summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRoman Gushchin <guro@fb.com>2020-08-11 18:30:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-08-12 10:57:55 -0700
commit3e38e0aaca9eafb12b1c4b731d1c10975cbe7974 (patch)
tree9df2be98d1908c91e92c1a968931d70ea8db0896
parent772616b031f06e05846488b01dab46a7c832da13 (diff)
mm: memcg: charge memcg percpu memory to the parent cgroup
Memory cgroups are using large chunks of percpu memory to store vmstat data. Yet this memory is not accounted at all, so in the case when there are many (dying) cgroups, it's not exactly clear where all the memory is. Because the size of memory cgroup internal structures can dramatically exceed the size of object or page which is pinning it in the memory, it's not a good idea to simply ignore it. It actually breaks the isolation between cgroups. Let's account the consumed percpu memory to the parent cgroup. [guro@fb.com: add WARN_ON_ONCE()s, per Johannes] Link: http://lkml.kernel.org/r/20200811170611.GB1507044@carbon.DHCP.thefacebook.com Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Shakeel Butt <shakeelb@google.com> Acked-by: Dennis Zhou <dennis@kernel.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Tobin C. Harding <tobin@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Waiman Long <longman@redhat.com> Cc: Bixuan Cui <cuibixuan@huawei.com> Cc: Michal Koutný <mkoutny@suse.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Link: http://lkml.kernel.org/r/20200623184515.4132564-5-guro@fb.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/memcontrol.c20
1 files changed, 16 insertions, 4 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36d5300f9b69..f1fd265b9f9e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5131,13 +5131,18 @@ 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);
+ /* We charge the parent cgroup, never the current task */
+ WARN_ON_ONCE(!current->active_memcg);
+
+ pn->lruvec_stat_local = alloc_percpu_gfp(struct lruvec_stat,
+ GFP_KERNEL_ACCOUNT);
if (!pn->lruvec_stat_local) {
kfree(pn);
return 1;
}
- pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
+ pn->lruvec_stat_cpu = alloc_percpu_gfp(struct lruvec_stat,
+ GFP_KERNEL_ACCOUNT);
if (!pn->lruvec_stat_cpu) {
free_percpu(pn->lruvec_stat_local);
kfree(pn);
@@ -5211,11 +5216,16 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
goto fail;
}
- memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
+ /* We charge the parent cgroup, never the current task */
+ WARN_ON_ONCE(!current->active_memcg);
+
+ memcg->vmstats_local = alloc_percpu_gfp(struct memcg_vmstats_percpu,
+ GFP_KERNEL_ACCOUNT);
if (!memcg->vmstats_local)
goto fail;
- memcg->vmstats_percpu = alloc_percpu(struct memcg_vmstats_percpu);
+ memcg->vmstats_percpu = alloc_percpu_gfp(struct memcg_vmstats_percpu,
+ GFP_KERNEL_ACCOUNT);
if (!memcg->vmstats_percpu)
goto fail;
@@ -5264,7 +5274,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
struct mem_cgroup *memcg;
long error = -ENOMEM;
+ memalloc_use_memcg(parent);
memcg = mem_cgroup_alloc();
+ memalloc_unuse_memcg();
if (IS_ERR(memcg))
return ERR_CAST(memcg);