Merge branch 'akpm' (Andrew's patch-bomb)

Merge Andrew's second set of patches: - MM - a few random fixes - a couple of RTC leftovers * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (120 commits) rtc/rtc-88pm80x: remove unneed devm_kfree rtc/rtc-88pm80x: assign ret only when rtc_register_driver fails mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables tmpfs: distribute interleave better across nodes mm: remove redundant initialization mm: warn if pg_data_t isn't initialized with zero mips: zero out pg_data_t when it's allocated memcg: gix memory accounting scalability in shrink_page_list mm/sparse: remove index_init_lock mm/sparse: more checks on mem_section number mm/sparse: optimize sparse_index_alloc memcg: add mem_cgroup_from_css() helper memcg: further prevent OOM with too many dirty pages memcg: prevent OOM with too many dirty pages mm: mmu_notifier: fix freed page still mapped in secondary MMU mm: memcg: only check anon swapin page charges for swap cache mm: memcg: only check swap cache pages for repeated charging mm: memcg: split swapin charge function into private and public part mm: memcg: remove needless !mm fixup to init_mm when charging mm: memcg: remove unneeded shmem charge type ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2012-07-31 19:25:39 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2012-07-31 19:25:39 -0700
commit: ac694dbdbc403c00e2c14d10bc7b8412cc378259 (patch)
tree: e37328cfbeaf43716dd5914cad9179e57e84df76 /include
parent: a40a1d3d0a2fd613fdec6d89d3c053268ced76ed (diff)
parent: 437ea90cc3afdca5229b41c6b1d38c4842756cb9 (diff)
30 files changed, 492 insertions, 74 deletions
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 489de625cd25..c97c6b9cd38e 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -17,6 +17,7 @@
 #include <linux/timer.h>
 #include <linux/writeback.h>
 #include <linux/atomic.h>
+#include <linux/sysctl.h>
 
 struct page;
 struct device;
@@ -304,6 +305,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
 void set_bdi_congested(struct backing_dev_info *bdi, int sync);
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(struct zone *zone, int sync, long timeout);
+int pdflush_proc_obsolete(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp, loff_t *ppos);
 
 static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
 {
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 0edb65dd8edd..7b7ac9ccec7a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -160,6 +160,7 @@ enum rq_flag_bits {
 	__REQ_FLUSH_SEQ,	/* request for flush sequence */
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
+	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -201,5 +202,6 @@ enum rq_flag_bits {
 #define REQ_IO_STAT		(1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
+#define REQ_KERNEL		(1 << __REQ_KERNEL)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 0bd390ce98b2..dfae957398c3 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -31,7 +31,7 @@ SUBSYS(cpuacct)
 
 /* */
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 SUBSYS(mem_cgroup)
 #endif
 
@@ -72,3 +72,9 @@ SUBSYS(net_prio)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_HUGETLB
+SUBSYS(hugetlb)
+#endif
+
+/* */
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 51a90b7f2d60..133ddcf83397 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -58,7 +58,7 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 	if (++zone->compact_considered > defer_limit)
 		zone->compact_considered = defer_limit;
 
-	return zone->compact_considered < (1UL << zone->compact_defer_shift);
+	return zone->compact_considered < defer_limit;
 }
 
 #else
@@ -85,7 +85,7 @@ static inline void defer_compaction(struct zone *zone, int order)
 
 static inline bool compaction_deferred(struct zone *zone, int order)
 {
-	return 1;
+	return true;
 }
 
 #endif /* CONFIG_COMPACTION */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b178f9e91e23..d7eed5b98ae2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -165,6 +165,8 @@ struct inodes_stat_t {
 #define READ			0
 #define WRITE			RW_MASK
 #define READA			RWA_MASK
+#define KERNEL_READ		(READ|REQ_KERNEL)
+#define KERNEL_WRITE		(WRITE|REQ_KERNEL)
 
 #define READ_SYNC		(READ | REQ_SYNC)
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
@@ -427,6 +429,7 @@ struct kstatfs;
 struct vm_area_struct;
 struct vfsmount;
 struct cred;
+struct swap_info_struct;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -636,6 +639,11 @@ struct address_space_operations {
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
+
+	/* swapfile support */
+	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
+				sector_t *span);
+	void (*swap_deactivate)(struct file *file);
 };
 
 extern const struct address_space_operations empty_aops;
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 1e49be49d324..4883f393f50a 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -23,6 +23,7 @@ struct vm_area_struct;
 #define ___GFP_REPEAT		0x400u
 #define ___GFP_NOFAIL		0x800u
 #define ___GFP_NORETRY		0x1000u
+#define ___GFP_MEMALLOC		0x2000u
 #define ___GFP_COMP		0x4000u
 #define ___GFP_ZERO		0x8000u
 #define ___GFP_NOMEMALLOC	0x10000u
@@ -76,9 +77,14 @@ struct vm_area_struct;
 #define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)	/* See above */
 #define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)	/* See above */
 #define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY) /* See above */
+#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)	/* Add compound page metadata */
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)	/* Return zeroed page on success */
-#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves */
+#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves.
+							 * This takes precedence over the
+							 * __GFP_MEMALLOC flag if both are
+							 * set
+							 */
 #define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */
 #define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
@@ -129,7 +135,7 @@ struct vm_area_struct;
 /* Control page allocator reclaim behavior */
 #define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
 
 /* Control slab gfp mask during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS))
@@ -379,6 +385,9 @@ void drain_local_pages(void *dummy);
  */
 extern gfp_t gfp_allowed_mask;
 
+/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
+
 extern void pm_restrict_gfp_mask(void);
 extern void pm_restore_gfp_mask(void);
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 774fa47b3b5b..ef788b5b4a35 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -39,10 +39,17 @@ extern unsigned long totalhigh_pages;
 
 void kmap_flush_unused(void);
 
+struct page *kmap_to_page(void *addr);
+
 #else /* CONFIG_HIGHMEM */
 
 static inline unsigned int nr_free_highpages(void) { return 0; }
 
+static inline struct page *kmap_to_page(void *addr)
+{
+	return virt_to_page(addr);
+}
+
 #define totalhigh_pages 0UL
 
 #ifndef ARCH_HAS_KMAP
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d5d6bbe2259e..225164842ab6 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -4,9 +4,11 @@
 #include <linux/mm_types.h>
 #include <linux/fs.h>
 #include <linux/hugetlb_inline.h>
+#include <linux/cgroup.h>
 
 struct ctl_table;
 struct user_struct;
+struct mmu_gather;
 
 #ifdef CONFIG_HUGETLB_PAGE
 
@@ -20,6 +22,11 @@ struct hugepage_subpool {
 	long max_hpages, used_hpages;
 };
 
+extern spinlock_t hugetlb_lock;
+extern int hugetlb_max_hstate __read_mostly;
+#define for_each_hstate(h) \
+	for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
+
 struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
@@ -40,9 +47,14 @@ int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			struct page **, struct vm_area_struct **,
 			unsigned long *, int *, int, unsigned int flags);
 void unmap_hugepage_range(struct vm_area_struct *,
-			unsigned long, unsigned long, struct page *);
-void __unmap_hugepage_range(struct vm_area_struct *,
-			unsigned long, unsigned long, struct page *);
+			  unsigned long, unsigned long, struct page *);
+void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+			  struct vm_area_struct *vma,
+			  unsigned long start, unsigned long end,
+			  struct page *ref_page);
+void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
+				unsigned long start, unsigned long end,
+				struct page *ref_page);
 int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
 void hugetlb_report_meminfo(struct seq_file *);
 int hugetlb_report_node_meminfo(int, char *);
@@ -98,7 +110,6 @@ static inline unsigned long hugetlb_total_pages(void)
 #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
 #define hugetlb_prefault(mapping, vma)		({ BUG(); 0; })
-#define unmap_hugepage_range(vma, start, end, page)	BUG()
 static inline void hugetlb_report_meminfo(struct seq_file *m)
 {
 }
@@ -112,13 +123,31 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
 #define huge_pte_offset(mm, address)	0
-#define dequeue_hwpoisoned_huge_page(page)	0
+static inline int dequeue_hwpoisoned_huge_page(struct page *page)
+{
+	return 0;
+}
+
 static inline void copy_huge_page(struct page *dst, struct page *src)
 {
 }
 
 #define hugetlb_change_protection(vma, address, end, newprot)
 
+static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+			struct vm_area_struct *vma, unsigned long start,
+			unsigned long end, struct page *ref_page)
+{
+	BUG();
+}
+
+static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
+			struct vm_area_struct *vma, unsigned long start,
+			unsigned long end, struct page *ref_page)
+{
+	BUG();
+}
+
 #endif /* !CONFIG_HUGETLB_PAGE */
 
 #define HUGETLB_ANON_FILE "anon_hugepage"
@@ -199,10 +228,15 @@ struct hstate {
 	unsigned long resv_huge_pages;
 	unsigned long surplus_huge_pages;
 	unsigned long nr_overcommit_huge_pages;
+	struct list_head hugepage_activelist;
 	struct list_head hugepage_freelists[MAX_NUMNODES];
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_CGROUP_HUGETLB
+	/* cgroup control files */
+	struct cftype cgroup_files[5];
+#endif
 	char name[HSTATE_NAME_LEN];
 };
 
@@ -302,6 +336,11 @@ static inline unsigned hstate_index_to_shift(unsigned index)
 	return hstates[index].order + PAGE_SHIFT;
 }
 
+static inline int hstate_index(struct hstate *h)
+{
+	return h - hstates;
+}
+
 #else
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
@@ -320,6 +359,7 @@ static inline unsigned int pages_per_huge_page(struct hstate *h)
 	return 1;
 }
 #define hstate_index_to_shift(index) 0
+#define hstate_index(h) 0
 #endif
 
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
new file mode 100644
index 000000000000..d73878c694b3
--- /dev/null
+++ b/include/linux/hugetlb_cgroup.h
@@ -0,0 +1,126 @@
+/*
+ * Copyright IBM Corporation, 2012
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#ifndef _LINUX_HUGETLB_CGROUP_H
+#define _LINUX_HUGETLB_CGROUP_H
+
+#include <linux/res_counter.h>
+
+struct hugetlb_cgroup;
+/*
+ * Minimum page order trackable by hugetlb cgroup.
+ * At least 3 pages are necessary for all the tracking information.
+ */
+#define HUGETLB_CGROUP_MIN_ORDER	2
+
+#ifdef CONFIG_CGROUP_HUGETLB
+
+static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
+{
+	VM_BUG_ON(!PageHuge(page));
+
+	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
+		return NULL;
+	return (struct hugetlb_cgroup *)page[2].lru.next;
+}
+
+static inline
+int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
+{
+	VM_BUG_ON(!PageHuge(page));
+
+	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
+		return -1;
+	page[2].lru.next = (void *)h_cg;
+	return 0;
+}
+
+static inline bool hugetlb_cgroup_disabled(void)
+{
+	if (hugetlb_subsys.disabled)
+		return true;
+	return false;
+}
+
+extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
+					struct hugetlb_cgroup **ptr);
+extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
+					 struct hugetlb_cgroup *h_cg,
+					 struct page *page);
+extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
+					 struct page *page);
+extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
+					   struct hugetlb_cgroup *h_cg);
+extern int hugetlb_cgroup_file_init(int idx) __init;
+extern void hugetlb_cgroup_migrate(struct page *oldhpage,
+				   struct page *newhpage);
+
+#else
+static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
+{
+	return NULL;
+}
+
+static inline
+int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
+{
+	return 0;
+}
+
+static inline bool hugetlb_cgroup_disabled(void)
+{
+	return true;
+}
+
+static inline int
+hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
+			     struct hugetlb_cgroup **ptr)
+{
+	return 0;
+}
+
+static inline void
+hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
+			     struct hugetlb_cgroup *h_cg,
+			     struct page *page)
+{
+	return;
+}
+
+static inline void
+hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page)
+{
+	return;
+}
+
+static inline void
+hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
+			       struct hugetlb_cgroup *h_cg)
+{
+	return;
+}
+
+static inline int __init hugetlb_cgroup_file_init(int idx)
+{
+	return 0;
+}
+
+static inline void hugetlb_cgroup_migrate(struct page *oldhpage,
+					  struct page *newhpage)
+{
+	return;
+}
+
+#endif  /* CONFIG_MEM_RES_CTLR_HUGETLB */
+#endif
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 83e7ba90d6e5..8d9489fdab2e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -38,7 +38,7 @@ struct mem_cgroup_reclaim_cookie {
 	unsigned int generation;
 };
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 /*
  * All "charge" functions with gfp_mask should use GFP_KERNEL or
  * (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't
@@ -72,8 +72,6 @@ extern void mem_cgroup_uncharge_end(void);
 extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_uncharge_cache_page(struct page *page);
 
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-				     int order);
 bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 				  struct mem_cgroup *memcg);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg);
@@ -100,9 +98,9 @@ int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
 
-extern int
-mem_cgroup_prepare_migration(struct page *page,
-	struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask);
+extern void
+mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
+			     struct mem_cgroup **memcgp);
 extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	struct page *oldpage, struct page *newpage, bool migration_ok);
 
@@ -124,7 +122,7 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 extern void mem_cgroup_replace_page_cache(struct page *oldpage,
 					struct page *newpage);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
 
@@ -182,7 +180,6 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
-u64 mem_cgroup_get_limit(struct mem_cgroup *memcg);
 
 void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -193,7 +190,7 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 bool mem_cgroup_bad_page_check(struct page *page);
 void mem_cgroup_print_bad_page(struct page *page);
 #endif
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+#else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
 static inline int mem_cgroup_newpage_charge(struct page *page,
@@ -279,11 +276,10 @@ static inline struct cgroup_subsys_state
 	return NULL;
 }
 
-static inline int
+static inline void
 mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-	struct mem_cgroup **memcgp, gfp_t gfp_mask)
+			     struct mem_cgroup **memcgp)
 {
-	return 0;
 }
 
 static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
@@ -366,12 +362,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return 0;
 }
 
-static inline
-u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
-{
-	return 0;
-}
-
 static inline void mem_cgroup_split_huge_fixup(struct page *head)
 {
 }
@@ -384,9 +374,9 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
 				struct page *newpage)
 {
 }
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+#endif /* CONFIG_MEMCG */
 
-#if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM)
+#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
 static inline bool
 mem_cgroup_bad_page_check(struct page *page)
 {
@@ -406,7 +396,7 @@ enum {
 };
 
 struct sock;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 void sock_update_memcg(struct sock *sk);
 void sock_release_memcg(struct sock *sk);
 #else
@@ -416,6 +406,6 @@ static inline void sock_update_memcg(struct sock *sk)
 static inline void sock_release_memcg(struct sock *sk)
 {
 }
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 855c337b20c3..ce7e6671968b 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -15,7 +15,7 @@ extern int migrate_page(struct address_space *,
 extern int migrate_pages(struct list_head *l, new_page_t x,
 			unsigned long private, bool offlining,
 			enum migrate_mode mode);
-extern int migrate_huge_pages(struct list_head *l, new_page_t x,
+extern int migrate_huge_page(struct page *, new_page_t x,
 			unsigned long private, bool offlining,
 			enum migrate_mode mode);
 
@@ -36,7 +36,7 @@ static inline void putback_lru_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
-static inline int migrate_huge_pages(struct list_head *l, new_page_t x,
+static inline int migrate_huge_page(struct page *page, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f9f279cf5b1b..bd079a1b0fdc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -805,6 +805,17 @@ static inline void *page_rmapping(struct page *page)
 	return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
 }
 
+extern struct address_space *__page_file_mapping(struct page *);
+
+static inline
+struct address_space *page_file_mapping(struct page *page)
+{
+	if (unlikely(PageSwapCache(page)))
+		return __page_file_mapping(page);
+
+	return page->mapping;
+}
+
 static inline int PageAnon(struct page *page)
 {
 	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
@@ -821,6 +832,20 @@ static inline pgoff_t page_index(struct page *page)
 	return page->index;
 }
 
+extern pgoff_t __page_file_index(struct page *page);
+
+/*
+ * Return the file index of the page. Regular pagecache pages use ->index
+ * whereas swapcache pages use swp_offset(->private)
+ */
+static inline pgoff_t page_file_index(struct page *page)
+{
+	if (unlikely(PageSwapCache(page)))
+		return __page_file_index(page);
+
+	return page->index;
+}
+
 /*
  * Return true if this page is mapped into pagetables.
  */
@@ -994,6 +1019,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			struct page **pages, struct vm_area_struct **vmas);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
+struct kvec;
+int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
+			struct page **pages);
+int get_kernel_page(unsigned long start, int write, struct page **pages);
 struct page *get_dump_page(unsigned long addr);
 
 extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
@@ -1331,6 +1360,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
 extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
+extern void zone_pcp_reset(struct zone *zone);
 
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;
@@ -1528,6 +1558,7 @@ void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
 static inline void vm_stat_account(struct mm_struct *mm,
 			unsigned long flags, struct file *file, long pages)
 {
+	mm->total_vm += pages;
 }
 #endif /* CONFIG_PROC_FS */
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 074eb98fe15d..bf7867200b95 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -54,6 +54,15 @@ struct page {
 		union {
 			pgoff_t index;		/* Our offset within mapping. */
 			void *freelist;		/* slub/slob first free object */
+			bool pfmemalloc;	/* If set by the page allocator,
+						 * ALLOC_NO_WATERMARKS was set
+						 * and the low watermark was not
+						 * met implying that the system
+						 * is under some pressure. The
+						 * caller should try ensure
+						 * this page is only used to
+						 * free other pages.
+						 */
 		};
 
 		union {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 458988bd55a1..2daa54f55db7 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -201,7 +201,7 @@ struct zone_reclaim_stat {
 struct lruvec {
 	struct list_head lists[NR_LRU_LISTS];
 	struct zone_reclaim_stat reclaim_stat;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	struct zone *zone;
 #endif
 };
@@ -209,7 +209,6 @@ struct lruvec {
 /* Mask used at gathering information at once (see memcontrol.c) */
 #define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE))
 #define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON))
-#define LRU_ALL_EVICTABLE (LRU_ALL_FILE | LRU_ALL_ANON)
 #define LRU_ALL	     ((1 << NR_LRU_LISTS) - 1)
 
 /* Isolate clean file */
@@ -369,6 +368,10 @@ struct zone {
 	 */
 	spinlock_t		lock;
 	int                     all_unreclaimable; /* All pages pinned */
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+	/* pfn where the last incremental compaction isolated free pages */
+	unsigned long		compact_cached_free_pfn;
+#endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
 	seqlock_t		span_seqlock;
@@ -475,6 +478,14 @@ struct zone {
 	 * rarely used fields:
 	 */
 	const char		*name;
+#ifdef CONFIG_MEMORY_ISOLATION
+	/*
+	 * the number of MIGRATE_ISOLATE *pageblock*.
+	 * We need this for free page counting. Look at zone_watermark_ok_safe.
+	 * It's protected by zone->lock
+	 */
+	int		nr_pageblock_isolate;
+#endif
 } ____cacheline_internodealigned_in_smp;
 
 typedef enum {
@@ -671,7 +682,7 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	struct page_cgroup *node_page_cgroup;
 #endif
 #endif
@@ -694,6 +705,7 @@ typedef struct pglist_data {
 					     range, including holes */
 	int node_id;
 	wait_queue_head_t kswapd_wait;
+	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;	/* Protected by lock_memory_hotplug() */
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
@@ -718,7 +730,7 @@ typedef struct pglist_data {
 #include <linux/memory_hotplug.h>
 
 extern struct mutex zonelists_mutex;
-void build_all_zonelists(void *data);
+void build_all_zonelists(pg_data_t *pgdat, struct zone *zone);
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
 bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		int classzone_idx, int alloc_flags);
@@ -736,7 +748,7 @@ extern void lruvec_init(struct lruvec *lruvec, struct zone *zone);
 
 static inline struct zone *lruvec_zone(struct lruvec *lruvec)
 {
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	return lruvec->zone;
 #else
 	return container_of(lruvec, struct zone, lruvec);
@@ -773,7 +785,7 @@ extern int movable_zone;
 
 static inline int zone_movable_is_highmem(void)
 {
-#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE)
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
 	return movable_zone == ZONE_HIGHMEM;
 #else
 	return 0;
@@ -1052,7 +1064,7 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 	/*
 	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
 	 * section. (see memcontrol.h/page_cgroup.h about this.)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 2889877318bc..1f8fc7f9bcd8 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -473,10 +473,10 @@ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
 			unsigned long);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
 			const struct iovec *iov, unsigned long nr_segs,
-			loff_t pos);
+			loff_t pos, bool uio);
 extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
 			const struct iovec *iov, unsigned long nr_segs,
-			loff_t pos);
+			loff_t pos, bool uio);
 
 /*
  * linux/fs/nfs/dir.c
diff --git a/include/linux/oom.h b/include/linux/oom.h
index e4c29bc72e70..49a3031fda50 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -40,15 +40,36 @@ enum oom_constraint {
 	CONSTRAINT_MEMCG,
 };
 
+enum oom_scan_t {
+	OOM_SCAN_OK,		/* scan thread and find its badness */
+	OOM_SCAN_CONTINUE,	/* do not consider thread for oom kill */
+	OOM_SCAN_ABORT,		/* abort the iteration and return */
+	OOM_SCAN_SELECT,	/* always select this thread first */
+};
+
 extern void compare_swap_oom_score_adj(int old_val, int new_val);
 extern int test_set_oom_score_adj(int new_val);
 
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
+extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
+			     unsigned int points, unsigned long totalpages,
+			     struct mem_cgroup *memcg, nodemask_t *nodemask,
+			     const char *message);
+
 extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 
+extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
+			       int order, const nodemask_t *nodemask);
+
+extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
+		unsigned long totalpages, const nodemask_t *nodemask,
+		bool force_kill);
+extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order);
+
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *mask, bool force_kill);
 extern int register_oom_notifier(struct notifier_block *nb);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c88d2a9451af..b5d13841604e 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -7,6 +7,7 @@
 
 #include <linux/types.h>
 #include <linux/bug.h>
+#include <linux/mmdebug.h>
 #ifndef __GENERATING_BOUNDS_H
 #include <linux/mm_types.h>
 #include <generated/bounds.h>
@@ -453,6 +454,34 @@ static inline int PageTransTail(struct page *page)
 }
 #endif
 
+/*
+ * If network-based swap is enabled, sl*b must keep track of whether pages
+ * were allocated from pfmemalloc reserves.
+ */
+static inline int PageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	return PageActive(page);
+}
+
+static inline void SetPageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	SetPageActive(page);
+}
+
+static inline void __ClearPageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	__ClearPageActive(page);
+}
+
+static inline void ClearPageSlabPfmemalloc(struct page *page)
+{
+	VM_BUG_ON(!PageSlab(page));
+	ClearPageActive(page);
+}
+
 #ifdef CONFIG_MMU
 #define __PG_MLOCKED		(1 << PG_mlocked)
 #else
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 3bdcab30ca41..105077aa7685 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -1,6 +1,11 @@
 #ifndef __LINUX_PAGEISOLATION_H
 #define __LINUX_PAGEISOLATION_H
 
+
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count);
+void set_pageblock_migratetype(struct page *page, int migratetype);
+int move_freepages_block(struct zone *zone, struct page *page,
+				int migratetype);
 /*
  * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
  * If specified range includes migrate types other than MOVABLE or CMA,
@@ -10,7 +15,7 @@
  * free all pages in the range. test_page_isolated() can be used for
  * test it.
  */
-extern int
+int
 start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			 unsigned migratetype);
 
@@ -18,7 +23,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
  * target range is [start_pfn, end_pfn)
  */
-extern int
+int
 undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			unsigned migratetype);
 
@@ -30,8 +35,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
 /*
  * Internal functions. Changes pageblock's migrate type.
  */
-extern int set_migratetype_isolate(struct page *page);
-extern void unset_migratetype_isolate(struct page *page, unsigned migratetype);
+int set_migratetype_isolate(struct page *page);
+void unset_migratetype_isolate(struct page *page, unsigned migratetype);
 
 
 #endif
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index a88cdba27809..777a524716db 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -12,7 +12,7 @@ enum {
 #ifndef __GENERATING_BOUNDS_H
 #include <generated/bounds.h>
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 #include <linux/bit_spinlock.h>
 
 /*
@@ -82,7 +82,7 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc)
 	bit_spin_unlock(PCG_LOCK, &pc->flags);
 }
 
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+#else /* CONFIG_MEMCG */
 struct page_cgroup;
 
 static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
@@ -102,11 +102,11 @@ static inline void __init page_cgroup_init_flatmem(void)
 {
 }
 
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
+#endif /* CONFIG_MEMCG */
 
 #include <linux/swap.h>
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
 					unsigned short old, unsigned short new);
 extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
@@ -138,7 +138,7 @@ static inline void swap_cgroup_swapoff(int type)
 	return;
 }
 
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_SWAP */
+#endif /* CONFIG_MEMCG_SWAP */
 
 #endif /* !__GENERATING_BOUNDS_H */
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7cfad3bbb0cc..e42c762f0dc7 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -286,6 +286,11 @@ static inline loff_t page_offset(struct page *page)
 	return ((loff_t)page->index) << PAGE_CACHE_SHIFT;
 }
 
+static inline loff_t page_file_offset(struct page *page)
+{
+	return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT;
+}
+
 extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
 				     unsigned long address);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 68dcffaa62a0..c147e7024f11 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1584,7 +1584,7 @@ struct task_struct {
 	/* bitmask and counter of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
+#ifdef CONFIG_MEMCG /* memcg uses this to do batch job */
 	struct memcg_batch_info {
 		int do_batch;	/* incremented when batch uncharge started */
 		struct mem_cgroup *memcg; /* target memcg of uncharge */
@@ -1894,6 +1894,13 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
+static inline void tsk_restore_flags(struct task_struct *task,
+				unsigned long orig_flags, unsigned long flags)
+{
+	task->flags &= ~flags;
+	task->flags |= orig_flags & flags;
+}
+
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p,
 			       const struct cpumask *new_mask);
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 07ceb97d53fa..ac6b8ee07825 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -20,7 +20,6 @@ struct shrink_control {
  * 'nr_to_scan' entries and attempt to free them up.  It should return
  * the number of objects which remain in the cache.  If it returns -1, it means
  * it cannot do any scanning at this time (eg. there is a risk of deadlock).
- * The callback must not return -1 if nr_to_scan is zero.
  *
  * The 'gfpmask' refers to the allocation we are currently trying to
  * fulfil.
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d205c4be7f5b..7632c87da2c9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -462,6 +462,7 @@ struct sk_buff {
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
+	__u8			pfmemalloc:1;
 	__u8			ooo_okay:1;
 	__u8			l4_rxhash:1;
 	__u8			wifi_acked_valid:1;
@@ -502,6 +503,15 @@ struct sk_buff {
 #include <linux/slab.h>
 
 
+#define SKB_ALLOC_FCLONE	0x01
+#define SKB_ALLOC_RX		0x02
+
+/* Returns true if the skb was allocated from PFMEMALLOC reserves */
+static inline bool skb_pfmemalloc(const struct sk_buff *skb)
+{
+	return unlikely(skb->pfmemalloc);
+}
+
 /*
  * skb might have a dst pointer attached, refcounted or not.
  * _skb_refdst low order bit is set if refcount was _not_ taken
@@ -565,7 +575,7 @@ extern bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 			     bool *fragstolen, int *delta_truesize);
 
 extern struct sk_buff *__alloc_skb(unsigned int size,
-				   gfp_t priority, int fclone, int node);
+				   gfp_t priority, int flags, int node);
 extern struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
@@ -576,7 +586,7 @@ static inline struct sk_buff *alloc_skb(unsigned int size,
 static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 					       gfp_t priority)
 {
-	return __alloc_skb(size, priority, 1, NUMA_NO_NODE);
+	return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE);
 }
 
 extern void skb_recycle(struct sk_buff *skb);
@@ -1237,6 +1247,17 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 {
 	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
+	/*
+	 * Propagate page->pfmemalloc to the skb if we can. The problem is
+	 * that not all callers have unique ownership of the page. If
+	 * pfmemalloc is set, we check the mapping as a mapping implies
+	 * page->index is set (index and pfmemalloc share space).
+	 * If it's a valid mapping, we cannot use page->pfmemalloc but we
+	 * do not lose pfmemalloc information as the pages would not be
+	 * allocated using __GFP_MEMALLOC.
+	 */
+	if (page->pfmemalloc && !page->mapping)
+		skb->pfmemalloc	= true;
 	frag->page.p		  = page;
 	frag->page_offset	  = off;
 	skb_frag_size_set(frag, size);
@@ -1753,6 +1774,61 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 	return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
 }
 
+/*
+ *	__skb_alloc_page - allocate pages for ps-rx on a skb and preserve pfmemalloc data
+ *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ *	@order: size of the allocation
+ *
+ * 	Allocate a new page.
+ *
+ * 	%NULL is returned if there is no free memory.
+*/
+static inline struct page *__skb_alloc_pages(gfp_t gfp_mask,
+					      struct sk_buff *skb,
+					      unsigned int order)
+{
+	struct page *page;
+
+	gfp_mask |= __GFP_COLD;
+
+	if (!(gfp_mask & __GFP_NOMEMALLOC))
+		gfp_mask |= __GFP_MEMALLOC;
+
+	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+	if (skb && page && page->pfmemalloc)
+		skb->pfmemalloc = true;
+
+	return page;
+}
+
+/**
+ *	__skb_alloc_page - allocate a page for ps-rx for a given skb and preserve pfmemalloc data
+ *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ *
+ * 	Allocate a new page.
+ *
+ * 	%NULL is returned if there is no free memory.
+ */
+static inline struct page *__skb_alloc_page(gfp_t gfp_mask,
+					     struct sk_buff *skb)
+{
+	return __skb_alloc_pages(gfp_mask, skb, 0);
+}
+
+/**
+ *	skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page
+ *	@page: The page that was allocated from skb_alloc_page
+ *	@skb: The skb that may need pfmemalloc set
+ */
+static inline void skb_propagate_pfmemalloc(struct page *page,
+					     struct sk_buff *skb)
+{
+	if (page && page->pfmemalloc)
+		skb->pfmemalloc = true;
+}
+
 /**
  * skb_frag_page - retrieve the page refered to by a paged fragment
  * @frag: the paged fragment
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 77d278defa70..cff40aa7db62 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -174,6 +174,8 @@ struct rpc_xprt {
 	unsigned long		state;		/* transport state */
 	unsigned char		shutdown   : 1,	/* being shut down */
 				resvport   : 1; /* use a reserved port */
+	unsigned int		swapper;	/* we're swapping over this
+						   transport */
 	unsigned int		bind_index;	/* bind function index */
 
 	/*
@@ -316,6 +318,7 @@ void			xprt_release_rqst_cong(struct rpc_task *task);
 void			xprt_disconnect_done(struct rpc_xprt *xprt);
 void			xprt_force_disconnect(struct rpc_xprt *xprt);
 void			xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
+int			xs_swapper(struct rpc_xprt *xprt, int enable);
 
 /*
  * Reserved bit positions in xprt->state
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c84ec68eaec9..388e70601413 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -151,6 +151,7 @@ enum {
 	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
+	SWP_FILE	= (1 << 7),	/* set after swap_activate success */
 					/* add others here before... */
 	SWP_SCANNING	= (1 << 8),	/* refcount in scan_swap_map */
 };
@@ -301,7 +302,7 @@ static inline void scan_unevictable_unregister_node(struct node *node)
 
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 extern int mem_cgroup_swappiness(struct mem_cgroup *mem);
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
@@ -309,7 +310,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 	return vm_swappiness;
 }
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
 #else
 static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
@@ -320,8 +321,14 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);
 extern int swap_writepage(struct page *page, struct writeback_control *wbc);
+extern int swap_set_page_dirty(struct page *page);
 extern void end_swap_bio_read(struct bio *bio, int err);
 
+int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
+		unsigned long nr_pages, sector_t start_block);
+int generic_swapfile_activate(struct swap_info_struct *, struct file *,
+		sector_t *);
+
 /* linux/mm/swap_state.c */
 extern struct address_space swapper_space;
 #define total_swapcache_pages  swapper_space.nrpages
@@ -356,11 +363,12 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
+extern struct swap_info_struct *page_swap_info(struct page *);
 extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 extern void
 mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
 #else
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 06f8e3858251..57f7b1091511 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGSTEAL_DIRECT),
 		FOR_ALL_ZONES(PGSCAN_KSWAPD),
 		FOR_ALL_ZONES(PGSCAN_DIRECT),
+		PGSCAN_DIRECT_THROTTLE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 65efb92da996..ad2cfd53dadc 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -179,11 +179,6 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
 #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
 
-static inline void zap_zone_vm_stats(struct zone *zone)
-{
-	memset(zone->vm_stat, 0, sizeof(zone->vm_stat));
-}
-
 extern void inc_zone_state(struct zone *, enum zone_stat_item);
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 6d0a0fcd80e7..c66fe3332d83 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -189,9 +189,4 @@ void tag_pages_for_writeback(struct address_space *mapping,
 
 void account_page_redirty(struct page *page);
 
-/* pdflush.c */
-extern int nr_pdflush_threads;	/* Global so it can be exported to sysctl
-				   read-only. */
-
-
 #endif		/* WRITEBACK_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index e067f8c18f88..b3730239bf18 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -621,6 +621,7 @@ enum sock_flags {
 	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
 	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
 	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
+	SOCK_MEMALLOC, /* VM depends on this socket for swapping */
 	SOCK_TIMESTAMPING_TX_HARDWARE,  /* %SOF_TIMESTAMPING_TX_HARDWARE */
 	SOCK_TIMESTAMPING_TX_SOFTWARE,  /* %SOF_TIMESTAMPING_TX_SOFTWARE */
 	SOCK_TIMESTAMPING_RX_HARDWARE,  /* %SOF_TIMESTAMPING_RX_HARDWARE */
@@ -658,6 +659,26 @@ static inline bool sock_flag(const struct sock *sk, enum sock_flags flag)
 	return test_bit(flag, &sk->sk_flags);
 }
 
+#ifdef CONFIG_NET
+extern struct static_key memalloc_socks;
+static inline int sk_memalloc_socks(void)
+{
+	return static_key_false(&memalloc_socks);
+}
+#else
+
+static inline int sk_memalloc_socks(void)
+{
+	return 0;
+}
+
+#endif
+
+static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask)
+{
+	return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC);
+}
+
 static inline void sk_acceptq_removed(struct sock *sk)
 {
 	sk->sk_ack_backlog--;
@@ -733,8 +754,13 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	return 0;
 }
 
+extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+
 static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
+	if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+		return __sk_backlog_rcv(sk, skb);
+
 	return sk->sk_backlog_rcv(sk, skb);
 }
 
@@ -798,6 +824,8 @@ extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
 extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
 extern int sk_stream_error(struct sock *sk, int flags, int err);
 extern void sk_stream_kill_queues(struct sock *sk);
+extern void sk_set_memalloc(struct sock *sk);
+extern void sk_clear_memalloc(struct sock *sk);
 
 extern int sk_wait_data(struct sock *sk, long *timeo);
 
@@ -913,7 +941,7 @@ struct proto {
 #ifdef SOCK_REFCNT_DEBUG
 	atomic_t		socks;
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 	/*
 	 * cgroup specific init/deinit functions. Called once for all
 	 * protocols that implement it, from cgroups populate function.
@@ -994,7 +1022,7 @@ inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
-#if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET)
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET)
 extern struct static_key memcg_socket_limit_enabled;
 static inline struct cg_proto *parent_cg_proto(struct proto *proto,
 					       struct cg_proto *cg_proto)
@@ -1301,12 +1329,14 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size)
 		__sk_mem_schedule(sk, size, SK_MEM_SEND);
 }
 
-static inline bool sk_rmem_schedule(struct sock *sk, int size)
+static inline bool
+sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size)
 {
 	if (!sk_has_account(sk))
 		return true;
-	return size <= sk->sk_forward_alloc ||
-		__sk_mem_schedule(sk, size, SK_MEM_RECV);
+	return size<= sk->sk_forward_alloc ||
+		__sk_mem_schedule(sk, size, SK_MEM_RECV) ||
+		skb_pfmemalloc(skb);
 }
 
 static inline void sk_mem_reclaim(struct sock *sk)
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index 9fe3a36646e9..d6fd8e5b14b7 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -30,6 +30,7 @@
 	{(unsigned long)__GFP_COMP,		"GFP_COMP"},		\
 	{(unsigned long)__GFP_ZERO,		"GFP_ZERO"},		\
 	{(unsigned long)__GFP_NOMEMALLOC,	"GFP_NOMEMALLOC"},	\
+	{(unsigned long)__GFP_MEMALLOC,		"GFP_MEMALLOC"},	\
 	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
 	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
author	Linus Torvalds <torvalds@linux-foundation.org>	2012-07-31 19:25:39 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2012-07-31 19:25:39 -0700
commit	ac694dbdbc403c00e2c14d10bc7b8412cc378259 (patch)
tree	e37328cfbeaf43716dd5914cad9179e57e84df76 /include
parent	a40a1d3d0a2fd613fdec6d89d3c053268ced76ed (diff)
parent	437ea90cc3afdca5229b41c6b1d38c4842756cb9 (diff)