Merge branch 'akpm' (incoming from Andrew)

Merge second patch-bomb from Andrew Morton:
 - the rest of MM
 - zram updates
 - zswap updates
 - exit
 - procfs
 - exec
 - wait
 - crash dump
 - lib/idr
 - rapidio
 - adfs, affs, bfs, ufs
 - cris
 - Kconfig things
 - initramfs
 - small amount of IPC material
 - percpu enhancements
 - early ioremap support
 - various other misc things

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (156 commits)
  MAINTAINERS: update Intel C600 SAS driver maintainers
  fs/ufs: remove unused ufs_super_block_third pointer
  fs/ufs: remove unused ufs_super_block_second pointer
  fs/ufs: remove unused ufs_super_block_first pointer
  fs/ufs/super.c: add __init to init_inodecache()
  doc/kernel-parameters.txt: add early_ioremap_debug
  arm64: add early_ioremap support
  arm64: initialize pgprot info earlier in boot
  x86: use generic early_ioremap
  mm: create generic early_ioremap() support
  x86/mm: sparse warning fix for early_memremap
  lglock: map to spinlock when !CONFIG_SMP
  percpu: add preemption checks to __this_cpu ops
  vmstat: use raw_cpu_ops to avoid false positives on preemption checks
  slub: use raw_cpu_inc for incrementing statistics
  net: replace __this_cpu_inc in route.c with raw_cpu_inc
  modules: use raw_cpu_write for initialization of per cpu refcount.
  mm: use raw_cpu ops for determining current NUMA node
  percpu: add raw_cpu_ops
  slub: fix leak of 'name' in sysfs_slab_add
  ...

20 files changed, 327 insertions, 244 deletions

diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index b4a745d7d9a..61f29e5ea84 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -44,7 +44,6 @@ struct linux_binprm {
 	unsigned interp_flags;
 	unsigned interp_data;
 	unsigned long loader, exec;
-	char tcomm[TASK_COMM_LEN];
 };
 
 #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 7032518f854..72ab536ad3d 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -25,6 +25,7 @@ extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
+void vmcore_cleanup(void);
 
 /* Architecture code defines this if there are other possible ELF
  * machine types, e.g. on bi-arch capable hardware. */
diff --git a/include/linux/idr.h b/include/linux/idr.h
index f669585c4fc..6af3400b9b2 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -133,69 +133,6 @@ static inline void *idr_find(struct idr *idr, int id)
 	for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id)
 
 /*
- * Don't use the following functions.  These exist only to suppress
- * deprecated warnings on EXPORT_SYMBOL()s.
- */
-int __idr_pre_get(struct idr *idp, gfp_t gfp_mask);
-int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id);
-void __idr_remove_all(struct idr *idp);
-
-/**
- * idr_pre_get - reserve resources for idr allocation
- * @idp:	idr handle
- * @gfp_mask:	memory allocation flags
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_pre_get(struct idr *idp, gfp_t gfp_mask)
-{
-	return __idr_pre_get(idp, gfp_mask);
-}
-
-/**
- * idr_get_new_above - allocate new idr entry above or equal to a start id
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @starting_id: id to start search at
- * @id: pointer to the allocated handle
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_get_new_above(struct idr *idp, void *ptr,
-						 int starting_id, int *id)
-{
-	return __idr_get_new_above(idp, ptr, starting_id, id);
-}
-
-/**
- * idr_get_new - allocate new idr entry
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @id: pointer to the allocated handle
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_get_new(struct idr *idp, void *ptr, int *id)
-{
-	return __idr_get_new_above(idp, ptr, 0, id);
-}
-
-/**
- * idr_remove_all - remove all ids from the given idr tree
- * @idp: idr handle
- *
- * If you're trying to destroy @idp, calling idr_destroy() is enough.
- * This is going away.  Don't use.
- */
-static inline void __deprecated idr_remove_all(struct idr *idp)
-{
-	__idr_remove_all(idp);
-}
-
-/*
  * IDA - IDR based id allocator, use when translation from id to
  * pointer isn't necessary.
  *
diff --git a/include/linux/io.h b/include/linux/io.h
index 8a18e75600c..b76e6e54580 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -41,7 +41,7 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end,
 /*
  * Managed iomap interface
  */
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 void __iomem * devm_ioport_map(struct device *dev, unsigned long port,
 			       unsigned int nr);
 void devm_ioport_unmap(struct device *dev, void __iomem *addr);
diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index 96549abe884..0081f000e34 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -25,6 +25,8 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 
+#ifdef CONFIG_SMP
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 #define LOCKDEP_INIT_MAP lockdep_init_map
 #else
@@ -57,4 +59,18 @@ void lg_local_unlock_cpu(struct lglock *lg, int cpu);
 void lg_global_lock(struct lglock *lg);
 void lg_global_unlock(struct lglock *lg);
 
+#else
+/* When !CONFIG_SMP, map lglock to spinlock */
+#define lglock spinlock
+#define DEFINE_LGLOCK(name) DEFINE_SPINLOCK(name)
+#define DEFINE_STATIC_LGLOCK(name) static DEFINE_SPINLOCK(name)
+#define lg_lock_init(lg, name) spin_lock_init(lg)
+#define lg_local_lock spin_lock
+#define lg_local_unlock spin_unlock
+#define lg_local_lock_cpu(lg, cpu) spin_lock(lg)
+#define lg_local_unlock_cpu(lg, cpu) spin_unlock(lg)
+#define lg_global_lock spin_lock
+#define lg_global_unlock spin_unlock
+#endif
+
 #endif
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index eccfb4a4b37..b569b8be5c5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -65,7 +65,7 @@ struct mem_cgroup_reclaim_cookie {
  * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.)
  */
 
-extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
+extern int mem_cgroup_charge_anon(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 /* for swap handling */
 extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
@@ -74,7 +74,7 @@ extern void mem_cgroup_commit_charge_swapin(struct page *page,
 					struct mem_cgroup *memcg);
 extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg);
 
-extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+extern int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask);
 
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
@@ -94,7 +94,6 @@ bool task_in_mem_cgroup(struct task_struct *task,
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
-extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
@@ -234,13 +233,13 @@ void mem_cgroup_print_bad_page(struct page *page);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
-static inline int mem_cgroup_newpage_charge(struct page *page,
+static inline int mem_cgroup_charge_anon(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
 	return 0;
 }
 
-static inline int mem_cgroup_cache_charge(struct page *page,
+static inline int mem_cgroup_charge_file(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
 	return 0;
@@ -294,11 +293,6 @@ static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	return NULL;
 }
 
-static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
-{
-	return NULL;
-}
-
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 		struct mem_cgroup *memcg)
 {
@@ -497,6 +491,9 @@ void __memcg_kmem_commit_charge(struct page *page,
 void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
+
+char *memcg_create_cache_name(struct mem_cgroup *memcg,
+			      struct kmem_cache *root_cache);
 int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s,
 			     struct kmem_cache *root_cache);
 void memcg_free_cache_params(struct kmem_cache *s);
@@ -510,7 +507,7 @@ struct kmem_cache *
 __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 
 void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
-void kmem_cache_destroy_memcg_children(struct kmem_cache *s);
+int __kmem_cache_destroy_memcg_children(struct kmem_cache *s);
 
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
@@ -664,10 +661,6 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	return cachep;
 }
-
-static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5f1ea756aac..3c1b968da0c 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -143,7 +143,6 @@ extern void numa_policy_init(void);
 extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
 				enum mpol_rebind_step step);
 extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
-extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 				unsigned long addr, gfp_t gfp_flags,
@@ -151,7 +150,7 @@ extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				const nodemask_t *mask);
-extern unsigned slab_node(void);
+extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 35300f390eb..abc848412e3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -177,6 +177,9 @@ extern unsigned int kobjsize(const void *objp);
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
+/* This mask defines which mm->def_flags a process can inherit its parent */
+#define VM_INIT_DEF_MASK	VM_NOHUGEPAGE
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
@@ -210,6 +213,10 @@ struct vm_fault {
 					 * is set (which is also implied by
 					 * VM_FAULT_ERROR).
 					 */
+	/* for ->map_pages() only */
+	pgoff_t max_pgoff;		/* map pages for offset from pgoff till
+					 * max_pgoff inclusive */
+	pte_t *pte;			/* pte entry associated with ->pgoff */
 };
 
 /*
@@ -221,6 +228,7 @@ struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
@@ -581,6 +589,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 		pte = pte_mkwrite(pte);
 	return pte;
 }
+
+void do_set_pte(struct vm_area_struct *vma, unsigned long address,
+		struct page *page, pte_t *pte, bool write, bool anon);
 #endif
 
 /*
@@ -684,7 +695,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
 #define NODES_MASK		((1UL << NODES_WIDTH) - 1)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
-#define LAST_CPUPID_MASK	((1UL << LAST_CPUPID_WIDTH) - 1)
+#define LAST_CPUPID_MASK	((1UL << LAST_CPUPID_SHIFT) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
 static inline enum zone_type page_zonenum(const struct page *page)
@@ -1836,6 +1847,7 @@ extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
+extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 /* mm/page-writeback.c */
@@ -1863,9 +1875,6 @@ void page_cache_async_readahead(struct address_space *mapping,
 				unsigned long size);
 
 unsigned long max_sane_readahead(unsigned long nr);
-unsigned long ra_submit(struct file_ra_state *ra,
-			struct address_space *mapping,
-			struct file *filp);
 
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 290901a8c1d..2b58d192ea2 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -342,9 +342,9 @@ struct mm_rss_stat {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct * mmap;		/* list of VMAs */
+	struct vm_area_struct *mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
-	struct vm_area_struct * mmap_cache;	/* last find_vma result */
+	u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 5042c036dda..2d57efa64cc 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -3,8 +3,8 @@
 
 struct page;
 
-extern void dump_page(struct page *page, char *reason);
-extern void dump_page_badflags(struct page *page, char *reason,
+extern void dump_page(struct page *page, const char *reason);
+extern void dump_page_badflags(struct page *page, const char *reason,
 			       unsigned long badflags);
 
 #ifdef CONFIG_DEBUG_VM
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index e3817d2441b..e7a0b95ed52 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -173,6 +173,12 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 
 extern void __bad_size_call_parameter(void);
 
+#ifdef CONFIG_DEBUG_PREEMPT
+extern void __this_cpu_preempt_check(const char *op);
+#else
+static inline void __this_cpu_preempt_check(const char *op) { }
+#endif
+
 #define __pcpu_size_call_return(stem, variable)				\
 ({	typeof(variable) pscr_ret__;					\
 	__verify_pcpu_ptr(&(variable));					\
@@ -243,6 +249,8 @@ do {									\
 } while (0)
 
 /*
+ * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com>
+ *
  * Optimized manipulation for memory allocated through the per cpu
  * allocator or for addresses of per cpu variables.
  *
@@ -296,7 +304,7 @@ do {									\
 do {									\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	*__this_cpu_ptr(&(pcp)) op val;					\
+	*raw_cpu_ptr(&(pcp)) op val;					\
 	raw_local_irq_restore(flags);					\
 } while (0)
 
@@ -381,8 +389,8 @@ do {									\
 	typeof(pcp) ret__;						\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	__this_cpu_add(pcp, val);					\
-	ret__ = __this_cpu_read(pcp);					\
+	raw_cpu_add(pcp, val);					\
+	ret__ = raw_cpu_read(pcp);					\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
 })
@@ -411,8 +419,8 @@ do {									\
 ({	typeof(pcp) ret__;						\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	ret__ = __this_cpu_read(pcp);					\
-	__this_cpu_write(pcp, nval);					\
+	ret__ = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
 })
@@ -439,9 +447,9 @@ do {									\
 	typeof(pcp) ret__;						\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	ret__ = __this_cpu_read(pcp);					\
+	ret__ = raw_cpu_read(pcp);					\
 	if (ret__ == (oval))						\
-		__this_cpu_write(pcp, nval);				\
+		raw_cpu_write(pcp, nval);				\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
 })
@@ -476,7 +484,7 @@ do {									\
 	int ret__;							\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+	ret__ = raw_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
 			oval1, oval2, nval1, nval2);			\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
@@ -504,12 +512,8 @@ do {									\
 #endif
 
 /*
- * Generic percpu operations for context that are safe from preemption/interrupts.
- * Either we do not care about races or the caller has the
- * responsibility of handling preemption/interrupt issues. Arch code can still
- * override these instructions since the arch per cpu code may be more
- * efficient and may actually get race freeness for free (that is the
- * case for x86 for example).
+ * Generic percpu operations for contexts where we do not want to do
+ * any checks for preemptiosn.
  *
  * If there is no other protection through preempt disable and/or
  * disabling interupts then one of these RMW operations can show unexpected
@@ -517,211 +521,285 @@ do {									\
  * or an interrupt occurred and the same percpu variable was modified from
  * the interrupt context.
  */
-#ifndef __this_cpu_read
-# ifndef __this_cpu_read_1
-#  define __this_cpu_read_1(pcp)	(*__this_cpu_ptr(&(pcp)))
+#ifndef raw_cpu_read
+# ifndef raw_cpu_read_1
+#  define raw_cpu_read_1(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# ifndef __this_cpu_read_2
-#  define __this_cpu_read_2(pcp)	(*__this_cpu_ptr(&(pcp)))
+# ifndef raw_cpu_read_2
+#  define raw_cpu_read_2(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# ifndef __this_cpu_read_4
-#  define __this_cpu_read_4(pcp)	(*__this_cpu_ptr(&(pcp)))
+# ifndef raw_cpu_read_4
+#  define raw_cpu_read_4(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# ifndef __this_cpu_read_8
-#  define __this_cpu_read_8(pcp)	(*__this_cpu_ptr(&(pcp)))
+# ifndef raw_cpu_read_8
+#  define raw_cpu_read_8(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# define __this_cpu_read(pcp)	__pcpu_size_call_return(__this_cpu_read_, (pcp))
+# define raw_cpu_read(pcp)	__pcpu_size_call_return(raw_cpu_read_, (pcp))
 #endif
 
-#define __this_cpu_generic_to_op(pcp, val, op)				\
+#define raw_cpu_generic_to_op(pcp, val, op)				\
 do {									\
-	*__this_cpu_ptr(&(pcp)) op val;					\
+	*raw_cpu_ptr(&(pcp)) op val;					\
 } while (0)
 
-#ifndef __this_cpu_write
-# ifndef __this_cpu_write_1
-#  define __this_cpu_write_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+
+#ifndef raw_cpu_write
+# ifndef raw_cpu_write_1
+#  define raw_cpu_write_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# ifndef __this_cpu_write_2
-#  define __this_cpu_write_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# ifndef raw_cpu_write_2
+#  define raw_cpu_write_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# ifndef __this_cpu_write_4
-#  define __this_cpu_write_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# ifndef raw_cpu_write_4
+#  define raw_cpu_write_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# ifndef __this_cpu_write_8
-#  define __this_cpu_write_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# ifndef raw_cpu_write_8
+#  define raw_cpu_write_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# define __this_cpu_write(pcp, val)	__pcpu_size_call(__this_cpu_write_, (pcp), (val))
+# define raw_cpu_write(pcp, val)	__pcpu_size_call(raw_cpu_write_, (pcp), (val))
 #endif
 
-#ifndef __this_cpu_add
-# ifndef __this_cpu_add_1
-#  define __this_cpu_add_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+#ifndef raw_cpu_add
+# ifndef raw_cpu_add_1
+#  define raw_cpu_add_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# ifndef __this_cpu_add_2
-#  define __this_cpu_add_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# ifndef raw_cpu_add_2
+#  define raw_cpu_add_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# ifndef __this_cpu_add_4
-#  define __this_cpu_add_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# ifndef raw_cpu_add_4
+#  define raw_cpu_add_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# ifndef __this_cpu_add_8
-#  define __this_cpu_add_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# ifndef raw_cpu_add_8
+#  define raw_cpu_add_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# define __this_cpu_add(pcp, val)	__pcpu_size_call(__this_cpu_add_, (pcp), (val))
+# define raw_cpu_add(pcp, val)	__pcpu_size_call(raw_cpu_add_, (pcp), (val))
 #endif
 
-#ifndef __this_cpu_sub
-# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(typeof(pcp))(val))
+#ifndef raw_cpu_sub
+# define raw_cpu_sub(pcp, val)	raw_cpu_add((pcp), -(val))
 #endif
 
-#ifndef __this_cpu_inc
-# define __this_cpu_inc(pcp)		__this_cpu_add((pcp), 1)
+#ifndef raw_cpu_inc
+# define raw_cpu_inc(pcp)		raw_cpu_add((pcp), 1)
 #endif
 
-#ifndef __this_cpu_dec
-# define __this_cpu_dec(pcp)		__this_cpu_sub((pcp), 1)
+#ifndef raw_cpu_dec
+# define raw_cpu_dec(pcp)		raw_cpu_sub((pcp), 1)
 #endif
 
-#ifndef __this_cpu_and
-# ifndef __this_cpu_and_1
-#  define __this_cpu_and_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+#ifndef raw_cpu_and
+# ifndef raw_cpu_and_1
+#  define raw_cpu_and_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# ifndef __this_cpu_and_2
-#  define __this_cpu_and_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# ifndef raw_cpu_and_2
+#  define raw_cpu_and_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# ifndef __this_cpu_and_4
-#  define __this_cpu_and_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# ifndef raw_cpu_and_4
+#  define raw_cpu_and_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# ifndef __this_cpu_and_8
-#  define __this_cpu_and_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# ifndef raw_cpu_and_8
+#  define raw_cpu_and_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# define __this_cpu_and(pcp, val)	__pcpu_size_call(__this_cpu_and_, (pcp), (val))
+# define raw_cpu_and(pcp, val)	__pcpu_size_call(raw_cpu_and_, (pcp), (val))
 #endif
 
-#ifndef __this_cpu_or
-# ifndef __this_cpu_or_1
-#  define __this_cpu_or_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+#ifndef raw_cpu_or
+# ifndef raw_cpu_or_1
+#  define raw_cpu_or_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# ifndef __this_cpu_or_2
-#  define __this_cpu_or_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# ifndef raw_cpu_or_2
+#  define raw_cpu_or_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# ifndef __this_cpu_or_4
-#  define __this_cpu_or_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# ifndef raw_cpu_or_4
+#  define raw_cpu_or_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# ifndef __this_cpu_or_8
-#  define __this_cpu_or_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# ifndef raw_cpu_or_8
+#  define raw_cpu_or_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# define __this_cpu_or(pcp, val)	__pcpu_size_call(__this_cpu_or_, (pcp), (val))
+# define raw_cpu_or(pcp, val)	__pcpu_size_call(raw_cpu_or_, (pcp), (val))
 #endif
 
-#define __this_cpu_generic_add_return(pcp, val)				\
+#define raw_cpu_generic_add_return(pcp, val)				\
 ({									\
-	__this_cpu_add(pcp, val);					\
-	__this_cpu_read(pcp);						\
+	raw_cpu_add(pcp, val);						\
+	raw_cpu_read(pcp);						\
 })
 
-#ifndef __this_cpu_add_return
-# ifndef __this_cpu_add_return_1
-#  define __this_cpu_add_return_1(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+#ifndef raw_cpu_add_return
+# ifndef raw_cpu_add_return_1
+#  define raw_cpu_add_return_1(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# ifndef __this_cpu_add_return_2
-#  define __this_cpu_add_return_2(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# ifndef raw_cpu_add_return_2
+#  define raw_cpu_add_return_2(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# ifndef __this_cpu_add_return_4
-#  define __this_cpu_add_return_4(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# ifndef raw_cpu_add_return_4
+#  define raw_cpu_add_return_4(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# ifndef __this_cpu_add_return_8
-#  define __this_cpu_add_return_8(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# ifndef raw_cpu_add_return_8
+#  define raw_cpu_add_return_8(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# define __this_cpu_add_return(pcp, val)	\
-	__pcpu_size_call_return2(__this_cpu_add_return_, pcp, val)
+# define raw_cpu_add_return(pcp, val)	\
+	__pcpu_size_call_return2(raw_add_return_, pcp, val)
 #endif
 
-#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
-#define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
-#define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)
+#define raw_cpu_sub_return(pcp, val)	raw_cpu_add_return(pcp, -(typeof(pcp))(val))
+#define raw_cpu_inc_return(pcp)	raw_cpu_add_return(pcp, 1)
+#define raw_cpu_dec_return(pcp)	raw_cpu_add_return(pcp, -1)
 
-#define __this_cpu_generic_xchg(pcp, nval)				\
+#define raw_cpu_generic_xchg(pcp, nval)					\
 ({	typeof(pcp) ret__;						\
-	ret__ = __this_cpu_read(pcp);					\
-	__this_cpu_write(pcp, nval);					\
+	ret__ = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
 	ret__;								\
 })
 
-#ifndef __this_cpu_xchg
-# ifndef __this_cpu_xchg_1
-#  define __this_cpu_xchg_1(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+#ifndef raw_cpu_xchg
+# ifndef raw_cpu_xchg_1
+#  define raw_cpu_xchg_1(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# ifndef __this_cpu_xchg_2
-#  define __this_cpu_xchg_2(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# ifndef raw_cpu_xchg_2
+#  define raw_cpu_xchg_2(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# ifndef __this_cpu_xchg_4
-#  define __this_cpu_xchg_4(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# ifndef raw_cpu_xchg_4
+#  define raw_cpu_xchg_4(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# ifndef __this_cpu_xchg_8
-#  define __this_cpu_xchg_8(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# ifndef raw_cpu_xchg_8
+#  define raw_cpu_xchg_8(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# define __this_cpu_xchg(pcp, nval)	\
-	__pcpu_size_call_return2(__this_cpu_xchg_, (pcp), nval)
+# define raw_cpu_xchg(pcp, nval)	\
+	__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval)
 #endif
 
-#define __this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
 	typeof(pcp) ret__;						\
-	ret__ = __this_cpu_read(pcp);					\
+	ret__ = raw_cpu_read(pcp);					\
 	if (ret__ == (oval))						\
-		__this_cpu_write(pcp, nval);				\
+		raw_cpu_write(pcp, nval);				\
 	ret__;								\
 })
 
-#ifndef __this_cpu_cmpxchg
-# ifndef __this_cpu_cmpxchg_1
-#  define __this_cpu_cmpxchg_1(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+#ifndef raw_cpu_cmpxchg
+# ifndef raw_cpu_cmpxchg_1
+#  define raw_cpu_cmpxchg_1(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# ifndef __this_cpu_cmpxchg_2
-#  define __this_cpu_cmpxchg_2(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# ifndef raw_cpu_cmpxchg_2
+#  define raw_cpu_cmpxchg_2(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# ifndef __this_cpu_cmpxchg_4
-#  define __this_cpu_cmpxchg_4(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# ifndef raw_cpu_cmpxchg_4
+#  define raw_cpu_cmpxchg_4(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# ifndef __this_cpu_cmpxchg_8
-#  define __this_cpu_cmpxchg_8(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# ifndef raw_cpu_cmpxchg_8
+#  define raw_cpu_cmpxchg_8(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# define __this_cpu_cmpxchg(pcp, oval, nval)	\
-	__pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval)
+# define raw_cpu_cmpxchg(pcp, oval, nval)	\
+	__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
 #endif
 
-#define __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
 ({									\
 	int __ret = 0;							\
-	if (__this_cpu_read(pcp1) == (oval1) &&				\
-			 __this_cpu_read(pcp2)  == (oval2)) {		\
-		__this_cpu_write(pcp1, (nval1));			\
-		__this_cpu_write(pcp2, (nval2));			\
+	if (raw_cpu_read(pcp1) == (oval1) &&				\
+			 raw_cpu_read(pcp2)  == (oval2)) {		\
+		raw_cpu_write(pcp1, (nval1));				\
+		raw_cpu_write(pcp2, (nval2));				\
 		__ret = 1;						\
 	}								\
 	(__ret);							\
 })
 
-#ifndef __this_cpu_cmpxchg_double
-# ifndef __this_cpu_cmpxchg_double_1
-#  define __this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#ifndef raw_cpu_cmpxchg_double
+# ifndef raw_cpu_cmpxchg_double_1
+#  define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
-# ifndef __this_cpu_cmpxchg_double_2
-#  define __this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# ifndef raw_cpu_cmpxchg_double_2
+#  define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
-# ifndef __this_cpu_cmpxchg_double_4
-#  define __this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# ifndef raw_cpu_cmpxchg_double_4
+#  define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
-# ifndef __this_cpu_cmpxchg_double_8
-#  define __this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# ifndef raw_cpu_cmpxchg_double_8
+#  define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
+# define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
+/*
+ * Generic percpu operations for context that are safe from preemption/interrupts.
+ */
+#ifndef __this_cpu_read
+# define __this_cpu_read(pcp) \
+	(__this_cpu_preempt_check("read"),__pcpu_size_call_return(raw_cpu_read_, (pcp)))
+#endif
+
+#ifndef __this_cpu_write
+# define __this_cpu_write(pcp, val)					\
+do { __this_cpu_preempt_check("write");					\
+     __pcpu_size_call(raw_cpu_write_, (pcp), (val));			\
+} while (0)
+#endif
+
+#ifndef __this_cpu_add
+# define __this_cpu_add(pcp, val)					 \
+do { __this_cpu_preempt_check("add");					\
+	__pcpu_size_call(raw_cpu_add_, (pcp), (val));			\
+} while (0)
+#endif
+
+#ifndef __this_cpu_sub
+# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(typeof(pcp))(val))
+#endif
+
+#ifndef __this_cpu_inc
+# define __this_cpu_inc(pcp)		__this_cpu_add((pcp), 1)
+#endif
+
+#ifndef __this_cpu_dec
+# define __this_cpu_dec(pcp)		__this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef __this_cpu_and
+# define __this_cpu_and(pcp, val)					\
+do { __this_cpu_preempt_check("and");					\
+	__pcpu_size_call(raw_cpu_and_, (pcp), (val));			\
+} while (0)
+
+#endif
+
+#ifndef __this_cpu_or
+# define __this_cpu_or(pcp, val)					\
+do { __this_cpu_preempt_check("or");					\
+	__pcpu_size_call(raw_cpu_or_, (pcp), (val));			\
+} while (0)
+#endif
+
+#ifndef __this_cpu_add_return
+# define __this_cpu_add_return(pcp, val)	\
+	(__this_cpu_preempt_check("add_return"),__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val))
+#endif
+
+#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
+#define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
+#define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)
+
+#ifndef __this_cpu_xchg
+# define __this_cpu_xchg(pcp, nval)	\
+	(__this_cpu_preempt_check("xchg"),__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval))
+#endif
+
+#ifndef __this_cpu_cmpxchg
+# define __this_cpu_cmpxchg(pcp, oval, nval)	\
+	(__this_cpu_preempt_check("cmpxchg"),__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval))
+#endif
+
+#ifndef __this_cpu_cmpxchg_double
 # define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__pcpu_double_call_return_bool(__this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+	(__this_cpu_preempt_check("cmpxchg_double"),__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)))
 #endif
 
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 201a6974965..56b7bc32db4 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -104,15 +104,13 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent);
  *       units, e.g. numbers, bytes, Kbytes, etc
  *
  * returns 0 on success and <0 if the counter->usage will exceed the
- * counter->limit _locked call expects the counter->lock to be taken
+ * 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_locked(struct res_counter *counter,
-					   unsigned long val, bool force);
 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,
@@ -125,12 +123,10 @@ int res_counter_charge_nofail(struct res_counter *counter,
  * @val: the amount of the resource
  *
  * these calls check for usage underflow and show a warning on the console
- * _locked call expects the counter->lock to be taken
  *
  * returns the total charges still present in @counter.
  */
 
-u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
 u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
 
 u64 res_counter_uncharge_until(struct res_counter *counter,
diff --git a/include/linux/rio.h b/include/linux/rio.h
index b71d5738e68..6bda06f2193 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -83,7 +83,7 @@
 #define RIO_CTAG_UDEVID	0x0001ffff /* Unique device identifier */
 
 extern struct bus_type rio_bus_type;
-extern struct device rio_bus;
+extern struct class rio_mport_class;
 
 struct rio_mport;
 struct rio_dev;
@@ -201,6 +201,7 @@ struct rio_dev {
 #define rio_dev_f(n) list_entry(n, struct rio_dev, net_list)
 #define	to_rio_dev(n) container_of(n, struct rio_dev, dev)
 #define sw_to_rio_dev(n) container_of(n, struct rio_dev, rswitch[0])
+#define	to_rio_mport(n) container_of(n, struct rio_mport, dev)
 
 /**
  * struct rio_msg - RIO message event
@@ -248,6 +249,7 @@ enum rio_phy_type {
  * @phy_type: RapidIO phy type
  * @phys_efptr: RIO port extended features pointer
  * @name: Port name string
+ * @dev: device structure associated with an mport
  * @priv: Master port private data
  * @dma: DMA device associated with mport
  * @nscan: RapidIO network enumeration/discovery operations
@@ -272,6 +274,7 @@ struct rio_mport {
 	enum rio_phy_type phy_type;	/* RapidIO phy type */
 	u32 phys_efptr;
 	unsigned char name[RIO_MAX_MPORT_NAME];
+	struct device dev;
 	void *priv;		/* Master port private data */
 #ifdef CONFIG_RAPIDIO_DMA_ENGINE
 	struct dma_device	dma;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7cb07fd2668..075b3056c0c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -132,6 +132,10 @@ struct perf_event_context;
 struct blk_plug;
 struct filename;
 
+#define VMACACHE_BITS 2
+#define VMACACHE_SIZE (1U << VMACACHE_BITS)
+#define VMACACHE_MASK (VMACACHE_SIZE - 1)
+
 /*
  * List of flags we want to share for kernel threads,
  * if only because they are not used by them anyway.
@@ -206,8 +210,9 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define __TASK_STOPPED		4
 #define __TASK_TRACED		8
 /* in tsk->exit_state */
-#define EXIT_ZOMBIE		16
-#define EXIT_DEAD		32
+#define EXIT_DEAD		16
+#define EXIT_ZOMBIE		32
+#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
 /* in tsk->state again */
 #define TASK_DEAD		64
 #define TASK_WAKEKILL		128
@@ -1235,6 +1240,9 @@ struct task_struct {
 #ifdef CONFIG_COMPAT_BRK
 	unsigned brk_randomized:1;
 #endif
+	/* per-thread vma caching */
+	u32 vmacache_seqnum;
+	struct vm_area_struct *vmacache[VMACACHE_SIZE];
 #if defined(SPLIT_RSS_COUNTING)
 	struct task_rss_stat	rss_stat;
 #endif
@@ -1844,7 +1852,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
 #define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
-#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK 0x80000000      /* this thread called freeze_processes and should not be frozen */
@@ -2351,7 +2358,7 @@ extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, i
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
-extern void set_task_comm(struct task_struct *tsk, char *from);
+extern void set_task_comm(struct task_struct *tsk, const char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/slab.h b/include/linux/slab.h
index b5b2df60299..3dd389aa91c 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -115,9 +115,9 @@ int slab_is_available(void);
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
 			void (*)(void *));
-struct kmem_cache *
-kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t,
-			unsigned long, void (*)(void *), struct kmem_cache *);
+#ifdef CONFIG_MEMCG_KMEM
+void kmem_cache_create_memcg(struct mem_cgroup *, struct kmem_cache *);
+#endif
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 void kmem_cache_free(struct kmem_cache *, void *);
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index f56bfa9e452..f2f7398848c 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -87,6 +87,9 @@ struct kmem_cache {
 #ifdef CONFIG_MEMCG_KMEM
 	struct memcg_cache_params *memcg_params;
 	int max_attr_size; /* for propagation, maximum size of a stored attr */
+#ifdef CONFIG_SYSFS
+	struct kset *memcg_kset;
+#endif
 #endif
 
 #ifdef CONFIG_NUMA
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 12ae6ce997d..7062330a132 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -188,7 +188,7 @@ DECLARE_PER_CPU(int, numa_node);
 /* Returns the number of the current Node. */
 static inline int numa_node_id(void)
 {
-	return __this_cpu_read(numa_node);
+	return raw_cpu_read(numa_node);
 }
 #endif
 
@@ -245,7 +245,7 @@ static inline void set_numa_mem(int node)
 /* Returns the number of the nearest Node with memory */
 static inline int numa_mem_id(void)
 {
-	return __this_cpu_read(_numa_mem_);
+	return raw_cpu_read(_numa_mem_);
 }
 #endif
 
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
new file mode 100644
index 00000000000..c3fa0fd4394
--- /dev/null
+++ b/include/linux/vmacache.h
@@ -0,0 +1,38 @@
+#ifndef __LINUX_VMACACHE_H
+#define __LINUX_VMACACHE_H
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+/*
+ * Hash based on the page number. Provides a good hit rate for
+ * workloads with good locality and those with random accesses as well.
+ */
+#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK)
+
+static inline void vmacache_flush(struct task_struct *tsk)
+{
+	memset(tsk->vmacache, 0, sizeof(tsk->vmacache));
+}
+
+extern void vmacache_flush_all(struct mm_struct *mm);
+extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
+extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
+						    unsigned long addr);
+
+#ifndef CONFIG_MMU
+extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long end);
+#endif
+
+static inline void vmacache_invalidate(struct mm_struct *mm)
+{
+	mm->vmacache_seqnum++;
+
+	/* deal with overflows */
+	if (unlikely(mm->vmacache_seqnum == 0))
+		vmacache_flush_all(mm);
+}
+
+#endif /* __LINUX_VMACACHE_H */
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index ea4476157e0..45c9cd1daf7 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -27,9 +27,13 @@ struct vm_event_state {
 
 DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
 
+/*
+ * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the
+ * local_irq_disable overhead.
+ */
 static inline void __count_vm_event(enum vm_event_item item)
 {
-	__this_cpu_inc(vm_event_states.event[item]);
+	raw_cpu_inc(vm_event_states.event[item]);
 }
 
 static inline void count_vm_event(enum vm_event_item item)
@@ -39,7 +43,7 @@ static inline void count_vm_event(enum vm_event_item item)
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
-	__this_cpu_add(vm_event_states.event[item], delta);
+	raw_cpu_add(vm_event_states.event[item], delta);
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 021b8a319b9..5777c13849b 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -178,7 +178,7 @@ int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
-void set_page_dirty_balance(struct page *page, int page_mkwrite);
+void set_page_dirty_balance(struct page *page);
 void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);