Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (132 commits)
  hugetlbfs: dirty pages as they are added to pagecache
  mm: export add_swap_extent()
  mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS
  tools/testing/selftests/vm/map_fixed_noreplace.c: add test for MAP_FIXED_NOREPLACE
  mm: thp: relocate flush_cache_range() in migrate_misplaced_transhuge_page()
  mm: thp: fix mmu_notifier in migrate_misplaced_transhuge_page()
  mm: thp: fix MADV_DONTNEED vs migrate_misplaced_transhuge_page race condition
  mm/kasan/quarantine.c: make quarantine_lock a raw_spinlock_t
  mm/gup: cache dev_pagemap while pinning pages
  Revert "x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"
  mm: return zero_resv_unavail optimization
  mm: zero remaining unavailable struct pages
  tools/testing/selftests/vm/gup_benchmark.c: add MAP_HUGETLB option
  tools/testing/selftests/vm/gup_benchmark.c: add MAP_SHARED option
  tools/testing/selftests/vm/gup_benchmark.c: allow user specified file
  tools/testing/selftests/vm/gup_benchmark.c: fix 'write' flag usage
  mm/gup_benchmark.c: add additional pinning methods
  mm/gup_benchmark.c: time put_page()
  mm: don't raise MEMCG_OOM event due to failed high-order allocation
  mm/page-writeback.c: fix range_cyclic writeback vs writepages deadlock
  ...

1 files changed, 16 insertions, 38 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e79cb59552d9..10a9b554d69f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1669,6 +1669,8 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
 		return OOM_SKIPPED;
 
+	memcg_memory_event(memcg, MEMCG_OOM);
+
 	/*
 	 * We are in the middle of the charge context here, so we
 	 * don't want to block when potentially sitting on a callstack
@@ -2250,8 +2252,6 @@ retry:
 	if (fatal_signal_pending(current))
 		goto force;
 
-	memcg_memory_event(mem_over_limit, MEMCG_OOM);
-
 	/*
 	 * keep retrying as long as the memcg oom killer is able to make
 	 * a forward progress or bypass the charge if the oom killer
@@ -2460,7 +2460,7 @@ static void memcg_kmem_cache_create_func(struct work_struct *w)
 /*
  * Enqueue the creation of a per-memcg kmem_cache.
  */
-static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
+static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 					       struct kmem_cache *cachep)
 {
 	struct memcg_kmem_cache_create_work *cw;
@@ -2478,25 +2478,6 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 	queue_work(memcg_kmem_cache_wq, &cw->work);
 }
 
-static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
-					     struct kmem_cache *cachep)
-{
-	/*
-	 * We need to stop accounting when we kmalloc, because if the
-	 * corresponding kmalloc cache is not yet created, the first allocation
-	 * in __memcg_schedule_kmem_cache_create will recurse.
-	 *
-	 * However, it is better to enclose the whole function. Depending on
-	 * the debugging options enabled, INIT_WORK(), for instance, can
-	 * trigger an allocation. This too, will make us recurse. Because at
-	 * this point we can't allow ourselves back into memcg_kmem_get_cache,
-	 * the safest choice is to do it like this, wrapping the whole function.
-	 */
-	current->memcg_kmem_skip_account = 1;
-	__memcg_schedule_kmem_cache_create(memcg, cachep);
-	current->memcg_kmem_skip_account = 0;
-}
-
 static inline bool memcg_kmem_bypass(void)
 {
 	if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD))
@@ -2531,9 +2512,6 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 	if (memcg_kmem_bypass())
 		return cachep;
 
-	if (current->memcg_kmem_skip_account)
-		return cachep;
-
 	memcg = get_mem_cgroup_from_current();
 	kmemcg_id = READ_ONCE(memcg->kmemcg_id);
 	if (kmemcg_id < 0)
@@ -4321,14 +4299,12 @@ static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
 
 static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
 {
-	VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0);
-	atomic_add(n, &memcg->id.ref);
+	refcount_add(n, &memcg->id.ref);
 }
 
 static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
 {
-	VM_BUG_ON(atomic_read(&memcg->id.ref) < n);
-	if (atomic_sub_and_test(n, &memcg->id.ref)) {
+	if (refcount_sub_and_test(n, &memcg->id.ref)) {
 		mem_cgroup_id_remove(memcg);
 
 		/* Memcg ID pins CSS */
@@ -4545,7 +4521,7 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	}
 
 	/* Online state pins memcg ID, memcg ID pins CSS */
-	atomic_set(&memcg->id.ref, 1);
+	refcount_set(&memcg->id.ref, 1);
 	css_get(css);
 	return 0;
 }
@@ -4573,6 +4549,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	memcg_offline_kmem(memcg);
 	wb_memcg_offline(memcg);
 
+	drain_all_stock(memcg);
+
 	mem_cgroup_id_put(memcg);
 }
 
@@ -5595,6 +5573,13 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "pgfault %lu\n", acc.events[PGFAULT]);
 	seq_printf(m, "pgmajfault %lu\n", acc.events[PGMAJFAULT]);
 
+	seq_printf(m, "workingset_refault %lu\n",
+		   acc.stat[WORKINGSET_REFAULT]);
+	seq_printf(m, "workingset_activate %lu\n",
+		   acc.stat[WORKINGSET_ACTIVATE]);
+	seq_printf(m, "workingset_nodereclaim %lu\n",
+		   acc.stat[WORKINGSET_NODERECLAIM]);
+
 	seq_printf(m, "pgrefill %lu\n", acc.events[PGREFILL]);
 	seq_printf(m, "pgscan %lu\n", acc.events[PGSCAN_KSWAPD] +
 		   acc.events[PGSCAN_DIRECT]);
@@ -5605,13 +5590,6 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "pglazyfree %lu\n", acc.events[PGLAZYFREE]);
 	seq_printf(m, "pglazyfreed %lu\n", acc.events[PGLAZYFREED]);
 
-	seq_printf(m, "workingset_refault %lu\n",
-		   acc.stat[WORKINGSET_REFAULT]);
-	seq_printf(m, "workingset_activate %lu\n",
-		   acc.stat[WORKINGSET_ACTIVATE]);
-	seq_printf(m, "workingset_nodereclaim %lu\n",
-		   acc.stat[WORKINGSET_NODERECLAIM]);
-
 	return 0;
 }
 
@@ -6377,7 +6355,7 @@ subsys_initcall(mem_cgroup_init);
 #ifdef CONFIG_MEMCG_SWAP
 static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
 {
-	while (!atomic_inc_not_zero(&memcg->id.ref)) {
+	while (!refcount_inc_not_zero(&memcg->id.ref)) {
 		/*
 		 * The root cgroup cannot be destroyed, so it's refcount must
 		 * always be >= 1.