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
  ...

1 files changed, 256 insertions, 205 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ba9138a4a1de..4f05735b02d3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -57,6 +57,7 @@
 #include <linux/lockdep.h>
 #include <linux/file.h>
 #include <linux/tracehook.h>
+#include <linux/seq_buf.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -485,7 +486,10 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	memcg = READ_ONCE(page->mem_cgroup);
+	if (PageHead(page) && PageSlab(page))
+		memcg = memcg_from_slab_page(page);
+	else
+		memcg = READ_ONCE(page->mem_cgroup);
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
 	if (memcg)
@@ -1163,7 +1167,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 		struct css_task_iter it;
 		struct task_struct *task;
 
-		css_task_iter_start(&iter->css, 0, &it);
+		css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it);
 		while (!ret && (task = css_task_iter_next(&it)))
 			ret = fn(task, arg);
 		css_task_iter_end(&it);
@@ -1255,32 +1259,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 		*lru_size += nr_pages;
 }
 
-bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
-{
-	struct mem_cgroup *task_memcg;
-	struct task_struct *p;
-	bool ret;
-
-	p = find_lock_task_mm(task);
-	if (p) {
-		task_memcg = get_mem_cgroup_from_mm(p->mm);
-		task_unlock(p);
-	} else {
-		/*
-		 * All threads may have already detached their mm's, but the oom
-		 * killer still needs to detect if they have already been oom
-		 * killed to prevent needlessly killing additional tasks.
-		 */
-		rcu_read_lock();
-		task_memcg = mem_cgroup_from_task(task);
-		css_get(&task_memcg->css);
-		rcu_read_unlock();
-	}
-	ret = mem_cgroup_is_descendant(task_memcg, memcg);
-	css_put(&task_memcg->css);
-	return ret;
-}
-
 /**
  * mem_cgroup_margin - calculate chargeable space of a memory cgroup
  * @memcg: the memory cgroup
@@ -1356,27 +1334,114 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
 	return false;
 }
 
-static const unsigned int memcg1_stats[] = {
-	MEMCG_CACHE,
-	MEMCG_RSS,
-	MEMCG_RSS_HUGE,
-	NR_SHMEM,
-	NR_FILE_MAPPED,
-	NR_FILE_DIRTY,
-	NR_WRITEBACK,
-	MEMCG_SWAP,
-};
+static char *memory_stat_format(struct mem_cgroup *memcg)
+{
+	struct seq_buf s;
+	int i;
 
-static const char *const memcg1_stat_names[] = {
-	"cache",
-	"rss",
-	"rss_huge",
-	"shmem",
-	"mapped_file",
-	"dirty",
-	"writeback",
-	"swap",
-};
+	seq_buf_init(&s, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE);
+	if (!s.buffer)
+		return NULL;
+
+	/*
+	 * Provide statistics on the state of the memory subsystem as
+	 * well as cumulative event counters that show past behavior.
+	 *
+	 * This list is ordered following a combination of these gradients:
+	 * 1) generic big picture -> specifics and details
+	 * 2) reflecting userspace activity -> reflecting kernel heuristics
+	 *
+	 * Current memory state:
+	 */
+
+	seq_buf_printf(&s, "anon %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_RSS) *
+		       PAGE_SIZE);
+	seq_buf_printf(&s, "file %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_CACHE) *
+		       PAGE_SIZE);
+	seq_buf_printf(&s, "kernel_stack %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) *
+		       1024);
+	seq_buf_printf(&s, "slab %llu\n",
+		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) +
+			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) *
+		       PAGE_SIZE);
+	seq_buf_printf(&s, "sock %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
+		       PAGE_SIZE);
+
+	seq_buf_printf(&s, "shmem %llu\n",
+		       (u64)memcg_page_state(memcg, NR_SHMEM) *
+		       PAGE_SIZE);
+	seq_buf_printf(&s, "file_mapped %llu\n",
+		       (u64)memcg_page_state(memcg, NR_FILE_MAPPED) *
+		       PAGE_SIZE);
+	seq_buf_printf(&s, "file_dirty %llu\n",
+		       (u64)memcg_page_state(memcg, NR_FILE_DIRTY) *
+		       PAGE_SIZE);
+	seq_buf_printf(&s, "file_writeback %llu\n",
+		       (u64)memcg_page_state(memcg, NR_WRITEBACK) *
+		       PAGE_SIZE);
+
+	/*
+	 * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter
+	 * with the NR_ANON_THP vm counter, but right now it's a pain in the
+	 * arse because it requires migrating the work out of rmap to a place
+	 * where the page->mem_cgroup is set up and stable.
+	 */
+	seq_buf_printf(&s, "anon_thp %llu\n",
+		       (u64)memcg_page_state(memcg, MEMCG_RSS_HUGE) *
+		       PAGE_SIZE);
+
+	for (i = 0; i < NR_LRU_LISTS; i++)
+		seq_buf_printf(&s, "%s %llu\n", mem_cgroup_lru_names[i],
+			       (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
+			       PAGE_SIZE);
+
+	seq_buf_printf(&s, "slab_reclaimable %llu\n",
+		       (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) *
+		       PAGE_SIZE);
+	seq_buf_printf(&s, "slab_unreclaimable %llu\n",
+		       (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) *
+		       PAGE_SIZE);
+
+	/* Accumulated memory events */
+
+	seq_buf_printf(&s, "pgfault %lu\n", memcg_events(memcg, PGFAULT));
+	seq_buf_printf(&s, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT));
+
+	seq_buf_printf(&s, "workingset_refault %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_REFAULT));
+	seq_buf_printf(&s, "workingset_activate %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_ACTIVATE));
+	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
+
+	seq_buf_printf(&s, "pgrefill %lu\n", memcg_events(memcg, PGREFILL));
+	seq_buf_printf(&s, "pgscan %lu\n",
+		       memcg_events(memcg, PGSCAN_KSWAPD) +
+		       memcg_events(memcg, PGSCAN_DIRECT));
+	seq_buf_printf(&s, "pgsteal %lu\n",
+		       memcg_events(memcg, PGSTEAL_KSWAPD) +
+		       memcg_events(memcg, PGSTEAL_DIRECT));
+	seq_buf_printf(&s, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE));
+	seq_buf_printf(&s, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE));
+	seq_buf_printf(&s, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE));
+	seq_buf_printf(&s, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED));
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	seq_buf_printf(&s, "thp_fault_alloc %lu\n",
+		       memcg_events(memcg, THP_FAULT_ALLOC));
+	seq_buf_printf(&s, "thp_collapse_alloc %lu\n",
+		       memcg_events(memcg, THP_COLLAPSE_ALLOC));
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+	/* The above should easily fit into one page */
+	WARN_ON_ONCE(seq_buf_has_overflowed(&s));
+
+	return s.buffer;
+}
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /**
@@ -1411,39 +1476,32 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *
  */
 void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *iter;
-	unsigned int i;
+	char *buf;
 
 	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
 		K((u64)page_counter_read(&memcg->memory)),
 		K((u64)memcg->memory.max), memcg->memory.failcnt);
-	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
-		K((u64)page_counter_read(&memcg->memsw)),
-		K((u64)memcg->memsw.max), memcg->memsw.failcnt);
-	pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
-		K((u64)page_counter_read(&memcg->kmem)),
-		K((u64)memcg->kmem.max), memcg->kmem.failcnt);
-
-	for_each_mem_cgroup_tree(iter, memcg) {
-		pr_info("Memory cgroup stats for ");
-		pr_cont_cgroup_path(iter->css.cgroup);
-		pr_cont(":");
-
-		for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
-			if (memcg1_stats[i] == MEMCG_SWAP && !do_swap_account)
-				continue;
-			pr_cont(" %s:%luKB", memcg1_stat_names[i],
-				K(memcg_page_state_local(iter,
-							 memcg1_stats[i])));
-		}
-
-		for (i = 0; i < NR_LRU_LISTS; i++)
-			pr_cont(" %s:%luKB", mem_cgroup_lru_names[i],
-				K(memcg_page_state_local(iter,
-							 NR_LRU_BASE + i)));
-
-		pr_cont("\n");
+	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n",
+			K((u64)page_counter_read(&memcg->swap)),
+			K((u64)memcg->swap.max), memcg->swap.failcnt);
+	else {
+		pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
+			K((u64)page_counter_read(&memcg->memsw)),
+			K((u64)memcg->memsw.max), memcg->memsw.failcnt);
+		pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
+			K((u64)page_counter_read(&memcg->kmem)),
+			K((u64)memcg->kmem.max), memcg->kmem.failcnt);
 	}
+
+	pr_info("Memory cgroup stats for ");
+	pr_cont_cgroup_path(memcg->css.cgroup);
+	pr_cont(":");
+	buf = memory_stat_format(memcg);
+	if (!buf)
+		return;
+	pr_info("%s", buf);
+	kfree(buf);
 }
 
 /*
@@ -2279,7 +2337,6 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long nr_reclaimed;
 	bool may_swap = true;
 	bool drained = false;
-	bool oomed = false;
 	enum oom_status oom_status;
 
 	if (mem_cgroup_is_root(memcg))
@@ -2366,7 +2423,7 @@ retry:
 	if (nr_retries--)
 		goto retry;
 
-	if (gfp_mask & __GFP_RETRY_MAYFAIL && oomed)
+	if (gfp_mask & __GFP_RETRY_MAYFAIL)
 		goto nomem;
 
 	if (gfp_mask & __GFP_NOFAIL)
@@ -2385,7 +2442,6 @@ retry:
 	switch (oom_status) {
 	case OOM_SUCCESS:
 		nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-		oomed = true;
 		goto retry;
 	case OOM_FAILED:
 		goto force;
@@ -2588,12 +2644,13 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 {
 	struct memcg_kmem_cache_create_work *cw;
 
+	if (!css_tryget_online(&memcg->css))
+		return;
+
 	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
 	if (!cw)
 		return;
 
-	css_get(&memcg->css);
-
 	cw->memcg = memcg;
 	cw->cachep = cachep;
 	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
@@ -2628,6 +2685,7 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
+	struct memcg_cache_array *arr;
 	int kmemcg_id;
 
 	VM_BUG_ON(!is_root_cache(cachep));
@@ -2635,14 +2693,28 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 	if (memcg_kmem_bypass())
 		return cachep;
 
-	memcg = get_mem_cgroup_from_current();
+	rcu_read_lock();
+
+	if (unlikely(current->active_memcg))
+		memcg = current->active_memcg;
+	else
+		memcg = mem_cgroup_from_task(current);
+
+	if (!memcg || memcg == root_mem_cgroup)
+		goto out_unlock;
+
 	kmemcg_id = READ_ONCE(memcg->kmemcg_id);
 	if (kmemcg_id < 0)
-		goto out;
+		goto out_unlock;
 
-	memcg_cachep = cache_from_memcg_idx(cachep, kmemcg_id);
-	if (likely(memcg_cachep))
-		return memcg_cachep;
+	arr = rcu_dereference(cachep->memcg_params.memcg_caches);
+
+	/*
+	 * Make sure we will access the up-to-date value. The code updating
+	 * memcg_caches issues a write barrier to match the data dependency
+	 * barrier inside READ_ONCE() (see memcg_create_kmem_cache()).
+	 */
+	memcg_cachep = READ_ONCE(arr->entries[kmemcg_id]);
 
 	/*
 	 * If we are in a safe context (can wait, and not in interrupt
@@ -2655,10 +2727,20 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 	 * memcg_create_kmem_cache, this means no further allocation
 	 * could happen with the slab_mutex held. So it's better to
 	 * defer everything.
+	 *
+	 * If the memcg is dying or memcg_cache is about to be released,
+	 * don't bother creating new kmem_caches. Because memcg_cachep
+	 * is ZEROed as the fist step of kmem offlining, we don't need
+	 * percpu_ref_tryget_live() here. css_tryget_online() check in
+	 * memcg_schedule_kmem_cache_create() will prevent us from
+	 * creation of a new kmem_cache.
 	 */
-	memcg_schedule_kmem_cache_create(memcg, cachep);
-out:
-	css_put(&memcg->css);
+	if (unlikely(!memcg_cachep))
+		memcg_schedule_kmem_cache_create(memcg, cachep);
+	else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt))
+		cachep = memcg_cachep;
+out_unlock:
+	rcu_read_unlock();
 	return cachep;
 }
 
@@ -2669,7 +2751,7 @@ out:
 void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 	if (!is_root_cache(cachep))
-		css_put(&cachep->memcg_params.memcg->css);
+		percpu_ref_put(&cachep->memcg_params.refcnt);
 }
 
 /**
@@ -2697,9 +2779,6 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 		cancel_charge(memcg, nr_pages);
 		return -ENOMEM;
 	}
-
-	page->mem_cgroup = memcg;
-
 	return 0;
 }
 
@@ -2722,12 +2801,30 @@ int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 	memcg = get_mem_cgroup_from_current();
 	if (!mem_cgroup_is_root(memcg)) {
 		ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg);
-		if (!ret)
+		if (!ret) {
+			page->mem_cgroup = memcg;
 			__SetPageKmemcg(page);
+		}
 	}
 	css_put(&memcg->css);
 	return ret;
 }
+
+/**
+ * __memcg_kmem_uncharge_memcg: uncharge a kmem page
+ * @memcg: memcg to uncharge
+ * @nr_pages: number of pages to uncharge
+ */
+void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg,
+				 unsigned int nr_pages)
+{
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		page_counter_uncharge(&memcg->kmem, nr_pages);
+
+	page_counter_uncharge(&memcg->memory, nr_pages);
+	if (do_memsw_account())
+		page_counter_uncharge(&memcg->memsw, nr_pages);
+}
 /**
  * __memcg_kmem_uncharge: uncharge a kmem page
  * @page: page to uncharge
@@ -2742,14 +2839,7 @@ void __memcg_kmem_uncharge(struct page *page, int order)
 		return;
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
-
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		page_counter_uncharge(&memcg->kmem, nr_pages);
-
-	page_counter_uncharge(&memcg->memory, nr_pages);
-	if (do_memsw_account())
-		page_counter_uncharge(&memcg->memsw, nr_pages);
-
+	__memcg_kmem_uncharge_memcg(memcg, nr_pages);
 	page->mem_cgroup = NULL;
 
 	/* slab pages do not have PageKmemcg flag set */
@@ -3168,15 +3258,15 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 	 */
 	memcg->kmem_state = KMEM_ALLOCATED;
 
-	memcg_deactivate_kmem_caches(memcg);
-
-	kmemcg_id = memcg->kmemcg_id;
-	BUG_ON(kmemcg_id < 0);
-
 	parent = parent_mem_cgroup(memcg);
 	if (!parent)
 		parent = root_mem_cgroup;
 
+	memcg_deactivate_kmem_caches(memcg, parent);
+
+	kmemcg_id = memcg->kmemcg_id;
+	BUG_ON(kmemcg_id < 0);
+
 	/*
 	 * Change kmemcg_id of this cgroup and all its descendants to the
 	 * parent's id, and then move all entries from this cgroup's list_lrus
@@ -3207,9 +3297,8 @@ static void memcg_free_kmem(struct mem_cgroup *memcg)
 		memcg_offline_kmem(memcg);
 
 	if (memcg->kmem_state == KMEM_ALLOCATED) {
-		memcg_destroy_kmem_caches(memcg);
+		WARN_ON(!list_empty(&memcg->kmem_caches));
 		static_branch_dec(&memcg_kmem_enabled_key);
-		WARN_ON(page_counter_read(&memcg->kmem));
 	}
 }
 #else
@@ -3472,6 +3561,28 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v)
 }
 #endif /* CONFIG_NUMA */
 
+static const unsigned int memcg1_stats[] = {
+	MEMCG_CACHE,
+	MEMCG_RSS,
+	MEMCG_RSS_HUGE,
+	NR_SHMEM,
+	NR_FILE_MAPPED,
+	NR_FILE_DIRTY,
+	NR_WRITEBACK,
+	MEMCG_SWAP,
+};
+
+static const char *const memcg1_stat_names[] = {
+	"cache",
+	"rss",
+	"rss_huge",
+	"shmem",
+	"mapped_file",
+	"dirty",
+	"writeback",
+	"swap",
+};
+
 /* Universal VM events cgroup1 shows, original sort order */
 static const unsigned int memcg1_events[] = {
 	PGPGIN,
@@ -3530,12 +3641,13 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
 		seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
-			   (u64)memcg_page_state(memcg, i) * PAGE_SIZE);
+			   (u64)memcg_page_state(memcg, memcg1_stats[i]) *
+			   PAGE_SIZE);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
 		seq_printf(m, "total_%s %llu\n", memcg1_event_names[i],
-			   (u64)memcg_events(memcg, i));
+			   (u64)memcg_events(memcg, memcg1_events[i]));
 
 	for (i = 0; i < NR_LRU_LISTS; i++)
 		seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i],
@@ -4634,6 +4746,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	/* The following stuff does not apply to the root */
 	if (!parent) {
+#ifdef CONFIG_MEMCG_KMEM
+		INIT_LIST_HEAD(&memcg->kmem_caches);
+#endif
 		root_mem_cgroup = memcg;
 		return &memcg->css;
 	}
@@ -5625,112 +5740,42 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static void __memory_events_show(struct seq_file *m, atomic_long_t *events)
+{
+	seq_printf(m, "low %lu\n", atomic_long_read(&events[MEMCG_LOW]));
+	seq_printf(m, "high %lu\n", atomic_long_read(&events[MEMCG_HIGH]));
+	seq_printf(m, "max %lu\n", atomic_long_read(&events[MEMCG_MAX]));
+	seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM]));
+	seq_printf(m, "oom_kill %lu\n",
+		   atomic_long_read(&events[MEMCG_OOM_KILL]));
+}
+
 static int memory_events_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	seq_printf(m, "low %lu\n",
-		   atomic_long_read(&memcg->memory_events[MEMCG_LOW]));
-	seq_printf(m, "high %lu\n",
-		   atomic_long_read(&memcg->memory_events[MEMCG_HIGH]));
-	seq_printf(m, "max %lu\n",
-		   atomic_long_read(&memcg->memory_events[MEMCG_MAX]));
-	seq_printf(m, "oom %lu\n",
-		   atomic_long_read(&memcg->memory_events[MEMCG_OOM]));
-	seq_printf(m, "oom_kill %lu\n",
-		   atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL]));
-
+	__memory_events_show(m, memcg->memory_events);
 	return 0;
 }
 
-static int memory_stat_show(struct seq_file *m, void *v)
+static int memory_events_local_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
-	int i;
-
-	/*
-	 * Provide statistics on the state of the memory subsystem as
-	 * well as cumulative event counters that show past behavior.
-	 *
-	 * This list is ordered following a combination of these gradients:
-	 * 1) generic big picture -> specifics and details
-	 * 2) reflecting userspace activity -> reflecting kernel heuristics
-	 *
-	 * Current memory state:
-	 */
-
-	seq_printf(m, "anon %llu\n",
-		   (u64)memcg_page_state(memcg, MEMCG_RSS) * PAGE_SIZE);
-	seq_printf(m, "file %llu\n",
-		   (u64)memcg_page_state(memcg, MEMCG_CACHE) * PAGE_SIZE);
-	seq_printf(m, "kernel_stack %llu\n",
-		   (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) * 1024);
-	seq_printf(m, "slab %llu\n",
-		   (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) +
-			 memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) *
-		   PAGE_SIZE);
-	seq_printf(m, "sock %llu\n",
-		   (u64)memcg_page_state(memcg, MEMCG_SOCK) * PAGE_SIZE);
-
-	seq_printf(m, "shmem %llu\n",
-		   (u64)memcg_page_state(memcg, NR_SHMEM) * PAGE_SIZE);
-	seq_printf(m, "file_mapped %llu\n",
-		   (u64)memcg_page_state(memcg, NR_FILE_MAPPED) * PAGE_SIZE);
-	seq_printf(m, "file_dirty %llu\n",
-		   (u64)memcg_page_state(memcg, NR_FILE_DIRTY) * PAGE_SIZE);
-	seq_printf(m, "file_writeback %llu\n",
-		   (u64)memcg_page_state(memcg, NR_WRITEBACK) * PAGE_SIZE);
 
-	/*
-	 * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter
-	 * with the NR_ANON_THP vm counter, but right now it's a pain in the
-	 * arse because it requires migrating the work out of rmap to a place
-	 * where the page->mem_cgroup is set up and stable.
-	 */
-	seq_printf(m, "anon_thp %llu\n",
-		   (u64)memcg_page_state(memcg, MEMCG_RSS_HUGE) * PAGE_SIZE);
-
-	for (i = 0; i < NR_LRU_LISTS; i++)
-		seq_printf(m, "%s %llu\n", mem_cgroup_lru_names[i],
-			   (u64)memcg_page_state(memcg, NR_LRU_BASE + i) *
-			   PAGE_SIZE);
-
-	seq_printf(m, "slab_reclaimable %llu\n",
-		   (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) *
-		   PAGE_SIZE);
-	seq_printf(m, "slab_unreclaimable %llu\n",
-		   (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) *
-		   PAGE_SIZE);
-
-	/* Accumulated memory events */
-
-	seq_printf(m, "pgfault %lu\n", memcg_events(memcg, PGFAULT));
-	seq_printf(m, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT));
-
-	seq_printf(m, "workingset_refault %lu\n",
-		   memcg_page_state(memcg, WORKINGSET_REFAULT));
-	seq_printf(m, "workingset_activate %lu\n",
-		   memcg_page_state(memcg, WORKINGSET_ACTIVATE));
-	seq_printf(m, "workingset_nodereclaim %lu\n",
-		   memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
-
-	seq_printf(m, "pgrefill %lu\n", memcg_events(memcg, PGREFILL));
-	seq_printf(m, "pgscan %lu\n", memcg_events(memcg, PGSCAN_KSWAPD) +
-		   memcg_events(memcg, PGSCAN_DIRECT));
-	seq_printf(m, "pgsteal %lu\n", memcg_events(memcg, PGSTEAL_KSWAPD) +
-		   memcg_events(memcg, PGSTEAL_DIRECT));
-	seq_printf(m, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE));
-	seq_printf(m, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE));
-	seq_printf(m, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE));
-	seq_printf(m, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED));
+	__memory_events_show(m, memcg->memory_events_local);
+	return 0;
+}
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	seq_printf(m, "thp_fault_alloc %lu\n",
-		   memcg_events(memcg, THP_FAULT_ALLOC));
-	seq_printf(m, "thp_collapse_alloc %lu\n",
-		   memcg_events(memcg, THP_COLLAPSE_ALLOC));
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+static int memory_stat_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
+	char *buf;
 
+	buf = memory_stat_format(memcg);
+	if (!buf)
+		return -ENOMEM;
+	seq_puts(m, buf);
+	kfree(buf);
 	return 0;
 }
 
@@ -5802,6 +5847,12 @@ static struct cftype memory_files[] = {
 		.seq_show = memory_events_show,
 	},
 	{
+		.name = "events.local",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct mem_cgroup, events_local_file),
+		.seq_show = memory_events_local_show,
+	},
+	{
 		.name = "stat",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = memory_stat_show,