1 files changed, 133 insertions, 77 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4390a8d5be41..8b920ce3ae02 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -116,6 +116,16 @@ struct scan_control {
 
 	/* Number of pages freed so far during a call to shrink_zones() */
 	unsigned long nr_reclaimed;
+
+	struct {
+		unsigned int dirty;
+		unsigned int unqueued_dirty;
+		unsigned int congested;
+		unsigned int writeback;
+		unsigned int immediate;
+		unsigned int file_taken;
+		unsigned int taken;
+	} nr;
 };
 
 #ifdef ARCH_HAS_PREFETCH
@@ -190,6 +200,29 @@ static bool sane_reclaim(struct scan_control *sc)
 #endif
 	return false;
 }
+
+static void set_memcg_congestion(pg_data_t *pgdat,
+				struct mem_cgroup *memcg,
+				bool congested)
+{
+	struct mem_cgroup_per_node *mn;
+
+	if (!memcg)
+		return;
+
+	mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+	WRITE_ONCE(mn->congested, congested);
+}
+
+static bool memcg_congested(pg_data_t *pgdat,
+			struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_per_node *mn;
+
+	mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+	return READ_ONCE(mn->congested);
+
+}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
@@ -200,6 +233,18 @@ static bool sane_reclaim(struct scan_control *sc)
 {
 	return true;
 }
+
+static inline void set_memcg_congestion(struct pglist_data *pgdat,
+				struct mem_cgroup *memcg, bool congested)
+{
+}
+
+static inline bool memcg_congested(struct pglist_data *pgdat,
+			struct mem_cgroup *memcg)
+{
+	return false;
+
+}
 #endif
 
 /*
@@ -648,7 +693,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
 
-	spin_lock_irqsave(&mapping->tree_lock, flags);
+	xa_lock_irqsave(&mapping->i_pages, flags);
 	/*
 	 * The non racy check for a busy page.
 	 *
@@ -672,7 +717,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	 * load is not satisfied before that of page->_refcount.
 	 *
 	 * Note that if SetPageDirty is always performed via set_page_dirty,
-	 * and thus under tree_lock, then this ordering is not required.
+	 * and thus under the i_pages lock, then this ordering is not required.
 	 */
 	if (unlikely(PageTransHuge(page)) && PageSwapCache(page))
 		refcount = 1 + HPAGE_PMD_NR;
@@ -690,7 +735,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		swp_entry_t swap = { .val = page_private(page) };
 		mem_cgroup_swapout(page, swap);
 		__delete_from_swap_cache(page);
-		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		xa_unlock_irqrestore(&mapping->i_pages, flags);
 		put_swap_page(page, swap);
 	} else {
 		void (*freepage)(struct page *);
@@ -711,13 +756,13 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		 * only page cache pages found in these are zero pages
 		 * covering holes, and because we don't want to mix DAX
 		 * exceptional entries and shadow exceptional entries in the
-		 * same page_tree.
+		 * same address_space.
 		 */
 		if (reclaimed && page_is_file_cache(page) &&
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
 			shadow = workingset_eviction(mapping, page);
 		__delete_from_page_cache(page, shadow);
-		spin_unlock_irqrestore(&mapping->tree_lock, flags);
+		xa_unlock_irqrestore(&mapping->i_pages, flags);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -726,7 +771,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	return 1;
 
 cannot_free:
-	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	xa_unlock_irqrestore(&mapping->i_pages, flags);
 	return 0;
 }
 
@@ -857,17 +902,6 @@ 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
  */
@@ -926,7 +960,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
 
 		/*
-		 * The number of dirty pages determines if a zone is marked
+		 * The number of dirty pages determines if a node is marked
 		 * reclaim_congested which affects wait_iff_congested. kswapd
 		 * will stall and start writing pages if the tail of the LRU
 		 * is all dirty unqueued pages.
@@ -1755,23 +1789,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	free_unref_page_list(&page_list);
 
 	/*
-	 * If reclaim is isolating dirty pages under writeback, it implies
-	 * that the long-lived page allocation rate is exceeding the page
-	 * laundering rate. Either the global limits are not being effective
-	 * at throttling processes due to the page distribution throughout
-	 * zones or there is heavy usage of a slow backing device. The
-	 * only option is to throttle from reclaim context which is not ideal
-	 * as there is no guarantee the dirtying process is throttled in the
-	 * same way balance_dirty_pages() manages.
-	 *
-	 * Once a zone is flagged ZONE_WRITEBACK, kswapd will count the number
-	 * of pages under pages flagged for immediate reclaim and stall if any
-	 * are encountered in the nr_immediate check below.
-	 */
-	if (stat.nr_writeback && stat.nr_writeback == nr_taken)
-		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
-
-	/*
 	 * If dirty pages are scanned that are not queued for IO, it
 	 * implies that flushers are not doing their job. This can
 	 * happen when memory pressure pushes dirty pages to the end of
@@ -1785,48 +1802,17 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (stat.nr_unqueued_dirty == nr_taken)
 		wakeup_flusher_threads(WB_REASON_VMSCAN);
 
-	/*
-	 * Legacy memcg will stall in page writeback so avoid forcibly
-	 * stalling here.
-	 */
-	if (sane_reclaim(sc)) {
-		/*
-		 * Tag a zone as congested if all the dirty pages scanned were
-		 * backed by a congested BDI and wait_iff_congested will stall.
-		 */
-		if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested)
-			set_bit(PGDAT_CONGESTED, &pgdat->flags);
-
-		/* Allow kswapd to start writing pages during reclaim. */
-		if (stat.nr_unqueued_dirty == nr_taken)
-			set_bit(PGDAT_DIRTY, &pgdat->flags);
-
-		/*
-		 * If kswapd scans pages marked marked for immediate
-		 * reclaim and under writeback (nr_immediate), it implies
-		 * that pages are cycling through the LRU faster than
-		 * they are written so also forcibly stall.
-		 */
-		if (stat.nr_immediate && current_may_throttle())
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
-	}
-
-	/*
-	 * Stall direct reclaim for IO completions if underlying BDIs or zone
-	 * is congested. Allow kswapd to continue until it starts encountering
-	 * unqueued dirty pages or cycling through the LRU too quickly.
-	 */
-	if (!sc->hibernation_mode && !current_is_kswapd() &&
-	    current_may_throttle())
-		wait_iff_congested(pgdat, BLK_RW_ASYNC, HZ/10);
+	sc->nr.dirty += stat.nr_dirty;
+	sc->nr.congested += stat.nr_congested;
+	sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
+	sc->nr.writeback += stat.nr_writeback;
+	sc->nr.immediate += stat.nr_immediate;
+	sc->nr.taken += nr_taken;
+	if (file)
+		sc->nr.file_taken += nr_taken;
 
 	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);
+			nr_scanned, nr_reclaimed, &stat, sc->priority, file);
 	return nr_reclaimed;
 }
 
@@ -2507,6 +2493,12 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	return true;
 }
 
+static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup *memcg)
+{
+	return test_bit(PGDAT_CONGESTED, &pgdat->flags) ||
+		(memcg && memcg_congested(pgdat, memcg));
+}
+
 static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 {
 	struct reclaim_state *reclaim_state = current->reclaim_state;
@@ -2522,6 +2514,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long node_lru_pages = 0;
 		struct mem_cgroup *memcg;
 
+		memset(&sc->nr, 0, sizeof(sc->nr));
+
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
 
@@ -2536,7 +2530,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 					sc->memcg_low_skipped = 1;
 					continue;
 				}
-				mem_cgroup_event(memcg, MEMCG_LOW);
+				memcg_memory_event(memcg, MEMCG_LOW);
 			}
 
 			reclaimed = sc->nr_reclaimed;
@@ -2587,6 +2581,67 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 		if (sc->nr_reclaimed - nr_reclaimed)
 			reclaimable = true;
 
+		if (current_is_kswapd()) {
+			/*
+			 * If reclaim is isolating dirty pages under writeback,
+			 * it implies that the long-lived page allocation rate
+			 * is exceeding the page laundering rate. Either the
+			 * global limits are not being effective at throttling
+			 * processes due to the page distribution throughout
+			 * zones or there is heavy usage of a slow backing
+			 * device. The only option is to throttle from reclaim
+			 * context which is not ideal as there is no guarantee
+			 * the dirtying process is throttled in the same way
+			 * balance_dirty_pages() manages.
+			 *
+			 * Once a node is flagged PGDAT_WRITEBACK, kswapd will
+			 * count the number of pages under pages flagged for
+			 * immediate reclaim and stall if any are encountered
+			 * in the nr_immediate check below.
+			 */
+			if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
+				set_bit(PGDAT_WRITEBACK, &pgdat->flags);
+
+			/*
+			 * Tag a node as congested if all the dirty pages
+			 * scanned were backed by a congested BDI and
+			 * wait_iff_congested will stall.
+			 */
+			if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
+				set_bit(PGDAT_CONGESTED, &pgdat->flags);
+
+			/* Allow kswapd to start writing pages during reclaim.*/
+			if (sc->nr.unqueued_dirty == sc->nr.file_taken)
+				set_bit(PGDAT_DIRTY, &pgdat->flags);
+
+			/*
+			 * If kswapd scans pages marked marked for immediate
+			 * reclaim and under writeback (nr_immediate), it
+			 * implies that pages are cycling through the LRU
+			 * faster than they are written so also forcibly stall.
+			 */
+			if (sc->nr.immediate)
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
+		}
+
+		/*
+		 * Legacy memcg will stall in page writeback so avoid forcibly
+		 * stalling in wait_iff_congested().
+		 */
+		if (!global_reclaim(sc) && sane_reclaim(sc) &&
+		    sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
+			set_memcg_congestion(pgdat, root, true);
+
+		/*
+		 * Stall direct reclaim for IO completions if underlying BDIs
+		 * and node is congested. Allow kswapd to continue until it
+		 * starts encountering unqueued dirty pages or cycling through
+		 * the LRU too quickly.
+		 */
+		if (!sc->hibernation_mode && !current_is_kswapd() &&
+		   current_may_throttle() && pgdat_memcg_congested(pgdat, root))
+			wait_iff_congested(BLK_RW_ASYNC, HZ/10);
+
 	} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
 
@@ -2802,6 +2857,7 @@ retry:
 			continue;
 		last_pgdat = zone->zone_pgdat;
 		snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat);
+		set_memcg_congestion(last_pgdat, sc->target_mem_cgroup, false);
 	}
 
 	delayacct_freepages_end();
@@ -3808,7 +3864,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 
 	if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
 		/*
-		 * Free memory by calling shrink zone with increasing
+		 * Free memory by calling shrink node with increasing
 		 * priorities until we have enough memory freed.
 		 */
 		do {