Merge branch 'akpm' (patches from Andrew)

Merge first patch-bomb from Andrew Morton:

 - A few hotfixes which missed 4.4 becasue I was asleep.  cc'ed to
   -stable

 - A few misc fixes

 - OCFS2 updates

 - Part of MM.  Including pretty large changes to page-flags handling
   and to thp management which have been buffered up for 2-3 cycles now.

  I have a lot of MM material this time.

[ It turns out the THP part wasn't quite ready, so that got dropped from
  this series  - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  zsmalloc: reorganize struct size_class to pack 4 bytes hole
  mm/zbud.c: use list_last_entry() instead of list_tail_entry()
  zram/zcomp: do not zero out zcomp private pages
  zram: pass gfp from zcomp frontend to backend
  zram: try vmalloc() after kmalloc()
  zram/zcomp: use GFP_NOIO to allocate streams
  mm: add tracepoint for scanning pages
  drivers/base/memory.c: fix kernel warning during memory hotplug on ppc64
  mm/page_isolation: use macro to judge the alignment
  mm: fix noisy sparse warning in LIBCFS_ALLOC_PRE()
  mm: rework virtual memory accounting
  include/linux/memblock.h: fix ordering of 'flags' argument in comments
  mm: move lru_to_page to mm_inline.h
  Documentation/filesystems: describe the shared memory usage/accounting
  memory-hotplug: don't BUG() in register_memory_resource()
  hugetlb: make mm and fs code explicitly non-modular
  mm/swapfile.c: use list_for_each_entry_safe in free_swap_count_continuations
  mm: /proc/pid/clear_refs: no need to clear VM_SOFTDIRTY in clear_soft_dirty_pmd()
  mm: make sure isolate_lru_page() is never called for tail page
  vmstat: make vmstat_updater deferrable again and shut down on idle
  ...

1 files changed, 56 insertions, 46 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index cd0e2413c358..2292468f2a30 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -85,32 +85,10 @@ enum mem_cgroup_events_target {
 	MEM_CGROUP_NTARGETS,
 };
 
-/*
- * Bits in struct cg_proto.flags
- */
-enum cg_proto_flags {
-	/* Currently active and new sockets should be assigned to cgroups */
-	MEMCG_SOCK_ACTIVE,
-	/* It was ever activated; we must disarm static keys on destruction */
-	MEMCG_SOCK_ACTIVATED,
-};
-
 struct cg_proto {
 	struct page_counter	memory_allocated;	/* Current allocated memory. */
-	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
 	int			memory_pressure;
-	long			sysctl_mem[3];
-	unsigned long		flags;
-	/*
-	 * memcg field is used to find which memcg we belong directly
-	 * Each memcg struct can hold more than one cg_proto, so container_of
-	 * won't really cut.
-	 *
-	 * The elegant solution would be having an inverse function to
-	 * proto_cgroup in struct proto, but that means polluting the structure
-	 * for everybody, instead of just for memcg users.
-	 */
-	struct mem_cgroup	*memcg;
+	bool			active;
 };
 
 #ifdef CONFIG_MEMCG
@@ -192,6 +170,9 @@ struct mem_cgroup {
 	unsigned long low;
 	unsigned long high;
 
+	/* Range enforcement for interrupt charges */
+	struct work_struct high_work;
+
 	unsigned long soft_limit;
 
 	/* vmpressure notifications */
@@ -268,6 +249,10 @@ struct mem_cgroup {
 	struct wb_domain cgwb_domain;
 #endif
 
+#ifdef CONFIG_INET
+	unsigned long		socket_pressure;
+#endif
+
 	/* List of events which userspace want to receive */
 	struct list_head event_list;
 	spinlock_t event_list_lock;
@@ -275,7 +260,8 @@ struct mem_cgroup {
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
 };
-extern struct cgroup_subsys_state *mem_cgroup_root_css;
+
+extern struct mem_cgroup *root_mem_cgroup;
 
 /**
  * mem_cgroup_events - count memory events against a cgroup
@@ -308,18 +294,34 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
-struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+#define mem_cgroup_from_counter(counter, member)	\
+	container_of(counter, struct mem_cgroup, member)
+
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,
 				   struct mem_cgroup_reclaim_cookie *);
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
+/**
+ * parent_mem_cgroup - find the accounting parent of a memcg
+ * @memcg: memcg whose parent to find
+ *
+ * Returns the parent memcg, or NULL if this is the root or the memory
+ * controller is in legacy no-hierarchy mode.
+ */
+static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+{
+	if (!memcg->memory.parent)
+		return NULL;
+	return mem_cgroup_from_counter(memcg->memory.parent, memory);
+}
+
 static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
 			      struct mem_cgroup *root)
 {
@@ -671,12 +673,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
-enum {
-	UNDER_LIMIT,
-	SOFT_LIMIT,
-	OVER_LIMIT,
-};
-
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
@@ -703,20 +699,35 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 struct sock;
-#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
 void sock_update_memcg(struct sock *sk);
 void sock_release_memcg(struct sock *sk);
-#else
-static inline void sock_update_memcg(struct sock *sk)
+bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
+void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
+#if defined(CONFIG_MEMCG) && defined(CONFIG_INET)
+extern struct static_key_false memcg_sockets_enabled_key;
+#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
+static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
+#ifdef CONFIG_MEMCG_KMEM
+	if (memcg->tcp_mem.memory_pressure)
+		return true;
+#endif
+	do {
+		if (time_before(jiffies, memcg->socket_pressure))
+			return true;
+	} while ((memcg = parent_mem_cgroup(memcg)));
+	return false;
 }
-static inline void sock_release_memcg(struct sock *sk)
+#else
+#define mem_cgroup_sockets_enabled 0
+static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
+	return false;
 }
-#endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */
+#endif
 
 #ifdef CONFIG_MEMCG_KMEM
-extern struct static_key memcg_kmem_enabled_key;
+extern struct static_key_false memcg_kmem_enabled_key;
 
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
@@ -732,7 +743,7 @@ void memcg_put_cache_ids(void);
 
 static inline bool memcg_kmem_enabled(void)
 {
-	return static_key_false(&memcg_kmem_enabled_key);
+	return static_branch_unlikely(&memcg_kmem_enabled_key);
 }
 
 static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
@@ -766,15 +777,13 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
-struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
+struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
 
-static inline bool __memcg_kmem_bypass(gfp_t gfp)
+static inline bool __memcg_kmem_bypass(void)
 {
 	if (!memcg_kmem_enabled())
 		return true;
-	if (gfp & __GFP_NOACCOUNT)
-		return true;
 	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
 		return true;
 	return false;
@@ -791,7 +800,9 @@ static inline bool __memcg_kmem_bypass(gfp_t gfp)
 static __always_inline int memcg_kmem_charge(struct page *page,
 					     gfp_t gfp, int order)
 {
-	if (__memcg_kmem_bypass(gfp))
+	if (__memcg_kmem_bypass())
+		return 0;
+	if (!(gfp & __GFP_ACCOUNT))
 		return 0;
 	return __memcg_kmem_charge(page, gfp, order);
 }
@@ -810,16 +821,15 @@ static __always_inline void memcg_kmem_uncharge(struct page *page, int order)
 /**
  * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
  * @cachep: the original global kmem cache
- * @gfp: allocation flags.
  *
  * All memory allocated from a per-memcg cache is charged to the owner memcg.
  */
 static __always_inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
-	if (__memcg_kmem_bypass(gfp))
+	if (__memcg_kmem_bypass())
 		return cachep;
-	return __memcg_kmem_get_cache(cachep);
+	return __memcg_kmem_get_cache(cachep, gfp);
 }
 
 static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep)