Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "27 fixes.

  There are three patches that aren't actually fixes. They're simple
  function renamings which are nice-to-have in mainline as ongoing net
  development depends on them."

* akpm: (27 commits)
  timerfd: export defines to userspace
  mm/hugetlb.c: fix reservation race when freeing surplus pages
  mm/slab.c: fix SLAB freelist randomization duplicate entries
  zram: support BDI_CAP_STABLE_WRITES
  zram: revalidate disk under init_lock
  mm: support anonymous stable page
  mm: add documentation for page fragment APIs
  mm: rename __page_frag functions to __page_frag_cache, drop order from drain
  mm: rename __alloc_page_frag to page_frag_alloc and __free_page_frag to page_frag_free
  mm, memcg: fix the active list aging for lowmem requests when memcg is enabled
  mm: don't dereference struct page fields of invalid pages
  mailmap: add codeaurora.org names for nameless email commits
  signal: protect SIGNAL_UNKILLABLE from unintentional clearing.
  mm: pmd dirty emulation in page fault handler
  ipc/sem.c: fix incorrect sem_lock pairing
  lib/Kconfig.debug: fix frv build failure
  mm: get rid of __GFP_OTHER_NODE
  mm: fix remote numa hits statistics
  mm: fix devm_memremap_pages crash, use mem_hotplug_{begin, done}
  ocfs2: fix crash caused by stale lvb with fsdlm plugin
  ...

12 files changed, 87 insertions, 46 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 4175dca4ac39..0fe0b6295ab5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -38,9 +38,8 @@ struct vm_area_struct;
 #define ___GFP_ACCOUNT		0x100000u
 #define ___GFP_NOTRACK		0x200000u
 #define ___GFP_DIRECT_RECLAIM	0x400000u
-#define ___GFP_OTHER_NODE	0x800000u
-#define ___GFP_WRITE		0x1000000u
-#define ___GFP_KSWAPD_RECLAIM	0x2000000u
+#define ___GFP_WRITE		0x800000u
+#define ___GFP_KSWAPD_RECLAIM	0x1000000u
 /* If the above are modified, __GFP_BITS_SHIFT may need updating */
 
 /*
@@ -172,11 +171,6 @@ struct vm_area_struct;
  * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of
  *   distinguishing in the source between false positives and allocations that
  *   cannot be supported (e.g. page tables).
- *
- * __GFP_OTHER_NODE is for allocations that are on a remote node but that
- *   should not be accounted for as a remote allocation in vmstat. A
- *   typical user would be khugepaged collapsing a huge page on a remote
- *   node.
  */
 #define __GFP_COLD	((__force gfp_t)___GFP_COLD)
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
@@ -184,10 +178,9 @@ struct vm_area_struct;
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
 #define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
-#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE)
 
 /* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT 26
+#define __GFP_BITS_SHIFT 25
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /*
@@ -506,11 +499,10 @@ extern void free_hot_cold_page(struct page *page, bool cold);
 extern void free_hot_cold_page_list(struct list_head *list, bool cold);
 
 struct page_frag_cache;
-extern void __page_frag_drain(struct page *page, unsigned int order,
-			      unsigned int count);
-extern void *__alloc_page_frag(struct page_frag_cache *nc,
-			       unsigned int fragsz, gfp_t gfp_mask);
-extern void __free_page_frag(void *addr);
+extern void __page_frag_cache_drain(struct page *page, unsigned int count);
+extern void *page_frag_alloc(struct page_frag_cache *nc,
+			     unsigned int fragsz, gfp_t gfp_mask);
+extern void page_frag_free(void *addr);
 
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 61d20c17f3b7..254698856b8f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -120,7 +120,7 @@ struct mem_cgroup_reclaim_iter {
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
-	unsigned long		lru_size[NR_LRU_LISTS];
+	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
 
@@ -432,7 +432,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
-		int nr_pages);
+		int zid, int nr_pages);
 
 unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 					   int nid, unsigned int lru_mask);
@@ -441,9 +441,23 @@ static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
 	struct mem_cgroup_per_node *mz;
+	unsigned long nr_pages = 0;
+	int zid;
 
 	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	return mz->lru_size[lru];
+	for (zid = 0; zid < MAX_NR_ZONES; zid++)
+		nr_pages += mz->lru_zone_size[zid][lru];
+	return nr_pages;
+}
+
+static inline
+unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
+		enum lru_list lru, int zone_idx)
+{
+	struct mem_cgroup_per_node *mz;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	return mz->lru_zone_size[zone_idx][lru];
 }
 
 void mem_cgroup_handle_over_high(void);
@@ -671,6 +685,12 @@ mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
 	return 0;
 }
+static inline
+unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
+		enum lru_list lru, int zone_idx)
+{
+	return 0;
+}
 
 static inline unsigned long
 mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index fe6b4036664a..b84615b0f64c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1210,8 +1210,8 @@ 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(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
-	       spinlock_t **ptlp);
+int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	unsigned long *pfn);
 int follow_phys(struct vm_area_struct *vma, unsigned long address,
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 71613e8a720f..41d376e7116d 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -39,7 +39,7 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
 {
 	__update_lru_size(lruvec, lru, zid, nr_pages);
 #ifdef CONFIG_MEMCG
-	mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
+	mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
 #endif
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4d1905245c7a..ad3ec9ec61f7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -854,6 +854,16 @@ struct signal_struct {
 
 #define SIGNAL_UNKILLABLE	0x00000040 /* for init: ignore fatal signals */
 
+#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \
+			  SIGNAL_STOP_CONTINUED)
+
+static inline void signal_set_stop_flags(struct signal_struct *sig,
+					 unsigned int flags)
+{
+	WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP));
+	sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags;
+}
+
 /* If true, all threads except ->group_exit_task have pending SIGKILL */
 static inline int signal_group_exit(const struct signal_struct *sig)
 {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b53c0cfd417e..a410715bbef8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2480,7 +2480,7 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 
 static inline void skb_free_frag(void *addr)
 {
-	__free_page_frag(addr);
+	page_frag_free(addr);
 }
 
 void *napi_alloc_frag(unsigned int fragsz);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 084b12bad198..4c5363566815 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -226,7 +226,7 @@ static inline const char *__check_heap_object(const void *ptr,
  * (PAGE_SIZE*2).  Larger requests are passed to the page allocator.
  */
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
+#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT - 1)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
@@ -239,7 +239,7 @@ static inline const char *__check_heap_object(const void *ptr,
  * be allocated from the same page.
  */
 #define KMALLOC_SHIFT_HIGH	PAGE_SHIFT
-#define KMALLOC_SHIFT_MAX	30
+#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT - 1)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 09f4be179ff3..7f47b7098b1b 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -150,8 +150,9 @@ enum {
 	SWP_FILE	= (1 << 7),	/* set after swap_activate success */
 	SWP_AREA_DISCARD = (1 << 8),	/* single-time swap area discards */
 	SWP_PAGE_DISCARD = (1 << 9),	/* freed swap page-cluster discards */
+	SWP_STABLE_WRITES = (1 << 10),	/* no overwrite PG_writeback pages */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 10),	/* refcount in scan_swap_map */
+	SWP_SCANNING	= (1 << 11),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
diff --git a/include/linux/timerfd.h b/include/linux/timerfd.h
index bd36ce431e32..bab0b1ad0613 100644
--- a/include/linux/timerfd.h
+++ b/include/linux/timerfd.h
@@ -8,23 +8,7 @@
 #ifndef _LINUX_TIMERFD_H
 #define _LINUX_TIMERFD_H
 
-/* For O_CLOEXEC and O_NONBLOCK */
-#include <linux/fcntl.h>
-
-/* For _IO helpers */
-#include <linux/ioctl.h>
-
-/*
- * CAREFUL: Check include/asm-generic/fcntl.h when defining
- * new flags, since they might collide with O_* ones. We want
- * to re-use O_* flags that couldn't possibly have a meaning
- * from eventfd, in order to leave a free define-space for
- * shared O_* flags.
- */
-#define TFD_TIMER_ABSTIME (1 << 0)
-#define TFD_TIMER_CANCEL_ON_SET (1 << 1)
-#define TFD_CLOEXEC O_CLOEXEC
-#define TFD_NONBLOCK O_NONBLOCK
+#include <uapi/linux/timerfd.h>
 
 #define TFD_SHARED_FCNTL_FLAGS (TFD_CLOEXEC | TFD_NONBLOCK)
 /* Flags for timerfd_create.  */
@@ -32,6 +16,4 @@
 /* Flags for timerfd_settime.  */
 #define TFD_SETTIME_FLAGS (TFD_TIMER_ABSTIME | TFD_TIMER_CANCEL_ON_SET)
 
-#define TFD_IOC_SET_TICKS	_IOW('T', 0, u64)
-
 #endif /* _LINUX_TIMERFD_H */
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 9e687ca9a307..15bf875d0e4a 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -47,8 +47,7 @@
 	{(unsigned long)__GFP_WRITE,		"__GFP_WRITE"},		\
 	{(unsigned long)__GFP_RECLAIM,		"__GFP_RECLAIM"},	\
 	{(unsigned long)__GFP_DIRECT_RECLAIM,	"__GFP_DIRECT_RECLAIM"},\
-	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"},\
-	{(unsigned long)__GFP_OTHER_NODE,	"__GFP_OTHER_NODE"}	\
+	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"__GFP_KSWAPD_RECLAIM"}\
 
 #define show_gfp_flags(flags)						\
 	(flags) ? __print_flags(flags, "|",				\
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index a8b93e685239..f330ba4547cf 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -414,6 +414,7 @@ header-y += telephony.h
 header-y += termios.h
 header-y += thermal.h
 header-y += time.h
+header-y += timerfd.h
 header-y += times.h
 header-y += timex.h
 header-y += tiocl.h
diff --git a/include/uapi/linux/timerfd.h b/include/uapi/linux/timerfd.h
new file mode 100644
index 000000000000..6fcfaa8da173
--- /dev/null
+++ b/include/uapi/linux/timerfd.h
@@ -0,0 +1,36 @@
+/*
+ *  include/linux/timerfd.h
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#ifndef _UAPI_LINUX_TIMERFD_H
+#define _UAPI_LINUX_TIMERFD_H
+
+#include <linux/types.h>
+
+/* For O_CLOEXEC and O_NONBLOCK */
+#include <linux/fcntl.h>
+
+/* For _IO helpers */
+#include <linux/ioctl.h>
+
+/*
+ * CAREFUL: Check include/asm-generic/fcntl.h when defining
+ * new flags, since they might collide with O_* ones. We want
+ * to re-use O_* flags that couldn't possibly have a meaning
+ * from eventfd, in order to leave a free define-space for
+ * shared O_* flags.
+ *
+ * Also make sure to update the masks in include/linux/timerfd.h
+ * when adding new flags.
+ */
+#define TFD_TIMER_ABSTIME (1 << 0)
+#define TFD_TIMER_CANCEL_ON_SET (1 << 1)
+#define TFD_CLOEXEC O_CLOEXEC
+#define TFD_NONBLOCK O_NONBLOCK
+
+#define TFD_IOC_SET_TICKS	_IOW('T', 0, __u64)
+
+#endif /* _UAPI_LINUX_TIMERFD_H */