Merge branch 'akpm' (patches from Andrew)

Merge first patchbomb from Andrew Morton:

 - a few misc things

 - ocfs2 udpates

 - kernel/watchdog.c feature work (took ages to get right)

 - most of MM.  A few tricky bits are held up and probably won't make 4.2.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (91 commits)
  mm: kmemleak_alloc_percpu() should follow the gfp from per_alloc()
  mm, thp: respect MPOL_PREFERRED policy with non-local node
  tmpfs: truncate prealloc blocks past i_size
  mm/memory hotplug: print the last vmemmap region at the end of hot add memory
  mm/mmap.c: optimization of do_mmap_pgoff function
  mm: kmemleak: optimise kmemleak_lock acquiring during kmemleak_scan
  mm: kmemleak: avoid deadlock on the kmemleak object insertion error path
  mm: kmemleak: do not acquire scan_mutex in kmemleak_do_cleanup()
  mm: kmemleak: fix delete_object_*() race when called on the same memory block
  mm: kmemleak: allow safe memory scanning during kmemleak disabling
  memcg: convert mem_cgroup->under_oom from atomic_t to int
  memcg: remove unused mem_cgroup->oom_wakeups
  frontswap: allow multiple backends
  x86, mirror: x86 enabling - find mirrored memory ranges
  mm/memblock: allocate boot time data structures from mirrored memory
  mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute
  mm: do not ignore mapping_gfp_mask in page cache allocation paths
  mm/cma.c: fix typos in comments
  mm/oom_kill.c: print points as unsigned int
  mm/hugetlb: handle races in alloc_huge_page and hugetlb_reserve_pages
  ...

16 files changed, 267 insertions, 55 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index bd910ce..29c57b2 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -96,11 +96,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address,
-				       pmd_t *pmdp)
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address,
+					    pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 	pmd_clear(pmdp);
@@ -109,13 +109,13 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
+static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
 					    unsigned long address, pmd_t *pmdp,
 					    int full)
 {
-	return pmdp_get_and_clear(mm, address, pmdp);
+	return pmdp_huge_get_and_clear(mm, address, pmdp);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
@@ -152,8 +152,8 @@ extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
 			      pte_t *ptep);
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
-extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
+#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
+extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
 			      unsigned long address,
 			      pmd_t *pmdp);
 #endif
@@ -189,6 +189,22 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp);
 #endif
 
+#ifndef pmdp_collapse_flush
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+#else
+static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+					unsigned long address,
+					pmd_t *pmdp)
+{
+	BUILD_BUG();
+	return *pmdp;
+}
+#define pmdp_collapse_flush pmdp_collapse_flush
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				       pgtable_t pgtable);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 0995c2d..f589222 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -357,12 +357,12 @@ extern void *alloc_large_system_hash(const char *tablename,
 /* Only NUMA needs hash distribution. 64bit NUMA architectures have
  * sufficient vmalloc space.
  */
-#if defined(CONFIG_NUMA) && defined(CONFIG_64BIT)
-#define HASHDIST_DEFAULT 1
+#ifdef CONFIG_NUMA
+#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT)
+extern int hashdist;		/* Distribute hashes across NUMA nodes? */
 #else
-#define HASHDIST_DEFAULT 0
+#define hashdist (0)
 #endif
-extern int hashdist;		/* Distribute hashes across NUMA nodes? */
 
 
 #endif /* _LINUX_BOOTMEM_H */
diff --git a/include/linux/configfs.h b/include/linux/configfs.h
index 34025df..c9e5c57 100644
--- a/include/linux/configfs.h
+++ b/include/linux/configfs.h
@@ -71,7 +71,6 @@ static inline char *config_item_name(struct config_item * item)
 	return item->ci_name;
 }
 
-extern void config_item_init(struct config_item *);
 extern void config_item_init_type_name(struct config_item *item,
 				       const char *name,
 				       struct config_item_type *type);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2092965..5f19efe 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -96,6 +96,8 @@ typedef	struct {
 #define EFI_MEMORY_WP		((u64)0x0000000000001000ULL)	/* write-protect */
 #define EFI_MEMORY_RP		((u64)0x0000000000002000ULL)	/* read-protect */
 #define EFI_MEMORY_XP		((u64)0x0000000000004000ULL)	/* execute-protect */
+#define EFI_MEMORY_MORE_RELIABLE \
+				((u64)0x0000000000010000ULL)	/* higher reliability */
 #define EFI_MEMORY_RUNTIME	((u64)0x8000000000000000ULL)	/* range requires runtime mapping */
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
@@ -868,6 +870,7 @@ extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if pos
 extern void efi_late_init(void);
 extern void efi_free_boot_services(void);
 extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size);
+extern void efi_find_mirror(void);
 #else
 static inline void efi_late_init(void) {}
 static inline void efi_free_boot_services(void) {}
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index 8293262..e65ef95 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -6,16 +6,16 @@
 #include <linux/bitops.h>
 
 struct frontswap_ops {
-	void (*init)(unsigned);
-	int (*store)(unsigned, pgoff_t, struct page *);
-	int (*load)(unsigned, pgoff_t, struct page *);
-	void (*invalidate_page)(unsigned, pgoff_t);
-	void (*invalidate_area)(unsigned);
+	void (*init)(unsigned); /* this swap type was just swapon'ed */
+	int (*store)(unsigned, pgoff_t, struct page *); /* store a page */
+	int (*load)(unsigned, pgoff_t, struct page *); /* load a page */
+	void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */
+	void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */
+	struct frontswap_ops *next; /* private pointer to next ops */
 };
 
 extern bool frontswap_enabled;
-extern struct frontswap_ops *
-	frontswap_register_ops(struct frontswap_ops *ops);
+extern void frontswap_register_ops(struct frontswap_ops *ops);
 extern void frontswap_shrink(unsigned long);
 extern unsigned long frontswap_curr_pages(void);
 extern void frontswap_writethrough(bool);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 0f313f9..65a517d 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -84,8 +84,6 @@ struct fsnotify_fname;
  * Each group much define these ops.  The fsnotify infrastructure will call
  * these operations for each relevant group.
  *
- * should_send_event - given a group, inode, and mask this function determines
- *		if the group is interested in this event.
  * handle_event - main call for a group to handle an fs event
  * free_group_priv - called when a group refcnt hits 0 to clean up the private union
  * freeing_mark - called when a mark is being destroyed for some reason.  The group
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index e705467..d0a1f99 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -28,7 +28,8 @@
 extern void kmemleak_init(void) __ref;
 extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			   gfp_t gfp) __ref;
-extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) __ref;
+extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+				  gfp_t gfp) __ref;
 extern void kmemleak_free(const void *ptr) __ref;
 extern void kmemleak_free_part(const void *ptr, size_t size) __ref;
 extern void kmemleak_free_percpu(const void __percpu *ptr) __ref;
@@ -71,7 +72,8 @@ static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
 					    gfp_t gfp)
 {
 }
-static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
+static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
+					 gfp_t gfp)
 {
 }
 static inline void kmemleak_free(const void *ptr)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 9497ec7..0215ffd 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -21,7 +21,11 @@
 #define INIT_PHYSMEM_REGIONS	4
 
 /* Definition of memblock flags. */
-#define MEMBLOCK_HOTPLUG	0x1	/* hotpluggable region */
+enum {
+	MEMBLOCK_NONE		= 0x0,	/* No special request */
+	MEMBLOCK_HOTPLUG	= 0x1,	/* hotpluggable region */
+	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
+};
 
 struct memblock_region {
 	phys_addr_t base;
@@ -61,7 +65,7 @@ extern bool movable_node_enabled;
 
 phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align,
 					    phys_addr_t start, phys_addr_t end,
-					    int nid);
+					    int nid, ulong flags);
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
 phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr);
@@ -75,6 +79,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
+int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
+ulong choose_memblock_flags(void);
 
 /* Low level functions */
 int memblock_add_range(struct memblock_type *type,
@@ -85,11 +91,13 @@ int memblock_remove_range(struct memblock_type *type,
 			  phys_addr_t base,
 			  phys_addr_t size);
 
-void __next_mem_range(u64 *idx, int nid, struct memblock_type *type_a,
+void __next_mem_range(u64 *idx, int nid, ulong flags,
+		      struct memblock_type *type_a,
 		      struct memblock_type *type_b, phys_addr_t *out_start,
 		      phys_addr_t *out_end, int *out_nid);
 
-void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a,
+void __next_mem_range_rev(u64 *idx, int nid, ulong flags,
+			  struct memblock_type *type_a,
 			  struct memblock_type *type_b, phys_addr_t *out_start,
 			  phys_addr_t *out_end, int *out_nid);
 
@@ -100,16 +108,17 @@ void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a,
  * @type_a: ptr to memblock_type to iterate
  * @type_b: ptr to memblock_type which excludes from the iteration
  * @nid: node selector, %NUMA_NO_NODE for all nodes
+ * @flags: pick from blocks based on memory attributes
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
  */
-#define for_each_mem_range(i, type_a, type_b, nid,			\
+#define for_each_mem_range(i, type_a, type_b, nid, flags,		\
 			   p_start, p_end, p_nid)			\
-	for (i = 0, __next_mem_range(&i, nid, type_a, type_b,		\
+	for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b,	\
 				     p_start, p_end, p_nid);		\
 	     i != (u64)ULLONG_MAX;					\
-	     __next_mem_range(&i, nid, type_a, type_b,			\
+	     __next_mem_range(&i, nid, flags, type_a, type_b,		\
 			      p_start, p_end, p_nid))
 
 /**
@@ -119,17 +128,18 @@ void __next_mem_range_rev(u64 *idx, int nid, struct memblock_type *type_a,
  * @type_a: ptr to memblock_type to iterate
  * @type_b: ptr to memblock_type which excludes from the iteration
  * @nid: node selector, %NUMA_NO_NODE for all nodes
+ * @flags: pick from blocks based on memory attributes
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
  */
-#define for_each_mem_range_rev(i, type_a, type_b, nid,			\
+#define for_each_mem_range_rev(i, type_a, type_b, nid, flags,		\
 			       p_start, p_end, p_nid)			\
 	for (i = (u64)ULLONG_MAX,					\
-		     __next_mem_range_rev(&i, nid, type_a, type_b,	\
+		     __next_mem_range_rev(&i, nid, flags, type_a, type_b,\
 					 p_start, p_end, p_nid);	\
 	     i != (u64)ULLONG_MAX;					\
-	     __next_mem_range_rev(&i, nid, type_a, type_b,		\
+	     __next_mem_range_rev(&i, nid, flags, type_a, type_b,	\
 				  p_start, p_end, p_nid))
 
 #ifdef CONFIG_MOVABLE_NODE
@@ -153,6 +163,11 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif
 
+static inline bool memblock_is_mirror(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_MIRROR;
+}
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
 			    unsigned long  *end_pfn);
@@ -181,13 +196,14 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
+ * @flags: pick from blocks based on memory attributes
  *
  * Walks over free (memory && !reserved) areas of memblock.  Available as
  * soon as memblock is initialized.
  */
-#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid)		\
+#define for_each_free_mem_range(i, nid, flags, p_start, p_end, p_nid)	\
 	for_each_mem_range(i, &memblock.memory, &memblock.reserved,	\
-			   nid, p_start, p_end, p_nid)
+			   nid, flags, p_start, p_end, p_nid)
 
 /**
  * for_each_free_mem_range_reverse - rev-iterate through free memblock areas
@@ -196,13 +212,15 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
+ * @flags: pick from blocks based on memory attributes
  *
  * Walks over free (memory && !reserved) areas of memblock in reverse
  * order.  Available as soon as memblock is initialized.
  */
-#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid)	\
+#define for_each_free_mem_range_reverse(i, nid, flags, p_start, p_end,	\
+					p_nid)				\
 	for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved,	\
-			       nid, p_start, p_end, p_nid)
+			       nid, flags, p_start, p_end, p_nid)
 
 static inline void memblock_set_region_flags(struct memblock_region *r,
 					     unsigned long flags)
@@ -273,7 +291,8 @@ static inline bool memblock_bottom_up(void) { return false; }
 #define MEMBLOCK_ALLOC_ACCESSIBLE	0
 
 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
-					phys_addr_t start, phys_addr_t end);
+					phys_addr_t start, phys_addr_t end,
+					ulong flags);
 phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
 				phys_addr_t max_addr);
 phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
diff --git a/include/linux/mm-arch-hooks.h b/include/linux/mm-arch-hooks.h
new file mode 100644
index 0000000..4efc3f5
--- /dev/null
+++ b/include/linux/mm-arch-hooks.h
@@ -0,0 +1,25 @@
+/*
+ * Generic mm no-op hooks.
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _LINUX_MM_ARCH_HOOKS_H
+#define _LINUX_MM_ARCH_HOOKS_H
+
+#include <asm/mm-arch-hooks.h>
+
+#ifndef arch_remap
+static inline void arch_remap(struct mm_struct *mm,
+			      unsigned long old_start, unsigned long old_end,
+			      unsigned long new_start, unsigned long new_end)
+{
+}
+#define arch_remap arch_remap
+#endif
+
+#endif /* _LINUX_MM_ARCH_HOOKS_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0755b9f..24ad583 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -499,7 +499,7 @@ static inline int page_count(struct page *page)
 
 static inline bool __compound_tail_refcounted(struct page *page)
 {
-	return !PageSlab(page) && !PageHeadHuge(page);
+	return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page);
 }
 
 /*
@@ -2146,12 +2146,47 @@ enum mf_flags {
 extern int memory_failure(unsigned long pfn, int trapno, int flags);
 extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
 extern int unpoison_memory(unsigned long pfn);
+extern int get_hwpoison_page(struct page *page);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
 extern atomic_long_t num_poisoned_pages;
 extern int soft_offline_page(struct page *page, int flags);
 
+
+/*
+ * Error handlers for various types of pages.
+ */
+enum mf_result {
+	MF_IGNORED,	/* Error: cannot be handled */
+	MF_FAILED,	/* Error: handling failed */
+	MF_DELAYED,	/* Will be handled later */
+	MF_RECOVERED,	/* Successfully recovered */
+};
+
+enum mf_action_page_type {
+	MF_MSG_KERNEL,
+	MF_MSG_KERNEL_HIGH_ORDER,
+	MF_MSG_SLAB,
+	MF_MSG_DIFFERENT_COMPOUND,
+	MF_MSG_POISONED_HUGE,
+	MF_MSG_HUGE,
+	MF_MSG_FREE_HUGE,
+	MF_MSG_UNMAP_FAILED,
+	MF_MSG_DIRTY_SWAPCACHE,
+	MF_MSG_CLEAN_SWAPCACHE,
+	MF_MSG_DIRTY_MLOCKED_LRU,
+	MF_MSG_CLEAN_MLOCKED_LRU,
+	MF_MSG_DIRTY_UNEVICTABLE_LRU,
+	MF_MSG_CLEAN_UNEVICTABLE_LRU,
+	MF_MSG_DIRTY_LRU,
+	MF_MSG_CLEAN_LRU,
+	MF_MSG_TRUNCATED_LRU,
+	MF_MSG_BUDDY,
+	MF_MSG_BUDDY_2ND,
+	MF_MSG_UNKNOWN,
+};
+
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
 extern void clear_huge_page(struct page *page,
 			    unsigned long addr,
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 95243d2..61cd67f 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -324,25 +324,25 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	___pte;								\
 })
 
-#define pmdp_clear_flush_notify(__vma, __haddr, __pmd)			\
+#define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd)		\
 ({									\
 	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
 	struct mm_struct *___mm = (__vma)->vm_mm;			\
 	pmd_t ___pmd;							\
 									\
-	___pmd = pmdp_clear_flush(__vma, __haddr, __pmd);		\
+	___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd);		\
 	mmu_notifier_invalidate_range(___mm, ___haddr,			\
 				      ___haddr + HPAGE_PMD_SIZE);	\
 									\
 	___pmd;								\
 })
 
-#define pmdp_get_and_clear_notify(__mm, __haddr, __pmd)			\
+#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd)		\
 ({									\
 	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
 	pmd_t ___pmd;							\
 									\
-	___pmd = pmdp_get_and_clear(__mm, __haddr, __pmd);		\
+	___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd);		\
 	mmu_notifier_invalidate_range(__mm, ___haddr,			\
 				      ___haddr + HPAGE_PMD_SIZE);	\
 									\
@@ -428,8 +428,8 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 #define ptep_clear_flush_young_notify ptep_clear_flush_young
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
 #define	ptep_clear_flush_notify ptep_clear_flush
-#define pmdp_clear_flush_notify pmdp_clear_flush
-#define pmdp_get_and_clear_notify pmdp_get_and_clear
+#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
+#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear
 #define set_pte_at_notify set_pte_at
 
 #endif /* CONFIG_MMU_NOTIFIER */
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 3d46fb4..f94da0e 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -67,6 +67,7 @@ extern int nmi_watchdog_enabled;
 extern int soft_watchdog_enabled;
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
+extern unsigned long *watchdog_cpumask_bits;
 extern int sysctl_softlockup_all_cpu_backtrace;
 struct ctl_table;
 extern int proc_watchdog(struct ctl_table *, int ,
@@ -77,6 +78,8 @@ extern int proc_soft_watchdog(struct ctl_table *, int ,
 			      void __user *, size_t *, loff_t *);
 extern int proc_watchdog_thresh(struct ctl_table *, int ,
 				void __user *, size_t *, loff_t *);
+extern int proc_watchdog_cpumask(struct ctl_table *, int,
+				 void __user *, size_t *, loff_t *);
 #endif
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 44b2f6f..7deecb7 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -32,6 +32,8 @@ enum oom_scan_t {
 /* Thread is the potential origin of an oom condition; kill first on oom */
 #define OOM_FLAG_ORIGIN		((__force oom_flags_t)0x1)
 
+extern struct mutex oom_lock;
+
 static inline void set_current_oom_origin(void)
 {
 	current->signal->oom_flags |= OOM_FLAG_ORIGIN;
@@ -47,9 +49,7 @@ static inline bool oom_task_origin(const struct task_struct *p)
 	return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN);
 }
 
-extern void mark_tsk_oom_victim(struct task_struct *tsk);
-
-extern void unmark_oom_victim(void);
+extern void mark_oom_victim(struct task_struct *tsk);
 
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
@@ -62,9 +62,6 @@ extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			     struct mem_cgroup *memcg, nodemask_t *nodemask,
 			     const char *message);
 
-extern bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_flags);
-extern void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_flags);
-
 extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 			       int order, const nodemask_t *nodemask,
 			       struct mem_cgroup *memcg);
@@ -75,6 +72,9 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 
 extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *mask, bool force_kill);
+
+extern void exit_oom_victim(void);
+
 extern int register_oom_notifier(struct notifier_block *nb);
 extern int unregister_oom_notifier(struct notifier_block *nb);
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index ffd24c8..9de2fdc 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -153,8 +153,30 @@ size_t ksize(const void *);
 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
 #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN
 #define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN)
+/*
+ * The KMALLOC_LOOP_LOW is the definition for the for loop index start number
+ * to create the kmalloc_caches object in create_kmalloc_caches(). The first
+ * and the second are 96 and 192. You can see that in the kmalloc_index(), if
+ * the KMALLOC_MIN_SIZE <= 32, then return 1 (96). If KMALLOC_MIN_SIZE <= 64,
+ * then return 2 (192). If the KMALLOC_MIN_SIZE is bigger than 64, we don't
+ * need to initialize 96 and 192. Go directly to start the KMALLOC_SHIFT_LOW.
+ */
+#if KMALLOC_MIN_SIZE <= 32
+#define KMALLOC_LOOP_LOW 1
+#elif KMALLOC_MIN_SIZE <= 64
+#define KMALLOC_LOOP_LOW 2
+#else
+#define KMALLOC_LOOP_LOW KMALLOC_SHIFT_LOW
+#endif
+
 #else
 #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
+/*
+ * The KMALLOC_MIN_SIZE of slub/slab/slob is 2^3/2^5/2^3. So, even slab is used.
+ * The KMALLOC_MIN_SIZE <= 32. The kmalloc-96 and kmalloc-192 should also be
+ * initialized.
+ */
+#define KMALLOC_LOOP_LOW 1
 #endif
 
 /*
@@ -240,8 +262,8 @@ extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
  * belongs to.
  * 0 = zero alloc
  * 1 =  65 .. 96 bytes
- * 2 = 120 .. 192 bytes
- * n = 2^(n-1) .. 2^n -1
+ * 2 = 129 .. 192 bytes
+ * n = 2^(n-1)+1 .. 2^n
  */
 static __always_inline int kmalloc_index(size_t size)
 {
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index d600afb..da3c593 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -27,6 +27,8 @@ struct smpboot_thread_data;
  * @pre_unpark:		Optional unpark function, called before the thread is
  *			unparked (cpu online). This is not guaranteed to be
  *			called on the target cpu of the thread. Careful!
+ * @cpumask:		Internal state.  To update which threads are unparked,
+ *			call smpboot_update_cpumask_percpu_thread().
  * @selfparking:	Thread is not parked by the park function.
  * @thread_comm:	The base name of the thread
  */
@@ -41,11 +43,14 @@ struct smp_hotplug_thread {
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
 	void				(*pre_unpark)(unsigned int cpu);
+	cpumask_var_t			cpumask;
 	bool				selfparking;
 	const char			*thread_comm;
 };
 
 int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
 void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
+int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
+					 const struct cpumask *);
 
 #endif
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 79abb9c..1443d79 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -11,6 +11,7 @@
 #include <linux/pci.h>
 #include <linux/aer.h>
 #include <linux/cper.h>
+#include <linux/mm.h>
 
 /*
  * MCE Extended Error Log trace event
@@ -232,6 +233,90 @@ TRACE_EVENT(aer_event,
 		__print_flags(__entry->status, "|", aer_uncorrectable_errors))
 );
 
+/*
+ * memory-failure recovery action result event
+ *
+ * unsigned long pfn -	Page Frame Number of the corrupted page
+ * int type	-	Page types of the corrupted page
+ * int result	-	Result of recovery action
+ */
+
+#ifdef CONFIG_MEMORY_FAILURE
+#define MF_ACTION_RESULT	\
+	EM ( MF_IGNORED, "Ignored" )	\
+	EM ( MF_FAILED,  "Failed" )	\
+	EM ( MF_DELAYED, "Delayed" )	\
+	EMe ( MF_RECOVERED, "Recovered" )
+
+#define MF_PAGE_TYPE		\
+	EM ( MF_MSG_KERNEL, "reserved kernel page" )			\
+	EM ( MF_MSG_KERNEL_HIGH_ORDER, "high-order kernel page" )	\
+	EM ( MF_MSG_SLAB, "kernel slab page" )				\
+	EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \
+	EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" )	\
+	EM ( MF_MSG_HUGE, "huge page" )					\
+	EM ( MF_MSG_FREE_HUGE, "free huge page" )			\
+	EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" )		\
+	EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" )		\
+	EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" )		\
+	EM ( MF_MSG_DIRTY_MLOCKED_LRU, "dirty mlocked LRU page" )	\
+	EM ( MF_MSG_CLEAN_MLOCKED_LRU, "clean mlocked LRU page" )	\
+	EM ( MF_MSG_DIRTY_UNEVICTABLE_LRU, "dirty unevictable LRU page" )	\
+	EM ( MF_MSG_CLEAN_UNEVICTABLE_LRU, "clean unevictable LRU page" )	\
+	EM ( MF_MSG_DIRTY_LRU, "dirty LRU page" )			\
+	EM ( MF_MSG_CLEAN_LRU, "clean LRU page" )			\
+	EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" )	\
+	EM ( MF_MSG_BUDDY, "free buddy page" )				\
+	EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" )		\
+	EMe ( MF_MSG_UNKNOWN, "unknown page" )
+
+/*
+ * First define the enums in MM_ACTION_RESULT to be exported to userspace
+ * via TRACE_DEFINE_ENUM().
+ */
+#undef EM
+#undef EMe
+#define EM(a, b) TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+MF_ACTION_RESULT
+MF_PAGE_TYPE
+
+/*
+ * Now redefine the EM() and EMe() macros to map the enums to the strings
+ * that will be printed in the output.
+ */
+#undef EM
+#undef EMe
+#define EM(a, b)		{ a, b },
+#define EMe(a, b)	{ a, b }
+
+TRACE_EVENT(memory_failure_event,
+	TP_PROTO(unsigned long pfn,
+		 int type,
+		 int result),
+
+	TP_ARGS(pfn, type, result),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, pfn)
+		__field(int, type)
+		__field(int, result)
+	),
+
+	TP_fast_assign(
+		__entry->pfn	= pfn;
+		__entry->type	= type;
+		__entry->result	= result;
+	),
+
+	TP_printk("pfn %#lx: recovery action for %s: %s",
+		__entry->pfn,
+		__print_symbolic(__entry->type, MF_PAGE_TYPE),
+		__print_symbolic(__entry->result, MF_ACTION_RESULT)
+	)
+);
+#endif /* CONFIG_MEMORY_FAILURE */
 #endif /* _TRACE_HW_EVENT_MC_H */
 
 /* This part must be outside protection */