Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "More mm/ work, plenty more to come

  Subsystems affected by this patch series: slub, memcg, gup, kasan,
  pagealloc, hugetlb, vmscan, tools, mempolicy, memblock, hugetlbfs,
  thp, mmap, kconfig"

* akpm: (131 commits)
  arm64: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  x86: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  riscv: support DEBUG_WX
  mm: add DEBUG_WX support
  drivers/base/memory.c: cache memory blocks in xarray to accelerate lookup
  mm/thp: rename pmd_mknotpresent() as pmd_mkinvalid()
  powerpc/mm: drop platform defined pmd_mknotpresent()
  mm: thp: don't need to drain lru cache when splitting and mlocking THP
  hugetlbfs: get unmapped area below TASK_UNMAPPED_BASE for hugetlbfs
  sparc32: register memory occupied by kernel as memblock.memory
  include/linux/memblock.h: fix minor typo and unclear comment
  mm, mempolicy: fix up gup usage in lookup_node
  tools/vm/page_owner_sort.c: filter out unneeded line
  mm: swap: memcg: fix memcg stats for huge pages
  mm: swap: fix vmstats for huge pages
  mm: vmscan: limit the range of LRU type balancing
  mm: vmscan: reclaim writepage is IO cost
  mm: vmscan: determine anon/file pressure balance at the reclaim root
  mm: balance LRU lists based on relative thrashing
  mm: only count actual rotations as LRU reclaim cost
  ...

16 files changed, 209 insertions, 159 deletions

diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 822f433ac95c..40f85decc2ee 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -122,7 +122,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 #ifndef __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
-	return *ptep;
+	return READ_ONCE(*ptep);
 }
 #endif
 
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index a0eabfbeb0e1..6fa0eea3f530 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -97,7 +97,7 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		struct page **page);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern enum compact_result compaction_suitable(struct zone *zone, int order,
-		unsigned int alloc_flags, int classzone_idx);
+		unsigned int alloc_flags, int highest_zoneidx);
 
 extern void defer_compaction(struct zone *zone, int order);
 extern bool compaction_deferred(struct zone *zone, int order);
@@ -182,7 +182,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 
 extern int kcompactd_run(int nid);
 extern void kcompactd_stop(int nid);
-extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx);
+extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx);
 
 #else
 static inline void reset_isolation_suitable(pg_data_t *pgdat)
@@ -190,7 +190,7 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 }
 
 static inline enum compact_result compaction_suitable(struct zone *zone, int order,
-					int alloc_flags, int classzone_idx)
+					int alloc_flags, int highest_zoneidx)
 {
 	return COMPACT_SKIPPED;
 }
@@ -232,7 +232,8 @@ static inline void kcompactd_stop(int nid)
 {
 }
 
-static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
+static inline void wakeup_kcompactd(pg_data_t *pgdat,
+				int order, int highest_zoneidx)
 {
 }
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 4aba4c86c626..67a0774e080b 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -110,6 +110,11 @@ struct vm_area_struct;
  * the caller guarantees the allocation will allow more memory to be freed
  * very shortly e.g. process exiting or swapping. Users either should
  * be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
+ * Users of this flag have to be extremely careful to not deplete the reserve
+ * completely and implement a throttling mechanism which controls the
+ * consumption of the reserve based on the amount of freed memory.
+ * Usage of a pre-allocated pool (e.g. mempool) should be always considered
+ * before using this flag.
  *
  * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
  * This takes precedence over the %__GFP_MEMALLOC flag if both are set.
@@ -307,7 +312,7 @@ struct vm_area_struct;
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
 #define GFP_MOVABLE_SHIFT 3
 
-static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
+static inline int gfp_migratetype(const gfp_t gfp_flags)
 {
 	VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
 	BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 92c21c5ccc58..0cced410e0bd 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -518,8 +518,8 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 int __init __alloc_bootmem_huge_page(struct hstate *h);
 int __init alloc_bootmem_huge_page(struct hstate *h);
 
-void __init hugetlb_bad_size(void);
 void __init hugetlb_add_hstate(unsigned order);
+bool __init arch_hugetlb_valid_size(unsigned long size);
 struct hstate *size_to_hstate(unsigned long size);
 
 #ifndef HUGE_MAX_HSTATE
@@ -590,6 +590,20 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h)
 
 #include <asm/hugetlb.h>
 
+#ifndef is_hugepage_only_range
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					unsigned long addr, unsigned long len)
+{
+	return 0;
+}
+#define is_hugepage_only_range is_hugepage_only_range
+#endif
+
+#ifndef arch_clear_hugepage_flags
+static inline void arch_clear_hugepage_flags(struct page *page) { }
+#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+#endif
+
 #ifndef arch_make_huge_pte
 static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 				       struct page *page, int writable)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 6bc37a731d27..017fae833d4a 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -41,7 +41,7 @@ enum memblock_flags {
 
 /**
  * struct memblock_region - represents a memory region
- * @base: physical address of the region
+ * @base: base address of the region
  * @size: size of the region
  * @flags: memory region attributes
  * @nid: NUMA node id
@@ -50,7 +50,7 @@ struct memblock_region {
 	phys_addr_t base;
 	phys_addr_t size;
 	enum memblock_flags flags;
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	int nid;
 #endif
 };
@@ -75,7 +75,7 @@ struct memblock_type {
  * struct memblock - memblock allocator metadata
  * @bottom_up: is bottom up direction?
  * @current_limit: physical address of the current allocation limit
- * @memory: usabe memory regions
+ * @memory: usable memory regions
  * @reserved: reserved memory regions
  * @physmem: all physical memory
  */
@@ -215,7 +215,6 @@ static inline bool memblock_is_nomap(struct memblock_region *m)
 	return m->flags & MEMBLOCK_NOMAP;
 }
 
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 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,
@@ -234,7 +233,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 #define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid)		\
 	for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
 	     i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
@@ -275,6 +273,9 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
 #define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \
 	for (; i != U64_MAX;					  \
 	     __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
+
+int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
+
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 /**
@@ -310,10 +311,10 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
 	for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved,	\
 			       nid, flags, p_start, p_end, p_nid)
 
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 int memblock_set_node(phys_addr_t base, phys_addr_t size,
 		      struct memblock_type *type, int nid);
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 static inline void memblock_set_region_node(struct memblock_region *r, int nid)
 {
 	r->nid = nid;
@@ -332,7 +333,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r)
 {
 	return 0;
 }
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
 
 /* Flags for memblock allocation APIs */
 #define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index bfe9533bb67e..e77197a62809 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -29,10 +29,7 @@ struct kmem_cache;
 
 /* Cgroup-specific page state, on top of universal node page state */
 enum memcg_stat_item {
-	MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS,
-	MEMCG_RSS,
-	MEMCG_RSS_HUGE,
-	MEMCG_SWAP,
+	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
 	/* XXX: why are these zone and not node counters? */
 	MEMCG_KERNEL_STACK_KB,
@@ -358,16 +355,8 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
 enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 						struct mem_cgroup *memcg);
 
-int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
-			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
-			  bool compound);
-int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
-			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
-			  bool compound);
-void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
-			      bool lrucare, bool compound);
-void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
-		bool compound);
+int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
+
 void mem_cgroup_uncharge(struct page *page);
 void mem_cgroup_uncharge_list(struct list_head *page_list);
 
@@ -568,7 +557,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
 void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
 
 #ifdef CONFIG_MEMCG_SWAP
-extern int do_swap_account;
+extern bool cgroup_memory_noswap;
 #endif
 
 struct mem_cgroup *lock_page_memcg(struct page *page);
@@ -708,16 +697,17 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
+	struct page *head = compound_head(page); /* rmap on tail pages */
 	pg_data_t *pgdat = page_pgdat(page);
 	struct lruvec *lruvec;
 
 	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!page->mem_cgroup) {
+	if (!head->mem_cgroup) {
 		__mod_node_page_state(pgdat, idx, val);
 		return;
 	}
 
-	lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat);
+	lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat);
 	__mod_lruvec_state(lruvec, idx, val);
 }
 
@@ -847,37 +837,12 @@ static inline enum mem_cgroup_protection mem_cgroup_protected(
 	return MEMCG_PROT_NONE;
 }
 
-static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
-					gfp_t gfp_mask,
-					struct mem_cgroup **memcgp,
-					bool compound)
-{
-	*memcgp = NULL;
-	return 0;
-}
-
-static inline int mem_cgroup_try_charge_delay(struct page *page,
-					      struct mm_struct *mm,
-					      gfp_t gfp_mask,
-					      struct mem_cgroup **memcgp,
-					      bool compound)
+static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+				    gfp_t gfp_mask)
 {
-	*memcgp = NULL;
 	return 0;
 }
 
-static inline void mem_cgroup_commit_charge(struct page *page,
-					    struct mem_cgroup *memcg,
-					    bool lrucare, bool compound)
-{
-}
-
-static inline void mem_cgroup_cancel_charge(struct page *page,
-					    struct mem_cgroup *memcg,
-					    bool compound)
-{
-}
-
 static inline void mem_cgroup_uncharge(struct page *page)
 {
 }
@@ -1277,6 +1242,19 @@ static inline void dec_lruvec_page_state(struct page *page,
 	mod_lruvec_page_state(page, idx, -1);
 }
 
+static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = lruvec_memcg(lruvec);
+	if (!memcg)
+		return NULL;
+	memcg = parent_mem_cgroup(memcg);
+	if (!memcg)
+		return NULL;
+	return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec));
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 59adb47efc55..66e0977f970a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -501,7 +501,6 @@ struct vm_fault {
 	pte_t orig_pte;			/* Value of PTE at the time of fault */
 
 	struct page *cow_page;		/* Page handler may use for COW fault */
-	struct mem_cgroup *memcg;	/* Cgroup cow_page belongs to */
 	struct page *page;		/* ->fault handlers should return a
 					 * page here, unless VM_FAULT_NOPAGE
 					 * is set (which is also implied by
@@ -867,7 +866,7 @@ enum compound_dtor_id {
 #endif
 	NR_COMPOUND_DTORS,
 };
-extern compound_page_dtor * const compound_page_dtors[];
+extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS];
 
 static inline void set_compound_page_dtor(struct page *page,
 		enum compound_dtor_id compound_dtor)
@@ -876,10 +875,10 @@ static inline void set_compound_page_dtor(struct page *page,
 	page[1].compound_dtor = compound_dtor;
 }
 
-static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
+static inline void destroy_compound_page(struct page *page)
 {
 	VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page);
-	return compound_page_dtors[page[1].compound_dtor];
+	compound_page_dtors[page[1].compound_dtor](page);
 }
 
 static inline unsigned int compound_order(struct page *page)
@@ -946,8 +945,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 	return pte;
 }
 
-vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
-		struct page *page);
+vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page);
 vm_fault_t finish_fault(struct vm_fault *vmf);
 vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 #endif
@@ -1827,6 +1825,8 @@ extern int mprotect_fixup(struct vm_area_struct *vma,
  */
 int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			  struct page **pages);
+int pin_user_pages_fast_only(unsigned long start, int nr_pages,
+			     unsigned int gup_flags, struct page **pages);
 /*
  * per-process(per-mm_struct) statistics.
  */
@@ -2327,9 +2327,7 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
 }
 
 extern void __init pagecache_init(void);
-extern void free_area_init(unsigned long * zones_size);
-extern void __init free_area_init_node(int nid, unsigned long * zones_size,
-		unsigned long zone_start_pfn, unsigned long *zholes_size);
+extern void __init free_area_init_memoryless_node(int nid);
 extern void free_initmem(void);
 
 /*
@@ -2399,34 +2397,26 @@ static inline unsigned long get_num_physpages(void)
 	return phys_pages;
 }
 
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 /*
- * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its
- * zones, allocate the backing mem_map and account for memory holes in a more
- * architecture independent manner. This is a substitute for creating the
- * zone_sizes[] and zholes_size[] arrays and passing them to
- * free_area_init_node()
+ * Using memblock node mappings, an architecture may initialise its
+ * zones, allocate the backing mem_map and account for memory holes in an
+ * architecture independent manner.
  *
  * An architecture is expected to register range of page frames backed by
  * physical memory with memblock_add[_node]() before calling
- * free_area_init_nodes() passing in the PFN each zone ends at. At a basic
+ * free_area_init() passing in the PFN each zone ends at. At a basic
  * usage, an architecture is expected to do something like
  *
  * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
  * 							 max_highmem_pfn};
  * for_each_valid_physical_page_range()
  * 	memblock_add_node(base, size, nid)
- * free_area_init_nodes(max_zone_pfns);
+ * free_area_init(max_zone_pfns);
  *
- * free_bootmem_with_active_regions() calls free_bootmem_node() for each
- * registered physical page range.  Similarly
  * sparse_memory_present_with_active_regions() calls memory_present() for
  * each range when SPARSEMEM is enabled.
- *
- * See mm/page_alloc.c for more information on each function exposed by
- * CONFIG_HAVE_MEMBLOCK_NODE_MAP.
  */
-extern void free_area_init_nodes(unsigned long *max_zone_pfn);
+void free_area_init(unsigned long *max_zone_pfn);
 unsigned long node_map_pfn_alignment(void);
 unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
 						unsigned long end_pfn);
@@ -2435,16 +2425,10 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn,
 extern void get_pfn_range_for_nid(unsigned int nid,
 			unsigned long *start_pfn, unsigned long *end_pfn);
 extern unsigned long find_min_pfn_with_active_regions(void);
-extern void free_bootmem_with_active_regions(int nid,
-						unsigned long max_low_pfn);
 extern void sparse_memory_present_with_active_regions(int nid);
 
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
-#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \
-    !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
-static inline int __early_pfn_to_nid(unsigned long pfn,
-					struct mminit_pfnnid_cache *state)
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+static inline int early_pfn_to_nid(unsigned long pfn)
 {
 	return 0;
 }
@@ -2480,6 +2464,7 @@ extern void setup_per_cpu_pageset(void);
 extern int min_free_kbytes;
 extern int watermark_boost_factor;
 extern int watermark_scale_factor;
+extern bool arch_has_descending_max_zone_pfns(void);
 
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;
@@ -2816,6 +2801,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
 #define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
+#define FOLL_FAST_ONLY	0x80000	/* gup_fast: prevent fall-back to slow gup */
 
 /*
  * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f5b6ccf41141..df1f08486d81 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -242,19 +242,6 @@ static inline bool is_active_lru(enum lru_list lru)
 	return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
 }
 
-struct zone_reclaim_stat {
-	/*
-	 * The pageout code in vmscan.c keeps track of how many of the
-	 * mem/swap backed and file backed pages are referenced.
-	 * The higher the rotated/scanned ratio, the more valuable
-	 * that cache is.
-	 *
-	 * The anon LRU stats live in [0], file LRU stats in [1]
-	 */
-	unsigned long		recent_rotated[2];
-	unsigned long		recent_scanned[2];
-};
-
 enum lruvec_flags {
 	LRUVEC_CONGESTED,		/* lruvec has many dirty pages
 					 * backed by a congested BDI
@@ -263,7 +250,13 @@ enum lruvec_flags {
 
 struct lruvec {
 	struct list_head		lists[NR_LRU_LISTS];
-	struct zone_reclaim_stat	reclaim_stat;
+	/*
+	 * These track the cost of reclaiming one LRU - file or anon -
+	 * over the other. As the observed cost of reclaiming one LRU
+	 * increases, the reclaim scan balance tips toward the other.
+	 */
+	unsigned long			anon_cost;
+	unsigned long			file_cost;
 	/* Evictions & activations on the inactive file list */
 	atomic_long_t			inactive_age;
 	/* Refaults at the time of last reclaim cycle */
@@ -680,6 +673,8 @@ typedef struct pglist_data {
 	/*
 	 * Must be held any time you expect node_start_pfn,
 	 * node_present_pages, node_spanned_pages or nr_zones to stay constant.
+	 * Also synchronizes pgdat->first_deferred_pfn during deferred page
+	 * init.
 	 *
 	 * pgdat_resize_lock() and pgdat_resize_unlock() are provided to
 	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
@@ -699,13 +694,13 @@ typedef struct pglist_data {
 	struct task_struct *kswapd;	/* Protected by
 					   mem_hotplug_begin/end() */
 	int kswapd_order;
-	enum zone_type kswapd_classzone_idx;
+	enum zone_type kswapd_highest_zoneidx;
 
 	int kswapd_failures;		/* Number of 'reclaimed == 0' runs */
 
 #ifdef CONFIG_COMPACTION
 	int kcompactd_max_order;
-	enum zone_type kcompactd_classzone_idx;
+	enum zone_type kcompactd_highest_zoneidx;
 	wait_queue_head_t kcompactd_wait;
 	struct task_struct *kcompactd;
 #endif
@@ -783,15 +778,15 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat)
 
 void build_all_zonelists(pg_data_t *pgdat);
 void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order,
-		   enum zone_type classzone_idx);
+		   enum zone_type highest_zoneidx);
 bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
-			 int classzone_idx, unsigned int alloc_flags,
+			 int highest_zoneidx, unsigned int alloc_flags,
 			 long free_pages);
 bool zone_watermark_ok(struct zone *z, unsigned int order,
-		unsigned long mark, int classzone_idx,
+		unsigned long mark, int highest_zoneidx,
 		unsigned int alloc_flags);
 bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-		unsigned long mark, int classzone_idx);
+		unsigned long mark, int highest_zoneidx);
 enum memmap_context {
 	MEMMAP_EARLY,
 	MEMMAP_HOTPLUG,
@@ -876,7 +871,7 @@ extern int movable_zone;
 #ifdef CONFIG_HIGHMEM
 static inline int zone_movable_is_highmem(void)
 {
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	return movable_zone == ZONE_HIGHMEM;
 #else
 	return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM;
@@ -1079,15 +1074,6 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 #include <asm/sparsemem.h>
 #endif
 
-#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
-	!defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
-static inline unsigned long early_pfn_to_nid(unsigned long pfn)
-{
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA));
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_FLATMEM
 #define pfn_to_nid(pfn)		(0)
 #endif
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 693cae9bfe66..7302efff5e65 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -4,6 +4,9 @@
  *
  * Copyright (C) 2008, 2009 secunet Security Networks AG
  * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * Copyright (c) 2020 Oracle and/or its affiliates.
+ * Author: Daniel Jordan <daniel.m.jordan@oracle.com>
  */
 
 #ifndef PADATA_H
@@ -24,7 +27,6 @@
  * @list: List entry, to attach to the padata lists.
  * @pd: Pointer to the internal control structure.
  * @cb_cpu: Callback cpu for serializatioon.
- * @cpu: Cpu for parallelization.
  * @seq_nr: Sequence number of the parallelized data object.
  * @info: Used to pass information from the parallel to the serial function.
  * @parallel: Parallel execution function.
@@ -34,7 +36,6 @@ struct padata_priv {
 	struct list_head	list;
 	struct parallel_data	*pd;
 	int			cb_cpu;
-	int			cpu;
 	unsigned int		seq_nr;
 	int			info;
 	void                    (*parallel)(struct padata_priv *padata);
@@ -68,15 +69,11 @@ struct padata_serial_queue {
 /**
  * struct padata_parallel_queue - The percpu padata parallel queue
  *
- * @parallel: List to wait for parallelization.
  * @reorder: List to wait for reordering after parallel processing.
- * @work: work struct for parallelization.
  * @num_obj: Number of objects that are processed by this cpu.
  */
 struct padata_parallel_queue {
-       struct padata_list    parallel;
        struct padata_list    reorder;
-       struct work_struct    work;
        atomic_t              num_obj;
 };
 
@@ -111,7 +108,7 @@ struct parallel_data {
 	struct padata_parallel_queue	__percpu *pqueue;
 	struct padata_serial_queue	__percpu *squeue;
 	atomic_t			refcnt;
-	atomic_t			seq_nr;
+	unsigned int			seq_nr;
 	unsigned int			processed;
 	int				cpu;
 	struct padata_cpumask		cpumask;
@@ -137,6 +134,31 @@ struct padata_shell {
 };
 
 /**
+ * struct padata_mt_job - represents one multithreaded job
+ *
+ * @thread_fn: Called for each chunk of work that a padata thread does.
+ * @fn_arg: The thread function argument.
+ * @start: The start of the job (units are job-specific).
+ * @size: size of this node's work (units are job-specific).
+ * @align: Ranges passed to the thread function fall on this boundary, with the
+ *         possible exceptions of the beginning and end of the job.
+ * @min_chunk: The minimum chunk size in job-specific units.  This allows
+ *             the client to communicate the minimum amount of work that's
+ *             appropriate for one worker thread to do at once.
+ * @max_threads: Max threads to use for the job, actual number may be less
+ *               depending on task size and minimum chunk size.
+ */
+struct padata_mt_job {
+	void (*thread_fn)(unsigned long start, unsigned long end, void *arg);
+	void			*fn_arg;
+	unsigned long		start;
+	unsigned long		size;
+	unsigned long		align;
+	unsigned long		min_chunk;
+	int			max_threads;
+};
+
+/**
  * struct padata_instance - The overall control structure.
  *
  * @cpu_online_node: Linkage for CPU online callback.
@@ -166,6 +188,12 @@ struct padata_instance {
 #define	PADATA_INVALID	4
 };
 
+#ifdef CONFIG_PADATA
+extern void __init padata_init(void);
+#else
+static inline void __init padata_init(void) {}
+#endif
+
 extern struct padata_instance *padata_alloc_possible(const char *name);
 extern void padata_free(struct padata_instance *pinst);
 extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst);
@@ -173,6 +201,7 @@ extern void padata_free_shell(struct padata_shell *ps);
 extern int padata_do_parallel(struct padata_shell *ps,
 			      struct padata_priv *padata, int *cb_cpu);
 extern void padata_do_serial(struct padata_priv *padata);
+extern void __init padata_do_multithreaded(struct padata_mt_job *job);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 			      cpumask_var_t cpumask);
 extern int padata_start(struct padata_instance *pinst);
diff --git a/include/linux/string.h b/include/linux/string.h
index 6dfbb2efa815..9b7a0632e87a 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -272,6 +272,31 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob
 void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter");
 
 #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
+
+#ifdef CONFIG_KASAN
+extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
+extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
+extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat);
+extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy);
+extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
+extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
+extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
+#else
+#define __underlying_memchr	__builtin_memchr
+#define __underlying_memcmp	__builtin_memcmp
+#define __underlying_memcpy	__builtin_memcpy
+#define __underlying_memmove	__builtin_memmove
+#define __underlying_memset	__builtin_memset
+#define __underlying_strcat	__builtin_strcat
+#define __underlying_strcpy	__builtin_strcpy
+#define __underlying_strlen	__builtin_strlen
+#define __underlying_strncat	__builtin_strncat
+#define __underlying_strncpy	__builtin_strncpy
+#endif
+
 __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 {
 	size_t p_size = __builtin_object_size(p, 0);
@@ -279,14 +304,14 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size)
 		__write_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_strncpy(p, q, size);
+	return __underlying_strncpy(p, q, size);
 }
 
 __FORTIFY_INLINE char *strcat(char *p, const char *q)
 {
 	size_t p_size = __builtin_object_size(p, 0);
 	if (p_size == (size_t)-1)
-		return __builtin_strcat(p, q);
+		return __underlying_strcat(p, q);
 	if (strlcat(p, q, p_size) >= p_size)
 		fortify_panic(__func__);
 	return p;
@@ -300,7 +325,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p)
 	/* Work around gcc excess stack consumption issue */
 	if (p_size == (size_t)-1 ||
 	    (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0'))
-		return __builtin_strlen(p);
+		return __underlying_strlen(p);
 	ret = strnlen(p, p_size);
 	if (p_size <= ret)
 		fortify_panic(__func__);
@@ -333,7 +358,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size)
 			__write_overflow();
 		if (len >= p_size)
 			fortify_panic(__func__);
-		__builtin_memcpy(p, q, len);
+		__underlying_memcpy(p, q, len);
 		p[len] = '\0';
 	}
 	return ret;
@@ -346,12 +371,12 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count)
 	size_t p_size = __builtin_object_size(p, 0);
 	size_t q_size = __builtin_object_size(q, 0);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
-		return __builtin_strncat(p, q, count);
+		return __underlying_strncat(p, q, count);
 	p_len = strlen(p);
 	copy_len = strnlen(q, count);
 	if (p_size < p_len + copy_len + 1)
 		fortify_panic(__func__);
-	__builtin_memcpy(p + p_len, q, copy_len);
+	__underlying_memcpy(p + p_len, q, copy_len);
 	p[p_len + copy_len] = '\0';
 	return p;
 }
@@ -363,7 +388,7 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size)
 		__write_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_memset(p, c, size);
+	return __underlying_memset(p, c, size);
 }
 
 __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
@@ -378,7 +403,7 @@ __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memcpy(p, q, size);
+	return __underlying_memcpy(p, q, size);
 }
 
 __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
@@ -393,7 +418,7 @@ __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memmove(p, q, size);
+	return __underlying_memmove(p, q, size);
 }
 
 extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
@@ -419,7 +444,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size)
 	}
 	if (p_size < size || q_size < size)
 		fortify_panic(__func__);
-	return __builtin_memcmp(p, q, size);
+	return __underlying_memcmp(p, q, size);
 }
 
 __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
@@ -429,7 +454,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size)
 		__read_overflow();
 	if (p_size < size)
 		fortify_panic(__func__);
-	return __builtin_memchr(p, c, size);
+	return __underlying_memchr(p, c, size);
 }
 
 void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
@@ -460,11 +485,22 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q)
 	size_t p_size = __builtin_object_size(p, 0);
 	size_t q_size = __builtin_object_size(q, 0);
 	if (p_size == (size_t)-1 && q_size == (size_t)-1)
-		return __builtin_strcpy(p, q);
+		return __underlying_strcpy(p, q);
 	memcpy(p, q, strlen(q) + 1);
 	return p;
 }
 
+/* Don't use these outside the FORITFY_SOURCE implementation */
+#undef __underlying_memchr
+#undef __underlying_memcmp
+#undef __underlying_memcpy
+#undef __underlying_memmove
+#undef __underlying_memset
+#undef __underlying_strcat
+#undef __underlying_strcpy
+#undef __underlying_strlen
+#undef __underlying_strncat
+#undef __underlying_strncpy
 #endif
 
 /**
diff --git a/include/linux/swap.h b/include/linux/swap.h
index e92176fc8824..4c5974bb9ba9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -334,9 +334,10 @@ extern unsigned long nr_free_pagecache_pages(void);
 
 
 /* linux/mm/swap.c */
+extern void lru_note_cost(struct lruvec *lruvec, bool file,
+			  unsigned int nr_pages);
+extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
-extern void lru_cache_add_anon(struct page *page);
-extern void lru_cache_add_file(struct page *page);
 extern void lru_add_page_tail(struct page *page, struct page *page_tail,
 			 struct lruvec *lruvec, struct list_head *head);
 extern void activate_page(struct page *);
@@ -651,11 +652,9 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 #endif
 
 #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
-extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
-					 gfp_t gfp_mask);
+extern void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask);
 #else
-static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg,
-						int node, gfp_t gfp_mask)
+static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask)
 {
 }
 #endif
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index ffef0f279747..24fc7c3ae7d6 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -35,6 +35,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGSCAN_KSWAPD,
 		PGSCAN_DIRECT,
 		PGSCAN_DIRECT_THROTTLE,
+		PGSCAN_ANON,
+		PGSCAN_FILE,
+		PGSTEAL_ANON,
+		PGSTEAL_FILE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index cb507151710f..aa961088c551 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -26,9 +26,11 @@ struct reclaim_stat {
 	unsigned nr_congested;
 	unsigned nr_writeback;
 	unsigned nr_immediate;
+	unsigned nr_pageout;
 	unsigned nr_activate[2];
 	unsigned nr_ref_keep;
 	unsigned nr_unmap_fail;
+	unsigned nr_lazyfree_fail;
 };
 
 enum writeback_stat_item {
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index e5bf6ee4e814..54e5bf081171 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -314,40 +314,44 @@ TRACE_EVENT(mm_compaction_kcompactd_sleep,
 
 DECLARE_EVENT_CLASS(kcompactd_wake_template,
 
-	TP_PROTO(int nid, int order, enum zone_type classzone_idx),
+	TP_PROTO(int nid, int order, enum zone_type highest_zoneidx),
 
-	TP_ARGS(nid, order, classzone_idx),
+	TP_ARGS(nid, order, highest_zoneidx),
 
 	TP_STRUCT__entry(
 		__field(int, nid)
 		__field(int, order)
-		__field(enum zone_type, classzone_idx)
+		__field(enum zone_type, highest_zoneidx)
 	),
 
 	TP_fast_assign(
 		__entry->nid = nid;
 		__entry->order = order;
-		__entry->classzone_idx = classzone_idx;
+		__entry->highest_zoneidx = highest_zoneidx;
 	),
 
+	/*
+	 * classzone_idx is previous name of the highest_zoneidx.
+	 * Reason not to change it is the ABI requirement of the tracepoint.
+	 */
 	TP_printk("nid=%d order=%d classzone_idx=%-8s",
 		__entry->nid,
 		__entry->order,
-		__print_symbolic(__entry->classzone_idx, ZONE_TYPE))
+		__print_symbolic(__entry->highest_zoneidx, ZONE_TYPE))
 );
 
 DEFINE_EVENT(kcompactd_wake_template, mm_compaction_wakeup_kcompactd,
 
-	TP_PROTO(int nid, int order, enum zone_type classzone_idx),
+	TP_PROTO(int nid, int order, enum zone_type highest_zoneidx),
 
-	TP_ARGS(nid, order, classzone_idx)
+	TP_ARGS(nid, order, highest_zoneidx)
 );
 
 DEFINE_EVENT(kcompactd_wake_template, mm_compaction_kcompactd_wake,
 
-	TP_PROTO(int nid, int order, enum zone_type classzone_idx),
+	TP_PROTO(int nid, int order, enum zone_type highest_zoneidx),
 
-	TP_ARGS(nid, order, classzone_idx)
+	TP_ARGS(nid, order, highest_zoneidx)
 );
 #endif
 
diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 70e32ff096ec..4fdb14a81108 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -12,6 +12,8 @@
 	EM( SCAN_SUCCEED,		"succeeded")			\
 	EM( SCAN_PMD_NULL,		"pmd_null")			\
 	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
+	EM( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")		\
+	EM( SCAN_EXCEED_SHARED_PTE,	"exceed_shared_pte")		\
 	EM( SCAN_PTE_NON_PRESENT,	"pte_non_present")		\
 	EM( SCAN_PTE_UFFD_WP,		"pte_uffd_wp")			\
 	EM( SCAN_PAGE_RO,		"no_writable_page")		\
@@ -31,7 +33,6 @@
 	EM( SCAN_DEL_PAGE_LRU,		"could_not_delete_page_from_lru")\
 	EM( SCAN_ALLOC_HUGE_PAGE_FAIL,	"alloc_huge_page_failed")	\
 	EM( SCAN_CGROUP_CHARGE_FAIL,	"ccgroup_charge_failed")	\
-	EM( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")		\
 	EM( SCAN_TRUNCATED,		"truncated")			\
 	EMe(SCAN_PAGE_HAS_PRIVATE,	"page_has_private")		\
 
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 74bb594ccb25..2070df64958e 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -265,7 +265,7 @@ TRACE_EVENT(mm_shrink_slab_end,
 );
 
 TRACE_EVENT(mm_vmscan_lru_isolate,
-	TP_PROTO(int classzone_idx,
+	TP_PROTO(int highest_zoneidx,
 		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
@@ -274,10 +274,10 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		isolate_mode_t isolate_mode,
 		int lru),
 
-	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru),
+	TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru),
 
 	TP_STRUCT__entry(
-		__field(int, classzone_idx)
+		__field(int, highest_zoneidx)
 		__field(int, order)
 		__field(unsigned long, nr_requested)
 		__field(unsigned long, nr_scanned)
@@ -288,7 +288,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 	),
 
 	TP_fast_assign(
-		__entry->classzone_idx = classzone_idx;
+		__entry->highest_zoneidx = highest_zoneidx;
 		__entry->order = order;
 		__entry->nr_requested = nr_requested;
 		__entry->nr_scanned = nr_scanned;
@@ -298,9 +298,13 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		__entry->lru = lru;
 	),
 
+	/*
+	 * classzone is previous name of the highest_zoneidx.
+	 * Reason not to change it is the ABI requirement of the tracepoint.
+	 */
 	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->highest_zoneidx,
 		__entry->order,
 		__entry->nr_requested,
 		__entry->nr_scanned,