Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "173 patches.

  Subsystems affected by this series: ia64, ocfs2, block, and mm (debug,
  pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
  bootmem, sparsemem, vmalloc, kasan, pagealloc, memory-failure,
  hugetlb, userfaultfd, vmscan, compaction, mempolicy, memblock,
  oom-kill, migration, ksm, percpu, vmstat, and madvise)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (173 commits)
  mm/madvise: add MADV_WILLNEED to process_madvise()
  mm/vmstat: remove unneeded return value
  mm/vmstat: simplify the array size calculation
  mm/vmstat: correct some wrong comments
  mm/percpu,c: remove obsolete comments of pcpu_chunk_populated()
  selftests: vm: add COW time test for KSM pages
  selftests: vm: add KSM merging time test
  mm: KSM: fix data type
  selftests: vm: add KSM merging across nodes test
  selftests: vm: add KSM zero page merging test
  selftests: vm: add KSM unmerge test
  selftests: vm: add KSM merge test
  mm/migrate: correct kernel-doc notation
  mm: wire up syscall process_mrelease
  mm: introduce process_mrelease system call
  memblock: make memblock_find_in_range method private
  mm/mempolicy.c: use in_task() in mempolicy_slab_node()
  mm/mempolicy: unify the create() func for bind/interleave/prefer-many policies
  mm/mempolicy: advertise new MPOL_PREFERRED_MANY
  mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY
  ...

25 files changed, 201 insertions, 92 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 1d7edad9914f..33207004cfde 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -116,6 +116,7 @@ struct bdi_writeback {
 	struct list_head b_dirty_time;	/* time stamps are dirty */
 	spinlock_t list_lock;		/* protects the b_* lists */
 
+	atomic_t writeback_inodes;	/* number of inodes under writeback */
 	struct percpu_counter stat[NR_WB_STAT_ITEMS];
 
 	unsigned long congested;	/* WB_[a]sync_congested flags */
@@ -142,6 +143,7 @@ struct bdi_writeback {
 	spinlock_t work_lock;		/* protects work_list & dwork scheduling */
 	struct list_head work_list;
 	struct delayed_work dwork;	/* work item used for writeback */
+	struct delayed_work bw_dwork;	/* work item used for bandwidth estimate */
 
 	unsigned long dirty_sleep;	/* last wait */
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 29530859d9ff..ac7f231b8825 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -288,6 +288,17 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
 	return inode->i_wb;
 }
 
+static inline struct bdi_writeback *inode_to_wb_wbc(
+				struct inode *inode,
+				struct writeback_control *wbc)
+{
+	/*
+	 * If wbc does not have inode attached, it means cgroup writeback was
+	 * disabled when wbc started. Just use the default wb in that case.
+	 */
+	return wbc->wb ? wbc->wb : &inode_to_bdi(inode)->wb;
+}
+
 /**
  * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
  * @inode: target inode
@@ -366,6 +377,14 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
 	return &inode_to_bdi(inode)->wb;
 }
 
+static inline struct bdi_writeback *inode_to_wb_wbc(
+				struct inode *inode,
+				struct writeback_control *wbc)
+{
+	return inode_to_wb(inode);
+}
+
+
 static inline struct bdi_writeback *
 unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index e7e99da31349..6486d3c19463 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -409,7 +409,7 @@ static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
 static inline void invalidate_bh_lrus_cpu(int cpu) {}
-static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; }
+static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
 #define buffer_heads_over_limit 0
 
 #endif /* CONFIG_BLOCK */
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index c24098c7acca..34bce35c808d 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -84,6 +84,8 @@ static inline unsigned long compact_gap(unsigned int order)
 extern unsigned int sysctl_compaction_proactiveness;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void *buffer, size_t *length, loff_t *ppos);
+extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table,
+		int write, void *buffer, size_t *length, loff_t *ppos);
 extern int sysctl_extfrag_threshold;
 extern int sysctl_compact_unevictable_allowed;
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index d9a606a9fc64..b4c49f9cc379 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -130,10 +130,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page
 }
 #endif
 
-#ifndef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
+#ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE
 static inline void flush_kernel_vmap_range(void *vaddr, int size)
 {
 }
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 0b8d1fdda3a1..c137396129db 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -121,6 +121,13 @@ static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg)
 	css_put(&h_cg->css);
 }
 
+static inline void resv_map_dup_hugetlb_cgroup_uncharge_info(
+						struct resv_map *resv_map)
+{
+	if (resv_map->css)
+		css_get(resv_map->css);
+}
+
 extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					struct hugetlb_cgroup **ptr);
 extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages,
@@ -199,6 +206,11 @@ static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg)
 {
 }
 
+static inline void resv_map_dup_hugetlb_cgroup_uncharge_info(
+						struct resv_map *resv_map)
+{
+}
+
 static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					       struct hugetlb_cgroup **ptr)
 {
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 4a53c3ca86bd..b066024c62e3 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -99,8 +99,6 @@ void memblock_discard(void);
 static inline void memblock_discard(void) {}
 #endif
 
-phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
-				   phys_addr_t size, phys_addr_t align);
 void memblock_allow_resize(void);
 int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
 int memblock_add(phys_addr_t base, phys_addr_t size);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 20151c4f1e0e..3096c9a0ee01 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -105,14 +105,6 @@ struct mem_cgroup_reclaim_iter {
 	unsigned int generation;
 };
 
-struct lruvec_stat {
-	long count[NR_VM_NODE_STAT_ITEMS];
-};
-
-struct batched_lruvec_stat {
-	s32 count[NR_VM_NODE_STAT_ITEMS];
-};
-
 /*
  * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
  * shrinkers, which have elements charged to this memcg.
@@ -123,24 +115,30 @@ struct shrinker_info {
 	unsigned long *map;
 };
 
+struct lruvec_stats_percpu {
+	/* Local (CPU and cgroup) state */
+	long state[NR_VM_NODE_STAT_ITEMS];
+
+	/* Delta calculation for lockless upward propagation */
+	long state_prev[NR_VM_NODE_STAT_ITEMS];
+};
+
+struct lruvec_stats {
+	/* Aggregated (CPU and subtree) state */
+	long state[NR_VM_NODE_STAT_ITEMS];
+
+	/* Pending child counts during tree propagation */
+	long state_pending[NR_VM_NODE_STAT_ITEMS];
+};
+
 /*
  * per-node information in memory controller.
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 
-	/*
-	 * Legacy local VM stats. This should be struct lruvec_stat and
-	 * cannot be optimized to struct batched_lruvec_stat. Because
-	 * the threshold of the lruvec_stat_cpu can be as big as
-	 * MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this
-	 * filed has no upper limit.
-	 */
-	struct lruvec_stat __percpu *lruvec_stat_local;
-
-	/* Subtree VM stats (batched updates) */
-	struct batched_lruvec_stat __percpu *lruvec_stat_cpu;
-	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+	struct lruvec_stats_percpu __percpu	*lruvec_stats_percpu;
+	struct lruvec_stats			lruvec_stats;
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
@@ -595,13 +593,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 }
 #endif
 
-static __always_inline bool memcg_stat_item_in_bytes(int idx)
-{
-	if (idx == MEMCG_PERCPU_B)
-		return true;
-	return vmstat_item_in_bytes(idx);
-}
-
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return (memcg == root_mem_cgroup);
@@ -693,13 +684,35 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
 		page_counter_read(&memcg->memory);
 }
 
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
+int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+			gfp_t gfp_mask);
+static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+				    gfp_t gfp_mask)
+{
+	if (mem_cgroup_disabled())
+		return 0;
+	return __mem_cgroup_charge(page, mm, gfp_mask);
+}
+
 int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
 				  gfp_t gfp, swp_entry_t entry);
 void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
 
-void mem_cgroup_uncharge(struct page *page);
-void mem_cgroup_uncharge_list(struct list_head *page_list);
+void __mem_cgroup_uncharge(struct page *page);
+static inline void mem_cgroup_uncharge(struct page *page)
+{
+	if (mem_cgroup_disabled())
+		return;
+	__mem_cgroup_uncharge(page);
+}
+
+void __mem_cgroup_uncharge_list(struct list_head *page_list);
+static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
+{
+	if (mem_cgroup_disabled())
+		return;
+	__mem_cgroup_uncharge_list(page_list);
+}
 
 void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
 
@@ -884,11 +897,6 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 	return !!(memcg->css.flags & CSS_ONLINE);
 }
 
-/*
- * For memory reclaim.
- */
-int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
-
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 		int zid, int nr_pages);
 
@@ -955,22 +963,21 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 	local_irq_restore(flags);
 }
 
+static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+{
+	return READ_ONCE(memcg->vmstats.state[idx]);
+}
+
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
-	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	x = atomic_long_read(&pn->lruvec_stat[idx]);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
+	return READ_ONCE(pn->lruvec_stats.state[idx]);
 }
 
 static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
@@ -985,7 +992,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	for_each_possible_cpu(cpu)
-		x += per_cpu(pn->lruvec_stat_local->count[idx], cpu);
+		x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -993,6 +1000,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return x;
 }
 
+void mem_cgroup_flush_stats(void);
+
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
 void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
@@ -1391,6 +1400,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 {
 }
 
+static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
+{
+	return 0;
+}
+
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
@@ -1403,6 +1417,10 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
+static inline void mem_cgroup_flush_stats(void)
+{
+}
+
 static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
 					    enum node_stat_item idx, int val)
 {
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 97e92e8b556a..d9a0b61cd432 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -90,7 +90,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size,
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
-extern struct memory_block *find_memory_block(struct mem_section *);
+extern struct memory_block *find_memory_block(unsigned long section_nr);
 typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
 extern int walk_memory_blocks(unsigned long start, unsigned long size,
 			      void *arg, walk_memory_blocks_func_t func);
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 0aaf91b496e2..4091692bed8c 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -184,6 +184,14 @@ extern bool vma_migratable(struct vm_area_struct *vma);
 extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
 extern void mpol_put_task_policy(struct task_struct *);
 
+extern bool numa_demotion_enabled;
+
+static inline bool mpol_is_preferred_many(struct mempolicy *pol)
+{
+	return  (pol->mode == MPOL_PREFERRED_MANY);
+}
+
+
 #else
 
 struct mempolicy {};
@@ -292,5 +300,13 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
 {
 	return NULL;
 }
+
+#define numa_demotion_enabled	false
+
+static inline bool mpol_is_preferred_many(struct mempolicy *pol)
+{
+	return  false;
+}
+
 #endif /* CONFIG_NUMA */
 #endif
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 23dadf7aeba8..326250996b4e 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -28,6 +28,7 @@ enum migrate_reason {
 	MR_NUMA_MISPLACED,
 	MR_CONTIG_RANGE,
 	MR_LONGTERM_PIN,
+	MR_DEMOTION,
 	MR_TYPES
 };
 
@@ -41,7 +42,8 @@ extern int migrate_page(struct address_space *mapping,
 			struct page *newpage, struct page *page,
 			enum migrate_mode mode);
 extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
-		unsigned long private, enum migrate_mode mode, int reason);
+		unsigned long private, enum migrate_mode mode, int reason,
+		unsigned int *ret_succeeded);
 extern struct page *alloc_migration_target(struct page *page, unsigned long private);
 extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
 
@@ -56,7 +58,7 @@ extern int migrate_page_move_mapping(struct address_space *mapping,
 static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t new,
 		free_page_t free, unsigned long private, enum migrate_mode mode,
-		int reason)
+		int reason, unsigned int *ret_succeeded)
 	{ return -ENOSYS; }
 static inline struct page *alloc_migration_target(struct page *page,
 		unsigned long private)
@@ -166,6 +168,14 @@ struct migrate_vma {
 int migrate_vma_setup(struct migrate_vma *args);
 void migrate_vma_pages(struct migrate_vma *migrate);
 void migrate_vma_finalize(struct migrate_vma *migrate);
+int next_demotion_node(int node);
+
+#else /* CONFIG_MIGRATION disabled: */
+
+static inline int next_demotion_node(int node)
+{
+	return NUMA_NO_NODE;
+}
 
 #endif /* CONFIG_MIGRATION */
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e59646a5d44d..ed2552c9aeca 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1216,18 +1216,10 @@ static inline void get_page(struct page *page)
 }
 
 bool __must_check try_grab_page(struct page *page, unsigned int flags);
-__maybe_unused struct page *try_grab_compound_head(struct page *page, int refs,
-						   unsigned int flags);
+struct page *try_grab_compound_head(struct page *page, int refs,
+				    unsigned int flags);
 
-
-static inline __must_check bool try_get_page(struct page *page)
-{
-	page = compound_head(page);
-	if (WARN_ON_ONCE(page_ref_count(page) <= 0))
-		return false;
-	page_ref_inc(page);
-	return true;
-}
+struct page *try_get_compound_head(struct page *page, int refs);
 
 static inline void put_page(struct page *page)
 {
@@ -1849,7 +1841,6 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
 struct kvec;
 int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
 			struct page **pages);
-int get_kernel_page(unsigned long start, int write, struct page **pages);
 struct page *get_dump_page(unsigned long addr);
 
 extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
@@ -3121,7 +3112,7 @@ extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
-extern void shake_page(struct page *p, int access);
+extern void shake_page(struct page *p);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index fcb535560028..1bd5f5955f9a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -846,6 +846,7 @@ typedef struct pglist_data {
 	enum zone_type kcompactd_highest_zoneidx;
 	wait_queue_head_t kcompactd_wait;
 	struct task_struct *kcompactd;
+	bool proactive_compact_trigger;
 #endif
 	/*
 	 * This is a per-node reserve of pages that are not available
@@ -1342,7 +1343,6 @@ static inline struct mem_section *__nr_to_section(unsigned long nr)
 		return NULL;
 	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
 }
-extern unsigned long __section_nr(struct mem_section *ms);
 extern size_t mem_section_usage_size(void);
 
 /*
@@ -1365,7 +1365,7 @@ extern size_t mem_section_usage_size(void);
 #define SECTION_TAINT_ZONE_DEVICE	(1UL<<4)
 #define SECTION_MAP_LAST_BIT		(1UL<<5)
 #define SECTION_MAP_MASK		(~(SECTION_MAP_LAST_BIT-1))
-#define SECTION_NID_SHIFT		3
+#define SECTION_NID_SHIFT		6
 
 static inline struct page *__section_mem_map_addr(struct mem_section *section)
 {
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ed02aa522263..5dcf446f42e5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -736,7 +736,7 @@ extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
 /*
  * Fault everything in given userspace address range in.
  */
-static inline int fault_in_pages_writeable(char __user *uaddr, int size)
+static inline int fault_in_pages_writeable(char __user *uaddr, size_t size)
 {
 	char __user *end = uaddr + size - 1;
 
@@ -763,7 +763,7 @@ static inline int fault_in_pages_writeable(char __user *uaddr, int size)
 	return 0;
 }
 
-static inline int fault_in_pages_readable(const char __user *uaddr, int size)
+static inline int fault_in_pages_readable(const char __user *uaddr, size_t size)
 {
 	volatile char c;
 	const char __user *end = uaddr + size - 1;
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index e24b1fe348e3..5561486fddef 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -174,13 +174,13 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 }
 
 #ifdef CONFIG_LOCKDEP
-extern void __fs_reclaim_acquire(void);
-extern void __fs_reclaim_release(void);
+extern void __fs_reclaim_acquire(unsigned long ip);
+extern void __fs_reclaim_release(unsigned long ip);
 extern void fs_reclaim_acquire(gfp_t gfp_mask);
 extern void fs_reclaim_release(gfp_t gfp_mask);
 #else
-static inline void __fs_reclaim_acquire(void) { }
-static inline void __fs_reclaim_release(void) { }
+static inline void __fs_reclaim_acquire(unsigned long ip) { }
+static inline void __fs_reclaim_release(unsigned long ip) { }
 static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
 static inline void fs_reclaim_release(gfp_t gfp_mask) { }
 #endif
@@ -306,7 +306,7 @@ set_active_memcg(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *old;
 
-	if (in_interrupt()) {
+	if (!in_task()) {
 		old = this_cpu_read(int_active_memcg);
 		this_cpu_write(int_active_memcg, memcg);
 	} else {
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 8e775ce517bb..166158b6e917 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -18,6 +18,7 @@ struct shmem_inode_info {
 	unsigned long		flags;
 	unsigned long		alloced;	/* data pages alloced to file */
 	unsigned long		swapped;	/* subtotal assigned to swap */
+	pgoff_t			fallocend;	/* highest fallocate endindex */
 	struct list_head        shrinklist;     /* shrinkable hpage inodes */
 	struct list_head	swaplist;	/* chain of maybes on swap */
 	struct shared_policy	policy;		/* NUMA memory alloc policy */
@@ -31,7 +32,7 @@ struct shmem_sb_info {
 	struct percpu_counter used_blocks;  /* How many are allocated */
 	unsigned long max_inodes;   /* How many inodes are allowed */
 	unsigned long free_inodes;  /* How many are left for allocation */
-	spinlock_t stat_lock;	    /* Serialize shmem_sb_info changes */
+	raw_spinlock_t stat_lock;   /* Serialize shmem_sb_info changes */
 	umode_t mode;		    /* Mount mode for root directory */
 	unsigned char huge;	    /* Whether to try for hugepages */
 	kuid_t uid;		    /* Mount uid for root directory */
@@ -85,7 +86,12 @@ extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
 extern int shmem_unuse(unsigned int type, bool frontswap,
 		       unsigned long *fs_pages_to_unuse);
 
-extern bool shmem_huge_enabled(struct vm_area_struct *vma);
+extern bool shmem_is_huge(struct vm_area_struct *vma,
+			  struct inode *inode, pgoff_t index);
+static inline bool shmem_huge_enabled(struct vm_area_struct *vma)
+{
+	return shmem_is_huge(vma, file_inode(vma->vm_file), vma->vm_pgoff);
+}
 extern unsigned long shmem_swap_usage(struct vm_area_struct *vma);
 extern unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 						pgoff_t start, pgoff_t end);
@@ -93,9 +99,8 @@ extern unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 /* Flag allocation requirements to shmem_getpage */
 enum sgp_type {
 	SGP_READ,	/* don't exceed i_size, don't allocate page */
+	SGP_NOALLOC,	/* similar, but fail on hole or use fallocated page */
 	SGP_CACHE,	/* don't exceed i_size, may allocate page */
-	SGP_NOHUGE,	/* like SGP_CACHE, but no huge pages */
-	SGP_HUGE,	/* like SGP_CACHE, huge pages preferred */
 	SGP_WRITE,	/* may exceed i_size, may allocate !Uptodate page */
 	SGP_FALLOC,	/* like SGP_WRITE, but make existing page Uptodate */
 };
@@ -119,6 +124,18 @@ static inline bool shmem_file(struct file *file)
 	return shmem_mapping(file->f_mapping);
 }
 
+/*
+ * If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages
+ * beyond i_size's notion of EOF, which fallocate has committed to reserving:
+ * which split_huge_page() must therefore not delete.  This use of a single
+ * "fallocend" per inode errs on the side of not deleting a reservation when
+ * in doubt: there are plenty of cases when it preserves unreserved pages.
+ */
+static inline pgoff_t shmem_fallocend(struct inode *inode, pgoff_t eof)
+{
+	return max(eof, SHMEM_I(inode)->fallocend);
+}
+
 extern bool shmem_charge(struct inode *inode, long pages);
 extern void shmem_uncharge(struct inode *inode, long pages);
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 6f5a43251593..ba52f3a3478e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -408,7 +408,7 @@ static inline bool node_reclaim_enabled(void)
 
 extern void check_move_unevictable_pages(struct pagevec *pvec);
 
-extern int kswapd_run(int nid);
+extern void kswapd_run(int nid);
 extern void kswapd_stop(int nid);
 
 #ifdef CONFIG_SWAP
@@ -721,7 +721,13 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 #endif
 
 #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-extern void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask);
+extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask);
+static inline  void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
+{
+	if (mem_cgroup_disabled())
+		return;
+	__cgroup_throttle_swaprate(page, gfp_mask);
+}
 #else
 static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
 {
@@ -730,8 +736,22 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
 
 #ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
-extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
-extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
+extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
+static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+{
+	if (mem_cgroup_disabled())
+		return 0;
+	return __mem_cgroup_try_charge_swap(page, entry);
+}
+
+extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
+static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
+{
+	if (mem_cgroup_disabled())
+		return;
+	__mem_cgroup_uncharge_swap(entry, nr_pages);
+}
+
 extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
 extern bool mem_cgroup_swap_full(struct page *page);
 #else
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2b47584eb843..60a3ab0ad2cc 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -915,6 +915,7 @@ asmlinkage long sys_mincore(unsigned long start, size_t len,
 asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior);
 asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec,
 			size_t vlen, int behavior, unsigned int flags);
+asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags);
 asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 			unsigned long prot, unsigned long pgoff,
 			unsigned long flags);
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 331d2ccf0bcc..33cea484d1ad 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -60,16 +60,16 @@ extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 
 extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
 			    unsigned long src_start, unsigned long len,
-			    bool *mmap_changing, __u64 mode);
+			    atomic_t *mmap_changing, __u64 mode);
 extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
 			      unsigned long dst_start,
 			      unsigned long len,
-			      bool *mmap_changing);
+			      atomic_t *mmap_changing);
 extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start,
-			      unsigned long len, bool *mmap_changing);
+			      unsigned long len, atomic_t *mmap_changing);
 extern int mwriteprotect_range(struct mm_struct *dst_mm,
 			       unsigned long start, unsigned long len,
-			       bool enable_wp, bool *mmap_changing);
+			       bool enable_wp, atomic_t *mmap_changing);
 
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index ae0dd1948c2b..a185cc75ff52 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -33,6 +33,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGREUSE,
 		PGSTEAL_KSWAPD,
 		PGSTEAL_DIRECT,
+		PGDEMOTE_KSWAPD,
+		PGDEMOTE_DIRECT,
 		PGSCAN_KSWAPD,
 		PGSCAN_DIRECT,
 		PGSCAN_DIRECT_THROTTLE,
diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h
index 6d28bc433c1c..6a2f51ebbfd3 100644
--- a/include/linux/vmpressure.h
+++ b/include/linux/vmpressure.h
@@ -37,7 +37,7 @@ extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio);
 extern void vmpressure_init(struct vmpressure *vmpr);
 extern void vmpressure_cleanup(struct vmpressure *vmpr);
 extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg);
-extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr);
+extern struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr);
 extern int vmpressure_register_event(struct mem_cgroup *memcg,
 				     struct eventfd_ctx *eventfd,
 				     const char *args);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 270677dc4f36..d1f65adf6a26 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -218,7 +218,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 void wbc_detach_inode(struct writeback_control *wbc);
 void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
 			      size_t bytes);
-int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages,
+int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
 			   enum wb_reason reason, struct wb_completion *done);
 void cgroup_writeback_umount(void);
 bool cleanup_offline_cgwb(struct bdi_writeback *wb);
@@ -374,7 +374,7 @@ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write,
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
 unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
 
-void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time);
+void wb_update_bandwidth(struct bdi_writeback *wb);
 void balance_dirty_pages_ratelimited(struct address_space *mapping);
 bool wb_over_bg_thresh(struct bdi_writeback *wb);
 
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index 9fb2a3bbcdfb..779f3fad9ecd 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -21,7 +21,8 @@
 	EM( MR_MEMPOLICY_MBIND,	"mempolicy_mbind")		\
 	EM( MR_NUMA_MISPLACED,	"numa_misplaced")		\
 	EM( MR_CONTIG_RANGE,	"contig_range")			\
-	EMe(MR_LONGTERM_PIN,	"longterm_pin")
+	EM( MR_LONGTERM_PIN,	"longterm_pin")			\
+	EMe(MR_DEMOTION,	"demotion")
 
 /*
  * First define the enums in the above macros to be exported to userspace
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index a9d6fcd95f42..14c8fe863c6d 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -877,9 +877,11 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
 #define __NR_memfd_secret 447
 __SYSCALL(__NR_memfd_secret, sys_memfd_secret)
 #endif
+#define __NR_process_mrelease 448
+__SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 
 #undef __NR_syscalls
-#define __NR_syscalls 448
+#define __NR_syscalls 449
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 19a00bc7fe86..046d0ccba4cd 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -22,6 +22,7 @@ enum {
 	MPOL_BIND,
 	MPOL_INTERLEAVE,
 	MPOL_LOCAL,
+	MPOL_PREFERRED_MANY,
 	MPOL_MAX,	/* always last member of enum */
 };