Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "Am experimenting with splitting MM up into identifiable subsystems
  perhaps with a view to gitifying it in complex ways. Also with more
  verbose "incoming" emails.

  Most of MM is here and a few other trees.

  Subsystems affected by this patch series:
   - hotfixes
   - iommu
   - scripts
   - arch/sh
   - ocfs2
   - mm:slab-generic
   - mm:slub
   - mm:kmemleak
   - mm:kasan
   - mm:cleanups
   - mm:debug
   - mm:pagecache
   - mm:swap
   - mm:memcg
   - mm:gup
   - mm:pagemap
   - mm:infrastructure
   - mm:vmalloc
   - mm:initialization
   - mm:pagealloc
   - mm:vmscan
   - mm:tools
   - mm:proc
   - mm:ras
   - mm:oom-kill

  hotfixes:
      mm: vmscan: scan anonymous pages on file refaults
      mm/nvdimm: add is_ioremap_addr and use that to check ioremap address
      mm/memcontrol: fix wrong statistics in memory.stat
      mm/z3fold.c: lock z3fold page before  __SetPageMovable()
      nilfs2: do not use unexported cpu_to_le32()/le32_to_cpu() in uapi header
      MAINTAINERS: nilfs2: update email address

  iommu:
      include/linux/dmar.h: replace single-char identifiers in macros

  scripts:
      scripts/decode_stacktrace: match basepath using shell prefix operator, not regex
      scripts/decode_stacktrace: look for modules with .ko.debug extension
      scripts/spelling.txt: drop "sepc" from the misspelling list
      scripts/spelling.txt: add spelling fix for prohibited
      scripts/decode_stacktrace: Accept dash/underscore in modules
      scripts/spelling.txt: add more spellings to spelling.txt

  arch/sh:
      arch/sh/configs/sdk7786_defconfig: remove CONFIG_LOGFS
      sh: config: remove left-over BACKLIGHT_LCD_SUPPORT
      sh: prevent warnings when using iounmap

  ocfs2:
      fs: ocfs: fix spelling mistake "hearbeating" -> "heartbeat"
      ocfs2/dlm: use struct_size() helper
      ocfs2: add last unlock times in locking_state
      ocfs2: add locking filter debugfs file
      ocfs2: add first lock wait time in locking_state
      ocfs: no need to check return value of debugfs_create functions
      fs/ocfs2/dlmglue.c: unneeded variable: "status"
      ocfs2: use kmemdup rather than duplicating its implementation

  mm:slab-generic:
    Patch series "mm/slab: Improved sanity checking":
      mm/slab: validate cache membership under freelist hardening
      mm/slab: sanity-check page type when looking up cache
      lkdtm/heap: add tests for freelist hardening

  mm:slub:
      mm/slub.c: avoid double string traverse in kmem_cache_flags()
      slub: don't panic for memcg kmem cache creation failure

  mm:kmemleak:
      mm/kmemleak.c: fix check for softirq context
      mm/kmemleak.c: change error at _write when kmemleak is disabled
      docs: kmemleak: add more documentation details

  mm:kasan:
      mm/kasan: print frame description for stack bugs
      Patch series "Bitops instrumentation for KASAN", v5:
        lib/test_kasan: add bitops tests
        x86: use static_cpu_has in uaccess region to avoid instrumentation
        asm-generic, x86: add bitops instrumentation for KASAN
      Patch series "mm/kasan: Add object validation in ksize()", v3:
        mm/kasan: introduce __kasan_check_{read,write}
        mm/kasan: change kasan_check_{read,write} to return boolean
        lib/test_kasan: Add test for double-kzfree detection
        mm/slab: refactor common ksize KASAN logic into slab_common.c
        mm/kasan: add object validation in ksize()

  mm:cleanups:
      include/linux/pfn_t.h: remove pfn_t_to_virt()
      Patch series "remove ARCH_SELECT_MEMORY_MODEL where it has no effect":
        arm: remove ARCH_SELECT_MEMORY_MODEL
        s390: remove ARCH_SELECT_MEMORY_MODEL
        sparc: remove ARCH_SELECT_MEMORY_MODEL
      mm/gup.c: make follow_page_mask() static
      mm/memory.c: trivial clean up in insert_page()
      mm: make !CONFIG_HUGE_PAGE wrappers into static inlines
      include/linux/mm_types.h: ifdef struct vm_area_struct::swap_readahead_info
      mm: remove the account_page_dirtied export
      mm/page_isolation.c: change the prototype of undo_isolate_page_range()
      include/linux/vmpressure.h: use spinlock_t instead of struct spinlock
      mm: remove the exporting of totalram_pages
      include/linux/pagemap.h: document trylock_page() return value

  mm:debug:
      mm/failslab.c: by default, do not fail allocations with direct reclaim only
      Patch series "debug_pagealloc improvements":
        mm, debug_pagelloc: use static keys to enable debugging
        mm, page_alloc: more extensive free page checking with debug_pagealloc
        mm, debug_pagealloc: use a page type instead of page_ext flag

  mm:pagecache:
      Patch series "fix filler_t callback type mismatches", v2:
        mm/filemap.c: fix an overly long line in read_cache_page
        mm/filemap: don't cast ->readpage to filler_t for do_read_cache_page
        jffs2: pass the correct prototype to read_cache_page
        9p: pass the correct prototype to read_cache_page
      mm/filemap.c: correct the comment about VM_FAULT_RETRY

  mm:swap:
      mm, swap: fix race between swapoff and some swap operations
      mm/swap_state.c: simplify total_swapcache_pages() with get_swap_device()
      mm, swap: use rbtree for swap_extent
      mm/mincore.c: fix race between swapoff and mincore

  mm:memcg:
      memcg, oom: no oom-kill for __GFP_RETRY_MAYFAIL
      memcg, fsnotify: no oom-kill for remote memcg charging
      mm, memcg: introduce memory.events.local
      mm: memcontrol: dump memory.stat during cgroup OOM
      Patch series "mm: reparent slab memory on cgroup removal", v7:
        mm: memcg/slab: postpone kmem_cache memcg pointer initialization to memcg_link_cache()
        mm: memcg/slab: rename slab delayed deactivation functions and fields
        mm: memcg/slab: generalize postponed non-root kmem_cache deactivation
        mm: memcg/slab: introduce __memcg_kmem_uncharge_memcg()
        mm: memcg/slab: unify SLAB and SLUB page accounting
        mm: memcg/slab: don't check the dying flag on kmem_cache creation
        mm: memcg/slab: synchronize access to kmem_cache dying flag using a spinlock
        mm: memcg/slab: rework non-root kmem_cache lifecycle management
        mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages
        mm: memcg/slab: reparent memcg kmem_caches on cgroup removal
      mm, memcg: add a memcg_slabinfo debugfs file

  mm:gup:
      Patch series "switch the remaining architectures to use generic GUP", v4:
        mm: use untagged_addr() for get_user_pages_fast addresses
        mm: simplify gup_fast_permitted
        mm: lift the x86_32 PAE version of gup_get_pte to common code
        MIPS: use the generic get_user_pages_fast code
        sh: add the missing pud_page definition
        sh: use the generic get_user_pages_fast code
        sparc64: add the missing pgd_page definition
        sparc64: define untagged_addr()
        sparc64: use the generic get_user_pages_fast code
        mm: rename CONFIG_HAVE_GENERIC_GUP to CONFIG_HAVE_FAST_GUP
        mm: reorder code blocks in gup.c
        mm: consolidate the get_user_pages* implementations
        mm: validate get_user_pages_fast flags
        mm: move the powerpc hugepd code to mm/gup.c
        mm: switch gup_hugepte to use try_get_compound_head
        mm: mark the page referenced in gup_hugepte
      mm/gup: speed up check_and_migrate_cma_pages() on huge page
      mm/gup.c: remove some BUG_ONs from get_gate_page()
      mm/gup.c: mark undo_dev_pagemap as __maybe_unused

  mm:pagemap:
      asm-generic, x86: introduce generic pte_{alloc,free}_one[_kernel]
      alpha: switch to generic version of pte allocation
      arm: switch to generic version of pte allocation
      arm64: switch to generic version of pte allocation
      csky: switch to generic version of pte allocation
      m68k: sun3: switch to generic version of pte allocation
      mips: switch to generic version of pte allocation
      nds32: switch to generic version of pte allocation
      nios2: switch to generic version of pte allocation
      parisc: switch to generic version of pte allocation
      riscv: switch to generic version of pte allocation
      um: switch to generic version of pte allocation
      unicore32: switch to generic version of pte allocation
      mm/pgtable: drop pgtable_t variable from pte_fn_t functions
      mm/memory.c: fail when offset == num in first check of __vm_map_pages()

  mm:infrastructure:
      mm/mmu_notifier: use hlist_add_head_rcu()

  mm:vmalloc:
      Patch series "Some cleanups for the KVA/vmalloc", v5:
        mm/vmalloc.c: remove "node" argument
        mm/vmalloc.c: preload a CPU with one object for split purpose
        mm/vmalloc.c: get rid of one single unlink_va() when merge
        mm/vmalloc.c: switch to WARN_ON() and move it under unlink_va()
      mm/vmalloc.c: spelling> s/informaion/information/

  mm:initialization:
      mm/large system hash: use vmalloc for size > MAX_ORDER when !hashdist
      mm/large system hash: clear hashdist when only one node with memory is booted

  mm:pagealloc:
      arm64: move jump_label_init() before parse_early_param()
      Patch series "add init_on_alloc/init_on_free boot options", v10:
        mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options
        mm: init: report memory auto-initialization features at boot time

  mm:vmscan:
      mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
      mm: vmscan: correct some vmscan counters for THP swapout

  mm:tools:
      tools/vm/slabinfo: order command line options
      tools/vm/slabinfo: add partial slab listing to -X
      tools/vm/slabinfo: add option to sort by partial slabs
      tools/vm/slabinfo: add sorting info to help menu

  mm:proc:
      proc: use down_read_killable mmap_sem for /proc/pid/maps
      proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
      proc: use down_read_killable mmap_sem for /proc/pid/pagemap
      proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
      proc: use down_read_killable mmap_sem for /proc/pid/map_files
      mm: use down_read_killable for locking mmap_sem in access_remote_vm
      mm: smaps: split PSS into components
      mm: vmalloc: show number of vmalloc pages in /proc/meminfo

  mm:ras:
      mm/memory-failure.c: clarify error message

  mm:oom-kill:
      mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
      mm, oom: refactor dump_tasks for memcg OOMs
      mm, oom: remove redundant task_in_mem_cgroup() check
      oom: decouple mems_allowed from oom_unkillable_task
      mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()"

* akpm: (147 commits)
  mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()
  oom: decouple mems_allowed from oom_unkillable_task
  mm, oom: remove redundant task_in_mem_cgroup() check
  mm, oom: refactor dump_tasks for memcg OOMs
  mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks()
  mm/memory-failure.c: clarify error message
  mm: vmalloc: show number of vmalloc pages in /proc/meminfo
  mm: smaps: split PSS into components
  mm: use down_read_killable for locking mmap_sem in access_remote_vm
  proc: use down_read_killable mmap_sem for /proc/pid/map_files
  proc: use down_read_killable mmap_sem for /proc/pid/clear_refs
  proc: use down_read_killable mmap_sem for /proc/pid/pagemap
  proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup
  proc: use down_read_killable mmap_sem for /proc/pid/maps
  tools/vm/slabinfo: add sorting info to help menu
  tools/vm/slabinfo: add option to sort by partial slabs
  tools/vm/slabinfo: add partial slab listing to -X
  tools/vm/slabinfo: order command line options
  mm: vmscan: correct some vmscan counters for THP swapout
  mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned
  ...

20 files changed, 610 insertions, 112 deletions

diff --git a/include/asm-generic/bitops-instrumented.h b/include/asm-generic/bitops-instrumented.h
new file mode 100644
index 000000000000..ddd1c6d9d8db
--- /dev/null
+++ b/include/asm-generic/bitops-instrumented.h
@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file provides wrappers with sanitizer instrumentation for bit
+ * operations.
+ *
+ * To use this functionality, an arch's bitops.h file needs to define each of
+ * the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
+ * arch___set_bit(), etc.).
+ */
+#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_H
+#define _ASM_GENERIC_BITOPS_INSTRUMENTED_H
+
+#include <linux/kasan-checks.h>
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_set_bit(nr, addr);
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic. If it is called on the same
+ * region of memory concurrently, the effect may be that only one operation
+ * succeeds.
+ */
+static inline void __set_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___set_bit(nr, addr);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ */
+static inline void clear_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_clear_bit(nr, addr);
+}
+
+/**
+ * __clear_bit - Clears a bit in memory
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * Unlike clear_bit(), this function is non-atomic. If it is called on the same
+ * region of memory concurrently, the effect may be that only one operation
+ * succeeds.
+ */
+static inline void __clear_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___clear_bit(nr, addr);
+}
+
+/**
+ * clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_clear_bit_unlock(nr, addr);
+}
+
+/**
+ * __clear_bit_unlock - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * This is a non-atomic operation but implies a release barrier before the
+ * memory operation. It can be used for an unlock if no other CPUs can
+ * concurrently modify other bits in the word.
+ */
+static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___clear_bit_unlock(nr, addr);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_change_bit(nr, addr);
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic. If it is called on the same
+ * region of memory concurrently, the effect may be that only one operation
+ * succeeds.
+ */
+static inline void __change_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___change_bit(nr, addr);
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_set_bit(nr, addr);
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic. If two instances of this operation race, one
+ * can appear to succeed but actually fail.
+ */
+static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch___test_and_set_bit(nr, addr);
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics if
+ * the returned value is 0.
+ * It can be used to implement bit locks.
+ */
+static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_set_bit_lock(nr, addr);
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_clear_bit(nr, addr);
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic. If two instances of this operation race, one
+ * can appear to succeed but actually fail.
+ */
+static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch___test_and_clear_bit(nr, addr);
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_change_bit(nr, addr);
+}
+
+/**
+ * __test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic. If two instances of this operation race, one
+ * can appear to succeed but actually fail.
+ */
+static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch___test_and_change_bit(nr, addr);
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline bool test_bit(long nr, const volatile unsigned long *addr)
+{
+	kasan_check_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit(nr, addr);
+}
+
+#if defined(arch_clear_bit_unlock_is_negative_byte)
+/**
+ * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                     byte is negative, for unlock.
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ *
+ * This is a bit of a one-trick-pony for the filemap code, which clears
+ * PG_locked and tests PG_waiters,
+ */
+static inline bool
+clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_clear_bit_unlock_is_negative_byte(nr, addr);
+}
+/* Let everybody know we have it. */
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_H */
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 948714c1535a..8476175c07e7 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -1,13 +1,112 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ASM_GENERIC_PGALLOC_H
 #define __ASM_GENERIC_PGALLOC_H
-/*
- * an empty file is enough for a nommu architecture
- */
+
 #ifdef CONFIG_MMU
-#error need to implement an architecture specific asm/pgalloc.h
+
+#define GFP_PGTABLE_KERNEL	(GFP_KERNEL | __GFP_ZERO)
+#define GFP_PGTABLE_USER	(GFP_PGTABLE_KERNEL | __GFP_ACCOUNT)
+
+/**
+ * __pte_alloc_one_kernel - allocate a page for PTE-level kernel page table
+ * @mm: the mm_struct of the current context
+ *
+ * This function is intended for architectures that need
+ * anything beyond simple page allocation.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm)
+{
+	return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL);
+}
+
+#ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+/**
+ * pte_alloc_one_kernel - allocate a page for PTE-level kernel page table
+ * @mm: the mm_struct of the current context
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+	return __pte_alloc_one_kernel(mm);
+}
+#endif
+
+/**
+ * pte_free_kernel - free PTE-level kernel page table page
+ * @mm: the mm_struct of the current context
+ * @pte: pointer to the memory containing the page table
+ */
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+/**
+ * __pte_alloc_one - allocate a page for PTE-level user page table
+ * @mm: the mm_struct of the current context
+ * @gfp: GFP flags to use for the allocation
+ *
+ * Allocates a page and runs the pgtable_page_ctor().
+ *
+ * This function is intended for architectures that need
+ * anything beyond simple page allocation or must have custom GFP flags.
+ *
+ * Return: `struct page` initialized as page table or %NULL on error
+ */
+static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp)
+{
+	struct page *pte;
+
+	pte = alloc_page(gfp);
+	if (!pte)
+		return NULL;
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
+	}
+
+	return pte;
+}
+
+#ifndef __HAVE_ARCH_PTE_ALLOC_ONE
+/**
+ * pte_alloc_one - allocate a page for PTE-level user page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocates a page and runs the pgtable_page_ctor().
+ *
+ * Return: `struct page` initialized as page table or %NULL on error
+ */
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
+}
 #endif
 
+/*
+ * Should really implement gc for free page table pages. This could be
+ * done with a reference count in struct page.
+ */
+
+/**
+ * pte_free - free PTE-level user page table page
+ * @mm: the mm_struct of the current context
+ * @pte_page: the `struct page` representing the page table
+ */
+static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
+{
+	pgtable_page_dtor(pte_page);
+	__free_page(pte_page);
+}
+
+#else /* CONFIG_MMU */
+
+/* This is enough for a nommu architecture */
 #define check_pgt_cache()          do { } while (0)
 
+#endif /* CONFIG_MMU */
+
 #endif /* __ASM_GENERIC_PGALLOC_H */
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 28813c6f44b6..a7cf3599d9a1 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -92,12 +92,14 @@ static inline bool dmar_rcu_check(void)
 
 #define	dmar_rcu_dereference(p)	rcu_dereference_check((p), dmar_rcu_check())
 
-#define	for_each_dev_scope(a, c, p, d)	\
-	for ((p) = 0; ((d) = (p) < (c) ? dmar_rcu_dereference((a)[(p)].dev) : \
-			NULL, (p) < (c)); (p)++)
-
-#define	for_each_active_dev_scope(a, c, p, d)	\
-	for_each_dev_scope((a), (c), (p), (d))	if (!(d)) { continue; } else
+#define for_each_dev_scope(devs, cnt, i, tmp)				\
+	for ((i) = 0; ((tmp) = (i) < (cnt) ?				\
+	    dmar_rcu_dereference((devs)[(i)].dev) : NULL, (i) < (cnt)); \
+	    (i)++)
+
+#define for_each_active_dev_scope(devs, cnt, i, tmp)			\
+	for_each_dev_scope((devs), (cnt), (i), (tmp))			\
+		if (!(tmp)) { continue; } else
 
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index edf476c8cfb9..edfca4278319 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -16,29 +16,11 @@ struct user_struct;
 struct mmu_gather;
 
 #ifndef is_hugepd
-/*
- * Some architectures requires a hugepage directory format that is
- * required to support multiple hugepage sizes. For example
- * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
- * introduced the same on powerpc. This allows for a more flexible hugepage
- * pagetable layout.
- */
 typedef struct { unsigned long pd; } hugepd_t;
 #define is_hugepd(hugepd) (0)
 #define __hugepd(x) ((hugepd_t) { (x) })
-static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-			      unsigned pdshift, unsigned long end,
-			      int write, struct page **pages, int *nr)
-{
-	return 0;
-}
-#else
-extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-		       unsigned pdshift, unsigned long end,
-		       int write, struct page **pages, int *nr);
 #endif
 
-
 #ifdef CONFIG_HUGETLB_PAGE
 
 #include <linux/mempolicy.h>
@@ -608,22 +590,92 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
-#define alloc_huge_page(v, a, r) NULL
-#define alloc_huge_page_node(h, nid) NULL
-#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL
-#define alloc_huge_page_vma(h, vma, address) NULL
-#define alloc_bootmem_huge_page(h) NULL
-#define hstate_file(f) NULL
-#define hstate_sizelog(s) NULL
-#define hstate_vma(v) NULL
-#define hstate_inode(i) NULL
-#define page_hstate(page) NULL
-#define huge_page_size(h) PAGE_SIZE
-#define huge_page_mask(h) PAGE_MASK
-#define vma_kernel_pagesize(v) PAGE_SIZE
-#define vma_mmu_pagesize(v) PAGE_SIZE
-#define huge_page_order(h) 0
-#define huge_page_shift(h) PAGE_SHIFT
+
+static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
+					   unsigned long addr,
+					   int avoid_reserve)
+{
+	return NULL;
+}
+
+static inline struct page *alloc_huge_page_node(struct hstate *h, int nid)
+{
+	return NULL;
+}
+
+static inline struct page *
+alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask)
+{
+	return NULL;
+}
+
+static inline struct page *alloc_huge_page_vma(struct hstate *h,
+					       struct vm_area_struct *vma,
+					       unsigned long address)
+{
+	return NULL;
+}
+
+static inline int __alloc_bootmem_huge_page(struct hstate *h)
+{
+	return 0;
+}
+
+static inline struct hstate *hstate_file(struct file *f)
+{
+	return NULL;
+}
+
+static inline struct hstate *hstate_sizelog(int page_size_log)
+{
+	return NULL;
+}
+
+static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+
+static inline struct hstate *hstate_inode(struct inode *i)
+{
+	return NULL;
+}
+
+static inline struct hstate *page_hstate(struct page *page)
+{
+	return NULL;
+}
+
+static inline unsigned long huge_page_size(struct hstate *h)
+{
+	return PAGE_SIZE;
+}
+
+static inline unsigned long huge_page_mask(struct hstate *h)
+{
+	return PAGE_MASK;
+}
+
+static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
+{
+	return PAGE_SIZE;
+}
+
+static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
+{
+	return PAGE_SIZE;
+}
+
+static inline unsigned int huge_page_order(struct hstate *h)
+{
+	return 0;
+}
+
+static inline unsigned int huge_page_shift(struct hstate *h)
+{
+	return PAGE_SHIFT;
+}
+
 static inline bool hstate_is_gigantic(struct hstate *h)
 {
 	return false;
diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h
index a61dc075e2ce..ac6aba632f2d 100644
--- a/include/linux/kasan-checks.h
+++ b/include/linux/kasan-checks.h
@@ -2,14 +2,43 @@
 #ifndef _LINUX_KASAN_CHECKS_H
 #define _LINUX_KASAN_CHECKS_H
 
-#if defined(__SANITIZE_ADDRESS__) || defined(__KASAN_INTERNAL)
-void kasan_check_read(const volatile void *p, unsigned int size);
-void kasan_check_write(const volatile void *p, unsigned int size);
+#include <linux/types.h>
+
+/*
+ * __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!
+ */
+#ifdef CONFIG_KASAN
+bool __kasan_check_read(const volatile void *p, unsigned int size);
+bool __kasan_check_write(const volatile void *p, unsigned int size);
+#else
+static inline bool __kasan_check_read(const volatile void *p, unsigned int size)
+{
+	return true;
+}
+static inline bool __kasan_check_write(const volatile void *p, unsigned int size)
+{
+	return true;
+}
+#endif
+
+/*
+ * kasan_check_*: Only available when the particular compilation unit has KASAN
+ * instrumentation enabled. May be used in header files.
+ */
+#ifdef __SANITIZE_ADDRESS__
+#define kasan_check_read __kasan_check_read
+#define kasan_check_write __kasan_check_write
 #else
-static inline void kasan_check_read(const volatile void *p, unsigned int size)
-{ }
-static inline void kasan_check_write(const volatile void *p, unsigned int size)
-{ }
+static inline bool kasan_check_read(const volatile void *p, unsigned int size)
+{
+	return true;
+}
+static inline bool kasan_check_write(const volatile void *p, unsigned int size)
+{
+	return true;
+}
 #endif
 
 #endif
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index b40ea104dd36..cc8a03cc9674 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -76,8 +76,11 @@ void kasan_free_shadow(const struct vm_struct *vm);
 int kasan_add_zero_shadow(void *start, unsigned long size);
 void kasan_remove_zero_shadow(void *start, unsigned long size);
 
-size_t ksize(const void *);
-static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
+size_t __ksize(const void *);
+static inline void kasan_unpoison_slab(const void *ptr)
+{
+	kasan_unpoison_shadow(ptr, __ksize(ptr));
+}
 size_t kasan_metadata_size(struct kmem_cache *cache);
 
 bool kasan_save_enable_multi_shot(void);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1dcb763bb610..44c41462be33 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -233,8 +233,9 @@ struct mem_cgroup {
 	/* OOM-Killer disable */
 	int		oom_kill_disable;
 
-	/* memory.events */
+	/* memory.events and memory.events.local */
 	struct cgroup_file events_file;
+	struct cgroup_file events_local_file;
 
 	/* handle for "memory.swap.events" */
 	struct cgroup_file swap_events_file;
@@ -281,6 +282,7 @@ struct mem_cgroup {
 
 	/* memory.events */
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
+	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
 
 	unsigned long		socket_pressure;
 
@@ -392,7 +394,6 @@ out:
 
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
 
-bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
@@ -747,6 +748,9 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 static inline void memcg_memory_event(struct mem_cgroup *memcg,
 				      enum memcg_memory_event event)
 {
+	atomic_long_inc(&memcg->memory_events_local[event]);
+	cgroup_file_notify(&memcg->events_local_file);
+
 	do {
 		atomic_long_inc(&memcg->memory_events[event]);
 		cgroup_file_notify(&memcg->events_file);
@@ -870,12 +874,6 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	return true;
 }
 
-static inline bool task_in_mem_cgroup(struct task_struct *task,
-				      const struct mem_cgroup *memcg)
-{
-	return true;
-}
-
 static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	return NULL;
@@ -1273,6 +1271,8 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge(struct page *page, int order);
 int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 			      struct mem_cgroup *memcg);
+void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg,
+				 unsigned int nr_pages);
 
 extern struct static_key_false memcg_kmem_enabled_key;
 extern struct workqueue_struct *memcg_kmem_cache_wq;
@@ -1314,6 +1314,14 @@ static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp,
 		return __memcg_kmem_charge_memcg(page, gfp, order, memcg);
 	return 0;
 }
+
+static inline void memcg_kmem_uncharge_memcg(struct page *page, int order,
+					     struct mem_cgroup *memcg)
+{
+	if (memcg_kmem_enabled())
+		__memcg_kmem_uncharge_memcg(memcg, 1 << order);
+}
+
 /*
  * helper for accessing a memcg's index. It will be used as an index in the
  * child cache array in kmem_cache, and also to derive its name. This function
diff --git a/include/linux/mm.h b/include/linux/mm.h
index dd0b5f4e1e45..f88f0eabcc5e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -633,6 +633,11 @@ static inline bool is_vmalloc_addr(const void *x)
 	return false;
 #endif
 }
+
+#ifndef is_ioremap_addr
+#define is_ioremap_addr(x) is_vmalloc_addr(x)
+#endif
+
 #ifdef CONFIG_MMU
 extern int is_vmalloc_or_module_addr(const void *x);
 #else
@@ -2681,8 +2686,7 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
 	return 0;
 }
 
-typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
-			void *data);
+typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
 			       unsigned long size, pte_fn_t fn, void *data);
 
@@ -2696,11 +2700,42 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 					int enable) { }
 #endif
 
-extern bool _debug_pagealloc_enabled;
+#ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON
+DECLARE_STATIC_KEY_TRUE(init_on_alloc);
+#else
+DECLARE_STATIC_KEY_FALSE(init_on_alloc);
+#endif
+static inline bool want_init_on_alloc(gfp_t flags)
+{
+	if (static_branch_unlikely(&init_on_alloc) &&
+	    !page_poisoning_enabled())
+		return true;
+	return flags & __GFP_ZERO;
+}
+
+#ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON
+DECLARE_STATIC_KEY_TRUE(init_on_free);
+#else
+DECLARE_STATIC_KEY_FALSE(init_on_free);
+#endif
+static inline bool want_init_on_free(void)
+{
+	return static_branch_unlikely(&init_on_free) &&
+	       !page_poisoning_enabled();
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT
+DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled);
+#else
+DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled);
+#endif
 
 static inline bool debug_pagealloc_enabled(void)
 {
-	return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled;
+	if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC))
+		return false;
+
+	return static_branch_unlikely(&_debug_pagealloc_enabled);
 }
 
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
@@ -2850,11 +2885,9 @@ extern long copy_huge_page_from_user(struct page *dst_page,
 				bool allow_pagefault);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
-extern struct page_ext_operations debug_guardpage_ops;
-
 #ifdef CONFIG_DEBUG_PAGEALLOC
 extern unsigned int _debug_guardpage_minorder;
-extern bool _debug_guardpage_enabled;
+DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled);
 
 static inline unsigned int debug_guardpage_minorder(void)
 {
@@ -2863,21 +2896,15 @@ static inline unsigned int debug_guardpage_minorder(void)
 
 static inline bool debug_guardpage_enabled(void)
 {
-	return _debug_guardpage_enabled;
+	return static_branch_unlikely(&_debug_guardpage_enabled);
 }
 
 static inline bool page_is_guard(struct page *page)
 {
-	struct page_ext *page_ext;
-
 	if (!debug_guardpage_enabled())
 		return false;
 
-	page_ext = lookup_page_ext(page);
-	if (unlikely(!page_ext))
-		return false;
-
-	return test_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
+	return PageGuard(page);
 }
 #else
 static inline unsigned int debug_guardpage_minorder(void) { return 0; }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8ec38b11b361..1d1093474c1a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -329,7 +329,9 @@ struct vm_area_struct {
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
+#ifdef CONFIG_SWAP
 	atomic_long_t swap_readahead_info;
+#endif
 #ifndef CONFIG_MMU
 	struct vm_region *vm_region;	/* NOMMU mapping region */
 #endif
diff --git a/include/linux/oom.h b/include/linux/oom.h
index d07992009265..c696c265f019 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -108,7 +108,6 @@ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm)
 bool __oom_reap_task_mm(struct mm_struct *mm);
 
 extern unsigned long oom_badness(struct task_struct *p,
-		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
 
 extern bool out_of_memory(struct oom_control *oc);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 9f8712a4b1a5..b848517da64c 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -703,6 +703,7 @@ PAGEFLAG_FALSE(DoubleMap)
 #define PG_offline	0x00000100
 #define PG_kmemcg	0x00000200
 #define PG_table	0x00000400
+#define PG_guard	0x00000800
 
 #define PageType(page, flag)						\
 	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
@@ -754,6 +755,11 @@ PAGE_TYPE_OPS(Kmemcg, kmemcg)
  */
 PAGE_TYPE_OPS(Table, table)
 
+/*
+ * Marks guardpages used with debug_pagealloc.
+ */
+PAGE_TYPE_OPS(Guard, guard)
+
 extern bool is_free_buddy_page(struct page *page);
 
 __PAGEFLAG(Isolated, isolated, PF_ANY);
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 280ae96dc4c3..1099c2fee20f 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -50,7 +50,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
  * target range is [start_pfn, end_pfn)
  */
-int
+void
 undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			unsigned migratetype);
 
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index f84f167ec04c..09592951725c 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -17,7 +17,6 @@ struct page_ext_operations {
 #ifdef CONFIG_PAGE_EXTENSION
 
 enum page_ext_flags {
-	PAGE_EXT_DEBUG_GUARD,
 	PAGE_EXT_OWNER,
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
 	PAGE_EXT_YOUNG,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index fe0b29bf2df7..c7552459a15f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -383,8 +383,7 @@ extern int read_cache_pages(struct address_space *mapping,
 static inline struct page *read_mapping_page(struct address_space *mapping,
 				pgoff_t index, void *data)
 {
-	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
-	return read_cache_page(mapping, index, filler, data);
+	return read_cache_page(mapping, index, NULL, data);
 }
 
 /*
@@ -452,6 +451,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
 
+/*
+ * Return true if the page was successfully locked
+ */
 static inline int trylock_page(struct page *page)
 {
 	page = compound_head(page);
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 3c202a11a79e..01e8037023f7 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -66,13 +66,6 @@ static inline phys_addr_t pfn_t_to_phys(pfn_t pfn)
 	return PFN_PHYS(pfn_t_to_pfn(pfn));
 }
 
-static inline void *pfn_t_to_virt(pfn_t pfn)
-{
-	if (pfn_t_has_page(pfn) && !is_device_private_page(pfn_t_to_page(pfn)))
-		return __va(pfn_t_to_phys(pfn));
-	return NULL;
-}
-
 static inline pfn_t page_to_pfn_t(struct page *page)
 {
 	return pfn_to_pfn_t(page_to_pfn(page));
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9449b19c5f10..56c9c7eed34e 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -16,6 +16,7 @@
 #include <linux/overflow.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
+#include <linux/percpu-refcount.h>
 
 
 /*
@@ -115,6 +116,10 @@
 /* Objects are reclaimable */
 #define SLAB_RECLAIM_ACCOUNT	((slab_flags_t __force)0x00020000U)
 #define SLAB_TEMPORARY		SLAB_RECLAIM_ACCOUNT	/* Objects are short-lived */
+
+/* Slab deactivation flag */
+#define SLAB_DEACTIVATED	((slab_flags_t __force)0x10000000U)
+
 /*
  * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests.
  *
@@ -151,8 +156,7 @@ void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 
 void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
-void memcg_deactivate_kmem_caches(struct mem_cgroup *);
-void memcg_destroy_kmem_caches(struct mem_cgroup *);
+void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *);
 
 /*
  * Please use this macro to create slab caches. Simply specify the
@@ -184,6 +188,7 @@ void * __must_check __krealloc(const void *, size_t, gfp_t);
 void * __must_check krealloc(const void *, size_t, gfp_t);
 void kfree(const void *);
 void kzfree(const void *);
+size_t __ksize(const void *);
 size_t ksize(const void *);
 
 #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
@@ -641,11 +646,12 @@ struct memcg_cache_params {
 			struct mem_cgroup *memcg;
 			struct list_head children_node;
 			struct list_head kmem_caches_node;
+			struct percpu_ref refcnt;
 
-			void (*deact_fn)(struct kmem_cache *);
+			void (*work_fn)(struct kmem_cache *);
 			union {
-				struct rcu_head deact_rcu_head;
-				struct work_struct deact_work;
+				struct rcu_head rcu_head;
+				struct work_struct work;
 			};
 		};
 	};
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4bfb5c4ac108..de2c67a33b7e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -148,7 +148,7 @@ struct zone;
  * We always assume that blocks are of size PAGE_SIZE.
  */
 struct swap_extent {
-	struct list_head list;
+	struct rb_node rb_node;
 	pgoff_t start_page;
 	pgoff_t nr_pages;
 	sector_t start_block;
@@ -175,8 +175,9 @@ enum {
 	SWP_PAGE_DISCARD = (1 << 10),	/* freed swap page-cluster discards */
 	SWP_STABLE_WRITES = (1 << 11),	/* no overwrite PG_writeback pages */
 	SWP_SYNCHRONOUS_IO = (1 << 12),	/* synchronous IO is efficient */
+	SWP_VALID	= (1 << 13),	/* swap is valid to be operated on? */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 13),	/* refcount in scan_swap_map */
+	SWP_SCANNING	= (1 << 14),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
@@ -247,8 +248,7 @@ struct swap_info_struct {
 	unsigned int cluster_next;	/* likely index for next allocation */
 	unsigned int cluster_nr;	/* countdown to next cluster search */
 	struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
-	struct swap_extent *curr_swap_extent;
-	struct swap_extent first_swap_extent;
+	struct rb_root swap_extent_root;/* root of the swap extent rbtree */
 	struct block_device *bdev;	/* swap device or bdev of swap file */
 	struct file *swap_file;		/* seldom referenced */
 	unsigned int old_block_size;	/* seldom referenced */
@@ -460,7 +460,7 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
-extern int __swap_count(struct swap_info_struct *si, swp_entry_t entry);
+extern int __swap_count(swp_entry_t entry);
 extern int __swp_swapcount(swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
@@ -470,6 +470,12 @@ extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
 extern void exit_swap_address_space(unsigned int type);
+extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
+
+static inline void put_swap_device(struct swap_info_struct *si)
+{
+	rcu_read_unlock();
+}
 
 #else /* CONFIG_SWAP */
 
@@ -576,7 +582,7 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
-static inline int __swap_count(struct swap_info_struct *si, swp_entry_t entry)
+static inline int __swap_count(swp_entry_t entry)
 {
 	return 0;
 }
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 51e131245379..9b21d0047710 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -72,10 +72,12 @@ extern void vm_unmap_aliases(void);
 
 #ifdef CONFIG_MMU
 extern void __init vmalloc_init(void);
+extern unsigned long vmalloc_nr_pages(void);
 #else
 static inline void vmalloc_init(void)
 {
 }
+static inline unsigned long vmalloc_nr_pages(void) { return 0; }
 #endif
 
 extern void *vmalloc(unsigned long size);
diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h
index 61e6fddfb26f..6d28bc433c1c 100644
--- a/include/linux/vmpressure.h
+++ b/include/linux/vmpressure.h
@@ -17,7 +17,7 @@ struct vmpressure {
 	unsigned long tree_scanned;
 	unsigned long tree_reclaimed;
 	/* The lock is used to keep the scanned/reclaimed above in sync. */
-	struct spinlock sr_lock;
+	spinlock_t sr_lock;
 
 	/* The list of vmpressure_event structs. */
 	struct list_head events;
diff --git a/include/uapi/linux/nilfs2_ondisk.h b/include/uapi/linux/nilfs2_ondisk.h
index a7e66ab11d1d..c23f91ae5fe8 100644
--- a/include/uapi/linux/nilfs2_ondisk.h
+++ b/include/uapi/linux/nilfs2_ondisk.h
@@ -29,7 +29,7 @@
 
 #include <linux/types.h>
 #include <linux/magic.h>
-
+#include <asm/byteorder.h>
 
 #define NILFS_INODE_BMAP_SIZE	7
 
@@ -533,19 +533,19 @@ enum {
 static inline void							\
 nilfs_checkpoint_set_##name(struct nilfs_checkpoint *cp)		\
 {									\
-	cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) |		\
-				   (1UL << NILFS_CHECKPOINT_##flag));	\
+	cp->cp_flags = __cpu_to_le32(__le32_to_cpu(cp->cp_flags) |	\
+				     (1UL << NILFS_CHECKPOINT_##flag));	\
 }									\
 static inline void							\
 nilfs_checkpoint_clear_##name(struct nilfs_checkpoint *cp)		\
 {									\
-	cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) &		\
+	cp->cp_flags = __cpu_to_le32(__le32_to_cpu(cp->cp_flags) &	\
 				   ~(1UL << NILFS_CHECKPOINT_##flag));	\
 }									\
 static inline int							\
 nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp)		\
 {									\
-	return !!(le32_to_cpu(cp->cp_flags) &				\
+	return !!(__le32_to_cpu(cp->cp_flags) &				\
 		  (1UL << NILFS_CHECKPOINT_##flag));			\
 }
 
@@ -595,20 +595,20 @@ enum {
 static inline void							\
 nilfs_segment_usage_set_##name(struct nilfs_segment_usage *su)		\
 {									\
-	su->su_flags = cpu_to_le32(le32_to_cpu(su->su_flags) |		\
+	su->su_flags = __cpu_to_le32(__le32_to_cpu(su->su_flags) |	\
 				   (1UL << NILFS_SEGMENT_USAGE_##flag));\
 }									\
 static inline void							\
 nilfs_segment_usage_clear_##name(struct nilfs_segment_usage *su)	\
 {									\
 	su->su_flags =							\
-		cpu_to_le32(le32_to_cpu(su->su_flags) &			\
+		__cpu_to_le32(__le32_to_cpu(su->su_flags) &		\
 			    ~(1UL << NILFS_SEGMENT_USAGE_##flag));      \
 }									\
 static inline int							\
 nilfs_segment_usage_##name(const struct nilfs_segment_usage *su)	\
 {									\
-	return !!(le32_to_cpu(su->su_flags) &				\
+	return !!(__le32_to_cpu(su->su_flags) &				\
 		  (1UL << NILFS_SEGMENT_USAGE_##flag));			\
 }
 
@@ -619,15 +619,15 @@ NILFS_SEGMENT_USAGE_FNS(ERROR, error)
 static inline void
 nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su)
 {
-	su->su_lastmod = cpu_to_le64(0);
-	su->su_nblocks = cpu_to_le32(0);
-	su->su_flags = cpu_to_le32(0);
+	su->su_lastmod = __cpu_to_le64(0);
+	su->su_nblocks = __cpu_to_le32(0);
+	su->su_flags = __cpu_to_le32(0);
 }
 
 static inline int
 nilfs_segment_usage_clean(const struct nilfs_segment_usage *su)
 {
-	return !le32_to_cpu(su->su_flags);
+	return !__le32_to_cpu(su->su_flags);
 }
 
 /**