },
+    { "harr",		8596 },
+    { "hearts",		9829 },
+    { "hellip",		8230 },
+    { "hibar",		175 },
+    { "iacute",		237 },
+    { "icirc",		238 },
+    { "iexcl",		161 },
+    { "igrave",		236 },
+    { "image",		8465 },
+    { "infin",		8734 },
+    { "int",		8747 },
+    { "iota",		953 },
+    { "iquest",		191 },
+    { "isin",		8712 },
+    { "iuml",		239 },
+    { "kappa",		954 },
+    { "lArr",		8656 },
+    { "lambda",		955 },
+    { "lang",		9001 },
+    { "laquo",		171 },
+    { "larr",		8592 },
+    { "lceil",		8968 },
+    { "ldquo",		8220 },
+    { "le",		8804 },
+    { "lfloor",		8970 },
+    { "lowast",		8727 },
+    { "loz",		9674 },
+    { "lrm",		8206 },
+    { "lsaquo",		8249 },
+    { "lsquo",		8216 },
+    { "lt",		'<' },
+    { "macr",		175 },
+    { "mdash",		8212 },
+    { "micro",		181 },
+    { "middot",		183 },
+    { "minus",		8722 },
+    { "mu",		956 },
+    { "nabla",		8711 },
+    { "nbsp",		160 },
+    { "ndash",		8211 },
+    { "ne",		8800 },
+    { "ni",		8715 },
+    { "not",		172 },
+    { "notin",		8713 },
+    { "nsub",		8836 },
+    { "ntilde",		241 },
+    { "nu",		957 },
+    { "oacute",		243 },
+    { "ocirc",		244 },
+    { "oelig",		339 },
+    { "ograve",		242 },
+    { "oline",		8254 },
+    { "omega",		969 },
+    { "omicron",	959 },
+    { "oplus",		8853 },
+    { "or",		8744 },
+    { "ordf",		170 },
+    { "ordm",		186 },
+    { "oslash",		248 },
+    { "otilde",		245 },
+    { "otimes",		8855 },
+    { "ouml",		246 },
+    { "para",		182 },
+    { "part",		8706 },
+    { "permil",		8240 },
+    { "perp",		8869 },
+    { "phi",		966 },
+    { "pi",		960 },
+    { "piv",		982 },
+    { "plusmn",		177 },
+    { "pound",		163 },
+    { "prime",		8242 },
+    { "prod",		8719 },
+    { "prop",		8733 },
+    { "psi",		968 },
+    { "quot",		'\"' },
+    { "rArr",		8658 },
+    { "radic",		8730 },
+    { "rang",		9002 },
+    { "raquo",		187 },
+    { "rarr",		8594 },
+    { "rceil",		8969 },
+    { "rdquo",		8221 },
+    { "real",		8476 },
+    { "reg",		174 },
+    { "rfloor",		8971 },
+    { "rho",		961 },
+    { "rlm",		8207 },
+    { "rsaquo",		8250 },
+    { "rsquo",		8217 },
+    { "sbquo",		8218 },
+    { "scaron",		353 },
+    { "sdot",		8901 },
+    { "sect",		167 },
+    { "shy",		173 },
+    { "sigma",		963 },
+    { "sigmaf",		962 },
+    { "sim",		8764 },
+    { "spades",		9824 },
+    { "sub",		8834 },
+    { "sube",		8838 },
+    { "sum",		8721 },
+    { "sup",		8835 },
+    { "sup1",		185 },
+    { "sup2",		178 },
+    { "sup3",		179 },
+    { "supe",		8839 },
+    { "szlig",		223 },
+    { "tau",		964 },
+    { "there4",		8756 },
+    { "theta",		952 },
+    { "thetasym",	977 },
+    { "thinsp",		8201 },
+    { "thorn",		254 },
+    { "tilde",		732 },
+    { "times",		215 },
+    { "trade",		8482 },
+    { "uArr",		8657 },
+    { "uacute",		250 },
+    { "uarr",		8593 },
+    { "ucirc",		251 },
+    { "ugrave",		249 },
+    { "uml",		168 },
+    { "upsih",		978 },
+    { "upsilon",	965 },
+    { "uuml",		252 },
+    { "weierp",		8472 },
+    { "xi",		958 },
+    { "yacute",		253 },
+    { "yen",		165 },
+    { "yuml",		255 },
+    { "zeta",		950 },
+    { "zwj",		8205 },
+    { "zwnj",		8204 }
+  };
+
+
+ /*
+  * Do a binary search for the named entity...
+  */
+
+  first = 0;
+  last  = (int)(sizeof(entities) / sizeof(entities[0]) - 1);
+
+  while ((last - first) > 1)
+  {
+    current = (first + last) / 2;
+
+    if ((diff = strcmp(name, entities[current].name)) == 0)
+      return (entities[current].val);
+    else if (diff < 0)
+      last = current;
+    else
+      first = current;
+  }
+
+ /*
+  * If we get here, there is a small chance that there is still
+  * a match; check first and last...
+  */
+
+  if (!strcmp(name, entities[first].name))
+    return (entities[first].val);
+  else if (!strcmp(name, entities[last].name))
+    return (entities[last].val);
+  else
+    return (-1);
+}
+
+
+/*
+ * End of "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-file.c b/tools/gator/daemon/mxml/mxml-file.c
new file mode 100644
index 000000000000..3812c253fc3e
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-file.c
@@ -0,0 +1,3056 @@
+/*
+ * "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $"
+ *
+ * File loading code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*** This file modified by ARM on 25 Aug 2014 to avoid pointer overflow when checking if the write position is beyond the end of the buffer in mxmlSaveString and mxml_string_putc ***/
+
+/*
+ * Include necessary headers...
+ */
+
+#ifndef WIN32
+#  include <unistd.h>
+#endif /* !WIN32 */
+#include "mxml-private.h"
+
+
+/*
+ * Character encoding...
+ */
+
+#define ENCODE_UTF8	0		/* UTF-8 */
+#define ENCODE_UTF16BE	1		/* UTF-16 Big-Endian */
+#define ENCODE_UTF16LE	2		/* UTF-16 Little-Endian */
+
+
+/*
+ * Macro to test for a bad XML character...
+ */
+
+#define mxml_bad_char(ch) ((ch) < ' ' && (ch) != '\n' && (ch) != '\r' && (ch) != '\t')
+
+
+/*
+ * Types and structures...
+ */
+
+typedef int (*_mxml_getc_cb_t)(void *, int *);
+typedef int (*_mxml_putc_cb_t)(int, void *);
+
+typedef struct _mxml_fdbuf_s		/**** File descriptor buffer ****/
+{
+  int		fd;			/* File descriptor */
+  unsigned char	*current,		/* Current position in buffer */
+		*end,			/* End of buffer */
+		buffer[8192];		/* Character buffer */
+} _mxml_fdbuf_t;
+
+
+/*
+ * Local functions...
+ */
+
+static int		mxml_add_char(int ch, char **ptr, char **buffer,
+			              int *bufsize);
+static int		mxml_fd_getc(void *p, int *encoding);
+static int		mxml_fd_putc(int ch, void *p);
+static int		mxml_fd_read(_mxml_fdbuf_t *buf);
+static int		mxml_fd_write(_mxml_fdbuf_t *buf);
+static int		mxml_file_getc(void *p, int *encoding);
+static int		mxml_file_putc(int ch, void *p);
+static int		mxml_get_entity(mxml_node_t *parent, void *p,
+			                int *encoding,
+					_mxml_getc_cb_t getc_cb);
+static inline int	mxml_isspace(int ch)
+			{
+			  return (ch == ' ' || ch == '\t' || ch == '\r' ||
+			          ch == '\n');
+			}
+static mxml_node_t	*mxml_load_data(mxml_node_t *top, void *p,
+			                mxml_load_cb_t cb,
+			                _mxml_getc_cb_t getc_cb,
+                                        mxml_sax_cb_t sax_cb, void *sax_data);
+static int		mxml_parse_element(mxml_node_t *node, void *p,
+			                   int *encoding,
+					   _mxml_getc_cb_t getc_cb);
+static int		mxml_string_getc(void *p, int *encoding);
+static int		mxml_string_putc(int ch, void *p);
+static int		mxml_write_name(const char *s, void *p,
+					_mxml_putc_cb_t putc_cb);
+static int		mxml_write_node(mxml_node_t *node, void *p,
+			                mxml_save_cb_t cb, int col,
+					_mxml_putc_cb_t putc_cb,
+					_mxml_global_t *global);
+static int		mxml_write_string(const char *s, void *p,
+					  _mxml_putc_cb_t putc_cb);
+static int		mxml_write_ws(mxml_node_t *node, void *p,
+			              mxml_save_cb_t cb, int ws,
+				      int col, _mxml_putc_cb_t putc_cb);
+
+
+/*
+ * 'mxmlLoadFd()' - Load a file descriptor into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlLoadFd(mxml_node_t    *top,		/* I - Top node */
+           int            fd,		/* I - File descriptor to read from */
+           mxml_load_cb_t cb)		/* I - Callback function or MXML_NO_CALLBACK */
+{
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer;
+
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, &buf, cb, mxml_fd_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadFile()' - Load a file into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlLoadFile(mxml_node_t    *top,	/* I - Top node */
+             FILE           *fp,	/* I - File to read from */
+             mxml_load_cb_t cb)		/* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, fp, cb, mxml_file_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadString()' - Load a string into an XML node tree.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t *				/* O - First node or NULL if the string has errors. */
+mxmlLoadString(mxml_node_t    *top,	/* I - Top node */
+               const char     *s,	/* I - String to load */
+               mxml_load_cb_t cb)	/* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, MXML_NO_CALLBACK,
+                         NULL));
+}
+
+
+/*
+ * 'mxmlSaveAllocString()' - Save an XML tree to an allocated string.
+ *
+ * This function returns a pointer to a string containing the textual
+ * representation of the XML node tree.  The string should be freed
+ * using the free() function when you are done with it.  NULL is returned
+ * if the node would produce an empty string or if the string cannot be
+ * allocated.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+char *					/* O - Allocated string or NULL */
+mxmlSaveAllocString(
+    mxml_node_t    *node,		/* I - Node to write */
+    mxml_save_cb_t cb)			/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	bytes;				/* Required bytes */
+  char	buffer[8192];			/* Temporary buffer */
+  char	*s;				/* Allocated string */
+
+
+ /*
+  * Write the node to the temporary buffer...
+  */
+
+  bytes = mxmlSaveString(node, buffer, sizeof(buffer), cb);
+
+  if (bytes <= 0)
+    return (NULL);
+
+  if (bytes < (int)(sizeof(buffer) - 1))
+  {
+   /*
+    * Node fit inside the buffer, so just duplicate that string and
+    * return...
+    */
+
+    return (strdup(buffer));
+  }
+
+ /*
+  * Allocate a buffer of the required size and save the node to the
+  * new buffer...
+  */
+
+  if ((s = malloc(bytes + 1)) == NULL)
+    return (NULL);
+
+  mxmlSaveString(node, s, bytes + 1, cb);
+
+ /*
+  * Return the allocated string...
+  */
+
+  return (s);
+}
+
+
+/*
+ * 'mxmlSaveFd()' - Save an XML tree to a file descriptor.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - 0 on success, -1 on error. */
+mxmlSaveFd(mxml_node_t    *node,	/* I - Node to write */
+           int            fd,		/* I - File descriptor to write to */
+	   mxml_save_cb_t cb)		/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int		col;			/* Final column */
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer + sizeof(buf.buffer);
+
+ /*
+  * Write the node...
+  */
+
+  if ((col = mxml_write_node(node, &buf, cb, 0, mxml_fd_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    if (mxml_fd_putc('\n', &buf) < 0)
+      return (-1);
+
+ /*
+  * Flush and return...
+  */
+
+  return (mxml_fd_write(&buf));
+}
+
+
+/*
+ * 'mxmlSaveFile()' - Save an XML tree to a file.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - 0 on success, -1 on error. */
+mxmlSaveFile(mxml_node_t    *node,	/* I - Node to write */
+             FILE           *fp,	/* I - File to write to */
+	     mxml_save_cb_t cb)		/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	col;				/* Final column */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Write the node...
+  */
+
+  if ((col = mxml_write_node(node, fp, cb, 0, mxml_file_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    if (putc('\n', fp) < 0)
+      return (-1);
+
+ /*
+  * Return 0 (success)...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSaveString()' - Save an XML node tree to a string.
+ *
+ * This function returns the total number of bytes that would be
+ * required for the string but only copies (bufsize - 1) characters
+ * into the specified buffer.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int					/* O - Size of string */
+mxmlSaveString(mxml_node_t    *node,	/* I - Node to write */
+               char           *buffer,	/* I - String buffer */
+               int            bufsize,	/* I - Size of string buffer */
+               mxml_save_cb_t cb)	/* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+  int	col;				/* Final column */
+  char	*ptr[3];			/* Pointers for putc_cb */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Write the node...
+  */
+
+  ptr[0] = buffer;
+  ptr[1] = buffer + bufsize;
+  ptr[2] = 0;
+
+  if ((col = mxml_write_node(node, ptr, cb, 0, mxml_string_putc, global)) < 0)
+    return (-1);
+
+  if (col > 0)
+    mxml_string_putc('\n', ptr);
+
+ /*
+  * Nul-terminate the buffer...
+  */
+
+  if (ptr[2] != 0)
+    buffer[bufsize - 1] = '\0';
+  else
+    ptr[0][0] = '\0';
+
+ /*
+  * Return the number of characters...
+  */
+
+  return (ptr[0] - buffer);
+}
+
+
+/*
+ * 'mxmlSAXLoadFd()' - Load a file descriptor into an XML node tree
+ *                     using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFd(mxml_node_t    *top,	/* I - Top node */
+              int            fd,	/* I - File descriptor to read from */
+              mxml_load_cb_t cb,	/* I - Callback function or MXML_NO_CALLBACK */
+              mxml_sax_cb_t  sax_cb,	/* I - SAX callback or MXML_NO_CALLBACK */
+              void           *sax_data)	/* I - SAX user data */
+{
+  _mxml_fdbuf_t	buf;			/* File descriptor buffer */
+
+
+ /*
+  * Initialize the file descriptor buffer...
+  */
+
+  buf.fd      = fd;
+  buf.current = buf.buffer;
+  buf.end     = buf.buffer;
+
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, &buf, cb, mxml_fd_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadFile()' - Load a file into an XML node tree
+ *                       using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFile(
+    mxml_node_t    *top,		/* I - Top node */
+    FILE           *fp,			/* I - File to read from */
+    mxml_load_cb_t cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    mxml_sax_cb_t  sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void           *sax_data)		/* I - SAX user data */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, fp, cb, mxml_file_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadString()' - Load a string into an XML node tree
+ *                         using a SAX callback.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - First node or NULL if the string has errors. */
+mxmlSAXLoadString(
+    mxml_node_t    *top,		/* I - Top node */
+    const char     *s,			/* I - String to load */
+    mxml_load_cb_t cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    mxml_sax_cb_t  sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void           *sax_data)		/* I - SAX user data */
+{
+ /*
+  * Read the XML data...
+  */
+
+  return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSetCustomHandlers()' - Set the handling functions for custom data.
+ *
+ * The load function accepts a node pointer and a data string and must
+ * return 0 on success and non-zero on error.
+ *
+ * The save function accepts a node pointer and must return a malloc'd
+ * string on success and NULL on error.
+ *
+ */
+
+void
+mxmlSetCustomHandlers(
+    mxml_custom_load_cb_t load,		/* I - Load function */
+    mxml_custom_save_cb_t save)		/* I - Save function */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->custom_load_cb = load;
+  global->custom_save_cb = save;
+}
+
+
+/*
+ * 'mxmlSetErrorCallback()' - Set the error message callback.
+ */
+
+void
+mxmlSetErrorCallback(mxml_error_cb_t cb)/* I - Error callback function */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->error_cb = cb;
+}
+
+
+/*
+ * 'mxmlSetWrapMargin()' - Set the wrap margin when saving XML data.
+ *
+ * Wrapping is disabled when "column" is 0.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlSetWrapMargin(int column)		/* I - Column for wrapping, 0 to disable wrapping */
+{
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+  global->wrap = column;
+}
+
+
+/*
+ * 'mxml_add_char()' - Add a character to a buffer, expanding as needed.
+ */
+
+static int				/* O  - 0 on success, -1 on error */
+mxml_add_char(int  ch,			/* I  - Character to add */
+              char **bufptr,		/* IO - Current position in buffer */
+	      char **buffer,		/* IO - Current buffer */
+	      int  *bufsize)		/* IO - Current buffer size */
+{
+  char	*newbuffer;			/* New buffer value */
+
+
+  if (*bufptr >= (*buffer + *bufsize - 4))
+  {
+   /*
+    * Increase the size of the buffer...
+    */
+
+    if (*bufsize < 1024)
+      (*bufsize) *= 2;
+    else
+      (*bufsize) += 1024;
+
+    if ((newbuffer = realloc(*buffer, *bufsize)) == NULL)
+    {
+      free(*buffer);
+
+      mxml_error("Unable to expand string buffer to %d bytes!", *bufsize);
+
+      return (-1);
+    }
+
+    *bufptr = newbuffer + (*bufptr - *buffer);
+    *buffer = newbuffer;
+  }
+
+  if (ch < 0x80)
+  {
+   /*
+    * Single byte ASCII...
+    */
+
+    *(*bufptr)++ = ch;
+  }
+  else if (ch < 0x800)
+  {
+   /*
+    * Two-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xc0 | (ch >> 6);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+  else if (ch < 0x10000)
+  {
+   /*
+    * Three-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xe0 | (ch >> 12);
+    *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+  else
+  {
+   /*
+    * Four-byte UTF-8...
+    */
+
+    *(*bufptr)++ = 0xf0 | (ch >> 18);
+    *(*bufptr)++ = 0x80 | ((ch >> 12) & 0x3f);
+    *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+    *(*bufptr)++ = 0x80 | (ch & 0x3f);
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_getc()' - Read a character from a file descriptor.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_fd_getc(void *p,			/* I  - File descriptor buffer */
+             int  *encoding)		/* IO - Encoding */
+{
+  _mxml_fdbuf_t	*buf;			/* File descriptor buffer */
+  int		ch,			/* Current character */
+		temp;			/* Temporary character */
+
+
+ /*
+  * Grab the next character in the buffer...
+  */
+
+  buf = (_mxml_fdbuf_t *)p;
+
+  if (buf->current >= buf->end)
+    if (mxml_fd_read(buf) < 0)
+      return (EOF);
+
+  ch = *(buf->current)++;
+
+  switch (*encoding)
+  {
+    case ENCODE_UTF8 :
+       /*
+	* Got a UTF-8 character; convert UTF-8 to Unicode and return...
+	*/
+
+	if (!(ch & 0x80))
+	{
+#if DEBUG > 1
+          printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+
+	  return (ch);
+        }
+	else if (ch == 0xfe)
+	{
+	 /*
+	  * UTF-16 big-endian BOM?
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  ch = *(buf->current)++;
+
+	  if (ch != 0xff)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16BE;
+
+	  return (mxml_fd_getc(p, encoding));
+	}
+	else if (ch == 0xff)
+	{
+	 /*
+	  * UTF-16 little-endian BOM?
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  ch = *(buf->current)++;
+
+	  if (ch != 0xfe)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16LE;
+
+	  return (mxml_fd_getc(p, encoding));
+	}
+	else if ((ch & 0xe0) == 0xc0)
+	{
+	 /*
+	  * Two-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+	  if (ch < 0x80)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else if ((ch & 0xf0) == 0xe0)
+	{
+	 /*
+	  * Three-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x800)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+
+         /*
+	  * Ignore (strip) Byte Order Mark (BOM)...
+	  */
+
+	  if (ch == 0xfeff)
+	    return (mxml_fd_getc(p, encoding));
+	}
+	else if ((ch & 0xf8) == 0xf0)
+	{
+	 /*
+	  * Four-byte value...
+	  */
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  if ((temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x10000)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else
+	  return (EOF);
+	break;
+
+    case ENCODE_UTF16BE :
+       /*
+        * Read UTF-16 big-endian char...
+	*/
+
+	if (buf->current >= buf->end)
+	  if (mxml_fd_read(buf) < 0)
+	    return (EOF);
+
+	temp = *(buf->current)++;
+
+	ch = (ch << 8) | temp;
+
+	if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  lch = *(buf->current)++;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  lch = (lch << 8) | temp;
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+
+    case ENCODE_UTF16LE :
+       /*
+        * Read UTF-16 little-endian char...
+	*/
+
+	if (buf->current >= buf->end)
+	  if (mxml_fd_read(buf) < 0)
+	    return (EOF);
+
+	temp = *(buf->current)++;
+
+	ch |= (temp << 8);
+
+        if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  lch = *(buf->current)++;
+
+	  if (buf->current >= buf->end)
+	    if (mxml_fd_read(buf) < 0)
+	      return (EOF);
+
+	  temp = *(buf->current)++;
+
+	  lch |= (temp << 8);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+  }
+
+#if DEBUG > 1
+  printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_fd_putc()' - Write a character to a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_putc(int  ch,			/* I - Character */
+             void *p)			/* I - File descriptor buffer */
+{
+  _mxml_fdbuf_t	*buf;			/* File descriptor buffer */
+
+
+ /*
+  * Flush the write buffer as needed...
+  */
+
+  buf = (_mxml_fdbuf_t *)p;
+
+  if (buf->current >= buf->end)
+    if (mxml_fd_write(buf) < 0)
+      return (-1);
+
+  *(buf->current)++ = ch;
+
+ /*
+  * Return successfully...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_read()' - Read a buffer of data from a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_read(_mxml_fdbuf_t *buf)		/* I - File descriptor buffer */
+{
+  int	bytes;				/* Bytes read... */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!buf)
+    return (-1);
+
+ /*
+  * Read from the file descriptor...
+  */
+
+  while ((bytes = read(buf->fd, buf->buffer, sizeof(buf->buffer))) < 0)
+#ifdef EINTR
+    if (errno != EAGAIN && errno != EINTR)
+#else
+    if (errno != EAGAIN)
+#endif /* EINTR */
+      return (-1);
+
+  if (bytes == 0)
+    return (-1);
+
+ /*
+  * Update the pointers and return success...
+  */
+
+  buf->current = buf->buffer;
+  buf->end     = buf->buffer + bytes;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_fd_write()' - Write a buffer of data to a file descriptor.
+ */
+
+static int				/* O - 0 on success, -1 on error */
+mxml_fd_write(_mxml_fdbuf_t *buf)	/* I - File descriptor buffer */
+{
+  int		bytes;			/* Bytes written */
+  unsigned char	*ptr;			/* Pointer into buffer */
+
+
+ /*
+  * Range check...
+  */
+
+  if (!buf)
+    return (-1);
+
+ /*
+  * Return 0 if there is nothing to write...
+  */
+
+  if (buf->current == buf->buffer)
+    return (0);
+
+ /*
+  * Loop until we have written everything...
+  */
+
+  for (ptr = buf->buffer; ptr < buf->current; ptr += bytes)
+    if ((bytes = write(buf->fd, ptr, buf->current - ptr)) < 0)
+      return (-1);
+
+ /*
+  * All done, reset pointers and return success...
+  */
+
+  buf->current = buf->buffer;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_file_getc()' - Get a character from a file.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_file_getc(void *p,			/* I  - Pointer to file */
+               int  *encoding)		/* IO - Encoding */
+{
+  int	ch,				/* Character from file */
+	temp;				/* Temporary character */
+  FILE	*fp;				/* Pointer to file */
+
+
+ /*
+  * Read a character from the file and see if it is EOF or ASCII...
+  */
+
+  fp = (FILE *)p;
+  ch = getc(fp);
+
+  if (ch == EOF)
+    return (EOF);
+
+  switch (*encoding)
+  {
+    case ENCODE_UTF8 :
+       /*
+	* Got a UTF-8 character; convert UTF-8 to Unicode and return...
+	*/
+
+	if (!(ch & 0x80))
+	{
+	  if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+
+#if DEBUG > 1
+          printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+        }
+	else if (ch == 0xfe)
+	{
+	 /*
+	  * UTF-16 big-endian BOM?
+	  */
+
+          ch = getc(fp);
+	  if (ch != 0xff)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16BE;
+
+	  return (mxml_file_getc(p, encoding));
+	}
+	else if (ch == 0xff)
+	{
+	 /*
+	  * UTF-16 little-endian BOM?
+	  */
+
+          ch = getc(fp);
+	  if (ch != 0xfe)
+	    return (EOF);
+
+	  *encoding = ENCODE_UTF16LE;
+
+	  return (mxml_file_getc(p, encoding));
+	}
+	else if ((ch & 0xe0) == 0xc0)
+	{
+	 /*
+	  * Two-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+	  if (ch < 0x80)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else if ((ch & 0xf0) == 0xe0)
+	{
+	 /*
+	  * Three-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x800)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+
+         /*
+	  * Ignore (strip) Byte Order Mark (BOM)...
+	  */
+
+	  if (ch == 0xfeff)
+	    return (mxml_file_getc(p, encoding));
+	}
+	else if ((ch & 0xf8) == 0xf0)
+	{
+	 /*
+	  * Four-byte value...
+	  */
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+	    return (EOF);
+
+	  ch = (ch << 6) | (temp & 0x3f);
+
+	  if (ch < 0x10000)
+	  {
+	    mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	    return (EOF);
+	  }
+	}
+	else
+	  return (EOF);
+	break;
+
+    case ENCODE_UTF16BE :
+       /*
+        * Read UTF-16 big-endian char...
+	*/
+
+	ch = (ch << 8) | getc(fp);
+
+	if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch = getc(fp);
+          lch = (lch << 8) | getc(fp);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+
+    case ENCODE_UTF16LE :
+       /*
+        * Read UTF-16 little-endian char...
+	*/
+
+	ch |= (getc(fp) << 8);
+
+        if (mxml_bad_char(ch))
+	{
+	  mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	     ch);
+	  return (EOF);
+	}
+        else if (ch >= 0xd800 && ch <= 0xdbff)
+	{
+	 /*
+	  * Multi-word UTF-16 char...
+	  */
+
+          int lch = getc(fp);
+          lch |= (getc(fp) << 8);
+
+          if (lch < 0xdc00 || lch >= 0xdfff)
+	    return (EOF);
+
+          ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	}
+	break;
+  }
+
+#if DEBUG > 1
+  printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_file_putc()' - Write a character to a file.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_file_putc(int  ch,			/* I - Character to write */
+               void *p)			/* I - Pointer to file */
+{
+  return (putc(ch, (FILE *)p) == EOF ? -1 : 0);
+}
+
+
+/*
+ * 'mxml_get_entity()' - Get the character corresponding to an entity...
+ */
+
+static int				/* O  - Character value or EOF on error */
+mxml_get_entity(mxml_node_t *parent,	/* I  - Parent node */
+		void        *p,		/* I  - Pointer to source */
+		int         *encoding,	/* IO - Character encoding */
+                int         (*getc_cb)(void *, int *))
+					/* I  - Get character function */
+{
+  int	ch;				/* Current character */
+  char	entity[64],			/* Entity string */
+	*entptr;			/* Pointer into entity */
+
+
+  entptr = entity;
+
+  while ((ch = (*getc_cb)(p, encoding)) != EOF)
+    if (ch > 126 || (!isalnum(ch) && ch != '#'))
+      break;
+    else if (entptr < (entity + sizeof(entity) - 1))
+      *entptr++ = ch;
+    else
+    {
+      mxml_error("Entity name too long under parent <%s>!",
+	         parent ? parent->value.element.name : "null");
+      break;
+    }
+
+  *entptr = '\0';
+
+  if (ch != ';')
+  {
+    mxml_error("Character entity \"%s\" not terminated under parent <%s>!",
+	       entity, parent ? parent->value.element.name : "null");
+    return (EOF);
+  }
+
+  if (entity[0] == '#')
+  {
+    if (entity[1] == 'x')
+      ch = strtol(entity + 2, NULL, 16);
+    else
+      ch = strtol(entity + 1, NULL, 10);
+  }
+  else if ((ch = mxmlEntityGetValue(entity)) < 0)
+    mxml_error("Entity name \"%s;\" not supported under parent <%s>!",
+	       entity, parent ? parent->value.element.name : "null");
+
+  if (mxml_bad_char(ch))
+  {
+    mxml_error("Bad control character 0x%02x under parent <%s> not allowed by XML standard!",
+               ch, parent ? parent->value.element.name : "null");
+    return (EOF);
+  }
+
+  return (ch);
+}
+
+
+/*
+ * 'mxml_load_data()' - Load data into an XML node tree.
+ */
+
+static mxml_node_t *			/* O - First node or NULL if the file could not be read. */
+mxml_load_data(
+    mxml_node_t     *top,		/* I - Top node */
+    void            *p,			/* I - Pointer to data */
+    mxml_load_cb_t  cb,			/* I - Callback function or MXML_NO_CALLBACK */
+    _mxml_getc_cb_t getc_cb,		/* I - Read function */
+    mxml_sax_cb_t   sax_cb,		/* I - SAX callback or MXML_NO_CALLBACK */
+    void            *sax_data)		/* I - SAX user data */
+{
+  mxml_node_t	*node,			/* Current node */
+		*first,			/* First node added */
+		*parent;		/* Current parent node */
+  int		ch,			/* Character from file */
+		whitespace;		/* Non-zero if whitespace seen */
+  char		*buffer,		/* String buffer */
+		*bufptr;		/* Pointer into buffer */
+  int		bufsize;		/* Size of buffer */
+  mxml_type_t	type;			/* Current node type */
+  int		encoding;		/* Character encoding */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+  static const char * const types[] =	/* Type strings... */
+		{
+		  "MXML_ELEMENT",	/* XML element with attributes */
+		  "MXML_INTEGER",	/* Integer value */
+		  "MXML_OPAQUE",	/* Opaque string */
+		  "MXML_REAL",		/* Real value */
+		  "MXML_TEXT",		/* Text fragment */
+		  "MXML_CUSTOM"		/* Custom data */
+		};
+
+
+ /*
+  * Read elements and other nodes from the file...
+  */
+
+  if ((buffer = malloc(64)) == NULL)
+  {
+    mxml_error("Unable to allocate string buffer!");
+    return (NULL);
+  }
+
+  bufsize    = 64;
+  bufptr     = buffer;
+  parent     = top;
+  first      = NULL;
+  whitespace = 0;
+  encoding   = ENCODE_UTF8;
+
+  if (cb && parent)
+    type = (*cb)(parent);
+  else if (parent)
+    type = MXML_TEXT;
+  else
+    type = MXML_IGNORE;
+
+  while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+  {
+    if ((ch == '<' ||
+         (mxml_isspace(ch) && type != MXML_OPAQUE && type != MXML_CUSTOM)) &&
+        bufptr > buffer)
+    {
+     /*
+      * Add a new value node...
+      */
+
+      *bufptr = '\0';
+
+      switch (type)
+      {
+	case MXML_INTEGER :
+            node = mxmlNewInteger(parent, strtol(buffer, &bufptr, 0));
+	    break;
+
+	case MXML_OPAQUE :
+            node = mxmlNewOpaque(parent, buffer);
+	    break;
+
+	case MXML_REAL :
+            node = mxmlNewReal(parent, strtod(buffer, &bufptr));
+	    break;
+
+	case MXML_TEXT :
+            node = mxmlNewText(parent, whitespace, buffer);
+	    break;
+
+	case MXML_CUSTOM :
+	    if (global->custom_load_cb)
+	    {
+	     /*
+	      * Use the callback to fill in the custom data...
+	      */
+
+              node = mxmlNewCustom(parent, NULL, NULL);
+
+	      if ((*global->custom_load_cb)(node, buffer))
+	      {
+	        mxml_error("Bad custom value '%s' in parent <%s>!",
+		           buffer, parent ? parent->value.element.name : "null");
+		mxmlDelete(node);
+		node = NULL;
+	      }
+	      break;
+	    }
+
+        default : /* Ignore... */
+	    node = NULL;
+	    break;
+      }
+
+      if (*bufptr)
+      {
+       /*
+        * Bad integer/real number value...
+	*/
+
+        mxml_error("Bad %s value '%s' in parent <%s>!",
+	           type == MXML_INTEGER ? "integer" : "real", buffer,
+		   parent ? parent->value.element.name : "null");
+	break;
+      }
+
+      bufptr     = buffer;
+      whitespace = mxml_isspace(ch) && type == MXML_TEXT;
+
+      if (!node && type != MXML_IGNORE)
+      {
+       /*
+	* Print error and return...
+	*/
+
+	mxml_error("Unable to add value node of type %s to parent <%s>!",
+	           types[type], parent ? parent->value.element.name : "null");
+	goto error;
+      }
+
+      if (sax_cb)
+      {
+        (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+        if (!mxmlRelease(node))
+          node = NULL;
+      }
+
+      if (!first && node)
+        first = node;
+    }
+    else if (mxml_isspace(ch) && type == MXML_TEXT)
+      whitespace = 1;
+
+   /*
+    * Add lone whitespace node if we have an element and existing
+    * whitespace...
+    */
+
+    if (ch == '<' && whitespace && type == MXML_TEXT)
+    {
+      if (parent)
+      {
+	node = mxmlNewText(parent, whitespace, "");
+
+	if (sax_cb)
+	{
+	  (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+	  if (!mxmlRelease(node))
+	    node = NULL;
+	}
+
+	if (!first && node)
+	  first = node;
+      }
+
+      whitespace = 0;
+    }
+
+    if (ch == '<')
+    {
+     /*
+      * Start of open/close tag...
+      */
+
+      bufptr = buffer;
+
+      while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+        if (mxml_isspace(ch) || ch == '>' || (ch == '/' && bufptr > buffer))
+	  break;
+	else if (ch == '<')
+	{
+	  mxml_error("Bare < in element!");
+	  goto error;
+	}
+	else if (ch == '&')
+	{
+	  if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+	    goto error;
+
+	  if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+	else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	  goto error;
+	else if (((bufptr - buffer) == 1 && buffer[0] == '?') ||
+	         ((bufptr - buffer) == 3 && !strncmp(buffer, "!--", 3)) ||
+	         ((bufptr - buffer) == 8 && !strncmp(buffer, "![CDATA[", 8)))
+	  break;
+
+      *bufptr = '\0';
+
+      if (!strcmp(buffer, "!--"))
+      {
+       /*
+        * Gather rest of comment...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && bufptr > (buffer + 4) &&
+	      bufptr[-3] != '-' && bufptr[-2] == '-' && bufptr[-1] == '-')
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole comment...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in comment node!");
+	  goto error;
+	}
+
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Just print error for now...
+	  */
+
+	  mxml_error("Unable to add comment node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  break;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_COMMENT, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+	if (node && !first)
+	  first = node;
+      }
+      else if (!strcmp(buffer, "![CDATA["))
+      {
+       /*
+        * Gather CDATA section...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && !strncmp(bufptr - 2, "]]", 2))
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole comment...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in CDATA node!");
+	  goto error;
+	}
+
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add CDATA node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_CDATA, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+	if (node && !first)
+	  first = node;
+      }
+      else if (buffer[0] == '?')
+      {
+       /*
+        * Gather rest of processing instruction...
+	*/
+
+	while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+	{
+	  if (ch == '>' && bufptr > buffer && bufptr[-1] == '?')
+	    break;
+	  else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	    goto error;
+	}
+
+       /*
+        * Error out if we didn't get the whole processing instruction...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in processing instruction node!");
+	  goto error;
+	}
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add processing instruction node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+        if (node)
+	{
+	  if (!first)
+            first = node;
+
+	  if (!parent)
+	  {
+	    parent = node;
+
+	    if (cb)
+	      type = (*cb)(parent);
+	  }
+	}
+      }
+      else if (buffer[0] == '!')
+      {
+       /*
+        * Gather rest of declaration...
+	*/
+
+	do
+	{
+	  if (ch == '>')
+	    break;
+	  else
+	  {
+            if (ch == '&')
+	      if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+		goto error;
+
+	    if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	      goto error;
+	  }
+	}
+        while ((ch = (*getc_cb)(p, &encoding)) != EOF);
+
+       /*
+        * Error out if we didn't get the whole declaration...
+	*/
+
+        if (ch != '>')
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Early EOF in declaration node!");
+	  goto error;
+	}
+
+       /*
+        * Otherwise add this as an element under the current parent...
+	*/
+
+	*bufptr = '\0';
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+	if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Print error and return...
+	  */
+
+	  mxml_error("Unable to add declaration node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+          if (!mxmlRelease(node))
+            node = NULL;
+        }
+
+        if (node)
+	{
+	  if (!first)
+            first = node;
+
+	  if (!parent)
+	  {
+	    parent = node;
+
+	    if (cb)
+	      type = (*cb)(parent);
+	  }
+	}
+      }
+      else if (buffer[0] == '/')
+      {
+       /*
+        * Handle close tag...
+	*/
+
+        if (!parent || strcmp(buffer + 1, parent->value.element.name))
+	{
+	 /*
+	  * Close tag doesn't match tree; print an error for now...
+	  */
+
+	  mxml_error("Mismatched close tag <%s> under parent <%s>!",
+	             buffer, parent ? parent->value.element.name : "(null)");
+          goto error;
+	}
+
+       /*
+        * Keep reading until we see >...
+	*/
+
+        while (ch != '>' && ch != EOF)
+	  ch = (*getc_cb)(p, &encoding);
+
+        node   = parent;
+        parent = parent->parent;
+
+        if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+          if (!mxmlRelease(node) && first == node)
+	    first = NULL;
+        }
+
+       /*
+	* Ascend into the parent and set the value type as needed...
+	*/
+
+	if (cb && parent)
+	  type = (*cb)(parent);
+      }
+      else
+      {
+       /*
+        * Handle open tag...
+	*/
+
+        if (!parent && first)
+	{
+	 /*
+	  * There can only be one root element!
+	  */
+
+	  mxml_error("<%s> cannot be a second root node after <%s>",
+	             buffer, first->value.element.name);
+          goto error;
+	}
+
+        if ((node = mxmlNewElement(parent, buffer)) == NULL)
+	{
+	 /*
+	  * Just print error for now...
+	  */
+
+	  mxml_error("Unable to add element node to parent <%s>!",
+	             parent ? parent->value.element.name : "null");
+	  goto error;
+	}
+
+        if (mxml_isspace(ch))
+        {
+	  if ((ch = mxml_parse_element(node, p, &encoding, getc_cb)) == EOF)
+	    goto error;
+        }
+        else if (ch == '/')
+	{
+	  if ((ch = (*getc_cb)(p, &encoding)) != '>')
+	  {
+	    mxml_error("Expected > but got '%c' instead for element <%s/>!",
+	               ch, buffer);
+            mxmlDelete(node);
+            goto error;
+	  }
+
+	  ch = '/';
+	}
+
+        if (sax_cb)
+          (*sax_cb)(node, MXML_SAX_ELEMENT_OPEN, sax_data);
+
+        if (!first)
+	  first = node;
+
+	if (ch == EOF)
+	  break;
+
+        if (ch != '/')
+	{
+	 /*
+	  * Descend into this node, setting the value type as needed...
+	  */
+
+	  parent = node;
+
+	  if (cb && parent)
+	    type = (*cb)(parent);
+	}
+        else if (sax_cb)
+        {
+          (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+          if (!mxmlRelease(node) && first == node)
+            first = NULL;
+        }
+      }
+
+      bufptr  = buffer;
+    }
+    else if (ch == '&')
+    {
+     /*
+      * Add character entity to current buffer...
+      */
+
+      if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+	goto error;
+
+      if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	goto error;
+    }
+    else if (type == MXML_OPAQUE || type == MXML_CUSTOM || !mxml_isspace(ch))
+    {
+     /*
+      * Add character to current buffer...
+      */
+
+      if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+	goto error;
+    }
+  }
+
+ /*
+  * Free the string buffer - we don't need it anymore...
+  */
+
+  free(buffer);
+
+ /*
+  * Find the top element and return it...
+  */
+
+  if (parent)
+  {
+    node = parent;
+
+    while (parent != top && parent->parent)
+      parent = parent->parent;
+
+    if (node != parent)
+    {
+      mxml_error("Missing close tag </%s> under parent <%s>!",
+	         node->value.element.name,
+		 node->parent ? node->parent->value.element.name : "(null)");
+
+      mxmlDelete(first);
+
+      return (NULL);
+    }
+  }
+
+  if (parent)
+    return (parent);
+  else
+    return (first);
+
+ /*
+  * Common error return...
+  */
+
+error:
+
+  mxmlDelete(first);
+
+  free(buffer);
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxml_parse_element()' - Parse an element for any attributes...
+ */
+
+static int				/* O  - Terminating character */
+mxml_parse_element(
+    mxml_node_t     *node,		/* I  - Element node */
+    void            *p,			/* I  - Data to read from */
+    int             *encoding,		/* IO - Encoding */
+    _mxml_getc_cb_t getc_cb)		/* I  - Data callback */
+{
+  int	ch,				/* Current character in file */
+	quote;				/* Quoting character */
+  char	*name,				/* Attribute name */
+	*value,				/* Attribute value */
+	*ptr;				/* Pointer into name/value */
+  int	namesize,			/* Size of name string */
+	valsize;			/* Size of value string */
+
+
+ /*
+  * Initialize the name and value buffers...
+  */
+
+  if ((name = malloc(64)) == NULL)
+  {
+    mxml_error("Unable to allocate memory for name!");
+    return (EOF);
+  }
+
+  namesize = 64;
+
+  if ((value = malloc(64)) == NULL)
+  {
+    free(name);
+    mxml_error("Unable to allocate memory for value!");
+    return (EOF);
+  }
+
+  valsize = 64;
+
+ /*
+  * Loop until we hit a >, /, ?, or EOF...
+  */
+
+  while ((ch = (*getc_cb)(p, encoding)) != EOF)
+  {
+#if DEBUG > 1
+    fprintf(stderr, "parse_element: ch='%c'\n", ch);
+#endif /* DEBUG > 1 */
+
+   /*
+    * Skip leading whitespace...
+    */
+
+    if (mxml_isspace(ch))
+      continue;
+
+   /*
+    * Stop at /, ?, or >...
+    */
+
+    if (ch == '/' || ch == '?')
+    {
+     /*
+      * Grab the > character and print an error if it isn't there...
+      */
+
+      quote = (*getc_cb)(p, encoding);
+
+      if (quote != '>')
+      {
+        mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+	           ch, node->value.element.name, quote);
+        goto error;
+      }
+
+      break;
+    }
+    else if (ch == '<')
+    {
+      mxml_error("Bare < in element %s!", node->value.element.name);
+      goto error;
+    }
+    else if (ch == '>')
+      break;
+
+   /*
+    * Read the attribute name...
+    */
+
+    name[0] = ch;
+    ptr     = name + 1;
+
+    if (ch == '\"' || ch == '\'')
+    {
+     /*
+      * Name is in quotes, so get a quoted string...
+      */
+
+      quote = ch;
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF)
+      {
+        if (ch == '&')
+	  if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	    goto error;
+
+	if (mxml_add_char(ch, &ptr, &name, &namesize))
+	  goto error;
+
+	if (ch == quote)
+          break;
+      }
+    }
+    else
+    {
+     /*
+      * Grab an normal, non-quoted name...
+      */
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>' ||
+	    ch == '?')
+          break;
+	else
+	{
+          if (ch == '&')
+	    if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	      goto error;
+
+	  if (mxml_add_char(ch, &ptr, &name, &namesize))
+	    goto error;
+	}
+    }
+
+    *ptr = '\0';
+
+    if (mxmlElementGetAttr(node, name))
+      goto error;
+
+    while (ch != EOF && mxml_isspace(ch))
+      ch = (*getc_cb)(p, encoding);
+
+    if (ch == '=')
+    {
+     /*
+      * Read the attribute value...
+      */
+
+      while ((ch = (*getc_cb)(p, encoding)) != EOF && mxml_isspace(ch));
+
+      if (ch == EOF)
+      {
+        mxml_error("Missing value for attribute '%s' in element %s!",
+	           name, node->value.element.name);
+        goto error;
+      }
+
+      if (ch == '\'' || ch == '\"')
+      {
+       /*
+        * Read quoted value...
+	*/
+
+        quote = ch;
+	ptr   = value;
+
+        while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	  if (ch == quote)
+	    break;
+	  else
+	  {
+	    if (ch == '&')
+	      if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	        goto error;
+
+	    if (mxml_add_char(ch, &ptr, &value, &valsize))
+	      goto error;
+	  }
+
+        *ptr = '\0';
+      }
+      else
+      {
+       /*
+        * Read unquoted value...
+	*/
+
+	value[0] = ch;
+	ptr      = value + 1;
+
+	while ((ch = (*getc_cb)(p, encoding)) != EOF)
+	  if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>')
+            break;
+	  else
+	  {
+	    if (ch == '&')
+	      if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+	        goto error;
+
+	    if (mxml_add_char(ch, &ptr, &value, &valsize))
+	      goto error;
+	  }
+
+        *ptr = '\0';
+      }
+
+     /*
+      * Set the attribute with the given string value...
+      */
+
+      mxmlElementSetAttr(node, name, value);
+    }
+    else
+    {
+      mxml_error("Missing value for attribute '%s' in element %s!",
+	         name, node->value.element.name);
+      goto error;
+    }
+
+   /*
+    * Check the end character...
+    */
+
+    if (ch == '/' || ch == '?')
+    {
+     /*
+      * Grab the > character and print an error if it isn't there...
+      */
+
+      quote = (*getc_cb)(p, encoding);
+
+      if (quote != '>')
+      {
+        mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+	           ch, node->value.element.name, quote);
+        ch = EOF;
+      }
+
+      break;
+    }
+    else if (ch == '>')
+      break;
+  }
+
+ /*
+  * Free the name and value buffers and return...
+  */
+
+  free(name);
+  free(value);
+
+  return (ch);
+
+ /*
+  * Common error return point...
+  */
+
+error:
+
+  free(name);
+  free(value);
+
+  return (EOF);
+}
+
+
+/*
+ * 'mxml_string_getc()' - Get a character from a string.
+ */
+
+static int				/* O  - Character or EOF */
+mxml_string_getc(void *p,		/* I  - Pointer to file */
+                 int  *encoding)	/* IO - Encoding */
+{
+  int		ch;			/* Character */
+  const char	**s;			/* Pointer to string pointer */
+
+
+  s = (const char **)p;
+
+  if ((ch = (*s)[0] & 255) != 0 || *encoding == ENCODE_UTF16LE)
+  {
+   /*
+    * Got character; convert UTF-8 to integer and return...
+    */
+
+    (*s)++;
+
+    switch (*encoding)
+    {
+      case ENCODE_UTF8 :
+	  if (!(ch & 0x80))
+	  {
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    if (mxml_bad_char(ch))
+	    {
+	      mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        		 ch);
+	      return (EOF);
+	    }
+
+	    return (ch);
+          }
+	  else if (ch == 0xfe)
+	  {
+	   /*
+	    * UTF-16 big-endian BOM?
+	    */
+
+            if (((*s)[0] & 255) != 0xff)
+	      return (EOF);
+
+	    *encoding = ENCODE_UTF16BE;
+	    (*s)++;
+
+	    return (mxml_string_getc(p, encoding));
+	  }
+	  else if (ch == 0xff)
+	  {
+	   /*
+	    * UTF-16 little-endian BOM?
+	    */
+
+            if (((*s)[0] & 255) != 0xfe)
+	      return (EOF);
+
+	    *encoding = ENCODE_UTF16LE;
+	    (*s)++;
+
+	    return (mxml_string_getc(p, encoding));
+	  }
+	  else if ((ch & 0xe0) == 0xc0)
+	  {
+	   /*
+	    * Two-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((ch & 0x1f) << 6) | ((*s)[0] & 0x3f);
+
+	    (*s)++;
+
+	    if (ch < 0x80)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else if ((ch & 0xf0) == 0xe0)
+	  {
+	   /*
+	    * Three-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80 ||
+        	((*s)[1] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((((ch & 0x0f) << 6) | ((*s)[0] & 0x3f)) << 6) | ((*s)[1] & 0x3f);
+
+	    (*s) += 2;
+
+	    if (ch < 0x800)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+	   /*
+	    * Ignore (strip) Byte Order Mark (BOM)...
+	    */
+
+	    if (ch == 0xfeff)
+	      return (mxml_string_getc(p, encoding));
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else if ((ch & 0xf8) == 0xf0)
+	  {
+	   /*
+	    * Four-byte value...
+	    */
+
+	    if (((*s)[0] & 0xc0) != 0x80 ||
+        	((*s)[1] & 0xc0) != 0x80 ||
+        	((*s)[2] & 0xc0) != 0x80)
+              return (EOF);
+
+	    ch = ((((((ch & 0x07) << 6) | ((*s)[0] & 0x3f)) << 6) |
+        	   ((*s)[1] & 0x3f)) << 6) | ((*s)[2] & 0x3f);
+
+	    (*s) += 3;
+
+	    if (ch < 0x10000)
+	    {
+	      mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+	      return (EOF);
+	    }
+
+#if DEBUG > 1
+            printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	    return (ch);
+	  }
+	  else
+	    return (EOF);
+
+      case ENCODE_UTF16BE :
+	 /*
+          * Read UTF-16 big-endian char...
+	  */
+
+	  ch = (ch << 8) | ((*s)[0] & 255);
+	  (*s) ++;
+
+          if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+          else if (ch >= 0xd800 && ch <= 0xdbff)
+	  {
+	   /*
+	    * Multi-word UTF-16 char...
+	    */
+
+            int lch;			/* Lower word */
+
+
+            if (!(*s)[0])
+	      return (EOF);
+
+            lch = (((*s)[0] & 255) << 8) | ((*s)[1] & 255);
+	    (*s) += 2;
+
+            if (lch < 0xdc00 || lch >= 0xdfff)
+	      return (EOF);
+
+            ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	  }
+
+#if DEBUG > 1
+          printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+
+      case ENCODE_UTF16LE :
+	 /*
+          * Read UTF-16 little-endian char...
+	  */
+
+	  ch = ch | (((*s)[0] & 255) << 8);
+
+	  if (!ch)
+	  {
+	    (*s) --;
+	    return (EOF);
+	  }
+
+	  (*s) ++;
+
+          if (mxml_bad_char(ch))
+	  {
+	    mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+        	       ch);
+	    return (EOF);
+	  }
+          else if (ch >= 0xd800 && ch <= 0xdbff)
+	  {
+	   /*
+	    * Multi-word UTF-16 char...
+	    */
+
+            int lch;			/* Lower word */
+
+
+            if (!(*s)[1])
+	      return (EOF);
+
+            lch = (((*s)[1] & 255) << 8) | ((*s)[0] & 255);
+	    (*s) += 2;
+
+            if (lch < 0xdc00 || lch >= 0xdfff)
+	      return (EOF);
+
+            ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+	  }
+
+#if DEBUG > 1
+          printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+	  return (ch);
+    }
+  }
+
+  return (EOF);
+}
+
+
+/*
+ * 'mxml_string_putc()' - Write a character to a string.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_string_putc(int  ch,		/* I - Character to write */
+                 void *p)		/* I - Pointer to string pointers */
+{
+  char	**pp;				/* Pointer to string pointers */
+
+
+  pp = (char **)p;
+
+  if (pp[2] == 0) {
+    if (pp[0] < pp[1])
+      pp[0][0] = ch;
+    else
+      pp[2] = (char *)1;
+  }
+
+  pp[0] ++;
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_name()' - Write a name string.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_write_name(const char *s,		/* I - Name to write */
+                void       *p,		/* I - Write pointer */
+		int        (*putc_cb)(int, void *))
+					/* I - Write callback */
+{
+  char		quote;			/* Quote character */
+  const char	*name;			/* Entity name */
+
+
+  if (*s == '\"' || *s == '\'')
+  {
+   /*
+    * Write a quoted name string...
+    */
+
+    if ((*putc_cb)(*s, p) < 0)
+      return (-1);
+
+    quote = *s++;
+
+    while (*s && *s != quote)
+    {
+      if ((name = mxmlEntityGetName(*s)) != NULL)
+      {
+	if ((*putc_cb)('&', p) < 0)
+          return (-1);
+
+        while (*name)
+	{
+	  if ((*putc_cb)(*name, p) < 0)
+            return (-1);
+
+          name ++;
+	}
+
+	if ((*putc_cb)(';', p) < 0)
+          return (-1);
+      }
+      else if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+
+      s ++;
+    }
+
+   /*
+    * Write the end quote...
+    */
+
+    if ((*putc_cb)(quote, p) < 0)
+      return (-1);
+  }
+  else
+  {
+   /*
+    * Write a non-quoted name string...
+    */
+
+    while (*s)
+    {
+      if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+
+      s ++;
+    }
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_node()' - Save an XML node to a file.
+ */
+
+static int				/* O - Column or -1 on error */
+mxml_write_node(mxml_node_t     *node,	/* I - Node to write */
+                void            *p,	/* I - File to write to */
+	        mxml_save_cb_t  cb,	/* I - Whitespace callback */
+		int             col,	/* I - Current column */
+		_mxml_putc_cb_t putc_cb,/* I - Output callback */
+		_mxml_global_t  *global)/* I - Global data */
+{
+  int		i,			/* Looping var */
+		width;			/* Width of attr + value */
+  mxml_attr_t	*attr;			/* Current attribute */
+  char		s[255];			/* Temporary string */
+
+
+ /*
+  * Print the node value...
+  */
+
+  switch (node->type)
+  {
+    case MXML_ELEMENT :
+	col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_OPEN, col, putc_cb);
+
+	if ((*putc_cb)('<', p) < 0)
+	  return (-1);
+	if (node->value.element.name[0] == '?' ||
+	    !strncmp(node->value.element.name, "!--", 3) ||
+	    !strncmp(node->value.element.name, "![CDATA[", 8))
+	{
+	 /*
+	  * Comments, CDATA, and processing instructions do not
+	  * use character entities.
+	  */
+
+	  const char	*ptr;		/* Pointer into name */
+
+
+	  for (ptr = node->value.element.name; *ptr; ptr ++)
+	    if ((*putc_cb)(*ptr, p) < 0)
+	      return (-1);
+	}
+	else if (mxml_write_name(node->value.element.name, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.element.name) + 1;
+
+	for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+	     i > 0;
+	     i --, attr ++)
+	{
+	  width = strlen(attr->name);
+
+	  if (attr->value)
+	    width += strlen(attr->value) + 3;
+
+	  if (global->wrap > 0 && (col + width) > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else
+	  {
+	    if ((*putc_cb)(' ', p) < 0)
+	      return (-1);
+
+	    col ++;
+	  }
+
+	  if (mxml_write_name(attr->name, p, putc_cb) < 0)
+	    return (-1);
+
+	  if (attr->value)
+	  {
+	    if ((*putc_cb)('=', p) < 0)
+	      return (-1);
+	    if ((*putc_cb)('\"', p) < 0)
+	      return (-1);
+	    if (mxml_write_string(attr->value, p, putc_cb) < 0)
+	      return (-1);
+	    if ((*putc_cb)('\"', p) < 0)
+	      return (-1);
+	  }
+
+	  col += width;
+	}
+
+	if (node->child)
+	{
+	 /*
+	  * Write children...
+	  */
+
+	  mxml_node_t *child;		/* Current child */
+
+
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+
+          for (child = node->child; child; child = child->next)
+	  {
+	    if ((col = mxml_write_node(child, p, cb, col, putc_cb, global)) < 0)
+	      return (-1);
+	  }
+
+	 /*
+	  * The ? and ! elements are special-cases and have no end tags...
+	  */
+
+	  if (node->value.element.name[0] != '!' &&
+	      node->value.element.name[0] != '?')
+	  {
+	    col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_CLOSE, col, putc_cb);
+
+	    if ((*putc_cb)('<', p) < 0)
+	      return (-1);
+	    if ((*putc_cb)('/', p) < 0)
+	      return (-1);
+	    if (mxml_write_string(node->value.element.name, p, putc_cb) < 0)
+	      return (-1);
+	    if ((*putc_cb)('>', p) < 0)
+	      return (-1);
+
+	    col += strlen(node->value.element.name) + 3;
+
+	    col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_CLOSE, col, putc_cb);
+	  }
+	}
+	else if (node->value.element.name[0] == '!' ||
+		 node->value.element.name[0] == '?')
+	{
+	 /*
+	  * The ? and ! elements are special-cases...
+	  */
+
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+	}
+	else
+	{
+	  if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  if ((*putc_cb)('/', p) < 0)
+	    return (-1);
+	  if ((*putc_cb)('>', p) < 0)
+	    return (-1);
+
+	  col += 3;
+
+	  col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+	}
+	break;
+
+    case MXML_INTEGER :
+	if (node->prev)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	sprintf(s, "%d", node->value.integer);
+	if (mxml_write_string(s, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(s);
+	break;
+
+    case MXML_OPAQUE :
+	if (mxml_write_string(node->value.opaque, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.opaque);
+	break;
+
+    case MXML_REAL :
+	if (node->prev)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	sprintf(s, "%f", node->value.real);
+	if (mxml_write_string(s, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(s);
+	break;
+
+    case MXML_TEXT :
+	if (node->value.text.whitespace && col > 0)
+	{
+	  if (global->wrap > 0 && col > global->wrap)
+	  {
+	    if ((*putc_cb)('\n', p) < 0)
+	      return (-1);
+
+	    col = 0;
+	  }
+	  else if ((*putc_cb)(' ', p) < 0)
+	    return (-1);
+	  else
+	    col ++;
+	}
+
+	if (mxml_write_string(node->value.text.string, p, putc_cb) < 0)
+	  return (-1);
+
+	col += strlen(node->value.text.string);
+	break;
+
+    case MXML_CUSTOM :
+	if (global->custom_save_cb)
+	{
+	  char	*data;		/* Custom data string */
+	  const char	*newline;	/* Last newline in string */
+
+
+	  if ((data = (*global->custom_save_cb)(node)) == NULL)
+	    return (-1);
+
+	  if (mxml_write_string(data, p, putc_cb) < 0)
+	    return (-1);
+
+	  if ((newline = strrchr(data, '\n')) == NULL)
+	    col += strlen(data);
+	  else
+	    col = strlen(newline);
+
+	  free(data);
+	  break;
+	}
+
+    default : /* Should never happen */
+	return (-1);
+  }
+
+  return (col);
+}
+
+
+/*
+ * 'mxml_write_string()' - Write a string, escaping & and < as needed.
+ */
+
+static int				/* O - 0 on success, -1 on failure */
+mxml_write_string(
+    const char      *s,			/* I - String to write */
+    void            *p,			/* I - Write pointer */
+    _mxml_putc_cb_t putc_cb)		/* I - Write callback */
+{
+  const char	*name;			/* Entity name, if any */
+
+
+  while (*s)
+  {
+    if ((name = mxmlEntityGetName(*s)) != NULL)
+    {
+      if ((*putc_cb)('&', p) < 0)
+        return (-1);
+
+      while (*name)
+      {
+	if ((*putc_cb)(*name, p) < 0)
+          return (-1);
+        name ++;
+      }
+
+      if ((*putc_cb)(';', p) < 0)
+        return (-1);
+    }
+    else if ((*putc_cb)(*s, p) < 0)
+      return (-1);
+
+    s ++;
+  }
+
+  return (0);
+}
+
+
+/*
+ * 'mxml_write_ws()' - Do whitespace callback...
+ */
+
+static int				/* O - New column */
+mxml_write_ws(mxml_node_t     *node,	/* I - Current node */
+              void            *p,	/* I - Write pointer */
+              mxml_save_cb_t  cb,	/* I - Callback function */
+	      int             ws,	/* I - Where value */
+	      int             col,	/* I - Current column */
+              _mxml_putc_cb_t putc_cb)	/* I - Write callback */
+{
+  const char	*s;			/* Whitespace string */
+
+
+  if (cb && (s = (*cb)(node, ws)) != NULL)
+  {
+    while (*s)
+    {
+      if ((*putc_cb)(*s, p) < 0)
+	return (-1);
+      else if (*s == '\n')
+	col = 0;
+      else if (*s == '\t')
+      {
+	col += MXML_TAB;
+	col = col - (col % MXML_TAB);
+      }
+      else
+	col ++;
+
+      s ++;
+    }
+  }
+
+  return (col);
+}
+
+
+/*
+ * End of "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-get.c b/tools/gator/daemon/mxml/mxml-get.c
new file mode 100644
index 000000000000..40ed3d0839b4
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-get.c
@@ -0,0 +1,452 @@
+/*
+ * "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node get functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlGetCDATA()' - Get the value for a CDATA node.
+ *
+ * @code NULL@ is returned if the node is not a CDATA element.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - CDATA value or NULL */
+mxmlGetCDATA(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT ||
+      strncmp(node->value.element.name, "![CDATA[", 8))
+    return (NULL);
+
+ /*
+  * Return the text following the CDATA declaration...
+  */
+
+  return (node->value.element.name + 8);
+}
+
+
+/*
+ * 'mxmlGetCustom()' - Get the value for a custom node.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a custom
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const void *				/* O - Custom value or NULL */
+mxmlGetCustom(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_CUSTOM)
+    return (node->value.custom.data);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_CUSTOM)
+    return (node->child->value.custom.data);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlGetElement()' - Get the name for an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Element name or NULL */
+mxmlGetElement(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the element name...
+  */
+
+  return (node->value.element.name);
+}
+
+
+/*
+ * 'mxmlGetFirstChild()' - Get the first child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - First child or NULL */
+mxmlGetFirstChild(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the first child node...
+  */
+
+  return (node->child);
+}
+
+
+/*
+ * 'mxmlGetInteger()' - Get the integer value from the specified node or its
+ *                      first child.
+ *
+ * 0 is returned if the node (or its first child) is not an integer value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* O - Integer value or 0 */
+mxmlGetInteger(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_INTEGER)
+    return (node->value.integer);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_INTEGER)
+    return (node->child->value.integer);
+  else
+    return (0);
+}
+
+
+/*
+ * 'mxmlGetLastChild()' - Get the last child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Last child or NULL */
+mxmlGetLastChild(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->last_child);
+}
+
+
+/*
+ * 'mxmlGetNextSibling()' - Get the next node for the current parent.
+ *
+ * @code NULL@ is returned if this is the last child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *
+mxmlGetNextSibling(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->next);
+}
+
+
+/*
+ * 'mxmlGetOpaque()' - Get an opaque string value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not an opaque
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Opaque string or NULL */
+mxmlGetOpaque(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_OPAQUE)
+    return (node->value.opaque);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_OPAQUE)
+    return (node->child->value.opaque);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlGetParent()' - Get the parent node.
+ *
+ * @code NULL@ is returned for a root node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Parent node or NULL */
+mxmlGetParent(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->parent);
+}
+
+
+/*
+ * 'mxmlGetPrevSibling()' - Get the previous node for the current parent.
+ *
+ * @code NULL@ is returned if this is the first child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Previous node or NULL */
+mxmlGetPrevSibling(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->prev);
+}
+
+
+/*
+ * 'mxmlGetReal()' - Get the real value for a node or its first child.
+ *
+ * 0.0 is returned if the node (or its first child) is not a real value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+double					/* O - Real value or 0.0 */
+mxmlGetReal(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0.0);
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_REAL)
+    return (node->value.real);
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_REAL)
+    return (node->child->value.real);
+  else
+    return (0.0);
+}
+
+
+/*
+ * 'mxmlGetText()' - Get the text value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a text node.
+ * The "whitespace" argument can be NULL.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char *				/* O - Text string or NULL */
+mxmlGetText(mxml_node_t *node,		/* I - Node to get */
+            int         *whitespace)	/* O - 1 if string is preceded by whitespace, 0 otherwise */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+  {
+    if (whitespace)
+      *whitespace = 0;
+
+    return (NULL);
+  }
+
+ /*
+  * Return the integer value...
+  */
+
+  if (node->type == MXML_TEXT)
+  {
+    if (whitespace)
+      *whitespace = node->value.text.whitespace;
+
+    return (node->value.text.string);
+  }
+  else if (node->type == MXML_ELEMENT &&
+           node->child &&
+	   node->child->type == MXML_TEXT)
+  {
+    if (whitespace)
+      *whitespace = node->child->value.text.whitespace;
+
+    return (node->child->value.text.string);
+  }
+  else
+  {
+    if (whitespace)
+      *whitespace = 0;
+
+    return (NULL);
+  }
+}
+
+
+/*
+ * 'mxmlGetType()' - Get the node type.
+ *
+ * @code MXML_IGNORE@ is returned if "node" is @code NULL@.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_type_t				/* O - Type of node */
+mxmlGetType(mxml_node_t *node)		/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (MXML_IGNORE);
+
+ /*
+  * Return the node type...
+  */
+
+  return (node->type);
+}
+
+
+/*
+ * 'mxmlGetUserData()' - Get the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+void *					/* O - User data pointer */
+mxmlGetUserData(mxml_node_t *node)	/* I - Node to get */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Return the user data pointer...
+  */
+
+  return (node->user_data);
+}
+
+
+/*
+ * End of "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-index.c b/tools/gator/daemon/mxml/mxml-index.c
new file mode 100644
index 000000000000..10814390d3a0
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-index.c
@@ -0,0 +1,659 @@
+/*
+ * "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Index support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Sort functions...
+ */
+
+static int	index_compare(mxml_index_t *ind, mxml_node_t *first,
+		              mxml_node_t *second);
+static int	index_find(mxml_index_t *ind, const char *element,
+		           const char *value, mxml_node_t *node);
+static void	index_sort(mxml_index_t *ind, int left, int right);
+
+
+/*
+ * 'mxmlIndexDelete()' - Delete an index.
+ */
+
+void
+mxmlIndexDelete(mxml_index_t *ind)	/* I - Index to delete */
+{
+ /*
+  * Range check input..
+  */
+
+  if (!ind)
+    return;
+
+ /*
+  * Free memory...
+  */
+
+  if (ind->attr)
+    free(ind->attr);
+
+  if (ind->alloc_nodes)
+    free(ind->nodes);
+
+  free(ind);
+}
+
+
+/*
+ * 'mxmlIndexEnum()' - Return the next node in the index.
+ *
+ * Nodes are returned in the sorted order of the index.
+ */
+
+mxml_node_t *				/* O - Next node or NULL if there is none */
+mxmlIndexEnum(mxml_index_t *ind)	/* I - Index to enumerate */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (NULL);
+
+ /*
+  * Return the next node...
+  */
+
+  if (ind->cur_node < ind->num_nodes)
+    return (ind->nodes[ind->cur_node ++]);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexFind()' - Find the next matching node.
+ *
+ * You should call mxmlIndexReset() prior to using this function for
+ * the first time with a particular set of "element" and "value"
+ * strings. Passing NULL for both "element" and "value" is equivalent
+ * to calling mxmlIndexEnum().
+ */
+
+mxml_node_t *				/* O - Node or NULL if none found */
+mxmlIndexFind(mxml_index_t *ind,	/* I - Index to search */
+              const char   *element,	/* I - Element name to find, if any */
+	      const char   *value)	/* I - Attribute value, if any */
+{
+  int		diff,			/* Difference between names */
+		current,		/* Current entity in search */
+		first,			/* First entity in search */
+		last;			/* Last entity in search */
+
+
+#ifdef DEBUG
+  printf("mxmlIndexFind(ind=%p, element=\"%s\", value=\"%s\")\n",
+         ind, element ? element : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!ind || (!ind->attr && value))
+  {
+#ifdef DEBUG
+    puts("    returning NULL...");
+    printf("    ind->attr=\"%s\"\n", ind->attr ? ind->attr : "(null)");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+
+ /*
+  * If both element and value are NULL, just enumerate the nodes in the
+  * index...
+  */
+
+  if (!element && !value)
+    return (mxmlIndexEnum(ind));
+
+ /*
+  * If there are no nodes in the index, return NULL...
+  */
+
+  if (!ind->num_nodes)
+  {
+#ifdef DEBUG
+    puts("    returning NULL...");
+    puts("    no nodes!");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+
+ /*
+  * If cur_node == 0, then find the first matching node...
+  */
+
+  if (ind->cur_node == 0)
+  {
+   /*
+    * Find the first node using a modified binary search algorithm...
+    */
+
+    first = 0;
+    last  = ind->num_nodes - 1;
+
+#ifdef DEBUG
+    printf("    find first time, num_nodes=%d...\n", ind->num_nodes);
+#endif /* DEBUG */
+
+    while ((last - first) > 1)
+    {
+      current = (first + last) / 2;
+
+#ifdef DEBUG
+      printf("    first=%d, last=%d, current=%d\n", first, last, current);
+#endif /* DEBUG */
+
+      if ((diff = index_find(ind, element, value, ind->nodes[current])) == 0)
+      {
+       /*
+        * Found a match, move back to find the first...
+	*/
+
+#ifdef DEBUG
+        puts("    match!");
+#endif /* DEBUG */
+
+        while (current > 0 &&
+	       !index_find(ind, element, value, ind->nodes[current - 1]))
+	  current --;
+
+#ifdef DEBUG
+        printf("    returning first match=%d\n", current);
+#endif /* DEBUG */
+
+       /*
+        * Return the first match and save the index to the next...
+	*/
+
+        ind->cur_node = current + 1;
+
+	return (ind->nodes[current]);
+      }
+      else if (diff < 0)
+	last = current;
+      else
+	first = current;
+
+#ifdef DEBUG
+      printf("    diff=%d\n", diff);
+#endif /* DEBUG */
+    }
+
+   /*
+    * If we get this far, then we found exactly 0 or 1 matches...
+    */
+
+    for (current = first; current <= last; current ++)
+      if (!index_find(ind, element, value, ind->nodes[current]))
+      {
+       /*
+	* Found exactly one (or possibly two) match...
+	*/
+
+#ifdef DEBUG
+	printf("    returning only match %d...\n", current);
+#endif /* DEBUG */
+
+	ind->cur_node = current + 1;
+
+	return (ind->nodes[current]);
+      }
+
+   /*
+    * No matches...
+    */
+
+    ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+    puts("    returning NULL...");
+#endif /* DEBUG */
+
+    return (NULL);
+  }
+  else if (ind->cur_node < ind->num_nodes &&
+           !index_find(ind, element, value, ind->nodes[ind->cur_node]))
+  {
+   /*
+    * Return the next matching node...
+    */
+
+#ifdef DEBUG
+    printf("    returning next match %d...\n", ind->cur_node);
+#endif /* DEBUG */
+
+    return (ind->nodes[ind->cur_node ++]);
+  }
+
+ /*
+  * If we get this far, then we have no matches...
+  */
+
+  ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+  puts("    returning NULL...");
+#endif /* DEBUG */
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexGetCount()' - Get the number of nodes in an index.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* I - Number of nodes in index */
+mxmlIndexGetCount(mxml_index_t *ind)	/* I - Index of nodes */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (0);
+
+ /*
+  * Return the number of nodes in the index...
+  */
+
+  return (ind->num_nodes);
+}
+
+
+/*
+ * 'mxmlIndexNew()' - Create a new index.
+ *
+ * The index will contain all nodes that contain the named element and/or
+ * attribute. If both "element" and "attr" are NULL, then the index will
+ * contain a sorted list of the elements in the node tree.  Nodes are
+ * sorted by element name and optionally by attribute value if the "attr"
+ * argument is not NULL.
+ */
+
+mxml_index_t *				/* O - New index */
+mxmlIndexNew(mxml_node_t *node,		/* I - XML node tree */
+             const char  *element,	/* I - Element to index or NULL for all */
+             const char  *attr)		/* I - Attribute to index or NULL for none */
+{
+  mxml_index_t	*ind;			/* New index */
+  mxml_node_t	*current,		/* Current node in index */
+  		**temp;			/* Temporary node pointer array */
+
+
+ /*
+  * Range check input...
+  */
+
+#ifdef DEBUG
+  printf("mxmlIndexNew(node=%p, element=\"%s\", attr=\"%s\")\n",
+         node, element ? element : "(null)", attr ? attr : "(null)");
+#endif /* DEBUG */
+
+  if (!node)
+    return (NULL);
+
+ /*
+  * Create a new index...
+  */
+
+  if ((ind = calloc(1, sizeof(mxml_index_t))) == NULL)
+  {
+    mxml_error("Unable to allocate %d bytes for index - %s",
+               sizeof(mxml_index_t), strerror(errno));
+    return (NULL);
+  }
+
+  if (attr)
+    ind->attr = strdup(attr);
+
+  if (!element && !attr)
+    current = node;
+  else
+    current = mxmlFindElement(node, node, element, attr, NULL, MXML_DESCEND);
+
+  while (current)
+  {
+    if (ind->num_nodes >= ind->alloc_nodes)
+    {
+      if (!ind->alloc_nodes)
+        temp = malloc(64 * sizeof(mxml_node_t *));
+      else
+        temp = realloc(ind->nodes, (ind->alloc_nodes + 64) * sizeof(mxml_node_t *));
+
+      if (!temp)
+      {
+       /*
+        * Unable to allocate memory for the index, so abort...
+	*/
+
+        mxml_error("Unable to allocate %d bytes for index: %s",
+	           (ind->alloc_nodes + 64) * sizeof(mxml_node_t *),
+		   strerror(errno));
+
+        mxmlIndexDelete(ind);
+	return (NULL);
+      }
+
+      ind->nodes       = temp;
+      ind->alloc_nodes += 64;
+    }
+
+    ind->nodes[ind->num_nodes ++] = current;
+
+    current = mxmlFindElement(current, node, element, attr, NULL, MXML_DESCEND);
+  }
+
+ /*
+  * Sort nodes based upon the search criteria...
+  */
+
+#ifdef DEBUG
+  {
+    int i;				/* Looping var */
+
+
+    printf("%d node(s) in index.\n\n", ind->num_nodes);
+
+    if (attr)
+    {
+      printf("Node      Address   Element         %s\n", attr);
+      puts("--------  --------  --------------  ------------------------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %-14.14s  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name,
+	       mxmlElementGetAttr(ind->nodes[i], attr));
+    }
+    else
+    {
+      puts("Node      Address   Element");
+      puts("--------  --------  --------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name);
+    }
+
+    putchar('\n');
+  }
+#endif /* DEBUG */
+
+  if (ind->num_nodes > 1)
+    index_sort(ind, 0, ind->num_nodes - 1);
+
+#ifdef DEBUG
+  {
+    int i;				/* Looping var */
+
+
+    puts("After sorting:\n");
+
+    if (attr)
+    {
+      printf("Node      Address   Element         %s\n", attr);
+      puts("--------  --------  --------------  ------------------------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %-14.14s  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name,
+	       mxmlElementGetAttr(ind->nodes[i], attr));
+    }
+    else
+    {
+      puts("Node      Address   Element");
+      puts("--------  --------  --------------");
+
+      for (i = 0; i < ind->num_nodes; i ++)
+	printf("%8d  %-8p  %s\n", i, ind->nodes[i],
+	       ind->nodes[i]->value.element.name);
+    }
+
+    putchar('\n');
+  }
+#endif /* DEBUG */
+
+ /*
+  * Return the new index...
+  */
+
+  return (ind);
+}
+
+
+/*
+ * 'mxmlIndexReset()' - Reset the enumeration/find pointer in the index and
+ *                      return the first node in the index.
+ *
+ * This function should be called prior to using mxmlIndexEnum() or
+ * mxmlIndexFind() for the first time.
+ */
+
+mxml_node_t *				/* O - First node or NULL if there is none */
+mxmlIndexReset(mxml_index_t *ind)	/* I - Index to reset */
+{
+#ifdef DEBUG
+  printf("mxmlIndexReset(ind=%p)\n", ind);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!ind)
+    return (NULL);
+
+ /*
+  * Set the index to the first element...
+  */
+
+  ind->cur_node = 0;
+
+ /*
+  * Return the first node...
+  */
+
+  if (ind->num_nodes)
+    return (ind->nodes[0]);
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'index_compare()' - Compare two nodes.
+ */
+
+static int				/* O - Result of comparison */
+index_compare(mxml_index_t *ind,	/* I - Index */
+              mxml_node_t  *first,	/* I - First node */
+              mxml_node_t  *second)	/* I - Second node */
+{
+  int	diff;				/* Difference */
+
+
+ /*
+  * Check the element name...
+  */
+
+  if ((diff = strcmp(first->value.element.name,
+                     second->value.element.name)) != 0)
+    return (diff);
+
+ /*
+  * Check the attribute value...
+  */
+
+  if (ind->attr)
+  {
+    if ((diff = strcmp(mxmlElementGetAttr(first, ind->attr),
+                       mxmlElementGetAttr(second, ind->attr))) != 0)
+      return (diff);
+  }
+
+ /*
+  * No difference, return 0...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'index_find()' - Compare a node with index values.
+ */
+
+static int				/* O - Result of comparison */
+index_find(mxml_index_t *ind,		/* I - Index */
+           const char   *element,	/* I - Element name or NULL */
+	   const char   *value,		/* I - Attribute value or NULL */
+           mxml_node_t  *node)		/* I - Node */
+{
+  int	diff;				/* Difference */
+
+
+ /*
+  * Check the element name...
+  */
+
+  if (element)
+  {
+    if ((diff = strcmp(element, node->value.element.name)) != 0)
+      return (diff);
+  }
+
+ /*
+  * Check the attribute value...
+  */
+
+  if (value)
+  {
+    if ((diff = strcmp(value, mxmlElementGetAttr(node, ind->attr))) != 0)
+      return (diff);
+  }
+
+ /*
+  * No difference, return 0...
+  */
+
+  return (0);
+}
+
+
+/*
+ * 'index_sort()' - Sort the nodes in the index...
+ *
+ * This function implements the classic quicksort algorithm...
+ */
+
+static void
+index_sort(mxml_index_t *ind,		/* I - Index to sort */
+           int          left,		/* I - Left node in partition */
+	   int          right)		/* I - Right node in partition */
+{
+  mxml_node_t	*pivot,			/* Pivot node */
+		*temp;			/* Swap node */
+  int		templ,			/* Temporary left node */
+		tempr;			/* Temporary right node */
+
+
+ /*
+  * Loop until we have sorted all the way to the right...
+  */
+
+  do
+  {
+   /*
+    * Sort the pivot in the current partition...
+    */
+
+    pivot = ind->nodes[left];
+
+    for (templ = left, tempr = right; templ < tempr;)
+    {
+     /*
+      * Move left while left node <= pivot node...
+      */
+
+      while ((templ < right) &&
+             index_compare(ind, ind->nodes[templ], pivot) <= 0)
+	templ ++;
+
+     /*
+      * Move right while right node > pivot node...
+      */
+
+      while ((tempr > left) &&
+             index_compare(ind, ind->nodes[tempr], pivot) > 0)
+	tempr --;
+
+     /*
+      * Swap nodes if needed...
+      */
+
+      if (templ < tempr)
+      {
+	temp              = ind->nodes[templ];
+	ind->nodes[templ] = ind->nodes[tempr];
+	ind->nodes[tempr] = temp;
+      }
+    }
+
+   /*
+    * When we get here, the right (tempr) node is the new position for the
+    * pivot node...
+    */
+
+    if (index_compare(ind, pivot, ind->nodes[tempr]) > 0)
+    {
+      ind->nodes[left]  = ind->nodes[tempr];
+      ind->nodes[tempr] = pivot;
+    }
+
+   /*
+    * Recursively sort the left partition as needed...
+    */
+
+    if (left < (tempr - 1))
+      index_sort(ind, left, tempr - 1);
+  }
+  while (right > (left = tempr + 1));
+}
+
+
+/*
+ * End of "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-node.c b/tools/gator/daemon/mxml/mxml-node.c
new file mode 100644
index 000000000000..128cda1a4cf2
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-node.c
@@ -0,0 +1,788 @@
+/*
+ * "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static mxml_node_t	*mxml_new(mxml_node_t *parent, mxml_type_t type);
+
+
+/*
+ * 'mxmlAdd()' - Add a node to a tree.
+ *
+ * Adds the specified node to the parent. If the child argument is not
+ * NULL, puts the new node before or after the specified child depending
+ * on the value of the where argument. If the child argument is NULL,
+ * puts the new node at the beginning of the child list (MXML_ADD_BEFORE)
+ * or at the end of the child list (MXML_ADD_AFTER). The constant
+ * MXML_ADD_TO_PARENT can be used to specify a NULL child pointer.
+ */
+
+void
+mxmlAdd(mxml_node_t *parent,		/* I - Parent node */
+        int         where,		/* I - Where to add, MXML_ADD_BEFORE or MXML_ADD_AFTER */
+        mxml_node_t *child,		/* I - Child node for where or MXML_ADD_TO_PARENT */
+	mxml_node_t *node)		/* I - Node to add */
+{
+#ifdef DEBUG
+  fprintf(stderr, "mxmlAdd(parent=%p, where=%d, child=%p, node=%p)\n", parent,
+          where, child, node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!parent || !node)
+    return;
+
+#if DEBUG > 1
+  fprintf(stderr, "    BEFORE: node->parent=%p\n", node->parent);
+  if (parent)
+  {
+    fprintf(stderr, "    BEFORE: parent->child=%p\n", parent->child);
+    fprintf(stderr, "    BEFORE: parent->last_child=%p\n", parent->last_child);
+    fprintf(stderr, "    BEFORE: parent->prev=%p\n", parent->prev);
+    fprintf(stderr, "    BEFORE: parent->next=%p\n", parent->next);
+  }
+#endif /* DEBUG > 1 */
+
+ /*
+  * Remove the node from any existing parent...
+  */
+
+  if (node->parent)
+    mxmlRemove(node);
+
+ /*
+  * Reset pointers...
+  */
+
+  node->parent = parent;
+
+  switch (where)
+  {
+    case MXML_ADD_BEFORE :
+        if (!child || child == parent->child || child->parent != parent)
+	{
+	 /*
+	  * Insert as first node under parent...
+	  */
+
+	  node->next = parent->child;
+
+	  if (parent->child)
+	    parent->child->prev = node;
+	  else
+	    parent->last_child = node;
+
+	  parent->child = node;
+	}
+	else
+	{
+	 /*
+	  * Insert node before this child...
+	  */
+
+	  node->next = child;
+	  node->prev = child->prev;
+
+	  if (child->prev)
+	    child->prev->next = node;
+	  else
+	    parent->child = node;
+
+	  child->prev = node;
+	}
+        break;
+
+    case MXML_ADD_AFTER :
+        if (!child || child == parent->last_child || child->parent != parent)
+	{
+	 /*
+	  * Insert as last node under parent...
+	  */
+
+	  node->parent = parent;
+	  node->prev   = parent->last_child;
+
+	  if (parent->last_child)
+	    parent->last_child->next = node;
+	  else
+	    parent->child = node;
+
+	  parent->last_child = node;
+        }
+	else
+	{
+	 /*
+	  * Insert node after this child...
+	  */
+
+	  node->prev = child;
+	  node->next = child->next;
+
+	  if (child->next)
+	    child->next->prev = node;
+	  else
+	    parent->last_child = node;
+
+	  child->next = node;
+	}
+        break;
+  }
+
+#if DEBUG > 1
+  fprintf(stderr, "    AFTER: node->parent=%p\n", node->parent);
+  if (parent)
+  {
+    fprintf(stderr, "    AFTER: parent->child=%p\n", parent->child);
+    fprintf(stderr, "    AFTER: parent->last_child=%p\n", parent->last_child);
+    fprintf(stderr, "    AFTER: parent->prev=%p\n", parent->prev);
+    fprintf(stderr, "    AFTER: parent->next=%p\n", parent->next);
+  }
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlDelete()' - Delete a node and all of its children.
+ *
+ * If the specified node has a parent, this function first removes the
+ * node from its parent using the mxmlRemove() function.
+ */
+
+void
+mxmlDelete(mxml_node_t *node)		/* I - Node to delete */
+{
+  int	i;				/* Looping var */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlDelete(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return;
+
+ /*
+  * Remove the node from its parent, if any...
+  */
+
+  mxmlRemove(node);
+
+ /*
+  * Delete children...
+  */
+
+  while (node->child)
+    mxmlDelete(node->child);
+
+ /*
+  * Now delete any node data...
+  */
+
+  switch (node->type)
+  {
+    case MXML_ELEMENT :
+        if (node->value.element.name)
+	  free(node->value.element.name);
+
+	if (node->value.element.num_attrs)
+	{
+	  for (i = 0; i < node->value.element.num_attrs; i ++)
+	  {
+	    if (node->value.element.attrs[i].name)
+	      free(node->value.element.attrs[i].name);
+	    if (node->value.element.attrs[i].value)
+	      free(node->value.element.attrs[i].value);
+	  }
+
+          free(node->value.element.attrs);
+	}
+        break;
+    case MXML_INTEGER :
+       /* Nothing to do */
+        break;
+    case MXML_OPAQUE :
+        if (node->value.opaque)
+	  free(node->value.opaque);
+        break;
+    case MXML_REAL :
+       /* Nothing to do */
+        break;
+    case MXML_TEXT :
+        if (node->value.text.string)
+	  free(node->value.text.string);
+        break;
+    case MXML_CUSTOM :
+        if (node->value.custom.data &&
+	    node->value.custom.destroy)
+	  (*(node->value.custom.destroy))(node->value.custom.data);
+	break;
+    default :
+        break;
+  }
+
+ /*
+  * Free this node...
+  */
+
+  free(node);
+}
+
+
+/*
+ * 'mxmlGetRefCount()' - Get the current reference (use) count for a node.
+ *
+ * The initial reference count of new nodes is 1. Use the @link mxmlRetain@
+ * and @link mxmlRelease@ functions to increment and decrement a node's
+ * reference count.
+ *
+ * @since Mini-XML 2.7@.
+ */
+
+int					/* O - Reference count */
+mxmlGetRefCount(mxml_node_t *node)	/* I - Node */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (0);
+
+ /*
+  * Return the reference count...
+  */
+
+  return (node->ref_count);
+}
+
+
+/*
+ * 'mxmlNewCDATA()' - Create a new CDATA node.
+ *
+ * The new CDATA node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * CDATA node has no parent. The data string must be nul-terminated and
+ * is copied into the new node. CDATA nodes use the MXML_ELEMENT type.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewCDATA(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+	     const char  *data)		/* I - Data string */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewCDATA(parent=%p, data=\"%s\")\n",
+          parent, data ? data : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!data)
+    return (NULL);
+
+ /*
+  * Create the node and set the name value...
+  */
+
+  if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+    node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewCustom()' - Create a new custom data node.
+ *
+ * The new custom node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent. NULL can be passed when the data in the
+ * node is not dynamically allocated or is separately managed.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewCustom(
+    mxml_node_t              *parent,	/* I - Parent node or MXML_NO_PARENT */
+    void                     *data,	/* I - Pointer to data */
+    mxml_custom_destroy_cb_t destroy)	/* I - Function to destroy data */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewCustom(parent=%p, data=%p, destroy=%p)\n", parent,
+          data, destroy);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the value...
+  */
+
+  if ((node = mxml_new(parent, MXML_CUSTOM)) != NULL)
+  {
+    node->value.custom.data    = data;
+    node->value.custom.destroy = destroy;
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewElement()' - Create a new element node.
+ *
+ * The new element node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewElement(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+               const char  *name)	/* I - Name of element */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewElement(parent=%p, name=\"%s\")\n", parent,
+          name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!name)
+    return (NULL);
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+    node->value.element.name = strdup(name);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewInteger()' - Create a new integer node.
+ *
+ * The new integer node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * integer node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewInteger(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+               int         integer)	/* I - Integer value */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewInteger(parent=%p, integer=%d)\n", parent, integer);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_INTEGER)) != NULL)
+    node->value.integer = integer;
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewOpaque()' - Create a new opaque string.
+ *
+ * The new opaque node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * opaque node has no parent. The opaque string must be nul-terminated and
+ * is copied into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewOpaque(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+              const char  *opaque)	/* I - Opaque string */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewOpaque(parent=%p, opaque=\"%s\")\n", parent,
+          opaque ? opaque : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!opaque)
+    return (NULL);
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_OPAQUE)) != NULL)
+    node->value.opaque = strdup(opaque);
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewReal()' - Create a new real number node.
+ *
+ * The new real number node is added to the end of the specified parent's
+ * child list. The constant MXML_NO_PARENT can be used to specify that
+ * the new real number node has no parent.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewReal(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+            double      real)		/* I - Real number value */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewReal(parent=%p, real=%g)\n", parent, real);
+#endif /* DEBUG */
+
+ /*
+  * Create the node and set the element name...
+  */
+
+  if ((node = mxml_new(parent, MXML_REAL)) != NULL)
+    node->value.real = real;
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewText()' - Create a new text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The text
+ * string must be nul-terminated and is copied into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewText(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+            int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	    const char  *string)	/* I - String */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewText(parent=%p, whitespace=%d, string=\"%s\")\n",
+          parent, whitespace, string ? string : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!string)
+    return (NULL);
+
+ /*
+  * Create the node and set the text value...
+  */
+
+  if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+  {
+    node->value.text.whitespace = whitespace;
+    node->value.text.string     = strdup(string);
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlNewTextf()' - Create a new formatted text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The format
+ * string must be nul-terminated and is formatted into the new node.
+ */
+
+mxml_node_t *				/* O - New node */
+mxmlNewTextf(mxml_node_t *parent,	/* I - Parent node or MXML_NO_PARENT */
+             int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	     const char  *format,	/* I - Printf-style frmat string */
+	     ...)			/* I - Additional args as needed */
+{
+  mxml_node_t	*node;			/* New node */
+  va_list	ap;			/* Pointer to arguments */
+
+
+#ifdef DEBUG
+  fprintf(stderr, "mxmlNewTextf(parent=%p, whitespace=%d, format=\"%s\", ...)\n",
+          parent, whitespace, format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!format)
+    return (NULL);
+
+ /*
+  * Create the node and set the text value...
+  */
+
+  if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+  {
+    va_start(ap, format);
+
+    node->value.text.whitespace = whitespace;
+    node->value.text.string     = _mxml_vstrdupf(format, ap);
+
+    va_end(ap);
+  }
+
+  return (node);
+}
+
+
+/*
+ * 'mxmlRemove()' - Remove a node from its parent.
+ *
+ * Does not free memory used by the node - use mxmlDelete() for that.
+ * This function does nothing if the node has no parent.
+ */
+
+void
+mxmlRemove(mxml_node_t *node)		/* I - Node to remove */
+{
+#ifdef DEBUG
+  fprintf(stderr, "mxmlRemove(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || !node->parent)
+    return;
+
+ /*
+  * Remove from parent...
+  */
+
+#if DEBUG > 1
+  fprintf(stderr, "    BEFORE: node->parent=%p\n", node->parent);
+  if (node->parent)
+  {
+    fprintf(stderr, "    BEFORE: node->parent->child=%p\n", node->parent->child);
+    fprintf(stderr, "    BEFORE: node->parent->last_child=%p\n", node->parent->last_child);
+  }
+  fprintf(stderr, "    BEFORE: node->child=%p\n", node->child);
+  fprintf(stderr, "    BEFORE: node->last_child=%p\n", node->last_child);
+  fprintf(stderr, "    BEFORE: node->prev=%p\n", node->prev);
+  fprintf(stderr, "    BEFORE: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+
+  if (node->prev)
+    node->prev->next = node->next;
+  else
+    node->parent->child = node->next;
+
+  if (node->next)
+    node->next->prev = node->prev;
+  else
+    node->parent->last_child = node->prev;
+
+  node->parent = NULL;
+  node->prev   = NULL;
+  node->next   = NULL;
+
+#if DEBUG > 1
+  fprintf(stderr, "    AFTER: node->parent=%p\n", node->parent);
+  if (node->parent)
+  {
+    fprintf(stderr, "    AFTER: node->parent->child=%p\n", node->parent->child);
+    fprintf(stderr, "    AFTER: node->parent->last_child=%p\n", node->parent->last_child);
+  }
+  fprintf(stderr, "    AFTER: node->child=%p\n", node->child);
+  fprintf(stderr, "    AFTER: node->last_child=%p\n", node->last_child);
+  fprintf(stderr, "    AFTER: node->prev=%p\n", node->prev);
+  fprintf(stderr, "    AFTER: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlNewXML()' - Create a new XML document tree.
+ *
+ * The "version" argument specifies the version number to put in the
+ * ?xml element node. If NULL, version 1.0 is assumed.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t *				/* O - New ?xml node */
+mxmlNewXML(const char *version)		/* I - Version number to use */
+{
+  char	element[1024];			/* Element text */
+
+
+  snprintf(element, sizeof(element), "?xml version=\"%s\" encoding=\"utf-8\"?",
+           version ? version : "1.0");
+
+  return (mxmlNewElement(NULL, element));
+}
+
+
+/*
+ * 'mxmlRelease()' - Release a node.
+ *
+ * When the reference count reaches zero, the node (and any children)
+ * is deleted via mxmlDelete().
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - New reference count */
+mxmlRelease(mxml_node_t *node)		/* I - Node */
+{
+  if (node)
+  {
+    if ((-- node->ref_count) <= 0)
+    {
+      mxmlDelete(node);
+      return (0);
+    }
+    else
+      return (node->ref_count);
+  }
+  else
+    return (-1);
+}
+
+
+/*
+ * 'mxmlRetain()' - Retain a node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - New reference count */
+mxmlRetain(mxml_node_t *node)		/* I - Node */
+{
+  if (node)
+    return (++ node->ref_count);
+  else
+    return (-1);
+}
+
+
+/*
+ * 'mxml_new()' - Create a new node.
+ */
+
+static mxml_node_t *			/* O - New node */
+mxml_new(mxml_node_t *parent,		/* I - Parent node */
+         mxml_type_t type)		/* I - Node type */
+{
+  mxml_node_t	*node;			/* New node */
+
+
+#if DEBUG > 1
+  fprintf(stderr, "mxml_new(parent=%p, type=%d)\n", parent, type);
+#endif /* DEBUG > 1 */
+
+ /*
+  * Allocate memory for the node...
+  */
+
+  if ((node = calloc(1, sizeof(mxml_node_t))) == NULL)
+  {
+#if DEBUG > 1
+    fputs("    returning NULL\n", stderr);
+#endif /* DEBUG > 1 */
+
+    return (NULL);
+  }
+
+#if DEBUG > 1
+  fprintf(stderr, "    returning %p\n", node);
+#endif /* DEBUG > 1 */
+
+ /*
+  * Set the node type...
+  */
+
+  node->type      = type;
+  node->ref_count = 1;
+
+ /*
+  * Add to the parent if present...
+  */
+
+  if (parent)
+    mxmlAdd(parent, MXML_ADD_AFTER, MXML_ADD_TO_PARENT, node);
+
+ /*
+  * Return the new node...
+  */
+
+  return (node);
+}
+
+
+/*
+ * End of "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.c b/tools/gator/daemon/mxml/mxml-private.c
new file mode 100644
index 000000000000..bec4bbfbf378
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.c
@@ -0,0 +1,323 @@
+/*
+ * "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * Some crazy people think that unloading a shared object is a good or safe
+ * thing to do.  Unfortunately, most objects are simply *not* safe to unload
+ * and bad things *will* happen.
+ *
+ * The following mess of conditional code allows us to provide a destructor
+ * function in Mini-XML for our thread-global storage so that it can possibly
+ * be unloaded safely, although since there is no standard way to do so I
+ * can't even provide any guarantees that you can do it safely on all platforms.
+ *
+ * This code currently supports AIX, HP-UX, Linux, Mac OS X, Solaris, and
+ * Windows.  It might work on the BSDs and IRIX, but I haven't tested that.
+ */
+
+#if defined(__sun) || defined(_AIX)
+#  pragma fini(_mxml_fini)
+#  define _MXML_FINI _mxml_fini
+#elif defined(__hpux)
+#  pragma FINI _mxml_fini
+#  define _MXML_FINI _mxml_fini
+#elif defined(__GNUC__) /* Linux and Mac OS X */
+#  define _MXML_FINI __attribute((destructor)) _mxml_fini
+#else
+#  define _MXML_FINI _fini
+#endif /* __sun */
+
+
+/*
+ * 'mxml_error()' - Display an error message.
+ */
+
+void
+mxml_error(const char *format,		/* I - Printf-style format string */
+           ...)				/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to arguments */
+  char		s[1024];		/* Message string */
+  _mxml_global_t *global = _mxml_global();
+					/* Global data */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!format)
+    return;
+
+ /*
+  * Format the error message string...
+  */
+
+  va_start(ap, format);
+
+  vsnprintf(s, sizeof(s), format, ap);
+
+  va_end(ap);
+
+ /*
+  * And then display the error message...
+  */
+
+  if (global->error_cb)
+    (*global->error_cb)(s);
+  else
+    fprintf(stderr, "mxml: %s\n", s);
+}
+
+
+/*
+ * 'mxml_ignore_cb()' - Default callback for ignored values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_ignore_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_IGNORE);
+}
+
+
+/*
+ * 'mxml_integer_cb()' - Default callback for integer values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_integer_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_INTEGER);
+}
+
+
+/*
+ * 'mxml_opaque_cb()' - Default callback for opaque values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_opaque_cb(mxml_node_t *node)	/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_OPAQUE);
+}
+
+
+/*
+ * 'mxml_real_cb()' - Default callback for real number values.
+ */
+
+mxml_type_t				/* O - Node type */
+mxml_real_cb(mxml_node_t *node)		/* I - Current node */
+{
+  (void)node;
+
+  return (MXML_REAL);
+}
+
+
+#ifdef HAVE_PTHREAD_H			/**** POSIX threading ****/
+#  include <pthread.h>
+
+static pthread_key_t	_mxml_key = -1;	/* Thread local storage key */
+static pthread_once_t	_mxml_key_once = PTHREAD_ONCE_INIT;
+					/* One-time initialization object */
+static void		_mxml_init(void);
+static void		_mxml_destructor(void *g);
+
+
+/*
+ * '_mxml_destructor()' - Free memory used for globals...
+ */
+
+static void
+_mxml_destructor(void *g)		/* I - Global data */
+{
+  free(g);
+}
+
+
+/*
+ * '_mxml_fini()' - Clean up when unloaded.
+ */
+
+static void
+_MXML_FINI(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  if (_mxml_key != -1)
+  {
+    if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) != NULL)
+      _mxml_destructor(global);
+
+    pthread_key_delete(_mxml_key);
+    _mxml_key = -1;
+  }
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  pthread_once(&_mxml_key_once, _mxml_init);
+
+  if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) == NULL)
+  {
+    global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+    pthread_setspecific(_mxml_key, global);
+
+    global->num_entity_cbs = 1;
+    global->entity_cbs[0]  = _mxml_entity_cb;
+    global->wrap           = 72;
+  }
+
+  return (global);
+}
+
+
+/*
+ * '_mxml_init()' - Initialize global data...
+ */
+
+static void
+_mxml_init(void)
+{
+  pthread_key_create(&_mxml_key, _mxml_destructor);
+}
+
+
+#elif defined(WIN32) && defined(MXML1_EXPORTS) /**** WIN32 threading ****/
+#  include <windows.h>
+
+static DWORD _mxml_tls_index;		/* Index for global storage */
+
+
+/*
+ * 'DllMain()' - Main entry for library.
+ */
+
+BOOL WINAPI				/* O - Success/failure */
+DllMain(HINSTANCE hinst,		/* I - DLL module handle */
+        DWORD     reason,		/* I - Reason */
+        LPVOID    reserved)		/* I - Unused */
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  (void)hinst;
+  (void)reserved;
+
+  switch (reason)
+  {
+    case DLL_PROCESS_ATTACH :		/* Called on library initialization */
+        if ((_mxml_tls_index = TlsAlloc()) == TLS_OUT_OF_INDEXES)
+          return (FALSE);
+        break;
+
+    case DLL_THREAD_DETACH :		/* Called when a thread terminates */
+        if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+          free(global);
+        break;
+
+    case DLL_PROCESS_DETACH :		/* Called when library is unloaded */
+        if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+          free(global);
+
+        TlsFree(_mxml_tls_index);
+        break;
+
+    default:
+        break;
+  }
+
+  return (TRUE);
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  _mxml_global_t	*global;	/* Global data */
+
+
+  if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) == NULL)
+  {
+    global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+
+    global->num_entity_cbs = 1;
+    global->entity_cbs[0]  = _mxml_entity_cb;
+    global->wrap           = 72;
+
+    TlsSetValue(_mxml_tls_index, (LPVOID)global);
+  }
+
+  return (global);
+}
+
+
+#else					/**** No threading ****/
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t *			/* O - Global data */
+_mxml_global(void)
+{
+  static _mxml_global_t	global =	/* Global data */
+  {
+    NULL,				/* error_cb */
+    1,					/* num_entity_cbs */
+    { _mxml_entity_cb },		/* entity_cbs */
+    72,					/* wrap */
+    NULL,				/* custom_load_cb */
+    NULL				/* custom_save_cb */
+  };
+
+
+  return (&global);
+}
+#endif /* HAVE_PTHREAD_H */
+
+
+/*
+ * End of "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.h b/tools/gator/daemon/mxml/mxml-private.h
new file mode 100644
index 000000000000..c5e4e6b6f27a
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.h
@@ -0,0 +1,50 @@
+/*
+ * "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private definitions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Global, per-thread data...
+ */
+
+typedef struct _mxml_global_s
+{
+  void	(*error_cb)(const char *);
+  int	num_entity_cbs;
+  int	(*entity_cbs[100])(const char *name);
+  int	wrap;
+  mxml_custom_load_cb_t	custom_load_cb;
+  mxml_custom_save_cb_t	custom_save_cb;
+} _mxml_global_t;
+
+
+/*
+ * Functions...
+ */
+
+extern _mxml_global_t	*_mxml_global(void);
+extern int		_mxml_entity_cb(const char *name);
+
+
+/*
+ * End of "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-search.c b/tools/gator/daemon/mxml/mxml-search.c
new file mode 100644
index 000000000000..313a52f0ce2f
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-search.c
@@ -0,0 +1,280 @@
+/*
+ * "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Search/navigation functions for Mini-XML, a small XML-like file
+ * parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlFindElement()' - Find the named element.
+ *
+ * The search is constrained by the name, attribute name, and value; any
+ * NULL names or values are treated as wildcards, so different kinds of
+ * searches can be implemented by looking for all elements of a given name
+ * or all elements with a specific attribute. The descend argument determines
+ * whether the search descends into child nodes; normally you will use
+ * MXML_DESCEND_FIRST for the initial search and MXML_NO_DESCEND to find
+ * additional direct descendents of the node. The top node argument
+ * constrains the search to a particular node's children.
+ */
+
+mxml_node_t *				/* O - Element node or NULL */
+mxmlFindElement(mxml_node_t *node,	/* I - Current node */
+                mxml_node_t *top,	/* I - Top node */
+                const char  *name,	/* I - Element name or NULL for any */
+		const char  *attr,	/* I - Attribute name, or NULL for none */
+		const char  *value,	/* I - Attribute value, or NULL for any */
+		int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  const char	*temp;			/* Current attribute value */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!node || !top || (!attr && value))
+    return (NULL);
+
+ /*
+  * Start with the next node...
+  */
+
+  node = mxmlWalkNext(node, top, descend);
+
+ /*
+  * Loop until we find a matching element...
+  */
+
+  while (node != NULL)
+  {
+   /*
+    * See if this node matches...
+    */
+
+    if (node->type == MXML_ELEMENT &&
+        node->value.element.name &&
+	(!name || !strcmp(node->value.element.name, name)))
+    {
+     /*
+      * See if we need to check for an attribute...
+      */
+
+      if (!attr)
+        return (node);			/* No attribute search, return it... */
+
+     /*
+      * Check for the attribute...
+      */
+
+      if ((temp = mxmlElementGetAttr(node, attr)) != NULL)
+      {
+       /*
+        * OK, we have the attribute, does it match?
+	*/
+
+	if (!value || !strcmp(value, temp))
+	  return (node);		/* Yes, return it... */
+      }
+    }
+
+   /*
+    * No match, move on to the next node...
+    */
+
+    if (descend == MXML_DESCEND)
+      node = mxmlWalkNext(node, top, MXML_DESCEND);
+    else
+      node = node->next;
+  }
+
+  return (NULL);
+}
+
+
+/*
+ * 'mxmlFindPath()' - Find a node with the given path.
+ *
+ * The "path" is a slash-separated list of element names. The name "*" is
+ * considered a wildcard for one or more levels of elements.  For example,
+ * "foo/one/two", "bar/two/one", "*\/one", and so forth.
+ *
+ * The first child node of the found node is returned if the given node has
+ * children and the first child is a value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *				/* O - Found node or NULL */
+mxmlFindPath(mxml_node_t *top,		/* I - Top node */
+	     const char  *path)		/* I - Path to element */
+{
+  mxml_node_t	*node;			/* Current node */
+  char		element[256];		/* Current element name */
+  const char	*pathsep;		/* Separator in path */
+  int		descend;		/* mxmlFindElement option */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (!top || !path || !*path)
+    return (NULL);
+
+ /*
+  * Search each element in the path...
+  */
+
+  node = top;
+  while (*path)
+  {
+   /*
+    * Handle wildcards...
+    */
+
+    if (!strncmp(path, "*/", 2))
+    {
+      path += 2;
+      descend = MXML_DESCEND;
+    }
+    else
+      descend = MXML_DESCEND_FIRST;
+
+   /*
+    * Get the next element in the path...
+    */
+
+    if ((pathsep = strchr(path, '/')) == NULL)
+      pathsep = path + strlen(path);
+
+    if (pathsep == path || (pathsep - path) >= sizeof(element))
+      return (NULL);
+
+    memcpy(element, path, pathsep - path);
+    element[pathsep - path] = '\0';
+
+    if (*pathsep)
+      path = pathsep + 1;
+    else
+      path = pathsep;
+
+   /*
+    * Search for the element...
+    */
+
+    if ((node = mxmlFindElement(node, node, element, NULL, NULL,
+                                descend)) == NULL)
+      return (NULL);
+  }
+
+ /*
+  * If we get this far, return the node or its first child...
+  */
+
+  if (node->child && node->child->type != MXML_ELEMENT)
+    return (node->child);
+  else
+    return (node);
+}
+
+
+/*
+ * 'mxmlWalkNext()' - Walk to the next logical node in the tree.
+ *
+ * The descend argument controls whether the first child is considered
+ * to be the next node. The top node argument constrains the walk to
+ * the node's children.
+ */
+
+mxml_node_t *				/* O - Next node or NULL */
+mxmlWalkNext(mxml_node_t *node,		/* I - Current node */
+             mxml_node_t *top,		/* I - Top node */
+             int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  if (!node)
+    return (NULL);
+  else if (node->child && descend)
+    return (node->child);
+  else if (node == top)
+    return (NULL);
+  else if (node->next)
+    return (node->next);
+  else if (node->parent && node->parent != top)
+  {
+    node = node->parent;
+
+    while (!node->next)
+      if (node->parent == top || !node->parent)
+        return (NULL);
+      else
+        node = node->parent;
+
+    return (node->next);
+  }
+  else
+    return (NULL);
+}
+
+
+/*
+ * 'mxmlWalkPrev()' - Walk to the previous logical node in the tree.
+ *
+ * The descend argument controls whether the previous node's last child
+ * is considered to be the previous node. The top node argument constrains
+ * the walk to the node's children.
+ */
+
+mxml_node_t *				/* O - Previous node or NULL */
+mxmlWalkPrev(mxml_node_t *node,		/* I - Current node */
+             mxml_node_t *top,		/* I - Top node */
+             int         descend)	/* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+  if (!node || node == top)
+    return (NULL);
+  else if (node->prev)
+  {
+    if (node->prev->last_child && descend)
+    {
+     /*
+      * Find the last child under the previous node...
+      */
+
+      node = node->prev->last_child;
+
+      while (node->last_child)
+        node = node->last_child;
+
+      return (node);
+    }
+    else
+      return (node->prev);
+  }
+  else if (node->parent != top)
+    return (node->parent);
+  else
+    return (NULL);
+}
+
+
+/*
+ * End of "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-set.c b/tools/gator/daemon/mxml/mxml-set.c
new file mode 100644
index 000000000000..16d4bf1050dd
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-set.c
@@ -0,0 +1,337 @@
+/*
+ * "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node set functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlSetCDATA()' - Set the element name of a CDATA node.
+ *
+ * The node is not changed if it (or its first child) is not a CDATA element node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetCDATA(mxml_node_t *node,		/* I - Node to set */
+             const char  *data)		/* I - New data string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      strncmp(node->value.element.name, "![CDATA[", 8) &&
+      node->child && node->child->type == MXML_ELEMENT &&
+      !strncmp(node->child->value.element.name, "![CDATA[", 8))
+    node = node->child;
+
+  if (!node || node->type != MXML_ELEMENT || !data ||
+      strncmp(node->value.element.name, "![CDATA[", 8))
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.element.name)
+    free(node->value.element.name);
+
+  node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetCustom()' - Set the data and destructor of a custom data node.
+ *
+ * The node is not changed if it (or its first child) is not a custom node.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetCustom(
+    mxml_node_t              *node,	/* I - Node to set */
+    void                     *data,	/* I - New data pointer */
+    mxml_custom_destroy_cb_t destroy)	/* I - New destructor function */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_CUSTOM)
+    node = node->child;
+
+  if (!node || node->type != MXML_CUSTOM)
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.custom.data && node->value.custom.destroy)
+    (*(node->value.custom.destroy))(node->value.custom.data);
+
+  node->value.custom.data    = data;
+  node->value.custom.destroy = destroy;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetElement()' - Set the name of an element node.
+ *
+ * The node is not changed if it is not an element node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetElement(mxml_node_t *node,	/* I - Node to set */
+               const char  *name)	/* I - New name string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node || node->type != MXML_ELEMENT || !name)
+    return (-1);
+
+ /*
+  * Free any old element value and set the new value...
+  */
+
+  if (node->value.element.name)
+    free(node->value.element.name);
+
+  node->value.element.name = strdup(name);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetInteger()' - Set the value of an integer node.
+ *
+ * The node is not changed if it (or its first child) is not an integer node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetInteger(mxml_node_t *node,	/* I - Node to set */
+               int         integer)	/* I - Integer value */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_INTEGER)
+    node = node->child;
+
+  if (!node || node->type != MXML_INTEGER)
+    return (-1);
+
+ /*
+  * Set the new value and return...
+  */
+
+  node->value.integer = integer;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetOpaque()' - Set the value of an opaque node.
+ *
+ * The node is not changed if it (or its first child) is not an opaque node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetOpaque(mxml_node_t *node,	/* I - Node to set */
+              const char  *opaque)	/* I - Opaque string */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_OPAQUE)
+    node = node->child;
+
+  if (!node || node->type != MXML_OPAQUE || !opaque)
+    return (-1);
+
+ /*
+  * Free any old opaque value and set the new value...
+  */
+
+  if (node->value.opaque)
+    free(node->value.opaque);
+
+  node->value.opaque = strdup(opaque);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetReal()' - Set the value of a real number node.
+ *
+ * The node is not changed if it (or its first child) is not a real number node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetReal(mxml_node_t *node,		/* I - Node to set */
+            double      real)		/* I - Real number value */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_REAL)
+    node = node->child;
+
+  if (!node || node->type != MXML_REAL)
+    return (-1);
+
+ /*
+  * Set the new value and return...
+  */
+
+  node->value.real = real;
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetText()' - Set the value of a text node.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetText(mxml_node_t *node,		/* I - Node to set */
+            int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+	    const char  *string)	/* I - String */
+{
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_TEXT)
+    node = node->child;
+
+  if (!node || node->type != MXML_TEXT || !string)
+    return (-1);
+
+ /*
+  * Free any old string value and set the new value...
+  */
+
+  if (node->value.text.string)
+    free(node->value.text.string);
+
+  node->value.text.whitespace = whitespace;
+  node->value.text.string     = strdup(string);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetTextf()' - Set the value of a text node to a formatted string.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetTextf(mxml_node_t *node,		/* I - Node to set */
+             int         whitespace,	/* I - 1 = leading whitespace, 0 = no whitespace */
+             const char  *format,	/* I - Printf-style format string */
+	     ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to arguments */
+
+
+ /*
+  * Range check input...
+  */
+
+  if (node && node->type == MXML_ELEMENT &&
+      node->child && node->child->type == MXML_TEXT)
+    node = node->child;
+
+  if (!node || node->type != MXML_TEXT || !format)
+    return (-1);
+
+ /*
+  * Free any old string value and set the new value...
+  */
+
+  if (node->value.text.string)
+    free(node->value.text.string);
+
+  va_start(ap, format);
+
+  node->value.text.whitespace = whitespace;
+  node->value.text.string     = _mxml_strdupf(format, ap);
+
+  va_end(ap);
+
+  return (0);
+}
+
+
+/*
+ * 'mxmlSetUserData()' - Set the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int					/* O - 0 on success, -1 on failure */
+mxmlSetUserData(mxml_node_t *node,	/* I - Node to set */
+                void        *data)	/* I - User data pointer */
+{
+ /*
+  * Range check input...
+  */
+
+  if (!node)
+    return (-1);
+
+ /*
+  * Set the user data pointer and return...
+  */
+
+  node->user_data = data;
+  return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-string.c b/tools/gator/daemon/mxml/mxml-string.c
new file mode 100644
index 000000000000..9d5b58e6adb7
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-string.c
@@ -0,0 +1,469 @@
+/*
+ * "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $"
+ *
+ * String functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+
+
+/*
+ * The va_copy macro is part of C99, but many compilers don't implement it.
+ * Provide a "direct assignment" implmentation when va_copy isn't defined...
+ */
+
+#ifndef va_copy
+#  ifdef __va_copy
+#    define va_copy(dst,src) __va_copy(dst,src)
+#  else
+#    define va_copy(dst,src) memcpy(&dst, src, sizeof(va_list))
+#  endif /* __va_copy */
+#endif /* va_copy */
+
+
+#ifndef HAVE_SNPRINTF
+/*
+ * '_mxml_snprintf()' - Format a string.
+ */
+
+int					/* O - Number of bytes formatted */
+_mxml_snprintf(char       *buffer,	/* I - Output buffer */
+               size_t     bufsize,	/* I - Size of output buffer */
+	       const char *format,	/* I - Printf-style format string */
+	       ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Argument list */
+  int		bytes;			/* Number of bytes formatted */
+
+
+  va_start(ap, format);
+  bytes = vsnprintf(buffer, bufsize, format, ap);
+  va_end(ap);
+
+  return (bytes);
+}
+#endif /* !HAVE_SNPRINTF */
+
+
+/*
+ * '_mxml_strdup()' - Duplicate a string.
+ */
+
+#ifndef HAVE_STRDUP
+char *					/* O - New string pointer */
+_mxml_strdup(const char *s)		/* I - String to duplicate */
+{
+  char	*t;				/* New string pointer */
+
+
+  if (s == NULL)
+    return (NULL);
+
+  if ((t = malloc(strlen(s) + 1)) == NULL)
+    return (NULL);
+
+  return (strcpy(t, s));
+}
+#endif /* !HAVE_STRDUP */
+
+
+/*
+ * '_mxml_strdupf()' - Format and duplicate a string.
+ */
+
+char *					/* O - New string pointer */
+_mxml_strdupf(const char *format,	/* I - Printf-style format string */
+              ...)			/* I - Additional arguments as needed */
+{
+  va_list	ap;			/* Pointer to additional arguments */
+  char		*s;			/* Pointer to formatted string */
+
+
+ /*
+  * Get a pointer to the additional arguments, format the string,
+  * and return it...
+  */
+
+  va_start(ap, format);
+  s = _mxml_vstrdupf(format, ap);
+  va_end(ap);
+
+  return (s);
+}
+
+
+#ifndef HAVE_VSNPRINTF
+/*
+ * '_mxml_vsnprintf()' - Format a string into a fixed size buffer.
+ */
+
+int					/* O - Number of bytes formatted */
+_mxml_vsnprintf(char       *buffer,	/* O - Output buffer */
+                size_t     bufsize,	/* O - Size of output buffer */
+		const char *format,	/* I - Printf-style format string */
+ 		va_list    ap)		/* I - Pointer to additional arguments */
+{
+  char		*bufptr,		/* Pointer to position in buffer */
+		*bufend,		/* Pointer to end of buffer */
+		sign,			/* Sign of format width */
+		size,			/* Size character (h, l, L) */
+		type;			/* Format type character */
+  int		width,			/* Width of field */
+		prec;			/* Number of characters of precision */
+  char		tformat[100],		/* Temporary format string for sprintf() */
+		*tptr,			/* Pointer into temporary format */
+		temp[1024];		/* Buffer for formatted numbers */
+  char		*s;			/* Pointer to string */
+  int		slen;			/* Length of string */
+  int		bytes;			/* Total number of bytes needed */
+
+
+ /*
+  * Loop through the format string, formatting as needed...
+  */
+
+  bufptr = buffer;
+  bufend = buffer + bufsize - 1;
+  bytes  = 0;
+
+  while (*format)
+  {
+    if (*format == '%')
+    {
+      tptr = tformat;
+      *tptr++ = *format++;
+
+      if (*format == '%')
+      {
+        if (bufptr && bufptr < bufend)
+          *bufptr++ = *format;
+        bytes ++;
+        format ++;
+	continue;
+      }
+      else if (strchr(" -+#\'", *format))
+      {
+        *tptr++ = *format;
+        sign = *format++;
+      }
+      else
+        sign = 0;
+
+      if (*format == '*')
+      {
+       /*
+        * Get width from argument...
+	*/
+
+	format ++;
+	width = va_arg(ap, int);
+
+	snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", width);
+	tptr += strlen(tptr);
+      }
+      else
+      {
+	width = 0;
+
+	while (isdigit(*format & 255))
+	{
+	  if (tptr < (tformat + sizeof(tformat) - 1))
+	    *tptr++ = *format;
+
+	  width = width * 10 + *format++ - '0';
+	}
+      }
+
+      if (*format == '.')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        format ++;
+
+        if (*format == '*')
+	{
+         /*
+	  * Get precision from argument...
+	  */
+
+	  format ++;
+	  prec = va_arg(ap, int);
+
+	  snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", prec);
+	  tptr += strlen(tptr);
+	}
+	else
+	{
+	  prec = 0;
+
+	  while (isdigit(*format & 255))
+	  {
+	    if (tptr < (tformat + sizeof(tformat) - 1))
+	      *tptr++ = *format;
+
+	    prec = prec * 10 + *format++ - '0';
+	  }
+	}
+      }
+      else
+        prec = -1;
+
+      if (*format == 'l' && format[1] == 'l')
+      {
+        size = 'L';
+
+	if (tptr < (tformat + sizeof(tformat) - 2))
+	{
+	  *tptr++ = 'l';
+	  *tptr++ = 'l';
+	}
+
+	format += 2;
+      }
+      else if (*format == 'h' || *format == 'l' || *format == 'L')
+      {
+	if (tptr < (tformat + sizeof(tformat) - 1))
+	  *tptr++ = *format;
+
+        size = *format++;
+      }
+
+      if (!*format)
+        break;
+
+      if (tptr < (tformat + sizeof(tformat) - 1))
+        *tptr++ = *format;
+
+      type  = *format++;
+      *tptr = '\0';
+
+      switch (type)
+      {
+	case 'E' : /* Floating point formats */
+	case 'G' :
+	case 'e' :
+	case 'f' :
+	case 'g' :
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+	    sprintf(temp, tformat, va_arg(ap, double));
+
+            bytes += strlen(temp);
+
+            if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+        case 'B' : /* Integer formats */
+	case 'X' :
+	case 'b' :
+        case 'd' :
+	case 'i' :
+	case 'o' :
+	case 'u' :
+	case 'x' :
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+#ifdef HAVE_LONG_LONG
+	    if (size == 'L')
+	      sprintf(temp, tformat, va_arg(ap, long long));
+	    else
+#endif /* HAVE_LONG_LONG */
+	    sprintf(temp, tformat, va_arg(ap, int));
+
+            bytes += strlen(temp);
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+	case 'p' : /* Pointer value */
+	    if ((width + 2) > sizeof(temp))
+	      break;
+
+	    sprintf(temp, tformat, va_arg(ap, void *));
+
+            bytes += strlen(temp);
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + strlen(temp)) > bufend)
+	      {
+		strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+		bufptr = bufend;
+	      }
+	      else
+	      {
+		strcpy(bufptr, temp);
+		bufptr += strlen(temp);
+	      }
+	    }
+	    break;
+
+        case 'c' : /* Character or character array */
+	    bytes += width;
+
+	    if (bufptr)
+	    {
+	      if (width <= 1)
+	        *bufptr++ = va_arg(ap, int);
+	      else
+	      {
+		if ((bufptr + width) > bufend)
+		  width = bufend - bufptr;
+
+		memcpy(bufptr, va_arg(ap, char *), (size_t)width);
+		bufptr += width;
+	      }
+	    }
+	    break;
+
+	case 's' : /* String */
+	    if ((s = va_arg(ap, char *)) == NULL)
+	      s = "(null)";
+
+	    slen = strlen(s);
+	    if (slen > width && prec != width)
+	      width = slen;
+
+            bytes += width;
+
+	    if (bufptr)
+	    {
+	      if ((bufptr + width) > bufend)
+	        width = bufend - bufptr;
+
+              if (slen > width)
+	        slen = width;
+
+	      if (sign == '-')
+	      {
+		strncpy(bufptr, s, (size_t)slen);
+		memset(bufptr + slen, ' ', (size_t)(width - slen));
+	      }
+	      else
+	      {
+		memset(bufptr, ' ', (size_t)(width - slen));
+		strncpy(bufptr + width - slen, s, (size_t)slen);
+	      }
+
+	      bufptr += width;
+	    }
+	    break;
+
+	case 'n' : /* Output number of chars so far */
+	    *(va_arg(ap, int *)) = bytes;
+	    break;
+      }
+    }
+    else
+    {
+      bytes ++;
+
+      if (bufptr && bufptr < bufend)
+        *bufptr++ = *format;
+
+      format ++;
+    }
+  }
+
+ /*
+  * Nul-terminate the string and return the number of characters needed.
+  */
+
+  *bufptr = '\0';
+
+  return (bytes);
+}
+#endif /* !HAVE_VSNPRINTF */
+
+
+/*
+ * '_mxml_vstrdupf()' - Format and duplicate a string.
+ */
+
+char *					/* O - New string pointer */
+_mxml_vstrdupf(const char *format,	/* I - Printf-style format string */
+               va_list    ap)		/* I - Pointer to additional arguments */
+{
+  int		bytes;			/* Number of bytes required */
+  char		*buffer,		/* String buffer */
+		temp[256];		/* Small buffer for first vsnprintf */
+  va_list	apcopy;			/* Copy of argument list */
+
+
+ /*
+  * First format with a tiny buffer; this will tell us how many bytes are
+  * needed...
+  */
+
+  va_copy(apcopy, ap);
+  bytes = vsnprintf(temp, sizeof(temp), format, apcopy);
+
+  if (bytes < sizeof(temp))
+  {
+   /*
+    * Hey, the formatted string fits in the tiny buffer, so just dup that...
+    */
+
+    return (strdup(temp));
+  }
+
+ /*
+  * Allocate memory for the whole thing and reformat to the new, larger
+  * buffer...
+  */
+
+  if ((buffer = calloc(1, bytes + 1)) != NULL)
+    vsnprintf(buffer, bytes + 1, format, ap);
+
+ /*
+  * Return the new string...
+  */
+
+  return (buffer);
+}
+
+
+/*
+ * End of "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml.h b/tools/gator/daemon/mxml/mxml.h
new file mode 100644
index 000000000000..bba5fd23a67b
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml.h
@@ -0,0 +1,332 @@
+/*
+ * "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Header file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law.  Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file.  If this file is
+ * missing or damaged, see the license at:
+ *
+ *     http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Prevent multiple inclusion...
+ */
+
+#ifndef _mxml_h_
+#  define _mxml_h_
+
+/*
+ * Include necessary headers...
+ */
+
+#  include <stdio.h>
+#  include <stdlib.h>
+#  include <string.h>
+#  include <ctype.h>
+#  include <errno.h>
+
+
+/*
+ * Constants...
+ */
+
+#  define MXML_MAJOR_VERSION	2	/* Major version number */
+#  define MXML_MINOR_VERSION	8	/* Minor version number */
+
+#  define MXML_TAB		8	/* Tabs every N columns */
+
+#  define MXML_NO_CALLBACK	0	/* Don't use a type callback */
+#  define MXML_INTEGER_CALLBACK	mxml_integer_cb
+					/* Treat all data as integers */
+#  define MXML_OPAQUE_CALLBACK	mxml_opaque_cb
+					/* Treat all data as opaque */
+#  define MXML_REAL_CALLBACK	mxml_real_cb
+					/* Treat all data as real numbers */
+#  define MXML_TEXT_CALLBACK	0	/* Treat all data as text */
+#  define MXML_IGNORE_CALLBACK	mxml_ignore_cb
+					/* Ignore all non-element content */
+
+#  define MXML_NO_PARENT	0	/* No parent for the node */
+
+#  define MXML_DESCEND		1	/* Descend when finding/walking */
+#  define MXML_NO_DESCEND	0	/* Don't descend when finding/walking */
+#  define MXML_DESCEND_FIRST	-1	/* Descend for first find */
+
+#  define MXML_WS_BEFORE_OPEN	0	/* Callback for before open tag */
+#  define MXML_WS_AFTER_OPEN	1	/* Callback for after open tag */
+#  define MXML_WS_BEFORE_CLOSE	2	/* Callback for before close tag */
+#  define MXML_WS_AFTER_CLOSE	3	/* Callback for after close tag */
+
+#  define MXML_ADD_BEFORE	0	/* Add node before specified node */
+#  define MXML_ADD_AFTER	1	/* Add node after specified node */
+#  define MXML_ADD_TO_PARENT	NULL	/* Add node relative to parent */
+
+
+/*
+ * Data types...
+ */
+
+typedef enum mxml_sax_event_e		/**** SAX event type. ****/
+{
+  MXML_SAX_CDATA,			/* CDATA node */
+  MXML_SAX_COMMENT,			/* Comment node */
+  MXML_SAX_DATA,			/* Data node */
+  MXML_SAX_DIRECTIVE,			/* Processing directive node */
+  MXML_SAX_ELEMENT_CLOSE,		/* Element closed */
+  MXML_SAX_ELEMENT_OPEN			/* Element opened */
+} mxml_sax_event_t;
+
+typedef enum mxml_type_e		/**** The XML node type. ****/
+{
+  MXML_IGNORE = -1,			/* Ignore/throw away node @since Mini-XML 2.3@ */
+  MXML_ELEMENT,				/* XML element with attributes */
+  MXML_INTEGER,				/* Integer value */
+  MXML_OPAQUE,				/* Opaque string */
+  MXML_REAL,				/* Real value */
+  MXML_TEXT,				/* Text fragment */
+  MXML_CUSTOM				/* Custom data @since Mini-XML 2.1@ */
+} mxml_type_t;
+
+typedef void (*mxml_custom_destroy_cb_t)(void *);
+					/**** Custom data destructor ****/
+
+typedef void (*mxml_error_cb_t)(const char *);
+					/**** Error callback function ****/
+
+typedef struct mxml_attr_s		/**** An XML element attribute value. @private@ ****/
+{
+  char			*name;		/* Attribute name */
+  char			*value;		/* Attribute value */
+} mxml_attr_t;
+
+typedef struct mxml_element_s		/**** An XML element value. @private@ ****/
+{
+  char			*name;		/* Name of element */
+  int			num_attrs;	/* Number of attributes */
+  mxml_attr_t		*attrs;		/* Attributes */
+} mxml_element_t;
+
+typedef struct mxml_text_s		/**** An XML text value. @private@ ****/
+{
+  int			whitespace;	/* Leading whitespace? */
+  char			*string;	/* Fragment string */
+} mxml_text_t;
+
+typedef struct mxml_custom_s		/**** An XML custom value. @private@ ****/
+{
+  void			*data;		/* Pointer to (allocated) custom data */
+  mxml_custom_destroy_cb_t destroy;	/* Pointer to destructor function */
+} mxml_custom_t;
+
+typedef union mxml_value_u		/**** An XML node value. @private@ ****/
+{
+  mxml_element_t	element;	/* Element */
+  int			integer;	/* Integer number */
+  char			*opaque;	/* Opaque string */
+  double		real;		/* Real number */
+  mxml_text_t		text;		/* Text fragment */
+  mxml_custom_t		custom;		/* Custom data @since Mini-XML 2.1@ */
+} mxml_value_t;
+
+struct mxml_node_s			/**** An XML node. @private@ ****/
+{
+  mxml_type_t		type;		/* Node type */
+  struct mxml_node_s	*next;		/* Next node under same parent */
+  struct mxml_node_s	*prev;		/* Previous node under same parent */
+  struct mxml_node_s	*parent;	/* Parent node */
+  struct mxml_node_s	*child;		/* First child node */
+  struct mxml_node_s	*last_child;	/* Last child node */
+  mxml_value_t		value;		/* Node value */
+  int			ref_count;	/* Use count */
+  void			*user_data;	/* User data */
+};
+
+typedef struct mxml_node_s mxml_node_t;	/**** An XML node. ****/
+
+struct mxml_index_s			 /**** An XML node index. @private@ ****/
+{
+  char			*attr;		/* Attribute used for indexing or NULL */
+  int			num_nodes;	/* Number of nodes in index */
+  int			alloc_nodes;	/* Allocated nodes in index */
+  int			cur_node;	/* Current node */
+  mxml_node_t		**nodes;	/* Node array */
+};
+
+typedef struct mxml_index_s mxml_index_t;
+					/**** An XML node index. ****/
+
+typedef int (*mxml_custom_load_cb_t)(mxml_node_t *, const char *);
+					/**** Custom data load callback function ****/
+
+typedef char *(*mxml_custom_save_cb_t)(mxml_node_t *);
+					/**** Custom data save callback function ****/
+
+typedef int (*mxml_entity_cb_t)(const char *);
+					/**** Entity callback function */
+
+typedef mxml_type_t (*mxml_load_cb_t)(mxml_node_t *);
+					/**** Load callback function ****/
+
+typedef const char *(*mxml_save_cb_t)(mxml_node_t *, int);
+					/**** Save callback function ****/
+
+typedef void (*mxml_sax_cb_t)(mxml_node_t *, mxml_sax_event_t, void *);
+					/**** SAX callback function ****/
+
+
+/*
+ * C++ support...
+ */
+
+#  ifdef __cplusplus
+extern "C" {
+#  endif /* __cplusplus */
+
+/*
+ * Prototypes...
+ */
+
+extern void		mxmlAdd(mxml_node_t *parent, int where,
+			        mxml_node_t *child, mxml_node_t *node);
+extern void		mxmlDelete(mxml_node_t *node);
+extern void		mxmlElementDeleteAttr(mxml_node_t *node,
+			                      const char *name);
+extern const char	*mxmlElementGetAttr(mxml_node_t *node, const char *name);
+extern void		mxmlElementSetAttr(mxml_node_t *node, const char *name,
+			                   const char *value);
+extern void		mxmlElementSetAttrf(mxml_node_t *node, const char *name,
+			                    const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern int		mxmlEntityAddCallback(mxml_entity_cb_t cb);
+extern const char	*mxmlEntityGetName(int val);
+extern int		mxmlEntityGetValue(const char *name);
+extern void		mxmlEntityRemoveCallback(mxml_entity_cb_t cb);
+extern mxml_node_t	*mxmlFindElement(mxml_node_t *node, mxml_node_t *top,
+			                 const char *name, const char *attr,
+					 const char *value, int descend);
+extern mxml_node_t	*mxmlFindPath(mxml_node_t *node, const char *path);
+extern const char	*mxmlGetCDATA(mxml_node_t *node);
+extern const void	*mxmlGetCustom(mxml_node_t *node);
+extern const char	*mxmlGetElement(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetFirstChild(mxml_node_t *node);
+extern int		mxmlGetInteger(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetLastChild(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetNextSibling(mxml_node_t *node);
+extern const char	*mxmlGetOpaque(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetParent(mxml_node_t *node);
+extern mxml_node_t	*mxmlGetPrevSibling(mxml_node_t *node);
+extern double		mxmlGetReal(mxml_node_t *node);
+extern int		mxmlGetRefCount(mxml_node_t *node);
+extern const char	*mxmlGetText(mxml_node_t *node, int *whitespace);
+extern mxml_type_t	mxmlGetType(mxml_node_t *node);
+extern void		*mxmlGetUserData(mxml_node_t *node);
+extern void		mxmlIndexDelete(mxml_index_t *ind);
+extern mxml_node_t	*mxmlIndexEnum(mxml_index_t *ind);
+extern mxml_node_t	*mxmlIndexFind(mxml_index_t *ind,
+			               const char *element,
+			               const char *value);
+extern int		mxmlIndexGetCount(mxml_index_t *ind);
+extern mxml_index_t	*mxmlIndexNew(mxml_node_t *node, const char *element,
+			              const char *attr);
+extern mxml_node_t	*mxmlIndexReset(mxml_index_t *ind);
+extern mxml_node_t	*mxmlLoadFd(mxml_node_t *top, int fd,
+			            mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlLoadFile(mxml_node_t *top, FILE *fp,
+			              mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlLoadString(mxml_node_t *top, const char *s,
+			                mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t	*mxmlNewCDATA(mxml_node_t *parent, const char *string);
+extern mxml_node_t	*mxmlNewCustom(mxml_node_t *parent, void *data,
+			               mxml_custom_destroy_cb_t destroy);
+extern mxml_node_t	*mxmlNewElement(mxml_node_t *parent, const char *name);
+extern mxml_node_t	*mxmlNewInteger(mxml_node_t *parent, int integer);
+extern mxml_node_t	*mxmlNewOpaque(mxml_node_t *parent, const char *opaque);
+extern mxml_node_t	*mxmlNewReal(mxml_node_t *parent, double real);
+extern mxml_node_t	*mxmlNewText(mxml_node_t *parent, int whitespace,
+			             const char *string);
+extern mxml_node_t	*mxmlNewTextf(mxml_node_t *parent, int whitespace,
+			              const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern mxml_node_t	*mxmlNewXML(const char *version);
+extern int		mxmlRelease(mxml_node_t *node);
+extern void		mxmlRemove(mxml_node_t *node);
+extern int		mxmlRetain(mxml_node_t *node);
+extern char		*mxmlSaveAllocString(mxml_node_t *node,
+			        	     mxml_save_cb_t cb);
+extern int		mxmlSaveFd(mxml_node_t *node, int fd,
+			           mxml_save_cb_t cb);
+extern int		mxmlSaveFile(mxml_node_t *node, FILE *fp,
+			             mxml_save_cb_t cb);
+extern int		mxmlSaveString(mxml_node_t *node, char *buffer,
+			               int bufsize, mxml_save_cb_t cb);
+extern mxml_node_t	*mxmlSAXLoadFd(mxml_node_t *top, int fd,
+			               mxml_type_t (*cb)(mxml_node_t *),
+			               mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t	*mxmlSAXLoadFile(mxml_node_t *top, FILE *fp,
+			                 mxml_type_t (*cb)(mxml_node_t *),
+			                 mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t	*mxmlSAXLoadString(mxml_node_t *top, const char *s,
+			                   mxml_type_t (*cb)(mxml_node_t *),
+			                   mxml_sax_cb_t sax, void *sax_data);
+extern int		mxmlSetCDATA(mxml_node_t *node, const char *data);
+extern int		mxmlSetCustom(mxml_node_t *node, void *data,
+			              mxml_custom_destroy_cb_t destroy);
+extern void		mxmlSetCustomHandlers(mxml_custom_load_cb_t load,
+			                      mxml_custom_save_cb_t save);
+extern int		mxmlSetElement(mxml_node_t *node, const char *name);
+extern void		mxmlSetErrorCallback(mxml_error_cb_t cb);
+extern int		mxmlSetInteger(mxml_node_t *node, int integer);
+extern int		mxmlSetOpaque(mxml_node_t *node, const char *opaque);
+extern int		mxmlSetReal(mxml_node_t *node, double real);
+extern int		mxmlSetText(mxml_node_t *node, int whitespace,
+			            const char *string);
+extern int		mxmlSetTextf(mxml_node_t *node, int whitespace,
+			             const char *format, ...)
+#    ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+#    endif /* __GNUC__ */
+;
+extern int		mxmlSetUserData(mxml_node_t *node, void *data);
+extern void		mxmlSetWrapMargin(int column);
+extern mxml_node_t	*mxmlWalkNext(mxml_node_t *node, mxml_node_t *top,
+			              int descend);
+extern mxml_node_t	*mxmlWalkPrev(mxml_node_t *node, mxml_node_t *top,
+			              int descend);
+
+
+/*
+ * Semi-private functions...
+ */
+
+extern void		mxml_error(const char *format, ...);
+extern mxml_type_t	mxml_ignore_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_integer_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_opaque_cb(mxml_node_t *node);
+extern mxml_type_t	mxml_real_cb(mxml_node_t *node);
+
+
+/*
+ * C++ support...
+ */
+
+#  ifdef __cplusplus
+}
+#  endif /* __cplusplus */
+#endif /* !_mxml_h_ */
+
+
+/*
+ * End of "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 1587ea392ad6..30e8e0c3f117 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4321,6 +4321,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 					      format, len_arg, arg);
 				trace_seq_terminate(&p);
 				trace_seq_puts(s, p.buffer);
+				trace_seq_destroy(&p);
 				arg = arg->next;
 				break;
 			default:
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a59743fa3ef7..0001c9aa8b71 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -36,6 +36,7 @@ struct events_stats {
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
 	u32 nr_unprocessable_samples;
+	u32 nr_unordered_events;
 };
 
 enum hist_column {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5da6ce74c676..c1f20e91f968 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -638,8 +638,7 @@ int perf_session_queue_event(struct perf_session *s, union perf_event *event,
 		return -ETIME;
 
 	if (timestamp < s->ordered_samples.last_flush) {
-		printf("Warning: Timestamp below last timeslice flush\n");
-		return -EINVAL;
+		s->stats.nr_unordered_events++;
 	}
 
 	if (!list_empty(sc)) {
@@ -1135,6 +1134,8 @@ static void perf_session__warn_about_errors(const struct perf_session *session,
 			    "Do you have a KVM guest running and not using 'perf kvm'?\n",
 			    session->stats.nr_unprocessable_samples);
 	}
+	if (session->stats.nr_unordered_events != 0)
+		ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events);
 }
 
 volatile int session_done;
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 32487ed18354..3d5979b23e50 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -4,6 +4,7 @@ TARGETS += efivarfs
 TARGETS += kcmp
 TARGETS += memory-hotplug
 TARGETS += mqueue
+TARGETS += mount
 TARGETS += net
 TARGETS += ptrace
 TARGETS += timers
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
new file mode 100644
index 000000000000..337d853c2b72
--- /dev/null
+++ b/tools/testing/selftests/mount/Makefile
@@ -0,0 +1,17 @@
+# Makefile for mount selftests.
+
+all: unprivileged-remount-test
+
+unprivileged-remount-test: unprivileged-remount-test.c
+	gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test
+
+# Allow specific tests to be selected.
+test_unprivileged_remount: unprivileged-remount-test
+	@if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi
+
+run_tests: all test_unprivileged_remount
+
+clean:
+	rm -f unprivileged-remount-test
+
+.PHONY: all test_unprivileged_remount
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
new file mode 100644
index 000000000000..517785052f1c
--- /dev/null
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -0,0 +1,370 @@
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#ifndef CLONE_NEWNS
+# define CLONE_NEWNS 0x00020000
+#endif
+#ifndef CLONE_NEWUTS
+# define CLONE_NEWUTS 0x04000000
+#endif
+#ifndef CLONE_NEWIPC
+# define CLONE_NEWIPC 0x08000000
+#endif
+#ifndef CLONE_NEWNET
+# define CLONE_NEWNET 0x40000000
+#endif
+#ifndef CLONE_NEWUSER
+# define CLONE_NEWUSER 0x10000000
+#endif
+#ifndef CLONE_NEWPID
+# define CLONE_NEWPID 0x20000000
+#endif
+
+#ifndef MS_REC
+# define MS_REC 16384
+#endif
+#ifndef MS_RELATIME
+# define MS_RELATIME (1 << 21)
+#endif
+#ifndef MS_STRICTATIME
+# define MS_STRICTATIME (1 << 24)
+#endif
+
+static void die(char *fmt, ...)
+{
+	va_list ap;
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
+static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
+{
+	char buf[4096];
+	int fd;
+	ssize_t written;
+	int buf_len;
+
+	buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+	if (buf_len < 0) {
+		die("vsnprintf failed: %s\n",
+		    strerror(errno));
+	}
+	if (buf_len >= sizeof(buf)) {
+		die("vsnprintf output truncated\n");
+	}
+
+	fd = open(filename, O_WRONLY);
+	if (fd < 0) {
+		if ((errno == ENOENT) && enoent_ok)
+			return;
+		die("open of %s failed: %s\n",
+		    filename, strerror(errno));
+	}
+	written = write(fd, buf, buf_len);
+	if (written != buf_len) {
+		if (written >= 0) {
+			die("short write to %s\n", filename);
+		} else {
+			die("write to %s failed: %s\n",
+				filename, strerror(errno));
+		}
+	}
+	if (close(fd) != 0) {
+		die("close of %s failed: %s\n",
+			filename, strerror(errno));
+	}
+}
+
+static void maybe_write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(true, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vmaybe_write_file(false, filename, fmt, ap);
+	va_end(ap);
+
+}
+
+static int read_mnt_flags(const char *path)
+{
+	int ret;
+	struct statvfs stat;
+	int mnt_flags;
+
+	ret = statvfs(path, &stat);
+	if (ret != 0) {
+		die("statvfs of %s failed: %s\n",
+			path, strerror(errno));
+	}
+	if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \
+			ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \
+			ST_SYNCHRONOUS | ST_MANDLOCK)) {
+		die("Unrecognized mount flags\n");
+	}
+	mnt_flags = 0;
+	if (stat.f_flag & ST_RDONLY)
+		mnt_flags |= MS_RDONLY;
+	if (stat.f_flag & ST_NOSUID)
+		mnt_flags |= MS_NOSUID;
+	if (stat.f_flag & ST_NODEV)
+		mnt_flags |= MS_NODEV;
+	if (stat.f_flag & ST_NOEXEC)
+		mnt_flags |= MS_NOEXEC;
+	if (stat.f_flag & ST_NOATIME)
+		mnt_flags |= MS_NOATIME;
+	if (stat.f_flag & ST_NODIRATIME)
+		mnt_flags |= MS_NODIRATIME;
+	if (stat.f_flag & ST_RELATIME)
+		mnt_flags |= MS_RELATIME;
+	if (stat.f_flag & ST_SYNCHRONOUS)
+		mnt_flags |= MS_SYNCHRONOUS;
+	if (stat.f_flag & ST_MANDLOCK)
+		mnt_flags |= ST_MANDLOCK;
+
+	return mnt_flags;
+}
+
+static void create_and_enter_userns(void)
+{
+	uid_t uid;
+	gid_t gid;
+
+	uid = getuid();
+	gid = getgid();
+
+	if (unshare(CLONE_NEWUSER) !=0) {
+		die("unshare(CLONE_NEWUSER) failed: %s\n",
+			strerror(errno));
+	}
+
+	maybe_write_file("/proc/self/setgroups", "deny");
+	write_file("/proc/self/uid_map", "0 %d 1", uid);
+	write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+	if (setgid(0) != 0) {
+		die ("setgid(0) failed %s\n",
+			strerror(errno));
+	}
+	if (setuid(0) != 0) {
+		die("setuid(0) failed %s\n",
+			strerror(errno));
+	}
+}
+
+static
+bool test_unpriv_remount(const char *fstype, const char *mount_options,
+			 int mount_flags, int remount_flags, int invalid_flags)
+{
+	pid_t child;
+
+	child = fork();
+	if (child == -1) {
+		die("fork failed: %s\n",
+			strerror(errno));
+	}
+	if (child != 0) { /* parent */
+		pid_t pid;
+		int status;
+		pid = waitpid(child, &status, 0);
+		if (pid == -1) {
+			die("waitpid failed: %s\n",
+				strerror(errno));
+		}
+		if (pid != child) {
+			die("waited for %d got %d\n",
+				child, pid);
+		}
+		if (!WIFEXITED(status)) {
+			die("child did not terminate cleanly\n");
+		}
+		return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+	}
+
+	create_and_enter_userns();
+	if (unshare(CLONE_NEWNS) != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) {
+		die("mount of %s with options '%s' on /tmp failed: %s\n",
+		    fstype,
+		    mount_options? mount_options : "",
+		    strerror(errno));
+	}
+
+	create_and_enter_userns();
+
+	if (unshare(CLONE_NEWNS) != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	if (mount("/tmp", "/tmp", "none",
+		  MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp failed: %s\n",
+		    strerror(errno));
+	}
+
+	if (mount("/tmp", "/tmp", "none",
+		  MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp with invalid flags "
+		    "succeeded unexpectedly\n");
+	}
+	exit(EXIT_SUCCESS);
+}
+
+static bool test_unpriv_remount_simple(int mount_flags)
+{
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0);
+}
+
+static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
+{
+	return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags,
+				   invalid_flags);
+}
+
+static bool test_priv_mount_unpriv_remount(void)
+{
+	pid_t child;
+	int ret;
+	const char *orig_path = "/dev";
+	const char *dest_path = "/tmp";
+	int orig_mnt_flags, remount_mnt_flags;
+
+	child = fork();
+	if (child == -1) {
+		die("fork failed: %s\n",
+			strerror(errno));
+	}
+	if (child != 0) { /* parent */
+		pid_t pid;
+		int status;
+		pid = waitpid(child, &status, 0);
+		if (pid == -1) {
+			die("waitpid failed: %s\n",
+				strerror(errno));
+		}
+		if (pid != child) {
+			die("waited for %d got %d\n",
+				child, pid);
+		}
+		if (!WIFEXITED(status)) {
+			die("child did not terminate cleanly\n");
+		}
+		return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+	}
+
+	orig_mnt_flags = read_mnt_flags(orig_path);
+
+	create_and_enter_userns();
+	ret = unshare(CLONE_NEWNS);
+	if (ret != 0) {
+		die("unshare(CLONE_NEWNS) failed: %s\n",
+			strerror(errno));
+	}
+
+	ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL);
+	if (ret != 0) {
+		die("recursive bind mount of %s onto %s failed: %s\n",
+			orig_path, dest_path, strerror(errno));
+	}
+
+	ret = mount(dest_path, dest_path, "none",
+		    MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL);
+	if (ret != 0) {
+		/* system("cat /proc/self/mounts"); */
+		die("remount of /tmp failed: %s\n",
+		    strerror(errno));
+	}
+
+	remount_mnt_flags = read_mnt_flags(dest_path);
+	if (orig_mnt_flags != remount_mnt_flags) {
+		die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n",
+			dest_path, orig_path);
+	}
+	exit(EXIT_SUCCESS);
+}
+
+int main(int argc, char **argv)
+{
+	if (!test_unpriv_remount_simple(MS_RDONLY)) {
+		die("MS_RDONLY malfunctions\n");
+	}
+	if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) {
+		die("MS_NODEV malfunctions\n");
+	}
+	if (!test_unpriv_remount_simple(MS_NOSUID)) {
+		die("MS_NOSUID malfunctions\n");
+	}
+	if (!test_unpriv_remount_simple(MS_NOEXEC)) {
+		die("MS_NOEXEC malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_RELATIME,
+				       MS_NOATIME))
+	{
+		die("MS_RELATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_STRICTATIME,
+				       MS_NOATIME))
+	{
+		die("MS_STRICTATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_NOATIME,
+				       MS_STRICTATIME))
+	{
+		die("MS_NOATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME,
+				       MS_NOATIME))
+	{
+		die("MS_RELATIME|MS_NODIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME,
+				       MS_NOATIME))
+	{
+		die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME,
+				       MS_STRICTATIME))
+	{
+		die("MS_NOATIME|MS_DIRATIME malfunctions\n");
+	}
+	if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME))
+	{
+		die("Default atime malfunctions\n");
+	}
+	if (!test_priv_mount_unpriv_remount()) {
+		die("Mount flags unexpectedly changed after remount\n");
+	}
+	return EXIT_SUCCESS;
+}
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index fe1e66b6ef40..a87e99f37c52 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -116,8 +116,8 @@ static const struct {
 	.header = {
 		.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC),
 		.length = cpu_to_le32(sizeof descriptors),
-		.fs_count = 3,
-		.hs_count = 3,
+		.fs_count = cpu_to_le32(3),
+		.hs_count = cpu_to_le32(3),
 	},
 	.fs_descs = {
 		.intf = {
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index bdb71a26ae35..00ea679b3826 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -172,7 +172,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
 							 GFP_ATOMIC);
 				if (likely(r == 0)) {
 					++started;
-					if (unlikely(!virtqueue_kick(vq->vq))
+					if (unlikely(!virtqueue_kick(vq->vq)))
 						r = -1;
 				}
 			} else
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index fbe1a48bd629..fc0c5e603eb4 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -6,6 +6,9 @@ config HAVE_KVM
 config HAVE_KVM_IRQCHIP
        bool
 
+config HAVE_KVM_IRQFD
+       bool
+
 config HAVE_KVM_IRQ_ROUTING
        bool
 
@@ -22,6 +25,10 @@ config KVM_MMIO
 config KVM_ASYNC_PF
        bool
 
+# Toggle to switch between direct notification and batch job
+config KVM_ASYNC_PF_SYNC
+       bool
+
 config HAVE_KVM_MSI
        bool
 
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
new file mode 100644
index 000000000000..01124ef3690a
--- /dev/null
+++ b/virt/kvm/arm/vgic-v2.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (C) 2012,2013 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+static struct vgic_lr vgic_v2_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+	struct vgic_lr lr_desc;
+	u32 val = vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr];
+
+	lr_desc.irq	= val & GICH_LR_VIRTUALID;
+	if (lr_desc.irq <= 15)
+		lr_desc.source	= (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
+	else
+		lr_desc.source = 0;
+	lr_desc.state	= 0;
+
+	if (val & GICH_LR_PENDING_BIT)
+		lr_desc.state |= LR_STATE_PENDING;
+	if (val & GICH_LR_ACTIVE_BIT)
+		lr_desc.state |= LR_STATE_ACTIVE;
+	if (val & GICH_LR_EOI)
+		lr_desc.state |= LR_EOI_INT;
+
+	return lr_desc;
+}
+
+static void vgic_v2_set_lr(struct kvm_vcpu *vcpu, int lr,
+			   struct vgic_lr lr_desc)
+{
+	u32 lr_val = (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) | lr_desc.irq;
+
+	if (lr_desc.state & LR_STATE_PENDING)
+		lr_val |= GICH_LR_PENDING_BIT;
+	if (lr_desc.state & LR_STATE_ACTIVE)
+		lr_val |= GICH_LR_ACTIVE_BIT;
+	if (lr_desc.state & LR_EOI_INT)
+		lr_val |= GICH_LR_EOI;
+
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val;
+}
+
+static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+				  struct vgic_lr lr_desc)
+{
+	if (!(lr_desc.state & LR_STATE_MASK))
+		set_bit(lr, (unsigned long *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr);
+}
+
+static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+#if BITS_PER_LONG == 64
+	val  = vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[1];
+	val <<= 32;
+	val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[0];
+#else
+	val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
+#endif
+	return val;
+}
+
+static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+#if BITS_PER_LONG == 64
+	val  = vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[1];
+	val <<= 32;
+	val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[0];
+#else
+	val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
+#endif
+	return val;
+}
+
+static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
+{
+	u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr;
+	u32 ret = 0;
+
+	if (misr & GICH_MISR_EOI)
+		ret |= INT_STATUS_EOI;
+	if (misr & GICH_MISR_U)
+		ret |= INT_STATUS_UNDERFLOW;
+
+	return ret;
+}
+
+static void vgic_v2_enable_underflow(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr |= GICH_HCR_UIE;
+}
+
+static void vgic_v2_disable_underflow(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr &= ~GICH_HCR_UIE;
+}
+
+static void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr;
+
+	vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >> GICH_VMCR_CTRL_SHIFT;
+	vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >> GICH_VMCR_ALIAS_BINPOINT_SHIFT;
+	vmcrp->bpr  = (vmcr & GICH_VMCR_BINPOINT_MASK) >> GICH_VMCR_BINPOINT_SHIFT;
+	vmcrp->pmr  = (vmcr & GICH_VMCR_PRIMASK_MASK) >> GICH_VMCR_PRIMASK_SHIFT;
+}
+
+static void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+	u32 vmcr;
+
+	vmcr  = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
+	vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) & GICH_VMCR_ALIAS_BINPOINT_MASK;
+	vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & GICH_VMCR_BINPOINT_MASK;
+	vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
+
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
+}
+
+static void vgic_v2_enable(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * By forcing VMCR to zero, the GIC will restore the binary
+	 * points to their reset values. Anything else resets to zero
+	 * anyway.
+	 */
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0;
+
+	/* Get the show on the road... */
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN;
+}
+
+static const struct vgic_ops vgic_v2_ops = {
+	.get_lr			= vgic_v2_get_lr,
+	.set_lr			= vgic_v2_set_lr,
+	.sync_lr_elrsr		= vgic_v2_sync_lr_elrsr,
+	.get_elrsr		= vgic_v2_get_elrsr,
+	.get_eisr		= vgic_v2_get_eisr,
+	.get_interrupt_status	= vgic_v2_get_interrupt_status,
+	.enable_underflow	= vgic_v2_enable_underflow,
+	.disable_underflow	= vgic_v2_disable_underflow,
+	.get_vmcr		= vgic_v2_get_vmcr,
+	.set_vmcr		= vgic_v2_set_vmcr,
+	.enable			= vgic_v2_enable,
+};
+
+static struct vgic_params vgic_v2_params;
+
+/**
+ * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
+ * @node:	pointer to the DT node
+ * @ops: 	address of a pointer to the GICv2 operations
+ * @params:	address of a pointer to HW-specific parameters
+ *
+ * Returns 0 if a GICv2 has been found, with the low level operations
+ * in *ops and the HW parameters in *params. Returns an error code
+ * otherwise.
+ */
+int vgic_v2_probe(struct device_node *vgic_node,
+		  const struct vgic_ops **ops,
+		  const struct vgic_params **params)
+{
+	int ret;
+	struct resource vctrl_res;
+	struct resource vcpu_res;
+	struct vgic_params *vgic = &vgic_v2_params;
+
+	vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
+	if (!vgic->maint_irq) {
+		kvm_err("error getting vgic maintenance irq from DT\n");
+		ret = -ENXIO;
+		goto out;
+	}
+
+	ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
+	if (ret) {
+		kvm_err("Cannot obtain GICH resource\n");
+		goto out;
+	}
+
+	vgic->vctrl_base = of_iomap(vgic_node, 2);
+	if (!vgic->vctrl_base) {
+		kvm_err("Cannot ioremap GICH\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	vgic->nr_lr = readl_relaxed(vgic->vctrl_base + GICH_VTR);
+	vgic->nr_lr = (vgic->nr_lr & 0x3f) + 1;
+
+	ret = create_hyp_io_mappings(vgic->vctrl_base,
+				     vgic->vctrl_base + resource_size(&vctrl_res),
+				     vctrl_res.start);
+	if (ret) {
+		kvm_err("Cannot map VCTRL into hyp\n");
+		goto out_unmap;
+	}
+
+	if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
+		kvm_err("Cannot obtain GICV resource\n");
+		ret = -ENXIO;
+		goto out_unmap;
+	}
+
+	if (!PAGE_ALIGNED(vcpu_res.start)) {
+		kvm_err("GICV physical address 0x%llx not page aligned\n",
+			(unsigned long long)vcpu_res.start);
+		ret = -ENXIO;
+		goto out_unmap;
+	}
+
+	if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+		kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+			(unsigned long long)resource_size(&vcpu_res),
+			PAGE_SIZE);
+		ret = -ENXIO;
+		goto out_unmap;
+	}
+
+	vgic->vcpu_base = vcpu_res.start;
+
+	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+		 vctrl_res.start, vgic->maint_irq);
+
+	vgic->type = VGIC_V2;
+	*ops = &vgic_v2_ops;
+	*params = vgic;
+	goto out;
+
+out_unmap:
+	iounmap(vgic->vctrl_base);
+out:
+	of_node_put(vgic_node);
+	return ret;
+}
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
new file mode 100644
index 000000000000..1c2c8eef0599
--- /dev/null
+++ b/virt/kvm/arm/vgic-v3.c
@@ -0,0 +1,247 @@
+/*
+ * Copyright (C) 2013 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+/* These are for GICv2 emulation only */
+#define GICH_LR_VIRTUALID		(0x3ffUL << 0)
+#define GICH_LR_PHYSID_CPUID_SHIFT	(10)
+#define GICH_LR_PHYSID_CPUID		(7UL << GICH_LR_PHYSID_CPUID_SHIFT)
+
+/*
+ * LRs are stored in reverse order in memory. make sure we index them
+ * correctly.
+ */
+#define LR_INDEX(lr)			(VGIC_V3_MAX_LRS - 1 - lr)
+
+static u32 ich_vtr_el2;
+
+static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+	struct vgic_lr lr_desc;
+	u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)];
+
+	lr_desc.irq	= val & GICH_LR_VIRTUALID;
+	if (lr_desc.irq <= 15)
+		lr_desc.source	= (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
+	else
+		lr_desc.source = 0;
+	lr_desc.state	= 0;
+
+	if (val & ICH_LR_PENDING_BIT)
+		lr_desc.state |= LR_STATE_PENDING;
+	if (val & ICH_LR_ACTIVE_BIT)
+		lr_desc.state |= LR_STATE_ACTIVE;
+	if (val & ICH_LR_EOI)
+		lr_desc.state |= LR_EOI_INT;
+
+	return lr_desc;
+}
+
+static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
+			   struct vgic_lr lr_desc)
+{
+	u64 lr_val = (((u32)lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) |
+		      lr_desc.irq);
+
+	if (lr_desc.state & LR_STATE_PENDING)
+		lr_val |= ICH_LR_PENDING_BIT;
+	if (lr_desc.state & LR_STATE_ACTIVE)
+		lr_val |= ICH_LR_ACTIVE_BIT;
+	if (lr_desc.state & LR_EOI_INT)
+		lr_val |= ICH_LR_EOI;
+
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)] = lr_val;
+}
+
+static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+				  struct vgic_lr lr_desc)
+{
+	if (!(lr_desc.state & LR_STATE_MASK))
+		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
+}
+
+static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr;
+}
+
+static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr;
+}
+
+static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu)
+{
+	u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr;
+	u32 ret = 0;
+
+	if (misr & ICH_MISR_EOI)
+		ret |= INT_STATUS_EOI;
+	if (misr & ICH_MISR_U)
+		ret |= INT_STATUS_UNDERFLOW;
+
+	return ret;
+}
+
+static void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+	u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr;
+
+	vmcrp->ctlr = (vmcr & ICH_VMCR_CTLR_MASK) >> ICH_VMCR_CTLR_SHIFT;
+	vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
+	vmcrp->bpr  = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
+	vmcrp->pmr  = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
+}
+
+static void vgic_v3_enable_underflow(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr |= ICH_HCR_UIE;
+}
+
+static void vgic_v3_disable_underflow(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr &= ~ICH_HCR_UIE;
+}
+
+static void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+	u32 vmcr;
+
+	vmcr  = (vmcrp->ctlr << ICH_VMCR_CTLR_SHIFT) & ICH_VMCR_CTLR_MASK;
+	vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
+	vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
+	vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
+
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr;
+}
+
+static void vgic_v3_enable(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * By forcing VMCR to zero, the GIC will restore the binary
+	 * points to their reset values. Anything else resets to zero
+	 * anyway.
+	 */
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = 0;
+
+	/* Get the show on the road... */
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr = ICH_HCR_EN;
+}
+
+static const struct vgic_ops vgic_v3_ops = {
+	.get_lr			= vgic_v3_get_lr,
+	.set_lr			= vgic_v3_set_lr,
+	.sync_lr_elrsr		= vgic_v3_sync_lr_elrsr,
+	.get_elrsr		= vgic_v3_get_elrsr,
+	.get_eisr		= vgic_v3_get_eisr,
+	.get_interrupt_status	= vgic_v3_get_interrupt_status,
+	.enable_underflow	= vgic_v3_enable_underflow,
+	.disable_underflow	= vgic_v3_disable_underflow,
+	.get_vmcr		= vgic_v3_get_vmcr,
+	.set_vmcr		= vgic_v3_set_vmcr,
+	.enable			= vgic_v3_enable,
+};
+
+static struct vgic_params vgic_v3_params;
+
+/**
+ * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
+ * @node:	pointer to the DT node
+ * @ops: 	address of a pointer to the GICv3 operations
+ * @params:	address of a pointer to HW-specific parameters
+ *
+ * Returns 0 if a GICv3 has been found, with the low level operations
+ * in *ops and the HW parameters in *params. Returns an error code
+ * otherwise.
+ */
+int vgic_v3_probe(struct device_node *vgic_node,
+		  const struct vgic_ops **ops,
+		  const struct vgic_params **params)
+{
+	int ret = 0;
+	u32 gicv_idx;
+	struct resource vcpu_res;
+	struct vgic_params *vgic = &vgic_v3_params;
+
+	vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
+	if (!vgic->maint_irq) {
+		kvm_err("error getting vgic maintenance irq from DT\n");
+		ret = -ENXIO;
+		goto out;
+	}
+
+	ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2);
+
+	/*
+	 * The ListRegs field is 5 bits, but there is a architectural
+	 * maximum of 16 list registers. Just ignore bit 4...
+	 */
+	vgic->nr_lr = (ich_vtr_el2 & 0xf) + 1;
+
+	if (of_property_read_u32(vgic_node, "#redistributor-regions", &gicv_idx))
+		gicv_idx = 1;
+
+	gicv_idx += 3; /* Also skip GICD, GICC, GICH */
+	if (of_address_to_resource(vgic_node, gicv_idx, &vcpu_res)) {
+		kvm_err("Cannot obtain GICV region\n");
+		ret = -ENXIO;
+		goto out;
+	}
+
+	if (!PAGE_ALIGNED(vcpu_res.start)) {
+		kvm_err("GICV physical address 0x%llx not page aligned\n",
+			(unsigned long long)vcpu_res.start);
+		ret = -ENXIO;
+		goto out;
+	}
+
+	if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+		kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+			(unsigned long long)resource_size(&vcpu_res),
+			PAGE_SIZE);
+		ret = -ENXIO;
+		goto out;
+	}
+
+	vgic->vcpu_base = vcpu_res.start;
+	vgic->vctrl_base = NULL;
+	vgic->type = VGIC_V3;
+
+	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+		 vcpu_res.start, vgic->maint_irq);
+
+	*ops = &vgic_v3_ops;
+	*params = vgic;
+
+out:
+	of_node_put(vgic_node);
+	return ret;
+}
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 8ca405cd7c1a..8e1dc03342c3 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -36,21 +36,22 @@
  * How the whole thing works (courtesy of Christoffer Dall):
  *
  * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
- *   something is pending
- * - VGIC pending interrupts are stored on the vgic.irq_state vgic
- *   bitmap (this bitmap is updated by both user land ioctls and guest
- *   mmio ops, and other in-kernel peripherals such as the
- *   arch. timers) and indicate the 'wire' state.
+ *   something is pending on the CPU interface.
+ * - Interrupts that are pending on the distributor are stored on the
+ *   vgic.irq_pending vgic bitmap (this bitmap is updated by both user land
+ *   ioctls and guest mmio ops, and other in-kernel peripherals such as the
+ *   arch. timers).
  * - Every time the bitmap changes, the irq_pending_on_cpu oracle is
  *   recalculated
  * - To calculate the oracle, we need info for each cpu from
  *   compute_pending_for_cpu, which considers:
- *   - PPI: dist->irq_state & dist->irq_enable
- *   - SPI: dist->irq_state & dist->irq_enable & dist->irq_spi_target
- *   - irq_spi_target is a 'formatted' version of the GICD_ICFGR
+ *   - PPI: dist->irq_pending & dist->irq_enable
+ *   - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target
+ *   - irq_spi_target is a 'formatted' version of the GICD_ITARGETSRn
  *     registers, stored on each vcpu. We only keep one bit of
  *     information per interrupt, making sure that only one vcpu can
  *     accept the interrupt.
+ * - If any of the above state changes, we must recalculate the oracle.
  * - The same is true when injecting an interrupt, except that we only
  *   consider a single interrupt at a time. The irq_spi_cpu array
  *   contains the target CPU for each SPI.
@@ -60,13 +61,18 @@
  * the 'line' again. This is achieved as such:
  *
  * - When a level interrupt is moved onto a vcpu, the corresponding
- *   bit in irq_active is set. As long as this bit is set, the line
+ *   bit in irq_queued is set. As long as this bit is set, the line
  *   will be ignored for further interrupts. The interrupt is injected
  *   into the vcpu with the GICH_LR_EOI bit set (generate a
  *   maintenance interrupt on EOI).
  * - When the interrupt is EOIed, the maintenance interrupt fires,
- *   and clears the corresponding bit in irq_active. This allow the
+ *   and clears the corresponding bit in irq_queued. This allows the
  *   interrupt line to be sampled again.
+ * - Note that level-triggered interrupts can also be set to pending from
+ *   writes to GICD_ISPENDRn and lowering the external input line does not
+ *   cause the interrupt to become inactive in such a situation.
+ *   Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become
+ *   inactive as long as the external input line is held high.
  */
 
 #define VGIC_ADDR_UNDEF		(-1)
@@ -76,14 +82,6 @@
 #define IMPLEMENTER_ARM		0x43b
 #define GICC_ARCH_VERSION_V2	0x2
 
-/* Physical address of vgic virtual cpu interface */
-static phys_addr_t vgic_vcpu_base;
-
-/* Virtual control interface base address */
-static void __iomem *vgic_vctrl_base;
-
-static struct device_node *vgic_node;
-
 #define ACCESS_READ_VALUE	(1 << 0)
 #define ACCESS_READ_RAZ		(0 << 0)
 #define ACCESS_READ_MASK(x)	((x) & (1 << 0))
@@ -94,30 +92,76 @@ static struct device_node *vgic_node;
 #define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))
 
 static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
+static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
 static void vgic_update_state(struct kvm *kvm);
 static void vgic_kick_vcpus(struct kvm *kvm);
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi);
 static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
-static u32 vgic_nr_lr;
+static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
+static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
+static void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+
+static const struct vgic_ops *vgic_ops;
+static const struct vgic_params *vgic;
+
+/*
+ * struct vgic_bitmap contains a bitmap made of unsigned longs, but
+ * extracts u32s out of them.
+ *
+ * This does not work on 64-bit BE systems, because the bitmap access
+ * will store two consecutive 32-bit words with the higher-addressed
+ * register's bits at the lower index and the lower-addressed register's
+ * bits at the higher index.
+ *
+ * Therefore, swizzle the register index when accessing the 32-bit word
+ * registers to access the right register's value.
+ */
+#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 64
+#define REG_OFFSET_SWIZZLE	1
+#else
+#define REG_OFFSET_SWIZZLE	0
+#endif
+
+static int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs)
+{
+	int nr_longs;
 
-static unsigned int vgic_maint_irq;
+	nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
+
+	b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL);
+	if (!b->private)
+		return -ENOMEM;
+
+	b->shared = b->private + nr_cpus;
+
+	return 0;
+}
+
+static void vgic_free_bitmap(struct vgic_bitmap *b)
+{
+	kfree(b->private);
+	b->private = NULL;
+	b->shared = NULL;
+}
 
 static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
 				int cpuid, u32 offset)
 {
 	offset >>= 2;
 	if (!offset)
-		return x->percpu[cpuid].reg;
+		return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE;
 	else
-		return x->shared.reg + offset - 1;
+		return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
 }
 
 static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
 				   int cpuid, int irq)
 {
 	if (irq < VGIC_NR_PRIVATE_IRQS)
-		return test_bit(irq, x->percpu[cpuid].reg_ul);
+		return test_bit(irq, x->private + cpuid);
 
-	return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared.reg_ul);
+	return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
 }
 
 static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
@@ -126,9 +170,9 @@ static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
 	unsigned long *reg;
 
 	if (irq < VGIC_NR_PRIVATE_IRQS) {
-		reg = x->percpu[cpuid].reg_ul;
+		reg = x->private + cpuid;
 	} else {
-		reg =  x->shared.reg_ul;
+		reg = x->shared;
 		irq -= VGIC_NR_PRIVATE_IRQS;
 	}
 
@@ -140,24 +184,49 @@ static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
 
 static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
 {
-	if (unlikely(cpuid >= VGIC_MAX_CPUS))
-		return NULL;
-	return x->percpu[cpuid].reg_ul;
+	return x->private + cpuid;
 }
 
 static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
 {
-	return x->shared.reg_ul;
+	return x->shared;
+}
+
+static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs)
+{
+	int size;
+
+	size  = nr_cpus * VGIC_NR_PRIVATE_IRQS;
+	size += nr_irqs - VGIC_NR_PRIVATE_IRQS;
+
+	x->private = kzalloc(size, GFP_KERNEL);
+	if (!x->private)
+		return -ENOMEM;
+
+	x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32);
+	return 0;
+}
+
+static void vgic_free_bytemap(struct vgic_bytemap *b)
+{
+	kfree(b->private);
+	b->private = NULL;
+	b->shared = NULL;
 }
 
 static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
 {
-	offset >>= 2;
-	BUG_ON(offset > (VGIC_NR_IRQS / 4));
-	if (offset < 8)
-		return x->percpu[cpuid] + offset;
-	else
-		return x->shared + offset - 8;
+	u32 *reg;
+
+	if (offset < VGIC_NR_PRIVATE_IRQS) {
+		reg = x->private;
+		offset += cpuid * VGIC_NR_PRIVATE_IRQS;
+	} else {
+		reg = x->shared;
+		offset -= VGIC_NR_PRIVATE_IRQS;
+	}
+
+	return reg + (offset / sizeof(u32));
 }
 
 #define VGIC_CFG_LEVEL	0
@@ -179,46 +248,81 @@ static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
 	return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
 }
 
-static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq)
+static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
+}
+
+static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq);
+	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1);
 }
 
-static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq)
+static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1);
+	vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
 }
 
-static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq)
+static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0);
+	return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1);
+}
+
+static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0);
+}
+
+static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
 }
 
 static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	return vgic_bitmap_get_irq_val(&dist->irq_state, vcpu->vcpu_id, irq);
+	return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
 }
 
-static void vgic_dist_irq_set(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 1);
+	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
 }
 
-static void vgic_dist_irq_clear(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 
-	vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 0);
+	vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0);
 }
 
 static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
@@ -239,14 +343,19 @@ static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
 			  vcpu->arch.vgic_cpu.pending_shared);
 }
 
+static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
+{
+	return vgic_irq_is_edge(vcpu, irq) || !vgic_irq_is_queued(vcpu, irq);
+}
+
 static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
 {
-	return *((u32 *)mmio->data) & mask;
+	return le32_to_cpu(*((u32 *)mmio->data)) & mask;
 }
 
 static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
 {
-	*((u32 *)mmio->data) = value & mask;
+	*((u32 *)mmio->data) = cpu_to_le32(value) & mask;
 }
 
 /**
@@ -330,7 +439,7 @@ static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
 
 	case 4:			/* GICD_TYPER */
 		reg  = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
-		reg |= (VGIC_NR_IRQS >> 5) - 1;
+		reg |= (vcpu->kvm->arch.vgic.nr_irqs >> 5) - 1;
 		vgic_reg_access(mmio, &reg, word_offset,
 				ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
 		break;
@@ -392,11 +501,33 @@ static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
 					struct kvm_exit_mmio *mmio,
 					phys_addr_t offset)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
-				       vcpu->vcpu_id, offset);
+	u32 *reg, orig;
+	u32 level_mask;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu->vcpu_id, offset);
+	level_mask = (~(*reg));
+
+	/* Mark both level and edge triggered irqs as pending */
+	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+	orig = *reg;
 	vgic_reg_access(mmio, reg, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+
 	if (mmio->is_write) {
+		/* Set the soft-pending flag only for level-triggered irqs */
+		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+					  vcpu->vcpu_id, offset);
+		vgic_reg_access(mmio, reg, offset,
+				ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+		*reg &= level_mask;
+
+		/* Ignore writes to SGIs */
+		if (offset < 2) {
+			*reg &= ~0xffff;
+			*reg |= orig & 0xffff;
+		}
+
 		vgic_update_state(vcpu->kvm);
 		return true;
 	}
@@ -408,11 +539,34 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
 					  struct kvm_exit_mmio *mmio,
 					  phys_addr_t offset)
 {
-	u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
-				       vcpu->vcpu_id, offset);
+	u32 *level_active;
+	u32 *reg, orig;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+	reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+	orig = *reg;
 	vgic_reg_access(mmio, reg, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
 	if (mmio->is_write) {
+		/* Re-set level triggered level-active interrupts */
+		level_active = vgic_bitmap_get_reg(&dist->irq_level,
+					  vcpu->vcpu_id, offset);
+		reg = vgic_bitmap_get_reg(&dist->irq_pending,
+					  vcpu->vcpu_id, offset);
+		*reg |= *level_active;
+
+		/* Ignore writes to SGIs */
+		if (offset < 2) {
+			*reg &= ~0xffff;
+			*reg |= orig & 0xffff;
+		}
+
+		/* Clear soft-pending flags */
+		reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+					  vcpu->vcpu_id, offset);
+		vgic_reg_access(mmio, reg, offset,
+				ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+
 		vgic_update_state(vcpu->kvm);
 		return true;
 	}
@@ -548,11 +702,10 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 	u32 val;
 	u32 *reg;
 
-	offset >>= 1;
 	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				  vcpu->vcpu_id, offset);
+				  vcpu->vcpu_id, offset >> 1);
 
-	if (offset & 2)
+	if (offset & 4)
 		val = *reg >> 16;
 	else
 		val = *reg & 0xffff;
@@ -561,13 +714,13 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 	vgic_reg_access(mmio, &val, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
 	if (mmio->is_write) {
-		if (offset < 4) {
+		if (offset < 8) {
 			*reg = ~0U; /* Force PPIs/SGIs to 1 */
 			return false;
 		}
 
 		val = vgic_cfg_compress(val);
-		if (offset & 2) {
+		if (offset & 4) {
 			*reg &= 0xffff;
 			*reg |= val << 16;
 		} else {
@@ -594,18 +747,6 @@ static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
 	return false;
 }
 
-#define LR_CPUID(lr)	\
-	(((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT)
-#define LR_IRQID(lr)	\
-	((lr) & GICH_LR_VIRTUALID)
-
-static void vgic_retire_lr(int lr_nr, int irq, struct vgic_cpu *vgic_cpu)
-{
-	clear_bit(lr_nr, vgic_cpu->lr_used);
-	vgic_cpu->vgic_lr[lr_nr] &= ~GICH_LR_STATE;
-	vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
-}
-
 /**
  * vgic_unqueue_irqs - move pending IRQs from LRs to the distributor
  * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
@@ -623,13 +764,10 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	int vcpu_id = vcpu->vcpu_id;
-	int i, irq, source_cpu;
-	u32 *lr;
+	int i;
 
 	for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
-		lr = &vgic_cpu->vgic_lr[i];
-		irq = LR_IRQID(*lr);
-		source_cpu = LR_CPUID(*lr);
+		struct vgic_lr lr = vgic_get_lr(vcpu, i);
 
 		/*
 		 * There are three options for the state bits:
@@ -641,7 +779,7 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 		 * If the LR holds only an active interrupt (not pending) then
 		 * just leave it alone.
 		 */
-		if ((*lr & GICH_LR_STATE) == GICH_LR_ACTIVE_BIT)
+		if ((lr.state & LR_STATE_MASK) == LR_STATE_ACTIVE)
 			continue;
 
 		/*
@@ -650,18 +788,21 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
 		 * is fine, then we are only setting a few bits that were
 		 * already set.
 		 */
-		vgic_dist_irq_set(vcpu, irq);
-		if (irq < VGIC_NR_SGIS)
-			dist->irq_sgi_sources[vcpu_id][irq] |= 1 << source_cpu;
-		*lr &= ~GICH_LR_PENDING_BIT;
+		vgic_dist_irq_set_pending(vcpu, lr.irq);
+		if (lr.irq < VGIC_NR_SGIS)
+			*vgic_get_sgi_sources(dist, vcpu_id, lr.irq) |= 1 << lr.source;
+		lr.state &= ~LR_STATE_PENDING;
+		vgic_set_lr(vcpu, i, lr);
 
 		/*
 		 * If there's no state left on the LR (it could still be
 		 * active), then the LR does not hold any useful info and can
 		 * be marked as free for other use.
 		 */
-		if (!(*lr & GICH_LR_STATE))
-			vgic_retire_lr(i, irq, vgic_cpu);
+		if (!(lr.state & LR_STATE_MASK)) {
+			vgic_retire_lr(i, lr.irq, vcpu);
+			vgic_irq_clear_queued(vcpu, lr.irq);
+		}
 
 		/* Finally update the VGIC state. */
 		vgic_update_state(vcpu->kvm);
@@ -675,7 +816,7 @@ static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int sgi;
-	int min_sgi = (offset & ~0x3) * 4;
+	int min_sgi = (offset & ~0x3);
 	int max_sgi = min_sgi + 3;
 	int vcpu_id = vcpu->vcpu_id;
 	u32 reg = 0;
@@ -683,7 +824,7 @@ static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 	/* Copy source SGIs from distributor side */
 	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
 		int shift = 8 * (sgi - min_sgi);
-		reg |= (u32)dist->irq_sgi_sources[vcpu_id][sgi] << shift;
+		reg |= ((u32)*vgic_get_sgi_sources(dist, vcpu_id, sgi)) << shift;
 	}
 
 	mmio_data_write(mmio, ~0, reg);
@@ -696,7 +837,7 @@ static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int sgi;
-	int min_sgi = (offset & ~0x3) * 4;
+	int min_sgi = (offset & ~0x3);
 	int max_sgi = min_sgi + 3;
 	int vcpu_id = vcpu->vcpu_id;
 	u32 reg;
@@ -707,14 +848,15 @@ static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 	/* Clear pending SGIs on the distributor */
 	for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
 		u8 mask = reg >> (8 * (sgi - min_sgi));
+		u8 *src = vgic_get_sgi_sources(dist, vcpu_id, sgi);
 		if (set) {
-			if ((dist->irq_sgi_sources[vcpu_id][sgi] & mask) != mask)
+			if ((*src & mask) != mask)
 				updated = true;
-			dist->irq_sgi_sources[vcpu_id][sgi] |= mask;
+			*src |= mask;
 		} else {
-			if (dist->irq_sgi_sources[vcpu_id][sgi] & mask)
+			if (*src & mask)
 				updated = true;
-			dist->irq_sgi_sources[vcpu_id][sgi] &= ~mask;
+			*src &= ~mask;
 		}
 	}
 
@@ -753,6 +895,7 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
 struct mmio_range {
 	phys_addr_t base;
 	unsigned long len;
+	int bits_per_irq;
 	bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
 			    phys_addr_t offset);
 };
@@ -761,56 +904,67 @@ static const struct mmio_range vgic_dist_ranges[] = {
 	{
 		.base		= GIC_DIST_CTRL,
 		.len		= 12,
+		.bits_per_irq	= 0,
 		.handle_mmio	= handle_mmio_misc,
 	},
 	{
 		.base		= GIC_DIST_IGROUP,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
 		.base		= GIC_DIST_ENABLE_SET,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_set_enable_reg,
 	},
 	{
 		.base		= GIC_DIST_ENABLE_CLEAR,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_clear_enable_reg,
 	},
 	{
 		.base		= GIC_DIST_PENDING_SET,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_set_pending_reg,
 	},
 	{
 		.base		= GIC_DIST_PENDING_CLEAR,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_clear_pending_reg,
 	},
 	{
 		.base		= GIC_DIST_ACTIVE_SET,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
 		.base		= GIC_DIST_ACTIVE_CLEAR,
-		.len		= VGIC_NR_IRQS / 8,
+		.len		= VGIC_MAX_IRQS / 8,
+		.bits_per_irq	= 1,
 		.handle_mmio	= handle_mmio_raz_wi,
 	},
 	{
 		.base		= GIC_DIST_PRI,
-		.len		= VGIC_NR_IRQS,
+		.len		= VGIC_MAX_IRQS,
+		.bits_per_irq	= 8,
 		.handle_mmio	= handle_mmio_priority_reg,
 	},
 	{
 		.base		= GIC_DIST_TARGET,
-		.len		= VGIC_NR_IRQS,
+		.len		= VGIC_MAX_IRQS,
+		.bits_per_irq	= 8,
 		.handle_mmio	= handle_mmio_target_reg,
 	},
 	{
 		.base		= GIC_DIST_CONFIG,
-		.len		= VGIC_NR_IRQS / 4,
+		.len		= VGIC_MAX_IRQS / 4,
+		.bits_per_irq	= 2,
 		.handle_mmio	= handle_mmio_cfg_reg,
 	},
 	{
@@ -848,6 +1002,22 @@ struct mmio_range *find_matching_range(const struct mmio_range *ranges,
 	return NULL;
 }
 
+static bool vgic_validate_access(const struct vgic_dist *dist,
+				 const struct mmio_range *range,
+				 unsigned long offset)
+{
+	int irq;
+
+	if (!range->bits_per_irq)
+		return true;	/* Not an irq-based access */
+
+	irq = offset * 8 / range->bits_per_irq;
+	if (irq >= dist->nr_irqs)
+		return false;
+
+	return true;
+}
+
 /**
  * vgic_handle_mmio - handle an in-kernel MMIO access
  * @vcpu:	pointer to the vcpu performing the access
@@ -887,7 +1057,13 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	spin_lock(&vcpu->kvm->arch.vgic.lock);
 	offset = mmio->phys_addr - range->base - base;
-	updated_state = range->handle_mmio(vcpu, mmio, offset);
+	if (vgic_validate_access(dist, range, offset)) {
+		updated_state = range->handle_mmio(vcpu, mmio, offset);
+	} else {
+		vgic_reg_access(mmio, NULL, offset,
+				ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+		updated_state = false;
+	}
 	spin_unlock(&vcpu->kvm->arch.vgic.lock);
 	kvm_prepare_mmio(run, mmio);
 	kvm_handle_mmio_return(vcpu, run);
@@ -898,6 +1074,11 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	return true;
 }
 
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi)
+{
+	return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi;
+}
+
 static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -916,6 +1097,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 	case 0:
 		if (!target_cpus)
 			return;
+		break;
 
 	case 1:
 		target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
@@ -929,8 +1111,8 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		if (target_cpus & 1) {
 			/* Flag the SGI as pending */
-			vgic_dist_irq_set(vcpu, sgi);
-			dist->irq_sgi_sources[c][sgi] |= 1 << vcpu_id;
+			vgic_dist_irq_set_pending(vcpu, sgi);
+			*vgic_get_sgi_sources(dist, c, sgi) |= 1 << vcpu_id;
 			kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
 		}
 
@@ -938,32 +1120,38 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 	}
 }
 
+static int vgic_nr_shared_irqs(struct vgic_dist *dist)
+{
+	return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
+}
+
 static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
 	unsigned long pending_private, pending_shared;
+	int nr_shared = vgic_nr_shared_irqs(dist);
 	int vcpu_id;
 
 	vcpu_id = vcpu->vcpu_id;
 	pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
 	pend_shared = vcpu->arch.vgic_cpu.pending_shared;
 
-	pending = vgic_bitmap_get_cpu_map(&dist->irq_state, vcpu_id);
+	pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
 	enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
 	bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
 
-	pending = vgic_bitmap_get_shared_map(&dist->irq_state);
+	pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
 	enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
-	bitmap_and(pend_shared, pending, enabled, VGIC_NR_SHARED_IRQS);
+	bitmap_and(pend_shared, pending, enabled, nr_shared);
 	bitmap_and(pend_shared, pend_shared,
 		   vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
-		   VGIC_NR_SHARED_IRQS);
+		   nr_shared);
 
 	pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
-	pending_shared = find_first_bit(pend_shared, VGIC_NR_SHARED_IRQS);
+	pending_shared = find_first_bit(pend_shared, nr_shared);
 	return (pending_private < VGIC_NR_PRIVATE_IRQS ||
-		pending_shared < VGIC_NR_SHARED_IRQS);
+		pending_shared < vgic_nr_shared_irqs(dist));
 }
 
 /*
@@ -977,20 +1165,85 @@ static void vgic_update_state(struct kvm *kvm)
 	int c;
 
 	if (!dist->enabled) {
-		set_bit(0, &dist->irq_pending_on_cpu);
+		set_bit(0, dist->irq_pending_on_cpu);
 		return;
 	}
 
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		if (compute_pending_for_cpu(vcpu)) {
 			pr_debug("CPU%d has pending interrupts\n", c);
-			set_bit(c, &dist->irq_pending_on_cpu);
+			set_bit(c, dist->irq_pending_on_cpu);
 		}
 	}
 }
 
-#define MK_LR_PEND(src, irq)	\
-	(GICH_LR_PENDING_BIT | ((src) << GICH_LR_PHYSID_CPUID_SHIFT) | (irq))
+static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+	return vgic_ops->get_lr(vcpu, lr);
+}
+
+static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr,
+			       struct vgic_lr vlr)
+{
+	vgic_ops->set_lr(vcpu, lr, vlr);
+}
+
+static void vgic_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+			       struct vgic_lr vlr)
+{
+	vgic_ops->sync_lr_elrsr(vcpu, lr, vlr);
+}
+
+static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu)
+{
+	return vgic_ops->get_elrsr(vcpu);
+}
+
+static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu)
+{
+	return vgic_ops->get_eisr(vcpu);
+}
+
+static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
+{
+	return vgic_ops->get_interrupt_status(vcpu);
+}
+
+static inline void vgic_enable_underflow(struct kvm_vcpu *vcpu)
+{
+	vgic_ops->enable_underflow(vcpu);
+}
+
+static inline void vgic_disable_underflow(struct kvm_vcpu *vcpu)
+{
+	vgic_ops->disable_underflow(vcpu);
+}
+
+static inline void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+	vgic_ops->get_vmcr(vcpu, vmcr);
+}
+
+static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+	vgic_ops->set_vmcr(vcpu, vmcr);
+}
+
+static inline void vgic_enable(struct kvm_vcpu *vcpu)
+{
+	vgic_ops->enable(vcpu);
+}
+
+static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr);
+
+	vlr.state = 0;
+	vgic_set_lr(vcpu, lr_nr, vlr);
+	clear_bit(lr_nr, vgic_cpu->lr_used);
+	vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+}
 
 /*
  * An interrupt may have been disabled after being made pending on the
@@ -1006,13 +1259,13 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	int lr;
 
-	for_each_set_bit(lr, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
-		int irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
+	for_each_set_bit(lr, vgic_cpu->lr_used, vgic->nr_lr) {
+		struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
 
-		if (!vgic_irq_is_enabled(vcpu, irq)) {
-			vgic_retire_lr(lr, irq, vgic_cpu);
-			if (vgic_irq_is_active(vcpu, irq))
-				vgic_irq_clear_active(vcpu, irq);
+		if (!vgic_irq_is_enabled(vcpu, vlr.irq)) {
+			vgic_retire_lr(lr, vlr.irq, vcpu);
+			if (vgic_irq_is_queued(vcpu, vlr.irq))
+				vgic_irq_clear_queued(vcpu, vlr.irq);
 		}
 	}
 }
@@ -1024,40 +1277,48 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
 static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	struct vgic_lr vlr;
 	int lr;
 
 	/* Sanitize the input... */
 	BUG_ON(sgi_source_id & ~7);
 	BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
-	BUG_ON(irq >= VGIC_NR_IRQS);
+	BUG_ON(irq >= dist->nr_irqs);
 
 	kvm_debug("Queue IRQ%d\n", irq);
 
 	lr = vgic_cpu->vgic_irq_lr_map[irq];
 
 	/* Do we have an active interrupt for the same CPUID? */
-	if (lr != LR_EMPTY &&
-	    (LR_CPUID(vgic_cpu->vgic_lr[lr]) == sgi_source_id)) {
-		kvm_debug("LR%d piggyback for IRQ%d %x\n",
-			  lr, irq, vgic_cpu->vgic_lr[lr]);
-		BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
-		vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;
-		return true;
+	if (lr != LR_EMPTY) {
+		vlr = vgic_get_lr(vcpu, lr);
+		if (vlr.source == sgi_source_id) {
+			kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
+			BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
+			vlr.state |= LR_STATE_PENDING;
+			vgic_set_lr(vcpu, lr, vlr);
+			return true;
+		}
 	}
 
 	/* Try to use another LR for this interrupt */
 	lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used,
-			       vgic_cpu->nr_lr);
-	if (lr >= vgic_cpu->nr_lr)
+			       vgic->nr_lr);
+	if (lr >= vgic->nr_lr)
 		return false;
 
 	kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id);
-	vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq);
 	vgic_cpu->vgic_irq_lr_map[irq] = lr;
 	set_bit(lr, vgic_cpu->lr_used);
 
+	vlr.irq = irq;
+	vlr.source = sgi_source_id;
+	vlr.state = LR_STATE_PENDING;
 	if (!vgic_irq_is_edge(vcpu, irq))
-		vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;
+		vlr.state |= LR_EOI_INT;
+
+	vgic_set_lr(vcpu, lr, vlr);
 
 	return true;
 }
@@ -1069,14 +1330,14 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 	int vcpu_id = vcpu->vcpu_id;
 	int c;
 
-	sources = dist->irq_sgi_sources[vcpu_id][irq];
+	sources = *vgic_get_sgi_sources(dist, vcpu_id, irq);
 
-	for_each_set_bit(c, &sources, VGIC_MAX_CPUS) {
+	for_each_set_bit(c, &sources, dist->nr_cpus) {
 		if (vgic_queue_irq(vcpu, c, irq))
 			clear_bit(c, &sources);
 	}
 
-	dist->irq_sgi_sources[vcpu_id][irq] = sources;
+	*vgic_get_sgi_sources(dist, vcpu_id, irq) = sources;
 
 	/*
 	 * If the sources bitmap has been cleared it means that we
@@ -1085,7 +1346,7 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 	 * our emulated gic and can get rid of them.
 	 */
 	if (!sources) {
-		vgic_dist_irq_clear(vcpu, irq);
+		vgic_dist_irq_clear_pending(vcpu, irq);
 		vgic_cpu_irq_clear(vcpu, irq);
 		return true;
 	}
@@ -1095,15 +1356,15 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
 
 static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
 {
-	if (vgic_irq_is_active(vcpu, irq))
+	if (!vgic_can_sample_irq(vcpu, irq))
 		return true; /* level interrupt, already queued */
 
 	if (vgic_queue_irq(vcpu, 0, irq)) {
 		if (vgic_irq_is_edge(vcpu, irq)) {
-			vgic_dist_irq_clear(vcpu, irq);
+			vgic_dist_irq_clear_pending(vcpu, irq);
 			vgic_cpu_irq_clear(vcpu, irq);
 		} else {
-			vgic_irq_set_active(vcpu, irq);
+			vgic_irq_set_queued(vcpu, irq);
 		}
 
 		return true;
@@ -1148,66 +1409,83 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	}
 
 	/* SPIs */
-	for_each_set_bit(i, vgic_cpu->pending_shared, VGIC_NR_SHARED_IRQS) {
+	for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) {
 		if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
 			overflow = 1;
 	}
 
 epilog:
 	if (overflow) {
-		vgic_cpu->vgic_hcr |= GICH_HCR_UIE;
+		vgic_enable_underflow(vcpu);
 	} else {
-		vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
+		vgic_disable_underflow(vcpu);
 		/*
 		 * We're about to run this VCPU, and we've consumed
 		 * everything the distributor had in store for
 		 * us. Claim we don't have anything pending. We'll
 		 * adjust that if needed while exiting.
 		 */
-		clear_bit(vcpu_id, &dist->irq_pending_on_cpu);
+		clear_bit(vcpu_id, dist->irq_pending_on_cpu);
 	}
 }
 
 static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 {
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	u32 status = vgic_get_interrupt_status(vcpu);
 	bool level_pending = false;
 
-	kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);
+	kvm_debug("STATUS = %08x\n", status);
 
-	if (vgic_cpu->vgic_misr & GICH_MISR_EOI) {
+	if (status & INT_STATUS_EOI) {
 		/*
 		 * Some level interrupts have been EOIed. Clear their
 		 * active bit.
 		 */
-		int lr, irq;
+		u64 eisr = vgic_get_eisr(vcpu);
+		unsigned long *eisr_ptr = (unsigned long *)&eisr;
+		int lr;
+
+		for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
+			struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
+			WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
 
-		for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_eisr,
-				 vgic_cpu->nr_lr) {
-			irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
+			vgic_irq_clear_queued(vcpu, vlr.irq);
+			WARN_ON(vlr.state & LR_STATE_MASK);
+			vlr.state = 0;
+			vgic_set_lr(vcpu, lr, vlr);
 
-			vgic_irq_clear_active(vcpu, irq);
-			vgic_cpu->vgic_lr[lr] &= ~GICH_LR_EOI;
+			/*
+			 * If the IRQ was EOIed it was also ACKed and we we
+			 * therefore assume we can clear the soft pending
+			 * state (should it had been set) for this interrupt.
+			 *
+			 * Note: if the IRQ soft pending state was set after
+			 * the IRQ was acked, it actually shouldn't be
+			 * cleared, but we have no way of knowing that unless
+			 * we start trapping ACKs when the soft-pending state
+			 * is set.
+			 */
+			vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
 
 			/* Any additional pending interrupt? */
-			if (vgic_dist_irq_is_pending(vcpu, irq)) {
-				vgic_cpu_irq_set(vcpu, irq);
+			if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
+				vgic_cpu_irq_set(vcpu, vlr.irq);
 				level_pending = true;
 			} else {
-				vgic_cpu_irq_clear(vcpu, irq);
+				vgic_dist_irq_clear_pending(vcpu, vlr.irq);
+				vgic_cpu_irq_clear(vcpu, vlr.irq);
 			}
 
 			/*
 			 * Despite being EOIed, the LR may not have
 			 * been marked as empty.
 			 */
-			set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
-			vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT;
+			vgic_sync_lr_elrsr(vcpu, lr, vlr);
 		}
 	}
 
-	if (vgic_cpu->vgic_misr & GICH_MISR_U)
-		vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
+	if (status & INT_STATUS_UNDERFLOW)
+		vgic_disable_underflow(vcpu);
 
 	return level_pending;
 }
@@ -1220,30 +1498,32 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+	u64 elrsr;
+	unsigned long *elrsr_ptr;
 	int lr, pending;
 	bool level_pending;
 
 	level_pending = vgic_process_maintenance(vcpu);
+	elrsr = vgic_get_elrsr(vcpu);
+	elrsr_ptr = (unsigned long *)&elrsr;
 
 	/* Clear mappings for empty LRs */
-	for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr,
-			 vgic_cpu->nr_lr) {
-		int irq;
+	for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) {
+		struct vgic_lr vlr;
 
 		if (!test_and_clear_bit(lr, vgic_cpu->lr_used))
 			continue;
 
-		irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
+		vlr = vgic_get_lr(vcpu, lr);
 
-		BUG_ON(irq >= VGIC_NR_IRQS);
-		vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+		BUG_ON(vlr.irq >= dist->nr_irqs);
+		vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
 	}
 
 	/* Check if we still have something up our sleeve... */
-	pending = find_first_zero_bit((unsigned long *)vgic_cpu->vgic_elrsr,
-				      vgic_cpu->nr_lr);
-	if (level_pending || pending < vgic_cpu->nr_lr)
-		set_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
+	pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
+	if (level_pending || pending < vgic->nr_lr)
+		set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
 }
 
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
@@ -1277,7 +1557,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return 0;
 
-	return test_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
+	return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
 }
 
 static void vgic_kick_vcpus(struct kvm *kvm)
@@ -1297,34 +1577,36 @@ static void vgic_kick_vcpus(struct kvm *kvm)
 
 static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
 {
-	int is_edge = vgic_irq_is_edge(vcpu, irq);
-	int state = vgic_dist_irq_is_pending(vcpu, irq);
+	int edge_triggered = vgic_irq_is_edge(vcpu, irq);
 
 	/*
 	 * Only inject an interrupt if:
 	 * - edge triggered and we have a rising edge
 	 * - level triggered and we change level
 	 */
-	if (is_edge)
+	if (edge_triggered) {
+		int state = vgic_dist_irq_is_pending(vcpu, irq);
 		return level > state;
-	else
+	} else {
+		int state = vgic_dist_irq_get_level(vcpu, irq);
 		return level != state;
+	}
 }
 
-static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
+static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
 				  unsigned int irq_num, bool level)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	struct kvm_vcpu *vcpu;
-	int is_edge, is_level;
+	int edge_triggered, level_triggered;
 	int enabled;
 	bool ret = true;
 
 	spin_lock(&dist->lock);
 
 	vcpu = kvm_get_vcpu(kvm, cpuid);
-	is_edge = vgic_irq_is_edge(vcpu, irq_num);
-	is_level = !is_edge;
+	edge_triggered = vgic_irq_is_edge(vcpu, irq_num);
+	level_triggered = !edge_triggered;
 
 	if (!vgic_validate_injection(vcpu, irq_num, level)) {
 		ret = false;
@@ -1338,10 +1620,19 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
 
 	kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
 
-	if (level)
-		vgic_dist_irq_set(vcpu, irq_num);
-	else
-		vgic_dist_irq_clear(vcpu, irq_num);
+	if (level) {
+		if (level_triggered)
+			vgic_dist_irq_set_level(vcpu, irq_num);
+		vgic_dist_irq_set_pending(vcpu, irq_num);
+	} else {
+		if (level_triggered) {
+			vgic_dist_irq_clear_level(vcpu, irq_num);
+			if (!vgic_dist_irq_soft_pend(vcpu, irq_num))
+				vgic_dist_irq_clear_pending(vcpu, irq_num);
+		} else {
+			vgic_dist_irq_clear_pending(vcpu, irq_num);
+		}
+	}
 
 	enabled = vgic_irq_is_enabled(vcpu, irq_num);
 
@@ -1350,7 +1641,7 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
 		goto out;
 	}
 
-	if (is_level && vgic_irq_is_active(vcpu, irq_num)) {
+	if (!vgic_can_sample_irq(vcpu, irq_num)) {
 		/*
 		 * Level interrupt in progress, will be picked up
 		 * when EOId.
@@ -1361,7 +1652,7 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
 
 	if (level) {
 		vgic_cpu_irq_set(vcpu, irq_num);
-		set_bit(cpuid, &dist->irq_pending_on_cpu);
+		set_bit(cpuid, dist->irq_pending_on_cpu);
 	}
 
 out:
@@ -1387,7 +1678,8 @@ out:
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 			bool level)
 {
-	if (vgic_update_irq_state(kvm, cpuid, irq_num, level))
+	if (likely(vgic_initialized(kvm)) &&
+	    vgic_update_irq_pending(kvm, cpuid, irq_num, level))
 		vgic_kick_vcpus(kvm);
 
 	return 0;
@@ -1404,6 +1696,32 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	kfree(vgic_cpu->pending_shared);
+	kfree(vgic_cpu->vgic_irq_lr_map);
+	vgic_cpu->pending_shared = NULL;
+	vgic_cpu->vgic_irq_lr_map = NULL;
+}
+
+static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+	int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
+	vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
+	vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL);
+
+	if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
+		kvm_vgic_vcpu_destroy(vcpu);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 /**
  * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
  * @vcpu: pointer to the vcpu struct
@@ -1411,16 +1729,13 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
  * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
  * this vcpu and enable the VGIC for this VCPU
  */
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int i;
 
-	if (vcpu->vcpu_id >= VGIC_MAX_CPUS)
-		return -EBUSY;
-
-	for (i = 0; i < VGIC_NR_IRQS; i++) {
+	for (i = 0; i < dist->nr_irqs; i++) {
 		if (i < VGIC_NR_PPIS)
 			vgic_bitmap_set_irq_val(&dist->irq_enabled,
 						vcpu->vcpu_id, i, 1);
@@ -1432,119 +1747,119 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	}
 
 	/*
-	 * By forcing VMCR to zero, the GIC will restore the binary
-	 * points to their reset values. Anything else resets to zero
-	 * anyway.
+	 * Store the number of LRs per vcpu, so we don't have to go
+	 * all the way to the distributor structure to find out. Only
+	 * assembly code should use this one.
 	 */
-	vgic_cpu->vgic_vmcr = 0;
+	vgic_cpu->nr_lr = vgic->nr_lr;
 
-	vgic_cpu->nr_lr = vgic_nr_lr;
-	vgic_cpu->vgic_hcr = GICH_HCR_EN; /* Get the show on the road... */
-
-	return 0;
+	vgic_enable(vcpu);
 }
 
-static void vgic_init_maintenance_interrupt(void *info)
+void kvm_vgic_destroy(struct kvm *kvm)
 {
-	enable_percpu_irq(vgic_maint_irq, 0);
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vgic_vcpu_destroy(vcpu);
+
+	vgic_free_bitmap(&dist->irq_enabled);
+	vgic_free_bitmap(&dist->irq_level);
+	vgic_free_bitmap(&dist->irq_pending);
+	vgic_free_bitmap(&dist->irq_soft_pend);
+	vgic_free_bitmap(&dist->irq_queued);
+	vgic_free_bitmap(&dist->irq_cfg);
+	vgic_free_bytemap(&dist->irq_priority);
+	if (dist->irq_spi_target) {
+		for (i = 0; i < dist->nr_cpus; i++)
+			vgic_free_bitmap(&dist->irq_spi_target[i]);
+	}
+	kfree(dist->irq_sgi_sources);
+	kfree(dist->irq_spi_cpu);
+	kfree(dist->irq_spi_target);
+	kfree(dist->irq_pending_on_cpu);
+	dist->irq_sgi_sources = NULL;
+	dist->irq_spi_cpu = NULL;
+	dist->irq_spi_target = NULL;
+	dist->irq_pending_on_cpu = NULL;
 }
 
-static int vgic_cpu_notify(struct notifier_block *self,
-			   unsigned long action, void *cpu)
+/*
+ * Allocate and initialize the various data structures. Must be called
+ * with kvm->lock held!
+ */
+static int vgic_init_maps(struct kvm *kvm)
 {
-	switch (action) {
-	case CPU_STARTING:
-	case CPU_STARTING_FROZEN:
-		vgic_init_maintenance_interrupt(NULL);
-		break;
-	case CPU_DYING:
-	case CPU_DYING_FROZEN:
-		disable_percpu_irq(vgic_maint_irq);
-		break;
-	}
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct kvm_vcpu *vcpu;
+	int nr_cpus, nr_irqs;
+	int ret, i;
 
-	return NOTIFY_OK;
-}
+	if (dist->nr_cpus)	/* Already allocated */
+		return 0;
 
-static struct notifier_block vgic_cpu_nb = {
-	.notifier_call = vgic_cpu_notify,
-};
+	nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
+	if (!nr_cpus)		/* No vcpus? Can't be good... */
+		return -EINVAL;
 
-int kvm_vgic_hyp_init(void)
-{
-	int ret;
-	struct resource vctrl_res;
-	struct resource vcpu_res;
+	/*
+	 * If nobody configured the number of interrupts, use the
+	 * legacy one.
+	 */
+	if (!dist->nr_irqs)
+		dist->nr_irqs = VGIC_NR_IRQS_LEGACY;
 
-	vgic_node = of_find_compatible_node(NULL, NULL, "arm,cortex-a15-gic");
-	if (!vgic_node) {
-		kvm_err("error: no compatible vgic node in DT\n");
-		return -ENODEV;
-	}
+	nr_irqs = dist->nr_irqs;
 
-	vgic_maint_irq = irq_of_parse_and_map(vgic_node, 0);
-	if (!vgic_maint_irq) {
-		kvm_err("error getting vgic maintenance irq from DT\n");
-		ret = -ENXIO;
-		goto out;
-	}
+	ret  = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
+	ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
+	ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);
 
-	ret = request_percpu_irq(vgic_maint_irq, vgic_maintenance_handler,
-				 "vgic", kvm_get_running_vcpus());
-	if (ret) {
-		kvm_err("Cannot register interrupt %d\n", vgic_maint_irq);
+	if (ret)
 		goto out;
-	}
 
-	ret = register_cpu_notifier(&vgic_cpu_nb);
-	if (ret) {
-		kvm_err("Cannot register vgic CPU notifier\n");
-		goto out_free_irq;
-	}
-
-	ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
-	if (ret) {
-		kvm_err("Cannot obtain VCTRL resource\n");
-		goto out_free_irq;
-	}
-
-	vgic_vctrl_base = of_iomap(vgic_node, 2);
-	if (!vgic_vctrl_base) {
-		kvm_err("Cannot ioremap VCTRL\n");
+	dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL);
+	dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL);
+	dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus,
+				       GFP_KERNEL);
+	dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
+					   GFP_KERNEL);
+	if (!dist->irq_sgi_sources ||
+	    !dist->irq_spi_cpu ||
+	    !dist->irq_spi_target ||
+	    !dist->irq_pending_on_cpu) {
 		ret = -ENOMEM;
-		goto out_free_irq;
+		goto out;
 	}
 
-	vgic_nr_lr = readl_relaxed(vgic_vctrl_base + GICH_VTR);
-	vgic_nr_lr = (vgic_nr_lr & 0x3f) + 1;
-
-	ret = create_hyp_io_mappings(vgic_vctrl_base,
-				     vgic_vctrl_base + resource_size(&vctrl_res),
-				     vctrl_res.start);
-	if (ret) {
-		kvm_err("Cannot map VCTRL into hyp\n");
-		goto out_unmap;
-	}
+	for (i = 0; i < nr_cpus; i++)
+		ret |= vgic_init_bitmap(&dist->irq_spi_target[i],
+					nr_cpus, nr_irqs);
 
-	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
-		 vctrl_res.start, vgic_maint_irq);
-	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+	if (ret)
+		goto out;
 
-	if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
-		kvm_err("Cannot obtain VCPU resource\n");
-		ret = -ENXIO;
-		goto out_unmap;
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
+		if (ret) {
+			kvm_err("VGIC: Failed to allocate vcpu memory\n");
+			break;
+		}
 	}
-	vgic_vcpu_base = vcpu_res.start;
 
-	goto out;
+	for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
+		vgic_set_target_reg(kvm, 0, i);
 
-out_unmap:
-	iounmap(vgic_vctrl_base);
-out_free_irq:
-	free_percpu_irq(vgic_maint_irq, kvm_get_running_vcpus());
 out:
-	of_node_put(vgic_node);
+	if (ret)
+		kvm_vgic_destroy(kvm);
+
 	return ret;
 }
 
@@ -1559,6 +1874,7 @@ out:
  */
 int kvm_vgic_init(struct kvm *kvm)
 {
+	struct kvm_vcpu *vcpu;
 	int ret = 0, i;
 
 	if (!irqchip_in_kernel(kvm))
@@ -1576,18 +1892,26 @@ int kvm_vgic_init(struct kvm *kvm)
 		goto out;
 	}
 
+	ret = vgic_init_maps(kvm);
+	if (ret) {
+		kvm_err("Unable to allocate maps\n");
+		goto out;
+	}
+
 	ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
-				    vgic_vcpu_base, KVM_VGIC_V2_CPU_SIZE);
+				    vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE);
 	if (ret) {
 		kvm_err("Unable to remap VGIC CPU to VCPU\n");
 		goto out;
 	}
 
-	for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4)
-		vgic_set_target_reg(kvm, 0, i);
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vgic_vcpu_init(vcpu);
 
 	kvm->arch.vgic.ready = true;
 out:
+	if (ret)
+		kvm_vgic_destroy(kvm);
 	mutex_unlock(&kvm->lock);
 	return ret;
 }
@@ -1623,7 +1947,8 @@ int kvm_vgic_create(struct kvm *kvm)
 	}
 
 	spin_lock_init(&kvm->arch.vgic.lock);
-	kvm->arch.vgic.vctrl_base = vgic_vctrl_base;
+	kvm->arch.vgic.in_kernel = true;
+	kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
 
@@ -1638,7 +1963,7 @@ out:
 	return ret;
 }
 
-static bool vgic_ioaddr_overlap(struct kvm *kvm)
+static int vgic_ioaddr_overlap(struct kvm *kvm)
 {
 	phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
 	phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;
@@ -1667,10 +1992,11 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
 	if (addr + size < addr)
 		return -EINVAL;
 
+	*ioaddr = addr;
 	ret = vgic_ioaddr_overlap(kvm);
 	if (ret)
-		return ret;
-	*ioaddr = addr;
+		*ioaddr = VGIC_ADDR_UNDEF;
+
 	return ret;
 }
 
@@ -1721,39 +2047,40 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
 static bool handle_cpu_mmio_misc(struct kvm_vcpu *vcpu,
 				 struct kvm_exit_mmio *mmio, phys_addr_t offset)
 {
-	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
-	u32 reg, mask = 0, shift = 0;
 	bool updated = false;
+	struct vgic_vmcr vmcr;
+	u32 *vmcr_field;
+	u32 reg;
+
+	vgic_get_vmcr(vcpu, &vmcr);
 
 	switch (offset & ~0x3) {
 	case GIC_CPU_CTRL:
-		mask = GICH_VMCR_CTRL_MASK;
-		shift = GICH_VMCR_CTRL_SHIFT;
+		vmcr_field = &vmcr.ctlr;
 		break;
 	case GIC_CPU_PRIMASK:
-		mask = GICH_VMCR_PRIMASK_MASK;
-		shift = GICH_VMCR_PRIMASK_SHIFT;
+		vmcr_field = &vmcr.pmr;
 		break;
 	case GIC_CPU_BINPOINT:
-		mask = GICH_VMCR_BINPOINT_MASK;
-		shift = GICH_VMCR_BINPOINT_SHIFT;
+		vmcr_field = &vmcr.bpr;
 		break;
 	case GIC_CPU_ALIAS_BINPOINT:
-		mask = GICH_VMCR_ALIAS_BINPOINT_MASK;
-		shift = GICH_VMCR_ALIAS_BINPOINT_SHIFT;
+		vmcr_field = &vmcr.abpr;
 		break;
+	default:
+		BUG();
 	}
 
 	if (!mmio->is_write) {
-		reg = (vgic_cpu->vgic_vmcr & mask) >> shift;
+		reg = *vmcr_field;
 		mmio_data_write(mmio, ~0, reg);
 	} else {
 		reg = mmio_data_read(mmio, ~0);
-		reg = (reg << shift) & mask;
-		if (reg != (vgic_cpu->vgic_vmcr & mask))
+		if (reg != *vmcr_field) {
+			*vmcr_field = reg;
+			vgic_set_vmcr(vcpu, &vmcr);
 			updated = true;
-		vgic_cpu->vgic_vmcr &= ~mask;
-		vgic_cpu->vgic_vmcr |= reg;
+		}
 	}
 	return updated;
 }
@@ -1825,6 +2152,10 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
+	ret = vgic_init_maps(dev->kvm);
+	if (ret)
+		goto out;
+
 	if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
 		ret = -EINVAL;
 		goto out;
@@ -1922,6 +2253,36 @@ static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 
 		return vgic_attr_regs_access(dev, attr, &reg, true);
 	}
+	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		u32 val;
+		int ret = 0;
+
+		if (get_user(val, uaddr))
+			return -EFAULT;
+
+		/*
+		 * We require:
+		 * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs
+		 * - at most 1024 interrupts
+		 * - a multiple of 32 interrupts
+		 */
+		if (val < (VGIC_NR_PRIVATE_IRQS + 32) ||
+		    val > VGIC_MAX_IRQS ||
+		    (val & 31))
+			return -EINVAL;
+
+		mutex_lock(&dev->kvm->lock);
+
+		if (vgic_initialized(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
+			ret = -EBUSY;
+		else
+			dev->kvm->arch.vgic.nr_irqs = val;
+
+		mutex_unlock(&dev->kvm->lock);
+
+		return ret;
+	}
 
 	}
 
@@ -1958,6 +2319,11 @@ static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		r = put_user(reg, uaddr);
 		break;
 	}
+	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+		u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+		r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
+		break;
+	}
 
 	}
 
@@ -1994,6 +2360,8 @@ static int vgic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
 		offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
 		return vgic_has_attr_regs(vgic_cpu_ranges, offset);
+	case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
+		return 0;
 	}
 	return -ENXIO;
 }
@@ -2008,7 +2376,7 @@ static int vgic_create(struct kvm_device *dev, u32 type)
 	return kvm_vgic_create(dev->kvm);
 }
 
-struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+static struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.name = "kvm-arm-vgic",
 	.create = vgic_create,
 	.destroy = vgic_destroy,
@@ -2016,3 +2384,81 @@ struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.get_attr = vgic_get_attr,
 	.has_attr = vgic_has_attr,
 };
+
+static void vgic_init_maintenance_interrupt(void *info)
+{
+	enable_percpu_irq(vgic->maint_irq, 0);
+}
+
+static int vgic_cpu_notify(struct notifier_block *self,
+			   unsigned long action, void *cpu)
+{
+	switch (action) {
+	case CPU_STARTING:
+	case CPU_STARTING_FROZEN:
+		vgic_init_maintenance_interrupt(NULL);
+		break;
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		disable_percpu_irq(vgic->maint_irq);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block vgic_cpu_nb = {
+	.notifier_call = vgic_cpu_notify,
+};
+
+static const struct of_device_id vgic_ids[] = {
+	{ .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
+	{ .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
+	{},
+};
+
+int kvm_vgic_hyp_init(void)
+{
+	const struct of_device_id *matched_id;
+	int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
+			  const struct vgic_params **);
+	struct device_node *vgic_node;
+	int ret;
+
+	vgic_node = of_find_matching_node_and_match(NULL,
+						    vgic_ids, &matched_id);
+	if (!vgic_node) {
+		kvm_err("error: no compatible GIC node found\n");
+		return -ENODEV;
+	}
+
+	vgic_probe = matched_id->data;
+	ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
+	if (ret)
+		return ret;
+
+	ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
+				 "vgic", kvm_get_running_vcpus());
+	if (ret) {
+		kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
+		return ret;
+	}
+
+	ret = register_cpu_notifier(&vgic_cpu_nb);
+	if (ret) {
+		kvm_err("Cannot register vgic CPU notifier\n");
+		goto out_free_irq;
+	}
+
+	/* Callback into for arch code for setup */
+	vgic_arch_setup(vgic);
+
+	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
+	return kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
+				       KVM_DEV_TYPE_ARM_VGIC_V2);
+
+out_free_irq:
+	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
+	return ret;
+}
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8631d9c14320..d6a3d0993d88 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -28,6 +28,21 @@
 #include "async_pf.h"
 #include <trace/events/kvm.h>
 
+static inline void kvm_async_page_present_sync(struct kvm_vcpu *vcpu,
+					       struct kvm_async_pf *work)
+{
+#ifdef CONFIG_KVM_ASYNC_PF_SYNC
+	kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+static inline void kvm_async_page_present_async(struct kvm_vcpu *vcpu,
+						struct kvm_async_pf *work)
+{
+#ifndef CONFIG_KVM_ASYNC_PF_SYNC
+	kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+
 static struct kmem_cache *async_pf_cache;
 
 int kvm_async_pf_init(void)
@@ -65,11 +80,10 @@ static void async_pf_execute(struct work_struct *work)
 
 	might_sleep();
 
-	use_mm(mm);
 	down_read(&mm->mmap_sem);
-	get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL);
+	get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL);
 	up_read(&mm->mmap_sem);
-	unuse_mm(mm);
+	kvm_async_page_present_sync(vcpu, apf);
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
@@ -85,7 +99,7 @@ static void async_pf_execute(struct work_struct *work)
 	if (waitqueue_active(&vcpu->wq))
 		wake_up_interruptible(&vcpu->wq);
 
-	mmdrop(mm);
+	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
 }
 
@@ -97,11 +111,16 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 			list_entry(vcpu->async_pf.queue.next,
 				   typeof(*work), queue);
 		list_del(&work->queue);
+
+#ifdef CONFIG_KVM_ASYNC_PF_SYNC
+		flush_work(&work->work);
+#else
 		if (cancel_work_sync(&work->work)) {
-			mmdrop(work->mm);
+			mmput(work->mm);
 			kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
 			kmem_cache_free(async_pf_cache, work);
 		}
+#endif
 	}
 
 	spin_lock(&vcpu->async_pf.lock);
@@ -130,7 +149,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 		spin_unlock(&vcpu->async_pf.lock);
 
 		kvm_arch_async_page_ready(vcpu, work);
-		kvm_arch_async_page_present(vcpu, work);
+		kvm_async_page_present_async(vcpu, work);
 
 		list_del(&work->queue);
 		vcpu->async_pf.queued--;
@@ -138,7 +157,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 		       struct kvm_arch_async_pf *arch)
 {
 	struct kvm_async_pf *work;
@@ -159,10 +178,10 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	work->wakeup_all = false;
 	work->vcpu = vcpu;
 	work->gva = gva;
-	work->addr = gfn_to_hva(vcpu->kvm, gfn);
+	work->addr = hva;
 	work->arch = *arch;
 	work->mm = current->mm;
-	atomic_inc(&work->mm->mm_count);
+	atomic_inc(&work->mm->mm_users);
 	kvm_get_kvm(work->vcpu->kvm);
 
 	/* this can't really happen otherwise gfn_to_pfn_async
@@ -180,7 +199,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	return 1;
 retry_sync:
 	kvm_put_kvm(work->vcpu->kvm);
-	mmdrop(work->mm);
+	mmput(work->mm);
 	kmem_cache_free(async_pf_cache, work);
 	return 0;
 }
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index abe4d6043b36..0ab1411eb007 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -31,11 +31,14 @@
 #include <linux/list.h>
 #include <linux/eventfd.h>
 #include <linux/kernel.h>
+#include <linux/srcu.h>
 #include <linux/slab.h>
+#include <linux/seqlock.h>
+#include <trace/events/kvm.h>
 
 #include "iodev.h"
 
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
 /*
  * --------------------------------------------------------------------
  * irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -74,7 +77,8 @@ struct _irqfd {
 	struct kvm *kvm;
 	wait_queue_t wait;
 	/* Update side is protected by irqfds.lock */
-	struct kvm_kernel_irq_routing_entry __rcu *irq_entry;
+	struct kvm_kernel_irq_routing_entry irq_entry;
+	seqcount_t irq_entry_sc;
 	/* Used for level IRQ fast-path */
 	int gsi;
 	struct work_struct inject;
@@ -118,19 +122,22 @@ static void
 irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
 {
 	struct _irqfd_resampler *resampler;
+	struct kvm *kvm;
 	struct _irqfd *irqfd;
+	int idx;
 
 	resampler = container_of(kian, struct _irqfd_resampler, notifier);
+	kvm = resampler->kvm;
 
-	kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+	kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
 		    resampler->notifier.gsi, 0, false);
 
-	rcu_read_lock();
+	idx = srcu_read_lock(&kvm->irq_srcu);
 
 	list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
 		eventfd_signal(irqfd->resamplefd, 1);
 
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
 static void
@@ -142,7 +149,7 @@ irqfd_resampler_shutdown(struct _irqfd *irqfd)
 	mutex_lock(&kvm->irqfds.resampler_lock);
 
 	list_del_rcu(&irqfd->resampler_link);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 
 	if (list_empty(&resampler->list)) {
 		list_del(&resampler->link);
@@ -219,19 +226,24 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
 	struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
 	unsigned long flags = (unsigned long)key;
-	struct kvm_kernel_irq_routing_entry *irq;
+	struct kvm_kernel_irq_routing_entry irq;
 	struct kvm *kvm = irqfd->kvm;
+	unsigned seq;
+	int idx;
 
 	if (flags & POLLIN) {
-		rcu_read_lock();
-		irq = rcu_dereference(irqfd->irq_entry);
+		idx = srcu_read_lock(&kvm->irq_srcu);
+		do {
+			seq = read_seqcount_begin(&irqfd->irq_entry_sc);
+			irq = irqfd->irq_entry;
+		} while (read_seqcount_retry(&irqfd->irq_entry_sc, seq));
 		/* An event has been signaled, inject an interrupt */
-		if (irq)
-			kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
+		if (irq.type == KVM_IRQ_ROUTING_MSI)
+			kvm_set_msi(&irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
 					false);
 		else
 			schedule_work(&irqfd->inject);
-		rcu_read_unlock();
+		srcu_read_unlock(&kvm->irq_srcu, idx);
 	}
 
 	if (flags & POLLHUP) {
@@ -267,34 +279,37 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
 }
 
 /* Must be called under irqfds.lock */
-static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
-			 struct kvm_irq_routing_table *irq_rt)
+static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd)
 {
 	struct kvm_kernel_irq_routing_entry *e;
+	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
+	int i, n_entries;
 
-	if (irqfd->gsi >= irq_rt->nr_rt_entries) {
-		rcu_assign_pointer(irqfd->irq_entry, NULL);
-		return;
-	}
+	n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi);
+
+	write_seqcount_begin(&irqfd->irq_entry_sc);
+
+	irqfd->irq_entry.type = 0;
 
-	hlist_for_each_entry(e, &irq_rt->map[irqfd->gsi], link) {
+	e = entries;
+	for (i = 0; i < n_entries; ++i, ++e) {
 		/* Only fast-path MSI. */
 		if (e->type == KVM_IRQ_ROUTING_MSI)
-			rcu_assign_pointer(irqfd->irq_entry, e);
-		else
-			rcu_assign_pointer(irqfd->irq_entry, NULL);
+			irqfd->irq_entry = *e;
 	}
+
+	write_seqcount_end(&irqfd->irq_entry_sc);
 }
 
 static int
 kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 {
-	struct kvm_irq_routing_table *irq_rt;
 	struct _irqfd *irqfd, *tmp;
 	struct fd f;
 	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
 	int ret;
 	unsigned int events;
+	int idx;
 
 	irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
 	if (!irqfd)
@@ -305,6 +320,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	INIT_LIST_HEAD(&irqfd->list);
 	INIT_WORK(&irqfd->inject, irqfd_inject);
 	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
+	seqcount_init(&irqfd->irq_entry_sc);
 
 	f = fdget(args->fd);
 	if (!f.file) {
@@ -363,7 +379,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 		}
 
 		list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
-		synchronize_rcu();
+		synchronize_srcu(&kvm->irq_srcu);
 
 		mutex_unlock(&kvm->irqfds.resampler_lock);
 	}
@@ -387,9 +403,9 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 		goto fail;
 	}
 
-	irq_rt = rcu_dereference_protected(kvm->irq_routing,
-					   lockdep_is_held(&kvm->irqfds.lock));
-	irqfd_update(kvm, irqfd, irq_rt);
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irqfd_update(kvm, irqfd);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	events = f.file->f_op->poll(f.file, &irqfd->pt);
 
@@ -428,12 +444,73 @@ out:
 	kfree(irqfd);
 	return ret;
 }
+
+bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+	struct kvm_irq_ack_notifier *kian;
+	int gsi, idx;
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
+					 link)
+			if (kian->gsi == gsi) {
+				srcu_read_unlock(&kvm->irq_srcu, idx);
+				return true;
+			}
+
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
+
+void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+	struct kvm_irq_ack_notifier *kian;
+	int gsi, idx;
+
+	trace_kvm_ack_irq(irqchip, pin);
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
+					 link)
+			if (kian->gsi == gsi)
+				kian->irq_acked(kian);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+void kvm_register_irq_ack_notifier(struct kvm *kvm,
+				   struct kvm_irq_ack_notifier *kian)
+{
+	mutex_lock(&kvm->irq_lock);
+	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
+	mutex_unlock(&kvm->irq_lock);
+#ifdef __KVM_HAVE_IOAPIC
+	kvm_vcpu_request_scan_ioapic(kvm);
+#endif
+}
+
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+				    struct kvm_irq_ack_notifier *kian)
+{
+	mutex_lock(&kvm->irq_lock);
+	hlist_del_init_rcu(&kian->link);
+	mutex_unlock(&kvm->irq_lock);
+	synchronize_srcu(&kvm->irq_srcu);
+#ifdef __KVM_HAVE_IOAPIC
+	kvm_vcpu_request_scan_ioapic(kvm);
+#endif
+}
 #endif
 
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
 	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
@@ -442,7 +519,7 @@ kvm_eventfd_init(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -461,14 +538,14 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
 		if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) {
 			/*
-			 * This rcu_assign_pointer is needed for when
+			 * This clearing of irq_entry.type is needed for when
 			 * another thread calls kvm_irq_routing_update before
 			 * we flush workqueue below (we synchronize with
 			 * kvm_irq_routing_update using irqfds.lock).
-			 * It is paired with synchronize_rcu done by caller
-			 * of that function.
 			 */
-			rcu_assign_pointer(irqfd->irq_entry, NULL);
+			write_seqcount_begin(&irqfd->irq_entry_sc);
+			irqfd->irq_entry.type = 0;
+			write_seqcount_end(&irqfd->irq_entry_sc);
 			irqfd_deactivate(irqfd);
 		}
 	}
@@ -523,20 +600,17 @@ kvm_irqfd_release(struct kvm *kvm)
 }
 
 /*
- * Change irq_routing and irqfd.
- * Caller must invoke synchronize_rcu afterwards.
+ * Take note of a change in irq routing.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
  */
-void kvm_irq_routing_update(struct kvm *kvm,
-			    struct kvm_irq_routing_table *irq_rt)
+void kvm_irq_routing_update(struct kvm *kvm)
 {
 	struct _irqfd *irqfd;
 
 	spin_lock_irq(&kvm->irqfds.lock);
 
-	rcu_assign_pointer(kvm->irq_routing, irq_rt);
-
 	list_for_each_entry(irqfd, &kvm->irqfds.items, list)
-		irqfd_update(kvm, irqfd, irq_rt);
+		irqfd_update(kvm, irqfd);
 
 	spin_unlock_irq(&kvm->irqfds.lock);
 }
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index ce9ed99ad7dc..b47541dd798f 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -203,10 +203,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
 	spin_lock(&ioapic->lock);
 	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
 		e = &ioapic->redirtbl[index];
-		if (!e->fields.mask &&
-			(e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
-			 kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
-				 index) || index == RTC_GSI)) {
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
 				e->fields.dest_id, e->fields.dest_mode)) {
 				__set_bit(e->fields.vector,
@@ -306,7 +305,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
 		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
 				ioapic->rtc_status.dest_map);
-		ioapic->rtc_status.pending_eoi = ret;
+		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
 	} else
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
 
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 0df7d4b34dfe..1f0dc1e5f1f0 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -43,13 +43,13 @@ static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages);
 
 static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
-			   unsigned long size)
+			   unsigned long npages)
 {
 	gfn_t end_gfn;
 	pfn_t pfn;
 
 	pfn     = gfn_to_pfn_memslot(slot, gfn);
-	end_gfn = gfn + (size >> PAGE_SHIFT);
+	end_gfn = gfn + npages;
 	gfn    += 1;
 
 	if (is_error_noslot_pfn(pfn))
@@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 	return pfn;
 }
 
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; ++i)
+		kvm_release_pfn_clean(pfn + i);
+}
+
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
 	gfn_t gfn, end_gfn;
@@ -111,7 +119,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		 * Pin all pages we are about to map in memory. This is
 		 * important because we unmap and unpin in 4kb steps later.
 		 */
-		pfn = kvm_pin_pages(slot, gfn, page_size);
+		pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
 		if (is_error_noslot_pfn(pfn)) {
 			gfn += 1;
 			continue;
@@ -123,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
 			       "iommu failed to map pfn=%llx\n", pfn);
+			kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
 			goto unmap_pages;
 		}
 
@@ -134,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 	return 0;
 
 unmap_pages:
-	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
+	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
 	return r;
 }
 
@@ -266,14 +275,6 @@ out_unlock:
 	return r;
 }
 
-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
-{
-	unsigned long i;
-
-	for (i = 0; i < npages; ++i)
-		kvm_release_pfn_clean(pfn + i);
-}
-
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages)
 {
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index e2e6b4473a96..963b8995a9e8 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -160,9 +160,10 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
  */
 int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 {
+	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
 	struct kvm_kernel_irq_routing_entry *e;
 	int ret = -EINVAL;
-	struct kvm_irq_routing_table *irq_rt;
+	int idx;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
 
@@ -174,17 +175,15 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	 * Since there's no easy way to do this, we only support injecting MSI
 	 * which is limited to 1:1 GSI mapping.
 	 */
-	rcu_read_lock();
-	irq_rt = rcu_dereference(kvm->irq_routing);
-	if (irq < irq_rt->nr_rt_entries)
-		hlist_for_each_entry(e, &irq_rt->map[irq], link) {
-			if (likely(e->type == KVM_IRQ_ROUTING_MSI))
-				ret = kvm_set_msi_inatomic(e, kvm);
-			else
-				ret = -EWOULDBLOCK;
-			break;
-		}
-	rcu_read_unlock();
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
+		e = &entries[0];
+		if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+			ret = kvm_set_msi_inatomic(e, kvm);
+		else
+			ret = -EWOULDBLOCK;
+	}
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;
 }
 
@@ -253,26 +252,25 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 	mutex_lock(&kvm->irq_lock);
 	hlist_del_rcu(&kimn->link);
 	mutex_unlock(&kvm->irq_lock);
-	synchronize_rcu();
+	synchronize_srcu(&kvm->irq_srcu);
 }
 
 void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 			     bool mask)
 {
 	struct kvm_irq_mask_notifier *kimn;
-	int gsi;
+	int idx, gsi;
 
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
 	if (gsi != -1)
 		hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
 			if (kimn->irq == gsi)
 				kimn->func(kimn, mask);
-	rcu_read_unlock();
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
-			  struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
 	int r = -EINVAL;
@@ -303,7 +301,6 @@ int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
 		e->irqchip.pin = ue->u.irqchip.pin + delta;
 		if (e->irqchip.pin >= max_pin)
 			goto out;
-		rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
 		break;
 	case KVM_IRQ_ROUTING_MSI:
 		e->set = kvm_set_msi;
@@ -322,13 +319,13 @@ out:
 
 #define IOAPIC_ROUTING_ENTRY(irq) \
 	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
-	  .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) }
+	  .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
 #define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
 
 #ifdef CONFIG_X86
 #  define PIC_ROUTING_ENTRY(irq) \
 	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
-	  .u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 }
+	  .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
 #  define ROUTING_ENTRY2(irq) \
 	IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
 #else
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 20dc9e4a8f6c..7f256f31df10 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -26,69 +26,47 @@
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
+#include <linux/srcu.h>
 #include <linux/export.h>
 #include <trace/events/kvm.h>
 #include "irq.h"
 
-bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
-	struct kvm_irq_ack_notifier *kian;
-	int gsi;
-
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
-	if (gsi != -1)
-		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
-					 link)
-			if (kian->gsi == gsi) {
-				rcu_read_unlock();
-				return true;
-			}
-
-	rcu_read_unlock();
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
+struct kvm_irq_routing_table {
+	int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
+	struct kvm_kernel_irq_routing_entry *rt_entries;
+	u32 nr_rt_entries;
+	/*
+	 * Array indexed by gsi. Each entry contains list of irq chips
+	 * the gsi is connected to.
+	 */
+	struct hlist_head map[0];
+};
 
-void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
+int kvm_irq_map_gsi(struct kvm *kvm,
+		    struct kvm_kernel_irq_routing_entry *entries, int gsi)
 {
-	struct kvm_irq_ack_notifier *kian;
-	int gsi;
-
-	trace_kvm_ack_irq(irqchip, pin);
-
-	rcu_read_lock();
-	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
-	if (gsi != -1)
-		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
-					 link)
-			if (kian->gsi == gsi)
-				kian->irq_acked(kian);
-	rcu_read_unlock();
-}
+	struct kvm_irq_routing_table *irq_rt;
+	struct kvm_kernel_irq_routing_entry *e;
+	int n = 0;
+
+	irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
+					lockdep_is_held(&kvm->irq_lock));
+	if (gsi < irq_rt->nr_rt_entries) {
+		hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
+			entries[n] = *e;
+			++n;
+		}
+	}
 
-void kvm_register_irq_ack_notifier(struct kvm *kvm,
-				   struct kvm_irq_ack_notifier *kian)
-{
-	mutex_lock(&kvm->irq_lock);
-	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
-	mutex_unlock(&kvm->irq_lock);
-#ifdef __KVM_HAVE_IOAPIC
-	kvm_vcpu_request_scan_ioapic(kvm);
-#endif
+	return n;
 }
 
-void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
-				    struct kvm_irq_ack_notifier *kian)
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
-	mutex_lock(&kvm->irq_lock);
-	hlist_del_init_rcu(&kian->link);
-	mutex_unlock(&kvm->irq_lock);
-	synchronize_rcu();
-#ifdef __KVM_HAVE_IOAPIC
-	kvm_vcpu_request_scan_ioapic(kvm);
-#endif
+	struct kvm_irq_routing_table *irq_rt;
+
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+	return irq_rt->chip[irqchip][pin];
 }
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
@@ -114,9 +92,8 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 		bool line_status)
 {
-	struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
-	int ret = -1, i = 0;
-	struct kvm_irq_routing_table *irq_rt;
+	struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS];
+	int ret = -1, i, idx;
 
 	trace_kvm_set_irq(irq, level, irq_source_id);
 
@@ -124,12 +101,9 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 	 * IOAPIC.  So set the bit in both. The guest will ignore
 	 * writes to the unused one.
 	 */
-	rcu_read_lock();
-	irq_rt = rcu_dereference(kvm->irq_routing);
-	if (irq < irq_rt->nr_rt_entries)
-		hlist_for_each_entry(e, &irq_rt->map[irq], link)
-			irq_set[i++] = *e;
-	rcu_read_unlock();
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	i = kvm_irq_map_gsi(kvm, irq_set, irq);
+	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	while(i--) {
 		int r;
@@ -170,9 +144,11 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt,
 
 	e->gsi = ue->gsi;
 	e->type = ue->type;
-	r = kvm_set_routing_entry(rt, e, ue);
+	r = kvm_set_routing_entry(e, ue);
 	if (r)
 		goto out;
+	if (e->type == KVM_IRQ_ROUTING_IRQCHIP)
+		rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi;
 
 	hlist_add_head(&e->link, &rt->map[e->gsi]);
 	r = 0;
@@ -223,10 +199,11 @@ int kvm_set_irq_routing(struct kvm *kvm,
 
 	mutex_lock(&kvm->irq_lock);
 	old = kvm->irq_routing;
-	kvm_irq_routing_update(kvm, new);
+	rcu_assign_pointer(kvm->irq_routing, new);
+	kvm_irq_routing_update(kvm);
 	mutex_unlock(&kvm->irq_lock);
 
-	synchronize_rcu();
+	synchronize_srcu_expedited(&kvm->irq_srcu);
 
 	new = old;
 	r = 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 03a0381b1cb7..a0f02bc7b264 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -52,6 +52,7 @@
 
 #include <asm/processor.h>
 #include <asm/io.h>
+#include <asm/ioctl.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
@@ -95,14 +96,12 @@ static int hardware_enable_all(void);
 static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-static void update_memslots(struct kvm_memslots *slots,
-			    struct kvm_memory_slot *new, u64 last_generation);
 
 static void kvm_release_pfn_dirty(pfn_t pfn);
 static void mark_page_dirty_in_slot(struct kvm *kvm,
 				    struct kvm_memory_slot *memslot, gfn_t gfn);
 
-bool kvm_rebooting;
+__visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;
@@ -110,7 +109,7 @@ static bool largepages_enabled = true;
 bool kvm_is_mmio_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn))
-		return PageReserved(pfn_to_page(pfn));
+		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
 
 	return true;
 }
@@ -129,7 +128,8 @@ int vcpu_load(struct kvm_vcpu *vcpu)
 		struct pid *oldpid = vcpu->pid;
 		struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
 		rcu_assign_pointer(vcpu->pid, newpid);
-		synchronize_rcu();
+		if (oldpid)
+			synchronize_rcu();
 		put_pid(oldpid);
 	}
 	cpu = get_cpu();
@@ -457,14 +457,16 @@ static struct kvm *kvm_create_vm(unsigned long type)
 
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 	r = hardware_enable_all();
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->mask_notifier_list);
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
@@ -473,10 +475,19 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	r = -ENOMEM;
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
+
+	/*
+	 * Init kvm generation close to the maximum to easily test the
+	 * code of handling generation number wrap-around.
+	 */
+	kvm->memslots->generation = -150;
+
 	kvm_init_memslots_id(kvm);
 	if (init_srcu_struct(&kvm->srcu))
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
+	if (init_srcu_struct(&kvm->irq_srcu))
+		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
 					GFP_KERNEL);
@@ -505,10 +516,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	return kvm;
 
 out_err:
+	cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
 	cleanup_srcu_struct(&kvm->srcu);
-out_err_nosrcu:
+out_err_no_srcu:
 	hardware_disable_all();
-out_err_nodisable:
+out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
 	kfree(kvm->memslots);
@@ -604,6 +617,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
 	hardware_disable_all();
@@ -682,8 +696,7 @@ static void sort_memslots(struct kvm_memslots *slots)
 }
 
 static void update_memslots(struct kvm_memslots *slots,
-			    struct kvm_memory_slot *new,
-			    u64 last_generation)
+			    struct kvm_memory_slot *new)
 {
 	if (new) {
 		int id = new->id;
@@ -694,15 +707,13 @@ static void update_memslots(struct kvm_memslots *slots,
 		if (new->npages != npages)
 			sort_memslots(slots);
 	}
-
-	slots->generation = last_generation + 1;
 }
 
 static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
-#ifdef KVM_CAP_READONLY_MEM
+#ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
 
@@ -717,10 +728,24 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 {
 	struct kvm_memslots *old_memslots = kvm->memslots;
 
-	update_memslots(slots, new, kvm->memslots->generation);
+	/*
+	 * Set the low bit in the generation, which disables SPTE caching
+	 * until the end of synchronize_srcu_expedited.
+	 */
+	WARN_ON(old_memslots->generation & 1);
+	slots->generation = old_memslots->generation + 1;
+
+	update_memslots(slots, new);
 	rcu_assign_pointer(kvm->memslots, slots);
 	synchronize_srcu_expedited(&kvm->srcu);
 
+	/*
+	 * Increment the new memslot generation a second time. This prevents
+	 * vm exits that race with memslot updates from caching a memslot
+	 * generation that will (potentially) be valid forever.
+	 */
+	slots->generation++;
+
 	kvm_arch_memslots_updated(kvm);
 
 	return old_memslots;
@@ -771,7 +796,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
-	r = -EINVAL;
 	if (npages > KVM_MEM_MAX_NR_PAGES)
 		goto out;
 
@@ -785,7 +809,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new.npages = npages;
 	new.flags = mem->flags;
 
-	r = -EINVAL;
 	if (npages) {
 		if (!old.npages)
 			change = KVM_MR_CREATE;
@@ -841,7 +864,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	}
 
 	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
-		r = -ENOMEM;
 		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
 				GFP_KERNEL);
 		if (!slots)
@@ -1070,9 +1092,9 @@ EXPORT_SYMBOL_GPL(gfn_to_hva);
  * If writable is set to false, the hva returned by this function is only
  * allowed to be read.
  */
-unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
+				      gfn_t gfn, bool *writable)
 {
-	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 	unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
 
 	if (!kvm_is_error_hva(hva) && writable)
@@ -1081,6 +1103,13 @@ unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
 	return hva;
 }
 
+unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+{
+	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+
+	return gfn_to_hva_memslot_prot(slot, gfn, writable);
+}
+
 static int kvm_read_hva(void *data, void __user *hva, int len)
 {
 	return __copy_from_user(data, hva, len);
@@ -1720,7 +1749,7 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 	rcu_read_lock();
 	pid = rcu_dereference(target->pid);
 	if (pid)
-		task = get_pid_task(target->pid, PIDTYPE_PID);
+		task = get_pid_task(pid, PIDTYPE_PID);
 	rcu_read_unlock();
 	if (!task)
 		return ret;
@@ -1763,8 +1792,7 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 	bool eligible;
 
 	eligible = !vcpu->spin_loop.in_spin_loop ||
-			(vcpu->spin_loop.in_spin_loop &&
-			 vcpu->spin_loop.dy_eligible);
+		    vcpu->spin_loop.dy_eligible;
 
 	if (vcpu->spin_loop.in_spin_loop)
 		kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
@@ -1804,7 +1832,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (vcpu == me)
 				continue;
-			if (waitqueue_active(&vcpu->wq))
+			if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;
@@ -1970,6 +1998,9 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	if (vcpu->kvm->mm != current->mm)
 		return -EIO;
 
+	if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
+		return -EINVAL;
+
 #if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS)
 	/*
 	 * Special cases: vcpu ioctls that are asynchronous to vcpu execution,
@@ -2254,6 +2285,33 @@ struct kvm_device *kvm_device_from_filp(struct file *filp)
 	return filp->private_data;
 }
 
+static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
+#ifdef CONFIG_KVM_MPIC
+	[KVM_DEV_TYPE_FSL_MPIC_20]	= &kvm_mpic_ops,
+	[KVM_DEV_TYPE_FSL_MPIC_42]	= &kvm_mpic_ops,
+#endif
+
+#ifdef CONFIG_KVM_XICS
+	[KVM_DEV_TYPE_XICS]		= &kvm_xics_ops,
+#endif
+
+#ifdef CONFIG_S390
+	[KVM_DEV_TYPE_FLIC]		= &kvm_flic_ops,
+#endif
+};
+
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
+{
+	if (type >= ARRAY_SIZE(kvm_device_ops_table))
+		return -ENOSPC;
+
+	if (kvm_device_ops_table[type] != NULL)
+		return -EEXIST;
+
+	kvm_device_ops_table[type] = ops;
+	return 0;
+}
+
 static int kvm_ioctl_create_device(struct kvm *kvm,
 				   struct kvm_create_device *cd)
 {
@@ -2262,31 +2320,12 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
 	int ret;
 
-	switch (cd->type) {
-#ifdef CONFIG_KVM_MPIC
-	case KVM_DEV_TYPE_FSL_MPIC_20:
-	case KVM_DEV_TYPE_FSL_MPIC_42:
-		ops = &kvm_mpic_ops;
-		break;
-#endif
-#ifdef CONFIG_KVM_XICS
-	case KVM_DEV_TYPE_XICS:
-		ops = &kvm_xics_ops;
-		break;
-#endif
-#ifdef CONFIG_KVM_VFIO
-	case KVM_DEV_TYPE_VFIO:
-		ops = &kvm_vfio_ops;
-		break;
-#endif
-#ifdef CONFIG_KVM_ARM_VGIC
-	case KVM_DEV_TYPE_ARM_VGIC_V2:
-		ops = &kvm_arm_vgic_v2_ops;
-		break;
-#endif
-	default:
+	if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
+		return -ENODEV;
+
+	ops = kvm_device_ops_table[cd->type];
+	if (ops == NULL)
 		return -ENODEV;
-	}
 
 	if (test)
 		return 0;
@@ -2316,6 +2355,34 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	return 0;
 }
 
+static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
+{
+	switch (arg) {
+	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
+	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+	case KVM_CAP_SET_BOOT_CPU_ID:
+#endif
+	case KVM_CAP_INTERNAL_ERROR_DATA:
+#ifdef CONFIG_HAVE_KVM_MSI
+	case KVM_CAP_SIGNAL_MSI:
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
+	case KVM_CAP_IRQFD_RESAMPLE:
+#endif
+	case KVM_CAP_CHECK_EXTENSION_VM:
+		return 1;
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+	case KVM_CAP_IRQ_ROUTING:
+		return KVM_MAX_IRQ_ROUTES;
+#endif
+	default:
+		break;
+	}
+	return kvm_vm_ioctl_check_extension(kvm, arg);
+}
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -2479,6 +2546,9 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_CHECK_EXTENSION:
+		r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
+		break;
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)
@@ -2563,33 +2633,6 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 	return r;
 }
 
-static long kvm_dev_ioctl_check_extension_generic(long arg)
-{
-	switch (arg) {
-	case KVM_CAP_USER_MEMORY:
-	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
-	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
-	case KVM_CAP_SET_BOOT_CPU_ID:
-#endif
-	case KVM_CAP_INTERNAL_ERROR_DATA:
-#ifdef CONFIG_HAVE_KVM_MSI
-	case KVM_CAP_SIGNAL_MSI:
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-	case KVM_CAP_IRQFD_RESAMPLE:
-#endif
-		return 1;
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-	case KVM_CAP_IRQ_ROUTING:
-		return KVM_MAX_IRQ_ROUTES;
-#endif
-	default:
-		break;
-	}
-	return kvm_dev_ioctl_check_extension(arg);
-}
-
 static long kvm_dev_ioctl(struct file *filp,
 			  unsigned int ioctl, unsigned long arg)
 {
@@ -2597,7 +2640,6 @@ static long kvm_dev_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_GET_API_VERSION:
-		r = -EINVAL;
 		if (arg)
 			goto out;
 		r = KVM_API_VERSION;
@@ -2606,10 +2648,9 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = kvm_dev_ioctl_create_vm(arg);
 		break;
 	case KVM_CHECK_EXTENSION:
-		r = kvm_dev_ioctl_check_extension_generic(arg);
+		r = kvm_vm_ioctl_check_extension_generic(NULL, arg);
 		break;
 	case KVM_GET_VCPU_MMAP_SIZE:
-		r = -EINVAL;
 		if (arg)
 			goto out;
 		r = PAGE_SIZE;     /* struct kvm_run */
@@ -2654,7 +2695,7 @@ static void hardware_enable_nolock(void *junk)
 
 	cpumask_set_cpu(cpu, cpus_hardware_enabled);
 
-	r = kvm_arch_hardware_enable(NULL);
+	r = kvm_arch_hardware_enable();
 
 	if (r) {
 		cpumask_clear_cpu(cpu, cpus_hardware_enabled);
@@ -2679,7 +2720,7 @@ static void hardware_disable_nolock(void *junk)
 	if (!cpumask_test_cpu(cpu, cpus_hardware_enabled))
 		return;
 	cpumask_clear_cpu(cpu, cpus_hardware_enabled);
-	kvm_arch_hardware_disable(NULL);
+	kvm_arch_hardware_disable();
 }
 
 static void hardware_disable(void)
@@ -3108,6 +3149,8 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 	if (vcpu->preempted)
 		vcpu->preempted = false;
 
+	kvm_arch_sched_in(vcpu, cpu);
+
 	kvm_arch_vcpu_load(vcpu, cpu);
 }
 
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index b4f9507ae650..4c8a2e17ed81 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -233,6 +233,16 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
 }
 
+static int kvm_vfio_create(struct kvm_device *dev, u32 type);
+
+static struct kvm_device_ops kvm_vfio_ops = {
+	.name = "kvm-vfio",
+	.create = kvm_vfio_create,
+	.destroy = kvm_vfio_destroy,
+	.set_attr = kvm_vfio_set_attr,
+	.has_attr = kvm_vfio_has_attr,
+};
+
 static int kvm_vfio_create(struct kvm_device *dev, u32 type)
 {
 	struct kvm_device *tmp;
@@ -255,10 +265,8 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type)
 	return 0;
 }
 
-struct kvm_device_ops kvm_vfio_ops = {
-	.name = "kvm-vfio",
-	.create = kvm_vfio_create,
-	.destroy = kvm_vfio_destroy,
-	.set_attr = kvm_vfio_set_attr,
-	.has_attr = kvm_vfio_has_attr,
-};
+static int __init kvm_vfio_ops_init(void)
+{
+	return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
+}
+module_init(kvm_vfio_ops_init);