Merge branch 'akpm' (patches from Andrew Morton)

Merge more patches from Andrew Morton:
 "The rest of MM.  Plus one misc cleanup"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (35 commits)
  mm/Kconfig: add MMU dependency for MIGRATION.
  kernel: replace strict_strto*() with kstrto*()
  mm, thp: count thp_fault_fallback anytime thp fault fails
  thp: consolidate code between handle_mm_fault() and do_huge_pmd_anonymous_page()
  thp: do_huge_pmd_anonymous_page() cleanup
  thp: move maybe_pmd_mkwrite() out of mk_huge_pmd()
  mm: cleanup add_to_page_cache_locked()
  thp: account anon transparent huge pages into NR_ANON_PAGES
  truncate: drop 'oldsize' truncate_pagecache() parameter
  mm: make lru_add_drain_all() selective
  memcg: document cgroup dirty/writeback memory statistics
  memcg: add per cgroup writeback pages accounting
  memcg: check for proper lock held in mem_cgroup_update_page_stat
  memcg: remove MEMCG_NR_FILE_MAPPED
  memcg: reduce function dereference
  memcg: avoid overflow caused by PAGE_ALIGN
  memcg: rename RESOURCE_MAX to RES_COUNTER_MAX
  memcg: correct RESOURCE_MAX to ULLONG_MAX
  mm: memcg: do not trap chargers with full callstack on OOM
  mm: memcg: rework and document OOM waiting and wakeup
  ...

6 files changed, 143 insertions, 25 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b60de92e2ed..3935428c57c 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -96,9 +96,6 @@ extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			  pmd_t *dst_pmd, pmd_t *src_pmd,
 			  struct vm_area_struct *vma,
 			  unsigned long addr, unsigned long end);
-extern int handle_pte_fault(struct mm_struct *mm,
-			    struct vm_area_struct *vma, unsigned long address,
-			    pte_t *pte, pmd_t *pmd, unsigned int flags);
 extern int split_huge_page_to_list(struct page *page, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c416092e32..60e95872da2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -30,9 +30,21 @@ struct page;
 struct mm_struct;
 struct kmem_cache;
 
-/* Stats that can be updated by kernel. */
-enum mem_cgroup_page_stat_item {
-	MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */
+/*
+ * The corresponding mem_cgroup_stat_names is defined in mm/memcontrol.c,
+ * These two lists should keep in accord with each other.
+ */
+enum mem_cgroup_stat_index {
+	/*
+	 * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
+	 */
+	MEM_CGROUP_STAT_CACHE,		/* # of pages charged as cache */
+	MEM_CGROUP_STAT_RSS,		/* # of pages charged as anon rss */
+	MEM_CGROUP_STAT_RSS_HUGE,	/* # of pages charged as anon huge */
+	MEM_CGROUP_STAT_FILE_MAPPED,	/* # of pages charged as file rss */
+	MEM_CGROUP_STAT_WRITEBACK,	/* # of pages under writeback */
+	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
+	MEM_CGROUP_STAT_NSTATS,
 };
 
 struct mem_cgroup_reclaim_cookie {
@@ -41,6 +53,23 @@ struct mem_cgroup_reclaim_cookie {
 	unsigned int generation;
 };
 
+enum mem_cgroup_filter_t {
+	VISIT,		/* visit current node */
+	SKIP,		/* skip the current node and continue traversal */
+	SKIP_TREE,	/* skip the whole subtree and continue traversal */
+};
+
+/*
+ * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to
+ * iterate through the hierarchy tree. Each tree element is checked by the
+ * predicate before it is returned by the iterator. If a filter returns
+ * SKIP or SKIP_TREE then the iterator code continues traversal (with the
+ * next node down the hierarchy or the next node that doesn't belong under the
+ * memcg's subtree).
+ */
+typedef enum mem_cgroup_filter_t
+(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root);
+
 #ifdef CONFIG_MEMCG
 /*
  * All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -108,9 +137,18 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	struct page *oldpage, struct page *newpage, bool migration_ok);
 
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
-				   struct mem_cgroup *,
-				   struct mem_cgroup_reclaim_cookie *);
+struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
+				   struct mem_cgroup *prev,
+				   struct mem_cgroup_reclaim_cookie *reclaim,
+				   mem_cgroup_iter_filter cond);
+
+static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
+				   struct mem_cgroup *prev,
+				   struct mem_cgroup_reclaim_cookie *reclaim)
+{
+	return mem_cgroup_iter_cond(root, prev, reclaim, NULL);
+}
+
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
 /*
@@ -125,6 +163,48 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 extern void mem_cgroup_replace_page_cache(struct page *oldpage,
 					struct page *newpage);
 
+/**
+ * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task
+ * @new: true to enable, false to disable
+ *
+ * Toggle whether a failed memcg charge should invoke the OOM killer
+ * or just return -ENOMEM.  Returns the previous toggle state.
+ *
+ * NOTE: Any path that enables the OOM killer before charging must
+ *       call mem_cgroup_oom_synchronize() afterward to finalize the
+ *       OOM handling and clean up.
+ */
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+	bool old;
+
+	old = current->memcg_oom.may_oom;
+	current->memcg_oom.may_oom = new;
+
+	return old;
+}
+
+static inline void mem_cgroup_enable_oom(void)
+{
+	bool old = mem_cgroup_toggle_oom(true);
+
+	WARN_ON(old == true);
+}
+
+static inline void mem_cgroup_disable_oom(void)
+{
+	bool old = mem_cgroup_toggle_oom(false);
+
+	WARN_ON(old == false);
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+	return p->memcg_oom.in_memcg_oom;
+}
+
+bool mem_cgroup_oom_synchronize(void);
+
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
@@ -165,24 +245,24 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
 }
 
 void mem_cgroup_update_page_stat(struct page *page,
-				 enum mem_cgroup_page_stat_item idx,
+				 enum mem_cgroup_stat_index idx,
 				 int val);
 
 static inline void mem_cgroup_inc_page_stat(struct page *page,
-					    enum mem_cgroup_page_stat_item idx)
+					    enum mem_cgroup_stat_index idx)
 {
 	mem_cgroup_update_page_stat(page, idx, 1);
 }
 
 static inline void mem_cgroup_dec_page_stat(struct page *page,
-					    enum mem_cgroup_page_stat_item idx)
+					    enum mem_cgroup_stat_index idx)
 {
 	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
-						gfp_t gfp_mask,
-						unsigned long *total_scanned);
+enum mem_cgroup_filter_t
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
+		struct mem_cgroup *root);
 
 void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
@@ -296,6 +376,15 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 		struct page *oldpage, struct page *newpage, bool migration_ok)
 {
 }
+static inline struct mem_cgroup *
+mem_cgroup_iter_cond(struct mem_cgroup *root,
+		struct mem_cgroup *prev,
+		struct mem_cgroup_reclaim_cookie *reclaim,
+		mem_cgroup_iter_filter cond)
+{
+	/* first call must return non-NULL, second return NULL */
+	return (struct mem_cgroup *)(unsigned long)!prev;
+}
 
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
@@ -348,22 +437,45 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page,
 {
 }
 
+static inline bool mem_cgroup_toggle_oom(bool new)
+{
+	return false;
+}
+
+static inline void mem_cgroup_enable_oom(void)
+{
+}
+
+static inline void mem_cgroup_disable_oom(void)
+{
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_oom_synchronize(void)
+{
+	return false;
+}
+
 static inline void mem_cgroup_inc_page_stat(struct page *page,
-					    enum mem_cgroup_page_stat_item idx)
+					    enum mem_cgroup_stat_index idx)
 {
 }
 
 static inline void mem_cgroup_dec_page_stat(struct page *page,
-					    enum mem_cgroup_page_stat_item idx)
+					    enum mem_cgroup_stat_index idx)
 {
 }
 
 static inline
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
-					    gfp_t gfp_mask,
-					    unsigned long *total_scanned)
+enum mem_cgroup_filter_t
+mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
+		struct mem_cgroup *root)
 {
-	return 0;
+	return VISIT;
 }
 
 static inline void mem_cgroup_split_huge_fixup(struct page *head)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index caf543c7eaa..8b6e55ee885 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -176,6 +176,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_RETRY_NOWAIT	0x10	/* Don't drop mmap_sem and wait when retrying */
 #define FAULT_FLAG_KILLABLE	0x20	/* The fault task is in SIGKILL killable region */
 #define FAULT_FLAG_TRIED	0x40	/* second try */
+#define FAULT_FLAG_USER		0x80	/* The fault originated in userspace */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -876,11 +877,12 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
 #define VM_FAULT_RETRY	0x0400	/* ->fault blocked, must retry */
+#define VM_FAULT_FALLBACK 0x0800	/* huge page fault failed, fall back to small */
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
 #define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
-			 VM_FAULT_HWPOISON_LARGE)
+			 VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
@@ -984,7 +986,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 	unmap_mapping_range(mapping, holebegin, holelen, 0);
 }
 
-extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
+extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 96a509b6be0..201a6974965 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -54,7 +54,7 @@ struct res_counter {
 	struct res_counter *parent;
 };
 
-#define RESOURCE_MAX (unsigned long long)LLONG_MAX
+#define RES_COUNTER_MAX ULLONG_MAX
 
 /**
  * Helpers to interact with userspace
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 45f254dddaf..6682da36b29 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1393,6 +1393,13 @@ struct task_struct {
 		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
 	} memcg_batch;
 	unsigned int memcg_kmem_skip_account;
+	struct memcg_oom_info {
+		unsigned int may_oom:1;
+		unsigned int in_memcg_oom:1;
+		unsigned int oom_locked:1;
+		int wakeups;
+		struct mem_cgroup *wait_on_memcg;
+	} memcg_oom;
 #endif
 #ifdef CONFIG_UPROBES
 	struct uprobe_task *utask;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c03c139219c..46ba0c6c219 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -280,7 +280,7 @@ extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
-extern int lru_add_drain_all(void);
+extern void lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_page(struct page *page);
 extern void swap_setup(void);