1 files changed, 174 insertions, 18 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index eeb3bc9d1d36..8d01243d9560 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -133,7 +133,7 @@ long vm_total_pages;	/* The total number of pages which the VM controls */
 static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
@@ -687,6 +687,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 	cond_resched();
 
+	mem_cgroup_uncharge_start();
 	while (!list_empty(page_list)) {
 		enum page_references references;
 		struct address_space *mapping;
@@ -720,9 +721,41 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
 
 		if (PageWriteback(page)) {
-			nr_writeback++;
-			unlock_page(page);
-			goto keep;
+			/*
+			 * memcg doesn't have any dirty pages throttling so we
+			 * could easily OOM just because too many pages are in
+			 * writeback and there is nothing else to reclaim.
+			 *
+			 * Check __GFP_IO, certainly because a loop driver
+			 * thread might enter reclaim, and deadlock if it waits
+			 * on a page for which it is needed to do the write
+			 * (loop masks off __GFP_IO|__GFP_FS for this reason);
+			 * but more thought would probably show more reasons.
+			 *
+			 * Don't require __GFP_FS, since we're not going into
+			 * the FS, just waiting on its writeback completion.
+			 * Worryingly, ext4 gfs2 and xfs allocate pages with
+			 * grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so
+			 * testing may_enter_fs here is liable to OOM on them.
+			 */
+			if (global_reclaim(sc) ||
+			    !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
+				/*
+				 * This is slightly racy - end_page_writeback()
+				 * might have just cleared PageReclaim, then
+				 * setting PageReclaim here end up interpreted
+				 * as PageReadahead - but that does not matter
+				 * enough to care.  What we do want is for this
+				 * page to have PageReclaim set next time memcg
+				 * reclaim reaches the tests above, so it will
+				 * then wait_on_page_writeback() to avoid OOM;
+				 * and it's also appropriate in global reclaim.
+				 */
+				SetPageReclaim(page);
+				nr_writeback++;
+				goto keep_locked;
+			}
+			wait_on_page_writeback(page);
 		}
 
 		references = page_check_references(page, sc);
@@ -921,6 +954,7 @@ keep:
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
+	mem_cgroup_uncharge_end();
 	*ret_nr_dirty += nr_dirty;
 	*ret_nr_writeback += nr_writeback;
 	return nr_reclaimed;
@@ -1567,7 +1601,8 @@ static int vmscan_swappiness(struct scan_control *sc)
  * by looking at the fraction of the pages scanned we did rotate back
  * onto the active list instead of evict.
  *
- * nr[0] = anon pages to scan; nr[1] = file pages to scan
+ * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
+ * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
  */
 static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 			   unsigned long *nr)
@@ -2111,6 +2146,83 @@ out:
 	return 0;
 }
 
+static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
+{
+	struct zone *zone;
+	unsigned long pfmemalloc_reserve = 0;
+	unsigned long free_pages = 0;
+	int i;
+	bool wmark_ok;
+
+	for (i = 0; i <= ZONE_NORMAL; i++) {
+		zone = &pgdat->node_zones[i];
+		pfmemalloc_reserve += min_wmark_pages(zone);
+		free_pages += zone_page_state(zone, NR_FREE_PAGES);
+	}
+
+	wmark_ok = free_pages > pfmemalloc_reserve / 2;
+
+	/* kswapd must be awake if processes are being throttled */
+	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
+		pgdat->classzone_idx = min(pgdat->classzone_idx,
+						(enum zone_type)ZONE_NORMAL);
+		wake_up_interruptible(&pgdat->kswapd_wait);
+	}
+
+	return wmark_ok;
+}
+
+/*
+ * Throttle direct reclaimers if backing storage is backed by the network
+ * and the PFMEMALLOC reserve for the preferred node is getting dangerously
+ * depleted. kswapd will continue to make progress and wake the processes
+ * when the low watermark is reached
+ */
+static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
+					nodemask_t *nodemask)
+{
+	struct zone *zone;
+	int high_zoneidx = gfp_zone(gfp_mask);
+	pg_data_t *pgdat;
+
+	/*
+	 * Kernel threads should not be throttled as they may be indirectly
+	 * responsible for cleaning pages necessary for reclaim to make forward
+	 * progress. kjournald for example may enter direct reclaim while
+	 * committing a transaction where throttling it could forcing other
+	 * processes to block on log_wait_commit().
+	 */
+	if (current->flags & PF_KTHREAD)
+		return;
+
+	/* Check if the pfmemalloc reserves are ok */
+	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
+	pgdat = zone->zone_pgdat;
+	if (pfmemalloc_watermark_ok(pgdat))
+		return;
+
+	/* Account for the throttling */
+	count_vm_event(PGSCAN_DIRECT_THROTTLE);
+
+	/*
+	 * If the caller cannot enter the filesystem, it's possible that it
+	 * is due to the caller holding an FS lock or performing a journal
+	 * transaction in the case of a filesystem like ext[3|4]. In this case,
+	 * it is not safe to block on pfmemalloc_wait as kswapd could be
+	 * blocked waiting on the same lock. Instead, throttle for up to a
+	 * second before continuing.
+	 */
+	if (!(gfp_mask & __GFP_FS)) {
+		wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
+			pfmemalloc_watermark_ok(pgdat), HZ);
+		return;
+	}
+
+	/* Throttle until kswapd wakes the process */
+	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+		pfmemalloc_watermark_ok(pgdat));
+}
+
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				gfp_t gfp_mask, nodemask_t *nodemask)
 {
@@ -2130,6 +2242,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.gfp_mask = sc.gfp_mask,
 	};
 
+	throttle_direct_reclaim(gfp_mask, zonelist, nodemask);
+
+	/*
+	 * Do not enter reclaim if fatal signal is pending. 1 is returned so
+	 * that the page allocator does not consider triggering OOM
+	 */
+	if (fatal_signal_pending(current))
+		return 1;
+
 	trace_mm_vmscan_direct_reclaim_begin(order,
 				sc.may_writepage,
 				gfp_mask);
@@ -2141,7 +2262,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	return nr_reclaimed;
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_MEMCG
 
 unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 						gfp_t gfp_mask, bool noswap,
@@ -2274,8 +2395,13 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
 	return balanced_pages >= (present_pages >> 2);
 }
 
-/* is kswapd sleeping prematurely? */
-static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
+/*
+ * Prepare kswapd for sleeping. This verifies that there are no processes
+ * waiting in throttle_direct_reclaim() and that watermarks have been met.
+ *
+ * Returns true if kswapd is ready to sleep
+ */
+static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 					int classzone_idx)
 {
 	int i;
@@ -2284,7 +2410,21 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
 
 	/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
 	if (remaining)
-		return true;
+		return false;
+
+	/*
+	 * There is a potential race between when kswapd checks its watermarks
+	 * and a process gets throttled. There is also a potential race if
+	 * processes get throttled, kswapd wakes, a large process exits therby
+	 * balancing the zones that causes kswapd to miss a wakeup. If kswapd
+	 * is going to sleep, no process should be sleeping on pfmemalloc_wait
+	 * so wake them now if necessary. If necessary, processes will wake
+	 * kswapd and get throttled again
+	 */
+	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
+		wake_up(&pgdat->pfmemalloc_wait);
+		return false;
+	}
 
 	/* Check the watermark levels */
 	for (i = 0; i <= classzone_idx; i++) {
@@ -2317,9 +2457,9 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
 	 * must be balanced
 	 */
 	if (order)
-		return !pgdat_balanced(pgdat, balanced, classzone_idx);
+		return pgdat_balanced(pgdat, balanced, classzone_idx);
 	else
-		return !all_zones_ok;
+		return all_zones_ok;
 }
 
 /*
@@ -2537,7 +2677,7 @@ loop_again:
 				 * consider it to be no longer congested. It's
 				 * possible there are dirty pages backed by
 				 * congested BDIs but as pressure is relieved,
-				 * spectulatively avoid congestion waits
+				 * speculatively avoid congestion waits
 				 */
 				zone_clear_flag(zone, ZONE_CONGESTED);
 				if (i <= *classzone_idx)
@@ -2545,6 +2685,16 @@ loop_again:
 			}
 
 		}
+
+		/*
+		 * If the low watermark is met there is no need for processes
+		 * to be throttled on pfmemalloc_wait as they should not be
+		 * able to safely make forward progress. Wake them
+		 */
+		if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
+				pfmemalloc_watermark_ok(pgdat))
+			wake_up(&pgdat->pfmemalloc_wait);
+
 		if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
 			break;		/* kswapd: all done */
 		/*
@@ -2646,7 +2796,7 @@ out:
 	}
 
 	/*
-	 * Return the order we were reclaiming at so sleeping_prematurely()
+	 * Return the order we were reclaiming at so prepare_kswapd_sleep()
 	 * makes a decision on the order we were last reclaiming at. However,
 	 * if another caller entered the allocator slow path while kswapd
 	 * was awake, order will remain at the higher level
@@ -2666,7 +2816,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 
 	/* Try to sleep for a short interval */
-	if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
 		remaining = schedule_timeout(HZ/10);
 		finish_wait(&pgdat->kswapd_wait, &wait);
 		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
@@ -2676,7 +2826,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	 * After a short sleep, check if it was a premature sleep. If not, then
 	 * go fully to sleep until explicitly woken up.
 	 */
-	if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+	if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
 		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
 
 		/*
@@ -2688,7 +2838,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 		 * them before going back to sleep.
 		 */
 		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
-		schedule();
+
+		if (!kthread_should_stop())
+			schedule();
+
 		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
 	} else {
 		if (remaining)
@@ -2955,14 +3108,17 @@ int kswapd_run(int nid)
 }
 
 /*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined.  Caller must
+ * hold lock_memory_hotplug().
  */
 void kswapd_stop(int nid)
 {
 	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
 
-	if (kswapd)
+	if (kswapd) {
 		kthread_stop(kswapd);
+		NODE_DATA(nid)->kswapd = NULL;
+	}
 }
 
 static int __init kswapd_init(void)