Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "16 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/devm_memremap_pages: fix final page put race
  PCI/P2PDMA: track pgmap references per resource, not globally
  lib/genalloc: introduce chunk owners
  PCI/P2PDMA: fix the gen_pool_add_virt() failure path
  mm/devm_memremap_pages: introduce devm_memunmap_pages
  drivers/base/devres: introduce devm_release_action()
  mm/vmscan.c: fix trying to reclaim unevictable LRU page
  coredump: fix race condition between collapse_huge_page() and core dumping
  mm/mlock.c: change count_mm_mlocked_page_nr return type
  mm: mmu_gather: remove __tlb_reset_range() for force flush
  fs/ocfs2: fix race in ocfs2_dentry_attach_lock()
  mm/vmscan.c: fix recent_rotated history
  mm/mlock.c: mlockall error for flag MCL_ONFAULT
  scripts/decode_stacktrace.sh: prefix addr2line with $CROSS_COMPILE
  mm/list_lru.c: fix memory leak in __memcg_init_list_lru_node
  mm: memcontrol: don't batch updates of local VM stats and events

1 files changed, 28 insertions, 13 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ca0bc6e6be13..ba9138a4a1de 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -691,11 +691,12 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 	if (mem_cgroup_disabled())
 		return;
 
+	__this_cpu_add(memcg->vmstats_local->stat[idx], val);
+
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup *mi;
 
-		atomic_long_add(x, &memcg->vmstats_local[idx]);
 		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 			atomic_long_add(x, &mi->vmstats[idx]);
 		x = 0;
@@ -745,11 +746,12 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__mod_memcg_state(memcg, idx, val);
 
 	/* Update lruvec */
+	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup_per_node *pi;
 
-		atomic_long_add(x, &pn->lruvec_stat_local[idx]);
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
 			atomic_long_add(x, &pi->lruvec_stat[idx]);
 		x = 0;
@@ -771,11 +773,12 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 	if (mem_cgroup_disabled())
 		return;
 
+	__this_cpu_add(memcg->vmstats_local->events[idx], count);
+
 	x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]);
 	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup *mi;
 
-		atomic_long_add(x, &memcg->vmevents_local[idx]);
 		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 			atomic_long_add(x, &mi->vmevents[idx]);
 		x = 0;
@@ -790,7 +793,12 @@ static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
 
 static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
 {
-	return atomic_long_read(&memcg->vmevents_local[event]);
+	long x = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		x += per_cpu(memcg->vmstats_local->events[event], cpu);
+	return x;
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
@@ -2191,11 +2199,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 			long x;
 
 			x = this_cpu_xchg(memcg->vmstats_percpu->stat[i], 0);
-			if (x) {
-				atomic_long_add(x, &memcg->vmstats_local[i]);
+			if (x)
 				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 					atomic_long_add(x, &memcg->vmstats[i]);
-			}
 
 			if (i >= NR_VM_NODE_STAT_ITEMS)
 				continue;
@@ -2205,12 +2211,10 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 
 				pn = mem_cgroup_nodeinfo(memcg, nid);
 				x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0);
-				if (x) {
-					atomic_long_add(x, &pn->lruvec_stat_local[i]);
+				if (x)
 					do {
 						atomic_long_add(x, &pn->lruvec_stat[i]);
 					} while ((pn = parent_nodeinfo(pn, nid)));
-				}
 			}
 		}
 
@@ -2218,11 +2222,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 			long x;
 
 			x = this_cpu_xchg(memcg->vmstats_percpu->events[i], 0);
-			if (x) {
-				atomic_long_add(x, &memcg->vmevents_local[i]);
+			if (x)
 				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 					atomic_long_add(x, &memcg->vmevents[i]);
-			}
 		}
 	}
 
@@ -4483,8 +4485,15 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
+	pn->lruvec_stat_local = alloc_percpu(struct lruvec_stat);
+	if (!pn->lruvec_stat_local) {
+		kfree(pn);
+		return 1;
+	}
+
 	pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
 	if (!pn->lruvec_stat_cpu) {
+		free_percpu(pn->lruvec_stat_local);
 		kfree(pn);
 		return 1;
 	}
@@ -4506,6 +4515,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 		return;
 
 	free_percpu(pn->lruvec_stat_cpu);
+	free_percpu(pn->lruvec_stat_local);
 	kfree(pn);
 }
 
@@ -4516,6 +4526,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
+	free_percpu(memcg->vmstats_local);
 	kfree(memcg);
 }
 
@@ -4544,6 +4555,10 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (memcg->id.id < 0)
 		goto fail;
 
+	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
+	if (!memcg->vmstats_local)
+		goto fail;
+
 	memcg->vmstats_percpu = alloc_percpu(struct memcg_vmstats_percpu);
 	if (!memcg->vmstats_percpu)
 		goto fail;