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
  ...

.mailmap

@@ -137,6 +137,7 @@ Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
 Rudolf Marek <R.Marek@sh.cvut.cz>
 Rui Saraiva <rmps@joel.ist.utl.pt>
 Sachin P Sant <ssant@in.ibm.com>
+Sarangdhar Joshi <spjoshi@codeaurora.org>
 Sam Ravnborg <sam@mars.ravnborg.org>
 Santosh Shilimkar <ssantosh@kernel.org>
 Santosh Shilimkar <santosh.shilimkar@oracle.org>
@@ -150,10 +151,13 @@ Shuah Khan <shuah@kernel.org> <shuah.kh@samsung.com>
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
+Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
+Subhash Jadavani <subhashj@codeaurora.org>
 Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
 Sumit Semwal <sumit.semwal@ti.com>
 Tejun Heo <htejun@gmail.com>
 Thomas Graf <tgraf@suug.ch>
+Thomas Pedersen <twp@codeaurora.org>
 Tony Luck <tony.luck@intel.com>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>

Documentation/vm/page_frags

@@ -0,0 +1,42 @@
+Page fragments
+--------------
+
+A page fragment is an arbitrary-length arbitrary-offset area of memory
+which resides within a 0 or higher order compound page.  Multiple
+fragments within that page are individually refcounted, in the page's
+reference counter.
+
+The page_frag functions, page_frag_alloc and page_frag_free, provide a
+simple allocation framework for page fragments.  This is used by the
+network stack and network device drivers to provide a backing region of
+memory for use as either an sk_buff->head, or to be used in the "frags"
+portion of skb_shared_info.
+
+In order to make use of the page fragment APIs a backing page fragment
+cache is needed.  This provides a central point for the fragment allocation
+and tracks allows multiple calls to make use of a cached page.  The
+advantage to doing this is that multiple calls to get_page can be avoided
+which can be expensive at allocation time.  However due to the nature of
+this caching it is required that any calls to the cache be protected by
+either a per-cpu limitation, or a per-cpu limitation and forcing interrupts
+to be disabled when executing the fragment allocation.
+
+The network stack uses two separate caches per CPU to handle fragment
+allocation.  The netdev_alloc_cache is used by callers making use of the
+__netdev_alloc_frag and __netdev_alloc_skb calls.  The napi_alloc_cache is
+used by callers of the __napi_alloc_frag and __napi_alloc_skb calls.  The
+main difference between these two calls is the context in which they may be
+called.  The "netdev" prefixed functions are usable in any context as these
+functions will disable interrupts, while the "napi" prefixed functions are
+only usable within the softirq context.
+
+Many network device drivers use a similar methodology for allocating page
+fragments, but the page fragments are cached at the ring or descriptor
+level.  In order to enable these cases it is necessary to provide a generic
+way of tearing down a page cache.  For this reason __page_frag_cache_drain
+was implemented.  It allows for freeing multiple references from a single
+page via a single call.  The advantage to doing this is that it allows for
+cleaning up the multiple references that were added to a page in order to
+avoid calling get_page per allocation.
+
+Alexander Duyck, Nov 29, 2016.

MAINTAINERS

@@ -81,7 +81,6 @@ Descriptions of section entries:
 	Q: Patchwork web based patch tracking system site
 	T: SCM tree type and location.
 	   Type is one of: git, hg, quilt, stgit, topgit
-	B: Bug tracking system location.
 	S: Status, one of the following:
 	   Supported:	Someone is actually paid to look after this.
 	   Maintained:	Someone actually looks after it.

drivers/block/zram/zram_drv.c

@@ -25,6 +25,7 @@
 #include <linux/genhd.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
+#include <linux/backing-dev.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/err.h>
@@ -112,6 +113,14 @@ static inline bool is_partial_io(struct bio_vec *bvec)
 	return bvec->bv_len != PAGE_SIZE;
 }
 
+static void zram_revalidate_disk(struct zram *zram)
+{
+	revalidate_disk(zram->disk);
+	/* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */
+	zram->disk->queue->backing_dev_info.capabilities |=
+		BDI_CAP_STABLE_WRITES;
+}
+
 /*
  * Check if request is within bounds and aligned on zram logical blocks.
  */
@@ -1095,15 +1104,9 @@ static ssize_t disksize_store(struct device *dev,
 	zram->comp = comp;
 	zram->disksize = disksize;
 	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
+	zram_revalidate_disk(zram);
 	up_write(&zram->init_lock);
 
-	/*
-	 * Revalidate disk out of the init_lock to avoid lockdep splat.
-	 * It's okay because disk's capacity is protected by init_lock
-	 * so that revalidate_disk always sees up-to-date capacity.
-	 */
-	revalidate_disk(zram->disk);
-
 	return len;
 
 out_destroy_comp:
@@ -1149,7 +1152,7 @@ static ssize_t reset_store(struct device *dev,
 	/* Make sure all the pending I/O are finished */
 	fsync_bdev(bdev);
 	zram_reset_device(zram);
-	revalidate_disk(zram->disk);
+	zram_revalidate_disk(zram);
 	bdput(bdev);
 
 	mutex_lock(&bdev->bd_mutex);

drivers/net/ethernet/intel/igb/igb_main.c

@@ -3962,8 +3962,8 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 				     PAGE_SIZE,
 				     DMA_FROM_DEVICE,
 				     DMA_ATTR_SKIP_CPU_SYNC);
-		__page_frag_drain(buffer_info->page, 0,
-				  buffer_info->pagecnt_bias);
+		__page_frag_cache_drain(buffer_info->page,
+					buffer_info->pagecnt_bias);
 
 		buffer_info->page = NULL;
 	}
@@ -6991,7 +6991,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
 				     PAGE_SIZE, DMA_FROM_DEVICE,
 				     DMA_ATTR_SKIP_CPU_SYNC);
-		__page_frag_drain(page, 0, rx_buffer->pagecnt_bias);
+		__page_frag_cache_drain(page, rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of rx_buffer */

fs/dax.c

@@ -691,8 +691,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
 				      pgoff_t index, unsigned long pfn)
 {
 	struct vm_area_struct *vma;
-	pte_t *ptep;
-	pte_t pte;
+	pte_t pte, *ptep = NULL;
+	pmd_t *pmdp = NULL;
 	spinlock_t *ptl;
 	bool changed;
 
@@ -707,21 +707,42 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
 
 		address = pgoff_address(index, vma);
 		changed = false;
-		if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+		if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl))
 			continue;
-		if (pfn != pte_pfn(*ptep))
-			goto unlock;
-		if (!pte_dirty(*ptep) && !pte_write(*ptep))
-			goto unlock;
 
-		flush_cache_page(vma, address, pfn);
-		pte = ptep_clear_flush(vma, address, ptep);
-		pte = pte_wrprotect(pte);
-		pte = pte_mkclean(pte);
-		set_pte_at(vma->vm_mm, address, ptep, pte);
-		changed = true;
-unlock:
-		pte_unmap_unlock(ptep, ptl);
+		if (pmdp) {
+#ifdef CONFIG_FS_DAX_PMD
+			pmd_t pmd;
+
+			if (pfn != pmd_pfn(*pmdp))
+				goto unlock_pmd;
+			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
+				goto unlock_pmd;
+
+			flush_cache_page(vma, address, pfn);
+			pmd = pmdp_huge_clear_flush(vma, address, pmdp);
+			pmd = pmd_wrprotect(pmd);
+			pmd = pmd_mkclean(pmd);
+			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+			changed = true;
+unlock_pmd:
+			spin_unlock(ptl);
+#endif
+		} else {
+			if (pfn != pte_pfn(*ptep))
+				goto unlock_pte;
+			if (!pte_dirty(*ptep) && !pte_write(*ptep))
+				goto unlock_pte;
+
+			flush_cache_page(vma, address, pfn);
+			pte = ptep_clear_flush(vma, address, ptep);
+			pte = pte_wrprotect(pte);
+			pte = pte_mkclean(pte);
+			set_pte_at(vma->vm_mm, address, ptep, pte);
+			changed = true;
+unlock_pte:
+			pte_unmap_unlock(ptep, ptl);
+		}
 
 		if (changed)
 			mmu_notifier_invalidate_page(vma->vm_mm, address);

fs/ocfs2/dlmglue.c

@@ -3303,6 +3303,16 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
 	mlog(ML_BASTS, "lockres %s, level %d => %d\n", lockres->l_name,
 	     lockres->l_level, new_level);
 
+	/*
+	 * On DLM_LKF_VALBLK, fsdlm behaves differently with o2cb. It always
+	 * expects DLM_LKF_VALBLK being set if the LKB has LVB, so that
+	 * we can recover correctly from node failure. Otherwise, we may get
+	 * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set.
+	 */
+	if (!ocfs2_is_o2cb_active() &&
+	    lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
+		lvb = 1;
+
 	if (lvb)
 		dlm_flags |= DLM_LKF_VALBLK;
 

fs/ocfs2/stackglue.c

@@ -48,6 +48,12 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
  */
 static struct ocfs2_stack_plugin *active_stack;
 
+inline int ocfs2_is_o2cb_active(void)
+{
+	return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB);
+}
+EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active);
+
 static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name)
 {
 	struct ocfs2_stack_plugin *p;

fs/ocfs2/stackglue.h

@@ -298,6 +298,9 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
+/* In ocfs2_downconvert_lock(), we need to know which stack we are using */
+int ocfs2_is_o2cb_active(void);
+
 extern struct kset *ocfs2_kset;
 
 #endif  /* STACKGLUE_H */

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)

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,

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,

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
 }
 

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)
 {

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);

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

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

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 */

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, "|",				\

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

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 */

ipc/sem.c

@@ -1977,7 +1977,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		}
 
 		rcu_read_lock();
-		sem_lock(sma, sops, nsops);
+		locknum = sem_lock(sma, sops, nsops);
 
 		if (!ipc_valid_object(&sma->sem_perm))
 			goto out_unlock_free;

kernel/bpf/arraymap.c

@@ -56,7 +56,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	    attr->value_size == 0 || attr->map_flags)
 		return ERR_PTR(-EINVAL);
 
-	if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1))
+	if (attr->value_size > KMALLOC_MAX_SIZE)
 		/* if value_size is bigger, the user space won't be able to
 		 * access the elements.
 		 */

kernel/bpf/hashtab.c

@@ -274,7 +274,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		 */
 		goto free_htab;
 
-	if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) -
+	if (htab->map.value_size >= KMALLOC_MAX_SIZE -
 	    MAX_BPF_STACK - sizeof(struct htab_elem))
 		/* if value_size is bigger, the user space won't be able to
 		 * access the elements via bpf syscall. This check also makes

kernel/memremap.c

@@ -246,7 +246,9 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(resource_size(res), SECTION_SIZE);
+	mem_hotplug_begin();
 	arch_remove_memory(align_start, align_size);
+	mem_hotplug_done();
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
 	pgmap_radix_release(res);
 	dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
@@ -358,7 +360,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
 	if (error)
 		goto err_pfn_remap;
 
+	mem_hotplug_begin();
 	error = arch_add_memory(nid, align_start, align_size, true);
+	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;
 

kernel/signal.c

@@ -346,7 +346,7 @@ static bool task_participate_group_stop(struct task_struct *task)
 	 * fresh group stop.  Read comment in do_signal_stop() for details.
 	 */
 	if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) {
-		sig->flags = SIGNAL_STOP_STOPPED;
+		signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED);
 		return true;
 	}
 	return false;
@@ -843,7 +843,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
 			 * will take ->siglock, notice SIGNAL_CLD_MASK, and
 			 * notify its parent. See get_signal_to_deliver().
 			 */
-			signal->flags = why | SIGNAL_STOP_CONTINUED;
+			signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED);
 			signal->group_stop_count = 0;
 			signal->group_exit_code = 0;
 		}

lib/Kconfig.debug

@@ -164,7 +164,7 @@ config DEBUG_INFO_REDUCED
 
 config DEBUG_INFO_SPLIT
 	bool "Produce split debuginfo in .dwo files"
-	depends on DEBUG_INFO
+	depends on DEBUG_INFO && !FRV
 	help
 	  Generate debug info into separate .dwo files. This significantly
 	  reduces the build directory size for builds with DEBUG_INFO,

mm/filemap.c

@@ -138,7 +138,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 				dax_radix_locked_entry(0, RADIX_DAX_EMPTY));
 			/* Wakeup waiters for exceptional entry lock */
 			dax_wake_mapping_entry_waiter(mapping, page->index, p,
-						      false);
+						      true);
 		}
 	}
 	__radix_tree_replace(&mapping->page_tree, node, slot, page,

mm/huge_memory.c

@@ -883,15 +883,17 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd)
 {
 	pmd_t entry;
 	unsigned long haddr;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (unlikely(!pmd_same(*vmf->pmd, orig_pmd)))
 		goto unlock;
 
 	entry = pmd_mkyoung(orig_pmd);
+	if (write)
+		entry = pmd_mkdirty(entry);
 	haddr = vmf->address & HPAGE_PMD_MASK;
-	if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry,
-				vmf->flags & FAULT_FLAG_WRITE))
+	if (pmdp_set_access_flags(vmf->vma, haddr, vmf->pmd, entry, write))
 		update_mmu_cache_pmd(vmf->vma, vmf->address, vmf->pmd);
 
 unlock:
@@ -919,8 +921,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd,
 	}
 
 	for (i = 0; i < HPAGE_PMD_NR; i++) {
-		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE |
-					       __GFP_OTHER_NODE, vma,
+		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma,
 					       vmf->address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
 			     mem_cgroup_try_charge(pages[i], vma->vm_mm,

mm/hugetlb.c

@@ -1773,23 +1773,32 @@ free:
 }
 
 /*
- * When releasing a hugetlb pool reservation, any surplus pages that were
- * allocated to satisfy the reservation must be explicitly freed if they were
- * never used.
- * Called with hugetlb_lock held.
+ * This routine has two main purposes:
+ * 1) Decrement the reservation count (resv_huge_pages) by the value passed
+ *    in unused_resv_pages.  This corresponds to the prior adjustments made
+ *    to the associated reservation map.
+ * 2) Free any unused surplus pages that may have been allocated to satisfy
+ *    the reservation.  As many as unused_resv_pages may be freed.
+ *
+ * Called with hugetlb_lock held.  However, the lock could be dropped (and
+ * reacquired) during calls to cond_resched_lock.  Whenever dropping the lock,
+ * we must make sure nobody else can claim pages we are in the process of
+ * freeing.  Do this by ensuring resv_huge_page always is greater than the
+ * number of huge pages we plan to free when dropping the lock.
  */
 static void return_unused_surplus_pages(struct hstate *h,
 					unsigned long unused_resv_pages)
 {
 	unsigned long nr_pages;
 
-	/* Uncommit the reservation */
-	h->resv_huge_pages -= unused_resv_pages;
-
 	/* Cannot return gigantic pages currently */
 	if (hstate_is_gigantic(h))
-		return;
+		goto out;
 
+	/*
+	 * Part (or even all) of the reservation could have been backed
+	 * by pre-allocated pages. Only free surplus pages.
+	 */
 	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
 
 	/*
@@ -1799,12 +1808,22 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * when the nodes with surplus pages have no free pages.
 	 * free_pool_huge_page() will balance the the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
+	 *
+	 * Note that we decrement resv_huge_pages as we free the pages.  If
+	 * we drop the lock, resv_huge_pages will still be sufficiently large
+	 * to cover subsequent pages we may free.
 	 */
 	while (nr_pages--) {
+		h->resv_huge_pages--;
+		unused_resv_pages--;
 		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
-			break;
+			goto out;
 		cond_resched_lock(&hugetlb_lock);
 	}
+
+out:
+	/* Fully uncommit the reservation */
+	h->resv_huge_pages -= unused_resv_pages;
 }
 
 

mm/khugepaged.c

@@ -943,7 +943,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
 	/* Only allocate from the target node */
-	gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_OTHER_NODE | __GFP_THISNODE;
+	gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
 
 	/*
 	 * Before allocating the hugepage, release the mmap_sem read lock.
@@ -1242,7 +1242,6 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 	struct vm_area_struct *vma;
 	unsigned long addr;
 	pmd_t *pmd, _pmd;
-	bool deposited = false;
 
 	i_mmap_lock_write(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -1267,26 +1266,10 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 			spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
 			/* assume page table is clear */
 			_pmd = pmdp_collapse_flush(vma, addr, pmd);
-			/*
-			 * now deposit the pgtable for arch that need it
-			 * otherwise free it.
-			 */
-			if (arch_needs_pgtable_deposit()) {
-				/*
-				 * The deposit should be visibile only after
-				 * collapse is seen by others.
-				 */
-				smp_wmb();
-				pgtable_trans_huge_deposit(vma->vm_mm, pmd,
-							   pmd_pgtable(_pmd));
-				deposited = true;
-			}
 			spin_unlock(ptl);
 			up_write(&vma->vm_mm->mmap_sem);
-			if (!deposited) {
-				atomic_long_dec(&vma->vm_mm->nr_ptes);
-				pte_free(vma->vm_mm, pmd_pgtable(_pmd));
-			}
+			atomic_long_dec(&vma->vm_mm->nr_ptes);
+			pte_free(vma->vm_mm, pmd_pgtable(_pmd));
 		}
 	}
 	i_mmap_unlock_write(mapping);
@@ -1326,8 +1309,7 @@ static void collapse_shmem(struct mm_struct *mm,
 	VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
 
 	/* Only allocate from the target node */
-	gfp = alloc_hugepage_khugepaged_gfpmask() |
-		__GFP_OTHER_NODE | __GFP_THISNODE;
+	gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE;
 
 	new_page = khugepaged_alloc_page(hpage, gfp, node);
 	if (!new_page) {

mm/memcontrol.c

@@ -625,8 +625,8 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 					   int nid, unsigned int lru_mask)
 {
+	struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg);
 	unsigned long nr = 0;
-	struct mem_cgroup_per_node *mz;
 	enum lru_list lru;
 
 	VM_BUG_ON((unsigned)nid >= nr_node_ids);
@@ -634,8 +634,7 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 	for_each_lru(lru) {
 		if (!(BIT(lru) & lru_mask))
 			continue;
-		mz = mem_cgroup_nodeinfo(memcg, nid);
-		nr += mz->lru_size[lru];
+		nr += mem_cgroup_get_lru_size(lruvec, lru);
 	}
 	return nr;
 }
@@ -1002,6 +1001,7 @@ out:
  * mem_cgroup_update_lru_size - account for adding or removing an lru page
  * @lruvec: mem_cgroup per zone lru vector
  * @lru: index of lru list the page is sitting on
+ * @zid: zone id of the accounted pages
  * @nr_pages: positive when adding or negative when removing
  *
  * This function must be called under lru_lock, just before a page is added
@@ -1009,27 +1009,25 @@ out:
  * so as to allow it to check that lru_size 0 is consistent with list_empty).
  */
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
-				int nr_pages)
+				int zid, int nr_pages)
 {
 	struct mem_cgroup_per_node *mz;
 	unsigned long *lru_size;
 	long size;
-	bool empty;
 
 	if (mem_cgroup_disabled())
 		return;
 
 	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	lru_size = mz->lru_size + lru;
-	empty = list_empty(lruvec->lists + lru);
+	lru_size = &mz->lru_zone_size[zid][lru];
 
 	if (nr_pages < 0)
 		*lru_size += nr_pages;
 
 	size = *lru_size;
-	if (WARN_ONCE(size < 0 || empty != !size,
-		"%s(%p, %d, %d): lru_size %ld but %sempty\n",
-		__func__, lruvec, lru, nr_pages, size, empty ? "" : "not ")) {
+	if (WARN_ONCE(size < 0,
+		"%s(%p, %d, %d): lru_size %ld\n",
+		__func__, lruvec, lru, nr_pages, size)) {
 		VM_BUG_ON(1);
 		*lru_size = 0;
 	}

mm/memory.c

@@ -3772,8 +3772,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-static int __follow_pte(struct mm_struct *mm, unsigned long address,
-		pte_t **ptepp, spinlock_t **ptlp)
+static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+		pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -3790,11 +3790,20 @@ static int __follow_pte(struct mm_struct *mm, unsigned long address,
 
 	pmd = pmd_offset(pud, address);
 	VM_BUG_ON(pmd_trans_huge(*pmd));
-	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-		goto out;
 
-	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
-	if (pmd_huge(*pmd))
+	if (pmd_huge(*pmd)) {
+		if (!pmdpp)
+			goto out;
+
+		*ptlp = pmd_lock(mm, pmd);
+		if (pmd_huge(*pmd)) {
+			*pmdpp = pmd;
+			return 0;
+		}
+		spin_unlock(*ptlp);
+	}
+
+	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 
 	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
@@ -3810,16 +3819,30 @@ out:
 	return -EINVAL;
 }
 
-int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp,
-	       spinlock_t **ptlp)
+static inline int follow_pte(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, spinlock_t **ptlp)
+{
+	int res;
+
+	/* (void) is needed to make gcc happy */
+	(void) __cond_lock(*ptlp,
+			   !(res = __follow_pte_pmd(mm, address, ptepp, NULL,
+					   ptlp)));
+	return res;
+}
+
+int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	int res;
 
 	/* (void) is needed to make gcc happy */
 	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte(mm, address, ptepp, ptlp)));
+			   !(res = __follow_pte_pmd(mm, address, ptepp, pmdpp,
+					   ptlp)));
 	return res;
 }
+EXPORT_SYMBOL(follow_pte_pmd);
 
 /**
  * follow_pfn - look up PFN at a user virtual address

mm/page_alloc.c

@@ -1864,14 +1864,14 @@ int move_freepages(struct zone *zone,
 #endif
 
 	for (page = start_page; page <= end_page;) {
-		/* Make sure we are not inadvertently changing nodes */
-		VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
-
 		if (!pfn_valid_within(page_to_pfn(page))) {
 			page++;
 			continue;
 		}
 
+		/* Make sure we are not inadvertently changing nodes */
+		VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
+
 		if (!PageBuddy(page)) {
 			page++;
 			continue;
@@ -2583,30 +2583,22 @@ int __isolate_free_page(struct page *page, unsigned int order)
  * Update NUMA hit/miss statistics
  *
  * Must be called with interrupts disabled.
- *
- * When __GFP_OTHER_NODE is set assume the node of the preferred
- * zone is the local node. This is useful for daemons who allocate
- * memory on behalf of other processes.
  */
-static inline void zone_statistics(struct zone *preferred_zone, struct zone *z,
-								gfp_t flags)
+static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 {
 #ifdef CONFIG_NUMA
-	int local_nid = numa_node_id();
 	enum zone_stat_item local_stat = NUMA_LOCAL;
 
-	if (unlikely(flags & __GFP_OTHER_NODE)) {
+	if (z->node != numa_node_id())
 		local_stat = NUMA_OTHER;
-		local_nid = preferred_zone->node;
-	}
 
-	if (z->node == local_nid) {
+	if (z->node == preferred_zone->node)
 		__inc_zone_state(z, NUMA_HIT);
-		__inc_zone_state(z, local_stat);
-	} else {
+	else {
 		__inc_zone_state(z, NUMA_MISS);
 		__inc_zone_state(preferred_zone, NUMA_FOREIGN);
 	}
+	__inc_zone_state(z, local_stat);
 #endif
 }
 
@@ -2674,7 +2666,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 	}
 
 	__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
-	zone_statistics(preferred_zone, zone, gfp_flags);
+	zone_statistics(preferred_zone, zone);
 	local_irq_restore(flags);
 
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
@@ -3904,8 +3896,8 @@ EXPORT_SYMBOL(free_pages);
  * drivers to provide a backing region of memory for use as either an
  * sk_buff->head, or to be used in the "frags" portion of skb_shared_info.
  */
-static struct page *__page_frag_refill(struct page_frag_cache *nc,
-				       gfp_t gfp_mask)
+static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
+					     gfp_t gfp_mask)
 {
 	struct page *page = NULL;
 	gfp_t gfp = gfp_mask;
@@ -3925,22 +3917,23 @@ static struct page *__page_frag_refill(struct page_frag_cache *nc,
 	return page;
 }
 
-void __page_frag_drain(struct page *page, unsigned int order,
-		       unsigned int count)
+void __page_frag_cache_drain(struct page *page, unsigned int count)
 {
 	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
 
 	if (page_ref_sub_and_test(page, count)) {
+		unsigned int order = compound_order(page);
+
 		if (order == 0)
 			free_hot_cold_page(page, false);
 		else
 			__free_pages_ok(page, order);
 	}
 }
-EXPORT_SYMBOL(__page_frag_drain);
+EXPORT_SYMBOL(__page_frag_cache_drain);
 
-void *__alloc_page_frag(struct page_frag_cache *nc,
-			unsigned int fragsz, gfp_t gfp_mask)
+void *page_frag_alloc(struct page_frag_cache *nc,
+		      unsigned int fragsz, gfp_t gfp_mask)
 {
 	unsigned int size = PAGE_SIZE;
 	struct page *page;
@@ -3948,7 +3941,7 @@ void *__alloc_page_frag(struct page_frag_cache *nc,
 
 	if (unlikely(!nc->va)) {
 refill:
-		page = __page_frag_refill(nc, gfp_mask);
+		page = __page_frag_cache_refill(nc, gfp_mask);
 		if (!page)
 			return NULL;
 
@@ -3991,19 +3984,19 @@ refill:
 
 	return nc->va + offset;
 }
-EXPORT_SYMBOL(__alloc_page_frag);
+EXPORT_SYMBOL(page_frag_alloc);
 
 /*
  * Frees a page fragment allocated out of either a compound or order 0 page.
  */
-void __free_page_frag(void *addr)
+void page_frag_free(void *addr)
 {
 	struct page *page = virt_to_head_page(addr);
 
 	if (unlikely(put_page_testzero(page)))
 		__free_pages_ok(page, compound_order(page));
 }
-EXPORT_SYMBOL(__free_page_frag);
+EXPORT_SYMBOL(page_frag_free);
 
 static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		size_t size)

mm/slab.c

@@ -2457,7 +2457,6 @@ union freelist_init_state {
 		unsigned int pos;
 		unsigned int *list;
 		unsigned int count;
-		unsigned int rand;
 	};
 	struct rnd_state rnd_state;
 };
@@ -2483,8 +2482,7 @@ static bool freelist_state_initialize(union freelist_init_state *state,
 	} else {
 		state->list = cachep->random_seq;
 		state->count = count;
-		state->pos = 0;
-		state->rand = rand;
+		state->pos = rand % count;
 		ret = true;
 	}
 	return ret;
@@ -2493,7 +2491,9 @@ static bool freelist_state_initialize(union freelist_init_state *state,
 /* Get the next entry on the list and randomize it using a random shift */
 static freelist_idx_t next_random_slot(union freelist_init_state *state)
 {
-	return (state->list[state->pos++] + state->rand) % state->count;
+	if (state->pos >= state->count)
+		state->pos = 0;
+	return state->list[state->pos++];
 }
 
 /* Swap two freelist entries */

mm/swapfile.c

@@ -943,11 +943,25 @@ bool reuse_swap_page(struct page *page, int *total_mapcount)
 	count = page_trans_huge_mapcount(page, total_mapcount);
 	if (count <= 1 && PageSwapCache(page)) {
 		count += page_swapcount(page);
-		if (count == 1 && !PageWriteback(page)) {
+		if (count != 1)
+			goto out;
+		if (!PageWriteback(page)) {
 			delete_from_swap_cache(page);
 			SetPageDirty(page);
+		} else {
+			swp_entry_t entry;
+			struct swap_info_struct *p;
+
+			entry.val = page_private(page);
+			p = swap_info_get(entry);
+			if (p->flags & SWP_STABLE_WRITES) {
+				spin_unlock(&p->lock);
+				return false;
+			}
+			spin_unlock(&p->lock);
 		}
 	}
+out:
 	return count <= 1;
 }
 
@@ -2448,6 +2462,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		error = -ENOMEM;
 		goto bad_swap;
 	}
+
+	if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
+		p->flags |= SWP_STABLE_WRITES;
+
 	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
 		int cpu;
 

mm/vmscan.c

@@ -242,6 +242,16 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
 	return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 }
 
+unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru,
+				   int zone_idx)
+{
+	if (!mem_cgroup_disabled())
+		return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx);
+
+	return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx],
+			       NR_ZONE_LRU_BASE + lru);
+}
+
 /*
  * Add a shrinker callback to be called from the vm.
  */
@@ -1382,8 +1392,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
  * be complete before mem_cgroup_update_lru_size due to a santity check.
  */
 static __always_inline void update_lru_sizes(struct lruvec *lruvec,
-			enum lru_list lru, unsigned long *nr_zone_taken,
-			unsigned long nr_taken)
+			enum lru_list lru, unsigned long *nr_zone_taken)
 {
 	int zid;
 
@@ -1392,11 +1401,11 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
 			continue;
 
 		__update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
-	}
-
 #ifdef CONFIG_MEMCG
-	mem_cgroup_update_lru_size(lruvec, lru, -nr_taken);
+		mem_cgroup_update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
 #endif
+	}
+
 }
 
 /*
@@ -1501,7 +1510,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	*nr_scanned = scan;
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
 				    nr_taken, mode, is_file_lru(lru));
-	update_lru_sizes(lruvec, lru, nr_zone_taken, nr_taken);
+	update_lru_sizes(lruvec, lru, nr_zone_taken);
 	return nr_taken;
 }
 
@@ -2047,10 +2056,8 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 		if (!managed_zone(zone))
 			continue;
 
-		inactive_zone = zone_page_state(zone,
-				NR_ZONE_LRU_BASE + (file * LRU_FILE));
-		active_zone = zone_page_state(zone,
-				NR_ZONE_LRU_BASE + (file * LRU_FILE) + LRU_ACTIVE);
+		inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid);
+		active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid);
 
 		inactive -= min(inactive, inactive_zone);
 		active -= min(active, active_zone);

net/core/skbuff.c

@@ -369,7 +369,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 
 	local_irq_save(flags);
 	nc = this_cpu_ptr(&netdev_alloc_cache);
-	data = __alloc_page_frag(nc, fragsz, gfp_mask);
+	data = page_frag_alloc(nc, fragsz, gfp_mask);
 	local_irq_restore(flags);
 	return data;
 }
@@ -391,7 +391,7 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 
-	return __alloc_page_frag(&nc->page, fragsz, gfp_mask);
+	return page_frag_alloc(&nc->page, fragsz, gfp_mask);
 }
 
 void *napi_alloc_frag(unsigned int fragsz)
@@ -441,7 +441,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 	local_irq_save(flags);
 
 	nc = this_cpu_ptr(&netdev_alloc_cache);
-	data = __alloc_page_frag(nc, len, gfp_mask);
+	data = page_frag_alloc(nc, len, gfp_mask);
 	pfmemalloc = nc->pfmemalloc;
 
 	local_irq_restore(flags);
@@ -505,7 +505,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 	if (sk_memalloc_socks())
 		gfp_mask |= __GFP_MEMALLOC;
 
-	data = __alloc_page_frag(&nc->page, len, gfp_mask);
+	data = page_frag_alloc(&nc->page, len, gfp_mask);
 	if (unlikely(!data))
 		return NULL;
 

tools/perf/builtin-kmem.c

@@ -655,7 +655,6 @@ static const struct {
 	{ "__GFP_RECLAIM",		"R" },
 	{ "__GFP_DIRECT_RECLAIM",	"DR" },
 	{ "__GFP_KSWAPD_RECLAIM",	"KR" },
-	{ "__GFP_OTHER_NODE",		"ON" },
 };
 
 static size_t max_gfp_len;