Merge branch 'for-linus' into work.misc

3 files changed, 70 insertions, 31 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e234c21a5e6c..fc10620967c7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -903,14 +903,20 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		if (prev && reclaim->generation != iter->generation)
 			goto out_unlock;
 
-		do {
+		while (1) {
 			pos = READ_ONCE(iter->position);
+			if (!pos || css_tryget(&pos->css))
+				break;
 			/*
-			 * A racing update may change the position and
-			 * put the last reference, hence css_tryget(),
-			 * or retry to see the updated position.
+			 * css reference reached zero, so iter->position will
+			 * be cleared by ->css_released. However, we should not
+			 * rely on this happening soon, because ->css_released
+			 * is called from a work queue, and by busy-waiting we
+			 * might block it. So we clear iter->position right
+			 * away.
 			 */
-		} while (pos && !css_tryget(&pos->css));
+			(void)cmpxchg(&iter->position, pos, NULL);
+		}
 	}
 
 	if (pos)
@@ -956,17 +962,13 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	}
 
 	if (reclaim) {
-		if (cmpxchg(&iter->position, pos, memcg) == pos) {
-			if (memcg)
-				css_get(&memcg->css);
-			if (pos)
-				css_put(&pos->css);
-		}
-
 		/*
-		 * pairs with css_tryget when dereferencing iter->position
-		 * above.
+		 * The position could have already been updated by a competing
+		 * thread, so check that the value hasn't changed since we read
+		 * it to avoid reclaiming from the same cgroup twice.
 		 */
+		(void)cmpxchg(&iter->position, pos, memcg);
+
 		if (pos)
 			css_put(&pos->css);
 
@@ -999,6 +1001,28 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
 		css_put(&prev->css);
 }
 
+static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+{
+	struct mem_cgroup *memcg = dead_memcg;
+	struct mem_cgroup_reclaim_iter *iter;
+	struct mem_cgroup_per_zone *mz;
+	int nid, zid;
+	int i;
+
+	while ((memcg = parent_mem_cgroup(memcg))) {
+		for_each_node(nid) {
+			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+				mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
+				for (i = 0; i <= DEF_PRIORITY; i++) {
+					iter = &mz->iter[i];
+					cmpxchg(&iter->position,
+						dead_memcg, NULL);
+				}
+			}
+		}
+	}
+}
+
 /*
  * Iteration constructs for visiting all cgroups (under a tree).  If
  * loops are exited prematurely (break), mem_cgroup_iter_break() must
@@ -4324,6 +4348,13 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	wb_memcg_offline(memcg);
 }
 
+static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	invalidate_reclaim_iterators(memcg);
+}
+
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
@@ -5185,6 +5216,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.css_alloc = mem_cgroup_css_alloc,
 	.css_online = mem_cgroup_css_online,
 	.css_offline = mem_cgroup_css_offline,
+	.css_released = mem_cgroup_css_released,
 	.css_free = mem_cgroup_css_free,
 	.css_reset = mem_cgroup_css_reset,
 	.can_attach = mem_cgroup_can_attach,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 67d488ab495e..a042a9d537bb 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1375,23 +1375,30 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
  */
 int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long pfn;
+	unsigned long pfn, sec_end_pfn;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
-	for (pfn = start_pfn;
+	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
 	     pfn < end_pfn;
-	     pfn += MAX_ORDER_NR_PAGES) {
-		i = 0;
-		/* This is just a CONFIG_HOLES_IN_ZONE check.*/
-		while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i))
-			i++;
-		if (i == MAX_ORDER_NR_PAGES)
+	     pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+		/* Make sure the memory section is present first */
+		if (!present_section_nr(pfn_to_section_nr(pfn)))
 			continue;
-		page = pfn_to_page(pfn + i);
-		if (zone && page_zone(page) != zone)
-			return 0;
-		zone = page_zone(page);
+		for (; pfn < sec_end_pfn && pfn < end_pfn;
+		     pfn += MAX_ORDER_NR_PAGES) {
+			i = 0;
+			/* This is just a CONFIG_HOLES_IN_ZONE check.*/
+			while ((i < MAX_ORDER_NR_PAGES) &&
+				!pfn_valid_within(pfn + i))
+				i++;
+			if (i == MAX_ORDER_NR_PAGES)
+				continue;
+			page = pfn_to_page(pfn + i);
+			if (zone && page_zone(page) != zone)
+				return 0;
+			zone = page_zone(page);
+		}
 	}
 	return 1;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0d5712b0206c..4ebc17d948cb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -219,7 +219,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
  * particular counter cannot be updated from interrupt context.
  */
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-				int delta)
+			   long delta)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
 	s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -318,8 +318,8 @@ EXPORT_SYMBOL(__dec_zone_page_state);
  *     1       Overstepping half of threshold
  *     -1      Overstepping minus half of threshold
 */
-static inline void mod_state(struct zone *zone,
-       enum zone_stat_item item, int delta, int overstep_mode)
+static inline void mod_state(struct zone *zone, enum zone_stat_item item,
+			     long delta, int overstep_mode)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
 	s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -357,7 +357,7 @@ static inline void mod_state(struct zone *zone,
 }
 
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
+			 long delta)
 {
 	mod_state(zone, item, delta, 0);
 }
@@ -384,7 +384,7 @@ EXPORT_SYMBOL(dec_zone_page_state);
  * Use interrupt disable to serialize counter updates
  */
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
+			 long delta)
 {
 	unsigned long flags;