Reset to 3.12.37

1 files changed, 150 insertions, 75 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 05e6095..ee8363f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -163,7 +163,8 @@ static unsigned long zone_reclaimable_pages(struct zone *zone)
 
 bool zone_reclaimable(struct zone *zone)
 {
-	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
+	return zone_page_state(zone, NR_PAGES_SCANNED) <
+		zone_reclaimable_pages(zone) * 6;
 }
 
 static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
@@ -224,15 +225,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	unsigned long freed = 0;
 	unsigned long long delta;
 	long total_scan;
-	long max_pass;
+	long freeable;
 	long nr;
 	long new_nr;
 	int nid = shrinkctl->nid;
 	long batch_size = shrinker->batch ? shrinker->batch
 					  : SHRINK_BATCH;
 
-	max_pass = shrinker->count_objects(shrinker, shrinkctl);
-	if (max_pass == 0)
+	freeable = shrinker->count_objects(shrinker, shrinkctl);
+	if (freeable == 0)
 		return 0;
 
 	/*
@@ -244,14 +245,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 
 	total_scan = nr;
 	delta = (4 * nr_pages_scanned) / shrinker->seeks;
-	delta *= max_pass;
+	delta *= freeable;
 	do_div(delta, lru_pages + 1);
 	total_scan += delta;
 	if (total_scan < 0) {
 		printk(KERN_ERR
 		"shrink_slab: %pF negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
-		total_scan = max_pass;
+		total_scan = freeable;
 	}
 
 	/*
@@ -260,38 +261,55 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	 * shrinkers to return -1 all the time. This results in a large
 	 * nr being built up so when a shrink that can do some work
 	 * comes along it empties the entire cache due to nr >>>
-	 * max_pass.  This is bad for sustaining a working set in
+	 * freeable. This is bad for sustaining a working set in
 	 * memory.
 	 *
 	 * Hence only allow the shrinker to scan the entire cache when
 	 * a large delta change is calculated directly.
 	 */
-	if (delta < max_pass / 4)
-		total_scan = min(total_scan, max_pass / 2);
+	if (delta < freeable / 4)
+		total_scan = min(total_scan, freeable / 2);
 
 	/*
 	 * Avoid risking looping forever due to too large nr value:
 	 * never try to free more than twice the estimate number of
 	 * freeable entries.
 	 */
-	if (total_scan > max_pass * 2)
-		total_scan = max_pass * 2;
+	if (total_scan > freeable * 2)
+		total_scan = freeable * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
 				nr_pages_scanned, lru_pages,
-				max_pass, delta, total_scan);
+				freeable, delta, total_scan);
 
-	while (total_scan >= batch_size) {
+	/*
+	 * Normally, we should not scan less than batch_size objects in one
+	 * pass to avoid too frequent shrinker calls, but if the slab has less
+	 * than batch_size objects in total and we are really tight on memory,
+	 * we will try to reclaim all available objects, otherwise we can end
+	 * up failing allocations although there are plenty of reclaimable
+	 * objects spread over several slabs with usage less than the
+	 * batch_size.
+	 *
+	 * We detect the "tight on memory" situations by looking at the total
+	 * number of objects we want to scan (total_scan). If it is greater
+	 * than the total number of objects on slab (freeable), we must be
+	 * scanning at high prio and therefore should try to reclaim as much as
+	 * possible.
+	 */
+	while (total_scan >= batch_size ||
+	       total_scan >= freeable) {
 		unsigned long ret;
+		unsigned long nr_to_scan = min(batch_size, total_scan);
 
-		shrinkctl->nr_to_scan = batch_size;
+		shrinkctl->nr_to_scan = nr_to_scan;
 		ret = shrinker->scan_objects(shrinker, shrinkctl);
 		if (ret == SHRINK_STOP)
 			break;
 		freed += ret;
 
-		count_vm_events(SLABS_SCANNED, batch_size);
-		total_scan -= batch_size;
+		count_vm_events(SLABS_SCANNED, nr_to_scan);
+		total_scan -= nr_to_scan;
 
 		cond_resched();
 	}
@@ -352,16 +370,17 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl,
 	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
-		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
-			if (!node_online(shrinkctl->nid))
-				continue;
-
-			if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
-			    (shrinkctl->nid != 0))
-				break;
-
+		if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) {
+			shrinkctl->nid = 0;
 			freed += shrink_slab_node(shrinkctl, shrinker,
-				 nr_pages_scanned, lru_pages);
+					nr_pages_scanned, lru_pages);
+			continue;
+		}
+
+		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+			if (node_online(shrinkctl->nid))
+				freed += shrink_slab_node(shrinkctl, shrinker,
+						nr_pages_scanned, lru_pages);
 
 		}
 	}
@@ -1089,7 +1108,7 @@ keep:
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
 
-	free_hot_cold_page_list(&free_pages, 1);
+	free_hot_cold_page_list(&free_pages, true);
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
@@ -1126,7 +1145,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 			TTU_UNMAP|TTU_IGNORE_ACCESS,
 			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
 	list_splice(&clean_pages, page_list);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
+	mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
 	return ret;
 }
 
@@ -1452,7 +1471,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
 
 	if (global_reclaim(sc)) {
-		zone->pages_scanned += nr_scanned;
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
 		if (current_is_kswapd())
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned);
 		else
@@ -1487,7 +1506,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	spin_unlock_irq(&zone->lru_lock);
 
-	free_hot_cold_page_list(&page_list, 1);
+	free_hot_cold_page_list(&page_list, true);
 
 	/*
 	 * If reclaim is isolating dirty pages under writeback, it implies
@@ -1522,19 +1541,18 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * If dirty pages are scanned that are not queued for IO, it
 		 * implies that flushers are not keeping up. In this case, flag
 		 * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
-		 * pages from reclaim context. It will forcibly stall in the
-		 * next check.
+		 * pages from reclaim context.
 		 */
 		if (nr_unqueued_dirty == nr_taken)
 			zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
 
 		/*
-		 * In addition, 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
+		 * 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 (nr_unqueued_dirty == nr_taken || nr_immediate)
+		if (nr_immediate)
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
@@ -1642,7 +1660,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
 				     &nr_scanned, sc, isolate_mode, lru);
 	if (global_reclaim(sc))
-		zone->pages_scanned += nr_scanned;
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
 
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
@@ -1708,7 +1726,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&zone->lru_lock);
 
-	free_hot_cold_page_list(&l_hold, 1);
+	free_hot_cold_page_list(&l_hold, true);
 }
 
 #ifdef CONFIG_SWAP
@@ -1830,7 +1848,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	struct zone *zone = lruvec_zone(lruvec);
 	unsigned long anon_prio, file_prio;
 	enum scan_balance scan_balance;
-	unsigned long anon, file, free;
+	unsigned long anon, file;
 	bool force_scan = false;
 	unsigned long ap, fp;
 	enum lru_list lru;
@@ -1878,11 +1896,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 		goto out;
 	}
 
-	anon  = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
-		get_lru_size(lruvec, LRU_INACTIVE_ANON);
-	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
-		get_lru_size(lruvec, LRU_INACTIVE_FILE);
-
 	/*
 	 * If it's foreseeable that reclaiming the file cache won't be
 	 * enough to get the zone back into a desirable shape, we have
@@ -1890,8 +1903,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	 * thrashing - remaining file pages alone.
 	 */
 	if (global_reclaim(sc)) {
-		free = zone_page_state(zone, NR_FREE_PAGES);
-		if (unlikely(file + free <= high_wmark_pages(zone))) {
+		unsigned long zonefile;
+		unsigned long zonefree;
+
+		zonefree = zone_page_state(zone, NR_FREE_PAGES);
+		zonefile = zone_page_state(zone, NR_ACTIVE_FILE) +
+			   zone_page_state(zone, NR_INACTIVE_FILE);
+
+		if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) {
 			scan_balance = SCAN_ANON;
 			goto out;
 		}
@@ -1926,6 +1945,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	 *
 	 * anon in [0], file in [1]
 	 */
+
+	anon  = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
+		get_lru_size(lruvec, LRU_INACTIVE_ANON);
+	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
+		get_lru_size(lruvec, LRU_INACTIVE_FILE);
+
 	spin_lock_irq(&zone->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
 		reclaim_stat->recent_scanned[0] /= 2;
@@ -2001,13 +2026,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct blk_plug plug;
-	bool scan_adjusted = false;
+	bool scan_adjusted;
 
 	get_scan_count(lruvec, sc, nr);
 
 	/* Record the original scan target for proportional adjustments later */
 	memcpy(targets, nr, sizeof(nr));
 
+	/*
+	 * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
+	 * event that can occur when there is little memory pressure e.g.
+	 * multiple streaming readers/writers. Hence, we do not abort scanning
+	 * when the requested number of pages are reclaimed when scanning at
+	 * DEF_PRIORITY on the assumption that the fact we are direct
+	 * reclaiming implies that kswapd is not keeping up and it is best to
+	 * do a batch of work at once. For memcg reclaim one check is made to
+	 * abort proportional reclaim if either the file or anon lru has already
+	 * dropped to zero at the first pass.
+	 */
+	scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
+			 sc->priority == DEF_PRIORITY);
+
 	blk_start_plug(&plug);
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
@@ -2028,17 +2067,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 			continue;
 
 		/*
-		 * For global direct reclaim, reclaim only the number of pages
-		 * requested. Less care is taken to scan proportionally as it
-		 * is more important to minimise direct reclaim stall latency
-		 * than it is to properly age the LRU lists.
-		 */
-		if (global_reclaim(sc) && !current_is_kswapd())
-			break;
-
-		/*
 		 * For kswapd and memcg, reclaim at least the number of pages
-		 * requested. Ensure that the anon and file LRUs shrink
+		 * requested. Ensure that the anon and file LRUs are scanned
 		 * proportionally what was requested by get_scan_count(). We
 		 * stop reclaiming one LRU and reduce the amount scanning
 		 * proportional to the original scan target.
@@ -2046,6 +2076,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
 		nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
 
+		/*
+		 * It's just vindictive to attack the larger once the smaller
+		 * has gone to zero.  And given the way we stop scanning the
+		 * smaller below, this makes sure that we only make one nudge
+		 * towards proportionality once we've got nr_to_reclaim.
+		 */
+		if (!nr_file || !nr_anon)
+			break;
+
 		if (nr_file > nr_anon) {
 			unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
 						targets[LRU_ACTIVE_ANON] + 1;
@@ -2407,8 +2446,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			unsigned long lru_pages = 0;
 
 			nodes_clear(shrink->nodes_to_scan);
-			for_each_zone_zonelist(zone, z, zonelist,
-					gfp_zone(sc->gfp_mask)) {
+			for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_zone(sc->gfp_mask), sc->nodemask) {
 				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 					continue;
 
@@ -2484,10 +2523,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
+		if (!populated_zone(zone))
+			continue;
+
 		pfmemalloc_reserve += min_wmark_pages(zone);
 		free_pages += zone_page_state(zone, NR_FREE_PAGES);
 	}
 
+	/* If there are no reserves (unexpected config) then do not throttle */
+	if (!pfmemalloc_reserve)
+		return true;
+
 	wmark_ok = free_pages > pfmemalloc_reserve / 2;
 
 	/* kswapd must be awake if processes are being throttled */
@@ -2512,9 +2558,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 					nodemask_t *nodemask)
 {
+	struct zoneref *z;
 	struct zone *zone;
-	int high_zoneidx = gfp_zone(gfp_mask);
-	pg_data_t *pgdat;
+	pg_data_t *pgdat = NULL;
 
 	/*
 	 * Kernel threads should not be throttled as they may be indirectly
@@ -2533,10 +2579,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	if (fatal_signal_pending(current))
 		goto out;
 
-	/* Check if the pfmemalloc reserves are ok */
-	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
-	pgdat = zone->zone_pgdat;
-	if (pfmemalloc_watermark_ok(pgdat))
+	/*
+	 * Check if the pfmemalloc reserves are ok by finding the first node
+	 * with a usable ZONE_NORMAL or lower zone. The expectation is that
+	 * GFP_KERNEL will be required for allocating network buffers when
+	 * swapping over the network so ZONE_HIGHMEM is unusable.
+	 *
+	 * Throttling is based on the first usable node and throttled processes
+	 * wait on a queue until kswapd makes progress and wakes them. There
+	 * is an affinity then between processes waking up and where reclaim
+	 * progress has been made assuming the process wakes on the same node.
+	 * More importantly, processes running on remote nodes will not compete
+	 * for remote pfmemalloc reserves and processes on different nodes
+	 * should make reasonable progress.
+	 */
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_mask, nodemask) {
+		if (zone_idx(zone) > ZONE_NORMAL)
+			continue;
+
+		/* Throttle based on the first usable node */
+		pgdat = zone->zone_pgdat;
+		if (pfmemalloc_watermark_ok(pgdat))
+			goto out;
+		break;
+	}
+
+	/* If no zone was usable by the allocation flags then do not throttle */
+	if (!pgdat)
 		goto out;
 
 	/* Account for the throttling */
@@ -2798,18 +2868,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 		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
+	 * The throttled processes are normally woken up in balance_pgdat() as
+	 * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+	 * race between when kswapd checks the watermarks and a process gets
+	 * throttled. There is also a potential race if processes get
+	 * throttled, kswapd wakes, a large process exits thereby balancing the
+	 * zones, which causes kswapd to exit balance_pgdat() before reaching
+	 * the wake up checks. If kswapd is going to sleep, no process should
+	 * be sleeping on pfmemalloc_wait, so wake them now if necessary. If
+	 * the wake up is premature, processes will wake kswapd and get
+	 * throttled again. The difference from wake ups in balance_pgdat() is
+	 * that here we are under prepare_to_wait().
 	 */
-	if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
-		wake_up(&pgdat->pfmemalloc_wait);
-		return false;
-	}
+	if (waitqueue_active(&pgdat->pfmemalloc_wait))
+		wake_up_all(&pgdat->pfmemalloc_wait);
 
 	return pgdat_balanced(pgdat, order, classzone_idx);
 }
@@ -3267,7 +3339,10 @@ static int kswapd(void *p)
 		}
 	}
 
+	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
 	current->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
+
 	return 0;
 }