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, 67 insertions, 27 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index dbcfdfce1b82..e5acb9714436 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -804,7 +804,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct lruvec *lruvec;
 	unsigned long flags = 0;
-	bool locked = false;
+	struct lruvec *locked = NULL;
 	struct page *page = NULL, *valid_page = NULL;
 	unsigned long start_pfn = low_pfn;
 	bool skip_on_failure = false;
@@ -868,11 +868,20 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * contention, to give chance to IRQs. Abort completely if
 		 * a fatal signal is pending.
 		 */
-		if (!(low_pfn % SWAP_CLUSTER_MAX)
-		    && compact_unlock_should_abort(&pgdat->lru_lock,
-					    flags, &locked, cc)) {
-			low_pfn = 0;
-			goto fatal_pending;
+		if (!(low_pfn % SWAP_CLUSTER_MAX)) {
+			if (locked) {
+				unlock_page_lruvec_irqrestore(locked, flags);
+				locked = NULL;
+			}
+
+			if (fatal_signal_pending(current)) {
+				cc->contended = true;
+
+				low_pfn = 0;
+				goto fatal_pending;
+			}
+
+			cond_resched();
 		}
 
 		if (!pfn_valid_within(low_pfn))
@@ -890,6 +899,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
 			if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
 				low_pfn = end_pfn;
+				page = NULL;
 				goto isolate_abort;
 			}
 			valid_page = page;
@@ -943,9 +953,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			if (unlikely(__PageMovable(page)) &&
 					!PageIsolated(page)) {
 				if (locked) {
-					spin_unlock_irqrestore(&pgdat->lru_lock,
-									flags);
-					locked = false;
+					unlock_page_lruvec_irqrestore(locked, flags);
+					locked = NULL;
 				}
 
 				if (!isolate_movable_page(page, isolate_mode))
@@ -971,10 +980,34 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!(cc->gfp_mask & __GFP_FS) && page_mapping(page))
 			goto isolate_fail;
 
+		/*
+		 * Be careful not to clear PageLRU until after we're
+		 * sure the page is not being freed elsewhere -- the
+		 * page release code relies on it.
+		 */
+		if (unlikely(!get_page_unless_zero(page)))
+			goto isolate_fail;
+
+		if (__isolate_lru_page_prepare(page, isolate_mode) != 0)
+			goto isolate_fail_put;
+
+		/* Try isolate the page */
+		if (!TestClearPageLRU(page))
+			goto isolate_fail_put;
+
+		rcu_read_lock();
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
+
 		/* If we already hold the lock, we can skip some rechecking */
-		if (!locked) {
-			locked = compact_lock_irqsave(&pgdat->lru_lock,
-								&flags, cc);
+		if (lruvec != locked) {
+			if (locked)
+				unlock_page_lruvec_irqrestore(locked, flags);
+
+			compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
+			locked = lruvec;
+			rcu_read_unlock();
+
+			lruvec_memcg_debug(lruvec, page);
 
 			/* Try get exclusive access under lock */
 			if (!skip_updated) {
@@ -983,10 +1016,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 					goto isolate_abort;
 			}
 
-			/* Recheck PageLRU and PageCompound under lock */
-			if (!PageLRU(page))
-				goto isolate_fail;
-
 			/*
 			 * Page become compound since the non-locked check,
 			 * and it's on LRU. It can only be a THP so the order
@@ -994,15 +1023,11 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			 */
 			if (unlikely(PageCompound(page) && !cc->alloc_contig)) {
 				low_pfn += compound_nr(page) - 1;
-				goto isolate_fail;
+				SetPageLRU(page);
+				goto isolate_fail_put;
 			}
-		}
-
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-
-		/* Try isolate the page */
-		if (__isolate_lru_page(page, isolate_mode) != 0)
-			goto isolate_fail;
+		} else
+			rcu_read_unlock();
 
 		/* The whole page is taken off the LRU; skip the tail pages. */
 		if (PageCompound(page))
@@ -1032,6 +1057,15 @@ isolate_success:
 		}
 
 		continue;
+
+isolate_fail_put:
+		/* Avoid potential deadlock in freeing page under lru_lock */
+		if (locked) {
+			unlock_page_lruvec_irqrestore(locked, flags);
+			locked = NULL;
+		}
+		put_page(page);
+
 isolate_fail:
 		if (!skip_on_failure)
 			continue;
@@ -1043,8 +1077,8 @@ isolate_fail:
 		 */
 		if (nr_isolated) {
 			if (locked) {
-				spin_unlock_irqrestore(&pgdat->lru_lock, flags);
-				locked = false;
+				unlock_page_lruvec_irqrestore(locked, flags);
+				locked = NULL;
 			}
 			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
@@ -1068,9 +1102,15 @@ isolate_fail:
 	if (unlikely(low_pfn > end_pfn))
 		low_pfn = end_pfn;
 
+	page = NULL;
+
 isolate_abort:
 	if (locked)
-		spin_unlock_irqrestore(&pgdat->lru_lock, flags);
+		unlock_page_lruvec_irqrestore(locked, flags);
+	if (page) {
+		SetPageLRU(page);
+		put_page(page);
+	}
 
 	/*
 	 * Updated the cached scanner pfn once the pageblock has been scanned