Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "A few small subsystems and some of MM.

  172 patches.

  Subsystems affected by this patch series: hexagon, scripts, ntfs,
  ocfs2, vfs, and mm (slab-generic, slab, slub, debug, pagecache, swap,
  memcg, pagemap, mprotect, mremap, page-reporting, vmalloc, kasan,
  pagealloc, memory-failure, hugetlb, vmscan, z3fold, compaction,
  mempolicy, oom-kill, hugetlbfs, and migration)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (172 commits)
  mm/migrate: remove unneeded semicolons
  hugetlbfs: remove unneeded return value of hugetlb_vmtruncate()
  hugetlbfs: fix some comment typos
  hugetlbfs: correct some obsolete comments about inode i_mutex
  hugetlbfs: make hugepage size conversion more readable
  hugetlbfs: remove meaningless variable avoid_reserve
  hugetlbfs: correct obsolete function name in hugetlbfs_read_iter()
  hugetlbfs: use helper macro default_hstate in init_hugetlbfs_fs
  hugetlbfs: remove useless BUG_ON(!inode) in hugetlbfs_setattr()
  hugetlbfs: remove special hugetlbfs_set_page_dirty()
  mm/hugetlb: change hugetlb_reserve_pages() to type bool
  mm, oom: fix a comment in dump_task()
  mm/mempolicy: use helper range_in_vma() in queue_pages_test_walk()
  numa balancing: migrate on fault among multiple bound nodes
  mm, compaction: make fast_isolate_freepages() stay within zone
  mm/compaction: fix misbehaviors of fast_find_migrateblock()
  mm/compaction: correct deferral logic for proactive compaction
  mm/compaction: remove duplicated VM_BUG_ON_PAGE !PageLocked
  mm/compaction: remove rcu_read_lock during page compaction
  z3fold: simplify the zhdr initialization code in init_z3fold_page()
  ...

117 files changed, 2027 insertions, 1734 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index c513eafaddea..9acc57f68f31 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1299,6 +1299,10 @@ PAGE_SIZE multiple when read back.
 		Amount of cached filesystem data that was modified and
 		is currently being written back to disk
 
+	  swapcached
+		Amount of swap cached in memory. The swapcache is accounted
+		against both memory and swap usage.
+
 	  anon_thp
 		Amount of memory used in anonymous mappings backed by
 		transparent hugepages
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 186ad235bf32..bab6a8b01202 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4904,14 +4904,6 @@
 			last alloc / free. For more information see
 			Documentation/vm/slub.rst.
 
-	slub_memcg_sysfs=	[MM, SLUB]
-			Determines whether to enable sysfs directories for
-			memory cgroup sub-caches. 1 to enable, 0 to disable.
-			The default is determined by CONFIG_SLUB_MEMCG_SYSFS_ON.
-			Enabling this can lead to a very high number of	debug
-			directories and files being created under
-			/sys/kernel/slub.
-
 	slub_max_order= [MM, SLUB]
 			Determines the maximum allowed order for slabs.
 			A high setting may cause OOMs due to memory
diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index e35a3f2fb006..586cd4b86428 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -983,11 +983,11 @@ that benefit from having their data cached, zone_reclaim_mode should be
 left disabled as the caching effect is likely to be more important than
 data locality.
 
-zone_reclaim may be enabled if it's known that the workload is partitioned
-such that each partition fits within a NUMA node and that accessing remote
-memory would cause a measurable performance reduction.  The page allocator
-will then reclaim easily reusable pages (those page cache pages that are
-currently not used) before allocating off node pages.
+Consider enabling one or more zone_reclaim mode bits if it's known that the
+workload is partitioned such that each partition fits within a NUMA node
+and that accessing remote memory would cause a measurable performance
+reduction.  The page allocator will take additional actions before
+allocating off node pages.
 
 Allowing zone reclaim to write out pages stops processes that are
 writing large amounts of data from dirtying pages on other nodes. Zone
diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index 2adffb3f7914..201b5423303b 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -19,11 +19,8 @@ User Space Memory Access
 Memory Allocation Controls
 ==========================
 
-Functions which need to allocate memory often use GFP flags to express
-how that memory should be allocated. The GFP acronym stands for "get
-free pages", the underlying memory allocation function. Not every GFP
-flag is allowed to every function which may allocate memory. Most
-users will want to use a plain ``GFP_KERNEL``.
+.. kernel-doc:: include/linux/gfp.h
+   :internal:
 
 .. kernel-doc:: include/linux/gfp.h
    :doc: Page mobility and placement hints
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index a248ac3941be..cde14aeefca7 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -147,15 +147,14 @@ negative values to distinguish between different kinds of inaccessible memory
 like redzones or freed memory (see mm/kasan/kasan.h).
 
 In the report above the arrows point to the shadow byte 03, which means that
-the accessed address is partially accessible.
-
-For tag-based KASAN this last report section shows the memory tags around the
-accessed address (see `Implementation details`_ section).
+the accessed address is partially accessible. For tag-based KASAN modes this
+last report section shows the memory tags around the accessed address
+(see the `Implementation details`_ section).
 
 Boot parameters
 ~~~~~~~~~~~~~~~
 
-Hardware tag-based KASAN mode (see the section about different mode below) is
+Hardware tag-based KASAN mode (see the section about various modes below) is
 intended for use in production as a security mitigation. Therefore it supports
 boot parameters that allow to disable KASAN competely or otherwise control
 particular KASAN features.
@@ -289,6 +288,13 @@ reserved to tag freed memory regions.
 Hardware tag-based KASAN currently only supports tagging of
 kmem_cache_alloc/kmalloc and page_alloc memory.
 
+If the hardware doesn't support MTE (pre ARMv8.5), hardware tag-based KASAN
+won't be enabled. In this case all boot parameters are ignored.
+
+Note, that enabling CONFIG_KASAN_HW_TAGS always results in in-kernel TBI being
+enabled. Even when kasan.mode=off is provided, or when the hardware doesn't
+support MTE (but supports TBI).
+
 What memory accesses are sanitised by KASAN?
 --------------------------------------------
 
@@ -352,17 +358,17 @@ unmapped. This will require changes in arch-specific code.
 This allows ``VMAP_STACK`` support on x86, and can simplify support of
 architectures that do not have a fixed module region.
 
-CONFIG_KASAN_KUNIT_TEST & CONFIG_TEST_KASAN_MODULE
---------------------------------------------------
+CONFIG_KASAN_KUNIT_TEST and CONFIG_KASAN_MODULE_TEST
+----------------------------------------------------
 
-KASAN tests consist on two parts:
+KASAN tests consist of two parts:
 
 1. Tests that are integrated with the KUnit Test Framework. Enabled with
 ``CONFIG_KASAN_KUNIT_TEST``. These tests can be run and partially verified
 automatically in a few different ways, see the instructions below.
 
 2. Tests that are currently incompatible with KUnit. Enabled with
-``CONFIG_TEST_KASAN_MODULE`` and can only be run as a module. These tests can
+``CONFIG_KASAN_MODULE_TEST`` and can only be run as a module. These tests can
 only be verified manually, by loading the kernel module and inspecting the
 kernel log for KASAN reports.
 
diff --git a/Documentation/vm/arch_pgtable_helpers.rst b/Documentation/vm/arch_pgtable_helpers.rst
index f3591ee3aaa8..552567d863b8 100644
--- a/Documentation/vm/arch_pgtable_helpers.rst
+++ b/Documentation/vm/arch_pgtable_helpers.rst
@@ -50,7 +50,7 @@ PTE Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pte_mkwrite               | Creates a writable PTE                           |
 +---------------------------+--------------------------------------------------+
-| pte_mkwrprotect           | Creates a write protected PTE                    |
+| pte_wrprotect             | Creates a write protected PTE                    |
 +---------------------------+--------------------------------------------------+
 | pte_mkspecial             | Creates a special PTE                            |
 +---------------------------+--------------------------------------------------+
@@ -120,7 +120,7 @@ PMD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pmd_mkwrite               | Creates a writable PMD                           |
 +---------------------------+--------------------------------------------------+
-| pmd_mkwrprotect           | Creates a write protected PMD                    |
+| pmd_wrprotect             | Creates a write protected PMD                    |
 +---------------------------+--------------------------------------------------+
 | pmd_mkspecial             | Creates a special PMD                            |
 +---------------------------+--------------------------------------------------+
@@ -186,7 +186,7 @@ PUD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pud_mkwrite               | Creates a writable PUD                           |
 +---------------------------+--------------------------------------------------+
-| pud_mkwrprotect           | Creates a write protected PUD                    |
+| pud_wrprotect             | Creates a write protected PUD                    |
 +---------------------------+--------------------------------------------------+
 | pud_mkdevmap              | Creates a ZONE_DEVICE mapped PUD                 |
 +---------------------------+--------------------------------------------------+
@@ -224,7 +224,7 @@ HugeTLB Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | huge_pte_mkwrite          | Creates a writable HugeTLB                       |
 +---------------------------+--------------------------------------------------+
-| huge_pte_mkwrprotect      | Creates a write protected HugeTLB                |
+| huge_pte_wrprotect        | Creates a write protected HugeTLB                |
 +---------------------------+--------------------------------------------------+
 | huge_ptep_get_and_clear   | Clears a HugeTLB                                 |
 +---------------------------+--------------------------------------------------+
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index bc09af26c1b8..c759faf7a1ff 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -244,6 +244,7 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 
 #ifdef CONFIG_KASAN_HW_TAGS
 #define arch_enable_tagging()			mte_enable_kernel()
+#define arch_set_tagging_report_once(state)	mte_set_report_once(state)
 #define arch_init_tags(max_tag)			mte_init_tags(max_tag)
 #define arch_get_random_tag()			mte_get_random_tag()
 #define arch_get_mem_tag(addr)			mte_get_mem_tag(addr)
diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
index 26349a4b5e2e..3748d5bb88c0 100644
--- a/arch/arm64/include/asm/mte-kasan.h
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -32,6 +32,9 @@ void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag);
 void mte_enable_kernel(void);
 void mte_init_tags(u64 max_tag);
 
+void mte_set_report_once(bool state);
+bool mte_report_once(void);
+
 #else /* CONFIG_ARM64_MTE */
 
 static inline u8 mte_get_ptr_tag(void *ptr)
@@ -60,6 +63,15 @@ static inline void mte_init_tags(u64 max_tag)
 {
 }
 
+static inline void mte_set_report_once(bool state)
+{
+}
+
+static inline bool mte_report_once(void)
+{
+	return false;
+}
+
 #endif /* CONFIG_ARM64_MTE */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 80b62fe49dcf..2cfc850809ce 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -25,6 +25,8 @@
 
 u64 gcr_kernel_excl __ro_after_init;
 
+static bool report_fault_once = true;
+
 static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
 {
 	pte_t old_pte = READ_ONCE(*ptep);
@@ -158,6 +160,16 @@ void mte_enable_kernel(void)
 	isb();
 }
 
+void mte_set_report_once(bool state)
+{
+	WRITE_ONCE(report_fault_once, state);
+}
+
+bool mte_report_once(void)
+{
+	return READ_ONCE(report_fault_once);
+}
+
 static void update_sctlr_el1_tcf0(u64 tcf0)
 {
 	/* ISB required for the kernel uaccess routines */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2e339f0bd958..dc9f96442edc 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -302,12 +302,24 @@ static void die_kernel_fault(const char *msg, unsigned long addr,
 static void report_tag_fault(unsigned long addr, unsigned int esr,
 			     struct pt_regs *regs)
 {
-	bool is_write  = ((esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT) != 0;
+	static bool reported;
+	bool is_write;
+
+	if (READ_ONCE(reported))
+		return;
+
+	/*
+	 * This is used for KASAN tests and assumes that no MTE faults
+	 * happened before running the tests.
+	 */
+	if (mte_report_once())
+		WRITE_ONCE(reported, true);
 
 	/*
 	 * SAS bits aren't set for all faults reported in EL1, so we can't
 	 * find out access size.
 	 */
+	is_write = !!(esr & ESR_ELx_WNR);
 	kasan_report(addr, 0, is_write, regs->pc);
 }
 #else
@@ -319,12 +331,8 @@ static inline void report_tag_fault(unsigned long addr, unsigned int esr,
 static void do_tag_recovery(unsigned long addr, unsigned int esr,
 			   struct pt_regs *regs)
 {
-	static bool reported;
 
-	if (!READ_ONCE(reported)) {
-		report_tag_fault(addr, esr, regs);
-		WRITE_ONCE(reported, true);
-	}
+	report_tag_fault(addr, esr, regs);
 
 	/*
 	 * Disable MTE Tag Checking on the local CPU for the current EL.
diff --git a/arch/hexagon/configs/comet_defconfig b/arch/hexagon/configs/comet_defconfig
index e324f65f41e7..f19ae2ab0aaa 100644
--- a/arch/hexagon/configs/comet_defconfig
+++ b/arch/hexagon/configs/comet_defconfig
@@ -1,7 +1,6 @@
 CONFIG_SMP=y
 CONFIG_DEFAULT_MMAP_MIN_ADDR=0
 CONFIG_HZ_100=y
-CONFIG_EXPERIMENTAL=y
 CONFIG_CROSS_COMPILE="hexagon-"
 CONFIG_LOCALVERSION="-smp"
 # CONFIG_LOCALVERSION_AUTO is not set
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 779b6972aa84..9b4efe89e62d 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -517,12 +517,6 @@ extern struct page *zero_page_memmap_ptr;
 	__changed;							\
 })
 #endif
-
-#  ifdef CONFIG_VIRTUAL_MEM_MAP
-  /* arch mem_map init routine is needed due to holes in a virtual mem_map */
-    extern void memmap_init (unsigned long size, int nid, unsigned long zone,
-			     unsigned long start_pfn);
-#  endif /* CONFIG_VIRTUAL_MEM_MAP */
 # endif /* !__ASSEMBLY__ */
 
 /*
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index b19f47a5a305..16d0d7d22657 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -536,18 +536,20 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 		    / sizeof(struct page));
 
 	if (map_start < map_end)
-		memmap_init_zone((unsigned long)(map_end - map_start),
+		memmap_init_range((unsigned long)(map_end - map_start),
 				 args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end),
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	return 0;
 }
 
-void __meminit
-memmap_init (unsigned long size, int nid, unsigned long zone,
-	     unsigned long start_pfn)
+void __meminit memmap_init_zone(struct zone *zone)
 {
+	int nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+	unsigned long start_pfn = zone->zone_start_pfn;
+	unsigned long size = zone->spanned_pages;
+
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size,
+		memmap_init_range(size, nid, zone_id, start_pfn, start_pfn + size,
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	} else {
 		struct page *start;
@@ -557,7 +559,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 		args.start = start;
 		args.end = start + size;
 		args.nid = nid;
-		args.zone = zone;
+		args.zone = zone_id;
 
 		efi_memmap_walk(virtual_memmap_init, &args);
 	}
diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c
index bd4b0656add3..61891af25019 100644
--- a/arch/mips/mm/pgtable-32.c
+++ b/arch/mips/mm/pgtable-32.c
@@ -45,7 +45,6 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
-	flush_tlb_all();
 }
 #endif /* defined(CONFIG_TRANSPARENT_HUGEPAGE) */
 
diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c
index 183ff9f9c026..7536f7804c44 100644
--- a/arch/mips/mm/pgtable-64.c
+++ b/arch/mips/mm/pgtable-64.c
@@ -100,7 +100,6 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
-	flush_tlb_all();
 }
 
 void __init pagetable_init(void)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 04f71c7bc3f8..f449dbb2c746 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -372,14 +372,19 @@ static ssize_t node_read_meminfo(struct device *dev,
 	struct pglist_data *pgdat = NODE_DATA(nid);
 	struct sysinfo i;
 	unsigned long sreclaimable, sunreclaimable;
+	unsigned long swapcached = 0;
 
 	si_meminfo_node(&i, nid);
 	sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B);
 	sunreclaimable = node_page_state_pages(pgdat, NR_SLAB_UNRECLAIMABLE_B);
+#ifdef CONFIG_SWAP
+	swapcached = node_page_state_pages(pgdat, NR_SWAPCACHE);
+#endif
 	len = sysfs_emit_at(buf, len,
 			    "Node %d MemTotal:       %8lu kB\n"
 			    "Node %d MemFree:        %8lu kB\n"
 			    "Node %d MemUsed:        %8lu kB\n"
+			    "Node %d SwapCached:     %8lu kB\n"
 			    "Node %d Active:         %8lu kB\n"
 			    "Node %d Inactive:       %8lu kB\n"
 			    "Node %d Active(anon):   %8lu kB\n"
@@ -391,6 +396,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 			    nid, K(i.totalram),
 			    nid, K(i.freeram),
 			    nid, K(i.totalram - i.freeram),
+			    nid, K(swapcached),
 			    nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) +
 				   node_page_state(pgdat, NR_ACTIVE_FILE)),
 			    nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) +
@@ -461,16 +467,11 @@ static ssize_t node_read_meminfo(struct device *dev,
 			     nid, K(sunreclaimable)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 			     ,
-			     nid, K(node_page_state(pgdat, NR_ANON_THPS) *
-				    HPAGE_PMD_NR),
-			     nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
-				    HPAGE_PMD_NR),
-			     nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
-				    HPAGE_PMD_NR),
-			     nid, K(node_page_state(pgdat, NR_FILE_THPS) *
-				    HPAGE_PMD_NR),
-			     nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) *
-				    HPAGE_PMD_NR)
+			     nid, K(node_page_state(pgdat, NR_ANON_THPS)),
+			     nid, K(node_page_state(pgdat, NR_SHMEM_THPS)),
+			     nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
+			     nid, K(node_page_state(pgdat, NR_FILE_THPS)),
+			     nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED))
 #endif
 			    );
 	len += hugetlb_report_node_meminfo(buf, len, nid);
@@ -519,10 +520,14 @@ static ssize_t node_read_vmstat(struct device *dev,
 				     sum_zone_numa_state(nid, i));
 
 #endif
-	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-		len += sysfs_emit_at(buf, len, "%s %lu\n",
-				     node_stat_name(i),
-				     node_page_state_pages(pgdat, i));
+	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+		unsigned long pages = node_page_state_pages(pgdat, i);
+
+		if (vmstat_item_print_in_thp(i))
+			pages /= HPAGE_PMD_NR;
+		len += sysfs_emit_at(buf, len, "%s %lu\n", node_stat_name(i),
+				     pages);
+	}
 
 	return len;
 }
diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c
index bcc92aecf666..1b72edc01cfb 100644
--- a/drivers/video/fbdev/acornfb.c
+++ b/drivers/video/fbdev/acornfb.c
@@ -921,40 +921,6 @@ static int acornfb_detect_monitortype(void)
 	return 4;
 }
 
-/*
- * This enables the unused memory to be freed on older Acorn machines.
- * We are freeing memory on behalf of the architecture initialisation
- * code here.
- */
-static inline void
-free_unused_pages(unsigned int virtual_start, unsigned int virtual_end)
-{
-	int mb_freed = 0;
-
-	/*
-	 * Align addresses
-	 */
-	virtual_start = PAGE_ALIGN(virtual_start);
-	virtual_end = PAGE_ALIGN(virtual_end);
-
-	while (virtual_start < virtual_end) {
-		struct page *page;
-
-		/*
-		 * Clear page reserved bit,
-		 * set count to 1, and free
-		 * the page.
-		 */
-		page = virt_to_page(virtual_start);
-		__free_reserved_page(page);
-
-		virtual_start += PAGE_SIZE;
-		mb_freed += PAGE_SIZE / 1024;
-	}
-
-	printk("acornfb: freed %dK memory\n", mb_freed);
-}
-
 static int acornfb_probe(struct platform_device *dev)
 {
 	unsigned long size;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index ec26179c8062..91ff9bfd7c1a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1270,7 +1270,7 @@ rescan:
 	return ret;
 }
 /*
- * Only exported for for loop and dasd for historic reasons.  Don't use in new
+ * Only exported for loop and dasd for historic reasons.  Don't use in new
  * code!
  */
 EXPORT_SYMBOL_GPL(bdev_disk_changed);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index be9e3900cce8..bf2c51a9607a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3634,7 +3634,7 @@ static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			return ret;
 	}
 
-	return generic_file_buffered_read(iocb, to, ret);
+	return filemap_read(iocb, to, ret);
 }
 
 const struct file_operations btrfs_file_operations = {
diff --git a/fs/buffer.c b/fs/buffer.c
index 32647d2011df..0cb7ffd4977c 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -847,7 +847,8 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 	if (retry)
 		gfp |= __GFP_NOFAIL;
 
-	memcg = get_mem_cgroup_from_page(page);
+	/* The page lock pins the memcg */
+	memcg = page_memcg(page);
 	old_memcg = set_active_memcg(memcg);
 
 	head = NULL;
@@ -868,7 +869,6 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 	}
 out:
 	set_active_memcg(old_memcg);
-	mem_cgroup_put(memcg);
 	return head;
 /*
  * In case anything failed, we just free everything we got.
@@ -2083,7 +2083,8 @@ static int __block_commit_write(struct inode *inode, struct page *page,
 			set_buffer_uptodate(bh);
 			mark_buffer_dirty(bh);
 		}
-		clear_buffer_new(bh);
+		if (buffer_new(bh))
+			clear_buffer_new(bh);
 
 		block_start = block_end;
 		bh = bh->b_this_page;
diff --git a/fs/dcache.c b/fs/dcache.c
index 799d9e4f0bcd..7d24ff7eb206 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2176,8 +2176,8 @@ EXPORT_SYMBOL(d_obtain_root);
  * same inode, only the actual correct case is stored in the dcache for
  * case-insensitive filesystems.
  *
- * For a case-insensitive lookup match and if the the case-exact dentry
- * already exists in in the dcache, use it and return it.
+ * For a case-insensitive lookup match and if the case-exact dentry
+ * already exists in the dcache, use it and return it.
  *
  * If no entry exists with the exact case name, allocate new dentry with
  * the exact case, and return the spliced entry.
diff --git a/fs/direct-io.c b/fs/direct-io.c
index aa1083ecd623..0957e1bb8eb2 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -462,7 +462,7 @@ static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio)
  * Wait for the next BIO to complete.  Remove it and return it.  NULL is
  * returned once all BIOs have been completed.  This must only be called once
  * all bios have been issued so that dio->refcount can only decrease.  This
- * requires that that the caller hold a reference on the dio.
+ * requires that the caller hold a reference on the dio.
  */
 static struct bio *dio_await_one(struct dio *dio)
 {
@@ -1279,7 +1279,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	if (retval == -ENOTBLK) {
 		/*
 		 * The remaining part of the request will be
-		 * be handled by buffered I/O when we return
+		 * handled by buffered I/O when we return
 		 */
 		retval = 0;
 	}
diff --git a/fs/exec.c b/fs/exec.c
index 6f3c02066ce3..18594f11c31f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1455,7 +1455,7 @@ EXPORT_SYMBOL(finalize_exec);
 /*
  * Prepare credentials and lock ->cred_guard_mutex.
  * setup_new_exec() commits the new creds and drops the lock.
- * Or, if exec fails before, free_bprm() should release ->cred and
+ * Or, if exec fails before, free_bprm() should release ->cred
  * and unlock.
  */
 static int prepare_bprm_creds(struct linux_binprm *bprm)
@@ -1841,7 +1841,7 @@ static int bprm_execve(struct linux_binprm *bprm,
 
 out:
 	/*
-	 * If past the point of no return ensure the the code never
+	 * If past the point of no return ensure the code never
 	 * returns to the userspace process.  Use an existing fatal
 	 * signal if present otherwise terminate the process with
 	 * SIGSEGV.
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 01263ffbc4c0..ec6feeccc276 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -173,7 +173,7 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
 
 	/*
 	 * With handle we don't look at the execute bit on the
-	 * the directory. Ideally we would like CAP_DAC_SEARCH.
+	 * directory. Ideally we would like CAP_DAC_SEARCH.
 	 * But we don't have that
 	 */
 	if (!capable(CAP_DAC_READ_SEARCH)) {
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 588f8d1240aa..c6636b4c4ccf 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -844,11 +844,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 	if (WARN_ON(PageMlocked(oldpage)))
 		goto out_fallback_unlock;
 
-	err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL);
-	if (err) {
-		unlock_page(newpage);
-		goto out_put_old;
-	}
+	replace_page_cache_page(oldpage, newpage);
 
 	get_page(newpage);
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b7a72f577aab..701c82c36138 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -171,7 +171,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	file_accessed(file);
 
 	ret = -ENOMEM;
-	if (hugetlb_reserve_pages(inode,
+	if (!hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
 				vma->vm_flags))
@@ -310,7 +310,7 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset,
 
 /*
  * Support for read() - Find the page attached to f_mapping and copy out the
- * data. Its *very* similar to do_generic_mapping_read(), we can't use that
+ * data. Its *very* similar to generic_file_buffered_read(), we can't use that
  * since it has PAGE_SIZE assumptions.
  */
 static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -442,15 +442,15 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
  *
  * truncation is indicated by end of range being LLONG_MAX
  *	In this case, we first scan the range and release found pages.
- *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
+ *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserve
  *	maps and global counts.  Page faults can not race with truncation
  *	in this routine.  hugetlb_no_page() holds i_mmap_rwsem and prevents
  *	page faults in the truncated range by checking i_size.  i_size is
  *	modified while holding i_mmap_rwsem.
  * hole punch is indicated if end is not LLONG_MAX
  *	In the hole punch case we scan the range and release found pages.
- *	Only when releasing a page is the associated region/reserv map
- *	deleted.  The region/reserv map for ranges without associated
+ *	Only when releasing a page is the associated region/reserve map
+ *	deleted.  The region/reserve map for ranges without associated
  *	pages are not modified.  Page faults can race with hole punch.
  *	This is indicated if we find a mapped page.
  * Note: If the passed end of range value is beyond the end of file, but
@@ -567,7 +567,7 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
+static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 {
 	pgoff_t pgoff;
 	struct address_space *mapping = inode->i_mapping;
@@ -582,7 +582,6 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
 	i_mmap_unlock_write(mapping);
 	remove_inode_hugepages(inode, offset, LLONG_MAX);
-	return 0;
 }
 
 static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
@@ -604,7 +603,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
 		inode_lock(inode);
 
-		/* protected by i_mutex */
+		/* protected by i_rwsem */
 		if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
 			inode_unlock(inode);
 			return -EPERM;
@@ -680,7 +679,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		 */
 		struct page *page;
 		unsigned long addr;
-		int avoid_reserve = 0;
 
 		cond_resched();
 
@@ -716,8 +714,15 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 			continue;
 		}
 
-		/* Allocate page and add to page cache */
-		page = alloc_huge_page(&pseudo_vma, addr, avoid_reserve);
+		/*
+		 * Allocate page without setting the avoid_reserve argument.
+		 * There certainly are no reserves associated with the
+		 * pseudo_vma.  However, there could be shared mappings with
+		 * reserves for the file at the inode level.  If we fallocate
+		 * pages in these areas, we need to consume the reserves
+		 * to keep reservation accounting consistent.
+		 */
+		page = alloc_huge_page(&pseudo_vma, addr, 0);
 		hugetlb_drop_vma_policy(&pseudo_vma);
 		if (IS_ERR(page)) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
@@ -735,7 +740,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 
 		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 
-		set_page_huge_active(page);
+		SetHPageMigratable(page);
 		/*
 		 * unlock_page because locked by add_to_page_cache()
 		 * put_page() due to reference from alloc_huge_page()
@@ -761,8 +766,6 @@ static int hugetlbfs_setattr(struct user_namespace *mnt_userns,
 	unsigned int ia_valid = attr->ia_valid;
 	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
-	BUG_ON(!inode);
-
 	error = setattr_prepare(&init_user_ns, dentry, attr);
 	if (error)
 		return error;
@@ -773,13 +776,11 @@ static int hugetlbfs_setattr(struct user_namespace *mnt_userns,
 
 		if (newsize & ~huge_page_mask(h))
 			return -EINVAL;
-		/* protected by i_mutex */
+		/* protected by i_rwsem */
 		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
 		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
 			return -EPERM;
-		error = hugetlb_vmtruncate(inode, newsize);
-		if (error)
-			return error;
+		hugetlb_vmtruncate(inode, newsize);
 	}
 
 	setattr_copy(&init_user_ns, inode, attr);
@@ -952,17 +953,6 @@ static int hugetlbfs_symlink(struct user_namespace *mnt_userns,
 	return error;
 }
 
-/*
- * mark the head page dirty
- */
-static int hugetlbfs_set_page_dirty(struct page *page)
-{
-	struct page *head = compound_head(page);
-
-	SetPageDirty(head);
-	return 0;
-}
-
 static int hugetlbfs_migrate_page(struct address_space *mapping,
 				struct page *newpage, struct page *page,
 				enum migrate_mode mode)
@@ -973,15 +963,9 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 
-	/*
-	 * page_private is subpool pointer in hugetlb pages.  Transfer to
-	 * new page.  PagePrivate is not associated with page_private for
-	 * hugetlb pages and can not be set here as only page_huge_active
-	 * pages can be migrated.
-	 */
-	if (page_private(page)) {
-		set_page_private(newpage, page_private(page));
-		set_page_private(page, 0);
+	if (hugetlb_page_subpool(page)) {
+		hugetlb_set_page_subpool(newpage, hugetlb_page_subpool(page));
+		hugetlb_set_page_subpool(page, NULL);
 	}
 
 	if (mode != MIGRATE_SYNC_NO_COPY)
@@ -1156,7 +1140,7 @@ static void hugetlbfs_destroy_inode(struct inode *inode)
 static const struct address_space_operations hugetlbfs_aops = {
 	.write_begin	= hugetlbfs_write_begin,
 	.write_end	= hugetlbfs_write_end,
-	.set_page_dirty	= hugetlbfs_set_page_dirty,
+	.set_page_dirty	=  __set_page_dirty_no_writeback,
 	.migratepage    = hugetlbfs_migrate_page,
 	.error_remove_page	= hugetlbfs_error_remove_page,
 };
@@ -1356,7 +1340,7 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	/*
 	 * Allocate and initialize subpool if maximum or minimum size is
-	 * specified.  Any needed reservations (for minimim size) are taken
+	 * specified.  Any needed reservations (for minimum size) are taken
 	 * taken when the subpool is created.
 	 */
 	if (ctx->max_hpages != -1 || ctx->min_hpages != -1) {
@@ -1499,7 +1483,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	if (hugetlb_reserve_pages(inode, 0,
+	if (!hugetlb_reserve_pages(inode, 0,
 			size >> huge_page_shift(hstate_inode(inode)), NULL,
 			acctflag))
 		file = ERR_PTR(-ENOMEM);
@@ -1533,8 +1517,8 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h)
 		put_fs_context(fc);
 	}
 	if (IS_ERR(mnt))
-		pr_err("Cannot mount internal hugetlbfs for page size %uK",
-		       1U << (h->order + PAGE_SHIFT - 10));
+		pr_err("Cannot mount internal hugetlbfs for page size %luK",
+		       huge_page_size(h) >> 10);
 	return mnt;
 }
 
@@ -1562,7 +1546,7 @@ static int __init init_hugetlbfs_fs(void)
 		goto out_free;
 
 	/* default hstate mount is required */
-	mnt = mount_one_hugetlbfs(&hstates[default_hstate_idx]);
+	mnt = mount_one_hugetlbfs(&default_hstate);
 	if (IS_ERR(mnt)) {
 		error = PTR_ERR(mnt);
 		goto out_unreg;
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 4435dbbc0b63..f5c058b3192c 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -629,6 +629,12 @@ static int ntfs_read_locked_inode(struct inode *vi)
 	}
 	a = ctx->attr;
 	/* Get the standard information attribute value. */
+	if ((u8 *)a + le16_to_cpu(a->data.resident.value_offset)
+			+ le32_to_cpu(a->data.resident.value_length) >
+			(u8 *)ctx->mrec + vol->mft_record_size) {
+		ntfs_error(vi->i_sb, "Corrupt standard information attribute in inode.");
+		goto unm_err_out;
+	}
 	si = (STANDARD_INFORMATION*)((u8*)a +
 			le16_to_cpu(a->data.resident.value_offset));
 
diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h
index 85422761ff43..5d4bf7a3259f 100644
--- a/fs/ntfs/layout.h
+++ b/fs/ntfs/layout.h
@@ -703,7 +703,7 @@ typedef struct {
 /* 14*/	le16 instance;		/* The instance of this attribute record. This
 				   number is unique within this mft record (see
 				   MFT_RECORD/next_attribute_instance notes in
-				   in mft.h for more details). */
+				   mft.h for more details). */
 /* 16*/	union {
 		/* Resident attributes. */
 		struct {
@@ -1838,7 +1838,7 @@ typedef struct {
  * Also, each security descriptor is stored twice in the $SDS stream with a
  * fixed offset of 0x40000 bytes (256kib, the Windows cache manager's max size)
  * between them; i.e. if a SDS_ENTRY specifies an offset of 0x51d0, then the
- * the first copy of the security descriptor will be at offset 0x51d0 in the
+ * first copy of the security descriptor will be at offset 0x51d0 in the
  * $SDS data stream and the second copy will be at offset 0x451d0.
  */
 typedef struct {
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 0179a73a3fa2..12a7590601dd 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -2042,7 +2042,7 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g
 			o2hb_nego_timeout_handler,
 			reg, NULL, &reg->hr_handler_list);
 	if (ret)
-		goto free;
+		goto remove_item;
 
 	ret = o2net_register_handler(O2HB_NEGO_APPROVE_MSG, reg->hr_key,
 			sizeof(struct o2hb_nego_msg),
@@ -2057,6 +2057,12 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g
 
 unregister_handler:
 	o2net_unregister_handler_list(&reg->hr_handler_list);
+remove_item:
+	spin_lock(&o2hb_live_lock);
+	list_del(&reg->hr_all_item);
+	if (o2hb_global_heartbeat_active())
+		clear_bit(reg->hr_region_num, o2hb_region_bitmap);
+	spin_unlock(&o2hb_live_lock);
 free:
 	kfree(reg);
 	return ERR_PTR(ret);
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index 6abaded3ff6b..70a10764f249 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -165,16 +165,6 @@ void __dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
 	spin_unlock(&lock->spinlock);
 }
 
-void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
-{
-	BUG_ON(!dlm);
-	BUG_ON(!lock);
-
-	spin_lock(&dlm->ast_lock);
-	__dlm_queue_bast(dlm, lock);
-	spin_unlock(&dlm->ast_lock);
-}
-
 static void dlm_update_lvb(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 			   struct dlm_lock *lock)
 {
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index c8a444622faa..58d57e25d384 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -17,10 +17,7 @@
 
 #define DLM_LOCKID_NAME_MAX    32
 
-#define DLM_DOMAIN_NAME_MAX_LEN    255
 #define DLM_LOCK_RES_OWNER_UNKNOWN     O2NM_MAX_NODES
-#define DLM_THREAD_SHUFFLE_INTERVAL    5     // flush everything every 5 passes
-#define DLM_THREAD_MS                  200   // flush at least every 200 ms
 
 #define DLM_HASH_SIZE_DEFAULT	(1 << 17)
 #if DLM_HASH_SIZE_DEFAULT < PAGE_SIZE
@@ -902,7 +899,6 @@ void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
 		struct dlm_lock_resource *res);
 
 void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
-void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void __dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void dlm_do_local_ast(struct dlm_ctxt *dlm,
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index c26937824be1..c19a463fac55 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -978,7 +978,7 @@ static int ocfs2_get_refcount_cpos_end(struct ocfs2_caching_info *ci,
 		return 0;
 	}
 
-	if (!eb || (eb && !eb->h_next_leaf_blk)) {
+	if (!eb || !eb->h_next_leaf_blk) {
 		/*
 		 * We are the last extent rec, so any high cpos should
 		 * be stored in this leaf refcount block.
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 2febc76e9de7..079f8826993e 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -973,8 +973,6 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 		 * quota files */
 		dquot_disable(sb, type, DQUOT_USAGE_ENABLED |
 					DQUOT_LIMITS_ENABLED);
-		if (!inode)
-			continue;
 		iput(inode);
 	}
 }
diff --git a/fs/pipe.c b/fs/pipe.c
index 39c96845a72f..bfd946a9ad01 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -171,7 +171,7 @@ EXPORT_SYMBOL(generic_pipe_buf_try_steal);
  *
  * Description:
  *	This function grabs an extra reference to @buf. It's used in
- *	in the tee() system call, when we duplicate the buffers in one
+ *	the tee() system call, when we duplicate the buffers in one
  *	pipe into another.
  */
 bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index d6fc74619625..6fa761c9cc78 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -129,15 +129,15 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	show_val_kb(m, "AnonHugePages:  ",
-		    global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR);
+		    global_node_page_state(NR_ANON_THPS));
 	show_val_kb(m, "ShmemHugePages: ",
-		    global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR);
+		    global_node_page_state(NR_SHMEM_THPS));
 	show_val_kb(m, "ShmemPmdMapped: ",
-		    global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR);
+		    global_node_page_state(NR_SHMEM_PMDMAPPED));
 	show_val_kb(m, "FileHugePages:  ",
-		    global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR);
+		    global_node_page_state(NR_FILE_THPS));
 	show_val_kb(m, "FilePmdMapped:  ",
-		    global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR);
+		    global_node_page_state(NR_FILE_PMDMAPPED));
 #endif
 
 #ifdef CONFIG_CMA
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index c3a345c28a93..9a15334da208 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -1503,11 +1503,8 @@ int vmcore_add_device_dump(struct vmcoredd_data *data)
 	return 0;
 
 out_err:
-	if (buf)
-		vfree(buf);
-
-	if (dump)
-		vfree(dump);
+	vfree(buf);
+	vfree(dump);
 
 	return ret;
 }
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 3c2658c8fde0..9ebd17d7befb 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -151,6 +151,18 @@ static int ramfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	return error;
 }
 
+static int ramfs_tmpfile(struct user_namespace *mnt_userns,
+			 struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct inode *inode;
+
+	inode = ramfs_get_inode(dir->i_sb, dir, mode, 0);
+	if (!inode)
+		return -ENOSPC;
+	d_tmpfile(dentry, inode);
+	return 0;
+}
+
 static const struct inode_operations ramfs_dir_inode_operations = {
 	.create		= ramfs_create,
 	.lookup		= simple_lookup,
@@ -161,6 +173,7 @@ static const struct inode_operations ramfs_dir_inode_operations = {
 	.rmdir		= simple_rmdir,
 	.mknod		= ramfs_mknod,
 	.rename		= simple_rename,
+	.tmpfile	= ramfs_tmpfile,
 };
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 418b772d6eca..ec8f3ddf4a6a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3080,8 +3080,8 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
 		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
-extern ssize_t generic_file_buffered_read(struct kiocb *iocb,
-		struct iov_iter *to, ssize_t already_read);
+ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to,
+		ssize_t already_read);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 80544d5c08e7..220cd553a9e7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -8,6 +8,20 @@
 #include <linux/linkage.h>
 #include <linux/topology.h>
 
+/* The typedef is in types.h but we want the documentation here */
+#if 0
+/**
+ * typedef gfp_t - Memory allocation flags.
+ *
+ * GFP flags are commonly used throughout Linux to indicate how memory
+ * should be allocated.  The GFP acronym stands for get_free_pages(),
+ * the underlying memory allocation function.  Not every GFP flag is
+ * supported by every function which may allocate memory.  Most users
+ * will want to use a plain ``GFP_KERNEL``.
+ */
+typedef unsigned int __bitwise gfp_t;
+#endif
+
 struct vm_area_struct;
 
 /*
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 1bbe96dc8be6..7902c7d8b55f 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -127,11 +127,6 @@ static inline unsigned long totalhigh_pages(void)
 	return (unsigned long)atomic_long_read(&_totalhigh_pages);
 }
 
-static inline void totalhigh_pages_inc(void)
-{
-	atomic_long_inc(&_totalhigh_pages);
-}
-
 static inline void totalhigh_pages_add(long count)
 {
 	atomic_long_add(count, &_totalhigh_pages);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 6a19f35f836b..ba973efcd369 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -78,6 +78,7 @@ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn,
 }
 
 enum transparent_hugepage_flag {
+	TRANSPARENT_HUGEPAGE_NEVER_DAX,
 	TRANSPARENT_HUGEPAGE_FLAG,
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
 	TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
@@ -123,6 +124,13 @@ extern unsigned long transparent_hugepage_flags;
  */
 static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
 {
+
+	/*
+	 * If the hardware/firmware marked hugepage support disabled.
+	 */
+	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX))
+		return false;
+
 	if (vma->vm_flags & VM_NOHUGEPAGE)
 		return false;
 
@@ -134,12 +142,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
 
 	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
 		return true;
-	/*
-	 * For dax vmas, try to always use hugepage mappings. If the kernel does
-	 * not support hugepages, fsdax mappings will fallback to PAGE_SIZE
-	 * mappings, and device-dax namespaces, that try to guarantee a given
-	 * mapping size, will fail to enable
-	 */
+
 	if (vma_is_dax(vma))
 		return true;
 
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b5807f23caf8..cccd1aab69dd 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -37,7 +37,7 @@ struct hugepage_subpool {
 	struct hstate *hstate;
 	long min_hpages;	/* Minimum huge pages or -1 if no minimum. */
 	long rsv_hpages;	/* Pages reserved against global pool to */
-				/* sasitfy minimum size. */
+				/* satisfy minimum size. */
 };
 
 struct resv_map {
@@ -139,7 +139,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte,
 				unsigned long dst_addr,
 				unsigned long src_addr,
 				struct page **pagep);
-int hugetlb_reserve_pages(struct inode *inode, long from, long to,
+bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
@@ -472,6 +472,84 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long flags);
 #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
 
+/*
+ * huegtlb page specific state flags.  These flags are located in page.private
+ * of the hugetlb head page.  Functions created via the below macros should be
+ * used to manipulate these flags.
+ *
+ * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at
+ *	allocation time.  Cleared when page is fully instantiated.  Free
+ *	routine checks flag to restore a reservation on error paths.
+ *	Synchronization:  Examined or modified by code that knows it has
+ *	the only reference to page.  i.e. After allocation but before use
+ *	or when the page is being freed.
+ * HPG_migratable  - Set after a newly allocated page is added to the page
+ *	cache and/or page tables.  Indicates the page is a candidate for
+ *	migration.
+ *	Synchronization:  Initially set after new page allocation with no
+ *	locking.  When examined and modified during migration processing
+ *	(isolate, migrate, putback) the hugetlb_lock is held.
+ * HPG_temporary - - Set on a page that is temporarily allocated from the buddy
+ *	allocator.  Typically used for migration target pages when no pages
+ *	are available in the pool.  The hugetlb free page path will
+ *	immediately free pages with this flag set to the buddy allocator.
+ *	Synchronization: Can be set after huge page allocation from buddy when
+ *	code knows it has only reference.  All other examinations and
+ *	modifications require hugetlb_lock.
+ * HPG_freed - Set when page is on the free lists.
+ *	Synchronization: hugetlb_lock held for examination and modification.
+ */
+enum hugetlb_page_flags {
+	HPG_restore_reserve = 0,
+	HPG_migratable,
+	HPG_temporary,
+	HPG_freed,
+	__NR_HPAGEFLAGS,
+};
+
+/*
+ * Macros to create test, set and clear function definitions for
+ * hugetlb specific page flags.
+ */
+#ifdef CONFIG_HUGETLB_PAGE
+#define TESTHPAGEFLAG(uname, flname)				\
+static inline int HPage##uname(struct page *page)		\
+	{ return test_bit(HPG_##flname, &(page->private)); }
+
+#define SETHPAGEFLAG(uname, flname)				\
+static inline void SetHPage##uname(struct page *page)		\
+	{ set_bit(HPG_##flname, &(page->private)); }
+
+#define CLEARHPAGEFLAG(uname, flname)				\
+static inline void ClearHPage##uname(struct page *page)		\
+	{ clear_bit(HPG_##flname, &(page->private)); }
+#else
+#define TESTHPAGEFLAG(uname, flname)				\
+static inline int HPage##uname(struct page *page)		\
+	{ return 0; }
+
+#define SETHPAGEFLAG(uname, flname)				\
+static inline void SetHPage##uname(struct page *page)		\
+	{ }
+
+#define CLEARHPAGEFLAG(uname, flname)				\
+static inline void ClearHPage##uname(struct page *page)		\
+	{ }
+#endif
+
+#define HPAGEFLAG(uname, flname)				\
+	TESTHPAGEFLAG(uname, flname)				\
+	SETHPAGEFLAG(uname, flname)				\
+	CLEARHPAGEFLAG(uname, flname)				\
+
+/*
+ * Create functions associated with hugetlb page flags
+ */
+HPAGEFLAG(RestoreReserve, restore_reserve)
+HPAGEFLAG(Migratable, migratable)
+HPAGEFLAG(Temporary, temporary)
+HPAGEFLAG(Freed, freed)
+
 #ifdef CONFIG_HUGETLB_PAGE
 
 #define HSTATE_NAME_LEN 32
@@ -531,6 +609,20 @@ extern unsigned int default_hstate_idx;
 
 #define default_hstate (hstates[default_hstate_idx])
 
+/*
+ * hugetlb page subpool pointer located in hpage[1].private
+ */
+static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
+{
+	return (struct hugepage_subpool *)(hpage+1)->private;
+}
+
+static inline void hugetlb_set_page_subpool(struct page *hpage,
+					struct hugepage_subpool *subpool)
+{
+	set_page_private(hpage+1, (unsigned long)subpool);
+}
+
 static inline struct hstate *hstate_file(struct file *f)
 {
 	return hstate_inode(file_inode(f));
@@ -770,8 +862,6 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 }
 #endif
 
-void set_page_huge_active(struct page *page);
-
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h
index ca5e89fb10d3..3d6d22a25bdc 100644
--- a/include/linux/kasan-checks.h
+++ b/include/linux/kasan-checks.h
@@ -5,6 +5,12 @@
 #include <linux/types.h>
 
 /*
+ * The annotations present in this file are only relevant for the software
+ * KASAN modes that rely on compiler instrumentation, and will be optimized
+ * away for the hardware tag-based KASAN mode. Use kasan_check_byte() instead.
+ */
+
+/*
  * __kasan_check_*: Always available when KASAN is enabled. This may be used
  * even in compilation units that selectively disable KASAN, but must use KASAN
  * to validate access to an address.   Never use these in header files!
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 0aea9e2a2a01..7eaf2d9effb4 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -185,19 +185,18 @@ static __always_inline void * __must_check kasan_init_slab_obj(
 }
 
 bool __kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip);
-static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object,
-						unsigned long ip)
+static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object)
 {
 	if (kasan_enabled())
-		return __kasan_slab_free(s, object, ip);
+		return __kasan_slab_free(s, object, _RET_IP_);
 	return false;
 }
 
 void __kasan_slab_free_mempool(void *ptr, unsigned long ip);
-static __always_inline void kasan_slab_free_mempool(void *ptr, unsigned long ip)
+static __always_inline void kasan_slab_free_mempool(void *ptr)
 {
 	if (kasan_enabled())
-		__kasan_slab_free_mempool(ptr, ip);
+		__kasan_slab_free_mempool(ptr, _RET_IP_);
 }
 
 void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
@@ -241,12 +240,25 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 }
 
 void __kasan_kfree_large(void *ptr, unsigned long ip);
-static __always_inline void kasan_kfree_large(void *ptr, unsigned long ip)
+static __always_inline void kasan_kfree_large(void *ptr)
 {
 	if (kasan_enabled())
-		__kasan_kfree_large(ptr, ip);
+		__kasan_kfree_large(ptr, _RET_IP_);
 }
 
+/*
+ * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for
+ * the hardware tag-based mode that doesn't rely on compiler instrumentation.
+ */
+bool __kasan_check_byte(const void *addr, unsigned long ip);
+static __always_inline bool kasan_check_byte(const void *addr)
+{
+	if (kasan_enabled())
+		return __kasan_check_byte(addr, _RET_IP_);
+	return true;
+}
+
+
 bool kasan_save_enable_multi_shot(void);
 void kasan_restore_multi_shot(bool enabled);
 
@@ -277,12 +289,11 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
 {
 	return (void *)object;
 }
-static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
-				   unsigned long ip)
+static inline bool kasan_slab_free(struct kmem_cache *s, void *object)
 {
 	return false;
 }
-static inline void kasan_slab_free_mempool(void *ptr, unsigned long ip) {}
+static inline void kasan_slab_free_mempool(void *ptr) {}
 static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
 				   gfp_t flags)
 {
@@ -302,7 +313,11 @@ static inline void *kasan_krealloc(const void *object, size_t new_size,
 {
 	return (void *)object;
 }
-static inline void kasan_kfree_large(void *ptr, unsigned long ip) {}
+static inline void kasan_kfree_large(void *ptr) {}
+static inline bool kasan_check_byte(const void *address)
+{
+	return true;
+}
 
 #endif /* CONFIG_KASAN */
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index eeb0b52203e9..e6dc793d587d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -92,6 +92,10 @@ struct lruvec_stat {
 	long count[NR_VM_NODE_STAT_ITEMS];
 };
 
+struct batched_lruvec_stat {
+	s32 count[NR_VM_NODE_STAT_ITEMS];
+};
+
 /*
  * Bitmap of shrinker::id corresponding to memcg-aware shrinkers,
  * which have elements charged to this memcg.
@@ -107,11 +111,17 @@ struct memcg_shrinker_map {
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 
-	/* Legacy local VM stats */
+	/*
+	 * Legacy local VM stats. This should be struct lruvec_stat and
+	 * cannot be optimized to struct batched_lruvec_stat. Because
+	 * the threshold of the lruvec_stat_cpu can be as big as
+	 * MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this
+	 * filed has no upper limit.
+	 */
 	struct lruvec_stat __percpu *lruvec_stat_local;
 
 	/* Subtree VM stats (batched updates) */
-	struct lruvec_stat __percpu *lruvec_stat_cpu;
+	struct batched_lruvec_stat __percpu *lruvec_stat_cpu;
 	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
@@ -475,19 +485,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
-/*
- * set_page_objcgs - associate a page with a object cgroups vector
- * @page: a pointer to the page struct
- * @objcgs: a pointer to the object cgroups vector
- *
- * Atomically associates a page with a vector of object cgroups.
- */
-static inline bool set_page_objcgs(struct page *page,
-					struct obj_cgroup **objcgs)
-{
-	return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs |
-			MEMCG_DATA_OBJCGS);
-}
 #else
 static inline struct obj_cgroup **page_objcgs(struct page *page)
 {
@@ -498,12 +495,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 {
 	return NULL;
 }
-
-static inline bool set_page_objcgs(struct page *page,
-					struct obj_cgroup **objcgs)
-{
-	return true;
-}
 #endif
 
 static __always_inline bool memcg_stat_item_in_bytes(int idx)
@@ -689,8 +680,6 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
-struct mem_cgroup *get_mem_cgroup_from_page(struct page *page);
-
 struct lruvec *lock_page_lruvec(struct page *page);
 struct lruvec *lock_page_lruvec_irq(struct page *page);
 struct lruvec *lock_page_lruvec_irqsave(struct page *page,
@@ -1200,11 +1189,6 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return NULL;
 }
 
-static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
-{
-	return NULL;
-}
-
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1601,9 +1585,6 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
-int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
-			unsigned int nr_pages);
-void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages);
 int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 4594838a0f7c..3a389633b68f 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -89,7 +89,7 @@ extern int PageMovable(struct page *page);
 extern void __SetPageMovable(struct page *page, struct address_space *mapping);
 extern void __ClearPageMovable(struct page *page);
 #else
-static inline int PageMovable(struct page *page) { return 0; };
+static inline int PageMovable(struct page *page) { return 0; }
 static inline void __SetPageMovable(struct page *page,
 				struct address_space *mapping)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7deb7168104d..77e64e3eac80 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1187,6 +1187,9 @@ static inline void get_page(struct page *page)
 }
 
 bool __must_check try_grab_page(struct page *page, unsigned int flags);
+__maybe_unused struct page *try_grab_compound_head(struct page *page, int refs,
+						   unsigned int flags);
+
 
 static inline __must_check bool try_get_page(struct page *page)
 {
@@ -2310,32 +2313,20 @@ extern void free_initmem(void);
 extern unsigned long free_reserved_area(void *start, void *end,
 					int poison, const char *s);
 
-#ifdef	CONFIG_HIGHMEM
-/*
- * Free a highmem page into the buddy system, adjusting totalhigh_pages
- * and totalram_pages.
- */
-extern void free_highmem_page(struct page *page);
-#endif
-
 extern void adjust_managed_page_count(struct page *page, long count);
 extern void mem_init_print_info(const char *str);
 
 extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
-static inline void __free_reserved_page(struct page *page)
+static inline void free_reserved_page(struct page *page)
 {
 	ClearPageReserved(page);
 	init_page_count(page);
 	__free_page(page);
-}
-
-static inline void free_reserved_page(struct page *page)
-{
-	__free_reserved_page(page);
 	adjust_managed_page_count(page, 1);
 }
+#define free_highmem_page(page) free_reserved_page(page)
 
 static inline void mark_page_reserved(struct page *page)
 {
@@ -2405,9 +2396,10 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long,
+extern void memmap_init_range(unsigned long, int, unsigned long,
 		unsigned long, unsigned long, enum meminit_context,
 		struct vmem_altmap *, int migratetype);
+extern void memmap_init_zone(struct zone *zone);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 8fc71e9d7bb0..355ea1ee32bd 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -24,7 +24,7 @@ static inline int page_is_file_lru(struct page *page)
 	return !PageSwapBacked(page);
 }
 
-static __always_inline void __update_lru_size(struct lruvec *lruvec,
+static __always_inline void update_lru_size(struct lruvec *lruvec,
 				enum lru_list lru, enum zone_type zid,
 				int nr_pages)
 {
@@ -33,76 +33,27 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec,
 	__mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
 	__mod_zone_page_state(&pgdat->node_zones[zid],
 				NR_ZONE_LRU_BASE + lru, nr_pages);
-}
-
-static __always_inline void update_lru_size(struct lruvec *lruvec,
-				enum lru_list lru, enum zone_type zid,
-				int nr_pages)
-{
-	__update_lru_size(lruvec, lru, zid, nr_pages);
 #ifdef CONFIG_MEMCG
 	mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
 #endif
 }
 
-static __always_inline void add_page_to_lru_list(struct page *page,
-				struct lruvec *lruvec, enum lru_list lru)
-{
-	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
-	list_add(&page->lru, &lruvec->lists[lru]);
-}
-
-static __always_inline void add_page_to_lru_list_tail(struct page *page,
-				struct lruvec *lruvec, enum lru_list lru)
-{
-	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
-	list_add_tail(&page->lru, &lruvec->lists[lru]);
-}
-
-static __always_inline void del_page_from_lru_list(struct page *page,
-				struct lruvec *lruvec, enum lru_list lru)
-{
-	list_del(&page->lru);
-	update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page));
-}
-
 /**
- * page_lru_base_type - which LRU list type should a page be on?
- * @page: the page to test
- *
- * Used for LRU list index arithmetic.
- *
- * Returns the base LRU type - file or anon - @page should be on.
+ * __clear_page_lru_flags - clear page lru flags before releasing a page
+ * @page: the page that was on lru and now has a zero reference
  */
-static inline enum lru_list page_lru_base_type(struct page *page)
+static __always_inline void __clear_page_lru_flags(struct page *page)
 {
-	if (page_is_file_lru(page))
-		return LRU_INACTIVE_FILE;
-	return LRU_INACTIVE_ANON;
-}
+	VM_BUG_ON_PAGE(!PageLRU(page), page);
 
-/**
- * page_off_lru - which LRU list was page on? clearing its lru flags.
- * @page: the page to test
- *
- * Returns the LRU list a page was on, as an index into the array of LRU
- * lists; and clears its Unevictable or Active flags, ready for freeing.
- */
-static __always_inline enum lru_list page_off_lru(struct page *page)
-{
-	enum lru_list lru;
+	__ClearPageLRU(page);
 
-	if (PageUnevictable(page)) {
-		__ClearPageUnevictable(page);
-		lru = LRU_UNEVICTABLE;
-	} else {
-		lru = page_lru_base_type(page);
-		if (PageActive(page)) {
-			__ClearPageActive(page);
-			lru += LRU_ACTIVE;
-		}
-	}
-	return lru;
+	/* this shouldn't happen, so leave the flags to bad_page() */
+	if (PageActive(page) && PageUnevictable(page))
+		return;
+
+	__ClearPageActive(page);
+	__ClearPageUnevictable(page);
 }
 
 /**
@@ -116,13 +67,41 @@ static __always_inline enum lru_list page_lru(struct page *page)
 {
 	enum lru_list lru;
 
+	VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
+
 	if (PageUnevictable(page))
-		lru = LRU_UNEVICTABLE;
-	else {
-		lru = page_lru_base_type(page);
-		if (PageActive(page))
-			lru += LRU_ACTIVE;
-	}
+		return LRU_UNEVICTABLE;
+
+	lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
+	if (PageActive(page))
+		lru += LRU_ACTIVE;
+
 	return lru;
 }
+
+static __always_inline void add_page_to_lru_list(struct page *page,
+				struct lruvec *lruvec)
+{
+	enum lru_list lru = page_lru(page);
+
+	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
+	list_add(&page->lru, &lruvec->lists[lru]);
+}
+
+static __always_inline void add_page_to_lru_list_tail(struct page *page,
+				struct lruvec *lruvec)
+{
+	enum lru_list lru = page_lru(page);
+
+	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
+	list_add_tail(&page->lru, &lruvec->lists[lru]);
+}
+
+static __always_inline void del_page_from_lru_list(struct page *page,
+				struct lruvec *lruvec)
+{
+	list_del(&page->lru);
+	update_lru_size(lruvec, page_lru(page), page_zonenum(page),
+			-thp_nr_pages(page));
+}
 #endif
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b593316bff3d..9198b7ade85f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -206,10 +206,30 @@ enum node_stat_item {
 	NR_KERNEL_SCS_KB,	/* measured in KiB */
 #endif
 	NR_PAGETABLE,		/* used for pagetables */
+#ifdef CONFIG_SWAP
+	NR_SWAPCACHE,
+#endif
 	NR_VM_NODE_STAT_ITEMS
 };
 
 /*
+ * Returns true if the item should be printed in THPs (/proc/vmstat
+ * currently prints number of anon, file and shmem THPs. But the item
+ * is charged in pages).
+ */
+static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return false;
+
+	return item == NR_ANON_THPS ||
+	       item == NR_FILE_THPS ||
+	       item == NR_SHMEM_THPS ||
+	       item == NR_SHMEM_PMDMAPPED ||
+	       item == NR_FILE_PMDMAPPED;
+}
+
+/*
  * Returns true if the value is measured in bytes (most vmstat values are
  * measured in pages). This defines the API part, the internal representation
  * might be different.
@@ -872,8 +892,6 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 #endif
 }
 
-extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx);
-
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 int local_memory_node(int node_id);
 #else
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index ec5d0290e0ee..db914477057b 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -592,15 +592,9 @@ static inline void ClearPageCompound(struct page *page)
 #ifdef CONFIG_HUGETLB_PAGE
 int PageHuge(struct page *page);
 int PageHeadHuge(struct page *page);
-bool page_huge_active(struct page *page);
 #else
 TESTPAGEFLAG_FALSE(Huge)
 TESTPAGEFLAG_FALSE(HeadHuge)
-
-static inline bool page_huge_active(struct page *page)
-{
-	return 0;
-}
 #endif
 
 
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 85bd413e784e..679591301994 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -12,7 +12,6 @@ struct page_counter {
 	unsigned long low;
 	unsigned long high;
 	unsigned long max;
-	struct page_counter *parent;
 
 	/* effective memory.min and memory.min usage tracking */
 	unsigned long emin;
@@ -27,6 +26,14 @@ struct page_counter {
 	/* legacy */
 	unsigned long watermark;
 	unsigned long failcnt;
+
+	/*
+	 * 'parent' is placed here to be far from 'usage' to reduce
+	 * cache false sharing, as 'usage' is written mostly while
+	 * parent is frequently read for cgroup's hierarchical
+	 * counting nature.
+	 */
+	struct page_counter *parent;
 };
 
 #if BITS_PER_LONG == 32
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index d5570deff400..bd629d676a27 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -681,8 +681,7 @@ static inline int wait_on_page_locked_killable(struct page *page)
 	return wait_on_page_bit_killable(compound_head(page), PG_locked);
 }
 
-extern void put_and_wait_on_page_locked(struct page *page);
-
+int put_and_wait_on_page_locked(struct page *page, int state);
 void wait_on_page_writeback(struct page *page);
 extern void end_page_writeback(struct page *page);
 void wait_for_stable_page(struct page *page);
@@ -757,7 +756,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern void delete_from_page_cache(struct page *page);
 extern void __delete_from_page_cache(struct page *page, void *shadow);
-int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
+void replace_page_cache_page(struct page *old, struct page *new);
 void delete_from_page_cache_batch(struct address_space *mapping,
 				  struct pagevec *pvec);
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3f1f7ae0fbe9..32f665b1ee85 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -356,7 +356,7 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page,
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
-extern int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
+extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode);
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
@@ -408,7 +408,11 @@ 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);
+static inline unsigned long total_swapcache_pages(void)
+{
+	return global_node_page_state(NR_SWAPCACHE);
+}
+
 extern void show_swap_cache_info(void);
 extern int add_to_swap(struct page *page);
 extern void *get_shadow_from_swap_cache(swp_entry_t entry);
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index f65b1f6db22d..40845b0d5dad 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -115,7 +115,7 @@ DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node,
 	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
 );
 
-DECLARE_EVENT_CLASS(kmem_free,
+TRACE_EVENT(kfree,
 
 	TP_PROTO(unsigned long call_site, const void *ptr),
 
@@ -135,18 +135,26 @@ DECLARE_EVENT_CLASS(kmem_free,
 		  (void *)__entry->call_site, __entry->ptr)
 );
 
-DEFINE_EVENT(kmem_free, kfree,
+TRACE_EVENT(kmem_cache_free,
 
-	TP_PROTO(unsigned long call_site, const void *ptr),
+	TP_PROTO(unsigned long call_site, const void *ptr, const char *name),
 
-	TP_ARGS(call_site, ptr)
-);
+	TP_ARGS(call_site, ptr, name),
 
-DEFINE_EVENT(kmem_free, kmem_cache_free,
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	const char *,	name		)
+	),
 
-	TP_PROTO(unsigned long call_site, const void *ptr),
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->name		= name;
+	),
 
-	TP_ARGS(call_site, ptr)
+	TP_printk("call_site=%pS ptr=%p name=%s",
+		  (void *)__entry->call_site, __entry->ptr, __entry->name)
 );
 
 TRACE_EVENT(mm_page_free,
diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
index 8fd1babae761..e1735fe7c76a 100644
--- a/include/trace/events/pagemap.h
+++ b/include/trace/events/pagemap.h
@@ -27,24 +27,21 @@
 
 TRACE_EVENT(mm_lru_insertion,
 
-	TP_PROTO(
-		struct page *page,
-		int lru
-	),
+	TP_PROTO(struct page *page),
 
-	TP_ARGS(page, lru),
+	TP_ARGS(page),
 
 	TP_STRUCT__entry(
 		__field(struct page *,	page	)
 		__field(unsigned long,	pfn	)
-		__field(int,		lru	)
+		__field(enum lru_list,	lru	)
 		__field(unsigned long,	flags	)
 	),
 
 	TP_fast_assign(
 		__entry->page	= page;
 		__entry->pfn	= page_to_pfn(page);
-		__entry->lru	= lru;
+		__entry->lru	= page_lru(page);
 		__entry->flags	= trace_pagemap_flags(page);
 	),
 
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 3354774af61e..8948467b3992 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -28,12 +28,14 @@ enum {
 /* Flags for set_mempolicy */
 #define MPOL_F_STATIC_NODES	(1 << 15)
 #define MPOL_F_RELATIVE_NODES	(1 << 14)
+#define MPOL_F_NUMA_BALANCING	(1 << 13) /* Optimize with NUMA balancing if possible */
 
 /*
  * MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to
  * either set_mempolicy() or mbind().
  */
-#define MPOL_MODE_FLAGS	(MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES)
+#define MPOL_MODE_FLAGS							\
+	(MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES | MPOL_F_NUMA_BALANCING)
 
 /* Flags for get_mempolicy */
 #define MPOL_F_NODE	(1<<0)	/* return next IL mode instead of node mask */
diff --git a/init/Kconfig b/init/Kconfig
index c2a18f56e944..0bf5b340b80e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1861,20 +1861,6 @@ config SLUB_DEBUG
 	  SLUB sysfs support. /sys/slab will not exist and there will be
 	  no support for cache validation etc.
 
-config SLUB_MEMCG_SYSFS_ON
-	default n
-	bool "Enable memcg SLUB sysfs support by default" if EXPERT
-	depends on SLUB && SYSFS && MEMCG
-	help
-	  SLUB creates a directory under /sys/kernel/slab for each
-	  allocation cache to host info and debug files. If memory
-	  cgroup is enabled, each cache can have per memory cgroup
-	  caches. SLUB can create the same sysfs directories for these
-	  caches under /sys/kernel/slab/CACHE/cgroup but it can lead
-	  to a very high number of debug files being created. This is
-	  controlled by slub_memcg_sysfs boot parameter and this
-	  config option determines the parameter's default value.
-
 config COMPAT_BRK
 	bool "Disable heap randomization"
 	default y
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index f5fa4ba126bf..624ae1df7984 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -190,11 +190,11 @@ config KASAN_KUNIT_TEST
 	  kernel debugging features like KASAN.
 
 	  For more information on KUnit and unit tests in general, please refer
-	  to the KUnit documentation in Documentation/dev-tools/kunit
+	  to the KUnit documentation in Documentation/dev-tools/kunit.
 
-config TEST_KASAN_MODULE
+config KASAN_MODULE_TEST
 	tristate "KUnit-incompatible tests of KASAN bug detection capabilities"
-	depends on m && KASAN
+	depends on m && KASAN && !KASAN_HW_TAGS
 	help
 	  This is a part of the KASAN test suite that is incompatible with
 	  KUnit. Currently includes tests that do bad copy_from/to_user
diff --git a/lib/Makefile b/lib/Makefile
index fb7d946bb8c3..b5307d3eec1a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -66,7 +66,7 @@ obj-$(CONFIG_TEST_IDA) += test_ida.o
 obj-$(CONFIG_KASAN_KUNIT_TEST) += test_kasan.o
 CFLAGS_test_kasan.o += -fno-builtin
 CFLAGS_test_kasan.o += $(call cc-disable-warning, vla)
-obj-$(CONFIG_TEST_KASAN_MODULE) += test_kasan_module.o
+obj-$(CONFIG_KASAN_MODULE_TEST) += test_kasan_module.o
 CFLAGS_test_kasan_module.o += -fno-builtin
 obj-$(CONFIG_TEST_UBSAN) += test_ubsan.o
 CFLAGS_test_ubsan.o += $(call cc-disable-warning, vla)
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 2947274cc2d3..25576303897b 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -13,6 +13,7 @@
 #include <linux/mman.h>
 #include <linux/module.h>
 #include <linux/printk.h>
+#include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/uaccess.h>
@@ -28,10 +29,9 @@
 #define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_GRANULE_SIZE)
 
 /*
- * We assign some test results to these globals to make sure the tests
- * are not eliminated as dead code.
+ * Some tests use these global variables to store return values from function
+ * calls that could otherwise be eliminated by the compiler as dead code.
  */
-
 void *kasan_ptr_result;
 int kasan_int_result;
 
@@ -39,40 +39,81 @@ static struct kunit_resource resource;
 static struct kunit_kasan_expectation fail_data;
 static bool multishot;
 
+/*
+ * Temporarily enable multi-shot mode. Otherwise, KASAN would only report the
+ * first detected bug and panic the kernel if panic_on_warn is enabled. For
+ * hardware tag-based KASAN also allow tag checking to be reenabled for each
+ * test, see the comment for KUNIT_EXPECT_KASAN_FAIL().
+ */
 static int kasan_test_init(struct kunit *test)
 {
-	/*
-	 * Temporarily enable multi-shot mode and set panic_on_warn=0.
-	 * Otherwise, we'd only get a report for the first case.
-	 */
-	multishot = kasan_save_enable_multi_shot();
+	if (!kasan_enabled()) {
+		kunit_err(test, "can't run KASAN tests with KASAN disabled");
+		return -1;
+	}
 
+	multishot = kasan_save_enable_multi_shot();
+	kasan_set_tagging_report_once(false);
 	return 0;
 }
 
 static void kasan_test_exit(struct kunit *test)
 {
+	kasan_set_tagging_report_once(true);
 	kasan_restore_multi_shot(multishot);
 }
 
 /**
- * KUNIT_EXPECT_KASAN_FAIL() - Causes a test failure when the expression does
- * not cause a KASAN error. This uses a KUnit resource named "kasan_data." Do
- * Do not use this name for a KUnit resource outside here.
+ * KUNIT_EXPECT_KASAN_FAIL() - check that the executed expression produces a
+ * KASAN report; causes a test failure otherwise. This relies on a KUnit
+ * resource named "kasan_data". Do not use this name for KUnit resources
+ * outside of KASAN tests.
  *
+ * For hardware tag-based KASAN, when a tag fault happens, tag checking is
+ * normally auto-disabled. When this happens, this test handler reenables
+ * tag checking. As tag checking can be only disabled or enabled per CPU, this
+ * handler disables migration (preemption).
+ *
+ * Since the compiler doesn't see that the expression can change the fail_data
+ * fields, it can reorder or optimize away the accesses to those fields.
+ * Use READ/WRITE_ONCE() for the accesses and compiler barriers around the
+ * expression to prevent that.
  */
-#define KUNIT_EXPECT_KASAN_FAIL(test, condition) do { \
-	fail_data.report_expected = true; \
-	fail_data.report_found = false; \
-	kunit_add_named_resource(test, \
-				NULL, \
-				NULL, \
-				&resource, \
-				"kasan_data", &fail_data); \
-	condition; \
-	KUNIT_EXPECT_EQ(test, \
-			fail_data.report_expected, \
-			fail_data.report_found); \
+#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do {		\
+	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS))			\
+		migrate_disable();				\
+	WRITE_ONCE(fail_data.report_expected, true);		\
+	WRITE_ONCE(fail_data.report_found, false);		\
+	kunit_add_named_resource(test,				\
+				NULL,				\
+				NULL,				\
+				&resource,			\
+				"kasan_data", &fail_data);	\
+	barrier();						\
+	expression;						\
+	barrier();						\
+	KUNIT_EXPECT_EQ(test,					\
+			READ_ONCE(fail_data.report_expected),	\
+			READ_ONCE(fail_data.report_found));	\
+	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) {			\
+		if (READ_ONCE(fail_data.report_found))		\
+			kasan_enable_tagging();			\
+		migrate_enable();				\
+	}							\
+} while (0)
+
+#define KASAN_TEST_NEEDS_CONFIG_ON(test, config) do {			\
+	if (!IS_ENABLED(config)) {					\
+		kunit_info((test), "skipping, " #config " required");	\
+		return;							\
+	}								\
+} while (0)
+
+#define KASAN_TEST_NEEDS_CONFIG_OFF(test, config) do {			\
+	if (IS_ENABLED(config)) {					\
+		kunit_info((test), "skipping, " #config " enabled");	\
+		return;							\
+	}								\
 } while (0)
 
 static void kmalloc_oob_right(struct kunit *test)
@@ -111,23 +152,24 @@ static void kmalloc_node_oob_right(struct kunit *test)
 	kfree(ptr);
 }
 
+/*
+ * These kmalloc_pagealloc_* tests try allocating a memory chunk that doesn't
+ * fit into a slab cache and therefore is allocated via the page allocator
+ * fallback. Since this kind of fallback is only implemented for SLUB, these
+ * tests are limited to that allocator.
+ */
 static void kmalloc_pagealloc_oob_right(struct kunit *test)
 {
 	char *ptr;
 	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
 
-	if (!IS_ENABLED(CONFIG_SLUB)) {
-		kunit_info(test, "CONFIG_SLUB is not enabled.");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
 
-	/* Allocate a chunk that does not fit into a SLUB cache to trigger
-	 * the page allocator fallback.
-	 */
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
 	KUNIT_EXPECT_KASAN_FAIL(test, ptr[size + OOB_TAG_OFF] = 0);
+
 	kfree(ptr);
 }
 
@@ -136,15 +178,12 @@ static void kmalloc_pagealloc_uaf(struct kunit *test)
 	char *ptr;
 	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
 
-	if (!IS_ENABLED(CONFIG_SLUB)) {
-		kunit_info(test, "CONFIG_SLUB is not enabled.");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
-
 	kfree(ptr);
+
 	KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] = 0);
 }
 
@@ -153,10 +192,7 @@ static void kmalloc_pagealloc_invalid_free(struct kunit *test)
 	char *ptr;
 	size_t size = KMALLOC_MAX_CACHE_SIZE + 10;
 
-	if (!IS_ENABLED(CONFIG_SLUB)) {
-		kunit_info(test, "CONFIG_SLUB is not enabled.");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_SLUB);
 
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
@@ -164,11 +200,49 @@ static void kmalloc_pagealloc_invalid_free(struct kunit *test)
 	KUNIT_EXPECT_KASAN_FAIL(test, kfree(ptr + 1));
 }
 
+static void pagealloc_oob_right(struct kunit *test)
+{
+	char *ptr;
+	struct page *pages;
+	size_t order = 4;
+	size_t size = (1UL << (PAGE_SHIFT + order));
+
+	/*
+	 * With generic KASAN page allocations have no redzones, thus
+	 * out-of-bounds detection is not guaranteed.
+	 * See https://bugzilla.kernel.org/show_bug.cgi?id=210503.
+	 */
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_GENERIC);
+
+	pages = alloc_pages(GFP_KERNEL, order);
+	ptr = page_address(pages);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+
+	KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 0);
+	free_pages((unsigned long)ptr, order);
+}
+
+static void pagealloc_uaf(struct kunit *test)
+{
+	char *ptr;
+	struct page *pages;
+	size_t order = 4;
+
+	pages = alloc_pages(GFP_KERNEL, order);
+	ptr = page_address(pages);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+	free_pages((unsigned long)ptr, order);
+
+	KUNIT_EXPECT_KASAN_FAIL(test, ptr[0] = 0);
+}
+
 static void kmalloc_large_oob_right(struct kunit *test)
 {
 	char *ptr;
 	size_t size = KMALLOC_MAX_CACHE_SIZE - 256;
-	/* Allocate a chunk that is large enough, but still fits into a slab
+
+	/*
+	 * Allocate a chunk that is large enough, but still fits into a slab
 	 * and does not trigger the page allocator fallback in SLUB.
 	 */
 	ptr = kmalloc(size, GFP_KERNEL);
@@ -217,10 +291,7 @@ static void kmalloc_oob_16(struct kunit *test)
 	} *ptr1, *ptr2;
 
 	/* This test is specifically crafted for the generic mode. */
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
-		kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
 
 	ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
@@ -355,7 +426,9 @@ static void kmalloc_uaf2(struct kunit *test)
 {
 	char *ptr1, *ptr2;
 	size_t size = 43;
+	int counter = 0;
 
+again:
 	ptr1 = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
 
@@ -364,6 +437,15 @@ static void kmalloc_uaf2(struct kunit *test)
 	ptr2 = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
 
+	/*
+	 * For tag-based KASAN ptr1 and ptr2 tags might happen to be the same.
+	 * Allow up to 16 attempts at generating different tags.
+	 */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC) && ptr1 == ptr2 && counter++ < 16) {
+		kfree(ptr2);
+		goto again;
+	}
+
 	KUNIT_EXPECT_KASAN_FAIL(test, ptr1[40] = 'x');
 	KUNIT_EXPECT_PTR_NE(test, ptr1, ptr2);
 
@@ -402,10 +484,11 @@ static void kmem_cache_oob(struct kunit *test)
 {
 	char *p;
 	size_t size = 200;
-	struct kmem_cache *cache = kmem_cache_create("test_cache",
-						size, 0,
-						0, NULL);
+	struct kmem_cache *cache;
+
+	cache = kmem_cache_create("test_cache", size, 0, 0, NULL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
+
 	p = kmem_cache_alloc(cache, GFP_KERNEL);
 	if (!p) {
 		kunit_err(test, "Allocation failed: %s\n", __func__);
@@ -414,11 +497,12 @@ static void kmem_cache_oob(struct kunit *test)
 	}
 
 	KUNIT_EXPECT_KASAN_FAIL(test, *p = p[size + OOB_TAG_OFF]);
+
 	kmem_cache_free(cache, p);
 	kmem_cache_destroy(cache);
 }
 
-static void memcg_accounted_kmem_cache(struct kunit *test)
+static void kmem_cache_accounted(struct kunit *test)
 {
 	int i;
 	char *p;
@@ -445,6 +529,31 @@ free_cache:
 	kmem_cache_destroy(cache);
 }
 
+static void kmem_cache_bulk(struct kunit *test)
+{
+	struct kmem_cache *cache;
+	size_t size = 200;
+	char *p[10];
+	bool ret;
+	int i;
+
+	cache = kmem_cache_create("test_cache", size, 0, 0, NULL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache);
+
+	ret = kmem_cache_alloc_bulk(cache, GFP_KERNEL, ARRAY_SIZE(p), (void **)&p);
+	if (!ret) {
+		kunit_err(test, "Allocation failed: %s\n", __func__);
+		kmem_cache_destroy(cache);
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(p); i++)
+		p[i][0] = p[i][size - 1] = 42;
+
+	kmem_cache_free_bulk(cache, ARRAY_SIZE(p), (void **)&p);
+	kmem_cache_destroy(cache);
+}
+
 static char global_array[10];
 
 static void kasan_global_oob(struct kunit *test)
@@ -453,14 +562,12 @@ static void kasan_global_oob(struct kunit *test)
 	char *p = &global_array[ARRAY_SIZE(global_array) + i];
 
 	/* Only generic mode instruments globals. */
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
-		kunit_info(test, "CONFIG_KASAN_GENERIC required");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
 
 	KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
 }
 
+/* Check that ksize() makes the whole object accessible. */
 static void ksize_unpoisons_memory(struct kunit *test)
 {
 	char *ptr;
@@ -469,11 +576,32 @@ static void ksize_unpoisons_memory(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	real_size = ksize(ptr);
-	/* This access doesn't trigger an error. */
+
+	/* This access shouldn't trigger a KASAN report. */
 	ptr[size] = 'x';
-	/* This one does. */
+
+	/* This one must. */
 	KUNIT_EXPECT_KASAN_FAIL(test, ptr[real_size] = 'y');
+
+	kfree(ptr);
+}
+
+/*
+ * Check that a use-after-free is detected by ksize() and via normal accesses
+ * after it.
+ */
+static void ksize_uaf(struct kunit *test)
+{
+	char *ptr;
+	int size = 128 - KASAN_GRANULE_SIZE;
+
+	ptr = kmalloc(size, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	kfree(ptr);
+
+	KUNIT_EXPECT_KASAN_FAIL(test, ksize(ptr));
+	KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = *ptr);
+	KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = *(ptr + size));
 }
 
 static void kasan_stack_oob(struct kunit *test)
@@ -482,10 +610,7 @@ static void kasan_stack_oob(struct kunit *test)
 	volatile int i = OOB_TAG_OFF;
 	char *p = &stack_array[ARRAY_SIZE(stack_array) + i];
 
-	if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
-		kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_STACK);
 
 	KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
 }
@@ -497,15 +622,8 @@ static void kasan_alloca_oob_left(struct kunit *test)
 	char *p = alloca_array - 1;
 
 	/* Only generic mode instruments dynamic allocas. */
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
-		kunit_info(test, "CONFIG_KASAN_GENERIC required");
-		return;
-	}
-
-	if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
-		kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_STACK);
 
 	KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
 }
@@ -517,15 +635,8 @@ static void kasan_alloca_oob_right(struct kunit *test)
 	char *p = alloca_array + i;
 
 	/* Only generic mode instruments dynamic allocas. */
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
-		kunit_info(test, "CONFIG_KASAN_GENERIC required");
-		return;
-	}
-
-	if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
-		kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_STACK);
 
 	KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
 }
@@ -568,7 +679,7 @@ static void kmem_cache_invalid_free(struct kunit *test)
 		return;
 	}
 
-	/* Trigger invalid free, the object doesn't get freed */
+	/* Trigger invalid free, the object doesn't get freed. */
 	KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_free(cache, p + 1));
 
 	/*
@@ -585,12 +696,11 @@ static void kasan_memchr(struct kunit *test)
 	char *ptr;
 	size_t size = 24;
 
-	/* See https://bugzilla.kernel.org/show_bug.cgi?id=206337 */
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
-		kunit_info(test,
-			"str* functions are not instrumented with CONFIG_AMD_MEM_ENCRYPT");
-		return;
-	}
+	/*
+	 * str* functions are not instrumented with CONFIG_AMD_MEM_ENCRYPT.
+	 * See https://bugzilla.kernel.org/show_bug.cgi?id=206337 for details.
+	 */
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_AMD_MEM_ENCRYPT);
 
 	if (OOB_TAG_OFF)
 		size = round_up(size, OOB_TAG_OFF);
@@ -610,12 +720,11 @@ static void kasan_memcmp(struct kunit *test)
 	size_t size = 24;
 	int arr[9];
 
-	/* See https://bugzilla.kernel.org/show_bug.cgi?id=206337 */
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
-		kunit_info(test,
-			"str* functions are not instrumented with CONFIG_AMD_MEM_ENCRYPT");
-		return;
-	}
+	/*
+	 * str* functions are not instrumented with CONFIG_AMD_MEM_ENCRYPT.
+	 * See https://bugzilla.kernel.org/show_bug.cgi?id=206337 for details.
+	 */
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_AMD_MEM_ENCRYPT);
 
 	if (OOB_TAG_OFF)
 		size = round_up(size, OOB_TAG_OFF);
@@ -634,12 +743,11 @@ static void kasan_strings(struct kunit *test)
 	char *ptr;
 	size_t size = 24;
 
-	/* See https://bugzilla.kernel.org/show_bug.cgi?id=206337 */
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
-		kunit_info(test,
-			"str* functions are not instrumented with CONFIG_AMD_MEM_ENCRYPT");
-		return;
-	}
+	/*
+	 * str* functions are not instrumented with CONFIG_AMD_MEM_ENCRYPT.
+	 * See https://bugzilla.kernel.org/show_bug.cgi?id=206337 for details.
+	 */
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_AMD_MEM_ENCRYPT);
 
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
@@ -700,13 +808,10 @@ static void kasan_bitops_generic(struct kunit *test)
 	long *bits;
 
 	/* This test is specifically crafted for the generic mode. */
-	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
-		kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
 
 	/*
-	 * Allocate 1 more byte, which causes kzalloc to round up to 16-bytes;
+	 * Allocate 1 more byte, which causes kzalloc to round up to 16 bytes;
 	 * this way we do not actually corrupt other memory.
 	 */
 	bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
@@ -731,19 +836,16 @@ static void kasan_bitops_tags(struct kunit *test)
 {
 	long *bits;
 
-	/* This test is specifically crafted for the tag-based mode. */
-	if (IS_ENABLED(CONFIG_KASAN_GENERIC)) {
-		kunit_info(test, "CONFIG_KASAN_SW_TAGS required\n");
-		return;
-	}
+	/* This test is specifically crafted for tag-based modes. */
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_GENERIC);
 
-	/* Allocation size will be rounded to up granule size, which is 16. */
-	bits = kzalloc(sizeof(*bits), GFP_KERNEL);
+	/* kmalloc-64 cache will be used and the last 16 bytes will be the redzone. */
+	bits = kzalloc(48, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
 
-	/* Do the accesses past the 16 allocated bytes. */
-	kasan_bitops_modify(test, BITS_PER_LONG, &bits[1]);
-	kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, &bits[1]);
+	/* Do the accesses past the 48 allocated bytes, but within the redone. */
+	kasan_bitops_modify(test, BITS_PER_LONG, (void *)bits + 48);
+	kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, (void *)bits + 48);
 
 	kfree(bits);
 }
@@ -764,10 +866,7 @@ static void vmalloc_oob(struct kunit *test)
 {
 	void *area;
 
-	if (!IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
-		kunit_info(test, "CONFIG_KASAN_VMALLOC is not enabled.");
-		return;
-	}
+	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_VMALLOC);
 
 	/*
 	 * We have to be careful not to hit the guard page.
@@ -780,6 +879,94 @@ static void vmalloc_oob(struct kunit *test)
 	vfree(area);
 }
 
+/*
+ * Check that the assigned pointer tag falls within the [KASAN_TAG_MIN,
+ * KASAN_TAG_KERNEL) range (note: excluding the match-all tag) for tag-based
+ * modes.
+ */
+static void match_all_not_assigned(struct kunit *test)
+{
+	char *ptr;
+	struct page *pages;
+	int i, size, order;
+
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_GENERIC);
+
+	for (i = 0; i < 256; i++) {
+		size = (get_random_int() % 1024) + 1;
+		ptr = kmalloc(size, GFP_KERNEL);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+		KUNIT_EXPECT_GE(test, (u8)get_tag(ptr), (u8)KASAN_TAG_MIN);
+		KUNIT_EXPECT_LT(test, (u8)get_tag(ptr), (u8)KASAN_TAG_KERNEL);
+		kfree(ptr);
+	}
+
+	for (i = 0; i < 256; i++) {
+		order = (get_random_int() % 4) + 1;
+		pages = alloc_pages(GFP_KERNEL, order);
+		ptr = page_address(pages);
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+		KUNIT_EXPECT_GE(test, (u8)get_tag(ptr), (u8)KASAN_TAG_MIN);
+		KUNIT_EXPECT_LT(test, (u8)get_tag(ptr), (u8)KASAN_TAG_KERNEL);
+		free_pages((unsigned long)ptr, order);
+	}
+}
+
+/* Check that 0xff works as a match-all pointer tag for tag-based modes. */
+static void match_all_ptr_tag(struct kunit *test)
+{
+	char *ptr;
+	u8 tag;
+
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_GENERIC);
+
+	ptr = kmalloc(128, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+
+	/* Backup the assigned tag. */
+	tag = get_tag(ptr);
+	KUNIT_EXPECT_NE(test, tag, (u8)KASAN_TAG_KERNEL);
+
+	/* Reset the tag to 0xff.*/
+	ptr = set_tag(ptr, KASAN_TAG_KERNEL);
+
+	/* This access shouldn't trigger a KASAN report. */
+	*ptr = 0;
+
+	/* Recover the pointer tag and free. */
+	ptr = set_tag(ptr, tag);
+	kfree(ptr);
+}
+
+/* Check that there are no match-all memory tags for tag-based modes. */
+static void match_all_mem_tag(struct kunit *test)
+{
+	char *ptr;
+	int tag;
+
+	KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_GENERIC);
+
+	ptr = kmalloc(128, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+	KUNIT_EXPECT_NE(test, (u8)get_tag(ptr), (u8)KASAN_TAG_KERNEL);
+
+	/* For each possible tag value not matching the pointer tag. */
+	for (tag = KASAN_TAG_MIN; tag <= KASAN_TAG_KERNEL; tag++) {
+		if (tag == get_tag(ptr))
+			continue;
+
+		/* Mark the first memory granule with the chosen memory tag. */
+		kasan_poison(ptr, KASAN_GRANULE_SIZE, (u8)tag);
+
+		/* This access must cause a KASAN report. */
+		KUNIT_EXPECT_KASAN_FAIL(test, *ptr = 0);
+	}
+
+	/* Recover the memory tag and free. */
+	kasan_poison(ptr, KASAN_GRANULE_SIZE, get_tag(ptr));
+	kfree(ptr);
+}
+
 static struct kunit_case kasan_kunit_test_cases[] = {
 	KUNIT_CASE(kmalloc_oob_right),
 	KUNIT_CASE(kmalloc_oob_left),
@@ -787,6 +974,8 @@ static struct kunit_case kasan_kunit_test_cases[] = {
 	KUNIT_CASE(kmalloc_pagealloc_oob_right),
 	KUNIT_CASE(kmalloc_pagealloc_uaf),
 	KUNIT_CASE(kmalloc_pagealloc_invalid_free),
+	KUNIT_CASE(pagealloc_oob_right),
+	KUNIT_CASE(pagealloc_uaf),
 	KUNIT_CASE(kmalloc_large_oob_right),
 	KUNIT_CASE(kmalloc_oob_krealloc_more),
 	KUNIT_CASE(kmalloc_oob_krealloc_less),
@@ -804,12 +993,14 @@ static struct kunit_case kasan_kunit_test_cases[] = {
 	KUNIT_CASE(kfree_via_page),
 	KUNIT_CASE(kfree_via_phys),
 	KUNIT_CASE(kmem_cache_oob),
-	KUNIT_CASE(memcg_accounted_kmem_cache),
+	KUNIT_CASE(kmem_cache_accounted),
+	KUNIT_CASE(kmem_cache_bulk),
 	KUNIT_CASE(kasan_global_oob),
 	KUNIT_CASE(kasan_stack_oob),
 	KUNIT_CASE(kasan_alloca_oob_left),
 	KUNIT_CASE(kasan_alloca_oob_right),
 	KUNIT_CASE(ksize_unpoisons_memory),
+	KUNIT_CASE(ksize_uaf),
 	KUNIT_CASE(kmem_cache_double_free),
 	KUNIT_CASE(kmem_cache_invalid_free),
 	KUNIT_CASE(kasan_memchr),
@@ -819,6 +1010,9 @@ static struct kunit_case kasan_kunit_test_cases[] = {
 	KUNIT_CASE(kasan_bitops_tags),
 	KUNIT_CASE(kmalloc_double_kzfree),
 	KUNIT_CASE(vmalloc_oob),
+	KUNIT_CASE(match_all_not_assigned),
+	KUNIT_CASE(match_all_ptr_tag),
+	KUNIT_CASE(match_all_mem_tag),
 	{}
 };
 
diff --git a/lib/test_kasan_module.c b/lib/test_kasan_module.c
index 3b4cc77992d2..eee017ff8980 100644
--- a/lib/test_kasan_module.c
+++ b/lib/test_kasan_module.c
@@ -123,8 +123,9 @@ static noinline void __init kasan_workqueue_uaf(void)
 static int __init test_kasan_module_init(void)
 {
 	/*
-	 * Temporarily enable multi-shot mode. Otherwise, we'd only get a
-	 * report for the first case.
+	 * Temporarily enable multi-shot mode. Otherwise, KASAN would only
+	 * report the first detected bug and panic the kernel if panic_on_warn
+	 * is enabled.
 	 */
 	bool multishot = kasan_save_enable_multi_shot();
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index e33797579338..eca555f658d9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -32,6 +32,8 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -69,7 +71,6 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	global_dirty_limits(&background_thresh, &dirty_thresh);
 	wb_thresh = wb_calc_thresh(wb, dirty_thresh);
 
-#define K(x) ((x) << (PAGE_SHIFT - 10))
 	seq_printf(m,
 		   "BdiWriteback:       %10lu kB\n"
 		   "BdiReclaimable:     %10lu kB\n"
@@ -98,7 +99,6 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   nr_more_io,
 		   nr_dirty_time,
 		   !list_empty(&bdi->bdi_list), bdi->wb.state);
-#undef K
 
 	return 0;
 }
@@ -146,8 +146,6 @@ static ssize_t read_ahead_kb_store(struct device *dev,
 	return count;
 }
 
-#define K(pages) ((pages) << (PAGE_SHIFT - 10))
-
 #define BDI_SHOW(name, expr)						\
 static ssize_t name##_show(struct device *dev,				\
 			   struct device_attribute *attr, char *buf)	\
diff --git a/mm/compaction.c b/mm/compaction.c
index 190ccdaa6c19..e04f4476e68e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -137,7 +137,6 @@ EXPORT_SYMBOL(__SetPageMovable);
 
 void __ClearPageMovable(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageMovable(page), page);
 	/*
 	 * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE
@@ -988,14 +987,13 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (unlikely(!get_page_unless_zero(page)))
 			goto isolate_fail;
 
-		if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
+		if (!__isolate_lru_page_prepare(page, isolate_mode))
 			goto isolate_fail_put;
 
 		/* Try isolate the page */
 		if (!TestClearPageLRU(page))
 			goto isolate_fail_put;
 
-		rcu_read_lock();
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		/* If we already hold the lock, we can skip some rechecking */
@@ -1005,7 +1003,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 			compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
 			locked = lruvec;
-			rcu_read_unlock();
 
 			lruvec_memcg_debug(lruvec, page);
 
@@ -1026,15 +1023,14 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 				SetPageLRU(page);
 				goto isolate_fail_put;
 			}
-		} else
-			rcu_read_unlock();
+		}
 
 		/* The whole page is taken off the LRU; skip the tail pages. */
 		if (PageCompound(page))
 			low_pfn += compound_nr(page) - 1;
 
 		/* Successfully isolated */
-		del_page_from_lru_list(page, lruvec, page_lru(page));
+		del_page_from_lru_list(page, lruvec);
 		mod_node_page_state(page_pgdat(page),
 				NR_ISOLATED_ANON + page_is_file_lru(page),
 				thp_nr_pages(page));
@@ -1288,7 +1284,7 @@ static void
 fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long nr_isolated)
 {
 	unsigned long start_pfn, end_pfn;
-	struct page *page = pfn_to_page(pfn);
+	struct page *page;
 
 	/* Do not search around if there are enough pages already */
 	if (cc->nr_freepages >= cc->nr_migratepages)
@@ -1299,8 +1295,12 @@ fast_isolate_around(struct compact_control *cc, unsigned long pfn, unsigned long
 		return;
 
 	/* Pageblock boundaries */
-	start_pfn = pageblock_start_pfn(pfn);
-	end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone)) - 1;
+	start_pfn = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn);
+	end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone));
+
+	page = pageblock_pfn_to_page(start_pfn, end_pfn, cc->zone);
+	if (!page)
+		return;
 
 	/* Scan before */
 	if (start_pfn != pfn) {
@@ -1402,7 +1402,8 @@ fast_isolate_freepages(struct compact_control *cc)
 			pfn = page_to_pfn(freepage);
 
 			if (pfn >= highest)
-				highest = pageblock_start_pfn(pfn);
+				highest = max(pageblock_start_pfn(pfn),
+					      cc->zone->zone_start_pfn);
 
 			if (pfn >= low_pfn) {
 				cc->fast_search_fail = 0;
@@ -1472,7 +1473,8 @@ fast_isolate_freepages(struct compact_control *cc)
 			} else {
 				if (cc->direct_compaction && pfn_valid(min_pfn)) {
 					page = pageblock_pfn_to_page(min_pfn,
-						pageblock_end_pfn(min_pfn),
+						min(pageblock_end_pfn(min_pfn),
+						    zone_end_pfn(cc->zone)),
 						cc->zone);
 					cc->free_pfn = min_pfn;
 				}
@@ -1702,6 +1704,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 	unsigned long pfn = cc->migrate_pfn;
 	unsigned long high_pfn;
 	int order;
+	bool found_block = false;
 
 	/* Skip hints are relied on to avoid repeats on the fast search */
 	if (cc->ignore_skip_hint)
@@ -1744,7 +1747,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 	high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance);
 
 	for (order = cc->order - 1;
-	     order >= PAGE_ALLOC_COSTLY_ORDER && pfn == cc->migrate_pfn && nr_scanned < limit;
+	     order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit;
 	     order--) {
 		struct free_area *area = &cc->zone->free_area[order];
 		struct list_head *freelist;
@@ -1759,7 +1762,11 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 		list_for_each_entry(freepage, freelist, lru) {
 			unsigned long free_pfn;
 
-			nr_scanned++;
+			if (nr_scanned++ >= limit) {
+				move_freelist_tail(freelist, freepage);
+				break;
+			}
+
 			free_pfn = page_to_pfn(freepage);
 			if (free_pfn < high_pfn) {
 				/*
@@ -1768,12 +1775,8 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 				 * the list assumes an entry is deleted, not
 				 * reordered.
 				 */
-				if (get_pageblock_skip(freepage)) {
-					if (list_is_last(freelist, &freepage->lru))
-						break;
-
+				if (get_pageblock_skip(freepage))
 					continue;
-				}
 
 				/* Reorder to so a future search skips recent pages */
 				move_freelist_tail(freelist, freepage);
@@ -1781,15 +1784,10 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 				update_fast_start_pfn(cc, free_pfn);
 				pfn = pageblock_start_pfn(free_pfn);
 				cc->fast_search_fail = 0;
+				found_block = true;
 				set_pageblock_skip(freepage);
 				break;
 			}
-
-			if (nr_scanned >= limit) {
-				cc->fast_search_fail++;
-				move_freelist_tail(freelist, freepage);
-				break;
-			}
 		}
 		spin_unlock_irqrestore(&cc->zone->lock, flags);
 	}
@@ -1800,9 +1798,10 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
 	 * If fast scanning failed then use a cached entry for a page block
 	 * that had free pages as the basis for starting a linear scan.
 	 */
-	if (pfn == cc->migrate_pfn)
+	if (!found_block) {
+		cc->fast_search_fail++;
 		pfn = reinit_migrate_pfn(cc);
-
+	}
 	return pfn;
 }
 
@@ -1926,20 +1925,28 @@ static bool kswapd_is_running(pg_data_t *pgdat)
 
 /*
  * A zone's fragmentation score is the external fragmentation wrt to the
- * COMPACTION_HPAGE_ORDER scaled by the zone's size. It returns a value
- * in the range [0, 100].
+ * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100].
+ */
+static unsigned int fragmentation_score_zone(struct zone *zone)
+{
+	return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+}
+
+/*
+ * A weighted zone's fragmentation score is the external fragmentation
+ * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It
+ * returns a value in the range [0, 100].
  *
  * The scaling factor ensures that proactive compaction focuses on larger
  * zones like ZONE_NORMAL, rather than smaller, specialized zones like
  * ZONE_DMA32. For smaller zones, the score value remains close to zero,
  * and thus never exceeds the high threshold for proactive compaction.
  */
-static unsigned int fragmentation_score_zone(struct zone *zone)
+static unsigned int fragmentation_score_zone_weighted(struct zone *zone)
 {
 	unsigned long score;
 
-	score = zone->present_pages *
-			extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+	score = zone->present_pages * fragmentation_score_zone(zone);
 	return div64_ul(score, zone->zone_pgdat->node_present_pages + 1);
 }
 
@@ -1959,7 +1966,7 @@ static unsigned int fragmentation_score_node(pg_data_t *pgdat)
 		struct zone *zone;
 
 		zone = &pgdat->node_zones[zoneid];
-		score += fragmentation_score_zone(zone);
+		score += fragmentation_score_zone_weighted(zone);
 	}
 
 	return score;
diff --git a/mm/debug.c b/mm/debug.c
index 8a40b3fefbeb..0bdda8407f71 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -110,6 +110,11 @@ void __dump_page(struct page *page, const char *reason)
 					head_compound_mapcount(head));
 		}
 	}
+
+#ifdef CONFIG_MEMCG
+	if (head->memcg_data)
+		pr_warn("memcg:%lx\n", head->memcg_data);
+#endif
 	if (PageKsm(page))
 		type = "ksm ";
 	else if (PageAnon(page))
@@ -180,11 +185,6 @@ hex_only:
 
 	if (reason)
 		pr_warn("page dumped because: %s\n", reason);
-
-#ifdef CONFIG_MEMCG
-	if (!page_poisoned && page->memcg_data)
-		pr_warn("pages's memcg:%lx\n", page->memcg_data);
-#endif
 }
 
 void dump_page(struct page *page, const char *reason)
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index c05d9dcf7891..a9bd6ce1ba02 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -58,11 +58,23 @@
 #define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK)
 #define RANDOM_NZVALUE	GENMASK(7, 0)
 
-static void __init pte_basic_tests(unsigned long pfn, pgprot_t prot)
+static void __init pte_basic_tests(unsigned long pfn, int idx)
 {
+	pgprot_t prot = protection_map[idx];
 	pte_t pte = pfn_pte(pfn, prot);
+	unsigned long val = idx, *ptr = &val;
+
+	pr_debug("Validating PTE basic (%pGv)\n", ptr);
+
+	/*
+	 * This test needs to be executed after the given page table entry
+	 * is created with pfn_pte() to make sure that protection_map[idx]
+	 * does not have the dirty bit enabled from the beginning. This is
+	 * important for platforms like arm64 where (!PTE_RDONLY) indicate
+	 * dirty bit being set.
+	 */
+	WARN_ON(pte_dirty(pte_wrprotect(pte)));
 
-	pr_debug("Validating PTE basic\n");
 	WARN_ON(!pte_same(pte, pte));
 	WARN_ON(!pte_young(pte_mkyoung(pte_mkold(pte))));
 	WARN_ON(!pte_dirty(pte_mkdirty(pte_mkclean(pte))));
@@ -70,6 +82,8 @@ static void __init pte_basic_tests(unsigned long pfn, pgprot_t prot)
 	WARN_ON(pte_young(pte_mkold(pte_mkyoung(pte))));
 	WARN_ON(pte_dirty(pte_mkclean(pte_mkdirty(pte))));
 	WARN_ON(pte_write(pte_wrprotect(pte_mkwrite(pte))));
+	WARN_ON(pte_dirty(pte_wrprotect(pte_mkclean(pte))));
+	WARN_ON(!pte_dirty(pte_wrprotect(pte_mkdirty(pte))));
 }
 
 static void __init pte_advanced_tests(struct mm_struct *mm,
@@ -129,14 +143,27 @@ static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot)
+static void __init pmd_basic_tests(unsigned long pfn, int idx)
 {
+	pgprot_t prot = protection_map[idx];
 	pmd_t pmd = pfn_pmd(pfn, prot);
+	unsigned long val = idx, *ptr = &val;
 
 	if (!has_transparent_hugepage())
 		return;
 
-	pr_debug("Validating PMD basic\n");
+	pr_debug("Validating PMD basic (%pGv)\n", ptr);
+
+	/*
+	 * This test needs to be executed after the given page table entry
+	 * is created with pfn_pmd() to make sure that protection_map[idx]
+	 * does not have the dirty bit enabled from the beginning. This is
+	 * important for platforms like arm64 where (!PTE_RDONLY) indicate
+	 * dirty bit being set.
+	 */
+	WARN_ON(pmd_dirty(pmd_wrprotect(pmd)));
+
+
 	WARN_ON(!pmd_same(pmd, pmd));
 	WARN_ON(!pmd_young(pmd_mkyoung(pmd_mkold(pmd))));
 	WARN_ON(!pmd_dirty(pmd_mkdirty(pmd_mkclean(pmd))));
@@ -144,6 +171,8 @@ static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot)
 	WARN_ON(pmd_young(pmd_mkold(pmd_mkyoung(pmd))));
 	WARN_ON(pmd_dirty(pmd_mkclean(pmd_mkdirty(pmd))));
 	WARN_ON(pmd_write(pmd_wrprotect(pmd_mkwrite(pmd))));
+	WARN_ON(pmd_dirty(pmd_wrprotect(pmd_mkclean(pmd))));
+	WARN_ON(!pmd_dirty(pmd_wrprotect(pmd_mkdirty(pmd))));
 	/*
 	 * A huge page does not point to next level page table
 	 * entry. Hence this must qualify as pmd_bad().
@@ -249,19 +278,35 @@ static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot)
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot)
+static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx)
 {
+	pgprot_t prot = protection_map[idx];
 	pud_t pud = pfn_pud(pfn, prot);
+	unsigned long val = idx, *ptr = &val;
 
 	if (!has_transparent_hugepage())
 		return;
 
-	pr_debug("Validating PUD basic\n");
+	pr_debug("Validating PUD basic (%pGv)\n", ptr);
+
+	/*
+	 * This test needs to be executed after the given page table entry
+	 * is created with pfn_pud() to make sure that protection_map[idx]
+	 * does not have the dirty bit enabled from the beginning. This is
+	 * important for platforms like arm64 where (!PTE_RDONLY) indicate
+	 * dirty bit being set.
+	 */
+	WARN_ON(pud_dirty(pud_wrprotect(pud)));
+
 	WARN_ON(!pud_same(pud, pud));
 	WARN_ON(!pud_young(pud_mkyoung(pud_mkold(pud))));
+	WARN_ON(!pud_dirty(pud_mkdirty(pud_mkclean(pud))));
+	WARN_ON(pud_dirty(pud_mkclean(pud_mkdirty(pud))));
 	WARN_ON(!pud_write(pud_mkwrite(pud_wrprotect(pud))));
 	WARN_ON(pud_write(pud_wrprotect(pud_mkwrite(pud))));
 	WARN_ON(pud_young(pud_mkold(pud_mkyoung(pud))));
+	WARN_ON(pud_dirty(pud_wrprotect(pud_mkclean(pud))));
+	WARN_ON(!pud_dirty(pud_wrprotect(pud_mkdirty(pud))));
 
 	if (mm_pmd_folded(mm))
 		return;
@@ -359,7 +404,7 @@ static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot)
 #endif /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
 
 #else  /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { }
 static void __init pud_advanced_tests(struct mm_struct *mm,
 				      struct vm_area_struct *vma, pud_t *pudp,
 				      unsigned long pfn, unsigned long vaddr,
@@ -372,8 +417,8 @@ static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot)
 }
 #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 #else  /* !CONFIG_TRANSPARENT_HUGEPAGE */
-static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot) { }
-static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot) { }
+static void __init pmd_basic_tests(unsigned long pfn, int idx) { }
+static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { }
 static void __init pmd_advanced_tests(struct mm_struct *mm,
 				      struct vm_area_struct *vma, pmd_t *pmdp,
 				      unsigned long pfn, unsigned long vaddr,
@@ -899,6 +944,7 @@ static int __init debug_vm_pgtable(void)
 	unsigned long vaddr, pte_aligned, pmd_aligned;
 	unsigned long pud_aligned, p4d_aligned, pgd_aligned;
 	spinlock_t *ptl = NULL;
+	int idx;
 
 	pr_info("Validating architecture page table helpers\n");
 	prot = vm_get_page_prot(VMFLAGS);
@@ -963,9 +1009,25 @@ static int __init debug_vm_pgtable(void)
 	saved_pmdp = pmd_offset(pudp, 0UL);
 	saved_ptep = pmd_pgtable(pmd);
 
-	pte_basic_tests(pte_aligned, prot);
-	pmd_basic_tests(pmd_aligned, prot);
-	pud_basic_tests(pud_aligned, prot);
+	/*
+	 * Iterate over the protection_map[] to make sure that all
+	 * the basic page table transformation validations just hold
+	 * true irrespective of the starting protection value for a
+	 * given page table entry.
+	 */
+	for (idx = 0; idx < ARRAY_SIZE(protection_map); idx++) {
+		pte_basic_tests(pte_aligned, idx);
+		pmd_basic_tests(pmd_aligned, idx);
+		pud_basic_tests(mm, pud_aligned, idx);
+	}
+
+	/*
+	 * Both P4D and PGD level tests are very basic which do not
+	 * involve creating page table entries from the protection
+	 * value and the given pfn. Hence just keep them out from
+	 * the above iteration for now to save some test execution
+	 * time.
+	 */
 	p4d_basic_tests(p4d_aligned, prot);
 	pgd_basic_tests(pgd_aligned, prot);
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 6ff2a3fb0dc7..46a8b9e82434 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -206,9 +206,9 @@ static void unaccount_page_cache_page(struct address_space *mapping,
 	if (PageSwapBacked(page)) {
 		__mod_lruvec_page_state(page, NR_SHMEM, -nr);
 		if (PageTransHuge(page))
-			__dec_lruvec_page_state(page, NR_SHMEM_THPS);
+			__mod_lruvec_page_state(page, NR_SHMEM_THPS, -nr);
 	} else if (PageTransHuge(page)) {
-		__dec_lruvec_page_state(page, NR_FILE_THPS);
+		__mod_lruvec_page_state(page, NR_FILE_THPS, -nr);
 		filemap_nr_thps_dec(mapping);
 	}
 
@@ -777,7 +777,6 @@ EXPORT_SYMBOL(file_write_and_wait_range);
  * replace_page_cache_page - replace a pagecache page with a new one
  * @old:	page to be replaced
  * @new:	page to replace with
- * @gfp_mask:	allocation mode
  *
  * This function replaces a page in the pagecache with a new one.  On
  * success it acquires the pagecache reference for the new page and
@@ -786,10 +785,8 @@ EXPORT_SYMBOL(file_write_and_wait_range);
  * caller must do that.
  *
  * The remove + add is atomic.  This function cannot fail.
- *
- * Return: %0
  */
-int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
+void replace_page_cache_page(struct page *old, struct page *new)
 {
 	struct address_space *mapping = old->mapping;
 	void (*freepage)(struct page *) = mapping->a_ops->freepage;
@@ -824,8 +821,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 	if (freepage)
 		freepage(old);
 	put_page(old);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
@@ -1348,61 +1343,26 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr)
 }
 EXPORT_SYMBOL(wait_on_page_bit_killable);
 
-static int __wait_on_page_locked_async(struct page *page,
-				       struct wait_page_queue *wait, bool set)
-{
-	struct wait_queue_head *q = page_waitqueue(page);
-	int ret = 0;
-
-	wait->page = page;
-	wait->bit_nr = PG_locked;
-
-	spin_lock_irq(&q->lock);
-	__add_wait_queue_entry_tail(q, &wait->wait);
-	SetPageWaiters(page);
-	if (set)
-		ret = !trylock_page(page);
-	else
-		ret = PageLocked(page);
-	/*
-	 * If we were successful now, we know we're still on the
-	 * waitqueue as we're still under the lock. This means it's
-	 * safe to remove and return success, we know the callback
-	 * isn't going to trigger.
-	 */
-	if (!ret)
-		__remove_wait_queue(q, &wait->wait);
-	else
-		ret = -EIOCBQUEUED;
-	spin_unlock_irq(&q->lock);
-	return ret;
-}
-
-static int wait_on_page_locked_async(struct page *page,
-				     struct wait_page_queue *wait)
-{
-	if (!PageLocked(page))
-		return 0;
-	return __wait_on_page_locked_async(compound_head(page), wait, false);
-}
-
 /**
  * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
  * @page: The page to wait for.
+ * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc).
  *
  * The caller should hold a reference on @page.  They expect the page to
  * become unlocked relatively soon, but do not wish to hold up migration
  * (for example) by holding the reference while waiting for the page to
  * come unlocked.  After this function returns, the caller should not
  * dereference @page.
+ *
+ * Return: 0 if the page was unlocked or -EINTR if interrupted by a signal.
  */
-void put_and_wait_on_page_locked(struct page *page)
+int put_and_wait_on_page_locked(struct page *page, int state)
 {
 	wait_queue_head_t *q;
 
 	page = compound_head(page);
 	q = page_waitqueue(page);
-	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP);
+	return wait_on_page_bit_common(q, page, PG_locked, state, DROP);
 }
 
 /**
@@ -1558,7 +1518,28 @@ EXPORT_SYMBOL_GPL(__lock_page_killable);
 
 int __lock_page_async(struct page *page, struct wait_page_queue *wait)
 {
-	return __wait_on_page_locked_async(page, wait, true);
+	struct wait_queue_head *q = page_waitqueue(page);
+	int ret = 0;
+
+	wait->page = page;
+	wait->bit_nr = PG_locked;
+
+	spin_lock_irq(&q->lock);
+	__add_wait_queue_entry_tail(q, &wait->wait);
+	SetPageWaiters(page);
+	ret = !trylock_page(page);
+	/*
+	 * If we were successful now, we know we're still on the
+	 * waitqueue as we're still under the lock. This means it's
+	 * safe to remove and return success, we know the callback
+	 * isn't going to trigger.
+	 */
+	if (!ret)
+		__remove_wait_queue(q, &wait->wait);
+	else
+		ret = -EIOCBQUEUED;
+	spin_unlock_irq(&q->lock);
+	return ret;
 }
 
 /*
@@ -2173,287 +2154,267 @@ static void shrink_readahead_size_eio(struct file_ra_state *ra)
 	ra->ra_pages /= 4;
 }
 
-static int lock_page_for_iocb(struct kiocb *iocb, struct page *page)
+/*
+ * filemap_get_read_batch - Get a batch of pages for read
+ *
+ * Get a batch of pages which represent a contiguous range of bytes
+ * in the file.  No tail pages will be returned.  If @index is in the
+ * middle of a THP, the entire THP will be returned.  The last page in
+ * the batch may have Readahead set or be not Uptodate so that the
+ * caller can take the appropriate action.
+ */
+static void filemap_get_read_batch(struct address_space *mapping,
+		pgoff_t index, pgoff_t max, struct pagevec *pvec)
 {
-	if (iocb->ki_flags & IOCB_WAITQ)
-		return lock_page_async(page, iocb->ki_waitq);
-	else if (iocb->ki_flags & IOCB_NOWAIT)
-		return trylock_page(page) ? 0 : -EAGAIN;
-	else
-		return lock_page_killable(page);
+	XA_STATE(xas, &mapping->i_pages, index);
+	struct page *head;
+
+	rcu_read_lock();
+	for (head = xas_load(&xas); head; head = xas_next(&xas)) {
+		if (xas_retry(&xas, head))
+			continue;
+		if (xas.xa_index > max || xa_is_value(head))
+			break;
+		if (!page_cache_get_speculative(head))
+			goto retry;
+
+		/* Has the page moved or been split? */
+		if (unlikely(head != xas_reload(&xas)))
+			goto put_page;
+
+		if (!pagevec_add(pvec, head))
+			break;
+		if (!PageUptodate(head))
+			break;
+		if (PageReadahead(head))
+			break;
+		xas.xa_index = head->index + thp_nr_pages(head) - 1;
+		xas.xa_offset = (xas.xa_index >> xas.xa_shift) & XA_CHUNK_MASK;
+		continue;
+put_page:
+		put_page(head);
+retry:
+		xas_reset(&xas);
+	}
+	rcu_read_unlock();
 }
 
-static struct page *
-generic_file_buffered_read_readpage(struct kiocb *iocb,
-				    struct file *filp,
-				    struct address_space *mapping,
-				    struct page *page)
+static int filemap_read_page(struct file *file, struct address_space *mapping,
+		struct page *page)
 {
-	struct file_ra_state *ra = &filp->f_ra;
 	int error;
 
-	if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) {
-		unlock_page(page);
-		put_page(page);
-		return ERR_PTR(-EAGAIN);
-	}
-
 	/*
-	 * A previous I/O error may have been due to temporary
-	 * failures, eg. multipath errors.
-	 * PG_error will be set again if readpage fails.
+	 * A previous I/O error may have been due to temporary failures,
+	 * eg. multipath errors.  PG_error will be set again if readpage
+	 * fails.
 	 */
 	ClearPageError(page);
 	/* Start the actual read. The read will unlock the page. */
-	error = mapping->a_ops->readpage(filp, page);
+	error = mapping->a_ops->readpage(file, page);
+	if (error)
+		return error;
 
-	if (unlikely(error)) {
-		put_page(page);
-		return error != AOP_TRUNCATED_PAGE ? ERR_PTR(error) : NULL;
-	}
+	error = wait_on_page_locked_killable(page);
+	if (error)
+		return error;
+	if (PageUptodate(page))
+		return 0;
+	if (!page->mapping)	/* page truncated */
+		return AOP_TRUNCATED_PAGE;
+	shrink_readahead_size_eio(&file->f_ra);
+	return -EIO;
+}
 
-	if (!PageUptodate(page)) {
-		error = lock_page_for_iocb(iocb, page);
-		if (unlikely(error)) {
-			put_page(page);
-			return ERR_PTR(error);
-		}
-		if (!PageUptodate(page)) {
-			if (page->mapping == NULL) {
-				/*
-				 * invalidate_mapping_pages got it
-				 */
-				unlock_page(page);
-				put_page(page);
-				return NULL;
-			}
-			unlock_page(page);
-			shrink_readahead_size_eio(ra);
-			put_page(page);
-			return ERR_PTR(-EIO);
-		}
-		unlock_page(page);
+static bool filemap_range_uptodate(struct address_space *mapping,
+		loff_t pos, struct iov_iter *iter, struct page *page)
+{
+	int count;
+
+	if (PageUptodate(page))
+		return true;
+	/* pipes can't handle partially uptodate pages */
+	if (iov_iter_is_pipe(iter))
+		return false;
+	if (!mapping->a_ops->is_partially_uptodate)
+		return false;
+	if (mapping->host->i_blkbits >= (PAGE_SHIFT + thp_order(page)))
+		return false;
+
+	count = iter->count;
+	if (page_offset(page) > pos) {
+		count -= page_offset(page) - pos;
+		pos = 0;
+	} else {
+		pos -= page_offset(page);
 	}
 
-	return page;
+	return mapping->a_ops->is_partially_uptodate(page, pos, count);
 }
 
-static struct page *
-generic_file_buffered_read_pagenotuptodate(struct kiocb *iocb,
-					   struct file *filp,
-					   struct iov_iter *iter,
-					   struct page *page,
-					   loff_t pos, loff_t count)
+static int filemap_update_page(struct kiocb *iocb,
+		struct address_space *mapping, struct iov_iter *iter,
+		struct page *page)
 {
-	struct address_space *mapping = filp->f_mapping;
-	struct inode *inode = mapping->host;
 	int error;
 
-	/*
-	 * See comment in do_read_cache_page on why
-	 * wait_on_page_locked is used to avoid unnecessarily
-	 * serialisations and why it's safe.
-	 */
-	if (iocb->ki_flags & IOCB_WAITQ) {
-		error = wait_on_page_locked_async(page,
-						iocb->ki_waitq);
-	} else {
-		error = wait_on_page_locked_killable(page);
-	}
-	if (unlikely(error)) {
-		put_page(page);
-		return ERR_PTR(error);
+	if (!trylock_page(page)) {
+		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
+			return -EAGAIN;
+		if (!(iocb->ki_flags & IOCB_WAITQ)) {
+			put_and_wait_on_page_locked(page, TASK_KILLABLE);
+			return AOP_TRUNCATED_PAGE;
+		}
+		error = __lock_page_async(page, iocb->ki_waitq);
+		if (error)
+			return error;
 	}
-	if (PageUptodate(page))
-		return page;
 
-	if (inode->i_blkbits == PAGE_SHIFT ||
-			!mapping->a_ops->is_partially_uptodate)
-		goto page_not_up_to_date;
-	/* pipes can't handle partially uptodate pages */
-	if (unlikely(iov_iter_is_pipe(iter)))
-		goto page_not_up_to_date;
-	if (!trylock_page(page))
-		goto page_not_up_to_date;
-	/* Did it get truncated before we got the lock? */
 	if (!page->mapping)
-		goto page_not_up_to_date_locked;
-	if (!mapping->a_ops->is_partially_uptodate(page,
-				pos & ~PAGE_MASK, count))
-		goto page_not_up_to_date_locked;
-	unlock_page(page);
-	return page;
+		goto truncated;
 
-page_not_up_to_date:
-	/* Get exclusive access to the page ... */
-	error = lock_page_for_iocb(iocb, page);
-	if (unlikely(error)) {
-		put_page(page);
-		return ERR_PTR(error);
-	}
-
-page_not_up_to_date_locked:
-	/* Did it get truncated before we got the lock? */
-	if (!page->mapping) {
-		unlock_page(page);
-		put_page(page);
-		return NULL;
-	}
+	error = 0;
+	if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
+		goto unlock;
 
-	/* Did somebody else fill it already? */
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		return page;
-	}
+	error = -EAGAIN;
+	if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
+		goto unlock;
 
-	return generic_file_buffered_read_readpage(iocb, filp, mapping, page);
+	error = filemap_read_page(iocb->ki_filp, mapping, page);
+	if (error == AOP_TRUNCATED_PAGE)
+		put_page(page);
+	return error;
+truncated:
+	unlock_page(page);
+	put_page(page);
+	return AOP_TRUNCATED_PAGE;
+unlock:
+	unlock_page(page);
+	return error;
 }
 
-static struct page *
-generic_file_buffered_read_no_cached_page(struct kiocb *iocb,
-					  struct iov_iter *iter)
+static int filemap_create_page(struct file *file,
+		struct address_space *mapping, pgoff_t index,
+		struct pagevec *pvec)
 {
-	struct file *filp = iocb->ki_filp;
-	struct address_space *mapping = filp->f_mapping;
-	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
 	struct page *page;
 	int error;
 
-	if (iocb->ki_flags & IOCB_NOIO)
-		return ERR_PTR(-EAGAIN);
-
-	/*
-	 * Ok, it wasn't cached, so we need to create a new
-	 * page..
-	 */
 	page = page_cache_alloc(mapping);
 	if (!page)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	error = add_to_page_cache_lru(page, mapping, index,
-				      mapping_gfp_constraint(mapping, GFP_KERNEL));
-	if (error) {
-		put_page(page);
-		return error != -EEXIST ? ERR_PTR(error) : NULL;
-	}
+			mapping_gfp_constraint(mapping, GFP_KERNEL));
+	if (error == -EEXIST)
+		error = AOP_TRUNCATED_PAGE;
+	if (error)
+		goto error;
 
-	return generic_file_buffered_read_readpage(iocb, filp, mapping, page);
+	error = filemap_read_page(file, mapping, page);
+	if (error)
+		goto error;
+
+	pagevec_add(pvec, page);
+	return 0;
+error:
+	put_page(page);
+	return error;
 }
 
-static int generic_file_buffered_read_get_pages(struct kiocb *iocb,
-						struct iov_iter *iter,
-						struct page **pages,
-						unsigned int nr)
+static int filemap_readahead(struct kiocb *iocb, struct file *file,
+		struct address_space *mapping, struct page *page,
+		pgoff_t last_index)
+{
+	if (iocb->ki_flags & IOCB_NOIO)
+		return -EAGAIN;
+	page_cache_async_readahead(mapping, &file->f_ra, file, page,
+			page->index, last_index - page->index);
+	return 0;
+}
+
+static int filemap_get_pages(struct kiocb *iocb, struct iov_iter *iter,
+		struct pagevec *pvec)
 {
 	struct file *filp = iocb->ki_filp;
 	struct address_space *mapping = filp->f_mapping;
 	struct file_ra_state *ra = &filp->f_ra;
 	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
-	pgoff_t last_index = (iocb->ki_pos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
-	int i, j, nr_got, err = 0;
+	pgoff_t last_index;
+	struct page *page;
+	int err = 0;
 
-	nr = min_t(unsigned long, last_index - index, nr);
-find_page:
+	last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE);
+retry:
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
-	nr_got = find_get_pages_contig(mapping, index, nr, pages);
-	if (nr_got)
-		goto got_pages;
-
-	if (iocb->ki_flags & IOCB_NOIO)
-		return -EAGAIN;
-
-	page_cache_sync_readahead(mapping, ra, filp, index, last_index - index);
-
-	nr_got = find_get_pages_contig(mapping, index, nr, pages);
-	if (nr_got)
-		goto got_pages;
-
-	pages[0] = generic_file_buffered_read_no_cached_page(iocb, iter);
-	err = PTR_ERR_OR_ZERO(pages[0]);
-	if (!IS_ERR_OR_NULL(pages[0]))
-		nr_got = 1;
-got_pages:
-	for (i = 0; i < nr_got; i++) {
-		struct page *page = pages[i];
-		pgoff_t pg_index = index + i;
-		loff_t pg_pos = max(iocb->ki_pos,
-				    (loff_t) pg_index << PAGE_SHIFT);
-		loff_t pg_count = iocb->ki_pos + iter->count - pg_pos;
-
-		if (PageReadahead(page)) {
-			if (iocb->ki_flags & IOCB_NOIO) {
-				for (j = i; j < nr_got; j++)
-					put_page(pages[j]);
-				nr_got = i;
-				err = -EAGAIN;
-				break;
-			}
-			page_cache_async_readahead(mapping, ra, filp, page,
-					pg_index, last_index - pg_index);
-		}
-
-		if (!PageUptodate(page)) {
-			if ((iocb->ki_flags & IOCB_NOWAIT) ||
-			    ((iocb->ki_flags & IOCB_WAITQ) && i)) {
-				for (j = i; j < nr_got; j++)
-					put_page(pages[j]);
-				nr_got = i;
-				err = -EAGAIN;
-				break;
-			}
+	filemap_get_read_batch(mapping, index, last_index, pvec);
+	if (!pagevec_count(pvec)) {
+		if (iocb->ki_flags & IOCB_NOIO)
+			return -EAGAIN;
+		page_cache_sync_readahead(mapping, ra, filp, index,
+				last_index - index);
+		filemap_get_read_batch(mapping, index, last_index, pvec);
+	}
+	if (!pagevec_count(pvec)) {
+		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
+			return -EAGAIN;
+		err = filemap_create_page(filp, mapping,
+				iocb->ki_pos >> PAGE_SHIFT, pvec);
+		if (err == AOP_TRUNCATED_PAGE)
+			goto retry;
+		return err;
+	}
 
-			page = generic_file_buffered_read_pagenotuptodate(iocb,
-					filp, iter, page, pg_pos, pg_count);
-			if (IS_ERR_OR_NULL(page)) {
-				for (j = i + 1; j < nr_got; j++)
-					put_page(pages[j]);
-				nr_got = i;
-				err = PTR_ERR_OR_ZERO(page);
-				break;
-			}
-		}
+	page = pvec->pages[pagevec_count(pvec) - 1];
+	if (PageReadahead(page)) {
+		err = filemap_readahead(iocb, filp, mapping, page, last_index);
+		if (err)
+			goto err;
+	}
+	if (!PageUptodate(page)) {
+		if ((iocb->ki_flags & IOCB_WAITQ) && pagevec_count(pvec) > 1)
+			iocb->ki_flags |= IOCB_NOWAIT;
+		err = filemap_update_page(iocb, mapping, iter, page);
+		if (err)
+			goto err;
 	}
 
-	if (likely(nr_got))
-		return nr_got;
-	if (err)
-		return err;
-	/*
-	 * No pages and no error means we raced and should retry:
-	 */
-	goto find_page;
+	return 0;
+err:
+	if (err < 0)
+		put_page(page);
+	if (likely(--pvec->nr))
+		return 0;
+	if (err == AOP_TRUNCATED_PAGE)
+		goto retry;
+	return err;
 }
 
 /**
- * generic_file_buffered_read - generic file read routine
- * @iocb:	the iocb to read
- * @iter:	data destination
- * @written:	already copied
- *
- * This is a generic file read routine, and uses the
- * mapping->a_ops->readpage() function for the actual low-level stuff.
+ * filemap_read - Read data from the page cache.
+ * @iocb: The iocb to read.
+ * @iter: Destination for the data.
+ * @already_read: Number of bytes already read by the caller.
  *
- * This is really ugly. But the goto's actually try to clarify some
- * of the logic when it comes to error handling etc.
+ * Copies data from the page cache.  If the data is not currently present,
+ * uses the readahead and readpage address_space operations to fetch it.
  *
- * Return:
- * * total number of bytes copied, including those the were already @written
- * * negative error code if nothing was copied
+ * Return: Total number of bytes copied, including those already read by
+ * the caller.  If an error happens before any bytes are copied, returns
+ * a negative error number.
  */
-ssize_t generic_file_buffered_read(struct kiocb *iocb,
-		struct iov_iter *iter, ssize_t written)
+ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
+		ssize_t already_read)
 {
 	struct file *filp = iocb->ki_filp;
 	struct file_ra_state *ra = &filp->f_ra;
 	struct address_space *mapping = filp->f_mapping;
 	struct inode *inode = mapping->host;
-	struct page *pages_onstack[PAGEVEC_SIZE], **pages = NULL;
-	unsigned int nr_pages = min_t(unsigned int, 512,
-			((iocb->ki_pos + iter->count + PAGE_SIZE - 1) >> PAGE_SHIFT) -
-			(iocb->ki_pos >> PAGE_SHIFT));
-	int i, pg_nr, error = 0;
+	struct pagevec pvec;
+	int i, error = 0;
 	bool writably_mapped;
 	loff_t isize, end_offset;
 
@@ -2463,14 +2424,7 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		return 0;
 
 	iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
-
-	if (nr_pages > ARRAY_SIZE(pages_onstack))
-		pages = kmalloc_array(nr_pages, sizeof(void *), GFP_KERNEL);
-
-	if (!pages) {
-		pages = pages_onstack;
-		nr_pages = min_t(unsigned int, nr_pages, ARRAY_SIZE(pages_onstack));
-	}
+	pagevec_init(&pvec);
 
 	do {
 		cond_resched();
@@ -2480,16 +2434,12 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		 * can no longer safely return -EIOCBQUEUED. Hence mark
 		 * an async read NOWAIT at that point.
 		 */
-		if ((iocb->ki_flags & IOCB_WAITQ) && written)
+		if ((iocb->ki_flags & IOCB_WAITQ) && already_read)
 			iocb->ki_flags |= IOCB_NOWAIT;
 
-		i = 0;
-		pg_nr = generic_file_buffered_read_get_pages(iocb, iter,
-							     pages, nr_pages);
-		if (pg_nr < 0) {
-			error = pg_nr;
+		error = filemap_get_pages(iocb, iter, &pvec);
+		if (error < 0)
 			break;
-		}
 
 		/*
 		 * i_size must be checked after we know the pages are Uptodate.
@@ -2502,13 +2452,8 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		isize = i_size_read(inode);
 		if (unlikely(iocb->ki_pos >= isize))
 			goto put_pages;
-
 		end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
 
-		while ((iocb->ki_pos >> PAGE_SHIFT) + pg_nr >
-		       (end_offset + PAGE_SIZE - 1) >> PAGE_SHIFT)
-			put_page(pages[--pg_nr]);
-
 		/*
 		 * Once we start copying data, we don't want to be touching any
 		 * cachelines that might be contended:
@@ -2521,27 +2466,35 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		 */
 		if (iocb->ki_pos >> PAGE_SHIFT !=
 		    ra->prev_pos >> PAGE_SHIFT)
-			mark_page_accessed(pages[0]);
-		for (i = 1; i < pg_nr; i++)
-			mark_page_accessed(pages[i]);
+			mark_page_accessed(pvec.pages[0]);
 
-		for (i = 0; i < pg_nr; i++) {
-			unsigned int offset = iocb->ki_pos & ~PAGE_MASK;
-			unsigned int bytes = min_t(loff_t, end_offset - iocb->ki_pos,
-						   PAGE_SIZE - offset);
-			unsigned int copied;
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			size_t page_size = thp_size(page);
+			size_t offset = iocb->ki_pos & (page_size - 1);
+			size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos,
+					     page_size - offset);
+			size_t copied;
 
+			if (end_offset < page_offset(page))
+				break;
+			if (i > 0)
+				mark_page_accessed(page);
 			/*
 			 * If users can be writing to this page using arbitrary
 			 * virtual addresses, take care about potential aliasing
 			 * before reading the page on the kernel side.
 			 */
-			if (writably_mapped)
-				flush_dcache_page(pages[i]);
+			if (writably_mapped) {
+				int j;
+
+				for (j = 0; j < thp_nr_pages(page); j++)
+					flush_dcache_page(page + j);
+			}
 
-			copied = copy_page_to_iter(pages[i], offset, bytes, iter);
+			copied = copy_page_to_iter(page, offset, bytes, iter);
 
-			written += copied;
+			already_read += copied;
 			iocb->ki_pos += copied;
 			ra->prev_pos = iocb->ki_pos;
 
@@ -2551,18 +2504,16 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 			}
 		}
 put_pages:
-		for (i = 0; i < pg_nr; i++)
-			put_page(pages[i]);
+		for (i = 0; i < pagevec_count(&pvec); i++)
+			put_page(pvec.pages[i]);
+		pagevec_reinit(&pvec);
 	} while (iov_iter_count(iter) && iocb->ki_pos < isize && !error);
 
 	file_accessed(filp);
 
-	if (pages != pages_onstack)
-		kfree(pages);
-
-	return written ? written : error;
+	return already_read ? already_read : error;
 }
-EXPORT_SYMBOL_GPL(generic_file_buffered_read);
+EXPORT_SYMBOL_GPL(filemap_read);
 
 /**
  * generic_file_read_iter - generic filesystem read routine
@@ -2592,7 +2543,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	ssize_t retval = 0;
 
 	if (!count)
-		goto out; /* skip atime */
+		return 0; /* skip atime */
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		struct file *file = iocb->ki_filp;
@@ -2610,7 +2561,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 						iocb->ki_pos,
 					        iocb->ki_pos + count - 1);
 			if (retval < 0)
-				goto out;
+				return retval;
 		}
 
 		file_accessed(file);
@@ -2620,7 +2571,8 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 			iocb->ki_pos += retval;
 			count -= retval;
 		}
-		iov_iter_revert(iter, count - iov_iter_count(iter));
+		if (retval != -EIOCBQUEUED)
+			iov_iter_revert(iter, count - iov_iter_count(iter));
 
 		/*
 		 * Btrfs can have a short DIO read if we encounter
@@ -2633,12 +2585,10 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 		 */
 		if (retval < 0 || !count || iocb->ki_pos >= size ||
 		    IS_DAX(inode))
-			goto out;
+			return retval;
 	}
 
-	retval = generic_file_buffered_read(iocb, iter, retval);
-out:
-	return retval;
+	return filemap_read(iocb, iter, retval);
 }
 EXPORT_SYMBOL(generic_file_read_iter);
 
@@ -3431,7 +3381,8 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 		}
 		iocb->ki_pos = pos;
 	}
-	iov_iter_revert(from, write_len - iov_iter_count(from));
+	if (written != -EIOCBQUEUED)
+		iov_iter_revert(from, write_len - iov_iter_count(from));
 out:
 	return written;
 }
diff --git a/mm/gup.c b/mm/gup.c
index e4c224cd9661..e40579624f10 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -78,9 +78,8 @@ static inline struct page *try_get_compound_head(struct page *page, int refs)
  * considered failure, and furthermore, a likely bug in the caller, so a warning
  * is also emitted.
  */
-static __maybe_unused struct page *try_grab_compound_head(struct page *page,
-							  int refs,
-							  unsigned int flags)
+__maybe_unused struct page *try_grab_compound_head(struct page *page,
+						   int refs, unsigned int flags)
 {
 	if (flags & FOLL_GET)
 		return try_get_compound_head(page, refs);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 91ca9b103ee5..d77605c30f2e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -386,7 +386,11 @@ static int __init hugepage_init(void)
 	struct kobject *hugepage_kobj;
 
 	if (!has_transparent_hugepage()) {
-		transparent_hugepage_flags = 0;
+		/*
+		 * Hardware doesn't support hugepages, hence disable
+		 * DAX PMD support.
+		 */
+		transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX;
 		return -EINVAL;
 	}
 
@@ -636,6 +640,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
 		lru_cache_add_inactive_or_unevictable(page, vma);
 		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
 		set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
+		update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 		add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
 		mm_inc_nr_ptes(vma->vm_mm);
 		spin_unlock(vmf->ptl);
@@ -690,20 +695,19 @@ static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
 }
 
 /* Caller must hold page table lock. */
-static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
+static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
 		struct page *zero_page)
 {
 	pmd_t entry;
 	if (!pmd_none(*pmd))
-		return false;
+		return;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
 	if (pgtable)
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
 	mm_inc_nr_ptes(mm);
-	return true;
 }
 
 vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
@@ -749,6 +753,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			} else {
 				set_huge_zero_page(pgtable, vma->vm_mm, vma,
 						   haddr, vmf->pmd, zero_page);
+				update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
 				spin_unlock(vmf->ptl);
 			}
 		} else {
@@ -1439,7 +1444,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 		if (!get_page_unless_zero(page))
 			goto out_unlock;
 		spin_unlock(vmf->ptl);
-		put_and_wait_on_page_locked(page);
+		put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
 		goto out;
 	}
 
@@ -1475,7 +1480,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 		if (!get_page_unless_zero(page))
 			goto out_unlock;
 		spin_unlock(vmf->ptl);
-		put_and_wait_on_page_locked(page);
+		put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
 		goto out;
 	}
 
@@ -2176,7 +2181,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		lock_page_memcg(page);
 		if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
 			/* Last compound_mapcount is gone. */
-			__dec_lruvec_page_state(page, NR_ANON_THPS);
+			__mod_lruvec_page_state(page, NR_ANON_THPS,
+						-HPAGE_PMD_NR);
 			if (TestClearPageDoubleMap(page)) {
 				/* No need in mapcount reference anymore */
 				for (i = 0; i < HPAGE_PMD_NR; i++)
@@ -2751,10 +2757,14 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		}
 		spin_unlock(&ds_queue->split_queue_lock);
 		if (mapping) {
+			int nr = thp_nr_pages(head);
+
 			if (PageSwapBacked(head))
-				__dec_lruvec_page_state(head, NR_SHMEM_THPS);
+				__mod_lruvec_page_state(head, NR_SHMEM_THPS,
+							-nr);
 			else
-				__dec_lruvec_page_state(head, NR_FILE_THPS);
+				__mod_lruvec_page_state(head, NR_FILE_THPS,
+							-nr);
 		}
 
 		__split_huge_page(page, list, end);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 905a7d549b00..8fb42c6dd74b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -79,34 +79,29 @@ DEFINE_SPINLOCK(hugetlb_lock);
 static int num_fault_mutexes;
 struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
 
-static inline bool PageHugeFreed(struct page *head)
-{
-	return page_private(head + 4) == -1UL;
-}
+/* Forward declaration */
+static int hugetlb_acct_memory(struct hstate *h, long delta);
 
-static inline void SetPageHugeFreed(struct page *head)
+static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
-	set_page_private(head + 4, -1UL);
-}
+	if (spool->count)
+		return false;
+	if (spool->max_hpages != -1)
+		return spool->used_hpages == 0;
+	if (spool->min_hpages != -1)
+		return spool->rsv_hpages == spool->min_hpages;
 
-static inline void ClearPageHugeFreed(struct page *head)
-{
-	set_page_private(head + 4, 0);
+	return true;
 }
 
-/* Forward declaration */
-static int hugetlb_acct_memory(struct hstate *h, long delta);
-
 static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
 {
-	bool free = (spool->count == 0) && (spool->used_hpages == 0);
-
 	spin_unlock(&spool->lock);
 
 	/* If no pages are used, and no other handles to the subpool
 	 * remain, give up any reservations based on minimum size and
 	 * free the subpool */
-	if (free) {
+	if (subpool_is_free(spool)) {
 		if (spool->min_hpages != -1)
 			hugetlb_acct_memory(spool->hstate,
 						-spool->min_hpages);
@@ -1043,7 +1038,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	list_move(&page->lru, &h->hugepage_freelists[nid]);
 	h->free_huge_pages++;
 	h->free_huge_pages_node[nid]++;
-	SetPageHugeFreed(page);
+	SetHPageFreed(page);
 }
 
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
@@ -1060,7 +1055,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 
 		list_move(&page->lru, &h->hugepage_activelist);
 		set_page_refcounted(page);
-		ClearPageHugeFreed(page);
+		ClearHPageFreed(page);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
 		return page;
@@ -1133,7 +1128,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
 	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
 	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
-		SetPagePrivate(page);
+		SetHPageRestoreReserve(page);
 		h->resv_huge_pages--;
 	}
 
@@ -1224,8 +1219,7 @@ static void destroy_compound_gigantic_page(struct page *page,
 	struct page *p = page + 1;
 
 	atomic_set(compound_mapcount_ptr(page), 0);
-	if (hpage_pincount_available(page))
-		atomic_set(compound_pincount_ptr(page), 0);
+	atomic_set(compound_pincount_ptr(page), 0);
 
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
 		clear_compound_head(p);
@@ -1312,14 +1306,16 @@ static inline void destroy_compound_gigantic_page(struct page *page,
 static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
+	struct page *subpage = page;
 
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
-	for (i = 0; i < pages_per_huge_page(h); i++) {
-		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+	for (i = 0; i < pages_per_huge_page(h);
+	     i++, subpage = mem_map_next(subpage, page, i)) {
+		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
 				1 << PG_active | 1 << PG_private |
 				1 << PG_writeback);
@@ -1353,52 +1349,6 @@ struct hstate *size_to_hstate(unsigned long size)
 	return NULL;
 }
 
-/*
- * Test to determine whether the hugepage is "active/in-use" (i.e. being linked
- * to hstate->hugepage_activelist.)
- *
- * This function can be called for tail pages, but never returns true for them.
- */
-bool page_huge_active(struct page *page)
-{
-	return PageHeadHuge(page) && PagePrivate(&page[1]);
-}
-
-/* never called for tail page */
-void set_page_huge_active(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	SetPagePrivate(&page[1]);
-}
-
-static void clear_page_huge_active(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	ClearPagePrivate(&page[1]);
-}
-
-/*
- * Internal hugetlb specific page flag. Do not use outside of the hugetlb
- * code
- */
-static inline bool PageHugeTemporary(struct page *page)
-{
-	if (!PageHuge(page))
-		return false;
-
-	return (unsigned long)page[2].mapping == -1U;
-}
-
-static inline void SetPageHugeTemporary(struct page *page)
-{
-	page[2].mapping = (void *)-1U;
-}
-
-static inline void ClearPageHugeTemporary(struct page *page)
-{
-	page[2].mapping = NULL;
-}
-
 static void __free_huge_page(struct page *page)
 {
 	/*
@@ -1407,24 +1357,23 @@ static void __free_huge_page(struct page *page)
 	 */
 	struct hstate *h = page_hstate(page);
 	int nid = page_to_nid(page);
-	struct hugepage_subpool *spool =
-		(struct hugepage_subpool *)page_private(page);
+	struct hugepage_subpool *spool = hugetlb_page_subpool(page);
 	bool restore_reserve;
 
 	VM_BUG_ON_PAGE(page_count(page), page);
 	VM_BUG_ON_PAGE(page_mapcount(page), page);
 
-	set_page_private(page, 0);
+	hugetlb_set_page_subpool(page, NULL);
 	page->mapping = NULL;
-	restore_reserve = PagePrivate(page);
-	ClearPagePrivate(page);
+	restore_reserve = HPageRestoreReserve(page);
+	ClearHPageRestoreReserve(page);
 
 	/*
-	 * If PagePrivate() was set on page, page allocation consumed a
+	 * If HPageRestoreReserve was set on page, page allocation consumed a
 	 * reservation.  If the page was associated with a subpool, there
 	 * would have been a page reserved in the subpool before allocation
 	 * via hugepage_subpool_get_pages().  Since we are 'restoring' the
-	 * reservtion, do not call hugepage_subpool_put_pages() as this will
+	 * reservation, do not call hugepage_subpool_put_pages() as this will
 	 * remove the reserved page from the subpool.
 	 */
 	if (!restore_reserve) {
@@ -1439,7 +1388,7 @@ static void __free_huge_page(struct page *page)
 	}
 
 	spin_lock(&hugetlb_lock);
-	clear_page_huge_active(page);
+	ClearHPageMigratable(page);
 	hugetlb_cgroup_uncharge_page(hstate_index(h),
 				     pages_per_huge_page(h), page);
 	hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
@@ -1447,9 +1396,9 @@ static void __free_huge_page(struct page *page)
 	if (restore_reserve)
 		h->resv_huge_pages++;
 
-	if (PageHugeTemporary(page)) {
+	if (HPageTemporary(page)) {
 		list_del(&page->lru);
-		ClearPageHugeTemporary(page);
+		ClearHPageTemporary(page);
 		update_and_free_page(h, page);
 	} else if (h->surplus_huge_pages_node[nid]) {
 		/* remove the page from active list */
@@ -1516,12 +1465,13 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
+	hugetlb_set_page_subpool(page, NULL);
 	set_hugetlb_cgroup(page, NULL);
 	set_hugetlb_cgroup_rsvd(page, NULL);
 	spin_lock(&hugetlb_lock);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
-	ClearPageHugeFreed(page);
+	ClearHPageFreed(page);
 	spin_unlock(&hugetlb_lock);
 }
 
@@ -1553,9 +1503,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order)
 		set_compound_head(p, page);
 	}
 	atomic_set(compound_mapcount_ptr(page), -1);
-
-	if (hpage_pincount_available(page))
-		atomic_set(compound_pincount_ptr(page), 0);
+	atomic_set(compound_pincount_ptr(page), 0);
 }
 
 /*
@@ -1794,7 +1742,7 @@ retry:
 		 * We should make sure that the page is already on the free list
 		 * when it is dissolved.
 		 */
-		if (unlikely(!PageHugeFreed(head))) {
+		if (unlikely(!HPageFreed(head))) {
 			spin_unlock(&hugetlb_lock);
 			cond_resched();
 
@@ -1885,7 +1833,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 	 * codeflow
 	 */
 	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
-		SetPageHugeTemporary(page);
+		SetHPageTemporary(page);
 		spin_unlock(&hugetlb_lock);
 		put_page(page);
 		return NULL;
@@ -1916,7 +1864,7 @@ static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
 	 * We do not account these pages as surplus because they are only
 	 * temporary and will be released properly on the last reference
 	 */
-	SetPageHugeTemporary(page);
+	SetHPageTemporary(page);
 
 	return page;
 }
@@ -2254,24 +2202,24 @@ static long vma_add_reservation(struct hstate *h,
  * This routine is called to restore a reservation on error paths.  In the
  * specific error paths, a huge page was allocated (via alloc_huge_page)
  * and is about to be freed.  If a reservation for the page existed,
- * alloc_huge_page would have consumed the reservation and set PagePrivate
- * in the newly allocated page.  When the page is freed via free_huge_page,
- * the global reservation count will be incremented if PagePrivate is set.
- * However, free_huge_page can not adjust the reserve map.  Adjust the
- * reserve map here to be consistent with global reserve count adjustments
- * to be made by free_huge_page.
+ * alloc_huge_page would have consumed the reservation and set
+ * HPageRestoreReserve in the newly allocated page.  When the page is freed
+ * via free_huge_page, the global reservation count will be incremented if
+ * HPageRestoreReserve is set.  However, free_huge_page can not adjust the
+ * reserve map.  Adjust the reserve map here to be consistent with global
+ * reserve count adjustments to be made by free_huge_page.
  */
 static void restore_reserve_on_error(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long address,
 			struct page *page)
 {
-	if (unlikely(PagePrivate(page))) {
+	if (unlikely(HPageRestoreReserve(page))) {
 		long rc = vma_needs_reservation(h, vma, address);
 
 		if (unlikely(rc < 0)) {
 			/*
 			 * Rare out of memory condition in reserve map
-			 * manipulation.  Clear PagePrivate so that
+			 * manipulation.  Clear HPageRestoreReserve so that
 			 * global reserve count will not be incremented
 			 * by free_huge_page.  This will make it appear
 			 * as though the reservation for this page was
@@ -2280,7 +2228,7 @@ static void restore_reserve_on_error(struct hstate *h,
 			 * is better than inconsistent global huge page
 			 * accounting of reserve counts.
 			 */
-			ClearPagePrivate(page);
+			ClearHPageRestoreReserve(page);
 		} else if (rc) {
 			rc = vma_add_reservation(h, vma, address);
 			if (unlikely(rc < 0))
@@ -2288,7 +2236,7 @@ static void restore_reserve_on_error(struct hstate *h,
 				 * See above comment about rare out of
 				 * memory condition.
 				 */
-				ClearPagePrivate(page);
+				ClearHPageRestoreReserve(page);
 		} else
 			vma_end_reservation(h, vma, address);
 	}
@@ -2369,7 +2317,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 		if (!page)
 			goto out_uncharge_cgroup;
 		if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
-			SetPagePrivate(page);
+			SetHPageRestoreReserve(page);
 			h->resv_huge_pages--;
 		}
 		spin_lock(&hugetlb_lock);
@@ -2387,7 +2335,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 
 	spin_unlock(&hugetlb_lock);
 
-	set_page_private(page, (unsigned long)spool);
+	hugetlb_set_page_subpool(page, spool);
 
 	map_commit = vma_commit_reservation(h, vma, addr);
 	if (unlikely(map_chg > map_commit)) {
@@ -2476,7 +2424,7 @@ static void __init gather_bootmem_prealloc(void)
 		struct hstate *h = m->hstate;
 
 		WARN_ON(page_count(page) != 1);
-		prep_compound_huge_page(page, h->order);
+		prep_compound_huge_page(page, huge_page_order(h));
 		WARN_ON(PageReserved(page));
 		prep_new_huge_page(h, page, page_to_nid(page));
 		put_page(page); /* free it into the hugepage allocator */
@@ -2488,7 +2436,7 @@ static void __init gather_bootmem_prealloc(void)
 		 * side-effects, like CommitLimit going negative.
 		 */
 		if (hstate_is_gigantic(h))
-			adjust_managed_page_count(page, 1 << h->order);
+			adjust_managed_page_count(page, pages_per_huge_page(h));
 		cond_resched();
 	}
 }
@@ -2520,7 +2468,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 		if (hstate_is_gigantic(h)) {
 			if (hugetlb_cma_size) {
 				pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
-				break;
+				goto free;
 			}
 			if (!alloc_bootmem_huge_page(h))
 				break;
@@ -2538,7 +2486,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 			h->max_huge_pages, buf, i);
 		h->max_huge_pages = i;
 	}
-
+free:
 	kfree(node_alloc_noretry);
 }
 
@@ -2988,8 +2936,10 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
 		return -ENOMEM;
 
 	retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
-	if (retval)
+	if (retval) {
 		kobject_put(hstate_kobjs[hi]);
+		hstate_kobjs[hi] = NULL;
+	}
 
 	return retval;
 }
@@ -3159,6 +3109,9 @@ static int __init hugetlb_init(void)
 {
 	int i;
 
+	BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE <
+			__NR_HPAGEFLAGS);
+
 	if (!hugepages_supported()) {
 		if (hugetlb_max_hstate || default_hstate_max_huge_pages)
 			pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n");
@@ -3239,7 +3192,7 @@ void __init hugetlb_add_hstate(unsigned int order)
 	BUG_ON(order == 0);
 	h = &hstates[hugetlb_max_hstate++];
 	h->order = order;
-	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
+	h->mask = ~(huge_page_size(h) - 1);
 	for (i = 0; i < MAX_NUMNODES; ++i)
 		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
 	INIT_LIST_HEAD(&h->hugepage_activelist);
@@ -3408,8 +3361,7 @@ static unsigned int allowed_mems_nr(struct hstate *h)
 	mpol_allowed = policy_nodemask_current(gfp_mask);
 
 	for_each_node_mask(node, cpuset_current_mems_allowed) {
-		if (!mpol_allowed ||
-		    (mpol_allowed && node_isset(node, *mpol_allowed)))
+		if (!mpol_allowed || node_isset(node, *mpol_allowed))
 			nr += array[node];
 	}
 
@@ -3515,7 +3467,7 @@ void hugetlb_report_meminfo(struct seq_file *m)
 	for_each_hstate(h) {
 		unsigned long count = h->nr_huge_pages;
 
-		total += (PAGE_SIZE << huge_page_order(h)) * count;
+		total += huge_page_size(h) * count;
 
 		if (h == &default_hstate)
 			seq_printf(m,
@@ -3528,10 +3480,10 @@ void hugetlb_report_meminfo(struct seq_file *m)
 				   h->free_huge_pages,
 				   h->resv_huge_pages,
 				   h->surplus_huge_pages,
-				   (PAGE_SIZE << huge_page_order(h)) / 1024);
+				   huge_page_size(h) / SZ_1K);
 	}
 
-	seq_printf(m, "Hugetlb:        %8lu kB\n", total / 1024);
+	seq_printf(m, "Hugetlb:        %8lu kB\n", total / SZ_1K);
 }
 
 int hugetlb_report_node_meminfo(char *buf, int len, int nid)
@@ -3565,7 +3517,7 @@ void hugetlb_show_meminfo(void)
 				h->nr_huge_pages_node[nid],
 				h->free_huge_pages_node[nid],
 				h->surplus_huge_pages_node[nid],
-				1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
+				huge_page_size(h) / SZ_1K);
 }
 
 void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
@@ -3589,6 +3541,9 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
 {
 	int ret = -ENOMEM;
 
+	if (!delta)
+		return 0;
+
 	spin_lock(&hugetlb_lock);
 	/*
 	 * When cpuset is configured, it breaks the strict hugetlb page
@@ -3685,15 +3640,13 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
 
 static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma)
 {
-	struct hstate *hstate = hstate_vma(vma);
-
-	return 1UL << huge_page_shift(hstate);
+	return huge_page_size(hstate_vma(vma));
 }
 
 /*
  * We cannot handle pagefaults against hugetlb pages at all.  They cause
  * handle_mm_fault() to try to instantiate regular-sized pages in the
- * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
+ * hugepage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
  * this far.
  */
 static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
@@ -4017,7 +3970,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 
 /*
  * This is called when the original mapper is failing to COW a MAP_PRIVATE
- * mappping it owns the reserve page for. The intention is to unmap the page
+ * mapping it owns the reserve page for. The intention is to unmap the page
  * from other VMAs and let the children be SIGKILLed if they are faulting the
  * same region.
  */
@@ -4196,7 +4149,7 @@ retry_avoidcopy:
 	spin_lock(ptl);
 	ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
 	if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) {
-		ClearPagePrivate(new_page);
+		ClearHPageRestoreReserve(new_page);
 
 		/* Break COW */
 		huge_ptep_clear_flush(vma, haddr, ptep);
@@ -4205,7 +4158,7 @@ retry_avoidcopy:
 				make_huge_pte(vma, new_page, 1));
 		page_remove_rmap(old_page, true);
 		hugepage_add_new_anon_rmap(new_page, vma, haddr);
-		set_page_huge_active(new_page);
+		SetHPageMigratable(new_page);
 		/* Make the old page be freed below */
 		new_page = old_page;
 	}
@@ -4263,7 +4216,7 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 
 	if (err)
 		return err;
-	ClearPagePrivate(page);
+	ClearHPageRestoreReserve(page);
 
 	/*
 	 * set page dirty so that it will not be removed from cache/file
@@ -4425,7 +4378,7 @@ retry:
 		goto backout;
 
 	if (anon_rmap) {
-		ClearPagePrivate(page);
+		ClearHPageRestoreReserve(page);
 		hugepage_add_new_anon_rmap(page, vma, haddr);
 	} else
 		page_dup_rmap(page, true);
@@ -4442,12 +4395,12 @@ retry:
 	spin_unlock(ptl);
 
 	/*
-	 * Only make newly allocated pages active.  Existing pages found
-	 * in the pagecache could be !page_huge_active() if they have been
-	 * isolated for migration.
+	 * Only set HPageMigratable in newly allocated pages.  Existing pages
+	 * found in the pagecache may not have HPageMigratableset if they have
+	 * been isolated for migration.
 	 */
 	if (new_page)
-		set_page_huge_active(page);
+		SetHPageMigratable(page);
 
 	unlock_page(page);
 out:
@@ -4477,7 +4430,7 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
 }
 #else
 /*
- * For uniprocesor systems we always use a single mutex, so just
+ * For uniprocessor systems we always use a single mutex, so just
  * return 0 and avoid the hashing overhead.
  */
 u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
@@ -4739,7 +4692,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	if (vm_shared) {
 		page_dup_rmap(page, true);
 	} else {
-		ClearPagePrivate(page);
+		ClearHPageRestoreReserve(page);
 		hugepage_add_new_anon_rmap(page, dst_vma, dst_addr);
 	}
 
@@ -4758,7 +4711,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	update_mmu_cache(dst_vma, dst_addr, dst_pte);
 
 	spin_unlock(ptl);
-	set_page_huge_active(page);
+	SetHPageMigratable(page);
 	if (vm_shared)
 		unlock_page(page);
 	ret = 0;
@@ -4773,6 +4726,20 @@ out_release_nounlock:
 	goto out;
 }
 
+static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma,
+				 int refs, struct page **pages,
+				 struct vm_area_struct **vmas)
+{
+	int nr;
+
+	for (nr = 0; nr < refs; nr++) {
+		if (likely(pages))
+			pages[nr] = mem_map_offset(page, nr);
+		if (vmas)
+			vmas[nr] = vma;
+	}
+}
+
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
@@ -4782,7 +4749,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long vaddr = *position;
 	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
-	int err = -EFAULT;
+	int err = -EFAULT, refs;
 
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
@@ -4902,20 +4869,29 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			continue;
 		}
 
-same_page:
+		refs = min3(pages_per_huge_page(h) - pfn_offset,
+			    (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder);
+
+		if (pages || vmas)
+			record_subpages_vmas(mem_map_offset(page, pfn_offset),
+					     vma, refs,
+					     likely(pages) ? pages + i : NULL,
+					     vmas ? vmas + i : NULL);
+
 		if (pages) {
-			pages[i] = mem_map_offset(page, pfn_offset);
 			/*
-			 * try_grab_page() should always succeed here, because:
-			 * a) we hold the ptl lock, and b) we've just checked
-			 * that the huge page is present in the page tables. If
-			 * the huge page is present, then the tail pages must
-			 * also be present. The ptl prevents the head page and
-			 * tail pages from being rearranged in any way. So this
-			 * page must be available at this point, unless the page
-			 * refcount overflowed:
+			 * try_grab_compound_head() should always succeed here,
+			 * because: a) we hold the ptl lock, and b) we've just
+			 * checked that the huge page is present in the page
+			 * tables. If the huge page is present, then the tail
+			 * pages must also be present. The ptl prevents the
+			 * head page and tail pages from being rearranged in
+			 * any way. So this page must be available at this
+			 * point, unless the page refcount overflowed:
 			 */
-			if (WARN_ON_ONCE(!try_grab_page(pages[i], flags))) {
+			if (WARN_ON_ONCE(!try_grab_compound_head(pages[i],
+								 refs,
+								 flags))) {
 				spin_unlock(ptl);
 				remainder = 0;
 				err = -ENOMEM;
@@ -4923,21 +4899,10 @@ same_page:
 			}
 		}
 
-		if (vmas)
-			vmas[i] = vma;
-
-		vaddr += PAGE_SIZE;
-		++pfn_offset;
-		--remainder;
-		++i;
-		if (vaddr < vma->vm_end && remainder &&
-				pfn_offset < pages_per_huge_page(h)) {
-			/*
-			 * We use pfn_offset to avoid touching the pageframes
-			 * of this compound page.
-			 */
-			goto same_page;
-		}
+		vaddr += (refs << PAGE_SHIFT);
+		remainder -= refs;
+		i += refs;
+
 		spin_unlock(ptl);
 	}
 	*nr_pages = remainder;
@@ -5051,12 +5016,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	return pages << h->order;
 }
 
-int hugetlb_reserve_pages(struct inode *inode,
+/* Return true if reservation was successful, false otherwise.  */
+bool hugetlb_reserve_pages(struct inode *inode,
 					long from, long to,
 					struct vm_area_struct *vma,
 					vm_flags_t vm_flags)
 {
-	long ret, chg, add = -1;
+	long chg, add = -1;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
@@ -5066,7 +5032,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	/* This should never happen */
 	if (from > to) {
 		VM_WARN(1, "%s called with a negative range\n", __func__);
-		return -EINVAL;
+		return false;
 	}
 
 	/*
@@ -5075,7 +5041,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * without using reserves
 	 */
 	if (vm_flags & VM_NORESERVE)
-		return 0;
+		return true;
 
 	/*
 	 * Shared mappings base their reservation on the number of pages that
@@ -5097,7 +5063,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 		/* Private mapping. */
 		resv_map = resv_map_alloc();
 		if (!resv_map)
-			return -ENOMEM;
+			return false;
 
 		chg = to - from;
 
@@ -5105,18 +5071,12 @@ int hugetlb_reserve_pages(struct inode *inode,
 		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
 	}
 
-	if (chg < 0) {
-		ret = chg;
+	if (chg < 0)
 		goto out_err;
-	}
 
-	ret = hugetlb_cgroup_charge_cgroup_rsvd(
-		hstate_index(h), chg * pages_per_huge_page(h), &h_cg);
-
-	if (ret < 0) {
-		ret = -ENOMEM;
+	if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h),
+				chg * pages_per_huge_page(h), &h_cg) < 0)
 		goto out_err;
-	}
 
 	if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) {
 		/* For private mappings, the hugetlb_cgroup uncharge info hangs
@@ -5131,19 +5091,15 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * reservations already in place (gbl_reserve).
 	 */
 	gbl_reserve = hugepage_subpool_get_pages(spool, chg);
-	if (gbl_reserve < 0) {
-		ret = -ENOSPC;
+	if (gbl_reserve < 0)
 		goto out_uncharge_cgroup;
-	}
 
 	/*
 	 * Check enough hugepages are available for the reservation.
 	 * Hand the pages back to the subpool if there are not
 	 */
-	ret = hugetlb_acct_memory(h, gbl_reserve);
-	if (ret < 0) {
+	if (hugetlb_acct_memory(h, gbl_reserve) < 0)
 		goto out_put_pages;
-	}
 
 	/*
 	 * Account for the reservations made. Shared mappings record regions
@@ -5161,7 +5117,6 @@ int hugetlb_reserve_pages(struct inode *inode,
 
 		if (unlikely(add < 0)) {
 			hugetlb_acct_memory(h, -gbl_reserve);
-			ret = add;
 			goto out_put_pages;
 		} else if (unlikely(chg > add)) {
 			/*
@@ -5182,7 +5137,8 @@ int hugetlb_reserve_pages(struct inode *inode,
 			hugetlb_acct_memory(h, -rsv_adjust);
 		}
 	}
-	return 0;
+	return true;
+
 out_put_pages:
 	/* put back original number of pages, chg */
 	(void)hugepage_subpool_put_pages(spool, chg);
@@ -5198,7 +5154,7 @@ out_err:
 			region_abort(resv_map, from, to, regions_needed);
 	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_put(&resv_map->refs, resv_map_release);
-	return ret;
+	return false;
 }
 
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
@@ -5259,7 +5215,7 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
 	 */
 	if (pmd_index(addr) != pmd_index(saddr) ||
 	    vm_flags != svm_flags ||
-	    sbase < svma->vm_start || svma->vm_end < s_end)
+	    !range_in_vma(svma, sbase, s_end))
 		return 0;
 
 	return saddr;
@@ -5286,21 +5242,23 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end)
 {
-	unsigned long a_start, a_end;
+	unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE),
+		v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
 
-	if (!(vma->vm_flags & VM_MAYSHARE))
+	/*
+	 * vma need span at least one aligned PUD size and the start,end range
+	 * must at least partialy within it.
+	 */
+	if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) ||
+		(*end <= v_start) || (*start >= v_end))
 		return;
 
 	/* Extend the range to be PUD aligned for a worst case scenario */
-	a_start = ALIGN_DOWN(*start, PUD_SIZE);
-	a_end = ALIGN(*end, PUD_SIZE);
+	if (*start > v_start)
+		*start = ALIGN_DOWN(*start, PUD_SIZE);
 
-	/*
-	 * Intersect the range with the vma range, since pmd sharing won't be
-	 * across vma after all
-	 */
-	*start = max(vma->vm_start, a_start);
-	*end = min(vma->vm_end, a_end);
+	if (*end < v_end)
+		*end = ALIGN(*end, PUD_SIZE);
 }
 
 /*
@@ -5583,12 +5541,13 @@ bool isolate_huge_page(struct page *page, struct list_head *list)
 	bool ret = true;
 
 	spin_lock(&hugetlb_lock);
-	if (!PageHeadHuge(page) || !page_huge_active(page) ||
+	if (!PageHeadHuge(page) ||
+	    !HPageMigratable(page) ||
 	    !get_page_unless_zero(page)) {
 		ret = false;
 		goto unlock;
 	}
-	clear_page_huge_active(page);
+	ClearHPageMigratable(page);
 	list_move_tail(&page->lru, list);
 unlock:
 	spin_unlock(&hugetlb_lock);
@@ -5597,9 +5556,8 @@ unlock:
 
 void putback_active_hugepage(struct page *page)
 {
-	VM_BUG_ON_PAGE(!PageHead(page), page);
 	spin_lock(&hugetlb_lock);
-	set_page_huge_active(page);
+	SetHPageMigratable(page);
 	list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist);
 	spin_unlock(&hugetlb_lock);
 	put_page(page);
@@ -5622,12 +5580,12 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason)
 	 * here as well otherwise the global surplus count will not match
 	 * the per-node's.
 	 */
-	if (PageHugeTemporary(newpage)) {
+	if (HPageTemporary(newpage)) {
 		int old_nid = page_to_nid(oldpage);
 		int new_nid = page_to_nid(newpage);
 
-		SetPageHugeTemporary(oldpage);
-		ClearPageHugeTemporary(newpage);
+		SetHPageTemporary(oldpage);
+		ClearHPageTemporary(newpage);
 
 		spin_lock(&hugetlb_lock);
 		if (h->surplus_huge_pages_node[old_nid]) {
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 9182848dda3e..f68b51fcda3d 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -113,7 +113,7 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup,
 			rsvd_parent);
 
 		limit = round_down(PAGE_COUNTER_MAX,
-				   1 << huge_page_order(&hstates[idx]));
+				   pages_per_huge_page(&hstates[idx]));
 
 		ret = page_counter_set_max(
 			hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx),
@@ -460,7 +460,7 @@ static int hugetlb_cgroup_read_u64_max(struct seq_file *seq, void *v)
 	counter = &h_cg->hugepage[idx];
 
 	limit = round_down(PAGE_COUNTER_MAX,
-			   1 << huge_page_order(&hstates[idx]));
+			   pages_per_huge_page(&hstates[idx]));
 
 	switch (MEMFILE_ATTR(cft->private)) {
 	case RES_RSVD_USAGE:
@@ -507,7 +507,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 		return ret;
 
 	idx = MEMFILE_IDX(of_cft(of)->private);
-	nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx]));
+	nr_pages = round_down(nr_pages, pages_per_huge_page(&hstates[idx]));
 
 	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_RSVD_LIMIT:
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index b25167664ead..b18189ef3a92 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -60,7 +60,7 @@ void kasan_disable_current(void)
 
 void __kasan_unpoison_range(const void *address, size_t size)
 {
-	unpoison_range(address, size);
+	kasan_unpoison(address, size);
 }
 
 #if CONFIG_KASAN_STACK
@@ -69,7 +69,7 @@ void kasan_unpoison_task_stack(struct task_struct *task)
 {
 	void *base = task_stack_page(task);
 
-	unpoison_range(base, THREAD_SIZE);
+	kasan_unpoison(base, THREAD_SIZE);
 }
 
 /* Unpoison the stack for the current task beyond a watermark sp value. */
@@ -82,7 +82,7 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 	 */
 	void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1));
 
-	unpoison_range(base, watermark - base);
+	kasan_unpoison(base, watermark - base);
 }
 #endif /* CONFIG_KASAN_STACK */
 
@@ -105,18 +105,17 @@ void __kasan_alloc_pages(struct page *page, unsigned int order)
 	if (unlikely(PageHighMem(page)))
 		return;
 
-	tag = random_tag();
+	tag = kasan_random_tag();
 	for (i = 0; i < (1 << order); i++)
 		page_kasan_tag_set(page + i, tag);
-	unpoison_range(page_address(page), PAGE_SIZE << order);
+	kasan_unpoison(page_address(page), PAGE_SIZE << order);
 }
 
 void __kasan_free_pages(struct page *page, unsigned int order)
 {
 	if (likely(!PageHighMem(page)))
-		poison_range(page_address(page),
-				PAGE_SIZE << order,
-				KASAN_FREE_PAGE);
+		kasan_poison(page_address(page), PAGE_SIZE << order,
+			     KASAN_FREE_PAGE);
 }
 
 /*
@@ -246,18 +245,18 @@ void __kasan_poison_slab(struct page *page)
 
 	for (i = 0; i < compound_nr(page); i++)
 		page_kasan_tag_reset(page + i);
-	poison_range(page_address(page), page_size(page),
+	kasan_poison(page_address(page), page_size(page),
 		     KASAN_KMALLOC_REDZONE);
 }
 
 void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
 {
-	unpoison_range(object, cache->object_size);
+	kasan_unpoison(object, cache->object_size);
 }
 
 void __kasan_poison_object_data(struct kmem_cache *cache, void *object)
 {
-	poison_range(object, cache->object_size, KASAN_KMALLOC_REDZONE);
+	kasan_poison(object, cache->object_size, KASAN_KMALLOC_REDZONE);
 }
 
 /*
@@ -294,7 +293,7 @@ static u8 assign_tag(struct kmem_cache *cache, const void *object,
 	 * set, assign a tag when the object is being allocated (init == false).
 	 */
 	if (!cache->ctor && !(cache->flags & SLAB_TYPESAFE_BY_RCU))
-		return init ? KASAN_TAG_KERNEL : random_tag();
+		return init ? KASAN_TAG_KERNEL : kasan_random_tag();
 
 	/* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */
 #ifdef CONFIG_SLAB
@@ -305,7 +304,7 @@ static u8 assign_tag(struct kmem_cache *cache, const void *object,
 	 * For SLUB assign a random tag during slab creation, otherwise reuse
 	 * the already assigned tag.
 	 */
-	return init ? random_tag() : get_tag(object);
+	return init ? kasan_random_tag() : get_tag(object);
 #endif
 }
 
@@ -346,12 +345,12 @@ static bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 	if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
 		return false;
 
-	if (check_invalid_free(tagged_object)) {
+	if (!kasan_byte_accessible(tagged_object)) {
 		kasan_report_invalid_free(tagged_object, ip);
 		return true;
 	}
 
-	poison_range(object, cache->object_size, KASAN_KMALLOC_FREE);
+	kasan_poison(object, cache->object_size, KASAN_KMALLOC_FREE);
 
 	if (!kasan_stack_collection_enabled())
 		return false;
@@ -361,7 +360,7 @@ static bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 
 	kasan_set_free_info(cache, object, tag);
 
-	return quarantine_put(cache, object);
+	return kasan_quarantine_put(cache, object);
 }
 
 bool __kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip)
@@ -386,7 +385,7 @@ void __kasan_slab_free_mempool(void *ptr, unsigned long ip)
 			kasan_report_invalid_free(ptr, ip);
 			return;
 		}
-		poison_range(ptr, page_size(page), KASAN_FREE_PAGE);
+		kasan_poison(ptr, page_size(page), KASAN_FREE_PAGE);
 	} else {
 		____kasan_slab_free(page->slab_cache, ptr, ip, false);
 	}
@@ -409,7 +408,7 @@ static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object,
 	u8 tag;
 
 	if (gfpflags_allow_blocking(flags))
-		quarantine_reduce();
+		kasan_quarantine_reduce();
 
 	if (unlikely(object == NULL))
 		return NULL;
@@ -421,9 +420,9 @@ static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object,
 	tag = assign_tag(cache, object, false, keep_tag);
 
 	/* Tag is ignored in set_tag without CONFIG_KASAN_SW/HW_TAGS */
-	unpoison_range(set_tag(object, tag), size);
-	poison_range((void *)redzone_start, redzone_end - redzone_start,
-		     KASAN_KMALLOC_REDZONE);
+	kasan_unpoison(set_tag(object, tag), size);
+	kasan_poison((void *)redzone_start, redzone_end - redzone_start,
+			   KASAN_KMALLOC_REDZONE);
 
 	if (kasan_stack_collection_enabled())
 		set_alloc_info(cache, (void *)object, flags);
@@ -452,7 +451,7 @@ void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size,
 	unsigned long redzone_end;
 
 	if (gfpflags_allow_blocking(flags))
-		quarantine_reduce();
+		kasan_quarantine_reduce();
 
 	if (unlikely(ptr == NULL))
 		return NULL;
@@ -462,8 +461,8 @@ void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size,
 				KASAN_GRANULE_SIZE);
 	redzone_end = (unsigned long)ptr + page_size(page);
 
-	unpoison_range(ptr, size);
-	poison_range((void *)redzone_start, redzone_end - redzone_start,
+	kasan_unpoison(ptr, size);
+	kasan_poison((void *)redzone_start, redzone_end - redzone_start,
 		     KASAN_PAGE_REDZONE);
 
 	return (void *)ptr;
@@ -491,3 +490,12 @@ void __kasan_kfree_large(void *ptr, unsigned long ip)
 		kasan_report_invalid_free(ptr, ip);
 	/* The object will be poisoned by kasan_free_pages(). */
 }
+
+bool __kasan_check_byte(const void *address, unsigned long ip)
+{
+	if (!kasan_byte_accessible(address)) {
+		kasan_report((unsigned long)address, 1, false, ip);
+		return false;
+	}
+	return true;
+}
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 5106b84b07d4..3f17a1218055 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -158,7 +158,7 @@ static __always_inline bool memory_is_poisoned(unsigned long addr, size_t size)
 	return memory_is_poisoned_n(addr, size);
 }
 
-static __always_inline bool check_memory_region_inline(unsigned long addr,
+static __always_inline bool check_region_inline(unsigned long addr,
 						size_t size, bool write,
 						unsigned long ret_ip)
 {
@@ -179,37 +179,37 @@ static __always_inline bool check_memory_region_inline(unsigned long addr,
 	return !kasan_report(addr, size, write, ret_ip);
 }
 
-bool check_memory_region(unsigned long addr, size_t size, bool write,
-				unsigned long ret_ip)
+bool kasan_check_range(unsigned long addr, size_t size, bool write,
+					unsigned long ret_ip)
 {
-	return check_memory_region_inline(addr, size, write, ret_ip);
+	return check_region_inline(addr, size, write, ret_ip);
 }
 
-bool check_invalid_free(void *addr)
+bool kasan_byte_accessible(const void *addr)
 {
 	s8 shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr));
 
-	return shadow_byte < 0 || shadow_byte >= KASAN_GRANULE_SIZE;
+	return shadow_byte >= 0 && shadow_byte < KASAN_GRANULE_SIZE;
 }
 
 void kasan_cache_shrink(struct kmem_cache *cache)
 {
-	quarantine_remove_cache(cache);
+	kasan_quarantine_remove_cache(cache);
 }
 
 void kasan_cache_shutdown(struct kmem_cache *cache)
 {
 	if (!__kmem_cache_empty(cache))
-		quarantine_remove_cache(cache);
+		kasan_quarantine_remove_cache(cache);
 }
 
 static void register_global(struct kasan_global *global)
 {
 	size_t aligned_size = round_up(global->size, KASAN_GRANULE_SIZE);
 
-	unpoison_range(global->beg, global->size);
+	kasan_unpoison(global->beg, global->size);
 
-	poison_range(global->beg + aligned_size,
+	kasan_poison(global->beg + aligned_size,
 		     global->size_with_redzone - aligned_size,
 		     KASAN_GLOBAL_REDZONE);
 }
@@ -231,7 +231,7 @@ EXPORT_SYMBOL(__asan_unregister_globals);
 #define DEFINE_ASAN_LOAD_STORE(size)					\
 	void __asan_load##size(unsigned long addr)			\
 	{								\
-		check_memory_region_inline(addr, size, false, _RET_IP_);\
+		check_region_inline(addr, size, false, _RET_IP_);	\
 	}								\
 	EXPORT_SYMBOL(__asan_load##size);				\
 	__alias(__asan_load##size)					\
@@ -239,7 +239,7 @@ EXPORT_SYMBOL(__asan_unregister_globals);
 	EXPORT_SYMBOL(__asan_load##size##_noabort);			\
 	void __asan_store##size(unsigned long addr)			\
 	{								\
-		check_memory_region_inline(addr, size, true, _RET_IP_);	\
+		check_region_inline(addr, size, true, _RET_IP_);	\
 	}								\
 	EXPORT_SYMBOL(__asan_store##size);				\
 	__alias(__asan_store##size)					\
@@ -254,7 +254,7 @@ DEFINE_ASAN_LOAD_STORE(16);
 
 void __asan_loadN(unsigned long addr, size_t size)
 {
-	check_memory_region(addr, size, false, _RET_IP_);
+	kasan_check_range(addr, size, false, _RET_IP_);
 }
 EXPORT_SYMBOL(__asan_loadN);
 
@@ -264,7 +264,7 @@ EXPORT_SYMBOL(__asan_loadN_noabort);
 
 void __asan_storeN(unsigned long addr, size_t size)
 {
-	check_memory_region(addr, size, true, _RET_IP_);
+	kasan_check_range(addr, size, true, _RET_IP_);
 }
 EXPORT_SYMBOL(__asan_storeN);
 
@@ -290,11 +290,11 @@ void __asan_alloca_poison(unsigned long addr, size_t size)
 
 	WARN_ON(!IS_ALIGNED(addr, KASAN_ALLOCA_REDZONE_SIZE));
 
-	unpoison_range((const void *)(addr + rounded_down_size),
-		       size - rounded_down_size);
-	poison_range(left_redzone, KASAN_ALLOCA_REDZONE_SIZE,
+	kasan_unpoison((const void *)(addr + rounded_down_size),
+			size - rounded_down_size);
+	kasan_poison(left_redzone, KASAN_ALLOCA_REDZONE_SIZE,
 		     KASAN_ALLOCA_LEFT);
-	poison_range(right_redzone, padding_size + KASAN_ALLOCA_REDZONE_SIZE,
+	kasan_poison(right_redzone, padding_size + KASAN_ALLOCA_REDZONE_SIZE,
 		     KASAN_ALLOCA_RIGHT);
 }
 EXPORT_SYMBOL(__asan_alloca_poison);
@@ -305,7 +305,7 @@ void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom)
 	if (unlikely(!stack_top || stack_top > stack_bottom))
 		return;
 
-	unpoison_range(stack_top, stack_bottom - stack_top);
+	kasan_unpoison(stack_top, stack_bottom - stack_top);
 }
 EXPORT_SYMBOL(__asan_allocas_unpoison);
 
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index d558799b25b3..b31aeef505dd 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -185,3 +185,19 @@ struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
 
 	return &alloc_meta->free_track[0];
 }
+
+#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
+
+void kasan_set_tagging_report_once(bool state)
+{
+	hw_set_tagging_report_once(state);
+}
+EXPORT_SYMBOL_GPL(kasan_set_tagging_report_once);
+
+void kasan_enable_tagging(void)
+{
+	hw_enable_tagging();
+}
+EXPORT_SYMBOL_GPL(kasan_enable_tagging);
+
+#endif
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 8c706e7652f2..cc14b6e6c14c 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -36,6 +36,12 @@ extern bool kasan_flag_panic __ro_after_init;
 #define KASAN_TAG_INVALID	0xFE /* inaccessible memory tag */
 #define KASAN_TAG_MAX		0xFD /* maximum value for random tags */
 
+#ifdef CONFIG_KASAN_HW_TAGS
+#define KASAN_TAG_MIN		0xF0 /* mimimum value for random tags */
+#else
+#define KASAN_TAG_MIN		0x00 /* mimimum value for random tags */
+#endif
+
 #ifdef CONFIG_KASAN_GENERIC
 #define KASAN_FREE_PAGE         0xFF  /* page was freed */
 #define KASAN_PAGE_REDZONE      0xFE  /* redzone for kmalloc_large allocations */
@@ -195,14 +201,14 @@ static inline bool addr_has_metadata(const void *addr)
 }
 
 /**
- * check_memory_region - Check memory region, and report if invalid access.
+ * kasan_check_range - Check memory region, and report if invalid access.
  * @addr: the accessed address
  * @size: the accessed size
  * @write: true if access is a write access
  * @ret_ip: return address
  * @return: true if access was valid, false if invalid
  */
-bool check_memory_region(unsigned long addr, size_t size, bool write,
+bool kasan_check_range(unsigned long addr, size_t size, bool write,
 				unsigned long ret_ip);
 
 #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
@@ -215,19 +221,19 @@ static inline bool addr_has_metadata(const void *addr)
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
-void print_tags(u8 addr_tag, const void *addr);
+void kasan_print_tags(u8 addr_tag, const void *addr);
 #else
-static inline void print_tags(u8 addr_tag, const void *addr) { }
+static inline void kasan_print_tags(u8 addr_tag, const void *addr) { }
 #endif
 
-void *find_first_bad_addr(void *addr, size_t size);
-const char *get_bug_type(struct kasan_access_info *info);
-void metadata_fetch_row(char *buffer, void *row);
+void *kasan_find_first_bad_addr(void *addr, size_t size);
+const char *kasan_get_bug_type(struct kasan_access_info *info);
+void kasan_metadata_fetch_row(char *buffer, void *row);
 
 #if defined(CONFIG_KASAN_GENERIC) && CONFIG_KASAN_STACK
-void print_address_stack_frame(const void *addr);
+void kasan_print_address_stack_frame(const void *addr);
 #else
-static inline void print_address_stack_frame(const void *addr) { }
+static inline void kasan_print_address_stack_frame(const void *addr) { }
 #endif
 
 bool kasan_report(unsigned long addr, size_t size,
@@ -244,13 +250,13 @@ struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
 
 #if defined(CONFIG_KASAN_GENERIC) && \
 	(defined(CONFIG_SLAB) || defined(CONFIG_SLUB))
-bool quarantine_put(struct kmem_cache *cache, void *object);
-void quarantine_reduce(void);
-void quarantine_remove_cache(struct kmem_cache *cache);
+bool kasan_quarantine_put(struct kmem_cache *cache, void *object);
+void kasan_quarantine_reduce(void);
+void kasan_quarantine_remove_cache(struct kmem_cache *cache);
 #else
-static inline bool quarantine_put(struct kmem_cache *cache, void *object) { return false; }
-static inline void quarantine_reduce(void) { }
-static inline void quarantine_remove_cache(struct kmem_cache *cache) { }
+static inline bool kasan_quarantine_put(struct kmem_cache *cache, void *object) { return false; }
+static inline void kasan_quarantine_reduce(void) { }
+static inline void kasan_quarantine_remove_cache(struct kmem_cache *cache) { }
 #endif
 
 #ifndef arch_kasan_set_tag
@@ -274,6 +280,9 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
 #ifndef arch_init_tags
 #define arch_init_tags(max_tag)
 #endif
+#ifndef arch_set_tagging_report_once
+#define arch_set_tagging_report_once(state)
+#endif
 #ifndef arch_get_random_tag
 #define arch_get_random_tag()	(0xFF)
 #endif
@@ -286,48 +295,66 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
 
 #define hw_enable_tagging()			arch_enable_tagging()
 #define hw_init_tags(max_tag)			arch_init_tags(max_tag)
+#define hw_set_tagging_report_once(state)	arch_set_tagging_report_once(state)
 #define hw_get_random_tag()			arch_get_random_tag()
 #define hw_get_mem_tag(addr)			arch_get_mem_tag(addr)
 #define hw_set_mem_tag_range(addr, size, tag)	arch_set_mem_tag_range((addr), (size), (tag))
 
+#else /* CONFIG_KASAN_HW_TAGS */
+
+#define hw_enable_tagging()
+#define hw_set_tagging_report_once(state)
+
 #endif /* CONFIG_KASAN_HW_TAGS */
 
+#if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
+
+void kasan_set_tagging_report_once(bool state);
+void kasan_enable_tagging(void);
+
+#else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */
+
+static inline void kasan_set_tagging_report_once(bool state) { }
+static inline void kasan_enable_tagging(void) { }
+
+#endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */
+
 #ifdef CONFIG_KASAN_SW_TAGS
-u8 random_tag(void);
+u8 kasan_random_tag(void);
 #elif defined(CONFIG_KASAN_HW_TAGS)
-static inline u8 random_tag(void) { return hw_get_random_tag(); }
+static inline u8 kasan_random_tag(void) { return hw_get_random_tag(); }
 #else
-static inline u8 random_tag(void) { return 0; }
+static inline u8 kasan_random_tag(void) { return 0; }
 #endif
 
 #ifdef CONFIG_KASAN_HW_TAGS
 
-static inline void poison_range(const void *address, size_t size, u8 value)
+static inline void kasan_poison(const void *address, size_t size, u8 value)
 {
 	hw_set_mem_tag_range(kasan_reset_tag(address),
 			round_up(size, KASAN_GRANULE_SIZE), value);
 }
 
-static inline void unpoison_range(const void *address, size_t size)
+static inline void kasan_unpoison(const void *address, size_t size)
 {
 	hw_set_mem_tag_range(kasan_reset_tag(address),
 			round_up(size, KASAN_GRANULE_SIZE), get_tag(address));
 }
 
-static inline bool check_invalid_free(void *addr)
+static inline bool kasan_byte_accessible(const void *addr)
 {
 	u8 ptr_tag = get_tag(addr);
-	u8 mem_tag = hw_get_mem_tag(addr);
+	u8 mem_tag = hw_get_mem_tag((void *)addr);
 
-	return (mem_tag == KASAN_TAG_INVALID) ||
-		(ptr_tag != KASAN_TAG_KERNEL && ptr_tag != mem_tag);
+	return (mem_tag != KASAN_TAG_INVALID) &&
+		(ptr_tag == KASAN_TAG_KERNEL || ptr_tag == mem_tag);
 }
 
 #else /* CONFIG_KASAN_HW_TAGS */
 
-void poison_range(const void *address, size_t size, u8 value);
-void unpoison_range(const void *address, size_t size);
-bool check_invalid_free(void *addr);
+void kasan_poison(const void *address, size_t size, u8 value);
+void kasan_unpoison(const void *address, size_t size);
+bool kasan_byte_accessible(const void *addr);
 
 #endif /* CONFIG_KASAN_HW_TAGS */
 
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 55783125a767..728fb24c5683 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -168,7 +168,7 @@ static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
 	qlist_init(q);
 }
 
-bool quarantine_put(struct kmem_cache *cache, void *object)
+bool kasan_quarantine_put(struct kmem_cache *cache, void *object)
 {
 	unsigned long flags;
 	struct qlist_head *q;
@@ -184,11 +184,11 @@ bool quarantine_put(struct kmem_cache *cache, void *object)
 
 	/*
 	 * Note: irq must be disabled until after we move the batch to the
-	 * global quarantine. Otherwise quarantine_remove_cache() can miss
-	 * some objects belonging to the cache if they are in our local temp
-	 * list. quarantine_remove_cache() executes on_each_cpu() at the
-	 * beginning which ensures that it either sees the objects in per-cpu
-	 * lists or in the global quarantine.
+	 * global quarantine. Otherwise kasan_quarantine_remove_cache() can
+	 * miss some objects belonging to the cache if they are in our local
+	 * temp list. kasan_quarantine_remove_cache() executes on_each_cpu()
+	 * at the beginning which ensures that it either sees the objects in
+	 * per-cpu lists or in the global quarantine.
 	 */
 	local_irq_save(flags);
 
@@ -222,7 +222,7 @@ bool quarantine_put(struct kmem_cache *cache, void *object)
 	return true;
 }
 
-void quarantine_reduce(void)
+void kasan_quarantine_reduce(void)
 {
 	size_t total_size, new_quarantine_size, percpu_quarantines;
 	unsigned long flags;
@@ -234,7 +234,7 @@ void quarantine_reduce(void)
 		return;
 
 	/*
-	 * srcu critical section ensures that quarantine_remove_cache()
+	 * srcu critical section ensures that kasan_quarantine_remove_cache()
 	 * will not miss objects belonging to the cache while they are in our
 	 * local to_free list. srcu is chosen because (1) it gives us private
 	 * grace period domain that does not interfere with anything else,
@@ -309,15 +309,15 @@ static void per_cpu_remove_cache(void *arg)
 }
 
 /* Free all quarantined objects belonging to cache. */
-void quarantine_remove_cache(struct kmem_cache *cache)
+void kasan_quarantine_remove_cache(struct kmem_cache *cache)
 {
 	unsigned long flags, i;
 	struct qlist_head to_free = QLIST_INIT;
 
 	/*
 	 * Must be careful to not miss any objects that are being moved from
-	 * per-cpu list to the global quarantine in quarantine_put(),
-	 * nor objects being freed in quarantine_reduce(). on_each_cpu()
+	 * per-cpu list to the global quarantine in kasan_quarantine_put(),
+	 * nor objects being freed in kasan_quarantine_reduce(). on_each_cpu()
 	 * achieves the first goal, while synchronize_srcu() achieves the
 	 * second.
 	 */
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index c0fb21797550..234f35a84f19 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -61,7 +61,7 @@ __setup("kasan_multi_shot", kasan_set_multi_shot);
 static void print_error_description(struct kasan_access_info *info)
 {
 	pr_err("BUG: KASAN: %s in %pS\n",
-		get_bug_type(info), (void *)info->ip);
+		kasan_get_bug_type(info), (void *)info->ip);
 	if (info->access_size)
 		pr_err("%s of size %zu at addr %px by task %s/%d\n",
 			info->is_write ? "Write" : "Read", info->access_size,
@@ -247,7 +247,7 @@ static void print_address_description(void *addr, u8 tag)
 		dump_page(page, "kasan: bad access detected");
 	}
 
-	print_address_stack_frame(addr);
+	kasan_print_address_stack_frame(addr);
 }
 
 static bool meta_row_is_guilty(const void *row, const void *addr)
@@ -293,7 +293,7 @@ static void print_memory_metadata(const void *addr)
 		 * function, because generic functions may try to
 		 * access kasan mapping for the passed address.
 		 */
-		metadata_fetch_row(&metadata[0], row);
+		kasan_metadata_fetch_row(&metadata[0], row);
 
 		print_hex_dump(KERN_ERR, buffer,
 			DUMP_PREFIX_NONE, META_BYTES_PER_ROW, 1,
@@ -331,7 +331,7 @@ static void kasan_update_kunit_status(struct kunit *cur_test)
 	}
 
 	kasan_data = (struct kunit_kasan_expectation *)resource->data;
-	kasan_data->report_found = true;
+	WRITE_ONCE(kasan_data->report_found, true);
 	kunit_put_resource(resource);
 }
 #endif /* IS_ENABLED(CONFIG_KUNIT) */
@@ -350,7 +350,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
 
 	start_report(&flags);
 	pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", (void *)ip);
-	print_tags(tag, object);
+	kasan_print_tags(tag, object);
 	pr_err("\n");
 	print_address_description(object, tag);
 	pr_err("\n");
@@ -378,7 +378,8 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write,
 
 	info.access_addr = tagged_addr;
 	if (addr_has_metadata(untagged_addr))
-		info.first_bad_addr = find_first_bad_addr(tagged_addr, size);
+		info.first_bad_addr =
+			kasan_find_first_bad_addr(tagged_addr, size);
 	else
 		info.first_bad_addr = untagged_addr;
 	info.access_size = size;
@@ -389,7 +390,7 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write,
 
 	print_error_description(&info);
 	if (addr_has_metadata(untagged_addr))
-		print_tags(get_tag(tagged_addr), info.first_bad_addr);
+		kasan_print_tags(get_tag(tagged_addr), info.first_bad_addr);
 	pr_err("\n");
 
 	if (addr_has_metadata(untagged_addr)) {
diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c
index 8a9c889872da..41f374585144 100644
--- a/mm/kasan/report_generic.c
+++ b/mm/kasan/report_generic.c
@@ -30,7 +30,7 @@
 #include "kasan.h"
 #include "../slab.h"
 
-void *find_first_bad_addr(void *addr, size_t size)
+void *kasan_find_first_bad_addr(void *addr, size_t size)
 {
 	void *p = addr;
 
@@ -105,7 +105,7 @@ static const char *get_wild_bug_type(struct kasan_access_info *info)
 	return bug_type;
 }
 
-const char *get_bug_type(struct kasan_access_info *info)
+const char *kasan_get_bug_type(struct kasan_access_info *info)
 {
 	/*
 	 * If access_size is a negative number, then it has reason to be
@@ -123,7 +123,7 @@ const char *get_bug_type(struct kasan_access_info *info)
 	return get_wild_bug_type(info);
 }
 
-void metadata_fetch_row(char *buffer, void *row)
+void kasan_metadata_fetch_row(char *buffer, void *row)
 {
 	memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW);
 }
@@ -263,7 +263,7 @@ static bool __must_check get_address_stack_frame_info(const void *addr,
 	return true;
 }
 
-void print_address_stack_frame(const void *addr)
+void kasan_print_address_stack_frame(const void *addr)
 {
 	unsigned long offset;
 	const char *frame_descr;
diff --git a/mm/kasan/report_hw_tags.c b/mm/kasan/report_hw_tags.c
index 57114f0e14d1..42b2168755d6 100644
--- a/mm/kasan/report_hw_tags.c
+++ b/mm/kasan/report_hw_tags.c
@@ -15,17 +15,17 @@
 
 #include "kasan.h"
 
-const char *get_bug_type(struct kasan_access_info *info)
+const char *kasan_get_bug_type(struct kasan_access_info *info)
 {
 	return "invalid-access";
 }
 
-void *find_first_bad_addr(void *addr, size_t size)
+void *kasan_find_first_bad_addr(void *addr, size_t size)
 {
 	return kasan_reset_tag(addr);
 }
 
-void metadata_fetch_row(char *buffer, void *row)
+void kasan_metadata_fetch_row(char *buffer, void *row)
 {
 	int i;
 
@@ -33,7 +33,7 @@ void metadata_fetch_row(char *buffer, void *row)
 		buffer[i] = hw_get_mem_tag(row + i * KASAN_GRANULE_SIZE);
 }
 
-void print_tags(u8 addr_tag, const void *addr)
+void kasan_print_tags(u8 addr_tag, const void *addr)
 {
 	u8 memory_tag = hw_get_mem_tag((void *)addr);
 
diff --git a/mm/kasan/report_sw_tags.c b/mm/kasan/report_sw_tags.c
index 1b026793ad57..3d20d3451d9e 100644
--- a/mm/kasan/report_sw_tags.c
+++ b/mm/kasan/report_sw_tags.c
@@ -29,7 +29,7 @@
 #include "kasan.h"
 #include "../slab.h"
 
-const char *get_bug_type(struct kasan_access_info *info)
+const char *kasan_get_bug_type(struct kasan_access_info *info)
 {
 #ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
 	struct kasan_alloc_meta *alloc_meta;
@@ -72,7 +72,7 @@ const char *get_bug_type(struct kasan_access_info *info)
 	return "invalid-access";
 }
 
-void *find_first_bad_addr(void *addr, size_t size)
+void *kasan_find_first_bad_addr(void *addr, size_t size)
 {
 	u8 tag = get_tag(addr);
 	void *p = kasan_reset_tag(addr);
@@ -83,12 +83,12 @@ void *find_first_bad_addr(void *addr, size_t size)
 	return p;
 }
 
-void metadata_fetch_row(char *buffer, void *row)
+void kasan_metadata_fetch_row(char *buffer, void *row)
 {
 	memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW);
 }
 
-void print_tags(u8 addr_tag, const void *addr)
+void kasan_print_tags(u8 addr_tag, const void *addr)
 {
 	u8 *shadow = (u8 *)kasan_mem_to_shadow(addr);
 
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index 7c2c08c55f32..80adc85d0393 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -27,20 +27,20 @@
 
 bool __kasan_check_read(const volatile void *p, unsigned int size)
 {
-	return check_memory_region((unsigned long)p, size, false, _RET_IP_);
+	return kasan_check_range((unsigned long)p, size, false, _RET_IP_);
 }
 EXPORT_SYMBOL(__kasan_check_read);
 
 bool __kasan_check_write(const volatile void *p, unsigned int size)
 {
-	return check_memory_region((unsigned long)p, size, true, _RET_IP_);
+	return kasan_check_range((unsigned long)p, size, true, _RET_IP_);
 }
 EXPORT_SYMBOL(__kasan_check_write);
 
 #undef memset
 void *memset(void *addr, int c, size_t len)
 {
-	if (!check_memory_region((unsigned long)addr, len, true, _RET_IP_))
+	if (!kasan_check_range((unsigned long)addr, len, true, _RET_IP_))
 		return NULL;
 
 	return __memset(addr, c, len);
@@ -50,8 +50,8 @@ void *memset(void *addr, int c, size_t len)
 #undef memmove
 void *memmove(void *dest, const void *src, size_t len)
 {
-	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
-	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
+	if (!kasan_check_range((unsigned long)src, len, false, _RET_IP_) ||
+	    !kasan_check_range((unsigned long)dest, len, true, _RET_IP_))
 		return NULL;
 
 	return __memmove(dest, src, len);
@@ -61,8 +61,8 @@ void *memmove(void *dest, const void *src, size_t len)
 #undef memcpy
 void *memcpy(void *dest, const void *src, size_t len)
 {
-	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
-	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
+	if (!kasan_check_range((unsigned long)src, len, false, _RET_IP_) ||
+	    !kasan_check_range((unsigned long)dest, len, true, _RET_IP_))
 		return NULL;
 
 	return __memcpy(dest, src, len);
@@ -72,7 +72,7 @@ void *memcpy(void *dest, const void *src, size_t len)
  * Poisons the shadow memory for 'size' bytes starting from 'addr'.
  * Memory addresses should be aligned to KASAN_GRANULE_SIZE.
  */
-void poison_range(const void *address, size_t size, u8 value)
+void kasan_poison(const void *address, size_t size, u8 value)
 {
 	void *shadow_start, *shadow_end;
 
@@ -89,8 +89,9 @@ void poison_range(const void *address, size_t size, u8 value)
 
 	__memset(shadow_start, value, shadow_end - shadow_start);
 }
+EXPORT_SYMBOL(kasan_poison);
 
-void unpoison_range(const void *address, size_t size)
+void kasan_unpoison(const void *address, size_t size)
 {
 	u8 tag = get_tag(address);
 
@@ -101,7 +102,7 @@ void unpoison_range(const void *address, size_t size)
 	 */
 	address = kasan_reset_tag(address);
 
-	poison_range(address, size, tag);
+	kasan_poison(address, size, tag);
 
 	if (size & KASAN_GRANULE_MASK) {
 		u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size);
@@ -286,7 +287,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 	 * // vmalloc() allocates memory
 	 * // let a = area->addr
 	 * // we reach kasan_populate_vmalloc
-	 * // and call unpoison_range:
+	 * // and call kasan_unpoison:
 	 * STORE shadow(a), unpoison_val
 	 * ...
 	 * STORE shadow(a+99), unpoison_val	x = LOAD p
@@ -321,7 +322,7 @@ void kasan_poison_vmalloc(const void *start, unsigned long size)
 		return;
 
 	size = round_up(size, KASAN_GRANULE_SIZE);
-	poison_range(start, size, KASAN_VMALLOC_INVALID);
+	kasan_poison(start, size, KASAN_VMALLOC_INVALID);
 }
 
 void kasan_unpoison_vmalloc(const void *start, unsigned long size)
@@ -329,7 +330,7 @@ void kasan_unpoison_vmalloc(const void *start, unsigned long size)
 	if (!is_vmalloc_or_module_addr(start))
 		return;
 
-	unpoison_range(start, size);
+	kasan_unpoison(start, size);
 }
 
 static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c
index 5dcd830805b2..94c2d33be333 100644
--- a/mm/kasan/sw_tags.c
+++ b/mm/kasan/sw_tags.c
@@ -57,7 +57,7 @@ void __init kasan_init_sw_tags(void)
  * sequence has in fact positive effect, since interrupts that randomly skew
  * PRNG at unpredictable points do only good.
  */
-u8 random_tag(void)
+u8 kasan_random_tag(void)
 {
 	u32 state = this_cpu_read(prng_state);
 
@@ -67,7 +67,7 @@ u8 random_tag(void)
 	return (u8)(state % (KASAN_TAG_MAX + 1));
 }
 
-bool check_memory_region(unsigned long addr, size_t size, bool write,
+bool kasan_check_range(unsigned long addr, size_t size, bool write,
 				unsigned long ret_ip)
 {
 	u8 tag;
@@ -118,24 +118,24 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
 	return true;
 }
 
-bool check_invalid_free(void *addr)
+bool kasan_byte_accessible(const void *addr)
 {
 	u8 tag = get_tag(addr);
 	u8 shadow_byte = READ_ONCE(*(u8 *)kasan_mem_to_shadow(kasan_reset_tag(addr)));
 
-	return (shadow_byte == KASAN_TAG_INVALID) ||
-		(tag != KASAN_TAG_KERNEL && tag != shadow_byte);
+	return (shadow_byte != KASAN_TAG_INVALID) &&
+		(tag == KASAN_TAG_KERNEL || tag == shadow_byte);
 }
 
 #define DEFINE_HWASAN_LOAD_STORE(size)					\
 	void __hwasan_load##size##_noabort(unsigned long addr)		\
 	{								\
-		check_memory_region(addr, size, false, _RET_IP_);	\
+		kasan_check_range(addr, size, false, _RET_IP_);	\
 	}								\
 	EXPORT_SYMBOL(__hwasan_load##size##_noabort);			\
 	void __hwasan_store##size##_noabort(unsigned long addr)		\
 	{								\
-		check_memory_region(addr, size, true, _RET_IP_);	\
+		kasan_check_range(addr, size, true, _RET_IP_);		\
 	}								\
 	EXPORT_SYMBOL(__hwasan_store##size##_noabort)
 
@@ -147,19 +147,19 @@ DEFINE_HWASAN_LOAD_STORE(16);
 
 void __hwasan_loadN_noabort(unsigned long addr, unsigned long size)
 {
-	check_memory_region(addr, size, false, _RET_IP_);
+	kasan_check_range(addr, size, false, _RET_IP_);
 }
 EXPORT_SYMBOL(__hwasan_loadN_noabort);
 
 void __hwasan_storeN_noabort(unsigned long addr, unsigned long size)
 {
-	check_memory_region(addr, size, true, _RET_IP_);
+	kasan_check_range(addr, size, true, _RET_IP_);
 }
 EXPORT_SYMBOL(__hwasan_storeN_noabort);
 
 void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size)
 {
-	poison_range((void *)addr, size, tag);
+	kasan_poison((void *)addr, size, tag);
 }
 EXPORT_SYMBOL(__hwasan_tag_memory);
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index fb0fdaec34d5..75e246f680f4 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1643,6 +1643,7 @@ static void collapse_file(struct mm_struct *mm,
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
 	int nr_none = 0, result = SCAN_SUCCEED;
 	bool is_shmem = shmem_file(file);
+	int nr;
 
 	VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
 	VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
@@ -1854,11 +1855,12 @@ out_unlock:
 		put_page(page);
 		goto xa_unlocked;
 	}
+	nr = thp_nr_pages(new_page);
 
 	if (is_shmem)
-		__inc_lruvec_page_state(new_page, NR_SHMEM_THPS);
+		__mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr);
 	else {
-		__inc_lruvec_page_state(new_page, NR_FILE_THPS);
+		__mod_lruvec_page_state(new_page, NR_FILE_THPS, nr);
 		filemap_nr_thps_inc(mapping);
 	}
 
diff --git a/mm/list_lru.c b/mm/list_lru.c
index fe230081690b..6f067b6b935f 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -373,21 +373,13 @@ static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
 	struct list_lru_memcg *memcg_lrus;
 	/*
 	 * This is called when shrinker has already been unregistered,
-	 * and nobody can use it. So, there is no need to use kvfree_rcu_local().
+	 * and nobody can use it. So, there is no need to use kvfree_rcu().
 	 */
 	memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, true);
 	__memcg_destroy_list_lru_node(memcg_lrus, 0, memcg_nr_cache_ids);
 	kvfree(memcg_lrus);
 }
 
-static void kvfree_rcu_local(struct rcu_head *head)
-{
-	struct list_lru_memcg *mlru;
-
-	mlru = container_of(head, struct list_lru_memcg, rcu);
-	kvfree(mlru);
-}
-
 static int memcg_update_list_lru_node(struct list_lru_node *nlru,
 				      int old_size, int new_size)
 {
@@ -419,7 +411,7 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru,
 	rcu_assign_pointer(nlru->memcg_lrus, new);
 	spin_unlock_irq(&nlru->lock);
 
-	call_rcu(&old->rcu, kvfree_rcu_local);
+	kvfree_rcu(old, rcu);
 	return 0;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0b9bd354e97e..845eec01ef9d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -255,6 +255,11 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
 #ifdef CONFIG_MEMCG_KMEM
 extern spinlock_t css_set_lock;
 
+static int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
+			       unsigned int nr_pages);
+static void __memcg_kmem_uncharge(struct mem_cgroup *memcg,
+				  unsigned int nr_pages);
+
 static void obj_cgroup_release(struct percpu_ref *ref)
 {
 	struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
@@ -447,8 +452,7 @@ static void memcg_free_shrinker_maps(struct mem_cgroup *memcg)
 	for_each_node(nid) {
 		pn = mem_cgroup_nodeinfo(memcg, nid);
 		map = rcu_dereference_protected(pn->shrinker_map, true);
-		if (map)
-			kvfree(map);
+		kvfree(map);
 		rcu_assign_pointer(pn->shrinker_map, NULL);
 	}
 }
@@ -1043,29 +1047,6 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 }
 EXPORT_SYMBOL(get_mem_cgroup_from_mm);
 
-/**
- * get_mem_cgroup_from_page: Obtain a reference on given page's memcg.
- * @page: page from which memcg should be extracted.
- *
- * Obtain a reference on page->memcg and returns it if successful. Otherwise
- * root_mem_cgroup is returned.
- */
-struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
-{
-	struct mem_cgroup *memcg = page_memcg(page);
-
-	if (mem_cgroup_disabled())
-		return NULL;
-
-	rcu_read_lock();
-	/* Page should not get uncharged and freed memcg under us. */
-	if (!memcg || WARN_ON_ONCE(!css_tryget(&memcg->css)))
-		memcg = root_mem_cgroup;
-	rcu_read_unlock();
-	return memcg;
-}
-EXPORT_SYMBOL(get_mem_cgroup_from_page);
-
 static __always_inline struct mem_cgroup *active_memcg(void)
 {
 	if (in_interrupt())
@@ -1080,13 +1061,9 @@ static __always_inline struct mem_cgroup *get_active_memcg(void)
 
 	rcu_read_lock();
 	memcg = active_memcg();
-	if (memcg) {
-		/* current->active_memcg must hold a ref. */
-		if (WARN_ON_ONCE(!css_tryget(&memcg->css)))
-			memcg = root_mem_cgroup;
-		else
-			memcg = current->active_memcg;
-	}
+	/* remote memcg must hold a ref. */
+	if (memcg && WARN_ON_ONCE(!css_tryget(&memcg->css)))
+		memcg = root_mem_cgroup;
 	rcu_read_unlock();
 
 	return memcg;
@@ -1346,20 +1323,19 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
  * lock_page_lruvec - lock and return lruvec for a given page.
  * @page: the page
  *
- * This series functions should be used in either conditions:
- * PageLRU is cleared or unset
- * or page->_refcount is zero
- * or page is locked.
+ * These functions are safe to use under any of the following conditions:
+ * - page locked
+ * - PageLRU cleared
+ * - lock_page_memcg()
+ * - page->_refcount is zero
  */
 struct lruvec *lock_page_lruvec(struct page *page)
 {
 	struct lruvec *lruvec;
 	struct pglist_data *pgdat = page_pgdat(page);
 
-	rcu_read_lock();
 	lruvec = mem_cgroup_page_lruvec(page, pgdat);
 	spin_lock(&lruvec->lru_lock);
-	rcu_read_unlock();
 
 	lruvec_memcg_debug(lruvec, page);
 
@@ -1371,10 +1347,8 @@ struct lruvec *lock_page_lruvec_irq(struct page *page)
 	struct lruvec *lruvec;
 	struct pglist_data *pgdat = page_pgdat(page);
 
-	rcu_read_lock();
 	lruvec = mem_cgroup_page_lruvec(page, pgdat);
 	spin_lock_irq(&lruvec->lru_lock);
-	rcu_read_unlock();
 
 	lruvec_memcg_debug(lruvec, page);
 
@@ -1386,10 +1360,8 @@ struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags)
 	struct lruvec *lruvec;
 	struct pglist_data *pgdat = page_pgdat(page);
 
-	rcu_read_lock();
 	lruvec = mem_cgroup_page_lruvec(page, pgdat);
 	spin_lock_irqsave(&lruvec->lru_lock, *flags);
-	rcu_read_unlock();
 
 	lruvec_memcg_debug(lruvec, page);
 
@@ -1512,72 +1484,73 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
 
 struct memory_stat {
 	const char *name;
-	unsigned int ratio;
 	unsigned int idx;
 };
 
-static struct memory_stat memory_stats[] = {
-	{ "anon", PAGE_SIZE, NR_ANON_MAPPED },
-	{ "file", PAGE_SIZE, NR_FILE_PAGES },
-	{ "kernel_stack", 1024, NR_KERNEL_STACK_KB },
-	{ "pagetables", PAGE_SIZE, NR_PAGETABLE },
-	{ "percpu", 1, MEMCG_PERCPU_B },
-	{ "sock", PAGE_SIZE, MEMCG_SOCK },
-	{ "shmem", PAGE_SIZE, NR_SHMEM },
-	{ "file_mapped", PAGE_SIZE, NR_FILE_MAPPED },
-	{ "file_dirty", PAGE_SIZE, NR_FILE_DIRTY },
-	{ "file_writeback", PAGE_SIZE, NR_WRITEBACK },
+static const struct memory_stat memory_stats[] = {
+	{ "anon",			NR_ANON_MAPPED			},
+	{ "file",			NR_FILE_PAGES			},
+	{ "kernel_stack",		NR_KERNEL_STACK_KB		},
+	{ "pagetables",			NR_PAGETABLE			},
+	{ "percpu",			MEMCG_PERCPU_B			},
+	{ "sock",			MEMCG_SOCK			},
+	{ "shmem",			NR_SHMEM			},
+	{ "file_mapped",		NR_FILE_MAPPED			},
+	{ "file_dirty",			NR_FILE_DIRTY			},
+	{ "file_writeback",		NR_WRITEBACK			},
+#ifdef CONFIG_SWAP
+	{ "swapcached",			NR_SWAPCACHE			},
+#endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	/*
-	 * The ratio will be initialized in memory_stats_init(). Because
-	 * on some architectures, the macro of HPAGE_PMD_SIZE is not
-	 * constant(e.g. powerpc).
-	 */
-	{ "anon_thp", 0, NR_ANON_THPS },
-	{ "file_thp", 0, NR_FILE_THPS },
-	{ "shmem_thp", 0, NR_SHMEM_THPS },
+	{ "anon_thp",			NR_ANON_THPS			},
+	{ "file_thp",			NR_FILE_THPS			},
+	{ "shmem_thp",			NR_SHMEM_THPS			},
 #endif
-	{ "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON },
-	{ "active_anon", PAGE_SIZE, NR_ACTIVE_ANON },
-	{ "inactive_file", PAGE_SIZE, NR_INACTIVE_FILE },
-	{ "active_file", PAGE_SIZE, NR_ACTIVE_FILE },
-	{ "unevictable", PAGE_SIZE, NR_UNEVICTABLE },
-
-	/*
-	 * Note: The slab_reclaimable and slab_unreclaimable must be
-	 * together and slab_reclaimable must be in front.
-	 */
-	{ "slab_reclaimable", 1, NR_SLAB_RECLAIMABLE_B },
-	{ "slab_unreclaimable", 1, NR_SLAB_UNRECLAIMABLE_B },
+	{ "inactive_anon",		NR_INACTIVE_ANON		},
+	{ "active_anon",		NR_ACTIVE_ANON			},
+	{ "inactive_file",		NR_INACTIVE_FILE		},
+	{ "active_file",		NR_ACTIVE_FILE			},
+	{ "unevictable",		NR_UNEVICTABLE			},
+	{ "slab_reclaimable",		NR_SLAB_RECLAIMABLE_B		},
+	{ "slab_unreclaimable",		NR_SLAB_UNRECLAIMABLE_B		},
 
 	/* The memory events */
-	{ "workingset_refault_anon", 1, WORKINGSET_REFAULT_ANON },
-	{ "workingset_refault_file", 1, WORKINGSET_REFAULT_FILE },
-	{ "workingset_activate_anon", 1, WORKINGSET_ACTIVATE_ANON },
-	{ "workingset_activate_file", 1, WORKINGSET_ACTIVATE_FILE },
-	{ "workingset_restore_anon", 1, WORKINGSET_RESTORE_ANON },
-	{ "workingset_restore_file", 1, WORKINGSET_RESTORE_FILE },
-	{ "workingset_nodereclaim", 1, WORKINGSET_NODERECLAIM },
+	{ "workingset_refault_anon",	WORKINGSET_REFAULT_ANON		},
+	{ "workingset_refault_file",	WORKINGSET_REFAULT_FILE		},
+	{ "workingset_activate_anon",	WORKINGSET_ACTIVATE_ANON	},
+	{ "workingset_activate_file",	WORKINGSET_ACTIVATE_FILE	},
+	{ "workingset_restore_anon",	WORKINGSET_RESTORE_ANON		},
+	{ "workingset_restore_file",	WORKINGSET_RESTORE_FILE		},
+	{ "workingset_nodereclaim",	WORKINGSET_NODERECLAIM		},
 };
 
-static int __init memory_stats_init(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		if (memory_stats[i].idx == NR_ANON_THPS ||
-		    memory_stats[i].idx == NR_FILE_THPS ||
-		    memory_stats[i].idx == NR_SHMEM_THPS)
-			memory_stats[i].ratio = HPAGE_PMD_SIZE;
-#endif
-		VM_BUG_ON(!memory_stats[i].ratio);
-		VM_BUG_ON(memory_stats[i].idx >= MEMCG_NR_STAT);
+/* Translate stat items to the correct unit for memory.stat output */
+static int memcg_page_state_unit(int item)
+{
+	switch (item) {
+	case MEMCG_PERCPU_B:
+	case NR_SLAB_RECLAIMABLE_B:
+	case NR_SLAB_UNRECLAIMABLE_B:
+	case WORKINGSET_REFAULT_ANON:
+	case WORKINGSET_REFAULT_FILE:
+	case WORKINGSET_ACTIVATE_ANON:
+	case WORKINGSET_ACTIVATE_FILE:
+	case WORKINGSET_RESTORE_ANON:
+	case WORKINGSET_RESTORE_FILE:
+	case WORKINGSET_NODERECLAIM:
+		return 1;
+	case NR_KERNEL_STACK_KB:
+		return SZ_1K;
+	default:
+		return PAGE_SIZE;
 	}
+}
 
-	return 0;
+static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg,
+						    int item)
+{
+	return memcg_page_state(memcg, item) * memcg_page_state_unit(item);
 }
-pure_initcall(memory_stats_init);
 
 static char *memory_stat_format(struct mem_cgroup *memcg)
 {
@@ -1602,13 +1575,12 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		u64 size;
 
-		size = memcg_page_state(memcg, memory_stats[i].idx);
-		size *= memory_stats[i].ratio;
+		size = memcg_page_state_output(memcg, memory_stats[i].idx);
 		seq_buf_printf(&s, "%s %llu\n", memory_stats[i].name, size);
 
 		if (unlikely(memory_stats[i].idx == NR_SLAB_UNRECLAIMABLE_B)) {
-			size = memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
-			       memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B);
+			size += memcg_page_state_output(memcg,
+							NR_SLAB_RECLAIMABLE_B);
 			seq_buf_printf(&s, "slab %llu\n", size);
 		}
 	}
@@ -2935,9 +2907,10 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp)
+				 gfp_t gfp, bool new_page)
 {
 	unsigned int objects = objs_per_slab_page(s, page);
+	unsigned long memcg_data;
 	void *vec;
 
 	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
@@ -2945,11 +2918,25 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 	if (!vec)
 		return -ENOMEM;
 
-	if (!set_page_objcgs(page, vec))
+	memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
+	if (new_page) {
+		/*
+		 * If the slab page is brand new and nobody can yet access
+		 * it's memcg_data, no synchronization is required and
+		 * memcg_data can be simply assigned.
+		 */
+		page->memcg_data = memcg_data;
+	} else if (cmpxchg(&page->memcg_data, 0, memcg_data)) {
+		/*
+		 * If the slab page is already in use, somebody can allocate
+		 * and assign obj_cgroups in parallel. In this case the existing
+		 * objcg vector should be reused.
+		 */
 		kfree(vec);
-	else
-		kmemleak_not_leak(vec);
+		return 0;
+	}
 
+	kmemleak_not_leak(vec);
 	return 0;
 }
 
@@ -3077,8 +3064,8 @@ static void memcg_free_cache_id(int id)
  *
  * Returns 0 on success, an error code on failure.
  */
-int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
-			unsigned int nr_pages)
+static int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
+			       unsigned int nr_pages)
 {
 	struct page_counter *counter;
 	int ret;
@@ -3110,7 +3097,7 @@ int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,
  * @memcg: memcg to uncharge
  * @nr_pages: number of pages to uncharge
  */
-void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages)
+static void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		page_counter_uncharge(&memcg->kmem, nr_pages);
@@ -4072,10 +4059,6 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
 		nr = memcg_page_state_local(memcg, memcg1_stats[i]);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		if (memcg1_stats[i] == NR_ANON_THPS)
-			nr *= HPAGE_PMD_NR;
-#endif
 		seq_printf(m, "%s %lu\n", memcg1_stat_names[i], nr * PAGE_SIZE);
 	}
 
@@ -4106,10 +4089,6 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
 		nr = memcg_page_state(memcg, memcg1_stats[i]);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		if (memcg1_stats[i] == NR_ANON_THPS)
-			nr *= HPAGE_PMD_NR;
-#endif
 		seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
 						(u64)nr * PAGE_SIZE);
 	}
@@ -5193,7 +5172,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 		return 1;
 	}
 
-	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct lruvec_stat,
+	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct batched_lruvec_stat,
 					       GFP_KERNEL_ACCOUNT);
 	if (!pn->lruvec_stat_cpu) {
 		free_percpu(pn->lruvec_stat_local);
@@ -5642,7 +5621,6 @@ static int mem_cgroup_move_account(struct page *page,
 				__mod_lruvec_state(to_vec, NR_ANON_THPS,
 						   nr_pages);
 			}
-
 		}
 	} else {
 		__mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages);
@@ -6393,6 +6371,12 @@ static int memory_stat_show(struct seq_file *m, void *v)
 }
 
 #ifdef CONFIG_NUMA
+static inline unsigned long lruvec_page_state_output(struct lruvec *lruvec,
+						     int item)
+{
+	return lruvec_page_state(lruvec, item) * memcg_page_state_unit(item);
+}
+
 static int memory_numa_stat_show(struct seq_file *m, void *v)
 {
 	int i;
@@ -6410,8 +6394,8 @@ static int memory_numa_stat_show(struct seq_file *m, void *v)
 			struct lruvec *lruvec;
 
 			lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
-			size = lruvec_page_state(lruvec, memory_stats[i].idx);
-			size *= memory_stats[i].ratio;
+			size = lruvec_page_state_output(lruvec,
+							memory_stats[i].idx);
 			seq_printf(m, " N%d=%llu", nid, size);
 		}
 		seq_putc(m, '\n');
@@ -6760,7 +6744,19 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 	memcg_check_events(memcg, page);
 	local_irq_enable();
 
-	if (PageSwapCache(page)) {
+	/*
+	 * Cgroup1's unified memory+swap counter has been charged with the
+	 * new swapcache page, finish the transfer by uncharging the swap
+	 * slot. The swap slot would also get uncharged when it dies, but
+	 * it can stick around indefinitely and we'd count the page twice
+	 * the entire time.
+	 *
+	 * Cgroup2 has separate resource counters for memory and swap,
+	 * so this is a non-issue here. Memory and swap charge lifetimes
+	 * correspond 1:1 to page and swap slot lifetimes: we charge the
+	 * page to memory here, and uncharge swap when the slot is freed.
+	 */
+	if (do_memsw_account() && PageSwapCache(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
 		/*
 		 * The swap entry might not get freed for a long time,
@@ -6851,31 +6847,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 	css_put(&ug->memcg->css);
 }
 
-static void uncharge_list(struct list_head *page_list)
-{
-	struct uncharge_gather ug;
-	struct list_head *next;
-
-	uncharge_gather_clear(&ug);
-
-	/*
-	 * Note that the list can be a single page->lru; hence the
-	 * do-while loop instead of a simple list_for_each_entry().
-	 */
-	next = page_list->next;
-	do {
-		struct page *page;
-
-		page = list_entry(next, struct page, lru);
-		next = page->lru.next;
-
-		uncharge_page(page, &ug);
-	} while (next != page_list);
-
-	if (ug.memcg)
-		uncharge_batch(&ug);
-}
-
 /**
  * mem_cgroup_uncharge - uncharge a page
  * @page: page to uncharge
@@ -6907,11 +6878,17 @@ void mem_cgroup_uncharge(struct page *page)
  */
 void mem_cgroup_uncharge_list(struct list_head *page_list)
 {
+	struct uncharge_gather ug;
+	struct page *page;
+
 	if (mem_cgroup_disabled())
 		return;
 
-	if (!list_empty(page_list))
-		uncharge_list(page_list);
+	uncharge_gather_clear(&ug);
+	list_for_each_entry(page, page_list, lru)
+		uncharge_page(page, &ug);
+	if (ug.memcg)
+		uncharge_batch(&ug);
 }
 
 /**
@@ -7078,6 +7055,14 @@ static int __init mem_cgroup_init(void)
 {
 	int cpu, node;
 
+	/*
+	 * Currently s32 type (can refer to struct batched_lruvec_stat) is
+	 * used for per-memcg-per-cpu caching of per-node statistics. In order
+	 * to work fine, we should make sure that the overfill threshold can't
+	 * exceed S32_MAX / PAGE_SIZE.
+	 */
+	BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE);
+
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
 				  memcg_hotplug_cpu_dead);
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e9481632fcd1..55c671904aac 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -243,9 +243,13 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags)
 			pfn, t->comm, t->pid);
 
 	if (flags & MF_ACTION_REQUIRED) {
-		WARN_ON_ONCE(t != current);
-		ret = force_sig_mceerr(BUS_MCEERR_AR,
+		if (t == current)
+			ret = force_sig_mceerr(BUS_MCEERR_AR,
 					 (void __user *)tk->addr, addr_lsb);
+		else
+			/* Signal other processes sharing the page if they have PF_MCE_EARLY set. */
+			ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr,
+				addr_lsb, t);
 	} else {
 		/*
 		 * Don't use force here, it's convenient if the signal
@@ -440,26 +444,26 @@ static struct task_struct *find_early_kill_thread(struct task_struct *tsk)
  * Determine whether a given process is "early kill" process which expects
  * to be signaled when some page under the process is hwpoisoned.
  * Return task_struct of the dedicated thread (main thread unless explicitly
- * specified) if the process is "early kill," and otherwise returns NULL.
+ * specified) if the process is "early kill" and otherwise returns NULL.
  *
- * Note that the above is true for Action Optional case, but not for Action
- * Required case where SIGBUS should sent only to the current thread.
+ * Note that the above is true for Action Optional case. For Action Required
+ * case, it's only meaningful to the current thread which need to be signaled
+ * with SIGBUS, this error is Action Optional for other non current
+ * processes sharing the same error page,if the process is "early kill", the
+ * task_struct of the dedicated thread will also be returned.
  */
 static struct task_struct *task_early_kill(struct task_struct *tsk,
 					   int force_early)
 {
 	if (!tsk->mm)
 		return NULL;
-	if (force_early) {
-		/*
-		 * Comparing ->mm here because current task might represent
-		 * a subthread, while tsk always points to the main thread.
-		 */
-		if (tsk->mm == current->mm)
-			return current;
-		else
-			return NULL;
-	}
+	/*
+	 * Comparing ->mm here because current task might represent
+	 * a subthread, while tsk always points to the main thread.
+	 */
+	if (force_early && tsk->mm == current->mm)
+		return current;
+
 	return find_early_kill_thread(tsk);
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 5da964079678..784249f3307b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2177,11 +2177,11 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned long pfn, pgprot_t prot)
 {
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	spinlock_t *ptl;
 	int err = 0;
 
-	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
+	mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
 	arch_enter_lazy_mmu_mode();
@@ -2195,7 +2195,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(pte - 1, ptl);
+	pte_unmap_unlock(mapped_pte, ptl);
 	return err;
 }
 
@@ -2394,18 +2394,18 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     pte_fn_t fn, void *data, bool create,
 				     pgtbl_mod_mask *mask)
 {
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	int err = 0;
 	spinlock_t *ptl;
 
 	if (create) {
-		pte = (mm == &init_mm) ?
+		mapped_pte = pte = (mm == &init_mm) ?
 			pte_alloc_kernel_track(pmd, addr, mask) :
 			pte_alloc_map_lock(mm, pmd, addr, &ptl);
 		if (!pte)
 			return -ENOMEM;
 	} else {
-		pte = (mm == &init_mm) ?
+		mapped_pte = pte = (mm == &init_mm) ?
 			pte_offset_kernel(pmd, addr) :
 			pte_offset_map_lock(mm, pmd, addr, &ptl);
 	}
@@ -2428,7 +2428,7 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	arch_leave_lazy_mmu_mode();
 
 	if (mm != &init_mm)
-		pte_unmap_unlock(pte-1, ptl);
+		pte_unmap_unlock(mapped_pte, ptl);
 	return err;
 }
 
@@ -5177,17 +5177,19 @@ long copy_huge_page_from_user(struct page *dst_page,
 	void *page_kaddr;
 	unsigned long i, rc = 0;
 	unsigned long ret_val = pages_per_huge_page * PAGE_SIZE;
+	struct page *subpage = dst_page;
 
-	for (i = 0; i < pages_per_huge_page; i++) {
+	for (i = 0; i < pages_per_huge_page;
+	     i++, subpage = mem_map_next(subpage, dst_page, i)) {
 		if (allow_pagefault)
-			page_kaddr = kmap(dst_page + i);
+			page_kaddr = kmap(subpage);
 		else
-			page_kaddr = kmap_atomic(dst_page + i);
+			page_kaddr = kmap_atomic(subpage);
 		rc = copy_from_user(page_kaddr,
 				(const void __user *)(src + i * PAGE_SIZE),
 				PAGE_SIZE);
 		if (allow_pagefault)
-			kunmap(dst_page + i);
+			kunmap(subpage);
 		else
 			kunmap_atomic(page_kaddr);
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f9d57b9be8c7..abe43c1ae920 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -713,7 +713,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * expects the zone spans the pfn range. All the pages in the range
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
-	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0,
+	memmap_init_range(nr_pages, nid, zone_idx(zone), start_pfn, 0,
 			 MEMINIT_HOTPLUG, altmap, migratetype);
 
 	set_zone_contiguous(zone);
@@ -1260,7 +1260,14 @@ static int scan_movable_pages(unsigned long start, unsigned long end,
 		if (!PageHuge(page))
 			continue;
 		head = compound_head(page);
-		if (page_huge_active(head))
+		/*
+		 * This test is racy as we hold no reference or lock.  The
+		 * hugetlb page could have been free'ed and head is no longer
+		 * a hugetlb page before the following check.  In such unlikely
+		 * cases false positives and negatives are possible.  Calling
+		 * code must deal with these scenarios.
+		 */
+		if (HPageMigratable(head))
 			goto found;
 		skip = compound_nr(head) - (page - head);
 		pfn += skip - 1;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2c3a86502053..ab51132547b8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -677,7 +677,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 	unsigned long flags = qp->flags;
 
 	/* range check first */
-	VM_BUG_ON_VMA((vma->vm_start > start) || (vma->vm_end < end), vma);
+	VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma);
 
 	if (!qp->first) {
 		qp->first = vma;
@@ -875,6 +875,16 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 		goto out;
 	}
 
+	if (flags & MPOL_F_NUMA_BALANCING) {
+		if (new && new->mode == MPOL_BIND) {
+			new->flags |= (MPOL_F_MOF | MPOL_F_MORON);
+		} else {
+			ret = -EINVAL;
+			mpol_put(new);
+			goto out;
+		}
+	}
+
 	ret = mpol_set_nodemask(new, nodes, scratch);
 	if (ret) {
 		mpol_put(new);
@@ -2486,6 +2496,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 		break;
 
 	case MPOL_BIND:
+		/* Optimize placement among multiple nodes via NUMA balancing */
+		if (pol->flags & MPOL_F_MORON) {
+			if (node_isset(thisnid, pol->v.nodes))
+				break;
+			goto out;
+		}
 
 		/*
 		 * allows binding to multiple nodes.
diff --git a/mm/mempool.c b/mm/mempool.c
index 624ed51b060f..79959fac27d7 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -104,7 +104,7 @@ static inline void poison_element(mempool_t *pool, void *element)
 static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
-		kasan_slab_free_mempool(element, _RET_IP_);
+		kasan_slab_free_mempool(element);
 	else if (pool->alloc == mempool_alloc_pages)
 		kasan_free_pages(element, (unsigned long)pool->pool_data);
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 20ca887ea769..62b81d5257aa 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -331,7 +331,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 	if (!get_page_unless_zero(page))
 		goto out;
 	pte_unmap_unlock(ptep, ptl);
-	put_and_wait_on_page_locked(page);
+	put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
 	return;
 out:
 	pte_unmap_unlock(ptep, ptl);
@@ -365,7 +365,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
 	if (!get_page_unless_zero(page))
 		goto unlock;
 	spin_unlock(ptl);
-	put_and_wait_on_page_locked(page);
+	put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
 	return;
 unlock:
 	spin_unlock(ptl);
@@ -500,6 +500,12 @@ int migrate_page_move_mapping(struct address_space *mapping,
 			__mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
 			__mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
 		}
+#ifdef CONFIG_SWAP
+		if (PageSwapCache(page)) {
+			__mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr);
+			__mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr);
+		}
+#endif
 		if (dirty && mapping_can_writeback(mapping)) {
 			__mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr);
 			__mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr);
diff --git a/mm/mlock.c b/mm/mlock.c
index 55b3b3672977..73960bb3464d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -278,8 +278,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 			 */
 			if (TestClearPageLRU(page)) {
 				lruvec = relock_page_lruvec_irq(page, lruvec);
-				del_page_from_lru_list(page, lruvec,
-							page_lru(page));
+				del_page_from_lru_list(page, lruvec);
 				continue;
 			} else
 				__munlock_isolation_failed(page);
diff --git a/mm/mmap.c b/mm/mmap.c
index 90673febce6a..3f287599a7a3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -189,7 +189,6 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
 		struct list_head *uf);
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
-	unsigned long retval;
 	unsigned long newbrk, oldbrk, origbrk;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *next;
@@ -281,9 +280,8 @@ success:
 	return brk;
 
 out:
-	retval = origbrk;
 	mmap_write_unlock(mm);
-	return retval;
+	return origbrk;
 }
 
 static inline unsigned long vma_compute_gap(struct vm_area_struct *vma)
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ab709023e9aa..94188df1ee55 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -617,10 +617,11 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 		if (tmp > end)
 			tmp = end;
 
-		if (vma->vm_ops && vma->vm_ops->mprotect)
+		if (vma->vm_ops && vma->vm_ops->mprotect) {
 			error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
-		if (error)
-			goto out;
+			if (error)
+				goto out;
+		}
 
 		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
 		if (error)
diff --git a/mm/mremap.c b/mm/mremap.c
index 47192691fe32..ec8f840399ed 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -593,6 +593,14 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		/* We always clear VM_LOCKED[ONFAULT] on the old vma */
 		vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
 
+		/*
+		 * anon_vma links of the old vma is no longer needed after its page
+		 * table has been moved.
+		 */
+		if (new_vma != vma && vma->vm_start == old_addr &&
+			vma->vm_end == (old_addr + old_len))
+			unlink_anon_vmas(vma);
+
 		/* Because we won't unmap we don't need to touch locked_vm */
 		return new_addr;
 	}
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c9a33ffe38b7..9efaf430cfd3 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -395,9 +395,8 @@ static int dump_task(struct task_struct *p, void *arg)
 	task = find_lock_task_mm(p);
 	if (!task) {
 		/*
-		 * This is a kthread or all of p's threads have already
-		 * detached their mm's.  There's no need to report
-		 * them; they can't be oom killed anyway.
+		 * All of p's threads have already detached their mm's. There's
+		 * no need to report them; they can't be oom killed anyway.
 		 */
 		return 0;
 	}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef5070fed76b..ddccc59f2f72 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5584,10 +5584,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(node_page_state(pgdat, NR_WRITEBACK)),
 			K(node_page_state(pgdat, NR_SHMEM)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
-			K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
-					* HPAGE_PMD_NR),
-			K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
+			K(node_page_state(pgdat, NR_SHMEM_THPS)),
+			K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
+			K(node_page_state(pgdat, NR_ANON_THPS)),
 #endif
 			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
 			node_page_state(pgdat, NR_KERNEL_STACK_KB),
@@ -6122,7 +6121,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
  * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
-void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
+void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone,
 		unsigned long start_pfn, unsigned long zone_end_pfn,
 		enum meminit_context context,
 		struct vmem_altmap *altmap, int migratetype)
@@ -6259,23 +6258,21 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	}
 }
 
-void __meminit __weak memmap_init(unsigned long size, int nid,
-				  unsigned long zone,
-				  unsigned long range_start_pfn)
+void __meminit __weak memmap_init_zone(struct zone *zone)
 {
+	unsigned long zone_start_pfn = zone->zone_start_pfn;
+	unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
+	int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone);
 	unsigned long start_pfn, end_pfn;
-	unsigned long range_end_pfn = range_start_pfn + size;
-	int i;
 
 	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
-		start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn);
-		end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn);
+		start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
+		end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn);
 
-		if (end_pfn > start_pfn) {
-			size = end_pfn - start_pfn;
-			memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn,
-					 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
-		}
+		if (end_pfn > start_pfn)
+			memmap_init_range(end_pfn - start_pfn, nid,
+					zone_id, start_pfn, zone_end_pfn,
+					MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	}
 }
 
@@ -6768,25 +6765,22 @@ static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned l
 	return usemapsize / 8;
 }
 
-static void __ref setup_usemap(struct pglist_data *pgdat,
-				struct zone *zone,
-				unsigned long zone_start_pfn,
-				unsigned long zonesize)
+static void __ref setup_usemap(struct zone *zone)
 {
-	unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
+	unsigned long usemapsize = usemap_size(zone->zone_start_pfn,
+					       zone->spanned_pages);
 	zone->pageblock_flags = NULL;
 	if (usemapsize) {
 		zone->pageblock_flags =
 			memblock_alloc_node(usemapsize, SMP_CACHE_BYTES,
-					    pgdat->node_id);
+					    zone_to_nid(zone));
 		if (!zone->pageblock_flags)
 			panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n",
-			      usemapsize, zone->name, pgdat->node_id);
+			      usemapsize, zone->name, zone_to_nid(zone));
 	}
 }
 #else
-static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
-				unsigned long zone_start_pfn, unsigned long zonesize) {}
+static inline void setup_usemap(struct zone *zone) {}
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -6933,7 +6927,6 @@ static void __init free_area_init_core(struct pglist_data *pgdat)
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, freesize, memmap_pages;
-		unsigned long zone_start_pfn = zone->zone_start_pfn;
 
 		size = zone->spanned_pages;
 		freesize = zone->present_pages;
@@ -6981,9 +6974,9 @@ static void __init free_area_init_core(struct pglist_data *pgdat)
 			continue;
 
 		set_pageblock_order();
-		setup_usemap(pgdat, zone, zone_start_pfn, size);
-		init_currently_empty_zone(zone, zone_start_pfn, size);
-		memmap_init(size, nid, j, zone_start_pfn);
+		setup_usemap(zone);
+		init_currently_empty_zone(zone, zone->zone_start_pfn, size);
+		memmap_init_zone(zone);
 	}
 }
 
@@ -7698,17 +7691,6 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 	return pages;
 }
 
-#ifdef	CONFIG_HIGHMEM
-void free_highmem_page(struct page *page)
-{
-	__free_reserved_page(page);
-	totalram_pages_inc();
-	atomic_long_inc(&page_zone(page)->managed_pages);
-	totalhigh_pages_inc();
-}
-#endif
-
-
 void __init mem_init_print_info(const char *str)
 {
 	unsigned long physpages, codesize, datasize, rosize, bss_size;
diff --git a/mm/page_io.c b/mm/page_io.c
index 92f7941c6d01..485fa5cca4a2 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -41,9 +41,9 @@ void end_swap_bio_write(struct bio *bio)
 		 * Also clear PG_reclaim to avoid rotate_reclaimable_page()
 		 */
 		set_page_dirty(page);
-		pr_alert("Write-error on swap-device (%u:%u:%llu)\n",
-			 MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
-			 (unsigned long long)bio->bi_iter.bi_sector);
+		pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
 		ClearPageReclaim(page);
 	}
 	end_page_writeback(page);
@@ -106,9 +106,9 @@ static void end_swap_bio_read(struct bio *bio)
 	if (bio->bi_status) {
 		SetPageError(page);
 		ClearPageUptodate(page);
-		pr_alert("Read-error on swap-device (%u:%u:%llu)\n",
-			 MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
-			 (unsigned long long)bio->bi_iter.bi_sector);
+		pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n",
+				     MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
+				     (unsigned long long)bio->bi_iter.bi_sector);
 		goto out;
 	}
 
diff --git a/mm/page_owner.c b/mm/page_owner.c
index af464bb7fbe7..d15c7c4994f5 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -263,8 +263,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	struct page *page;
 	struct page_ext *page_ext;
 	struct page_owner *page_owner;
-	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
-	unsigned long end_pfn = pfn + zone->spanned_pages;
+	unsigned long pfn, block_end_pfn;
+	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long count[MIGRATE_TYPES] = { 0, };
 	int pageblock_mt, page_mt;
 	int i;
diff --git a/mm/page_reporting.c b/mm/page_reporting.c
index cd8e13d41df4..c50d93ffa252 100644
--- a/mm/page_reporting.c
+++ b/mm/page_reporting.c
@@ -211,7 +211,7 @@ page_reporting_cycle(struct page_reporting_dev_info *prdev, struct zone *zone,
 	}
 
 	/* Rotate any leftover pages to the head of the freelist */
-	if (&next->lru != list && !list_is_first(&next->lru, list))
+	if (!list_entry_is_head(next, list, lru) && !list_is_first(&next->lru, list))
 		list_rotate_to_front(&next->lru, list);
 
 	spin_unlock_irq(&zone->lock);
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9578db83e312..c2210e1cdb51 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -135,8 +135,9 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
 {
 	pmd_t pmd;
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
-			   !pmd_devmap(*pmdp)) || !pmd_present(*pmdp));
+	VM_BUG_ON(!pmd_present(*pmdp));
+	/* Below assumes pmd_present() is true */
+	VM_BUG_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
diff --git a/mm/rmap.c b/mm/rmap.c
index 08c56aaf72eb..e26ae119a131 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -413,8 +413,15 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
-	if (vma->anon_vma)
+	if (vma->anon_vma) {
 		vma->anon_vma->degree--;
+
+		/*
+		 * vma would still be needed after unlink, and anon_vma will be prepared
+		 * when handle fault.
+		 */
+		vma->anon_vma = NULL;
+	}
 	unlock_anon_vma_root(root);
 
 	/*
@@ -1144,7 +1151,7 @@ void do_page_add_anon_rmap(struct page *page,
 		 * disabled.
 		 */
 		if (compound)
-			__inc_lruvec_page_state(page, NR_ANON_THPS);
+			__mod_lruvec_page_state(page, NR_ANON_THPS, nr);
 		__mod_lruvec_page_state(page, NR_ANON_MAPPED, nr);
 	}
 
@@ -1186,7 +1193,7 @@ void page_add_new_anon_rmap(struct page *page,
 		if (hpage_pincount_available(page))
 			atomic_set(compound_pincount_ptr(page), 0);
 
-		__inc_lruvec_page_state(page, NR_ANON_THPS);
+		__mod_lruvec_page_state(page, NR_ANON_THPS, nr);
 	} else {
 		/* Anon THP always mapped first with PMD */
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
@@ -1211,16 +1218,20 @@ void page_add_file_rmap(struct page *page, bool compound)
 	VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
 	lock_page_memcg(page);
 	if (compound && PageTransHuge(page)) {
-		for (i = 0, nr = 0; i < thp_nr_pages(page); i++) {
+		int nr_pages = thp_nr_pages(page);
+
+		for (i = 0, nr = 0; i < nr_pages; i++) {
 			if (atomic_inc_and_test(&page[i]._mapcount))
 				nr++;
 		}
 		if (!atomic_inc_and_test(compound_mapcount_ptr(page)))
 			goto out;
 		if (PageSwapBacked(page))
-			__inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
+			__mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED,
+						nr_pages);
 		else
-			__inc_node_page_state(page, NR_FILE_PMDMAPPED);
+			__mod_lruvec_page_state(page, NR_FILE_PMDMAPPED,
+						nr_pages);
 	} else {
 		if (PageTransCompound(page) && page_mapping(page)) {
 			VM_WARN_ON_ONCE(!PageLocked(page));
@@ -1252,16 +1263,20 @@ static void page_remove_file_rmap(struct page *page, bool compound)
 
 	/* page still mapped by someone else? */
 	if (compound && PageTransHuge(page)) {
-		for (i = 0, nr = 0; i < thp_nr_pages(page); i++) {
+		int nr_pages = thp_nr_pages(page);
+
+		for (i = 0, nr = 0; i < nr_pages; i++) {
 			if (atomic_add_negative(-1, &page[i]._mapcount))
 				nr++;
 		}
 		if (!atomic_add_negative(-1, compound_mapcount_ptr(page)))
 			return;
 		if (PageSwapBacked(page))
-			__dec_node_page_state(page, NR_SHMEM_PMDMAPPED);
+			__mod_lruvec_page_state(page, NR_SHMEM_PMDMAPPED,
+						-nr_pages);
 		else
-			__dec_node_page_state(page, NR_FILE_PMDMAPPED);
+			__mod_lruvec_page_state(page, NR_FILE_PMDMAPPED,
+						-nr_pages);
 	} else {
 		if (!atomic_add_negative(-1, &page->_mapcount))
 			return;
@@ -1292,7 +1307,7 @@ static void page_remove_anon_compound_rmap(struct page *page)
 	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
 		return;
 
-	__dec_lruvec_page_state(page, NR_ANON_THPS);
+	__mod_lruvec_page_state(page, NR_ANON_THPS, -thp_nr_pages(page));
 
 	if (TestClearPageDoubleMap(page)) {
 		/*
diff --git a/mm/shmem.c b/mm/shmem.c
index 7924b3bf46fb..ff741d229701 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -713,7 +713,7 @@ next:
 		}
 		if (PageTransHuge(page)) {
 			count_vm_event(THP_FILE_ALLOC);
-			__inc_lruvec_page_state(page, NR_SHMEM_THPS);
+			__mod_lruvec_page_state(page, NR_SHMEM_THPS, nr);
 		}
 		mapping->nrpages += nr;
 		__mod_lruvec_page_state(page, NR_FILE_PAGES, nr);
diff --git a/mm/slab.c b/mm/slab.c
index dcc55e78f353..35c68d99d460 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -272,7 +272,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
 #define	STATS_DEC_ACTIVE(x)	((x)->num_active--)
 #define	STATS_INC_ALLOCED(x)	((x)->num_allocations++)
 #define	STATS_INC_GROWN(x)	((x)->grown++)
-#define	STATS_ADD_REAPED(x,y)	((x)->reaped += (y))
+#define	STATS_ADD_REAPED(x, y)	((x)->reaped += (y))
 #define	STATS_SET_HIGH(x)						\
 	do {								\
 		if ((x)->num_active > (x)->high_mark)			\
@@ -296,7 +296,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
 #define	STATS_DEC_ACTIVE(x)	do { } while (0)
 #define	STATS_INC_ALLOCED(x)	do { } while (0)
 #define	STATS_INC_GROWN(x)	do { } while (0)
-#define	STATS_ADD_REAPED(x,y)	do { (void)(y); } while (0)
+#define	STATS_ADD_REAPED(x, y)	do { (void)(y); } while (0)
 #define	STATS_SET_HIGH(x)	do { } while (0)
 #define	STATS_INC_ERR(x)	do { } while (0)
 #define	STATS_INC_NODEALLOCS(x)	do { } while (0)
@@ -332,7 +332,7 @@ static int obj_offset(struct kmem_cache *cachep)
 static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
 {
 	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	return (unsigned long long*) (objp + obj_offset(cachep) -
+	return (unsigned long long *) (objp + obj_offset(cachep) -
 				      sizeof(unsigned long long));
 }
 
@@ -580,7 +580,7 @@ static int transfer_objects(struct array_cache *to,
 	if (!nr)
 		return 0;
 
-	memcpy(to->entry + to->avail, from->entry + from->avail -nr,
+	memcpy(to->entry + to->avail, from->entry + from->avail - nr,
 			sizeof(void *) *nr);
 
 	from->avail -= nr;
@@ -1379,7 +1379,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 		return NULL;
 	}
 
-	account_slab_page(page, cachep->gfporder, cachep);
+	account_slab_page(page, cachep->gfporder, cachep, flags);
 	__SetPageSlab(page);
 	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
 	if (sk_memalloc_socks() && page_is_pfmemalloc(page))
@@ -1790,8 +1790,7 @@ static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 }
 
 slab_flags_t kmem_cache_flags(unsigned int object_size,
-	slab_flags_t flags, const char *name,
-	void (*ctor)(void *))
+	slab_flags_t flags, const char *name)
 {
 	return flags;
 }
@@ -2738,7 +2737,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 
 #else
 #define kfree_debugcheck(x) do { } while(0)
-#define cache_free_debugcheck(x,objp,z) (objp)
+#define cache_free_debugcheck(x, objp, z) (objp)
 #endif
 
 static inline void fixup_objfreelist_debug(struct kmem_cache *cachep,
@@ -3025,7 +3024,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 	return objp;
 }
 #else
-#define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
+#define cache_alloc_debugcheck_after(a, b, objp, d) (objp)
 #endif
 
 static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
@@ -3421,7 +3420,7 @@ static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
 		memset(objp, 0, cachep->object_size);
 
 	/* Put the object into the quarantine, don't touch it for now. */
-	if (kasan_slab_free(cachep, objp, _RET_IP_))
+	if (kasan_slab_free(cachep, objp))
 		return;
 
 	/* Use KCSAN to help debug racy use-after-free. */
@@ -3717,7 +3716,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 	__cache_free(cachep, objp, _RET_IP_);
 	local_irq_restore(flags);
 
-	trace_kmem_cache_free(_RET_IP_, objp);
+	trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
diff --git a/mm/slab.h b/mm/slab.h
index ecad9b57bc44..076582f58f68 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -110,8 +110,7 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		   slab_flags_t flags, void (*ctor)(void *));
 
 slab_flags_t kmem_cache_flags(unsigned int object_size,
-	slab_flags_t flags, const char *name,
-	void (*ctor)(void *));
+	slab_flags_t flags, const char *name);
 #else
 static inline struct kmem_cache *
 __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
@@ -119,8 +118,7 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 { return NULL; }
 
 static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
-	slab_flags_t flags, const char *name,
-	void (*ctor)(void *))
+	slab_flags_t flags, const char *name)
 {
 	return flags;
 }
@@ -240,7 +238,7 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 
 #ifdef CONFIG_MEMCG_KMEM
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp);
+				 gfp_t gfp, bool new_page);
 
 static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
@@ -317,7 +315,8 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 			page = virt_to_head_page(p[i]);
 
 			if (!page_objcgs(page) &&
-			    memcg_alloc_page_obj_cgroups(page, s, flags)) {
+			    memcg_alloc_page_obj_cgroups(page, s, flags,
+							 false)) {
 				obj_cgroup_uncharge(objcg, obj_full_size(s));
 				continue;
 			}
@@ -381,7 +380,8 @@ static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 }
 
 static inline int memcg_alloc_page_obj_cgroups(struct page *page,
-					       struct kmem_cache *s, gfp_t gfp)
+					       struct kmem_cache *s, gfp_t gfp,
+					       bool new_page)
 {
 	return 0;
 }
@@ -422,8 +422,12 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 }
 
 static __always_inline void account_slab_page(struct page *page, int order,
-					      struct kmem_cache *s)
+					      struct kmem_cache *s,
+					      gfp_t gfp)
 {
+	if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
+		memcg_alloc_page_obj_cgroups(page, s, gfp, true);
+
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index adbace4256ef..7c8298c17145 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -197,7 +197,7 @@ struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
 	size = ALIGN(size, sizeof(void *));
 	align = calculate_alignment(flags, align, size);
 	size = ALIGN(size, align);
-	flags = kmem_cache_flags(size, flags, name, NULL);
+	flags = kmem_cache_flags(size, flags, name);
 
 	if (flags & SLAB_NEVER_MERGE)
 		return NULL;
@@ -309,9 +309,6 @@ kmem_cache_create_usercopy(const char *name,
 	const char *cache_name;
 	int err;
 
-	get_online_cpus();
-	get_online_mems();
-
 	mutex_lock(&slab_mutex);
 
 	err = kmem_cache_sanity_check(name, size);
@@ -360,9 +357,6 @@ kmem_cache_create_usercopy(const char *name,
 out_unlock:
 	mutex_unlock(&slab_mutex);
 
-	put_online_mems();
-	put_online_cpus();
-
 	if (err) {
 		if (flags & SLAB_PANIC)
 			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
@@ -486,9 +480,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
-	get_online_cpus();
-	get_online_mems();
-
 	mutex_lock(&slab_mutex);
 
 	s->refcount--;
@@ -503,9 +494,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	}
 out_unlock:
 	mutex_unlock(&slab_mutex);
-
-	put_online_mems();
-	put_online_cpus();
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
@@ -522,12 +510,10 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
 {
 	int ret;
 
-	get_online_cpus();
-	get_online_mems();
+
 	kasan_cache_shrink(cachep);
 	ret = __kmem_cache_shrink(cachep);
-	put_online_mems();
-	put_online_cpus();
+
 	return ret;
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
@@ -912,8 +898,8 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
 	page = alloc_pages(flags, order);
 	if (likely(page)) {
 		ret = page_address(page);
-		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
-				    PAGE_SIZE << order);
+		mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
+				      PAGE_SIZE << order);
 	}
 	ret = kasan_kmalloc_large(ret, size, flags);
 	/* As ret might get tagged, call kmemleak hook after KASAN. */
@@ -1232,19 +1218,21 @@ size_t ksize(const void *objp)
 	size_t size;
 
 	/*
-	 * We need to check that the pointed to object is valid, and only then
-	 * unpoison the shadow memory below. We use __kasan_check_read(), to
-	 * generate a more useful report at the time ksize() is called (rather
-	 * than later where behaviour is undefined due to potential
-	 * use-after-free or double-free).
+	 * We need to first check that the pointer to the object is valid, and
+	 * only then unpoison the memory. The report printed from ksize() is
+	 * more useful, then when it's printed later when the behaviour could
+	 * be undefined due to a potential use-after-free or double-free.
+	 *
+	 * We use kasan_check_byte(), which is supported for the hardware
+	 * tag-based KASAN mode, unlike kasan_check_read/write().
 	 *
-	 * If the pointed to memory is invalid we return 0, to avoid users of
+	 * If the pointed to memory is invalid, we return 0 to avoid users of
 	 * ksize() writing to and potentially corrupting the memory region.
 	 *
 	 * We want to perform the check before __ksize(), to avoid potentially
 	 * crashing in __ksize() due to accessing invalid metadata.
 	 */
-	if (unlikely(ZERO_OR_NULL_PTR(objp)) || !__kasan_check_read(objp, 1))
+	if (unlikely(ZERO_OR_NULL_PTR(objp)) || !kasan_check_byte(objp))
 		return 0;
 
 	size = __ksize(objp);
diff --git a/mm/slob.c b/mm/slob.c
index ef87ada8705d..0578429b991b 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -673,7 +673,7 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 		__kmem_cache_free(b, c->size);
 	}
 
-	trace_kmem_cache_free(_RET_IP_, b);
+	trace_kmem_cache_free(_RET_IP_, b, c->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
diff --git a/mm/slub.c b/mm/slub.c
index f5baf429654f..b2833ce85c92 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -235,6 +235,14 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
 #endif
 }
 
+/*
+ * Tracks for which NUMA nodes we have kmem_cache_nodes allocated.
+ * Corresponds to node_state[N_NORMAL_MEMORY], but can temporarily
+ * differ during memory hotplug/hotremove operations.
+ * Protected by slab_mutex.
+ */
+static nodemask_t slab_nodes;
+
 /********************************************************************
  * 			Core slab cache functions
  *******************************************************************/
@@ -1400,7 +1408,6 @@ __setup("slub_debug", setup_slub_debug);
  * @object_size:	the size of an object without meta data
  * @flags:		flags to set
  * @name:		name of the cache
- * @ctor:		constructor function
  *
  * Debug option(s) are applied to @flags. In addition to the debug
  * option(s), if a slab name (or multiple) is specified i.e.
@@ -1408,13 +1415,21 @@ __setup("slub_debug", setup_slub_debug);
  * then only the select slabs will receive the debug option(s).
  */
 slab_flags_t kmem_cache_flags(unsigned int object_size,
-	slab_flags_t flags, const char *name,
-	void (*ctor)(void *))
+	slab_flags_t flags, const char *name)
 {
 	char *iter;
 	size_t len;
 	char *next_block;
 	slab_flags_t block_flags;
+	slab_flags_t slub_debug_local = slub_debug;
+
+	/*
+	 * If the slab cache is for debugging (e.g. kmemleak) then
+	 * don't store user (stack trace) information by default,
+	 * but let the user enable it via the command line below.
+	 */
+	if (flags & SLAB_NOLEAKTRACE)
+		slub_debug_local &= ~SLAB_STORE_USER;
 
 	len = strlen(name);
 	next_block = slub_debug_string;
@@ -1449,7 +1464,7 @@ slab_flags_t kmem_cache_flags(unsigned int object_size,
 		}
 	}
 
-	return flags | slub_debug;
+	return flags | slub_debug_local;
 }
 #else /* !CONFIG_SLUB_DEBUG */
 static inline void setup_object_debug(struct kmem_cache *s,
@@ -1474,8 +1489,7 @@ static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
 slab_flags_t kmem_cache_flags(unsigned int object_size,
-	slab_flags_t flags, const char *name,
-	void (*ctor)(void *))
+	slab_flags_t flags, const char *name)
 {
 	return flags;
 }
@@ -1514,7 +1528,7 @@ static inline void *kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
 static __always_inline void kfree_hook(void *x)
 {
 	kmemleak_free(x);
-	kasan_kfree_large(x, _RET_IP_);
+	kasan_kfree_large(x);
 }
 
 static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x)
@@ -1544,7 +1558,7 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x)
 				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
 
 	/* KASAN might put x into memory quarantine, delaying its reuse */
-	return kasan_slab_free(s, x, _RET_IP_);
+	return kasan_slab_free(s, x);
 }
 
 static inline bool slab_free_freelist_hook(struct kmem_cache *s,
@@ -1771,7 +1785,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	page->objects = oo_objects(oo);
 
-	account_slab_page(page, oo_order(oo), s);
+	account_slab_page(page, oo_order(oo), s, flags);
 
 	page->slab_cache = s;
 	__SetPageSlab(page);
@@ -2153,9 +2167,9 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 {
 	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
-	int lock = 0;
+	int lock = 0, free_delta = 0;
 	enum slab_modes l = M_NONE, m = M_NONE;
-	void *nextfree;
+	void *nextfree, *freelist_iter, *freelist_tail;
 	int tail = DEACTIVATE_TO_HEAD;
 	struct page new;
 	struct page old;
@@ -2166,45 +2180,34 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 	}
 
 	/*
-	 * Stage one: Free all available per cpu objects back
-	 * to the page freelist while it is still frozen. Leave the
-	 * last one.
-	 *
-	 * There is no need to take the list->lock because the page
-	 * is still frozen.
+	 * Stage one: Count the objects on cpu's freelist as free_delta and
+	 * remember the last object in freelist_tail for later splicing.
 	 */
-	while (freelist && (nextfree = get_freepointer(s, freelist))) {
-		void *prior;
-		unsigned long counters;
+	freelist_tail = NULL;
+	freelist_iter = freelist;
+	while (freelist_iter) {
+		nextfree = get_freepointer(s, freelist_iter);
 
 		/*
 		 * If 'nextfree' is invalid, it is possible that the object at
-		 * 'freelist' is already corrupted.  So isolate all objects
-		 * starting at 'freelist'.
+		 * 'freelist_iter' is already corrupted.  So isolate all objects
+		 * starting at 'freelist_iter' by skipping them.
 		 */
-		if (freelist_corrupted(s, page, &freelist, nextfree))
+		if (freelist_corrupted(s, page, &freelist_iter, nextfree))
 			break;
 
-		do {
-			prior = page->freelist;
-			counters = page->counters;
-			set_freepointer(s, freelist, prior);
-			new.counters = counters;
-			new.inuse--;
-			VM_BUG_ON(!new.frozen);
-
-		} while (!__cmpxchg_double_slab(s, page,
-			prior, counters,
-			freelist, new.counters,
-			"drain percpu freelist"));
+		freelist_tail = freelist_iter;
+		free_delta++;
 
-		freelist = nextfree;
+		freelist_iter = nextfree;
 	}
 
 	/*
-	 * Stage two: Ensure that the page is unfrozen while the
-	 * list presence reflects the actual number of objects
-	 * during unfreeze.
+	 * Stage two: Unfreeze the page while splicing the per-cpu
+	 * freelist to the head of page's freelist.
+	 *
+	 * Ensure that the page is unfrozen while the list presence
+	 * reflects the actual number of objects during unfreeze.
 	 *
 	 * We setup the list membership and then perform a cmpxchg
 	 * with the count. If there is a mismatch then the page
@@ -2217,15 +2220,15 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 	 */
 redo:
 
-	old.freelist = page->freelist;
-	old.counters = page->counters;
+	old.freelist = READ_ONCE(page->freelist);
+	old.counters = READ_ONCE(page->counters);
 	VM_BUG_ON(!old.frozen);
 
 	/* Determine target state of the slab */
 	new.counters = old.counters;
-	if (freelist) {
-		new.inuse--;
-		set_freepointer(s, freelist, old.freelist);
+	if (freelist_tail) {
+		new.inuse -= free_delta;
+		set_freepointer(s, freelist_tail, old.freelist);
 		new.freelist = freelist;
 	} else
 		new.freelist = old.freelist;
@@ -2672,7 +2675,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 		 * ignore the node constraint
 		 */
 		if (unlikely(node != NUMA_NO_NODE &&
-			     !node_state(node, N_NORMAL_MEMORY)))
+			     !node_isset(node, slab_nodes)))
 			node = NUMA_NO_NODE;
 		goto new_slab;
 	}
@@ -2683,7 +2686,7 @@ redo:
 		 * same as above but node_match() being false already
 		 * implies node != NUMA_NO_NODE
 		 */
-		if (!node_state(node, N_NORMAL_MEMORY)) {
+		if (!node_isset(node, slab_nodes)) {
 			node = NUMA_NO_NODE;
 			goto redo;
 		} else {
@@ -3157,7 +3160,7 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 	if (!s)
 		return;
 	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
-	trace_kmem_cache_free(_RET_IP_, x);
+	trace_kmem_cache_free(_RET_IP_, x, s->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
@@ -3266,7 +3269,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 		if (!df.page)
 			continue;
 
-		slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_);
+		slab_free(df.s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_);
 	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
@@ -3586,7 +3589,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s)
 {
 	int node;
 
-	for_each_node_state(node, N_NORMAL_MEMORY) {
+	for_each_node_mask(node, slab_nodes) {
 		struct kmem_cache_node *n;
 
 		if (slab_state == DOWN) {
@@ -3797,7 +3800,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 
 static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
 {
-	s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor);
+	s->flags = kmem_cache_flags(s->size, flags, s->name);
 #ifdef CONFIG_SLAB_FREELIST_HARDENED
 	s->random = get_random_long();
 #endif
@@ -4039,8 +4042,8 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	page = alloc_pages_node(node, flags, order);
 	if (page) {
 		ptr = page_address(page);
-		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
-				    PAGE_SIZE << order);
+		mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
+				      PAGE_SIZE << order);
 	}
 
 	return kmalloc_large_node_hook(ptr, size, flags);
@@ -4171,8 +4174,8 @@ void kfree(const void *x)
 
 		BUG_ON(!PageCompound(page));
 		kfree_hook(object);
-		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
-				    -(PAGE_SIZE << order));
+		mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
+				      -(PAGE_SIZE << order));
 		__free_pages(page, order);
 		return;
 	}
@@ -4267,8 +4270,6 @@ static int slab_mem_going_offline_callback(void *arg)
 
 static void slab_mem_offline_callback(void *arg)
 {
-	struct kmem_cache_node *n;
-	struct kmem_cache *s;
 	struct memory_notify *marg = arg;
 	int offline_node;
 
@@ -4282,21 +4283,12 @@ static void slab_mem_offline_callback(void *arg)
 		return;
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list) {
-		n = get_node(s, offline_node);
-		if (n) {
-			/*
-			 * if n->nr_slabs > 0, slabs still exist on the node
-			 * that is going down. We were unable to free them,
-			 * and offline_pages() function shouldn't call this
-			 * callback. So, we must fail.
-			 */
-			BUG_ON(slabs_node(s, offline_node));
-
-			s->node[offline_node] = NULL;
-			kmem_cache_free(kmem_cache_node, n);
-		}
-	}
+	node_clear(offline_node, slab_nodes);
+	/*
+	 * We no longer free kmem_cache_node structures here, as it would be
+	 * racy with all get_node() users, and infeasible to protect them with
+	 * slab_mutex.
+	 */
 	mutex_unlock(&slab_mutex);
 }
 
@@ -4323,6 +4315,12 @@ static int slab_mem_going_online_callback(void *arg)
 	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list) {
 		/*
+		 * The structure may already exist if the node was previously
+		 * onlined and offlined.
+		 */
+		if (get_node(s, nid))
+			continue;
+		/*
 		 * XXX: kmem_cache_alloc_node will fallback to other nodes
 		 *      since memory is not yet available from the node that
 		 *      is brought up.
@@ -4335,6 +4333,11 @@ static int slab_mem_going_online_callback(void *arg)
 		init_kmem_cache_node(n);
 		s->node[nid] = n;
 	}
+	/*
+	 * Any cache created after this point will also have kmem_cache_node
+	 * initialized for the new node.
+	 */
+	node_set(nid, slab_nodes);
 out:
 	mutex_unlock(&slab_mutex);
 	return ret;
@@ -4415,6 +4418,7 @@ void __init kmem_cache_init(void)
 {
 	static __initdata struct kmem_cache boot_kmem_cache,
 		boot_kmem_cache_node;
+	int node;
 
 	if (debug_guardpage_minorder())
 		slub_max_order = 0;
@@ -4422,6 +4426,13 @@ void __init kmem_cache_init(void)
 	kmem_cache_node = &boot_kmem_cache_node;
 	kmem_cache = &boot_kmem_cache;
 
+	/*
+	 * Initialize the nodemask for which we will allocate per node
+	 * structures. Here we don't need taking slab_mutex yet.
+	 */
+	for_each_node_state(node, N_NORMAL_MEMORY)
+		node_set(node, slab_nodes);
+
 	create_boot_cache(kmem_cache_node, "kmem_cache_node",
 		sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN, 0, 0);
 
@@ -4932,22 +4943,6 @@ enum slab_stat_type {
 #define SO_OBJECTS	(1 << SL_OBJECTS)
 #define SO_TOTAL	(1 << SL_TOTAL)
 
-#ifdef CONFIG_MEMCG
-static bool memcg_sysfs_enabled = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON);
-
-static int __init setup_slub_memcg_sysfs(char *str)
-{
-	int v;
-
-	if (get_option(&str, &v) > 0)
-		memcg_sysfs_enabled = v;
-
-	return 1;
-}
-
-__setup("slub_memcg_sysfs=", setup_slub_memcg_sysfs);
-#endif
-
 static ssize_t show_slab_objects(struct kmem_cache *s,
 				 char *buf, unsigned long flags)
 {
diff --git a/mm/swap.c b/mm/swap.c
index 2cca7141470c..ab3258afcbeb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -83,9 +83,8 @@ static void __page_cache_release(struct page *page)
 		unsigned long flags;
 
 		lruvec = lock_page_lruvec_irqsave(page, &flags);
-		VM_BUG_ON_PAGE(!PageLRU(page), page);
-		__ClearPageLRU(page);
-		del_page_from_lru_list(page, lruvec, page_off_lru(page));
+		del_page_from_lru_list(page, lruvec);
+		__clear_page_lru_flags(page);
 		unlock_page_lruvec_irqrestore(lruvec, flags);
 	}
 	__ClearPageWaiters(page);
@@ -229,9 +228,9 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
 static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
 {
 	if (!PageUnevictable(page)) {
-		del_page_from_lru_list(page, lruvec, page_lru(page));
+		del_page_from_lru_list(page, lruvec);
 		ClearPageActive(page);
-		add_page_to_lru_list_tail(page, lruvec, page_lru(page));
+		add_page_to_lru_list_tail(page, lruvec);
 		__count_vm_events(PGROTATED, thp_nr_pages(page));
 	}
 }
@@ -308,13 +307,11 @@ void lru_note_cost_page(struct page *page)
 static void __activate_page(struct page *page, struct lruvec *lruvec)
 {
 	if (!PageActive(page) && !PageUnevictable(page)) {
-		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
-		del_page_from_lru_list(page, lruvec, lru);
+		del_page_from_lru_list(page, lruvec);
 		SetPageActive(page);
-		lru += LRU_ACTIVE;
-		add_page_to_lru_list(page, lruvec, lru);
+		add_page_to_lru_list(page, lruvec);
 		trace_mm_lru_activate(page);
 
 		__count_vm_events(PGACTIVATE, nr_pages);
@@ -519,8 +516,7 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
  */
 static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 {
-	int lru;
-	bool active;
+	bool active = PageActive(page);
 	int nr_pages = thp_nr_pages(page);
 
 	if (PageUnevictable(page))
@@ -530,10 +526,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 	if (page_mapped(page))
 		return;
 
-	active = PageActive(page);
-	lru = page_lru_base_type(page);
-
-	del_page_from_lru_list(page, lruvec, lru + active);
+	del_page_from_lru_list(page, lruvec);
 	ClearPageActive(page);
 	ClearPageReferenced(page);
 
@@ -543,14 +536,14 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 		 * It can make readahead confusing.  But race window
 		 * is _really_ small and  it's non-critical problem.
 		 */
-		add_page_to_lru_list(page, lruvec, lru);
+		add_page_to_lru_list(page, lruvec);
 		SetPageReclaim(page);
 	} else {
 		/*
 		 * The page's writeback ends up during pagevec
 		 * We moves tha page into tail of inactive.
 		 */
-		add_page_to_lru_list_tail(page, lruvec, lru);
+		add_page_to_lru_list_tail(page, lruvec);
 		__count_vm_events(PGROTATED, nr_pages);
 	}
 
@@ -564,13 +557,12 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec)
 static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec)
 {
 	if (PageActive(page) && !PageUnevictable(page)) {
-		int lru = page_lru_base_type(page);
 		int nr_pages = thp_nr_pages(page);
 
-		del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE);
+		del_page_from_lru_list(page, lruvec);
 		ClearPageActive(page);
 		ClearPageReferenced(page);
-		add_page_to_lru_list(page, lruvec, lru);
+		add_page_to_lru_list(page, lruvec);
 
 		__count_vm_events(PGDEACTIVATE, nr_pages);
 		__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
@@ -582,11 +574,9 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
 {
 	if (PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
-		bool active = PageActive(page);
 		int nr_pages = thp_nr_pages(page);
 
-		del_page_from_lru_list(page, lruvec,
-				       LRU_INACTIVE_ANON + active);
+		del_page_from_lru_list(page, lruvec);
 		ClearPageActive(page);
 		ClearPageReferenced(page);
 		/*
@@ -595,7 +585,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec)
 		 * anonymous pages
 		 */
 		ClearPageSwapBacked(page);
-		add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE);
+		add_page_to_lru_list(page, lruvec);
 
 		__count_vm_events(PGLAZYFREE, nr_pages);
 		__count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE,
@@ -918,9 +908,8 @@ void release_pages(struct page **pages, int nr)
 			if (prev_lruvec != lruvec)
 				lock_batch = 0;
 
-			VM_BUG_ON_PAGE(!PageLRU(page), page);
-			__ClearPageLRU(page);
-			del_page_from_lru_list(page, lruvec, page_off_lru(page));
+			del_page_from_lru_list(page, lruvec);
+			__clear_page_lru_flags(page);
 		}
 
 		__ClearPageWaiters(page);
@@ -958,7 +947,6 @@ EXPORT_SYMBOL(__pagevec_release);
 
 static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 {
-	enum lru_list lru;
 	int was_unevictable = TestClearPageUnevictable(page);
 	int nr_pages = thp_nr_pages(page);
 
@@ -994,19 +982,17 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
 	smp_mb__after_atomic();
 
 	if (page_evictable(page)) {
-		lru = page_lru(page);
 		if (was_unevictable)
 			__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
 	} else {
-		lru = LRU_UNEVICTABLE;
 		ClearPageActive(page);
 		SetPageUnevictable(page);
 		if (!was_unevictable)
 			__count_vm_events(UNEVICTABLE_PGCULLED, nr_pages);
 	}
 
-	add_page_to_lru_list(page, lruvec, lru);
-	trace_mm_lru_insertion(page, lru);
+	add_page_to_lru_list(page, lruvec);
+	trace_mm_lru_insertion(page);
 }
 
 /*
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 0357fbe70645..be9de6d5b516 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -193,8 +193,7 @@ static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type,
 			cache->slots_ret = NULL;
 		}
 		spin_unlock_irq(&cache->free_lock);
-		if (slots)
-			kvfree(slots);
+		kvfree(slots);
 	}
 }
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 751c1ef2fe0e..c1a648d9092b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -68,32 +68,6 @@ static struct {
 	unsigned long find_total;
 } swap_cache_info;
 
-unsigned long total_swapcache_pages(void)
-{
-	unsigned int i, j, nr;
-	unsigned long ret = 0;
-	struct address_space *spaces;
-	struct swap_info_struct *si;
-
-	for (i = 0; i < MAX_SWAPFILES; i++) {
-		swp_entry_t entry = swp_entry(i, 1);
-
-		/* Avoid get_swap_device() to warn for bad swap entry */
-		if (!swp_swap_info(entry))
-			continue;
-		/* Prevent swapoff to free swapper_spaces */
-		si = get_swap_device(entry);
-		if (!si)
-			continue;
-		nr = nr_swapper_spaces[i];
-		spaces = swapper_spaces[i];
-		for (j = 0; j < nr; j++)
-			ret += spaces[j].nrpages;
-		put_swap_device(si);
-	}
-	return ret;
-}
-
 static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
 
 void show_swap_cache_info(void)
@@ -163,6 +137,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry,
 		address_space->nrexceptional -= nr_shadows;
 		address_space->nrpages += nr;
 		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
+		__mod_lruvec_page_state(page, NR_SWAPCACHE, nr);
 		ADD_CACHE_INFO(add_total, nr);
 unlock:
 		xas_unlock_irq(&xas);
@@ -203,6 +178,7 @@ void __delete_from_swap_cache(struct page *page,
 		address_space->nrexceptional += nr;
 	address_space->nrpages -= nr;
 	__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, -nr);
+	__mod_lruvec_page_state(page, NR_SWAPCACHE, -nr);
 	ADD_CACHE_INFO(del_total, nr);
 }
 
@@ -537,7 +513,6 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		workingset_refault(page, shadow);
 
 	/* Caller will initiate read into locked page */
-	SetPageWorkingset(page);
 	lru_cache_add(page);
 	*new_page_allocated = true;
 	return page;
@@ -927,7 +902,7 @@ static struct attribute *swap_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group swap_attr_group = {
+static const struct attribute_group swap_attr_group = {
 	.attrs = swap_attrs,
 };
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 96799a2f6957..f039745989d2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1157,13 +1157,13 @@ static struct swap_info_struct *__swap_info_get(swp_entry_t entry)
 	return p;
 
 bad_offset:
-	pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val);
+	pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val);
 	goto out;
 bad_device:
-	pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val);
+	pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val);
 	goto out;
 bad_nofile:
-	pr_err("swap_info_get: %s%08lx\n", Bad_file, entry.val);
+	pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
 out:
 	return NULL;
 }
@@ -1180,7 +1180,7 @@ static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
 	return p;
 
 bad_free:
-	pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val);
+	pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val);
 out:
 	return NULL;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b1b574ad199d..562e87cbd7a1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -310,7 +310,8 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
  * @lru: lru to use
  * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list)
  */
-unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
+static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru,
+				     int zone_idx)
 {
 	unsigned long size = 0;
 	int zid;
@@ -1539,19 +1540,17 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
  * page:	page to consider
  * mode:	one of the LRU isolation modes defined above
  *
- * returns 0 on success, -ve errno on failure.
+ * returns true on success, false on failure.
  */
-int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
+bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
 {
-	int ret = -EBUSY;
-
 	/* Only take pages on the LRU. */
 	if (!PageLRU(page))
-		return ret;
+		return false;
 
 	/* Compaction should not handle unevictable pages but CMA can do so */
 	if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
-		return ret;
+		return false;
 
 	/*
 	 * To minimise LRU disruption, the caller can indicate that it only
@@ -1564,7 +1563,7 @@ int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
 	if (mode & ISOLATE_ASYNC_MIGRATE) {
 		/* All the caller can do on PageWriteback is block */
 		if (PageWriteback(page))
-			return ret;
+			return false;
 
 		if (PageDirty(page)) {
 			struct address_space *mapping;
@@ -1580,20 +1579,20 @@ int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
 			 * from the page cache.
 			 */
 			if (!trylock_page(page))
-				return ret;
+				return false;
 
 			mapping = page_mapping(page);
 			migrate_dirty = !mapping || mapping->a_ops->migratepage;
 			unlock_page(page);
 			if (!migrate_dirty)
-				return ret;
+				return false;
 		}
 	}
 
 	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
-		return ret;
+		return false;
 
-	return 0;
+	return true;
 }
 
 /*
@@ -1677,35 +1676,31 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * only when the page is being freed somewhere else.
 		 */
 		scan += nr_pages;
-		switch (__isolate_lru_page_prepare(page, mode)) {
-		case 0:
-			/*
-			 * Be careful not to clear PageLRU until after we're
-			 * sure the page is not being freed elsewhere -- the
-			 * page release code relies on it.
-			 */
-			if (unlikely(!get_page_unless_zero(page)))
-				goto busy;
-
-			if (!TestClearPageLRU(page)) {
-				/*
-				 * This page may in other isolation path,
-				 * but we still hold lru_lock.
-				 */
-				put_page(page);
-				goto busy;
-			}
-
-			nr_taken += nr_pages;
-			nr_zone_taken[page_zonenum(page)] += nr_pages;
-			list_move(&page->lru, dst);
-			break;
+		if (!__isolate_lru_page_prepare(page, mode)) {
+			/* It is being freed elsewhere */
+			list_move(&page->lru, src);
+			continue;
+		}
+		/*
+		 * Be careful not to clear PageLRU until after we're
+		 * sure the page is not being freed elsewhere -- the
+		 * page release code relies on it.
+		 */
+		if (unlikely(!get_page_unless_zero(page))) {
+			list_move(&page->lru, src);
+			continue;
+		}
 
-		default:
-busy:
-			/* else it is being freed elsewhere */
+		if (!TestClearPageLRU(page)) {
+			/* Another thread is already isolating this page */
+			put_page(page);
 			list_move(&page->lru, src);
+			continue;
 		}
+
+		nr_taken += nr_pages;
+		nr_zone_taken[page_zonenum(page)] += nr_pages;
+		list_move(&page->lru, dst);
 	}
 
 	/*
@@ -1772,7 +1767,7 @@ int isolate_lru_page(struct page *page)
 
 		get_page(page);
 		lruvec = lock_page_lruvec_irq(page);
-		del_page_from_lru_list(page, lruvec, page_lru(page));
+		del_page_from_lru_list(page, lruvec);
 		unlock_page_lruvec_irq(lruvec);
 		ret = 0;
 	}
@@ -1829,7 +1824,6 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 	int nr_pages, nr_moved = 0;
 	LIST_HEAD(pages_to_free);
 	struct page *page;
-	enum lru_list lru;
 
 	while (!list_empty(list)) {
 		page = lru_to_page(list);
@@ -1856,8 +1850,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 		SetPageLRU(page);
 
 		if (unlikely(put_page_testzero(page))) {
-			__ClearPageLRU(page);
-			__ClearPageActive(page);
+			__clear_page_lru_flags(page);
 
 			if (unlikely(PageCompound(page))) {
 				spin_unlock_irq(&lruvec->lru_lock);
@@ -1874,11 +1867,8 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 		 * inhibits memcg migration).
 		 */
 		VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page);
-		lru = page_lru(page);
+		add_page_to_lru_list(page, lruvec);
 		nr_pages = thp_nr_pages(page);
-
-		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
-		list_add(&page->lru, &lruvec->lists[lru]);
 		nr_moved += nr_pages;
 		if (PageActive(page))
 			workingset_age_nonresident(lruvec, nr_pages);
@@ -4095,8 +4085,13 @@ module_init(kswapd_init)
  */
 int node_reclaim_mode __read_mostly;
 
-#define RECLAIM_WRITE (1<<0)	/* Writeout pages during reclaim */
-#define RECLAIM_UNMAP (1<<1)	/* Unmap pages during reclaim */
+/*
+ * These bit locations are exposed in the vm.zone_reclaim_mode sysctl
+ * ABI.  New bits are OK, but existing bits can never change.
+ */
+#define RECLAIM_ZONE  (1<<0)   /* Run shrink_inactive_list on the zone */
+#define RECLAIM_WRITE (1<<1)   /* Writeout pages during reclaim */
+#define RECLAIM_UNMAP (1<<2)   /* Unmap pages during reclaim */
 
 /*
  * Priority for NODE_RECLAIM. This determines the fraction of pages
@@ -4292,12 +4287,9 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 
 		lruvec = relock_page_lruvec_irq(page, lruvec);
 		if (page_evictable(page) && PageUnevictable(page)) {
-			enum lru_list lru = page_lru_base_type(page);
-
-			VM_BUG_ON_PAGE(PageActive(page), page);
+			del_page_from_lru_list(page, lruvec);
 			ClearPageUnevictable(page);
-			del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
-			add_page_to_lru_list(page, lruvec, lru);
+			add_page_to_lru_list(page, lruvec);
 			pgrescued += nr_pages;
 		}
 		SetPageLRU(page);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f8942160fc95..a0e949542204 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1215,6 +1215,9 @@ const char * const vmstat_text[] = {
 	"nr_shadow_call_stack",
 #endif
 	"nr_page_table_pages",
+#ifdef CONFIG_SWAP
+	"nr_swapcached",
+#endif
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
@@ -1619,8 +1622,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 	if (is_zone_first_populated(pgdat, zone)) {
 		seq_printf(m, "\n  per-node stats");
 		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+			unsigned long pages = node_page_state_pages(pgdat, i);
+
+			if (vmstat_item_print_in_thp(i))
+				pages /= HPAGE_PMD_NR;
 			seq_printf(m, "\n      %-12s %lu", node_stat_name(i),
-				   node_page_state_pages(pgdat, i));
+				   pages);
 		}
 	}
 	seq_printf(m,
@@ -1740,8 +1747,11 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
 	v += NR_VM_NUMA_STAT_ITEMS;
 #endif
 
-	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
 		v[i] = global_node_page_state_pages(i);
+		if (vmstat_item_print_in_thp(i))
+			v[i] /= HPAGE_PMD_NR;
+	}
 	v += NR_VM_NODE_STAT_ITEMS;
 
 	global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
diff --git a/mm/workingset.c b/mm/workingset.c
index 10e96de945b3..cd39902c1062 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -263,10 +263,10 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
-	workingset_age_nonresident(lruvec, thp_nr_pages(page));
 	/* XXX: target_memcg can be NULL, go through lruvec */
 	memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
 	eviction = atomic_long_read(&lruvec->nonresident_age);
+	workingset_age_nonresident(lruvec, thp_nr_pages(page));
 	return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
 }
 
@@ -461,6 +461,8 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 	unsigned long pages;
 
 	nodes = list_lru_shrink_count(&shadow_nodes, sc);
+	if (!nodes)
+		return SHRINK_EMPTY;
 
 	/*
 	 * Approximate a reasonable limit for the nodes
@@ -503,9 +505,6 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 
 	max_nodes = pages >> (XA_CHUNK_SHIFT - 3);
 
-	if (!nodes)
-		return SHRINK_EMPTY;
-
 	if (nodes <= max_nodes)
 		return 0;
 	return nodes - max_nodes;
diff --git a/mm/z3fold.c b/mm/z3fold.c
index dacb0d70fa61..c1ccf6bb0ffb 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -413,16 +413,10 @@ static struct z3fold_header *init_z3fold_page(struct page *page, bool headless,
 	if (!slots)
 		return NULL;
 
+	memset(zhdr, 0, sizeof(*zhdr));
 	spin_lock_init(&zhdr->page_lock);
 	kref_init(&zhdr->refcount);
-	zhdr->first_chunks = 0;
-	zhdr->middle_chunks = 0;
-	zhdr->last_chunks = 0;
-	zhdr->first_num = 0;
-	zhdr->start_middle = 0;
 	zhdr->cpu = -1;
-	zhdr->foreign_handles = 0;
-	zhdr->mapped_count = 0;
 	zhdr->slots = slots;
 	zhdr->pool = pool;
 	INIT_LIST_HEAD(&zhdr->buddy);
@@ -541,8 +535,7 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked)
 	spin_unlock(&pool->stale_lock);
 }
 
-static void __attribute__((__unused__))
-			release_z3fold_page(struct kref *ref)
+static void release_z3fold_page(struct kref *ref)
 {
 	struct z3fold_header *zhdr = container_of(ref, struct z3fold_header,
 						refcount);
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 953f4a2de1e5..2e3ba91a5072 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -103,6 +103,7 @@ alloated||allocated
 allocatote||allocate
 allocatrd||allocated
 allocte||allocate
+allocted||allocated
 allpication||application
 alocate||allocate
 alogirhtms||algorithms
@@ -339,6 +340,7 @@ comppatible||compatible
 compres||compress
 compresion||compression
 comression||compression
+comunicate||communicate
 comunication||communication
 conbination||combination
 conditionaly||conditionally
@@ -466,6 +468,7 @@ developpment||development
 deveolpment||development
 devided||divided
 deviece||device
+devision||division
 diable||disable
 dicline||decline
 dictionnary||dictionary
@@ -479,6 +482,7 @@ difinition||definition
 digial||digital
 dimention||dimension
 dimesions||dimensions
+diconnected||disconnected
 disgest||digest
 dispalying||displaying
 diplay||display
@@ -518,6 +522,7 @@ downlads||downloads
 droped||dropped
 droput||dropout
 druing||during
+dyanmic||dynamic
 dynmaic||dynamic
 eanable||enable
 eanble||enable
@@ -542,6 +547,7 @@ encrupted||encrypted
 encrypiton||encryption
 encryptio||encryption
 endianess||endianness
+enpoint||endpoint
 enhaced||enhanced
 enlightnment||enlightenment
 enqueing||enqueuing
@@ -566,6 +572,7 @@ estbalishment||establishment
 etsablishment||establishment
 etsbalishment||establishment
 evalution||evaluation
+exeeds||exceeds
 excecutable||executable
 exceded||exceeded
 exceds||exceeds
@@ -574,6 +581,7 @@ excellant||excellent
 execeeded||exceeded
 execeeds||exceeds
 exeed||exceed
+exeeds||exceeds
 exeuction||execution
 existance||existence
 existant||existent
@@ -641,6 +649,7 @@ forwardig||forwarding
 frambuffer||framebuffer
 framming||framing
 framwork||framework
+frequence||frequency
 frequncy||frequency
 frequancy||frequency
 frome||from
@@ -683,10 +692,12 @@ handfull||handful
 hanlde||handle
 hanled||handled
 happend||happened
+hardare||hardware
 harware||hardware
 havind||having
 heirarchically||hierarchically
 helpfull||helpful
+heterogenous||heterogeneous
 hexdecimal||hexadecimal
 hybernate||hibernate
 hierachy||hierarchy
@@ -731,6 +742,7 @@ inconsistant||inconsistent
 increas||increase
 incremeted||incremented
 incrment||increment
+incuding||including
 inculde||include
 indendation||indentation
 indended||intended
@@ -741,6 +753,7 @@ indiate||indicate
 indicat||indicate
 inexpect||inexpected
 inferface||interface
+infinit||infinite
 infomation||information
 informatiom||information
 informations||information
@@ -771,6 +784,7 @@ instace||instance
 instal||install
 instanciate||instantiate
 instanciated||instantiated
+instuments||instruments
 insufficent||insufficient
 inteface||interface
 integreated||integrated
@@ -869,12 +883,14 @@ mailformed||malformed
 malplaced||misplaced
 malplace||misplace
 managable||manageable
+managament||management
 managment||management
 mangement||management
 manger||manager
 manoeuvering||maneuvering
 manufaucturing||manufacturing
 mappping||mapping
+maping||mapping
 matchs||matches
 mathimatical||mathematical
 mathimatic||mathematic
@@ -886,6 +902,7 @@ meetign||meeting
 memeory||memory
 memmber||member
 memoery||memory
+memroy||memory
 ment||meant
 mergable||mergeable
 mesage||message
@@ -999,6 +1016,7 @@ overlaping||overlapping
 overide||override
 overrided||overridden
 overriden||overridden
+overrrun||overrun
 overun||overrun
 overwritting||overwriting
 overwriten||overwritten
@@ -1035,6 +1053,7 @@ peforming||performing
 peice||piece
 pendantic||pedantic
 peprocessor||preprocessor
+perfomance||performance
 perfoming||performing
 perfomring||performing
 periperal||peripheral
@@ -1100,6 +1119,7 @@ prodecure||procedure
 progamming||programming
 progams||programs
 progess||progress
+programable||programmable
 programers||programmers
 programm||program
 programms||programs
@@ -1144,6 +1164,7 @@ recieved||received
 recieve||receive
 reciever||receiver
 recieves||receives
+recieving||receiving
 recogniced||recognised
 recognizeable||recognizable
 recommanded||recommended
@@ -1247,6 +1268,7 @@ searchs||searches
 secquence||sequence
 secund||second
 segement||segment
+seleted||selected
 semaphone||semaphore
 senario||scenario
 senarios||scenarios
@@ -1263,6 +1285,7 @@ seqeunce||sequence
 seqeuncer||sequencer
 seqeuencer||sequencer
 sequece||sequence
+sequemce||sequence
 sequencial||sequential
 serivce||service
 serveral||several
@@ -1333,6 +1356,7 @@ suble||subtle
 substract||subtract
 submited||submitted
 submition||submission
+succeded||succeeded
 suceed||succeed
 succesfully||successfully
 succesful||successful
@@ -1353,6 +1377,7 @@ supportin||supporting
 suppoted||supported
 suppported||supported
 suppport||support
+supprot||support
 supress||suppress
 surpressed||suppressed
 surpresses||suppresses
@@ -1401,6 +1426,7 @@ thresold||threshold
 throught||through
 trackling||tracking
 troughput||throughput
+trys||tries
 thses||these
 tiggers||triggers
 tiggered||triggered
@@ -1414,7 +1440,9 @@ traking||tracking
 tramsmitted||transmitted
 tramsmit||transmit
 tranasction||transaction
+tranceiver||transceiver
 tranfer||transfer
+tranmission||transmission
 transcevier||transceiver
 transciever||transceiver
 transferd||transferred
@@ -1468,6 +1496,7 @@ unnecesary||unnecessary
 unneedingly||unnecessarily
 unnsupported||unsupported
 unmached||unmatched
+unprecise||imprecise
 unregester||unregister
 unresgister||unregister
 unrgesiter||unregister
@@ -1503,6 +1532,7 @@ varient||variant
 vaule||value
 verbse||verbose
 veify||verify
+veriosn||version
 verisons||versions
 verison||version
 verson||version
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 080a3d6cbd75..80e7b822a432 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -666,7 +666,7 @@ static void add_ignores(struct objtool_file *file)
 static const char *uaccess_safe_builtin[] = {
 	/* KASAN */
 	"kasan_report",
-	"check_memory_region",
+	"kasan_check_range",
 	/* KASAN out-of-line */
 	"__asan_loadN_noabort",
 	"__asan_load1_noabort",