1 files changed, 107 insertions, 100 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 242368592ea7..257cba79a96d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1539,9 +1539,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
  *
  * returns 0 on success, -ve errno on failure.
  */
-int __isolate_lru_page(struct page *page, isolate_mode_t mode)
+int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode)
 {
-	int ret = -EINVAL;
+	int ret = -EBUSY;
 
 	/* Only take pages on the LRU. */
 	if (!PageLRU(page))
@@ -1551,8 +1551,6 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 	if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
 		return ret;
 
-	ret = -EBUSY;
-
 	/*
 	 * To minimise LRU disruption, the caller can indicate that it only
 	 * wants to isolate pages it will be able to operate on without
@@ -1593,20 +1591,9 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)
 	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
 		return ret;
 
-	if (likely(get_page_unless_zero(page))) {
-		/*
-		 * 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.
-		 */
-		ClearPageLRU(page);
-		ret = 0;
-	}
-
-	return ret;
+	return 0;
 }
 
-
 /*
  * Update LRU sizes after isolating pages. The LRU size updates must
  * be complete before mem_cgroup_update_lru_size due to a sanity check.
@@ -1626,14 +1613,16 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
 }
 
 /**
- * pgdat->lru_lock is heavily contended.  Some of the functions that
+ * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
+ *
+ * lruvec->lru_lock is heavily contended.  Some of the functions that
  * shrink the lists perform better by taking out a batch of pages
  * and working on them outside the LRU lock.
  *
  * For pagecache intensive workloads, this function is the hottest
  * spot in the kernel (apart from copy_*_user functions).
  *
- * Appropriate locks must be held before calling this function.
+ * Lru_lock must be held before calling this function.
  *
  * @nr_to_scan:	The number of eligible pages to look through on the list.
  * @lruvec:	The LRU vector to pull pages from.
@@ -1666,8 +1655,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
 
-		VM_BUG_ON_PAGE(!PageLRU(page), page);
-
 		nr_pages = compound_nr(page);
 		total_scan += nr_pages;
 
@@ -1688,20 +1675,34 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * only when the page is being freed somewhere else.
 		 */
 		scan += nr_pages;
-		switch (__isolate_lru_page(page, mode)) {
+		switch (__isolate_lru_page_prepare(page, mode)) {
 		case 0:
+			/*
+			 * 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 busy;
+
+			if (!TestClearPageLRU(page)) {
+				/*
+				 * This page may in other isolation path,
+				 * but we still hold lru_lock.
+				 */
+				put_page(page);
+				goto busy;
+			}
+
 			nr_taken += nr_pages;
 			nr_zone_taken[page_zonenum(page)] += nr_pages;
 			list_move(&page->lru, dst);
 			break;
 
-		case -EBUSY:
+		default:
+busy:
 			/* else it is being freed elsewhere */
 			list_move(&page->lru, src);
-			continue;
-
-		default:
-			BUG();
 		}
 	}
 
@@ -1764,21 +1765,16 @@ int isolate_lru_page(struct page *page)
 	VM_BUG_ON_PAGE(!page_count(page), page);
 	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
-	if (PageLRU(page)) {
-		pg_data_t *pgdat = page_pgdat(page);
+	if (TestClearPageLRU(page)) {
 		struct lruvec *lruvec;
 
-		spin_lock_irq(&pgdat->lru_lock);
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-		if (PageLRU(page)) {
-			int lru = page_lru(page);
-			get_page(page);
-			ClearPageLRU(page);
-			del_page_from_lru_list(page, lruvec, lru);
-			ret = 0;
-		}
-		spin_unlock_irq(&pgdat->lru_lock);
+		get_page(page);
+		lruvec = lock_page_lruvec_irq(page);
+		del_page_from_lru_list(page, lruvec, page_lru(page));
+		unlock_page_lruvec_irq(lruvec);
+		ret = 0;
 	}
+
 	return ret;
 }
 
@@ -1820,29 +1816,14 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 }
 
 /*
- * This moves pages from @list to corresponding LRU list.
- *
- * We move them the other way if the page is referenced by one or more
- * processes, from rmap.
- *
- * If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold zone_lru_lock across the whole operation.  But if
- * the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop zone_lru_lock around each page.  It's impossible to balance
- * this, so instead we remove the pages from the LRU while processing them.
- * It is safe to rely on PG_active against the non-LRU pages in here because
- * nobody will play with that bit on a non-LRU page.
- *
- * The downside is that we have to touch page->_refcount against each page.
- * But we had to alter page->flags anyway.
+ * move_pages_to_lru() moves pages from private @list to appropriate LRU list.
+ * On return, @list is reused as a list of pages to be freed by the caller.
  *
  * Returns the number of pages moved to the given lruvec.
  */
-
 static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 						     struct list_head *list)
 {
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	int nr_pages, nr_moved = 0;
 	LIST_HEAD(pages_to_free);
 	struct page *page;
@@ -1851,38 +1832,54 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
 	while (!list_empty(list)) {
 		page = lru_to_page(list);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
+		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			list_del(&page->lru);
-			spin_unlock_irq(&pgdat->lru_lock);
+			spin_unlock_irq(&lruvec->lru_lock);
 			putback_lru_page(page);
-			spin_lock_irq(&pgdat->lru_lock);
+			spin_lock_irq(&lruvec->lru_lock);
 			continue;
 		}
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
+		/*
+		 * The SetPageLRU needs to be kept here for list integrity.
+		 * Otherwise:
+		 *   #0 move_pages_to_lru             #1 release_pages
+		 *   if !put_page_testzero
+		 *				      if (put_page_testzero())
+		 *				        !PageLRU //skip lru_lock
+		 *     SetPageLRU()
+		 *     list_add(&page->lru,)
+		 *                                        list_add(&page->lru,)
+		 */
 		SetPageLRU(page);
-		lru = page_lru(page);
 
-		nr_pages = thp_nr_pages(page);
-		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
-		list_move(&page->lru, &lruvec->lists[lru]);
-
-		if (put_page_testzero(page)) {
+		if (unlikely(put_page_testzero(page))) {
 			__ClearPageLRU(page);
 			__ClearPageActive(page);
-			del_page_from_lru_list(page, lruvec, lru);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&pgdat->lru_lock);
+				spin_unlock_irq(&lruvec->lru_lock);
 				destroy_compound_page(page);
-				spin_lock_irq(&pgdat->lru_lock);
+				spin_lock_irq(&lruvec->lru_lock);
 			} else
 				list_add(&page->lru, &pages_to_free);
-		} else {
-			nr_moved += nr_pages;
-			if (PageActive(page))
-				workingset_age_nonresident(lruvec, nr_pages);
+
+			continue;
 		}
+
+		/*
+		 * All pages were isolated from the same lruvec (and isolation
+		 * inhibits memcg migration).
+		 */
+		VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page);
+		lru = page_lru(page);
+		nr_pages = thp_nr_pages(page);
+
+		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
+		list_add(&page->lru, &lruvec->lists[lru]);
+		nr_moved += nr_pages;
+		if (PageActive(page))
+			workingset_age_nonresident(lruvec, nr_pages);
 	}
 
 	/*
@@ -1939,7 +1936,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	lru_add_drain();
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
 				     &nr_scanned, sc, lru);
@@ -1951,27 +1948,25 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
 	__count_vm_events(PGSCAN_ANON + file, nr_scanned);
 
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	if (nr_taken == 0)
 		return 0;
 
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
-	spin_lock_irq(&pgdat->lru_lock);
-
+	spin_lock_irq(&lruvec->lru_lock);
 	move_pages_to_lru(lruvec, &page_list);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	lru_note_cost(lruvec, file, stat.nr_pageout);
 	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
 	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
+	spin_unlock_irq(&lruvec->lru_lock);
 
-	spin_unlock_irq(&pgdat->lru_lock);
-
+	lru_note_cost(lruvec, file, stat.nr_pageout);
 	mem_cgroup_uncharge_list(&page_list);
 	free_unref_page_list(&page_list);
 
@@ -2003,6 +1998,23 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	return nr_reclaimed;
 }
 
+/*
+ * shrink_active_list() moves pages from the active LRU to the inactive LRU.
+ *
+ * We move them the other way if the page is referenced by one or more
+ * processes.
+ *
+ * If the pages are mostly unmapped, the processing is fast and it is
+ * appropriate to hold lru_lock across the whole operation.  But if
+ * the pages are mapped, the processing is slow (page_referenced()), so
+ * we should drop lru_lock around each page.  It's impossible to balance
+ * this, so instead we remove the pages from the LRU while processing them.
+ * It is safe to rely on PG_active against the non-LRU pages in here because
+ * nobody will play with that bit on a non-LRU page.
+ *
+ * The downside is that we have to touch page->_refcount against each page.
+ * But we had to alter page->flags anyway.
+ */
 static void shrink_active_list(unsigned long nr_to_scan,
 			       struct lruvec *lruvec,
 			       struct scan_control *sc,
@@ -2022,7 +2034,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	lru_add_drain();
 
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
 				     &nr_scanned, sc, lru);
@@ -2033,7 +2045,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 		__count_vm_events(PGREFILL, nr_scanned);
 	__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
 
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	while (!list_empty(&l_hold)) {
 		cond_resched();
@@ -2079,7 +2091,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move pages back to the lru list.
 	 */
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&lruvec->lru_lock);
 
 	nr_activate = move_pages_to_lru(lruvec, &l_active);
 	nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
@@ -2090,7 +2102,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&lruvec->lru_lock);
 
 	mem_cgroup_uncharge_list(&l_active);
 	free_unref_page_list(&l_active);
@@ -2678,10 +2690,10 @@ again:
 	/*
 	 * Determine the scan balance between anon and file LRUs.
 	 */
-	spin_lock_irq(&pgdat->lru_lock);
+	spin_lock_irq(&target_lruvec->lru_lock);
 	sc->anon_cost = target_lruvec->anon_cost;
 	sc->file_cost = target_lruvec->file_cost;
-	spin_unlock_irq(&pgdat->lru_lock);
+	spin_unlock_irq(&target_lruvec->lru_lock);
 
 	/*
 	 * Target desirable inactive:active list ratios for the anon
@@ -4257,15 +4269,13 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
  */
 void check_move_unevictable_pages(struct pagevec *pvec)
 {
-	struct lruvec *lruvec;
-	struct pglist_data *pgdat = NULL;
+	struct lruvec *lruvec = NULL;
 	int pgscanned = 0;
 	int pgrescued = 0;
 	int i;
 
 	for (i = 0; i < pvec->nr; i++) {
 		struct page *page = pvec->pages[i];
-		struct pglist_data *pagepgdat = page_pgdat(page);
 		int nr_pages;
 
 		if (PageTransTail(page))
@@ -4274,18 +4284,12 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 		nr_pages = thp_nr_pages(page);
 		pgscanned += nr_pages;
 
-		if (pagepgdat != pgdat) {
-			if (pgdat)
-				spin_unlock_irq(&pgdat->lru_lock);
-			pgdat = pagepgdat;
-			spin_lock_irq(&pgdat->lru_lock);
-		}
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-
-		if (!PageLRU(page) || !PageUnevictable(page))
+		/* block memcg migration during page moving between lru */
+		if (!TestClearPageLRU(page))
 			continue;
 
-		if (page_evictable(page)) {
+		lruvec = relock_page_lruvec_irq(page, lruvec);
+		if (page_evictable(page) && PageUnevictable(page)) {
 			enum lru_list lru = page_lru_base_type(page);
 
 			VM_BUG_ON_PAGE(PageActive(page), page);
@@ -4294,12 +4298,15 @@ void check_move_unevictable_pages(struct pagevec *pvec)
 			add_page_to_lru_list(page, lruvec, lru);
 			pgrescued += nr_pages;
 		}
+		SetPageLRU(page);
 	}
 
-	if (pgdat) {
+	if (lruvec) {
 		__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
 		__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
-		spin_unlock_irq(&pgdat->lru_lock);
+		unlock_page_lruvec_irq(lruvec);
+	} else if (pgscanned) {
+		count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
 	}
 }
 EXPORT_SYMBOL_GPL(check_move_unevictable_pages);