Merge branch 'akpm-current/current'

179 files changed, 4490 insertions, 1956 deletions

diff --git a/Documentation/devicetree/bindings/w1/omap-hdq.txt b/Documentation/devicetree/bindings/w1/omap-hdq.txt
index fef794741bd1..913c5f91a0f9 100644
--- a/Documentation/devicetree/bindings/w1/omap-hdq.txt
+++ b/Documentation/devicetree/bindings/w1/omap-hdq.txt
@@ -1,11 +1,15 @@
 * OMAP HDQ One wire bus master controller
 
 Required properties:
-- compatible : should be "ti,omap3-1w"
+- compatible : should be "ti,omap3-1w" or "ti,am4372-hdq"
 - reg : Address and length of the register set for the device
 - interrupts : interrupt line.
 - ti,hwmods : "hdq1w"
 
+Optional properties:
+- ti,mode: should be "hdq": HDQ mode  "1w": one-wire mode.
+	   If not specified HDQ mode is implied.
+
 Example:
 
 - From omap3.dtsi
@@ -14,4 +18,5 @@ Example:
 	reg = <0x480b2000 0x1000>;
 	interrupts = <58>;
 	ti,hwmods = "hdq1w";
+	ti,mode = "hdq";
   };
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index d411ca63c8b6..1e3be5ab536e 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -174,6 +174,7 @@ read the file /proc/PID/status:
   VmLib:      1412 kB
   VmPTE:        20 kb
   VmSwap:        0 kB
+  HugetlbPages:          0 kB (0*2048kB)
   Threads:        1
   SigQ:   0/28578
   SigPnd: 0000000000000000
@@ -237,6 +238,8 @@ Table 1-2: Contents of the status files (as of 4.1)
  VmPTE                       size of page table entries
  VmPMD                       size of second level page tables
  VmSwap                      size of swap usage (the number of referred swapents)
+ HugetlbPages                size of hugetlb memory portions (with additional info
+                             about number of mapped hugepages for each page size)
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
  SigPnd                      bitmap of pending signals for the thread
@@ -423,6 +426,8 @@ Private_Clean:         0 kB
 Private_Dirty:         0 kB
 Referenced:          892 kB
 Anonymous:             0 kB
+AnonHugePages:         0 kB
+HugetlbPages:          0 kB
 Swap:                  0 kB
 SwapPss:               0 kB
 KernelPageSize:        4 kB
@@ -440,20 +445,31 @@ The "proportional set size" (PSS) of a process is the count of pages it has
 in memory, where each page is divided by the number of processes sharing it.
 So if a process has 1000 pages all to itself, and 1000 shared with one other
 process, its PSS will be 1500.
+
 Note that even a page which is part of a MAP_SHARED mapping, but has only
-a single pte mapped, i.e.  is currently used by only one process, is accounted
-as private and not as shared.
+a single pte mapped, i.e.  is currently used by only one process, is
+accounted as private and not as shared.
+
 "Referenced" indicates the amount of memory currently marked as referenced or
 accessed.
-"Anonymous" shows the amount of memory that does not belong to any file.  Even
-a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
-and a page is modified, the file page is replaced by a private anonymous copy.
+
+"Anonymous" shows the amount of memory that does not belong to any file.
+Even a mapping associated with a file may contain anonymous pages: when
+MAP_PRIVATE and a page is modified, the file page is replaced by a private
+anonymous copy.
+
+"AnonHugePages" shows the ammount of memory backed by transparent hugepage.
+
+"HugetlbPages" shows the ammount of memory backed by hugetlbfs page (which is
+not counted in "Rss" or "Pss" field for historical reasons.)
+
 "Swap" shows how much would-be-anonymous memory is also used, but out on
-swap.
-"SwapPss" shows proportional swap share of this mapping.
-"VmFlags" field deserves a separate description. This member represents the kernel
-flags associated with the particular virtual memory area in two letter encoded
-manner. The codes are the following:
+swap.  SwapPss" shows proportional swap share of this mapping.
+
+"VmFlags" field deserves a separate description.  This member represents
+the kernel flags associated with the particular virtual memory area in two
+letter encoded manner.  The codes are the following:
+
     rd  - readable
     wr  - writeable
     ex  - executable
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index ce1126aceed8..223c32171dcc 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -180,6 +180,16 @@ dos1xfloppy  -- If set, use a fallback default BIOS Parameter Block
 
 <bool>: 0,1,yes,no,true,false
 
+LIMITATION
+---------------------------------------------------------------------
+* The fallocated region of file is discarded at umount/evict time
+  when using fallocate with FALLOC_FL_KEEP_SIZE.
+  So, User should assume that fallocated region can be discarded at
+  last close if there is memory pressure resulting in eviction of
+  the inode from the memory. As a result, for any dependency on
+  the fallocated region, user should make sure to recheck fallocate
+  after reopening the file.
+
 TODO
 ----------------------------------------------------------------------
 * Need to get rid of the raw scanning stuff.  Instead, always use
diff --git a/Documentation/kasan.txt b/Documentation/kasan.txt
index 0d32355a4c34..94c881579374 100644
--- a/Documentation/kasan.txt
+++ b/Documentation/kasan.txt
@@ -1,32 +1,31 @@
-Kernel address sanitizer
-================
+KernelAddressSanitizer (KASAN)
+==============================
 
 0. Overview
 ===========
 
-Kernel Address sanitizer (KASan) is a dynamic memory error detector. It provides
+KernelAddressSANitizer (KASAN) is a dynamic memory error detector. It provides
 a fast and comprehensive solution for finding use-after-free and out-of-bounds
 bugs.
 
-KASan uses compile-time instrumentation for checking every memory access,
-therefore you will need a gcc version of 4.9.2 or later. KASan could detect out
-of bounds accesses to stack or global variables, but only if gcc 5.0 or later was
-used to built the kernel.
+KASAN uses compile-time instrumentation for checking every memory access,
+therefore you will need a GCC version 4.9.2 or later. GCC 5.0 or later is
+required for detection of out-of-bounds accesses to stack or global variables.
 
-Currently KASan is supported only for x86_64 architecture and requires that the
-kernel be built with the SLUB allocator.
+Currently KASAN is supported only for x86_64 architecture and requires the
+kernel to be built with the SLUB allocator.
 
 1. Usage
-=========
+========
 
 To enable KASAN configure kernel with:
 
 	  CONFIG_KASAN = y
 
-and choose between CONFIG_KASAN_OUTLINE and CONFIG_KASAN_INLINE. Outline/inline
-is compiler instrumentation types. The former produces smaller binary the
-latter is 1.1 - 2 times faster. Inline instrumentation requires a gcc version
-of 5.0 or later.
+and choose between CONFIG_KASAN_OUTLINE and CONFIG_KASAN_INLINE. Outline and
+inline are compiler instrumentation types. The former produces smaller binary
+the latter is 1.1 - 2 times faster. Inline instrumentation requires a GCC
+version 5.0 or later.
 
 Currently KASAN works only with the SLUB memory allocator.
 For better bug detection and nicer report, enable CONFIG_STACKTRACE and put
@@ -42,7 +41,7 @@ similar to the following to the respective kernel Makefile:
                 KASAN_SANITIZE := n
 
 1.1 Error reports
-==========
+=================
 
 A typical out of bounds access report looks like this:
 
@@ -119,14 +118,16 @@ Memory state around the buggy address:
  ffff8800693bc800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ==================================================================
 
-First sections describe slub object where bad access happened.
-See 'SLUB Debug output' section in Documentation/vm/slub.txt for details.
+The header of the report discribe what kind of bug happened and what kind of
+access caused it. It's followed by the description of the accessed slub object
+(see 'SLUB Debug output' section in Documentation/vm/slub.txt for details) and
+the description of the accessed memory page.
 
 In the last section the report shows memory state around the accessed address.
-Reading this part requires some more understanding of how KASAN works.
+Reading this part requires some understanding of how KASAN works.
 
-Each 8 bytes of memory are encoded in one shadow byte as accessible,
-partially accessible, freed or they can be part of a redzone.
+The state of each 8 aligned bytes of memory is encoded in one shadow byte.
+Those 8 bytes can be accessible, partially accessible, freed or be a redzone.
 We use the following encoding for each shadow byte: 0 means that all 8 bytes
 of the corresponding memory region are accessible; number N (1 <= N <= 7) means
 that the first N bytes are accessible, and other (8 - N) bytes are not;
@@ -139,7 +140,7 @@ the accessed address is partially accessible.
 
 
 2. Implementation details
-========================
+=========================
 
 From a high level, our approach to memory error detection is similar to that
 of kmemcheck: use shadow memory to record whether each byte of memory is safe
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 2216eb187c21..2ec6d84f391c 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -244,6 +244,14 @@ dentry names:
 
 	Passed by reference.
 
+task_struct comm name:
+
+        %pT
+
+        For printing task_struct->comm.
+
+	Passed by reference (NULL for "current").
+
 struct va_format:
 
 	%pV
diff --git a/Documentation/vm/split_page_table_lock b/Documentation/vm/split_page_table_lock
index 6dea4fd5c961..62842a857dab 100644
--- a/Documentation/vm/split_page_table_lock
+++ b/Documentation/vm/split_page_table_lock
@@ -54,8 +54,8 @@ everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
 which must be called on PTE table allocation / freeing.
 
 Make sure the architecture doesn't use slab allocator for page table
-allocation: slab uses page->slab_cache and page->first_page for its pages.
-These fields share storage with page->ptl.
+allocation: slab uses page->slab_cache for its pages.
+This field shares storage with page->ptl.
 
 PMD split lock only makes sense if you have more than two page table
 levels.
diff --git a/Documentation/w1/masters/omap-hdq b/Documentation/w1/masters/omap-hdq
index 884dc284b215..234522709a5f 100644
--- a/Documentation/w1/masters/omap-hdq
+++ b/Documentation/w1/masters/omap-hdq
@@ -44,3 +44,9 @@ e.g:
 insmod omap_hdq.ko W1_ID=2
 inamod w1_bq27000.ko F_ID=2
 
+The driver also supports 1-wire mode. In this mode, there is no need to
+pass slave ID as parameter. The driver will auto-detect slaves connected
+to the bus using SEARCH_ROM procedure. 1-wire mode can be selected by
+setting "ti,mode" property to "1w" in DT (see
+Documentation/devicetree/bindings/w1/omap-hdq.txt for more details).
+By default driver is in HDQ mode.
diff --git a/MAINTAINERS b/MAINTAINERS
index 17dc91042f6c..0b316624119b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6464,11 +6464,11 @@ F:	drivers/hwmon/ltc4261.c
 LTP (Linux Test Project)
 M:	Mike Frysinger <vapier@gentoo.org>
 M:	Cyril Hrubis <chrubis@suse.cz>
-M:	Wanlong Gao <gaowanlong@cn.fujitsu.com>
+M:	Wanlong Gao <wanlong.gao@gmail.com>
 M:	Jan Stancek <jstancek@redhat.com>
 M:	Stanislav Kholmanskikh <stanislav.kholmanskikh@oracle.com>
 M:	Alexey Kodanev <alexey.kodanev@oracle.com>
-L:	ltp-list@lists.sourceforge.net (subscribers-only)
+L:	ltp@lists.linux.it (subscribers-only)
 W:	http://linux-test-project.github.io/
 T:	git git://github.com/linux-test-project/ltp.git
 S:	Maintained
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index f05bdb4b1cb9..ff4049155c84 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -297,7 +297,9 @@ static inline void __iomem * ioremap_nocache(unsigned long offset,
 					     unsigned long size)
 {
 	return ioremap(offset, size);
-} 
+}
+
+#define ioremap_uc ioremap_nocache
 
 static inline void iounmap(volatile void __iomem *addr)
 {
diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 0086b472bc2b..d828beb5e69b 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -37,6 +37,9 @@
 
 #define MCL_CURRENT	 8192		/* lock all currently mapped pages */
 #define MCL_FUTURE	16384		/* lock all additions to address space */
+#define MCL_ONFAULT	32768		/* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL	0		/* no further special treatment */
 #define MADV_RANDOM	1		/* expect random page references */
@@ -44,6 +47,7 @@
 #define MADV_WILLNEED	3		/* will need these pages */
 #define	MADV_SPACEAVAIL	5		/* ensure resources are available */
 #define MADV_DONTNEED	6		/* don't need these pages */
+#define MADV_FREE	7		/* free pages only if memory pressure */
 
 /* common/generic parameters */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/arch/alpha/lib/udelay.c b/arch/alpha/lib/udelay.c
index 69d52aa37bae..f2d81ff38aa6 100644
--- a/arch/alpha/lib/udelay.c
+++ b/arch/alpha/lib/udelay.c
@@ -30,6 +30,7 @@ __delay(int loops)
 		"	bgt %0,1b"
 		: "=&r" (tmp), "=r" (loops) : "1"(loops));
 }
+EXPORT_SYMBOL(__delay);
 
 #ifdef CONFIG_SMP
 #define LPJ	 cpu_data[smp_processor_id()].loops_per_jiffy
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index a745a2a53853..6d6012a320b2 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -249,6 +249,7 @@ PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
 PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
 PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkclean,   &= ~L_PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 9769f1eefe3b..dade8d148cd9 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -783,7 +783,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else {
-		fault = probe_kernel_address(instrptr, instr);
+		fault = probe_kernel_address((void *)instrptr, instr);
 		instr = __mem_to_opcode_arm(instr);
 	}
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index f6c07e55f89e..1fd02241f7ce 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -323,10 +323,12 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(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_mkclean(pmd)	pte_pmd(pte_mkclean(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))
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index cfcb876cae6b..a6f8daff8e3b 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -61,12 +61,19 @@
  */
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL	0		/* no further special treatment */
 #define MADV_RANDOM	1		/* expect random page references */
 #define MADV_SEQUENTIAL 2		/* expect sequential page references */
 #define MADV_WILLNEED	3		/* will need these pages */
 #define MADV_DONTNEED	4		/* don't need these pages */
+#define MADV_FREE	5		/* free pages only if memory pressure */
 
 /* common parameters: try to keep these consistent across architectures */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index c03088f9f514..d0bdfaa13ee9 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -377,16 +377,17 @@
 #define __NR_memfd_create		(__NR_Linux + 354)
 #define __NR_bpf			(__NR_Linux + 355)
 #define __NR_execveat			(__NR_Linux + 356)
+#define __NR_mlock2			(__NR_Linux + 357)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		356
+#define __NR_Linux_syscalls		357
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		356
+#define __NR_O32_Linux_syscalls		357
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -711,16 +712,17 @@
 #define __NR_memfd_create		(__NR_Linux + 314)
 #define __NR_bpf			(__NR_Linux + 315)
 #define __NR_execveat			(__NR_Linux + 316)
+#define __NR_mlock2			(__NR_Linux + 317)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		316
+#define __NR_Linux_syscalls		317
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		316
+#define __NR_64_Linux_syscalls		317
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1049,15 +1051,16 @@
 #define __NR_memfd_create		(__NR_Linux + 318)
 #define __NR_bpf			(__NR_Linux + 319)
 #define __NR_execveat			(__NR_Linux + 320)
+#define __NR_mlock2			(__NR_Linux + 321)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		320
+#define __NR_Linux_syscalls		321
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		320
+#define __NR_N32_Linux_syscalls		321
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 4cc13508d967..b0b377aa1d5d 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -599,3 +599,4 @@ EXPORT(sys_call_table)
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 4355 */
 	PTR	sys_execveat
+	PTR	sys_mlock2
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index a6f6b762c47a..f12eb03c0961 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -436,4 +436,5 @@ EXPORT(sys_call_table)
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 5315 */
 	PTR	sys_execveat
+	PTR	sys_mlock2
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 4b2010654c46..ecdd65a2b02c 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -429,4 +429,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_memfd_create
 	PTR	sys_bpf
 	PTR	compat_sys_execveat		/* 6320 */
+	PTR	sys_mlock2
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f543ff4feef9..7a8b2dff16d3 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -584,4 +584,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 4355 */
 	PTR	compat_sys_execveat
+	PTR	sys_mlock2
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 294d251ca7b2..84f6bd365c7c 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -31,6 +31,9 @@
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL     0               /* no further special treatment */
 #define MADV_RANDOM     1               /* expect random page references */
@@ -40,6 +43,7 @@
 #define MADV_SPACEAVAIL 5               /* insure that resources are reserved */
 #define MADV_VPS_PURGE  6               /* Purge pages from VM page cache */
 #define MADV_VPS_INHERIT 7              /* Inherit parents page size */
+#define MADV_FREE	8		/* free pages only if memory pressure */
 
 /* common/generic parameters */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index fa1dfb7f7b48..85e15c8067be 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -507,9 +507,11 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 6ea26df0a73c..03c06ba7464f 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -22,6 +22,7 @@
 
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
+#define MCL_ONFAULT	0x8000		/* lock all pages that are faulted in */
 
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 8b9502adaf79..8d8a541211d0 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -80,7 +80,7 @@ static void __init setup_node_to_cpumask_map(void)
 		setup_nr_node_ids();
 
 	/* allocate the map */
-	for (node = 0; node < nr_node_ids; node++)
+	for_each_node(node)
 		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
 
 	/* cpumask_of_node() will now work */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 131d36fcd07a..5833dc5ee7d7 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -717,6 +717,15 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	pte_t pte = __pte(pmd_val(pmd));
+
+	pte = pte_mkclean(pte);
+
+	return __pmd(pte_val(pte));
+}
+
 static inline pmd_t pmd_mkyoung(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h
index 0b14df33cffa..9765896ecb2c 100644
--- a/arch/sparc/include/uapi/asm/mman.h
+++ b/arch/sparc/include/uapi/asm/mman.h
@@ -17,6 +17,7 @@
 
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
+#define MCL_ONFAULT	0x8000		/* lock all pages that are faulted in */
 
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
diff --git a/arch/tile/include/uapi/asm/mman.h b/arch/tile/include/uapi/asm/mman.h
index 81b8fc348d63..63ee13faf17d 100644
--- a/arch/tile/include/uapi/asm/mman.h
+++ b/arch/tile/include/uapi/asm/mman.h
@@ -36,6 +36,7 @@
  */
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
 
 
 #endif /* _ASM_TILE_MMAN_H */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cacba6300a59..e0e19f85d8e5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2117,6 +2117,9 @@ config USE_PERCPU_NUMA_NODE_ID
 	def_bool y
 	depends on NUMA
 
+config HAVE_MEMORYLESS_NODES
+	def_bool NUMA
+
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	def_bool y
 	depends on X86_64 || X86_PAE
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 0d553e54171b..2ee62dba0373 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -9,13 +9,13 @@
 # Changed by many, many contributors over the years.
 #
 
+KASAN_SANITIZE := n
+
 # If you want to preset the SVGA mode, uncomment the next line and
 # set SVGA_MODE to whatever number you want.
 # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
 # The number is the same as you would ordinarily press at bootup.
 
-KASAN_SANITIZE := n
-
 SVGA_MODE	:= -DSVGA_MODE=NORMAL_VGA
 
 targets		:= vmlinux.bin setup.bin setup.elf bzImage
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 7663c455b9f6..143ef9f37932 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -382,3 +382,4 @@
 373	i386	shutdown		sys_shutdown
 374	i386	userfaultfd		sys_userfaultfd
 375	i386	membarrier		sys_membarrier
+376	i386	mlock2			sys_mlock2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 278842fdf1f6..314a90bfc09c 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -331,6 +331,7 @@
 322	64	execveat		stub_execveat
 323	common	userfaultfd		sys_userfaultfd
 324	common	membarrier		sys_membarrier
+325	common	mlock2			sys_mlock2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 867da5bbb4a3..b964d54300e1 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -267,6 +267,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd)
 	return pmd_clear_flags(pmd, _PAGE_ACCESSED);
 }
 
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_DIRTY);
+}
+
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
 	return pmd_clear_flags(pmd, _PAGE_RW);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index e75907601a41..3625ac798821 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -705,8 +705,14 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 
 	nid = acpi_get_node(handle);
 	if (nid != -1) {
+		if (try_online_node(nid)) {
+			pr_warn("failed to online node%d for CPU%d, use node%d instead.\n",
+				nid, cpu, first_node(node_online_map));
+			nid = first_node(node_online_map);
+		}
 		set_apicid_to_node(physid, nid);
 		numa_set_node(cpu, nid);
+		set_cpu_numa_mem(cpu, local_memory_node(nid));
 	}
 #endif
 }
@@ -733,9 +739,10 @@ int acpi_unmap_cpu(int cpu)
 {
 #ifdef CONFIG_ACPI_NUMA
 	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
+	set_cpu_numa_mem(cpu, NUMA_NO_NODE);
 #endif
 
-	per_cpu(x86_cpu_to_apicid, cpu) = -1;
+	per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
 	set_cpu_present(cpu, false);
 	num_processors--;
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 819ab3f9c9c7..22db575a2fec 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -337,6 +337,7 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
 			      kaslr_offset());
+	VMCOREINFO_PHYS_BASE(phys_base);
 }
 
 /* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e0c198e5f920..a2a58e5337fb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -155,6 +155,8 @@ static void smp_callin(void)
 	 */
 	phys_id = read_apic_id();
 
+	set_numa_mem(local_memory_node(cpu_to_node(cpuid)));
+
 	/*
 	 * the boot CPU has finished the init stage and is spinning
 	 * on callin_map until we finish. We are free to set up this
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 9ce5da27b136..d470cf219a2d 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -126,5 +126,5 @@ void __init kasan_init(void)
 	__flush_tlb_all();
 	init_task.kasan_depth = 0;
 
-	pr_info("Kernel address sanitizer initialized\n");
+	pr_info("KernelAddressSanitizer initialized\n");
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f653ed0c..e5a3b35083a6 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -22,6 +22,7 @@
 
 int __initdata numa_off;
 nodemask_t numa_nodes_parsed __initdata;
+static nodemask_t numa_nodes_empty __initdata;
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -562,17 +563,16 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 			end = max(mi->blk[i].end, end);
 		}
 
-		if (start >= end)
-			continue;
-
 		/*
 		 * Don't confuse VM with a node that doesn't have the
 		 * minimum amount of memory:
 		 */
-		if (end && (end - start) < NODE_MIN_SIZE)
-			continue;
-
-		alloc_node_data(nid);
+		if (start < end && (end - start) >= NODE_MIN_SIZE) {
+			alloc_node_data(nid);
+		} else if (IS_ENABLED(CONFIG_HAVE_MEMORYLESS_NODES)) {
+			alloc_node_data(nid);
+			node_set(nid, numa_nodes_empty);
+		}
 	}
 
 	/* Dump memblock with node info and return. */
@@ -589,16 +589,18 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
  */
 static void __init numa_init_array(void)
 {
-	int rr, i;
+	int i, rr = MAX_NUMNODES;
 
-	rr = first_node(node_online_map);
 	for (i = 0; i < nr_cpu_ids; i++) {
-		if (early_cpu_to_node(i) != NUMA_NO_NODE)
-			continue;
+		/* Search for an onlined node with memory */
+		do {
+			if (rr != MAX_NUMNODES)
+				rr = next_node(rr, node_online_map);
+			if (rr == MAX_NUMNODES)
+				rr = first_node(node_online_map);
+		} while (node_isset(rr, numa_nodes_empty));
+
 		numa_set_node(i, rr);
-		rr = next_node(rr, node_online_map);
-		if (rr == MAX_NUMNODES)
-			rr = first_node(node_online_map);
 	}
 }
 
@@ -646,14 +648,6 @@ static int __init numa_init(int (*init_func)(void))
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < nr_cpu_ids; i++) {
-		int nid = early_cpu_to_node(i);
-
-		if (nid == NUMA_NO_NODE)
-			continue;
-		if (!node_online(nid))
-			numa_clear_node(i);
-	}
 	numa_init_array();
 
 	return 0;
@@ -708,9 +702,12 @@ static __init int find_near_online_node(int node)
 {
 	int n, val;
 	int min_val = INT_MAX;
-	int best_node = -1;
+	int best_node = NUMA_NO_NODE;
 
 	for_each_online_node(n) {
+		if (node_isset(n, numa_nodes_empty))
+			continue;
+
 		val = node_distance(node, n);
 
 		if (val < min_val) {
@@ -751,6 +748,22 @@ void __init init_cpu_to_node(void)
 		if (!node_online(node))
 			node = find_near_online_node(node);
 		numa_set_node(cpu, node);
+		if (node_spanned_pages(node))
+			set_cpu_numa_mem(cpu, node);
+		if (IS_ENABLED(CONFIG_HAVE_MEMORYLESS_NODES))
+			node_clear(node, numa_nodes_empty);
+	}
+
+	/* Destroy empty nodes */
+	if (IS_ENABLED(CONFIG_HAVE_MEMORYLESS_NODES)) {
+		int nid;
+		const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
+
+		for_each_node_mask(nid, numa_nodes_empty) {
+			node_set_offline(nid);
+			memblock_free(__pa(node_data[nid]), nd_size);
+			node_data[nid] = NULL;
+		}
 	}
 }
 
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index f3dfe0d921c2..44c6764d9146 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -169,7 +169,6 @@ CONFIG_FLATMEM_MANUAL=y
 # CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 # CONFIG_PHYS_ADDR_T_64BIT is not set
 CONFIG_ZONE_DMA_FLAG=1
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 201aec0e0446..83c5150b06f9 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -74,12 +74,19 @@
  */
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
 
 #define MADV_NORMAL	0		/* no further special treatment */
 #define MADV_RANDOM	1		/* expect random page references */
 #define MADV_SEQUENTIAL	2		/* expect sequential page references */
 #define MADV_WILLNEED	3		/* will need these pages */
 #define MADV_DONTNEED	4		/* don't need these pages */
+#define MADV_FREE	5		/* free pages only if memory pressure */
 
 /* common parameters: try to keep these consistent across architectures */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/block/genhd.c b/block/genhd.c
index 0c706f33a599..3213b66515f0 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -850,7 +850,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
+	if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) &&
 				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 965d1afb0eaa..5cb13ca3a3ac 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -330,12 +330,14 @@ void zcomp_destroy(struct zcomp *comp)
  * allocate new zcomp and initialize it. return compressing
  * backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL)
  * if requested algorithm is not supported, ERR_PTR(-ENOMEM) in
- * case of allocation error.
+ * case of allocation error, or any other error potentially
+ * returned by functions zcomp_strm_{multi,single}_create.
  */
 struct zcomp *zcomp_create(const char *compress, int max_strm)
 {
 	struct zcomp *comp;
 	struct zcomp_backend *backend;
+	int error;
 
 	backend = find_backend(compress);
 	if (!backend)
@@ -347,12 +349,12 @@ struct zcomp *zcomp_create(const char *compress, int max_strm)
 
 	comp->backend = backend;
 	if (max_strm > 1)
-		zcomp_strm_multi_create(comp, max_strm);
+		error = zcomp_strm_multi_create(comp, max_strm);
 	else
-		zcomp_strm_single_create(comp);
-	if (!comp->stream) {
+		error = zcomp_strm_single_create(comp);
+	if (error) {
 		kfree(comp);
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(error);
 	}
 	return comp;
 }
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 9fa15bb9d118..c93aeb876125 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -365,6 +365,9 @@ static ssize_t comp_algorithm_store(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 	size_t sz;
 
+	if (!zcomp_available_algorithm(buf))
+		return -EINVAL;
+
 	down_write(&zram->init_lock);
 	if (init_done(zram)) {
 		up_write(&zram->init_lock);
@@ -378,9 +381,6 @@ static ssize_t comp_algorithm_store(struct device *dev,
 	if (sz > 0 && zram->compressor[sz - 1] == '\n')
 		zram->compressor[sz - 1] = 0x00;
 
-	if (!zcomp_available_algorithm(zram->compressor))
-		len = -EINVAL;
-
 	up_write(&zram->init_lock);
 	return len;
 }
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index 4924d381b664..daa2ff12101b 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -38,8 +38,6 @@
 #include "drm_legacy.h"
 #include "drm_internal.h"
 
-static int drm_notifier(void *priv);
-
 static int drm_lock_take(struct drm_lock_data *lock_data, unsigned int context);
 
 /**
@@ -118,14 +116,8 @@ int drm_legacy_lock(struct drm_device *dev, void *data,
 	 * really probably not the correct answer but lets us debug xkb
  	 * xserver for now */
 	if (!file_priv->is_master) {
-		sigemptyset(&dev->sigmask);
-		sigaddset(&dev->sigmask, SIGSTOP);
-		sigaddset(&dev->sigmask, SIGTSTP);
-		sigaddset(&dev->sigmask, SIGTTIN);
-		sigaddset(&dev->sigmask, SIGTTOU);
 		dev->sigdata.context = lock->context;
 		dev->sigdata.lock = master->lock.hw_lock;
-		block_all_signals(drm_notifier, dev, &dev->sigmask);
 	}
 
 	if (dev->driver->dma_quiescent && (lock->flags & _DRM_LOCK_QUIESCENT))
@@ -169,7 +161,6 @@ int drm_legacy_unlock(struct drm_device *dev, void *data, struct drm_file *file_
 		/* FIXME: Should really bail out here. */
 	}
 
-	unblock_all_signals();
 	return 0;
 }
 
@@ -288,38 +279,6 @@ int drm_legacy_lock_free(struct drm_lock_data *lock_data, unsigned int context)
 }
 
 /**
- * If we get here, it means that the process has called DRM_IOCTL_LOCK
- * without calling DRM_IOCTL_UNLOCK.
- *
- * If the lock is not held, then let the signal proceed as usual.  If the lock
- * is held, then set the contended flag and keep the signal blocked.
- *
- * \param priv pointer to a drm_device structure.
- * \return one if the signal should be delivered normally, or zero if the
- * signal should be blocked.
- */
-static int drm_notifier(void *priv)
-{
-	struct drm_device *dev = priv;
-	struct drm_hw_lock *lock = dev->sigdata.lock;
-	unsigned int old, new, prev;
-
-	/* Allow signal delivery if lock isn't held */
-	if (!lock || !_DRM_LOCK_IS_HELD(lock->lock)
-	    || _DRM_LOCKING_CONTEXT(lock->lock) != dev->sigdata.context)
-		return 1;
-
-	/* Otherwise, set flag to force call to
-	   drmUnlock */
-	do {
-		old = lock->lock;
-		new = old | _DRM_LOCK_CONT;
-		prev = cmpxchg(&lock->lock, old, new);
-	} while (prev != old);
-	return 0;
-}
-
-/**
  * This function returns immediately and takes the hw lock
  * with the kernel context if it is free, otherwise it gets the highest priority when and if
  * it is eventually released.
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index 340b44d9e8cf..fa0aafebc672 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -238,7 +238,7 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name,
 
 	mq->mmr_blade = uv_cpu_to_blade_id(cpu);
 
-	nid = cpu_to_node(cpu);
+	nid = cpu_to_mem(cpu);
 	page = __alloc_pages_node(nid,
 				      GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				      pg_order);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 738aca68f665..0f6298330c7a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1518,7 +1518,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 rx_packet_len, rx_header_len, rx_sph, rx_hbo;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	const int current_node = numa_node_id();
+	const int current_node = numa_mem_id();
 	struct i40e_vsi *vsi = rx_ring->vsi;
 	u16 i = rx_ring->next_to_clean;
 	union i40e_rx_desc *rx_desc;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 7e91d825c760..e1b67ebab111 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -997,7 +997,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 rx_packet_len, rx_header_len, rx_sph, rx_hbo;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	const int current_node = numa_node_id();
+	const int current_node = numa_mem_id();
 	struct i40e_vsi *vsi = rx_ring->vsi;
 	u16 i = rx_ring->next_to_clean;
 	union i40e_rx_desc *rx_desc;
diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c
index e7d448963a24..0e2f43bccf1f 100644
--- a/drivers/w1/masters/omap_hdq.c
+++ b/drivers/w1/masters/omap_hdq.c
@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include <linux/sched.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
 
 #include "../w1.h"
 #include "../w1_int.h"
@@ -27,21 +28,23 @@
 #define OMAP_HDQ_TX_DATA			0x04
 #define OMAP_HDQ_RX_DATA			0x08
 #define OMAP_HDQ_CTRL_STATUS			0x0c
-#define OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK	(1<<6)
-#define OMAP_HDQ_CTRL_STATUS_CLOCKENABLE	(1<<5)
-#define OMAP_HDQ_CTRL_STATUS_GO			(1<<4)
-#define OMAP_HDQ_CTRL_STATUS_INITIALIZATION	(1<<2)
-#define OMAP_HDQ_CTRL_STATUS_DIR		(1<<1)
-#define OMAP_HDQ_CTRL_STATUS_MODE		(1<<0)
+#define OMAP_HDQ_CTRL_STATUS_SINGLE		BIT(7)
+#define OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK	BIT(6)
+#define OMAP_HDQ_CTRL_STATUS_CLOCKENABLE	BIT(5)
+#define OMAP_HDQ_CTRL_STATUS_GO                 BIT(4)
+#define OMAP_HDQ_CTRL_STATUS_PRESENCE		BIT(3)
+#define OMAP_HDQ_CTRL_STATUS_INITIALIZATION	BIT(2)
+#define OMAP_HDQ_CTRL_STATUS_DIR		BIT(1)
 #define OMAP_HDQ_INT_STATUS			0x10
-#define OMAP_HDQ_INT_STATUS_TXCOMPLETE		(1<<2)
-#define OMAP_HDQ_INT_STATUS_RXCOMPLETE		(1<<1)
-#define OMAP_HDQ_INT_STATUS_TIMEOUT		(1<<0)
+#define OMAP_HDQ_INT_STATUS_TXCOMPLETE		BIT(2)
+#define OMAP_HDQ_INT_STATUS_RXCOMPLETE		BIT(1)
+#define OMAP_HDQ_INT_STATUS_TIMEOUT		BIT(0)
 #define OMAP_HDQ_SYSCONFIG			0x14
-#define OMAP_HDQ_SYSCONFIG_SOFTRESET		(1<<1)
-#define OMAP_HDQ_SYSCONFIG_AUTOIDLE		(1<<0)
+#define OMAP_HDQ_SYSCONFIG_SOFTRESET		BIT(1)
+#define OMAP_HDQ_SYSCONFIG_AUTOIDLE		BIT(0)
+#define OMAP_HDQ_SYSCONFIG_NOIDLE		0x0
 #define OMAP_HDQ_SYSSTATUS			0x18
-#define OMAP_HDQ_SYSSTATUS_RESETDONE		(1<<0)
+#define OMAP_HDQ_SYSSTATUS_RESETDONE		BIT(0)
 
 #define OMAP_HDQ_FLAG_CLEAR			0
 #define OMAP_HDQ_FLAG_SET			1
@@ -67,6 +70,10 @@ struct hdq_data {
 	 * the data wrire or read.
 	 */
 	int			init_trans;
+	int                     rrw;
+	/* mode: 0-HDQ 1-W1 */
+	int                     mode;
+
 };
 
 static int omap_hdq_probe(struct platform_device *pdev);
@@ -74,6 +81,7 @@ static int omap_hdq_remove(struct platform_device *pdev);
 
 static const struct of_device_id omap_hdq_dt_ids[] = {
 	{ .compatible = "ti,omap3-1w" },
+	{ .compatible = "ti,am4372-hdq" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, omap_hdq_dt_ids);
@@ -90,15 +98,12 @@ static struct platform_driver omap_hdq_driver = {
 static u8 omap_w1_read_byte(void *_hdq);
 static void omap_w1_write_byte(void *_hdq, u8 byte);
 static u8 omap_w1_reset_bus(void *_hdq);
-static void omap_w1_search_bus(void *_hdq, struct w1_master *master_dev,
-		u8 search_type,	w1_slave_found_callback slave_found);
 
 
 static struct w1_bus_master omap_w1_master = {
 	.read_byte	= omap_w1_read_byte,
 	.write_byte	= omap_w1_write_byte,
 	.reset_bus	= omap_w1_reset_bus,
-	.search		= omap_w1_search_bus,
 };
 
 /* HDQ register I/O routines */
@@ -122,6 +127,15 @@ static inline u8 hdq_reg_merge(struct hdq_data *hdq_data, u32 offset,
 	return new_val;
 }
 
+static void hdq_disable_interrupt(struct hdq_data *hdq_data, u32 offset,
+				  u32 mask)
+{
+	u32 ie;
+
+	ie = readl(hdq_data->hdq_base + offset);
+	writel(ie & mask, hdq_data->hdq_base + offset);
+}
+
 /*
  * Wait for one or more bits in flag change.
  * HDQ_FLAG_SET: wait until any bit in the flag is set.
@@ -229,13 +243,7 @@ static irqreturn_t hdq_isr(int irq, void *_hdq)
 	return IRQ_HANDLED;
 }
 
-/* HDQ Mode: always return success */
-static u8 omap_w1_reset_bus(void *_hdq)
-{
-	return 0;
-}
-
-/* W1 search callback function */
+/* W1 search callback function  in HDQ mode */
 static void omap_w1_search_bus(void *_hdq, struct w1_master *master_dev,
 		u8 search_type, w1_slave_found_callback slave_found)
 {
@@ -262,9 +270,10 @@ static int _omap_hdq_reset(struct hdq_data *hdq_data)
 	int ret;
 	u8 tmp_status;
 
-	hdq_reg_out(hdq_data, OMAP_HDQ_SYSCONFIG, OMAP_HDQ_SYSCONFIG_SOFTRESET);
+	hdq_reg_out(hdq_data, OMAP_HDQ_SYSCONFIG,
+		    OMAP_HDQ_SYSCONFIG_SOFTRESET);
 	/*
-	 * Select HDQ mode & enable clocks.
+	 * Select HDQ/1W mode & enable clocks.
 	 * It is observed that INT flags can't be cleared via a read and GO/INIT
 	 * won't return to zero if interrupt is disabled. So we always enable
 	 * interrupt.
@@ -282,7 +291,8 @@ static int _omap_hdq_reset(struct hdq_data *hdq_data)
 	else {
 		hdq_reg_out(hdq_data, OMAP_HDQ_CTRL_STATUS,
 			OMAP_HDQ_CTRL_STATUS_CLOCKENABLE |
-			OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK);
+			OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK |
+			hdq_data->mode);
 		hdq_reg_out(hdq_data, OMAP_HDQ_SYSCONFIG,
 			OMAP_HDQ_SYSCONFIG_AUTOIDLE);
 	}
@@ -334,6 +344,18 @@ static int omap_hdq_break(struct hdq_data *hdq_data)
 		ret = -ETIMEDOUT;
 		goto out;
 	}
+
+	/*
+	 * check for the presence detect bit to get
+	 * set to show that the slave is responding
+	 */
+	if (!(hdq_reg_in(hdq_data, OMAP_HDQ_CTRL_STATUS) &
+			OMAP_HDQ_CTRL_STATUS_PRESENCE)) {
+		dev_dbg(hdq_data->dev, "Presence bit not set\n");
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+
 	/*
 	 * wait for both INIT and GO bits rerurn to zero.
 	 * zero wait time expected for interrupt mode.
@@ -368,6 +390,8 @@ static int hdq_read_byte(struct hdq_data *hdq_data, u8 *val)
 		goto out;
 	}
 
+	hdq_data->hdq_irqstatus = 0;
+
 	if (!(hdq_data->hdq_irqstatus & OMAP_HDQ_INT_STATUS_RXCOMPLETE)) {
 		hdq_reg_merge(hdq_data, OMAP_HDQ_CTRL_STATUS,
 			OMAP_HDQ_CTRL_STATUS_DIR | OMAP_HDQ_CTRL_STATUS_GO,
@@ -400,7 +424,7 @@ rtn:
 
 }
 
-/* Enable clocks and set the controller to HDQ mode */
+/* Enable clocks and set the controller to HDQ/1W mode */
 static int omap_hdq_get(struct hdq_data *hdq_data)
 {
 	int ret = 0;
@@ -422,7 +446,7 @@ static int omap_hdq_get(struct hdq_data *hdq_data)
 
 			pm_runtime_get_sync(hdq_data->dev);
 
-			/* make sure HDQ is out of reset */
+			/* make sure HDQ/1W is out of reset */
 			if (!(hdq_reg_in(hdq_data, OMAP_HDQ_SYSSTATUS) &
 				OMAP_HDQ_SYSSTATUS_RESETDONE)) {
 				ret = _omap_hdq_reset(hdq_data);
@@ -430,12 +454,13 @@ static int omap_hdq_get(struct hdq_data *hdq_data)
 					/* back up the count */
 					hdq_data->hdq_usecount--;
 			} else {
-				/* select HDQ mode & enable clocks */
+				/* select HDQ/1W mode & enable clocks */
 				hdq_reg_out(hdq_data, OMAP_HDQ_CTRL_STATUS,
 					OMAP_HDQ_CTRL_STATUS_CLOCKENABLE |
-					OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK);
+					OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK |
+					hdq_data->mode);
 				hdq_reg_out(hdq_data, OMAP_HDQ_SYSCONFIG,
-					OMAP_HDQ_SYSCONFIG_AUTOIDLE);
+					OMAP_HDQ_SYSCONFIG_NOIDLE);
 				hdq_reg_in(hdq_data, OMAP_HDQ_INT_STATUS);
 			}
 		}
@@ -456,6 +481,8 @@ static int omap_hdq_put(struct hdq_data *hdq_data)
 	if (ret < 0)
 		return -EINTR;
 
+	hdq_reg_out(hdq_data, OMAP_HDQ_SYSCONFIG,
+		    OMAP_HDQ_SYSCONFIG_AUTOIDLE);
 	if (0 == hdq_data->hdq_usecount) {
 		dev_dbg(hdq_data->dev, "attempt to decrement use count"
 			" when it is zero");
@@ -471,6 +498,100 @@ static int omap_hdq_put(struct hdq_data *hdq_data)
 	return ret;
 }
 
+/*
+ * W1 triplet callback function - used for searching ROM addresses.
+ * Registered only when controller is in 1-wire mode.
+ */
+static u8 omap_w1_triplet(void *_hdq, u8 bdir)
+{
+	u8 id_bit, comp_bit;
+	int err;
+	u8 ret = 0x3; /* no slaves responded */
+	struct hdq_data *hdq_data = _hdq;
+	u8 ctrl = OMAP_HDQ_CTRL_STATUS_SINGLE | OMAP_HDQ_CTRL_STATUS_GO |
+		  OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK;
+	u8 mask = ctrl | OMAP_HDQ_CTRL_STATUS_DIR;
+
+	omap_hdq_get(_hdq);
+
+	err = mutex_lock_interruptible(&hdq_data->hdq_mutex);
+	if (err < 0) {
+		dev_dbg(hdq_data->dev, "Could not acquire mutex\n");
+		goto rtn;
+	}
+
+	hdq_data->hdq_irqstatus = 0;
+	/* read id_bit */
+	hdq_reg_merge(_hdq, OMAP_HDQ_CTRL_STATUS,
+		      ctrl | OMAP_HDQ_CTRL_STATUS_DIR, mask);
+	err = wait_event_timeout(hdq_wait_queue,
+				 (hdq_data->hdq_irqstatus
+				  & OMAP_HDQ_INT_STATUS_RXCOMPLETE),
+				 OMAP_HDQ_TIMEOUT);
+	if (err == 0) {
+		dev_dbg(hdq_data->dev, "RX wait elapsed\n");
+		goto out;
+	}
+	id_bit = (hdq_reg_in(_hdq, OMAP_HDQ_RX_DATA) & 0x01);
+
+	hdq_data->hdq_irqstatus = 0;
+	/* read comp_bit */
+	hdq_reg_merge(_hdq, OMAP_HDQ_CTRL_STATUS,
+		      ctrl | OMAP_HDQ_CTRL_STATUS_DIR, mask);
+	err = wait_event_timeout(hdq_wait_queue,
+				 (hdq_data->hdq_irqstatus
+				  & OMAP_HDQ_INT_STATUS_RXCOMPLETE),
+				 OMAP_HDQ_TIMEOUT);
+	if (err == 0) {
+		dev_dbg(hdq_data->dev, "RX wait elapsed\n");
+		goto out;
+	}
+	comp_bit = (hdq_reg_in(_hdq, OMAP_HDQ_RX_DATA) & 0x01);
+
+	if (id_bit && comp_bit) {
+		ret = 0x03;  /* no slaves responded */
+		goto out;
+	}
+	if (!id_bit && !comp_bit) {
+		/* Both bits are valid, take the direction given */
+		ret = bdir ? 0x04 : 0;
+	} else {
+		/* Only one bit is valid, take that direction */
+		bdir = id_bit;
+		ret = id_bit ? 0x05 : 0x02;
+	}
+
+	/* write bdir bit */
+	hdq_reg_out(_hdq, OMAP_HDQ_TX_DATA, bdir);
+	hdq_reg_merge(_hdq, OMAP_HDQ_CTRL_STATUS, ctrl, mask);
+	err = wait_event_timeout(hdq_wait_queue,
+				 (hdq_data->hdq_irqstatus
+				  & OMAP_HDQ_INT_STATUS_TXCOMPLETE),
+				 OMAP_HDQ_TIMEOUT);
+	if (err == 0) {
+		dev_dbg(hdq_data->dev, "TX wait elapsed\n");
+		goto out;
+	}
+
+	hdq_reg_merge(_hdq, OMAP_HDQ_CTRL_STATUS, 0,
+		      OMAP_HDQ_CTRL_STATUS_SINGLE);
+
+out:
+	mutex_unlock(&hdq_data->hdq_mutex);
+rtn:
+	omap_hdq_put(_hdq);
+	return ret;
+}
+
+/* reset callback */
+static u8 omap_w1_reset_bus(void *_hdq)
+{
+	omap_hdq_get(_hdq);
+	omap_hdq_break(_hdq);
+	omap_hdq_put(_hdq);
+	return 0;
+}
+
 /* Read a byte of data from the device */
 static u8 omap_w1_read_byte(void *_hdq)
 {
@@ -478,6 +599,10 @@ static u8 omap_w1_read_byte(void *_hdq)
 	u8 val = 0;
 	int ret;
 
+	/* First write to initialize the transfer */
+	if (hdq_data->init_trans == 0)
+		omap_hdq_get(hdq_data);
+
 	ret = hdq_read_byte(hdq_data, &val);
 	if (ret) {
 		ret = mutex_lock_interruptible(&hdq_data->hdq_mutex);
@@ -491,6 +616,10 @@ static u8 omap_w1_read_byte(void *_hdq)
 		return -1;
 	}
 
+	hdq_disable_interrupt(hdq_data, OMAP_HDQ_CTRL_STATUS,
+			      ~OMAP_HDQ_CTRL_STATUS_INTERRUPTMASK);
+	hdq_data->hdq_usecount = 0;
+
 	/* Write followed by a read, release the module */
 	if (hdq_data->init_trans) {
 		ret = mutex_lock_interruptible(&hdq_data->hdq_mutex);
@@ -517,6 +646,14 @@ static void omap_w1_write_byte(void *_hdq, u8 byte)
 	if (hdq_data->init_trans == 0)
 		omap_hdq_get(hdq_data);
 
+	/*
+	 * We need to reset the slave before
+	 * issuing the SKIP ROM command, else
+	 * the slave will not work.
+	 */
+	if (byte == W1_SKIP_ROM)
+		omap_hdq_break(hdq_data);
+
 	ret = mutex_lock_interruptible(&hdq_data->hdq_mutex);
 	if (ret < 0) {
 		dev_dbg(hdq_data->dev, "Could not acquire mutex\n");
@@ -551,6 +688,7 @@ static int omap_hdq_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret, irq;
 	u8 rev;
+	const char *mode;
 
 	hdq_data = devm_kzalloc(dev, sizeof(*hdq_data), GFP_KERNEL);
 	if (!hdq_data) {
@@ -567,10 +705,21 @@ static int omap_hdq_probe(struct platform_device *pdev)
 		return PTR_ERR(hdq_data->hdq_base);
 
 	hdq_data->hdq_usecount = 0;
+	hdq_data->rrw = 0;
 	mutex_init(&hdq_data->hdq_mutex);
 
 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_dbg(&pdev->dev, "pm_runtime_get_sync failed\n");
+		goto err_w1;
+	}
+
+	ret = _omap_hdq_reset(hdq_data);
+	if (ret) {
+		dev_dbg(&pdev->dev, "reset failed\n");
+		return -EINVAL;
+	}
 
 	rev = hdq_reg_in(hdq_data, OMAP_HDQ_REVISION);
 	dev_info(&pdev->dev, "OMAP HDQ Hardware Rev %c.%c. Driver in %s mode\n",
@@ -594,6 +743,15 @@ static int omap_hdq_probe(struct platform_device *pdev)
 
 	pm_runtime_put_sync(&pdev->dev);
 
+	ret = of_property_read_string(pdev->dev.of_node, "ti,mode", &mode);
+	if (ret < 0 || !strcmp(mode, "hdq")) {
+		hdq_data->mode = 0;
+		omap_w1_master.search = omap_w1_search_bus;
+	} else {
+		hdq_data->mode = 1;
+		omap_w1_master.triplet = omap_w1_triplet;
+	}
+
 	omap_w1_master.data = hdq_data;
 
 	ret = w1_add_master_device(&omap_w1_master);
@@ -635,8 +793,8 @@ static int omap_hdq_remove(struct platform_device *pdev)
 module_platform_driver(omap_hdq_driver);
 
 module_param(w1_id, int, S_IRUSR);
-MODULE_PARM_DESC(w1_id, "1-wire id for the slave detection");
+MODULE_PARM_DESC(w1_id, "1-wire id for the slave detection in HDQ mode");
 
 MODULE_AUTHOR("Texas Instruments");
-MODULE_DESCRIPTION("HDQ driver Library");
+MODULE_DESCRIPTION("HDQ-1W driver Library");
 MODULE_LICENSE("GPL");
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3abc447783aa..6b747394f6f5 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -231,7 +231,8 @@ out_unlock:
 	if (res < 0 && fl->fl_type != F_UNLCK) {
 		fl_type = fl->fl_type;
 		fl->fl_type = F_UNLCK;
-		res = posix_lock_file_wait(filp, fl);
+		/* Even if this fails we want to return the remote error */
+		posix_lock_file_wait(filp, fl);
 		fl->fl_type = fl_type;
 	}
 out:
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index e2a6af1508af..94f81962368c 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3390,13 +3390,13 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	 * should have access to this page, we're safe to simply set
 	 * PG_locked without checking it first.
 	 */
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	rc = add_to_page_cache_locked(page, mapping,
 				      page->index, GFP_KERNEL);
 
 	/* give up if we can't stick it in the cache */
 	if (rc) {
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 		return rc;
 	}
 
@@ -3417,10 +3417,10 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 		if (*bytes + PAGE_CACHE_SIZE > rsize)
 			break;
 
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (add_to_page_cache_locked(page, mapping, page->index,
 								GFP_KERNEL)) {
-			__clear_page_locked(page);
+			__ClearPageLocked(page);
 			break;
 		}
 		list_move_tail(&page->lru, tmplist);
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 8850254136ae..7002467bfbac 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -106,7 +106,10 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 
 	if (!journal) {
-		ret = generic_file_fsync(file, start, end, datasync);
+		if (test_opt(inode->i_sb, BARRIER))
+			ret = generic_file_fsync(file, start, end, datasync);
+		else
+			ret = __generic_file_fsync(file, start, end, datasync);
 		if (!ret && !hlist_empty(&inode->i_dentry))
 			ret = ext4_sync_parent(inode);
 		goto out;
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 93fc62232ec2..5d384921524d 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -301,15 +301,59 @@ static int fat_bmap_cluster(struct inode *inode, int cluster)
 	return dclus;
 }
 
-int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
-	     unsigned long *mapped_blocks, int create)
+int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+			   sector_t last_block,
+			   unsigned long *mapped_blocks, sector_t *bmap)
 {
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int cluster, offset;
+
+	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
+	offset  = sector & (sbi->sec_per_clus - 1);
+	cluster = fat_bmap_cluster(inode, cluster);
+	if (cluster < 0)
+		return cluster;
+	else if (cluster) {
+		*bmap = fat_clus_to_blknr(sbi, cluster) + offset;
+		*mapped_blocks = sbi->sec_per_clus - offset;
+		if (*mapped_blocks > last_block - sector)
+			*mapped_blocks = last_block - sector;
+	}
+
+	return 0;
+}
+
+static int is_exceed_eof(struct inode *inode, sector_t sector,
+			 sector_t *last_block, int create)
+{
+	struct super_block *sb = inode->i_sb;
 	const unsigned long blocksize = sb->s_blocksize;
 	const unsigned char blocksize_bits = sb->s_blocksize_bits;
+
+	*last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
+	if (sector >= *last_block) {
+		if (!create)
+			return 1;
+
+		/*
+		 * ->mmu_private can access on only allocation path.
+		 * (caller must hold ->i_mutex)
+		 */
+		*last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
+			>> blocksize_bits;
+		if (sector >= *last_block)
+			return 1;
+	}
+
+	return 0;
+}
+
+int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
+	     unsigned long *mapped_blocks, int create, bool from_bmap)
+{
+	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
 	sector_t last_block;
-	int cluster, offset;
 
 	*phys = 0;
 	*mapped_blocks = 0;
@@ -321,31 +365,16 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 		return 0;
 	}
 
-	last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
-	if (sector >= last_block) {
-		if (!create)
+	if (!from_bmap) {
+		if (is_exceed_eof(inode, sector, &last_block, create))
 			return 0;
-
-		/*
-		 * ->mmu_private can access on only allocation path.
-		 * (caller must hold ->i_mutex)
-		 */
-		last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
-			>> blocksize_bits;
+	} else {
+		last_block = inode->i_blocks >>
+				(inode->i_sb->s_blocksize_bits - 9);
 		if (sector >= last_block)
 			return 0;
 	}
 
-	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
-	offset  = sector & (sbi->sec_per_clus - 1);
-	cluster = fat_bmap_cluster(inode, cluster);
-	if (cluster < 0)
-		return cluster;
-	else if (cluster) {
-		*phys = fat_clus_to_blknr(sbi, cluster) + offset;
-		*mapped_blocks = sbi->sec_per_clus - offset;
-		if (*mapped_blocks > last_block - sector)
-			*mapped_blocks = last_block - sector;
-	}
-	return 0;
+	return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks,
+				      phys);
 }
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 4afc4d9d2e41..4c71c8c76426 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -91,7 +91,7 @@ next:
 
 	*bh = NULL;
 	iblock = *pos >> sb->s_blocksize_bits;
-	err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0);
+	err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0, false);
 	if (err || !phys)
 		return -1;	/* beyond EOF or error */
 
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index be5e15323bab..4307cd4f8da0 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -285,8 +285,11 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
 extern void fat_cache_inval_inode(struct inode *inode);
 extern int fat_get_cluster(struct inode *inode, int cluster,
 			   int *fclus, int *dclus);
+extern int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+				  sector_t last_block,
+				  unsigned long *mapped_blocks, sector_t *bmap);
 extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
-		    unsigned long *mapped_blocks, int create);
+		    unsigned long *mapped_blocks, int create, bool from_bmap);
 
 /* fat/dir.c */
 extern const struct file_operations fat_dir_operations;
@@ -384,6 +387,7 @@ static inline unsigned long fat_dir_hash(int logstart)
 {
 	return hash_32(logstart, FAT_HASH_BITS);
 }
+extern int fat_add_cluster(struct inode *inode);
 
 /* fat/misc.c */
 extern __printf(3, 4) __cold
diff --git a/fs/fat/file.c b/fs/fat/file.c
index a08f1039909a..43d3475da83a 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -14,8 +14,12 @@
 #include <linux/backing-dev.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
+#include <linux/falloc.h>
 #include "fat.h"
 
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len);
+
 static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr)
 {
 	u32 attr;
@@ -177,6 +181,7 @@ const struct file_operations fat_file_operations = {
 #endif
 	.fsync		= fat_file_fsync,
 	.splice_read	= generic_file_splice_read,
+	.fallocate	= fat_fallocate,
 };
 
 static int fat_cont_expand(struct inode *inode, loff_t size)
@@ -215,6 +220,62 @@ out:
 	return err;
 }
 
+/*
+ * Preallocate space for a file. This implements fat's fallocate file
+ * operation, which gets called from sys_fallocate system call. User
+ * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set
+ * we just allocate clusters without zeroing them out. Otherwise we
+ * allocate and zero out clusters via an expanding truncate.
+ */
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len)
+{
+	int nr_cluster; /* Number of clusters to be allocated */
+	loff_t mm_bytes; /* Number of bytes to be allocated for file */
+	loff_t ondisksize; /* block aligned on-disk size in bytes*/
+	struct inode *inode = file->f_mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int err = 0;
+
+	/* No support for hole punch or other fallocate flags. */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	/* No support for dir */
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&inode->i_mutex);
+	if (mode & FALLOC_FL_KEEP_SIZE) {
+		ondisksize = inode->i_blocks << 9;
+		if ((offset + len) <= ondisksize)
+			goto error;
+
+		/* First compute the number of clusters to be allocated */
+		mm_bytes = offset + len - ondisksize;
+		nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >>
+			sbi->cluster_bits;
+
+		/* Start the allocation.We are not zeroing out the clusters */
+		while (nr_cluster-- > 0) {
+			err = fat_add_cluster(inode);
+			if (err)
+				goto error;
+		}
+	} else {
+		if ((offset + len) <= i_size_read(inode))
+			goto error;
+
+		/* This is just an expanding truncate */
+		err = fat_cont_expand(inode, (offset + len));
+	}
+
+error:
+	mutex_unlock(&inode->i_mutex);
+	return err;
+}
+
 /* Free all clusters after the skip'th cluster. */
 static int fat_free(struct inode *inode, int skip)
 {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 509411dd3698..d04c87da4255 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -93,7 +93,7 @@ static struct fat_floppy_defaults {
 },
 };
 
-static int fat_add_cluster(struct inode *inode)
+int fat_add_cluster(struct inode *inode)
 {
 	int err, cluster;
 
@@ -115,10 +115,10 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
 	unsigned long mapped_blocks;
-	sector_t phys;
+	sector_t phys, last_block;
 	int err, offset;
 
-	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
+	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
 	if (err)
 		return err;
 	if (phys) {
@@ -135,8 +135,14 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 		return -EIO;
 	}
 
+	last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9);
 	offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
-	if (!offset) {
+	/*
+	 * allocate a cluster according to the following.
+	 * 1) no more available blocks
+	 * 2) not part of fallocate region
+	 */
+	if (!offset && !(iblock < last_block)) {
 		/* TODO: multiple cluster allocation would be desirable. */
 		err = fat_add_cluster(inode);
 		if (err)
@@ -148,7 +154,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	*max_blocks = min(mapped_blocks, *max_blocks);
 	MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;
 
-	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
+	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false);
 	if (err)
 		return err;
 
@@ -273,13 +279,38 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	return ret;
 }
 
+static int fat_get_block_bmap(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh_result, int create)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int err;
+	sector_t bmap;
+	unsigned long mapped_blocks;
+
+	BUG_ON(create != 0);
+
+	err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true);
+	if (err)
+		return err;
+
+	if (bmap) {
+		map_bh(bh_result, sb, bmap);
+		max_blocks = min(mapped_blocks, max_blocks);
+	}
+
+	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
+
+	return 0;
+}
+
 static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t blocknr;
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
-	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);
 
 	return blocknr;
@@ -553,13 +584,43 @@ out:
 
 EXPORT_SYMBOL_GPL(fat_build_inode);
 
+static int __fat_write_inode(struct inode *inode, int wait);
+
+static void fat_free_eofblocks(struct inode *inode)
+{
+	/* Release unwritten fallocated blocks on inode eviction. */
+	if ((inode->i_blocks << 9) >
+			round_up(MSDOS_I(inode)->mmu_private,
+				MSDOS_SB(inode->i_sb)->cluster_size)) {
+		int err;
+
+		fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private);
+		/* Fallocate results in updating the i_start/iogstart
+		 * for the zero byte file. So, make it return to
+		 * original state during evict and commit it to avoid
+		 * any corruption on the next access to the cluster
+		 * chain for the file.
+		 */
+		err = __fat_write_inode(inode, inode_needs_sync(inode));
+		if (err) {
+			fat_msg(inode->i_sb, KERN_WARNING, "Failed to "
+					"update on disk inode for unused "
+					"fallocated blocks, inode could be "
+					"corrupted. Please run fsck");
+		}
+
+	}
+}
+
 static void fat_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		fat_truncate_blocks(inode, 0);
-	}
+	} else
+		fat_free_eofblocks(inode);
+
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	fat_cache_inval_inode(inode);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 316adb968b65..10d317d65092 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -139,6 +139,13 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
+	if (!vma->vm_mm->hugetlb_usage) {
+		vma->vm_mm->hugetlb_usage = kzalloc(sizeof(struct hugetlb_usage),
+							GFP_KERNEL);
+		if (!vma->vm_mm->hugetlb_usage)
+			return -ENOMEM;
+	}
+
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
 	mutex_lock(&inode->i_mutex);
@@ -162,6 +169,11 @@ out:
 	return ret;
 }
 
+void exit_hugetlb_mmap(struct mm_struct *mm)
+{
+	kfree(mm->hugetlb_usage);
+}
+
 /*
  * Called under down_write(mmap_sem).
  */
diff --git a/fs/mpage.c b/fs/mpage.c
index 778a4ddef77a..2ebf91652ecb 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -482,6 +482,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct buffer_head map_bh;
 	loff_t i_size = i_size_read(inode);
 	int ret = 0;
+	int wr = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 
 	if (page_has_buffers(page)) {
 		struct buffer_head *head = page_buffers(page);
@@ -590,7 +591,7 @@ page_is_mapped:
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -617,7 +618,7 @@ alloc_new:
 	wbc_account_io(wbc, page, PAGE_SIZE);
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		goto alloc_new;
 	}
 
@@ -627,7 +628,7 @@ alloc_new:
 	set_page_writeback(page);
 	unlock_page(page);
 	if (boundary || (first_unmapped != blocks_per_page)) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
@@ -639,7 +640,7 @@ alloc_new:
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 	if (mpd->use_writepage) {
 		ret = mapping->a_ops->writepage(page, wbc);
@@ -695,8 +696,11 @@ mpage_writepages(struct address_space *mapping,
 		};
 
 		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
-		if (mpd.bio)
-			mpage_bio_submit(WRITE, mpd.bio);
+		if (mpd.bio) {
+			int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : WRITE);
+			mpage_bio_submit(wr, mpd.bio);
+		}
 	}
 	blk_finish_plug(&plug);
 	return ret;
@@ -713,8 +717,11 @@ int mpage_writepage(struct page *page, get_block_t get_block,
 		.use_writepage = 0,
 	};
 	int ret = __mpage_writepage(page, wbc, &mpd);
-	if (mpd.bio)
-		mpage_bio_submit(WRITE, mpd.bio);
+	if (mpd.bio) {
+		int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+			  WRITE_SYNC : WRITE);
+		mpage_bio_submit(wr, mpd.bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepage);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 5b1e2a497e51..b8d08d0d0a4d 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -706,7 +706,19 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	int ret;
 	unsigned flags = 0;
 
-	/* don't allow invalid bits: we don't want flags set */
+	/*
+	 * We share a lot of code with fs/dnotify.  We also share
+	 * the bit layout between inotify's IN_* and the fsnotify
+	 * FS_*.  This check ensures that only the inotify IN_*
+	 * bits get passed in and set in watches/events.
+	 */
+	if (unlikely(mask & ~ALL_INOTIFY_BITS))
+		return -EINVAL;
+	/*
+	 * Require at least one valid bit set in the mask.
+	 * Without _something_ set, we would have no events to
+	 * watch for.
+	 */
 	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
 		return -EINVAL;
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 86181d6526dc..0a1e33e12183 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -2516,21 +2516,6 @@ static int ocfs2_update_edge_lengths(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 	u32 range;
 
-	/*
-	 * In normal tree rotation process, we will never touch the
-	 * tree branch above subtree_index and ocfs2_extend_rotate_transaction
-	 * doesn't reserve the credits for them either.
-	 *
-	 * But we do have a special case here which will update the rightmost
-	 * records for all the bh in the path.
-	 * So we have to allocate extra credits and access them.
-	 */
-	ret = ocfs2_extend_trans(handle, subtree_index);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
-
 	ret = ocfs2_journal_access_path(et->et_ci, handle, path);
 	if (ret) {
 		mlog_errno(ret);
@@ -2956,7 +2941,7 @@ static int __ocfs2_rotate_tree_left(handle_t *handle,
 		     right_path->p_node[subtree_root].bh->b_blocknr,
 		     right_path->p_tree_depth);
 
-		ret = ocfs2_extend_rotate_transaction(handle, subtree_root,
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
 						      orig_credits, left_path);
 		if (ret) {
 			mlog_errno(ret);
@@ -3029,21 +3014,9 @@ static int ocfs2_remove_rightmost_path(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 	struct ocfs2_extent_list *el;
 
-
 	ret = ocfs2_et_sanity_check(et);
 	if (ret)
 		goto out;
-	/*
-	 * There's two ways we handle this depending on
-	 * whether path is the only existing one.
-	 */
-	ret = ocfs2_extend_rotate_transaction(handle, 0,
-					      handle->h_buffer_credits,
-					      path);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
-	}
 
 	ret = ocfs2_journal_access_path(et->et_ci, handle, path);
 	if (ret) {
@@ -3641,6 +3614,14 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path,
 		 */
 		if (le16_to_cpu(right_rec->e_leaf_clusters) == 0 &&
 		    le16_to_cpu(el->l_next_free_rec) == 1) {
+			/* extend credit for ocfs2_remove_rightmost_path */
+			ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					right_path);
+			if (ret) {
+				mlog_errno(ret);
+				goto out;
+			}
 
 			ret = ocfs2_remove_rightmost_path(handle, et,
 							  right_path,
@@ -3679,6 +3660,14 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 	BUG_ON(ctxt->c_contig_type == CONTIG_NONE);
 
 	if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) {
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 		/*
 		 * The merge code will need to create an empty
 		 * extent to take the place of the newly
@@ -3727,6 +3716,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 		 */
 		BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0]));
 
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		/* The merge left us with an empty extent, remove it. */
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		if (ret) {
@@ -3748,6 +3746,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 			goto out;
 		}
 
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		/*
 		 * Error from this last rotate is not critical, so
@@ -3783,6 +3790,16 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 		}
 
 		if (ctxt->c_split_covers_rec) {
+			/* extend credit for ocfs2_remove_rightmost_path */
+			ret = ocfs2_extend_rotate_transaction(handle, 0,
+					handle->h_buffer_credits,
+					path);
+			if (ret) {
+				mlog_errno(ret);
+				ret = 0;
+				goto out;
+			}
+
 			/*
 			 * The merge may have left an empty extent in
 			 * our leaf. Try to rotate it away.
@@ -5342,6 +5359,15 @@ static int ocfs2_truncate_rec(handle_t *handle,
 	struct ocfs2_extent_block *eb;
 
 	if (ocfs2_is_empty_extent(&el->l_recs[0]) && index > 0) {
+		/* extend credit for ocfs2_remove_rightmost_path */
+		ret = ocfs2_extend_rotate_transaction(handle, 0,
+				handle->h_buffer_credits,
+				path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_rotate_tree_left(handle, et, path, dealloc);
 		if (ret) {
 			mlog_errno(ret);
@@ -5928,16 +5954,6 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 
 		ocfs2_journal_dirty(handle, tl_bh);
 
-		/* TODO: Perhaps we can calculate the bulk of the
-		 * credits up front rather than extending like
-		 * this. */
-		status = ocfs2_extend_trans(handle,
-					    OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
-
 		rec = tl->tl_recs[i];
 		start_blk = ocfs2_clusters_to_blocks(data_alloc_inode->i_sb,
 						    le32_to_cpu(rec.t_start));
@@ -5958,6 +5974,13 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 				goto bail;
 			}
 		}
+
+		status = ocfs2_extend_trans(handle,
+				OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
 		i--;
 	}
 
@@ -6016,7 +6039,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_UPDATE);
+	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 64b11d90eca6..4bb992145385 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -499,152 +499,6 @@ bail:
 	return status;
 }
 
-/*
- * TODO: Make this into a generic get_blocks function.
- *
- * From do_direct_io in direct-io.c:
- *  "So what we do is to permit the ->get_blocks function to populate
- *   bh.b_size with the size of IO which is permitted at this offset and
- *   this i_blkbits."
- *
- * This function is called directly from get_more_blocks in direct-io.c.
- *
- * called like this: dio->get_blocks(dio->inode, fs_startblk,
- * 					fs_count, map_bh, dio->rw == WRITE);
- */
-static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
-				     struct buffer_head *bh_result, int create)
-{
-	int ret;
-	u32 cpos = 0;
-	int alloc_locked = 0;
-	u64 p_blkno, inode_blocks, contig_blocks;
-	unsigned int ext_flags;
-	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
-	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
-	unsigned long len = bh_result->b_size;
-	unsigned int clusters_to_alloc = 0, contig_clusters = 0;
-
-	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
-
-	/* This function won't even be called if the request isn't all
-	 * nicely aligned and of the right size, so there's no need
-	 * for us to check any of that. */
-
-	inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
-
-	down_read(&OCFS2_I(inode)->ip_alloc_sem);
-
-	/* This figures out the size of the next contiguous block, and
-	 * our logical offset */
-	ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
-					  &contig_blocks, &ext_flags);
-	up_read(&OCFS2_I(inode)->ip_alloc_sem);
-
-	if (ret) {
-		mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
-		     (unsigned long long)iblock);
-		ret = -EIO;
-		goto bail;
-	}
-
-	/* We should already CoW the refcounted extent in case of create. */
-	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
-
-	/* allocate blocks if no p_blkno is found, and create == 1 */
-	if (!p_blkno && create) {
-		ret = ocfs2_inode_lock(inode, NULL, 1);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto bail;
-		}
-
-		alloc_locked = 1;
-
-		down_write(&OCFS2_I(inode)->ip_alloc_sem);
-
-		/* fill hole, allocate blocks can't be larger than the size
-		 * of the hole */
-		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
-		contig_clusters = ocfs2_clusters_for_blocks(inode->i_sb,
-				contig_blocks);
-		if (clusters_to_alloc > contig_clusters)
-			clusters_to_alloc = contig_clusters;
-
-		/* allocate extent and insert them into the extent tree */
-		ret = ocfs2_extend_allocation(inode, cpos,
-				clusters_to_alloc, 0);
-		if (ret < 0) {
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-			mlog_errno(ret);
-			goto bail;
-		}
-
-		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
-				&contig_blocks, &ext_flags);
-		if (ret < 0) {
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
-					(unsigned long long)iblock);
-			ret = -EIO;
-			goto bail;
-		}
-		up_write(&OCFS2_I(inode)->ip_alloc_sem);
-	}
-
-	/*
-	 * get_more_blocks() expects us to describe a hole by clearing
-	 * the mapped bit on bh_result().
-	 *
-	 * Consider an unwritten extent as a hole.
-	 */
-	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
-		map_bh(bh_result, inode->i_sb, p_blkno);
-	else
-		clear_buffer_mapped(bh_result);
-
-	/* make sure we don't map more than max_blocks blocks here as
-	   that's all the kernel will handle at this point. */
-	if (max_blocks < contig_blocks)
-		contig_blocks = max_blocks;
-	bh_result->b_size = contig_blocks << blocksize_bits;
-bail:
-	if (alloc_locked)
-		ocfs2_inode_unlock(inode, 1);
-	return ret;
-}
-
-/*
- * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
- * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
- * to protect io on one node from truncation on another.
- */
-static void ocfs2_dio_end_io(struct kiocb *iocb,
-			     loff_t offset,
-			     ssize_t bytes,
-			     void *private)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	int level;
-
-	/* this io's submitter should not have unlocked this before we could */
-	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
-
-	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
-		ocfs2_iocb_clear_unaligned_aio(iocb);
-
-		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
-	}
-
-	/* Let rw unlock to be done later to protect append direct io write */
-	if (offset + bytes <= i_size_read(inode)) {
-		ocfs2_iocb_clear_rw_locked(iocb);
-
-		level = ocfs2_iocb_rw_locked_level(iocb);
-		ocfs2_rw_unlock(inode, level);
-	}
-}
-
 static int ocfs2_releasepage(struct page *page, gfp_t wait)
 {
 	if (!page_has_buffers(page))
@@ -652,361 +506,6 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
-static int ocfs2_is_overwrite(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset)
-{
-	int ret = 0;
-	u32 v_cpos = 0;
-	u32 p_cpos = 0;
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-
-	v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
-	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
-			&num_clusters, &ext_flags);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
-	}
-
-	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
-		return 1;
-
-	return 0;
-}
-
-static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset,
-		u64 zero_len, int cluster_align)
-{
-	u32 p_cpos = 0;
-	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-	int ret = 0;
-
-	if (offset <= i_size_read(inode) || cluster_align)
-		return 0;
-
-	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
-			&ext_flags);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
-	}
-
-	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-		u64 s = i_size_read(inode);
-		sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
-			(do_div(s, osb->s_clustersize) >> 9);
-
-		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
-				zero_len >> 9, GFP_NOFS, false);
-		if (ret < 0)
-			mlog_errno(ret);
-	}
-
-	return ret;
-}
-
-static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb,
-		struct inode *inode, loff_t offset)
-{
-	u64 zero_start, zero_len, total_zero_len;
-	u32 p_cpos = 0, clusters_to_add;
-	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-	u32 size_div, offset_div;
-	int ret = 0;
-
-	{
-		u64 o = offset;
-		u64 s = i_size_read(inode);
-
-		offset_div = do_div(o, osb->s_clustersize);
-		size_div = do_div(s, osb->s_clustersize);
-	}
-
-	if (offset <= i_size_read(inode))
-		return 0;
-
-	clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) -
-		ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode));
-	total_zero_len = offset - i_size_read(inode);
-	if (clusters_to_add)
-		total_zero_len -= offset_div;
-
-	/* Allocate clusters to fill out holes, and this is only needed
-	 * when we add more than one clusters. Otherwise the cluster will
-	 * be allocated during direct IO */
-	if (clusters_to_add > 1) {
-		ret = ocfs2_extend_allocation(inode,
-				OCFS2_I(inode)->ip_clusters,
-				clusters_to_add - 1, 0);
-		if (ret) {
-			mlog_errno(ret);
-			goto out;
-		}
-	}
-
-	while (total_zero_len) {
-		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
-				&ext_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) +
-			size_div;
-		zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) -
-			size_div;
-		zero_len = min(total_zero_len, zero_len);
-
-		if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-					zero_start >> 9, zero_len >> 9,
-					GFP_NOFS, false);
-			if (ret < 0) {
-				mlog_errno(ret);
-				goto out;
-			}
-		}
-
-		total_zero_len -= zero_len;
-		v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div);
-
-		/* Only at first iteration can be cluster not aligned.
-		 * So set size_div to 0 for the rest */
-		size_div = 0;
-	}
-
-out:
-	return ret;
-}
-
-static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
-		struct iov_iter *iter,
-		loff_t offset)
-{
-	ssize_t ret = 0;
-	ssize_t written = 0;
-	bool orphaned = false;
-	int is_overwrite = 0;
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file)->i_mapping->host;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct buffer_head *di_bh = NULL;
-	size_t count = iter->count;
-	journal_t *journal = osb->journal->j_journal;
-	u64 zero_len_head, zero_len_tail;
-	int cluster_align_head, cluster_align_tail;
-	loff_t final_size = offset + count;
-	int append_write = offset >= i_size_read(inode) ? 1 : 0;
-	unsigned int num_clusters = 0;
-	unsigned int ext_flags = 0;
-
-	{
-		u64 o = offset;
-		u64 s = i_size_read(inode);
-
-		zero_len_head = do_div(o, 1 << osb->s_clustersize_bits);
-		cluster_align_head = !zero_len_head;
-
-		zero_len_tail = osb->s_clustersize -
-			do_div(s, osb->s_clustersize);
-		if ((offset - i_size_read(inode)) < zero_len_tail)
-			zero_len_tail = offset - i_size_read(inode);
-		cluster_align_tail = !zero_len_tail;
-	}
-
-	/*
-	 * when final_size > inode->i_size, inode->i_size will be
-	 * updated after direct write, so add the inode to orphan
-	 * dir first.
-	 */
-	if (final_size > i_size_read(inode)) {
-		ret = ocfs2_add_inode_to_orphan(osb, inode);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-		orphaned = true;
-	}
-
-	if (append_write) {
-		ret = ocfs2_inode_lock(inode, NULL, 1);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto clean_orphan;
-		}
-
-		/* zeroing out the previously allocated cluster tail
-		 * that but not zeroed */
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
-			down_read(&OCFS2_I(inode)->ip_alloc_sem);
-			ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
-					zero_len_tail, cluster_align_tail);
-			up_read(&OCFS2_I(inode)->ip_alloc_sem);
-		} else {
-			down_write(&OCFS2_I(inode)->ip_alloc_sem);
-			ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
-					offset);
-			up_write(&OCFS2_I(inode)->ip_alloc_sem);
-		}
-		if (ret < 0) {
-			mlog_errno(ret);
-			ocfs2_inode_unlock(inode, 1);
-			goto clean_orphan;
-		}
-
-		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
-		if (is_overwrite < 0) {
-			mlog_errno(is_overwrite);
-			ocfs2_inode_unlock(inode, 1);
-			goto clean_orphan;
-		}
-
-		ocfs2_inode_unlock(inode, 1);
-	}
-
-	written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
-				       offset, ocfs2_direct_IO_get_blocks,
-				       ocfs2_dio_end_io, NULL, 0);
-	/* overwrite aio may return -EIOCBQUEUED, and it is not an error */
-	if ((written < 0) && (written != -EIOCBQUEUED)) {
-		loff_t i_size = i_size_read(inode);
-
-		if (offset + count > i_size) {
-			ret = ocfs2_inode_lock(inode, &di_bh, 1);
-			if (ret < 0) {
-				mlog_errno(ret);
-				goto clean_orphan;
-			}
-
-			if (i_size == i_size_read(inode)) {
-				ret = ocfs2_truncate_file(inode, di_bh,
-						i_size);
-				if (ret < 0) {
-					if (ret != -ENOSPC)
-						mlog_errno(ret);
-
-					ocfs2_inode_unlock(inode, 1);
-					brelse(di_bh);
-					di_bh = NULL;
-					goto clean_orphan;
-				}
-			}
-
-			ocfs2_inode_unlock(inode, 1);
-			brelse(di_bh);
-			di_bh = NULL;
-
-			ret = jbd2_journal_force_commit(journal);
-			if (ret < 0)
-				mlog_errno(ret);
-		}
-	} else if (written > 0 && append_write && !is_overwrite &&
-			!cluster_align_head) {
-		/* zeroing out the allocated cluster head */
-		u32 p_cpos = 0;
-		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
-
-		ret = ocfs2_inode_lock(inode, NULL, 0);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto clean_orphan;
-		}
-
-		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
-				&num_clusters, &ext_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			ocfs2_inode_unlock(inode, 0);
-			goto clean_orphan;
-		}
-
-		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
-
-		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-				(u64)p_cpos << (osb->s_clustersize_bits - 9),
-				zero_len_head >> 9, GFP_NOFS, false);
-		if (ret < 0)
-			mlog_errno(ret);
-
-		ocfs2_inode_unlock(inode, 0);
-	}
-
-clean_orphan:
-	if (orphaned) {
-		int tmp_ret;
-		int update_isize = written > 0 ? 1 : 0;
-		loff_t end = update_isize ? offset + written : 0;
-
-		tmp_ret = ocfs2_inode_lock(inode, &di_bh, 1);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(ret);
-			goto out;
-		}
-
-		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
-				update_isize, end);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(ret);
-			brelse(di_bh);
-			goto out;
-		}
-
-		ocfs2_inode_unlock(inode, 1);
-		brelse(di_bh);
-
-		tmp_ret = jbd2_journal_force_commit(journal);
-		if (tmp_ret < 0) {
-			ret = tmp_ret;
-			mlog_errno(tmp_ret);
-		}
-	}
-
-out:
-	if (ret >= 0)
-		ret = written;
-	return ret;
-}
-
-static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-			       loff_t offset)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file)->i_mapping->host;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	int full_coherency = !(osb->s_mount_opt &
-			OCFS2_MOUNT_COHERENCY_BUFFERED);
-
-	/*
-	 * Fallback to buffered I/O if we see an inode without
-	 * extents.
-	 */
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-		return 0;
-
-	/* Fallback to buffered I/O if we are appending and
-	 * concurrent O_DIRECT writes are allowed.
-	 */
-	if (i_size_read(inode) <= offset && !full_coherency)
-		return 0;
-
-	if (iov_iter_rw(iter) == READ)
-		return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
-					    iter, offset,
-					    ocfs2_direct_IO_get_blocks,
-					    ocfs2_dio_end_io, NULL, 0);
-	else
-		return ocfs2_direct_IO_write(iocb, iter, offset);
-}
-
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
 					    u32 cpos,
 					    unsigned int *start,
@@ -1193,6 +692,13 @@ next_bh:
 
 #define OCFS2_MAX_CLUSTERS_PER_PAGE	(PAGE_CACHE_SIZE / OCFS2_MIN_CLUSTERSIZE)
 
+struct ocfs2_unwritten_extent {
+	struct list_head	ue_node;
+	struct list_head	ue_ip_node;
+	u32			ue_cpos;
+	u32			ue_phys;
+};
+
 /*
  * Describe the state of a single cluster to be written to.
  */
@@ -1204,7 +710,7 @@ struct ocfs2_write_cluster_desc {
 	 * filled.
 	 */
 	unsigned	c_new;
-	unsigned	c_unwritten;
+	unsigned	c_clear_unwritten;
 	unsigned	c_needs_zero;
 };
 
@@ -1216,6 +722,9 @@ struct ocfs2_write_ctxt {
 	/* First cluster allocated in a nonsparse extend */
 	u32				w_first_new_cpos;
 
+	/* Type of caller. Must be one of buffer, mmap, direct.  */
+	ocfs2_write_type_t		w_type;
+
 	struct ocfs2_write_cluster_desc	w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];
 
 	/*
@@ -1264,6 +773,8 @@ struct ocfs2_write_ctxt {
 	struct buffer_head		*w_di_bh;
 
 	struct ocfs2_cached_dealloc_ctxt w_dealloc;
+
+	struct list_head		w_unwritten_list;
 };
 
 void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
@@ -1302,8 +813,25 @@ static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_free_unwritten_list(struct inode *inode,
+				 struct list_head *head)
+{
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL;
+
+	list_for_each_entry_safe(ue, tmp, head, ue_node) {
+		list_del(&ue->ue_node);
+		spin_lock(&oi->ip_lock);
+		list_del(&ue->ue_ip_node);
+		spin_unlock(&oi->ip_lock);
+		kfree(ue);
+	}
+}
+
+static void ocfs2_free_write_ctxt(struct inode *inode,
+				  struct ocfs2_write_ctxt *wc)
 {
+	ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list);
 	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
@@ -1311,7 +839,8 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 
 static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 				  struct ocfs2_super *osb, loff_t pos,
-				  unsigned len, struct buffer_head *di_bh)
+				  unsigned len, ocfs2_write_type_t type,
+				  struct buffer_head *di_bh)
 {
 	u32 cend;
 	struct ocfs2_write_ctxt *wc;
@@ -1326,6 +855,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 	wc->w_clen = cend - wc->w_cpos + 1;
 	get_bh(di_bh);
 	wc->w_di_bh = di_bh;
+	wc->w_type = type;
 
 	if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits))
 		wc->w_large_pages = 1;
@@ -1333,6 +863,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 		wc->w_large_pages = 0;
 
 	ocfs2_init_dealloc_ctxt(&wc->w_dealloc);
+	INIT_LIST_HEAD(&wc->w_unwritten_list);
 
 	*wcp = wc;
 
@@ -1393,12 +924,13 @@ static void ocfs2_write_failure(struct inode *inode,
 		to = user_pos + user_len;
 	struct page *tmppage;
 
-	ocfs2_zero_new_buffers(wc->w_target_page, from, to);
+	if (wc->w_target_page)
+		ocfs2_zero_new_buffers(wc->w_target_page, from, to);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		tmppage = wc->w_pages[i];
 
-		if (page_has_buffers(tmppage)) {
+		if (tmppage && page_has_buffers(tmppage)) {
 			if (ocfs2_should_order_data(inode))
 				ocfs2_jbd2_file_inode(wc->w_handle, inode);
 
@@ -1528,11 +1060,13 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 		wc->w_num_pages = 1;
 		start = target_index;
 	}
+	end_index = (user_pos + user_len - 1) >> PAGE_CACHE_SHIFT;
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		index = start + i;
 
-		if (index == target_index && mmap_page) {
+		if (index >= target_index && index <= end_index &&
+		    wc->w_type == OCFS2_WRITE_MMAP) {
 			/*
 			 * ocfs2_pagemkwrite() is a little different
 			 * and wants us to directly use the page
@@ -1551,6 +1085,11 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			page_cache_get(mmap_page);
 			wc->w_pages[i] = mmap_page;
 			wc->w_target_locked = true;
+		} else if (index >= target_index && index <= end_index &&
+			   wc->w_type == OCFS2_WRITE_DIRECT) {
+			/* Direct write has no mapping page. */
+			wc->w_pages[i] = NULL;
+			continue;
 		} else {
 			wc->w_pages[i] = find_or_create_page(mapping, index,
 							     GFP_NOFS);
@@ -1575,19 +1114,20 @@ out:
  * Prepare a single cluster for write one cluster into the file.
  */
 static int ocfs2_write_cluster(struct address_space *mapping,
-			       u32 phys, unsigned int unwritten,
+			       u32 *phys, unsigned int new,
+			       unsigned int clear_unwritten,
 			       unsigned int should_zero,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       struct ocfs2_write_ctxt *wc, u32 cpos,
 			       loff_t user_pos, unsigned user_len)
 {
-	int ret, i, new;
-	u64 v_blkno, p_blkno;
+	int ret, i;
+	u64 p_blkno;
 	struct inode *inode = mapping->host;
 	struct ocfs2_extent_tree et;
+	int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
 
-	new = phys == 0 ? 1 : 0;
 	if (new) {
 		u32 tmp_pos;
 
@@ -1597,9 +1137,9 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		 */
 		tmp_pos = cpos;
 		ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
-					   &tmp_pos, 1, 0, wc->w_di_bh,
-					   wc->w_handle, data_ac,
-					   meta_ac, NULL);
+					   &tmp_pos, 1, !clear_unwritten,
+					   wc->w_di_bh, wc->w_handle,
+					   data_ac, meta_ac, NULL);
 		/*
 		 * This shouldn't happen because we must have already
 		 * calculated the correct meta data allocation required. The
@@ -1616,11 +1156,11 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 			mlog_errno(ret);
 			goto out;
 		}
-	} else if (unwritten) {
+	} else if (clear_unwritten) {
 		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
 					      wc->w_di_bh);
 		ret = ocfs2_mark_extent_written(inode, &et,
-						wc->w_handle, cpos, 1, phys,
+						wc->w_handle, cpos, 1, *phys,
 						meta_ac, &wc->w_dealloc);
 		if (ret < 0) {
 			mlog_errno(ret);
@@ -1628,30 +1168,33 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		}
 	}
 
-	if (should_zero)
-		v_blkno = ocfs2_clusters_to_blocks(inode->i_sb, cpos);
-	else
-		v_blkno = user_pos >> inode->i_sb->s_blocksize_bits;
-
 	/*
 	 * The only reason this should fail is due to an inability to
 	 * find the extent added.
 	 */
-	ret = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, NULL,
-					  NULL);
+	ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL);
 	if (ret < 0) {
 		mlog(ML_ERROR, "Get physical blkno failed for inode %llu, "
-			    "at logical block %llu",
-			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
-			    (unsigned long long)v_blkno);
+			    "at logical cluster %u",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos);
 		goto out;
 	}
 
-	BUG_ON(p_blkno == 0);
+	BUG_ON(*phys == 0);
+
+	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys);
+	if (!should_zero)
+		p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		int tmpret;
 
+		/* This is the direct io target page. */
+		if (wc->w_pages[i] == NULL) {
+			p_blkno++;
+			continue;
+		}
+
 		tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc,
 						      wc->w_pages[i], cpos,
 						      user_pos, user_len,
@@ -1698,8 +1241,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
 		if ((cluster_off + local_len) > osb->s_clustersize)
 			local_len = osb->s_clustersize - cluster_off;
 
-		ret = ocfs2_write_cluster(mapping, desc->c_phys,
-					  desc->c_unwritten,
+		ret = ocfs2_write_cluster(mapping, &desc->c_phys,
+					  desc->c_new,
+					  desc->c_clear_unwritten,
 					  desc->c_needs_zero,
 					  data_ac, meta_ac,
 					  wc, desc->c_cpos, pos, local_len);
@@ -1770,6 +1314,66 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
 }
 
 /*
+ * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to
+ * do the zero work. And should not to clear UNWRITTEN since it will be cleared
+ * by the direct io procedure.
+ * If this is a new extent that allocated by direct io, we should mark it in
+ * the ip_unwritten_list.
+ */
+static int ocfs2_unwritten_check(struct inode *inode,
+				 struct ocfs2_write_ctxt *wc,
+				 struct ocfs2_write_cluster_desc *desc)
+{
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_unwritten_extent *ue = NULL, *new = NULL;
+	int ret = 0;
+
+	if (!desc->c_needs_zero)
+		return 0;
+
+retry:
+	spin_lock(&oi->ip_lock);
+	/* Needs not to zero no metter buffer or direct. The one who is zero
+	 * the cluster is doing zero. And he will clear unwritten after all
+	 * cluster io finished. */
+	list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) {
+		if (desc->c_cpos == ue->ue_cpos) {
+			BUG_ON(desc->c_new);
+			desc->c_needs_zero = 0;
+			desc->c_clear_unwritten = 0;
+			goto unlock;
+		}
+	}
+
+	if (wc->w_type != OCFS2_WRITE_DIRECT)
+		goto unlock;
+
+	if (new == NULL) {
+		spin_unlock(&oi->ip_lock);
+		new = kmalloc(sizeof(struct ocfs2_unwritten_extent),
+			     GFP_NOFS);
+		if (new == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		goto retry;
+	}
+	/* This direct write will doing zero. */
+	new->ue_cpos = desc->c_cpos;
+	new->ue_phys = desc->c_phys;
+	desc->c_clear_unwritten = 0;
+	list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list);
+	list_add_tail(&new->ue_node, &wc->w_unwritten_list);
+	new = NULL;
+unlock:
+	spin_unlock(&oi->ip_lock);
+out:
+	if (new)
+		kfree(new);
+	return ret;
+}
+
+/*
  * Populate each single-cluster write descriptor in the write context
  * with information about the i/o to be done.
  *
@@ -1844,14 +1448,21 @@ static int ocfs2_populate_write_desc(struct inode *inode,
 		if (phys == 0) {
 			desc->c_new = 1;
 			desc->c_needs_zero = 1;
+			desc->c_clear_unwritten = 1;
 			*clusters_to_alloc = *clusters_to_alloc + 1;
 		}
 
 		if (ext_flags & OCFS2_EXT_UNWRITTEN) {
-			desc->c_unwritten = 1;
+			desc->c_clear_unwritten = 1;
 			desc->c_needs_zero = 1;
 		}
 
+		ret = ocfs2_unwritten_check(inode, wc, desc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
 		num_clusters--;
 	}
 
@@ -2014,8 +1625,10 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode,
 	if (ret)
 		mlog_errno(ret);
 
-	wc->w_first_new_cpos =
-		ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
+	/* There is no wc if this is call from direct. */
+	if (wc)
+		wc->w_first_new_cpos =
+			ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
 
 	return ret;
 }
@@ -2069,9 +1682,8 @@ out:
 	return ret;
 }
 
-int ocfs2_write_begin_nolock(struct file *filp,
-			     struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page)
 {
@@ -2088,7 +1700,7 @@ int ocfs2_write_begin_nolock(struct file *filp,
 	int try_free = 1, ret1;
 
 try_again:
-	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh);
+	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh);
 	if (ret) {
 		mlog_errno(ret);
 		return ret;
@@ -2107,14 +1719,17 @@ try_again:
 		}
 	}
 
-	if (ocfs2_sparse_alloc(osb))
-		ret = ocfs2_zero_tail(inode, di_bh, pos);
-	else
-		ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len,
-						   wc);
-	if (ret) {
-		mlog_errno(ret);
-		goto out;
+	/* Direct io change i_size late, should not zero tail here. */
+	if (type != OCFS2_WRITE_DIRECT) {
+		if (ocfs2_sparse_alloc(osb))
+			ret = ocfs2_zero_tail(inode, di_bh, pos);
+		else
+			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+							   len, wc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 	}
 
 	ret = ocfs2_check_range_for_refcount(inode, pos, len);
@@ -2145,7 +1760,7 @@ try_again:
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			(long long)i_size_read(inode),
 			le32_to_cpu(di->i_clusters),
-			pos, len, flags, mmap_page,
+			pos, len, type, mmap_page,
 			clusters_to_alloc, extents_to_split);
 
 	/*
@@ -2175,17 +1790,17 @@ try_again:
 
 		credits = ocfs2_calc_extend_credits(inode->i_sb,
 						    &di->id2.i_list);
-
-	}
+	} else if (type == OCFS2_WRITE_DIRECT)
+		/* direct write needs not to start trans if no extents alloc. */
+		goto success;
 
 	/*
 	 * We have to zero sparse allocated clusters, unwritten extent clusters,
 	 * and non-sparse clusters we just extended.  For non-sparse writes,
 	 * we know zeros will only be needed in the first and/or last cluster.
 	 */
-	if (clusters_to_alloc || extents_to_split ||
-	    (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
-			    wc->w_desc[wc->w_clen - 1].c_needs_zero)))
+	if (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
+			   wc->w_desc[wc->w_clen - 1].c_needs_zero))
 		cluster_of_pages = 1;
 	else
 		cluster_of_pages = 0;
@@ -2252,7 +1867,8 @@ try_again:
 		ocfs2_free_alloc_context(meta_ac);
 
 success:
-	*pagep = wc->w_target_page;
+	if (pagep)
+		*pagep = wc->w_target_page;
 	*fsdata = wc;
 	return 0;
 out_quota:
@@ -2263,7 +1879,7 @@ out_commit:
 	ocfs2_commit_trans(osb, handle);
 
 out:
-	ocfs2_free_write_ctxt(wc);
+	ocfs2_free_write_ctxt(inode, wc);
 
 	if (data_ac) {
 		ocfs2_free_alloc_context(data_ac);
@@ -2315,8 +1931,8 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep,
-				       fsdata, di_bh, NULL);
+	ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER,
+				       pagep, fsdata, di_bh, NULL);
 	if (ret) {
 		mlog_errno(ret);
 		goto out_fail;
@@ -2373,12 +1989,16 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 	handle_t *handle = wc->w_handle;
 	struct page *tmppage;
 
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-			OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		copied = ret;
-		mlog_errno(ret);
-		goto out;
+	BUG_ON(!list_empty(&wc->w_unwritten_list));
+
+	if (handle) {
+		ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+				wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			copied = ret;
+			mlog_errno(ret);
+			goto out;
+		}
 	}
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
@@ -2386,18 +2006,23 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		goto out_write_size;
 	}
 
-	if (unlikely(copied < len)) {
+	if (unlikely(copied < len) && wc->w_target_page) {
 		if (!PageUptodate(wc->w_target_page))
 			copied = 0;
 
 		ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
 				       start+len);
 	}
-	flush_dcache_page(wc->w_target_page);
+	if (wc->w_target_page)
+		flush_dcache_page(wc->w_target_page);
 
 	for(i = 0; i < wc->w_num_pages; i++) {
 		tmppage = wc->w_pages[i];
 
+		/* This is the direct io target page. */
+		if (tmppage == NULL)
+			continue;
+
 		if (tmppage == wc->w_target_page) {
 			from = wc->w_target_from;
 			to = wc->w_target_to;
@@ -2416,25 +2041,29 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 
 		if (page_has_buffers(tmppage)) {
-			if (ocfs2_should_order_data(inode))
-				ocfs2_jbd2_file_inode(wc->w_handle, inode);
+			if (handle && ocfs2_should_order_data(inode))
+				ocfs2_jbd2_file_inode(handle, inode);
 			block_commit_write(tmppage, from, to);
 		}
 	}
 
 out_write_size:
-	pos += copied;
-	if (pos > i_size_read(inode)) {
-		i_size_write(inode, pos);
-		mark_inode_dirty(inode);
-	}
-	inode->i_blocks = ocfs2_inode_sector_count(inode);
-	di->i_size = cpu_to_le64((u64)i_size_read(inode));
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-	di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
-	di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
-	ocfs2_update_inode_fsync_trans(handle, inode, 1);
-	ocfs2_journal_dirty(handle, wc->w_di_bh);
+	/* Direct io do not update i_size here. */
+	if (wc->w_type != OCFS2_WRITE_DIRECT) {
+		pos += copied;
+		if (pos > i_size_read(inode)) {
+			i_size_write(inode, pos);
+			mark_inode_dirty(inode);
+		}
+		inode->i_blocks = ocfs2_inode_sector_count(inode);
+		di->i_size = cpu_to_le64((u64)i_size_read(inode));
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+		di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+		ocfs2_update_inode_fsync_trans(handle, inode, 1);
+	}
+	if (handle)
+		ocfs2_journal_dirty(handle, wc->w_di_bh);
 
 out:
 	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
@@ -2444,7 +2073,8 @@ out:
 	 */
 	ocfs2_unlock_pages(wc);
 
-	ocfs2_commit_trans(osb, handle);
+	if (handle)
+		ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
@@ -2469,6 +2099,340 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
+struct ocfs2_dio_write_ctxt {
+	struct list_head	dw_zero_list;
+	unsigned		dw_zero_count;
+	int			dw_orphaned;
+	pid_t			dw_writer_pid;
+};
+
+static struct ocfs2_dio_write_ctxt *
+ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
+{
+	struct ocfs2_dio_write_ctxt *dwc = NULL;
+
+	if (bh->b_private)
+		return bh->b_private;
+
+	dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS);
+	if (dwc == NULL)
+		return NULL;
+	INIT_LIST_HEAD(&dwc->dw_zero_list);
+	dwc->dw_zero_count = 0;
+	dwc->dw_orphaned = 0;
+	dwc->dw_writer_pid = task_pid_nr(current);
+	bh->b_private = dwc;
+	*alloc = 1;
+
+	return dwc;
+}
+
+static void ocfs2_dio_free_write_ctx(struct inode *inode,
+				     struct ocfs2_dio_write_ctxt *dwc)
+{
+	ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
+	kfree(dwc);
+}
+
+/*
+ * TODO: Make this into a generic get_blocks function.
+ *
+ * From do_direct_io in direct-io.c:
+ *  "So what we do is to permit the ->get_blocks function to populate
+ *   bh.b_size with the size of IO which is permitted at this offset and
+ *   this i_blkbits."
+ *
+ * This function is called directly from get_more_blocks in direct-io.c.
+ *
+ * called like this: dio->get_blocks(dio->inode, fs_startblk,
+ * 					fs_count, map_bh, dio->rw == WRITE);
+ */
+static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
+			       struct buffer_head *bh_result, int create)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_write_ctxt *wc;
+	struct ocfs2_write_cluster_desc *desc = NULL;
+	struct ocfs2_dio_write_ctxt *dwc = NULL;
+	struct buffer_head *di_bh = NULL;
+	u64 p_blkno;
+	loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
+	unsigned len, total_len = bh_result->b_size;
+	int ret = 0, first_get_block = 0;
+
+	len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
+	len = min(total_len, len);
+
+	mlog(0, "get block of %lu at %llu:%u req %u\n",
+			inode->i_ino, pos, len, total_len);
+
+	/* This is the fast path for re-write. */
+	ret = ocfs2_get_block(inode, iblock, bh_result, create);
+
+	if (buffer_mapped(bh_result) &&
+	    !buffer_new(bh_result) &&
+	    ret == 0)
+		goto out;
+
+	/* Clear state set by ocfs2_get_block. */
+	bh_result->b_state = 0;
+
+	dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
+	if (unlikely(dwc == NULL)) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
+	    ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
+	    !dwc->dw_orphaned) {
+		/*
+		 * when we are going to alloc extents beyond file size, add the
+		 * inode to orphan dir, so we can recall those spaces when
+		 * system crashed during write.
+		 */
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+		dwc->dw_orphaned = 1;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (first_get_block) {
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_tail(inode, di_bh, pos);
+		else
+			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+							   total_len, NULL);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto unlock;
+		}
+	}
+
+	ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
+				       OCFS2_WRITE_DIRECT, NULL,
+				       (void **)&wc, di_bh, NULL);
+	if (ret) {
+		mlog_errno(ret);
+		goto unlock;
+	}
+
+	desc = &wc->w_desc[0];
+
+	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
+	BUG_ON(p_blkno == 0);
+	p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
+
+	map_bh(bh_result, inode->i_sb, p_blkno);
+	bh_result->b_size = len;
+	if (desc->c_needs_zero)
+		set_buffer_new(bh_result);
+
+	/* May sleep in end_io. It should not happen in a irq context. So defer
+	 * it to dio work queue. */
+	set_buffer_defer_completion(bh_result);
+
+	if (!list_empty(&wc->w_unwritten_list)) {
+		struct ocfs2_unwritten_extent *ue = NULL;
+
+		ue = list_first_entry(&wc->w_unwritten_list,
+				      struct ocfs2_unwritten_extent,
+				      ue_node);
+		BUG_ON(ue->ue_cpos != desc->c_cpos);
+		/* The physical address may be 0, fill it. */
+		ue->ue_phys = desc->c_phys;
+
+		list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
+		dwc->dw_zero_count++;
+	}
+
+	ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, NULL, wc);
+	BUG_ON(ret != len);
+	ret = 0;
+unlock:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+out:
+	if (ret < 0)
+		ret = -EIO;
+	return ret;
+}
+
+static void ocfs2_dio_end_io_write(struct inode *inode,
+				   struct ocfs2_dio_write_ctxt *dwc,
+				   loff_t offset,
+				   ssize_t bytes)
+{
+	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_extent_tree et;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct ocfs2_unwritten_extent *ue = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_alloc_context *data_ac = NULL;
+	struct ocfs2_alloc_context *meta_ac = NULL;
+	handle_t *handle = NULL;
+	loff_t end = offset + bytes;
+	int ret = 0, credits = 0, locked = 0;
+
+	ocfs2_init_dealloc_ctxt(&dealloc);
+
+	/* We do clear unwritten, delete orphan, change i_size here. If neither
+	 * of these happen, we can skip all this. */
+	if (list_empty(&dwc->dw_zero_list) &&
+	    end <= i_size_read(inode) &&
+	    !dwc->dw_orphaned)
+		goto out;
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
+	 * are in that context. */
+	if (dwc->dw_writer_pid != task_pid_nr(current)) {
+		mutex_lock(&inode->i_mutex);
+		locked = 1;
+	}
+
+	/* Delete orphan before acquire i_mutex. */
+	if (dwc->dw_orphaned) {
+		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
+
+		end = end > i_size_read(inode) ? end : 0;
+
+		ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
+				!!end, end);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+	di = (struct ocfs2_dinode *)di_bh;
+
+	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
+
+	ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
+				    &data_ac, &meta_ac);
+
+	credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
+
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto unlock;
+	}
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto commit;
+	}
+
+	list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
+		ret = ocfs2_mark_extent_written(inode, &et, handle,
+						ue->ue_cpos, 1,
+						ue->ue_phys,
+						meta_ac, &dealloc);
+		if (ret < 0) {
+			mlog_errno(ret);
+			break;
+		}
+	}
+
+	if (end > i_size_read(inode)) {
+		ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+commit:
+	ocfs2_commit_trans(osb, handle);
+unlock:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+out:
+	ocfs2_run_deallocs(osb, &dealloc);
+	if (locked)
+		mutex_unlock(&inode->i_mutex);
+	ocfs2_dio_free_write_ctx(inode, dwc);
+	if (data_ac)
+		ocfs2_free_alloc_context(data_ac);
+	if (meta_ac)
+		ocfs2_free_alloc_context(meta_ac);
+}
+
+/*
+ * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
+ * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
+ * to protect io on one node from truncation on another.
+ */
+static void ocfs2_dio_end_io(struct kiocb *iocb,
+			     loff_t offset,
+			     ssize_t bytes,
+			     void *private)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	int level;
+
+	/* this io's submitter should not have unlocked this before we could */
+	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
+
+	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
+		ocfs2_iocb_clear_unaligned_aio(iocb);
+
+		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
+	}
+
+	if (private)
+		ocfs2_dio_end_io_write(inode, private, offset, bytes);
+
+	ocfs2_iocb_clear_rw_locked(iocb);
+
+	level = ocfs2_iocb_rw_locked_level(iocb);
+	ocfs2_rw_unlock(inode, level);
+}
+
+static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			       loff_t offset)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	loff_t end = offset + iter->count;
+	get_block_t *get_block;
+
+	/*
+	 * Fallback to buffered I/O if we see an inode without
+	 * extents.
+	 */
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+		return 0;
+
+	/* Fallback to buffered I/O if we do not support append dio. */
+	if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb))
+		return 0;
+
+	if (iov_iter_rw(iter) == READ)
+		get_block = ocfs2_get_block;
+	else
+		get_block = ocfs2_dio_get_block;
+
+	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+				    iter, offset, get_block,
+				    ocfs2_dio_end_io, NULL, 0);
+}
+
 const struct address_space_operations ocfs2_aops = {
 	.readpage		= ocfs2_readpage,
 	.readpages		= ocfs2_readpages,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 24e496d6bdcd..d06b80f58f83 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -47,9 +47,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata);
 
-int ocfs2_write_begin_nolock(struct file *filp,
-			     struct address_space *mapping,
-			     loff_t pos, unsigned len, unsigned flags,
+typedef enum {
+	OCFS2_WRITE_BUFFER = 0,
+	OCFS2_WRITE_DIRECT,
+	OCFS2_WRITE_MMAP,
+} ocfs2_write_type_t;
+
+int ocfs2_write_begin_nolock(struct address_space *mapping,
+			     loff_t pos, unsigned len, ocfs2_write_type_t type,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page);
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 0e5b4515f92e..05346fb8d5fd 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1373,44 +1373,6 @@ out:
 	return ret;
 }
 
-/*
- * Will look for holes and unwritten extents in the range starting at
- * pos for count bytes (inclusive).
- */
-static int ocfs2_check_range_for_holes(struct inode *inode, loff_t pos,
-				       size_t count)
-{
-	int ret = 0;
-	unsigned int extent_flags;
-	u32 cpos, clusters, extent_len, phys_cpos;
-	struct super_block *sb = inode->i_sb;
-
-	cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
-	clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
-
-	while (clusters) {
-		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
-					 &extent_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		if (phys_cpos == 0 || (extent_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = 1;
-			break;
-		}
-
-		if (extent_len > clusters)
-			extent_len = clusters;
-
-		clusters -= extent_len;
-		cpos += extent_len;
-	}
-out:
-	return ret;
-}
-
 static int ocfs2_write_remove_suid(struct inode *inode)
 {
 	int ret;
@@ -2121,18 +2083,12 @@ out:
 
 static int ocfs2_prepare_inode_for_write(struct file *file,
 					 loff_t pos,
-					 size_t count,
-					 int appending,
-					 int *direct_io,
-					 int *has_refcount)
+					 size_t count)
 {
 	int ret = 0, meta_level = 0;
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
 	loff_t end;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	int full_coherency = !(osb->s_mount_opt &
-		OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
@@ -2181,10 +2137,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 							       pos,
 							       count,
 							       &meta_level);
-			if (has_refcount)
-				*has_refcount = 1;
-			if (direct_io)
-				*direct_io = 0;
 		}
 
 		if (ret < 0) {
@@ -2192,67 +2144,12 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 			goto out_unlock;
 		}
 
-		/*
-		 * Skip the O_DIRECT checks if we don't need
-		 * them.
-		 */
-		if (!direct_io || !(*direct_io))
-			break;
-
-		/*
-		 * There's no sane way to do direct writes to an inode
-		 * with inline data.
-		 */
-		if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-			*direct_io = 0;
-			break;
-		}
-
-		/*
-		 * Allowing concurrent direct writes means
-		 * i_size changes wouldn't be synchronized, so
-		 * one node could wind up truncating another
-		 * nodes writes.
-		 */
-		if (end > i_size_read(inode) && !full_coherency) {
-			*direct_io = 0;
-			break;
-		}
-
-		/*
-		 * Fallback to old way if the feature bit is not set.
-		 */
-		if (end > i_size_read(inode) &&
-				!ocfs2_supports_append_dio(osb)) {
-			*direct_io = 0;
-			break;
-		}
-
-		/*
-		 * We don't fill holes during direct io, so
-		 * check for them here. If any are found, the
-		 * caller will have to retake some cluster
-		 * locks and initiate the io as buffered.
-		 */
-		ret = ocfs2_check_range_for_holes(inode, pos, count);
-		if (ret == 1) {
-			/*
-			 * Fallback to old way if the feature bit is not set.
-			 * Otherwise try dio first and then complete the rest
-			 * request through buffer io.
-			 */
-			if (!ocfs2_supports_append_dio(osb))
-				*direct_io = 0;
-			ret = 0;
-		} else if (ret < 0)
-			mlog_errno(ret);
 		break;
 	}
 
 out_unlock:
 	trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
-					    pos, appending, count,
-					    direct_io, has_refcount);
+					    pos, count);
 
 	if (meta_level >= 0)
 		ocfs2_inode_unlock(inode, meta_level);
@@ -2264,18 +2161,16 @@ out:
 static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 				    struct iov_iter *from)
 {
-	int direct_io, appending, rw_level;
-	int can_do_direct, has_refcount = 0;
+	int direct_io, rw_level;
 	ssize_t written = 0;
 	ssize_t ret;
-	size_t count = iov_iter_count(from), orig_count;
+	size_t count = iov_iter_count(from);
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
 	int unaligned_dio = 0;
-	int dropped_dio = 0;
 	int append_write = ((iocb->ki_pos + count) >=
 			i_size_read(inode) ? 1 : 0);
 
@@ -2288,12 +2183,10 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	if (count == 0)
 		return 0;
 
-	appending = iocb->ki_flags & IOCB_APPEND ? 1 : 0;
 	direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 
 	mutex_lock(&inode->i_mutex);
 
-relock:
 	/*
 	 * Concurrent O_DIRECT writes are allowed with
 	 * mount_option "coherency=buffered".
@@ -2326,7 +2219,6 @@ relock:
 		ocfs2_inode_unlock(inode, 1);
 	}
 
-	orig_count = iov_iter_count(from);
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0) {
 		if (ret)
@@ -2335,9 +2227,7 @@ relock:
 	}
 	count = ret;
 
-	can_do_direct = direct_io;
-	ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, appending,
-					    &can_do_direct, &has_refcount);
+	ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count);
 	if (ret < 0) {
 		mlog_errno(ret);
 		goto out;
@@ -2346,22 +2236,6 @@ relock:
 	if (direct_io && !is_sync_kiocb(iocb))
 		unaligned_dio = ocfs2_is_io_unaligned(inode, count, iocb->ki_pos);
 
-	/*
-	 * We can't complete the direct I/O as requested, fall back to
-	 * buffered I/O.
-	 */
-	if (direct_io && !can_do_direct) {
-		ocfs2_rw_unlock(inode, rw_level);
-
-		rw_level = -1;
-
-		direct_io = 0;
-		iocb->ki_flags &= ~IOCB_DIRECT;
-		iov_iter_reexpand(from, orig_count);
-		dropped_dio = 1;
-		goto relock;
-	}
-
 	if (unaligned_dio) {
 		/*
 		 * Wait on previous unaligned aio to complete before
@@ -2397,7 +2271,7 @@ relock:
 		goto no_sync;
 
 	if (((file->f_flags & O_DSYNC) && !direct_io) ||
-	    IS_SYNC(inode) || dropped_dio) {
+	    IS_SYNC(inode)) {
 		ret = filemap_fdatawrite_range(file->f_mapping,
 					       iocb->ki_pos - written,
 					       iocb->ki_pos - 1);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 8f87e05ee25d..0fd9ebdd3ed8 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1125,6 +1125,9 @@ static void ocfs2_clear_inode(struct inode *inode)
 	mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
 			"Clear inode of %llu, inode has io markers\n",
 			(unsigned long long)oi->ip_blkno);
+	mlog_bug_on_msg(!list_empty(&oi->ip_unwritten_list),
+			"Clear inode of %llu, inode has unwritten extents\n",
+			(unsigned long long)oi->ip_blkno);
 
 	ocfs2_extent_map_trunc(inode, 0);
 
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ca3431ee7f24..b5052411fb6d 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -57,6 +57,9 @@ struct ocfs2_inode_info
 	u32				ip_flags; /* see below */
 	u32				ip_attr; /* inode attributes */
 
+	/* Record unwritten extents during direct io. */
+	struct list_head		ip_unwritten_list;
+
 	/* protected by recovery_lock. */
 	struct inode			*ip_next_orphan;
 
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 9581d190f6e1..a88707a0f4da 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -104,8 +104,8 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 	if (page->index == last_index)
 		len = ((size - 1) & ~PAGE_CACHE_MASK) + 1;
 
-	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, 0, &locked_page,
-				       &fsdata, di_bh, page);
+	ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP,
+				       &locked_page, &fsdata, di_bh, page);
 	if (ret) {
 		if (ret != -ENOSPC)
 			mlog_errno(ret);
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b7c6a8..09d0c89a9daf 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1450,28 +1450,20 @@ DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_remove_inode_range);
 
 TRACE_EVENT(ocfs2_prepare_inode_for_write,
 	TP_PROTO(unsigned long long ino, unsigned long long saved_pos,
-		 int appending, unsigned long count,
-		 int *direct_io, int *has_refcount),
-	TP_ARGS(ino, saved_pos, appending, count, direct_io, has_refcount),
+		 unsigned long count),
+	TP_ARGS(ino, saved_pos, count),
 	TP_STRUCT__entry(
 		__field(unsigned long long, ino)
 		__field(unsigned long long, saved_pos)
-		__field(int, appending)
 		__field(unsigned long, count)
-		__field(int, direct_io)
-		__field(int, has_refcount)
 	),
 	TP_fast_assign(
 		__entry->ino = ino;
 		__entry->saved_pos = saved_pos;
-		__entry->appending = appending;
 		__entry->count = count;
-		__entry->direct_io = direct_io ? *direct_io : -1;
-		__entry->has_refcount = has_refcount ? *has_refcount : -1;
 	),
-	TP_printk("%llu %llu %d %lu %d %d", __entry->ino,
-		  __entry->saved_pos, __entry->appending, __entry->count,
-		  __entry->direct_io, __entry->has_refcount)
+	TP_printk("%llu %llu %lu", __entry->ino,
+		  __entry->saved_pos, __entry->count)
 );
 
 DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 2de4c8a9340c..0b28d583b951 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1744,6 +1744,7 @@ static void ocfs2_inode_init_once(void *data)
 	spin_lock_init(&oi->ip_lock);
 	ocfs2_extent_map_init(&oi->vfs_inode);
 	INIT_LIST_HEAD(&oi->ip_io_markers);
+	INIT_LIST_HEAD(&oi->ip_unwritten_list);
 	oi->ip_dir_start_lookup = 0;
 	mutex_init(&oi->ip_unaligned_aio);
 	init_rwsem(&oi->ip_alloc_sem);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e2d46adb54b4..d5d41ab246c0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -70,6 +70,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		ptes >> 10,
 		pmds >> 10,
 		swap << (PAGE_SHIFT-10));
+	hugetlb_report_usage(m, mm);
 }
 
 unsigned long task_vsize(struct mm_struct *mm)
@@ -446,6 +447,7 @@ struct mem_size_stats {
 	unsigned long anonymous;
 	unsigned long anonymous_thp;
 	unsigned long swap;
+	unsigned long hugetlb;
 	u64 pss;
 	u64 swap_pss;
 };
@@ -625,12 +627,38 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 	seq_putc(m, '\n');
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
+				 unsigned long addr, unsigned long end,
+				 struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	struct page *page = NULL;
+
+	if (pte_present(*pte)) {
+		page = vm_normal_page(vma, addr, *pte);
+	} else if (is_swap_pte(*pte)) {
+		swp_entry_t swpent = pte_to_swp_entry(*pte);
+
+		if (is_migration_entry(swpent))
+			page = migration_entry_to_page(swpent);
+	}
+	if (page)
+		mss->hugetlb += huge_page_size(hstate_vma(vma));
+	return 0;
+}
+#endif /* HUGETLB_PAGE */
+
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	struct mm_walk smaps_walk = {
 		.pmd_entry = smaps_pte_range,
+#ifdef CONFIG_HUGETLB_PAGE
+		.hugetlb_entry = smaps_hugetlb_range,
+#endif
 		.mm = vma->vm_mm,
 		.private = &mss,
 	};
@@ -652,6 +680,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
+		   "HugetlbPages:   %8lu kB\n"
 		   "Swap:           %8lu kB\n"
 		   "SwapPss:        %8lu kB\n"
 		   "KernelPageSize: %8lu kB\n"
@@ -667,6 +696,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
 		   mss.anonymous_thp >> 10,
+		   mss.hugetlb >> 10,
 		   mss.swap >> 10,
 		   (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
 		   vma_kernel_pagesize(vma) >> 10,
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 634e676072cb..50311703135b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -467,8 +467,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * the fault_*wqh.
 	 */
 	spin_lock(&ctx->fault_pending_wqh.lock);
-	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, &range);
-	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range);
+	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
+	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
 	wake_up_poll(&ctx->fd_wqh, POLLHUP);
@@ -650,10 +650,10 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx,
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/* wake all in the range and autoremove */
 	if (waitqueue_active(&ctx->fault_pending_wqh))
-		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0,
+		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
 				     range);
 	if (waitqueue_active(&ctx->fault_wqh))
-		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, range);
+		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 }
 
@@ -1287,8 +1287,10 @@ static struct file *userfaultfd_file_create(int flags)
 
 	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
 				  O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
-	if (IS_ERR(file))
+	if (IS_ERR(file)) {
+		mmput(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
+	}
 out:
 	return file;
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 8b5ce7c5d9bb..f56cdcecc1c9 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -822,7 +822,6 @@ struct drm_device {
 
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
 	unsigned int num_crtcs;                  /**< Number of CRTCs on this device */
-	sigset_t sigmask;
 
 	struct {
 		int context;
diff --git a/include/linux/crc64_ecma.h b/include/linux/crc64_ecma.h
new file mode 100644
index 000000000000..bba7a4d692b3
--- /dev/null
+++ b/include/linux/crc64_ecma.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * 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 Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``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 Freescale Semiconductor 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.
+ */
+
+#ifndef __CRC64_ECMA_H_
+#define __CRC64_ECMA_H_
+
+#include <linux/types.h>
+
+
+#define CRC64_DEFAULT_INITVAL           0xFFFFFFFFFFFFFFFFULL
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * @pdata:	pointer to the data to compute checksum for.
+ * @nbytes:	number of bytes in data buffer.
+ * @seed:	CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed);
+
+#endif /* __CRC64_ECMA_H_ */
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ecb080d6ff42..412013b0bf2f 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
+extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, unsigned long addr);
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr);
@@ -58,6 +61,7 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 				     unsigned long address,
 				     enum page_check_address_pmd_flag flag,
 				     spinlock_t **ptl);
+extern int pmd_freeable(pmd_t pmd);
 
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5e35379f58a5..329b59811159 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -483,6 +483,25 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 #define hugepages_supported() (HPAGE_SHIFT != 0)
 #endif
 
+struct hugetlb_usage {
+	atomic_long_t count[HUGE_MAX_HSTATE];
+};
+
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm);
+void exit_hugetlb_mmap(struct mm_struct *mm);
+int hugetlb_fork(struct mm_struct *new, struct mm_struct *old);
+
+static inline void inc_hugetlb_count(struct mm_struct *mm, struct hstate *h)
+{
+	VM_BUG_ON_MM(!mm->hugetlb_usage, mm);
+	atomic_long_inc(&mm->hugetlb_usage->count[hstate_index(h)]);
+}
+
+static inline void dec_hugetlb_count(struct mm_struct *mm, struct hstate *h)
+{
+	VM_BUG_ON_MM(!mm->hugetlb_usage, mm);
+	atomic_long_dec(&mm->hugetlb_usage->count[hstate_index(h)]);
+}
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
@@ -519,6 +538,23 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 {
 	return &mm->page_table_lock;
 }
+
+static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
+{
+}
+
+static inline void exit_hugetlb_mmap(struct mm_struct *mm)
+{
+}
+
+static inline int hugetlb_fork(struct mm_struct *new, struct mm_struct *old)
+{
+	return 0;
+}
+
+static inline void dec_hugetlb_count(struct mm_struct *mm, struct hstate *h)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index bcc853eccc85..75e34b900748 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -32,7 +32,7 @@ static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
 
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return NULL;
-	return (struct hugetlb_cgroup *)page[2].lru.next;
+	return (struct hugetlb_cgroup *)page[2].private;
 }
 
 static inline
@@ -42,7 +42,7 @@ int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
 
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return -1;
-	page[2].lru.next = (void *)h_cg;
+	page[2].private	= (unsigned long)h_cg;
 	return 0;
 }
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5582410727cb..2c13f747ac2e 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -413,6 +413,8 @@ extern __printf(2, 3)
 char *kasprintf(gfp_t gfp, const char *fmt, ...);
 extern __printf(2, 0)
 char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
+extern __printf(2, 0)
+const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list args);
 
 extern __scanf(2, 3)
 int sscanf(const char *, const char *, ...);
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index d140b1e9faa7..2da38f093391 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -269,6 +269,8 @@ unsigned long paddr_vmcoreinfo_note(void);
 	vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
 #define VMCOREINFO_CONFIG(name) \
 	vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
+#define VMCOREINFO_PHYS_BASE(value) \
+	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index c518eb589260..24daf8fc4d7c 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -89,10 +89,6 @@ int memblock_add_range(struct memblock_type *type,
 		       phys_addr_t base, phys_addr_t size,
 		       int nid, unsigned long flags);
 
-int memblock_remove_range(struct memblock_type *type,
-			  phys_addr_t base,
-			  phys_addr_t size);
-
 void __next_mem_range(u64 *idx, int nid, ulong flags,
 		      struct memblock_type *type_a,
 		      struct memblock_type *type_b, phys_addr_t *out_start,
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ad800e62cb7a..7dd8d215ca7c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -402,24 +402,26 @@ static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
+void mem_cgroup_handle_over_high(void);
+
 void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 				struct task_struct *p);
 
 static inline void mem_cgroup_oom_enable(void)
 {
-	WARN_ON(current->memcg_oom.may_oom);
-	current->memcg_oom.may_oom = 1;
+	WARN_ON(current->memcg_may_oom);
+	current->memcg_may_oom = 1;
 }
 
 static inline void mem_cgroup_oom_disable(void)
 {
-	WARN_ON(!current->memcg_oom.may_oom);
-	current->memcg_oom.may_oom = 0;
+	WARN_ON(!current->memcg_may_oom);
+	current->memcg_may_oom = 0;
 }
 
 static inline bool task_in_memcg_oom(struct task_struct *p)
 {
-	return p->memcg_oom.memcg;
+	return p->memcg_in_oom;
 }
 
 bool mem_cgroup_oom_synchronize(bool wait);
@@ -621,6 +623,10 @@ static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 {
 }
 
+static inline void mem_cgroup_handle_over_high(void)
+{
+}
+
 static inline void mem_cgroup_oom_enable(void)
 {
 }
@@ -770,6 +776,17 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 		      unsigned long nr_pages);
 void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
 
+static inline bool __memcg_kmem_bypass(gfp_t gfp)
+{
+	if (!memcg_kmem_enabled())
+		return true;
+	if (gfp & __GFP_NOACCOUNT)
+		return true;
+	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+		return true;
+	return false;
+}
+
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
@@ -785,26 +802,8 @@ void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
 static inline bool
 memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 {
-	if (!memcg_kmem_enabled())
-		return true;
-
-	if (gfp & __GFP_NOACCOUNT)
+	if (__memcg_kmem_bypass(gfp))
 		return true;
-	/*
-	 * __GFP_NOFAIL allocations will move on even if charging is not
-	 * possible. Therefore we don't even try, and have this allocation
-	 * unaccounted. We could in theory charge it forcibly, but we hope
-	 * those allocations are rare, and won't be worth the trouble.
-	 */
-	if (gfp & __GFP_NOFAIL)
-		return true;
-	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
-		return true;
-
-	/* If the test is dying, just let it go. */
-	if (unlikely(fatal_signal_pending(current)))
-		return true;
-
 	return __memcg_kmem_newpage_charge(gfp, memcg, order);
 }
 
@@ -847,17 +846,8 @@ memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
 static __always_inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
-	if (!memcg_kmem_enabled())
-		return cachep;
-	if (gfp & __GFP_NOACCOUNT)
-		return cachep;
-	if (gfp & __GFP_NOFAIL)
+	if (__memcg_kmem_bypass(gfp))
 		return cachep;
-	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
-		return cachep;
-	if (unlikely(fatal_signal_pending(current)))
-		return cachep;
-
 	return __memcg_kmem_get_cache(cachep);
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 91c08f6f0dc9..82972d9d6ba5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -139,6 +139,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
+#define VM_LOCKONFAULT	0x00080000	/* Lock the pages covered when they are faulted in */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
@@ -202,6 +203,9 @@ extern unsigned int kobjsize(const void *objp);
 /* This mask defines which mm->def_flags a process can inherit its parent */
 #define VM_INIT_DEF_MASK	VM_NOHUGEPAGE
 
+/* This mask is used to clear all the VMA flags used by mlock */
+#define VM_LOCKED_CLEAR_MASK	(~(VM_LOCKED | VM_LOCKONFAULT))
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
@@ -426,46 +430,6 @@ static inline void compound_unlock_irqrestore(struct page *page,
 #endif
 }
 
-static inline struct page *compound_head_by_tail(struct page *tail)
-{
-	struct page *head = tail->first_page;
-
-	/*
-	 * page->first_page may be a dangling pointer to an old
-	 * compound page, so recheck that it is still a tail
-	 * page before returning.
-	 */
-	smp_rmb();
-	if (likely(PageTail(tail)))
-		return head;
-	return tail;
-}
-
-/*
- * Since either compound page could be dismantled asynchronously in THP
- * or we access asynchronously arbitrary positioned struct page, there
- * would be tail flag race. To handle this race, we should call
- * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
- */
-static inline struct page *compound_head(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return compound_head_by_tail(page);
-	return page;
-}
-
-/*
- * If we access compound page synchronously such as access to
- * allocated page, there is no need to handle tail flag race, so we can
- * check tail flag directly without any synchronization primitive.
- */
-static inline struct page *compound_head_fast(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return page->first_page;
-	return page;
-}
-
 /*
  * The atomic page->_mapcount, starts from -1: so that transitions
  * both from it and to it can be tracked, using atomic_inc_and_test
@@ -514,7 +478,7 @@ static inline void get_huge_page_tail(struct page *page)
 	VM_BUG_ON_PAGE(!PageTail(page), page);
 	VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
 	VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
-	if (compound_tail_refcounted(page->first_page))
+	if (compound_tail_refcounted(compound_head(page)))
 		atomic_inc(&page->_mapcount);
 }
 
@@ -537,13 +501,7 @@ static inline struct page *virt_to_head_page(const void *x)
 {
 	struct page *page = virt_to_page(x);
 
-	/*
-	 * We don't need to worry about synchronization of tail flag
-	 * when we call virt_to_head_page() since it is only called for
-	 * already allocated page and this page won't be freed until
-	 * this virt_to_head_page() is finished. So use _fast variant.
-	 */
-	return compound_head_fast(page);
+	return compound_head(page);
 }
 
 /*
@@ -564,28 +522,42 @@ int split_free_page(struct page *page);
 /*
  * Compound pages have a destructor function.  Provide a
  * prototype for that function and accessor functions.
- * These are _only_ valid on the head of a PG_compound page.
+ * These are _only_ valid on the head of a compound page.
  */
+typedef void compound_page_dtor(struct page *);
+
+/* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */
+enum compound_dtor_id {
+	NULL_COMPOUND_DTOR,
+	COMPOUND_PAGE_DTOR,
+#ifdef CONFIG_HUGETLB_PAGE
+	HUGETLB_PAGE_DTOR,
+#endif
+	NR_COMPOUND_DTORS,
+};
+extern compound_page_dtor * const compound_page_dtors[];
 
 static inline void set_compound_page_dtor(struct page *page,
-						compound_page_dtor *dtor)
+		enum compound_dtor_id compound_dtor)
 {
-	page[1].compound_dtor = dtor;
+	VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page);
+	page[1].compound_dtor = compound_dtor;
 }
 
 static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
 {
-	return page[1].compound_dtor;
+	VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page);
+	return compound_page_dtors[page[1].compound_dtor];
 }
 
-static inline int compound_order(struct page *page)
+static inline unsigned int compound_order(struct page *page)
 {
 	if (!PageHead(page))
 		return 0;
 	return page[1].compound_order;
 }
 
-static inline void set_compound_order(struct page *page, unsigned long order)
+static inline void set_compound_order(struct page *page, unsigned int order)
 {
 	page[1].compound_order = order;
 }
@@ -1547,8 +1519,7 @@ static inline bool ptlock_init(struct page *page)
 	 * with 0. Make sure nobody took it in use in between.
 	 *
 	 * It can happen if arch try to use slab for page table allocation:
-	 * slab code uses page->slab_cache and page->first_page (for tail
-	 * pages), which share storage with page->ptl.
+	 * slab code uses page->slab_cache, which share storage with page->ptl.
 	 */
 	VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page);
 	if (!ptlock_alloc(page))
@@ -1816,7 +1787,8 @@ extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 
 extern __printf(3, 4)
-void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
+void warn_alloc_failed(gfp_t gfp_mask, unsigned int order,
+		const char *fmt, ...);
 
 extern void setup_per_cpu_pageset(void);
 
@@ -2015,8 +1987,6 @@ void page_cache_async_readahead(struct address_space *mapping,
 				pgoff_t offset,
 				unsigned long size);
 
-unsigned long max_sane_readahead(unsigned long nr);
-
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
 
@@ -2116,6 +2086,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
 #define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
+#define FOLL_MLOCK	0x1000	/* lock present pages */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3d6baa7d4534..b328d86d8ec3 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -28,8 +28,6 @@ struct mem_cgroup;
 		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
 #define ALLOC_SPLIT_PTLOCKS	(SPINLOCK_SIZE > BITS_PER_LONG/8)
 
-typedef void compound_page_dtor(struct page *);
-
 /*
  * Each physical page in the system has a struct page associated with
  * it to keep track of whatever it is we are using the page for at the
@@ -113,7 +111,13 @@ struct page {
 		};
 	};
 
-	/* Third double word block */
+	/*
+	 * Third double word block
+	 *
+	 * WARNING: bit 0 of the first word encode PageTail(). That means
+	 * the rest users of the storage space MUST NOT use the bit to
+	 * avoid collision and false-positive PageTail().
+	 */
 	union {
 		struct list_head lru;	/* Pageout list, eg. active_list
 					 * protected by zone->lru_lock !
@@ -131,18 +135,37 @@ struct page {
 #endif
 		};
 
-		struct slab *slab_page; /* slab fields */
 		struct rcu_head rcu_head;	/* Used by SLAB
 						 * when destroying via RCU
 						 */
-		/* First tail page of compound page */
+		/* Tail pages of compound page */
 		struct {
-			compound_page_dtor *compound_dtor;
-			unsigned long compound_order;
+			unsigned long compound_head; /* If bit zero is set */
+
+			/* First tail page only */
+#ifdef CONFIG_64BIT
+			/*
+			 * On 64 bit system we have enough space in struct page
+			 * to encode compound_dtor and compound_order with
+			 * unsigned int. It can help compiler generate better or
+			 * smaller code on some archtectures.
+			 */
+			unsigned int compound_dtor;
+			unsigned int compound_order;
+#else
+			unsigned short int compound_dtor;
+			unsigned short int compound_order;
+#endif
 		};
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
-		pgtable_t pmd_huge_pte; /* protected by page->ptl */
+		struct {
+			unsigned long __pad;	/* do not overlay pmd_huge_pte
+						 * with compound_head to avoid
+						 * possible bit 0 collision.
+						 */
+			pgtable_t pmd_huge_pte; /* protected by page->ptl */
+		};
 #endif
 	};
 
@@ -163,7 +186,6 @@ struct page {
 #endif
 #endif
 		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
-		struct page *first_page;	/* Compound tail pages */
 	};
 
 #ifdef CONFIG_MEMCG
@@ -366,6 +388,10 @@ struct mm_rss_stat {
 	atomic_long_t count[NR_MM_COUNTERS];
 };
 
+#ifdef CONFIG_HUGETLB_PAGE
+struct hugetlb_usage;
+#endif
+
 struct kioctx_table;
 struct mm_struct {
 	struct vm_area_struct *mmap;		/* list of VMAs */
@@ -486,6 +512,9 @@ struct mm_struct {
 	/* address of the bounds directory */
 	void __user *bd_addr;
 #endif
+#ifdef CONFIG_HUGETLB_PAGE
+	struct hugetlb_usage *hugetlb_usage;
+#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d94347737292..2d7e660cdefe 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -823,8 +823,7 @@ enum memmap_context {
 	MEMMAP_HOTPLUG,
 };
 extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
-				     unsigned long size,
-				     enum memmap_context context);
+				     unsigned long size);
 
 extern void lruvec_init(struct lruvec *lruvec);
 
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index c12f2147c350..52666d90ca94 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -386,6 +386,7 @@ extern int param_get_ullong(char *buffer, const struct kernel_param *kp);
 extern const struct kernel_param_ops param_ops_charp;
 extern int param_set_charp(const char *val, const struct kernel_param *kp);
 extern int param_get_charp(char *buffer, const struct kernel_param *kp);
+extern void param_free_charp(void *arg);
 #define param_check_charp(name, p) __param_check(name, p, char *)
 
 /* We used to allow int as well as bool.  We're taking that away! */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 416509e26d6d..ab1a0e9c5087 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -86,12 +86,7 @@ enum pageflags {
 	PG_private,		/* If pagecache, has fs-private data */
 	PG_private_2,		/* If pagecache, has fs aux data */
 	PG_writeback,		/* Page is under writeback */
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
 	PG_head,		/* A head page */
-	PG_tail,		/* A tail page */
-#else
-	PG_compound,		/* A compound page */
-#endif
 	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
@@ -138,49 +133,68 @@ enum pageflags {
 
 #ifndef __GENERATING_BOUNDS_H
 
+/* Page flags policies wrt compound pages */
+#define PF_ANY(page, enforce)	page
+#define PF_HEAD(page, enforce)	compound_head(page)
+#define PF_NO_TAIL(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageTail(page), page);		\
+		else							\
+			page = compound_head(page);			\
+		page;})
+#define PF_NO_COMPOUND(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageCompound(page), page);	\
+		page;})
+
 /*
  * Macros to create function definitions for page flags
  */
-#define TESTPAGEFLAG(uname, lname)					\
-static inline int Page##uname(const struct page *page)			\
-			{ return test_bit(PG_##lname, &page->flags); }
+#define TESTPAGEFLAG(uname, lname, policy)				\
+static inline int Page##uname(struct page *page)			\
+	{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
 
-#define SETPAGEFLAG(uname, lname)					\
+#define SETPAGEFLAG(uname, lname, policy)				\
 static inline void SetPage##uname(struct page *page)			\
-			{ set_bit(PG_##lname, &page->flags); }
+	{ set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define CLEARPAGEFLAG(uname, lname)					\
+#define CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void ClearPage##uname(struct page *page)			\
-			{ clear_bit(PG_##lname, &page->flags); }
+	{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __SETPAGEFLAG(uname, lname)					\
+#define __SETPAGEFLAG(uname, lname, policy)				\
 static inline void __SetPage##uname(struct page *page)			\
-			{ __set_bit(PG_##lname, &page->flags); }
+	{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __CLEARPAGEFLAG(uname, lname)					\
+#define __CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void __ClearPage##uname(struct page *page)		\
-			{ __clear_bit(PG_##lname, &page->flags); }
+	{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTSETFLAG(uname, lname)					\
+#define TESTSETFLAG(uname, lname, policy)				\
 static inline int TestSetPage##uname(struct page *page)			\
-		{ return test_and_set_bit(PG_##lname, &page->flags); }
+	{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTCLEARFLAG(uname, lname)					\
+#define TESTCLEARFLAG(uname, lname, policy)				\
 static inline int TestClearPage##uname(struct page *page)		\
-		{ return test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __TESTCLEARFLAG(uname, lname)					\
+#define __TESTCLEARFLAG(uname, lname, policy)				\
 static inline int __TestClearPage##uname(struct page *page)		\
-		{ return __test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return __test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname)
+#define PAGEFLAG(uname, lname, policy)					\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	SETPAGEFLAG(uname, lname, policy)				\
+	CLEARPAGEFLAG(uname, lname, policy)
 
-#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	__SETPAGEFLAG(uname, lname)  __CLEARPAGEFLAG(uname, lname)
+#define __PAGEFLAG(uname, lname, policy)				\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	__SETPAGEFLAG(uname, lname, policy)				\
+	__CLEARPAGEFLAG(uname, lname, policy)
 
-#define TESTSCFLAG(uname, lname)					\
-	TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
+#define TESTSCFLAG(uname, lname, policy)				\
+	TESTSETFLAG(uname, lname, policy)				\
+	TESTCLEARFLAG(uname, lname, policy)
 
 #define TESTPAGEFLAG_FALSE(uname)					\
 static inline int Page##uname(const struct page *page) { return 0; }
@@ -209,47 +223,61 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; }
 #define TESTSCFLAG_FALSE(uname)						\
 	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
 
-struct page;	/* forward declaration */
-
-TESTPAGEFLAG(Locked, locked)
-PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error)
-PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
-	__SETPAGEFLAG(Referenced, referenced)
-PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
-PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
-PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
-	TESTCLEARFLAG(Active, active)
-__PAGEFLAG(Slab, slab)
-PAGEFLAG(Checked, checked)		/* Used by some filesystems */
-PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
-PAGEFLAG(SavePinned, savepinned);			/* Xen */
-PAGEFLAG(Foreign, foreign);				/* Xen */
-PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
-	__SETPAGEFLAG(SwapBacked, swapbacked)
-
-__PAGEFLAG(SlobFree, slob_free)
+/* Forward declarations */
+struct page;
+static inline int PageCompound(struct page *page);
+static inline int PageTail(struct page *page);
+static struct page *compound_head(struct page *page);
+
+__PAGEFLAG(Locked, locked, PF_NO_TAIL)
+PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
+PAGEFLAG(Referenced, referenced, PF_HEAD)
+	TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
+	__SETPAGEFLAG(Referenced, referenced, PF_HEAD)
+PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
+	__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
+PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
+PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
+	TESTCLEARFLAG(Active, active, PF_HEAD)
+__PAGEFLAG(Slab, slab, PF_NO_TAIL)
+__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL)
+PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */
+
+/* Xen */
+PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND)
+PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND)
+PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND)
+
+PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
+	__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
+PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
+	__CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
+	__SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
 
 /*
  * Private page markings that may be used by the filesystem that owns the page
  * for its own purposes.
  * - PG_private and PG_private_2 cause releasepage() and co to be invoked
  */
-PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
-	__CLEARPAGEFLAG(Private, private)
-PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
-PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY)
+	__CLEARPAGEFLAG(Private, private, PF_ANY)
+PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
+PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
+	TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
 
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
-TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-PAGEFLAG(MappedToDisk, mappedtodisk)
+TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND)
+	TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND)
+PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_COMPOUND)
 
 /* PG_readahead is only used for reads; PG_reclaim is only for writes */
-PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
-PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim)
+PAGEFLAG(Reclaim, reclaim, PF_NO_COMPOUND)
+	TESTCLEARFLAG(Reclaim, reclaim, PF_NO_COMPOUND)
+PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
+	TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND)
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -262,31 +290,33 @@ PAGEFLAG_FALSE(HighMem)
 #endif
 
 #ifdef CONFIG_SWAP
-PAGEFLAG(SwapCache, swapcache)
+PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
 
-PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
-	TESTCLEARFLAG(Unevictable, unevictable)
+PAGEFLAG(Unevictable, unevictable, PF_HEAD)
+	__CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD)
+	TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD)
 
 #ifdef CONFIG_MMU
-PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked)
-	TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked)
+PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
+	TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL)
+	__TESTCLEARFLAG(Mlocked, mlocked, PF_NO_TAIL)
 #else
 PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
 	TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
 #endif
 
 #ifdef CONFIG_ARCH_USES_PG_UNCACHED
-PAGEFLAG(Uncached, uncached)
+PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(Uncached)
 #endif
 
 #ifdef CONFIG_MEMORY_FAILURE
-PAGEFLAG(HWPoison, hwpoison)
-TESTSCFLAG(HWPoison, hwpoison)
+PAGEFLAG(HWPoison, hwpoison, PF_ANY)
+TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 #else
 PAGEFLAG_FALSE(HWPoison)
@@ -294,10 +324,10 @@ PAGEFLAG_FALSE(HWPoison)
 #endif
 
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
-TESTPAGEFLAG(Young, young)
-SETPAGEFLAG(Young, young)
-TESTCLEARFLAG(Young, young)
-PAGEFLAG(Idle, idle)
+TESTPAGEFLAG(Young, young, PF_ANY)
+SETPAGEFLAG(Young, young, PF_ANY)
+TESTCLEARFLAG(Young, young, PF_ANY)
+PAGEFLAG(Idle, idle, PF_ANY)
 #endif
 
 /*
@@ -322,6 +352,7 @@ PAGEFLAG(Idle, idle)
 
 static inline int PageAnon(struct page *page)
 {
+	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
 }
 
@@ -334,6 +365,7 @@ static inline int PageAnon(struct page *page)
  */
 static inline int PageKsm(struct page *page)
 {
+	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
 				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
 }
@@ -345,8 +377,9 @@ u64 stable_page_flags(struct page *page);
 
 static inline int PageUptodate(struct page *page)
 {
-	int ret = test_bit(PG_uptodate, &(page)->flags);
-
+	int ret;
+	page = compound_head(page);
+	ret = test_bit(PG_uptodate, &(page)->flags);
 	/*
 	 * Must ensure that the data we read out of the page is loaded
 	 * _after_ we've loaded page->flags to check for PageUptodate.
@@ -363,22 +396,24 @@ static inline int PageUptodate(struct page *page)
 
 static inline void __SetPageUptodate(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	smp_wmb();
-	__set_bit(PG_uptodate, &(page)->flags);
+	__set_bit(PG_uptodate, &page->flags);
 }
 
 static inline void SetPageUptodate(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	/*
 	 * Memory barrier must be issued before setting the PG_uptodate bit,
 	 * so that all previous stores issued in order to bring the page
 	 * uptodate are actually visible before PageUptodate becomes true.
 	 */
 	smp_wmb();
-	set_bit(PG_uptodate, &(page)->flags);
+	set_bit(PG_uptodate, &page->flags);
 }
 
-CLEARPAGEFLAG(Uptodate, uptodate)
+CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
 
 int test_clear_page_writeback(struct page *page);
 int __test_set_page_writeback(struct page *page, bool keep_write);
@@ -398,85 +433,46 @@ 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
- * flags for PageHead() and PageTail() checks of compound pages so that bit
- * tests can be used in performance sensitive paths. PageCompound is
- * generally not used in hot code paths except arch/powerpc/mm/init_64.c
- * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
- * and avoid handling those in real mode.
- */
-__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
-__PAGEFLAG(Tail, tail)
-
-static inline int PageCompound(struct page *page)
-{
-	return page->flags & ((1L << PG_head) | (1L << PG_tail));
+__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
 
-}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline void ClearPageCompound(struct page *page)
+static inline int PageTail(struct page *page)
 {
-	BUG_ON(!PageHead(page));
-	ClearPageHead(page);
+	return READ_ONCE(page->compound_head) & 1;
 }
-#endif
-
-#define PG_head_mask ((1L << PG_head))
 
-#else
-/*
- * Reduce page flag use as much as possible by overlapping
- * compound page flags with the flags used for page cache pages. Possible
- * because PageCompound is always set for compound pages and not for
- * pages on the LRU and/or pagecache.
- */
-TESTPAGEFLAG(Compound, compound)
-__SETPAGEFLAG(Head, compound)  __CLEARPAGEFLAG(Head, compound)
-
-/*
- * PG_reclaim is used in combination with PG_compound to mark the
- * head and tail of a compound page. This saves one page flag
- * but makes it impossible to use compound pages for the page cache.
- * The PG_reclaim bit would have to be used for reclaim or readahead
- * if compound pages enter the page cache.
- *
- * PG_compound & PG_reclaim	=> Tail page
- * PG_compound & ~PG_reclaim	=> Head page
- */
-#define PG_head_mask ((1L << PG_compound))
-#define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim))
-
-static inline int PageHead(struct page *page)
+static inline void set_compound_head(struct page *page, struct page *head)
 {
-	return ((page->flags & PG_head_tail_mask) == PG_head_mask);
+	WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
 }
 
-static inline int PageTail(struct page *page)
+static inline void clear_compound_head(struct page *page)
 {
-	return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask);
+	WRITE_ONCE(page->compound_head, 0);
 }
 
-static inline void __SetPageTail(struct page *page)
+static inline struct page *compound_head(struct page *page)
 {
-	page->flags |= PG_head_tail_mask;
+	unsigned long head = READ_ONCE(page->compound_head);
+
+	if (unlikely(head & 1))
+		return (struct page *) (head - 1);
+	return page;
 }
 
-static inline void __ClearPageTail(struct page *page)
+static inline int PageCompound(struct page *page)
 {
-	page->flags &= ~PG_head_tail_mask;
-}
+	return PageHead(page) || PageTail(page);
 
+}
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline void ClearPageCompound(struct page *page)
 {
-	BUG_ON((page->flags & PG_head_tail_mask) != (1 << PG_compound));
-	clear_bit(PG_compound, &page->flags);
+	BUG_ON(!PageHead(page));
+	ClearPageHead(page);
 }
 #endif
 
-#endif /* !PAGEFLAGS_EXTENDED */
+#define PG_head_mask ((1L << PG_head))
 
 #ifdef CONFIG_HUGETLB_PAGE
 int PageHuge(struct page *page);
@@ -529,21 +525,9 @@ static inline int PageTransTail(struct page *page)
 }
 
 #else
-
-static inline int PageTransHuge(struct page *page)
-{
-	return 0;
-}
-
-static inline int PageTransCompound(struct page *page)
-{
-	return 0;
-}
-
-static inline int PageTransTail(struct page *page)
-{
-	return 0;
-}
+TESTPAGEFLAG_FALSE(TransHuge)
+TESTPAGEFLAG_FALSE(TransCompound)
+TESTPAGEFLAG_FALSE(TransTail)
 #endif
 
 /*
@@ -670,6 +654,10 @@ static inline int page_has_private(struct page *page)
 	return !!(page->flags & PAGE_FLAGS_PRIVATE);
 }
 
+#undef PF_ANY
+#undef PF_HEAD
+#undef PF_NO_TAIL
+#undef PF_NO_COMPOUND
 #endif /* !__GENERATING_BOUNDS_H */
 
 #endif	/* PAGE_FLAGS_H */
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 2baeee12f48e..e942558b3585 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -44,7 +44,7 @@ enum pageblock_bits {
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
 /* Huge page sizes are variable */
-extern int pageblock_order;
+extern unsigned int pageblock_order;
 
 #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a6c78e00ea96..3e95fb6a77af 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -426,18 +426,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
 
-static inline void __set_page_locked(struct page *page)
-{
-	__set_bit(PG_locked, &page->flags);
-}
-
-static inline void __clear_page_locked(struct page *page)
-{
-	__clear_bit(PG_locked, &page->flags);
-}
-
 static inline int trylock_page(struct page *page)
 {
+	page = compound_head(page);
 	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
 }
 
@@ -490,9 +481,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page,
 
 static inline int wait_on_page_locked_killable(struct page *page)
 {
-	if (PageLocked(page))
-		return wait_on_page_bit_killable(page, PG_locked);
-	return 0;
+	if (!PageLocked(page))
+		return 0;
+	return wait_on_page_bit_killable(compound_head(page), PG_locked);
 }
 
 extern wait_queue_head_t *page_waitqueue(struct page *page);
@@ -511,7 +502,7 @@ static inline void wake_up_page(struct page *page, int bit)
 static inline void wait_on_page_locked(struct page *page)
 {
 	if (PageLocked(page))
-		wait_on_page_bit(page, PG_locked);
+		wait_on_page_bit(compound_head(page), PG_locked);
 }
 
 /* 
@@ -657,17 +648,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
- * the page is new, so we can just run __set_page_locked() against it.
+ * the page is new, so we can just run __SetPageLocked() against it.
  */
 static inline int add_to_page_cache(struct page *page,
 		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
 {
 	int error;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
 	if (unlikely(error))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	return error;
 }
 
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 317e16de09e5..4a27153574e2 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -27,11 +27,15 @@
  * Magic number "tsta" to indicate a static timer initializer
  * for the object debugging code.
  */
-#define TIMER_ENTRY_STATIC	((void *) 0x74737461)
+#define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
 
 /********** mm/debug-pagealloc.c **********/
 #define PAGE_POISON 0xaa
 
+/********** mm/page_alloc.c ************/
+
+#define TAIL_MAPPING	((void *) 0x400 + POISON_POINTER_DELTA)
+
 /********** mm/slab.c **********/
 /*
  * Magic nums for obj red zoning.
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 29446aeef36e..0860336c6c40 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -85,6 +85,7 @@ enum ttu_flags {
 	TTU_UNMAP = 1,			/* unmap mode */
 	TTU_MIGRATION = 2,		/* migration mode */
 	TTU_MUNLOCK = 4,		/* munlock mode */
+	TTU_FREE = 8,			/* free mode */
 
 	TTU_IGNORE_MLOCK = (1 << 8),	/* ignore mlock */
 	TTU_IGNORE_ACCESS = (1 << 9),	/* don't age */
@@ -186,7 +187,8 @@ static inline void page_dup_rmap(struct page *page)
  * Called from mm/vmscan.c to handle paging out
  */
 int page_referenced(struct page *, int is_locked,
-			struct mem_cgroup *memcg, unsigned long *vm_flags);
+			struct mem_cgroup *memcg, unsigned long *vm_flags,
+			int *is_pte_dirty);
 
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 
@@ -263,9 +265,12 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
 
 static inline int page_referenced(struct page *page, int is_locked,
 				  struct mem_cgroup *memcg,
-				  unsigned long *vm_flags)
+				  unsigned long *vm_flags,
+				  int *is_pte_dirty)
 {
 	*vm_flags = 0;
+	if (is_pte_dirty)
+		*is_pte_dirty = 0;
 	return 0;
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bd38b3ee9e83..6503472e57d4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1451,7 +1451,9 @@ struct task_struct {
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
 	unsigned sched_migrated:1;
-
+#ifdef CONFIG_MEMCG
+	unsigned memcg_may_oom:1;
+#endif
 #ifdef CONFIG_MEMCG_KMEM
 	unsigned memcg_kmem_skip_account:1;
 #endif
@@ -1558,9 +1560,7 @@ struct task_struct {
 
 	unsigned long sas_ss_sp;
 	size_t sas_ss_size;
-	int (*notifier)(void *priv);
-	void *notifier_data;
-	sigset_t *notifier_mask;
+
 	struct callback_head *task_works;
 
 	struct audit_context *audit_context;
@@ -1782,12 +1782,12 @@ struct task_struct {
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_MEMCG
-	struct memcg_oom_info {
-		struct mem_cgroup *memcg;
-		gfp_t gfp_mask;
-		int order;
-		unsigned int may_oom:1;
-	} memcg_oom;
+	struct mem_cgroup *memcg_in_oom;
+	gfp_t memcg_oom_gfp_mask;
+	int memcg_oom_order;
+
+	/* number of pages to reclaim on returning to userland */
+	unsigned int memcg_nr_pages_over_high;
 #endif
 #ifdef CONFIG_UPROBES
 	struct uprobe_task *utask;
@@ -2464,9 +2464,6 @@ static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, s
 	return ret;
 }
 
-extern void block_all_signals(int (*notifier)(void *priv), void *priv,
-			      sigset_t *mask);
-extern void unblock_all_signals(void);
 extern void release_task(struct task_struct * p);
 extern int send_sig_info(int, struct siginfo *, struct task_struct *);
 extern int force_sigsegv(int, struct task_struct *);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 7e37d448ed91..7c82e3b307a3 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -111,7 +111,7 @@ struct mem_cgroup;
  * struct kmem_cache related prototypes
  */
 void __init kmem_cache_init(void);
-int slab_is_available(void);
+bool slab_is_available(void);
 
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
diff --git a/include/linux/string.h b/include/linux/string.h
index a8d90db9c4b0..d5dfe3e75572 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -118,6 +118,7 @@ extern void kfree_const(const void *x);
 extern char *kstrdup(const char *s, gfp_t gfp);
 extern const char *kstrdup_const(const char *s, gfp_t gfp);
 extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
+extern char *kstrimdup(const char *s, gfp_t gfp);
 extern void *kmemdup(const void *src, size_t len, gfp_t gfp);
 
 extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7ba7dccaf0e7..b0f9d6a7a799 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -154,7 +154,7 @@ enum {
 	SWP_SCANNING	= (1 << 10),	/* refcount in scan_swap_map */
 };
 
-#define SWAP_CLUSTER_MAX 32UL
+#define SWAP_CLUSTER_MAX 256UL
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
 /*
@@ -308,6 +308,7 @@ extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_file_page(struct page *page);
+extern void deactivate_page(struct page *page);
 extern void swap_setup(void);
 
 extern void add_page_to_unevictable_list(struct page *page);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a460e2ef2843..a156b82dd14c 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -887,4 +887,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 
 asmlinkage long sys_membarrier(int cmd, int flags);
 
+asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
+
 #endif
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 84d497297c5f..26c152122a42 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -50,6 +50,7 @@
 #include <linux/ptrace.h>
 #include <linux/security.h>
 #include <linux/task_work.h>
+#include <linux/memcontrol.h>
 struct linux_binprm;
 
 /*
@@ -188,6 +189,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	smp_mb__after_atomic();
 	if (unlikely(current->task_works))
 		task_work_run();
+
+	mem_cgroup_handle_over_high();
 }
 
 #endif	/* <linux/tracehook.h> */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d6f2c2c5b043..558129af828a 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -75,36 +75,6 @@ static inline unsigned long __copy_from_user_nocache(void *to,
 
 #endif		/* ARCH_HAS_NOCACHE_UACCESS */
 
-/**
- * probe_kernel_address(): safely attempt to read from a location
- * @addr: address to read from - its type is type typeof(retval)*
- * @retval: read into this variable
- *
- * Safely read from address @addr into variable @revtal.  If a kernel fault
- * happens, handle that and return -EFAULT.
- * We ensure that the __get_user() is executed in atomic context so that
- * do_page_fault() doesn't attempt to take mmap_sem.  This makes
- * probe_kernel_address() suitable for use within regions where the caller
- * already holds mmap_sem, or other locks which nest inside mmap_sem.
- * This must be a macro because __get_user() needs to know the types of the
- * args.
- *
- * We don't include enough header files to be able to do the set_fs().  We
- * require that the probe_kernel_address() caller will do that.
- */
-#define probe_kernel_address(addr, retval)		\
-	({						\
-		long ret;				\
-		mm_segment_t old_fs = get_fs();		\
-							\
-		set_fs(KERNEL_DS);			\
-		pagefault_disable();			\
-		ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval));		\
-		pagefault_enable();			\
-		set_fs(old_fs);				\
-		ret;					\
-	})
-
 /*
  * probe_kernel_read(): safely attempt to read from a location
  * @dst: pointer to the buffer that shall take the data
@@ -131,4 +101,14 @@ extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size
 
 extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 
+/**
+ * probe_kernel_address(): safely attempt to read from a location
+ * @addr: address to read from
+ * @retval: read into this variable
+ *
+ * Returns 0 on success, or -EFAULT.
+ */
+#define probe_kernel_address(addr, retval)		\
+	probe_kernel_read(&retval, addr, sizeof(retval))
+
 #endif		/* __LINUX_UACCESS_H__ */
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 9246d32dc973..2b1cef88b827 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
+		PGLAZYFREED,
 		FOR_ALL_ZONES(PGREFILL),
 		FOR_ALL_ZONES(PGSTEAL_KSWAPD),
 		FOR_ALL_ZONES(PGSTEAL_DIRECT),
diff --git a/include/linux/wait.h b/include/linux/wait.h
index d3d077228d4c..1e1bf9f963a9 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 
 typedef int wait_bit_action_f(struct wait_bit_key *);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
-			  void *key);
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
@@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 #define wake_up_poll(x, m)						\
 	__wake_up(x, TASK_NORMAL, 1, (void *) (m))
 #define wake_up_locked_poll(x, m)					\
-	__wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m))
+	__wake_up_locked_key((x), TASK_NORMAL, (void *) (m))
 #define wake_up_interruptible_poll(x, m)				\
 	__wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m))
 #define wake_up_interruptible_sync_poll(x, m)				\
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index 42f8ec992452..2e97b7707dff 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -38,10 +38,10 @@ enum zpool_mapmode {
 
 bool zpool_has_pool(char *type);
 
-struct zpool *zpool_create_pool(char *type, char *name,
+struct zpool *zpool_create_pool(const char *type, const char *name,
 			gfp_t gfp, const struct zpool_ops *ops);
 
-char *zpool_get_type(struct zpool *pool);
+const char *zpool_get_type(struct zpool *pool);
 
 void zpool_destroy_pool(struct zpool *pool);
 
@@ -83,7 +83,9 @@ struct zpool_driver {
 	atomic_t refcount;
 	struct list_head list;
 
-	void *(*create)(char *name, gfp_t gfp, const struct zpool_ops *ops,
+	void *(*create)(const char *name,
+			gfp_t gfp,
+			const struct zpool_ops *ops,
 			struct zpool *zpool);
 	void (*destroy)(void *pool);
 
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 6398dfae53f1..34eb16098a33 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -41,7 +41,7 @@ struct zs_pool_stats {
 
 struct zs_pool;
 
-struct zs_pool *zs_create_pool(char *name, gfp_t flags);
+struct zs_pool *zs_create_pool(const char *name, gfp_t flags);
 void zs_destroy_pool(struct zs_pool *pool);
 
 unsigned long zs_malloc(struct zs_pool *pool, size_t size);
diff --git a/include/linux/zutil.h b/include/linux/zutil.h
index 6adfa9a6ffe9..663689521759 100644
--- a/include/linux/zutil.h
+++ b/include/linux/zutil.h
@@ -68,10 +68,10 @@ typedef uLong (*check_func) (uLong check, const Byte *buf,
    An Adler-32 checksum is almost as reliable as a CRC32 but can be computed
    much faster. Usage example:
 
-     uLong adler = adler32(0L, NULL, 0);
+     uLong adler = zlib_adler32(0L, NULL, 0);
 
      while (read_buffer(buffer, length) != EOF) {
-       adler = adler32(adler, buffer, length);
+       adler = zlib_adler32(adler, buffer, length);
      }
      if (adler != original_adler) error();
 */
diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
new file mode 100644
index 000000000000..1efc7f1dc9bd
--- /dev/null
+++ b/include/trace/events/huge_memory.h
@@ -0,0 +1,165 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM huge_memory
+
+#if !defined(__HUGE_MEMORY_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __HUGE_MEMORY_H
+
+#include  <linux/tracepoint.h>
+
+#include <trace/events/gfpflags.h>
+
+#define SCAN_STATUS							\
+	EM( SCAN_FAIL,			"failed")			\
+	EM( SCAN_SUCCEED,		"succeeded")			\
+	EM( SCAN_PMD_NULL,		"pmd_null")			\
+	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
+	EM( SCAN_PTE_NON_PRESENT,	"pte_non_present")		\
+	EM( SCAN_PAGE_RO,		"no_writable_page")		\
+	EM( SCAN_NO_REFERENCED_PAGE,	"no_referenced_page")		\
+	EM( SCAN_PAGE_NULL,		"page_null")			\
+	EM( SCAN_SCAN_ABORT,		"scan_aborted")			\
+	EM( SCAN_PAGE_COUNT,		"not_suitable_page_count")	\
+	EM( SCAN_PAGE_LRU,		"page_not_in_lru")		\
+	EM( SCAN_PAGE_LOCK,		"page_locked")			\
+	EM( SCAN_PAGE_ANON,		"page_not_anon")		\
+	EM( SCAN_ANY_PROCESS,		"no_process_for_page")		\
+	EM( SCAN_VMA_NULL,		"vma_null")			\
+	EM( SCAN_VMA_CHECK,		"vma_check_failed")		\
+	EM( SCAN_ADDRESS_RANGE,		"not_suitable_address_range")	\
+	EM( SCAN_SWAP_CACHE_PAGE,	"page_swap_cache")		\
+	EM( SCAN_DEL_PAGE_LRU,		"could_not_delete_page_from_lru")\
+	EM( SCAN_ALLOC_HUGE_PAGE_FAIL,	"alloc_huge_page_failed")	\
+	EM( SCAN_CGROUP_CHARGE_FAIL,	"ccgroup_charge_failed")	\
+	EMe( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")
+
+#undef EM
+#undef EMe
+#define EM(a, b)	TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+SCAN_STATUS
+
+#undef EM
+#undef EMe
+#define EM(a, b)	{a, b},
+#define EMe(a, b)	{a, b}
+
+TRACE_EVENT(mm_khugepaged_scan_pmd,
+
+	TP_PROTO(struct mm_struct *mm, unsigned long pfn, bool writable,
+		 bool referenced, int none_or_zero, int status, int unmapped),
+
+	TP_ARGS(mm, pfn, writable, referenced, none_or_zero, status, unmapped),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__field(unsigned long, pfn)
+		__field(bool, writable)
+		__field(bool, referenced)
+		__field(int, none_or_zero)
+		__field(int, status)
+		__field(int, unmapped)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__entry->pfn = pfn;
+		__entry->writable = writable;
+		__entry->referenced = referenced;
+		__entry->none_or_zero = none_or_zero;
+		__entry->status = status;
+		__entry->unmapped = unmapped;
+	),
+
+	TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s, unmapped=%d",
+		__entry->mm,
+		__entry->pfn,
+		__entry->writable,
+		__entry->referenced,
+		__entry->none_or_zero,
+		__print_symbolic(__entry->status, SCAN_STATUS),
+		__entry->unmapped)
+);
+
+TRACE_EVENT(mm_collapse_huge_page,
+
+	TP_PROTO(struct mm_struct *mm, int isolated, int status),
+
+	TP_ARGS(mm, isolated, status),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__field(int, isolated)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__entry->isolated = isolated;
+		__entry->status = status;
+	),
+
+	TP_printk("mm=%p, isolated=%d, status=%s",
+		__entry->mm,
+		__entry->isolated,
+		__print_symbolic(__entry->status, SCAN_STATUS))
+);
+
+TRACE_EVENT(mm_collapse_huge_page_isolate,
+
+	TP_PROTO(unsigned long pfn, int none_or_zero,
+		 bool referenced, bool  writable, int status),
+
+	TP_ARGS(pfn, none_or_zero, referenced, writable, status),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, pfn)
+		__field(int, none_or_zero)
+		__field(bool, referenced)
+		__field(bool, writable)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->pfn = pfn;
+		__entry->none_or_zero = none_or_zero;
+		__entry->referenced = referenced;
+		__entry->writable = writable;
+		__entry->status = status;
+	),
+
+	TP_printk("scan_pfn=0x%lx, none_or_zero=%d, referenced=%d, writable=%d, status=%s",
+		__entry->pfn,
+		__entry->none_or_zero,
+		__entry->referenced,
+		__entry->writable,
+		__print_symbolic(__entry->status, SCAN_STATUS))
+);
+
+TRACE_EVENT(mm_collapse_huge_page_swapin,
+
+	TP_PROTO(struct mm_struct *mm, int swapped_in, int ret),
+
+	TP_ARGS(mm, swapped_in, ret),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__field(int, swapped_in)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__entry->swapped_in = swapped_in;
+		__entry->ret = ret;
+	),
+
+	TP_printk("mm=%p, swapped_in=%d, ret=%d",
+		__entry->mm,
+		__entry->swapped_in,
+		__entry->ret)
+);
+
+#endif /* __HUGE_MEMORY_H */
+#include <trace/define_trace.h>
+
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36f1046..0e821e3c3d45 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -25,6 +25,11 @@
 # define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
 #endif
 
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT	0x01		/* Lock pages in range after they are faulted in, do not prefault */
+
 #define MS_ASYNC	1		/* sync memory asynchronously */
 #define MS_INVALIDATE	2		/* invalidate the caches */
 #define MS_SYNC		4		/* synchronous memory sync */
@@ -34,6 +39,7 @@
 #define MADV_SEQUENTIAL	2		/* expect sequential page references */
 #define MADV_WILLNEED	3		/* will need these pages */
 #define MADV_DONTNEED	4		/* don't need these pages */
+#define MADV_FREE	5		/* free pages only if memory pressure */
 
 /* common parameters: try to keep these consistent across architectures */
 #define MADV_REMOVE	9		/* remove these pages & resources */
diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h
index e9fe6fd2a074..7162cd4cca73 100644
--- a/include/uapi/asm-generic/mman.h
+++ b/include/uapi/asm-generic/mman.h
@@ -17,5 +17,6 @@
 
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
+#define MCL_ONFAULT	4		/* lock all pages that are faulted in */
 
 #endif /* __ASM_GENERIC_MMAN_H */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8da542a2874d..1324b0292ec2 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -709,17 +709,21 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
 __SYSCALL(__NR_bpf, sys_bpf)
 #define __NR_execveat 281
 __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
-#define __NR_membarrier 282
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
 __SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 283
+#define __NR_syscalls 285
 
 /*
  * All syscalls below here should go away really,
  * these are provided for both review and as a porting
  * help for the C library version.
-*
+ *
  * Last chance: are any of these important enough to
  * enable by default?
  */
diff --git a/ipc/msg.c b/ipc/msg.c
index 66c4f567eb73..f675689290ca 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -37,6 +37,7 @@
 #include <linux/rwsem.h>
 #include <linux/nsproxy.h>
 #include <linux/ipc_namespace.h>
+#include <linux/freezer.h>
 
 #include <asm/current.h>
 #include <linux/uaccess.h>
@@ -675,7 +676,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 
 		ipc_unlock_object(&msq->q_perm);
 		rcu_read_unlock();
-		schedule();
+		freezable_schedule();
 
 		rcu_read_lock();
 		ipc_lock_object(&msq->q_perm);
@@ -917,7 +918,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl
 
 		ipc_unlock_object(&msq->q_perm);
 		rcu_read_unlock();
-		schedule();
+		freezable_schedule();
 
 		/* Lockless receive, part 1:
 		 * Disable preemption.  We don't hold a reference to the queue
diff --git a/kernel/fork.c b/kernel/fork.c
index 7d5f0f118a63..b85aa851b408 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -425,6 +425,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	retval = khugepaged_fork(mm, oldmm);
 	if (retval)
 		goto out;
+	retval = hugetlb_fork(mm, oldmm);
+	if (retval)
+		goto out;
 
 	prev = NULL;
 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
@@ -454,7 +457,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		tmp->vm_mm = mm;
 		if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
-		tmp->vm_flags &= ~(VM_LOCKED|VM_UFFD_MISSING|VM_UFFD_WP);
+		tmp->vm_flags &=
+			~(VM_LOCKED|VM_LOCKONFAULT|VM_UFFD_MISSING|VM_UFFD_WP);
 		tmp->vm_next = tmp->vm_prev = NULL;
 		tmp->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 		file = tmp->vm_file;
diff --git a/kernel/params.c b/kernel/params.c
index b6554aa71094..93a380a2345d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -325,10 +325,11 @@ int param_get_charp(char *buffer, const struct kernel_param *kp)
 }
 EXPORT_SYMBOL(param_get_charp);
 
-static void param_free_charp(void *arg)
+void param_free_charp(void *arg)
 {
 	maybe_kfree_parameter(*((char **)arg));
 }
+EXPORT_SYMBOL(param_free_charp);
 
 const struct kernel_param_ops param_ops_charp = {
 	.set = param_set_charp,
diff --git a/kernel/profile.c b/kernel/profile.c
index 99513e1160e5..e02d1e783eb4 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -336,7 +336,7 @@ static int profile_cpu_callback(struct notifier_block *info,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		node = cpu_to_mem(cpu);
+		node = cpu_to_node(cpu);
 		per_cpu(cpu_profile_flip, cpu) = 0;
 		if (!per_cpu(cpu_profile_hits, cpu)[1]) {
 			page = __alloc_pages_node(node,
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 272d9322bc5d..052e02672d12 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -106,10 +106,9 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr,
-			  void *key)
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
 {
-	__wake_up_common(q, mode, nr, 0, key);
+	__wake_up_common(q, mode, 1, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
@@ -284,7 +283,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
 	if (!list_empty(&wait->task_list))
 		list_del_init(&wait->task_list);
 	else if (waitqueue_active(q))
-		__wake_up_locked_key(q, mode, 1, key);
+		__wake_up_locked_key(q, mode, key);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(abort_exclusive_wait);
diff --git a/kernel/signal.c b/kernel/signal.c
index 0f6bbbe77b46..f2cbd4ed5cd4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -503,41 +503,6 @@ int unhandled_signal(struct task_struct *tsk, int sig)
 	return !tsk->ptrace;
 }
 
-/*
- * Notify the system that a driver wants to block all signals for this
- * process, and wants to be notified if any signals at all were to be
- * sent/acted upon.  If the notifier routine returns non-zero, then the
- * signal will be acted upon after all.  If the notifier routine returns 0,
- * then then signal will be blocked.  Only one block per process is
- * allowed.  priv is a pointer to private data that the notifier routine
- * can use to determine if the signal should be blocked or not.
- */
-void
-block_all_signals(int (*notifier)(void *priv), void *priv, sigset_t *mask)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&current->sighand->siglock, flags);
-	current->notifier_mask = mask;
-	current->notifier_data = priv;
-	current->notifier = notifier;
-	spin_unlock_irqrestore(&current->sighand->siglock, flags);
-}
-
-/* Notify the system that blocking has ended. */
-
-void
-unblock_all_signals(void)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&current->sighand->siglock, flags);
-	current->notifier = NULL;
-	current->notifier_data = NULL;
-	recalc_sigpending();
-	spin_unlock_irqrestore(&current->sighand->siglock, flags);
-}
-
 static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
 {
 	struct sigqueue *q, *first = NULL;
@@ -580,19 +545,8 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
 {
 	int sig = next_signal(pending, mask);
 
-	if (sig) {
-		if (current->notifier) {
-			if (sigismember(current->notifier_mask, sig)) {
-				if (!(current->notifier)(current->notifier_data)) {
-					clear_thread_flag(TIF_SIGPENDING);
-					return 0;
-				}
-			}
-		}
-
+	if (sig)
 		collect_signal(sig, pending, info);
-	}
-
 	return sig;
 }
 
@@ -2483,9 +2437,6 @@ EXPORT_SYMBOL(force_sig);
 EXPORT_SYMBOL(send_sig);
 EXPORT_SYMBOL(send_sig_info);
 EXPORT_SYMBOL(sigprocmask);
-EXPORT_SYMBOL(block_all_signals);
-EXPORT_SYMBOL(unblock_all_signals);
-
 
 /*
  * System call entry points.
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index a02decf15583..0623787ec67a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -194,6 +194,7 @@ cond_syscall(sys_mlock);
 cond_syscall(sys_munlock);
 cond_syscall(sys_mlockall);
 cond_syscall(sys_munlockall);
+cond_syscall(sys_mlock2);
 cond_syscall(sys_mincore);
 cond_syscall(sys_madvise);
 cond_syscall(sys_mremap);
diff --git a/lib/Kconfig b/lib/Kconfig
index 2e491ac15622..34f99838c20f 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -185,6 +185,13 @@ config CRC8
 	  when they need to do cyclic redundancy check according CRC8
 	  algorithm. Module will be called crc8.
 
+config CRC64_ECMA
+	tristate "CRC64 ECMA function"
+	help
+	  This option provides CRC64 ECMA function. Drivers may select this
+	  when they need to do cyclic redundancy check according to the CRC64
+	  ECMA algorithm.
+
 config AUDIT_GENERIC
 	bool
 	depends on AUDIT && !AUDIT_ARCH
diff --git a/lib/Makefile b/lib/Makefile
index 13a7c6ae3fec..1ac9e32c6499 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_CRC32)	+= crc32.o
 obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
+obj-$(CONFIG_CRC64_ECMA)	+= crc64_ecma.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
 obj-$(CONFIG_842_COMPRESS) += 842/
diff --git a/lib/crc64_ecma.c b/lib/crc64_ecma.c
new file mode 100644
index 000000000000..41629ea5a60c
--- /dev/null
+++ b/lib/crc64_ecma.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * 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 Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``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 Freescale Semiconductor 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.
+ */
+
+#include <linux/module.h>
+#include <linux/crc64_ecma.h>
+
+
+#define CRC64_BYTE_MASK			0xFF
+#define CRC64_TABLE_SIZE		256
+
+
+struct crc64_table {
+	u64 seed;
+	u64 table[CRC64_TABLE_SIZE];
+};
+
+
+static struct crc64_table CRC64_ECMA_182 = {
+	CRC64_DEFAULT_INITVAL,
+	{
+		0x0000000000000000ULL,
+		0xb32e4cbe03a75f6fULL,
+		0xf4843657a840a05bULL,
+		0x47aa7ae9abe7ff34ULL,
+		0x7bd0c384ff8f5e33ULL,
+		0xc8fe8f3afc28015cULL,
+		0x8f54f5d357cffe68ULL,
+		0x3c7ab96d5468a107ULL,
+		0xf7a18709ff1ebc66ULL,
+		0x448fcbb7fcb9e309ULL,
+		0x0325b15e575e1c3dULL,
+		0xb00bfde054f94352ULL,
+		0x8c71448d0091e255ULL,
+		0x3f5f08330336bd3aULL,
+		0x78f572daa8d1420eULL,
+		0xcbdb3e64ab761d61ULL,
+		0x7d9ba13851336649ULL,
+		0xceb5ed8652943926ULL,
+		0x891f976ff973c612ULL,
+		0x3a31dbd1fad4997dULL,
+		0x064b62bcaebc387aULL,
+		0xb5652e02ad1b6715ULL,
+		0xf2cf54eb06fc9821ULL,
+		0x41e11855055bc74eULL,
+		0x8a3a2631ae2dda2fULL,
+		0x39146a8fad8a8540ULL,
+		0x7ebe1066066d7a74ULL,
+		0xcd905cd805ca251bULL,
+		0xf1eae5b551a2841cULL,
+		0x42c4a90b5205db73ULL,
+		0x056ed3e2f9e22447ULL,
+		0xb6409f5cfa457b28ULL,
+		0xfb374270a266cc92ULL,
+		0x48190ecea1c193fdULL,
+		0x0fb374270a266cc9ULL,
+		0xbc9d3899098133a6ULL,
+		0x80e781f45de992a1ULL,
+		0x33c9cd4a5e4ecdceULL,
+		0x7463b7a3f5a932faULL,
+		0xc74dfb1df60e6d95ULL,
+		0x0c96c5795d7870f4ULL,
+		0xbfb889c75edf2f9bULL,
+		0xf812f32ef538d0afULL,
+		0x4b3cbf90f69f8fc0ULL,
+		0x774606fda2f72ec7ULL,
+		0xc4684a43a15071a8ULL,
+		0x83c230aa0ab78e9cULL,
+		0x30ec7c140910d1f3ULL,
+		0x86ace348f355aadbULL,
+		0x3582aff6f0f2f5b4ULL,
+		0x7228d51f5b150a80ULL,
+		0xc10699a158b255efULL,
+		0xfd7c20cc0cdaf4e8ULL,
+		0x4e526c720f7dab87ULL,
+		0x09f8169ba49a54b3ULL,
+		0xbad65a25a73d0bdcULL,
+		0x710d64410c4b16bdULL,
+		0xc22328ff0fec49d2ULL,
+		0x85895216a40bb6e6ULL,
+		0x36a71ea8a7ace989ULL,
+		0x0adda7c5f3c4488eULL,
+		0xb9f3eb7bf06317e1ULL,
+		0xfe5991925b84e8d5ULL,
+		0x4d77dd2c5823b7baULL,
+		0x64b62bcaebc387a1ULL,
+		0xd7986774e864d8ceULL,
+		0x90321d9d438327faULL,
+		0x231c512340247895ULL,
+		0x1f66e84e144cd992ULL,
+		0xac48a4f017eb86fdULL,
+		0xebe2de19bc0c79c9ULL,
+		0x58cc92a7bfab26a6ULL,
+		0x9317acc314dd3bc7ULL,
+		0x2039e07d177a64a8ULL,
+		0x67939a94bc9d9b9cULL,
+		0xd4bdd62abf3ac4f3ULL,
+		0xe8c76f47eb5265f4ULL,
+		0x5be923f9e8f53a9bULL,
+		0x1c4359104312c5afULL,
+		0xaf6d15ae40b59ac0ULL,
+		0x192d8af2baf0e1e8ULL,
+		0xaa03c64cb957be87ULL,
+		0xeda9bca512b041b3ULL,
+		0x5e87f01b11171edcULL,
+		0x62fd4976457fbfdbULL,
+		0xd1d305c846d8e0b4ULL,
+		0x96797f21ed3f1f80ULL,
+		0x2557339fee9840efULL,
+		0xee8c0dfb45ee5d8eULL,
+		0x5da24145464902e1ULL,
+		0x1a083bacedaefdd5ULL,
+		0xa9267712ee09a2baULL,
+		0x955cce7fba6103bdULL,
+		0x267282c1b9c65cd2ULL,
+		0x61d8f8281221a3e6ULL,
+		0xd2f6b4961186fc89ULL,
+		0x9f8169ba49a54b33ULL,
+		0x2caf25044a02145cULL,
+		0x6b055fede1e5eb68ULL,
+		0xd82b1353e242b407ULL,
+		0xe451aa3eb62a1500ULL,
+		0x577fe680b58d4a6fULL,
+		0x10d59c691e6ab55bULL,
+		0xa3fbd0d71dcdea34ULL,
+		0x6820eeb3b6bbf755ULL,
+		0xdb0ea20db51ca83aULL,
+		0x9ca4d8e41efb570eULL,
+		0x2f8a945a1d5c0861ULL,
+		0x13f02d374934a966ULL,
+		0xa0de61894a93f609ULL,
+		0xe7741b60e174093dULL,
+		0x545a57dee2d35652ULL,
+		0xe21ac88218962d7aULL,
+		0x5134843c1b317215ULL,
+		0x169efed5b0d68d21ULL,
+		0xa5b0b26bb371d24eULL,
+		0x99ca0b06e7197349ULL,
+		0x2ae447b8e4be2c26ULL,
+		0x6d4e3d514f59d312ULL,
+		0xde6071ef4cfe8c7dULL,
+		0x15bb4f8be788911cULL,
+		0xa6950335e42fce73ULL,
+		0xe13f79dc4fc83147ULL,
+		0x521135624c6f6e28ULL,
+		0x6e6b8c0f1807cf2fULL,
+		0xdd45c0b11ba09040ULL,
+		0x9aefba58b0476f74ULL,
+		0x29c1f6e6b3e0301bULL,
+		0xc96c5795d7870f42ULL,
+		0x7a421b2bd420502dULL,
+		0x3de861c27fc7af19ULL,
+		0x8ec62d7c7c60f076ULL,
+		0xb2bc941128085171ULL,
+		0x0192d8af2baf0e1eULL,
+		0x4638a2468048f12aULL,
+		0xf516eef883efae45ULL,
+		0x3ecdd09c2899b324ULL,
+		0x8de39c222b3eec4bULL,
+		0xca49e6cb80d9137fULL,
+		0x7967aa75837e4c10ULL,
+		0x451d1318d716ed17ULL,
+		0xf6335fa6d4b1b278ULL,
+		0xb199254f7f564d4cULL,
+		0x02b769f17cf11223ULL,
+		0xb4f7f6ad86b4690bULL,
+		0x07d9ba1385133664ULL,
+		0x4073c0fa2ef4c950ULL,
+		0xf35d8c442d53963fULL,
+		0xcf273529793b3738ULL,
+		0x7c0979977a9c6857ULL,
+		0x3ba3037ed17b9763ULL,
+		0x888d4fc0d2dcc80cULL,
+		0x435671a479aad56dULL,
+		0xf0783d1a7a0d8a02ULL,
+		0xb7d247f3d1ea7536ULL,
+		0x04fc0b4dd24d2a59ULL,
+		0x3886b22086258b5eULL,
+		0x8ba8fe9e8582d431ULL,
+		0xcc0284772e652b05ULL,
+		0x7f2cc8c92dc2746aULL,
+		0x325b15e575e1c3d0ULL,
+		0x8175595b76469cbfULL,
+		0xc6df23b2dda1638bULL,
+		0x75f16f0cde063ce4ULL,
+		0x498bd6618a6e9de3ULL,
+		0xfaa59adf89c9c28cULL,
+		0xbd0fe036222e3db8ULL,
+		0x0e21ac88218962d7ULL,
+		0xc5fa92ec8aff7fb6ULL,
+		0x76d4de52895820d9ULL,
+		0x317ea4bb22bfdfedULL,
+		0x8250e80521188082ULL,
+		0xbe2a516875702185ULL,
+		0x0d041dd676d77eeaULL,
+		0x4aae673fdd3081deULL,
+		0xf9802b81de97deb1ULL,
+		0x4fc0b4dd24d2a599ULL,
+		0xfceef8632775faf6ULL,
+		0xbb44828a8c9205c2ULL,
+		0x086ace348f355aadULL,
+		0x34107759db5dfbaaULL,
+		0x873e3be7d8faa4c5ULL,
+		0xc094410e731d5bf1ULL,
+		0x73ba0db070ba049eULL,
+		0xb86133d4dbcc19ffULL,
+		0x0b4f7f6ad86b4690ULL,
+		0x4ce50583738cb9a4ULL,
+		0xffcb493d702be6cbULL,
+		0xc3b1f050244347ccULL,
+		0x709fbcee27e418a3ULL,
+		0x3735c6078c03e797ULL,
+		0x841b8ab98fa4b8f8ULL,
+		0xadda7c5f3c4488e3ULL,
+		0x1ef430e13fe3d78cULL,
+		0x595e4a08940428b8ULL,
+		0xea7006b697a377d7ULL,
+		0xd60abfdbc3cbd6d0ULL,
+		0x6524f365c06c89bfULL,
+		0x228e898c6b8b768bULL,
+		0x91a0c532682c29e4ULL,
+		0x5a7bfb56c35a3485ULL,
+		0xe955b7e8c0fd6beaULL,
+		0xaeffcd016b1a94deULL,
+		0x1dd181bf68bdcbb1ULL,
+		0x21ab38d23cd56ab6ULL,
+		0x9285746c3f7235d9ULL,
+		0xd52f0e859495caedULL,
+		0x6601423b97329582ULL,
+		0xd041dd676d77eeaaULL,
+		0x636f91d96ed0b1c5ULL,
+		0x24c5eb30c5374ef1ULL,
+		0x97eba78ec690119eULL,
+		0xab911ee392f8b099ULL,
+		0x18bf525d915feff6ULL,
+		0x5f1528b43ab810c2ULL,
+		0xec3b640a391f4fadULL,
+		0x27e05a6e926952ccULL,
+		0x94ce16d091ce0da3ULL,
+		0xd3646c393a29f297ULL,
+		0x604a2087398eadf8ULL,
+		0x5c3099ea6de60cffULL,
+		0xef1ed5546e415390ULL,
+		0xa8b4afbdc5a6aca4ULL,
+		0x1b9ae303c601f3cbULL,
+		0x56ed3e2f9e224471ULL,
+		0xe5c372919d851b1eULL,
+		0xa26908783662e42aULL,
+		0x114744c635c5bb45ULL,
+		0x2d3dfdab61ad1a42ULL,
+		0x9e13b115620a452dULL,
+		0xd9b9cbfcc9edba19ULL,
+		0x6a978742ca4ae576ULL,
+		0xa14cb926613cf817ULL,
+		0x1262f598629ba778ULL,
+		0x55c88f71c97c584cULL,
+		0xe6e6c3cfcadb0723ULL,
+		0xda9c7aa29eb3a624ULL,
+		0x69b2361c9d14f94bULL,
+		0x2e184cf536f3067fULL,
+		0x9d36004b35545910ULL,
+		0x2b769f17cf112238ULL,
+		0x9858d3a9ccb67d57ULL,
+		0xdff2a94067518263ULL,
+		0x6cdce5fe64f6dd0cULL,
+		0x50a65c93309e7c0bULL,
+		0xe388102d33392364ULL,
+		0xa4226ac498dedc50ULL,
+		0x170c267a9b79833fULL,
+		0xdcd7181e300f9e5eULL,
+		0x6ff954a033a8c131ULL,
+		0x28532e49984f3e05ULL,
+		0x9b7d62f79be8616aULL,
+		0xa707db9acf80c06dULL,
+		0x14299724cc279f02ULL,
+		0x5383edcd67c06036ULL,
+		0xe0ada17364673f59ULL
+	}
+};
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void)
+{
+	return CRC64_ECMA_182.seed;
+}
+EXPORT_SYMBOL(crc64_ecma_seed);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * pdata: pointer to the data to compute checksum for.
+ * nbytes: number of bytes in data buffer.
+ * seed: CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed)
+{
+	unsigned int i;
+	u64 crc = seed;
+
+	for (i = 0; i < nbytes; i++)
+		crc = CRC64_ECMA_182.table[(crc ^ pdata[i]) & CRC64_BYTE_MASK] ^
+			(crc >> 8);
+
+	return crc;
+}
+EXPORT_SYMBOL(crc64_ecma);
+
+MODULE_DESCRIPTION("CRC64 ECMA function");
+MODULE_AUTHOR("Freescale Semiconductor Inc.");
+MODULE_LICENSE("GPL");
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index e491e02eff54..e3952e9c8ec0 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -42,7 +42,7 @@ extern struct _ddebug __stop___verbose[];
 
 struct ddebug_table {
 	struct list_head link;
-	char *mod_name;
+	const char *mod_name;
 	unsigned int num_ddebugs;
 	struct _ddebug *ddebugs;
 };
@@ -841,12 +841,12 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 			     const char *name)
 {
 	struct ddebug_table *dt;
-	char *new_name;
+	const char *new_name;
 
 	dt = kzalloc(sizeof(*dt), GFP_KERNEL);
 	if (dt == NULL)
 		return -ENOMEM;
-	new_name = kstrdup(name, GFP_KERNEL);
+	new_name = kstrdup_const(name, GFP_KERNEL);
 	if (new_name == NULL) {
 		kfree(dt);
 		return -ENOMEM;
@@ -907,7 +907,7 @@ int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *module)
 static void ddebug_table_free(struct ddebug_table *dt)
 {
 	list_del_init(&dt->link);
-	kfree(dt->mod_name);
+	kfree_const(dt->mod_name);
 	kfree(dt);
 }
 
diff --git a/lib/halfmd4.c b/lib/halfmd4.c
index a8fe6274a13c..137e861d9690 100644
--- a/lib/halfmd4.c
+++ b/lib/halfmd4.c
@@ -1,6 +1,7 @@
 #include <linux/compiler.h>
 #include <linux/export.h>
 #include <linux/cryptohash.h>
+#include <linux/bitops.h>
 
 /* F, G and H are basic MD4 functions: selection, majority, parity */
 #define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
@@ -14,7 +15,7 @@
  * Rotation is separate from addition to prevent recomputation
  */
 #define ROUND(f, a, b, c, d, x, s)	\
-	(a += f(b, c, d) + x, a = (a << s) | (a >> (32 - s)))
+	(a += f(b, c, d) + x, a = rol32(a, s))
 #define K1 0
 #define K2 013240474631UL
 #define K3 015666365641UL
diff --git a/lib/kasprintf.c b/lib/kasprintf.c
index 32f12150fc4f..f194e6e593e1 100644
--- a/lib/kasprintf.c
+++ b/lib/kasprintf.c
@@ -31,6 +31,22 @@ char *kvasprintf(gfp_t gfp, const char *fmt, va_list ap)
 }
 EXPORT_SYMBOL(kvasprintf);
 
+/*
+ * If fmt contains no % (or is exactly %s), use kstrdup_const. If fmt
+ * (or the sole vararg) points to rodata, we will then save a memory
+ * allocation and string copy. In any case, the return value should be
+ * freed using kfree_const().
+ */
+const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list ap)
+{
+	if (!strchr(fmt, '%'))
+		return kstrdup_const(fmt, gfp);
+	if (!strcmp(fmt, "%s"))
+		return kstrdup_const(va_arg(ap, const char*), gfp);
+	return kvasprintf(gfp, fmt, ap);
+}
+EXPORT_SYMBOL(kvasprintf_const);
+
 char *kasprintf(gfp_t gfp, const char *fmt, ...)
 {
 	va_list ap;
diff --git a/lib/kobject.c b/lib/kobject.c
index 3e3a5c3cb330..fee2fd950306 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -257,18 +257,32 @@ static int kobject_add_internal(struct kobject *kobj)
 int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
 				  va_list vargs)
 {
-	char *s;
+	const char *s;
 
 	if (kobj->name && !fmt)
 		return 0;
 
-	s = kvasprintf(GFP_KERNEL, fmt, vargs);
+	s = kvasprintf_const(GFP_KERNEL, fmt, vargs);
 	if (!s)
 		return -ENOMEM;
 
-	/* ewww... some of these buggers have '/' in the name ... */
-	strreplace(s, '/', '!');
-	kfree(kobj->name);
+	/*
+	 * ewww... some of these buggers have '/' in the name ... If
+	 * that's the case, we need to make sure we have an actual
+	 * allocated copy to modify, since kvasprintf_const may have
+	 * returned something from .rodata.
+	 */
+	if (strchr(s, '/')) {
+		char *t;
+
+		t = kstrdup(s, GFP_KERNEL);
+		kfree_const(s);
+		if (!t)
+			return -ENOMEM;
+		strreplace(t, '/', '!');
+		s = t;
+	}
+	kfree_const(kobj->name);
 	kobj->name = s;
 
 	return 0;
@@ -466,7 +480,7 @@ int kobject_rename(struct kobject *kobj, const char *new_name)
 	envp[0] = devpath_string;
 	envp[1] = NULL;
 
-	name = dup_name = kstrdup(new_name, GFP_KERNEL);
+	name = dup_name = kstrdup_const(new_name, GFP_KERNEL);
 	if (!name) {
 		error = -ENOMEM;
 		goto out;
@@ -486,7 +500,7 @@ int kobject_rename(struct kobject *kobj, const char *new_name)
 	kobject_uevent_env(kobj, KOBJ_MOVE, envp);
 
 out:
-	kfree(dup_name);
+	kfree_const(dup_name);
 	kfree(devpath_string);
 	kfree(devpath);
 	kobject_put(kobj);
@@ -632,7 +646,7 @@ static void kobject_cleanup(struct kobject *kobj)
 	/* free name if we allocated it */
 	if (name) {
 		pr_debug("kobject: '%s': free name\n", name);
-		kfree(name);
+		kfree_const(name);
 	}
 }
 
diff --git a/lib/llist.c b/lib/llist.c
index 0b0e9779d675..ae5872b1df0c 100644
--- a/lib/llist.c
+++ b/lib/llist.c
@@ -66,12 +66,12 @@ struct llist_node *llist_del_first(struct llist_head *head)
 {
 	struct llist_node *entry, *old_entry, *next;
 
-	entry = head->first;
+	entry = smp_load_acquire(&head->first);
 	for (;;) {
 		if (entry == NULL)
 			return NULL;
 		old_entry = entry;
-		next = entry->next;
+		next = READ_ONCE(entry->next);
 		entry = cmpxchg(&head->first, old_entry, next);
 		if (entry == old_entry)
 			break;
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 54036ce2e2dd..5939f63d90cd 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -59,7 +59,11 @@ void string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 	}
 
 	exp = divisor[units] / (u32)blk_size;
-	if (size >= exp) {
+	/*
+	 * size must be strictly greater than exp here to ensure that remainder
+	 * is greater than divisor[units] coming out of the if below.
+	 */
+	if (size > exp) {
 		remainder = do_div(size, divisor[units]);
 		remainder *= blk_size;
 		i++;
diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c
index 8e376efd88a4..ee67adab1346 100644
--- a/lib/test-string_helpers.c
+++ b/lib/test-string_helpers.c
@@ -326,6 +326,30 @@ out:
 	kfree(out_test);
 }
 
+static __init void test_string_get_size_one(u64 size, u64 blk_size,
+					    const enum string_size_units units,
+					    const char *exp_result)
+{
+	char buf[256];
+
+	string_get_size(size, blk_size, units, buf, sizeof(buf));
+	if (!strncmp(buf, exp_result, min(sizeof(buf), strlen(exp_result))))
+		return;
+
+	pr_warn("Test 'test_string_get_size_one' failed!\n");
+	pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %d\n",
+		size, blk_size, units);
+	pr_warn("expected: %s, got %s\n", exp_result, buf);
+
+}
+
+static __init void test_string_get_size(void)
+{
+	test_string_get_size_one(16384, 512, STRING_UNITS_2, "8.00 MiB");
+	test_string_get_size_one(8192, 4096, STRING_UNITS_10, "32.7 MB");
+	test_string_get_size_one(1, 512, STRING_UNITS_10, "512 B");
+}
+
 static int __init test_string_helpers_init(void)
 {
 	unsigned int i;
@@ -344,6 +368,9 @@ static int __init test_string_helpers_init(void)
 	for (i = 0; i < (ESCAPE_ANY_NP | ESCAPE_HEX) + 1; i++)
 		test_string_escape("escape 1", escape1, i, TEST_STRING_2_DICT_1);
 
+	/* Test string_get_size() */
+	test_string_get_size();
+
 	return -EINVAL;
 }
 module_init(test_string_helpers_init);
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index c1efb1b61017..c32f3b0048dc 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -138,6 +138,71 @@ static noinline void __init kmalloc_oob_16(void)
 	kfree(ptr2);
 }
 
+static noinline void __init kmalloc_oob_memset_2(void)
+{
+	char *ptr;
+	size_t size = 8;
+
+	pr_info("out-of-bounds in memset2\n");
+	ptr = kmalloc(size, GFP_KERNEL);
+	if (!ptr) {
+		pr_err("Allocation failed\n");
+		return;
+	}
+
+	memset(ptr+7, 0, 2);
+	kfree(ptr);
+}
+
+static noinline void __init kmalloc_oob_memset_4(void)
+{
+	char *ptr;
+	size_t size = 8;
+
+	pr_info("out-of-bounds in memset4\n");
+	ptr = kmalloc(size, GFP_KERNEL);
+	if (!ptr) {
+		pr_err("Allocation failed\n");
+		return;
+	}
+
+	memset(ptr+5, 0, 4);
+	kfree(ptr);
+}
+
+
+static noinline void __init kmalloc_oob_memset_8(void)
+{
+	char *ptr;
+	size_t size = 8;
+
+	pr_info("out-of-bounds in memset8\n");
+	ptr = kmalloc(size, GFP_KERNEL);
+	if (!ptr) {
+		pr_err("Allocation failed\n");
+		return;
+	}
+
+	memset(ptr+1, 0, 8);
+	kfree(ptr);
+}
+
+static noinline void __init kmalloc_oob_memset_16(void)
+{
+	char *ptr;
+	size_t size = 16;
+
+	pr_info("out-of-bounds in memset16\n");
+	ptr = kmalloc(size, GFP_KERNEL);
+	if (!ptr) {
+		pr_err("Allocation failed\n");
+		return;
+	}
+
+	memset(ptr+1, 0, 16);
+	kfree(ptr);
+}
+
 static noinline void __init kmalloc_oob_in_memset(void)
 {
 	char *ptr;
@@ -264,6 +329,10 @@ static int __init kmalloc_tests_init(void)
 	kmalloc_oob_krealloc_less();
 	kmalloc_oob_16();
 	kmalloc_oob_in_memset();
+	kmalloc_oob_memset_2();
+	kmalloc_oob_memset_4();
+	kmalloc_oob_memset_8();
+	kmalloc_oob_memset_16();
 	kmalloc_uaf();
 	kmalloc_uaf_memset();
 	kmalloc_uaf2();
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 95cd63b43b99..becd87facf48 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1361,6 +1361,21 @@ char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec,
 	}
 }
 
+static noinline_for_stack
+char *comm_name(char *buf, char *end, struct task_struct *tsk,
+		struct printf_spec spec, const char *fmt)
+{
+	char name[TASK_COMM_LEN];
+
+	/* Caller can pass NULL instead of current. */
+	if (!tsk)
+		tsk = current;
+	/* Not using get_task_comm() in case I'm in IRQ context. */
+	memcpy(name, tsk->comm, TASK_COMM_LEN);
+	name[sizeof(name) - 1] = '\0';
+	return string(buf, end, name, spec);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -1448,6 +1463,7 @@ int kptr_restrict __read_mostly;
  * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address
  *        (legacy clock framework) of the clock
  * - 'Cr' For a clock, it prints the current rate of the clock
+ * - 'T' task_struct->comm
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -1459,7 +1475,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 {
 	int default_width = 2 * sizeof(void *) + (spec.flags & SPECIAL ? 2 : 0);
 
-	if (!ptr && *fmt != 'K') {
+	if (!ptr && *fmt != 'K' && *fmt != 'T') {
 		/*
 		 * Print (null) with the same width as a pointer so it makes
 		 * tabular output look nice.
@@ -1598,6 +1614,8 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return dentry_name(buf, end,
 				   ((const struct file *)ptr)->f_path.dentry,
 				   spec, fmt);
+	case 'T':
+		return comm_name(buf, end, ptr, spec, fmt);
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
diff --git a/mm/Kconfig b/mm/Kconfig
index 0d9fdcd01e47..97a4e06b15c0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -200,18 +200,6 @@ config MEMORY_HOTREMOVE
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 
-#
-# If we have space for more page flags then we can enable additional
-# optimizations and functionality.
-#
-# Regular Sparsemem takes page flag bits for the sectionid if it does not
-# use a virtual memmap. Disable extended page flags for 32 bit platforms
-# that require the use of a sectionid in the page flags.
-#
-config PAGEFLAGS_EXTENDED
-	def_bool y
-	depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
-
 # Heavily threaded applications may benefit from splitting the mm-wide
 # page_table_lock, so that faults on different parts of the user address
 # space can be handled with less contention: split it at this NR_CPUS.
diff --git a/mm/debug.c b/mm/debug.c
index 6c1b3ea61bfd..668aa35191ca 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -25,12 +25,7 @@ static const struct trace_print_flags pageflag_names[] = {
 	{1UL << PG_private,		"private"	},
 	{1UL << PG_private_2,		"private_2"	},
 	{1UL << PG_writeback,		"writeback"	},
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
 	{1UL << PG_head,		"head"		},
-	{1UL << PG_tail,		"tail"		},
-#else
-	{1UL << PG_compound,		"compound"	},
-#endif
 	{1UL << PG_swapcache,		"swapcache"	},
 	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
 	{1UL << PG_reclaim,		"reclaim"	},
@@ -125,6 +120,7 @@ static const struct trace_print_flags vmaflags_names[] = {
 	{VM_GROWSDOWN,			"growsdown"	},
 	{VM_PFNMAP,			"pfnmap"	},
 	{VM_DENYWRITE,			"denywrite"	},
+	{VM_LOCKONFAULT,		"lockonfault"	},
 	{VM_LOCKED,			"locked"	},
 	{VM_IO,				"io"		},
 	{VM_SEQ_READ,			"seqread"	},
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 17ae14b5aefa..6d5717bd7197 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -126,7 +126,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 	/*
 	 * Mappings have to be page-aligned
 	 */
-	offset = phys_addr & ~PAGE_MASK;
+	offset = offset_in_page(phys_addr);
 	phys_addr &= PAGE_MASK;
 	size = PAGE_ALIGN(last_addr + 1) - phys_addr;
 
@@ -189,7 +189,7 @@ void __init early_iounmap(void __iomem *addr, unsigned long size)
 	if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)))
 		return;
 
-	offset = virt_addr & ~PAGE_MASK;
+	offset = offset_in_page(virt_addr);
 	nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT;
 
 	idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
@@ -234,7 +234,7 @@ void __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size)
 	char *p;
 
 	while (size) {
-		slop = src & ~PAGE_MASK;
+		slop = offset_in_page(src);
 		clen = size;
 		if (clen > MAX_MAP_CHUNK - slop)
 			clen = MAX_MAP_CHUNK - slop;
diff --git a/mm/filemap.c b/mm/filemap.c
index 72940fb38666..363607691427 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -641,11 +641,11 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	void *shadow = NULL;
 	int ret;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	ret = __add_to_page_cache_locked(page, mapping, offset,
 					 gfp_mask, &shadow);
 	if (unlikely(ret))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	else {
 		/*
 		 * The page might have been evicted from cache only
@@ -768,6 +768,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  */
 void unlock_page(struct page *page)
 {
+	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	clear_bit_unlock(PG_locked, &page->flags);
 	smp_mb__after_atomic();
@@ -832,18 +833,20 @@ EXPORT_SYMBOL_GPL(page_endio);
  */
 void __lock_page(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
+	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
 
 int __lock_page_killable(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	return __wait_on_bit_lock(page_waitqueue(page), &wait,
+	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
 					bit_wait_io, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
@@ -1807,7 +1810,6 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
 				   struct file *file,
 				   pgoff_t offset)
 {
-	unsigned long ra_pages;
 	struct address_space *mapping = file->f_mapping;
 
 	/* If we don't want any read-ahead, don't bother */
@@ -1836,10 +1838,9 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
 	/*
 	 * mmap read-around
 	 */
-	ra_pages = max_sane_readahead(ra->ra_pages);
-	ra->start = max_t(long, 0, offset - ra_pages / 2);
-	ra->size = ra_pages;
-	ra->async_size = ra_pages / 4;
+	ra->start = max_t(long, 0, offset - ra->ra_pages / 2);
+	ra->size = ra->ra_pages;
+	ra->async_size = ra->ra_pages / 4;
 	ra_submit(ra, mapping, file);
 }
 
diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index cdabcb93c6a6..7cf2b7163222 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -7,7 +7,7 @@
 #include <linux/pagemap.h>
 #include <linux/sched.h>
 
-/*
+/**
  * get_vaddr_frames() - map virtual addresses to pfns
  * @start:	starting user address
  * @nr_frames:	number of pages / pfns from start to map
diff --git a/mm/gup.c b/mm/gup.c
index a798293fc648..deafa2c91b36 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -129,7 +129,7 @@ retry:
 		 */
 		mark_page_accessed(page);
 	}
-	if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) {
+	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
 		/*
 		 * The preliminary mapping check is mainly to avoid the
 		 * pointless overhead of lock_page on the ZERO_PAGE
@@ -299,6 +299,9 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	unsigned int fault_flags = 0;
 	int ret;
 
+	/* mlock all present pages, but do not fault in new pages */
+	if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
+		return -ENOENT;
 	/* For mm_populate(), just skip the stack guard page. */
 	if ((*flags & FOLL_POPULATE) &&
 			(stack_guard_page_start(vma, address) ||
@@ -890,7 +893,10 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
 	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
 
-	gup_flags = FOLL_TOUCH | FOLL_POPULATE;
+	gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
+	if (vma->vm_flags & VM_LOCKONFAULT)
+		gup_flags &= ~FOLL_POPULATE;
+
 	/*
 	 * We want to touch writable mappings with a write fault in order
 	 * to break COW, except for shared mappings because these don't COW
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4b06b8db9df2..4b057abd8615 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -26,11 +26,40 @@
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
+#include <linux/swapops.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
 #include "internal.h"
 
+enum scan_result {
+	SCAN_FAIL,
+	SCAN_SUCCEED,
+	SCAN_PMD_NULL,
+	SCAN_EXCEED_NONE_PTE,
+	SCAN_PTE_NON_PRESENT,
+	SCAN_PAGE_RO,
+	SCAN_NO_REFERENCED_PAGE,
+	SCAN_PAGE_NULL,
+	SCAN_SCAN_ABORT,
+	SCAN_PAGE_COUNT,
+	SCAN_PAGE_LRU,
+	SCAN_PAGE_LOCK,
+	SCAN_PAGE_ANON,
+	SCAN_ANY_PROCESS,
+	SCAN_VMA_NULL,
+	SCAN_VMA_CHECK,
+	SCAN_ADDRESS_RANGE,
+	SCAN_SWAP_CACHE_PAGE,
+	SCAN_DEL_PAGE_LRU,
+	SCAN_ALLOC_HUGE_PAGE_FAIL,
+	SCAN_CGROUP_CHARGE_FAIL,
+	SCAN_EXCEED_SWAP_PTE
+};
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/huge_memory.h>
+
 /*
  * By default transparent hugepage support is disabled in order that avoid
  * to risk increase the memory footprint of applications without a guaranteed
@@ -67,6 +96,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
  * fault.
  */
 static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
+static unsigned int khugepaged_max_ptes_swap __read_mostly = HPAGE_PMD_NR/8;
 
 static int khugepaged(void *none);
 static int khugepaged_slab_init(void);
@@ -553,6 +583,33 @@ static struct kobj_attribute khugepaged_max_ptes_none_attr =
 	__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
 	       khugepaged_max_ptes_none_store);
 
+static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj,
+					     struct kobj_attribute *attr,
+					     char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_max_ptes_swap);
+}
+
+static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj,
+					      struct kobj_attribute *attr,
+					      const char *buf, size_t count)
+{
+	int err;
+	unsigned long max_ptes_swap;
+
+	err  = kstrtoul(buf, 10, &max_ptes_swap);
+	if (err || max_ptes_swap > HPAGE_PMD_NR-1)
+		return -EINVAL;
+
+	khugepaged_max_ptes_swap = max_ptes_swap;
+
+	return count;
+}
+
+static struct kobj_attribute khugepaged_max_ptes_swap_attr =
+	__ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show,
+	       khugepaged_max_ptes_swap_store);
+
 static struct attribute *khugepaged_attr[] = {
 	&khugepaged_defrag_attr.attr,
 	&khugepaged_max_ptes_none_attr.attr,
@@ -561,6 +618,7 @@ static struct attribute *khugepaged_attr[] = {
 	&full_scans_attr.attr,
 	&scan_sleep_millisecs_attr.attr,
 	&alloc_sleep_millisecs_attr.attr,
+	&khugepaged_max_ptes_swap_attr.attr,
 	NULL,
 };
 
@@ -1307,7 +1365,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  pmd, _pmd,  1))
 			update_mmu_cache_pmd(vma, addr, pmd);
 	}
-	if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) {
+	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
 		if (page->mapping && trylock_page(page)) {
 			lru_add_drain();
 			if (page->mapping)
@@ -1453,6 +1511,36 @@ out:
 	return 0;
 }
 
+int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		 pmd_t *pmd, unsigned long addr)
+
+{
+	spinlock_t *ptl;
+	struct mm_struct *mm = tlb->mm;
+	int ret = 1;
+
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		struct page *page;
+		pmd_t orig_pmd;
+
+		orig_pmd = pmdp_huge_get_and_clear(mm, addr, pmd);
+
+		/* No hugepage in swapcache */
+		page = pmd_page(orig_pmd);
+		VM_BUG_ON_PAGE(PageSwapCache(page), page);
+
+		orig_pmd = pmd_mkold(orig_pmd);
+		orig_pmd = pmd_mkclean(orig_pmd);
+
+		set_pmd_at(mm, addr, pmd, orig_pmd);
+		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		spin_unlock(ptl);
+		ret = 0;
+	}
+
+	return ret;
+}
+
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
@@ -1668,6 +1756,11 @@ unlock:
 	return NULL;
 }
 
+int pmd_freeable(pmd_t pmd)
+{
+	return !pmd_dirty(pmd);
+}
+
 static int __split_huge_page_splitting(struct page *page,
 				       struct vm_area_struct *vma,
 				       unsigned long address)
@@ -1755,8 +1848,7 @@ static void __split_huge_page_refcount(struct page *page,
 				      (1L << PG_unevictable)));
 		page_tail->flags |= (1L << PG_dirty);
 
-		/* clear PageTail before overwriting first_page */
-		smp_wmb();
+		clear_compound_head(page_tail);
 
 		if (page_is_young(page))
 			set_page_young(page_tail);
@@ -1779,7 +1871,7 @@ static void __split_huge_page_refcount(struct page *page,
 		*/
 		page_tail->_mapcount = page->_mapcount;
 
-		BUG_ON(page_tail->mapping);
+		BUG_ON(page_tail->mapping != TAIL_MAPPING);
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
@@ -2199,25 +2291,31 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					unsigned long address,
 					pte_t *pte)
 {
-	struct page *page;
+	struct page *page = NULL;
 	pte_t *_pte;
-	int none_or_zero = 0;
+	int none_or_zero = 0, result = 0;
 	bool referenced = false, writable = false;
 	for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
 			if (!userfaultfd_armed(vma) &&
-			    ++none_or_zero <= khugepaged_max_ptes_none)
+			    ++none_or_zero <= khugepaged_max_ptes_none) {
 				continue;
-			else
+			} else {
+				result = SCAN_EXCEED_NONE_PTE;
 				goto out;
+			}
 		}
-		if (!pte_present(pteval))
+		if (!pte_present(pteval)) {
+			result = SCAN_PTE_NON_PRESENT;
 			goto out;
+		}
 		page = vm_normal_page(vma, address, pteval);
-		if (unlikely(!page))
+		if (unlikely(!page)) {
+			result = SCAN_PAGE_NULL;
 			goto out;
+		}
 
 		VM_BUG_ON_PAGE(PageCompound(page), page);
 		VM_BUG_ON_PAGE(!PageAnon(page), page);
@@ -2229,8 +2327,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 * is needed to serialize against split_huge_page
 		 * when invoked from the VM.
 		 */
-		if (!trylock_page(page))
+		if (!trylock_page(page)) {
+			result = SCAN_PAGE_LOCK;
 			goto out;
+		}
 
 		/*
 		 * cannot use mapcount: can't collapse if there's a gup pin.
@@ -2239,6 +2339,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 */
 		if (page_count(page) != 1 + !!PageSwapCache(page)) {
 			unlock_page(page);
+			result = SCAN_PAGE_COUNT;
 			goto out;
 		}
 		if (pte_write(pteval)) {
@@ -2246,6 +2347,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		} else {
 			if (PageSwapCache(page) && !reuse_swap_page(page)) {
 				unlock_page(page);
+				result = SCAN_SWAP_CACHE_PAGE;
 				goto out;
 			}
 			/*
@@ -2260,6 +2362,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		 */
 		if (isolate_lru_page(page)) {
 			unlock_page(page);
+			result = SCAN_DEL_PAGE_LRU;
 			goto out;
 		}
 		/* 0 stands for page_is_file_cache(page) == false */
@@ -2273,10 +2376,21 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = true;
 	}
-	if (likely(referenced && writable))
-		return 1;
+	if (likely(writable)) {
+		if (likely(referenced)) {
+			result = SCAN_SUCCEED;
+			trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero,
+							    referenced, writable, result);
+			return 1;
+		}
+	} else {
+		result = SCAN_PAGE_RO;
+	}
+
 out:
 	release_pte_pages(pte, _pte);
+	trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero,
+					    referenced, writable, result);
 	return 0;
 }
 
@@ -2504,6 +2618,47 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 	return true;
 }
 
+/*
+ * Bring missing pages in from swap, to complete THP collapse.
+ * Only done if khugepaged_scan_pmd believes it is worthwhile.
+ *
+ * Called and returns without pte mapped or spinlocks held,
+ * but with mmap_sem held to protect against vma changes.
+ */
+
+static void __collapse_huge_page_swapin(struct mm_struct *mm,
+					struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmd,
+					pte_t *pte)
+{
+	unsigned long _address;
+	pte_t pteval = *pte;
+	int swapped_in = 0, ret = 0;
+
+	pte = pte_offset_map(pmd, address);
+	for (_address = address; _address < address + HPAGE_PMD_NR*PAGE_SIZE;
+	     pte++, _address += PAGE_SIZE) {
+		pteval = *pte;
+		if (!is_swap_pte(pteval))
+			continue;
+		swapped_in++;
+		ret = do_swap_page(mm, vma, _address, pte, pmd,
+				   FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT,
+				   pteval);
+		if (ret & VM_FAULT_ERROR) {
+			trace_mm_collapse_huge_page_swapin(mm, swapped_in, 0);
+			return;
+		}
+		/* pte is unmapped now, we need to map it */
+		pte = pte_offset_map(pmd, _address);
+	}
+	pte--;
+	pte_unmap(pte);
+	trace_mm_collapse_huge_page_swapin(mm, swapped_in, 1);
+}
+
+
+
 static void collapse_huge_page(struct mm_struct *mm,
 				   unsigned long address,
 				   struct page **hpage,
@@ -2515,7 +2670,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	pgtable_t pgtable;
 	struct page *new_page;
 	spinlock_t *pmd_ptl, *pte_ptl;
-	int isolated;
+	int isolated, result = 0;
 	unsigned long hstart, hend;
 	struct mem_cgroup *memcg;
 	unsigned long mmun_start;	/* For mmu_notifiers */
@@ -2530,12 +2685,16 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	/* release the mmap_sem read lock. */
 	new_page = khugepaged_alloc_page(hpage, gfp, mm, vma, address, node);
-	if (!new_page)
-		return;
+	if (!new_page) {
+		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
+		goto out_nolock;
+	}
 
 	if (unlikely(mem_cgroup_try_charge(new_page, mm,
-					   gfp, &memcg)))
-		return;
+					   gfp, &memcg))) {
+		result = SCAN_CGROUP_CHARGE_FAIL;
+		goto out_nolock;
+	}
 
 	/*
 	 * Prevent all access to pagetables with the exception of
@@ -2543,24 +2702,36 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	down_write(&mm->mmap_sem);
-	if (unlikely(khugepaged_test_exit(mm)))
+	if (unlikely(khugepaged_test_exit(mm))) {
+		result = SCAN_ANY_PROCESS;
 		goto out;
+	}
 
 	vma = find_vma(mm, address);
-	if (!vma)
+	if (!vma) {
+		result = SCAN_VMA_NULL;
 		goto out;
+	}
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
-	if (address < hstart || address + HPAGE_PMD_SIZE > hend)
+	if (address < hstart || address + HPAGE_PMD_SIZE > hend) {
+		result = SCAN_ADDRESS_RANGE;
 		goto out;
-	if (!hugepage_vma_check(vma))
+	}
+	if (!hugepage_vma_check(vma)) {
+		result = SCAN_VMA_CHECK;
 		goto out;
+	}
 	pmd = mm_find_pmd(mm, address);
-	if (!pmd)
+	if (!pmd) {
+		result = SCAN_PMD_NULL;
 		goto out;
+	}
 
 	anon_vma_lock_write(vma->anon_vma);
 
+	__collapse_huge_page_swapin(mm, vma, address, pmd, pte);
+
 	pte = pte_offset_map(pmd, address);
 	pte_ptl = pte_lockptr(mm, pmd);
 
@@ -2594,6 +2765,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
 		spin_unlock(pmd_ptl);
 		anon_vma_unlock_write(vma->anon_vma);
+		result = SCAN_FAIL;
 		goto out;
 	}
 
@@ -2631,10 +2803,15 @@ static void collapse_huge_page(struct mm_struct *mm,
 	*hpage = NULL;
 
 	khugepaged_pages_collapsed++;
+	result = SCAN_SUCCEED;
 out_up_write:
 	up_write(&mm->mmap_sem);
+	trace_mm_collapse_huge_page(mm, isolated, result);
 	return;
 
+out_nolock:
+	trace_mm_collapse_huge_page(mm, isolated, result);
+	return;
 out:
 	mem_cgroup_cancel_charge(new_page, memcg);
 	goto out_up_write;
@@ -2647,39 +2824,55 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 {
 	pmd_t *pmd;
 	pte_t *pte, *_pte;
-	int ret = 0, none_or_zero = 0;
-	struct page *page;
+	int ret = 0, none_or_zero = 0, result = 0;
+	struct page *page = NULL;
 	unsigned long _address;
 	spinlock_t *ptl;
-	int node = NUMA_NO_NODE;
+	int node = NUMA_NO_NODE, unmapped = 0;
 	bool writable = false, referenced = false;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
 	pmd = mm_find_pmd(mm, address);
-	if (!pmd)
+	if (!pmd) {
+		result = SCAN_PMD_NULL;
 		goto out;
+	}
 
 	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
+		if (is_swap_pte(pteval)) {
+			if (++unmapped <= khugepaged_max_ptes_swap) {
+				continue;
+			} else {
+				ret = SCAN_EXCEED_SWAP_PTE;
+				goto out_unmap;
+			}
+		}
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
 			if (!userfaultfd_armed(vma) &&
-			    ++none_or_zero <= khugepaged_max_ptes_none)
+			    ++none_or_zero <= khugepaged_max_ptes_none) {
 				continue;
-			else
+			} else {
+				result = SCAN_EXCEED_NONE_PTE;
 				goto out_unmap;
+			}
 		}
-		if (!pte_present(pteval))
+		if (!pte_present(pteval)) {
+			result = SCAN_PTE_NON_PRESENT;
 			goto out_unmap;
+		}
 		if (pte_write(pteval))
 			writable = true;
 
 		page = vm_normal_page(vma, _address, pteval);
-		if (unlikely(!page))
+		if (unlikely(!page)) {
+			result = SCAN_PAGE_NULL;
 			goto out_unmap;
+		}
 		/*
 		 * Record which node the original page is from and save this
 		 * information to khugepaged_node_load[].
@@ -2687,26 +2880,49 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		 * hit record.
 		 */
 		node = page_to_nid(page);
-		if (khugepaged_scan_abort(node))
+		if (khugepaged_scan_abort(node)) {
+			result = SCAN_SCAN_ABORT;
 			goto out_unmap;
+		}
 		khugepaged_node_load[node]++;
 		VM_BUG_ON_PAGE(PageCompound(page), page);
-		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
+		if (!PageLRU(page)) {
+		result = SCAN_SCAN_ABORT;
 			goto out_unmap;
+		}
+		if (PageLocked(page)) {
+			result = SCAN_PAGE_LOCK;
+			goto out_unmap;
+		}
+		if (!PageAnon(page)) {
+			result = SCAN_PAGE_ANON;
+			goto out_unmap;
+		}
+
 		/*
 		 * cannot use mapcount: can't collapse if there's a gup pin.
 		 * The page must only be referenced by the scanned process
 		 * and page swap cache.
 		 */
-		if (page_count(page) != 1 + !!PageSwapCache(page))
+		if (page_count(page) != 1 + !!PageSwapCache(page)) {
+			result = SCAN_PAGE_COUNT;
 			goto out_unmap;
+		}
 		if (pte_young(pteval) ||
 		    page_is_young(page) || PageReferenced(page) ||
 		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = true;
 	}
-	if (referenced && writable)
-		ret = 1;
+	if (writable) {
+		if (referenced) {
+			result = SCAN_SUCCEED;
+			ret = 1;
+		} else {
+			result = SCAN_NO_REFERENCED_PAGE;
+		}
+	} else {
+		result = SCAN_PAGE_RO;
+	}
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
 	if (ret) {
@@ -2715,6 +2931,8 @@ out_unmap:
 		collapse_huge_page(mm, address, hpage, vma, node);
 	}
 out:
+	trace_mm_khugepaged_scan_pmd(mm, page_to_pfn(page), writable, referenced,
+				     none_or_zero, result, unmapped);
 	return ret;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 999fb0aef8f1..dc8f879d2eaa 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -994,23 +994,22 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 
 #if defined(CONFIG_CMA) && defined(CONFIG_X86_64)
 static void destroy_compound_gigantic_page(struct page *page,
-					unsigned long order)
+					unsigned int order)
 {
 	int i;
 	int nr_pages = 1 << order;
 	struct page *p = page + 1;
 
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
-		__ClearPageTail(p);
+		clear_compound_head(p);
 		set_page_refcounted(p);
-		p->first_page = NULL;
 	}
 
 	set_compound_order(page, 0);
 	__ClearPageHead(page);
 }
 
-static void free_gigantic_page(struct page *page, unsigned order)
+static void free_gigantic_page(struct page *page, unsigned int order)
 {
 	free_contig_range(page_to_pfn(page), 1 << order);
 }
@@ -1054,7 +1053,7 @@ static bool zone_spans_last_pfn(const struct zone *zone,
 	return zone_spans_pfn(zone, last_pfn);
 }
 
-static struct page *alloc_gigantic_page(int nid, unsigned order)
+static struct page *alloc_gigantic_page(int nid, unsigned int order)
 {
 	unsigned long nr_pages = 1 << order;
 	unsigned long ret, pfn, flags;
@@ -1090,7 +1089,7 @@ static struct page *alloc_gigantic_page(int nid, unsigned order)
 }
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
-static void prep_compound_gigantic_page(struct page *page, unsigned long order);
+static void prep_compound_gigantic_page(struct page *page, unsigned int order);
 
 static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid)
 {
@@ -1123,9 +1122,9 @@ static int alloc_fresh_gigantic_page(struct hstate *h,
 static inline bool gigantic_page_supported(void) { return true; }
 #else
 static inline bool gigantic_page_supported(void) { return false; }
-static inline void free_gigantic_page(struct page *page, unsigned order) { }
+static inline void free_gigantic_page(struct page *page, unsigned int order) { }
 static inline void destroy_compound_gigantic_page(struct page *page,
-						unsigned long order) { }
+						unsigned int order) { }
 static inline int alloc_fresh_gigantic_page(struct hstate *h,
 					nodemask_t *nodes_allowed) { return 0; }
 #endif
@@ -1146,7 +1145,7 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 				1 << PG_writeback);
 	}
 	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
-	set_compound_page_dtor(page, NULL);
+	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
 		destroy_compound_gigantic_page(page, huge_page_order(h));
@@ -1242,7 +1241,7 @@ void free_huge_page(struct page *page)
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	INIT_LIST_HEAD(&page->lru);
-	set_compound_page_dtor(page, free_huge_page);
+	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 	spin_lock(&hugetlb_lock);
 	set_hugetlb_cgroup(page, NULL);
 	h->nr_huge_pages++;
@@ -1251,7 +1250,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	put_page(page); /* free it into the hugepage allocator */
 }
 
-static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+static void prep_compound_gigantic_page(struct page *page, unsigned int order)
 {
 	int i;
 	int nr_pages = 1 << order;
@@ -1276,10 +1275,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 		 */
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
-		p->first_page = page;
-		/* Make sure p->first_page is always valid for PageTail() */
-		smp_wmb();
-		__SetPageTail(p);
+		set_compound_head(p, page);
 	}
 }
 
@@ -1294,7 +1290,7 @@ int PageHuge(struct page *page)
 		return 0;
 
 	page = compound_head(page);
-	return get_compound_page_dtor(page) == free_huge_page;
+	return page[1].compound_dtor == HUGETLB_PAGE_DTOR;
 }
 EXPORT_SYMBOL_GPL(PageHuge);
 
@@ -1491,7 +1487,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 	if (page) {
 		INIT_LIST_HEAD(&page->lru);
 		r_nid = page_to_nid(page);
-		set_compound_page_dtor(page, free_huge_page);
+		set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 		set_hugetlb_cgroup(page, NULL);
 		/*
 		 * We incremented the global counters already
@@ -1872,7 +1868,8 @@ found:
 	return 1;
 }
 
-static void __init prep_compound_huge_page(struct page *page, int order)
+static void __init prep_compound_huge_page(struct page *page,
+		unsigned int order)
 {
 	if (unlikely(order > (MAX_ORDER - 1)))
 		prep_compound_gigantic_page(page, order);
@@ -2583,7 +2580,7 @@ static int __init hugetlb_init(void)
 module_init(hugetlb_init);
 
 /* Should be called on processing a hugepagesz=... option */
-void __init hugetlb_add_hstate(unsigned order)
+void __init hugetlb_add_hstate(unsigned int order)
 {
 	struct hstate *h;
 	unsigned long i;
@@ -2790,6 +2787,49 @@ void hugetlb_show_meminfo(void)
 				1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
 }
 
+static unsigned long mm_hstate_usage(struct mm_struct *mm, int hs_idx)
+{
+	if (!mm->hugetlb_usage)
+		return 0;
+	return atomic_long_read(&mm->hugetlb_usage->count[hs_idx]);
+}
+
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
+{
+	int i;
+	unsigned long total_usage = 0;
+
+	for (i = 0; i < HUGE_MAX_HSTATE; i++) {
+		total_usage += mm_hstate_usage(mm, i) *
+			(huge_page_size(&hstates[i]) >> 10);
+	}
+
+	seq_printf(m, "HugetlbPages:\t%8lu kB (", total_usage);
+	for (i = 0; i < HUGE_MAX_HSTATE; i++) {
+		if (huge_page_order(&hstates[i]) == 0)
+			break;
+		if (i > 0)
+			seq_puts(m, " ");
+
+		seq_printf(m, "%ld*%lukB", mm_hstate_usage(mm, i),
+			huge_page_size(&hstates[i]) >> 10);
+	}
+	seq_puts(m, ")\n");
+}
+
+int hugetlb_fork(struct mm_struct *new, struct mm_struct *old)
+{
+	if (old->hugetlb_usage) {
+		new->hugetlb_usage = kmalloc(sizeof(struct hugetlb_usage),
+							GFP_KERNEL);
+		if (!new->hugetlb_usage)
+			return -ENOMEM;
+		memcpy(new->hugetlb_usage, old->hugetlb_usage,
+			sizeof(struct hugetlb_usage));
+	}
+	return 0;
+}
+
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
@@ -3025,6 +3065,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			get_page(ptepage);
 			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
+			inc_hugetlb_count(dst, h);
 		}
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
@@ -3105,6 +3146,7 @@ again:
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);
 
+		dec_hugetlb_count(mm, h);
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
 		if (force_flush) {
@@ -3501,6 +3543,7 @@ retry:
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
 
+	inc_hugetlb_count(mm, h);
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
 		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
@@ -4020,8 +4063,8 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
 	unsigned long s_end = sbase + PUD_SIZE;
 
 	/* Allow segments to share if only one is marked locked */
-	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
-	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+	unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+	unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK;
 
 	/*
 	 * match the virtual addresses, permission and the alignment of the
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 6e0057439a46..6a4426372698 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -384,7 +384,7 @@ void __init hugetlb_cgroup_file_init(void)
 		/*
 		 * Add cgroup control files only if the huge page consists
 		 * of more than two normal pages. This is because we use
-		 * page[2].lru.next for storing cgroup details.
+		 * page[2].private for storing cgroup details.
 		 */
 		if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER)
 			__hugetlb_cgroup_file_init(hstate_index(h));
diff --git a/mm/internal.h b/mm/internal.h
index bc0fa9a69e46..247a381256e8 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -14,6 +14,10 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 
+extern int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long address, pte_t *page_table, pmd_t *pmd,
+			unsigned int flags, pte_t orig_pte);
+
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 
@@ -61,9 +65,9 @@ static inline void __get_page_tail_foll(struct page *page,
 	 * speculative page access (like in
 	 * page_cache_get_speculative()) on tail pages.
 	 */
-	VM_BUG_ON_PAGE(atomic_read(&page->first_page->_count) <= 0, page);
+	VM_BUG_ON_PAGE(atomic_read(&compound_head(page)->_count) <= 0, page);
 	if (get_page_head)
-		atomic_inc(&page->first_page->_count);
+		atomic_inc(&compound_head(page)->_count);
 	get_huge_page_tail(page);
 }
 
@@ -157,7 +161,7 @@ __find_buddy_index(unsigned long page_idx, unsigned int order)
 extern int __isolate_free_page(struct page *page, unsigned int order);
 extern void __free_pages_bootmem(struct page *page, unsigned long pfn,
 					unsigned int order);
-extern void prep_compound_page(struct page *page, unsigned long order);
+extern void prep_compound_page(struct page *page, unsigned int order);
 #ifdef CONFIG_MEMORY_FAILURE
 extern bool is_free_buddy_page(struct page *page);
 #endif
@@ -215,7 +219,7 @@ int find_suitable_fallback(struct free_area *area, unsigned int order,
  * page cannot be allocated or merged in parallel. Alternatively, it must
  * handle invalid values gracefully, and use page_order_unsafe() below.
  */
-static inline unsigned long page_order(struct page *page)
+static inline unsigned int page_order(struct page *page)
 {
 	/* PageBuddy() must be checked by the caller */
 	return page_private(page);
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 7b28e9cdf1c7..d41b21bce6a0 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -4,7 +4,7 @@
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
- * Some of code borrowed from https://github.com/xairy/linux by
+ * Some code borrowed from https://github.com/xairy/kasan-prototype by
  *        Andrey Konovalov <adech.fo@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -86,6 +86,11 @@ static __always_inline bool memory_is_poisoned_2(unsigned long addr)
 		if (memory_is_poisoned_1(addr + 1))
 			return true;
 
+		/*
+		 * If single shadow byte covers 2-byte access, we don't
+		 * need to do anything more. Otherwise, test the first
+		 * shadow byte.
+		 */
 		if (likely(((addr + 1) & KASAN_SHADOW_MASK) != 0))
 			return false;
 
@@ -103,6 +108,11 @@ static __always_inline bool memory_is_poisoned_4(unsigned long addr)
 		if (memory_is_poisoned_1(addr + 3))
 			return true;
 
+		/*
+		 * If single shadow byte covers 4-byte access, we don't
+		 * need to do anything more. Otherwise, test the first
+		 * shadow byte.
+		 */
 		if (likely(((addr + 3) & KASAN_SHADOW_MASK) >= 3))
 			return false;
 
@@ -120,7 +130,12 @@ static __always_inline bool memory_is_poisoned_8(unsigned long addr)
 		if (memory_is_poisoned_1(addr + 7))
 			return true;
 
-		if (likely(((addr + 7) & KASAN_SHADOW_MASK) >= 7))
+		/*
+		 * If single shadow byte covers 8-byte access, we don't
+		 * need to do anything more. Otherwise, test the first
+		 * shadow byte.
+		 */
+		if (likely(IS_ALIGNED(addr, KASAN_SHADOW_SCALE_SIZE)))
 			return false;
 
 		return unlikely(*(u8 *)shadow_addr);
@@ -135,12 +150,16 @@ static __always_inline bool memory_is_poisoned_16(unsigned long addr)
 
 	if (unlikely(*shadow_addr)) {
 		u16 shadow_first_bytes = *(u16 *)shadow_addr;
-		s8 last_byte = (addr + 15) & KASAN_SHADOW_MASK;
 
 		if (unlikely(shadow_first_bytes))
 			return true;
 
-		if (likely(!last_byte))
+		/*
+		 * If two shadow bytes covers 16-byte access, we don't
+		 * need to do anything more. Otherwise, test the last
+		 * shadow byte.
+		 */
+		if (likely(IS_ALIGNED(addr, KASAN_SHADOW_SCALE_SIZE)))
 			return false;
 
 		return memory_is_poisoned_1(addr + 15);
@@ -204,7 +223,7 @@ static __always_inline bool memory_is_poisoned_n(unsigned long addr,
 		s8 *last_shadow = (s8 *)kasan_mem_to_shadow((void *)last_byte);
 
 		if (unlikely(ret != (unsigned long)last_shadow ||
-			((last_byte & KASAN_SHADOW_MASK) >= *last_shadow)))
+			((long)(last_byte & KASAN_SHADOW_MASK) >= *last_shadow)))
 			return true;
 	}
 	return false;
@@ -236,18 +255,12 @@ static __always_inline bool memory_is_poisoned(unsigned long addr, size_t size)
 static __always_inline void check_memory_region(unsigned long addr,
 						size_t size, bool write)
 {
-	struct kasan_access_info info;
-
 	if (unlikely(size == 0))
 		return;
 
 	if (unlikely((void *)addr <
 		kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) {
-		info.access_addr = (void *)addr;
-		info.access_size = size;
-		info.is_write = write;
-		info.ip = _RET_IP_;
-		kasan_report_user_access(&info);
+		kasan_report(addr, size, write, _RET_IP_);
 		return;
 	}
 
@@ -525,7 +538,7 @@ static int kasan_mem_notifier(struct notifier_block *nb,
 
 static int __init kasan_memhotplug_init(void)
 {
-	pr_err("WARNING: KASan doesn't support memory hot-add\n");
+	pr_err("WARNING: KASAN doesn't support memory hot-add\n");
 	pr_err("Memory hot-add will be disabled\n");
 
 	hotplug_memory_notifier(kasan_mem_notifier, 0);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index c242adf6bc85..4f6c62e5c21e 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -54,16 +54,13 @@ struct kasan_global {
 #endif
 };
 
-void kasan_report_error(struct kasan_access_info *info);
-void kasan_report_user_access(struct kasan_access_info *info);
-
 static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 {
 	return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET)
 		<< KASAN_SHADOW_SCALE_SHIFT);
 }
 
-static inline bool kasan_enabled(void)
+static inline bool kasan_report_enabled(void)
 {
 	return !current->kasan_depth;
 }
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index e07c94fbd0ac..f5e068afb58e 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -4,7 +4,7 @@
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
- * Some of code borrowed from https://github.com/xairy/linux by
+ * Some code borrowed from https://github.com/xairy/kasan-prototype by
  *        Andrey Konovalov <adech.fo@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -22,6 +22,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/kasan.h>
+#include <linux/module.h>
 
 #include <asm/sections.h>
 
@@ -48,34 +49,49 @@ static const void *find_first_bad_addr(const void *addr, size_t size)
 
 static void print_error_description(struct kasan_access_info *info)
 {
-	const char *bug_type = "unknown crash";
-	u8 shadow_val;
+	const char *bug_type = "unknown-crash";
+	u8 *shadow_addr;
 
 	info->first_bad_addr = find_first_bad_addr(info->access_addr,
 						info->access_size);
 
-	shadow_val = *(u8 *)kasan_mem_to_shadow(info->first_bad_addr);
+	shadow_addr = (u8 *)kasan_mem_to_shadow(info->first_bad_addr);
 
-	switch (shadow_val) {
-	case KASAN_FREE_PAGE:
-	case KASAN_KMALLOC_FREE:
-		bug_type = "use after free";
+	/*
+	 * If shadow byte value is in [0, KASAN_SHADOW_SCALE_SIZE) we can look
+	 * at the next shadow byte to determine the type of the bad access.
+	 */
+	if (*shadow_addr > 0 && *shadow_addr <= KASAN_SHADOW_SCALE_SIZE - 1)
+		shadow_addr++;
+
+	switch (*shadow_addr) {
+	case 0 ... KASAN_SHADOW_SCALE_SIZE - 1:
+		/*
+		 * In theory it's still possible to see these shadow values
+		 * due to a data race in the kernel code.
+		 */
+		bug_type = "out-of-bounds";
 		break;
 	case KASAN_PAGE_REDZONE:
 	case KASAN_KMALLOC_REDZONE:
+		bug_type = "slab-out-of-bounds";
+		break;
 	case KASAN_GLOBAL_REDZONE:
-	case 0 ... KASAN_SHADOW_SCALE_SIZE - 1:
-		bug_type = "out of bounds access";
+		bug_type = "global-out-of-bounds";
 		break;
 	case KASAN_STACK_LEFT:
 	case KASAN_STACK_MID:
 	case KASAN_STACK_RIGHT:
 	case KASAN_STACK_PARTIAL:
-		bug_type = "out of bounds on stack";
+		bug_type = "stack-out-of-bounds";
+		break;
+	case KASAN_FREE_PAGE:
+	case KASAN_KMALLOC_FREE:
+		bug_type = "use-after-free";
 		break;
 	}
 
-	pr_err("BUG: KASan: %s in %pS at addr %p\n",
+	pr_err("BUG: KASAN: %s in %pS at addr %p\n",
 		bug_type, (void *)info->ip,
 		info->access_addr);
 	pr_err("%s of size %zu by task %s/%d\n",
@@ -85,9 +101,11 @@ static void print_error_description(struct kasan_access_info *info)
 
 static inline bool kernel_or_module_addr(const void *addr)
 {
-	return (addr >= (void *)_stext && addr < (void *)_end)
-		|| (addr >= (void *)MODULES_VADDR
-			&& addr < (void *)MODULES_END);
+	if (addr >= (void *)_stext && addr < (void *)_end)
+		return true;
+	if (is_module_address((unsigned long)addr))
+		return true;
+	return false;
 }
 
 static inline bool init_task_stack_addr(const void *addr)
@@ -161,15 +179,19 @@ static void print_shadow_for_address(const void *addr)
 	for (i = -SHADOW_ROWS_AROUND_ADDR; i <= SHADOW_ROWS_AROUND_ADDR; i++) {
 		const void *kaddr = kasan_shadow_to_mem(shadow_row);
 		char buffer[4 + (BITS_PER_LONG/8)*2];
+		char shadow_buf[SHADOW_BYTES_PER_ROW];
 
 		snprintf(buffer, sizeof(buffer),
 			(i == 0) ? ">%p: " : " %p: ", kaddr);
-
-		kasan_disable_current();
+		/*
+		 * We should not pass a shadow pointer to generic
+		 * function, because generic functions may try to
+		 * access kasan mapping for the passed address.
+		 */
+		memcpy(shadow_buf, shadow_row, SHADOW_BYTES_PER_ROW);
 		print_hex_dump(KERN_ERR, buffer,
 			DUMP_PREFIX_NONE, SHADOW_BYTES_PER_ROW, 1,
-			shadow_row, SHADOW_BYTES_PER_ROW, 0);
-		kasan_enable_current();
+			shadow_buf, SHADOW_BYTES_PER_ROW, 0);
 
 		if (row_is_guilty(shadow_row, shadow))
 			pr_err("%*c\n",
@@ -182,37 +204,42 @@ static void print_shadow_for_address(const void *addr)
 
 static DEFINE_SPINLOCK(report_lock);
 
-void kasan_report_error(struct kasan_access_info *info)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&report_lock, flags);
-	pr_err("================================="
-		"=================================\n");
-	print_error_description(info);
-	print_address_description(info);
-	print_shadow_for_address(info->first_bad_addr);
-	pr_err("================================="
-		"=================================\n");
-	spin_unlock_irqrestore(&report_lock, flags);
-}
-
-void kasan_report_user_access(struct kasan_access_info *info)
+static void kasan_report_error(struct kasan_access_info *info)
 {
 	unsigned long flags;
+	const char *bug_type;
 
+	/*
+	 * Make sure we don't end up in loop.
+	 */
+	kasan_disable_current();
 	spin_lock_irqsave(&report_lock, flags);
 	pr_err("================================="
 		"=================================\n");
-	pr_err("BUG: KASan: user-memory-access on address %p\n",
-		info->access_addr);
-	pr_err("%s of size %zu by task %s/%d\n",
-		info->is_write ? "Write" : "Read",
-		info->access_size, current->comm, task_pid_nr(current));
-	dump_stack();
+	if (info->access_addr <
+			kasan_shadow_to_mem((void *)KASAN_SHADOW_START)) {
+		if ((unsigned long)info->access_addr < PAGE_SIZE)
+			bug_type = "null-ptr-deref";
+		else if ((unsigned long)info->access_addr < TASK_SIZE)
+			bug_type = "user-memory-access";
+		else
+			bug_type = "wild-memory-access";
+		pr_err("BUG: KASAN: %s on address %p\n",
+			bug_type, info->access_addr);
+		pr_err("%s of size %zu by task %s/%d\n",
+			info->is_write ? "Write" : "Read",
+			info->access_size, current->comm,
+			task_pid_nr(current));
+		dump_stack();
+	} else {
+		print_error_description(info);
+		print_address_description(info);
+		print_shadow_for_address(info->first_bad_addr);
+	}
 	pr_err("================================="
 		"=================================\n");
 	spin_unlock_irqrestore(&report_lock, flags);
+	kasan_enable_current();
 }
 
 void kasan_report(unsigned long addr, size_t size,
@@ -220,13 +247,14 @@ void kasan_report(unsigned long addr, size_t size,
 {
 	struct kasan_access_info info;
 
-	if (likely(!kasan_enabled()))
+	if (likely(!kasan_report_enabled()))
 		return;
 
 	info.access_addr = (void *)addr;
 	info.access_size = size;
 	info.is_write = is_write;
 	info.ip = ip;
+
 	kasan_report_error(&info);
 }
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 77191eccdc6f..19423a45d7d7 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -479,7 +479,7 @@ static void put_object(struct kmemleak_object *object)
 static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
 {
 	unsigned long flags;
-	struct kmemleak_object *object = NULL;
+	struct kmemleak_object *object;
 
 	rcu_read_lock();
 	read_lock_irqsave(&kmemleak_lock, flags);
diff --git a/mm/ksm.c b/mm/ksm.c
index 7ee101eaacdf..bc7be0ee2080 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1884,7 +1884,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
 
 		SetPageDirty(new_page);
 		__SetPageUptodate(new_page);
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 	}
 
 	return new_page;
diff --git a/mm/list_lru.c b/mm/list_lru.c
index e1da19fac1b3..28237476b055 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -42,6 +42,10 @@ static void list_lru_unregister(struct list_lru *lru)
 #ifdef CONFIG_MEMCG_KMEM
 static inline bool list_lru_memcg_aware(struct list_lru *lru)
 {
+	/*
+	 * This needs node 0 to be always present, even
+	 * in the systems supporting sparse numa ids.
+	 */
 	return !!lru->node[0].memcg_lrus;
 }
 
@@ -377,16 +381,20 @@ static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
 {
 	int i;
 
-	for (i = 0; i < nr_node_ids; i++) {
-		if (!memcg_aware)
-			lru->node[i].memcg_lrus = NULL;
-		else if (memcg_init_list_lru_node(&lru->node[i]))
+	if (!memcg_aware)
+		return 0;
+
+	for_each_node(i) {
+		if (memcg_init_list_lru_node(&lru->node[i]))
 			goto fail;
 	}
 	return 0;
 fail:
-	for (i = i - 1; i >= 0; i--)
+	for (i = i - 1; i >= 0; i--) {
+		if (!lru->node[i].memcg_lrus)
+			continue;
 		memcg_destroy_list_lru_node(&lru->node[i]);
+	}
 	return -ENOMEM;
 }
 
@@ -397,7 +405,7 @@ static void memcg_destroy_list_lru(struct list_lru *lru)
 	if (!list_lru_memcg_aware(lru))
 		return;
 
-	for (i = 0; i < nr_node_ids; i++)
+	for_each_node(i)
 		memcg_destroy_list_lru_node(&lru->node[i]);
 }
 
@@ -409,16 +417,20 @@ static int memcg_update_list_lru(struct list_lru *lru,
 	if (!list_lru_memcg_aware(lru))
 		return 0;
 
-	for (i = 0; i < nr_node_ids; i++) {
+	for_each_node(i) {
 		if (memcg_update_list_lru_node(&lru->node[i],
 					       old_size, new_size))
 			goto fail;
 	}
 	return 0;
 fail:
-	for (i = i - 1; i >= 0; i--)
+	for (i = i - 1; i >= 0; i--) {
+		if (!lru->node[i].memcg_lrus)
+			continue;
+
 		memcg_cancel_update_list_lru_node(&lru->node[i],
 						  old_size, new_size);
+	}
 	return -ENOMEM;
 }
 
@@ -430,7 +442,7 @@ static void memcg_cancel_update_list_lru(struct list_lru *lru,
 	if (!list_lru_memcg_aware(lru))
 		return;
 
-	for (i = 0; i < nr_node_ids; i++)
+	for_each_node(i)
 		memcg_cancel_update_list_lru_node(&lru->node[i],
 						  old_size, new_size);
 }
@@ -485,7 +497,7 @@ static void memcg_drain_list_lru(struct list_lru *lru,
 	if (!list_lru_memcg_aware(lru))
 		return;
 
-	for (i = 0; i < nr_node_ids; i++)
+	for_each_node(i)
 		memcg_drain_list_lru_node(&lru->node[i], src_idx, dst_idx);
 }
 
@@ -522,7 +534,7 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 	if (!lru->node)
 		goto out;
 
-	for (i = 0; i < nr_node_ids; i++) {
+	for_each_node(i) {
 		spin_lock_init(&lru->node[i].lock);
 		if (key)
 			lockdep_set_class(&lru->node[i].lock, key);
diff --git a/mm/maccess.c b/mm/maccess.c
index 34fe24759ed1..1b13638d238d 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -13,6 +13,11 @@
  *
  * Safely read from address @src to the buffer at @dst.  If a kernel fault
  * happens, handle that and return -EFAULT.
+ *
+ * We ensure that the copy_from_user is executed in atomic context so that
+ * do_page_fault() doesn't attempt to take mmap_sem.  This makes
+ * probe_kernel_read() suitable for use within regions where the caller
+ * already holds mmap_sem, or other locks which nest inside mmap_sem.
  */
 
 long __weak probe_kernel_read(void *dst, const void *src, size_t size)
diff --git a/mm/madvise.c b/mm/madvise.c
index c889fcbb530e..16441f550cdf 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -20,6 +20,14 @@
 #include <linux/backing-dev.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/tlb.h>
+
+struct madvise_free_private {
+	struct vm_area_struct *vma;
+	struct mmu_gather *tlb;
+};
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -32,6 +40,7 @@ static int madvise_need_mmap_write(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 		return 0;
 	default:
 		/* be safe, default to 1. list exceptions explicitly */
@@ -256,6 +265,164 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	return 0;
 }
 
+static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+
+{
+	struct madvise_free_private *fp = walk->private;
+	struct mmu_gather *tlb = fp->tlb;
+	struct mm_struct *mm = tlb->mm;
+	struct vm_area_struct *vma = fp->vma;
+	spinlock_t *ptl;
+	pte_t *pte, ptent;
+	struct page *page;
+	swp_entry_t entry;
+	unsigned long next;
+	int nr_swap = 0;
+
+	next = pmd_addr_end(addr, end);
+	if (pmd_trans_huge(*pmd)) {
+		if (next - addr != HPAGE_PMD_SIZE)
+			split_huge_page_pmd(vma, addr, pmd);
+		else if (!madvise_free_huge_pmd(tlb, vma, pmd, addr))
+			goto next;
+		/* fall through */
+	}
+
+	if (pmd_trans_unstable(pmd))
+		return 0;
+
+	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	arch_enter_lazy_mmu_mode();
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+
+		if (pte_none(ptent))
+			continue;
+		/*
+		 * If the pte has swp_entry, just clear page table to
+		 * prevent swap-in which is more expensive rather than
+		 * (page allocation + zeroing).
+		 */
+		if (!pte_present(ptent)) {
+			entry = pte_to_swp_entry(ptent);
+			if (non_swap_entry(entry))
+				continue;
+			nr_swap--;
+			free_swap_and_cache(entry);
+			pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+			continue;
+		}
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		if (PageSwapCache(page)) {
+			if (!trylock_page(page))
+				continue;
+
+			if (!try_to_free_swap(page)) {
+				unlock_page(page);
+				continue;
+			}
+
+			ClearPageDirty(page);
+			unlock_page(page);
+		}
+
+		/*
+		 * Some of architecture(ex, PPC) don't update TLB
+		 * with set_pte_at and tlb_remove_tlb_entry so for
+		 * the portability, remap the pte with old|clean
+		 * after pte clearing.
+		 */
+		ptent = ptep_get_and_clear_full(mm, addr, pte,
+						tlb->fullmm);
+		ptent = pte_mkold(ptent);
+		ptent = pte_mkclean(ptent);
+		set_pte_at(mm, addr, pte, ptent);
+		if (PageActive(page))
+			deactivate_page(page);
+		tlb_remove_tlb_entry(tlb, pte, addr);
+	}
+
+	if (nr_swap) {
+		if (current->mm == mm)
+			sync_mm_rss(mm);
+
+		add_mm_counter(mm, MM_SWAPENTS, nr_swap);
+	}
+
+	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(pte - 1, ptl);
+next:
+	cond_resched();
+	return 0;
+}
+
+static void madvise_free_page_range(struct mmu_gather *tlb,
+			     struct vm_area_struct *vma,
+			     unsigned long addr, unsigned long end)
+{
+	struct madvise_free_private fp = {
+		.vma = vma,
+		.tlb = tlb,
+	};
+
+	struct mm_walk free_walk = {
+		.pmd_entry = madvise_free_pte_range,
+		.mm = vma->vm_mm,
+		.private = &fp,
+	};
+
+	BUG_ON(addr >= end);
+	tlb_start_vma(tlb, vma);
+	walk_page_range(addr, end, &free_walk);
+	tlb_end_vma(tlb, vma);
+}
+
+static int madvise_free_single_vma(struct vm_area_struct *vma,
+			unsigned long start_addr, unsigned long end_addr)
+{
+	unsigned long start, end;
+	struct mm_struct *mm = vma->vm_mm;
+	struct mmu_gather tlb;
+
+	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+		return -EINVAL;
+
+	/* MADV_FREE works for only anon vma at the moment */
+	if (!vma_is_anonymous(vma))
+		return -EINVAL;
+
+	start = max(vma->vm_start, start_addr);
+	if (start >= vma->vm_end)
+		return -EINVAL;
+	end = min(vma->vm_end, end_addr);
+	if (end <= vma->vm_start)
+		return -EINVAL;
+
+	lru_add_drain();
+	tlb_gather_mmu(&tlb, mm, start, end);
+	update_hiwater_rss(mm);
+
+	mmu_notifier_invalidate_range_start(mm, start, end);
+	madvise_free_page_range(&tlb, vma, start, end);
+	mmu_notifier_invalidate_range_end(mm, start, end);
+	tlb_finish_mmu(&tlb, start, end);
+
+	return 0;
+}
+
+static long madvise_free(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
+			     unsigned long start, unsigned long end)
+{
+	*prev = vma;
+	return madvise_free_single_vma(vma, start, end);
+}
+
 /*
  * Application no longer needs these pages.  If the pages are dirty,
  * it's OK to just throw them away.  The app will be more careful about
@@ -379,6 +546,14 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		return madvise_remove(vma, prev, start, end);
 	case MADV_WILLNEED:
 		return madvise_willneed(vma, prev, start, end);
+	case MADV_FREE:
+		/*
+		 * XXX: In this implementation, MADV_FREE works like
+		 * MADV_DONTNEED on swapless system or full swap.
+		 */
+		if (get_nr_swap_pages() > 0)
+			return madvise_free(vma, prev, start, end);
+		/* passthrough */
 	case MADV_DONTNEED:
 		return madvise_dontneed(vma, prev, start, end);
 	default:
@@ -398,6 +573,7 @@ madvise_behavior_valid(int behavior)
 	case MADV_REMOVE:
 	case MADV_WILLNEED:
 	case MADV_DONTNEED:
+	case MADV_FREE:
 #ifdef CONFIG_KSM
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE:
diff --git a/mm/memblock.c b/mm/memblock.c
index 1c7b647e5897..d300f1329814 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -706,7 +706,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 	return 0;
 }
 
-int __init_memblock memblock_remove_range(struct memblock_type *type,
+static int __init_memblock memblock_remove_range(struct memblock_type *type,
 					  phys_addr_t base, phys_addr_t size)
 {
 	int start_rgn, end_rgn;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6ddaeba34e09..5d9a6e8e96c1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/lockdep.h>
 #include <linux/file.h>
+#include <linux/tracehook.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -1652,7 +1653,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	if (!current->memcg_oom.may_oom)
+	if (!current->memcg_may_oom)
 		return;
 	/*
 	 * We are in the middle of the charge context here, so we
@@ -1669,9 +1670,9 @@ static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 	 * and when we know whether the fault was overall successful.
 	 */
 	css_get(&memcg->css);
-	current->memcg_oom.memcg = memcg;
-	current->memcg_oom.gfp_mask = mask;
-	current->memcg_oom.order = order;
+	current->memcg_in_oom = memcg;
+	current->memcg_oom_gfp_mask = mask;
+	current->memcg_oom_order = order;
 }
 
 /**
@@ -1693,7 +1694,7 @@ static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
  */
 bool mem_cgroup_oom_synchronize(bool handle)
 {
-	struct mem_cgroup *memcg = current->memcg_oom.memcg;
+	struct mem_cgroup *memcg = current->memcg_in_oom;
 	struct oom_wait_info owait;
 	bool locked;
 
@@ -1721,8 +1722,8 @@ bool mem_cgroup_oom_synchronize(bool handle)
 	if (locked && !memcg->oom_kill_disable) {
 		mem_cgroup_unmark_under_oom(memcg);
 		finish_wait(&memcg_oom_waitq, &owait.wait);
-		mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
-					 current->memcg_oom.order);
+		mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask,
+					 current->memcg_oom_order);
 	} else {
 		schedule();
 		mem_cgroup_unmark_under_oom(memcg);
@@ -1739,7 +1740,7 @@ bool mem_cgroup_oom_synchronize(bool handle)
 		memcg_oom_recover(memcg);
 	}
 cleanup:
-	current->memcg_oom.memcg = NULL;
+	current->memcg_in_oom = NULL;
 	css_put(&memcg->css);
 	return true;
 }
@@ -1963,6 +1964,31 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+/*
+ * Scheduled by try_charge() to be executed from the userland return path
+ * and reclaims memory over the high limit.
+ */
+void mem_cgroup_handle_over_high(void)
+{
+	unsigned int nr_pages = current->memcg_nr_pages_over_high;
+	struct mem_cgroup *memcg, *pos;
+
+	if (likely(!nr_pages))
+		return;
+
+	pos = memcg = get_mem_cgroup_from_mm(current->mm);
+
+	do {
+		if (page_counter_read(&pos->memory) <= pos->high)
+			continue;
+		mem_cgroup_events(pos, MEMCG_HIGH, 1);
+		try_to_free_mem_cgroup_pages(pos, nr_pages, GFP_KERNEL, true);
+	} while ((pos = parent_mem_cgroup(pos)));
+
+	css_put(&memcg->css);
+	current->memcg_nr_pages_over_high = 0;
+}
+
 static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		      unsigned int nr_pages)
 {
@@ -1973,13 +1999,12 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long nr_reclaimed;
 	bool may_swap = true;
 	bool drained = false;
-	int ret = 0;
 
 	if (mem_cgroup_is_root(memcg))
-		goto done;
+		return 0;
 retry:
 	if (consume_stock(memcg, nr_pages))
-		goto done;
+		return 0;
 
 	if (!do_swap_account ||
 	    !page_counter_try_charge(&memcg->memsw, batch, &counter)) {
@@ -2007,7 +2032,7 @@ retry:
 	if (unlikely(test_thread_flag(TIF_MEMDIE) ||
 		     fatal_signal_pending(current) ||
 		     current->flags & PF_EXITING))
-		goto bypass;
+		goto force;
 
 	if (unlikely(task_in_memcg_oom(current)))
 		goto nomem;
@@ -2053,10 +2078,10 @@ retry:
 		goto retry;
 
 	if (gfp_mask & __GFP_NOFAIL)
-		goto bypass;
+		goto force;
 
 	if (fatal_signal_pending(current))
-		goto bypass;
+		goto force;
 
 	mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1);
 
@@ -2064,27 +2089,42 @@ retry:
 nomem:
 	if (!(gfp_mask & __GFP_NOFAIL))
 		return -ENOMEM;
-bypass:
-	return -EINTR;
+force:
+	/*
+	 * The allocation either can't fail or will lead to more memory
+	 * being freed very soon.  Allow memory usage go over the limit
+	 * temporarily by force charging it.
+	 */
+	page_counter_charge(&memcg->memory, nr_pages);
+	if (do_swap_account)
+		page_counter_charge(&memcg->memsw, nr_pages);
+	css_get_many(&memcg->css, nr_pages);
+
+	return 0;
 
 done_restock:
 	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
-	if (!(gfp_mask & __GFP_WAIT))
-		goto done;
+
 	/*
-	 * If the hierarchy is above the normal consumption range,
-	 * make the charging task trim their excess contribution.
+	 * If the hierarchy is above the normal consumption range, schedule
+	 * reclaim on returning to userland.  We can perform reclaim here
+	 * if __GFP_WAIT but let's always punt for simplicity and so that
+	 * GFP_KERNEL can consistently be used during reclaim.  @memcg is
+	 * not recorded as it most likely matches current's and won't
+	 * change in the meantime.  As high limit is checked again before
+	 * reclaim, the cost of mismatch is negligible.
 	 */
 	do {
-		if (page_counter_read(&memcg->memory) <= memcg->high)
-			continue;
-		mem_cgroup_events(memcg, MEMCG_HIGH, 1);
-		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
+		if (page_counter_read(&memcg->memory) > memcg->high) {
+			current->memcg_nr_pages_over_high += nr_pages;
+			set_notify_resume(current);
+			break;
+		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
-done:
-	return ret;
+
+	return 0;
 }
 
 static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
@@ -2176,28 +2216,7 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 		return ret;
 
 	ret = try_charge(memcg, gfp, nr_pages);
-	if (ret == -EINTR)  {
-		/*
-		 * try_charge() chose to bypass to root due to OOM kill or
-		 * fatal signal.  Since our only options are to either fail
-		 * the allocation or charge it to this cgroup, do it as a
-		 * temporary condition. But we can't fail. From a kmem/slab
-		 * perspective, the cache has already been selected, by
-		 * mem_cgroup_kmem_get_cache(), so it is too late to change
-		 * our minds.
-		 *
-		 * This condition will only trigger if the task entered
-		 * memcg_charge_kmem in a sane state, but was OOM-killed
-		 * during try_charge() above. Tasks that were already dying
-		 * when the allocation triggers should have been already
-		 * directed to the root cgroup in memcontrol.h
-		 */
-		page_counter_charge(&memcg->memory, nr_pages);
-		if (do_swap_account)
-			page_counter_charge(&memcg->memsw, nr_pages);
-		css_get_many(&memcg->css, nr_pages);
-		ret = 0;
-	} else if (ret)
+	if (ret)
 		page_counter_uncharge(&memcg->kmem, nr_pages);
 
 	return ret;
@@ -4402,22 +4421,10 @@ static int mem_cgroup_do_precharge(unsigned long count)
 		mc.precharge += count;
 		return ret;
 	}
-	if (ret == -EINTR) {
-		cancel_charge(root_mem_cgroup, count);
-		return ret;
-	}
 
 	/* Try charges one by one with reclaim */
 	while (count--) {
 		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
-		/*
-		 * In case of failure, any residual charges against
-		 * mc.to will be dropped by mem_cgroup_clear_mc()
-		 * later on.  However, cancel any charges that are
-		 * bypassed to root right away or they'll be lost.
-		 */
-		if (ret == -EINTR)
-			cancel_charge(root_mem_cgroup, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;
@@ -5322,11 +5329,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 	ret = try_charge(memcg, gfp_mask, nr_pages);
 
 	css_put(&memcg->css);
-
-	if (ret == -EINTR) {
-		memcg = root_mem_cgroup;
-		ret = 0;
-	}
 out:
 	*memcgp = memcg;
 	return ret;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 95882692e747..39591cce45ca 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -775,8 +775,6 @@ static int me_huge_page(struct page *p, unsigned long pfn)
 #define lru		(1UL << PG_lru)
 #define swapbacked	(1UL << PG_swapbacked)
 #define head		(1UL << PG_head)
-#define tail		(1UL << PG_tail)
-#define compound	(1UL << PG_compound)
 #define slab		(1UL << PG_slab)
 #define reserved	(1UL << PG_reserved)
 
@@ -799,12 +797,7 @@ static struct page_state {
 	 */
 	{ slab,		slab,		MF_MSG_SLAB,	me_kernel },
 
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
 	{ head,		head,		MF_MSG_HUGE,		me_huge_page },
-	{ tail,		tail,		MF_MSG_HUGE,		me_huge_page },
-#else
-	{ compound,	compound,	MF_MSG_HUGE,		me_huge_page },
-#endif
 
 	{ sc|dirty,	sc|dirty,	MF_MSG_DIRTY_SWAPCACHE,	me_swapcache_dirty },
 	{ sc|dirty,	sc,		MF_MSG_CLEAN_SWAPCACHE,	me_swapcache_clean },
@@ -1172,7 +1165,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	/*
 	 * We ignore non-LRU pages for good reasons.
 	 * - PG_locked is only well defined for LRU pages and a few others
-	 * - to avoid races with __set_page_locked()
+	 * - to avoid races with __SetPageLocked()
 	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
diff --git a/mm/memory.c b/mm/memory.c
index 9cb27470fee9..3bd465a6fa0d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2441,7 +2441,7 @@ EXPORT_SYMBOL(unmap_mapping_range);
  * We return with the mmap_sem locked or unlocked in the same cases
  * as does filemap_fault().
  */
-static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
+int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
 		unsigned int flags, pte_t orig_pte)
 {
@@ -3087,7 +3087,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
 	 * release semantics to prevent the compiler from undoing this copying.
 	 */
-	mapping = fault_page->mapping;
+	mapping = page_rmapping(fault_page);
 	unlock_page(fault_page);
 	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
 		/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index aa992e2df58a..4b62bbac5512 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -339,8 +339,8 @@ static int __ref ensure_zone_is_initialized(struct zone *zone,
 			unsigned long start_pfn, unsigned long num_pages)
 {
 	if (!zone_is_initialized(zone))
-		return init_currently_empty_zone(zone, start_pfn, num_pages,
-						 MEMMAP_HOTPLUG);
+		return init_currently_empty_zone(zone, start_pfn, num_pages);
+
 	return 0;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index c3cb566af3e2..5fe80755b4c3 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1159,7 +1159,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 			}
 		}
 	}
-	rc = nr_failed + retry;
+	nr_failed += retry;
+	rc = nr_failed;
 out:
 	if (nr_succeeded)
 		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
@@ -1754,7 +1755,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		flush_tlb_range(vma, mmun_start, mmun_end);
 
 	/* Prepare a page as a migration target */
-	__set_page_locked(new_page);
+	__SetPageLocked(new_page);
 	SetPageSwapBacked(new_page);
 
 	/* anon mapping, we can simply copy page->mapping to the new page: */
diff --git a/mm/mincore.c b/mm/mincore.c
index be25efde64a4..14bb9fb37f0c 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -234,7 +234,7 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
 
 	/* This also avoids any overflows on PAGE_CACHE_ALIGN */
 	pages = len >> PAGE_SHIFT;
-	pages += (len & ~PAGE_MASK) != 0;
+	pages += (offset_in_page(len)) != 0;
 
 	if (!access_ok(VERIFY_WRITE, vec, pages))
 		return -EFAULT;
diff --git a/mm/mlock.c b/mm/mlock.c
index 25936680064f..339d9e0949b6 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -422,7 +422,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 void munlock_vma_pages_range(struct vm_area_struct *vma,
 			     unsigned long start, unsigned long end)
 {
-	vma->vm_flags &= ~VM_LOCKED;
+	vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
 
 	while (start < end) {
 		struct page *page = NULL;
@@ -506,7 +506,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
-		goto out;	/* don't set VM_LOCKED,  don't count */
+		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
+		goto out;
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
@@ -554,13 +555,14 @@ out:
 	return ret;
 }
 
-static int do_mlock(unsigned long start, size_t len, int on)
+static int apply_vma_lock_flags(unsigned long start, size_t len,
+				vm_flags_t flags)
 {
 	unsigned long nstart, end, tmp;
 	struct vm_area_struct * vma, * prev;
 	int error;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
+	VM_BUG_ON(offset_in_page(start));
 	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 	if (end < start)
@@ -576,14 +578,11 @@ static int do_mlock(unsigned long start, size_t len, int on)
 		prev = vma;
 
 	for (nstart = start ; ; ) {
-		vm_flags_t newflags;
+		vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
 
-		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
-
-		newflags = vma->vm_flags & ~VM_LOCKED;
-		if (on)
-			newflags |= VM_LOCKED;
+		newflags |= flags;
 
+		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
 		tmp = vma->vm_end;
 		if (tmp > end)
 			tmp = end;
@@ -605,7 +604,7 @@ static int do_mlock(unsigned long start, size_t len, int on)
 	return error;
 }
 
-SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
+static int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
 {
 	unsigned long locked;
 	unsigned long lock_limit;
@@ -616,7 +615,7 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 	lru_add_drain_all();	/* flush pagevec */
 
-	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
+	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
@@ -629,7 +628,7 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 
 	/* check against resource limits */
 	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
-		error = do_mlock(start, len, 1);
+		error = apply_vma_lock_flags(start, len, flags);
 
 	up_write(&current->mm->mmap_sem);
 	if (error)
@@ -641,37 +640,75 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 	return 0;
 }
 
+SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
+{
+	return do_mlock(start, len, VM_LOCKED);
+}
+
+SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
+{
+	vm_flags_t vm_flags = VM_LOCKED;
+
+	if (flags & ~MLOCK_ONFAULT)
+		return -EINVAL;
+
+	if (flags & MLOCK_ONFAULT)
+		vm_flags |= VM_LOCKONFAULT;
+
+	return do_mlock(start, len, vm_flags);
+}
+
 SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
-	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
+	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 
 	down_write(&current->mm->mmap_sem);
-	ret = do_mlock(start, len, 0);
+	ret = apply_vma_lock_flags(start, len, 0);
 	up_write(&current->mm->mmap_sem);
 
 	return ret;
 }
 
-static int do_mlockall(int flags)
+/*
+ * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
+ * and translate into the appropriate modifications to mm->def_flags and/or the
+ * flags for all current VMAs.
+ *
+ * There are a couple of subtleties with this.  If mlockall() is called multiple
+ * times with different flags, the values do not necessarily stack.  If mlockall
+ * is called once including the MCL_FUTURE flag and then a second time without
+ * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
+ */
+static int apply_mlockall_flags(int flags)
 {
 	struct vm_area_struct * vma, * prev = NULL;
+	vm_flags_t to_add = 0;
 
-	if (flags & MCL_FUTURE)
+	current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
+	if (flags & MCL_FUTURE) {
 		current->mm->def_flags |= VM_LOCKED;
-	else
-		current->mm->def_flags &= ~VM_LOCKED;
-	if (flags == MCL_FUTURE)
-		goto out;
+
+		if (flags & MCL_ONFAULT)
+			current->mm->def_flags |= VM_LOCKONFAULT;
+
+		if (!(flags & MCL_CURRENT))
+			goto out;
+	}
+
+	if (flags & MCL_CURRENT) {
+		to_add |= VM_LOCKED;
+		if (flags & MCL_ONFAULT)
+			to_add |= VM_LOCKONFAULT;
+	}
 
 	for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
 		vm_flags_t newflags;
 
-		newflags = vma->vm_flags & ~VM_LOCKED;
-		if (flags & MCL_CURRENT)
-			newflags |= VM_LOCKED;
+		newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+		newflags |= to_add;
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
@@ -684,14 +721,13 @@ out:
 SYSCALL_DEFINE1(mlockall, int, flags)
 {
 	unsigned long lock_limit;
-	int ret = -EINVAL;
+	int ret;
 
-	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
-		goto out;
+	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)))
+		return -EINVAL;
 
-	ret = -EPERM;
 	if (!can_do_mlock())
-		goto out;
+		return -EPERM;
 
 	if (flags & MCL_CURRENT)
 		lru_add_drain_all();	/* flush pagevec */
@@ -704,11 +740,11 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 
 	if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
 	    capable(CAP_IPC_LOCK))
-		ret = do_mlockall(flags);
+		ret = apply_mlockall_flags(flags);
 	up_write(&current->mm->mmap_sem);
 	if (!ret && (flags & MCL_CURRENT))
 		mm_populate(0, TASK_SIZE);
-out:
+
 	return ret;
 }
 
@@ -717,7 +753,7 @@ SYSCALL_DEFINE0(munlockall)
 	int ret;
 
 	down_write(&current->mm->mmap_sem);
-	ret = do_mlockall(0);
+	ret = apply_mlockall_flags(0);
 	up_write(&current->mm->mmap_sem);
 	return ret;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 971dd2cb77d2..09dcfe12532d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -612,8 +612,6 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm,
 void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct rb_node **rb_link, struct rb_node *rb_parent)
 {
-	WARN_ONCE(vma->vm_file && !vma->vm_ops, "missing vma->vm_ops");
-
 	/* Update tracking information for the gap following the new vma. */
 	if (vma->vm_next)
 		vma_gap_update(vma->vm_next);
@@ -1304,7 +1302,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	 * that it represents a valid section of the address space.
 	 */
 	addr = get_unmapped_area(file, addr, len, pgoff, flags);
-	if (addr & ~PAGE_MASK)
+	if (offset_in_page(addr))
 		return addr;
 
 	/* Do simple checking here so the lower-level routines won't have
@@ -1475,7 +1473,7 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 
 	if (copy_from_user(&a, arg, sizeof(a)))
 		return -EFAULT;
-	if (a.offset & ~PAGE_MASK)
+	if (offset_in_page(a.offset))
 		return -EINVAL;
 
 	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
@@ -1492,13 +1490,14 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 int vma_wants_writenotify(struct vm_area_struct *vma)
 {
 	vm_flags_t vm_flags = vma->vm_flags;
+	const struct vm_operations_struct *vm_ops = vma->vm_ops;
 
 	/* If it was private or non-writable, the write bit is already clear */
 	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
 		return 0;
 
 	/* The backer wishes to know when pages are first written to? */
-	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
+	if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite))
 		return 1;
 
 	/* The open routine did something to the protections that pgprot_modify
@@ -1638,12 +1637,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		 */
 		WARN_ON_ONCE(addr != vma->vm_start);
 
-		/* All file mapping must have ->vm_ops set */
-		if (!vma->vm_ops) {
-			static const struct vm_operations_struct dummy_ops = {};
-			vma->vm_ops = &dummy_ops;
-		}
-
 		addr = vma->vm_start;
 		vm_flags = vma->vm_flags;
 	} else if (vm_flags & VM_SHARED) {
@@ -1670,7 +1663,7 @@ out:
 					vma == get_gate_vma(current->mm)))
 			mm->locked_vm += (len >> PAGE_SHIFT);
 		else
-			vma->vm_flags &= ~VM_LOCKED;
+			vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
 	}
 
 	if (file)
@@ -1996,7 +1989,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	 * can happen with large stack limits and large mmap()
 	 * allocations.
 	 */
-	if (addr & ~PAGE_MASK) {
+	if (offset_in_page(addr)) {
 		VM_BUG_ON(addr != -ENOMEM);
 		info.flags = 0;
 		info.low_limit = TASK_UNMAPPED_BASE;
@@ -2032,7 +2025,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 
 	if (addr > TASK_SIZE - len)
 		return -ENOMEM;
-	if (addr & ~PAGE_MASK)
+	if (offset_in_page(addr))
 		return -EINVAL;
 
 	addr = arch_rebalance_pgtables(addr, len);
@@ -2054,7 +2047,6 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 		return vma;
 
 	rb_node = mm->mm_rb.rb_node;
-	vma = NULL;
 
 	while (rb_node) {
 		struct vm_area_struct *tmp;
@@ -2543,7 +2535,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	unsigned long end;
 	struct vm_area_struct *vma, *prev, *last;
 
-	if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
+	if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start)
 		return -EINVAL;
 
 	len = PAGE_ALIGN(len);
@@ -2741,7 +2733,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
-	if (error & ~PAGE_MASK)
+	if (offset_in_page(error))
 		return error;
 
 	error = mlock_future_check(mm, mm->def_flags, len);
@@ -2865,6 +2857,7 @@ void exit_mmap(struct mm_struct *mm)
 			nr_accounted += vma_pages(vma);
 		vma = remove_vma(vma);
 	}
+	exit_hugetlb_mmap(mm);
 	vm_unacct_memory(nr_accounted);
 }
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 5a71cce8c6ea..c25bc6268e46 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -401,7 +401,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	unsigned long charged = 0;
 	unsigned long map_flags;
 
-	if (new_addr & ~PAGE_MASK)
+	if (offset_in_page(new_addr))
 		goto out;
 
 	if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len)
@@ -435,11 +435,11 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff +
 				((addr - vma->vm_start) >> PAGE_SHIFT),
 				map_flags);
-	if (ret & ~PAGE_MASK)
+	if (offset_in_page(ret))
 		goto out1;
 
 	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked);
-	if (!(ret & ~PAGE_MASK))
+	if (!(offset_in_page(ret)))
 		goto out;
 out1:
 	vm_unacct_memory(charged);
@@ -484,7 +484,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE))
 		return ret;
 
-	if (addr & ~PAGE_MASK)
+	if (offset_in_page(addr))
 		return ret;
 
 	old_len = PAGE_ALIGN(old_len);
@@ -566,7 +566,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 					vma->vm_pgoff +
 					((addr - vma->vm_start) >> PAGE_SHIFT),
 					map_flags);
-		if (new_addr & ~PAGE_MASK) {
+		if (offset_in_page(new_addr)) {
 			ret = new_addr;
 			goto out;
 		}
@@ -574,7 +574,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 		ret = move_vma(vma, addr, old_len, new_len, new_addr, &locked);
 	}
 out:
-	if (ret & ~PAGE_MASK) {
+	if (offset_in_page(ret)) {
 		vm_unacct_memory(charged);
 		locked = 0;
 	}
diff --git a/mm/msync.c b/mm/msync.c
index bb04d53ae852..24e612fefa04 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -38,7 +38,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;
-	if (start & ~PAGE_MASK)
+	if (offset_in_page(start))
 		goto out;
 	if ((flags & MS_ASYNC) && (flags & MS_SYNC))
 		goto out;
diff --git a/mm/nommu.c b/mm/nommu.c
index ab14a2014dea..1e0f1688d9a4 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1497,7 +1497,7 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 
 	if (copy_from_user(&a, arg, sizeof(a)))
 		return -EFAULT;
-	if (a.offset & ~PAGE_MASK)
+	if (offset_in_page(a.offset))
 		return -EINVAL;
 
 	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
@@ -1653,9 +1653,9 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 			goto erase_whole_vma;
 		if (start < vma->vm_start || end > vma->vm_end)
 			return -EINVAL;
-		if (start & ~PAGE_MASK)
+		if (offset_in_page(start))
 			return -EINVAL;
-		if (end != vma->vm_end && end & ~PAGE_MASK)
+		if (end != vma->vm_end && offset_in_page(end))
 			return -EINVAL;
 		if (start != vma->vm_start && end != vma->vm_end) {
 			ret = split_vma(mm, vma, start, 1);
@@ -1736,7 +1736,7 @@ static unsigned long do_mremap(unsigned long addr,
 	if (old_len == 0 || new_len == 0)
 		return (unsigned long) -EINVAL;
 
-	if (addr & ~PAGE_MASK)
+	if (offset_in_page(addr))
 		return -EINVAL;
 
 	if (flags & MREMAP_FIXED && new_addr != addr)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 48aaf7b9f253..9bcfd70b1eb8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -181,7 +181,7 @@ bool pm_suspended_storage(void)
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
-int pageblock_order __read_mostly;
+unsigned int pageblock_order __read_mostly;
 #endif
 
 static void __free_pages_ok(struct page *page, unsigned int order);
@@ -229,6 +229,15 @@ static char * const zone_names[MAX_NR_ZONES] = {
 #endif
 };
 
+static void free_compound_page(struct page *page);
+compound_page_dtor * const compound_page_dtors[] = {
+	NULL,
+	free_compound_page,
+#ifdef CONFIG_HUGETLB_PAGE
+	free_huge_page,
+#endif
+};
+
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
 
@@ -436,15 +445,15 @@ out:
 /*
  * Higher-order pages are called "compound pages".  They are structured thusly:
  *
- * The first PAGE_SIZE page is called the "head page".
+ * The first PAGE_SIZE page is called the "head page" and have PG_head set.
  *
- * The remaining PAGE_SIZE pages are called "tail pages".
+ * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded
+ * in bit 0 of page->compound_head. The rest of bits is pointer to head page.
  *
- * All pages have PG_compound set.  All tail pages have their ->first_page
- * pointing at the head page.
+ * The first tail page's ->compound_dtor holds the offset in array of compound
+ * page destructors. See compound_page_dtors.
  *
- * The first tail page's ->lru.next holds the address of the compound page's
- * put_page() function.  Its ->lru.prev holds the order of allocation.
+ * The first tail page's ->compound_order holds the order of allocation.
  * This usage means that zero-order pages may not be compound.
  */
 
@@ -453,21 +462,19 @@ static void free_compound_page(struct page *page)
 	__free_pages_ok(page, compound_order(page));
 }
 
-void prep_compound_page(struct page *page, unsigned long order)
+void prep_compound_page(struct page *page, unsigned int order)
 {
 	int i;
 	int nr_pages = 1 << order;
 
-	set_compound_page_dtor(page, free_compound_page);
+	set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
 	set_compound_order(page, order);
 	__SetPageHead(page);
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 		set_page_count(p, 0);
-		p->first_page = page;
-		/* Make sure p->first_page is always valid for PageTail() */
-		smp_wmb();
-		__SetPageTail(p);
+		p->mapping = TAIL_MAPPING;
+		set_compound_head(p, page);
 	}
 }
 
@@ -656,7 +663,7 @@ static inline void __free_one_page(struct page *page,
 	unsigned long combined_idx;
 	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
-	int max_order = MAX_ORDER;
+	unsigned int max_order = MAX_ORDER;
 
 	VM_BUG_ON(!zone_is_initialized(zone));
 	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
@@ -846,17 +853,35 @@ static void free_one_page(struct zone *zone,
 
 static int free_tail_pages_check(struct page *head_page, struct page *page)
 {
-	if (!IS_ENABLED(CONFIG_DEBUG_VM))
-		return 0;
+	int ret = 1;
+
+	/*
+	 * We rely page->lru.next never has bit 0 set, unless the page
+	 * is PageTail(). Let's make sure that's true even for poisoned ->lru.
+	 */
+	BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1);
+
+	if (!IS_ENABLED(CONFIG_DEBUG_VM)) {
+		ret = 0;
+		goto out;
+	}
+	if (page->mapping != TAIL_MAPPING) {
+		bad_page(page, "corrupted mapping in tail page", 0);
+		goto out;
+	}
 	if (unlikely(!PageTail(page))) {
 		bad_page(page, "PageTail not set", 0);
-		return 1;
+		goto out;
 	}
-	if (unlikely(page->first_page != head_page)) {
-		bad_page(page, "first_page not consistent", 0);
-		return 1;
+	if (unlikely(compound_head(page) != head_page)) {
+		bad_page(page, "compound_head not consistent", 0);
+		goto out;
 	}
-	return 0;
+	ret = 0;
+out:
+	page->mapping = NULL;
+	clear_compound_head(page);
+	return ret;
 }
 
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
@@ -904,6 +929,8 @@ static void init_reserved_page(unsigned long pfn)
 #else
 static inline void init_reserved_page(unsigned long pfn)
 {
+	/* Avoid false-positive PageTail() */
+	INIT_LIST_HEAD(&pfn_to_page(pfn)->lru);
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
@@ -1450,7 +1477,7 @@ int move_freepages(struct zone *zone,
 			  int migratetype)
 {
 	struct page *page;
-	unsigned long order;
+	unsigned int order;
 	int pages_moved = 0;
 
 #ifndef CONFIG_HOLES_IN_ZONE
@@ -1563,7 +1590,7 @@ static bool can_steal_fallback(unsigned int order, int start_mt)
 static void steal_suitable_fallback(struct zone *zone, struct page *page,
 							  int start_type)
 {
-	int current_order = page_order(page);
+	unsigned int current_order = page_order(page);
 	int pages;
 
 	/* Take ownership for orders >= pageblock_order */
@@ -2669,7 +2696,7 @@ static DEFINE_RATELIMIT_STATE(nopage_rs,
 		DEFAULT_RATELIMIT_INTERVAL,
 		DEFAULT_RATELIMIT_BURST);
 
-void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
+void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
 
@@ -2703,7 +2730,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 		va_end(args);
 	}
 
-	pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n",
+	pr_warn("%s: page allocation failure: order:%u, mode:0x%x\n",
 		current->comm, order, gfp_mask);
 
 	dump_stack();
@@ -3467,7 +3494,8 @@ void free_kmem_pages(unsigned long addr, unsigned int order)
 	}
 }
 
-static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
+static void *make_alloc_exact(unsigned long addr, unsigned int order,
+		size_t size)
 {
 	if (addr) {
 		unsigned long alloc_end = addr + (PAGE_SIZE << order);
@@ -3517,7 +3545,7 @@ EXPORT_SYMBOL(alloc_pages_exact);
  */
 void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
 {
-	unsigned order = get_order(size);
+	unsigned int order = get_order(size);
 	struct page *p = alloc_pages_node(nid, gfp_mask, order);
 	if (!p)
 		return NULL;
@@ -3819,7 +3847,8 @@ void show_free_areas(unsigned int filter)
 	}
 
 	for_each_populated_zone(zone) {
-		unsigned long nr[MAX_ORDER], flags, order, total = 0;
+		unsigned int order;
+		unsigned long nr[MAX_ORDER], flags, total = 0;
 		unsigned char types[MAX_ORDER];
 
 		if (skip_free_areas_node(filter, zone_to_nid(zone)))
@@ -4168,7 +4197,7 @@ static void build_zonelists(pg_data_t *pgdat)
 	nodemask_t used_mask;
 	int local_node, prev_node;
 	struct zonelist *zonelist;
-	int order = current_zonelist_order;
+	unsigned int order = current_zonelist_order;
 
 	/* initialize zonelists */
 	for (i = 0; i < MAX_ZONELISTS; i++) {
@@ -4362,13 +4391,13 @@ static int __build_all_zonelists(void *data)
 		/*
 		 * We now know the "local memory node" for each node--
 		 * i.e., the node of the first zone in the generic zonelist.
-		 * Set up numa_mem percpu variable for on-line cpus.  During
-		 * boot, only the boot cpu should be on-line;  we'll init the
-		 * secondary cpus' numa_mem as they come on-line.  During
-		 * node/memory hotplug, we'll fixup all on-line cpus.
+		 * Set up numa_mem percpu variable for all possible cpus
+		 * if associated node has been onlined.
 		 */
-		if (cpu_online(cpu))
+		if (node_online(cpu_to_node(cpu)))
 			set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
+		else
+			set_cpu_numa_mem(cpu, NUMA_NO_NODE);
 #endif
 	}
 
@@ -4900,8 +4929,7 @@ static __meminit void zone_pcp_init(struct zone *zone)
 
 int __meminit init_currently_empty_zone(struct zone *zone,
 					unsigned long zone_start_pfn,
-					unsigned long size,
-					enum memmap_context context)
+					unsigned long size)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	int ret;
@@ -5413,8 +5441,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 
 		set_pageblock_order();
 		setup_usemap(pgdat, zone, zone_start_pfn, size);
-		ret = init_currently_empty_zone(zone, zone_start_pfn,
-						size, MEMMAP_EARLY);
+		ret = init_currently_empty_zone(zone, zone_start_pfn, size);
 		BUG_ON(ret);
 		memmap_init(size, nid, j, zone_start_pfn);
 		zone_start_pfn += size;
@@ -6831,7 +6858,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		       unsigned migratetype)
 {
 	unsigned long outer_start, outer_end;
-	int ret = 0, order;
+	unsigned int order;
+	int ret = 0;
 
 	struct compact_control cc = {
 		.nr_migratepages = 0,
diff --git a/mm/percpu.c b/mm/percpu.c
index a63b4d82a141..8a943b97a053 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1554,12 +1554,12 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
 #ifdef CONFIG_SMP
 	PCPU_SETUP_BUG_ON(!ai->static_size);
-	PCPU_SETUP_BUG_ON((unsigned long)__per_cpu_start & ~PAGE_MASK);
+	PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start));
 #endif
 	PCPU_SETUP_BUG_ON(!base_addr);
-	PCPU_SETUP_BUG_ON((unsigned long)base_addr & ~PAGE_MASK);
+	PCPU_SETUP_BUG_ON(offset_in_page(base_addr));
 	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
-	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
+	PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size));
 	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
 	PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
 	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
@@ -1806,7 +1806,7 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
 
 	alloc_size = roundup(min_unit_size, atom_size);
 	upa = alloc_size / min_unit_size;
-	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+	while (alloc_size % upa || (offset_in_page(alloc_size / upa)))
 		upa--;
 	max_upa = upa;
 
@@ -1838,7 +1838,7 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
 	for (upa = max_upa; upa; upa--) {
 		int allocs = 0, wasted = 0;
 
-		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+		if (alloc_size % upa || (offset_in_page(alloc_size / upa)))
 			continue;
 
 		for (group = 0; group < nr_groups; group++) {
diff --git a/mm/readahead.c b/mm/readahead.c
index 60cd846a9a44..b4937a6bfcd6 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -213,7 +213,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
 		return -EINVAL;
 
-	nr_to_read = max_sane_readahead(nr_to_read);
+	nr_to_read = min(nr_to_read, inode_to_bdi(mapping->host)->ra_pages);
 	while (nr_to_read) {
 		int err;
 
@@ -232,16 +232,6 @@ 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, MAX_READAHEAD);
-}
-
 /*
  * Set the initial window size, round to next power of 2 and square
  * for small size, x 4 for medium, and x 2 for large
@@ -380,7 +370,7 @@ ondemand_readahead(struct address_space *mapping,
 		   bool hit_readahead_marker, pgoff_t offset,
 		   unsigned long req_size)
 {
-	unsigned long max = max_sane_readahead(ra->ra_pages);
+	unsigned long max = ra->ra_pages;
 	pgoff_t prev_offset;
 
 	/*
diff --git a/mm/rmap.c b/mm/rmap.c
index f5b5c1f3dcd7..4b0b8029ea5b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -818,6 +818,7 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 }
 
 struct page_referenced_arg {
+	int dirtied;
 	int mapcount;
 	int referenced;
 	unsigned long vm_flags;
@@ -832,6 +833,7 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	spinlock_t *ptl;
 	int referenced = 0;
+	int dirty = 0;
 	struct page_referenced_arg *pra = arg;
 
 	if (unlikely(PageTransHuge(page))) {
@@ -855,6 +857,15 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		/* go ahead even if the pmd is pmd_trans_splitting() */
 		if (pmdp_clear_flush_young_notify(vma, address, pmd))
 			referenced++;
+
+		/*
+		 * Use pmd_freeable instead of raw pmd_dirty because in some
+		 * of architecture, pmd_dirty is not defined unless
+		 * CONFIG_TRANSPARENT_HUGEPAGE is enabled
+		 */
+		if (!pmd_freeable(*pmd))
+			dirty++;
+
 		spin_unlock(ptl);
 	} else {
 		pte_t *pte;
@@ -884,6 +895,10 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			if (likely(!(vma->vm_flags & VM_SEQ_READ)))
 				referenced++;
 		}
+
+		if (pte_dirty(*pte))
+			dirty++;
+
 		pte_unmap_unlock(pte, ptl);
 	}
 
@@ -897,6 +912,9 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		pra->vm_flags |= vma->vm_flags;
 	}
 
+	if (dirty)
+		pra->dirtied++;
+
 	pra->mapcount--;
 	if (!pra->mapcount)
 		return SWAP_SUCCESS; /* To break the loop */
@@ -921,6 +939,7 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
  * @is_locked: caller holds lock on the page
  * @memcg: target memory cgroup
  * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
+ * @is_pte_dirty: ptes which have marked dirty bit - used for lazyfree page
  *
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
@@ -928,7 +947,8 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
 int page_referenced(struct page *page,
 		    int is_locked,
 		    struct mem_cgroup *memcg,
-		    unsigned long *vm_flags)
+		    unsigned long *vm_flags,
+		    int *is_pte_dirty)
 {
 	int ret;
 	int we_locked = 0;
@@ -943,6 +963,9 @@ int page_referenced(struct page *page,
 	};
 
 	*vm_flags = 0;
+	if (is_pte_dirty)
+		*is_pte_dirty = 0;
+
 	if (!page_mapped(page))
 		return 0;
 
@@ -970,6 +993,9 @@ int page_referenced(struct page *page,
 	if (we_locked)
 		unlock_page(page);
 
+	if (is_pte_dirty)
+		*is_pte_dirty = pra.dirtied;
+
 	return pra.referenced;
 }
 
@@ -1303,6 +1329,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	int ret = SWAP_AGAIN;
 	enum ttu_flags flags = (enum ttu_flags)arg;
+	int dirty = 0;
 
 	pte = page_check_address(page, mm, address, &ptl, 0);
 	if (!pte)
@@ -1345,14 +1372,17 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	}
 
 	/* Move the dirty bit to the physical page now the pte is gone. */
-	if (pte_dirty(pteval))
+	dirty = pte_dirty(pteval);
+	if (dirty)
 		set_page_dirty(page);
 
 	/* Update high watermark before we lower rss */
 	update_hiwater_rss(mm);
 
 	if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
-		if (!PageHuge(page)) {
+		if (PageHuge(page)) {
+			dec_hugetlb_count(mm, page_hstate(page));
+		} else {
 			if (PageAnon(page))
 				dec_mm_counter(mm, MM_ANONPAGES);
 			else
@@ -1374,6 +1404,19 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		swp_entry_t entry = { .val = page_private(page) };
 		pte_t swp_pte;
 
+		if (flags & TTU_FREE) {
+			VM_BUG_ON_PAGE(PageSwapCache(page), page);
+			if (!dirty && !PageDirty(page)) {
+				/* It's a freeable page by MADV_FREE */
+				dec_mm_counter(mm, MM_ANONPAGES);
+				goto discard;
+			} else {
+				set_pte_at(mm, address, pte, pteval);
+				ret = SWAP_FAIL;
+				goto out_unmap;
+			}
+		}
+
 		if (PageSwapCache(page)) {
 			/*
 			 * Store the swap location in the pte.
@@ -1414,6 +1457,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	} else
 		dec_mm_counter(mm, MM_FILEPAGES);
 
+discard:
 	page_remove_rmap(page);
 	page_cache_release(page);
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 48ce82926d93..1425863f5322 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -996,7 +996,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	copy_highpage(newpage, oldpage);
 	flush_dcache_page(newpage);
 
-	__set_page_locked(newpage);
+	__SetPageLocked(newpage);
 	SetPageUptodate(newpage);
 	SetPageSwapBacked(newpage);
 	set_page_private(newpage, swap_index);
@@ -1188,7 +1188,7 @@ repeat:
 		}
 
 		__SetPageSwapBacked(page);
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
diff --git a/mm/slab.c b/mm/slab.c
index c77ebe6cc87c..f80bbc1583fa 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1888,21 +1888,10 @@ static void slab_destroy(struct kmem_cache *cachep, struct page *page)
 
 	freelist = page->freelist;
 	slab_destroy_debugcheck(cachep, page);
-	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
-		struct rcu_head *head;
-
-		/*
-		 * RCU free overloads the RCU head over the LRU.
-		 * slab_page has been overloeaded over the LRU,
-		 * however it is not used from now on so that
-		 * we can use it safely.
-		 */
-		head = (void *)&page->rcu_head;
-		call_rcu(head, kmem_rcu_free);
-
-	} else {
+	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
+		call_rcu(&page->rcu_head, kmem_rcu_free);
+	else
 		kmem_freepages(cachep, page);
-	}
 
 	/*
 	 * From now on, we don't use freelist
@@ -2190,7 +2179,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 			size += BYTES_PER_WORD;
 	}
 #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
-	if (size >= kmalloc_size(INDEX_NODE + 1)
+	if (size >= kmalloc_size(INDEX_NODE) * 2
 	    && cachep->object_size > cache_line_size()
 	    && ALIGN(size, cachep->align) < PAGE_SIZE) {
 		cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 5ce4faeb16fb..113a6fd597db 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -692,7 +692,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
 
-int slab_is_available(void)
+bool slab_is_available(void)
 {
 	return slab_state >= UP;
 }
diff --git a/mm/slub.c b/mm/slub.c
index f614b5dc396b..bda33cc4f7e4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -338,11 +338,13 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
  */
 static __always_inline void slab_lock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	bit_spin_lock(PG_locked, &page->flags);
 }
 
 static __always_inline void slab_unlock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	__bit_spin_unlock(PG_locked, &page->flags);
 }
 
@@ -1507,10 +1509,7 @@ static void free_slab(struct kmem_cache *s, struct page *page)
 			VM_BUG_ON(s->reserved != sizeof(*head));
 			head = page_address(page) + offset;
 		} else {
-			/*
-			 * RCU free overloads the RCU head over the LRU
-			 */
-			head = (void *)&page->lru;
+			head = &page->rcu_head;
 		}
 
 		call_rcu(head, rcu_free_slab);
@@ -2298,23 +2297,15 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
  * And if we were unable to get a new slab from the partial slab lists then
  * we need to allocate a new slab. This is the slowest path since it involves
  * a call to the page allocator and the setup of a new slab.
+ *
+ * Version of __slab_alloc to use when we know that interrupts are
+ * already disabled (which is the case for bulk allocation).
  */
-static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
+static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			  unsigned long addr, struct kmem_cache_cpu *c)
 {
 	void *freelist;
 	struct page *page;
-	unsigned long flags;
-
-	local_irq_save(flags);
-#ifdef CONFIG_PREEMPT
-	/*
-	 * We may have been preempted and rescheduled on a different
-	 * cpu before disabling interrupts. Need to reload cpu area
-	 * pointer.
-	 */
-	c = this_cpu_ptr(s->cpu_slab);
-#endif
 
 	page = c->page;
 	if (!page)
@@ -2372,7 +2363,6 @@ load_freelist:
 	VM_BUG_ON(!c->page->frozen);
 	c->freelist = get_freepointer(s, freelist);
 	c->tid = next_tid(c->tid);
-	local_irq_restore(flags);
 	return freelist;
 
 new_slab:
@@ -2389,7 +2379,6 @@ new_slab:
 
 	if (unlikely(!freelist)) {
 		slab_out_of_memory(s, gfpflags, node);
-		local_irq_restore(flags);
 		return NULL;
 	}
 
@@ -2405,11 +2394,35 @@ new_slab:
 	deactivate_slab(s, page, get_freepointer(s, freelist));
 	c->page = NULL;
 	c->freelist = NULL;
-	local_irq_restore(flags);
 	return freelist;
 }
 
 /*
+ * Another one that disabled interrupt and compensates for possible
+ * cpu changes by refetching the per cpu area pointer.
+ */
+static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
+			  unsigned long addr, struct kmem_cache_cpu *c)
+{
+	void *p;
+	unsigned long flags;
+
+	local_irq_save(flags);
+#ifdef CONFIG_PREEMPT
+	/*
+	 * We may have been preempted and rescheduled on a different
+	 * cpu before disabling interrupts. Need to reload cpu area
+	 * pointer.
+	 */
+	c = this_cpu_ptr(s->cpu_slab);
+#endif
+
+	p = ___slab_alloc(s, gfpflags, node, addr, c);
+	local_irq_restore(flags);
+	return p;
+}
+
+/*
  * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
  * have the fastpath folded into their functions. So no function call
  * overhead for requests that can be satisfied on the fastpath.
@@ -2807,30 +2820,23 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 		void *object = c->freelist;
 
 		if (unlikely(!object)) {
-			local_irq_enable();
 			/*
 			 * Invoking slow path likely have side-effect
 			 * of re-populating per CPU c->freelist
 			 */
-			p[i] = __slab_alloc(s, flags, NUMA_NO_NODE,
+			p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE,
 					    _RET_IP_, c);
-			if (unlikely(!p[i])) {
-				__kmem_cache_free_bulk(s, i, p);
-				return false;
-			}
-			local_irq_disable();
+			if (unlikely(!p[i]))
+				goto error;
+
 			c = this_cpu_ptr(s->cpu_slab);
 			continue; /* goto for-loop */
 		}
 
 		/* kmem_cache debug support */
 		s = slab_pre_alloc_hook(s, flags);
-		if (unlikely(!s)) {
-			__kmem_cache_free_bulk(s, i, p);
-			c->tid = next_tid(c->tid);
-			local_irq_enable();
-			return false;
-		}
+		if (unlikely(!s))
+			goto error;
 
 		c->freelist = get_freepointer(s, object);
 		p[i] = object;
@@ -2850,6 +2856,11 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	}
 
 	return true;
+
+error:
+	__kmem_cache_free_bulk(s, i, p);
+	local_irq_enable();
+	return false;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
 
diff --git a/mm/swap.c b/mm/swap.c
index 983f692a47fd..ecbfd50df347 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -45,6 +45,7 @@ int page_cluster;
 static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
 static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
 static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
 
 /*
  * This path almost never happens for VM activity - pages are normally
@@ -201,7 +202,7 @@ out_put_single:
 				__put_single_page(page);
 			return;
 		}
-		VM_BUG_ON_PAGE(page_head != page->first_page, page);
+		VM_BUG_ON_PAGE(page_head != compound_head(page), page);
 		/*
 		 * We can release the refcount taken by
 		 * get_page_unless_zero() now that
@@ -262,7 +263,7 @@ static void put_compound_page(struct page *page)
 	 *  Case 3 is possible, as we may race with
 	 *  __split_huge_page_refcount tearing down a THP page.
 	 */
-	page_head = compound_head_by_tail(page);
+	page_head = compound_head(page);
 	if (!__compound_tail_refcounted(page_head))
 		put_unrefcounted_compound_page(page_head, page);
 	else
@@ -799,6 +800,24 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
 	update_page_reclaim_stat(lruvec, file, 0);
 }
 
+
+static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
+			    void *arg)
+{
+	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+		int file = page_is_file_cache(page);
+		int lru = page_lru_base_type(page);
+
+		del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE);
+		ClearPageActive(page);
+		ClearPageReferenced(page);
+		add_page_to_lru_list(page, lruvec, lru);
+
+		__count_vm_event(PGDEACTIVATE);
+		update_page_reclaim_stat(lruvec, file, 0);
+	}
+}
+
 /*
  * Drain pages out of the cpu's pagevecs.
  * Either "cpu" is the current CPU, and preemption has already been
@@ -825,6 +844,10 @@ void lru_add_drain_cpu(int cpu)
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
 
+	pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+	if (pagevec_count(pvec))
+		pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+
 	activate_page_drain(cpu);
 }
 
@@ -854,6 +877,26 @@ void deactivate_file_page(struct page *page)
 	}
 }
 
+/**
+ * deactivate_page - deactivate a page
+ * @page: page to deactivate
+ *
+ * deactivate_page() moves @page to the inactive list if @page was on the active
+ * list and was not an unevictable page.  This is done to accelerate the reclaim
+ * of @page.
+ */
+void deactivate_page(struct page *page)
+{
+	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+
+		page_cache_get(page);
+		if (!pagevec_add(pvec, page))
+			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+		put_cpu_var(lru_deactivate_pvecs);
+	}
+}
+
 void lru_add_drain(void)
 {
 	lru_add_drain_cpu(get_cpu());
@@ -883,6 +926,7 @@ void lru_add_drain_all(void)
 		if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
 		    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
 		    pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
+		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			schedule_work_on(cpu, work);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index d504adb7fa5f..d783872d746c 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -353,7 +353,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 
 		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 		SetPageSwapBacked(new_page);
 		err = __add_to_swap_cache(new_page, entry);
 		if (likely(!err)) {
@@ -367,7 +367,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 		radix_tree_preload_end();
 		ClearPageSwapBacked(new_page);
-		__clear_page_locked(new_page);
+		__ClearPageLocked(new_page);
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
diff --git a/mm/util.c b/mm/util.c
index 68ff8a5361e7..55012d786a35 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -3,6 +3,7 @@
 #include <linux/string.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
+#include <linux/ctype.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/security.h>
@@ -100,6 +101,35 @@ char *kstrndup(const char *s, size_t max, gfp_t gfp)
 EXPORT_SYMBOL(kstrndup);
 
 /**
+ * kstrimdup - Trim and copy a %NUL terminated string.
+ * @s: the string to trim and duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Returns an address, which the caller must kfree, containing
+ * a duplicate of the passed string with leading and/or trailing
+ * whitespace (as defined by isspace) removed.
+ */
+char *kstrimdup(const char *s, gfp_t gfp)
+{
+	char *buf;
+	char *begin = skip_spaces(s);
+	size_t len = strlen(begin);
+
+	while (len && isspace(begin[len - 1]))
+		len--;
+
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (!buf)
+		return NULL;
+
+	memcpy(buf, begin, len);
+	buf[len] = '\0';
+
+	return buf;
+}
+EXPORT_SYMBOL(kstrimdup);
+
+/**
  * kmemdup - duplicate region of memory
  *
  * @src: memory region to duplicate
@@ -309,7 +339,7 @@ unsigned long vm_mmap(struct file *file, unsigned long addr,
 {
 	if (unlikely(offset + PAGE_ALIGN(len) < offset))
 		return -EINVAL;
-	if (unlikely(offset & ~PAGE_MASK))
+	if (unlikely(offset_in_page(offset)))
 		return -EINVAL;
 
 	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
@@ -355,7 +385,9 @@ struct anon_vma *page_anon_vma(struct page *page)
 
 struct address_space *page_mapping(struct page *page)
 {
-	unsigned long mapping;
+	struct address_space *mapping;
+
+	page = compound_head(page);
 
 	/* This happens if someone calls flush_dcache_page on slab page */
 	if (unlikely(PageSlab(page)))
@@ -368,10 +400,10 @@ struct address_space *page_mapping(struct page *page)
 		return swap_address_space(entry);
 	}
 
-	mapping = (unsigned long)page->mapping;
-	if (mapping & PAGE_MAPPING_FLAGS)
+	mapping = page->mapping;
+	if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
 		return NULL;
-	return page->mapping;
+	return mapping;
 }
 
 int overcommit_ratio_handler(struct ctl_table *table, int write,
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 2faaa2976447..b51b73330f87 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -358,7 +358,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	struct vmap_area *first;
 
 	BUG_ON(!size);
-	BUG_ON(size & ~PAGE_MASK);
+	BUG_ON(offset_in_page(size));
 	BUG_ON(!is_power_of_2(align));
 
 	va = kmalloc_node(sizeof(struct vmap_area),
@@ -936,7 +936,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 	void *vaddr = NULL;
 	unsigned int order;
 
-	BUG_ON(size & ~PAGE_MASK);
+	BUG_ON(offset_in_page(size));
 	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
 	if (WARN_ON(size == 0)) {
 		/*
@@ -989,7 +989,7 @@ static void vb_free(const void *addr, unsigned long size)
 	unsigned int order;
 	struct vmap_block *vb;
 
-	BUG_ON(size & ~PAGE_MASK);
+	BUG_ON(offset_in_page(size));
 	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
 
 	flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size);
@@ -1902,7 +1902,7 @@ static int aligned_vread(char *buf, char *addr, unsigned long count)
 	while (count) {
 		unsigned long offset, length;
 
-		offset = (unsigned long)addr & ~PAGE_MASK;
+		offset = offset_in_page(addr);
 		length = PAGE_SIZE - offset;
 		if (length > count)
 			length = count;
@@ -1941,7 +1941,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count)
 	while (count) {
 		unsigned long offset, length;
 
-		offset = (unsigned long)addr & ~PAGE_MASK;
+		offset = offset_in_page(addr);
 		length = PAGE_SIZE - offset;
 		if (length > count)
 			length = count;
@@ -2392,7 +2392,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 	bool purged = false;
 
 	/* verify parameters and allocate data structures */
-	BUG_ON(align & ~PAGE_MASK || !is_power_of_2(align));
+	BUG_ON(offset_in_page(align) || !is_power_of_2(align));
 	for (last_area = 0, area = 0; area < nr_vms; area++) {
 		start = offsets[area];
 		end = start + sizes[area];
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2d978b28a410..db5339dd4a32 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -791,13 +791,17 @@ enum page_references {
 };
 
 static enum page_references page_check_references(struct page *page,
-						  struct scan_control *sc)
+						  struct scan_control *sc,
+						  bool *freeable)
 {
 	int referenced_ptes, referenced_page;
 	unsigned long vm_flags;
+	int pte_dirty;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
-					  &vm_flags);
+					  &vm_flags, &pte_dirty);
 	referenced_page = TestClearPageReferenced(page);
 
 	/*
@@ -838,6 +842,10 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_KEEP;
 	}
 
+	if (PageAnon(page) && !pte_dirty && !PageSwapCache(page) &&
+			!PageDirty(page))
+		*freeable = true;
+
 	/* Reclaim if clean, defer dirty pages to writeback */
 	if (referenced_page && !PageSwapBacked(page))
 		return PAGEREF_RECLAIM_CLEAN;
@@ -906,6 +914,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		int may_enter_fs;
 		enum page_references references = PAGEREF_RECLAIM_CLEAN;
 		bool dirty, writeback;
+		bool freeable = false;
 
 		cond_resched();
 
@@ -1028,7 +1037,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (!force_reclaim)
-			references = page_check_references(page, sc);
+			references = page_check_references(page, sc,
+							&freeable);
 
 		switch (references) {
 		case PAGEREF_ACTIVATE:
@@ -1045,23 +1055,31 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * Try to allocate it some swap space here.
 		 */
 		if (PageAnon(page) && !PageSwapCache(page)) {
-			if (!(sc->gfp_mask & __GFP_IO))
-				goto keep_locked;
-			if (!add_to_swap(page, page_list))
-				goto activate_locked;
-			may_enter_fs = 1;
-
-			/* Adding to swap updated mapping */
-			mapping = page_mapping(page);
+			if (!freeable) {
+				if (!(sc->gfp_mask & __GFP_IO))
+					goto keep_locked;
+				if (!add_to_swap(page, page_list))
+					goto activate_locked;
+				may_enter_fs = 1;
+				/* Adding to swap updated mapping */
+				mapping = page_mapping(page);
+			} else {
+				if (likely(!PageTransHuge(page)))
+					goto unmap;
+				/* try_to_unmap isn't aware of THP page */
+				if (unlikely(split_huge_page_to_list(page,
+								page_list)))
+					goto keep_locked;
+			}
 		}
-
+unmap:
 		/*
 		 * The page is mapped into the page tables of one or more
 		 * processes. Try to unmap it here.
 		 */
-		if (page_mapped(page) && mapping) {
-			switch (try_to_unmap(page,
-					ttu_flags|TTU_BATCH_FLUSH)) {
+		if (page_mapped(page) && (mapping || freeable)) {
+			switch (try_to_unmap(page, freeable ?
+					TTU_FREE : ttu_flags|TTU_BATCH_FLUSH)) {
 			case SWAP_FAIL:
 				goto activate_locked;
 			case SWAP_AGAIN:
@@ -1069,7 +1087,20 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			case SWAP_MLOCK:
 				goto cull_mlocked;
 			case SWAP_SUCCESS:
-				; /* try to free the page below */
+				/* try to free the page below */
+				if (!freeable)
+					break;
+				/*
+				 * Freeable anon page doesn't have mapping
+				 * due to skipping of swapcache so we free
+				 * page in here rather than __remove_mapping.
+				 */
+				VM_BUG_ON_PAGE(PageSwapCache(page), page);
+				if (!page_freeze_refs(page, 1))
+					goto keep_locked;
+				__ClearPageLocked(page);
+				count_vm_event(PGLAZYFREED);
+				goto free_it;
 			}
 		}
 
@@ -1184,7 +1215,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * we obviously don't have to worry about waking up a process
 		 * waiting on the page lock, because there are no references.
 		 */
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 free_it:
 		nr_reclaimed++;
 
@@ -1445,6 +1476,32 @@ int isolate_lru_page(struct page *page)
 	return ret;
 }
 
+static int __too_many_isolated(struct zone *zone, int file,
+			       struct scan_control *sc, int safe)
+{
+	unsigned long inactive, isolated;
+
+	if (safe) {
+		inactive = zone_page_state_snapshot(zone,
+				NR_INACTIVE_ANON + 2 * file);
+		isolated = zone_page_state_snapshot(zone,
+				NR_ISOLATED_ANON + file);
+	} else {
+		inactive = zone_page_state(zone, NR_INACTIVE_ANON + 2 * file);
+		isolated = zone_page_state(zone, NR_ISOLATED_ANON + file);
+	}
+
+	/*
+	 * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
+	 * won't get blocked by normal direct-reclaimers, forming a circular
+	 * deadlock.
+	 */
+	if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
+		inactive >>= 3;
+
+	return isolated > inactive;
+}
+
 /*
  * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
  * then get resheduled. When there are massive number of tasks doing page
@@ -1453,33 +1510,24 @@ int isolate_lru_page(struct page *page)
  * unnecessary swapping, thrashing and OOM.
  */
 static int too_many_isolated(struct zone *zone, int file,
-		struct scan_control *sc)
+			     struct scan_control *sc)
 {
-	unsigned long inactive, isolated;
-
 	if (current_is_kswapd())
 		return 0;
 
 	if (!sane_reclaim(sc))
 		return 0;
 
-	if (file) {
-		inactive = zone_page_state(zone, NR_INACTIVE_FILE);
-		isolated = zone_page_state(zone, NR_ISOLATED_FILE);
-	} else {
-		inactive = zone_page_state(zone, NR_INACTIVE_ANON);
-		isolated = zone_page_state(zone, NR_ISOLATED_ANON);
-	}
-
 	/*
-	 * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
-	 * won't get blocked by normal direct-reclaimers, forming a circular
-	 * deadlock.
+	 * __too_many_isolated(safe=0) is fast but inaccurate, because it
+	 * doesn't account for the vm_stat_diff[] counters.  So if it looks
+	 * like too_many_isolated() is about to return true, fall back to the
+	 * slower, more accurate zone_page_state_snapshot().
 	 */
-	if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
-		inactive >>= 3;
+	if (unlikely(__too_many_isolated(zone, file, sc, 0)))
+		return __too_many_isolated(zone, file, sc, 1);
 
-	return isolated > inactive;
+	return 0;
 }
 
 static noinline_for_stack void
@@ -1816,7 +1864,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		}
 
 		if (page_referenced(page, 0, sc->target_mem_cgroup,
-				    &vm_flags)) {
+				    &vm_flags, NULL)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
 			 * Identify referenced, file-backed active pages and
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4f5cd974e11a..1fd0886a389f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -759,6 +759,7 @@ const char * const vmstat_text[] = {
 
 	"pgfault",
 	"pgmajfault",
+	"pglazyfreed",
 
 	TEXTS_FOR_ZONES("pgrefill")
 	TEXTS_FOR_ZONES("pgsteal_kswapd")
diff --git a/mm/zbud.c b/mm/zbud.c
index fa48bcdff9d5..d8a181fd779b 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -137,7 +137,7 @@ static const struct zbud_ops zbud_zpool_ops = {
 	.evict =	zbud_zpool_evict
 };
 
-static void *zbud_zpool_create(char *name, gfp_t gfp,
+static void *zbud_zpool_create(const char *name, gfp_t gfp,
 			       const struct zpool_ops *zpool_ops,
 			       struct zpool *zpool)
 {
diff --git a/mm/zpool.c b/mm/zpool.c
index 8f670d3e8706..fd3ff719c32c 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -18,8 +18,6 @@
 #include <linux/zpool.h>
 
 struct zpool {
-	char *type;
-
 	struct zpool_driver *driver;
 	void *pool;
 	const struct zpool_ops *ops;
@@ -73,7 +71,8 @@ int zpool_unregister_driver(struct zpool_driver *driver)
 }
 EXPORT_SYMBOL(zpool_unregister_driver);
 
-static struct zpool_driver *zpool_get_driver(char *type)
+/* this assumes @type is null-terminated. */
+static struct zpool_driver *zpool_get_driver(const char *type)
 {
 	struct zpool_driver *driver;
 
@@ -113,6 +112,8 @@ static void zpool_put_driver(struct zpool_driver *driver)
  * not be loaded, and calling @zpool_create_pool() with the pool type will
  * fail.
  *
+ * The @type string must be null-terminated.
+ *
  * Returns: true if @type pool is available, false if not
  */
 bool zpool_has_pool(char *type)
@@ -145,9 +146,11 @@ EXPORT_SYMBOL(zpool_has_pool);
  *
  * Implementations must guarantee this to be thread-safe.
  *
+ * The @type and @name strings must be null-terminated.
+ *
  * Returns: New zpool on success, NULL on failure.
  */
-struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
+struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp,
 		const struct zpool_ops *ops)
 {
 	struct zpool_driver *driver;
@@ -174,7 +177,6 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
 		return NULL;
 	}
 
-	zpool->type = driver->type;
 	zpool->driver = driver;
 	zpool->pool = driver->create(name, gfp, ops, zpool);
 	zpool->ops = ops;
@@ -208,7 +210,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp,
  */
 void zpool_destroy_pool(struct zpool *zpool)
 {
-	pr_debug("destroying pool type %s\n", zpool->type);
+	pr_debug("destroying pool type %s\n", zpool->driver->type);
 
 	spin_lock(&pools_lock);
 	list_del(&zpool->list);
@@ -228,9 +230,9 @@ void zpool_destroy_pool(struct zpool *zpool)
  *
  * Returns: The type of zpool.
  */
-char *zpool_get_type(struct zpool *zpool)
+const char *zpool_get_type(struct zpool *zpool)
 {
-	return zpool->type;
+	return zpool->driver->type;
 }
 
 /**
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index f135b1b6fcdc..f59e8ebb9dad 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -16,7 +16,7 @@
  * struct page(s) to form a zspage.
  *
  * Usage of struct page fields:
- *	page->first_page: points to the first component (0-order) page
+ *	page->private: points to the first component (0-order) page
  *	page->index (union with page->freelist): offset of the first object
  *		starting in this page. For the first page, this is
  *		always 0, so we use this field (aka freelist) to point
@@ -26,8 +26,7 @@
  *
  *	For _first_ page only:
  *
- *	page->private (union with page->first_page): refers to the
- *		component page after the first page
+ *	page->private: refers to the component page after the first page
  *		If the page is first_page for huge object, it stores handle.
  *		Look at size_class->huge.
  *	page->freelist: points to the first free object in zspage.
@@ -237,7 +236,7 @@ struct link_free {
 };
 
 struct zs_pool {
-	char *name;
+	const char *name;
 
 	struct size_class **size_class;
 	struct kmem_cache *handle_cachep;
@@ -311,7 +310,7 @@ static void record_obj(unsigned long handle, unsigned long obj)
 
 #ifdef CONFIG_ZPOOL
 
-static void *zs_zpool_create(char *name, gfp_t gfp,
+static void *zs_zpool_create(const char *name, gfp_t gfp,
 			     const struct zpool_ops *zpool_ops,
 			     struct zpool *zpool)
 {
@@ -548,7 +547,7 @@ static const struct file_operations zs_stat_size_ops = {
 	.release        = single_release,
 };
 
-static int zs_pool_stat_create(char *name, struct zs_pool *pool)
+static int zs_pool_stat_create(const char *name, struct zs_pool *pool)
 {
 	struct dentry *entry;
 
@@ -588,7 +587,7 @@ static void __exit zs_stat_exit(void)
 {
 }
 
-static inline int zs_pool_stat_create(char *name, struct zs_pool *pool)
+static inline int zs_pool_stat_create(const char *name, struct zs_pool *pool)
 {
 	return 0;
 }
@@ -764,7 +763,7 @@ static struct page *get_first_page(struct page *page)
 	if (is_first_page(page))
 		return page;
 	else
-		return page->first_page;
+		return (struct page *)page_private(page);
 }
 
 static struct page *get_next_page(struct page *page)
@@ -949,7 +948,7 @@ static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
 	 * Allocate individual pages and link them together as:
 	 * 1. first page->private = first sub-page
 	 * 2. all sub-pages are linked together using page->lru
-	 * 3. each sub-page is linked to the first page using page->first_page
+	 * 3. each sub-page is linked to the first page using page->private
 	 *
 	 * For each size class, First/Head pages are linked together using
 	 * page->lru. Also, we set PG_private to identify the first page
@@ -974,7 +973,7 @@ static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
 		if (i == 1)
 			set_page_private(first_page, (unsigned long)page);
 		if (i >= 1)
-			page->first_page = first_page;
+			set_page_private(page, (unsigned long)first_page);
 		if (i >= 2)
 			list_add(&page->lru, &prev_page->lru);
 		if (i == class->pages_per_zspage - 1)	/* last page */
@@ -1866,7 +1865,7 @@ static int zs_register_shrinker(struct zs_pool *pool)
  * On success, a pointer to the newly created pool is returned,
  * otherwise NULL.
  */
-struct zs_pool *zs_create_pool(char *name, gfp_t flags)
+struct zs_pool *zs_create_pool(const char *name, gfp_t flags)
 {
 	int i;
 	struct zs_pool *pool;
diff --git a/mm/zswap.c b/mm/zswap.c
index 4043df7c672f..56ad553bb8a1 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -82,33 +82,27 @@ module_param_named(enabled, zswap_enabled, bool, 0644);
 
 /* Crypto compressor to use */
 #define ZSWAP_COMPRESSOR_DEFAULT "lzo"
-static char zswap_compressor[CRYPTO_MAX_ALG_NAME] = ZSWAP_COMPRESSOR_DEFAULT;
-static struct kparam_string zswap_compressor_kparam = {
-	.string =	zswap_compressor,
-	.maxlen =	sizeof(zswap_compressor),
-};
+static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
 static int zswap_compressor_param_set(const char *,
 				      const struct kernel_param *);
 static struct kernel_param_ops zswap_compressor_param_ops = {
 	.set =		zswap_compressor_param_set,
-	.get =		param_get_string,
+	.get =		param_get_charp,
+	.free =		param_free_charp,
 };
 module_param_cb(compressor, &zswap_compressor_param_ops,
-		&zswap_compressor_kparam, 0644);
+		&zswap_compressor, 0644);
 
 /* Compressed storage zpool to use */
 #define ZSWAP_ZPOOL_DEFAULT "zbud"
-static char zswap_zpool_type[32 /* arbitrary */] = ZSWAP_ZPOOL_DEFAULT;
-static struct kparam_string zswap_zpool_kparam = {
-	.string =	zswap_zpool_type,
-	.maxlen =	sizeof(zswap_zpool_type),
-};
+static char *zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
 static int zswap_zpool_param_set(const char *, const struct kernel_param *);
 static struct kernel_param_ops zswap_zpool_param_ops = {
-	.set =	zswap_zpool_param_set,
-	.get =	param_get_string,
+	.set =		zswap_zpool_param_set,
+	.get =		param_get_charp,
+	.free =		param_free_charp,
 };
-module_param_cb(zpool, &zswap_zpool_param_ops, &zswap_zpool_kparam, 0644);
+module_param_cb(zpool, &zswap_zpool_param_ops, &zswap_zpool_type, 0644);
 
 /* The maximum percentage of memory that the compressed pool can occupy */
 static unsigned int zswap_max_pool_percent = 20;
@@ -342,7 +336,7 @@ static void zswap_entry_put(struct zswap_tree *tree,
 static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 				pgoff_t offset)
 {
-	struct zswap_entry *entry = NULL;
+	struct zswap_entry *entry;
 
 	entry = zswap_rb_search(root, offset);
 	if (entry)
@@ -615,19 +609,29 @@ error:
 	return NULL;
 }
 
-static struct zswap_pool *__zswap_pool_create_fallback(void)
+static __init struct zswap_pool *__zswap_pool_create_fallback(void)
 {
 	if (!crypto_has_comp(zswap_compressor, 0, 0)) {
+		if (!strcmp(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT)) {
+			pr_err("default compressor %s not available\n",
+			       zswap_compressor);
+			return NULL;
+		}
 		pr_err("compressor %s not available, using default %s\n",
 		       zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT);
-		strncpy(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT,
-			sizeof(zswap_compressor));
+		param_free_charp(&zswap_compressor);
+		zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
 	}
 	if (!zpool_has_pool(zswap_zpool_type)) {
+		if (!strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
+			pr_err("default zpool %s not available\n",
+			       zswap_zpool_type);
+			return NULL;
+		}
 		pr_err("zpool %s not available, using default %s\n",
 		       zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT);
-		strncpy(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT,
-			sizeof(zswap_zpool_type));
+		param_free_charp(&zswap_zpool_type);
+		zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
 	}
 
 	return zswap_pool_create(zswap_zpool_type, zswap_compressor);
@@ -684,43 +688,39 @@ static void zswap_pool_put(struct zswap_pool *pool)
 * param callbacks
 **********************************/
 
+/* val must be a null-terminated string */
 static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 			     char *type, char *compressor)
 {
 	struct zswap_pool *pool, *put_pool = NULL;
-	char str[kp->str->maxlen], *s;
+	char *s = strstrip((char *)val);
 	int ret;
 
-	/*
-	 * kp is either zswap_zpool_kparam or zswap_compressor_kparam, defined
-	 * at the top of this file, so maxlen is CRYPTO_MAX_ALG_NAME (64) or
-	 * 32 (arbitrary).
-	 */
-	strlcpy(str, val, kp->str->maxlen);
-	s = strim(str);
+	/* no change required */
+	if (!strcmp(s, *(char **)kp->arg))
+		return 0;
 
 	/* if this is load-time (pre-init) param setting,
 	 * don't create a pool; that's done during init.
 	 */
 	if (!zswap_init_started)
-		return param_set_copystring(s, kp);
-
-	/* no change required */
-	if (!strncmp(kp->str->string, s, kp->str->maxlen))
-		return 0;
+		return param_set_charp(s, kp);
 
 	if (!type) {
-		type = s;
-		if (!zpool_has_pool(type)) {
-			pr_err("zpool %s not available\n", type);
+		if (!zpool_has_pool(s)) {
+			pr_err("zpool %s not available\n", s);
 			return -ENOENT;
 		}
+		type = s;
 	} else if (!compressor) {
-		compressor = s;
-		if (!crypto_has_comp(compressor, 0, 0)) {
-			pr_err("compressor %s not available\n", compressor);
+		if (!crypto_has_comp(s, 0, 0)) {
+			pr_err("compressor %s not available\n", s);
 			return -ENOENT;
 		}
+		compressor = s;
+	} else {
+		WARN_ON(1);
+		return -EINVAL;
 	}
 
 	spin_lock(&zswap_pools_lock);
@@ -736,7 +736,7 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 	}
 
 	if (pool)
-		ret = param_set_copystring(s, kp);
+		ret = param_set_charp(s, kp);
 	else
 		ret = -EINVAL;
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index c8db44ab2ee7..95cd5fd3a780 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -71,7 +71,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			   const struct sk_buff *skb)
 {
 	struct flow_stats *stats;
-	int node = numa_node_id();
+	int node = numa_mem_id();
 	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	stats = rcu_dereference(flow->stats[node]);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 425ca2f37dd9..f14f24ee9983 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -297,7 +297,7 @@ static int rpc_complete_task(struct rpc_task *task)
 	clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
 	ret = atomic_dec_and_test(&task->tk_count);
 	if (waitqueue_active(wq))
-		__wake_up_locked_key(wq, TASK_NORMAL, 1, &k);
+		__wake_up_locked_key(wq, TASK_NORMAL, &k);
 	spin_unlock_irqrestore(&wq->lock, flags);
 	return ret;
 }
diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile
index 877a50355d7f..a1a97085847d 100644
--- a/tools/testing/selftests/membarrier/Makefile
+++ b/tools/testing/selftests/membarrier/Makefile
@@ -1,11 +1,10 @@
 CFLAGS += -g -I../../../../usr/include/
 
-all:
-	$(CC) $(CFLAGS) membarrier_test.c -o membarrier_test
-
 TEST_PROGS := membarrier_test
 
+all: $(TEST_PROGS)
+
 include ../lib.mk
 
 clean:
-	$(RM) membarrier_test
+	$(RM) $(TEST_PROGS)
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index dde312508007..535f0fef4d0b 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -1,9 +1,6 @@
 #define _GNU_SOURCE
-#define __EXPORTED_HEADERS__
-
 #include <linux/membarrier.h>
-#include <asm-generic/unistd.h>
-#include <sys/syscall.h>
+#include <syscall.h>
 #include <stdio.h>
 #include <errno.h>
 #include <string.h>
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d36fab7d8ebd..e4bb1de1d526 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,10 +1,12 @@
 # Makefile for vm selftests
 
-CFLAGS = -Wall
+CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 BINARIES = compaction_test
 BINARIES += hugepage-mmap
 BINARIES += hugepage-shm
 BINARIES += map_hugetlb
+BINARIES += mlock2-tests
+BINARIES += on-fault-limit
 BINARIES += thuge-gen
 BINARIES += transhuge-stress
 BINARIES += userfaultfd
@@ -12,8 +14,11 @@ BINARIES += userfaultfd
 all: $(BINARIES)
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^ -lrt
-userfaultfd: userfaultfd.c
-	$(CC) $(CFLAGS) -O2 -o $@ $^ -lpthread
+userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h
+	$(CC) $(CFLAGS) -O2 -o $@ $< -lpthread
+
+../../../../usr/include/linux/kernel.h:
+	make -C ../../../.. headers_install
 
 TEST_PROGS := run_vmtests
 TEST_FILES := $(BINARIES)
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
new file mode 100644
index 000000000000..909802e90855
--- /dev/null
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -0,0 +1,737 @@
+#include <sys/mman.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <syscall.h>
+#include <errno.h>
+#include <stdbool.h>
+
+#ifndef MLOCK_ONFAULT
+#define MLOCK_ONFAULT 1
+#endif
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int mlock2_(void *start, size_t len, int flags)
+{
+#ifdef __NR_mlock2
+	return syscall(__NR_mlock2, start, len, flags);
+#else
+	errno = ENOSYS;
+	return -1;
+#endif
+}
+
+struct vm_boundaries {
+	unsigned long start;
+	unsigned long end;
+};
+
+static int get_vm_area(unsigned long addr, struct vm_boundaries *area)
+{
+	FILE *file;
+	int ret = 1;
+	char line[1024] = {0};
+	char *end_addr;
+	char *stop;
+	unsigned long start;
+	unsigned long end;
+
+	if (!area)
+		return ret;
+
+	file = fopen("/proc/self/maps", "r");
+	if (!file) {
+		perror("fopen");
+		return ret;
+	}
+
+	memset(area, 0, sizeof(struct vm_boundaries));
+
+	while(fgets(line, 1024, file)) {
+		end_addr = strchr(line, '-');
+		if (!end_addr) {
+			printf("cannot parse /proc/self/maps\n");
+			goto out;
+		}
+		*end_addr = '\0';
+		end_addr++;
+		stop = strchr(end_addr, ' ');
+		if (!stop) {
+			printf("cannot parse /proc/self/maps\n");
+			goto out;
+		}
+		stop = '\0';
+
+		sscanf(line, "%lx", &start);
+		sscanf(end_addr, "%lx", &end);
+
+		if (start <= addr && end > addr) {
+			area->start = start;
+			area->end = end;
+			ret = 0;
+			goto out;
+		}
+	}
+out:
+	fclose(file);
+	return ret;
+}
+
+static uint64_t get_pageflags(unsigned long addr)
+{
+	FILE *file;
+	uint64_t pfn;
+	unsigned long offset;
+
+	file = fopen("/proc/self/pagemap", "r");
+	if (!file) {
+		perror("fopen pagemap");
+		_exit(1);
+	}
+
+	offset = addr / getpagesize() * sizeof(pfn);
+
+	if (fseek(file, offset, SEEK_SET)) {
+		perror("fseek pagemap");
+		_exit(1);
+	}
+
+	if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
+		perror("fread pagemap");
+		_exit(1);
+	}
+
+	fclose(file);
+	return pfn;
+}
+
+static uint64_t get_kpageflags(unsigned long pfn)
+{
+	uint64_t flags;
+	FILE *file;
+
+	file = fopen("/proc/kpageflags", "r");
+	if (!file) {
+		perror("fopen kpageflags");
+		_exit(1);
+	}
+
+	if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
+		perror("fseek kpageflags");
+		_exit(1);
+	}
+
+	if (fread(&flags, sizeof(flags), 1, file) != 1) {
+		perror("fread kpageflags");
+		_exit(1);
+	}
+
+	fclose(file);
+	return flags;
+}
+
+static FILE *seek_to_smaps_entry(unsigned long addr)
+{
+	FILE *file;
+	char *line = NULL;
+	size_t size = 0;
+	unsigned long start, end;
+	char perms[5];
+	unsigned long offset;
+	char dev[32];
+	unsigned long inode;
+	char path[BUFSIZ];
+
+	file = fopen("/proc/self/smaps", "r");
+	if (!file) {
+		perror("fopen smaps");
+		_exit(1);
+	}
+
+	while (getline(&line, &size, file) > 0) {
+		if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n",
+			   &start, &end, perms, &offset, dev, &inode, path) < 6)
+			goto next;
+
+		if (start <= addr && addr < end)
+			goto out;
+
+next:
+		free(line);
+		line = NULL;
+		size = 0;
+	}
+
+	fclose(file);
+	file = NULL;
+
+out:
+	free(line);
+	return file;
+}
+
+#define VMFLAGS "VmFlags:"
+
+static bool is_vmflag_set(unsigned long addr, const char *vmflag)
+{
+	char *line = NULL;
+	char *flags;
+	size_t size = 0;
+	bool ret = false;
+	FILE *smaps;
+
+	smaps = seek_to_smaps_entry(addr);
+	if (!smaps) {
+		printf("Unable to parse /proc/self/smaps\n");
+		goto out;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, VMFLAGS)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		flags = line + strlen(VMFLAGS);
+		ret = (strstr(flags, vmflag) != NULL);
+		goto out;
+	}
+
+out:
+	free(line);
+	fclose(smaps);
+	return ret;
+}
+
+#define SIZE "Size:"
+#define RSS  "Rss:"
+#define LOCKED "lo"
+
+static bool is_vma_lock_on_fault(unsigned long addr)
+{
+	bool ret = false;
+	bool locked;
+	FILE *smaps = NULL;
+	unsigned long vma_size, vma_rss;
+	char *line = NULL;
+	char *value;
+	size_t size = 0;
+
+	locked = is_vmflag_set(addr, LOCKED);
+	if (!locked)
+		goto out;
+
+	smaps = seek_to_smaps_entry(addr);
+	if (!smaps) {
+		printf("Unable to parse /proc/self/smaps\n");
+		goto out;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, SIZE)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		value = line + strlen(SIZE);
+		if (sscanf(value, "%lu kB", &vma_size) < 1) {
+			printf("Unable to parse smaps entry for Size\n");
+			goto out;
+		}
+		break;
+	}
+
+	while (getline(&line, &size, smaps) > 0) {
+		if (!strstr(line, RSS)) {
+			free(line);
+			line = NULL;
+			size = 0;
+			continue;
+		}
+
+		value = line + strlen(RSS);
+		if (sscanf(value, "%lu kB", &vma_rss) < 1) {
+			printf("Unable to parse smaps entry for Rss\n");
+			goto out;
+		}
+		break;
+	}
+
+	ret = locked && (vma_rss < vma_size);
+out:
+	free(line);
+	if (smaps)
+		fclose(smaps);
+	return ret;
+}
+
+#define PRESENT_BIT     0x8000000000000000
+#define PFN_MASK        0x007FFFFFFFFFFFFF
+#define UNEVICTABLE_BIT (1UL << 18)
+
+static int lock_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Both pages should be present */
+	if (((page1_flags & PRESENT_BIT) == 0) ||
+	    ((page2_flags & PRESENT_BIT) == 0)) {
+		printf("Failed to make both pages present\n");
+		return 1;
+	}
+
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	/* Both pages should be unevictable */
+	if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
+	    ((page2_flags & UNEVICTABLE_BIT) == 0)) {
+		printf("Failed to make both pages unevictable\n");
+		return 1;
+	}
+
+	if (!is_vmflag_set((unsigned long)map, LOCKED)) {
+		printf("VMA flag %s is missing on page 1\n", LOCKED);
+		return 1;
+	}
+
+	if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+		printf("VMA flag %s is missing on page 2\n", LOCKED);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int unlock_lock_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
+		printf("A page is still marked unevictable after unlock\n");
+		return 1;
+	}
+
+	if (is_vmflag_set((unsigned long)map, LOCKED)) {
+		printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
+		return 1;
+	}
+
+	if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+		printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int test_mlock_lock()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	if (mlock2_(map, 2 * page_size, 0)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(0)");
+		goto unmap;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	/* Now unlock and recheck attributes */
+	if (munlock(map, 2 * page_size)) {
+		perror("munlock()");
+		goto unmap;
+	}
+
+	ret = unlock_lock_check(map);
+
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int onfault_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Neither page should be present */
+	if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
+		printf("Pages were made present by MLOCK_ONFAULT\n");
+		return 1;
+	}
+
+	*map = 'a';
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+
+	/* Only page 1 should be present */
+	if ((page1_flags & PRESENT_BIT) == 0) {
+		printf("Page 1 is not present after fault\n");
+		return 1;
+	} else if (page2_flags & PRESENT_BIT) {
+		printf("Page 2 was made present\n");
+		return 1;
+	}
+
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+	/* Page 1 should be unevictable */
+	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+		printf("Failed to make faulted page unevictable\n");
+		return 1;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map)) {
+		printf("VMA is not marked for lock on fault\n");
+		return 1;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA is not marked for lock on fault\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int unlock_onfault_check(char *map)
+{
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags;
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+	if (page1_flags & UNEVICTABLE_BIT) {
+		printf("Page 1 is still marked unevictable after unlock\n");
+		return 1;
+	}
+
+	if (is_vma_lock_on_fault((unsigned long)map) ||
+	    is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA is still lock on fault after unlock\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int test_mlock_onfault()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(MLOCK_ONFAULT)");
+		goto unmap;
+	}
+
+	if (onfault_check(map))
+		goto unmap;
+
+	/* Now unlock and recheck attributes */
+	if (munlock(map, 2 * page_size)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("munlock()");
+		goto unmap;
+	}
+
+	ret = unlock_onfault_check(map);
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int test_lock_onfault_of_present()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+	uint64_t page1_flags, page2_flags;
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("test_mlock_locked mmap");
+		goto out;
+	}
+
+	*map = 'a';
+
+	if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock2(MLOCK_ONFAULT)");
+		goto unmap;
+	}
+
+	page1_flags = get_pageflags((unsigned long)map);
+	page2_flags = get_pageflags((unsigned long)map + page_size);
+	page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+	page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+	/* Page 1 should be unevictable */
+	if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+		printf("Failed to make present page unevictable\n");
+		goto unmap;
+	}
+
+	if (!is_vma_lock_on_fault((unsigned long)map) ||
+	    !is_vma_lock_on_fault((unsigned long)map + page_size)) {
+		printf("VMA with present pages is not marked lock on fault\n");
+		goto unmap;
+	}
+	ret = 0;
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	return ret;
+}
+
+static int test_munlockall()
+{
+	char *map;
+	int ret = 1;
+	unsigned long page_size = getpagesize();
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+	if (map == MAP_FAILED) {
+		perror("test_munlockall mmap");
+		goto out;
+	}
+
+	if (mlockall(MCL_CURRENT)) {
+		perror("mlockall(MCL_CURRENT)");
+		goto out;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	if (unlock_lock_check(map))
+		goto unmap;
+
+	munmap(map, 2 * page_size);
+
+	map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+	if (map == MAP_FAILED) {
+		perror("test_munlockall second mmap");
+		goto out;
+	}
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT)) {
+		perror("mlockall(MCL_CURRENT | MCL_ONFAULT)");
+		goto unmap;
+	}
+
+	if (onfault_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	if (unlock_onfault_check(map))
+		goto unmap;
+
+	if (mlockall(MCL_CURRENT | MCL_FUTURE)) {
+		perror("mlockall(MCL_CURRENT | MCL_FUTURE)");
+		goto out;
+	}
+
+	if (lock_check(map))
+		goto unmap;
+
+	if (munlockall()) {
+		perror("munlockall()");
+		goto unmap;
+	}
+
+	ret = unlock_lock_check(map);
+
+unmap:
+	munmap(map, 2 * page_size);
+out:
+	munlockall();
+	return ret;
+}
+
+static int test_vma_management(bool call_mlock)
+{
+	int ret = 1;
+	void *map;
+	unsigned long page_size = getpagesize();
+	struct vm_boundaries page1;
+	struct vm_boundaries page2;
+	struct vm_boundaries page3;
+
+	map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+	if (map == MAP_FAILED) {
+		perror("mmap()");
+		return ret;
+	}
+
+	if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
+		if (errno == ENOSYS) {
+			printf("Cannot call new mlock family, skipping test\n");
+			_exit(0);
+		}
+		perror("mlock(ONFAULT)\n");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/*
+	 * Before we unlock a portion, we need to that all three pages are in
+	 * the same VMA.  If they are not we abort this test (Note that this is
+	 * not a failure)
+	 */
+	if (page1.start != page2.start || page2.start != page3.start) {
+		printf("VMAs are not merged to start, aborting test\n");
+		ret = 0;
+		goto out;
+	}
+
+	if (munlock(map + page_size, page_size)) {
+		perror("munlock()");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/* All three VMAs should be different */
+	if (page1.start == page2.start || page2.start == page3.start) {
+		printf("failed to split VMA for munlock\n");
+		goto out;
+	}
+
+	/* Now unlock the first and third page and check the VMAs again */
+	if (munlock(map, page_size * 3)) {
+		perror("munlock()");
+		goto out;
+	}
+
+	if (get_vm_area((unsigned long)map, &page1) ||
+	    get_vm_area((unsigned long)map + page_size, &page2) ||
+	    get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+		printf("couldn't find mapping in /proc/self/maps\n");
+		goto out;
+	}
+
+	/* Now all three VMAs should be the same */
+	if (page1.start != page2.start || page2.start != page3.start) {
+		printf("failed to merge VMAs after munlock\n");
+		goto out;
+	}
+
+	ret = 0;
+out:
+	munmap(map, 3 * page_size);
+	return ret;
+}
+
+static int test_mlockall(int (test_function)(bool call_mlock))
+{
+	int ret = 1;
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+		perror("mlockall");
+		return ret;
+	}
+
+	ret = test_function(false);
+	munlockall();
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	int ret = 0;
+	ret += test_mlock_lock();
+	ret += test_mlock_onfault();
+	ret += test_munlockall();
+	ret += test_lock_onfault_of_present();
+	ret += test_vma_management(true);
+	ret += test_mlockall(test_vma_management);
+	return ret;
+}
+
diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c
new file mode 100644
index 000000000000..245acccce42d
--- /dev/null
+++ b/tools/testing/selftests/vm/on-fault-limit.c
@@ -0,0 +1,47 @@
+#include <sys/mman.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int test_limit(void)
+{
+	int ret = 1;
+	struct rlimit lims;
+	void *map;
+
+	if (getrlimit(RLIMIT_MEMLOCK, &lims)) {
+		perror("getrlimit");
+		return ret;
+	}
+
+	if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+		perror("mlockall");
+		return ret;
+	}
+
+	map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, 0, 0);
+	if (map != MAP_FAILED)
+		printf("mmap should have failed, but didn't\n");
+	else {
+		ret = 0;
+		munmap(map, 2 * lims.rlim_max);
+	}
+
+	munlockall();
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	int ret = 0;
+
+	ret += test_limit();
+	return ret;
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 9179ce8df485..2df21b3bb26d 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -106,4 +106,26 @@ else
 	echo "[PASS]"
 fi
 
+echo "--------------------"
+echo "running on-fault-limit"
+echo "--------------------"
+sudo -u nobody ./on-fault-limit
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
+echo "--------------------"
+echo "running mlock2-tests"
+echo "--------------------"
+./mlock2-tests
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 exit $exitcode
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 7c1d958857d2..d77ed41b2094 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -64,19 +64,9 @@
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
 #include <pthread.h>
-#include "../../../../include/uapi/linux/userfaultfd.h"
-
-#ifdef __x86_64__
-#define __NR_userfaultfd 323
-#elif defined(__i386__)
-#define __NR_userfaultfd 374
-#elif defined(__powewrpc__)
-#define __NR_userfaultfd 364
-#elif defined(__s390__)
-#define __NR_userfaultfd 355
-#else
-#error "missing __NR_userfaultfd definition"
-#endif
+#include <linux/userfaultfd.h>
+
+#ifdef __NR_userfaultfd
 
 static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
 
@@ -432,7 +422,7 @@ static int userfaultfd_stress(void)
 	struct uffdio_register uffdio_register;
 	struct uffdio_api uffdio_api;
 	unsigned long cpu;
-	int uffd_flags;
+	int uffd_flags, err;
 	unsigned long userfaults[nr_cpus];
 
 	if (posix_memalign(&area, page_size, nr_pages * page_size)) {
@@ -475,6 +465,14 @@ static int userfaultfd_stress(void)
 		*area_mutex(area_src, nr) = (pthread_mutex_t)
 			PTHREAD_MUTEX_INITIALIZER;
 		count_verify[nr] = *area_count(area_src, nr) = 1;
+		/*
+		 * In the transition between 255 to 256, powerpc will
+		 * read out of order in my_bcmp and see both bytes as
+		 * zero, so leave a placeholder below always non-zero
+		 * after the count, to avoid my_bcmp to trigger false
+		 * positives.
+		 */
+		*(area_count(area_src, nr) + 1) = 1;
 	}
 
 	pipefd = malloc(sizeof(int) * nr_cpus * 2);
@@ -501,6 +499,7 @@ static int userfaultfd_stress(void)
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, 16*1024*1024);
 
+	err = 0;
 	while (bounces--) {
 		unsigned long expected_ioctls;
 
@@ -581,20 +580,13 @@ static int userfaultfd_stress(void)
 		/* verification */
 		if (bounces & BOUNCE_VERIFY) {
 			for (nr = 0; nr < nr_pages; nr++) {
-				if (my_bcmp(area_dst,
-					    area_dst + nr * page_size,
-					    sizeof(pthread_mutex_t))) {
-					fprintf(stderr,
-						"error mutex 2 %lu\n",
-						nr);
-					bounces = 0;
-				}
 				if (*area_count(area_dst, nr) != count_verify[nr]) {
 					fprintf(stderr,
 						"error area_count %Lu %Lu %lu\n",
 						*area_count(area_src, nr),
 						count_verify[nr],
 						nr);
+					err = 1;
 					bounces = 0;
 				}
 			}
@@ -611,7 +603,7 @@ static int userfaultfd_stress(void)
 		printf("\n");
 	}
 
-	return 0;
+	return err;
 }
 
 int main(int argc, char **argv)
@@ -620,8 +612,8 @@ int main(int argc, char **argv)
 		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
 	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
 	page_size = sysconf(_SC_PAGE_SIZE);
-	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) >
-	    page_size)
+	if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
+	    > page_size)
 		fprintf(stderr, "Impossible to run this test\n"), exit(2);
 	nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size /
 		nr_cpus;
@@ -639,3 +631,15 @@ int main(int argc, char **argv)
 	       nr_pages, nr_pages_per_cpu);
 	return userfaultfd_stress();
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+	return 0;
+}
+
+#endif /* __NR_userfaultfd */