Merge branch 'tracking-kernel.org-3.10.y' into linux-lng

33 files changed, 300 insertions, 82 deletions

diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi
index 5d3ed5aafc69..0af879a4eafa 100644
--- a/arch/arm/boot/dts/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/at91rm9200.dtsi
@@ -35,8 +35,12 @@
 		ssc2 = &ssc2;
 	};
 	cpus {
-		cpu@0 {
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
 			compatible = "arm,arm920t";
+			device_type = "cpu";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index 84c4bef2d726..0dbdb846f90a 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -32,8 +32,12 @@
 		ssc0 = &ssc0;
 	};
 	cpus {
-		cpu@0 {
-			compatible = "arm,arm926ejs";
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			compatible = "arm,arm926ej-s";
+			device_type = "cpu";
 		};
 	};
 
@@ -340,6 +344,14 @@
 					};
 				};
 
+				i2c_gpio0 {
+					pinctrl_i2c_gpio0: i2c_gpio0-0 {
+						atmel,pins =
+							<0 23 0x0 0x3   /* PA23 gpio I2C_SDA pin */
+							 0 24 0x0 0x3>; /* PA24 gpio I2C_SCL pin */
+					};
+				};
+
 				pioA: gpio@fffff400 {
 					compatible = "atmel,at91rm9200-gpio";
 					reg = <0xfffff400 0x200>;
@@ -592,6 +604,8 @@
 		i2c-gpio,delay-us = <2>;	/* ~100 kHz */
 		#address-cells = <1>;
 		#size-cells = <0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_i2c_gpio0>;
 		status = "disabled";
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 94b58ab2cc08..fcd38f89904e 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -29,8 +29,12 @@
 		ssc1 = &ssc1;
 	};
 	cpus {
-		cpu@0 {
-			compatible = "arm,arm926ejs";
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			compatible = "arm,arm926ej-s";
+			device_type = "cpu";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index bf18a735c37d..479a0622cdb8 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -35,8 +35,12 @@
 		ssc1 = &ssc1;
 	};
 	cpus {
-		cpu@0 {
-			compatible = "arm,arm926ejs";
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			compatible = "arm,arm926ej-s";
+			device_type = "cpu";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index 8d25f889928e..a92ec78349a2 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -31,8 +31,12 @@
 		ssc0 = &ssc0;
 	};
 	cpus {
-		cpu@0 {
-			compatible = "arm,arm926ejs";
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			compatible = "arm,arm926ej-s";
+			device_type = "cpu";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index b5833d1f7cff..2b2b6923d16b 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -33,8 +33,12 @@
 		ssc0 = &ssc0;
 	};
 	cpus {
-		cpu@0 {
-			compatible = "arm,arm926ejs";
+		#address-cells = <0>;
+		#size-cells = <0>;
+
+		cpu {
+			compatible = "arm,arm926ej-s";
+			device_type = "cpu";
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 5000e0d42849..642775d7ca67 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -35,8 +35,12 @@
 		ssc1 = &ssc1;
 	};
 	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
 		cpu@0 {
+			device_type = "cpu";
 			compatible = "arm,cortex-a5";
+			reg = <0x0>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index e7ef619a70a2..06ef8b625dba 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -16,8 +16,12 @@
 	interrupt-parent = <&intc>;
 
 	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
 		cpu@0 {
+			device_type = "cpu";
 			compatible = "arm,cortex-a8";
+			reg = <0x0>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 31fa38f8cc98..d2852547b572 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -17,8 +17,12 @@
 	interrupt-parent = <&intc>;
 
 	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
 		cpu@0 {
+			device_type = "cpu";
 			compatible = "arm,cortex-a8";
+			reg = <0x0>;
 		};
 	};
 
diff --git a/arch/arm/mach-versatile/include/mach/platform.h b/arch/arm/mach-versatile/include/mach/platform.h
index ec087407b163..6f938ccb0c54 100644
--- a/arch/arm/mach-versatile/include/mach/platform.h
+++ b/arch/arm/mach-versatile/include/mach/platform.h
@@ -231,12 +231,14 @@
 /* PCI space */
 #define VERSATILE_PCI_BASE             0x41000000	/* PCI Interface */
 #define VERSATILE_PCI_CFG_BASE	       0x42000000
+#define VERSATILE_PCI_IO_BASE          0x43000000
 #define VERSATILE_PCI_MEM_BASE0        0x44000000
 #define VERSATILE_PCI_MEM_BASE1        0x50000000
 #define VERSATILE_PCI_MEM_BASE2        0x60000000
 /* Sizes of above maps */
 #define VERSATILE_PCI_BASE_SIZE	       0x01000000
 #define VERSATILE_PCI_CFG_BASE_SIZE    0x02000000
+#define VERSATILE_PCI_IO_BASE_SIZE     0x01000000
 #define VERSATILE_PCI_MEM_BASE0_SIZE   0x0c000000	/* 32Mb */
 #define VERSATILE_PCI_MEM_BASE1_SIZE   0x10000000	/* 256Mb */
 #define VERSATILE_PCI_MEM_BASE2_SIZE   0x10000000	/* 256Mb */
diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c
index e92e5e0705bc..c97be4ea76d2 100644
--- a/arch/arm/mach-versatile/pci.c
+++ b/arch/arm/mach-versatile/pci.c
@@ -43,9 +43,9 @@
 #define PCI_IMAP0		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0)
 #define PCI_IMAP1		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4)
 #define PCI_IMAP2		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8)
-#define PCI_SMAP0		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10)
-#define PCI_SMAP1		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
-#define PCI_SMAP2		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP0		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
+#define PCI_SMAP1		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP2		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x1c)
 #define PCI_SELFID		__IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc)
 
 #define DEVICE_ID_OFFSET		0x00
@@ -170,8 +170,8 @@ static struct pci_ops pci_versatile_ops = {
 	.write	= versatile_write_config,
 };
 
-static struct resource io_mem = {
-	.name	= "PCI I/O space",
+static struct resource unused_mem = {
+	.name	= "PCI unused",
 	.start	= VERSATILE_PCI_MEM_BASE0,
 	.end	= VERSATILE_PCI_MEM_BASE0+VERSATILE_PCI_MEM_BASE0_SIZE-1,
 	.flags	= IORESOURCE_MEM,
@@ -195,9 +195,9 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 {
 	int ret = 0;
 
-	ret = request_resource(&iomem_resource, &io_mem);
+	ret = request_resource(&iomem_resource, &unused_mem);
 	if (ret) {
-		printk(KERN_ERR "PCI: unable to allocate I/O "
+		printk(KERN_ERR "PCI: unable to allocate unused "
 		       "memory region (%d)\n", ret);
 		goto out;
 	}
@@ -205,7 +205,7 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 	if (ret) {
 		printk(KERN_ERR "PCI: unable to allocate non-prefetchable "
 		       "memory region (%d)\n", ret);
-		goto release_io_mem;
+		goto release_unused_mem;
 	}
 	ret = request_resource(&iomem_resource, &pre_mem);
 	if (ret) {
@@ -225,8 +225,8 @@ static int __init pci_versatile_setup_resources(struct pci_sys_data *sys)
 
  release_non_mem:
 	release_resource(&non_mem);
- release_io_mem:
-	release_resource(&io_mem);
+ release_unused_mem:
+	release_resource(&unused_mem);
  out:
 	return ret;
 }
@@ -246,7 +246,7 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys)
 		goto out;
 	}
 
-	ret = pci_ioremap_io(0, VERSATILE_PCI_MEM_BASE0);
+	ret = pci_ioremap_io(0, VERSATILE_PCI_IO_BASE);
 	if (ret)
 		goto out;
 
@@ -295,6 +295,19 @@ int __init pci_versatile_setup(int nr, struct pci_sys_data *sys)
 	__raw_writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_2);
 
 	/*
+	 * For many years the kernel and QEMU were symbiotically buggy
+	 * in that they both assumed the same broken IRQ mapping.
+	 * QEMU therefore attempts to auto-detect old broken kernels
+	 * so that they still work on newer QEMU as they did on old
+	 * QEMU. Since we now use the correct (ie matching-hardware)
+	 * IRQ mapping we write a definitely different value to a
+	 * PCI_INTERRUPT_LINE register to tell QEMU that we expect
+	 * real hardware behaviour and it need not be backwards
+	 * compatible for us. This write is harmless on real hardware.
+	 */
+	__raw_writel(0, VERSATILE_PCI_VIRT_BASE+PCI_INTERRUPT_LINE);
+
+	/*
 	 * Do not to map Versatile FPGA PCI device into memory space
 	 */
 	pci_slot_ignore |= (1 << myslot);
@@ -327,13 +340,13 @@ static int __init versatile_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq;
 
-	/* slot,  pin,	irq
-	 *  24     1     IRQ_SIC_PCI0
-	 *  25     1     IRQ_SIC_PCI1
-	 *  26     1     IRQ_SIC_PCI2
-	 *  27     1     IRQ_SIC_PCI3
+	/*
+	 * Slot	INTA	INTB	INTC	INTD
+	 * 31	PCI1	PCI2	PCI3	PCI0
+	 * 30	PCI0	PCI1	PCI2	PCI3
+	 * 29	PCI3	PCI0	PCI1	PCI2
 	 */
-	irq = IRQ_SIC_PCI0 + ((slot - 24 + pin - 1) & 3);
+	irq = IRQ_SIC_PCI0 + ((slot + 2 + pin - 1) & 3);
 
 	return irq;
 }
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 13609e01f4b7..81edd31bb4ac 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -170,6 +170,7 @@ static void __init xen_percpu_init(void *unused)
 	per_cpu(xen_vcpu, cpu) = vcpup;
 
 	enable_percpu_irq(xen_events_irq, 0);
+	put_cpu();
 }
 
 static void xen_restart(char str, const char *cmd)
@@ -272,12 +273,15 @@ core_initcall(xen_guest_init);
 
 static int __init xen_pm_init(void)
 {
+	if (!xen_domain())
+		return -ENODEV;
+
 	pm_power_off = xen_power_off;
 	arm_pm_restart = xen_restart;
 
 	return 0;
 }
-subsys_initcall(xen_pm_init);
+late_initcall(xen_pm_init);
 
 static irqreturn_t xen_arm_callback(int irq, void *arg)
 {
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 12e6ccb88691..cea1594ff933 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -325,7 +325,10 @@ validate_event(struct pmu_hw_events *hw_events,
 	if (is_software_event(event))
 		return 1;
 
-	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+		return 1;
+
+	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
 	return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
@@ -781,7 +784,7 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define	ARMV8_EVTYPE_MASK	0xc00000ff	/* Mask for writable bits */
+#define	ARMV8_EVTYPE_MASK	0xc80000ff	/* Mask for writable bits */
 #define	ARMV8_EVTYPE_EVENT	0xff		/* Mask for EVENT bits */
 
 /*
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 765ef30e3e1c..733017b3dfe7 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -164,7 +164,7 @@ static void __init ar933x_clocks_init(void)
 		ath79_ahb_clk.rate = freq / t;
 	}
 
-	ath79_wdt_clk.rate = ath79_ref_clk.rate;
+	ath79_wdt_clk.rate = ath79_ahb_clk.rate;
 	ath79_uart_clk.rate = ath79_ref_clk.rate;
 }
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 74991fee2e62..fe404e77246e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -986,6 +986,7 @@ config RELOCATABLE
 	  must live at a different physical address than the primary
 	  kernel.
 
+# This value must have zeroes in the bottom 60 bits otherwise lots will break
 config PAGE_OFFSET
 	hex
 	default "0xc000000000000000"
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 988c812aab5b..b9f426212d3a 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -211,9 +211,19 @@ extern long long virt_phys_offset;
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET))
 #define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET)
 #else
+#ifdef CONFIG_PPC64
+/*
+ * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET
+ * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit.
+ */
+#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET))
+#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL)
+
+#else /* 32-bit, non book E */
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START))
 #define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START)
 #endif
+#endif
 
 /*
  * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index ee5b690a0bed..52e5758ea368 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -764,6 +764,16 @@ int fix_alignment(struct pt_regs *regs)
 	nb = aligninfo[instr].len;
 	flags = aligninfo[instr].flags;
 
+	/* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
+	if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
+		nb = 8;
+		flags = LD+SW;
+	} else if (IS_XFORM(instruction) &&
+		   ((instruction >> 1) & 0x3ff) == 660) {
+		nb = 8;
+		flags = ST+SW;
+	}
+
 	/* Byteswap little endian loads and stores */
 	swiz = 0;
 	if (regs->msr & MSR_LE) {
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index d92f3871e9cf..e2a0a162299b 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -35,7 +35,13 @@
 #include <asm/vdso_datapage.h>
 #include <asm/vio.h>
 #include <asm/mmu.h>
+#include <asm/machdep.h>
 
+
+/*
+ * This isn't a module but we expose that to userspace
+ * via /proc so leave the definitions here
+ */
 #define MODULE_VERS "1.9"
 #define MODULE_NAME "lparcfg"
 
@@ -418,7 +424,8 @@ static void parse_em_data(struct seq_file *m)
 {
 	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
 
-	if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
+	    plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
 		seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
 }
 
@@ -677,7 +684,6 @@ static int lparcfg_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations lparcfg_fops = {
-	.owner		= THIS_MODULE,
 	.read		= seq_read,
 	.write		= lparcfg_write,
 	.open		= lparcfg_open,
@@ -699,14 +705,4 @@ static int __init lparcfg_init(void)
 	}
 	return 0;
 }
-
-static void __exit lparcfg_cleanup(void)
-{
-	remove_proc_subtree("powerpc/lparcfg", NULL);
-}
-
-module_init(lparcfg_init);
-module_exit(lparcfg_cleanup);
-MODULE_DESCRIPTION("Interface for LPAR configuration data");
-MODULE_AUTHOR("Dave Engebretsen");
-MODULE_LICENSE("GPL");
+machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 94c1dd46b83d..a3a5cb8ee7ea 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -19,6 +19,7 @@
 #include <asm/hvcall.h>
 #include <asm/xics.h>
 #include <asm/debug.h>
+#include <asm/time.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c11c8238797c..54b998f2750d 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -354,7 +354,7 @@ static int alloc_dispatch_log_kmem_cache(void)
 }
 early_initcall(alloc_dispatch_log_kmem_cache);
 
-static void pSeries_idle(void)
+static void pseries_lpar_idle(void)
 {
 	/* This would call on the cpuidle framework, and the back-end pseries
 	 * driver to  go to idle states
@@ -362,10 +362,22 @@ static void pSeries_idle(void)
 	if (cpuidle_idle_call()) {
 		/* On error, execute default handler
 		 * to go into low thread priority and possibly
-		 * low power mode.
+		 * low power mode by cedeing processor to hypervisor
 		 */
-		HMT_low();
-		HMT_very_low();
+
+		/* Indicate to hypervisor that we are idle. */
+		get_lppaca()->idle = 1;
+
+		/*
+		 * Yield the processor to the hypervisor.  We return if
+		 * an external interrupt occurs (which are driven prior
+		 * to returning here) or if a prod occurs from another
+		 * processor. When returning here, external interrupts
+		 * are enabled.
+		 */
+		cede_processor();
+
+		get_lppaca()->idle = 0;
 	}
 }
 
@@ -456,15 +468,14 @@ static void __init pSeries_setup_arch(void)
 
 	pSeries_nvram_init();
 
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
-		ppc_md.power_save = pSeries_idle;
-	}
-
-	if (firmware_has_feature(FW_FEATURE_LPAR))
+		ppc_md.power_save = pseries_lpar_idle;
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
-	else
+	} else {
+		/* No special idle routine */
 		ppc_md.enable_pmcs = power4_enable_pmcs;
+	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
 
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 95feaa47a2fb..c70a234a3f8c 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -200,6 +200,7 @@ extern int os_unmap_memory(void *addr, int len);
 extern int os_drop_memory(void *addr, int length);
 extern int can_drop_memory(void);
 extern void os_flush_stdout(void);
+extern int os_mincore(void *addr, unsigned long len);
 
 /* execvp.c */
 extern int execvp_noalloc(char *buf, const char *file, char *const argv[]);
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index babe21826e3e..d8b78a03855c 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -13,7 +13,7 @@ clean-files :=
 obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
 	physmem.o process.o ptrace.o reboot.o sigio.o \
 	signal.o smp.o syscall.o sysrq.o time.o tlb.o trap.o \
-	um_arch.o umid.o skas/
+	um_arch.o umid.o maccess.o skas/
 
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)	+= gprof_syms.o
diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
new file mode 100644
index 000000000000..1f3d5c4910d1
--- /dev/null
+++ b/arch/um/kernel/maccess.c
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2013 Richard Weinberger <richrd@nod.at>
+ *
+ * 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/uaccess.h>
+#include <linux/kernel.h>
+#include <os.h>
+
+long probe_kernel_read(void *dst, const void *src, size_t size)
+{
+	void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
+
+	if ((unsigned long)src < PAGE_SIZE || size <= 0)
+		return -EFAULT;
+
+	if (os_mincore(psrc, size + src - psrc) <= 0)
+		return -EFAULT;
+
+	return __probe_kernel_read(dst, src, size);
+}
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index b8f34c9e53ae..67b9c8f5a89e 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -4,6 +4,7 @@
  */
 
 #include <stdio.h>
+#include <stdlib.h>
 #include <unistd.h>
 #include <errno.h>
 #include <signal.h>
@@ -232,6 +233,57 @@ out:
 	return ok;
 }
 
+static int os_page_mincore(void *addr)
+{
+	char vec[2];
+	int ret;
+
+	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
+	if (ret < 0) {
+		if (errno == ENOMEM || errno == EINVAL)
+			return 0;
+		else
+			return -errno;
+	}
+
+	return vec[0] & 1;
+}
+
+int os_mincore(void *addr, unsigned long len)
+{
+	char *vec;
+	int ret, i;
+
+	if (len <= UM_KERN_PAGE_SIZE)
+		return os_page_mincore(addr);
+
+	vec = calloc(1, (len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE);
+	if (!vec)
+		return -ENOMEM;
+
+	ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
+	if (ret < 0) {
+		if (errno == ENOMEM || errno == EINVAL)
+			ret = 0;
+		else
+			ret = -errno;
+
+		goto out;
+	}
+
+	for (i = 0; i < ((len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE); i++) {
+		if (!(vec[i] & 1)) {
+			ret = 0;
+			goto out;
+		}
+	}
+
+	ret = 1;
+out:
+	free(vec);
+	return ret;
+}
+
 void init_new_thread_signals(void)
 {
 	set_handler(SIGSEGV);
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index cf1a471a18a2..10adb41f162e 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -459,7 +459,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 46fc474fd819..f50de6951738 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src,
 						 int len, __wsum sum,
 						 int *err_ptr)
 {
+	__wsum ret;
+
 	might_sleep();
-	return csum_partial_copy_generic((__force void *)src, dst,
-					 len, sum, err_ptr, NULL);
+	stac();
+	ret = csum_partial_copy_generic((__force void *)src, dst,
+					len, sum, err_ptr, NULL);
+	clac();
+
+	return ret;
 }
 
 /*
@@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src,
 					   int len, __wsum sum,
 					   int *err_ptr)
 {
+	__wsum ret;
+
 	might_sleep();
-	if (access_ok(VERIFY_WRITE, dst, len))
-		return csum_partial_copy_generic(src, (__force void *)dst,
-						 len, sum, NULL, err_ptr);
+	if (access_ok(VERIFY_WRITE, dst, len)) {
+		stac();
+		ret = csum_partial_copy_generic(src, (__force void *)dst,
+						len, sum, NULL, err_ptr);
+		clac();
+		return ret;
+	}
 
 	if (len)
 		*err_ptr = -EFAULT;
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index fa5f71e021d5..e6833c655e59 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -32,11 +32,20 @@
 #define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
 #define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
 #define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
-#define MCACOD		  0xffff     /* MCA Error Code */
+
+/*
+ * Note that the full MCACOD field of IA32_MCi_STATUS MSR is
+ * bits 15:0.  But bit 12 is the 'F' bit, defined for corrected
+ * errors to indicate that errors are being filtered by hardware.
+ * We should mask out bit 12 when looking for specific signatures
+ * of uncorrected errors - so the F bit is deliberately skipped
+ * in this #define.
+ */
+#define MCACOD		  0xefff     /* MCA Error Code */
 
 /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
 #define MCACOD_SCRUB	0x00C0	/* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK	0xfff0
+#define MCACOD_SCRUBMSK	0xeff0	/* Skip bit 12 ('F' bit) */
 #define MCACOD_L3WB	0x017A	/* L3 Explicit Writeback */
 #define MCACOD_DATA	0x0134	/* Data Load */
 #define MCACOD_INSTR	0x0150	/* Instruction Fetch */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index cdbf36776106..be12c534fd59 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Re-load page tables */
 		load_cr3(next->pgd);
 
-		/* stop flush ipis for the previous mm */
+		/* Stop flush ipis for the previous mm */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
+		/* Load the LDT, if the LDT is different: */
 		if (unlikely(prev->context.ldt != next->context.ldt))
 			load_LDT_nolock(&next->context);
 	}
 #ifdef CONFIG_SMP
-	else {
+	  else {
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
 
-		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
-			/* We were in lazy tlb mode and leave_mm disabled
+		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+			/*
+			 * On established mms, the mm_cpumask is only changed
+			 * from irq context, from ptep_clear_flush() while in
+			 * lazy tlb mode, and here. Irqs are blocked during
+			 * schedule, protecting us from simultaneous changes.
+			 */
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+			/*
+			 * We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
 			 */
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7ea79c5fa1f2..492b29802f57 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = {
 
 #define AVX_XOR_SPEED \
 do { \
-	if (cpu_has_avx) \
+	if (cpu_has_avx && cpu_has_osxsave) \
 		xor_speed(&xor_block_avx); \
 } while (0)
 
 #define AVX_SELECT(FASTEST) \
-	(cpu_has_avx ? &xor_block_avx : FASTEST)
+	(cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
 
 #else
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 3048ded1b598..59554dca96ec 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{}
 };
@@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids);
 
 static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{}
 };
@@ -81,13 +83,20 @@ int amd_cache_northbridges(void)
 			next_northbridge(misc, amd_nb_misc_ids);
 		node_to_amd_nb(i)->link = link =
 			next_northbridge(link, amd_nb_link_ids);
-        }
+	}
 
+	/* GART present only on Fam15h upto model 0fh */
 	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-	    boot_cpu_data.x86 == 0x15)
+	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
 		amd_northbridges.flags |= AMD_NB_GART;
 
 	/*
+	 * Check for L3 cache presence.
+	 */
+	if (!cpuid_edx(0x80000006))
+		return 0;
+
+	/*
 	 * Some CPU families support L3 Cache Index Disable. There are some
 	 * limitations because of E382 and E388 on family 0x10.
 	 */
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 69562992e457..087ab2af381a 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -364,7 +364,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  */
 		restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
@@ -429,7 +429,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  If provided, use a stub
 		   already in userspace.  */
@@ -496,7 +496,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
 
 		if (ksig->ka.sa.sa_flags & SA_RESTORER) {
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 25b7ae8d058a..7609e0e421ec 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -6,6 +6,7 @@
  */
 #include <asm/checksum.h>
 #include <linux/module.h>
+#include <asm/smap.h>
 
 /**
  * csum_partial_copy_from_user - Copy and checksum from user space.
@@ -52,8 +53,10 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
 			len -= 2;
 		}
 	}
+	stac();
 	isum = csum_partial_copy_generic((__force const void *)src,
 				dst, len, isum, errp, NULL);
+	clac();
 	if (unlikely(*errp))
 		goto out_err;
 
@@ -82,6 +85,8 @@ __wsum
 csum_partial_copy_to_user(const void *src, void __user *dst,
 			  int len, __wsum isum, int *errp)
 {
+	__wsum ret;
+
 	might_sleep();
 
 	if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) {
@@ -105,8 +110,11 @@ csum_partial_copy_to_user(const void *src, void __user *dst,
 	}
 
 	*errp = 0;
-	return csum_partial_copy_generic(src, (void __force *)dst,
-					 len, isum, NULL, errp);
+	stac();
+	ret = csum_partial_copy_generic(src, (void __force *)dst,
+					len, isum, NULL, errp);
+	clac();
+	return ret;
 }
 EXPORT_SYMBOL(csum_partial_copy_to_user);
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1f34e9219775..7a5bf1b76e2f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -78,8 +78,8 @@ __ref void *alloc_low_pages(unsigned int num)
 	return __va(pfn << PAGE_SHIFT);
 }
 
-/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE	(5 * PAGE_SIZE)
+/* need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS */
+#define INIT_PGT_BUF_SIZE	(6 * PAGE_SIZE)
 RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
 void  __init early_alloc_pgt_buf(void)
 {