Merge branch 'akpm-current/current'

149 files changed, 3437 insertions, 2948 deletions

diff --git a/Documentation/cgroups/hugetlb.txt b/Documentation/cgroups/hugetlb.txt
index a9faaca1f029..106245c3aecc 100644
--- a/Documentation/cgroups/hugetlb.txt
+++ b/Documentation/cgroups/hugetlb.txt
@@ -29,7 +29,7 @@ Brief summary of control files
 
  hugetlb.<hugepagesize>.limit_in_bytes     # set/show limit of "hugepagesize" hugetlb usage
  hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb  usage recorded
- hugetlb.<hugepagesize>.usage_in_bytes     # show current res_counter usage for "hugepagesize" hugetlb
+ hugetlb.<hugepagesize>.usage_in_bytes     # show current usage for "hugepagesize" hugetlb
  hugetlb.<hugepagesize>.failcnt		   # show the number of allocation failure due to HugeTLB limit
 
 For a system supporting two hugepage size (16M and 16G) the control
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 02ab997a1ed2..f624727ab404 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -52,9 +52,9 @@ Brief summary of control files.
  tasks				 # attach a task(thread) and show list of threads
  cgroup.procs			 # show list of processes
  cgroup.event_control		 # an interface for event_fd()
- memory.usage_in_bytes		 # show current res_counter usage for memory
+ memory.usage_in_bytes		 # show current usage for memory
 				 (See 5.5 for details)
- memory.memsw.usage_in_bytes	 # show current res_counter usage for memory+Swap
+ memory.memsw.usage_in_bytes	 # show current usage for memory+Swap
 				 (See 5.5 for details)
  memory.limit_in_bytes		 # set/show limit of memory usage
  memory.memsw.limit_in_bytes	 # set/show limit of memory+Swap usage
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
deleted file mode 100644
index 762ca54eb929..000000000000
--- a/Documentation/cgroups/resource_counter.txt
+++ /dev/null
@@ -1,197 +0,0 @@
-
-		The Resource Counter
-
-The resource counter, declared at include/linux/res_counter.h,
-is supposed to facilitate the resource management by controllers
-by providing common stuff for accounting.
-
-This "stuff" includes the res_counter structure and routines
-to work with it.
-
-
-
-1. Crucial parts of the res_counter structure
-
- a. unsigned long long usage
-
- 	The usage value shows the amount of a resource that is consumed
-	by a group at a given time. The units of measurement should be
-	determined by the controller that uses this counter. E.g. it can
-	be bytes, items or any other unit the controller operates on.
-
- b. unsigned long long max_usage
-
- 	The maximal value of the usage over time.
-
- 	This value is useful when gathering statistical information about
-	the particular group, as it shows the actual resource requirements
-	for a particular group, not just some usage snapshot.
-
- c. unsigned long long limit
-
- 	The maximal allowed amount of resource to consume by the group. In
-	case the group requests for more resources, so that the usage value
-	would exceed the limit, the resource allocation is rejected (see
-	the next section).
-
- d. unsigned long long failcnt
-
- 	The failcnt stands for "failures counter". This is the number of
-	resource allocation attempts that failed.
-
- c. spinlock_t lock
-
- 	Protects changes of the above values.
-
-
-
-2. Basic accounting routines
-
- a. void res_counter_init(struct res_counter *rc,
-				struct res_counter *rc_parent)
-
- 	Initializes the resource counter. As usual, should be the first
-	routine called for a new counter.
-
-	The struct res_counter *parent can be used to define a hierarchical
-	child -> parent relationship directly in the res_counter structure,
-	NULL can be used to define no relationship.
-
- c. int res_counter_charge(struct res_counter *rc, unsigned long val,
-				struct res_counter **limit_fail_at)
-
-	When a resource is about to be allocated it has to be accounted
-	with the appropriate resource counter (controller should determine
-	which one to use on its own). This operation is called "charging".
-
-	This is not very important which operation - resource allocation
-	or charging - is performed first, but
-	  * if the allocation is performed first, this may create a
-	    temporary resource over-usage by the time resource counter is
-	    charged;
-	  * if the charging is performed first, then it should be uncharged
-	    on error path (if the one is called).
-
-	If the charging fails and a hierarchical dependency exists, the
-	limit_fail_at parameter is set to the particular res_counter element
-	where the charging failed.
-
- d. u64 res_counter_uncharge(struct res_counter *rc, unsigned long val)
-
-	When a resource is released (freed) it should be de-accounted
-	from the resource counter it was accounted to.  This is called
-	"uncharging". The return value of this function indicate the amount
-	of charges still present in the counter.
-
-	The _locked routines imply that the res_counter->lock is taken.
-
- e. u64 res_counter_uncharge_until
-		(struct res_counter *rc, struct res_counter *top,
-		 unsigned long val)
-
-	Almost same as res_counter_uncharge() but propagation of uncharge
-	stops when rc == top. This is useful when kill a res_counter in
-	child cgroup.
-
- 2.1 Other accounting routines
-
-    There are more routines that may help you with common needs, like
-    checking whether the limit is reached or resetting the max_usage
-    value. They are all declared in include/linux/res_counter.h.
-
-
-
-3. Analyzing the resource counter registrations
-
- a. If the failcnt value constantly grows, this means that the counter's
-    limit is too tight. Either the group is misbehaving and consumes too
-    many resources, or the configuration is not suitable for the group
-    and the limit should be increased.
-
- b. The max_usage value can be used to quickly tune the group. One may
-    set the limits to maximal values and either load the container with
-    a common pattern or leave one for a while. After this the max_usage
-    value shows the amount of memory the container would require during
-    its common activity.
-
-    Setting the limit a bit above this value gives a pretty good
-    configuration that works in most of the cases.
-
- c. If the max_usage is much less than the limit, but the failcnt value
-    is growing, then the group tries to allocate a big chunk of resource
-    at once.
-
- d. If the max_usage is much less than the limit, but the failcnt value
-    is 0, then this group is given too high limit, that it does not
-    require. It is better to lower the limit a bit leaving more resource
-    for other groups.
-
-
-
-4. Communication with the control groups subsystem (cgroups)
-
-All the resource controllers that are using cgroups and resource counters
-should provide files (in the cgroup filesystem) to work with the resource
-counter fields. They are recommended to adhere to the following rules:
-
- a. File names
-
- 	Field name	File name
-	---------------------------------------------------
-	usage		usage_in_<unit_of_measurement>
-	max_usage	max_usage_in_<unit_of_measurement>
-	limit		limit_in_<unit_of_measurement>
-	failcnt		failcnt
-	lock		no file :)
-
- b. Reading from file should show the corresponding field value in the
-    appropriate format.
-
- c. Writing to file
-
- 	Field		Expected behavior
-	----------------------------------
-	usage		prohibited
-	max_usage	reset to usage
-	limit		set the limit
-	failcnt		reset to zero
-
-
-
-5. Usage example
-
- a. Declare a task group (take a look at cgroups subsystem for this) and
-    fold a res_counter into it
-
-	struct my_group {
-		struct res_counter res;
-
-		<other fields>
-	}
-
- b. Put hooks in resource allocation/release paths
-
- 	int alloc_something(...)
-	{
-		if (res_counter_charge(res_counter_ptr, amount) < 0)
-			return -ENOMEM;
-
-		<allocate the resource and return to the caller>
-	}
-
-	void release_something(...)
-	{
-		res_counter_uncharge(res_counter_ptr, amount);
-
-		<release the resource>
-	}
-
-    In order to keep the usage value self-consistent, both the
-    "res_counter_ptr" and the "amount" in release_something() should be
-    the same as they were in the alloc_something() when the releasing
-    resource was allocated.
-
- c. Provide the way to read res_counter values and set them (the cgroups
-    still can help with it).
-
- c. Compile and run :)
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 79699c200766..62261c04060a 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -2,9 +2,6 @@
 LED handling under Linux
 ========================
 
-If you're reading this and thinking about keyboard leds, these are
-handled by the input subsystem and the led class is *not* needed.
-
 In its simplest form, the LED class just allows control of LEDs from
 userspace. LEDs appear in /sys/class/leds/. The maximum brightness of the
 LED is defined in max_brightness file. The brightness file will set the brightness
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 5a615c14f75d..8858db8f8805 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -216,6 +216,12 @@ dentry names:
 	equivalent of %s dentry->d_name.name we used to use, %pd<n> prints
 	n last components.  %pD does the same thing for struct file.
 
+task_struct comm name:
+
+        %pT
+
+        For printing task_struct->comm.
+
 struct va_format:
 
 	%pV
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 57baff5bdb80..d7fc4abf7cf0 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -115,10 +115,12 @@ set during run time.
 
 auto_msgmni:
 
-Enables/Disables automatic recomputing of msgmni upon memory add/remove
-or upon ipc namespace creation/removal (see the msgmni description
-above). Echoing "1" into this file enables msgmni automatic recomputing.
-Echoing "0" turns it off. auto_msgmni default value is 1.
+This variable has no effect and may be removed in future kernel
+releases. Reading it always returns 0.
+Up to Linux 3.17, it enabled/disabled automatic recomputing of msgmni
+upon memory add/remove or upon ipc namespace creation/removal.
+Echoing "1" into this file enabled msgmni automatic recomputing.
+Echoing "0" turned it off. auto_msgmni default value was 1.
 
 
 ==============================================================
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 89c4b5ccc68d..6bcc5595b731 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -5,6 +5,7 @@ config ARM
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_USE_BUILTIN_BSWAP
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index ac9afde76dea..3ac8bb1a1898 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,6 +1,7 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_USE_CMPXCHG_LOCKREF
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 5845ffea67c3..dc063fe6646a 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2662,7 +2662,7 @@ pfm_context_create(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg
 
 	ret = -ENOMEM;
 
-	fd = get_unused_fd();
+	fd = get_unused_fd_flags(0);
 	if (fd < 0)
 		return fd;
 
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 6feded3b0c4c..0583778bc31f 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -1,5 +1,6 @@
 config MICROBLAZE
 	def_bool y
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_OPTIONAL_GPIOLIB
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 88eace4e28c3..0ff466271d56 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -128,6 +128,7 @@ config PPC
 	select HAVE_BPF_JIT if PPC64
 	select HAVE_ARCH_JUMP_LABEL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_TIME_VSYSCALL_OLD
@@ -148,6 +149,7 @@ config PPC
 	select HAVE_ARCH_AUDITSYSCALL
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
+	select HAVE_GENERIC_RCU_GUP
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 623f2971ce0e..7855cce9c969 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -48,7 +48,7 @@ static inline unsigned int hugepd_shift(hugepd_t hpd)
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
 				    unsigned pdshift)
 {
 	/*
@@ -58,9 +58,9 @@ static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
 	 */
 	unsigned long idx = 0;
 
-	pte_t *dir = hugepd_page(*hpdp);
+	pte_t *dir = hugepd_page(hpd);
 #ifndef CONFIG_PPC_FSL_BOOK3E
-	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
+	idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
 #endif
 
 	return dir + idx;
@@ -193,7 +193,7 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 }
 
 #define hugepd_shift(x) 0
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
 				    unsigned pdshift)
 {
 	return 0;
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 26fe1ae15212..aa430ec14895 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -379,12 +379,12 @@ static inline int hugepd_ok(hugepd_t hpd)
 }
 #endif
 
-#define is_hugepd(pdep)               (hugepd_ok(*((hugepd_t *)(pdep))))
+#define is_hugepd(hpd)               (hugepd_ok(hpd))
 int pgd_huge(pgd_t pgd);
 #else /* CONFIG_HUGETLB_PAGE */
 #define is_hugepd(pdep)			0
-#define pgd_huge(pgd)			0
 #endif /* CONFIG_HUGETLB_PAGE */
+#define __hugepd(x) ((hugepd_t) { (x) })
 
 struct page;
 extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index ae153c40ab7c..29c36242cc6a 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -575,6 +575,5 @@ static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
 	 */
 	return true;
 }
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 316f9a5da173..4a67c1ddb91b 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -274,11 +274,6 @@ extern void paging_init(void);
  */
 extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 
-extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr,
-		      unsigned long end, int write, struct page **pages, int *nr);
-
-extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		       unsigned long end, int write, struct page **pages, int *nr);
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_large(pmd)		0
 #define has_transparent_hugepage() 0
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 325e861616a1..438dcd3fd0d1 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -6,7 +6,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
-obj-y				:= fault.o mem.o pgtable.o gup.o mmap.o \
+obj-y				:= fault.o mem.o pgtable.o mmap.o \
 				   init_$(CONFIG_WORD_SIZE).o \
 				   pgtable_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
deleted file mode 100644
index d8746684f606..000000000000
--- a/arch/powerpc/mm/gup.c
+++ /dev/null
@@ -1,235 +0,0 @@
-/*
- * Lockless get_user_pages_fast for powerpc
- *
- * Copyright (C) 2008 Nick Piggin
- * Copyright (C) 2008 Novell Inc.
- */
-#undef DEBUG
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-
-#ifdef __HAVE_ARCH_PTE_SPECIAL
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long mask, result;
-	pte_t *ptep;
-
-	result = _PAGE_PRESENT|_PAGE_USER;
-	if (write)
-		result |= _PAGE_RW;
-	mask = result | _PAGE_SPECIAL;
-
-	ptep = pte_offset_kernel(&pmd, addr);
-	do {
-		pte_t pte = ACCESS_ONCE(*ptep);
-		struct page *page;
-		/*
-		 * Similar to the PMD case, NUMA hinting must take slow path
-		 */
-		if (pte_numa(pte))
-			return 0;
-
-		if ((pte_val(pte) & mask) != result)
-			return 0;
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
-		if (!page_cache_get_speculative(page))
-			return 0;
-		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(page);
-			return 0;
-		}
-		pages[*nr] = page;
-		(*nr)++;
-
-	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 1;
-}
-
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
-		int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pmd_t *pmdp;
-
-	pmdp = pmd_offset(&pud, addr);
-	do {
-		pmd_t pmd = ACCESS_ONCE(*pmdp);
-
-		next = pmd_addr_end(addr, end);
-		/*
-		 * If we find a splitting transparent hugepage we
-		 * return zero. That will result in taking the slow
-		 * path which will call wait_split_huge_page()
-		 * if the pmd is still in splitting state
-		 */
-		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
-			return 0;
-		if (pmd_huge(pmd) || pmd_large(pmd)) {
-			/*
-			 * NUMA hinting faults need to be handled in the GUP
-			 * slowpath for accounting purposes and so that they
-			 * can be serialised against THP migration.
-			 */
-			if (pmd_numa(pmd))
-				return 0;
-
-			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
-					 write, pages, nr))
-				return 0;
-		} else if (is_hugepd(pmdp)) {
-			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
-					addr, next, write, pages, nr))
-				return 0;
-		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
-			return 0;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
-		int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pud_t *pudp;
-
-	pudp = pud_offset(&pgd, addr);
-	do {
-		pud_t pud = ACCESS_ONCE(*pudp);
-
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			return 0;
-		if (pud_huge(pud)) {
-			if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next,
-					 write, pages, nr))
-				return 0;
-		} else if (is_hugepd(pudp)) {
-			if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT,
-					addr, next, write, pages, nr))
-				return 0;
-		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
-			return 0;
-	} while (pudp++, addr = next, addr != end);
-
-	return 1;
-}
-
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr, len, end;
-	unsigned long next;
-	unsigned long flags;
-	pgd_t *pgdp;
-	int nr = 0;
-
-	pr_devel("%s(%lx,%x,%s)\n", __func__, start, nr_pages, write ? "write" : "read");
-
-	start &= PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-
-	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
-					start, len)))
-		return 0;
-
-	pr_devel("  aligned: %lx .. %lx\n", start, end);
-
-	/*
-	 * XXX: batch / limit 'nr', to avoid large irq off latency
-	 * needs some instrumenting to determine the common sizes used by
-	 * important workloads (eg. DB2), and whether limiting the batch size
-	 * will decrease performance.
-	 *
-	 * It seems like we're in the clear for the moment. Direct-IO is
-	 * the main guy that batches up lots of get_user_pages, and even
-	 * they are limited to 64-at-a-time which is not so many.
-	 */
-	/*
-	 * This doesn't prevent pagetable teardown, but does prevent
-	 * the pagetables from being freed on powerpc.
-	 *
-	 * So long as we atomically load page table pointers versus teardown,
-	 * we can follow the address down to the the page and take a ref on it.
-	 */
-	local_irq_save(flags);
-
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd_t pgd = ACCESS_ONCE(*pgdp);
-
-		pr_devel("  %016lx: normal pgd %p\n", addr,
-			 (void *)pgd_val(pgd));
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (pgd_huge(pgd)) {
-			if (!gup_hugepte((pte_t *)pgdp, PGDIR_SIZE, addr, next,
-					 write, pages, &nr))
-				break;
-		} else if (is_hugepd(pgdp)) {
-			if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT,
-					addr, next, write, pages, &nr))
-				break;
-		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-
-	local_irq_restore(flags);
-
-	return nr;
-}
-
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	int nr, ret;
-
-	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	ret = nr;
-
-	if (nr < nr_pages) {
-		pr_devel("  slow path ! nr = %d\n", nr);
-
-		/* Try to get the remaining pages with get_user_pages */
-		start += nr << PAGE_SHIFT;
-		pages += nr;
-
-		down_read(&mm->mmap_sem);
-		ret = get_user_pages(current, mm, start,
-				     nr_pages - nr, write, 0, pages, NULL);
-		up_read(&mm->mmap_sem);
-
-		/* Have to be a bit careful with return values */
-		if (nr > 0) {
-			if (ret < 0)
-				ret = nr;
-			else
-				ret += nr;
-		}
-	}
-
-	return ret;
-}
-
-#endif /* __HAVE_ARCH_PTE_SPECIAL */
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7e70ae968e5f..b8d228ca50fd 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -230,7 +230,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
 		return NULL;
 
-	return hugepte_offset(hpdp, addr, pdshift);
+	return hugepte_offset(*hpdp, addr, pdshift);
 }
 
 #else
@@ -270,7 +270,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
 		return NULL;
 
-	return hugepte_offset(hpdp, addr, pdshift);
+	return hugepte_offset(*hpdp, addr, pdshift);
 }
 #endif
 
@@ -538,7 +538,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	do {
 		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
-		if (!is_hugepd(pmd)) {
+		if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
 			/*
 			 * if it is not hugepd pointer, we should already find
 			 * it cleared.
@@ -587,7 +587,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	do {
 		pud = pud_offset(pgd, addr);
 		next = pud_addr_end(addr, end);
-		if (!is_hugepd(pud)) {
+		if (!is_hugepd(__hugepd(pud_val(*pud)))) {
 			if (pud_none_or_clear_bad(pud))
 				continue;
 			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
@@ -653,7 +653,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	do {
 		next = pgd_addr_end(addr, end);
 		pgd = pgd_offset(tlb->mm, addr);
-		if (!is_hugepd(pgd)) {
+		if (!is_hugepd(__hugepd(pgd_val(*pgd)))) {
 			if (pgd_none_or_clear_bad(pgd))
 				continue;
 			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
@@ -713,18 +713,17 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 	return (__boundary - 1 < end - 1) ? __boundary : end;
 }
 
-int gup_hugepd(hugepd_t *hugepd, unsigned pdshift,
-	       unsigned long addr, unsigned long end,
-	       int write, struct page **pages, int *nr)
+int gup_hugepd(hugepd_t hugepd, unsigned long addr, unsigned pdshift,
+	       unsigned long end, int write, struct page **pages, int *nr)
 {
 	pte_t *ptep;
-	unsigned long sz = 1UL << hugepd_shift(*hugepd);
+	unsigned long sz = 1UL << hugepd_shift(hugepd);
 	unsigned long next;
 
 	ptep = hugepte_offset(hugepd, addr, pdshift);
 	do {
 		next = hugepte_addr_end(addr, end, sz);
-		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
+		if (!gup_huge_pte(*ptep, ptep, addr, sz, end, write, pages, nr))
 			return 0;
 	} while (ptep++, addr = next, addr != end);
 
@@ -961,7 +960,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 	else if (pgd_huge(pgd)) {
 		ret_pte = (pte_t *) pgdp;
 		goto out;
-	} else if (is_hugepd(&pgd))
+	} else if (is_hugepd(__hugepd(pgd_val(pgd))))
 		hpdp = (hugepd_t *)&pgd;
 	else {
 		/*
@@ -978,7 +977,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 		else if (pud_huge(pud)) {
 			ret_pte = (pte_t *) pudp;
 			goto out;
-		} else if (is_hugepd(&pud))
+		} else if (is_hugepd(__hugepd(pud_val(pud))))
 			hpdp = (hugepd_t *)&pud;
 		else {
 			pdshift = PMD_SHIFT;
@@ -999,7 +998,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 			if (pmd_huge(pmd) || pmd_large(pmd)) {
 				ret_pte = (pte_t *) pmdp;
 				goto out;
-			} else if (is_hugepd(&pmd))
+			} else if (is_hugepd(__hugepd(pmd_val(pmd))))
 				hpdp = (hugepd_t *)&pmd;
 			else
 				return pte_offset_kernel(&pmd, ea);
@@ -1008,7 +1007,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
 	if (!hpdp)
 		return NULL;
 
-	ret_pte = hugepte_offset(hpdp, ea, pdshift);
+	ret_pte = hugepte_offset(*hpdp, ea, pdshift);
 	pdshift = hugepd_shift(*hpdp);
 out:
 	if (shift)
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 87ba7cf99cd7..51effcec30d8 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -301,7 +301,7 @@ static int spufs_context_open(struct path *path)
 	int ret;
 	struct file *filp;
 
-	ret = get_unused_fd();
+	ret = get_unused_fd_flags(0);
 	if (ret < 0)
 		return ret;
 
@@ -518,7 +518,7 @@ static int spufs_gang_open(struct path *path)
 	int ret;
 	struct file *filp;
 
-	ret = get_unused_fd();
+	ret = get_unused_fd_flags(0);
 	if (ret < 0)
 		return ret;
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f2cf1f90295b..68b68d755fdf 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -65,6 +65,7 @@ config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK
 	select ARCH_INLINE_READ_LOCK_BH
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 244fb4c81e25..6db486ad7ca5 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -16,6 +16,7 @@ config SUPERH
 	select HAVE_DEBUG_BUGVERBOSE
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_KERNEL_GZIP
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 77c0ae35551a..6115af9e2ffa 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,6 +24,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAS_FAST_MULTIPLIER
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_AOUT if X86_32
diff --git a/block/bio.c b/block/bio.c
index 3e6e1986a5b2..96db147444a8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -748,6 +748,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 				}
 			}
 
+			bio->bi_iter.bi_size += len;
 			goto done;
 		}
 
@@ -764,29 +765,32 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		return 0;
 
 	/*
-	 * we might lose a segment or two here, but rather that than
-	 * make this too complex.
+	 * setup the new entry, we might clear it again later if we
+	 * cannot add the page
+	 */
+	bvec = &bio->bi_io_vec[bio->bi_vcnt];
+	bvec->bv_page = page;
+	bvec->bv_len = len;
+	bvec->bv_offset = offset;
+	bio->bi_vcnt++;
+	bio->bi_phys_segments++;
+	bio->bi_iter.bi_size += len;
+
+	/*
+	 * Perform a recount if the number of segments is greater
+	 * than queue_max_segments(q).
 	 */
 
-	while (bio->bi_phys_segments >= queue_max_segments(q)) {
+	while (bio->bi_phys_segments > queue_max_segments(q)) {
 
 		if (retried_segments)
-			return 0;
+			goto failed;
 
 		retried_segments = 1;
 		blk_recount_segments(q, bio);
 	}
 
 	/*
-	 * setup the new entry, we might clear it again later if we
-	 * cannot add the page
-	 */
-	bvec = &bio->bi_io_vec[bio->bi_vcnt];
-	bvec->bv_page = page;
-	bvec->bv_len = len;
-	bvec->bv_offset = offset;
-
-	/*
 	 * if queue has other restrictions (eg varying max sector size
 	 * depending on offset), it can specify a merge_bvec_fn in the
 	 * queue to get further control
@@ -795,7 +799,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		struct bvec_merge_data bvm = {
 			.bi_bdev = bio->bi_bdev,
 			.bi_sector = bio->bi_iter.bi_sector,
-			.bi_size = bio->bi_iter.bi_size,
+			.bi_size = bio->bi_iter.bi_size - len,
 			.bi_rw = bio->bi_rw,
 		};
 
@@ -803,23 +807,25 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		 * merge_bvec_fn() returns number of bytes it can accept
 		 * at this offset
 		 */
-		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
-			bvec->bv_page = NULL;
-			bvec->bv_len = 0;
-			bvec->bv_offset = 0;
-			return 0;
-		}
+		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len)
+			goto failed;
 	}
 
 	/* If we may be able to merge these biovecs, force a recount */
-	if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
+	if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
 		bio->bi_flags &= ~(1 << BIO_SEG_VALID);
 
-	bio->bi_vcnt++;
-	bio->bi_phys_segments++;
  done:
-	bio->bi_iter.bi_size += len;
 	return len;
+
+ failed:
+	bvec->bv_page = NULL;
+	bvec->bv_len = 0;
+	bvec->bv_offset = 0;
+	bio->bi_vcnt--;
+	bio->bi_iter.bi_size -= len;
+	blk_recount_segments(q, bio);
+	return 0;
 }
 
 /**
diff --git a/block/genhd.c b/block/genhd.c
index bd3060684ab2..8542ceb6044b 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/base/Kconfig b/drivers/base/Kconfig
index 61a33f4ba608..487e20ab430c 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -264,18 +264,24 @@ comment "Default contiguous memory area size:"
 config CMA_SIZE_MBYTES
 	int "Size in Mega Bytes"
 	depends on !CMA_SIZE_SEL_PERCENTAGE
+	default 0 if X86
 	default 16
 	help
 	  Defines the size (in MiB) of the default memory area for Contiguous
-	  Memory Allocator.
+	  Memory Allocator.  If the size of 0 is selected, CMA is disabled by
+	  default, but it can be enabled by passing cma=size[MG] to the kernel.
+
 
 config CMA_SIZE_PERCENTAGE
 	int "Percentage of total memory"
 	depends on !CMA_SIZE_SEL_MBYTES
+	default 0 if X86
 	default 10
 	help
 	  Defines the size of the default memory area for Contiguous Memory
 	  Allocator as a percentage of the total memory in the system.
+	  If 0 percent is selected, CMA is disabled by default, but it can be
+	  enabled by passing cma=size[MG] to the kernel.
 
 choice
 	prompt "Selected region size"
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 473ff4892401..950fff9ce453 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -223,9 +223,10 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 #undef pr_fmt
 #define pr_fmt(fmt) fmt
 
-static void rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
+static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
 	dev_set_cma_area(dev, rmem->priv);
+	return 0;
 }
 
 static void rmem_cma_device_release(struct reserved_mem *rmem,
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index a11ff74a5127..9eac8de9e8b7 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -178,6 +178,15 @@ comment "Input Device Drivers"
 
 source "drivers/input/keyboard/Kconfig"
 
+config INPUT_LEDS
+	bool "LED Support"
+	depends on LEDS_CLASS = INPUT || LEDS_CLASS = y
+	select LEDS_TRIGGERS
+	default y
+	help
+	  This option enables support for LEDs on keyboards managed
+	  by the input layer.
+
 source "drivers/input/mouse/Kconfig"
 
 source "drivers/input/joystick/Kconfig"
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 5ca3f631497f..2ab5f3336da5 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -6,6 +6,9 @@
 
 obj-$(CONFIG_INPUT)		+= input-core.o
 input-core-y := input.o input-compat.o input-mt.o ff-core.o
+ifeq ($(CONFIG_INPUT_LEDS),y)
+input-core-y += leds.o
+endif
 
 obj-$(CONFIG_INPUT_FF_MEMLESS)	+= ff-memless.o
 obj-$(CONFIG_INPUT_POLLDEV)	+= input-polldev.o
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 0f175f55782b..0ffaa8764652 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -711,6 +711,9 @@ static void input_disconnect_device(struct input_dev *dev)
 		handle->open = 0;
 
 	spin_unlock_irq(&dev->event_lock);
+
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_disconnect(dev);
 }
 
 /**
@@ -2137,6 +2140,9 @@ int input_register_device(struct input_dev *dev)
 
 	list_add_tail(&dev->node, &input_dev_list);
 
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_connect(dev);
+
 	list_for_each_entry(handler, &input_handler_list, node)
 		input_attach_handler(dev, handler);
 
diff --git a/drivers/input/leds.c b/drivers/input/leds.c
new file mode 100644
index 000000000000..dca4a506c660
--- /dev/null
+++ b/drivers/input/leds.c
@@ -0,0 +1,276 @@
+/*
+ * LED support for the input layer
+ *
+ * Copyright 2010-2014 Samuel Thibault <samuel.thibault@ens-lyon.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/input.h>
+
+/*
+ * Keyboard LEDs are propagated by default like the following example:
+ *
+ * VT keyboard numlock trigger
+ * -> vt::numl VT LED
+ * -> vt-numl VT trigger
+ * -> per-device inputX::numl LED
+ *
+ * Userland can however choose the trigger for the vt::numl LED, or
+ * independently choose the trigger for any inputx::numl LED.
+ *
+ *
+ * VT LED classes and triggers are registered on-demand according to
+ * existing LED devices
+ */
+
+/* Handler for VT LEDs, just triggers the corresponding VT trigger. */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness);
+static struct led_classdev vt_leds[LED_CNT] = {
+#define DEFINE_INPUT_LED(vt_led, nam, deftrig) \
+	[vt_led] = { \
+		.name = "vt::"nam, \
+		.max_brightness = 1, \
+		.brightness_set = vt_led_set, \
+		.default_trigger = deftrig, \
+	}
+/* Default triggers for the VT LEDs just correspond to the legacy
+ * usage. */
+	DEFINE_INPUT_LED(LED_NUML, "numl", "kbd-numlock"),
+	DEFINE_INPUT_LED(LED_CAPSL, "capsl", "kbd-capslock"),
+	DEFINE_INPUT_LED(LED_SCROLLL, "scrolll", "kbd-scrollock"),
+	DEFINE_INPUT_LED(LED_COMPOSE, "compose", NULL),
+	DEFINE_INPUT_LED(LED_KANA, "kana", "kbd-kanalock"),
+	DEFINE_INPUT_LED(LED_SLEEP, "sleep", NULL),
+	DEFINE_INPUT_LED(LED_SUSPEND, "suspend", NULL),
+	DEFINE_INPUT_LED(LED_MUTE, "mute", NULL),
+	DEFINE_INPUT_LED(LED_MISC, "misc", NULL),
+	DEFINE_INPUT_LED(LED_MAIL, "mail", NULL),
+	DEFINE_INPUT_LED(LED_CHARGING, "charging", NULL),
+};
+static const char *const vt_led_names[LED_CNT] = {
+	[LED_NUML] = "numl",
+	[LED_CAPSL] = "capsl",
+	[LED_SCROLLL] = "scrolll",
+	[LED_COMPOSE] = "compose",
+	[LED_KANA] = "kana",
+	[LED_SLEEP] = "sleep",
+	[LED_SUSPEND] = "suspend",
+	[LED_MUTE] = "mute",
+	[LED_MISC] = "misc",
+	[LED_MAIL] = "mail",
+	[LED_CHARGING] = "charging",
+};
+/* Handler for hotplug initialization */
+static void vt_led_trigger_activate(struct led_classdev *cdev);
+/* VT triggers */
+static struct led_trigger vt_led_triggers[LED_CNT] = {
+#define DEFINE_INPUT_LED_TRIGGER(vt_led, nam) \
+	[vt_led] = { \
+		.name = "vt-"nam, \
+		.activate = vt_led_trigger_activate, \
+	}
+	DEFINE_INPUT_LED_TRIGGER(LED_NUML, "numl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CAPSL, "capsl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SCROLLL, "scrolll"),
+	DEFINE_INPUT_LED_TRIGGER(LED_COMPOSE, "compose"),
+	DEFINE_INPUT_LED_TRIGGER(LED_KANA, "kana"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SLEEP, "sleep"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SUSPEND, "suspend"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MUTE, "mute"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MISC, "misc"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MAIL, "mail"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CHARGING, "charging"),
+};
+
+/* Lock for registration coherency */
+static DEFINE_MUTEX(vt_led_registered_lock);
+
+/* Which VT LED classes and triggers are registered */
+static unsigned long vt_led_registered[BITS_TO_LONGS(LED_CNT)];
+
+/* Number of input devices having each LED */
+static int vt_led_references[LED_CNT];
+
+static int vt_led_state[LED_CNT];
+static struct work_struct vt_led_work[LED_CNT];
+
+static void vt_led_cb(struct work_struct *work)
+{
+	int led = work - vt_led_work;
+
+	led_trigger_event(&vt_led_triggers[led], vt_led_state[led]);
+}
+
+/* VT LED state change, tell the VT trigger.  */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	int led = cdev - vt_leds;
+
+	vt_led_state[led] = !!brightness;
+	schedule_work(&vt_led_work[led]);
+}
+
+/* LED state change for some keyboard, notify that keyboard.  */
+static void perdevice_input_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	struct input_dev *dev;
+	struct led_classdev *leds;
+	int led;
+
+	dev = cdev->dev->platform_data;
+	if (!dev)
+		/* Still initializing */
+		return;
+	leds = dev->leds;
+	led = cdev - leds;
+
+	input_event(dev, EV_LED, led, !!brightness);
+	input_event(dev, EV_SYN, SYN_REPORT, 0);
+}
+
+/* Keyboard hotplug, initialize its LED status */
+static void vt_led_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - vt_led_triggers;
+
+	if (cdev->brightness_set)
+		cdev->brightness_set(cdev, vt_leds[led].brightness);
+}
+
+/* Free led stuff from input device, used at abortion and disconnection.  */
+static void input_led_delete(struct input_dev *dev)
+{
+	if (dev) {
+		struct led_classdev *leds = dev->leds;
+		if (leds) {
+			int i;
+			for (i = 0; i < LED_CNT; i++)
+				kfree(leds[i].name);
+			kfree(leds);
+			dev->leds = NULL;
+		}
+	}
+}
+
+/* A new input device with potential LEDs to connect.  */
+int input_led_connect(struct input_dev *dev)
+{
+	int i, error = 0;
+	struct led_classdev *leds;
+
+	dev->leds = leds = kcalloc(LED_CNT, sizeof(*leds), GFP_KERNEL);
+	if (!dev->leds)
+		return -ENOMEM;
+
+	/* lazily register missing VT LEDs */
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			if (!vt_led_references[i]) {
+				led_trigger_register(&vt_led_triggers[i]);
+				/* This keyboard is first to have led i,
+				 * try to register it */
+				if (!led_classdev_register(NULL, &vt_leds[i]))
+					vt_led_references[i] = 1;
+				else
+					led_trigger_unregister(&vt_led_triggers[i]);
+			} else
+				vt_led_references[i]++;
+		}
+	mutex_unlock(&vt_led_registered_lock);
+
+	/* and register this device's LEDs */
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			leds[i].name = kasprintf(GFP_KERNEL, "%s::%s",
+						dev_name(&dev->dev),
+						vt_led_names[i]);
+			if (!leds[i].name) {
+				error = -ENOMEM;
+				goto err;
+			}
+			leds[i].max_brightness = 1;
+			leds[i].brightness_set = perdevice_input_led_set;
+			leds[i].default_trigger = vt_led_triggers[i].name;
+		}
+
+	/* No issue so far, we can register for real.  */
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name) {
+			led_classdev_register(&dev->dev, &leds[i]);
+			leds[i].dev->platform_data = dev;
+			perdevice_input_led_set(&leds[i],
+					vt_leds[i].brightness);
+		}
+
+	return 0;
+
+err:
+	input_led_delete(dev);
+	return error;
+}
+
+/*
+ * Disconnected input device. Clean it, and deregister now-useless VT LEDs
+ * and triggers.
+ */
+void input_led_disconnect(struct input_dev *dev)
+{
+	int i;
+	struct led_classdev *leds = dev->leds;
+
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name)
+			led_classdev_unregister(&leds[i]);
+
+	input_led_delete(dev);
+
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++) {
+		if (!vt_leds[i].name || !test_bit(i, dev->ledbit))
+			continue;
+
+		vt_led_references[i]--;
+		if (vt_led_references[i]) {
+			/* Still some devices needing it */
+			continue;
+		}
+
+		led_classdev_unregister(&vt_leds[i]);
+		led_trigger_unregister(&vt_led_triggers[i]);
+		clear_bit(i, vt_led_registered);
+	}
+	mutex_unlock(&vt_led_registered_lock);
+}
+
+static int __init input_led_init(void)
+{
+	unsigned i;
+
+	for (i = 0; i < LED_CNT; i++)
+		INIT_WORK(&vt_led_work[i], vt_led_cb);
+
+	return 0;
+}
+
+static void __exit input_led_exit(void)
+{
+}
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("User LED support for input layer");
+MODULE_AUTHOR("Samuel Thibault <samuel.thibault@ens-lyon.org>");
+module_init(input_led_init);
+module_exit(input_led_exit);
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index a210338cfeb1..808095b452ab 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -11,9 +11,6 @@ menuconfig NEW_LEDS
 	  Say Y to enable Linux LED support.  This allows control of supported
 	  LEDs from both userspace and optionally, by kernel events (triggers).
 
-	  This is not related to standard keyboard LEDs which are controlled
-	  via the input system.
-
 if NEW_LEDS
 
 config LEDS_CLASS
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 54be83d3efdd..374480cb69bf 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -343,7 +343,7 @@ void st_int_recv(void *disc_data,
 			/* Unknow packet? */
 		default:
 			type = *ptr;
-			if (st_gdata->list[type] == NULL) {
+			if (type >= ST_MAX_CHANNELS || st_gdata->list[type] == NULL) {
 				pr_err("chip/interface misbehavior dropping"
 					" frame starting with 0x%02x", type);
 				goto done;
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 59fb12e84e6b..dc566b38645f 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -243,23 +243,27 @@ static inline struct reserved_mem *__find_rmem(struct device_node *node)
  * This function assign memory region pointed by "memory-region" device tree
  * property to the given device.
  */
-void of_reserved_mem_device_init(struct device *dev)
+int of_reserved_mem_device_init(struct device *dev)
 {
 	struct reserved_mem *rmem;
 	struct device_node *np;
+	int ret;
 
 	np = of_parse_phandle(dev->of_node, "memory-region", 0);
 	if (!np)
-		return;
+		return -ENODEV;
 
 	rmem = __find_rmem(np);
 	of_node_put(np);
 
 	if (!rmem || !rmem->ops || !rmem->ops->device_init)
-		return;
+		return -EINVAL;
+
+	ret = rmem->ops->device_init(rmem, dev);
+	if (ret == 0)
+		dev_info(dev, "assigned reserved memory node %s\n", rmem->name);
 
-	rmem->ops->device_init(rmem, dev);
-	dev_info(dev, "assigned reserved memory node %s\n", rmem->name);
+	return ret;
 }
 
 /**
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 94ae1798d48a..6dd12ddbabc6 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1320,7 +1320,7 @@ config RTC_DRV_LPC32XX
 
 config RTC_DRV_PM8XXX
 	tristate "Qualcomm PMIC8XXX RTC"
-	depends on MFD_PM8XXX
+	depends on MFD_PM8XXX || MFD_SPMI_PMIC
 	help
 	  If you say yes here you get support for the
 	  Qualcomm PMIC8XXX RTC.
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 5b2717f5dafa..818ea97f403c 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -30,6 +30,14 @@ static int __rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm)
 	else {
 		memset(tm, 0, sizeof(struct rtc_time));
 		err = rtc->ops->read_time(rtc->dev.parent, tm);
+		if (err < 0) {
+			dev_err(&rtc->dev, "read_time: fail to read\n");
+			return err;
+		}
+
+		err = rtc_valid_tm(tm);
+		if (err < 0)
+			dev_err(&rtc->dev, "read_time: rtc_time isn't valid\n");
 	}
 	return err;
 }
diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c
index 197699f358c7..af8881772217 100644
--- a/drivers/rtc/rtc-pm8xxx.c
+++ b/drivers/rtc/rtc-pm8xxx.c
@@ -27,21 +27,36 @@
 
 /* RTC_CTRL register bit fields */
 #define PM8xxx_RTC_ENABLE		BIT(7)
-#define PM8xxx_RTC_ALARM_ENABLE		BIT(1)
 #define PM8xxx_RTC_ALARM_CLEAR		BIT(0)
 
 #define NUM_8_BIT_RTC_REGS		0x4
 
 /**
+ * struct pm8xxx_rtc_regs - describe RTC registers per PMIC versions
+ * @ctrl: base address of control register
+ * @write: base address of write register
+ * @read: base address of read register
+ * @alarm_ctrl: base address of alarm control register
+ * @alarm_ctrl2: base address of alarm control2 register
+ * @alarm_rw: base address of alarm read-write register
+ * @alarm_en: alarm enable mask
+ */
+struct pm8xxx_rtc_regs {
+	unsigned int ctrl;
+	unsigned int write;
+	unsigned int read;
+	unsigned int alarm_ctrl;
+	unsigned int alarm_ctrl2;
+	unsigned int alarm_rw;
+	unsigned int alarm_en;
+};
+
+/**
  * struct pm8xxx_rtc -  rtc driver internal structure
  * @rtc:		rtc device for this driver.
  * @regmap:		regmap used to access RTC registers
  * @allow_set_time:	indicates whether writing to the RTC is allowed
  * @rtc_alarm_irq:	rtc alarm irq number.
- * @rtc_base:		address of rtc control register.
- * @rtc_read_base:	base address of read registers.
- * @rtc_write_base:	base address of write registers.
- * @alarm_rw_base:	base address of alarm registers.
  * @ctrl_reg:		rtc control register.
  * @rtc_dev:		device structure.
  * @ctrl_reg_lock:	spinlock protecting access to ctrl_reg.
@@ -51,11 +66,7 @@ struct pm8xxx_rtc {
 	struct regmap *regmap;
 	bool allow_set_time;
 	int rtc_alarm_irq;
-	int rtc_base;
-	int rtc_read_base;
-	int rtc_write_base;
-	int alarm_rw_base;
-	u8 ctrl_reg;
+	const struct pm8xxx_rtc_regs *regs;
 	struct device *rtc_dev;
 	spinlock_t ctrl_reg_lock;
 };
@@ -71,8 +82,10 @@ static int pm8xxx_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	int rc, i;
 	unsigned long secs, irq_flags;
-	u8 value[NUM_8_BIT_RTC_REGS], alarm_enabled = 0, ctrl_reg;
+	u8 value[NUM_8_BIT_RTC_REGS], alarm_enabled = 0;
+	unsigned int ctrl_reg;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
+	const struct pm8xxx_rtc_regs *regs = rtc_dd->regs;
 
 	if (!rtc_dd->allow_set_time)
 		return -EACCES;
@@ -87,30 +100,32 @@ static int pm8xxx_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	dev_dbg(dev, "Seconds value to be written to RTC = %lu\n", secs);
 
 	spin_lock_irqsave(&rtc_dd->ctrl_reg_lock, irq_flags);
-	ctrl_reg = rtc_dd->ctrl_reg;
 
-	if (ctrl_reg & PM8xxx_RTC_ALARM_ENABLE) {
+	rc = regmap_read(rtc_dd->regmap, regs->ctrl, &ctrl_reg);
+	if (rc)
+		goto rtc_rw_fail;
+
+	if (ctrl_reg & regs->alarm_en) {
 		alarm_enabled = 1;
-		ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
-		rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+		ctrl_reg &= ~regs->alarm_en;
+		rc = regmap_write(rtc_dd->regmap, regs->ctrl, ctrl_reg);
 		if (rc) {
 			dev_err(dev, "Write to RTC control register failed\n");
 			goto rtc_rw_fail;
 		}
-		rtc_dd->ctrl_reg = ctrl_reg;
 	} else {
 		spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
 	}
 
 	/* Write 0 to Byte[0] */
-	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_write_base, 0);
+	rc = regmap_write(rtc_dd->regmap, regs->write, 0);
 	if (rc) {
 		dev_err(dev, "Write to RTC write data register failed\n");
 		goto rtc_rw_fail;
 	}
 
 	/* Write Byte[1], Byte[2], Byte[3] */
-	rc = regmap_bulk_write(rtc_dd->regmap, rtc_dd->rtc_write_base + 1,
+	rc = regmap_bulk_write(rtc_dd->regmap, regs->write + 1,
 			       &value[1], sizeof(value) - 1);
 	if (rc) {
 		dev_err(dev, "Write to RTC write data register failed\n");
@@ -118,20 +133,19 @@ static int pm8xxx_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	}
 
 	/* Write Byte[0] */
-	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_write_base, value[0]);
+	rc = regmap_write(rtc_dd->regmap, regs->write, value[0]);
 	if (rc) {
 		dev_err(dev, "Write to RTC write data register failed\n");
 		goto rtc_rw_fail;
 	}
 
 	if (alarm_enabled) {
-		ctrl_reg |= PM8xxx_RTC_ALARM_ENABLE;
-		rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+		ctrl_reg |= regs->alarm_en;
+		rc = regmap_write(rtc_dd->regmap, regs->ctrl, ctrl_reg);
 		if (rc) {
 			dev_err(dev, "Write to RTC control register failed\n");
 			goto rtc_rw_fail;
 		}
-		rtc_dd->ctrl_reg = ctrl_reg;
 	}
 
 rtc_rw_fail:
@@ -148,9 +162,9 @@ static int pm8xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	unsigned long secs;
 	unsigned int reg;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
+	const struct pm8xxx_rtc_regs *regs = rtc_dd->regs;
 
-	rc = regmap_bulk_read(rtc_dd->regmap, rtc_dd->rtc_read_base,
-			      value, sizeof(value));
+	rc = regmap_bulk_read(rtc_dd->regmap, regs->read, value, sizeof(value));
 	if (rc) {
 		dev_err(dev, "RTC read data register failed\n");
 		return rc;
@@ -160,14 +174,14 @@ static int pm8xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	 * Read the LSB again and check if there has been a carry over.
 	 * If there is, redo the read operation.
 	 */
-	rc = regmap_read(rtc_dd->regmap, rtc_dd->rtc_read_base, &reg);
+	rc = regmap_read(rtc_dd->regmap, regs->read, &reg);
 	if (rc < 0) {
 		dev_err(dev, "RTC read data register failed\n");
 		return rc;
 	}
 
 	if (unlikely(reg < value[0])) {
-		rc = regmap_bulk_read(rtc_dd->regmap, rtc_dd->rtc_read_base,
+		rc = regmap_bulk_read(rtc_dd->regmap, regs->read,
 				      value, sizeof(value));
 		if (rc) {
 			dev_err(dev, "RTC read data register failed\n");
@@ -195,9 +209,11 @@ static int pm8xxx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 static int pm8xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
 	int rc, i;
-	u8 value[NUM_8_BIT_RTC_REGS], ctrl_reg;
+	u8 value[NUM_8_BIT_RTC_REGS];
+	unsigned int ctrl_reg;
 	unsigned long secs, irq_flags;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
+	const struct pm8xxx_rtc_regs *regs = rtc_dd->regs;
 
 	rtc_tm_to_time(&alarm->time, &secs);
 
@@ -208,28 +224,28 @@ static int pm8xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 
 	spin_lock_irqsave(&rtc_dd->ctrl_reg_lock, irq_flags);
 
-	rc = regmap_bulk_write(rtc_dd->regmap, rtc_dd->alarm_rw_base, value,
+	rc = regmap_bulk_write(rtc_dd->regmap, regs->alarm_rw, value,
 			       sizeof(value));
 	if (rc) {
 		dev_err(dev, "Write to RTC ALARM register failed\n");
 		goto rtc_rw_fail;
 	}
 
-	ctrl_reg = rtc_dd->ctrl_reg;
+	rc = regmap_read(rtc_dd->regmap, regs->alarm_ctrl, &ctrl_reg);
+	if (rc)
+		goto rtc_rw_fail;
 
 	if (alarm->enabled)
-		ctrl_reg |= PM8xxx_RTC_ALARM_ENABLE;
+		ctrl_reg |= regs->alarm_en;
 	else
-		ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
+		ctrl_reg &= ~regs->alarm_en;
 
-	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+	rc = regmap_write(rtc_dd->regmap, regs->alarm_ctrl, ctrl_reg);
 	if (rc) {
-		dev_err(dev, "Write to RTC control register failed\n");
+		dev_err(dev, "Write to RTC alarm control register failed\n");
 		goto rtc_rw_fail;
 	}
 
-	rtc_dd->ctrl_reg = ctrl_reg;
-
 	dev_dbg(dev, "Alarm Set for h:r:s=%d:%d:%d, d/m/y=%d/%d/%d\n",
 		alarm->time.tm_hour, alarm->time.tm_min,
 		alarm->time.tm_sec, alarm->time.tm_mday,
@@ -245,8 +261,9 @@ static int pm8xxx_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 	u8 value[NUM_8_BIT_RTC_REGS];
 	unsigned long secs;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
+	const struct pm8xxx_rtc_regs *regs = rtc_dd->regs;
 
-	rc = regmap_bulk_read(rtc_dd->regmap, rtc_dd->alarm_rw_base, value,
+	rc = regmap_bulk_read(rtc_dd->regmap, regs->alarm_rw, value,
 			      sizeof(value));
 	if (rc) {
 		dev_err(dev, "RTC alarm time read failed\n");
@@ -276,25 +293,26 @@ static int pm8xxx_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 	int rc;
 	unsigned long irq_flags;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
-	u8 ctrl_reg;
+	const struct pm8xxx_rtc_regs *regs = rtc_dd->regs;
+	unsigned int ctrl_reg;
 
 	spin_lock_irqsave(&rtc_dd->ctrl_reg_lock, irq_flags);
 
-	ctrl_reg = rtc_dd->ctrl_reg;
+	rc = regmap_read(rtc_dd->regmap, regs->alarm_ctrl, &ctrl_reg);
+	if (rc)
+		goto rtc_rw_fail;
 
 	if (enable)
-		ctrl_reg |= PM8xxx_RTC_ALARM_ENABLE;
+		ctrl_reg |= regs->alarm_en;
 	else
-		ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
+		ctrl_reg &= ~regs->alarm_en;
 
-	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+	rc = regmap_write(rtc_dd->regmap, regs->alarm_ctrl, ctrl_reg);
 	if (rc) {
 		dev_err(dev, "Write to RTC control register failed\n");
 		goto rtc_rw_fail;
 	}
 
-	rtc_dd->ctrl_reg = ctrl_reg;
-
 rtc_rw_fail:
 	spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
 	return rc;
@@ -311,6 +329,7 @@ static const struct rtc_class_ops pm8xxx_rtc_ops = {
 static irqreturn_t pm8xxx_alarm_trigger(int irq, void *dev_id)
 {
 	struct pm8xxx_rtc *rtc_dd = dev_id;
+	const struct pm8xxx_rtc_regs *regs = rtc_dd->regs;
 	unsigned int ctrl_reg;
 	int rc;
 	unsigned long irq_flags;
@@ -320,48 +339,100 @@ static irqreturn_t pm8xxx_alarm_trigger(int irq, void *dev_id)
 	spin_lock_irqsave(&rtc_dd->ctrl_reg_lock, irq_flags);
 
 	/* Clear the alarm enable bit */
-	ctrl_reg = rtc_dd->ctrl_reg;
-	ctrl_reg &= ~PM8xxx_RTC_ALARM_ENABLE;
+	rc = regmap_read(rtc_dd->regmap, regs->alarm_ctrl, &ctrl_reg);
+	if (rc) {
+		spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
+		goto rtc_alarm_handled;
+	}
+
+	ctrl_reg &= ~regs->alarm_en;
 
-	rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
+	rc = regmap_write(rtc_dd->regmap, regs->alarm_ctrl, ctrl_reg);
 	if (rc) {
 		spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
 		dev_err(rtc_dd->rtc_dev,
-			"Write to RTC control register failed\n");
+			"Write to alarm control register failed\n");
 		goto rtc_alarm_handled;
 	}
 
-	rtc_dd->ctrl_reg = ctrl_reg;
 	spin_unlock_irqrestore(&rtc_dd->ctrl_reg_lock, irq_flags);
 
 	/* Clear RTC alarm register */
-	rc = regmap_read(rtc_dd->regmap,
-			 rtc_dd->rtc_base + PM8XXX_ALARM_CTRL_OFFSET,
-			 &ctrl_reg);
+	rc = regmap_read(rtc_dd->regmap, regs->alarm_ctrl2, &ctrl_reg);
 	if (rc) {
 		dev_err(rtc_dd->rtc_dev,
-			"RTC Alarm control register read failed\n");
+			"RTC Alarm control2 register read failed\n");
 		goto rtc_alarm_handled;
 	}
 
-	ctrl_reg &= ~PM8xxx_RTC_ALARM_CLEAR;
-	rc = regmap_write(rtc_dd->regmap,
-			  rtc_dd->rtc_base + PM8XXX_ALARM_CTRL_OFFSET,
-			  ctrl_reg);
+	ctrl_reg |= PM8xxx_RTC_ALARM_CLEAR;
+	rc = regmap_write(rtc_dd->regmap, regs->alarm_ctrl2, ctrl_reg);
 	if (rc)
 		dev_err(rtc_dd->rtc_dev,
-			"Write to RTC Alarm control register failed\n");
+			"Write to RTC Alarm control2 register failed\n");
 
 rtc_alarm_handled:
 	return IRQ_HANDLED;
 }
 
+static int pm8xxx_rtc_enable(struct pm8xxx_rtc *rtc_dd)
+{
+	const struct pm8xxx_rtc_regs *regs = rtc_dd->regs;
+	unsigned int ctrl_reg;
+	int rc;
+
+	/* Check if the RTC is on, else turn it on */
+	rc = regmap_read(rtc_dd->regmap, regs->ctrl, &ctrl_reg);
+	if (rc)
+		return rc;
+
+	if (!(ctrl_reg & PM8xxx_RTC_ENABLE)) {
+		ctrl_reg |= PM8xxx_RTC_ENABLE;
+		rc = regmap_write(rtc_dd->regmap, regs->ctrl, ctrl_reg);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static const struct pm8xxx_rtc_regs pm8921_regs = {
+	.ctrl		= 0x11d,
+	.write		= 0x11f,
+	.read		= 0x123,
+	.alarm_rw	= 0x127,
+	.alarm_ctrl	= 0x11d,
+	.alarm_ctrl2	= 0x11e,
+	.alarm_en	= BIT(1),
+};
+
+static const struct pm8xxx_rtc_regs pm8058_regs = {
+	.ctrl		= 0x1e8,
+	.write		= 0x1ea,
+	.read		= 0x1ee,
+	.alarm_rw	= 0x1f2,
+	.alarm_ctrl	= 0x1e8,
+	.alarm_ctrl2	= 0x1e9,
+	.alarm_en	= BIT(1),
+};
+
+static const struct pm8xxx_rtc_regs pm8941_regs = {
+	.ctrl		= 0x6046,
+	.write		= 0x6040,
+	.read		= 0x6048,
+	.alarm_rw	= 0x6140,
+	.alarm_ctrl	= 0x6146,
+	.alarm_ctrl2	= 0x6148,
+	.alarm_en	= BIT(7),
+};
+
 /*
  * Hardcoded RTC bases until IORESOURCE_REG mapping is figured out
  */
 static const struct of_device_id pm8xxx_id_table[] = {
-	{ .compatible = "qcom,pm8921-rtc", .data = (void *) 0x11D },
-	{ .compatible = "qcom,pm8058-rtc", .data = (void *) 0x1E8 },
+	{ .compatible = "qcom,pm8921-rtc", .data = &pm8921_regs },
+	{ .compatible = "qcom,pm8058-rtc", .data = &pm8058_regs },
+	{ .compatible = "qcom,pm8941-rtc", .data = &pm8941_regs },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, pm8xxx_id_table);
@@ -369,7 +440,6 @@ MODULE_DEVICE_TABLE(of, pm8xxx_id_table);
 static int pm8xxx_rtc_probe(struct platform_device *pdev)
 {
 	int rc;
-	unsigned int ctrl_reg;
 	struct pm8xxx_rtc *rtc_dd;
 	const struct of_device_id *match;
 
@@ -399,33 +469,12 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev)
 	rtc_dd->allow_set_time = of_property_read_bool(pdev->dev.of_node,
 						      "allow-set-time");
 
-	rtc_dd->rtc_base = (long) match->data;
-
-	/* Setup RTC register addresses */
-	rtc_dd->rtc_write_base = rtc_dd->rtc_base + PM8XXX_RTC_WRITE_OFFSET;
-	rtc_dd->rtc_read_base = rtc_dd->rtc_base + PM8XXX_RTC_READ_OFFSET;
-	rtc_dd->alarm_rw_base = rtc_dd->rtc_base + PM8XXX_ALARM_RW_OFFSET;
-
+	rtc_dd->regs = match->data;
 	rtc_dd->rtc_dev = &pdev->dev;
 
-	/* Check if the RTC is on, else turn it on */
-	rc = regmap_read(rtc_dd->regmap, rtc_dd->rtc_base, &ctrl_reg);
-	if (rc) {
-		dev_err(&pdev->dev, "RTC control register read failed!\n");
+	rc = pm8xxx_rtc_enable(rtc_dd);
+	if (rc)
 		return rc;
-	}
-
-	if (!(ctrl_reg & PM8xxx_RTC_ENABLE)) {
-		ctrl_reg |= PM8xxx_RTC_ENABLE;
-		rc = regmap_write(rtc_dd->regmap, rtc_dd->rtc_base, ctrl_reg);
-		if (rc) {
-			dev_err(&pdev->dev,
-				"Write to RTC control register failed\n");
-			return rc;
-		}
-	}
-
-	rtc_dd->ctrl_reg = ctrl_reg;
 
 	platform_set_drvdata(pdev, rtc_dd);
 
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index b24aa010f68c..65cd80bf9aec 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -13,6 +13,10 @@ config VT
 	bool "Virtual terminal" if EXPERT
 	depends on !S390 && !UML
 	select INPUT
+	select NEW_LEDS
+	select LEDS_CLASS
+	select LEDS_TRIGGERS
+	select INPUT_LEDS
 	default y
 	---help---
 	  If you say Y here, you will get support for terminal devices with
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index c039cfea5b11..9d00088d3ecf 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -33,6 +33,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/leds.h>
 
 #include <linux/kbd_kern.h>
 #include <linux/kbd_diacr.h>
@@ -130,6 +131,7 @@ static char rep;					/* flag telling character repeat */
 static int shift_state = 0;
 
 static unsigned char ledstate = 0xff;			/* undefined */
+static unsigned char lockstate = 0xff;			/* undefined */
 static unsigned char ledioctl;
 
 /*
@@ -961,6 +963,41 @@ static void k_brl(struct vc_data *vc, unsigned char value, char up_flag)
 	}
 }
 
+/* We route VT keyboard "leds" through triggers */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_ledstate[] = {
+#define DEFINE_LEDSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_ledstate_trigger_activate, \
+	}
+	DEFINE_LEDSTATE_TRIGGER(VC_SCROLLOCK, "kbd-scrollock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_NUMLOCK,   "kbd-numlock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_CAPSLOCK,  "kbd-capslock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_KANALOCK,  "kbd-kanalock"),
+#undef DEFINE_LEDSTATE_TRIGGER
+};
+
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_lockstate[] = {
+#define DEFINE_LOCKSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_lockstate_trigger_activate, \
+	}
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLOCK,  "kbd-shiftlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTGRLOCK,  "kbd-altgrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLOCK,   "kbd-ctrllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTLOCK,    "kbd-altlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLLOCK, "kbd-shiftllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTRLOCK, "kbd-shiftrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLLOCK,  "kbd-ctrlllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLRLOCK,  "kbd-ctrlrlock"),
+#undef DEFINE_LOCKSTATE_TRIGGER
+};
+
 /*
  * The leds display either (i) the status of NumLock, CapsLock, ScrollLock,
  * or (ii) whatever pattern of lights people want to show using KDSETLED,
@@ -995,18 +1032,25 @@ static inline unsigned char getleds(void)
 	return kb->ledflagstate;
 }
 
-static int kbd_update_leds_helper(struct input_handle *handle, void *data)
+/* Called on trigger connection, to set initial state */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev)
 {
-	unsigned char leds = *(unsigned char *)data;
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_ledstate;
 
-	if (test_bit(EV_LED, handle->dev->evbit)) {
-		input_inject_event(handle, EV_LED, LED_SCROLLL, !!(leds & 0x01));
-		input_inject_event(handle, EV_LED, LED_NUML,    !!(leds & 0x02));
-		input_inject_event(handle, EV_LED, LED_CAPSL,   !!(leds & 0x04));
-		input_inject_event(handle, EV_SYN, SYN_REPORT, 0);
-	}
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, ledstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
+}
 
-	return 0;
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_lockstate;
+
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, lockstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
 }
 
 /**
@@ -1095,16 +1139,29 @@ static void kbd_bh(unsigned long dummy)
 {
 	unsigned char leds;
 	unsigned long flags;
-	
+	int i;
+
 	spin_lock_irqsave(&led_lock, flags);
 	leds = getleds();
 	spin_unlock_irqrestore(&led_lock, flags);
 
 	if (leds != ledstate) {
-		input_handler_for_each_handle(&kbd_handler, &leds,
-					      kbd_update_leds_helper);
+		for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++)
+			if ((leds ^ ledstate) & (1 << i))
+				led_trigger_event(&ledtrig_ledstate[i],
+						leds & (1 << i)
+						? LED_FULL : LED_OFF);
 		ledstate = leds;
 	}
+
+	if (kbd->lockstate != lockstate) {
+		for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++)
+			if ((kbd->lockstate ^ lockstate) & (1 << i))
+				led_trigger_event(&ledtrig_lockstate[i],
+						kbd->lockstate & (1 << i)
+						? LED_FULL : LED_OFF);
+		lockstate = kbd->lockstate;
+	}
 }
 
 DECLARE_TASKLET_DISABLED(keyboard_tasklet, kbd_bh, 0);
@@ -1442,20 +1499,6 @@ static void kbd_disconnect(struct input_handle *handle)
 	kfree(handle);
 }
 
-/*
- * Start keyboard handler on the new keyboard by refreshing LED state to
- * match the rest of the system.
- */
-static void kbd_start(struct input_handle *handle)
-{
-	tasklet_disable(&keyboard_tasklet);
-
-	if (ledstate != 0xff)
-		kbd_update_leds_helper(handle, &ledstate);
-
-	tasklet_enable(&keyboard_tasklet);
-}
-
 static const struct input_device_id kbd_ids[] = {
 	{
 		.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
@@ -1477,7 +1520,6 @@ static struct input_handler kbd_handler = {
 	.match		= kbd_match,
 	.connect	= kbd_connect,
 	.disconnect	= kbd_disconnect,
-	.start		= kbd_start,
 	.name		= "kbd",
 	.id_table	= kbd_ids,
 };
@@ -1501,6 +1543,20 @@ int __init kbd_init(void)
 	if (error)
 		return error;
 
+	for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++) {
+		error = led_trigger_register(&ledtrig_ledstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_ledstate[i].name);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++) {
+		error = led_trigger_register(&ledtrig_lockstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_lockstate[i].name);
+	}
+
 	tasklet_enable(&keyboard_tasklet);
 	tasklet_schedule(&keyboard_tasklet);
 
diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index bea749329236..fb4e1bfce73b 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -181,8 +181,6 @@ int backlight_device_set_brightness(struct backlight_device *bd, int brightness)
 	}
 	mutex_unlock(&bd->ops_lock);
 
-	backlight_generate_event(bd, BACKLIGHT_UPDATE_SYSFS);
-
 	return rc;
 }
 EXPORT_SYMBOL(backlight_device_set_brightness);
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 9bca88159725..ff44ff3ff015 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -135,8 +135,10 @@ extern void	affs_fix_checksum(struct super_block *sb, struct buffer_head *bh);
 extern void	secs_to_datestamp(time_t secs, struct affs_date *ds);
 extern umode_t	prot_to_mode(u32 prot);
 extern void	mode_to_prot(struct inode *inode);
+__printf(3, 4)
 extern void	affs_error(struct super_block *sb, const char *function,
 			   const char *fmt, ...);
+__printf(3, 4)
 extern void	affs_warning(struct super_block *sb, const char *function,
 			     const char *fmt, ...);
 extern bool	affs_nofilenametruncate(const struct dentry *dentry);
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index abc853968fed..9643bdda99fe 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -10,8 +10,6 @@
 
 #include "affs.h"
 
-static char ErrorBuffer[256];
-
 /*
  * Functions for accessing Amiga-FFS structures.
  */
@@ -444,30 +442,30 @@ mode_to_prot(struct inode *inode)
 void
 affs_error(struct super_block *sb, const char *function, const char *fmt, ...)
 {
-	va_list	 args;
-
-	va_start(args,fmt);
-	vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
-	va_end(args);
+	struct va_format vaf;
+	va_list args;
 
-	pr_crit("error (device %s): %s(): %s\n", sb->s_id,
-		function,ErrorBuffer);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_crit("error (device %s): %s(): %pV\n", sb->s_id, function, &vaf);
 	if (!(sb->s_flags & MS_RDONLY))
 		pr_warn("Remounting filesystem read-only\n");
 	sb->s_flags |= MS_RDONLY;
+	va_end(args);
 }
 
 void
 affs_warning(struct super_block *sb, const char *function, const char *fmt, ...)
 {
-	va_list	 args;
+	struct va_format vaf;
+	va_list args;
 
-	va_start(args,fmt);
-	vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_warn("(device %s): %s(): %pV\n", sb->s_id, function, &vaf);
 	va_end(args);
-
-	pr_warn("(device %s): %s(): %s\n", sb->s_id,
-		function,ErrorBuffer);
 }
 
 bool
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 1ed590aafecf..8e510854f487 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -18,29 +18,7 @@
 #error PAGE_SIZE must be at least 4096
 #endif
 
-static int affs_grow_extcache(struct inode *inode, u32 lc_idx);
-static struct buffer_head *affs_alloc_extblock(struct inode *inode, struct buffer_head *bh, u32 ext);
-static inline struct buffer_head *affs_get_extblock(struct inode *inode, u32 ext);
 static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
-static int affs_file_open(struct inode *inode, struct file *filp);
-static int affs_file_release(struct inode *inode, struct file *filp);
-
-const struct file_operations affs_file_operations = {
-	.llseek		= generic_file_llseek,
-	.read		= new_sync_read,
-	.read_iter	= generic_file_read_iter,
-	.write		= new_sync_write,
-	.write_iter	= generic_file_write_iter,
-	.mmap		= generic_file_mmap,
-	.open		= affs_file_open,
-	.release	= affs_file_release,
-	.fsync		= affs_file_fsync,
-	.splice_read	= generic_file_splice_read,
-};
-
-const struct inode_operations affs_file_inode_operations = {
-	.setattr	= affs_notify_change,
-};
 
 static int
 affs_file_open(struct inode *inode, struct file *filp)
@@ -355,7 +333,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 
 		/* store new block */
 		if (bh_result->b_blocknr)
-			affs_warning(sb, "get_block", "block already set (%x)", bh_result->b_blocknr);
+			affs_warning(sb, "get_block", "block already set (%lx)",
+				     (unsigned long)bh_result->b_blocknr);
 		AFFS_BLOCK(sb, ext_bh, block) = cpu_to_be32(blocknr);
 		AFFS_HEAD(ext_bh)->block_count = cpu_to_be32(block + 1);
 		affs_adjust_checksum(ext_bh, blocknr - bh_result->b_blocknr + 1);
@@ -377,7 +356,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 	return 0;
 
 err_big:
-	affs_error(inode->i_sb,"get_block","strange block request %d", block);
+	affs_error(inode->i_sb, "get_block", "strange block request %d",
+		   (int)block);
 	return -EIO;
 err_ext:
 	// unlock cache
@@ -867,8 +847,9 @@ affs_truncate(struct inode *inode)
 	// lock cache
 	ext_bh = affs_get_extblock(inode, ext);
 	if (IS_ERR(ext_bh)) {
-		affs_warning(sb, "truncate", "unexpected read error for ext block %u (%d)",
-			     ext, PTR_ERR(ext_bh));
+		affs_warning(sb, "truncate",
+			     "unexpected read error for ext block %u (%ld)",
+			     (unsigned int)ext, PTR_ERR(ext_bh));
 		return;
 	}
 	if (AFFS_I(inode)->i_lc) {
@@ -914,8 +895,9 @@ affs_truncate(struct inode *inode)
 			struct buffer_head *bh = affs_bread_ino(inode, last_blk, 0);
 			u32 tmp;
 			if (IS_ERR(bh)) {
-				affs_warning(sb, "truncate", "unexpected read error for last block %u (%d)",
-					     ext, PTR_ERR(bh));
+				affs_warning(sb, "truncate",
+					     "unexpected read error for last block %u (%ld)",
+					     (unsigned int)ext, PTR_ERR(bh));
 				return;
 			}
 			tmp = be32_to_cpu(AFFS_DATA_HEAD(bh)->next);
@@ -961,3 +943,19 @@ int affs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	mutex_unlock(&inode->i_mutex);
 	return ret;
 }
+const struct file_operations affs_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
+	.mmap		= generic_file_mmap,
+	.open		= affs_file_open,
+	.release	= affs_file_release,
+	.fsync		= affs_file_fsync,
+	.splice_read	= generic_file_splice_read,
+};
+
+const struct inode_operations affs_file_inode_operations = {
+	.setattr	= affs_notify_change,
+};
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index fd8beb9657a2..1cc5377ba955 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -153,7 +153,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		/* if the binary should be opened on behalf of the
 		 * interpreter than keep it open and assign descriptor
 		 * to it */
- 		fd_binary = get_unused_fd();
+		fd_binary = get_unused_fd_flags(0);
  		if (fd_binary < 0) {
  			retval = fd_binary;
  			goto _ret;
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 6d00c419cbae..1ea780bc6376 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -38,7 +38,7 @@ static const struct cifs_sid sid_everyone = {
 	1, 1, {0, 0, 0, 0, 0, 1}, {0} };
 /* security id for Authenticated Users system group */
 static const struct cifs_sid sid_authusers = {
-	1, 1, {0, 0, 0, 0, 0, 5}, {__constant_cpu_to_le32(11)} };
+	1, 1, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(11)} };
 /* group users */
 static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
 
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 61d00a6e398f..fa13d5e79f64 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2477,14 +2477,14 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 		}
 		parm_data = (struct cifs_posix_lock *)
 			((char *)&pSMBr->hdr.Protocol + data_offset);
-		if (parm_data->lock_type == __constant_cpu_to_le16(CIFS_UNLCK))
+		if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK))
 			pLockData->fl_type = F_UNLCK;
 		else {
 			if (parm_data->lock_type ==
-					__constant_cpu_to_le16(CIFS_RDLCK))
+					cpu_to_le16(CIFS_RDLCK))
 				pLockData->fl_type = F_RDLCK;
 			else if (parm_data->lock_type ==
-					__constant_cpu_to_le16(CIFS_WRLCK))
+					cpu_to_le16(CIFS_WRLCK))
 				pLockData->fl_type = F_WRLCK;
 
 			pLockData->fl_start = le64_to_cpu(parm_data->start);
@@ -3276,25 +3276,25 @@ CIFSSMB_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->compression_state = cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
 
 	pSMB->TotalParameterCount = 0;
-	pSMB->TotalDataCount = __constant_cpu_to_le32(2);
+	pSMB->TotalDataCount = cpu_to_le32(2);
 	pSMB->MaxParameterCount = 0;
 	pSMB->MaxDataCount = 0;
 	pSMB->MaxSetupCount = 4;
 	pSMB->Reserved = 0;
 	pSMB->ParameterOffset = 0;
-	pSMB->DataCount = __constant_cpu_to_le32(2);
+	pSMB->DataCount = cpu_to_le32(2);
 	pSMB->DataOffset =
 		cpu_to_le32(offsetof(struct smb_com_transaction_compr_ioctl_req,
 				compression_state) - 4);  /* 84 */
 	pSMB->SetupCount = 4;
-	pSMB->SubCommand = __constant_cpu_to_le16(NT_TRANSACT_IOCTL);
+	pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
 	pSMB->ParameterCount = 0;
-	pSMB->FunctionCode = __constant_cpu_to_le32(FSCTL_SET_COMPRESSION);
+	pSMB->FunctionCode = cpu_to_le32(FSCTL_SET_COMPRESSION);
 	pSMB->IsFsctl = 1; /* FSCTL */
 	pSMB->IsRootFlag = 0;
 	pSMB->Fid = fid; /* file handle always le */
 	/* 3 byte pad, followed by 2 byte compress state */
-	pSMB->ByteCount = __constant_cpu_to_le16(5);
+	pSMB->ByteCount = cpu_to_le16(5);
 	inc_rfc1001_len(pSMB, 5);
 
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
@@ -3430,10 +3430,10 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL,
 	cifs_acl->version = cpu_to_le16(1);
 	if (acl_type == ACL_TYPE_ACCESS) {
 		cifs_acl->access_entry_count = cpu_to_le16(count);
-		cifs_acl->default_entry_count = __constant_cpu_to_le16(0xFFFF);
+		cifs_acl->default_entry_count = cpu_to_le16(0xFFFF);
 	} else if (acl_type == ACL_TYPE_DEFAULT) {
 		cifs_acl->default_entry_count = cpu_to_le16(count);
-		cifs_acl->access_entry_count = __constant_cpu_to_le16(0xFFFF);
+		cifs_acl->access_entry_count = cpu_to_le16(0xFFFF);
 	} else {
 		cifs_dbg(FYI, "unknown ACL type %d\n", acl_type);
 		return 0;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3e4d00a06c44..b123a64d7be4 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1066,7 +1066,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
-	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
 	if (!buf) {
 		free_xid(xid);
 		return -ENOMEM;
@@ -1401,7 +1401,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
-	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 57db63ff88da..ab0fda6e8e58 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -46,7 +46,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
 					CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4,
 					USHRT_MAX));
 	pSMB->req.MaxMpxCount = cpu_to_le16(ses->server->maxReq);
-	pSMB->req.VcNumber = __constant_cpu_to_le16(1);
+	pSMB->req.VcNumber = cpu_to_le16(1);
 
 	/* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */
 
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 45992944e238..7198eac5dddd 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -111,7 +111,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 		return -EINVAL;
 
 	max_num = max_buf / sizeof(struct smb2_lock_element);
-	buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -247,7 +247,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
 	}
 
 	max_num = max_buf / sizeof(struct smb2_lock_element);
-	buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf) {
 		free_xid(xid);
 		return -ENOMEM;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 1a08a34838fc..f1cefc9763ed 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -67,27 +67,27 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
  *  indexed by command in host byte order
  */
 static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
-	/* SMB2_NEGOTIATE */ __constant_cpu_to_le16(65),
-	/* SMB2_SESSION_SETUP */ __constant_cpu_to_le16(9),
-	/* SMB2_LOGOFF */ __constant_cpu_to_le16(4),
-	/* SMB2_TREE_CONNECT */ __constant_cpu_to_le16(16),
-	/* SMB2_TREE_DISCONNECT */ __constant_cpu_to_le16(4),
-	/* SMB2_CREATE */ __constant_cpu_to_le16(89),
-	/* SMB2_CLOSE */ __constant_cpu_to_le16(60),
-	/* SMB2_FLUSH */ __constant_cpu_to_le16(4),
-	/* SMB2_READ */ __constant_cpu_to_le16(17),
-	/* SMB2_WRITE */ __constant_cpu_to_le16(17),
-	/* SMB2_LOCK */ __constant_cpu_to_le16(4),
-	/* SMB2_IOCTL */ __constant_cpu_to_le16(49),
+	/* SMB2_NEGOTIATE */ cpu_to_le16(65),
+	/* SMB2_SESSION_SETUP */ cpu_to_le16(9),
+	/* SMB2_LOGOFF */ cpu_to_le16(4),
+	/* SMB2_TREE_CONNECT */ cpu_to_le16(16),
+	/* SMB2_TREE_DISCONNECT */ cpu_to_le16(4),
+	/* SMB2_CREATE */ cpu_to_le16(89),
+	/* SMB2_CLOSE */ cpu_to_le16(60),
+	/* SMB2_FLUSH */ cpu_to_le16(4),
+	/* SMB2_READ */ cpu_to_le16(17),
+	/* SMB2_WRITE */ cpu_to_le16(17),
+	/* SMB2_LOCK */ cpu_to_le16(4),
+	/* SMB2_IOCTL */ cpu_to_le16(49),
 	/* BB CHECK this ... not listed in documentation */
-	/* SMB2_CANCEL */ __constant_cpu_to_le16(0),
-	/* SMB2_ECHO */ __constant_cpu_to_le16(4),
-	/* SMB2_QUERY_DIRECTORY */ __constant_cpu_to_le16(9),
-	/* SMB2_CHANGE_NOTIFY */ __constant_cpu_to_le16(9),
-	/* SMB2_QUERY_INFO */ __constant_cpu_to_le16(9),
-	/* SMB2_SET_INFO */ __constant_cpu_to_le16(2),
+	/* SMB2_CANCEL */ cpu_to_le16(0),
+	/* SMB2_ECHO */ cpu_to_le16(4),
+	/* SMB2_QUERY_DIRECTORY */ cpu_to_le16(9),
+	/* SMB2_CHANGE_NOTIFY */ cpu_to_le16(9),
+	/* SMB2_QUERY_INFO */ cpu_to_le16(9),
+	/* SMB2_SET_INFO */ cpu_to_le16(2),
 	/* BB FIXME can also be 44 for lease break */
-	/* SMB2_OPLOCK_BREAK */ __constant_cpu_to_le16(24)
+	/* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
 };
 
 int
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index c5f521bcdee2..7ecac610b44b 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -600,7 +600,7 @@ smb2_clone_range(const unsigned int xid,
 		goto cchunk_out;
 
 	/* For now array only one chunk long, will make more flexible later */
-	pcchunk->ChunkCount = __constant_cpu_to_le32(1);
+	pcchunk->ChunkCount = cpu_to_le32(1);
 	pcchunk->Reserved = 0;
 	pcchunk->Reserved2 = 0;
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 8f1672bb82d5..08f73e168b0b 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1359,7 +1359,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	char *ret_data = NULL;
 
 	fsctl_input.CompressionState =
-			__constant_cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
+			cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SET_COMPRESSION, true /* is_fsctl */,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index e3188abdafd0..fbd4df1e1683 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -85,7 +85,7 @@
 /* BB FIXME - analyze following length BB */
 #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
 
-#define SMB2_PROTO_NUMBER __constant_cpu_to_le32(0x424d53fe)
+#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
 
 /*
  * SMB2 Header Definition
@@ -96,7 +96,7 @@
  *
  */
 
-#define SMB2_HEADER_STRUCTURE_SIZE __constant_cpu_to_le16(64)
+#define SMB2_HEADER_STRUCTURE_SIZE cpu_to_le16(64)
 
 struct smb2_hdr {
 	__be32 smb2_buf_length;	/* big endian on wire */
@@ -137,16 +137,16 @@ struct smb2_transform_hdr {
 } __packed;
 
 /* Encryption Algorithms */
-#define SMB2_ENCRYPTION_AES128_CCM	__constant_cpu_to_le16(0x0001)
+#define SMB2_ENCRYPTION_AES128_CCM	cpu_to_le16(0x0001)
 
 /*
  *	SMB2 flag definitions
  */
-#define SMB2_FLAGS_SERVER_TO_REDIR	__constant_cpu_to_le32(0x00000001)
-#define SMB2_FLAGS_ASYNC_COMMAND	__constant_cpu_to_le32(0x00000002)
-#define SMB2_FLAGS_RELATED_OPERATIONS	__constant_cpu_to_le32(0x00000004)
-#define SMB2_FLAGS_SIGNED		__constant_cpu_to_le32(0x00000008)
-#define SMB2_FLAGS_DFS_OPERATIONS	__constant_cpu_to_le32(0x10000000)
+#define SMB2_FLAGS_SERVER_TO_REDIR	cpu_to_le32(0x00000001)
+#define SMB2_FLAGS_ASYNC_COMMAND	cpu_to_le32(0x00000002)
+#define SMB2_FLAGS_RELATED_OPERATIONS	cpu_to_le32(0x00000004)
+#define SMB2_FLAGS_SIGNED		cpu_to_le32(0x00000008)
+#define SMB2_FLAGS_DFS_OPERATIONS	cpu_to_le32(0x10000000)
 
 /*
  *	Definitions for SMB2 Protocol Data Units (network frames)
@@ -157,7 +157,7 @@ struct smb2_transform_hdr {
  *
  */
 
-#define SMB2_ERROR_STRUCTURE_SIZE2 __constant_cpu_to_le16(9)
+#define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
 
 struct smb2_err_rsp {
 	struct smb2_hdr hdr;
@@ -502,12 +502,12 @@ struct create_context {
 #define SMB2_LEASE_HANDLE_CACHING_HE	0x02
 #define SMB2_LEASE_WRITE_CACHING_HE	0x04
 
-#define SMB2_LEASE_NONE			__constant_cpu_to_le32(0x00)
-#define SMB2_LEASE_READ_CACHING		__constant_cpu_to_le32(0x01)
-#define SMB2_LEASE_HANDLE_CACHING	__constant_cpu_to_le32(0x02)
-#define SMB2_LEASE_WRITE_CACHING	__constant_cpu_to_le32(0x04)
+#define SMB2_LEASE_NONE			cpu_to_le32(0x00)
+#define SMB2_LEASE_READ_CACHING		cpu_to_le32(0x01)
+#define SMB2_LEASE_HANDLE_CACHING	cpu_to_le32(0x02)
+#define SMB2_LEASE_WRITE_CACHING	cpu_to_le32(0x04)
 
-#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS __constant_cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS cpu_to_le32(0x02)
 
 #define SMB2_LEASE_KEY_SIZE 16
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a8bc47f75fa0..5b6e9f246233 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -107,7 +107,10 @@ 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/file.c b/fs/file.c
index ab3eb6a88239..ee738ea028fa 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -869,7 +869,7 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes)
 	struct file *file = fget_raw(fildes);
 
 	if (file) {
-		ret = get_unused_fd();
+		ret = get_unused_fd_flags(0);
 		if (ret >= 0)
 			fd_install(ret, file);
 		else
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 32602c667b4a..7892e6fddb66 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -38,21 +38,30 @@ int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 	return hfsplus_strcmp(&k1->cat.name, &k2->cat.name);
 }
 
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
-			   u32 parent, struct qstr *str)
+/* Generates key for catalog file/folders record. */
+int hfsplus_cat_build_key(struct super_block *sb,
+		hfsplus_btree_key *key, u32 parent, struct qstr *str)
 {
-	int len;
+	int len, err;
 
 	key->cat.parent = cpu_to_be32(parent);
-	if (str) {
-		hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
-					str->name, str->len);
-		len = be16_to_cpu(key->cat.name.length);
-	} else {
-		key->cat.name.length = 0;
-		len = 0;
-	}
+	err = hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
+			str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
+	len = be16_to_cpu(key->cat.name.length);
 	key->key_len = cpu_to_be16(6 + 2 * len);
+	return 0;
+}
+
+/* Generates key for catalog thread record. */
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+			hfsplus_btree_key *key, u32 parent)
+{
+	key->cat.parent = cpu_to_be32(parent);
+	key->cat.name.length = 0;
+	key->key_len = cpu_to_be16(6);
 }
 
 static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent,
@@ -167,11 +176,16 @@ static int hfsplus_fill_cat_thread(struct super_block *sb,
 				   hfsplus_cat_entry *entry, int type,
 				   u32 parentid, struct qstr *str)
 {
+	int err;
+
 	entry->type = cpu_to_be16(type);
 	entry->thread.reserved = 0;
 	entry->thread.parentID = cpu_to_be32(parentid);
-	hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
+	err = hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
 				str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
 	return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2;
 }
 
@@ -183,7 +197,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 	int err;
 	u16 type;
 
-	hfsplus_cat_build_key(sb, fd->search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd->search_key, cnid);
 	err = hfs_brec_read(fd, &tmp, sizeof(hfsplus_cat_entry));
 	if (err)
 		return err;
@@ -250,11 +264,16 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		return err;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry,
 		S_ISDIR(inode->i_mode) ?
 			HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD,
 		dir->i_ino, str);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto err2;
+	}
+
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -265,7 +284,10 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		goto err2;
 
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	if (unlikely(err))
+		goto err1;
+
 	entry_size = hfsplus_cat_build_record(&entry, cnid, inode);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
@@ -288,7 +310,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	return 0;
 
 err1:
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	if (!hfs_brec_find(&fd, hfs_find_rec_by_key))
 		hfs_brec_remove(&fd);
 err2:
@@ -313,7 +335,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (!str) {
 		int len;
 
-		hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+		hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 		err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 		if (err)
 			goto out;
@@ -329,7 +351,9 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 			off + 2, len);
 		fd.search_key->key_len = cpu_to_be16(6 + len);
 	} else
-		hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		if (unlikely(err))
+			goto out;
 
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
@@ -360,7 +384,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (err)
 		goto out;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -405,7 +429,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_fd = src_fd;
 
 	/* find the old dir entry and read the data */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -419,7 +447,11 @@ int hfsplus_rename_cat(u32 cnid,
 	type = be16_to_cpu(entry.type);
 
 	/* create new dir entry with the data from the old entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
+	err = hfsplus_cat_build_key(sb, dst_fd.search_key,
+			dst_dir->i_ino, dst_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -436,7 +468,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* finally remove the old entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -449,7 +485,7 @@ int hfsplus_rename_cat(u32 cnid,
 	src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* remove old thread entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, src_fd.search_key, cnid);
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -459,9 +495,14 @@ int hfsplus_rename_cat(u32 cnid,
 		goto out;
 
 	/* create new thread entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, dst_fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry, type,
 		dst_dir->i_ino, dst_name);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto out;
+	}
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 610a3260bef1..435bea231cc6 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -44,7 +44,10 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 	err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	if (err)
 		return ERR_PTR(err);
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino,
+			&dentry->d_name);
+	if (unlikely(err < 0))
+		goto fail;
 again:
 	err = hfs_brec_read(&fd, &entry, sizeof(entry));
 	if (err) {
@@ -97,9 +100,11 @@ again:
 					be32_to_cpu(entry.file.permissions.dev);
 				str.len = sprintf(name, "iNode%d", linkid);
 				str.name = name;
-				hfsplus_cat_build_key(sb, fd.search_key,
+				err = hfsplus_cat_build_key(sb, fd.search_key,
 					HFSPLUS_SB(sb)->hidden_dir->i_ino,
 					&str);
+				if (unlikely(err < 0))
+					goto fail;
 				goto again;
 			}
 		} else if (!dentry->d_fsdata)
@@ -145,7 +150,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
 		err = -ENOMEM;
 		goto out;
 	}
-	hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, inode->i_ino);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index eb5e059f481a..b0441d65fa54 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -443,8 +443,10 @@ int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *k1,
 			     const hfsplus_btree_key *k2);
 int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 			    const hfsplus_btree_key *k2);
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
+int hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
 			   u32 parent, struct qstr *str);
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+				     hfsplus_btree_key *key, u32 parent);
 void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
 int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 		     struct hfs_find_data *fd);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 4cf2024b87da..593af2fdcc2d 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -515,7 +515,9 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	err = hfs_find_init(sbi->cat_tree, &fd);
 	if (err)
 		goto out_put_root;
-	hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	if (unlikely(err < 0))
+		goto out_put_root;
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
 		if (entry.type != cpu_to_be16(HFSPLUS_FOLDER))
diff --git a/fs/mpage.c b/fs/mpage.c
index 3e79220babac..587c7ed4185d 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) {
@@ -614,7 +615,7 @@ alloc_new:
 	 */
 	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;
 	}
 
@@ -624,7 +625,7 @@ 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);
@@ -636,7 +637,7 @@ 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);
@@ -692,8 +693,11 @@ 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;
@@ -710,8 +714,11 @@ 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/inode_mark.c b/fs/notify/inode_mark.c
index 9ce062218de9..e8497144b323 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -288,20 +288,25 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		spin_unlock(&inode->i_lock);
 
 		/* In case the dropping of a reference would nuke next_i. */
-		if ((&next_i->i_sb_list != list) &&
-		    atomic_read(&next_i->i_count)) {
+		while (&next_i->i_sb_list != list) {
 			spin_lock(&next_i->i_lock);
-			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
+			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
+						atomic_read(&next_i->i_count)) {
 				__iget(next_i);
 				need_iput = next_i;
+				spin_unlock(&next_i->i_lock);
+				break;
 			}
 			spin_unlock(&next_i->i_lock);
+			next_i = list_entry(next_i->i_sb_list.next,
+						struct inode, i_sb_list);
 		}
 
 		/*
-		 * We can safely drop inode_sb_list_lock here because we hold
-		 * references on both inode and next_i.  Also no new inodes
-		 * will be added since the umount has begun.
+		 * We can safely drop inode_sb_list_lock here because either
+		 * we actually hold references on both inode and next_i or
+		 * end of list.  Also no new inodes will be added since the
+		 * umount has begun.
 		 */
 		spin_unlock(&inode_sb_list_lock);
 
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index a93bf9892256..fcae9ef1a328 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5662,7 +5662,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc)
+			     u64 refcount_loc, bool refcount_tree_locked)
 {
 	int ret, credits = 0, extra_blocks = 0;
 	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
@@ -5676,11 +5676,13 @@ int ocfs2_remove_btree_range(struct inode *inode,
 		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
 			 OCFS2_HAS_REFCOUNT_FL));
 
-		ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
-					       &ref_tree, NULL);
-		if (ret) {
-			mlog_errno(ret);
-			goto bail;
+		if (!refcount_tree_locked) {
+			ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+						       &ref_tree, NULL);
+			if (ret) {
+				mlog_errno(ret);
+				goto bail;
+			}
 		}
 
 		ret = ocfs2_prepare_refcount_change_for_del(inode,
@@ -7021,6 +7023,7 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
 	u64 refcount_loc = le64_to_cpu(di->i_refcount_loc);
 	struct ocfs2_extent_tree et;
 	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
 
 	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
 	ocfs2_init_dealloc_ctxt(&dealloc);
@@ -7130,9 +7133,18 @@ start:
 
 	phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
 
+	if ((flags & OCFS2_EXT_REFCOUNTED) && trunc_len && !ref_tree) {
+		status = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+				&ref_tree, NULL);
+		if (status) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					  phys_cpos, trunc_len, flags, &dealloc,
-					  refcount_loc);
+					  refcount_loc, true);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -7147,6 +7159,8 @@ start:
 	goto start;
 
 bail:
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
 
 	ocfs2_schedule_truncate_log_flush(osb, 1);
 
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index ca381c584127..fb09b97db162 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -142,7 +142,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc);
+			     u64 refcount_loc, bool refcount_tree_locked);
 
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
 			   struct ocfs2_extent_tree *et);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1ef547e49373..b63942f42373 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -28,6 +28,8 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
+#include <linux/math64.h>
 
 #include <cluster/masklog.h>
 
@@ -47,6 +49,9 @@
 #include "ocfs2_trace.h"
 
 #include "buffer_head_io.h"
+#include "dir.h"
+#include "namei.h"
+#include "sysfile.h"
 
 static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -506,18 +511,21 @@ bail:
  *
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
- *
- * Note that we never bother to allocate blocks here, and thus ignore the
- * create argument.
  */
 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;
+
+	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
@@ -539,6 +547,39 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	/* 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;
+
+		/* 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);
+		if (clusters_to_alloc > contig_blocks)
+			clusters_to_alloc = contig_blocks;
+
+		/* allocate extent and insert them into the extent tree */
+		ret = __ocfs2_extend_allocation(inode, cpos,
+				clusters_to_alloc, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
+				&contig_blocks, &ext_flags);
+		if (ret) {
+			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
+					(unsigned long long)iblock);
+			ret = -EIO;
+			goto bail;
+		}
+	}
+
 	/*
 	 * get_more_blocks() expects us to describe a hole by clearing
 	 * the mapped bit on bh_result().
@@ -555,7 +596,10 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	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;
 }
 
@@ -597,6 +641,166 @@ 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)
+{
+	ssize_t ret = 0;
+	u32 v_cpos = 0;
+	u32 p_cpos = 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	v_cpos = ocfs2_clusters_for_bytes(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 ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
+		struct iov_iter *iter,
+		loff_t offset)
+{
+	ssize_t ret = 0;
+	int orphan = 0;
+	int is_overwrite = 0;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_path.dentry->d_inode->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;
+	u32 p_cpos = 0;
+	u32 v_cpos = ocfs2_clusters_for_bytes(osb->sb, offset);
+	u32 zero_len;
+	int cluster_align;
+	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;
+
+	{
+		loff_t o = offset;
+
+		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align = !!zero_len;
+	}
+
+	/*
+	 * 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)
+			goto out;
+		orphan = 1;
+	}
+
+	if (append_write) {
+		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_extend(inode, di_bh, offset);
+		else
+			ret = ocfs2_extend_no_holes(inode, di_bh,
+					offset, offset);
+		if (ret < 0) {
+			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
+		if (is_overwrite < 0) {
+			mlog_errno(is_overwrite);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+	}
+
+	ret = blockdev_direct_IO(WRITE, iocb,
+			inode, iter, offset,
+			ocfs2_direct_IO_get_blocks);
+	if (unlikely(ret < 0)) {
+		loff_t isize = i_size_read(inode);
+
+		if (offset + count > isize) {
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto clean_orphan;
+			}
+			if (isize == i_size_read(inode)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						isize);
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+				}
+			}
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+
+			ret = jbd2_journal_force_commit(journal);
+			if (ret < 0)
+				mlog_errno(ret);
+		}
+	} else if (append_write && !is_overwrite && !cluster_align) {
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+				&num_clusters, &ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+				p_cpos << (osb->s_clustersize_bits - 9),
+				zero_len >> 9,
+				GFP_KERNEL);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+clean_orphan:
+	if (orphan) {
+		int update_isize = ret > 0 ? 1 : 0;
+		loff_t end = update_isize ? (offset + ret) : 0;
+
+		ret = ocfs2_del_inode_from_orphan(osb, inode,
+				update_isize, end);
+		if (ret < 0)
+			goto out;
+
+		ret = jbd2_journal_force_commit(journal);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+out:
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
 			       struct iov_iter *iter,
@@ -604,6 +808,9 @@ static ssize_t ocfs2_direct_IO(int rw,
 {
 	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
@@ -612,14 +819,20 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	/* Fallback to buffered I/O if we are appending. */
-	if (i_size_read(inode) <= offset)
+	/* 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;
 
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
-				    iter, offset,
-				    ocfs2_direct_IO_get_blocks,
-				    ocfs2_dio_end_io, NULL, 0);
+	if (rw == READ)
+		return __blockdev_direct_IO(rw, 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,
@@ -894,7 +1107,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 	}
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
@@ -915,7 +1128,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 		page_cache_release(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
 
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -1818,16 +2035,6 @@ try_again:
 		if (ret)
 			goto out_commit;
 	}
-	/*
-	 * We don't want this to fail in ocfs2_write_end(), so do it
-	 * here.
-	 */
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-				      OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_quota;
-	}
 
 	/*
 	 * Fill our page array first. That way we've grabbed enough so
@@ -1978,7 +2185,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
 {
-	int i;
+	int i, ret;
 	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2028,6 +2235,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 	}
 
+	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;
+	}
+
 out_write_size:
 	pos += copied;
 	if (pos > i_size_read(inode)) {
@@ -2042,11 +2257,20 @@ out_write_size:
 	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+out:
+	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
+	 * lock, or it will cause a deadlock since journal commit threads holds
+	 * this lock and will ask for the page lock when flushing the data.
+	 * put it here to preserve the unlock order.
+	 */
+	ocfs2_unlock_pages(wc);
+
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
-	ocfs2_free_write_ctxt(wc);
+	brelse(wc->w_di_bh);
+	kfree(wc);
 
 	return copied;
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 0717662b4aef..e737a4ce7d7a 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -4477,7 +4477,7 @@ int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh)
 		p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno);
 
 		ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen, 0,
-					       &dealloc, 0);
+					       &dealloc, 0, false);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index b46278f9ae44..fd6bbbbd7d78 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -385,8 +385,12 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 		head = &res->granted;
 
 	list_for_each_entry(lock, head, list) {
-		if (lock->ml.cookie == cookie)
+		/* if lock is found but unlock is pending ignore the bast */
+		if (lock->ml.cookie == cookie) {
+			if (lock->unlock_pending)
+				break;
 			goto do_ast;
+		}
 	}
 
 	mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, "
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 215e41abf101..8d660fc93144 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -498,16 +498,6 @@ static void dlm_lockres_release(struct kref *kref)
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
-	spin_lock(&dlm->track_lock);
-	if (!list_empty(&res->tracking))
-		list_del_init(&res->tracking);
-	else {
-		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
-		     res->lockname.len, res->lockname.name);
-		dlm_print_one_lock_resource(res);
-	}
-	spin_unlock(&dlm->track_lock);
-
 	atomic_dec(&dlm->res_cur_count);
 
 	if (!hlist_unhashed(&res->hash_node) ||
@@ -695,14 +685,6 @@ void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
 			res->inflight_assert_workers);
 }
 
-static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
-		struct dlm_lock_resource *res)
-{
-	spin_lock(&res->spinlock);
-	__dlm_lockres_grab_inflight_worker(dlm, res);
-	spin_unlock(&res->spinlock);
-}
-
 static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
 		struct dlm_lock_resource *res)
 {
@@ -1634,6 +1616,7 @@ send_response:
 		}
 		mlog(0, "%u is the owner of %.*s, cleaning everyone else\n",
 			     dlm->node_num, res->lockname.len, res->lockname.name);
+		spin_lock(&res->spinlock);
 		ret = dlm_dispatch_assert_master(dlm, res, 0, request->node_idx,
 						 DLM_ASSERT_MASTER_MLE_CLEANUP);
 		if (ret < 0) {
@@ -1641,7 +1624,8 @@ send_response:
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
 		} else
-			dlm_lockres_grab_inflight_worker(dlm, res);
+			__dlm_lockres_grab_inflight_worker(dlm, res);
+		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 3365839d2971..79b5af5e6a7b 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1656,14 +1656,18 @@ int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 	req.namelen = res->lockname.len;
 	memcpy(req.name, res->lockname.name, res->lockname.len);
 
+resend:
 	ret = o2net_send_message(DLM_MASTER_REQUERY_MSG, dlm->key,
 				 &req, sizeof(req), nodenum, &status);
-	/* XXX: negative status not handled properly here. */
 	if (ret < 0)
 		mlog(ML_ERROR, "Error %d when sending message %u (key "
 		     "0x%x) to node %u\n", ret, DLM_MASTER_REQUERY_MSG,
 		     dlm->key, nodenum);
-	else {
+	else if (status == -ENOMEM) {
+		mlog_errno(status);
+		msleep(50);
+		goto resend;
+	} else {
 		BUG_ON(status < 0);
 		BUG_ON(status > DLM_LOCK_RES_OWNER_UNKNOWN);
 		*real_master = (u8) (status & 0xff);
@@ -1705,9 +1709,13 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 			int ret = dlm_dispatch_assert_master(dlm, res,
 							     0, 0, flags);
 			if (ret < 0) {
-				mlog_errno(-ENOMEM);
-				/* retry!? */
-				BUG();
+				mlog_errno(ret);
+				spin_unlock(&res->spinlock);
+				dlm_lockres_put(res);
+				spin_unlock(&dlm->spinlock);
+				dlm_put(dlm);
+				/* sender will take care of this and retry */
+				return ret;
 			} else
 				__dlm_lockres_grab_inflight_worker(dlm, res);
 			spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 69aac6f088ad..2e5e6d5fffe8 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 
 	__dlm_unhash_lockres(dlm, res);
 
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+				res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 324dc93ac896..3e6d796fa720 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -295,7 +295,7 @@ out:
 	return ret;
 }
 
-static int ocfs2_set_inode_size(handle_t *handle,
+int ocfs2_set_inode_size(handle_t *handle,
 				struct inode *inode,
 				struct buffer_head *fe_bh,
 				u64 new_i_size)
@@ -441,7 +441,7 @@ out:
 	return status;
 }
 
-static int ocfs2_truncate_file(struct inode *inode,
+int ocfs2_truncate_file(struct inode *inode,
 			       struct buffer_head *di_bh,
 			       u64 new_i_size)
 {
@@ -557,7 +557,7 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 	return ret;
 }
 
-static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
 				     u32 clusters_to_add, int mark_unwritten)
 {
 	int status = 0;
@@ -1352,44 +1352,6 @@ 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;
@@ -1803,7 +1765,7 @@ static int ocfs2_remove_inode_range(struct inode *inode,
 
 		ret = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					       phys_cpos, trunc_len, flags,
-					       &dealloc, refcount_loc);
+					       &dealloc, refcount_loc, false);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto out;
@@ -2109,6 +2071,9 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	loff_t saved_pos = 0, 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
@@ -2197,23 +2162,11 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * one node could wind up truncating another
 		 * nodes writes.
 		 */
-		if (end > i_size_read(inode)) {
+		if (end > i_size_read(inode) && !full_coherency) {
 			*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, saved_pos, count);
-		if (ret == 1) {
-			*direct_io = 0;
-			ret = 0;
-		} else if (ret < 0)
-			mlog_errno(ret);
 		break;
 	}
 
@@ -2243,6 +2196,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
@@ -2357,11 +2311,51 @@ relock:
 
 	iov_iter_truncate(from, count);
 	if (direct_io) {
+		loff_t endbyte;
+		ssize_t written_buffered;
 		written = generic_file_direct_write(iocb, from, *ppos);
-		if (written < 0) {
+		if (written < 0 || written == count) {
 			ret = written;
 			goto out_dio;
 		}
+		/*
+		 * direct-io write to a hole: fall through to buffered I/O
+		 * for completing the rest of the request.
+		 */
+		*ppos += written;
+		count -= written;
+		written_buffered = generic_perform_write(file, from, *ppos);
+		/*
+		 * If generic_file_buffered_write() returned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero.  Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (written_buffered < 0) {
+			ret = written_buffered;
+			goto out;
+		}
+
+		/*
+		 * We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = *ppos + written_buffered - written - 1;
+		ret = filemap_write_and_wait_range(file->f_mapping, *ppos,
+				endbyte);
+		if (ret == 0) {
+			written = written_buffered;
+			invalidate_mapping_pages(mapping,
+					*ppos >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
 	} else {
 		current->backing_dev_info = file->f_mapping->backing_dev_info;
 		written = generic_perform_write(file, from, *ppos);
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 97bf761c9e7c..43e688a163aa 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -51,13 +51,22 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 			 struct ocfs2_alloc_context *data_ac,
 			 struct ocfs2_alloc_context *meta_ac,
 			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_set_inode_size(handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		u64 new_i_size);
 int ocfs2_simple_size_update(struct inode *inode,
 			     struct buffer_head *di_bh,
 			     u64 new_i_size);
+int ocfs2_truncate_file(struct inode *inode,
+		struct buffer_head *di_bh,
+		u64 new_i_size);
 int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
 			  u64 new_i_size, u64 zero_to);
 int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 		      loff_t zero_to);
+int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 437de7f768c6..21708cda4b8a 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1192,17 +1192,9 @@ void ocfs2_evict_inode(struct inode *inode)
 int ocfs2_drop_inode(struct inode *inode)
 {
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	int res;
-
 	trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink, oi->ip_flags);
-
-	if (oi->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)
-		res = 1;
-	else
-		res = generic_drop_inode(inode);
-
-	return res;
+	return 1;
 }
 
 /*
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4b0c68849b36..452ff5d55fc0 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -50,6 +50,8 @@
 #include "sysfile.h"
 #include "uptodate.h"
 #include "quota.h"
+#include "file.h"
+#include "namei.h"
 
 #include "buffer_head_io.h"
 #include "ocfs2_trace.h"
@@ -69,13 +71,15 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 				 int slot_num);
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot);
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type);
 static int ocfs2_commit_thread(void *arg);
 static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
-					    int slot_num,
-					    struct ocfs2_dinode *la_dinode,
-					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec);
+		int slot_num,
+		struct ocfs2_dinode *la_dinode,
+		struct ocfs2_dinode *tl_dinode,
+		struct ocfs2_quota_recovery *qrec,
+		enum ocfs2_orphan_reco_type orphan_reco_type);
 
 static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
 {
@@ -149,7 +153,8 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
+void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 	int i;
@@ -163,7 +168,8 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
 	for (i = 0; i < replay_map->rm_slots; i++)
 		if (replay_map->rm_replay_slots[i])
 			ocfs2_queue_recovery_completion(osb->journal, i, NULL,
-							NULL, NULL);
+							NULL, NULL,
+							orphan_reco_type);
 	replay_map->rm_state = REPLAY_DONE;
 }
 
@@ -1174,6 +1180,7 @@ struct ocfs2_la_recovery_item {
 	struct ocfs2_dinode	*lri_la_dinode;
 	struct ocfs2_dinode	*lri_tl_dinode;
 	struct ocfs2_quota_recovery *lri_qrec;
+	enum ocfs2_orphan_reco_type  lri_orphan_reco_type;
 };
 
 /* Does the second half of the recovery process. By this point, the
@@ -1195,6 +1202,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 	struct ocfs2_dinode *la_dinode, *tl_dinode;
 	struct ocfs2_la_recovery_item *item, *n;
 	struct ocfs2_quota_recovery *qrec;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 	LIST_HEAD(tmp_la_list);
 
 	trace_ocfs2_complete_recovery(
@@ -1212,6 +1220,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 		la_dinode = item->lri_la_dinode;
 		tl_dinode = item->lri_tl_dinode;
 		qrec = item->lri_qrec;
+		orphan_reco_type = item->lri_orphan_reco_type;
 
 		trace_ocfs2_complete_recovery_slot(item->lri_slot,
 			la_dinode ? le64_to_cpu(la_dinode->i_blkno) : 0,
@@ -1236,7 +1245,8 @@ void ocfs2_complete_recovery(struct work_struct *work)
 			kfree(tl_dinode);
 		}
 
-		ret = ocfs2_recover_orphans(osb, item->lri_slot);
+		ret = ocfs2_recover_orphans(osb, item->lri_slot,
+				orphan_reco_type);
 		if (ret < 0)
 			mlog_errno(ret);
 
@@ -1258,10 +1268,11 @@ void ocfs2_complete_recovery(struct work_struct *work)
  * tl_dinode, either manually on error, or by passing them to
  * ocfs2_complete_recovery */
 static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
-					    int slot_num,
-					    struct ocfs2_dinode *la_dinode,
-					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec)
+		int slot_num,
+		struct ocfs2_dinode *la_dinode,
+		struct ocfs2_dinode *tl_dinode,
+		struct ocfs2_quota_recovery *qrec,
+		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_la_recovery_item *item;
 
@@ -1285,6 +1296,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 	item->lri_slot = slot_num;
 	item->lri_tl_dinode = tl_dinode;
 	item->lri_qrec = qrec;
+	item->lri_orphan_reco_type = orphan_reco_type;
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
@@ -1304,7 +1316,8 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 	/* No need to queue up our truncate_log as regular cleanup will catch
 	 * that */
 	ocfs2_queue_recovery_completion(journal, osb->slot_num,
-					osb->local_alloc_copy, NULL, NULL);
+					osb->local_alloc_copy, NULL, NULL,
+					ORPHAN_NEED_TRUNCATE);
 	ocfs2_schedule_truncate_log_flush(osb, 0);
 
 	osb->local_alloc_copy = NULL;
@@ -1312,7 +1325,7 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 
 	/* queue to recover orphan slots for all offline slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 	ocfs2_free_replay_slots(osb);
 }
 
@@ -1323,7 +1336,8 @@ void ocfs2_complete_quota_recovery(struct ocfs2_super *osb)
 						osb->slot_num,
 						NULL,
 						NULL,
-						osb->quota_rec);
+						osb->quota_rec,
+						ORPHAN_NEED_TRUNCATE);
 		osb->quota_rec = NULL;
 	}
 }
@@ -1360,7 +1374,7 @@ restart:
 
 	/* queue recovery for our own slot */
 	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
-					NULL, NULL);
+					NULL, NULL, ORPHAN_NO_NEED_TRUNCATE);
 
 	spin_lock(&osb->osb_lock);
 	while (rm->rm_used) {
@@ -1419,13 +1433,14 @@ skip_recovery:
 			continue;
 		}
 		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec);
+						NULL, NULL, qrec,
+						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
 
 	/* queue recovery for offline slots */
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 
 bail:
 	mutex_lock(&osb->recovery_lock);
@@ -1712,7 +1727,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
 	/* This will kfree the memory pointed to by la_copy and tl_copy */
 	ocfs2_queue_recovery_completion(osb->journal, slot_num, la_copy,
-					tl_copy, NULL);
+					tl_copy, NULL, ORPHAN_NEED_TRUNCATE);
 
 	status = 0;
 done:
@@ -1902,7 +1917,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 
 	for (i = 0; i < osb->max_slots; i++)
 		ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL,
-						NULL);
+						NULL, ORPHAN_NO_NEED_TRUNCATE);
 	/*
 	 * We queued a recovery on orphan slots, increment the sequence
 	 * number and update LVB so other node will skip the scan for a while
@@ -2088,6 +2103,39 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
 	ocfs2_node_map_clear_bit(osb, &osb->osb_recovering_orphan_dirs, slot);
 }
 
+static int ocfs2_truncate_file_locked(struct inode *inode)
+{
+	struct buffer_head *di_bh = NULL;
+	int ret;
+
+	ret = ocfs2_rw_lock(inode, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		ocfs2_rw_unlock(inode, 1);
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_truncate_file(inode, di_bh, i_size_read(inode));
+	if (ret < 0) {
+		if (ret != -ENOSPC)
+			mlog_errno(ret);
+		ret = -ENOSPC;
+	}
+
+	ocfs2_inode_unlock(inode, 1);
+	ocfs2_rw_unlock(inode, 1);
+	brelse(di_bh);
+
+out:
+	return ret;
+}
+
 /*
  * Orphan recovery. Each mounted node has it's own orphan dir which we
  * must run during recovery. Our strategy here is to build a list of
@@ -2107,7 +2155,8 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
  *   advertising our state to ocfs2_delete_inode().
  */
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot)
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int ret = 0;
 	struct inode *inode = NULL;
@@ -2132,12 +2181,42 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 
 		iter = oi->ip_next_orphan;
 
-		spin_lock(&oi->ip_lock);
-		/* Set the proper information to get us going into
-		 * ocfs2_delete_inode. */
-		oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
-		spin_unlock(&oi->ip_lock);
+		/*
+		 * We need to take and drop the inode lock to
+		 * force read inode from disk.
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto next;
+		}
+		ocfs2_inode_unlock(inode, 0);
+
+		if (inode->i_nlink == 0) {
+			spin_lock(&oi->ip_lock);
+			/* The remote delete code may have set these on the
+			 * assumption that the other node would wipe them
+			 * successfully.  If they are still in the node's
+			 * orphan dir, we need to reset that state. */
+			oi->ip_flags &= ~(OCFS2_INODE_DELETED);
+
+			/* Set the proper information to get us going into
+			 * ocfs2_delete_inode. */
+			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
+			spin_unlock(&oi->ip_lock);
+		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
+			ret = ocfs2_truncate_file_locked(inode);
+			if (ret) {
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
+			if (ret)
+				mlog_errno(ret);
+		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
 
+next:
 		iput(inode);
 
 		inode = iter;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7f8cde94abfe..f4cd3c3e9fb7 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -472,6 +472,11 @@ static inline int ocfs2_unlink_credits(struct super_block *sb)
  * orphan dir index leaf */
 #define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)
 
+/* dinode + orphan dir dinode + extent tree leaf block + orphan dir entry +
+ * orphan dir index root + orphan dir index leaf */
+#define OCFS2_INODE_ADD_TO_ORPHAN_CREDITS  (2 * OCFS2_INODE_UPDATE_CREDITS + 4)
+#define OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS  OCFS2_INODE_ADD_TO_ORPHAN_CREDITS
+
 /* dinode update, old dir dinode update, new dir dinode update, old
  * dir dir entry, new dir dir entry, dir entry update for renaming
  * directory + target unlink + 3 x dir index leaves */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 8add6f1030d7..597692f94538 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -75,20 +75,6 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 			      handle_t *handle,
 			      struct ocfs2_alloc_context *inode_ac);
 
-static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
-				    struct inode **ret_orphan_dir,
-				    u64 blkno,
-				    char *name,
-				    struct ocfs2_dir_lookup_result *lookup);
-
-static int ocfs2_orphan_add(struct ocfs2_super *osb,
-			    handle_t *handle,
-			    struct inode *inode,
-			    struct buffer_head *fe_bh,
-			    char *name,
-			    struct ocfs2_dir_lookup_result *lookup,
-			    struct inode *orphan_dir_inode);
-
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     handle_t *handle,
 				     struct inode *inode,
@@ -2097,7 +2083,7 @@ static int __ocfs2_prepare_orphan_dir(struct inode *orphan_dir_inode,
  *
  * Returns non-zero on failure. 
  */
-static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
+int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    u64 blkno,
 				    char *name,
@@ -2137,7 +2123,7 @@ out:
 	return ret;
 }
 
-static int ocfs2_orphan_add(struct ocfs2_super *osb,
+int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
 			    struct inode *inode,
 			    struct buffer_head *fe_bh,
@@ -2500,6 +2486,153 @@ leave:
 	return status;
 }
 
+/* An orphan dir name is an 8 byte value, printed as a hex string */
+#define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+		struct inode *inode)
+{
+	char orphan_name[OCFS2_ORPHAN_NAMELEN + 1];
+	struct inode *orphan_dir_inode = NULL;
+	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
+	struct buffer_head *di_bh = NULL;
+	int status = 0;
+	handle_t *handle = NULL;
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,
+			OCFS2_I(inode)->ip_blkno,
+			orphan_name,
+			&orphan_insert);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_ADD_TO_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	status = ocfs2_orphan_add(osb, handle, inode, di_bh, orphan_name,
+			&orphan_insert, orphan_dir_inode);
+	if (status)
+		mlog_errno(status);
+
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	iput(orphan_dir_inode);
+
+	ocfs2_free_dir_lookup_result(&orphan_insert);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end)
+{
+	struct inode *orphan_dir_inode = NULL;
+	struct buffer_head *orphan_dir_bh = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+	handle_t *handle = NULL;
+	int status = 0;
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+
+	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+			ORPHAN_DIR_SYSTEM_INODE,
+			osb->slot_num);
+	if (!orphan_dir_inode) {
+		status = -EEXIST;
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	mutex_lock(&orphan_dir_inode->i_mutex);
+	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+	if (status < 0) {
+		mutex_unlock(&orphan_dir_inode->i_mutex);
+		iput(orphan_dir_inode);
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	status = ocfs2_orphan_del(osb, handle, orphan_dir_inode,
+			inode, orphan_dir_bh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	/*
+	 * We're going to journal the change of i_flags and i_orphaned_slot.
+	 * It's safe anyway, though some callers may duplicate the journaling.
+	 * Journaling within the func just make the logic look more
+	 * straightforward.
+	 */
+	status = ocfs2_journal_access_di(handle,
+			INODE_CACHE(inode),
+			di_bh,
+			OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	di->i_flags &= ~cpu_to_le32(OCFS2_ORPHANED_FL);
+	OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
+	di->i_orphaned_slot = 0;
+
+	if (update_isize) {
+		status = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (status)
+			mlog_errno(status);
+	} else
+		ocfs2_journal_dirty(handle, di_bh);
+
+bail_commit:
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	brelse(orphan_dir_bh);
+	iput(orphan_dir_inode);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *inode,
 				   struct dentry *dentry)
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index e5d059d4f115..5dcbd4becbe1 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -26,10 +26,23 @@
 #ifndef OCFS2_NAMEI_H
 #define OCFS2_NAMEI_H
 
+#include "dir.h"
+
 extern const struct inode_operations ocfs2_dir_iops;
 
 struct dentry *ocfs2_get_parent(struct dentry *child);
-
+int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
+		struct inode **ret_orphan_dir,
+		u64 blkno,
+		char *name,
+		struct ocfs2_dir_lookup_result *lookup);
+int ocfs2_orphan_add(struct ocfs2_super *osb,
+		handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		char *name,
+		struct ocfs2_dir_lookup_result *lookup,
+		struct inode *orphan_dir_inode);
 int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
 		     struct inode *orphan_dir_inode,
@@ -38,6 +51,11 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 int ocfs2_create_inode_in_orphan(struct inode *dir,
 				 int mode,
 				 struct inode **new_inode);
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+		struct inode *inode);
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index bbec539230fd..f74556501609 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -203,6 +203,11 @@ struct ocfs2_lock_res {
 #endif
 };
 
+enum ocfs2_orphan_reco_type {
+	ORPHAN_NO_NEED_TRUNCATE = 0,
+	ORPHAN_NEED_TRUNCATE,
+};
+
 enum ocfs2_orphan_scan_state {
 	ORPHAN_SCAN_ACTIVE,
 	ORPHAN_SCAN_INACTIVE
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 317b72641ebf..9f8fa1e5e8aa 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -31,9 +31,81 @@ static DEFINE_SPINLOCK(proc_subdir_lock);
 
 static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
 {
-	if (de->namelen != len)
-		return 0;
-	return !memcmp(name, de->name, len);
+	if (len < de->namelen)
+		return -1;
+	if (len > de->namelen)
+		return 1;
+
+	return memcmp(name, de->name, len);
+}
+
+static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
+{
+	struct rb_node *node = rb_first(&dir->subdir);
+
+	if (node == NULL)
+		return NULL;
+
+	return rb_entry(node, struct proc_dir_entry, subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
+{
+	struct rb_node *node = rb_next(&dir->subdir_node);
+
+	if (node == NULL)
+		return NULL;
+
+	return rb_entry(node, struct proc_dir_entry, subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
+					      const char *name,
+					      unsigned int len)
+{
+	struct rb_node *node = dir->subdir.rb_node;
+
+	while (node) {
+		struct proc_dir_entry *de = container_of(node,
+							 struct proc_dir_entry,
+							 subdir_node);
+		int result = proc_match(len, name, de);
+
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return de;
+	}
+	return NULL;
+}
+
+static bool pde_subdir_insert(struct proc_dir_entry *dir,
+			      struct proc_dir_entry *de)
+{
+	struct rb_root *root = &dir->subdir;
+	struct rb_node **new = &root->rb_node, *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct proc_dir_entry *this =
+			container_of(*new, struct proc_dir_entry, subdir_node);
+		int result = proc_match(de->namelen, de->name, this);
+
+		parent = *new;
+		if (result < 0)
+			new = &(*new)->rb_left;
+		else if (result > 0)
+			new = &(*new)->rb_right;
+		else
+			return false;
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&de->subdir_node, parent, new);
+	rb_insert_color(&de->subdir_node, root);
+	return true;
 }
 
 static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
@@ -92,10 +164,7 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
 			break;
 
 		len = next - cp;
-		for (de = de->subdir; de ; de = de->next) {
-			if (proc_match(len, cp, de))
-				break;
-		}
+		de = pde_subdir_find(de, cp, len);
 		if (!de) {
 			WARN(1, "name '%s'\n", name);
 			return -ENOENT;
@@ -183,19 +252,16 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 	struct inode *inode;
 
 	spin_lock(&proc_subdir_lock);
-	for (de = de->subdir; de ; de = de->next) {
-		if (de->namelen != dentry->d_name.len)
-			continue;
-		if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
-			pde_get(de);
-			spin_unlock(&proc_subdir_lock);
-			inode = proc_get_inode(dir->i_sb, de);
-			if (!inode)
-				return ERR_PTR(-ENOMEM);
-			d_set_d_op(dentry, &simple_dentry_operations);
-			d_add(dentry, inode);
-			return NULL;
-		}
+	de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
+	if (de) {
+		pde_get(de);
+		spin_unlock(&proc_subdir_lock);
+		inode = proc_get_inode(dir->i_sb, de);
+		if (!inode)
+			return ERR_PTR(-ENOMEM);
+		d_set_d_op(dentry, &simple_dentry_operations);
+		d_add(dentry, inode);
+		return NULL;
 	}
 	spin_unlock(&proc_subdir_lock);
 	return ERR_PTR(-ENOENT);
@@ -225,7 +291,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		return 0;
 
 	spin_lock(&proc_subdir_lock);
-	de = de->subdir;
+	de = pde_subdir_first(de);
 	i = ctx->pos - 2;
 	for (;;) {
 		if (!de) {
@@ -234,7 +300,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		}
 		if (!i)
 			break;
-		de = de->next;
+		de = pde_subdir_next(de);
 		i--;
 	}
 
@@ -249,7 +315,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		}
 		spin_lock(&proc_subdir_lock);
 		ctx->pos++;
-		next = de->next;
+		next = pde_subdir_next(de);
 		pde_put(de);
 		de = next;
 	} while (de);
@@ -286,9 +352,8 @@ static const struct inode_operations proc_dir_inode_operations = {
 
 static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
 {
-	struct proc_dir_entry *tmp;
 	int ret;
-	
+
 	ret = proc_alloc_inum(&dp->low_ino);
 	if (ret)
 		return ret;
@@ -308,17 +373,10 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
 	}
 
 	spin_lock(&proc_subdir_lock);
-
-	for (tmp = dir->subdir; tmp; tmp = tmp->next)
-		if (strcmp(tmp->name, dp->name) == 0) {
-			WARN(1, "proc_dir_entry '%s/%s' already registered\n",
-				dir->name, dp->name);
-			break;
-		}
-
-	dp->next = dir->subdir;
 	dp->parent = dir;
-	dir->subdir = dp;
+	if (pde_subdir_insert(dir, dp) == false)
+		WARN(1, "proc_dir_entry '%s/%s' already registered\n",
+		     dir->name, dp->name);
 	spin_unlock(&proc_subdir_lock);
 
 	return 0;
@@ -354,6 +412,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 	ent->namelen = qstr.len;
 	ent->mode = mode;
 	ent->nlink = nlink;
+	ent->subdir = RB_ROOT;
 	atomic_set(&ent->count, 1);
 	spin_lock_init(&ent->pde_unload_lock);
 	INIT_LIST_HEAD(&ent->pde_openers);
@@ -485,7 +544,6 @@ void pde_put(struct proc_dir_entry *pde)
  */
 void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 {
-	struct proc_dir_entry **p;
 	struct proc_dir_entry *de = NULL;
 	const char *fn = name;
 	unsigned int len;
@@ -497,14 +555,9 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 	}
 	len = strlen(fn);
 
-	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (proc_match(len, fn, *p)) {
-			de = *p;
-			*p = de->next;
-			de->next = NULL;
-			break;
-		}
-	}
+	de = pde_subdir_find(parent, fn, len);
+	if (de)
+		rb_erase(&de->subdir_node, &parent->subdir);
 	spin_unlock(&proc_subdir_lock);
 	if (!de) {
 		WARN(1, "name '%s'\n", name);
@@ -516,16 +569,15 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 	if (S_ISDIR(de->mode))
 		parent->nlink--;
 	de->nlink = 0;
-	WARN(de->subdir, "%s: removing non-empty directory "
-			 "'%s/%s', leaking at least '%s'\n", __func__,
-			 de->parent->name, de->name, de->subdir->name);
+	WARN(pde_subdir_first(de),
+	     "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
+	     __func__, de->parent->name, de->name, pde_subdir_first(de)->name);
 	pde_put(de);
 }
 EXPORT_SYMBOL(remove_proc_entry);
 
 int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 {
-	struct proc_dir_entry **p;
 	struct proc_dir_entry *root = NULL, *de, *next;
 	const char *fn = name;
 	unsigned int len;
@@ -537,24 +589,18 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 	}
 	len = strlen(fn);
 
-	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (proc_match(len, fn, *p)) {
-			root = *p;
-			*p = root->next;
-			root->next = NULL;
-			break;
-		}
-	}
+	root = pde_subdir_find(parent, fn, len);
 	if (!root) {
 		spin_unlock(&proc_subdir_lock);
 		return -ENOENT;
 	}
+	rb_erase(&root->subdir_node, &parent->subdir);
+
 	de = root;
 	while (1) {
-		next = de->subdir;
+		next = pde_subdir_first(de);
 		if (next) {
-			de->subdir = next->next;
-			next->next = NULL;
+			rb_erase(&next->subdir_node, &de->subdir);
 			de = next;
 			continue;
 		}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index aa7a0ee182e1..7fb1a4869fd0 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -24,10 +24,9 @@ struct mempolicy;
  * tree) of these proc_dir_entries, so that we can dynamically
  * add new files to /proc.
  *
- * The "next" pointer creates a linked list of one /proc directory,
- * while parent/subdir create the directory structure (every
- * /proc file has a parent, but "subdir" is NULL for all
- * non-directory entries).
+ * parent/subdir are used for the directory structure (every /proc file has a
+ * parent, but "subdir" is empty for all non-directory entries).
+ * subdir_node is used to build the rb tree "subdir" of the parent.
  */
 struct proc_dir_entry {
 	unsigned int low_ino;
@@ -38,7 +37,9 @@ struct proc_dir_entry {
 	loff_t size;
 	const struct inode_operations *proc_iops;
 	const struct file_operations *proc_fops;
-	struct proc_dir_entry *next, *parent, *subdir;
+	struct proc_dir_entry *parent;
+	struct rb_root subdir;
+	struct rb_node subdir_node;
 	void *data;
 	atomic_t count;		/* use count */
 	atomic_t in_use;	/* number of callers into module in progress; */
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index a63af3e0a612..1bde894bc624 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -192,6 +192,7 @@ static __net_init int proc_net_ns_init(struct net *net)
 	if (!netd)
 		goto out;
 
+	netd->subdir = RB_ROOT;
 	netd->data = net;
 	netd->nlink = 2;
 	netd->namelen = 3;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 094e44d4a6be..e74ac9f1a2c0 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -251,6 +251,7 @@ struct proc_dir_entry proc_root = {
 	.proc_iops	= &proc_root_inode_operations, 
 	.proc_fops	= &proc_root_operations,
 	.parent		= &proc_root,
+	.subdir		= RB_ROOT,
 	.name		= "/proc",
 };
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1d5196889048..9f96b25965c2 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -113,6 +113,19 @@ static inline void css_get(struct cgroup_subsys_state *css)
 }
 
 /**
+ * css_get_many - obtain references on the specified css
+ * @css: target css
+ * @n: number of references to get
+ *
+ * The caller must already have a reference.
+ */
+static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_get_many(&css->refcnt, n);
+}
+
+/**
  * css_tryget - try to obtain a reference on the specified css
  * @css: target css
  *
@@ -159,6 +172,19 @@ static inline void css_put(struct cgroup_subsys_state *css)
 		percpu_ref_put(&css->refcnt);
 }
 
+/**
+ * css_put_many - put css references
+ * @css: target css
+ * @n: number of references to put
+ *
+ * Put references obtained via css_get() and css_tryget_online().
+ */
+static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_put_many(&css->refcnt, n);
+}
+
 /* bits in struct cgroup flags field */
 enum {
 	/* Control Group requires release notifications to userspace */
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 60bdf8dc02a3..3238ffa33f68 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -33,10 +33,11 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone);
+			int alloc_flags, int classzone_idx);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
-extern unsigned long compaction_suitable(struct zone *zone, int order);
+extern unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -103,7 +104,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	return COMPACT_CONTINUE;
 }
@@ -116,7 +117,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 {
 }
 
-static inline unsigned long compaction_suitable(struct zone *zone, int order)
+static inline unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	return COMPACT_SKIPPED;
 }
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/file.h b/include/linux/file.h
index 4d69123377a2..f87d30882a24 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -66,7 +66,6 @@ extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
 extern void put_filp(struct file *);
 extern int get_unused_fd_flags(unsigned flags);
-#define get_unused_fd() get_unused_fd_flags(0)
 extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 41b30fd4d041..07d2699cdb51 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -381,8 +381,8 @@ extern void free_kmem_pages(unsigned long addr, unsigned int order);
 
 void page_alloc_init(void);
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
-void drain_all_pages(void);
-void drain_local_pages(void *dummy);
+void drain_all_pages(struct zone *zone);
+void drain_local_pages(struct zone *zone);
 
 /*
  * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6e6d338641fe..65e12a24ce1d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -138,6 +138,7 @@ static inline void hugetlb_show_meminfo(void)
 #define prepare_hugepage_range(file, addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
 #define pud_huge(x)	0
+#define pgd_huge(x)	0
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 0129f89cf98d..bcc853eccc85 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -16,7 +16,6 @@
 #define _LINUX_HUGETLB_CGROUP_H
 
 #include <linux/mmdebug.h>
-#include <linux/res_counter.h>
 
 struct hugetlb_cgroup;
 /*
diff --git a/include/linux/input.h b/include/linux/input.h
index 82ce323b9986..6453b22372ac 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -79,6 +79,7 @@ struct input_value {
  * @led: reflects current state of device's LEDs
  * @snd: reflects current state of sound effects
  * @sw: reflects current state of device's switches
+ * @leds: leds objects for the device's LEDs
  * @open: this method is called when the very first user calls
  *	input_open_device(). The driver must prepare the device
  *	to start generating events (start polling thread,
@@ -164,6 +165,8 @@ struct input_dev {
 	unsigned long snd[BITS_TO_LONGS(SND_CNT)];
 	unsigned long sw[BITS_TO_LONGS(SW_CNT)];
 
+	struct led_classdev *leds;
+
 	int (*open)(struct input_dev *dev);
 	void (*close)(struct input_dev *dev);
 	int (*flush)(struct input_dev *dev, struct file *file);
@@ -531,4 +534,22 @@ int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file);
 int input_ff_create_memless(struct input_dev *dev, void *data,
 		int (*play_effect)(struct input_dev *, void *, struct ff_effect *));
 
+#ifdef CONFIG_INPUT_LEDS
+
+int input_led_connect(struct input_dev *dev);
+void input_led_disconnect(struct input_dev *dev);
+
+#else
+
+static inline int input_led_connect(struct input_dev *dev)
+{
+	return 0;
+}
+
+static inline void input_led_disconnect(struct input_dev *dev)
+{
+}
+
+#endif
+
 #endif
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 35e7eca4e33b..e365d5ec69cb 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -7,15 +7,6 @@
 #include <linux/notifier.h>
 #include <linux/nsproxy.h>
 
-/*
- * ipc namespace events
- */
-#define IPCNS_MEMCHANGED   0x00000001   /* Notify lowmem size changed */
-#define IPCNS_CREATED  0x00000002   /* Notify new ipc namespace created */
-#define IPCNS_REMOVED  0x00000003   /* Notify ipc namespace removed */
-
-#define IPCNS_CALLBACK_PRI 0
-
 struct user_namespace;
 
 struct ipc_ids {
@@ -38,7 +29,6 @@ struct ipc_namespace {
 	unsigned int	msg_ctlmni;
 	atomic_t	msg_bytes;
 	atomic_t	msg_hdrs;
-	int		auto_msgmni;
 
 	size_t		shm_ctlmax;
 	size_t		shm_ctlall;
@@ -77,18 +67,8 @@ extern atomic_t nr_ipc_ns;
 extern spinlock_t mq_lock;
 
 #ifdef CONFIG_SYSVIPC
-extern int register_ipcns_notifier(struct ipc_namespace *);
-extern int cond_register_ipcns_notifier(struct ipc_namespace *);
-extern void unregister_ipcns_notifier(struct ipc_namespace *);
-extern int ipcns_notify(unsigned long);
 extern void shm_destroy_orphaned(struct ipc_namespace *ns);
 #else /* CONFIG_SYSVIPC */
-static inline int register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { }
-static inline int ipcns_notify(unsigned long l) { return 0; }
 static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
 #endif /* CONFIG_SYSVIPC */
 
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 6b394f0b5148..eeb307985715 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -6,7 +6,8 @@
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern int __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
-extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma);
+extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+				      unsigned long vm_flags);
 
 #define khugepaged_enabled()					       \
 	(transparent_hugepage_flags &				       \
@@ -35,13 +36,13 @@ static inline void khugepaged_exit(struct mm_struct *mm)
 		__khugepaged_exit(mm);
 }
 
-static inline int khugepaged_enter(struct vm_area_struct *vma)
+static inline int khugepaged_enter(struct vm_area_struct *vma,
+				   unsigned long vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags))
 		if ((khugepaged_always() ||
-		     (khugepaged_req_madv() &&
-		      vma->vm_flags & VM_HUGEPAGE)) &&
-		    !(vma->vm_flags & VM_NOHUGEPAGE))
+		     (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) &&
+		    !(vm_flags & VM_NOHUGEPAGE))
 			if (__khugepaged_enter(vma->vm_mm))
 				return -ENOMEM;
 	return 0;
@@ -54,11 +55,13 @@ static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 static inline void khugepaged_exit(struct mm_struct *mm)
 {
 }
-static inline int khugepaged_enter(struct vm_area_struct *vma)
+static inline int khugepaged_enter(struct vm_area_struct *vma,
+				   unsigned long vm_flags)
 {
 	return 0;
 }
-static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+					     unsigned long vm_flags)
 {
 	return 0;
 }
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 19df5d857411..0daf383f8f1c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -471,9 +471,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 	/*
 	 * __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 with
-	 * res_counter_charge_nofail, but we hope those allocations are rare,
-	 * and won't be worth the trouble.
+	 * 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;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 27eb1bfbe704..a565afe8a8b9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1220,6 +1220,32 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		    struct vm_area_struct **vmas);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
+
+#ifdef CONFIG_HAVE_GENERIC_RCU_GUP
+#ifndef is_hugepd
+/*
+ * Some architectures support hugepage directory format that is
+ * required to support different hugetlbfs sizes.
+ */
+typedef struct { unsigned long pd; } hugepd_t;
+#define is_hugepd(hugepd) (0)
+#define __hugepd(x) ((hugepd_t) { (x) })
+static inline int gup_hugepd(hugepd_t hugepd, unsigned long addr,
+			     unsigned pdshift, unsigned long end,
+			     int write, struct page **pages, int *nr)
+{
+	return 0;
+}
+#else
+extern int gup_hugepd(hugepd_t hugepd, unsigned long addr,
+		      unsigned pdshift, unsigned long end,
+		      int write, struct page **pages, int *nr);
+#endif
+extern int gup_huge_pte(pte_t orig, pte_t *ptep, unsigned long addr,
+			unsigned long sz, unsigned long end, int write,
+			struct page **pages, int *nr);
+#endif
+
 struct kvec;
 int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
 			struct page **pages);
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
index 5b5efae09135..ad2f67054372 100644
--- a/include/linux/of_reserved_mem.h
+++ b/include/linux/of_reserved_mem.h
@@ -16,7 +16,7 @@ struct reserved_mem {
 };
 
 struct reserved_mem_ops {
-	void	(*device_init)(struct reserved_mem *rmem,
+	int	(*device_init)(struct reserved_mem *rmem,
 			       struct device *dev);
 	void	(*device_release)(struct reserved_mem *rmem,
 				  struct device *dev);
@@ -28,14 +28,17 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem);
 	_OF_DECLARE(reservedmem, name, compat, init, reservedmem_of_init_fn)
 
 #ifdef CONFIG_OF_RESERVED_MEM
-void of_reserved_mem_device_init(struct device *dev);
+int of_reserved_mem_device_init(struct device *dev);
 void of_reserved_mem_device_release(struct device *dev);
 
 void fdt_init_reserved_mem(void);
 void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
 			       phys_addr_t base, phys_addr_t size);
 #else
-static inline void of_reserved_mem_device_init(struct device *dev) { }
+static inline int of_reserved_mem_device_init(struct device *dev)
+{
+	return -ENOSYS;
+}
 static inline void of_reserved_mem_device_release(struct device *pdev) { }
 
 static inline void fdt_init_reserved_mem(void) { }
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 647395a1a550..8927b6e443b5 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -50,6 +50,8 @@ static inline bool oom_task_origin(const struct task_struct *p)
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
+
+extern int oom_kills_count(void);
 extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			     unsigned int points, unsigned long totalpages,
 			     struct mem_cgroup *memcg, nodemask_t *nodemask,
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
new file mode 100644
index 000000000000..955421575d16
--- /dev/null
+++ b/include/linux/page_counter.h
@@ -0,0 +1,51 @@
+#ifndef _LINUX_PAGE_COUNTER_H
+#define _LINUX_PAGE_COUNTER_H
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+struct page_counter {
+	atomic_long_t count;
+	unsigned long limit;
+	struct page_counter *parent;
+
+	/* legacy */
+	unsigned long watermark;
+	unsigned long failcnt;
+};
+
+#if BITS_PER_LONG == 32
+#define PAGE_COUNTER_MAX LONG_MAX
+#else
+#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
+#endif
+
+static inline void page_counter_init(struct page_counter *counter,
+				     struct page_counter *parent)
+{
+	atomic_long_set(&counter->count, 0);
+	counter->limit = PAGE_COUNTER_MAX;
+	counter->parent = parent;
+}
+
+static inline unsigned long page_counter_read(struct page_counter *counter)
+{
+	return atomic_long_read(&counter->count);
+}
+
+void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail);
+void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_limit(struct page_counter *counter, unsigned long limit);
+int page_counter_memparse(const char *buf, unsigned long *nr_pages);
+
+static inline void page_counter_reset_watermark(struct page_counter *counter)
+{
+	counter->watermark = page_counter_read(counter);
+}
+
+#endif /* _LINUX_PAGE_COUNTER_H */
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index d5c89e0dd0e6..494ab0588b65 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -141,28 +141,42 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 }
 
 /**
- * percpu_ref_get - increment a percpu refcount
+ * percpu_ref_get_many - increment a percpu refcount
  * @ref: percpu_ref to get
+ * @nr: number of references to get
  *
- * Analagous to atomic_long_inc().
+ * Analogous to atomic_long_add().
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_get(struct percpu_ref *ref)
+static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_inc(*percpu_count);
+		this_cpu_add(*percpu_count, nr);
 	else
-		atomic_long_inc(&ref->count);
+		atomic_long_add(nr, &ref->count);
 
 	rcu_read_unlock_sched();
 }
 
 /**
+ * percpu_ref_get - increment a percpu refcount
+ * @ref: percpu_ref to get
+ *
+ * Analagous to atomic_long_inc().
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_get(struct percpu_ref *ref)
+{
+	percpu_ref_get_many(ref, 1);
+}
+
+/**
  * percpu_ref_tryget - try to increment a percpu refcount
  * @ref: percpu_ref to try-get
  *
@@ -225,29 +239,44 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 }
 
 /**
- * percpu_ref_put - decrement a percpu refcount
+ * percpu_ref_put_many - decrement a percpu refcount
  * @ref: percpu_ref to put
+ * @nr: number of references to put
  *
  * Decrement the refcount, and if 0, call the release function (which was passed
  * to percpu_ref_init())
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_put(struct percpu_ref *ref)
+static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_dec(*percpu_count);
-	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
+		this_cpu_sub(*percpu_count, nr);
+	else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
 		ref->release(ref);
 
 	rcu_read_unlock_sched();
 }
 
 /**
+ * percpu_ref_put - decrement a percpu refcount
+ * @ref: percpu_ref to put
+ *
+ * Decrement the refcount, and if 0, call the release function (which was passed
+ * to percpu_ref_init())
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_put(struct percpu_ref *ref)
+{
+	percpu_ref_put_many(ref, 1);
+}
+
+/**
  * percpu_ref_is_zero - test whether a percpu refcount reached zero
  * @ref: percpu_ref to test
  *
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
deleted file mode 100644
index 56b7bc32db4f..000000000000
--- a/include/linux/res_counter.h
+++ /dev/null
@@ -1,223 +0,0 @@
-#ifndef __RES_COUNTER_H__
-#define __RES_COUNTER_H__
-
-/*
- * Resource Counters
- * Contain common data types and routines for resource accounting
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- * See Documentation/cgroups/resource_counter.txt for more
- * info about what this counter is.
- */
-
-#include <linux/spinlock.h>
-#include <linux/errno.h>
-
-/*
- * The core object. the cgroup that wishes to account for some
- * resource may include this counter into its structures and use
- * the helpers described beyond
- */
-
-struct res_counter {
-	/*
-	 * the current resource consumption level
-	 */
-	unsigned long long usage;
-	/*
-	 * the maximal value of the usage from the counter creation
-	 */
-	unsigned long long max_usage;
-	/*
-	 * the limit that usage cannot exceed
-	 */
-	unsigned long long limit;
-	/*
-	 * the limit that usage can be exceed
-	 */
-	unsigned long long soft_limit;
-	/*
-	 * the number of unsuccessful attempts to consume the resource
-	 */
-	unsigned long long failcnt;
-	/*
-	 * the lock to protect all of the above.
-	 * the routines below consider this to be IRQ-safe
-	 */
-	spinlock_t lock;
-	/*
-	 * Parent counter, used for hierarchial resource accounting
-	 */
-	struct res_counter *parent;
-};
-
-#define RES_COUNTER_MAX ULLONG_MAX
-
-/**
- * Helpers to interact with userspace
- * res_counter_read_u64() - returns the value of the specified member.
- * res_counter_read/_write - put/get the specified fields from the
- * res_counter struct to/from the user
- *
- * @counter:     the counter in question
- * @member:  the field to work with (see RES_xxx below)
- * @buf:     the buffer to opeate on,...
- * @nbytes:  its size...
- * @pos:     and the offset.
- */
-
-u64 res_counter_read_u64(struct res_counter *counter, int member);
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *buf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *s));
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *res);
-
-/*
- * the field descriptors. one for each member of res_counter
- */
-
-enum {
-	RES_USAGE,
-	RES_MAX_USAGE,
-	RES_LIMIT,
-	RES_FAILCNT,
-	RES_SOFT_LIMIT,
-};
-
-/*
- * helpers for accounting
- */
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent);
-
-/*
- * charge - try to consume more resource.
- *
- * @counter: the counter
- * @val: the amount of the resource. each controller defines its own
- *       units, e.g. numbers, bytes, Kbytes, etc
- *
- * returns 0 on success and <0 if the counter->usage will exceed the
- * counter->limit
- *
- * charge_nofail works the same, except that it charges the resource
- * counter unconditionally, and returns < 0 if the after the current
- * charge we are over limit.
- */
-
-int __must_check res_counter_charge(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-int res_counter_charge_nofail(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-
-/*
- * uncharge - tell that some portion of the resource is released
- *
- * @counter: the counter
- * @val: the amount of the resource
- *
- * these calls check for usage underflow and show a warning on the console
- *
- * returns the total charges still present in @counter.
- */
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val);
-/**
- * res_counter_margin - calculate chargeable space of a counter
- * @cnt: the counter
- *
- * Returns the difference between the hard limit and the current usage
- * of resource counter @cnt.
- */
-static inline unsigned long long res_counter_margin(struct res_counter *cnt)
-{
-	unsigned long long margin;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->limit > cnt->usage)
-		margin = cnt->limit - cnt->usage;
-	else
-		margin = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return margin;
-}
-
-/**
- * Get the difference between the usage and the soft limit
- * @cnt: The counter
- *
- * Returns 0 if usage is less than or equal to soft limit
- * The difference between usage and soft limit, otherwise.
- */
-static inline unsigned long long
-res_counter_soft_limit_excess(struct res_counter *cnt)
-{
-	unsigned long long excess;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= cnt->soft_limit)
-		excess = 0;
-	else
-		excess = cnt->usage - cnt->soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return excess;
-}
-
-static inline void res_counter_reset_max(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->max_usage = cnt->usage;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline void res_counter_reset_failcnt(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->failcnt = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline int res_counter_set_limit(struct res_counter *cnt,
-		unsigned long long limit)
-{
-	unsigned long flags;
-	int ret = -EBUSY;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= limit) {
-		cnt->limit = limit;
-		ret = 0;
-	}
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return ret;
-}
-
-static inline int
-res_counter_set_soft_limit(struct res_counter *cnt,
-				unsigned long long soft_limit)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->soft_limit = soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return 0;
-}
-
-#endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 2e22a2e58f3a..a0c6fd5fb5c5 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -117,6 +117,7 @@ void *memchr_inv(const void *s, int c, size_t n);
 
 extern char *kstrdup(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/net/sock.h b/include/net/sock.h
index 7db3db112baa..0fa8cf908b65 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,8 +54,8 @@
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
-#include <linux/res_counter.h>
 #include <linux/static_key.h>
 #include <linux/aio.h>
 #include <linux/sched.h>
@@ -1061,7 +1061,7 @@ enum cg_proto_flags {
 };
 
 struct cg_proto {
-	struct res_counter	memory_allocated;	/* Current allocated memory. */
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
 	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
 	int			memory_pressure;
 	long			sysctl_mem[3];
@@ -1213,34 +1213,26 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 					      unsigned long amt,
 					      int *parent_status)
 {
-	struct res_counter *fail;
-	int ret;
+	page_counter_charge(&prot->memory_allocated, amt);
 
-	ret = res_counter_charge_nofail(&prot->memory_allocated,
-					amt << PAGE_SHIFT, &fail);
-	if (ret < 0)
+	if (page_counter_read(&prot->memory_allocated) >
+	    prot->memory_allocated.limit)
 		*parent_status = OVER_LIMIT;
 }
 
 static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
 					      unsigned long amt)
 {
-	res_counter_uncharge(&prot->memory_allocated, amt << PAGE_SHIFT);
-}
-
-static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
-{
-	u64 ret;
-	ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
-	return ret >> PAGE_SHIFT;
+	page_counter_uncharge(&prot->memory_allocated, amt);
 }
 
 static inline long
 sk_memory_allocated(const struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 
 	return atomic_long_read(prot->memory_allocated);
 }
@@ -1254,7 +1246,7 @@ sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
 		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
 		/* update the root cgroup regardless */
 		atomic_long_add_return(amt, prot->memory_allocated);
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 	}
 
 	return atomic_long_add_return(amt, prot->memory_allocated);
diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h
index a70375526578..f51c8001dbe5 100644
--- a/include/uapi/linux/msg.h
+++ b/include/uapi/linux/msg.h
@@ -51,16 +51,28 @@ struct msginfo {
 };
 
 /*
- * Scaling factor to compute msgmni:
- * the memory dedicated to msg queues (msgmni * msgmnb) should occupy
- * at most 1/MSG_MEM_SCALE of the lowmem (see the formula in ipc/msg.c):
- * up to 8MB       : msgmni = 16 (MSGMNI)
- * 4 GB            : msgmni = 8K
- * more than 16 GB : msgmni = 32K (IPCMNI)
+ * MSGMNI, MSGMAX and MSGMNB are default values which can be
+ * modified by sysctl.
+ *
+ * MSGMNI is the upper limit for the number of messages queues per
+ * namespace.
+ * It has been chosen to be as large possible without facilitating
+ * scenarios where userspace causes overflows when adjusting the limits via
+ * operations of the form retrieve current limit; add X; update limit".
+ *
+ * MSGMNB is the default size of a new message queue. Non-root tasks can
+ * decrease the size with msgctl(IPC_SET), root tasks
+ * (actually: CAP_SYS_RESOURCE) can both increase and decrease the queue
+ * size. The optimal value is application dependent.
+ * 16384 is used because it was always used (since 0.99.10)
+ *
+ * MAXMAX is the maximum size of an individual message, it's a global
+ * (per-namespace) limit that applies for all message queues.
+ * It's set to 1/2 of MSGMNB, to ensure that at least two messages fit into
+ * the queue. This is also an arbitrary choice (since 2.6.0).
  */
-#define MSG_MEM_SCALE 32
 
-#define MSGMNI    16   /* <= IPCMNI */     /* max # of msg queue identifiers */
+#define MSGMNI 32000   /* <= IPCMNI */     /* max # of msg queue identifiers */
 #define MSGMAX  8192   /* <= INT_MAX */   /* max size of message (bytes) */
 #define MSGMNB 16384   /* <= INT_MAX */   /* default max size of a message queue */
 
diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h
index 541fce03b50c..dd73b908b2f3 100644
--- a/include/uapi/linux/sem.h
+++ b/include/uapi/linux/sem.h
@@ -63,10 +63,22 @@ struct  seminfo {
 	int semaem;
 };
 
-#define SEMMNI  128             /* <= IPCMNI  max # of semaphore identifiers */
-#define SEMMSL  250             /* <= 8 000 max num of semaphores per id */
+/*
+ * SEMMNI, SEMMSL and SEMMNS are default values which can be
+ * modified by sysctl.
+ * The values has been chosen to be larger than necessary for any
+ * known configuration.
+ *
+ * SEMOPM should not be increased beyond 1000, otherwise there is the
+ * risk that semop()/semtimedop() fails due to kernel memory fragmentation when
+ * allocating the sop array.
+ */
+
+
+#define SEMMNI  32000           /* <= IPCMNI  max # of semaphore identifiers */
+#define SEMMSL  32000           /* <= INT_MAX max num of semaphores per id */
 #define SEMMNS  (SEMMNI*SEMMSL) /* <= INT_MAX max # of semaphores in system */
-#define SEMOPM  32	        /* <= 1 000 max num of ops per semop call */
+#define SEMOPM  500	        /* <= 1 000 max num of ops per semop call */
 #define SEMVMX  32767           /* <= 32767 semaphore maximum value */
 #define SEMAEM  SEMVMX          /* adjust on exit max value */
 
diff --git a/init/Kconfig b/init/Kconfig
index b454b162d2df..2229611528db 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -979,15 +979,12 @@ config CGROUP_CPUACCT
 	  Provides a simple Resource Controller for monitoring the
 	  total CPU consumed by the tasks in a cgroup.
 
-config RESOURCE_COUNTERS
-	bool "Resource counters"
-	help
-	  This option enables controller independent resource accounting
-	  infrastructure that works with cgroups.
+config PAGE_COUNTER
+       bool
 
 config MEMCG
 	bool "Memory Resource Controller for Control Groups"
-	depends on RESOURCE_COUNTERS
+	select PAGE_COUNTER
 	select EVENTFD
 	help
 	  Provides a memory resource controller that manages both anonymous
@@ -1055,7 +1052,8 @@ config MEMCG_KMEM
 
 config CGROUP_HUGETLB
 	bool "HugeTLB Resource Controller for Control Groups"
-	depends on RESOURCE_COUNTERS && HUGETLB_PAGE
+	depends on HUGETLB_PAGE
+	select PAGE_COUNTER
 	default n
 	help
 	  Provides a cgroup Resource Controller for HugeTLB pages.
diff --git a/ipc/Makefile b/ipc/Makefile
index 9075e172e52c..86c7300ecdf5 100644
--- a/ipc/Makefile
+++ b/ipc/Makefile
@@ -3,7 +3,7 @@
 #
 
 obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o
-obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o syscall.o
+obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o syscall.o
 obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o
 obj_mq-$(CONFIG_COMPAT) += compat_mq.o
 obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y)
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index e8075b247497..8ad93c29f511 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -62,29 +62,6 @@ static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_callback_dointvec_minmax(struct ctl_table *table, int write,
-	void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table ipc_table;
-	size_t lenp_bef = *lenp;
-	int rc;
-
-	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
-
-	if (write && !rc && lenp_bef == *lenp)
-		/*
-		 * Tunable has successfully been changed by hand. Disable its
-		 * automatic adjustment. This simply requires unregistering
-		 * the notifiers that trigger recalculation.
-		 */
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-
-	return rc;
-}
-
 static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -96,54 +73,19 @@ static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 					lenp, ppos);
 }
 
-/*
- * Routine that is called when the file "auto_msgmni" has successfully been
- * written.
- * Two values are allowed:
- * 0: unregister msgmni's callback routine from the ipc namespace notifier
- *    chain. This means that msgmni won't be recomputed anymore upon memory
- *    add/remove or ipc namespace creation/removal.
- * 1: register back the callback routine.
- */
-static void ipc_auto_callback(int val)
-{
-	if (!val)
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-	else {
-		/*
-		 * Re-enable automatic recomputing only if not already
-		 * enabled.
-		 */
-		recompute_msgmni(current->nsproxy->ipc_ns);
-		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
-	}
-}
-
-static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
+static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
-	int oldval;
-	int rc;
+	int dummy = 0;
 
 	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-	oldval = *((int *)(ipc_table.data));
+	ipc_table.data = &dummy;
 
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+	if (write)
+		pr_info_once("writing to auto_msgmni has no effect");
 
-	if (write && !rc) {
-		int newval = *((int *)(ipc_table.data));
-		/*
-		 * The file "auto_msgmni" has correctly been set.
-		 * React by (un)registering the corresponding tunable, if the
-		 * value has changed.
-		 */
-		if (newval != oldval)
-			ipc_auto_callback(newval);
-	}
-
-	return rc;
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 }
 
 #else
@@ -151,8 +93,7 @@ static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
 #define proc_ipc_dointvec	   NULL
 #define proc_ipc_dointvec_minmax   NULL
 #define proc_ipc_dointvec_minmax_orphans   NULL
-#define proc_ipc_callback_dointvec_minmax  NULL
-#define proc_ipcauto_dointvec_minmax NULL
+#define proc_ipc_auto_msgmni	   NULL
 #endif
 
 static int zero;
@@ -204,11 +145,20 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmni,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_callback_dointvec_minmax,
+		.proc_handler	= proc_ipc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &int_max,
 	},
 	{
+		.procname	= "auto_msgmni",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_auto_msgmni,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
 		.procname	=  "msgmnb",
 		.data		= &init_ipc_ns.msg_ctlmnb,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmnb),
@@ -224,15 +174,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec,
 	},
-	{
-		.procname	= "auto_msgmni",
-		.data		= &init_ipc_ns.auto_msgmni,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_ipcauto_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	{
 		.procname	= "sem_next_id",
diff --git a/ipc/ipcns_notifier.c b/ipc/ipcns_notifier.c
deleted file mode 100644
index b9b31a4f77e1..000000000000
--- a/ipc/ipcns_notifier.c
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * linux/ipc/ipcns_notifier.c
- * Copyright (C) 2007 BULL SA. Nadia Derbey
- *
- * Notification mechanism for ipc namespaces:
- * The callback routine registered in the memory chain invokes the ipcns
- * notifier chain with the IPCNS_MEMCHANGED event.
- * Each callback routine registered in the ipcns namespace recomputes msgmni
- * for the owning namespace.
- */
-
-#include <linux/msg.h>
-#include <linux/rcupdate.h>
-#include <linux/notifier.h>
-#include <linux/nsproxy.h>
-#include <linux/ipc_namespace.h>
-
-#include "util.h"
-
-
-
-static BLOCKING_NOTIFIER_HEAD(ipcns_chain);
-
-
-static int ipcns_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	struct ipc_namespace *ns;
-
-	switch (action) {
-	case IPCNS_MEMCHANGED:   /* amount of lowmem has changed */
-	case IPCNS_CREATED:
-	case IPCNS_REMOVED:
-		/*
-		 * It's time to recompute msgmni
-		 */
-		ns = container_of(self, struct ipc_namespace, ipcns_nb);
-		/*
-		 * No need to get a reference on the ns: the 1st job of
-		 * free_ipc_ns() is to unregister the callback routine.
-		 * blocking_notifier_chain_unregister takes the wr lock to do
-		 * it.
-		 * When this callback routine is called the rd lock is held by
-		 * blocking_notifier_call_chain.
-		 * So the ipc ns cannot be freed while we are here.
-		 */
-		recompute_msgmni(ns);
-		break;
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-int register_ipcns_notifier(struct ipc_namespace *ns)
-{
-	int rc;
-
-	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
-	ns->ipcns_nb.notifier_call = ipcns_callback;
-	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
-	rc = blocking_notifier_chain_register(&ipcns_chain, &ns->ipcns_nb);
-	if (!rc)
-		ns->auto_msgmni = 1;
-	return rc;
-}
-
-int cond_register_ipcns_notifier(struct ipc_namespace *ns)
-{
-	int rc;
-
-	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
-	ns->ipcns_nb.notifier_call = ipcns_callback;
-	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
-	rc = blocking_notifier_chain_cond_register(&ipcns_chain,
-							&ns->ipcns_nb);
-	if (!rc)
-		ns->auto_msgmni = 1;
-	return rc;
-}
-
-void unregister_ipcns_notifier(struct ipc_namespace *ns)
-{
-	blocking_notifier_chain_unregister(&ipcns_chain, &ns->ipcns_nb);
-	ns->auto_msgmni = 0;
-}
-
-int ipcns_notify(unsigned long val)
-{
-	return blocking_notifier_call_chain(&ipcns_chain, val, NULL);
-}
diff --git a/ipc/msg.c b/ipc/msg.c
index c5d8e3749985..a7261d5cbc89 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -989,43 +989,12 @@ SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
 	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
 }
 
-/*
- * Scale msgmni with the available lowmem size: the memory dedicated to msg
- * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
- * Also take into account the number of nsproxies created so far.
- * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
- */
-void recompute_msgmni(struct ipc_namespace *ns)
-{
-	struct sysinfo i;
-	unsigned long allowed;
-	int nb_ns;
-
-	si_meminfo(&i);
-	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
-		/ MSGMNB;
-	nb_ns = atomic_read(&nr_ipc_ns);
-	allowed /= nb_ns;
-
-	if (allowed < MSGMNI) {
-		ns->msg_ctlmni = MSGMNI;
-		return;
-	}
-
-	if (allowed > IPCMNI / nb_ns) {
-		ns->msg_ctlmni = IPCMNI / nb_ns;
-		return;
-	}
-
-	ns->msg_ctlmni = allowed;
-}
 
 void msg_init_ns(struct ipc_namespace *ns)
 {
 	ns->msg_ctlmax = MSGMAX;
 	ns->msg_ctlmnb = MSGMNB;
-
-	recompute_msgmni(ns);
+	ns->msg_ctlmni = MSGMNI;
 
 	atomic_set(&ns->msg_bytes, 0);
 	atomic_set(&ns->msg_hdrs, 0);
@@ -1069,9 +1038,6 @@ void __init msg_init(void)
 {
 	msg_init_ns(&init_ipc_ns);
 
-	printk(KERN_INFO "msgmni has been set to %d\n",
-		init_ipc_ns.msg_ctlmni);
-
 	ipc_init_proc_interface("sysvipc/msg",
 				"       key      msqid perms      cbytes       qnum lspid lrpid   uid   gid  cuid  cgid      stime      rtime      ctime\n",
 				IPC_MSG_IDS, sysvipc_msg_proc_show);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index b54468e48e32..1a3ffd40356e 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -45,14 +45,6 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	msg_init_ns(ns);
 	shm_init_ns(ns);
 
-	/*
-	 * msgmni has already been computed for the new ipc ns.
-	 * Thus, do the ipcns creation notification before registering that
-	 * new ipcns in the chain.
-	 */
-	ipcns_notify(IPCNS_CREATED);
-	register_ipcns_notifier(ns);
-
 	ns->user_ns = get_user_ns(user_ns);
 
 	return ns;
@@ -99,25 +91,11 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 
 static void free_ipc_ns(struct ipc_namespace *ns)
 {
-	/*
-	 * Unregistering the hotplug notifier at the beginning guarantees
-	 * that the ipc namespace won't be freed while we are inside the
-	 * callback routine. Since the blocking_notifier_chain_XXX routines
-	 * hold a rw lock on the notifier list, unregister_ipcns_notifier()
-	 * won't take the rw lock before blocking_notifier_call_chain() has
-	 * released the rd lock.
-	 */
-	unregister_ipcns_notifier(ns);
 	sem_exit_ns(ns);
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
 	atomic_dec(&nr_ipc_ns);
 
-	/*
-	 * Do the ipcns removal notification after decrementing nr_ipc_ns in
-	 * order to have a correct value when recomputing msgmni.
-	 */
-	ipcns_notify(IPCNS_REMOVED);
 	put_user_ns(ns->user_ns);
 	proc_free_inum(ns->proc_inum);
 	kfree(ns);
diff --git a/ipc/sem.c b/ipc/sem.c
index 454f6c6020a8..b9dc34498b00 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -326,10 +326,17 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 
 		/* Then check that the global lock is free */
 		if (!spin_is_locked(&sma->sem_perm.lock)) {
-			/* spin_is_locked() is not a memory barrier */
-			smp_mb();
+			/*
+			 * The ipc object lock check must be visible on all
+			 * cores before rechecking the complex count.  Otherwise
+			 * we can race with  another thread that does:
+			 *	complex_count++;
+			 *	spin_unlock(sem_perm.lock);
+			 */
+			smp_rmb();
 
-			/* Now repeat the test of complex_count:
+			/*
+			 * Now repeat the test of complex_count:
 			 * It can't change anymore until we drop sem->lock.
 			 * Thus: if is now 0, then it will stay 0.
 			 */
diff --git a/ipc/util.c b/ipc/util.c
index 88adc329888c..106bed0378ab 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -71,44 +71,6 @@ struct ipc_proc_iface {
 	int (*show)(struct seq_file *, void *);
 };
 
-static void ipc_memory_notifier(struct work_struct *work)
-{
-	ipcns_notify(IPCNS_MEMCHANGED);
-}
-
-static int ipc_memory_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier);
-
-	switch (action) {
-	case MEM_ONLINE:    /* memory successfully brought online */
-	case MEM_OFFLINE:   /* or offline: it's time to recompute msgmni */
-		/*
-		 * This is done by invoking the ipcns notifier chain with the
-		 * IPC_MEMCHANGED event.
-		 * In order not to keep the lock on the hotplug memory chain
-		 * for too long, queue a work item that will, when waken up,
-		 * activate the ipcns notification chain.
-		 */
-		schedule_work(&ipc_memory_wq);
-		break;
-	case MEM_GOING_ONLINE:
-	case MEM_GOING_OFFLINE:
-	case MEM_CANCEL_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block ipc_memory_nb = {
-	.notifier_call = ipc_memory_callback,
-	.priority = IPC_CALLBACK_PRI,
-};
-
 /**
  * ipc_init - initialise ipc subsystem
  *
@@ -124,8 +86,6 @@ static int __init ipc_init(void)
 	sem_init();
 	msg_init();
 	shm_init();
-	register_hotmemory_notifier(&ipc_memory_nb);
-	register_ipcns_notifier(&init_ipc_ns);
 	return 0;
 }
 device_initcall(ipc_init);
diff --git a/kernel/Makefile b/kernel/Makefile
index dc5c77544fd6..1ef793b4c0ed 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -57,7 +57,6 @@ obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
-obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
 obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index a23bcba7b594..07ce18ca71e0 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -473,6 +473,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 	int cpu;
 	int trace_on = 0;
 	int online_cpus = num_online_cpus();
+	u64 time_left;
 
 	kgdb_info[ks->cpu].enter_kgdb++;
 	kgdb_info[ks->cpu].exception_state |= exception_state;
@@ -597,9 +598,13 @@ return_normal:
 	/*
 	 * Wait for the other CPUs to be notified and be waiting for us:
 	 */
-	while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) +
-				atomic_read(&slaves_in_kgdb)) != online_cpus)
+	time_left = loops_per_jiffy * HZ;
+	while (kgdb_do_roundup && --time_left &&
+	       (atomic_read(&masters_in_kgdb) + atomic_read(&slaves_in_kgdb)) !=
+		   online_cpus)
 		cpu_relax();
+	if (!time_left)
+		pr_crit("KGDB: Timed out waiting for secondary CPUs.\n");
 
 	/*
 	 * At this point the primary processor is completely
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index 8859ca34dcfe..15e1a7af5dd0 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -129,6 +129,10 @@ int kdb_stub(struct kgdb_state *ks)
 		ks->pass_exception = 1;
 		KDB_FLAG_SET(CATASTROPHIC);
 	}
+	/* set CATASTROPHIC if the system contains unresponsive processors */
+	for_each_online_cpu(i)
+		if (!kgdb_info[i].enter_kgdb)
+			KDB_FLAG_SET(CATASTROPHIC);
 	if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) {
 		KDB_STATE_CLEAR(SSBPT);
 		KDB_STATE_CLEAR(DOING_SS);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 379650b984f8..0633e784f8cd 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2157,6 +2157,8 @@ static void kdb_cpu_status(void)
 	for (start_cpu = -1, i = 0; i < NR_CPUS; i++) {
 		if (!cpu_online(i)) {
 			state = 'F';	/* cpu is offline */
+		} else if (!kgdb_info[i].enter_kgdb) {
+			state = 'D';	/* cpu is online but unresponsive */
 		} else {
 			state = ' ';	/* cpu is responding to kdb */
 			if (kdb_task_state_char(KDB_TSK(i)) == 'I')
@@ -2210,7 +2212,7 @@ static int kdb_cpu(int argc, const char **argv)
 	/*
 	 * Validate cpunum
 	 */
-	if ((cpunum > NR_CPUS) || !cpu_online(cpunum))
+	if ((cpunum > NR_CPUS) || !kgdb_info[cpunum].enter_kgdb)
 		return KDB_BADCPUNUM;
 
 	dbg_switch_cpu = cpunum;
diff --git a/kernel/freezer.c b/kernel/freezer.c
index aa6a8aadb911..190d667f4e12 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -45,13 +45,28 @@ bool freezing_slow_path(struct task_struct *p)
 	if (pm_nosig_freezing || cgroup_freezing(p))
 		return true;
 
-	if (pm_freezing && !(p->flags & PF_KTHREAD))
+	if (!(p->flags & PF_KTHREAD))
 		return true;
 
 	return false;
 }
 EXPORT_SYMBOL(freezing_slow_path);
 
+static bool should_thaw_current(bool check_kthr_stop)
+{
+	if (!freezing(current))
+		return true;
+
+	if (check_kthr_stop && kthread_should_stop())
+		return true;
+
+	/* It might not be safe to check TIF_MEMDIE for pm freeze. */
+	if (cgroup_freezing(current) && test_thread_flag(TIF_MEMDIE))
+		return true;
+
+	return false;
+}
+
 /* Refrigerator is place where frozen processes are stored :-). */
 bool __refrigerator(bool check_kthr_stop)
 {
@@ -67,8 +82,7 @@ bool __refrigerator(bool check_kthr_stop)
 
 		spin_lock_irq(&freezer_lock);
 		current->flags |= PF_FROZEN;
-		if (!freezing(current) ||
-		    (check_kthr_stop && kthread_should_stop()))
+		if (should_thaw_current(check_kthr_stop))
 			current->flags &= ~PF_FROZEN;
 		spin_unlock_irq(&freezer_lock);
 
@@ -147,12 +161,6 @@ void __thaw_task(struct task_struct *p)
 {
 	unsigned long flags;
 
-	/*
-	 * Clear freezing and kick @p if FROZEN.  Clearing is guaranteed to
-	 * be visible to @p as waking up implies wmb.  Waking up inside
-	 * freezer_lock also prevents wakeups from leaking outside
-	 * refrigerator.
-	 */
 	spin_lock_irqsave(&freezer_lock, flags);
 	if (frozen(p))
 		wake_up_process(p);
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index 7ad56807defd..6ca0b99e5f0a 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -32,10 +32,13 @@ config GCOV_KERNEL
 	Note that the debugfs filesystem has to be mounted to access
 	profiling data.
 
+config ARCH_HAS_GCOV_PROFILE_ALL
+	def_bool n
+
 config GCOV_PROFILE_ALL
 	bool "Profile entire Kernel"
 	depends on GCOV_KERNEL
-	depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM
+	depends on ARCH_HAS_GCOV_PROFILE_ALL
 	default n
 	---help---
 	This options activates profiling for the entire kernel.
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 2abf9f6e9a61..9a8a01abbaed 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -600,7 +600,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 	if (!kexec_on_panic) {
 		image->swap_page = kimage_alloc_control_pages(image, 0);
 		if (!image->swap_page) {
-			pr_err(KERN_ERR "Could not allocate swap buffer\n");
+			pr_err("Could not allocate swap buffer\n");
 			goto out_free_control_pages;
 		}
 	}
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 7b323221b9ee..e88bf00a03c0 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -118,6 +118,7 @@ static int try_to_freeze_tasks(bool user_only)
 int freeze_processes(void)
 {
 	int error;
+	int oom_kills_saved;
 
 	error = __usermodehelper_disable(UMH_FREEZING);
 	if (error)
@@ -132,12 +133,40 @@ int freeze_processes(void)
 	pm_wakeup_clear();
 	printk("Freezing user space processes ... ");
 	pm_freezing = true;
+	oom_kills_saved = oom_kills_count();
 	error = try_to_freeze_tasks(true);
 	if (!error) {
-		printk("done.");
 		__usermodehelper_set_disable_depth(UMH_DISABLED);
 		oom_killer_disable();
+
+		/*
+		 * There was a OOM kill while we were freezing tasks
+		 * and the killed task might be still on the way out
+		 * so we have to double check for race.
+		 */
+		if (oom_kills_count() != oom_kills_saved) {
+			struct task_struct *g, *p;
+
+			read_lock(&tasklist_lock);
+			do_each_thread(g, p) {
+				if (p == current || freezer_should_skip(p) ||
+				    frozen(p))
+					continue;
+				error = -EBUSY;
+				break;
+			} while_each_thread(g, p);
+			read_unlock(&tasklist_lock);
+
+			if (error) {
+				__usermodehelper_set_disable_depth(UMH_ENABLED);
+				oom_killer_enable();
+				printk("OOM in progress. ");
+				goto done;
+			}
+		}
+		printk("done.");
 	}
+done:
 	printk("\n");
 	BUG_ON(in_atomic());
 
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
deleted file mode 100644
index e791130f85a7..000000000000
--- a/kernel/res_counter.c
+++ /dev/null
@@ -1,211 +0,0 @@
-/*
- * resource cgroups
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- */
-
-#include <linux/types.h>
-#include <linux/parser.h>
-#include <linux/fs.h>
-#include <linux/res_counter.h>
-#include <linux/uaccess.h>
-#include <linux/mm.h>
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent)
-{
-	spin_lock_init(&counter->lock);
-	counter->limit = RES_COUNTER_MAX;
-	counter->soft_limit = RES_COUNTER_MAX;
-	counter->parent = parent;
-}
-
-static u64 res_counter_uncharge_locked(struct res_counter *counter,
-				       unsigned long val)
-{
-	if (WARN_ON(counter->usage < val))
-		val = counter->usage;
-
-	counter->usage -= val;
-	return counter->usage;
-}
-
-static int res_counter_charge_locked(struct res_counter *counter,
-				     unsigned long val, bool force)
-{
-	int ret = 0;
-
-	if (counter->usage + val > counter->limit) {
-		counter->failcnt++;
-		ret = -ENOMEM;
-		if (!force)
-			return ret;
-	}
-
-	counter->usage += val;
-	if (counter->usage > counter->max_usage)
-		counter->max_usage = counter->usage;
-	return ret;
-}
-
-static int __res_counter_charge(struct res_counter *counter, unsigned long val,
-				struct res_counter **limit_fail_at, bool force)
-{
-	int ret, r;
-	unsigned long flags;
-	struct res_counter *c, *u;
-
-	r = ret = 0;
-	*limit_fail_at = NULL;
-	local_irq_save(flags);
-	for (c = counter; c != NULL; c = c->parent) {
-		spin_lock(&c->lock);
-		r = res_counter_charge_locked(c, val, force);
-		spin_unlock(&c->lock);
-		if (r < 0 && !ret) {
-			ret = r;
-			*limit_fail_at = c;
-			if (!force)
-				break;
-		}
-	}
-
-	if (ret < 0 && !force) {
-		for (u = counter; u != c; u = u->parent) {
-			spin_lock(&u->lock);
-			res_counter_uncharge_locked(u, val);
-			spin_unlock(&u->lock);
-		}
-	}
-	local_irq_restore(flags);
-
-	return ret;
-}
-
-int res_counter_charge(struct res_counter *counter, unsigned long val,
-			struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, false);
-}
-
-int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
-			      struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, true);
-}
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val)
-{
-	unsigned long flags;
-	struct res_counter *c;
-	u64 ret = 0;
-
-	local_irq_save(flags);
-	for (c = counter; c != top; c = c->parent) {
-		u64 r;
-		spin_lock(&c->lock);
-		r = res_counter_uncharge_locked(c, val);
-		if (c == counter)
-			ret = r;
-		spin_unlock(&c->lock);
-	}
-	local_irq_restore(flags);
-	return ret;
-}
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val)
-{
-	return res_counter_uncharge_until(counter, NULL, val);
-}
-
-static inline unsigned long long *
-res_counter_member(struct res_counter *counter, int member)
-{
-	switch (member) {
-	case RES_USAGE:
-		return &counter->usage;
-	case RES_MAX_USAGE:
-		return &counter->max_usage;
-	case RES_LIMIT:
-		return &counter->limit;
-	case RES_FAILCNT:
-		return &counter->failcnt;
-	case RES_SOFT_LIMIT:
-		return &counter->soft_limit;
-	};
-
-	BUG();
-	return NULL;
-}
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *userbuf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *st_buf))
-{
-	unsigned long long *val;
-	char buf[64], *s;
-
-	s = buf;
-	val = res_counter_member(counter, member);
-	if (read_strategy)
-		s += read_strategy(*val, s);
-	else
-		s += sprintf(s, "%llu\n", *val);
-	return simple_read_from_buffer((void __user *)userbuf, nbytes,
-			pos, buf, s - buf);
-}
-
-#if BITS_PER_LONG == 32
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	unsigned long flags;
-	u64 ret;
-
-	spin_lock_irqsave(&counter->lock, flags);
-	ret = *res_counter_member(counter, member);
-	spin_unlock_irqrestore(&counter->lock, flags);
-
-	return ret;
-}
-#else
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	return *res_counter_member(counter, member);
-}
-#endif
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *resp)
-{
-	char *end;
-	unsigned long long res;
-
-	/* return RES_COUNTER_MAX(unlimited) if "-1" is specified */
-	if (*buf == '-') {
-		int rc = kstrtoull(buf + 1, 10, &res);
-
-		if (rc)
-			return rc;
-		if (res != 1)
-			return -EINVAL;
-		*resp = RES_COUNTER_MAX;
-		return 0;
-	}
-
-	res = memparse(buf, &end);
-	if (*end != '\0')
-		return -EINVAL;
-
-	if (PAGE_ALIGN(res) >= res)
-		res = PAGE_ALIGN(res);
-	else
-		res = RES_COUNTER_MAX;
-
-	*resp = res;
-
-	return 0;
-}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4aada6d9fe74..5623845f9060 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -257,7 +257,7 @@ static struct ctl_table sysctl_base_table[] = {
 		.mode		= 0555,
 		.child		= dev_table,
 	},
-	{ }
+	{ .procname = NULL }
 };
 
 #ifdef CONFIG_SCHED_DEBUG
@@ -1103,7 +1103,7 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-	{ }
+	{ .procname = NULL }
 };
 
 static struct ctl_table vm_table[] = {
@@ -1485,12 +1485,12 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
-	{ }
+	{ .procname = NULL }
 };
 
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 static struct ctl_table binfmt_misc_table[] = {
-	{ }
+	{ .procname = NULL }
 };
 #endif
 
@@ -1658,7 +1658,7 @@ static struct ctl_table fs_table[] = {
 		.proc_handler	= &pipe_proc_fn,
 		.extra1		= &pipe_min_size,
 	},
-	{ }
+	{ .procname = NULL }
 };
 
 static struct ctl_table debug_table[] = {
@@ -1682,11 +1682,11 @@ static struct ctl_table debug_table[] = {
 		.extra2		= &one,
 	},
 #endif
-	{ }
+	{ .procname = NULL }
 };
 
 static struct ctl_table dev_table[] = {
-	{ }
+	{ .procname = NULL }
 };
 
 int __init sysctl_init(void)
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 42b463ad90f2..a81083797e97 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -73,7 +73,7 @@ static DEFINE_SPINLOCK(hash_lock);
  * SIGEV values.  Here we put out an error if this assumption fails.
  */
 #if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \
-                       ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD))
+		       ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD))
 #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
 #endif
 
@@ -254,7 +254,8 @@ static int posix_get_monotonic_coarse(clockid_t which_clock,
 	return 0;
 }
 
-static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
+static int posix_get_coarse_res(const clockid_t which_clock,
+				struct timespec *tp)
 {
 	*tp = ktime_to_timespec(KTIME_LOW_RES);
 	return 0;
@@ -335,14 +336,16 @@ static __init int init_posix_timers(void)
 	posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
 	posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
 	posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
-	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
-	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+	posix_timers_register_clock(CLOCK_REALTIME_COARSE,
+				    &clock_realtime_coarse);
+	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE,
+				    &clock_monotonic_coarse);
 	posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
 	posix_timers_register_clock(CLOCK_TAI, &clock_tai);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
-					sizeof (struct k_itimer), 0, SLAB_PANIC,
-					NULL);
+					       sizeof(struct k_itimer), 0,
+					       SLAB_PANIC, NULL);
 	return 0;
 }
 
@@ -496,11 +499,11 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 	return ret;
 }
 
-static struct pid *good_sigevent(sigevent_t * event)
+static struct pid *good_sigevent(sigevent_t *event)
 {
 	struct task_struct *rtn = current->group_leader;
 
-	if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
+	if ((event->sigev_notify & SIGEV_THREAD_ID) &&
 		(!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
 		 !same_thread_group(rtn, current) ||
 		 (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
@@ -517,18 +520,18 @@ void posix_timers_register_clock(const clockid_t clock_id,
 				 struct k_clock *new_clock)
 {
 	if ((unsigned) clock_id >= MAX_CLOCKS) {
-		printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
+		pr_warn("POSIX clock register failed for clock_id %d\n",
 		       clock_id);
 		return;
 	}
 
 	if (!new_clock->clock_get) {
-		printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n",
+		pr_warn("POSIX clock id %d lacks clock_get()\n",
 		       clock_id);
 		return;
 	}
 	if (!new_clock->clock_getres) {
-		printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n",
+		pr_warn("POSIX clock id %d lacks clock_getres()\n",
 		       clock_id);
 		return;
 	}
@@ -537,7 +540,7 @@ void posix_timers_register_clock(const clockid_t clock_id,
 }
 EXPORT_SYMBOL_GPL(posix_timers_register_clock);
 
-static struct k_itimer * alloc_posix_timer(void)
+static struct k_itimer *alloc_posix_timer(void)
 {
 	struct k_itimer *tmr;
 	tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL);
@@ -624,7 +627,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 	new_timer->it_overrun = -1;
 
 	if (timer_event_spec) {
-		if (copy_from_user(&event, timer_event_spec, sizeof (event))) {
+		if (copy_from_user(&event, timer_event_spec, sizeof(event))) {
 			error = -EFAULT;
 			goto out;
 		}
@@ -649,7 +652,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 	new_timer->sigq->info.si_code  = SI_TIMER;
 
 	if (copy_to_user(created_timer_id,
-			 &new_timer_id, sizeof (new_timer_id))) {
+			 &new_timer_id, sizeof(new_timer_id))) {
 		error = -EFAULT;
 		goto out;
 	}
@@ -750,7 +753,8 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
 	 */
 	if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
 	    (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
-		timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
+		timr->it_overrun += (unsigned int) hrtimer_forward(timer, now,
+								   iv);
 
 	remaining = ktime_sub(hrtimer_get_expires(timer), now);
 	/* Return 0 only, when the timer is expired and not pending */
@@ -787,7 +791,7 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 
 	unlock_timer(timr, flags);
 
-	if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
+	if (!ret && copy_to_user(setting, &cur_setting, sizeof(cur_setting)))
 		return -EFAULT;
 
 	return ret;
@@ -839,7 +843,7 @@ common_timer_set(struct k_itimer *timr, int flags,
 	if (hrtimer_try_to_cancel(timer) < 0)
 		return TIMER_RETRY;
 
-	timr->it_requeue_pending = (timr->it_requeue_pending + 2) & 
+	timr->it_requeue_pending = (timr->it_requeue_pending + 2) &
 		~REQUEUE_PENDING;
 	timr->it_overrun_last = 0;
 
@@ -859,9 +863,8 @@ common_timer_set(struct k_itimer *timr, int flags,
 	/* SIGEV_NONE timers are not queued ! See common_timer_get */
 	if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
 		/* Setup correct expiry time for relative timers */
-		if (mode == HRTIMER_MODE_REL) {
+		if (mode == HRTIMER_MODE_REL)
 			hrtimer_add_expires(timer, timer->base->get_time());
-		}
 		return 0;
 	}
 
@@ -884,7 +887,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	if (!new_setting)
 		return -EINVAL;
 
-	if (copy_from_user(&new_spec, new_setting, sizeof (new_spec)))
+	if (copy_from_user(&new_spec, new_setting, sizeof(new_spec)))
 		return -EFAULT;
 
 	if (!timespec_valid(&new_spec.it_interval) ||
@@ -903,12 +906,12 @@ retry:
 
 	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
-		rtn = NULL;	// We already got the old time...
+		rtn = NULL;	/* We already got the old time... */
 		goto retry;
 	}
 
 	if (old_setting && !error &&
-	    copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
+	    copy_to_user(old_setting, &old_spec, sizeof(old_spec)))
 		error = -EFAULT;
 
 	return error;
@@ -1010,14 +1013,14 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 	if (!kc || !kc->clock_set)
 		return -EINVAL;
 
-	if (copy_from_user(&new_tp, tp, sizeof (*tp)))
+	if (copy_from_user(&new_tp, tp, sizeof(*tp)))
 		return -EFAULT;
 
 	return kc->clock_set(which_clock, &new_tp);
 }
 
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
-		struct timespec __user *,tp)
+		struct timespec __user *, tp)
 {
 	struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec kernel_tp;
@@ -1028,7 +1031,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 
 	error = kc->clock_get(which_clock, &kernel_tp);
 
-	if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
+	if (!error && copy_to_user(tp, &kernel_tp, sizeof(kernel_tp)))
 		error = -EFAULT;
 
 	return error;
@@ -1069,7 +1072,7 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
 
 	error = kc->clock_getres(which_clock, &rtn_tp);
 
-	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
+	if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof(rtn_tp)))
 		error = -EFAULT;
 
 	return error;
@@ -1098,7 +1101,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (!kc->nsleep)
 		return -ENANOSLEEP_NOTSUP;
 
-	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
+	if (copy_from_user(&t, rqtp, sizeof(struct timespec)))
 		return -EFAULT;
 
 	if (!timespec_valid(&t))
diff --git a/lib/Kconfig b/lib/Kconfig
index 54cf309a92a5..2faf7b2de5b3 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -180,6 +180,13 @@ 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 7512dc978f18..84000ec74869 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -72,6 +72,7 @@ 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_ZLIB_INFLATE) += zlib_inflate/
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/vsprintf.c b/lib/vsprintf.c
index ec337f64f52d..d57551c031f4 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1240,6 +1240,21 @@ char *address_val(char *buf, char *end, const void *addr,
 	return number(buf, end, num, 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;
 
 /*
@@ -1318,6 +1333,7 @@ int kptr_restrict __read_mostly;
  *           (default assumed to be phys_addr_t, passed by reference)
  * - 'd[234]' For a dentry name (optionally 2-4 last components)
  * - 'D[234]' Same as 'd' but for a struct file
+ * - '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
@@ -1329,7 +1345,7 @@ 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.
@@ -1459,6 +1475,8 @@ 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/Makefile b/mm/Makefile
index 8405eb0023a9..6d9f40e922f7 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
+obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
 obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
diff --git a/mm/compaction.c b/mm/compaction.c
index edba18aed173..e6e740506c88 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -195,16 +195,12 @@ static void update_pageblock_skip(struct compact_control *cc,
 
 	/* Update where async and sync compaction should restart */
 	if (migrate_scanner) {
-		if (cc->finished_update_migrate)
-			return;
 		if (pfn > zone->compact_cached_migrate_pfn[0])
 			zone->compact_cached_migrate_pfn[0] = pfn;
 		if (cc->mode != MIGRATE_ASYNC &&
 		    pfn > zone->compact_cached_migrate_pfn[1])
 			zone->compact_cached_migrate_pfn[1] = pfn;
 	} else {
-		if (cc->finished_update_free)
-			return;
 		if (pfn < zone->compact_cached_free_pfn)
 			zone->compact_cached_free_pfn = pfn;
 	}
@@ -705,7 +701,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 
 isolate_success:
-		cc->finished_update_migrate = true;
 		list_add(&page->lru, migratelist);
 		cc->nr_migratepages++;
 		nr_isolated++;
@@ -784,6 +779,9 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 			cc->nr_migratepages = 0;
 			break;
 		}
+
+		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+			break;
 	}
 	acct_isolated(cc->zone, cc);
 
@@ -876,15 +874,6 @@ static void isolate_freepages(struct compact_control *cc)
 				block_start_pfn - pageblock_nr_pages;
 
 		/*
-		 * Set a flag that we successfully isolated in this pageblock.
-		 * In the next loop iteration, zone->compact_cached_free_pfn
-		 * will not be updated and thus it will effectively contain the
-		 * highest pageblock we isolated pages from.
-		 */
-		if (isolated)
-			cc->finished_update_free = true;
-
-		/*
 		 * isolate_freepages_block() might have aborted due to async
 		 * compaction being contended
 		 */
@@ -1069,9 +1058,9 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 
 	/* Compaction run is not finished if the watermark is not met */
 	watermark = low_wmark_pages(zone);
-	watermark += (1 << cc->order);
 
-	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
+							cc->alloc_flags))
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
@@ -1097,7 +1086,8 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
-unsigned long compaction_suitable(struct zone *zone, int order)
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
 	unsigned long watermark;
@@ -1134,7 +1124,7 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 		return COMPACT_SKIPPED;
 
 	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
-	    0, 0))
+	    classzone_idx, alloc_flags))
 		return COMPACT_PARTIAL;
 
 	return COMPACT_CONTINUE;
@@ -1148,7 +1138,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 
-	ret = compaction_suitable(zone, cc->order);
+	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
+							cc->classzone_idx);
 	switch (ret) {
 	case COMPACT_PARTIAL:
 	case COMPACT_SKIPPED:
@@ -1191,6 +1182,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	while ((ret = compact_finished(zone, cc, migratetype)) ==
 						COMPACT_CONTINUE) {
 		int err;
+		unsigned long last_migrated_pfn = 0;
 
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
@@ -1199,7 +1191,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			cc->nr_migratepages = 0;
 			goto out;
 		case ISOLATE_NONE:
-			continue;
+			/*
+			 * We haven't isolated and migrated anything, but
+			 * there might still be unflushed migrations from
+			 * previous cc->order aligned block.
+			 */
+			goto check_drain;
 		case ISOLATE_SUCCESS:
 			;
 		}
@@ -1224,6 +1221,39 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 				goto out;
 			}
 		}
+
+		/*
+		 * Record where we have freed pages by migration and not yet
+		 * flushed them to buddy allocator. Subtract 1, because often
+		 * we finish a pageblock and migrate_pfn points to the first
+		 * page* of the next one. In that case we want the drain below
+		 * to happen immediately.
+		 */
+		if (!last_migrated_pfn)
+			last_migrated_pfn = cc->migrate_pfn - 1;
+
+check_drain:
+		/*
+		 * Have we moved away from the previous cc->order aligned block
+		 * where we migrated from? If yes, flush the pages that were
+		 * freed, so that they can merge and compact_finished() can
+		 * detect immediately if allocation should succeed.
+		 */
+		if (cc->order > 0 && last_migrated_pfn) {
+			int cpu;
+			unsigned long current_block_start =
+				cc->migrate_pfn & ~((1UL << cc->order) - 1);
+
+			if (last_migrated_pfn < current_block_start) {
+				cpu = get_cpu();
+				lru_add_drain_cpu(cpu);
+				drain_local_pages(zone);
+				put_cpu();
+				/* No more flushing until we migrate again */
+				last_migrated_pfn = 0;
+			}
+		}
+
 	}
 
 out:
@@ -1237,7 +1267,8 @@ out:
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
+		int alloc_flags, int classzone_idx)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1247,6 +1278,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = mode,
+		.alloc_flags = alloc_flags,
+		.classzone_idx = classzone_idx,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1271,14 +1304,13 @@ int sysctl_extfrag_threshold = 500;
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that determines if compaction was aborted due to
  *	       need_resched() or lock contention
- * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1286,7 +1318,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_DEFERRED;
-	int alloc_flags = 0;
 	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
 
 	*contended = COMPACT_CONTENDED_NONE;
@@ -1295,10 +1326,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
-#ifdef CONFIG_CMA
-	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
@@ -1309,7 +1336,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-							&zone_contended);
+				&zone_contended, alloc_flags, classzone_idx);
 		rc = max(status, rc);
 		/*
 		 * It takes at least one zone that wasn't lock contended
@@ -1318,9 +1345,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
-		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags)) {
-			*candidate_zone = zone;
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
+					classzone_idx, alloc_flags)) {
 			/*
 			 * We think the allocation will succeed in this zone,
 			 * but it is not certain, hence the false. The caller
@@ -1342,7 +1368,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			goto break_loop;
 		}
 
-		if (mode != MIGRATE_ASYNC) {
+		if (mode != MIGRATE_ASYNC && status == COMPACT_COMPLETE) {
 			/*
 			 * We think that allocation won't succeed in this zone
 			 * so we defer compaction there. If it ends up
diff --git a/mm/gup.c b/mm/gup.c
index cd62c8c90d4a..13c560ef9ddf 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -786,65 +786,31 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 }
 #endif /* __HAVE_ARCH_PTE_SPECIAL */
 
-static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
+int gup_huge_pte(pte_t orig, pte_t *ptep, unsigned long addr,
+		 unsigned long sz, unsigned long end, int write,
+		 struct page **pages, int *nr)
 {
-	struct page *head, *page, *tail;
 	int refs;
+	unsigned long pte_end;
+	struct page *head, *page, *tail;
 
-	if (write && !pmd_write(orig))
-		return 0;
-
-	refs = 0;
-	head = pmd_page(orig);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	tail = page;
-	do {
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
 
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
+	if (write && !pte_write(orig))
 		return 0;
-	}
 
-	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+	if (!pte_present(orig))
 		return 0;
-	}
 
-	/*
-	 * Any tail pages need their mapcount reference taken before we
-	 * return. (This allows the THP code to bump their ref count when
-	 * they are split into base pages).
-	 */
-	while (refs--) {
-		if (PageTail(tail))
-			get_huge_page_tail(tail);
-		tail++;
-	}
-
-	return 1;
-}
-
-static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page, *tail;
-	int refs;
+	pte_end = (addr + sz) & ~(sz-1);
+	if (pte_end < end)
+		end = pte_end;
 
-	if (write && !pud_write(orig))
-		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(orig)));
 
 	refs = 0;
-	head = pud_page(orig);
-	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	head = pte_page(orig);
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
 	tail = page;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
@@ -859,13 +825,18 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 	}
 
-	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
+	if (unlikely(pte_val(orig) != pte_val(*ptep))) {
 		*nr -= refs;
 		while (refs--)
 			put_page(head);
 		return 0;
 	}
 
+	/*
+	 * Any tail pages need their mapcount reference taken before we
+	 * return. (This allows the THP code to bump their ref count when
+	 * they are split into base pages).
+	 */
 	while (refs--) {
 		if (PageTail(tail))
 			get_huge_page_tail(tail);
@@ -898,10 +869,19 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 			if (pmd_numa(pmd))
 				return 0;
 
-			if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
-				pages, nr))
+			if (!gup_huge_pte(__pte(pmd_val(pmd)), (pte_t *)pmdp,
+					  addr, PMD_SIZE, next,
+					  write, pages, nr))
 				return 0;
 
+		} else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
+			/*
+			 * architecture have different format for hugetlbfs
+			 * pmd format and THP pmd format
+			 */
+			if (!gup_hugepd(__hugepd(pmd_val(pmd)), addr, PMD_SHIFT,
+					next, write, pages, nr))
+				return 0;
 		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
 				return 0;
 	} while (pmdp++, addr = next, addr != end);
@@ -909,22 +889,27 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(pgdp, addr);
+	pudp = pud_offset(&pgd, addr);
 	do {
 		pud_t pud = ACCESS_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (pud_huge(pud)) {
-			if (!gup_huge_pud(pud, pudp, addr, next, write,
-					pages, nr))
+		if (unlikely(pud_huge(pud))) {
+			if (!gup_huge_pte(__pte(pud_val(pud)), (pte_t *)pudp,
+					  addr, PUD_SIZE, next,
+					  write, pages, nr))
+				return 0;
+		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
+			if (!gup_hugepd(__hugepd(pud_val(pud)), addr, PUD_SHIFT,
+					next, write, pages, nr))
 				return 0;
 		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
 			return 0;
@@ -970,10 +955,21 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	local_irq_save(flags);
 	pgdp = pgd_offset(mm, addr);
 	do {
+		pgd_t pgd = ACCESS_ONCE(*pgdp);
+
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(*pgdp))
+		if (pgd_none(pgd))
 			break;
-		else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
+		if (unlikely(pgd_huge(pgd))) {
+			if (!gup_huge_pte(__pte(pgd_val(pgd)), (pte_t *)pgdp,
+					  addr, PGDIR_SIZE, next,
+					  write, pages, &nr))
+				break;
+		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
+			if (!gup_hugepd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT,
+					next, write, pages, &nr))
+				break;
+		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);
@@ -1028,5 +1024,4 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 
 	return ret;
 }
-
 #endif /* CONFIG_HAVE_GENERIC_RCU_GUP */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 74c78aa8bc2f..de984159cf0b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -200,7 +200,7 @@ retry:
 	preempt_disable();
 	if (cmpxchg(&huge_zero_page, NULL, zero_page)) {
 		preempt_enable();
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		goto retry;
 	}
 
@@ -232,7 +232,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
-		__free_page(zero_page);
+		__free_pages(zero_page, compound_order(zero_page));
 		return HPAGE_PMD_NR;
 	}
 
@@ -803,7 +803,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return VM_FAULT_FALLBACK;
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
-	if (unlikely(khugepaged_enter(vma)))
+	if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
 		return VM_FAULT_OOM;
 	if (!(flags & FAULT_FLAG_WRITE) &&
 			transparent_hugepage_use_zero_page()) {
@@ -1970,7 +1970,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		if (unlikely(khugepaged_enter_vma_merge(vma)))
+		if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
 			return -ENOMEM;
 		break;
 	case MADV_NOHUGEPAGE:
@@ -2071,7 +2071,8 @@ int __khugepaged_enter(struct mm_struct *mm)
 	return 0;
 }
 
-int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+			       unsigned long vm_flags)
 {
 	unsigned long hstart, hend;
 	if (!vma->anon_vma)
@@ -2083,11 +2084,11 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
 	if (vma->vm_ops)
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
+	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
-		return khugepaged_enter(vma);
+		return khugepaged_enter(vma, vm_flags);
 	return 0;
 }
 
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index a67c26e0f360..037e1c00a5b7 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/page_counter.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
@@ -23,7 +24,7 @@ struct hugetlb_cgroup {
 	/*
 	 * the counter to account for hugepages from hugetlb.
 	 */
-	struct res_counter hugepage[HUGE_MAX_HSTATE];
+	struct page_counter hugepage[HUGE_MAX_HSTATE];
 };
 
 #define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
@@ -60,7 +61,7 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
 	int idx;
 
 	for (idx = 0; idx < hugetlb_max_hstate; idx++) {
-		if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
+		if (page_counter_read(&h_cg->hugepage[idx]))
 			return true;
 	}
 	return false;
@@ -79,12 +80,12 @@ hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	if (parent_h_cgroup) {
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx],
-					 &parent_h_cgroup->hugepage[idx]);
+			page_counter_init(&h_cgroup->hugepage[idx],
+					  &parent_h_cgroup->hugepage[idx]);
 	} else {
 		root_h_cgroup = h_cgroup;
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx], NULL);
+			page_counter_init(&h_cgroup->hugepage[idx], NULL);
 	}
 	return &h_cgroup->css;
 }
@@ -108,9 +109,8 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
 static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 				       struct page *page)
 {
-	int csize;
-	struct res_counter *counter;
-	struct res_counter *fail_res;
+	unsigned int nr_pages;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *page_hcg;
 	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
 
@@ -123,15 +123,15 @@ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 	if (!page_hcg || page_hcg != h_cg)
 		goto out;
 
-	csize = PAGE_SIZE << compound_order(page);
+	nr_pages = 1 << compound_order(page);
 	if (!parent) {
 		parent = root_h_cgroup;
 		/* root has no limit */
-		res_counter_charge_nofail(&parent->hugepage[idx],
-					  csize, &fail_res);
+		page_counter_charge(&parent->hugepage[idx], nr_pages);
 	}
 	counter = &h_cg->hugepage[idx];
-	res_counter_uncharge_until(counter, counter->parent, csize);
+	/* Take the pages off the local counter */
+	page_counter_cancel(counter, nr_pages);
 
 	set_hugetlb_cgroup(page, parent);
 out:
@@ -166,9 +166,8 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 				 struct hugetlb_cgroup **ptr)
 {
 	int ret = 0;
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = NULL;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		goto done;
@@ -187,7 +186,7 @@ again:
 	}
 	rcu_read_unlock();
 
-	ret = res_counter_charge(&h_cg->hugepage[idx], csize, &fail_res);
+	ret = page_counter_try_charge(&h_cg->hugepage[idx], nr_pages, &counter);
 	css_put(&h_cg->css);
 done:
 	*ptr = h_cg;
@@ -213,7 +212,6 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 				  struct page *page)
 {
 	struct hugetlb_cgroup *h_cg;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		return;
@@ -222,61 +220,76 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 	if (unlikely(!h_cg))
 		return;
 	set_hugetlb_cgroup(page, NULL);
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
 void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 				    struct hugetlb_cgroup *h_cg)
 {
-	unsigned long csize = nr_pages * PAGE_SIZE;
-
 	if (hugetlb_cgroup_disabled() || !h_cg)
 		return;
 
 	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
 		return;
 
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
 static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 				   struct cftype *cft)
 {
-	int idx, name;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
 
-	idx = MEMFILE_IDX(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)];
 
-	return res_counter_read_u64(&h_cg->hugepage[idx], name);
+	switch (MEMFILE_ATTR(cft->private)) {
+	case RES_USAGE:
+		return (u64)page_counter_read(counter) * PAGE_SIZE;
+	case RES_LIMIT:
+		return (u64)counter->limit * PAGE_SIZE;
+	case RES_MAX_USAGE:
+		return (u64)counter->watermark * PAGE_SIZE;
+	case RES_FAILCNT:
+		return counter->failcnt;
+	default:
+		BUG();
+	}
 }
 
+static DEFINE_MUTEX(hugetlb_limit_mutex);
+
 static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret;
-	unsigned long long val;
+	int ret, idx;
+	unsigned long nr_pages;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
+	if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */
+		return -EINVAL;
+
 	buf = strstrip(buf);
+	ret = page_counter_memparse(buf, &nr_pages);
+	if (ret)
+		return ret;
+
 	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
-		if (hugetlb_cgroup_is_root(h_cg)) {
-			/* Can't set limit on root */
-			ret = -EINVAL;
-			break;
-		}
-		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
-			break;
-		val = ALIGN(val, 1ULL << huge_page_shift(&hstates[idx]));
-		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+		mutex_lock(&hugetlb_limit_mutex);
+		ret = page_counter_limit(&h_cg->hugepage[idx], nr_pages);
+		mutex_unlock(&hugetlb_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -288,18 +301,18 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret = 0;
+	int ret = 0;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)];
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&h_cg->hugepage[idx]);
+		page_counter_reset_watermark(counter);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&h_cg->hugepage[idx]);
+		counter->failcnt = 0;
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/mm/internal.h b/mm/internal.h
index 829304090b90..4928beb3725a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -136,13 +136,10 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
-	bool finished_update_free;	/* True when the zone cached pfns are
-					 * no longer being updated
-					 */
-	bool finished_update_migrate;
-
 	int order;			/* order a direct compactor needs */
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
+	const int alloc_flags;		/* alloc flags of a direct compactor */
+	const int classzone_idx;	/* zone index of a direct compactor */
 	struct zone *zone;
 	int contended;			/* Signal need_sched() or lock
 					 * contention detected during
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 23976fd885fd..3a203c7ec6c7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -25,7 +25,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/res_counter.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/mm.h>
@@ -143,14 +143,8 @@ struct mem_cgroup_stat_cpu {
 	unsigned long targets[MEM_CGROUP_NTARGETS];
 };
 
-struct mem_cgroup_reclaim_iter {
-	/*
-	 * last scanned hierarchy member. Valid only if last_dead_count
-	 * matches memcg->dead_count of the hierarchy root group.
-	 */
-	struct mem_cgroup *last_visited;
-	int last_dead_count;
-
+struct reclaim_iter {
+	struct mem_cgroup *position;
 	/* scan generation, increased every round-trip */
 	unsigned int generation;
 };
@@ -162,10 +156,10 @@ struct mem_cgroup_per_zone {
 	struct lruvec		lruvec;
 	unsigned long		lru_size[NR_LRU_LISTS];
 
-	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
+	struct reclaim_iter	iter[DEF_PRIORITY + 1];
 
 	struct rb_node		tree_node;	/* RB tree node */
-	unsigned long long	usage_in_excess;/* Set to the value by which */
+	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
 	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
@@ -198,7 +192,7 @@ static struct mem_cgroup_tree soft_limit_tree __read_mostly;
 
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
-	u64 threshold;
+	unsigned long threshold;
 };
 
 /* For threshold */
@@ -284,10 +278,13 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
  */
 struct mem_cgroup {
 	struct cgroup_subsys_state css;
-	/*
-	 * the counter to account for memory usage
-	 */
-	struct res_counter res;
+
+	/* Accounted resources */
+	struct page_counter memory;
+	struct page_counter memsw;
+	struct page_counter kmem;
+
+	unsigned long soft_limit;
 
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
@@ -296,15 +293,6 @@ struct mem_cgroup {
 	int initialized;
 
 	/*
-	 * the counter to account for mem+swap usage.
-	 */
-	struct res_counter memsw;
-
-	/*
-	 * the counter to account for kernel memory usage.
-	 */
-	struct res_counter kmem;
-	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
@@ -352,7 +340,6 @@ struct mem_cgroup {
 	struct mem_cgroup_stat_cpu nocpu_base;
 	spinlock_t pcp_counter_lock;
 
-	atomic_t	dead_count;
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
 	struct cg_proto tcp_mem;
 #endif
@@ -382,7 +369,6 @@ struct mem_cgroup {
 /* internal only representation about the status of kmem accounting. */
 enum {
 	KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */
-	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
 };
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -396,22 +382,6 @@ static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
 }
 
-static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
-{
-	/*
-	 * Our caller must use css_get() first, because memcg_uncharge_kmem()
-	 * will call css_put() if it sees the memcg is dead.
-	 */
-	smp_wmb();
-	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
-		set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
-}
-
-static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
-{
-	return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
-				  &memcg->kmem_account_flags);
-}
 #endif
 
 /* Stuffs for move charges at task migration. */
@@ -650,7 +620,7 @@ static void disarm_kmem_keys(struct mem_cgroup *memcg)
 	 * This check can't live in kmem destruction function,
 	 * since the charges will outlive the cgroup
 	 */
-	WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0);
+	WARN_ON(page_counter_read(&memcg->kmem));
 }
 #else
 static void disarm_kmem_keys(struct mem_cgroup *memcg)
@@ -664,8 +634,6 @@ static void disarm_static_keys(struct mem_cgroup *memcg)
 	disarm_kmem_keys(memcg);
 }
 
-static void drain_all_stock_async(struct mem_cgroup *memcg);
-
 static struct mem_cgroup_per_zone *
 mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
 {
@@ -706,7 +674,7 @@ soft_limit_tree_from_page(struct page *page)
 
 static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
 					 struct mem_cgroup_tree_per_zone *mctz,
-					 unsigned long long new_usage_in_excess)
+					 unsigned long new_usage_in_excess)
 {
 	struct rb_node **p = &mctz->rb_root.rb_node;
 	struct rb_node *parent = NULL;
@@ -755,10 +723,21 @@ static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
 	spin_unlock_irqrestore(&mctz->lock, flags);
 }
 
+static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
+{
+	unsigned long nr_pages = page_counter_read(&memcg->memory);
+	unsigned long soft_limit = ACCESS_ONCE(memcg->soft_limit);
+	unsigned long excess = 0;
+
+	if (nr_pages > soft_limit)
+		excess = nr_pages - soft_limit;
+
+	return excess;
+}
 
 static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 {
-	unsigned long long excess;
+	unsigned long excess;
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup_tree_per_zone *mctz;
 
@@ -769,7 +748,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	 */
 	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		mz = mem_cgroup_page_zoneinfo(memcg, page);
-		excess = res_counter_soft_limit_excess(&memcg->res);
+		excess = soft_limit_excess(memcg);
 		/*
 		 * We have to update the tree if mz is on RB-tree or
 		 * mem is over its softlimit.
@@ -825,7 +804,7 @@ retry:
 	 * position in the tree.
 	 */
 	__mem_cgroup_remove_exceeded(mz, mctz);
-	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
+	if (!soft_limit_excess(mz->memcg) ||
 	    !css_tryget_online(&mz->memcg->css))
 		goto retry;
 done:
@@ -1062,122 +1041,6 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return memcg;
 }
 
-/*
- * Returns a next (in a pre-order walk) alive memcg (with elevated css
- * ref. count) or NULL if the whole root's subtree has been visited.
- *
- * helper function to be used by mem_cgroup_iter
- */
-static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
-		struct mem_cgroup *last_visited)
-{
-	struct cgroup_subsys_state *prev_css, *next_css;
-
-	prev_css = last_visited ? &last_visited->css : NULL;
-skip_node:
-	next_css = css_next_descendant_pre(prev_css, &root->css);
-
-	/*
-	 * Even if we found a group we have to make sure it is
-	 * alive. css && !memcg means that the groups should be
-	 * skipped and we should continue the tree walk.
-	 * last_visited css is safe to use because it is
-	 * protected by css_get and the tree walk is rcu safe.
-	 *
-	 * We do not take a reference on the root of the tree walk
-	 * because we might race with the root removal when it would
-	 * be the only node in the iterated hierarchy and mem_cgroup_iter
-	 * would end up in an endless loop because it expects that at
-	 * least one valid node will be returned. Root cannot disappear
-	 * because caller of the iterator should hold it already so
-	 * skipping css reference should be safe.
-	 */
-	if (next_css) {
-		struct mem_cgroup *memcg = mem_cgroup_from_css(next_css);
-
-		if (next_css == &root->css)
-			return memcg;
-
-		if (css_tryget_online(next_css)) {
-			/*
-			 * Make sure the memcg is initialized:
-			 * mem_cgroup_css_online() orders the the
-			 * initialization against setting the flag.
-			 */
-			if (smp_load_acquire(&memcg->initialized))
-				return memcg;
-			css_put(next_css);
-		}
-
-		prev_css = next_css;
-		goto skip_node;
-	}
-
-	return NULL;
-}
-
-static void mem_cgroup_iter_invalidate(struct mem_cgroup *root)
-{
-	/*
-	 * When a group in the hierarchy below root is destroyed, the
-	 * hierarchy iterator can no longer be trusted since it might
-	 * have pointed to the destroyed group.  Invalidate it.
-	 */
-	atomic_inc(&root->dead_count);
-}
-
-static struct mem_cgroup *
-mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
-		     struct mem_cgroup *root,
-		     int *sequence)
-{
-	struct mem_cgroup *position = NULL;
-	/*
-	 * A cgroup destruction happens in two stages: offlining and
-	 * release.  They are separated by a RCU grace period.
-	 *
-	 * If the iterator is valid, we may still race with an
-	 * offlining.  The RCU lock ensures the object won't be
-	 * released, tryget will fail if we lost the race.
-	 */
-	*sequence = atomic_read(&root->dead_count);
-	if (iter->last_dead_count == *sequence) {
-		smp_rmb();
-		position = iter->last_visited;
-
-		/*
-		 * We cannot take a reference to root because we might race
-		 * with root removal and returning NULL would end up in
-		 * an endless loop on the iterator user level when root
-		 * would be returned all the time.
-		 */
-		if (position && position != root &&
-		    !css_tryget_online(&position->css))
-			position = NULL;
-	}
-	return position;
-}
-
-static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
-				   struct mem_cgroup *last_visited,
-				   struct mem_cgroup *new_position,
-				   struct mem_cgroup *root,
-				   int sequence)
-{
-	/* root reference counting symmetric to mem_cgroup_iter_load */
-	if (last_visited && last_visited != root)
-		css_put(&last_visited->css);
-	/*
-	 * We store the sequence count from the time @last_visited was
-	 * loaded successfully instead of rereading it here so that we
-	 * don't lose destruction events in between.  We could have
-	 * raced with the destruction of @new_position after all.
-	 */
-	iter->last_visited = new_position;
-	smp_wmb();
-	iter->last_dead_count = sequence;
-}
-
 /**
  * mem_cgroup_iter - iterate over memory cgroup hierarchy
  * @root: hierarchy root
@@ -1199,8 +1062,10 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
 				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
+	struct reclaim_iter *uninitialized_var(iter);
+	struct cgroup_subsys_state *css = NULL;
 	struct mem_cgroup *memcg = NULL;
-	struct mem_cgroup *last_visited = NULL;
+	struct mem_cgroup *pos = NULL;
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -1209,50 +1074,101 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		root = root_mem_cgroup;
 
 	if (prev && !reclaim)
-		last_visited = prev;
+		pos = prev;
 
 	if (!root->use_hierarchy && root != root_mem_cgroup) {
 		if (prev)
-			goto out_css_put;
+			goto out;
 		return root;
 	}
 
 	rcu_read_lock();
-	while (!memcg) {
-		struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
-		int uninitialized_var(seq);
-
-		if (reclaim) {
-			struct mem_cgroup_per_zone *mz;
-
-			mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone);
-			iter = &mz->reclaim_iter[reclaim->priority];
-			if (prev && reclaim->generation != iter->generation) {
-				iter->last_visited = NULL;
-				goto out_unlock;
-			}
 
-			last_visited = mem_cgroup_iter_load(iter, root, &seq);
+	if (reclaim) {
+		struct mem_cgroup_per_zone *mz;
+
+		mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone);
+		iter = &mz->iter[reclaim->priority];
+
+		if (prev && reclaim->generation != iter->generation)
+			goto out_unlock;
+
+		do {
+			pos = ACCESS_ONCE(iter->position);
+			/*
+			 * A racing update may change the position and
+			 * put the last reference, hence css_tryget(),
+			 * or retry to see the updated position.
+			 */
+		} while (pos && !css_tryget(&pos->css));
+	}
+
+	if (pos)
+		css = &pos->css;
+
+	for (;;) {
+		css = css_next_descendant_pre(css, &root->css);
+		if (!css) {
+			/*
+			 * Reclaimers share the hierarchy walk, and a
+			 * new one might jump in right at the end of
+			 * the hierarchy - make sure they see at least
+			 * one group and restart from the beginning.
+			 */
+			if (!prev)
+				continue;
+			break;
 		}
 
-		memcg = __mem_cgroup_iter_next(root, last_visited);
+		/*
+		 * Verify the css and acquire a reference.  The root
+		 * is provided by the caller, so we know it's alive
+		 * and kicking, and don't take an extra reference.
+		 */
+		memcg = mem_cgroup_from_css(css);
+
+		if (css == &root->css)
+			break;
 
-		if (reclaim) {
-			mem_cgroup_iter_update(iter, last_visited, memcg, root,
-					seq);
+		if (css_tryget(css)) {
+			/*
+			 * Make sure the memcg is initialized:
+			 * mem_cgroup_css_online() orders the the
+			 * initialization against setting the flag.
+			 */
+			if (smp_load_acquire(&memcg->initialized))
+				break;
 
-			if (!memcg)
-				iter->generation++;
-			else if (!prev && memcg)
-				reclaim->generation = iter->generation;
+			css_put(css);
 		}
 
-		if (prev && !memcg)
-			goto out_unlock;
+		memcg = NULL;
 	}
+
+	if (reclaim) {
+		if (cmpxchg(&iter->position, pos, memcg) == pos) {
+			if (memcg)
+				css_get(&memcg->css);
+			if (pos)
+				css_put(&pos->css);
+		}
+
+		/*
+		 * pairs with css_tryget when dereferencing iter->position
+		 * above.
+		 */
+		if (pos)
+			css_put(&pos->css);
+
+		if (!memcg)
+			iter->generation++;
+		else if (!prev)
+			reclaim->generation = iter->generation;
+	}
+
 out_unlock:
 	rcu_read_unlock();
-out_css_put:
+out:
 	if (prev && prev != root)
 		css_put(&prev->css);
 
@@ -1492,7 +1408,7 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
-#define mem_cgroup_from_res_counter(counter, member)	\
+#define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
 /**
@@ -1504,12 +1420,23 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
  */
 static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 {
-	unsigned long long margin;
+	unsigned long margin = 0;
+	unsigned long count;
+	unsigned long limit;
 
-	margin = res_counter_margin(&memcg->res);
-	if (do_swap_account)
-		margin = min(margin, res_counter_margin(&memcg->memsw));
-	return margin >> PAGE_SHIFT;
+	count = page_counter_read(&memcg->memory);
+	limit = ACCESS_ONCE(memcg->memory.limit);
+	if (count < limit)
+		margin = limit - count;
+
+	if (do_swap_account) {
+		count = page_counter_read(&memcg->memsw);
+		limit = ACCESS_ONCE(memcg->memsw.limit);
+		if (count <= limit)
+			margin = min(margin, limit - count);
+	}
+
+	return margin;
 }
 
 int mem_cgroup_swappiness(struct mem_cgroup *memcg)
@@ -1650,18 +1577,15 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 
 	rcu_read_unlock();
 
-	pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->res, RES_FAILCNT));
-	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
-	pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
+	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->memory)),
+		K((u64)memcg->memory.limit), memcg->memory.failcnt);
+	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->memsw)),
+		K((u64)memcg->memsw.limit), memcg->memsw.failcnt);
+	pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->kmem)),
+		K((u64)memcg->kmem.limit), memcg->kmem.failcnt);
 
 	for_each_mem_cgroup_tree(iter, memcg) {
 		pr_info("Memory cgroup stats for ");
@@ -1701,28 +1625,17 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 /*
  * Return the memory (and swap, if configured) limit for a memcg.
  */
-static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
-	u64 limit;
-
-	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+	unsigned long limit;
 
-	/*
-	 * Do not consider swap space if we cannot swap due to swappiness
-	 */
+	limit = memcg->memory.limit;
 	if (mem_cgroup_swappiness(memcg)) {
-		u64 memsw;
-
-		limit += total_swap_pages << PAGE_SHIFT;
-		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+		unsigned long memsw_limit;
 
-		/*
-		 * If memsw is finite and limits the amount of swap space
-		 * available to this memcg, return that limit.
-		 */
-		limit = min(limit, memsw);
+		memsw_limit = memcg->memsw.limit;
+		limit = min(limit + total_swap_pages, memsw_limit);
 	}
-
 	return limit;
 }
 
@@ -1746,7 +1659,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	}
 
 	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
-	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
+	totalpages = mem_cgroup_get_limit(memcg) ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
 		struct task_struct *task;
@@ -1949,7 +1862,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 		.priority = 0,
 	};
 
-	excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+	excess = soft_limit_excess(root_memcg);
 
 	while (1) {
 		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
@@ -1980,7 +1893,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
 						     zone, &nr_scanned);
 		*total_scanned += nr_scanned;
-		if (!res_counter_soft_limit_excess(&root_memcg->res))
+		if (!soft_limit_excess(root_memcg))
 			break;
 	}
 	mem_cgroup_iter_break(root_memcg, victim);
@@ -2307,33 +2220,32 @@ static DEFINE_MUTEX(percpu_charge_mutex);
 static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	struct memcg_stock_pcp *stock;
-	bool ret = true;
+	bool ret = false;
 
 	if (nr_pages > CHARGE_BATCH)
-		return false;
+		return ret;
 
 	stock = &get_cpu_var(memcg_stock);
-	if (memcg == stock->cached && stock->nr_pages >= nr_pages)
+	if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
 		stock->nr_pages -= nr_pages;
-	else /* need to call res_counter_charge */
-		ret = false;
+		ret = true;
+	}
 	put_cpu_var(memcg_stock);
 	return ret;
 }
 
 /*
- * Returns stocks cached in percpu to res_counter and reset cached information.
+ * Returns stocks cached in percpu and reset cached information.
  */
 static void drain_stock(struct memcg_stock_pcp *stock)
 {
 	struct mem_cgroup *old = stock->cached;
 
 	if (stock->nr_pages) {
-		unsigned long bytes = stock->nr_pages * PAGE_SIZE;
-
-		res_counter_uncharge(&old->res, bytes);
+		page_counter_uncharge(&old->memory, stock->nr_pages);
 		if (do_swap_account)
-			res_counter_uncharge(&old->memsw, bytes);
+			page_counter_uncharge(&old->memsw, stock->nr_pages);
+		css_put_many(&old->css, stock->nr_pages);
 		stock->nr_pages = 0;
 	}
 	stock->cached = NULL;
@@ -2362,7 +2274,7 @@ static void __init memcg_stock_init(void)
 }
 
 /*
- * Cache charges(val) which is from res_counter, to local per_cpu area.
+ * Cache charges(val) to local per_cpu area.
  * This will be consumed by consume_stock() function, later.
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
@@ -2379,13 +2291,15 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 /*
  * Drains all per-CPU charge caches for given root_memcg resp. subtree
- * of the hierarchy under it. sync flag says whether we should block
- * until the work is done.
+ * of the hierarchy under it.
  */
-static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
+static void drain_all_stock(struct mem_cgroup *root_memcg)
 {
 	int cpu, curcpu;
 
+	/* If someone's already draining, avoid adding running more workers. */
+	if (!mutex_trylock(&percpu_charge_mutex))
+		return;
 	/* Notify other cpus that system-wide "drain" is running */
 	get_online_cpus();
 	curcpu = get_cpu();
@@ -2406,42 +2320,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
 		}
 	}
 	put_cpu();
-
-	if (!sync)
-		goto out;
-
-	for_each_online_cpu(cpu) {
-		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
-			flush_work(&stock->work);
-	}
-out:
 	put_online_cpus();
-}
-
-/*
- * Tries to drain stocked charges in other cpus. This function is asynchronous
- * and just put a work per cpu for draining localy on each cpu. Caller can
- * expects some charges will be back to res_counter later but cannot wait for
- * it.
- */
-static void drain_all_stock_async(struct mem_cgroup *root_memcg)
-{
-	/*
-	 * If someone calls draining, avoid adding more kworker runs.
-	 */
-	if (!mutex_trylock(&percpu_charge_mutex))
-		return;
-	drain_all_stock(root_memcg, false);
-	mutex_unlock(&percpu_charge_mutex);
-}
-
-/* This is a synchronous drain interface. */
-static void drain_all_stock_sync(struct mem_cgroup *root_memcg)
-{
-	/* called when force_empty is called */
-	mutex_lock(&percpu_charge_mutex);
-	drain_all_stock(root_memcg, true);
 	mutex_unlock(&percpu_charge_mutex);
 }
 
@@ -2497,9 +2376,8 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned int batch = max(CHARGE_BATCH, nr_pages);
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup *mem_over_limit;
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	unsigned long nr_reclaimed;
-	unsigned long long size;
 	bool may_swap = true;
 	bool drained = false;
 	int ret = 0;
@@ -2510,16 +2388,15 @@ retry:
 	if (consume_stock(memcg, nr_pages))
 		goto done;
 
-	size = batch * PAGE_SIZE;
 	if (!do_swap_account ||
-	    !res_counter_charge(&memcg->memsw, size, &fail_res)) {
-		if (!res_counter_charge(&memcg->res, size, &fail_res))
+	    !page_counter_try_charge(&memcg->memsw, batch, &counter)) {
+		if (!page_counter_try_charge(&memcg->memory, batch, &counter))
 			goto done_restock;
 		if (do_swap_account)
-			res_counter_uncharge(&memcg->memsw, size);
-		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
+			page_counter_uncharge(&memcg->memsw, batch);
+		mem_over_limit = mem_cgroup_from_counter(counter, memory);
 	} else {
-		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
+		mem_over_limit = mem_cgroup_from_counter(counter, memsw);
 		may_swap = false;
 	}
 
@@ -2552,7 +2429,7 @@ retry:
 		goto retry;
 
 	if (!drained) {
-		drain_all_stock_async(mem_over_limit);
+		drain_all_stock(mem_over_limit);
 		drained = true;
 		goto retry;
 	}
@@ -2594,6 +2471,7 @@ bypass:
 	return -EINTR;
 
 done_restock:
+	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
 done:
@@ -2602,32 +2480,14 @@ done:
 
 static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	unsigned long bytes = nr_pages * PAGE_SIZE;
-
 	if (mem_cgroup_is_root(memcg))
 		return;
 
-	res_counter_uncharge(&memcg->res, bytes);
+	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
-		res_counter_uncharge(&memcg->memsw, bytes);
-}
-
-/*
- * Cancel chrages in this cgroup....doesn't propagate to parent cgroup.
- * This is useful when moving usage to parent cgroup.
- */
-static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
-					unsigned int nr_pages)
-{
-	unsigned long bytes = nr_pages * PAGE_SIZE;
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 
-	if (mem_cgroup_is_root(memcg))
-		return;
-
-	res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes);
-	if (do_swap_account)
-		res_counter_uncharge_until(&memcg->memsw,
-						memcg->memsw.parent, bytes);
+	css_put_many(&memcg->css, nr_pages);
 }
 
 /*
@@ -2751,8 +2611,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 		unlock_page_lru(page, isolated);
 }
 
-static DEFINE_MUTEX(set_limit_mutex);
-
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or
@@ -2795,16 +2653,17 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v)
 }
 #endif
 
-static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
+			     unsigned long nr_pages)
 {
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	int ret = 0;
 
-	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
-	if (ret)
+	ret = page_counter_try_charge(&memcg->kmem, nr_pages, &counter);
+	if (ret < 0)
 		return ret;
 
-	ret = try_charge(memcg, gfp, size >> PAGE_SHIFT);
+	ret = try_charge(memcg, gfp, nr_pages);
 	if (ret == -EINTR)  {
 		/*
 		 * try_charge() chose to bypass to root due to OOM kill or
@@ -2821,37 +2680,27 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 		 * when the allocation triggers should have been already
 		 * directed to the root cgroup in memcontrol.h
 		 */
-		res_counter_charge_nofail(&memcg->res, size, &fail_res);
+		page_counter_charge(&memcg->memory, nr_pages);
 		if (do_swap_account)
-			res_counter_charge_nofail(&memcg->memsw, size,
-						  &fail_res);
+			page_counter_charge(&memcg->memsw, nr_pages);
+		css_get_many(&memcg->css, nr_pages);
 		ret = 0;
 	} else if (ret)
-		res_counter_uncharge(&memcg->kmem, size);
+		page_counter_uncharge(&memcg->kmem, nr_pages);
 
 	return ret;
 }
 
-static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
+static void memcg_uncharge_kmem(struct mem_cgroup *memcg,
+				unsigned long nr_pages)
 {
-	res_counter_uncharge(&memcg->res, size);
+	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
-		res_counter_uncharge(&memcg->memsw, size);
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 
-	/* Not down to 0 */
-	if (res_counter_uncharge(&memcg->kmem, size))
-		return;
+	page_counter_uncharge(&memcg->kmem, nr_pages);
 
-	/*
-	 * Releases a reference taken in kmem_cgroup_css_offline in case
-	 * this last uncharge is racing with the offlining code or it is
-	 * outliving the memcg existence.
-	 *
-	 * The memory barrier imposed by test&clear is paired with the
-	 * explicit one in memcg_kmem_mark_dead().
-	 */
-	if (memcg_kmem_test_and_clear_dead(memcg))
-		css_put(&memcg->css);
+	css_put_many(&memcg->css, nr_pages);
 }
 
 /*
@@ -3115,19 +2964,21 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
 
 int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order)
 {
+	unsigned int nr_pages = 1 << order;
 	int res;
 
-	res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp,
-				PAGE_SIZE << order);
+	res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages);
 	if (!res)
-		atomic_add(1 << order, &cachep->memcg_params->nr_pages);
+		atomic_add(nr_pages, &cachep->memcg_params->nr_pages);
 	return res;
 }
 
 void __memcg_uncharge_slab(struct kmem_cache *cachep, int order)
 {
-	memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order);
-	atomic_sub(1 << order, &cachep->memcg_params->nr_pages);
+	unsigned int nr_pages = 1 << order;
+
+	memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages);
+	atomic_sub(nr_pages, &cachep->memcg_params->nr_pages);
 }
 
 /*
@@ -3248,7 +3099,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 		return true;
 	}
 
-	ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
+	ret = memcg_charge_kmem(memcg, gfp, 1 << order);
 	if (!ret)
 		*_memcg = memcg;
 
@@ -3265,7 +3116,7 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
 
 	/* The page allocation failed. Revert */
 	if (!page) {
-		memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+		memcg_uncharge_kmem(memcg, 1 << order);
 		return;
 	}
 	/*
@@ -3298,7 +3149,7 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 		return;
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
-	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+	memcg_uncharge_kmem(memcg, 1 << order);
 }
 #else
 static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
@@ -3422,72 +3273,6 @@ out:
 	return ret;
 }
 
-/**
- * mem_cgroup_move_parent - moves page to the parent group
- * @page: the page to move
- * @pc: page_cgroup of the page
- * @child: page's cgroup
- *
- * move charges to its parent or the root cgroup if the group has no
- * parent (aka use_hierarchy==0).
- * Although this might fail (get_page_unless_zero, isolate_lru_page or
- * mem_cgroup_move_account fails) the failure is always temporary and
- * it signals a race with a page removal/uncharge or migration. In the
- * first case the page is on the way out and it will vanish from the LRU
- * on the next attempt and the call should be retried later.
- * Isolation from the LRU fails only if page has been isolated from
- * the LRU since we looked at it and that usually means either global
- * reclaim or migration going on. The page will either get back to the
- * LRU or vanish.
- * Finaly mem_cgroup_move_account fails only if the page got uncharged
- * (!PageCgroupUsed) or moved to a different group. The page will
- * disappear in the next attempt.
- */
-static int mem_cgroup_move_parent(struct page *page,
-				  struct page_cgroup *pc,
-				  struct mem_cgroup *child)
-{
-	struct mem_cgroup *parent;
-	unsigned int nr_pages;
-	unsigned long uninitialized_var(flags);
-	int ret;
-
-	VM_BUG_ON(mem_cgroup_is_root(child));
-
-	ret = -EBUSY;
-	if (!get_page_unless_zero(page))
-		goto out;
-	if (isolate_lru_page(page))
-		goto put;
-
-	nr_pages = hpage_nr_pages(page);
-
-	parent = parent_mem_cgroup(child);
-	/*
-	 * If no parent, move charges to root cgroup.
-	 */
-	if (!parent)
-		parent = root_mem_cgroup;
-
-	if (nr_pages > 1) {
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-		flags = compound_lock_irqsave(page);
-	}
-
-	ret = mem_cgroup_move_account(page, nr_pages,
-				pc, child, parent);
-	if (!ret)
-		__mem_cgroup_cancel_local_charge(child, nr_pages);
-
-	if (nr_pages > 1)
-		compound_unlock_irqrestore(page, flags);
-	putback_lru_page(page);
-put:
-	put_page(page);
-out:
-	return ret;
-}
-
 #ifdef CONFIG_MEMCG_SWAP
 static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
 					 bool charge)
@@ -3507,7 +3292,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
  *
  * Returns 0 on success, -EINVAL on failure.
  *
- * The caller must have charged to @to, IOW, called res_counter_charge() about
+ * The caller must have charged to @to, IOW, called page_counter_charge() about
  * both res and memsw, and called css_get().
  */
 static int mem_cgroup_move_swap_account(swp_entry_t entry,
@@ -3523,7 +3308,7 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 		mem_cgroup_swap_statistics(to, true);
 		/*
 		 * This function is only called from task migration context now.
-		 * It postpones res_counter and refcount handling till the end
+		 * It postpones page_counter and refcount handling till the end
 		 * of task migration(mem_cgroup_clear_mc()) for performance
 		 * improvement. But we cannot postpone css_get(to)  because if
 		 * the process that has been moved to @to does swap-in, the
@@ -3581,60 +3366,57 @@ void mem_cgroup_print_bad_page(struct page *page)
 }
 #endif
 
+static DEFINE_MUTEX(memcg_limit_mutex);
+
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
-				unsigned long long val)
+				   unsigned long limit)
 {
+	unsigned long curusage;
+	unsigned long oldusage;
+	bool enlarge = false;
 	int retry_count;
-	int ret = 0;
-	int children = mem_cgroup_count_children(memcg);
-	u64 curusage, oldusage;
-	int enlarge;
+	int ret;
 
 	/*
 	 * For keeping hierarchical_reclaim simple, how long we should retry
 	 * is depends on callers. We set our retry-count to be function
 	 * of # of children which we should visit in this loop.
 	 */
-	retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES *
+		      mem_cgroup_count_children(memcg);
 
-	oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+	oldusage = page_counter_read(&memcg->memory);
 
-	enlarge = 0;
-	while (retry_count) {
+	do {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		/*
-		 * Rather than hide all in some function, I do this in
-		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
-		 */
-		mutex_lock(&set_limit_mutex);
-		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val) {
+
+		mutex_lock(&memcg_limit_mutex);
+		if (limit > memcg->memsw.limit) {
+			mutex_unlock(&memcg_limit_mutex);
 			ret = -EINVAL;
-			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-
-		if (res_counter_read_u64(&memcg->res, RES_LIMIT) < val)
-			enlarge = 1;
-
-		ret = res_counter_set_limit(&memcg->res, val);
-		mutex_unlock(&set_limit_mutex);
+		if (limit > memcg->memory.limit)
+			enlarge = true;
+		ret = page_counter_limit(&memcg->memory, limit);
+		mutex_unlock(&memcg_limit_mutex);
 
 		if (!ret)
 			break;
 
 		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true);
 
-		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+		curusage = page_counter_read(&memcg->memory);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
 		else
 			oldusage = curusage;
-	}
+	} while (retry_count);
+
 	if (!ret && enlarge)
 		memcg_oom_recover(memcg);
 
@@ -3642,52 +3424,53 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 }
 
 static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
-					unsigned long long val)
+					 unsigned long limit)
 {
+	unsigned long curusage;
+	unsigned long oldusage;
+	bool enlarge = false;
 	int retry_count;
-	u64 oldusage, curusage;
-	int children = mem_cgroup_count_children(memcg);
-	int ret = -EBUSY;
-	int enlarge = 0;
+	int ret;
 
 	/* see mem_cgroup_resize_res_limit */
-	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
-	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
-	while (retry_count) {
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES *
+		      mem_cgroup_count_children(memcg);
+
+	oldusage = page_counter_read(&memcg->memsw);
+
+	do {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		/*
-		 * Rather than hide all in some function, I do this in
-		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
-		 */
-		mutex_lock(&set_limit_mutex);
-		if (res_counter_read_u64(&memcg->res, RES_LIMIT) > val) {
+
+		mutex_lock(&memcg_limit_mutex);
+		if (limit < memcg->memory.limit) {
+			mutex_unlock(&memcg_limit_mutex);
 			ret = -EINVAL;
-			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val)
-			enlarge = 1;
-		ret = res_counter_set_limit(&memcg->memsw, val);
-		mutex_unlock(&set_limit_mutex);
+		if (limit > memcg->memsw.limit)
+			enlarge = true;
+		ret = page_counter_limit(&memcg->memsw, limit);
+		mutex_unlock(&memcg_limit_mutex);
 
 		if (!ret)
 			break;
 
 		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, false);
 
-		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		curusage = page_counter_read(&memcg->memsw);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
 		else
 			oldusage = curusage;
-	}
+	} while (retry_count);
+
 	if (!ret && enlarge)
 		memcg_oom_recover(memcg);
+
 	return ret;
 }
 
@@ -3700,7 +3483,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	unsigned long reclaimed;
 	int loop = 0;
 	struct mem_cgroup_tree_per_zone *mctz;
-	unsigned long long excess;
+	unsigned long excess;
 	unsigned long nr_scanned;
 
 	if (order > 0)
@@ -3754,7 +3537,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			} while (1);
 		}
 		__mem_cgroup_remove_exceeded(mz, mctz);
-		excess = res_counter_soft_limit_excess(&mz->memcg->res);
+		excess = soft_limit_excess(mz->memcg);
 		/*
 		 * One school of thought says that we should not add
 		 * back the node to the tree if reclaim returns 0.
@@ -3783,107 +3566,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return nr_reclaimed;
 }
 
-/**
- * mem_cgroup_force_empty_list - clears LRU of a group
- * @memcg: group to clear
- * @node: NUMA node
- * @zid: zone id
- * @lru: lru to to clear
- *
- * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
- * reclaim the pages page themselves - pages are moved to the parent (or root)
- * group.
- */
-static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
-				int node, int zid, enum lru_list lru)
-{
-	struct lruvec *lruvec;
-	unsigned long flags;
-	struct list_head *list;
-	struct page *busy;
-	struct zone *zone;
-
-	zone = &NODE_DATA(node)->node_zones[zid];
-	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
-	list = &lruvec->lists[lru];
-
-	busy = NULL;
-	do {
-		struct page_cgroup *pc;
-		struct page *page;
-
-		spin_lock_irqsave(&zone->lru_lock, flags);
-		if (list_empty(list)) {
-			spin_unlock_irqrestore(&zone->lru_lock, flags);
-			break;
-		}
-		page = list_entry(list->prev, struct page, lru);
-		if (busy == page) {
-			list_move(&page->lru, list);
-			busy = NULL;
-			spin_unlock_irqrestore(&zone->lru_lock, flags);
-			continue;
-		}
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
-
-		pc = lookup_page_cgroup(page);
-
-		if (mem_cgroup_move_parent(page, pc, memcg)) {
-			/* found lock contention or "pc" is obsolete. */
-			busy = page;
-		} else
-			busy = NULL;
-		cond_resched();
-	} while (!list_empty(list));
-}
-
-/*
- * make mem_cgroup's charge to be 0 if there is no task by moving
- * all the charges and pages to the parent.
- * This enables deleting this mem_cgroup.
- *
- * Caller is responsible for holding css reference on the memcg.
- */
-static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
-{
-	int node, zid;
-	u64 usage;
-
-	do {
-		/* This is for making all *used* pages to be on LRU. */
-		lru_add_drain_all();
-		drain_all_stock_sync(memcg);
-		mem_cgroup_start_move(memcg);
-		for_each_node_state(node, N_MEMORY) {
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				enum lru_list lru;
-				for_each_lru(lru) {
-					mem_cgroup_force_empty_list(memcg,
-							node, zid, lru);
-				}
-			}
-		}
-		mem_cgroup_end_move(memcg);
-		memcg_oom_recover(memcg);
-		cond_resched();
-
-		/*
-		 * Kernel memory may not necessarily be trackable to a specific
-		 * process. So they are not migrated, and therefore we can't
-		 * expect their value to drop to 0 here.
-		 * Having res filled up with kmem only is enough.
-		 *
-		 * This is a safety check because mem_cgroup_force_empty_list
-		 * could have raced with mem_cgroup_replace_page_cache callers
-		 * so the lru seemed empty but the page could have been added
-		 * right after the check. RES_USAGE should be safe as we always
-		 * charge before adding to the LRU.
-		 */
-		usage = res_counter_read_u64(&memcg->res, RES_USAGE) -
-			res_counter_read_u64(&memcg->kmem, RES_USAGE);
-	} while (usage > 0);
-}
-
 /*
  * Test whether @memcg has children, dead or alive.  Note that this
  * function doesn't care whether @memcg has use_hierarchy enabled and
@@ -3921,7 +3603,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
-	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
+	while (nr_retries && page_counter_read(&memcg->memory)) {
 		int progress;
 
 		if (signal_pending(current))
@@ -3992,8 +3674,8 @@ out:
 	return retval;
 }
 
-static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
-					       enum mem_cgroup_stat_index idx)
+static unsigned long tree_stat(struct mem_cgroup *memcg,
+			       enum mem_cgroup_stat_index idx)
 {
 	struct mem_cgroup *iter;
 	long val = 0;
@@ -4011,55 +3693,72 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 {
 	u64 val;
 
-	if (!mem_cgroup_is_root(memcg)) {
+	if (mem_cgroup_is_root(memcg)) {
+		val = tree_stat(memcg, MEM_CGROUP_STAT_CACHE);
+		val += tree_stat(memcg, MEM_CGROUP_STAT_RSS);
+		if (swap)
+			val += tree_stat(memcg, MEM_CGROUP_STAT_SWAP);
+	} else {
 		if (!swap)
-			return res_counter_read_u64(&memcg->res, RES_USAGE);
+			val = page_counter_read(&memcg->memory);
 		else
-			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+			val = page_counter_read(&memcg->memsw);
 	}
-
-	/*
-	 * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
-	 * as well as in MEM_CGROUP_STAT_RSS_HUGE.
-	 */
-	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
-	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
-
-	if (swap)
-		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
-
 	return val << PAGE_SHIFT;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+	RES_SOFT_LIMIT,
+};
 
 static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	enum res_type type = MEMFILE_TYPE(cft->private);
-	int name = MEMFILE_ATTR(cft->private);
+	struct page_counter *counter;
 
-	switch (type) {
+	switch (MEMFILE_TYPE(cft->private)) {
 	case _MEM:
-		if (name == RES_USAGE)
-			return mem_cgroup_usage(memcg, false);
-		return res_counter_read_u64(&memcg->res, name);
+		counter = &memcg->memory;
+		break;
 	case _MEMSWAP:
-		if (name == RES_USAGE)
-			return mem_cgroup_usage(memcg, true);
-		return res_counter_read_u64(&memcg->memsw, name);
+		counter = &memcg->memsw;
+		break;
 	case _KMEM:
-		return res_counter_read_u64(&memcg->kmem, name);
+		counter = &memcg->kmem;
 		break;
 	default:
 		BUG();
 	}
+
+	switch (MEMFILE_ATTR(cft->private)) {
+	case RES_USAGE:
+		if (counter == &memcg->memory)
+			return mem_cgroup_usage(memcg, false);
+		if (counter == &memcg->memsw)
+			return mem_cgroup_usage(memcg, true);
+		return (u64)page_counter_read(counter) * PAGE_SIZE;
+	case RES_LIMIT:
+		return (u64)counter->limit * PAGE_SIZE;
+	case RES_MAX_USAGE:
+		return (u64)counter->watermark * PAGE_SIZE;
+	case RES_FAILCNT:
+		return counter->failcnt;
+	case RES_SOFT_LIMIT:
+		return (u64)memcg->soft_limit * PAGE_SIZE;
+	default:
+		BUG();
+	}
 }
 
 #ifdef CONFIG_MEMCG_KMEM
 /* should be called with activate_kmem_mutex held */
 static int __memcg_activate_kmem(struct mem_cgroup *memcg,
-				 unsigned long long limit)
+				 unsigned long nr_pages)
 {
 	int err = 0;
 	int memcg_id;
@@ -4106,7 +3805,7 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 	 * We couldn't have accounted to this cgroup, because it hasn't got the
 	 * active bit set yet, so this should succeed.
 	 */
-	err = res_counter_set_limit(&memcg->kmem, limit);
+	err = page_counter_limit(&memcg->kmem, nr_pages);
 	VM_BUG_ON(err);
 
 	static_key_slow_inc(&memcg_kmem_enabled_key);
@@ -4122,25 +3821,27 @@ out:
 }
 
 static int memcg_activate_kmem(struct mem_cgroup *memcg,
-			       unsigned long long limit)
+			       unsigned long nr_pages)
 {
 	int ret;
 
 	mutex_lock(&activate_kmem_mutex);
-	ret = __memcg_activate_kmem(memcg, limit);
+	ret = __memcg_activate_kmem(memcg, nr_pages);
 	mutex_unlock(&activate_kmem_mutex);
 	return ret;
 }
 
 static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long long val)
+				   unsigned long limit)
 {
 	int ret;
 
+	mutex_lock(&memcg_limit_mutex);
 	if (!memcg_kmem_is_active(memcg))
-		ret = memcg_activate_kmem(memcg, val);
+		ret = memcg_activate_kmem(memcg, limit);
 	else
-		ret = res_counter_set_limit(&memcg->kmem, val);
+		ret = page_counter_limit(&memcg->kmem, limit);
+	mutex_unlock(&memcg_limit_mutex);
 	return ret;
 }
 
@@ -4158,13 +3859,13 @@ static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 	 * after this point, because it has at least one child already.
 	 */
 	if (memcg_kmem_is_active(parent))
-		ret = __memcg_activate_kmem(memcg, RES_COUNTER_MAX);
+		ret = __memcg_activate_kmem(memcg, PAGE_COUNTER_MAX);
 	mutex_unlock(&activate_kmem_mutex);
 	return ret;
 }
 #else
 static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long long val)
+				   unsigned long limit)
 {
 	return -EINVAL;
 }
@@ -4178,110 +3879,69 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	enum res_type type;
-	int name;
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret;
 
 	buf = strstrip(buf);
-	type = MEMFILE_TYPE(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	ret = page_counter_memparse(buf, &nr_pages);
+	if (ret)
+		return ret;
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
 		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
 			ret = -EINVAL;
 			break;
 		}
-		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
+		switch (MEMFILE_TYPE(of_cft(of)->private)) {
+		case _MEM:
+			ret = mem_cgroup_resize_limit(memcg, nr_pages);
 			break;
-		if (type == _MEM)
-			ret = mem_cgroup_resize_limit(memcg, val);
-		else if (type == _MEMSWAP)
-			ret = mem_cgroup_resize_memsw_limit(memcg, val);
-		else if (type == _KMEM)
-			ret = memcg_update_kmem_limit(memcg, val);
-		else
-			return -EINVAL;
-		break;
-	case RES_SOFT_LIMIT:
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
+		case _MEMSWAP:
+			ret = mem_cgroup_resize_memsw_limit(memcg, nr_pages);
 			break;
-		/*
-		 * For memsw, soft limits are hard to implement in terms
-		 * of semantics, for now, we support soft limits for
-		 * control without swap
-		 */
-		if (type == _MEM)
-			ret = res_counter_set_soft_limit(&memcg->res, val);
-		else
-			ret = -EINVAL;
+		case _KMEM:
+			ret = memcg_update_kmem_limit(memcg, nr_pages);
+			break;
+		}
 		break;
-	default:
-		ret = -EINVAL; /* should be BUG() ? */
+	case RES_SOFT_LIMIT:
+		memcg->soft_limit = nr_pages;
+		ret = 0;
 		break;
 	}
 	return ret ?: nbytes;
 }
 
-static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
-		unsigned long long *mem_limit, unsigned long long *memsw_limit)
-{
-	unsigned long long min_limit, min_memsw_limit, tmp;
-
-	min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-	if (!memcg->use_hierarchy)
-		goto out;
-
-	while (memcg->css.parent) {
-		memcg = mem_cgroup_from_css(memcg->css.parent);
-		if (!memcg->use_hierarchy)
-			break;
-		tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
-		min_limit = min(min_limit, tmp);
-		tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-		min_memsw_limit = min(min_memsw_limit, tmp);
-	}
-out:
-	*mem_limit = min_limit;
-	*memsw_limit = min_memsw_limit;
-}
-
 static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
 				size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	int name;
-	enum res_type type;
+	struct page_counter *counter;
 
-	type = MEMFILE_TYPE(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	switch (MEMFILE_TYPE(of_cft(of)->private)) {
+	case _MEM:
+		counter = &memcg->memory;
+		break;
+	case _MEMSWAP:
+		counter = &memcg->memsw;
+		break;
+	case _KMEM:
+		counter = &memcg->kmem;
+		break;
+	default:
+		BUG();
+	}
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_MAX_USAGE:
-		if (type == _MEM)
-			res_counter_reset_max(&memcg->res);
-		else if (type == _MEMSWAP)
-			res_counter_reset_max(&memcg->memsw);
-		else if (type == _KMEM)
-			res_counter_reset_max(&memcg->kmem);
-		else
-			return -EINVAL;
+		page_counter_reset_watermark(counter);
 		break;
 	case RES_FAILCNT:
-		if (type == _MEM)
-			res_counter_reset_failcnt(&memcg->res);
-		else if (type == _MEMSWAP)
-			res_counter_reset_failcnt(&memcg->memsw);
-		else if (type == _KMEM)
-			res_counter_reset_failcnt(&memcg->kmem);
-		else
-			return -EINVAL;
+		counter->failcnt = 0;
 		break;
+	default:
+		BUG();
 	}
 
 	return nbytes;
@@ -4378,6 +4038,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void)
 static int memcg_stat_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	unsigned long memory, memsw;
 	struct mem_cgroup *mi;
 	unsigned int i;
 
@@ -4397,14 +4058,16 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   mem_cgroup_nr_lru_pages(memcg, BIT(i)) * PAGE_SIZE);
 
 	/* Hierarchical information */
-	{
-		unsigned long long limit, memsw_limit;
-		memcg_get_hierarchical_limit(memcg, &limit, &memsw_limit);
-		seq_printf(m, "hierarchical_memory_limit %llu\n", limit);
-		if (do_swap_account)
-			seq_printf(m, "hierarchical_memsw_limit %llu\n",
-				   memsw_limit);
+	memory = memsw = PAGE_COUNTER_MAX;
+	for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) {
+		memory = min(memory, mi->memory.limit);
+		memsw = min(memsw, mi->memsw.limit);
 	}
+	seq_printf(m, "hierarchical_memory_limit %llu\n",
+		   (u64)memory * PAGE_SIZE);
+	if (do_swap_account)
+		seq_printf(m, "hierarchical_memsw_limit %llu\n",
+			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		long long val = 0;
@@ -4488,7 +4151,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 {
 	struct mem_cgroup_threshold_ary *t;
-	u64 usage;
+	unsigned long usage;
 	int i;
 
 	rcu_read_lock();
@@ -4587,10 +4250,11 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	u64 threshold, usage;
+	unsigned long threshold;
+	unsigned long usage;
 	int i, size, ret;
 
-	ret = res_counter_memparse_write_strategy(args, &threshold);
+	ret = page_counter_memparse(args, &threshold);
 	if (ret)
 		return ret;
 
@@ -4680,7 +4344,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	u64 usage;
+	unsigned long usage;
 	int i, j, size;
 
 	mutex_lock(&memcg->thresholds_lock);
@@ -4846,40 +4510,6 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
 	mem_cgroup_sockets_destroy(memcg);
 }
-
-static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
-{
-	if (!memcg_kmem_is_active(memcg))
-		return;
-
-	/*
-	 * kmem charges can outlive the cgroup. In the case of slab
-	 * pages, for instance, a page contain objects from various
-	 * processes. As we prevent from taking a reference for every
-	 * such allocation we have to be careful when doing uncharge
-	 * (see memcg_uncharge_kmem) and here during offlining.
-	 *
-	 * The idea is that that only the _last_ uncharge which sees
-	 * the dead memcg will drop the last reference. An additional
-	 * reference is taken here before the group is marked dead
-	 * which is then paired with css_put during uncharge resp. here.
-	 *
-	 * Although this might sound strange as this path is called from
-	 * css_offline() when the referencemight have dropped down to 0 and
-	 * shouldn't be incremented anymore (css_tryget_online() would
-	 * fail) we do not have other options because of the kmem
-	 * allocations lifetime.
-	 */
-	css_get(&memcg->css);
-
-	memcg_kmem_mark_dead(memcg);
-
-	if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
-		return;
-
-	if (memcg_kmem_test_and_clear_dead(memcg))
-		css_put(&memcg->css);
-}
 #else
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
@@ -4889,10 +4519,6 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
 }
-
-static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
-{
-}
 #endif
 
 /*
@@ -5354,9 +4980,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
  */
 struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
-	if (!memcg->res.parent)
+	if (!memcg->memory.parent)
 		return NULL;
-	return mem_cgroup_from_res_counter(memcg->res.parent, res);
+	return mem_cgroup_from_counter(memcg->memory.parent, memory);
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
@@ -5401,9 +5027,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	/* root ? */
 	if (parent_css == NULL) {
 		root_mem_cgroup = memcg;
-		res_counter_init(&memcg->res, NULL);
-		res_counter_init(&memcg->memsw, NULL);
-		res_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->memsw, NULL);
+		page_counter_init(&memcg->kmem, NULL);
 	}
 
 	memcg->last_scanned_node = MAX_NUMNODES;
@@ -5442,18 +5068,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	memcg->swappiness = mem_cgroup_swappiness(parent);
 
 	if (parent->use_hierarchy) {
-		res_counter_init(&memcg->res, &parent->res);
-		res_counter_init(&memcg->memsw, &parent->memsw);
-		res_counter_init(&memcg->kmem, &parent->kmem);
+		page_counter_init(&memcg->memory, &parent->memory);
+		page_counter_init(&memcg->memsw, &parent->memsw);
+		page_counter_init(&memcg->kmem, &parent->kmem);
 
 		/*
 		 * No need to take a reference to the parent because cgroup
 		 * core guarantees its existence.
 		 */
 	} else {
-		res_counter_init(&memcg->res, NULL);
-		res_counter_init(&memcg->memsw, NULL);
-		res_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->memsw, NULL);
+		page_counter_init(&memcg->kmem, NULL);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
@@ -5478,29 +5104,10 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
-/*
- * Announce all parents that a group from their hierarchy is gone.
- */
-static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
-{
-	struct mem_cgroup *parent = memcg;
-
-	while ((parent = parent_mem_cgroup(parent)))
-		mem_cgroup_iter_invalidate(parent);
-
-	/*
-	 * if the root memcg is not hierarchical we have to check it
-	 * explicitely.
-	 */
-	if (!root_mem_cgroup->use_hierarchy)
-		mem_cgroup_iter_invalidate(root_mem_cgroup);
-}
-
 static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_event *event, *tmp;
-	struct cgroup_subsys_state *iter;
 
 	/*
 	 * Unregister events and notify userspace.
@@ -5514,17 +5121,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	}
 	spin_unlock(&memcg->event_list_lock);
 
-	kmem_cgroup_css_offline(memcg);
-
-	mem_cgroup_invalidate_reclaim_iterators(memcg);
-
-	/*
-	 * This requires that offlining is serialized.  Right now that is
-	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
-	 */
-	css_for_each_descendant_post(iter, css)
-		mem_cgroup_reparent_charges(mem_cgroup_from_css(iter));
-
 	memcg_unregister_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
@@ -5532,42 +5128,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	/*
-	 * XXX: css_offline() would be where we should reparent all
-	 * memory to prepare the cgroup for destruction.  However,
-	 * memcg does not do css_tryget_online() and res_counter charging
-	 * under the same RCU lock region, which means that charging
-	 * could race with offlining.  Offlining only happens to
-	 * cgroups with no tasks in them but charges can show up
-	 * without any tasks from the swapin path when the target
-	 * memcg is looked up from the swapout record and not from the
-	 * current task as it usually is.  A race like this can leak
-	 * charges and put pages with stale cgroup pointers into
-	 * circulation:
-	 *
-	 * #0                        #1
-	 *                           lookup_swap_cgroup_id()
-	 *                           rcu_read_lock()
-	 *                           mem_cgroup_lookup()
-	 *                           css_tryget_online()
-	 *                           rcu_read_unlock()
-	 * disable css_tryget_online()
-	 * call_rcu()
-	 *   offline_css()
-	 *     reparent_charges()
-	 *                           res_counter_charge()
-	 *                           css_put()
-	 *                             css_free()
-	 *                           pc->mem_cgroup = dead memcg
-	 *                           add page to lru
-	 *
-	 * The bulk of the charges are still moved in offline_css() to
-	 * avoid pinning a lot of pages in case a long-term reference
-	 * like a swapout record is deferring the css_free() to long
-	 * after offlining.  But this makes sure we catch any charges
-	 * made after offlining:
-	 */
-	mem_cgroup_reparent_charges(memcg);
 
 	memcg_destroy_kmem(memcg);
 	__mem_cgroup_free(memcg);
@@ -5590,10 +5150,10 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	mem_cgroup_resize_limit(memcg, ULLONG_MAX);
-	mem_cgroup_resize_memsw_limit(memcg, ULLONG_MAX);
-	memcg_update_kmem_limit(memcg, ULLONG_MAX);
-	res_counter_set_soft_limit(&memcg->res, ULLONG_MAX);
+	mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX);
+	mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX);
+	memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX);
+	memcg->soft_limit = 0;
 }
 
 #ifdef CONFIG_MMU
@@ -5888,7 +5448,6 @@ static void __mem_cgroup_clear_mc(void)
 {
 	struct mem_cgroup *from = mc.from;
 	struct mem_cgroup *to = mc.to;
-	int i;
 
 	/* we must uncharge all the leftover precharges from mc.to */
 	if (mc.precharge) {
@@ -5907,19 +5466,17 @@ static void __mem_cgroup_clear_mc(void)
 	if (mc.moved_swap) {
 		/* uncharge swap account from the old cgroup */
 		if (!mem_cgroup_is_root(mc.from))
-			res_counter_uncharge(&mc.from->memsw,
-					     PAGE_SIZE * mc.moved_swap);
-
-		for (i = 0; i < mc.moved_swap; i++)
-			css_put(&mc.from->css);
+			page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
 
 		/*
-		 * we charged both to->res and to->memsw, so we should
-		 * uncharge to->res.
+		 * we charged both to->memory and to->memsw, so we
+		 * should uncharge to->memory.
 		 */
 		if (!mem_cgroup_is_root(mc.to))
-			res_counter_uncharge(&mc.to->res,
-					     PAGE_SIZE * mc.moved_swap);
+			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
+
+		css_put_many(&mc.from->css, mc.moved_swap);
+
 		/* we've already done css_get(mc.to) */
 		mc.moved_swap = 0;
 	}
@@ -6285,7 +5842,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
 	memcg = mem_cgroup_lookup(id);
 	if (memcg) {
 		if (!mem_cgroup_is_root(memcg))
-			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+			page_counter_uncharge(&memcg->memsw, 1);
 		mem_cgroup_swap_statistics(memcg, false);
 		css_put(&memcg->css);
 	}
@@ -6451,11 +6008,9 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 
 	if (!mem_cgroup_is_root(memcg)) {
 		if (nr_mem)
-			res_counter_uncharge(&memcg->res,
-					     nr_mem * PAGE_SIZE);
+			page_counter_uncharge(&memcg->memory, nr_mem);
 		if (nr_memsw)
-			res_counter_uncharge(&memcg->memsw,
-					     nr_memsw * PAGE_SIZE);
+			page_counter_uncharge(&memcg->memsw, nr_memsw);
 		memcg_oom_recover(memcg);
 	}
 
@@ -6467,6 +6022,9 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 	__this_cpu_add(memcg->stat->nr_page_events, nr_anon + nr_file);
 	memcg_check_events(memcg, dummy_page);
 	local_irq_restore(flags);
+
+	if (!mem_cgroup_is_root(memcg))
+		css_put_many(&memcg->css, max(nr_mem, nr_memsw));
 }
 
 static void uncharge_list(struct list_head *page_list)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8639f6b28746..84e7ded04321 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -233,7 +233,7 @@ void shake_page(struct page *p, int access)
 		lru_add_drain_all();
 		if (PageLRU(p))
 			return;
-		drain_all_pages();
+		drain_all_pages(page_zone(p));
 		if (PageLRU(p) || is_free_buddy_page(p))
 			return;
 	}
@@ -1661,7 +1661,7 @@ static int __soft_offline_page(struct page *page, int flags)
 			if (!is_free_buddy_page(page))
 				lru_add_drain_all();
 			if (!is_free_buddy_page(page))
-				drain_all_pages();
+				drain_all_pages(page_zone(page));
 			SetPageHWPoison(page);
 			if (!is_free_buddy_page(page))
 				pr_info("soft offline: %#lx: page leaked\n",
diff --git a/mm/memory.c b/mm/memory.c
index 1cc6bfbd872e..64f82aacb0ce 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2978,6 +2978,8 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	int dirtied = 0;
 	int ret, tmp;
 
+	WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
+
 	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
@@ -3008,6 +3010,12 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (set_page_dirty(fault_page))
 		dirtied = 1;
+	/*
+	 * Take a local copy of the address_space - page.mapping may be zeroed
+	 * by truncate after unlock_page().   The address_space itself remains
+	 * 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;
 	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 29d8693d0c61..7b6705355465 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1699,7 +1699,7 @@ repeat:
 	if (drain) {
 		lru_add_drain_all();
 		cond_resched();
-		drain_all_pages();
+		drain_all_pages(zone);
 	}
 
 	pfn = scan_movable_pages(start_pfn, end_pfn);
@@ -1721,7 +1721,7 @@ repeat:
 	lru_add_drain_all();
 	yield();
 	/* drain pcp pages, this is synchronous. */
-	drain_all_pages();
+	drain_all_pages(zone);
 	/*
 	 * dissolve free hugepages in the memory block before doing offlining
 	 * actually in order to make hugetlbfs's object counting consistent.
diff --git a/mm/mmap.c b/mm/mmap.c
index 7f855206e7fb..87e82b38453c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1080,7 +1080,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				end, prev->vm_pgoff, NULL);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(prev);
+		khugepaged_enter_vma_merge(prev, vm_flags);
 		return prev;
 	}
 
@@ -1099,7 +1099,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				next->vm_pgoff - pglen, NULL);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(area);
+		khugepaged_enter_vma_merge(area, vm_flags);
 		return area;
 	}
 
@@ -2208,7 +2208,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		}
 	}
 	vma_unlock_anon_vma(vma);
-	khugepaged_enter_vma_merge(vma);
+	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(vma->vm_mm);
 	return error;
 }
@@ -2277,7 +2277,7 @@ int expand_downwards(struct vm_area_struct *vma,
 		}
 	}
 	vma_unlock_anon_vma(vma);
-	khugepaged_enter_vma_merge(vma);
+	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(vma->vm_mm);
 	return error;
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index bbf405a3a18f..ca96b01f4d7e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -266,8 +266,6 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 	 * Don't allow any other task to have access to the reserves.
 	 */
 	if (test_tsk_thread_flag(task, TIF_MEMDIE)) {
-		if (unlikely(frozen(task)))
-			__thaw_task(task);
 		if (!force_kill)
 			return OOM_SCAN_ABORT;
 	}
@@ -404,6 +402,18 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 		dump_tasks(memcg, nodemask);
 }
 
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+	return atomic_read(&oom_kills);
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
@@ -506,11 +516,13 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			pr_err("Kill process %d (%s) sharing same memory\n",
 				task_pid_nr(p), p->comm);
 			task_unlock(p);
+			atomic_inc(&oom_kills);
 			do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
 		}
 	rcu_read_unlock();
 
 	set_tsk_thread_flag(victim, TIF_MEMDIE);
+	atomic_inc(&oom_kills);
 	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
 	put_task_struct(victim);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 736d8e1b6381..dd73f9aa9615 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -750,6 +750,9 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	int i;
 	int bad = 0;
 
+	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PAGE(PageHead(page) && compound_order(page) != order, page);
+
 	trace_mm_page_free(page, order);
 	kmemcheck_free_shadow(page, order);
 
@@ -1276,55 +1279,75 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 #endif
 
 /*
- * Drain pages of the indicated processor.
+ * Drain pcplists of the indicated processor and zone.
  *
  * The processor must either be the current processor and the
  * thread pinned to the current processor or a processor that
  * is not online.
  */
-static void drain_pages(unsigned int cpu)
+static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	unsigned long flags;
-	struct zone *zone;
+	struct per_cpu_pageset *pset;
+	struct per_cpu_pages *pcp;
 
-	for_each_populated_zone(zone) {
-		struct per_cpu_pageset *pset;
-		struct per_cpu_pages *pcp;
+	local_irq_save(flags);
+	pset = per_cpu_ptr(zone->pageset, cpu);
 
-		local_irq_save(flags);
-		pset = per_cpu_ptr(zone->pageset, cpu);
+	pcp = &pset->pcp;
+	if (pcp->count) {
+		free_pcppages_bulk(zone, pcp->count, pcp);
+		pcp->count = 0;
+	}
+	local_irq_restore(flags);
+}
 
-		pcp = &pset->pcp;
-		if (pcp->count) {
-			free_pcppages_bulk(zone, pcp->count, pcp);
-			pcp->count = 0;
-		}
-		local_irq_restore(flags);
+/*
+ * Drain pcplists of all zones on the indicated processor.
+ *
+ * The processor must either be the current processor and the
+ * thread pinned to the current processor or a processor that
+ * is not online.
+ */
+static void drain_pages(unsigned int cpu)
+{
+	struct zone *zone;
+
+	for_each_populated_zone(zone) {
+		drain_pages_zone(cpu, zone);
 	}
 }
 
 /*
  * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ *
+ * The CPU has to be pinned. When zone parameter is non-NULL, spill just
+ * the single zone's pages.
  */
-void drain_local_pages(void *arg)
+void drain_local_pages(struct zone *zone)
 {
-	drain_pages(smp_processor_id());
+	int cpu = smp_processor_id();
+
+	if (zone)
+		drain_pages_zone(cpu, zone);
+	else
+		drain_pages(cpu);
 }
 
 /*
  * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
  *
+ * When zone parameter is non-NULL, spill just the single zone's pages.
+ *
  * Note that this code is protected against sending an IPI to an offline
  * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
  * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
  * nothing keeps CPUs from showing up after we populated the cpumask and
  * before the call to on_each_cpu_mask().
  */
-void drain_all_pages(void)
+void drain_all_pages(struct zone *zone)
 {
 	int cpu;
-	struct per_cpu_pageset *pcp;
-	struct zone *zone;
 
 	/*
 	 * Allocate in the BSS so we wont require allocation in
@@ -1339,20 +1362,31 @@ void drain_all_pages(void)
 	 * disables preemption as part of its processing
 	 */
 	for_each_online_cpu(cpu) {
+		struct per_cpu_pageset *pcp;
+		struct zone *z;
 		bool has_pcps = false;
-		for_each_populated_zone(zone) {
+
+		if (zone) {
 			pcp = per_cpu_ptr(zone->pageset, cpu);
-			if (pcp->pcp.count) {
+			if (pcp->pcp.count)
 				has_pcps = true;
-				break;
+		} else {
+			for_each_populated_zone(z) {
+				pcp = per_cpu_ptr(z->pageset, cpu);
+				if (pcp->pcp.count) {
+					has_pcps = true;
+					break;
+				}
 			}
 		}
+
 		if (has_pcps)
 			cpumask_set_cpu(cpu, &cpus_with_pcps);
 		else
 			cpumask_clear_cpu(cpu, &cpus_with_pcps);
 	}
-	on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
+	on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
+								zone, 1);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -2297,7 +2331,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
 	int *contended_compaction, bool *deferred_compaction)
 {
-	struct zone *last_compact_zone = NULL;
 	unsigned long compact_result;
 	struct page *page;
 
@@ -2308,7 +2341,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
 						contended_compaction,
-						&last_compact_zone);
+						alloc_flags, classzone_idx);
 	current->flags &= ~PF_MEMALLOC;
 
 	switch (compact_result) {
@@ -2327,10 +2360,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	 */
 	count_vm_event(COMPACTSTALL);
 
-	/* Page migration frees to the PCP lists but we want merging */
-	drain_pages(get_cpu());
-	put_cpu();
-
 	page = get_page_from_freelist(gfp_mask, nodemask,
 			order, zonelist, high_zoneidx,
 			alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2346,14 +2375,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	}
 
 	/*
-	 * last_compact_zone is where try_to_compact_pages thought allocation
-	 * should succeed, so it did not defer compaction. But here we know
-	 * that it didn't succeed, so we do the defer.
-	 */
-	if (last_compact_zone && mode != MIGRATE_ASYNC)
-		defer_compaction(last_compact_zone, order);
-
-	/*
 	 * It's bad if compaction run occurs and fails. The most likely reason
 	 * is that pages exist, but not enough to satisfy watermarks.
 	 */
@@ -2434,7 +2455,7 @@ retry:
 	 * pages are pinned on the per-cpu lists. Drain them and try again
 	 */
 	if (!page && !drained) {
-		drain_all_pages();
+		drain_all_pages(NULL);
 		drained = true;
 		goto retry;
 	}
@@ -3894,14 +3915,14 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 	else
 		page_group_by_mobility_disabled = 0;
 
-	printk("Built %i zonelists in %s order, mobility grouping %s.  "
+	pr_info("Built %i zonelists in %s order, mobility grouping %s.  "
 		"Total pages: %ld\n",
 			nr_online_nodes,
 			zonelist_order_name[current_zonelist_order],
 			page_group_by_mobility_disabled ? "off" : "on",
 			vm_total_pages);
 #ifdef CONFIG_NUMA
-	printk("Policy zone: %s\n", zone_names[policy_zone]);
+	pr_info("Policy zone: %s\n", zone_names[policy_zone]);
 #endif
 }
 
@@ -5335,33 +5356,33 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	find_zone_movable_pfns_for_nodes();
 
 	/* Print out the zone ranges */
-	printk("Zone ranges:\n");
+	pr_info("Zone ranges:\n");
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		if (i == ZONE_MOVABLE)
 			continue;
-		printk(KERN_CONT "  %-8s ", zone_names[i]);
+		pr_info("  %-8s ", zone_names[i]);
 		if (arch_zone_lowest_possible_pfn[i] ==
 				arch_zone_highest_possible_pfn[i])
-			printk(KERN_CONT "empty\n");
+			pr_cont("empty\n");
 		else
-			printk(KERN_CONT "[mem %0#10lx-%0#10lx]\n",
+			pr_cont("[mem %0#10lx-%0#10lx]\n",
 				arch_zone_lowest_possible_pfn[i] << PAGE_SHIFT,
 				(arch_zone_highest_possible_pfn[i]
 					<< PAGE_SHIFT) - 1);
 	}
 
 	/* Print out the PFNs ZONE_MOVABLE begins at in each node */
-	printk("Movable zone start for each node\n");
+	pr_info("Movable zone start for each node\n");
 	for (i = 0; i < MAX_NUMNODES; i++) {
 		if (zone_movable_pfn[i])
-			printk("  Node %d: %#010lx\n", i,
+			pr_info("  Node %d: %#010lx\n", i,
 			       zone_movable_pfn[i] << PAGE_SHIFT);
 	}
 
 	/* Print out the early node map */
-	printk("Early memory node ranges\n");
+	pr_info("Early memory node ranges\n");
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
-		printk("  node %3d: [mem %#010lx-%#010lx]\n", nid,
+		pr_info("  node %3d: [mem %#010lx-%#010lx]\n", nid,
 		       start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
 
 	/* Initialise every node */
@@ -5497,7 +5518,7 @@ void __init mem_init_print_info(const char *str)
 
 #undef	adj_init_size
 
-	printk("Memory: %luK/%luK available "
+	pr_info("Memory: %luK/%luK available "
 	       "(%luK kernel code, %luK rwdata, %luK rodata, "
 	       "%luK init, %luK bss, %luK reserved"
 #ifdef	CONFIG_HIGHMEM
@@ -6386,7 +6407,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 */
 
 	lru_add_drain_all();
-	drain_all_pages();
+	drain_all_pages(cc.zone);
 
 	order = 0;
 	outer_start = start;
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 3708264d2833..5331c2bd85a2 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -171,6 +171,7 @@ static void free_page_cgroup(void *addr)
 			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
+		kmemleak_free(addr);
 		free_pages_exact(addr, table_size);
 	}
 }
diff --git a/mm/page_counter.c b/mm/page_counter.c
new file mode 100644
index 000000000000..a009574fbba9
--- /dev/null
+++ b/mm/page_counter.c
@@ -0,0 +1,192 @@
+/*
+ * Lockless hierarchical page accounting & limiting
+ *
+ * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner
+ */
+
+#include <linux/page_counter.h>
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/bug.h>
+#include <asm/page.h>
+
+/**
+ * page_counter_cancel - take pages out of the local counter
+ * @counter: counter
+ * @nr_pages: number of pages to cancel
+ */
+void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
+{
+	long new;
+
+	new = atomic_long_sub_return(nr_pages, &counter->count);
+	/* More uncharges than charges? */
+	WARN_ON_ONCE(new < 0);
+}
+
+/**
+ * page_counter_charge - hierarchically charge pages
+ * @counter: counter
+ * @nr_pages: number of pages to charge
+ *
+ * NOTE: This does not consider any configured counter limits.
+ */
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent) {
+		long new;
+
+		new = atomic_long_add_return(nr_pages, &c->count);
+		/*
+		 * This is indeed racy, but we can live with some
+		 * inaccuracy in the watermark.
+		 */
+		if (new > c->watermark)
+			c->watermark = new;
+	}
+}
+
+/**
+ * page_counter_try_charge - try to hierarchically charge pages
+ * @counter: counter
+ * @nr_pages: number of pages to charge
+ * @fail: points first counter to hit its limit, if any
+ *
+ * Returns 0 on success, or -ENOMEM and @fail if the counter or one of
+ * its ancestors has hit its configured limit.
+ */
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent) {
+		long new;
+		/*
+		 * Charge speculatively to avoid an expensive CAS.  If
+		 * a bigger charge fails, it might falsely lock out a
+		 * racing smaller charge and send it into reclaim
+		 * early, but the error is limited to the difference
+		 * between the two sizes, which is less than 2M/4M in
+		 * case of a THP locking out a regular page charge.
+		 *
+		 * The atomic_long_add_return() implies a full memory
+		 * barrier between incrementing the count and reading
+		 * the limit.  When racing with page_counter_limit(),
+		 * we either see the new limit or the setter sees the
+		 * counter has changed and retries.
+		 */
+		new = atomic_long_add_return(nr_pages, &c->count);
+		if (new > c->limit) {
+			atomic_long_sub(nr_pages, &c->count);
+			/*
+			 * This is racy, but we can live with some
+			 * inaccuracy in the failcnt.
+			 */
+			c->failcnt++;
+			*fail = c;
+			goto failed;
+		}
+		/*
+		 * Just like with failcnt, we can live with some
+		 * inaccuracy in the watermark.
+		 */
+		if (new > c->watermark)
+			c->watermark = new;
+	}
+	return 0;
+
+failed:
+	for (c = counter; c != *fail; c = c->parent)
+		page_counter_cancel(c, nr_pages);
+
+	return -ENOMEM;
+}
+
+/**
+ * page_counter_uncharge - hierarchically uncharge pages
+ * @counter: counter
+ * @nr_pages: number of pages to uncharge
+ */
+void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent)
+		page_counter_cancel(c, nr_pages);
+}
+
+/**
+ * page_counter_limit - limit the number of pages allowed
+ * @counter: counter
+ * @limit: limit to set
+ *
+ * Returns 0 on success, -EBUSY if the current number of pages on the
+ * counter already exceeds the specified limit.
+ *
+ * The caller must serialize invocations on the same counter.
+ */
+int page_counter_limit(struct page_counter *counter, unsigned long limit)
+{
+	for (;;) {
+		unsigned long old;
+		long count;
+
+		/*
+		 * Update the limit while making sure that it's not
+		 * below the concurrently-changing counter value.
+		 *
+		 * The xchg implies two full memory barriers before
+		 * and after, so the read-swap-read is ordered and
+		 * ensures coherency with page_counter_try_charge():
+		 * that function modifies the count before checking
+		 * the limit, so if it sees the old limit, we see the
+		 * modified counter and retry.
+		 */
+		count = atomic_long_read(&counter->count);
+
+		if (count > limit)
+			return -EBUSY;
+
+		old = xchg(&counter->limit, limit);
+
+		if (atomic_long_read(&counter->count) <= count)
+			return 0;
+
+		counter->limit = old;
+		cond_resched();
+	}
+}
+
+/**
+ * page_counter_memparse - memparse() for page counter limits
+ * @buf: string to parse
+ * @nr_pages: returns the result in number of pages
+ *
+ * Returns -EINVAL, or 0 and @nr_pages on success.  @nr_pages will be
+ * limited to %PAGE_COUNTER_MAX.
+ */
+int page_counter_memparse(const char *buf, unsigned long *nr_pages)
+{
+	char unlimited[] = "-1";
+	char *end;
+	u64 bytes;
+
+	if (!strncmp(buf, unlimited, sizeof(unlimited))) {
+		*nr_pages = PAGE_COUNTER_MAX;
+		return 0;
+	}
+
+	bytes = memparse(buf, &end);
+	if (*end != '\0')
+		return -EINVAL;
+
+	*nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX);
+
+	return 0;
+}
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index d1473b2e9481..3c49ef07b95d 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -67,7 +67,7 @@ out:
 
 	spin_unlock_irqrestore(&zone->lock, flags);
 	if (!ret)
-		drain_all_pages();
+		drain_all_pages(zone);
 	return ret;
 }
 
diff --git a/mm/util.c b/mm/util.c
index fec39d4509a9..d25558ba661c 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>
@@ -62,6 +63,35 @@ 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
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 90520af7f186..8a18196fcdff 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -463,8 +463,7 @@ overflow:
 		goto retry;
 	}
 	if (printk_ratelimit())
-		printk(KERN_WARNING
-			"vmap allocation for size %lu failed: "
+		pr_warn("vmap allocation for size %lu failed: "
 			"use vmalloc=<size> to increase size.\n", size);
 	kfree(va);
 	return ERR_PTR(-EBUSY);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dcb47074ae03..4636d9e822c1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -260,8 +260,7 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	do_div(delta, lru_pages + 1);
 	total_scan += delta;
 	if (total_scan < 0) {
-		printk(KERN_ERR
-		"shrink_slab: %pF negative objects to delete nr=%ld\n",
+		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
 		total_scan = freeable;
 	}
@@ -875,7 +874,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * end of the LRU a second time.
 		 */
 		mapping = page_mapping(page);
-		if ((mapping && bdi_write_congested(mapping->backing_dev_info)) ||
+		if (((dirty || writeback) && mapping &&
+		     bdi_write_congested(mapping->backing_dev_info)) ||
 		    (writeback && PageReclaim(page)))
 			nr_congested++;
 
@@ -2249,7 +2249,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
 		return true;
 
 	/* If compaction would go ahead or the allocation would succeed, stop */
-	switch (compaction_suitable(zone, sc->order)) {
+	switch (compaction_suitable(zone, sc->order, 0, 0)) {
 	case COMPACT_PARTIAL:
 	case COMPACT_CONTINUE:
 		return false;
@@ -2346,7 +2346,7 @@ static inline bool compaction_ready(struct zone *zone, int order)
 	 * If compaction is not ready to start and allocation is not likely
 	 * to succeed without it, then keep reclaiming.
 	 */
-	if (compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (compaction_suitable(zone, order, 0, 0) == COMPACT_SKIPPED)
 		return false;
 
 	return watermark_ok;
@@ -2824,8 +2824,8 @@ static bool zone_balanced(struct zone *zone, int order,
 				    balance_gap, classzone_idx, 0))
 		return false;
 
-	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
-	    compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (IS_ENABLED(CONFIG_COMPACTION) && order && compaction_suitable(zone,
+				order, 0, classzone_idx) == COMPACT_SKIPPED)
 		return false;
 
 	return true;
@@ -2952,8 +2952,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 * from memory. Do not reclaim more than needed for compaction.
 	 */
 	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
-			compaction_suitable(zone, sc->order) !=
-				COMPACT_SKIPPED)
+			compaction_suitable(zone, sc->order, 0, classzone_idx)
+							!= COMPACT_SKIPPED)
 		testorder = 0;
 
 	/*
diff --git a/mm/zbud.c b/mm/zbud.c
index ecf1dbef6983..db8de747bd5a 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -132,7 +132,7 @@ static struct zbud_ops zbud_zpool_ops = {
 
 static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
 {
-	return zbud_create_pool(gfp, &zbud_zpool_ops);
+	return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL);
 }
 
 static void zbud_zpool_destroy(void *pool)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 839a48c3ca27..b3b57ef85830 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -214,7 +214,7 @@ struct link_free {
 };
 
 struct zs_pool {
-	struct size_class size_class[ZS_SIZE_CLASSES];
+	struct size_class *size_class[ZS_SIZE_CLASSES];
 
 	gfp_t flags;	/* allocation flags used when growing pool */
 	atomic_long_t pages_allocated;
@@ -468,7 +468,7 @@ static enum fullness_group fix_fullness_group(struct zs_pool *pool,
 	if (newfg == currfg)
 		goto out;
 
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	remove_zspage(page, class, currfg);
 	insert_zspage(page, class, newfg);
 	set_zspage_mapping(page, class_idx, newfg);
@@ -925,6 +925,23 @@ fail:
 	return notifier_to_errno(ret);
 }
 
+static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
+{
+	return pages_per_zspage * PAGE_SIZE / size;
+}
+
+static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+{
+	if (prev->pages_per_zspage != pages_per_zspage)
+		return false;
+
+	if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
+		!= get_maxobj_per_zspage(size, pages_per_zspage))
+		return false;
+
+	return true;
+}
+
 /**
  * zs_create_pool - Creates an allocation pool to work from.
  * @flags: allocation flags used to allocate pool metadata
@@ -945,25 +962,56 @@ struct zs_pool *zs_create_pool(gfp_t flags)
 	if (!pool)
 		return NULL;
 
-	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
+	/*
+	 * Iterate reversly, because, size of size_class that we want to use
+	 * for merging should be larger or equal to current size.
+	 */
+	for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
 		int size;
+		int pages_per_zspage;
 		struct size_class *class;
+		struct size_class *prev_class;
 
 		size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
 		if (size > ZS_MAX_ALLOC_SIZE)
 			size = ZS_MAX_ALLOC_SIZE;
+		pages_per_zspage = get_pages_per_zspage(size);
+
+		/*
+		 * size_class is used for normal zsmalloc operation such
+		 * as alloc/free for that size. Although it is natural that we
+		 * have one size_class for each size, there is a chance that we
+		 * can get more memory utilization if we use one size_class for
+		 * many different sizes whose size_class have same
+		 * characteristics. So, we makes size_class point to
+		 * previous size_class if possible.
+		 */
+		if (i < ZS_SIZE_CLASSES - 1) {
+			prev_class = pool->size_class[i + 1];
+			if (can_merge(prev_class, size, pages_per_zspage)) {
+				pool->size_class[i] = prev_class;
+				continue;
+			}
+		}
+
+		class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
+		if (!class)
+			goto err;
 
-		class = &pool->size_class[i];
 		class->size = size;
 		class->index = i;
+		class->pages_per_zspage = pages_per_zspage;
 		spin_lock_init(&class->lock);
-		class->pages_per_zspage = get_pages_per_zspage(size);
-
+		pool->size_class[i] = class;
 	}
 
 	pool->flags = flags;
 
 	return pool;
+
+err:
+	zs_destroy_pool(pool);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(zs_create_pool);
 
@@ -973,7 +1021,13 @@ void zs_destroy_pool(struct zs_pool *pool)
 
 	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
 		int fg;
-		struct size_class *class = &pool->size_class[i];
+		struct size_class *class = pool->size_class[i];
+
+		if (!class)
+			continue;
+
+		if (class->index != i)
+			continue;
 
 		for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
 			if (class->fullness_list[fg]) {
@@ -981,6 +1035,7 @@ void zs_destroy_pool(struct zs_pool *pool)
 					class->size, fg);
 			}
 		}
+		kfree(class);
 	}
 	kfree(pool);
 }
@@ -999,7 +1054,6 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 {
 	unsigned long obj;
 	struct link_free *link;
-	int class_idx;
 	struct size_class *class;
 
 	struct page *first_page, *m_page;
@@ -1008,9 +1062,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 	if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
 		return 0;
 
-	class_idx = get_size_class_index(size);
-	class = &pool->size_class[class_idx];
-	BUG_ON(class_idx != class->index);
+	class = pool->size_class[get_size_class_index(size)];
 
 	spin_lock(&class->lock);
 	first_page = find_get_zspage(class);
@@ -1063,7 +1115,7 @@ void zs_free(struct zs_pool *pool, unsigned long obj)
 	first_page = get_first_page(f_page);
 
 	get_zspage_mapping(first_page, &class_idx, &fullness);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
 
 	spin_lock(&class->lock);
@@ -1124,7 +1176,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 
 	obj_handle_to_location(handle, &page, &obj_idx);
 	get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
 	area = &get_cpu_var(zs_map_area);
@@ -1158,7 +1210,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 
 	obj_handle_to_location(handle, &page, &obj_idx);
 	get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
 	area = this_cpu_ptr(&zs_map_area);
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 1d191357bf88..272327134a1b 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -9,13 +9,13 @@
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	/*
-	 * The root cgroup does not use res_counters, but rather,
+	 * The root cgroup does not use page_counters, but rather,
 	 * rely on the data already collected by the network
 	 * subsystem
 	 */
-	struct res_counter *res_parent = NULL;
-	struct cg_proto *cg_proto, *parent_cg;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct page_counter *counter_parent = NULL;
+	struct cg_proto *cg_proto, *parent_cg;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
@@ -29,9 +29,9 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
 	if (parent_cg)
-		res_parent = &parent_cg->memory_allocated;
+		counter_parent = &parent_cg->memory_allocated;
 
-	res_counter_init(&cg_proto->memory_allocated, res_parent);
+	page_counter_init(&cg_proto->memory_allocated, counter_parent);
 	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
 
 	return 0;
@@ -50,7 +50,7 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
-static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
 {
 	struct cg_proto *cg_proto;
 	int i;
@@ -60,20 +60,17 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	if (!cg_proto)
 		return -EINVAL;
 
-	if (val > RES_COUNTER_MAX)
-		val = RES_COUNTER_MAX;
-
-	ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
+	ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages);
 	if (ret)
 		return ret;
 
 	for (i = 0; i < 3; i++)
-		cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT,
+		cg_proto->sysctl_mem[i] = min_t(long, nr_pages,
 						sysctl_tcp_mem[i]);
 
-	if (val == RES_COUNTER_MAX)
+	if (nr_pages == PAGE_COUNTER_MAX)
 		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-	else if (val != RES_COUNTER_MAX) {
+	else {
 		/*
 		 * The active bit needs to be written after the static_key
 		 * update. This is what guarantees that the socket activation
@@ -102,11 +99,20 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
+static DEFINE_MUTEX(tcp_limit_mutex);
+
 static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret = 0;
 
 	buf = strstrip(buf);
@@ -114,10 +120,12 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buf, &val);
+		ret = page_counter_memparse(buf, &nr_pages);
 		if (ret)
 			break;
-		ret = tcp_update_limit(memcg, val);
+		mutex_lock(&tcp_limit_mutex);
+		ret = tcp_update_limit(memcg, nr_pages);
+		mutex_unlock(&tcp_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -126,43 +134,36 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
-static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return default_val;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, type);
-}
-
-static u64 tcp_read_usage(struct mem_cgroup *memcg)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE);
-}
-
 static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg);
 	u64 val;
 
 	switch (cft->private) {
 	case RES_LIMIT:
-		val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
+		if (!cg_proto)
+			return PAGE_COUNTER_MAX;
+		val = cg_proto->memory_allocated.limit;
+		val *= PAGE_SIZE;
 		break;
 	case RES_USAGE:
-		val = tcp_read_usage(memcg);
+		if (!cg_proto)
+			val = atomic_long_read(&tcp_memory_allocated);
+		else
+			val = page_counter_read(&cg_proto->memory_allocated);
+		val *= PAGE_SIZE;
 		break;
 	case RES_FAILCNT:
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.failcnt;
+		break;
 	case RES_MAX_USAGE:
-		val = tcp_read_stat(memcg, cft->private, 0);
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.watermark;
+		val *= PAGE_SIZE;
 		break;
 	default:
 		BUG();
@@ -183,10 +184,10 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
 
 	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&cg_proto->memory_allocated);
+		page_counter_reset_watermark(&cg_proto->memory_allocated);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&cg_proto->memory_allocated);
+		cg_proto->memory_allocated.failcnt = 0;
 		break;
 	}
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 374abf443636..d94f5d879fb1 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2515,7 +2515,8 @@ sub process {
 			}
 		}
 
-		if ($line =~ /^\+.*\(\s*$Type\s*\)[ \t]+(?!$Assignment|$Arithmetic|{)/) {
+		if ($line =~ /^\+.*(\w+\s*)?\(\s*$Type\s*\)[ \t]+(?!$Assignment|$Arithmetic|[,;\({\[\<\>])/ &&
+		    (!defined($1) || $1 !~ /sizeof\s*/)) {
 			if (CHK("SPACING",
 				"No space is necessary after a cast\n" . $herecurr) &&
 			    $fix) {
@@ -3563,14 +3564,33 @@ sub process {
 						}
 					}
 
-				# , must have a space on the right.
+				# , must not have a space before and must have a space on the right.
 				} elsif ($op eq ',') {
+					my $rtrim_before = 0;
+					my $space_after = 0;
+					if ($ctx =~ /Wx./) {
+						if (ERROR("SPACING",
+							  "space prohibited before that '$op' $at\n" . $hereptr)) {
+							$line_fixed = 1;
+							$rtrim_before = 1;
+						}
+					}
 					if ($ctx !~ /.x[WEC]/ && $cc !~ /^}/) {
 						if (ERROR("SPACING",
 							  "space required after that '$op' $at\n" . $hereptr)) {
-							$good = $fix_elements[$n] . trim($fix_elements[$n + 1]) . " ";
 							$line_fixed = 1;
 							$last_after = $n;
+							$space_after = 1;
+						}
+					}
+					if ($rtrim_before || $space_after) {
+						if ($rtrim_before) {
+							$good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
+						} else {
+							$good = $fix_elements[$n] . trim($fix_elements[$n + 1]);
+						}
+						if ($space_after) {
+							$good .= " ";
 						}
 					}
 
@@ -4652,6 +4672,15 @@ sub process {
 			}
 		}
 
+# Check for __attribute__ weak, or __weak declarations (may have link issues)
+		if ($^V && $^V ge 5.10.0 &&
+		    $line =~ /(?:$Declare|$DeclareMisordered)\s*$Ident\s*$balanced_parens\s*(?:$Attribute)?\s*;/ &&
+		    ($line =~ /\b__attribute__\s*\(\s*\(.*\bweak\b/ ||
+		     $line =~ /\b__weak\b/)) {
+			ERROR("WEAK_DECLARATION",
+			      "Using weak declarations can have unintended link defects\n" . $herecurr);
+		}
+
 # check for sizeof(&)
 		if ($line =~ /\bsizeof\s*\(\s*\&/) {
 			WARN("SIZEOF_ADDRESS",
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index d515ec25ae9f..15d985ce42a7 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -53,6 +53,7 @@
 #define SMK_SENDING	2
 
 LIST_HEAD(smk_ipv6_port_list);
+static struct kmem_cache *smack_inode_cache;
 
 #ifdef CONFIG_SECURITY_SMACK_BRINGUP
 static void smk_bu_mode(int mode, char *s)
@@ -240,7 +241,7 @@ struct inode_smack *new_inode_smack(struct smack_known *skp)
 {
 	struct inode_smack *isp;
 
-	isp = kzalloc(sizeof(struct inode_smack), GFP_NOFS);
+	isp = kmem_cache_zalloc(smack_inode_cache, GFP_NOFS);
 	if (isp == NULL)
 		return NULL;
 
@@ -767,7 +768,7 @@ static int smack_inode_alloc_security(struct inode *inode)
  */
 static void smack_inode_free_security(struct inode *inode)
 {
-	kfree(inode->i_security);
+	kmem_cache_free(smack_inode_cache, inode->i_security);
 	inode->i_security = NULL;
 }
 
@@ -4264,10 +4265,16 @@ static __init int smack_init(void)
 	if (!security_module_enable(&smack_ops))
 		return 0;
 
+	smack_inode_cache = KMEM_CACHE(inode_smack, 0);
+	if (!smack_inode_cache)
+		return -ENOMEM;
+
 	tsp = new_task_smack(&smack_known_floor, &smack_known_floor,
 				GFP_KERNEL);
-	if (tsp == NULL)
+	if (tsp == NULL) {
+		kmem_cache_destroy(smack_inode_cache);
 		return -ENOMEM;
+	}
 
 	printk(KERN_INFO "Smack:  Initializing.\n");
 
diff --git a/usr/Kconfig b/usr/Kconfig
index 2d4c77eecf2e..572dcf7b6a44 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -46,17 +46,17 @@ config INITRAMFS_ROOT_GID
 	  If you are not sure, leave it set to "0".
 
 config RD_GZIP
-	bool "Support initial ramdisks compressed using gzip" if EXPERT
-	default y
+	bool "Support initial ramdisks compressed using gzip"
 	depends on BLK_DEV_INITRD
+	default y
 	select DECOMPRESS_GZIP
 	help
 	  Support loading of a gzip encoded initial ramdisk or cpio buffer.
 	  If unsure, say Y.
 
 config RD_BZIP2
-	bool "Support initial ramdisks compressed using bzip2" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using bzip2"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_BZIP2
 	help
@@ -64,8 +64,8 @@ config RD_BZIP2
 	  If unsure, say N.
 
 config RD_LZMA
-	bool "Support initial ramdisks compressed using LZMA" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using LZMA"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZMA
 	help
@@ -73,17 +73,17 @@ config RD_LZMA
 	  If unsure, say N.
 
 config RD_XZ
-	bool "Support initial ramdisks compressed using XZ" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using XZ"
 	depends on BLK_DEV_INITRD
+	default y
 	select DECOMPRESS_XZ
 	help
 	  Support loading of a XZ encoded initial ramdisk or cpio buffer.
 	  If unsure, say N.
 
 config RD_LZO
-	bool "Support initial ramdisks compressed using LZO" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using LZO"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZO
 	help
@@ -91,8 +91,8 @@ config RD_LZO
 	  If unsure, say N.
 
 config RD_LZ4
-	bool "Support initial ramdisks compressed using LZ4" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using LZ4"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZ4
 	help