Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "142 patches:

   - DAX updates

   - various misc bits

   - OCFS2 updates

   - most of MM"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (142 commits)
  mm/z3fold.c: limit first_num to the actual range of possible buddy indexes
  mm: fix <linux/pagemap.h> stray kernel-doc notation
  zram: remove obsolete sysfs attrs
  mm/memblock.c: remove unnecessary log and clean up
  oom-reaper: use madvise_dontneed() logic to decide if unmap the VMA
  mm: drop unused argument of zap_page_range()
  mm: drop zap_details::check_swap_entries
  mm: drop zap_details::ignore_dirty
  mm, page_alloc: warn_alloc nodemask is NULL when cpusets are disabled
  mm: help __GFP_NOFAIL allocations which do not trigger OOM killer
  mm, oom: do not enforce OOM killer for __GFP_NOFAIL automatically
  mm: consolidate GFP_NOFAIL checks in the allocator slowpath
  lib/show_mem.c: teach show_mem to work with the given nodemask
  arch, mm: remove arch specific show_mem
  mm, page_alloc: warn_alloc print nodemask
  mm, page_alloc: do not report all nodes in show_mem
  Revert "mm: bail out in shrink_inactive_list()"
  mm, vmscan: consider eligible zones in get_scan_count
  mm, vmscan: cleanup lru size claculations
  mm, vmscan: do not count freed pages as PGDEACTIVATE
  ...

25 files changed, 753 insertions, 146 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 2983e52efd07..1e77ff5818f1 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -71,15 +71,13 @@ static inline unsigned int dax_radix_order(void *entry)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, const struct iomap_ops *ops);
+int dax_iomap_pmd_fault(struct vm_fault *vmf, const struct iomap_ops *ops);
 #else
 static inline unsigned int dax_radix_order(void *entry)
 {
 	return 0;
 }
-static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
-		unsigned long address, pmd_t *pmd, unsigned int flags,
+static inline int dax_iomap_pmd_fault(struct vm_fault *vmf,
 		const struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 97e478d6b690..f0029e786205 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -33,6 +33,7 @@ enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
+	TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
 	TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 48c76d612d40..503099d8aada 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -65,7 +65,8 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int,
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 struct page **, struct vm_area_struct **,
-			 unsigned long *, unsigned long *, long, unsigned int);
+			 unsigned long *, unsigned long *, long, unsigned int,
+			 int *);
 void unmap_hugepage_range(struct vm_area_struct *,
 			  unsigned long, unsigned long, struct page *);
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,
@@ -81,6 +82,11 @@ void hugetlb_show_meminfo(void);
 unsigned long hugetlb_total_pages(void);
 int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, unsigned int flags);
+int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte,
+				struct vm_area_struct *dst_vma,
+				unsigned long dst_addr,
+				unsigned long src_addr,
+				struct page **pagep);
 int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
@@ -131,7 +137,7 @@ static inline unsigned long hugetlb_total_pages(void)
 	return 0;
 }
 
-#define follow_hugetlb_page(m,v,p,vs,a,b,i,w)	({ BUG(); 0; })
+#define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n)	({ BUG(); 0; })
 #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
 static inline void hugetlb_report_meminfo(struct seq_file *m)
@@ -149,6 +155,8 @@ static inline void hugetlb_show_meminfo(void)
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
+#define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
+				src_addr, pagep)	({ BUG(); 0; })
 #define huge_pte_offset(mm, address)	0
 static inline int dequeue_hwpoisoned_huge_page(struct page *page)
 {
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 5b759c9acf97..38bcf00cbed3 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -203,6 +203,7 @@ int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
 			    unsigned long  *end_pfn);
 void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 			  unsigned long *out_end_pfn, int *out_nid);
+unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn);
 
 /**
  * for_each_mem_pfn_range - early memory pfn range iterator
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 254698856b8f..5af377303880 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -253,6 +253,7 @@ struct mem_cgroup {
         /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
 	enum memcg_kmem_state kmem_state;
+	struct list_head kmem_caches;
 #endif
 
 	int last_scanned_node;
@@ -829,6 +830,7 @@ void memcg_kmem_uncharge(struct page *page, int order);
 
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 extern struct static_key_false memcg_kmem_enabled_key;
+extern struct workqueue_struct *memcg_kmem_cache_wq;
 
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6ff66d6fe8e2..574bc157a27c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -285,6 +285,17 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */
 #define FAULT_FLAG_INSTRUCTION  0x100	/* The fault was during an instruction fetch */
 
+#define FAULT_FLAG_TRACE \
+	{ FAULT_FLAG_WRITE,		"WRITE" }, \
+	{ FAULT_FLAG_MKWRITE,		"MKWRITE" }, \
+	{ FAULT_FLAG_ALLOW_RETRY,	"ALLOW_RETRY" }, \
+	{ FAULT_FLAG_RETRY_NOWAIT,	"RETRY_NOWAIT" }, \
+	{ FAULT_FLAG_KILLABLE,		"KILLABLE" }, \
+	{ FAULT_FLAG_TRIED,		"TRIED" }, \
+	{ FAULT_FLAG_USER,		"USER" }, \
+	{ FAULT_FLAG_REMOTE,		"REMOTE" }, \
+	{ FAULT_FLAG_INSTRUCTION,	"INSTRUCTION" }
+
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
@@ -340,8 +351,7 @@ 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);
+	int (*pmd_fault)(struct vm_fault *vmf);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 
@@ -1111,6 +1121,20 @@ static inline void clear_page_pfmemalloc(struct page *page)
 			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
 			 VM_FAULT_FALLBACK)
 
+#define VM_FAULT_RESULT_TRACE \
+	{ VM_FAULT_OOM,			"OOM" }, \
+	{ VM_FAULT_SIGBUS,		"SIGBUS" }, \
+	{ VM_FAULT_MAJOR,		"MAJOR" }, \
+	{ VM_FAULT_WRITE,		"WRITE" }, \
+	{ VM_FAULT_HWPOISON,		"HWPOISON" }, \
+	{ VM_FAULT_HWPOISON_LARGE,	"HWPOISON_LARGE" }, \
+	{ VM_FAULT_SIGSEGV,		"SIGSEGV" }, \
+	{ VM_FAULT_NOPAGE,		"NOPAGE" }, \
+	{ VM_FAULT_LOCKED,		"LOCKED" }, \
+	{ VM_FAULT_RETRY,		"RETRY" }, \
+	{ VM_FAULT_FALLBACK,		"FALLBACK" }, \
+	{ VM_FAULT_DONE_COW,		"DONE_COW" }
+
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
 #define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf)
@@ -1128,8 +1152,7 @@ extern void pagefault_out_of_memory(void);
  */
 #define SHOW_MEM_FILTER_NODES		(0x0001u)	/* disallowed nodes */
 
-extern void show_free_areas(unsigned int flags);
-extern bool skip_free_areas_node(unsigned int flags, int nid);
+extern void show_free_areas(unsigned int flags, nodemask_t *nodemask);
 
 int shmem_zero_setup(struct vm_area_struct *);
 #ifdef CONFIG_SHMEM
@@ -1152,8 +1175,6 @@ struct zap_details {
 	struct address_space *check_mapping;	/* Check page->mapping if set */
 	pgoff_t	first_index;			/* Lowest page->index to unmap */
 	pgoff_t last_index;			/* Highest page->index to unmap */
-	bool ignore_dirty;			/* Ignore dirty pages */
-	bool check_swap_entries;		/* Check also swap entries */
 };
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -1164,7 +1185,7 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		unsigned long size);
 void zap_page_range(struct vm_area_struct *vma, unsigned long address,
-		unsigned long size, struct zap_details *);
+		unsigned long size);
 void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long start, unsigned long end);
 
@@ -1359,6 +1380,16 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma)
 	return !vma->vm_ops;
 }
 
+#ifdef CONFIG_SHMEM
+/*
+ * The vma_is_shmem is not inline because it is used only by slow
+ * paths in userfault.
+ */
+bool vma_is_shmem(struct vm_area_struct *vma);
+#else
+static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; }
+#endif
+
 static inline int stack_guard_page_start(struct vm_area_struct *vma,
 					     unsigned long addr)
 {
@@ -1900,7 +1931,7 @@ extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
 extern void __init mmap_init(void);
-extern void show_mem(unsigned int flags);
+extern void show_mem(unsigned int flags, nodemask_t *nodemask);
 extern long si_mem_available(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
@@ -1908,8 +1939,8 @@ extern void si_meminfo_node(struct sysinfo *val, int nid);
 extern unsigned long arch_reserved_kernel_pages(void);
 #endif
 
-extern __printf(2, 3)
-void warn_alloc(gfp_t gfp_mask, const char *fmt, ...);
+extern __printf(3, 4)
+void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...);
 
 extern void setup_per_cpu_pageset(void);
 
@@ -2049,6 +2080,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len) {}
 
 /* These take the mm semaphore themselves */
 extern int __must_check vm_brk(unsigned long, unsigned long);
+extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long);
 extern int vm_munmap(unsigned long, size_t);
 extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
         unsigned long, unsigned long,
@@ -2400,6 +2432,10 @@ extern void clear_huge_page(struct page *page,
 extern void copy_user_huge_page(struct page *dst, struct page *src,
 				unsigned long addr, struct vm_area_struct *vma,
 				unsigned int pages_per_huge_page);
+extern long copy_huge_page_from_user(struct page *dst_page,
+				const void __user *usr_src,
+				unsigned int pages_per_huge_page,
+				bool allow_pagefault);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
 extern struct page_ext_operations debug_guardpage_ops;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f4aac87adcc3..82fc632fd11d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -779,7 +779,7 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 #endif
 }
 
-extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru);
+extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);
 
 #ifdef CONFIG_HAVE_MEMORY_PRESENT
 void memory_present(int nid, unsigned long start, unsigned long end);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 324c8dbad1e1..84943e8057ef 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -266,7 +266,6 @@ static inline struct page *find_get_page_flags(struct address_space *mapping,
 
 /**
  * find_lock_page - locate, pin and lock a pagecache page
- * pagecache_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
  *
@@ -482,19 +481,11 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
 }
 
 /*
- * This is exported only for wait_on_page_locked/wait_on_page_writeback,
- * and for filesystems which need to wait on PG_private.
+ * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc.,
+ * and should not be used directly.
  */
 extern void wait_on_page_bit(struct page *page, int bit_nr);
 extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
-extern void wake_up_page_bit(struct page *page, int bit_nr);
-
-static inline void wake_up_page(struct page *page, int bit)
-{
-	if (!PageWaiters(page))
-		return;
-	wake_up_page_bit(page, bit);
-}
 
 /* 
  * Wait for a page to be unlocked.
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index a3d90b9da18d..033fc7bbcefa 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -15,6 +15,12 @@
 #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
 #define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
 
+#define PFN_FLAGS_TRACE \
+	{ PFN_SG_CHAIN,	"SG_CHAIN" }, \
+	{ PFN_SG_LAST,	"SG_LAST" }, \
+	{ PFN_DEV,	"DEV" }, \
+	{ PFN_MAP,	"MAP" }
+
 static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
 	pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index ff078e7043b6..fdaac9d4d46d 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -124,4 +124,15 @@ static inline bool shmem_huge_enabled(struct vm_area_struct *vma)
 }
 #endif
 
+#ifdef CONFIG_SHMEM
+extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
+				  struct vm_area_struct *dst_vma,
+				  unsigned long dst_addr,
+				  unsigned long src_addr,
+				  struct page **pagep);
+#else
+#define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
+			       src_addr, pagep)        ({ BUG(); 0; })
+#endif
+
 #endif
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 4c5363566815..3c37a8c51921 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -545,22 +545,49 @@ struct memcg_cache_array {
  * array to be accessed without taking any locks, on relocation we free the old
  * version only after a grace period.
  *
- * Child caches will hold extra metadata needed for its operation. Fields are:
+ * Root and child caches hold different metadata.
  *
- * @memcg: pointer to the memcg this cache belongs to
- * @root_cache: pointer to the global, root cache, this cache was derived from
+ * @root_cache:	Common to root and child caches.  NULL for root, pointer to
+ *		the root cache for children.
  *
- * Both root and child caches of the same kind are linked into a list chained
- * through @list.
+ * The following fields are specific to root caches.
+ *
+ * @memcg_caches: kmemcg ID indexed table of child caches.  This table is
+ *		used to index child cachces during allocation and cleared
+ *		early during shutdown.
+ *
+ * @root_caches_node: List node for slab_root_caches list.
+ *
+ * @children:	List of all child caches.  While the child caches are also
+ *		reachable through @memcg_caches, a child cache remains on
+ *		this list until it is actually destroyed.
+ *
+ * The following fields are specific to child caches.
+ *
+ * @memcg:	Pointer to the memcg this cache belongs to.
+ *
+ * @children_node: List node for @root_cache->children list.
+ *
+ * @kmem_caches_node: List node for @memcg->kmem_caches list.
  */
 struct memcg_cache_params {
-	bool is_root_cache;
-	struct list_head list;
+	struct kmem_cache *root_cache;
 	union {
-		struct memcg_cache_array __rcu *memcg_caches;
+		struct {
+			struct memcg_cache_array __rcu *memcg_caches;
+			struct list_head __root_caches_node;
+			struct list_head children;
+		};
 		struct {
 			struct mem_cgroup *memcg;
-			struct kmem_cache *root_cache;
+			struct list_head children_node;
+			struct list_head kmem_caches_node;
+
+			void (*deact_fn)(struct kmem_cache *);
+			union {
+				struct rcu_head deact_rcu_head;
+				struct work_struct deact_work;
+			};
 		};
 	};
 };
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 75f56c2ef2d4..07ef550c6627 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -113,9 +113,9 @@ struct kmem_cache {
 
 #ifdef CONFIG_SYSFS
 #define SLAB_SUPPORTS_SYSFS
-void sysfs_slab_remove(struct kmem_cache *);
+void sysfs_slab_release(struct kmem_cache *);
 #else
-static inline void sysfs_slab_remove(struct kmem_cache *s)
+static inline void sysfs_slab_release(struct kmem_cache *s)
 {
 }
 #endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7f47b7098b1b..45e91dd6716d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -27,6 +27,7 @@ struct bio;
 #define SWAP_FLAGS_VALID	(SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \
 				 SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \
 				 SWAP_FLAG_DISCARD_PAGES)
+#define SWAP_BATCH 64
 
 static inline int current_is_kswapd(void)
 {
@@ -176,6 +177,12 @@ enum {
  * protected by swap_info_struct.lock.
  */
 struct swap_cluster_info {
+	spinlock_t lock;	/*
+				 * Protect swap_cluster_info fields
+				 * and swap_info_struct->swap_map
+				 * elements correspond to the swap
+				 * cluster
+				 */
 	unsigned int data:24;
 	unsigned int flags:8;
 };
@@ -337,8 +344,13 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *,
 		sector_t *);
 
 /* linux/mm/swap_state.c */
-extern struct address_space swapper_spaces[];
-#define swap_address_space(entry) (&swapper_spaces[swp_type(entry)])
+/* One swap address space for each 64M swap space */
+#define SWAP_ADDRESS_SPACE_SHIFT	14
+#define SWAP_ADDRESS_SPACE_PAGES	(1 << SWAP_ADDRESS_SPACE_SHIFT)
+extern struct address_space *swapper_spaces[];
+#define swap_address_space(entry)			    \
+	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
+		>> SWAP_ADDRESS_SPACE_SHIFT])
 extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *, struct list_head *list);
@@ -360,6 +372,7 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t,
 /* linux/mm/swapfile.c */
 extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
+extern bool has_usable_swap(void);
 
 /* Swap 50% full? Release swapcache more aggressively.. */
 static inline bool vm_swap_full(void)
@@ -375,23 +388,31 @@ static inline long get_nr_swap_pages(void)
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
 extern swp_entry_t get_swap_page_of_type(int);
+extern int get_swap_pages(int n, swp_entry_t swp_entries[]);
 extern int add_swap_count_continuation(swp_entry_t, gfp_t);
 extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
 extern void swapcache_free(swp_entry_t);
+extern void swapcache_free_entries(swp_entry_t *entries, int n);
 extern int free_swap_and_cache(swp_entry_t);
 extern int swap_type_of(dev_t, sector_t, struct block_device **);
 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 int __swp_swapcount(swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
 extern bool reuse_swap_page(struct page *, int *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
+extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
+extern void exit_swap_address_space(unsigned int type);
+
+extern int get_swap_slots(int n, swp_entry_t *slots);
+extern void swapcache_free_batch(swp_entry_t *entries, int n);
 
 #else /* CONFIG_SWAP */
 
@@ -479,6 +500,11 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
+static inline int __swp_swapcount(swp_entry_t entry)
+{
+	return 0;
+}
+
 static inline int swp_swapcount(swp_entry_t entry)
 {
 	return 0;
diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
new file mode 100644
index 000000000000..6ef92d17633d
--- /dev/null
+++ b/include/linux/swap_slots.h
@@ -0,0 +1,30 @@
+#ifndef _LINUX_SWAP_SLOTS_H
+#define _LINUX_SWAP_SLOTS_H
+
+#include <linux/swap.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+
+#define SWAP_SLOTS_CACHE_SIZE			SWAP_BATCH
+#define THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE	(5*SWAP_SLOTS_CACHE_SIZE)
+#define THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE	(2*SWAP_SLOTS_CACHE_SIZE)
+
+struct swap_slots_cache {
+	bool		lock_initialized;
+	struct mutex	alloc_lock; /* protects slots, nr, cur */
+	swp_entry_t	*slots;
+	int		nr;
+	int		cur;
+	spinlock_t	free_lock;  /* protects slots_ret, n_ret */
+	swp_entry_t	*slots_ret;
+	int		n_ret;
+};
+
+void disable_swap_slots_cache_lock(void);
+void reenable_swap_slots_cache_unlock(void);
+int enable_swap_slots_cache(void);
+int free_swap_slot(swp_entry_t entry);
+
+extern bool swap_slot_cache_enabled;
+
+#endif /* _LINUX_SWAP_SLOTS_H */
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 0f165507495c..0af63c4381b9 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -23,6 +23,10 @@ const char *trace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 				    const struct trace_print_flags *symbol_array);
 
 #if BITS_PER_LONG == 32
+const char *trace_print_flags_seq_u64(struct trace_seq *p, const char *delim,
+		      unsigned long long flags,
+		      const struct trace_print_flags_u64 *flag_array);
+
 const char *trace_print_symbols_seq_u64(struct trace_seq *p,
 					unsigned long long val,
 					const struct trace_print_flags_u64
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 11b92b047a1e..f431861f22f1 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -52,6 +52,20 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 	return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP);
 }
 
+extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
+extern void dup_userfaultfd_complete(struct list_head *);
+
+extern void mremap_userfaultfd_prep(struct vm_area_struct *,
+				    struct vm_userfaultfd_ctx *);
+extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
+					unsigned long from, unsigned long to,
+					unsigned long len);
+
+extern void madvise_userfault_dontneed(struct vm_area_struct *vma,
+				       struct vm_area_struct **prev,
+				       unsigned long start,
+				       unsigned long end);
+
 #else /* CONFIG_USERFAULTFD */
 
 /* mm helpers */
@@ -76,6 +90,34 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 	return false;
 }
 
+static inline int dup_userfaultfd(struct vm_area_struct *vma,
+				  struct list_head *l)
+{
+	return 0;
+}
+
+static inline void dup_userfaultfd_complete(struct list_head *l)
+{
+}
+
+static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
+					   struct vm_userfaultfd_ctx *ctx)
+{
+}
+
+static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
+					       unsigned long from,
+					       unsigned long to,
+					       unsigned long len)
+{
+}
+
+static inline void madvise_userfault_dontneed(struct vm_area_struct *vma,
+					      struct vm_area_struct **prev,
+					      unsigned long start,
+					      unsigned long end)
+{
+}
 #endif /* CONFIG_USERFAULTFD */
 
 #endif /* _LINUX_USERFAULTFD_K_H */
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 4d6ec58a8d45..6aa1b6cb5828 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -56,6 +56,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		COMPACTISOLATED,
 		COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
 		KCOMPACTD_WAKE,
+		KCOMPACTD_MIGRATE_SCANNED, KCOMPACTD_FREE_SCANNED,
 #endif
 #ifdef CONFIG_HUGETLB_PAGE
 		HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index cbdb90b6b308..0a18ab6483ff 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -9,62 +9,6 @@
 #include <linux/tracepoint.h>
 #include <trace/events/mmflags.h>
 
-#define COMPACTION_STATUS					\
-	EM( COMPACT_SKIPPED,		"skipped")		\
-	EM( COMPACT_DEFERRED,		"deferred")		\
-	EM( COMPACT_CONTINUE,		"continue")		\
-	EM( COMPACT_SUCCESS,		"success")		\
-	EM( COMPACT_PARTIAL_SKIPPED,	"partial_skipped")	\
-	EM( COMPACT_COMPLETE,		"complete")		\
-	EM( COMPACT_NO_SUITABLE_PAGE,	"no_suitable_page")	\
-	EM( COMPACT_NOT_SUITABLE_ZONE,	"not_suitable_zone")	\
-	EMe(COMPACT_CONTENDED,		"contended")
-
-#ifdef CONFIG_ZONE_DMA
-#define IFDEF_ZONE_DMA(X) X
-#else
-#define IFDEF_ZONE_DMA(X)
-#endif
-
-#ifdef CONFIG_ZONE_DMA32
-#define IFDEF_ZONE_DMA32(X) X
-#else
-#define IFDEF_ZONE_DMA32(X)
-#endif
-
-#ifdef CONFIG_HIGHMEM
-#define IFDEF_ZONE_HIGHMEM(X) X
-#else
-#define IFDEF_ZONE_HIGHMEM(X)
-#endif
-
-#define ZONE_TYPE						\
-	IFDEF_ZONE_DMA(		EM (ZONE_DMA,	 "DMA"))	\
-	IFDEF_ZONE_DMA32(	EM (ZONE_DMA32,	 "DMA32"))	\
-				EM (ZONE_NORMAL, "Normal")	\
-	IFDEF_ZONE_HIGHMEM(	EM (ZONE_HIGHMEM,"HighMem"))	\
-				EMe(ZONE_MOVABLE,"Movable")
-
-/*
- * First define the enums in the above macros to be exported to userspace
- * via TRACE_DEFINE_ENUM().
- */
-#undef EM
-#undef EMe
-#define EM(a, b)	TRACE_DEFINE_ENUM(a);
-#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
-
-COMPACTION_STATUS
-ZONE_TYPE
-
-/*
- * Now redefine the EM() and EMe() macros to map the enums to the strings
- * that will be printed in the output.
- */
-#undef EM
-#undef EMe
-#define EM(a, b)	{a, b},
-#define EMe(a, b)	{a, b}
 
 DECLARE_EVENT_CLASS(mm_compaction_isolate_template,
 
@@ -187,6 +131,7 @@ TRACE_EVENT(mm_compaction_begin,
 		__entry->sync ? "sync" : "async")
 );
 
+#ifdef CONFIG_COMPACTION
 TRACE_EVENT(mm_compaction_end,
 	TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn,
 		unsigned long free_pfn, unsigned long zone_end, bool sync,
@@ -220,6 +165,7 @@ TRACE_EVENT(mm_compaction_end,
 		__entry->sync ? "sync" : "async",
 		__print_symbolic(__entry->status, COMPACTION_STATUS))
 );
+#endif
 
 TRACE_EVENT(mm_compaction_try_to_compact_pages,
 
@@ -248,6 +194,7 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages,
 		__entry->prio)
 );
 
+#ifdef CONFIG_COMPACTION
 DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
 
 	TP_PROTO(struct zone *zone,
@@ -295,7 +242,6 @@ DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
 	TP_ARGS(zone, order, ret)
 );
 
-#ifdef CONFIG_COMPACTION
 DECLARE_EVENT_CLASS(mm_compaction_defer_template,
 
 	TP_PROTO(struct zone *zone, int order),
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
new file mode 100644
index 000000000000..c566ddc87f73
--- /dev/null
+++ b/include/trace/events/fs_dax.h
@@ -0,0 +1,156 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM fs_dax
+
+#if !defined(_TRACE_FS_DAX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FS_DAX_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(dax_pmd_fault_class,
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		pgoff_t max_pgoff, int result),
+	TP_ARGS(inode, vmf, max_pgoff, result),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long, vm_start)
+		__field(unsigned long, vm_end)
+		__field(unsigned long, vm_flags)
+		__field(unsigned long, address)
+		__field(pgoff_t, pgoff)
+		__field(pgoff_t, max_pgoff)
+		__field(dev_t, dev)
+		__field(unsigned int, flags)
+		__field(int, result)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->vm_start = vmf->vma->vm_start;
+		__entry->vm_end = vmf->vma->vm_end;
+		__entry->vm_flags = vmf->vma->vm_flags;
+		__entry->address = vmf->address;
+		__entry->flags = vmf->flags;
+		__entry->pgoff = vmf->pgoff;
+		__entry->max_pgoff = max_pgoff;
+		__entry->result = result;
+	),
+	TP_printk("dev %d:%d ino %#lx %s %s address %#lx vm_start "
+			"%#lx vm_end %#lx pgoff %#lx max_pgoff %#lx %s",
+		MAJOR(__entry->dev),
+		MINOR(__entry->dev),
+		__entry->ino,
+		__entry->vm_flags & VM_SHARED ? "shared" : "private",
+		__print_flags(__entry->flags, "|", FAULT_FLAG_TRACE),
+		__entry->address,
+		__entry->vm_start,
+		__entry->vm_end,
+		__entry->pgoff,
+		__entry->max_pgoff,
+		__print_flags(__entry->result, "|", VM_FAULT_RESULT_TRACE)
+	)
+)
+
+#define DEFINE_PMD_FAULT_EVENT(name) \
+DEFINE_EVENT(dax_pmd_fault_class, name, \
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
+		pgoff_t max_pgoff, int result), \
+	TP_ARGS(inode, vmf, max_pgoff, result))
+
+DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
+DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
+
+DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		struct page *zero_page,
+		void *radix_entry),
+	TP_ARGS(inode, vmf, zero_page, radix_entry),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long, vm_flags)
+		__field(unsigned long, address)
+		__field(struct page *, zero_page)
+		__field(void *, radix_entry)
+		__field(dev_t, dev)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->vm_flags = vmf->vma->vm_flags;
+		__entry->address = vmf->address;
+		__entry->zero_page = zero_page;
+		__entry->radix_entry = radix_entry;
+	),
+	TP_printk("dev %d:%d ino %#lx %s address %#lx zero_page %p "
+			"radix_entry %#lx",
+		MAJOR(__entry->dev),
+		MINOR(__entry->dev),
+		__entry->ino,
+		__entry->vm_flags & VM_SHARED ? "shared" : "private",
+		__entry->address,
+		__entry->zero_page,
+		(unsigned long)__entry->radix_entry
+	)
+)
+
+#define DEFINE_PMD_LOAD_HOLE_EVENT(name) \
+DEFINE_EVENT(dax_pmd_load_hole_class, name, \
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
+		struct page *zero_page, void *radix_entry), \
+	TP_ARGS(inode, vmf, zero_page, radix_entry))
+
+DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole);
+DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback);
+
+DECLARE_EVENT_CLASS(dax_pmd_insert_mapping_class,
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf,
+		long length, pfn_t pfn, void *radix_entry),
+	TP_ARGS(inode, vmf, length, pfn, radix_entry),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long, vm_flags)
+		__field(unsigned long, address)
+		__field(long, length)
+		__field(u64, pfn_val)
+		__field(void *, radix_entry)
+		__field(dev_t, dev)
+		__field(int, write)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->vm_flags = vmf->vma->vm_flags;
+		__entry->address = vmf->address;
+		__entry->write = vmf->flags & FAULT_FLAG_WRITE;
+		__entry->length = length;
+		__entry->pfn_val = pfn.val;
+		__entry->radix_entry = radix_entry;
+	),
+	TP_printk("dev %d:%d ino %#lx %s %s address %#lx length %#lx "
+			"pfn %#llx %s radix_entry %#lx",
+		MAJOR(__entry->dev),
+		MINOR(__entry->dev),
+		__entry->ino,
+		__entry->vm_flags & VM_SHARED ? "shared" : "private",
+		__entry->write ? "write" : "read",
+		__entry->address,
+		__entry->length,
+		__entry->pfn_val & ~PFN_FLAGS_MASK,
+		__print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|",
+			PFN_FLAGS_TRACE),
+		(unsigned long)__entry->radix_entry
+	)
+)
+
+#define DEFINE_PMD_INSERT_MAPPING_EVENT(name) \
+DEFINE_EVENT(dax_pmd_insert_mapping_class, name, \
+	TP_PROTO(struct inode *inode, struct vm_fault *vmf, \
+		long length, pfn_t pfn, void *radix_entry), \
+	TP_ARGS(inode, vmf, length, pfn, radix_entry))
+
+DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping);
+DEFINE_PMD_INSERT_MAPPING_EVENT(dax_pmd_insert_mapping_fallback);
+
+#endif /* _TRACE_FS_DAX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 15bf875d0e4a..304ff94363b2 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -1,3 +1,6 @@
+#include <linux/node.h>
+#include <linux/mmzone.h>
+#include <linux/compaction.h>
 /*
  * The order of these masks is important. Matching masks will be seen
  * first and the left over flags will end up showing by themselves.
@@ -171,3 +174,98 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY,	"softdirty"	)		\
 	(flags) ? __print_flags(flags, "|",				\
 	__def_vmaflag_names						\
 	) : "none"
+
+#ifdef CONFIG_COMPACTION
+#define COMPACTION_STATUS					\
+	EM( COMPACT_SKIPPED,		"skipped")		\
+	EM( COMPACT_DEFERRED,		"deferred")		\
+	EM( COMPACT_CONTINUE,		"continue")		\
+	EM( COMPACT_SUCCESS,		"success")		\
+	EM( COMPACT_PARTIAL_SKIPPED,	"partial_skipped")	\
+	EM( COMPACT_COMPLETE,		"complete")		\
+	EM( COMPACT_NO_SUITABLE_PAGE,	"no_suitable_page")	\
+	EM( COMPACT_NOT_SUITABLE_ZONE,	"not_suitable_zone")	\
+	EMe(COMPACT_CONTENDED,		"contended")
+
+/* High-level compaction status feedback */
+#define COMPACTION_FAILED	1
+#define COMPACTION_WITHDRAWN	2
+#define COMPACTION_PROGRESS	3
+
+#define compact_result_to_feedback(result)	\
+({						\
+	enum compact_result __result = result;	\
+	(compaction_failed(__result)) ? COMPACTION_FAILED : \
+		(compaction_withdrawn(__result)) ? COMPACTION_WITHDRAWN : COMPACTION_PROGRESS; \
+})
+
+#define COMPACTION_FEEDBACK		\
+	EM(COMPACTION_FAILED,		"failed")	\
+	EM(COMPACTION_WITHDRAWN,	"withdrawn")	\
+	EMe(COMPACTION_PROGRESS,	"progress")
+
+#define COMPACTION_PRIORITY						\
+	EM(COMPACT_PRIO_SYNC_FULL,	"COMPACT_PRIO_SYNC_FULL")	\
+	EM(COMPACT_PRIO_SYNC_LIGHT,	"COMPACT_PRIO_SYNC_LIGHT")	\
+	EMe(COMPACT_PRIO_ASYNC,		"COMPACT_PRIO_ASYNC")
+#else
+#define COMPACTION_STATUS
+#define COMPACTION_PRIORITY
+#define COMPACTION_FEEDBACK
+#endif
+
+#ifdef CONFIG_ZONE_DMA
+#define IFDEF_ZONE_DMA(X) X
+#else
+#define IFDEF_ZONE_DMA(X)
+#endif
+
+#ifdef CONFIG_ZONE_DMA32
+#define IFDEF_ZONE_DMA32(X) X
+#else
+#define IFDEF_ZONE_DMA32(X)
+#endif
+
+#ifdef CONFIG_HIGHMEM
+#define IFDEF_ZONE_HIGHMEM(X) X
+#else
+#define IFDEF_ZONE_HIGHMEM(X)
+#endif
+
+#define ZONE_TYPE						\
+	IFDEF_ZONE_DMA(		EM (ZONE_DMA,	 "DMA"))	\
+	IFDEF_ZONE_DMA32(	EM (ZONE_DMA32,	 "DMA32"))	\
+				EM (ZONE_NORMAL, "Normal")	\
+	IFDEF_ZONE_HIGHMEM(	EM (ZONE_HIGHMEM,"HighMem"))	\
+				EMe(ZONE_MOVABLE,"Movable")
+
+#define LRU_NAMES		\
+		EM (LRU_INACTIVE_ANON, "inactive_anon") \
+		EM (LRU_ACTIVE_ANON, "active_anon") \
+		EM (LRU_INACTIVE_FILE, "inactive_file") \
+		EM (LRU_ACTIVE_FILE, "active_file") \
+		EMe(LRU_UNEVICTABLE, "unevictable")
+
+/*
+ * First define the enums in the above macros to be exported to userspace
+ * via TRACE_DEFINE_ENUM().
+ */
+#undef EM
+#undef EMe
+#define EM(a, b)	TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+COMPACTION_STATUS
+COMPACTION_PRIORITY
+COMPACTION_FEEDBACK
+ZONE_TYPE
+LRU_NAMES
+
+/*
+ * Now redefine the EM() and EMe() macros to map the enums to the strings
+ * that will be printed in the output.
+ */
+#undef EM
+#undef EMe
+#define EM(a, b)	{a, b},
+#define EMe(a, b)	{a, b}
diff --git a/include/trace/events/oom.h b/include/trace/events/oom.h
index 1e974983757e..38baeb27221a 100644
--- a/include/trace/events/oom.h
+++ b/include/trace/events/oom.h
@@ -4,6 +4,7 @@
 #if !defined(_TRACE_OOM_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_OOM_H
 #include <linux/tracepoint.h>
+#include <trace/events/mmflags.h>
 
 TRACE_EVENT(oom_score_adj_update,
 
@@ -27,6 +28,86 @@ TRACE_EVENT(oom_score_adj_update,
 		__entry->pid, __entry->comm, __entry->oom_score_adj)
 );
 
+TRACE_EVENT(reclaim_retry_zone,
+
+	TP_PROTO(struct zoneref *zoneref,
+		int order,
+		unsigned long reclaimable,
+		unsigned long available,
+		unsigned long min_wmark,
+		int no_progress_loops,
+		bool wmark_check),
+
+	TP_ARGS(zoneref, order, reclaimable, available, min_wmark, no_progress_loops, wmark_check),
+
+	TP_STRUCT__entry(
+		__field(	int, node)
+		__field(	int, zone_idx)
+		__field(	int,	order)
+		__field(	unsigned long,	reclaimable)
+		__field(	unsigned long,	available)
+		__field(	unsigned long,	min_wmark)
+		__field(	int,	no_progress_loops)
+		__field(	bool,	wmark_check)
+	),
+
+	TP_fast_assign(
+		__entry->node = zone_to_nid(zoneref->zone);
+		__entry->zone_idx = zoneref->zone_idx;
+		__entry->order = order;
+		__entry->reclaimable = reclaimable;
+		__entry->available = available;
+		__entry->min_wmark = min_wmark;
+		__entry->no_progress_loops = no_progress_loops;
+		__entry->wmark_check = wmark_check;
+	),
+
+	TP_printk("node=%d zone=%-8s order=%d reclaimable=%lu available=%lu min_wmark=%lu no_progress_loops=%d wmark_check=%d",
+			__entry->node, __print_symbolic(__entry->zone_idx, ZONE_TYPE),
+			__entry->order,
+			__entry->reclaimable, __entry->available, __entry->min_wmark,
+			__entry->no_progress_loops,
+			__entry->wmark_check)
+);
+
+#ifdef CONFIG_COMPACTION
+TRACE_EVENT(compact_retry,
+
+	TP_PROTO(int order,
+		enum compact_priority priority,
+		enum compact_result result,
+		int retries,
+		int max_retries,
+		bool ret),
+
+	TP_ARGS(order, priority, result, retries, max_retries, ret),
+
+	TP_STRUCT__entry(
+		__field(	int, order)
+		__field(	int, priority)
+		__field(	int, result)
+		__field(	int, retries)
+		__field(	int, max_retries)
+		__field(	bool, ret)
+	),
+
+	TP_fast_assign(
+		__entry->order = order;
+		__entry->priority = priority;
+		__entry->result = compact_result_to_feedback(result);
+		__entry->retries = retries;
+		__entry->max_retries = max_retries;
+		__entry->ret = ret;
+	),
+
+	TP_printk("order=%d priority=%s compaction_result=%s retries=%d max_retries=%d should_retry=%d",
+			__entry->order,
+			__print_symbolic(__entry->priority, COMPACTION_PRIORITY),
+			__print_symbolic(__entry->result, COMPACTION_FEEDBACK),
+			__entry->retries, __entry->max_retries,
+			__entry->ret)
+);
+#endif /* CONFIG_COMPACTION */
 #endif
 
 /* This part must be outside protection */
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index c88fd0934e7e..27e8a5c77579 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -15,6 +15,7 @@
 #define RECLAIM_WB_MIXED	0x0010u
 #define RECLAIM_WB_SYNC		0x0004u /* Unused, all reclaim async */
 #define RECLAIM_WB_ASYNC	0x0008u
+#define RECLAIM_WB_LRU		(RECLAIM_WB_ANON|RECLAIM_WB_FILE)
 
 #define show_reclaim_flags(flags)				\
 	(flags) ? __print_flags(flags, "|",			\
@@ -269,26 +270,27 @@ TRACE_EVENT(mm_shrink_slab_end,
 		__entry->retval)
 );
 
-DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
-
+TRACE_EVENT(mm_vmscan_lru_isolate,
 	TP_PROTO(int classzone_idx,
 		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
+		unsigned long nr_skipped,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
-		int file),
+		int lru),
 
-	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru),
 
 	TP_STRUCT__entry(
 		__field(int, classzone_idx)
 		__field(int, order)
 		__field(unsigned long, nr_requested)
 		__field(unsigned long, nr_scanned)
+		__field(unsigned long, nr_skipped)
 		__field(unsigned long, nr_taken)
 		__field(isolate_mode_t, isolate_mode)
-		__field(int, file)
+		__field(int, lru)
 	),
 
 	TP_fast_assign(
@@ -296,47 +298,21 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		__entry->order = order;
 		__entry->nr_requested = nr_requested;
 		__entry->nr_scanned = nr_scanned;
+		__entry->nr_skipped = nr_skipped;
 		__entry->nr_taken = nr_taken;
 		__entry->isolate_mode = isolate_mode;
-		__entry->file = file;
+		__entry->lru = lru;
 	),
 
-	TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
+	TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s",
 		__entry->isolate_mode,
 		__entry->classzone_idx,
 		__entry->order,
 		__entry->nr_requested,
 		__entry->nr_scanned,
+		__entry->nr_skipped,
 		__entry->nr_taken,
-		__entry->file)
-);
-
-DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
-
-	TP_PROTO(int classzone_idx,
-		int order,
-		unsigned long nr_requested,
-		unsigned long nr_scanned,
-		unsigned long nr_taken,
-		isolate_mode_t isolate_mode,
-		int file),
-
-	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
-
-);
-
-DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
-
-	TP_PROTO(int classzone_idx,
-		int order,
-		unsigned long nr_requested,
-		unsigned long nr_scanned,
-		unsigned long nr_taken,
-		isolate_mode_t isolate_mode,
-		int file),
-
-	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
-
+		__print_symbolic(__entry->lru, LRU_NAMES))
 );
 
 TRACE_EVENT(mm_vmscan_writepage,
@@ -365,14 +341,27 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 
 	TP_PROTO(int nid,
 		unsigned long nr_scanned, unsigned long nr_reclaimed,
+		unsigned long nr_dirty, unsigned long nr_writeback,
+		unsigned long nr_congested, unsigned long nr_immediate,
+		unsigned long nr_activate, unsigned long nr_ref_keep,
+		unsigned long nr_unmap_fail,
 		int priority, int file),
 
-	TP_ARGS(nid, nr_scanned, nr_reclaimed, priority, file),
+	TP_ARGS(nid, nr_scanned, nr_reclaimed, nr_dirty, nr_writeback,
+		nr_congested, nr_immediate, nr_activate, nr_ref_keep,
+		nr_unmap_fail, priority, file),
 
 	TP_STRUCT__entry(
 		__field(int, nid)
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_reclaimed)
+		__field(unsigned long, nr_dirty)
+		__field(unsigned long, nr_writeback)
+		__field(unsigned long, nr_congested)
+		__field(unsigned long, nr_immediate)
+		__field(unsigned long, nr_activate)
+		__field(unsigned long, nr_ref_keep)
+		__field(unsigned long, nr_unmap_fail)
 		__field(int, priority)
 		__field(int, reclaim_flags)
 	),
@@ -381,17 +370,102 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 		__entry->nid = nid;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_reclaimed = nr_reclaimed;
+		__entry->nr_dirty = nr_dirty;
+		__entry->nr_writeback = nr_writeback;
+		__entry->nr_congested = nr_congested;
+		__entry->nr_immediate = nr_immediate;
+		__entry->nr_activate = nr_activate;
+		__entry->nr_ref_keep = nr_ref_keep;
+		__entry->nr_unmap_fail = nr_unmap_fail;
 		__entry->priority = priority;
 		__entry->reclaim_flags = trace_shrink_flags(file);
 	),
 
-	TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
+	TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate=%ld nr_ref_keep=%ld nr_unmap_fail=%ld priority=%d flags=%s",
 		__entry->nid,
 		__entry->nr_scanned, __entry->nr_reclaimed,
+		__entry->nr_dirty, __entry->nr_writeback,
+		__entry->nr_congested, __entry->nr_immediate,
+		__entry->nr_activate, __entry->nr_ref_keep,
+		__entry->nr_unmap_fail, __entry->priority,
+		show_reclaim_flags(__entry->reclaim_flags))
+);
+
+TRACE_EVENT(mm_vmscan_lru_shrink_active,
+
+	TP_PROTO(int nid, unsigned long nr_taken,
+		unsigned long nr_active, unsigned long nr_deactivated,
+		unsigned long nr_referenced, int priority, int file),
+
+	TP_ARGS(nid, nr_taken, nr_active, nr_deactivated, nr_referenced, priority, file),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(unsigned long, nr_taken)
+		__field(unsigned long, nr_active)
+		__field(unsigned long, nr_deactivated)
+		__field(unsigned long, nr_referenced)
+		__field(int, priority)
+		__field(int, reclaim_flags)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->nr_taken = nr_taken;
+		__entry->nr_active = nr_active;
+		__entry->nr_deactivated = nr_deactivated;
+		__entry->nr_referenced = nr_referenced;
+		__entry->priority = priority;
+		__entry->reclaim_flags = trace_shrink_flags(file);
+	),
+
+	TP_printk("nid=%d nr_taken=%ld nr_active=%ld nr_deactivated=%ld nr_referenced=%ld priority=%d flags=%s",
+		__entry->nid,
+		__entry->nr_taken,
+		__entry->nr_active, __entry->nr_deactivated, __entry->nr_referenced,
 		__entry->priority,
 		show_reclaim_flags(__entry->reclaim_flags))
 );
 
+TRACE_EVENT(mm_vmscan_inactive_list_is_low,
+
+	TP_PROTO(int nid, int reclaim_idx,
+		unsigned long total_inactive, unsigned long inactive,
+		unsigned long total_active, unsigned long active,
+		unsigned long ratio, int file),
+
+	TP_ARGS(nid, reclaim_idx, total_inactive, inactive, total_active, active, ratio, file),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(int, reclaim_idx)
+		__field(unsigned long, total_inactive)
+		__field(unsigned long, inactive)
+		__field(unsigned long, total_active)
+		__field(unsigned long, active)
+		__field(unsigned long, ratio)
+		__field(int, reclaim_flags)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->reclaim_idx = reclaim_idx;
+		__entry->total_inactive = total_inactive;
+		__entry->inactive = inactive;
+		__entry->total_active = total_active;
+		__entry->active = active;
+		__entry->ratio = ratio;
+		__entry->reclaim_flags = trace_shrink_flags(file) & RECLAIM_WB_LRU;
+	),
+
+	TP_printk("nid=%d reclaim_idx=%d total_inactive=%ld inactive=%ld total_active=%ld active=%ld ratio=%ld flags=%s",
+		__entry->nid,
+		__entry->reclaim_idx,
+		__entry->total_inactive, __entry->inactive,
+		__entry->total_active, __entry->active,
+		__entry->ratio,
+		show_reclaim_flags(__entry->reclaim_flags))
+);
 #endif /* _TRACE_VMSCAN_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 5c06f4af8323..00f643164ca2 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -283,8 +283,16 @@ TRACE_MAKE_SYSTEM_STR();
 		trace_print_symbols_seq(p, value, symbols);		\
 	})
 
+#undef __print_flags_u64
 #undef __print_symbolic_u64
 #if BITS_PER_LONG == 32
+#define __print_flags_u64(flag, delim, flag_array...)			\
+	({								\
+		static const struct trace_print_flags_u64 __flags[] =	\
+			{ flag_array, { -1, NULL } };			\
+		trace_print_flags_seq_u64(p, delim, flag, __flags);	\
+	})
+
 #define __print_symbolic_u64(value, symbol_array...)			\
 	({								\
 		static const struct trace_print_flags_u64 symbols[] =	\
@@ -292,6 +300,9 @@ TRACE_MAKE_SYSTEM_STR();
 		trace_print_symbols_seq_u64(p, value, symbols);	\
 	})
 #else
+#define __print_flags_u64(flag, delim, flag_array...)			\
+			__print_flags(flag, delim, flag_array)
+
 #define __print_symbolic_u64(value, symbol_array...)			\
 			__print_symbolic(value, symbol_array)
 #endif
diff --git a/include/uapi/asm-generic/ioctl.h b/include/uapi/asm-generic/ioctl.h
index 7e7c11b52143..749b32fe5623 100644
--- a/include/uapi/asm-generic/ioctl.h
+++ b/include/uapi/asm-generic/ioctl.h
@@ -48,6 +48,9 @@
 /*
  * Direction bits, which any architecture can choose to override
  * before including this file.
+ *
+ * NOTE: _IOC_WRITE means userland is writing and kernel is
+ * reading. _IOC_READ means userland is reading and kernel is writing.
  */
 
 #ifndef _IOC_NONE
@@ -72,7 +75,12 @@
 #define _IOC_TYPECHECK(t) (sizeof(t))
 #endif
 
-/* used to create numbers */
+/*
+ * Used to create numbers.
+ *
+ * NOTE: _IOW means userland is writing and kernel is reading. _IOR
+ * means userland is reading and kernel is writing.
+ */
 #define _IO(type,nr)		_IOC(_IOC_NONE,(type),(nr),0)
 #define _IOR(type,nr,size)	_IOC(_IOC_READ,(type),(nr),(_IOC_TYPECHECK(size)))
 #define _IOW(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),(_IOC_TYPECHECK(size)))
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 9057d7af3ae1..9ac4b68c54d1 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -11,13 +11,18 @@
 
 #include <linux/types.h>
 
-#define UFFD_API ((__u64)0xAA)
 /*
- * After implementing the respective features it will become:
- * #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \
- *			      UFFD_FEATURE_EVENT_FORK)
+ * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and
+ * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR.  In
+ * userfaultfd.h we assumed the kernel was reading (instead _IOC_READ
+ * means the userland is reading).
  */
-#define UFFD_API_FEATURES (0)
+#define UFFD_API ((__u64)0xAA)
+#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK |		\
+			   UFFD_FEATURE_EVENT_REMAP |		\
+			   UFFD_FEATURE_EVENT_MADVDONTNEED |	\
+			   UFFD_FEATURE_MISSING_HUGETLBFS |	\
+			   UFFD_FEATURE_MISSING_SHMEM)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -26,6 +31,9 @@
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
 	 (__u64)1 << _UFFDIO_ZEROPAGE)
+#define UFFD_API_RANGE_IOCTLS_BASIC		\
+	((__u64)1 << _UFFDIO_WAKE |		\
+	 (__u64)1 << _UFFDIO_COPY)
 
 /*
  * Valid ioctl command number range with this API is from 0x00 to
@@ -72,6 +80,21 @@ struct uffd_msg {
 		} pagefault;
 
 		struct {
+			__u32	ufd;
+		} fork;
+
+		struct {
+			__u64	from;
+			__u64	to;
+			__u64	len;
+		} remap;
+
+		struct {
+			__u64	start;
+			__u64	end;
+		} madv_dn;
+
+		struct {
 			/* unused reserved fields */
 			__u64	reserved1;
 			__u64	reserved2;
@@ -84,9 +107,9 @@ struct uffd_msg {
  * Start at 0x12 and not at 0 to be more strict against bugs.
  */
 #define UFFD_EVENT_PAGEFAULT	0x12
-#if 0 /* not available yet */
 #define UFFD_EVENT_FORK		0x13
-#endif
+#define UFFD_EVENT_REMAP	0x14
+#define UFFD_EVENT_MADVDONTNEED	0x15
 
 /* flags for UFFD_EVENT_PAGEFAULT */
 #define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
@@ -104,11 +127,37 @@ struct uffdio_api {
 	 * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE
 	 * are to be considered implicitly always enabled in all kernels as
 	 * long as the uffdio_api.api requested matches UFFD_API.
+	 *
+	 * UFFD_FEATURE_MISSING_HUGETLBFS means an UFFDIO_REGISTER
+	 * with UFFDIO_REGISTER_MODE_MISSING mode will succeed on
+	 * hugetlbfs virtual memory ranges. Adding or not adding
+	 * UFFD_FEATURE_MISSING_HUGETLBFS to uffdio_api.features has
+	 * no real functional effect after UFFDIO_API returns, but
+	 * it's only useful for an initial feature set probe at
+	 * UFFDIO_API time. There are two ways to use it:
+	 *
+	 * 1) by adding UFFD_FEATURE_MISSING_HUGETLBFS to the
+	 *    uffdio_api.features before calling UFFDIO_API, an error
+	 *    will be returned by UFFDIO_API on a kernel without
+	 *    hugetlbfs missing support
+	 *
+	 * 2) the UFFD_FEATURE_MISSING_HUGETLBFS can not be added in
+	 *    uffdio_api.features and instead it will be set by the
+	 *    kernel in the uffdio_api.features if the kernel supports
+	 *    it, so userland can later check if the feature flag is
+	 *    present in uffdio_api.features after UFFDIO_API
+	 *    succeeded.
+	 *
+	 * UFFD_FEATURE_MISSING_SHMEM works the same as
+	 * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem
+	 * (i.e. tmpfs and other shmem based APIs).
 	 */
-#if 0 /* not available yet */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
-#endif
+#define UFFD_FEATURE_EVENT_REMAP		(1<<2)
+#define UFFD_FEATURE_EVENT_MADVDONTNEED		(1<<3)
+#define UFFD_FEATURE_MISSING_HUGETLBFS		(1<<4)
+#define UFFD_FEATURE_MISSING_SHMEM		(1<<5)
 	__u64 features;
 
 	__u64 ioctls;