Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "More MM work: a memcg scalability improvememt"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/lru: revise the comments of lru_lock
  mm/lru: introduce relock_page_lruvec()
  mm/lru: replace pgdat lru_lock with lruvec lock
  mm/swap.c: serialize memcg changes in pagevec_lru_move_fn
  mm/compaction: do page isolation first in compaction
  mm/lru: introduce TestClearPageLRU()
  mm/mlock: remove __munlock_isolate_lru_page()
  mm/mlock: remove lru_lock on TestClearPageMlocked
  mm/vmscan: remove lruvec reget in move_pages_to_lru
  mm/lru: move lock into lru_note_cost
  mm/swap.c: fold vm event PGROTATED into pagevec_move_tail_fn
  mm/memcg: add debug checking in lock_page_memcg
  mm: page_idle_get_page() does not need lru_lock
  mm/rmap: stop store reordering issue on page->mapping
  mm/vmscan: remove unnecessary lruvec adding
  mm/thp: narrow lru locking
  mm/thp: simplify lru_add_page_tail()
  mm/thp: use head for head page in lru_add_page_tail()
  mm/thp: move lru_add_page_tail() to huge_memory.c

1 files changed, 81 insertions, 3 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9c5b14fe360e..e3c7ca7dc174 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -20,6 +20,9 @@
  * Lockless page tracking & accounting
  * Unified hierarchy configuration model
  * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
+ *
+ * Per memcg lru locking
+ * Copyright (C) 2020 Alibaba, Inc, Alex Shi
  */
 
 #include <linux/page_counter.h>
@@ -1322,6 +1325,23 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_VM
+void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	memcg = page_memcg(page);
+
+	if (!memcg)
+		VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page);
+	else
+		VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page);
+}
+#endif
+
 /**
  * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
  * @page: the page
@@ -1363,6 +1383,60 @@ out:
 }
 
 /**
+ * lock_page_lruvec - lock and return lruvec for a given page.
+ * @page: the page
+ *
+ * This series functions should be used in either conditions:
+ * PageLRU is cleared or unset
+ * or page->_refcount is zero
+ * or page is locked.
+ */
+struct lruvec *lock_page_lruvec(struct page *page)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock(&lruvec->lru_lock);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+struct lruvec *lock_page_lruvec_irq(struct page *page)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock_irq(&lruvec->lru_lock);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock_irqsave(&lruvec->lru_lock, *flags);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+/**
  * mem_cgroup_update_lru_size - account for adding or removing an lru page
  * @lruvec: mem_cgroup per zone lru vector
  * @lru: index of lru list the page is sitting on
@@ -2142,6 +2216,12 @@ again:
 	if (unlikely(!memcg))
 		return NULL;
 
+#ifdef CONFIG_PROVE_LOCKING
+	local_irq_save(flags);
+	might_lock(&memcg->move_lock);
+	local_irq_restore(flags);
+#endif
+
 	if (atomic_read(&memcg->moving_account) <= 0)
 		return memcg;
 
@@ -3263,10 +3343,8 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-
 /*
- * Because tail pages are not marked as "used", set it. We're under
- * pgdat->lru_lock and migration entries setup in all page mappings.
+ * Because page_memcg(head) is not set on compound tails, set it now.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {