Merge branch 'akpm' (patches from Andrew)

Merge second patch-bomb from Andrew Morton:
 "Almost all of the rest of MM.  There was an unusually large amount of
  MM material this time"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (141 commits)
  zpool: remove no-op module init/exit
  mm: zbud: constify the zbud_ops
  mm: zpool: constify the zpool_ops
  mm: swap: zswap: maybe_preload & refactoring
  zram: unify error reporting
  zsmalloc: remove null check from destroy_handle_cache()
  zsmalloc: do not take class lock in zs_shrinker_count()
  zsmalloc: use class->pages_per_zspage
  zsmalloc: consider ZS_ALMOST_FULL as migrate source
  zsmalloc: partial page ordering within a fullness_list
  zsmalloc: use shrinker to trigger auto-compaction
  zsmalloc: account the number of compacted pages
  zsmalloc/zram: introduce zs_pool_stats api
  zsmalloc: cosmetic compaction code adjustments
  zsmalloc: introduce zs_can_compact() function
  zsmalloc: always keep per-class stats
  zsmalloc: drop unused variable `nr_to_migrate'
  mm/memblock.c: fix comment in __next_mem_range()
  mm/page_alloc.c: fix type information of memoryless node
  memory-hotplug: fix comments in zone_spanned_pages_in_node() and zone_spanned_pages_in_node()
  ...

20 files changed, 549 insertions, 156 deletions

diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
index 316bd043319e..734ad4db388c 100644
--- a/include/asm-generic/early_ioremap.h
+++ b/include/asm-generic/early_ioremap.h
@@ -35,6 +35,12 @@ extern void early_ioremap_setup(void);
  */
 extern void early_ioremap_reset(void);
 
+/*
+ * Early copy from unmapped memory to kernel mapped memory.
+ */
+extern void copy_from_early_mem(void *dest, phys_addr_t src,
+				unsigned long size);
+
 #else
 static inline void early_ioremap_init(void) { }
 static inline void early_ioremap_setup(void) { }
diff --git a/include/linux/dax.h b/include/linux/dax.h
new file mode 100644
index 000000000000..b415e521528d
--- /dev/null
+++ b/include/linux/dax.h
@@ -0,0 +1,39 @@
+#ifndef _LINUX_DAX_H
+#define _LINUX_DAX_H
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <asm/pgtable.h>
+
+ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
+		  get_block_t, dio_iodone_t, int flags);
+int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
+int dax_truncate_page(struct inode *, loff_t from, get_block_t);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+		dax_iodone_t);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+		dax_iodone_t);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+#else
+static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t *pmd, unsigned int flags, get_block_t gb,
+				dax_iodone_t di)
+{
+	return VM_FAULT_FALLBACK;
+}
+#define __dax_pmd_fault dax_pmd_fault
+#endif
+int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
+#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
+#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
+
+static inline bool vma_is_dax(struct vm_area_struct *vma)
+{
+	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
+}
+#endif
diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h
index e1043f79122f..53ba737505df 100644
--- a/include/linux/dmapool.h
+++ b/include/linux/dmapool.h
@@ -24,6 +24,12 @@ void dma_pool_destroy(struct dma_pool *pool);
 void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 		     dma_addr_t *handle);
 
+static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
+				    dma_addr_t *handle)
+{
+	return dma_pool_alloc(pool, mem_flags | __GFP_ZERO, handle);
+}
+
 void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr);
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b2f9b9c25e41..72d8a844c692 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -52,7 +52,6 @@ struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
 struct iov_iter;
-struct vm_fault;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -2678,19 +2677,6 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
-ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
-		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_blocks(struct inode *, sector_t block, long size);
-int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
-int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
-int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
-
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
 			    loff_t file_offset);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index ad35f300b9a4..f92cbd2f4450 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -63,7 +63,10 @@ struct vm_area_struct;
  * but it is definitely preferable to use the flag rather than opencode endless
  * loop around allocator.
  *
- * __GFP_NORETRY: The VM implementation must not retry indefinitely.
+ * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
+ * return NULL when direct reclaim and memory compaction have failed to allow
+ * the allocation to succeed.  The OOM killer is not called with the current
+ * implementation.
  *
  * __GFP_MOVABLE: Flag that this page will be movable by the page migration
  * mechanism or reclaimed
@@ -300,22 +303,31 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 	return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
 }
 
-static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
-						unsigned int order)
+/*
+ * Allocate pages, preferring the node given as nid. The node must be valid and
+ * online. For more general interface, see alloc_pages_node().
+ */
+static inline struct page *
+__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
-	/* Unknown node is current node */
-	if (nid < 0)
-		nid = numa_node_id();
+	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
+	VM_WARN_ON(!node_online(nid));
 
 	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
 }
 
-static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask,
+/*
+ * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
+ * prefer the current CPU's closest node. Otherwise node must be valid and
+ * online.
+ */
+static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
 						unsigned int order)
 {
-	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid));
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
-	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
+	return __alloc_pages_node(nid, gfp_mask, order);
 }
 
 #ifdef CONFIG_NUMA
@@ -354,7 +366,6 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
 void free_pages_exact(void *virt, size_t size);
-/* This is different from alloc_pages_exact_node !!! */
 void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 #define __get_free_page(gfp_mask) \
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f10b20f05159..ecb080d6ff42 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -33,6 +33,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma,
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
 			int prot_numa);
+int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
+			unsigned long pfn, bool write);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
@@ -122,7 +124,7 @@ extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
 #endif
 extern int hugepage_madvise(struct vm_area_struct *vma,
 			    unsigned long *vm_flags, int advice);
-extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
@@ -138,15 +140,6 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 	else
 		return 0;
 }
-static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
-					 unsigned long start,
-					 unsigned long end,
-					 long adjust_next)
-{
-	if (!vma->anon_vma || vma->vm_ops)
-		return;
-	__vma_adjust_trans_huge(vma, start, end, adjust_next);
-}
 static inline int hpage_nr_pages(struct page *page)
 {
 	if (unlikely(PageTransHuge(page)))
@@ -164,6 +157,13 @@ static inline bool is_huge_zero_page(struct page *page)
 	return ACCESS_ONCE(huge_zero_page) == page;
 }
 
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+	return is_huge_zero_page(pmd_page(pmd));
+}
+
+struct page *get_huge_zero_page(void);
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d891f949466a..5e35379f58a5 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -35,6 +35,9 @@ struct resv_map {
 	struct kref refs;
 	spinlock_t lock;
 	struct list_head regions;
+	long adds_in_progress;
+	struct list_head region_cache;
+	long region_cache_count;
 };
 extern struct resv_map *resv_map_alloc(void);
 void resv_map_release(struct kref *ref);
@@ -80,11 +83,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
-void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
+long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
+						long freed);
 int dequeue_hwpoisoned_huge_page(struct page *page);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
 void free_huge_page(struct page *page);
+void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve);
+extern struct mutex *hugetlb_fault_mutex_table;
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+				struct vm_area_struct *vma,
+				struct address_space *mapping,
+				pgoff_t idx, unsigned long address);
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
@@ -320,9 +330,13 @@ struct huge_bootmem_page {
 #endif
 };
 
+struct page *alloc_huge_page(struct vm_area_struct *vma,
+				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
 struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
+int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
+			pgoff_t idx);
 
 /* arch callback */
 int __init alloc_bootmem_huge_page(struct hstate *h);
@@ -471,6 +485,7 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
+#define alloc_huge_page(v, a, r) NULL
 #define alloc_huge_page_node(h, nid) NULL
 #define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index cc4b01972060..c518eb589260 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -77,6 +77,8 @@ int memblock_remove(phys_addr_t base, phys_addr_t size);
 int memblock_free(phys_addr_t base, phys_addr_t size);
 int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
+bool memblock_overlaps_region(struct memblock_type *type,
+			      phys_addr_t base, phys_addr_t size);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
@@ -323,7 +325,7 @@ void memblock_enforce_memory_limit(phys_addr_t memory_limit);
 int memblock_is_memory(phys_addr_t addr);
 int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
 int memblock_is_reserved(phys_addr_t addr);
-int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
+bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
 extern void __memblock_dump_all(void);
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 73b02b0a8f60..d92b80b63c5c 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -23,6 +23,11 @@
 #include <linux/vm_event_item.h>
 #include <linux/hardirq.h>
 #include <linux/jump_label.h>
+#include <linux/page_counter.h>
+#include <linux/vmpressure.h>
+#include <linux/eventfd.h>
+#include <linux/mmzone.h>
+#include <linux/writeback.h>
 
 struct mem_cgroup;
 struct page;
@@ -67,12 +72,221 @@ enum mem_cgroup_events_index {
 	MEMCG_NR_EVENTS,
 };
 
+/*
+ * Per memcg event counter is incremented at every pagein/pageout. With THP,
+ * it will be incremated by the number of pages. This counter is used for
+ * for trigger some periodic events. This is straightforward and better
+ * than using jiffies etc. to handle periodic memcg event.
+ */
+enum mem_cgroup_events_target {
+	MEM_CGROUP_TARGET_THRESH,
+	MEM_CGROUP_TARGET_SOFTLIMIT,
+	MEM_CGROUP_TARGET_NUMAINFO,
+	MEM_CGROUP_NTARGETS,
+};
+
+/*
+ * Bits in struct cg_proto.flags
+ */
+enum cg_proto_flags {
+	/* Currently active and new sockets should be assigned to cgroups */
+	MEMCG_SOCK_ACTIVE,
+	/* It was ever activated; we must disarm static keys on destruction */
+	MEMCG_SOCK_ACTIVATED,
+};
+
+struct cg_proto {
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
+	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
+	int			memory_pressure;
+	long			sysctl_mem[3];
+	unsigned long		flags;
+	/*
+	 * memcg field is used to find which memcg we belong directly
+	 * Each memcg struct can hold more than one cg_proto, so container_of
+	 * won't really cut.
+	 *
+	 * The elegant solution would be having an inverse function to
+	 * proto_cgroup in struct proto, but that means polluting the structure
+	 * for everybody, instead of just for memcg users.
+	 */
+	struct mem_cgroup	*memcg;
+};
+
 #ifdef CONFIG_MEMCG
+struct mem_cgroup_stat_cpu {
+	long count[MEM_CGROUP_STAT_NSTATS];
+	unsigned long events[MEMCG_NR_EVENTS];
+	unsigned long nr_page_events;
+	unsigned long targets[MEM_CGROUP_NTARGETS];
+};
+
+struct mem_cgroup_reclaim_iter {
+	struct mem_cgroup *position;
+	/* scan generation, increased every round-trip */
+	unsigned int generation;
+};
+
+/*
+ * per-zone information in memory controller.
+ */
+struct mem_cgroup_per_zone {
+	struct lruvec		lruvec;
+	unsigned long		lru_size[NR_LRU_LISTS];
+
+	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
+
+	struct rb_node		tree_node;	/* RB tree node */
+	unsigned long		usage_in_excess;/* Set to the value by which */
+						/* the soft limit is exceeded*/
+	bool			on_tree;
+	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
+						/* use container_of	   */
+};
+
+struct mem_cgroup_per_node {
+	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
+};
+
+struct mem_cgroup_threshold {
+	struct eventfd_ctx *eventfd;
+	unsigned long threshold;
+};
+
+/* For threshold */
+struct mem_cgroup_threshold_ary {
+	/* An array index points to threshold just below or equal to usage. */
+	int current_threshold;
+	/* Size of entries[] */
+	unsigned int size;
+	/* Array of thresholds */
+	struct mem_cgroup_threshold entries[0];
+};
+
+struct mem_cgroup_thresholds {
+	/* Primary thresholds array */
+	struct mem_cgroup_threshold_ary *primary;
+	/*
+	 * Spare threshold array.
+	 * This is needed to make mem_cgroup_unregister_event() "never fail".
+	 * It must be able to store at least primary->size - 1 entries.
+	 */
+	struct mem_cgroup_threshold_ary *spare;
+};
+
+/*
+ * The memory controller data structure. The memory controller controls both
+ * page cache and RSS per cgroup. We would eventually like to provide
+ * statistics based on the statistics developed by Rik Van Riel for clock-pro,
+ * to help the administrator determine what knobs to tune.
+ */
+struct mem_cgroup {
+	struct cgroup_subsys_state css;
+
+	/* Accounted resources */
+	struct page_counter memory;
+	struct page_counter memsw;
+	struct page_counter kmem;
+
+	/* Normal memory consumption range */
+	unsigned long low;
+	unsigned long high;
+
+	unsigned long soft_limit;
+
+	/* vmpressure notifications */
+	struct vmpressure vmpressure;
+
+	/* css_online() has been completed */
+	int initialized;
+
+	/*
+	 * Should the accounting and control be hierarchical, per subtree?
+	 */
+	bool use_hierarchy;
+
+	/* protected by memcg_oom_lock */
+	bool		oom_lock;
+	int		under_oom;
+
+	int	swappiness;
+	/* OOM-Killer disable */
+	int		oom_kill_disable;
+
+	/* protect arrays of thresholds */
+	struct mutex thresholds_lock;
+
+	/* thresholds for memory usage. RCU-protected */
+	struct mem_cgroup_thresholds thresholds;
+
+	/* thresholds for mem+swap usage. RCU-protected */
+	struct mem_cgroup_thresholds memsw_thresholds;
+
+	/* For oom notifier event fd */
+	struct list_head oom_notify;
+
+	/*
+	 * Should we move charges of a task when a task is moved into this
+	 * mem_cgroup ? And what type of charges should we move ?
+	 */
+	unsigned long move_charge_at_immigrate;
+	/*
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 */
+	atomic_t		moving_account;
+	/* taken only while moving_account > 0 */
+	spinlock_t		move_lock;
+	struct task_struct	*move_lock_task;
+	unsigned long		move_lock_flags;
+	/*
+	 * percpu counter.
+	 */
+	struct mem_cgroup_stat_cpu __percpu *stat;
+	spinlock_t pcp_counter_lock;
+
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
+	struct cg_proto tcp_mem;
+#endif
+#if defined(CONFIG_MEMCG_KMEM)
+        /* Index in the kmem_cache->memcg_params.memcg_caches array */
+	int kmemcg_id;
+	bool kmem_acct_activated;
+	bool kmem_acct_active;
+#endif
+
+	int last_scanned_node;
+#if MAX_NUMNODES > 1
+	nodemask_t	scan_nodes;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
+#endif
+
+#ifdef CONFIG_CGROUP_WRITEBACK
+	struct list_head cgwb_list;
+	struct wb_domain cgwb_domain;
+#endif
+
+	/* List of events which userspace want to receive */
+	struct list_head event_list;
+	spinlock_t event_list_lock;
+
+	struct mem_cgroup_per_node *nodeinfo[0];
+	/* WARNING: nodeinfo must be the last member here */
+};
 extern struct cgroup_subsys_state *mem_cgroup_root_css;
 
-void mem_cgroup_events(struct mem_cgroup *memcg,
+/**
+ * mem_cgroup_events - count memory events against a cgroup
+ * @memcg: the memory cgroup
+ * @idx: the event index
+ * @nr: the number of events to account for
+ */
+static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 		       enum mem_cgroup_events_index idx,
-		       unsigned int nr);
+		       unsigned int nr)
+{
+	this_cpu_add(memcg->stat->events[idx], nr);
+}
 
 bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
 
@@ -90,15 +304,31 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
-bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
-			      struct mem_cgroup *root);
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 
-extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
-extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
+struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+static inline
+struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
+	return css ? container_of(css, struct mem_cgroup, css) : NULL;
+}
+
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
+				   struct mem_cgroup *,
+				   struct mem_cgroup_reclaim_cookie *);
+void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
-extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
-extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
+static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
+			      struct mem_cgroup *root)
+{
+	if (root == memcg)
+		return true;
+	if (!root->use_hierarchy)
+		return false;
+	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
+}
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 				   struct mem_cgroup *memcg)
@@ -114,24 +344,67 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	return match;
 }
 
-extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
-extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
+struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
 
-struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
-				   struct mem_cgroup *,
-				   struct mem_cgroup_reclaim_cookie *);
-void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
+static inline bool mem_cgroup_disabled(void)
+{
+	if (memory_cgrp_subsys.disabled)
+		return true;
+	return false;
+}
 
 /*
  * For memory reclaim.
  */
-int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec);
-bool mem_cgroup_lruvec_online(struct lruvec *lruvec);
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
-unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
-void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
-extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
-					struct task_struct *p);
+
+void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
+		int nr_pages);
+
+static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+{
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return true;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	memcg = mz->memcg;
+
+	return !!(memcg->css.flags & CSS_ONLINE);
+}
+
+static inline
+unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
+{
+	struct mem_cgroup_per_zone *mz;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	return mz->lru_size[lru];
+}
+
+static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
+{
+	unsigned long inactive_ratio;
+	unsigned long inactive;
+	unsigned long active;
+	unsigned long gb;
+
+	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
+	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);
+
+	gb = (inactive + active) >> (30 - PAGE_SHIFT);
+	if (gb)
+		inactive_ratio = int_sqrt(10 * gb);
+	else
+		inactive_ratio = 1;
+
+	return inactive * inactive_ratio < active;
+}
+
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+				struct task_struct *p);
 
 static inline void mem_cgroup_oom_enable(void)
 {
@@ -156,18 +429,26 @@ bool mem_cgroup_oom_synchronize(bool wait);
 extern int do_swap_account;
 #endif
 
-static inline bool mem_cgroup_disabled(void)
-{
-	if (memory_cgrp_subsys.disabled)
-		return true;
-	return false;
-}
-
 struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
-void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx, int val);
 void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
 
+/**
+ * mem_cgroup_update_page_stat - update page state statistics
+ * @memcg: memcg to account against
+ * @idx: page state item to account
+ * @val: number of pages (positive or negative)
+ *
+ * See mem_cgroup_begin_page_stat() for locking requirements.
+ */
+static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
+				 enum mem_cgroup_stat_index idx, int val)
+{
+	VM_BUG_ON(!rcu_read_lock_held());
+
+	if (memcg)
+		this_cpu_add(memcg->stat->count[idx], val);
+}
+
 static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
 					    enum mem_cgroup_stat_index idx)
 {
@@ -184,13 +465,31 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
-void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
 static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 					     enum vm_event_item idx)
 {
+	struct mem_cgroup *memcg;
+
 	if (mem_cgroup_disabled())
 		return;
-	__mem_cgroup_count_vm_event(mm, idx);
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!memcg))
+		goto out;
+
+	switch (idx) {
+	case PGFAULT:
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
+		break;
+	case PGMAJFAULT:
+		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
+		break;
+	default:
+		BUG();
+	}
+out:
+	rcu_read_unlock();
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
@@ -199,8 +498,6 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
-#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
-
 static inline void mem_cgroup_events(struct mem_cgroup *memcg,
 				     enum mem_cgroup_events_index idx,
 				     unsigned int nr)
@@ -275,12 +572,6 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
-static inline struct cgroup_subsys_state
-		*mem_cgroup_css(struct mem_cgroup *memcg)
-{
-	return NULL;
-}
-
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -428,8 +719,8 @@ static inline void sock_release_memcg(struct sock *sk)
 extern struct static_key memcg_kmem_enabled_key;
 
 extern int memcg_nr_cache_ids;
-extern void memcg_get_cache_ids(void);
-extern void memcg_put_cache_ids(void);
+void memcg_get_cache_ids(void);
+void memcg_put_cache_ids(void);
 
 /*
  * Helper macro to loop through all memcg-specific caches. Callers must still
@@ -444,7 +735,10 @@ static inline bool memcg_kmem_enabled(void)
 	return static_key_false(&memcg_kmem_enabled_key);
 }
 
-bool memcg_kmem_is_active(struct mem_cgroup *memcg);
+static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+	return memcg->kmem_acct_active;
+}
 
 /*
  * In general, we'll do everything in our power to not incur in any overhead
@@ -463,7 +757,15 @@ void __memcg_kmem_commit_charge(struct page *page,
 				       struct mem_cgroup *memcg, int order);
 void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
-int memcg_cache_id(struct mem_cgroup *memcg);
+/*
+ * helper for acessing a memcg's index. It will be used as an index in the
+ * child cache array in kmem_cache, and also to derive its name. This function
+ * will return -1 when this is not a kmem-limited memcg.
+ */
+static inline int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return memcg ? memcg->kmemcg_id : -1;
+}
 
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1171a292e06e..f25a957bf0ab 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -249,6 +249,8 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
+						pmd_t *, unsigned int flags);
 	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
@@ -307,18 +309,6 @@ struct inode;
 #define page_private(page)		((page)->private)
 #define set_page_private(page, v)	((page)->private = (v))
 
-/* It's valid only if the page is free path or free_list */
-static inline void set_freepage_migratetype(struct page *page, int migratetype)
-{
-	page->index = migratetype;
-}
-
-/* It's valid only if the page is free path or free_list */
-static inline int get_freepage_migratetype(struct page *page)
-{
-	return page->index;
-}
-
 /*
  * FIXME: take this include out, include page-flags.h in
  * files which need it (119 of them)
@@ -359,18 +349,6 @@ static inline int get_page_unless_zero(struct page *page)
 	return atomic_inc_not_zero(&page->_count);
 }
 
-/*
- * Try to drop a ref unless the page has a refcount of one, return false if
- * that is the case.
- * This is to make sure that the refcount won't bec