1 files changed, 116 insertions, 118 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 532a2a750952..7bb23ff229b6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -234,22 +234,39 @@ bool pgdat_reclaimable(struct pglist_data *pgdat)
 		pgdat_reclaimable_pages(pgdat) * 6;
 }
 
-unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru)
+/**
+ * lruvec_lru_size -  Returns the number of pages on the given LRU list.
+ * @lruvec: lru vector
+ * @lru: lru to use
+ * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list)
+ */
+unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
 {
+	unsigned long lru_size;
+	int zid;
+
 	if (!mem_cgroup_disabled())
-		return mem_cgroup_get_lru_size(lruvec, lru);
+		lru_size = mem_cgroup_get_lru_size(lruvec, lru);
+	else
+		lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 
-	return node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
-}
+	for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
+		struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
+		unsigned long size;
 
-unsigned long lruvec_zone_lru_size(struct lruvec *lruvec, enum lru_list lru,
-				   int zone_idx)
-{
-	if (!mem_cgroup_disabled())
-		return mem_cgroup_get_zone_lru_size(lruvec, lru, zone_idx);
+		if (!managed_zone(zone))
+			continue;
+
+		if (!mem_cgroup_disabled())
+			size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+		else
+			size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid],
+				       NR_ZONE_LRU_BASE + lru);
+		lru_size -= min(size, lru_size);
+	}
+
+	return lru_size;
 
-	return zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zone_idx],
-			       NR_ZONE_LRU_BASE + lru);
 }
 
 /*
@@ -912,6 +929,17 @@ static void page_check_dirty_writeback(struct page *page,
 		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
+struct reclaim_stat {
+	unsigned nr_dirty;
+	unsigned nr_unqueued_dirty;
+	unsigned nr_congested;
+	unsigned nr_writeback;
+	unsigned nr_immediate;
+	unsigned nr_activate;
+	unsigned nr_ref_keep;
+	unsigned nr_unmap_fail;
+};
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -919,22 +947,20 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				      struct pglist_data *pgdat,
 				      struct scan_control *sc,
 				      enum ttu_flags ttu_flags,
-				      unsigned long *ret_nr_dirty,
-				      unsigned long *ret_nr_unqueued_dirty,
-				      unsigned long *ret_nr_congested,
-				      unsigned long *ret_nr_writeback,
-				      unsigned long *ret_nr_immediate,
+				      struct reclaim_stat *stat,
 				      bool force_reclaim)
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
 	int pgactivate = 0;
-	unsigned long nr_unqueued_dirty = 0;
-	unsigned long nr_dirty = 0;
-	unsigned long nr_congested = 0;
-	unsigned long nr_reclaimed = 0;
-	unsigned long nr_writeback = 0;
-	unsigned long nr_immediate = 0;
+	unsigned nr_unqueued_dirty = 0;
+	unsigned nr_dirty = 0;
+	unsigned nr_congested = 0;
+	unsigned nr_reclaimed = 0;
+	unsigned nr_writeback = 0;
+	unsigned nr_immediate = 0;
+	unsigned nr_ref_keep = 0;
+	unsigned nr_unmap_fail = 0;
 
 	cond_resched();
 
@@ -1073,6 +1099,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		case PAGEREF_ACTIVATE:
 			goto activate_locked;
 		case PAGEREF_KEEP:
+			nr_ref_keep++;
 			goto keep_locked;
 		case PAGEREF_RECLAIM:
 		case PAGEREF_RECLAIM_CLEAN:
@@ -1110,6 +1137,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				(ttu_flags | TTU_BATCH_FLUSH | TTU_LZFREE) :
 				(ttu_flags | TTU_BATCH_FLUSH))) {
 			case SWAP_FAIL:
+				nr_unmap_fail++;
 				goto activate_locked;
 			case SWAP_AGAIN:
 				goto keep_locked;
@@ -1276,11 +1304,16 @@ keep:
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
 
-	*ret_nr_dirty += nr_dirty;
-	*ret_nr_congested += nr_congested;
-	*ret_nr_unqueued_dirty += nr_unqueued_dirty;
-	*ret_nr_writeback += nr_writeback;
-	*ret_nr_immediate += nr_immediate;
+	if (stat) {
+		stat->nr_dirty = nr_dirty;
+		stat->nr_congested = nr_congested;
+		stat->nr_unqueued_dirty = nr_unqueued_dirty;
+		stat->nr_writeback = nr_writeback;
+		stat->nr_immediate = nr_immediate;
+		stat->nr_activate = pgactivate;
+		stat->nr_ref_keep = nr_ref_keep;
+		stat->nr_unmap_fail = nr_unmap_fail;
+	}
 	return nr_reclaimed;
 }
 
@@ -1292,7 +1325,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 		.priority = DEF_PRIORITY,
 		.may_unmap = 1,
 	};
-	unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5;
+	unsigned long ret;
 	struct page *page, *next;
 	LIST_HEAD(clean_pages);
 
@@ -1305,8 +1338,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 	}
 
 	ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
-			TTU_UNMAP|TTU_IGNORE_ACCESS,
-			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
+			TTU_UNMAP|TTU_IGNORE_ACCESS, NULL, true);
 	list_splice(&clean_pages, page_list);
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);
 	return ret;
@@ -1437,6 +1469,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	unsigned long nr_taken = 0;
 	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
+	unsigned long skipped = 0, total_skipped = 0;
 	unsigned long scan, nr_pages;
 	LIST_HEAD(pages_skipped);
 
@@ -1488,14 +1521,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	 */
 	if (!list_empty(&pages_skipped)) {
 		int zid;
-		unsigned long total_skipped = 0;
 
 		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 			if (!nr_skipped[zid])
 				continue;
 
 			__count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]);
-			total_skipped += nr_skipped[zid];
+			skipped += nr_skipped[zid];
 		}
 
 		/*
@@ -1503,13 +1535,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * close to unreclaimable. If the LRU list is empty, account
 		 * skipped pages as a full scan.
 		 */
-		scan += list_empty(src) ? total_skipped : total_skipped >> 2;
+		total_skipped = list_empty(src) ? skipped : skipped >> 2;
 
 		list_splice(&pages_skipped, src);
 	}
-	*nr_scanned = scan;
-	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, scan,
-				    nr_taken, mode, is_file_lru(lru));
+	*nr_scanned = scan + total_skipped;
+	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
+				    scan, skipped, nr_taken, mode, lru);
 	update_lru_sizes(lruvec, lru, nr_zone_taken);
 	return nr_taken;
 }
@@ -1669,30 +1701,6 @@ static int current_may_throttle(void)
 		bdi_write_congested(current->backing_dev_info);
 }
 
-static bool inactive_reclaimable_pages(struct lruvec *lruvec,
-				struct scan_control *sc, enum lru_list lru)
-{
-	int zid;
-	struct zone *zone;
-	int file = is_file_lru(lru);
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-
-	if (!global_reclaim(sc))
-		return true;
-
-	for (zid = sc->reclaim_idx; zid >= 0; zid--) {
-		zone = &pgdat->node_zones[zid];
-		if (!managed_zone(zone))
-			continue;
-
-		if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
-				LRU_FILE * file) >= SWAP_CLUSTER_MAX)
-			return true;
-	}
-
-	return false;
-}
-
 /*
  * shrink_inactive_list() is a helper for shrink_node().  It returns the number
  * of reclaimed pages
@@ -1705,19 +1713,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	unsigned long nr_scanned;
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_taken;
-	unsigned long nr_dirty = 0;
-	unsigned long nr_congested = 0;
-	unsigned long nr_unqueued_dirty = 0;
-	unsigned long nr_writeback = 0;
-	unsigned long nr_immediate = 0;
+	struct reclaim_stat stat = {};
 	isolate_mode_t isolate_mode = 0;
 	int file = is_file_lru(lru);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 
-	if (!inactive_reclaimable_pages(lruvec, sc, lru))
-		return 0;
-
 	while (unlikely(too_many_isolated(pgdat, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
 
@@ -1754,9 +1755,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		return 0;
 
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, TTU_UNMAP,
-				&nr_dirty, &nr_unqueued_dirty, &nr_congested,
-				&nr_writeback, &nr_immediate,
-				false);
+				&stat, false);
 
 	spin_lock_irq(&pgdat->lru_lock);
 
@@ -1790,7 +1789,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * of pages under pages flagged for immediate reclaim and stall if any
 	 * are encountered in the nr_immediate check below.
 	 */
-	if (nr_writeback && nr_writeback == nr_taken)
+	if (stat.nr_writeback && stat.nr_writeback == nr_taken)
 		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
 
 	/*
@@ -1802,7 +1801,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * Tag a zone as congested if all the dirty pages scanned were
 		 * backed by a congested BDI and wait_iff_congested will stall.
 		 */
-		if (nr_dirty && nr_dirty == nr_congested)
+		if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested)
 			set_bit(PGDAT_CONGESTED, &pgdat->flags);
 
 		/*
@@ -1811,7 +1810,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * the pgdat PGDAT_DIRTY and kswapd will start writing pages from
 		 * reclaim context.
 		 */
-		if (nr_unqueued_dirty == nr_taken)
+		if (stat.nr_unqueued_dirty == nr_taken)
 			set_bit(PGDAT_DIRTY, &pgdat->flags);
 
 		/*
@@ -1820,7 +1819,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * that pages are cycling through the LRU faster than
 		 * they are written so also forcibly stall.
 		 */
-		if (nr_immediate && current_may_throttle())
+		if (stat.nr_immediate && current_may_throttle())
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
@@ -1835,6 +1834,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
 			nr_scanned, nr_reclaimed,
+			stat.nr_dirty,  stat.nr_writeback,
+			stat.nr_congested, stat.nr_immediate,
+			stat.nr_activate, stat.nr_ref_keep,
+			stat.nr_unmap_fail,
 			sc->priority, file);
 	return nr_reclaimed;
 }
@@ -1855,17 +1858,19 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
  *
  * The downside is that we have to touch page->_refcount against each page.
  * But we had to alter page->flags anyway.
+ *
+ * Returns the number of pages moved to the given lru.
  */
 
-static void move_active_pages_to_lru(struct lruvec *lruvec,
+static unsigned move_active_pages_to_lru(struct lruvec *lruvec,
 				     struct list_head *list,
 				     struct list_head *pages_to_free,
 				     enum lru_list lru)
 {
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-	unsigned long pgmoved = 0;
 	struct page *page;
 	int nr_pages;
+	int nr_moved = 0;
 
 	while (!list_empty(list)) {
 		page = lru_to_page(list);
@@ -1877,7 +1882,6 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 		nr_pages = hpage_nr_pages(page);
 		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
 		list_move(&page->lru, &lruvec->lists[lru]);
-		pgmoved += nr_pages;
 
 		if (put_page_testzero(page)) {
 			__ClearPageLRU(page);
@@ -1891,11 +1895,15 @@ static void move_active_pages_to_lru(struct lruvec *lruvec,
 				spin_lock_irq(&pgdat->lru_lock);
 			} else
 				list_add(&page->lru, pages_to_free);
+		} else {
+			nr_moved += nr_pages;
 		}
 	}
 
 	if (!is_active_lru(lru))
-		__count_vm_events(PGDEACTIVATE, pgmoved);
+		__count_vm_events(PGDEACTIVATE, nr_moved);
+
+	return nr_moved;
 }
 
 static void shrink_active_list(unsigned long nr_to_scan,
@@ -1911,7 +1919,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	LIST_HEAD(l_inactive);
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
-	unsigned long nr_rotated = 0;
+	unsigned nr_deactivate, nr_activate;
+	unsigned nr_rotated = 0;
 	isolate_mode_t isolate_mode = 0;
 	int file = is_file_lru(lru);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
@@ -1989,13 +1998,15 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	 */
 	reclaim_stat->recent_rotated[file] += nr_rotated;
 
-	move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
-	move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
+	nr_activate = move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
+	nr_deactivate = move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&pgdat->lru_lock);
 
 	mem_cgroup_uncharge_list(&l_hold);
 	free_hot_cold_page_list(&l_hold, true);
+	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
+			nr_deactivate, nr_rotated, sc->priority, file);
 }
 
 /*
@@ -2025,14 +2036,13 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *   10TB     320        32GB
  */
 static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
-						struct scan_control *sc)
+						struct scan_control *sc, bool trace)
 {
 	unsigned long inactive_ratio;
-	unsigned long inactive;
-	unsigned long active;
+	unsigned long inactive, active;
+	enum lru_list inactive_lru = file * LRU_FILE;
+	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
 	unsigned long gb;
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-	int zid;
 
 	/*
 	 * If we don't have swap space, anonymous page deactivation
@@ -2041,27 +2051,8 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	if (!file && !total_swap_pages)
 		return false;
 
-	inactive = lruvec_lru_size(lruvec, file * LRU_FILE);
-	active = lruvec_lru_size(lruvec, file * LRU_FILE + LRU_ACTIVE);
-
-	/*
-	 * For zone-constrained allocations, it is necessary to check if
-	 * deactivations are required for lowmem to be reclaimed. This
-	 * calculates the inactive/active pages available in eligible zones.
-	 */
-	for (zid = sc->reclaim_idx + 1; zid < MAX_NR_ZONES; zid++) {
-		struct zone *zone = &pgdat->node_zones[zid];
-		unsigned long inactive_zone, active_zone;
-
-		if (!managed_zone(zone))
-			continue;
-
-		inactive_zone = lruvec_zone_lru_size(lruvec, file * LRU_FILE, zid);
-		active_zone = lruvec_zone_lru_size(lruvec, (file * LRU_FILE) + LRU_ACTIVE, zid);
-
-		inactive -= min(inactive, inactive_zone);
-		active -= min(active, active_zone);
-	}
+	inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
+	active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
 
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
 	if (gb)
@@ -2069,6 +2060,13 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	else
 		inactive_ratio = 1;
 
+	if (trace)
+		trace_mm_vmscan_inactive_list_is_low(lruvec_pgdat(lruvec)->node_id,
+				sc->reclaim_idx,
+				lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive,
+				lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active,
+				inactive_ratio, file);
+
 	return inactive * inactive_ratio < active;
 }
 
@@ -2076,7 +2074,7 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 				 struct lruvec *lruvec, struct scan_control *sc)
 {
 	if (is_active_lru(lru)) {
-		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc))
+		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
 			shrink_active_list(nr_to_scan, lruvec, sc, lru);
 		return 0;
 	}
@@ -2207,8 +2205,8 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * lruvec even if it has plenty of old anonymous pages unless the
 	 * system is under heavy pressure.
 	 */
-	if (!inactive_list_is_low(lruvec, true, sc) &&
-	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
+	if (!inactive_list_is_low(lruvec, true, sc, false) &&
+	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2234,10 +2232,10 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * anon in [0], file in [1]
 	 */
 
-	anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON) +
-		lruvec_lru_size(lruvec, LRU_INACTIVE_ANON);
-	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE) +
-		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE);
+	anon  = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
+	file  = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
+		lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
 
 	spin_lock_irq(&pgdat->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
@@ -2275,7 +2273,7 @@ out:
 			unsigned long size;
 			unsigned long scan;
 
-			size = lruvec_lru_size(lruvec, lru);
+			size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
 			scan = size >> sc->priority;
 
 			if (!scan && pass && force_scan)
@@ -2432,7 +2430,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_list_is_low(lruvec, false, sc))
+	if (inactive_list_is_low(lruvec, false, sc, true))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -3082,7 +3080,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 
-		if (inactive_list_is_low(lruvec, false, sc))
+		if (inactive_list_is_low(lruvec, false, sc, true))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 					   sc, LRU_ACTIVE_ANON);