mm: thp: make deferred split shrinker memcg aware

Currently THP deferred split shrinker is not memcg aware, this may cause
premature OOM with some configuration.  For example the below test would
run into premature OOM easily:

$ cgcreate -g memory:thp
$ echo 4G > /sys/fs/cgroup/memory/thp/memory/limit_in_bytes
$ cgexec -g memory:thp transhuge-stress 4000

transhuge-stress comes from kernel selftest.

It is easy to hit OOM, but there are still a lot THP on the deferred split
queue, memcg direct reclaim can't touch them since the deferred split
shrinker is not memcg aware.

Convert deferred split shrinker memcg aware by introducing per memcg
deferred split queue.  The THP should be on either per node or per memcg
deferred split queue if it belongs to a memcg.  When the page is
immigrated to the other memcg, it will be immigrated to the target memcg's
deferred split queue too.

Reuse the second tail page's deferred_list for per memcg list since the
same THP can't be on multiple deferred split queues.

[yang.shi@linux.alibaba.com: simplify deferred split queue dereference per Kirill Tkhai]
  Link: http://lkml.kernel.org/r/1566496227-84952-5-git-send-email-yang.shi@linux.alibaba.com
Link: http://lkml.kernel.org/r/1565144277-36240-5-git-send-email-yang.shi@linux.alibaba.com
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/huge_mm.h

@@ -267,6 +267,15 @@ static inline bool thp_migration_supported(void)
 	return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
 }
 
+static inline struct list_head *page_deferred_list(struct page *page)
+{
+	/*
+	 * Global or memcg deferred list in the second tail pages is
+	 * occupied by compound_head.
+	 */
+	return &page[2].deferred_list;
+}
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })

include/linux/memcontrol.h

@@ -330,6 +330,10 @@ struct mem_cgroup {
 	struct list_head event_list;
 	spinlock_t event_list_lock;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct deferred_split deferred_split_queue;
+#endif
+
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
 };

include/linux/mm_types.h

@@ -138,6 +138,7 @@ struct page {
 		struct {	/* Second tail page of compound page */
 			unsigned long _compound_pad_1;	/* compound_head */
 			unsigned long _compound_pad_2;
+			/* For both global and memcg */
 			struct list_head deferred_list;
 		};
 		struct {	/* Page table pages */

mm/huge_memory.c

@@ -496,11 +496,25 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 	return pmd;
 }
 
-static inline struct list_head *page_deferred_list(struct page *page)
+#ifdef CONFIG_MEMCG
+static inline struct deferred_split *get_deferred_split_queue(struct page *page)
 {
-	/* ->lru in the tail pages is occupied by compound_head. */
-	return &page[2].deferred_list;
+	struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+
+	if (memcg)
+		return &memcg->deferred_split_queue;
+	else
+		return &pgdat->deferred_split_queue;
 }
+#else
+static inline struct deferred_split *get_deferred_split_queue(struct page *page)
+{
+	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+
+	return &pgdat->deferred_split_queue;
+}
+#endif
 
 void prep_transhuge_page(struct page *page)
 {
@@ -2691,7 +2705,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct page *head = compound_head(page);
 	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
-	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
+	struct deferred_split *ds_queue = get_deferred_split_queue(page);
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
 	int count, mapcount, extra_pins, ret;
@@ -2827,8 +2841,7 @@ out:
 
 void free_transhuge_page(struct page *page)
 {
-	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
-	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
+	struct deferred_split *ds_queue = get_deferred_split_queue(page);
 	unsigned long flags;
 
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
@@ -2842,17 +2855,37 @@ void free_transhuge_page(struct page *page)
 
 void deferred_split_huge_page(struct page *page)
 {
-	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
-	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
+	struct deferred_split *ds_queue = get_deferred_split_queue(page);
+#ifdef CONFIG_MEMCG
+	struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+#endif
 	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 
+	/*
+	 * The try_to_unmap() in page reclaim path might reach here too,
+	 * this may cause a race condition to corrupt deferred split queue.
+	 * And, if page reclaim is already handling the same page, it is
+	 * unnecessary to handle it again in shrinker.
+	 *
+	 * Check PageSwapCache to determine if the page is being
+	 * handled by page reclaim since THP swap would add the page into
+	 * swap cache before calling try_to_unmap().
+	 */
+	if (PageSwapCache(page))
+		return;
+
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	if (list_empty(page_deferred_list(page))) {
 		count_vm_event(THP_DEFERRED_SPLIT_PAGE);
 		list_add_tail(page_deferred_list(page), &ds_queue->split_queue);
 		ds_queue->split_queue_len++;
+#ifdef CONFIG_MEMCG
+		if (memcg)
+			memcg_set_shrinker_bit(memcg, page_to_nid(page),
+					       deferred_split_shrinker.id);
+#endif
 	}
 	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
 }
@@ -2862,6 +2895,11 @@ static unsigned long deferred_split_count(struct shrinker *shrink,
 {
 	struct pglist_data *pgdata = NODE_DATA(sc->nid);
 	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
+
+#ifdef CONFIG_MEMCG
+	if (sc->memcg)
+		ds_queue = &sc->memcg->deferred_split_queue;
+#endif
 	return READ_ONCE(ds_queue->split_queue_len);
 }
 
@@ -2875,6 +2913,11 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 	struct page *page;
 	int split = 0;
 
+#ifdef CONFIG_MEMCG
+	if (sc->memcg)
+		ds_queue = &sc->memcg->deferred_split_queue;
+#endif
+
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	/* Take pin on all head pages to avoid freeing them under us */
 	list_for_each_safe(pos, next, &ds_queue->split_queue) {
@@ -2921,7 +2964,8 @@ static struct shrinker deferred_split_shrinker = {
 	.count_objects = deferred_split_count,
 	.scan_objects = deferred_split_scan,
 	.seeks = DEFAULT_SEEKS,
-	.flags = SHRINKER_NUMA_AWARE,
+	.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE |
+		 SHRINKER_NONSLAB,
 };
 
 #ifdef CONFIG_DEBUG_FS

mm/memcontrol.c

@@ -5070,6 +5070,11 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
 		memcg->cgwb_frn[i].done =
 			__WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	spin_lock_init(&memcg->deferred_split_queue.split_queue_lock);
+	INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
+	memcg->deferred_split_queue.split_queue_len = 0;
 #endif
 	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return memcg;
@@ -5449,6 +5454,14 @@ static int mem_cgroup_move_account(struct page *page,
 		__mod_memcg_state(to, NR_WRITEBACK, nr_pages);
 	}
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (compound && !list_empty(page_deferred_list(page))) {
+		spin_lock(&from->deferred_split_queue.split_queue_lock);
+		list_del_init(page_deferred_list(page));
+		from->deferred_split_queue.split_queue_len--;
+		spin_unlock(&from->deferred_split_queue.split_queue_lock);
+	}
+#endif
 	/*
 	 * It is safe to change page->mem_cgroup here because the page
 	 * is referenced, charged, and isolated - we can't race with
@@ -5457,6 +5470,17 @@ static int mem_cgroup_move_account(struct page *page,
 
 	/* caller should have done css_get */
 	page->mem_cgroup = to;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (compound && list_empty(page_deferred_list(page))) {
+		spin_lock(&to->deferred_split_queue.split_queue_lock);
+		list_add_tail(page_deferred_list(page),
+			      &to->deferred_split_queue.split_queue);
+		to->deferred_split_queue.split_queue_len++;
+		spin_unlock(&to->deferred_split_queue.split_queue_lock);
+	}
+#endif
+
 	spin_unlock_irqrestore(&from->move_lock, flags);
 
 	ret = 0;