Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - misc fixes

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  mm: remove PG_highmem description
  tools, vm: new option to specify kpageflags file
  mm/swap.c: make functions and their kernel-doc agree
  mm, memory_hotplug: fix memmap initialization
  mm: correct comments regarding do_fault_around()
  mm: numa: do not trap faults on shared data section pages.
  hugetlb, mbind: fall back to default policy if vma is NULL
  hugetlb, mempolicy: fix the mbind hugetlb migration
  mm, hugetlb: further simplify hugetlb allocation API
  mm, hugetlb: get rid of surplus page accounting tricks
  mm, hugetlb: do not rely on overcommit limit during migration
  mm, hugetlb: integrate giga hugetlb more naturally to the allocation path
  mm, hugetlb: unify core page allocation accounting and initialization
  mm/memcontrol.c: try harder to decrease [memory,memsw].limit_in_bytes
  mm/memcontrol.c: make local symbol static
  mm/hmm: fix uninitialized use of 'entry' in hmm_vma_walk_pmd()
  include/linux/mmzone.h: fix explanation of lower bits in the SPARSEMEM mem_map pointer
  mm/compaction.c: fix comment for try_to_compact_pages()
  mm/page_ext.c: make page_ext_init a noop when CONFIG_PAGE_EXTENSION but nothing uses it
  zsmalloc: use U suffix for negative literals being shifted
  ...

15 files changed, 280 insertions, 238 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 868e68561f91..2cfa3075d148 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -309,19 +309,26 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_INVALIDATE
-extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
-			    pmd_t *pmdp);
-#endif
-
-#ifndef __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE
-static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma,
-					   unsigned long address, pmd_t *pmdp)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * This is an implementation of pmdp_establish() that is only suitable for an
+ * architecture that doesn't have hardware dirty/accessed bits. In this case we
+ * can't race with CPU which sets these bits and non-atomic aproach is fine.
+ */
+static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
 {
-
+	pmd_t old_pmd = *pmdp;
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+	return old_pmd;
 }
 #endif
 
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE
+extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 82a25880714a..36fa6a2a82e3 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -119,6 +119,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
+void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
@@ -129,7 +130,6 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
 
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
 
-extern int hugepages_treat_as_movable;
 extern int sysctl_hugetlb_shm_group;
 extern struct list_head huge_boot_pages;
 
@@ -158,6 +158,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
 bool is_hugetlb_entry_migration(pte_t pte);
+
 #else /* !CONFIG_HUGETLB_PAGE */
 
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
@@ -198,6 +199,7 @@ static inline bool isolate_huge_page(struct page *page, struct list_head *list)
 	return false;
 }
 #define putback_active_hugepage(p)	do {} while (0)
+#define move_hugetlb_state(old, new, reason)	do {} while (0)
 
 static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot)
@@ -271,6 +273,17 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
+struct hugetlbfs_inode_info {
+	struct shared_policy policy;
+	struct inode vfs_inode;
+	unsigned int seals;
+};
+
+static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
+{
+	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
+}
+
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
 struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
@@ -343,10 +356,10 @@ struct huge_bootmem_page {
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
-struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
-				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask);
+struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
+				unsigned long address);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
@@ -524,7 +537,7 @@ struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
 #define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL
-#define alloc_huge_page_noerr(v, a, r) NULL
+#define alloc_huge_page_vma(h, vma, address) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
 #define hstate_sizelog(s) NULL
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 69966c461d1c..882046863581 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -108,7 +108,10 @@ struct lruvec_stat {
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
-	struct lruvec_stat __percpu *lruvec_stat;
+
+	struct lruvec_stat __percpu *lruvec_stat_cpu;
+	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
@@ -227,10 +230,10 @@ struct mem_cgroup {
 	spinlock_t		move_lock;
 	struct task_struct	*move_lock_task;
 	unsigned long		move_lock_flags;
-	/*
-	 * percpu counter.
-	 */
-	struct mem_cgroup_stat_cpu __percpu *stat;
+
+	struct mem_cgroup_stat_cpu __percpu *stat_cpu;
+	atomic_long_t		stat[MEMCG_NR_STAT];
+	atomic_long_t		events[MEMCG_NR_EVENTS];
 
 	unsigned long		socket_pressure;
 
@@ -265,6 +268,12 @@ struct mem_cgroup {
 	/* WARNING: nodeinfo must be the last member here */
 };
 
+/*
+ * size of first charge trial. "32" comes from vmscan.c's magic value.
+ * TODO: maybe necessary to use big numbers in big irons.
+ */
+#define MEMCG_CHARGE_BATCH 32U
+
 extern struct mem_cgroup *root_mem_cgroup;
 
 static inline bool mem_cgroup_disabled(void)
@@ -272,13 +281,6 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline void mem_cgroup_event(struct mem_cgroup *memcg,
-				    enum memcg_event_item event)
-{
-	this_cpu_inc(memcg->stat->events[event]);
-	cgroup_file_notify(&memcg->events_file);
-}
-
 bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
 
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
@@ -492,32 +494,38 @@ void unlock_page_memcg(struct page *page);
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 					     int idx)
 {
-	long val = 0;
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		val += per_cpu(memcg->stat->count[idx], cpu);
-
-	if (val < 0)
-		val = 0;
-
-	return val;
+	long x = atomic_long_read(&memcg->stat[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void __mod_memcg_state(struct mem_cgroup *memcg,
 				     int idx, int val)
 {
-	if (!mem_cgroup_disabled())
-		__this_cpu_add(memcg->stat->count[idx], val);
+	long x;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	x = val + __this_cpu_read(memcg->stat_cpu->count[idx]);
+	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &memcg->stat[idx]);
+		x = 0;
+	}
+	__this_cpu_write(memcg->stat_cpu->count[idx], x);
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
 				   int idx, int val)
 {
-	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->count[idx], val);
+	preempt_disable();
+	__mod_memcg_state(memcg, idx, val);
+	preempt_enable();
 }
 
 /**
@@ -555,87 +563,108 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
-	long val = 0;
-	int cpu;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	for_each_possible_cpu(cpu)
-		val += per_cpu(pn->lruvec_stat->count[idx], cpu);
-
-	if (val < 0)
-		val = 0;
-
-	return val;
+	x = atomic_long_read(&pn->lruvec_stat[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline void __mod_lruvec_state(struct lruvec *lruvec,
 				      enum node_stat_item idx, int val)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
+	/* Update node */
 	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+
 	if (mem_cgroup_disabled())
 		return;
+
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+
+	/* Update memcg */
 	__mod_memcg_state(pn->memcg, idx, val);
-	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+
+	/* Update lruvec */
+	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
+	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &pn->lruvec_stat[idx]);
+		x = 0;
+	}
+	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
 }
 
 static inline void mod_lruvec_state(struct lruvec *lruvec,
 				    enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
-
-	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
-	if (mem_cgroup_disabled())
-		return;
-	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	mod_memcg_state(pn->memcg, idx, val);
-	this_cpu_add(pn->lruvec_stat->count[idx], val);
+	preempt_disable();
+	__mod_lruvec_state(lruvec, idx, val);
+	preempt_enable();
 }
 
 static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
+	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
 
-	__mod_node_page_state(page_pgdat(page), idx, val);
-	if (mem_cgroup_disabled() || !page->mem_cgroup)
+	/* Untracked pages have no memcg, no lruvec. Update only the node */
+	if (!page->mem_cgroup) {
+		__mod_node_page_state(pgdat, idx, val);
 		return;
-	__mod_memcg_state(page->mem_cgroup, idx, val);
-	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
-	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+	}
+
+	lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
+	__mod_lruvec_state(lruvec, idx, val);
 }
 
 static inline void mod_lruvec_page_state(struct page *page,
 					 enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
-
-	mod_node_page_state(page_pgdat(page), idx, val);
-	if (mem_cgroup_disabled() || !page->mem_cgroup)
-		return;
-	mod_memcg_state(page->mem_cgroup, idx, val);
-	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
-	this_cpu_add(pn->lruvec_stat->count[idx], val);
+	preempt_disable();
+	__mod_lruvec_page_state(page, idx, val);
+	preempt_enable();
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
+/* idx can be of type enum memcg_event_item or vm_event_item */
+static inline void __count_memcg_events(struct mem_cgroup *memcg,
+					int idx, unsigned long count)
+{
+	unsigned long x;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	x = count + __this_cpu_read(memcg->stat_cpu->events[idx]);
+	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &memcg->events[idx]);
+		x = 0;
+	}
+	__this_cpu_write(memcg->stat_cpu->events[idx], x);
+}
+
 static inline void count_memcg_events(struct mem_cgroup *memcg,
-				      enum vm_event_item idx,
-				      unsigned long count)
+				      int idx, unsigned long count)
 {
-	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->events[idx], count);
+	preempt_disable();
+	__count_memcg_events(memcg, idx, count);
+	preempt_enable();
 }
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
+/* idx can be of type enum memcg_event_item or vm_event_item */
 static inline void count_memcg_page_event(struct page *page,
 					  int idx)
 {
@@ -654,12 +683,20 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	if (likely(memcg)) {
-		this_cpu_inc(memcg->stat->events[idx]);
+		count_memcg_events(memcg, idx, 1);
 		if (idx == OOM_KILL)
 			cgroup_file_notify(&memcg->events_file);
 	}
 	rcu_read_unlock();
 }
+
+static inline void mem_cgroup_event(struct mem_cgroup *memcg,
+				    enum memcg_event_item event)
+{
+	count_memcg_events(memcg, event, 1);
+	cgroup_file_notify(&memcg->events_file);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7fc92384977e..173d2484f6e3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1312,8 +1312,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
 			struct vm_area_struct *vma);
-void unmap_mapping_range(struct address_space *mapping,
-		loff_t const holebegin, loff_t const holelen, int even_cows);
 int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 			     unsigned long *start, unsigned long *end,
 			     pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
@@ -1324,12 +1322,6 @@ int follow_phys(struct vm_area_struct *vma, unsigned long address,
 int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 			void *buf, int len, int write);
 
-static inline void unmap_shared_mapping_range(struct address_space *mapping,
-		loff_t const holebegin, loff_t const holelen)
-{
-	unmap_mapping_range(mapping, holebegin, holelen, 0);
-}
-
 extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
@@ -1344,6 +1336,10 @@ extern int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
+void unmap_mapping_pages(struct address_space *mapping,
+		pgoff_t start, pgoff_t nr, bool even_cows);
+void unmap_mapping_range(struct address_space *mapping,
+		loff_t const holebegin, loff_t const holelen, int even_cows);
 #else
 static inline int handle_mm_fault(struct vm_area_struct *vma,
 		unsigned long address, unsigned int flags)
@@ -1360,10 +1356,20 @@ static inline int fixup_user_fault(struct task_struct *tsk,
 	BUG();
 	return -EFAULT;
 }
+static inline void unmap_mapping_pages(struct address_space *mapping,
+		pgoff_t start, pgoff_t nr, bool even_cows) { }
+static inline void unmap_mapping_range(struct address_space *mapping,
+		loff_t const holebegin, loff_t const holelen, int even_cows) { }
 #endif
 
-extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
-		unsigned int gup_flags);
+static inline void unmap_shared_mapping_range(struct address_space *mapping,
+		loff_t const holebegin, loff_t const holelen)
+{
+	unmap_mapping_range(mapping, holebegin, holelen, 0);
+}
+
+extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
+		void *buf, int len, unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
 extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index cfd0ac4e5e0e..fd1af6b9591d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -31,28 +31,56 @@ struct hmm;
  * it to keep track of whatever it is we are using the page for at the
  * moment. Note that we have no way to track which tasks are using
  * a page, though if it is a pagecache page, rmap structures can tell us
- * who is mapping it.
+ * who is mapping it. If you allocate the page using alloc_pages(), you
+ * can use some of the space in struct page for your own purposes.
  *
- * The objects in struct page are organized in double word blocks in
- * order to allows us to use atomic double word operations on portions
- * of struct page. That is currently only used by slub but the arrangement
- * allows the use of atomic double word operations on the flags/mapping
- * and lru list pointers also.
+ * Pages that were once in the page cache may be found under the RCU lock
+ * even after they have been recycled to a different purpose.  The page
+ * cache reads and writes some of the fields in struct page to pin the
+ * page before checking that it's still in the page cache.  It is vital
+ * that all users of struct page:
+ * 1. Use the first word as PageFlags.
+ * 2. Clear or preserve bit 0 of page->compound_head.  It is used as
+ *    PageTail for compound pages, and the page cache must not see false
+ *    positives.  Some users put a pointer here (guaranteed to be at least
+ *    4-byte aligned), other users avoid using the field altogether.
+ * 3. page->_refcount must either not be used, or must be used in such a
+ *    way that other CPUs temporarily incrementing and then decrementing the
+ *    refcount does not cause problems.  On receiving the page from
+ *    alloc_pages(), the refcount will be positive.
+ * 4. Either preserve page->_mapcount or restore it to -1 before freeing it.
+ *
+ * If you allocate pages of order > 0, you can use the fields in the struct
+ * page associated with each page, but bear in mind that the pages may have
+ * been inserted individually into the page cache, so you must use the above
+ * four fields in a compatible way for each struct page.
+ *
+ * SLUB uses cmpxchg_double() to atomically update its freelist and
+ * counters.  That requires that freelist & counters be adjacent and
+ * double-word aligned.  We align all struct pages to double-word
+ * boundaries, and ensure that 'freelist' is aligned within the
+ * struct.
  */
+#ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE
+#define _struct_page_alignment	__aligned(2 * sizeof(unsigned long))
+#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE)
+#define _slub_counter_t		unsigned long
+#else
+#define _slub_counter_t		unsigned int
+#endif
+#else /* !CONFIG_HAVE_ALIGNED_STRUCT_PAGE */
+#define _struct_page_alignment
+#define _slub_counter_t		unsigned int
+#endif /* !CONFIG_HAVE_ALIGNED_STRUCT_PAGE */
+
 struct page {
 	/* First double word block */
 	unsigned long flags;		/* Atomic flags, some possibly
 					 * updated asynchronously */
 	union {
-		struct address_space *mapping;	/* If low bit clear, points to
-						 * inode address_space, or NULL.
-						 * If page mapped as anonymous
-						 * memory, low bit is set, and
-						 * it points to anon_vma object
-						 * or KSM private structure. See
-						 * PAGE_MAPPING_ANON and
-						 * PAGE_MAPPING_KSM.
-						 */
+		/* See page-flags.h for the definition of PAGE_MAPPING_FLAGS */
+		struct address_space *mapping;
+
 		void *s_mem;			/* slab first object */
 		atomic_t compound_mapcount;	/* first tail page */
 		/* page_deferred_list().next	 -- second tail page */
@@ -66,40 +94,27 @@ struct page {
 	};
 
 	union {
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
-	defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
-		/* Used for cmpxchg_double in slub */
-		unsigned long counters;
-#else
-		/*
-		 * Keep _refcount separate from slub cmpxchg_double data.
-		 * As the rest of the double word is protected by slab_lock
-		 * but _refcount is not.
-		 */
-		unsigned counters;
-#endif
-		struct {
+		_slub_counter_t counters;
+		unsigned int active;		/* SLAB */
+		struct {			/* SLUB */
+			unsigned inuse:16;
+			unsigned objects:15;
+			unsigned frozen:1;
+		};
+		int units;			/* SLOB */
+
+		struct {			/* Page cache */
+			/*
+			 * Count of ptes mapped in mms, to show when
+			 * page is mapped & limit reverse map searches.
+			 *
+			 * Extra information about page type may be
+			 * stored here for pages that are never mapped,
+			 * in which case the value MUST BE <= -2.
+			 * See page-flags.h for more details.
+			 */
+			atomic_t _mapcount;
 
-			union {
-				/*
-				 * Count of ptes mapped in mms, to show when
-				 * page is mapped & limit reverse map searches.
-				 *
-				 * Extra information about page type may be
-				 * stored here for pages that are never mapped,
-				 * in which case the value MUST BE <= -2.
-				 * See page-flags.h for more details.
-				 */
-				atomic_t _mapcount;
-
-				unsigned int active;		/* SLAB */
-				struct {			/* SLUB */
-					unsigned inuse:16;
-					unsigned objects:15;
-					unsigned frozen:1;
-				};
-				int units;			/* SLOB */
-			};
 			/*
 			 * Usage count, *USE WRAPPER FUNCTION* when manual
 			 * accounting. See page_ref.h
@@ -109,8 +124,6 @@ struct page {
 	};
 
 	/*
-	 * Third double word block
-	 *
 	 * WARNING: bit 0 of the first word encode PageTail(). That means
 	 * the rest users of the storage space MUST NOT use the bit to
 	 * avoid collision and false-positive PageTail().
@@ -145,19 +158,9 @@ struct page {
 			unsigned long compound_head; /* If bit zero is set */
 
 			/* First tail page only */
-#ifdef CONFIG_64BIT
-			/*
-			 * On 64 bit system we have enough space in struct page
-			 * to encode compound_dtor and compound_order with
-			 * unsigned int. It can help compiler generate better or
-			 * smaller code on some archtectures.
-			 */
-			unsigned int compound_dtor;
-			unsigned int compound_order;
-#else
-			unsigned short int compound_dtor;
-			unsigned short int compound_order;
-#endif
+			unsigned char compound_dtor;
+			unsigned char compound_order;
+			/* two/six bytes available here */
 		};
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
@@ -171,15 +174,14 @@ struct page {
 #endif
 	};
 
-	/* Remainder is not double word aligned */
 	union {
-		unsigned long private;		/* Mapping-private opaque data:
-					 	 * usually used for buffer_heads
-						 * if PagePrivate set; used for
-						 * swp_entry_t if PageSwapCache;
-						 * indicates order in the buddy
-						 * system if PG_buddy is set.
-						 */
+		/*
+		 * Mapping-private opaque data:
+		 * Usually used for buffer_heads if PagePrivate
+		 * Used for swp_entry_t if PageSwapCache
+		 * Indicates order in the buddy system if PageBuddy
+		 */
+		unsigned long private;
 #if USE_SPLIT_PTE_PTLOCKS
 #if ALLOC_SPLIT_PTLOCKS
 		spinlock_t *ptl;
@@ -212,15 +214,7 @@ struct page {
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
 	int _last_cpupid;
 #endif
-}
-/*
- * The struct page can be forced to be double word aligned so that atomic ops
- * on double words work. The SLUB allocator can make use of such a feature.
- */
-#ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE
-	__aligned(2 * sizeof(unsigned long))
-#endif
-;
+} _struct_page_alignment;
 
 #define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
 #define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index b25dc9db19fc..2d07a1ed5a31 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_MMU_NOTIFIER_H
 #define _LINUX_MMU_NOTIFIER_H
 
+#include <linux/types.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/mm_types.h>
@@ -10,6 +11,9 @@
 struct mmu_notifier;
 struct mmu_notifier_ops;
 
+/* mmu_notifier_ops flags */
+#define MMU_INVALIDATE_DOES_NOT_BLOCK	(0x01)
+
 #ifdef CONFIG_MMU_NOTIFIER
 
 /*
@@ -27,6 +31,15 @@ struct mmu_notifier_mm {
 
 struct mmu_notifier_ops {
 	/*
+	 * Flags to specify behavior of callbacks for this MMU notifier.
+	 * Used to determine which context an operation may be called.
+	 *
+	 * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not
+	 *	block
+	 */
+	int flags;
+
+	/*
 	 * Called either by mmu_notifier_unregister or when the mm is
 	 * being destroyed by exit_mmap, always before all pages are
 	 * freed. This can run concurrently with other mmu notifier
@@ -137,6 +150,10 @@ struct mmu_notifier_ops {
 	 * page. Pages will no longer be referenced by the linux
 	 * address space but may still be referenced by sptes until
 	 * the last refcount is dropped.
+	 *
+	 * If both of these callbacks cannot block, and invalidate_range
+	 * cannot block, mmu_notifier_ops.flags should have
+	 * MMU_INVALIDATE_DOES_NOT_BLOCK set.
 	 */
 	void (*invalidate_range_start)(struct mmu_notifier *mn,
 				       struct mm_struct *mm,
@@ -159,12 +176,13 @@ struct mmu_notifier_ops {
 	 * external TLB range needs to be flushed. For more in depth
 	 * discussion on this see Documentation/vm/mmu_notifier.txt
 	 *
-	 * The invalidate_range() function is called under the ptl
-	 * spin-lock and not allowed to sleep.
-	 *
 	 * Note that this function might be called with just a sub-range
 	 * of what was passed to invalidate_range_start()/end(), if
 	 * called between those functions.
+	 *
+	 * If this callback cannot block, and invalidate_range_{start,end}
+	 * cannot block, mmu_notifier_ops.flags should have
+	 * MMU_INVALIDATE_DOES_NOT_BLOCK set.
 	 */
 	void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm,
 				 unsigned long start, unsigned long end);
@@ -218,6 +236,7 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  bool only_end);
 extern void __mmu_notifier_invalidate_range(struct mm_struct *mm,
 				  unsigned long start, unsigned long end);
+extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm);
 
 static inline void mmu_notifier_release(struct mm_struct *mm)
 {
@@ -457,6 +476,11 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 {
 }
 
+static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm)
+{
+	return false;
+}
+
 static inline void mmu_notifier_mm_init(struct mm_struct *mm)
 {
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 67f2e3c38939..7522a6987595 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1166,8 +1166,16 @@ extern unsigned long usemap_size(void);
 
 /*
  * We use the lower bits of the mem_map pointer to store
- * a little bit of information.  There should be at least
- * 3 bits here due to 32-bit alignment.
+ * a little bit of information.  The pointer is calculated
+ * as mem_map - section_nr_to_pfn(pnum).  The result is
+ * aligned to the minimum alignment of the two values:
+ *   1. All mem_map arrays are page-aligned.
+ *   2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT
+ *      lowest bits.  PFN_SECTION_SHIFT is arch-specific
+ *      (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the
+ *      worst combination is powerpc with 256k pages,
+ *      which results in PFN_SECTION_SHIFT equal 6.
+ * To sum it up, at least 6 bits are available.
  */
 #define	SECTION_MARKED_PRESENT	(1UL<<0)
 #define SECTION_HAS_MEM_MAP	(1UL<<1)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 3ec44e27aa9d..50c2b8786831 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -46,11 +46,6 @@
  * guarantees that this bit is cleared for a page when it first is entered into
  * the page cache.
  *
- * PG_highmem pages are not permanently mapped into the kernel virtual address
- * space, they need to be kmapped separately for doing IO on the pages.  The
- * struct page (these bits with information) are always mapped into kernel
- * address space...
- *
  * PG_hwpoison indicates that a page got corrupted in hardware and contains
  * data with incorrect ECC bits that triggered a machine check. Accessing is
  * not safe since it may cause another machine check. Don't touch!
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 5fb6580f7f23..6dc456ac6136 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -9,14 +9,14 @@
 #ifndef _LINUX_PAGEVEC_H
 #define _LINUX_PAGEVEC_H
 
-/* 14 pointers + two long's align the pagevec structure to a power of two */
-#define PAGEVEC_SIZE	14
+/* 15 pointers + header align the pagevec structure to a power of two */
+#define PAGEVEC_SIZE	15
 
 struct page;
 struct address_space;
 
 struct pagevec {
-	unsigned long nr;
+	unsigned char nr;
 	bool percpu_pvec_drained;
 	struct page *pages[PAGEVEC_SIZE];
 };
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3d49b91b674d..bd422561a75e 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -11,7 +11,7 @@
 /*
  * Routines for handling mm_structs
  */
-extern struct mm_struct * mm_alloc(void);
+extern struct mm_struct *mm_alloc(void);
 
 /**
  * mmgrab() - Pin a &struct mm_struct.
@@ -35,27 +35,7 @@ static inline void mmgrab(struct mm_struct *mm)
 	atomic_inc(&mm->mm_count);
 }
 
-/* mmdrop drops the mm and the page tables */
-extern void __mmdrop(struct mm_struct *);
-static inline void mmdrop(struct mm_struct *mm)
-{
-	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
-		__mmdrop(mm);
-}
-
-static inline void mmdrop_async_fn(struct work_struct *work)
-{
-	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
-	__mmdrop(mm);
-}
-
-static inline void mmdrop_async(struct mm_struct *mm)
-{
-	if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
-		INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
-		schedule_work(&mm->async_put_work);
-	}
-}
+extern void mmdrop(struct mm_struct *mm);
 
 /**
  * mmget() - Pin the address space associated with a &struct mm_struct.
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 06b295bec00d..73b5e655a76e 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -112,13 +112,11 @@ extern void shmem_uncharge(struct inode *inode, long pages);
 
 #ifdef CONFIG_TMPFS
 
-extern int shmem_add_seals(struct file *file, unsigned int seals);
-extern int shmem_get_seals(struct file *file);
-extern long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
+extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
 
 #else
 
-static inline long shmem_fcntl(struct file *f, unsigned int c, unsigned long a)
+static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c2b8128799c1..7b6a59f722a3 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -332,7 +332,6 @@ extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_all(void);
-extern void lru_add_drain_all_cpuslocked(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_file_page(struct page *page);
 extern void mark_page_lazyfree(struct page *page);
@@ -345,7 +344,6 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
 
 /* linux/mm/vmscan.c */
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
-extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
 extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 1779c9817b39..a4c2317d8b9f 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -216,23 +216,6 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 	return x;
 }
 
-static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
-					enum node_stat_item item)
-{
-	long x = atomic_long_read(&pgdat->vm_stat[item]);
-
-#ifdef CONFIG_SMP
-	int cpu;
-	for_each_online_cpu(cpu)
-		x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item];
-
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
-
-
 #ifdef CONFIG_NUMA
 extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item);
 extern unsigned long sum_zone_node_page_state(int node,
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index 004ba807df96..7238865e75b0 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -108,4 +108,6 @@ void zpool_register_driver(struct zpool_driver *driver);
 
 int zpool_unregister_driver(struct zpool_driver *driver);
 
+bool zpool_evictable(struct zpool *pool);
+
 #endif
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index d70b53e65f43..e0b8b9173e1c 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -192,12 +192,12 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_re
 
 TRACE_EVENT(mm_shrink_slab_start,
 	TP_PROTO(struct shrinker *shr, struct shrink_control *sc,
-		long nr_objects_to_shrink, unsigned long pgs_scanned,
-		unsigned long lru_pgs, unsigned long cache_items,
-		unsigned long long delta, unsigned long total_scan),
+		long nr_objects_to_shrink, unsigned long cache_items,
+		unsigned long long delta, unsigned long total_scan,
+		int priority),
 
-	TP_ARGS(shr, sc, nr_objects_to_shrink, pgs_scanned, lru_pgs,
-		cache_items, delta, total_scan),
+	TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan,
+		priority),
 
 	TP_STRUCT__entry(
 		__field(struct shrinker *, shr)
@@ -205,11 +205,10 @@ TRACE_EVENT(mm_shrink_slab_start,
 		__field(int, nid)
 		__field(long, nr_objects_to_shrink)
 		__field(gfp_t, gfp_flags)
-		__field(unsigned long, pgs_scanned)
-		__field(unsigned long, lru_pgs)
 		__field(unsigned long, cache_items)
 		__field(unsigned long long, delta)
 		__field(unsigned long, total_scan)
+		__field(int, priority)
 	),
 
 	TP_fast_assign(
@@ -218,24 +217,22 @@ TRACE_EVENT(mm_shrink_slab_start,
 		__entry->nid = sc->nid;
 		__entry->nr_objects_to_shrink = nr_objects_to_shrink;
 		__entry->gfp_flags = sc->gfp_mask;
-		__entry->pgs_scanned = pgs_scanned;
-		__entry->lru_pgs = lru_pgs;
 		__entry->cache_items = cache_items;
 		__entry->delta = delta;
 		__entry->total_scan = total_scan;
+		__entry->priority = priority;
 	),
 
-	TP_printk("%pF %p: nid: %d objects to shrink %ld gfp_flags %s pgs_scanned %ld lru_pgs %ld cache items %ld delta %lld total_scan %ld",
+	TP_printk("%pF %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
 		__entry->shrink,
 		__entry->shr,
 		__entry->nid,
 		__entry->nr_objects_to_shrink,
 		show_gfp_flags(__entry->gfp_flags),
-		__entry->pgs_scanned,
-		__entry->lru_pgs,
 		__entry->cache_items,
 		__entry->delta,
-		__entry->total_scan)
+		__entry->total_scan,
+		__entry->priority)
 );
 
 TRACE_EVENT(mm_shrink_slab_end,