Merge branch 'akpm' (patches from Andrew)

Merge still more updates from Andrew Morton:
 "18 patches.

  Subsystems affected by this patch series: mm (memcg and cleanups) and
  epoll"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/Kconfig: fix spelling mistake "whats" -> "what's"
  selftests/filesystems: expand epoll with epoll_pwait2
  epoll: wire up syscall epoll_pwait2
  epoll: add syscall epoll_pwait2
  epoll: convert internal api to timespec64
  epoll: eliminate unnecessary lock for zero timeout
  epoll: replace gotos with a proper loop
  epoll: pull all code between fetch_events and send_event into the loop
  epoll: simplify and optimize busy loop logic
  epoll: move eavail next to the list_empty_careful check
  epoll: pull fatal signal checks into ep_send_events()
  epoll: simplify signal handling
  epoll: check for events when removing a timed out thread from the wait queue
  mm/memcontrol:rewrite mem_cgroup_page_lruvec()
  mm, kvm: account kvm_vcpu_mmap to kmemcg
  mm/memcg: remove unused definitions
  mm/memcg: warning on !memcg after readahead page charged
  mm/memcg: bail early from swap accounting if memcg disabled

5 files changed, 44 insertions, 121 deletions

diff --git a/include/linux/compat.h b/include/linux/compat.h
index 400c0941c8af..6e65be753603 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -537,6 +537,12 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
 			int maxevents, int timeout,
 			const compat_sigset_t __user *sigmask,
 			compat_size_t sigsetsize);
+asmlinkage long compat_sys_epoll_pwait2(int epfd,
+			struct epoll_event __user *events,
+			int maxevents,
+			const struct __kernel_timespec __user *timeout,
+			const compat_sigset_t __user *sigmask,
+			compat_size_t sigsetsize);
 
 /* fs/fcntl.c */
 asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 08ed57e02b73..d827bd7f3bfe 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -620,9 +620,10 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
 /**
  * mem_cgroup_lruvec - get the lru list vector for a memcg & node
  * @memcg: memcg of the wanted lruvec
+ * @pgdat: pglist_data
  *
  * Returns the lru list vector holding pages for a given @memcg &
- * @node combination. This can be the node lruvec, if the memory
+ * @pgdat combination. This can be the node lruvec, if the memory
  * controller is disabled.
  */
 static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
@@ -652,7 +653,21 @@ out:
 	return lruvec;
 }
 
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
+/**
+ * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
+ * @page: the page
+ * @pgdat: pgdat of the page
+ *
+ * This function relies on page->mem_cgroup being stable.
+ */
+static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
+						struct pglist_data *pgdat)
+{
+	struct mem_cgroup *memcg = page_memcg(page);
+
+	VM_WARN_ON_ONCE_PAGE(!memcg, page);
+	return mem_cgroup_lruvec(memcg, pgdat);
+}
 
 static inline bool lruvec_holds_page_lru_lock(struct page *page,
 					      struct lruvec *lruvec)
@@ -913,41 +928,6 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 	local_irq_restore(flags);
 }
 
-/**
- * mod_memcg_page_state - update page state statistics
- * @page: the page
- * @idx: page state item to account
- * @val: number of pages (positive or negative)
- *
- * The @page must be locked or the caller must use lock_page_memcg()
- * to prevent double accounting when the page is concurrently being
- * moved to another memcg:
- *
- *   lock_page(page) or lock_page_memcg(page)
- *   if (TestClearPageState(page))
- *     mod_memcg_page_state(page, state, -1);
- *   unlock_page(page) or unlock_page_memcg(page)
- *
- * Kernel pages are an exception to this, since they'll never move.
- */
-static inline void __mod_memcg_page_state(struct page *page,
-					  int idx, int val)
-{
-	struct mem_cgroup *memcg = page_memcg(page);
-
-	if (memcg)
-		__mod_memcg_state(memcg, idx, val);
-}
-
-static inline void mod_memcg_page_state(struct page *page,
-					int idx, int val)
-{
-	struct mem_cgroup *memcg = page_memcg(page);
-
-	if (memcg)
-		mod_memcg_state(memcg, idx, val);
-}
-
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
@@ -1395,18 +1375,6 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 {
 }
 
-static inline void __mod_memcg_page_state(struct page *page,
-					  int idx,
-					  int nr)
-{
-}
-
-static inline void mod_memcg_page_state(struct page *page,
-					int idx,
-					int nr)
-{
-}
-
 static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
@@ -1479,34 +1447,6 @@ static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
 }
 #endif /* CONFIG_MEMCG */
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __inc_memcg_state(struct mem_cgroup *memcg,
-				     int idx)
-{
-	__mod_memcg_state(memcg, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __dec_memcg_state(struct mem_cgroup *memcg,
-				     int idx)
-{
-	__mod_memcg_state(memcg, idx, -1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __inc_memcg_page_state(struct page *page,
-					  int idx)
-{
-	__mod_memcg_page_state(page, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void __dec_memcg_page_state(struct page *page,
-					  int idx)
-{
-	__mod_memcg_page_state(page, idx, -1);
-}
-
 static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
 {
 	__mod_lruvec_kmem_state(p, idx, 1);
@@ -1517,34 +1457,6 @@ static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx)
 	__mod_lruvec_kmem_state(p, idx, -1);
 }
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void inc_memcg_state(struct mem_cgroup *memcg,
-				   int idx)
-{
-	mod_memcg_state(memcg, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void dec_memcg_state(struct mem_cgroup *memcg,
-				   int idx)
-{
-	mod_memcg_state(memcg, idx, -1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void inc_memcg_page_state(struct page *page,
-					int idx)
-{
-	mod_memcg_page_state(page, idx, 1);
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void dec_memcg_page_state(struct page *page,
-					int idx)
-{
-	mod_memcg_page_state(page, idx, -1);
-}
-
 static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
 {
 	struct mem_cgroup *memcg;
@@ -1733,21 +1645,6 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order)
 		__memcg_kmem_uncharge_page(page, order);
 }
 
-static inline int memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
-				    unsigned int nr_pages)
-{
-	if (memcg_kmem_enabled())
-		return __memcg_kmem_charge(memcg, gfp, nr_pages);
-	return 0;
-}
-
-static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg,
-				       unsigned int nr_pages)
-{
-	if (memcg_kmem_enabled())
-		__memcg_kmem_uncharge(memcg, nr_pages);
-}
-
 /*
  * A helper for accessing memcg's kmem_id, used for getting
  * corresponding LRU lists.
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 2ad72d2c8cc5..5d0767cb424a 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -37,6 +37,18 @@ void dump_mm(const struct mm_struct *mm);
 			BUG();						\
 		}							\
 	} while (0)
+#define VM_WARN_ON_ONCE_PAGE(cond, page)	({			\
+	static bool __section(".data.once") __warned;			\
+	int __ret_warn_once = !!(cond);					\
+									\
+	if (unlikely(__ret_warn_once && !__warned)) {			\
+		dump_page(page, "VM_WARN_ON_ONCE_PAGE(" __stringify(cond)")");\
+		__warned = true;					\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn_once);					\
+})
+
 #define VM_WARN_ON(cond) (void)WARN_ON(cond)
 #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
 #define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
@@ -48,6 +60,7 @@ void dump_mm(const struct mm_struct *mm);
 #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
 #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_ONCE_PAGE(cond, page)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #endif
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index df0c3c74609e..f3929aff39cf 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -362,6 +362,11 @@ asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
 				int maxevents, int timeout,
 				const sigset_t __user *sigmask,
 				size_t sigsetsize);
+asmlinkage long sys_epoll_pwait2(int epfd, struct epoll_event __user *events,
+				 int maxevents,
+				 const struct __kernel_timespec __user *timeout,
+				 const sigset_t __user *sigmask,
+				 size_t sigsetsize);
 
 /* fs/fcntl.c */
 asmlinkage long sys_dup(unsigned int fildes);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index fc48c64700eb..728752917785 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
 #define __NR_process_madvise 440
 __SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_epoll_pwait2 441
+__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 441
+#define __NR_syscalls 442
 
 /*
  * 32 bit systems traditionally used different