| From 1019d14540ff92e9719de7ab56769efd3a8d6a6f Mon Sep 17 00:00:00 2001 |
| From: Vladimir Davydov <vdavydov.dev@gmail.com> |
| Date: Mon, 12 Dec 2016 16:41:29 -0800 |
| Subject: [PATCH] mm: memcontrol: use special workqueue for creating per-memcg |
| caches |
| |
| commit 13583c3d3224508582ec03d881d0b68dd3ee8e10 upstream. |
| |
| Creating a lot of cgroups at the same time might stall all worker |
| threads with kmem cache creation works, because kmem cache creation is |
| done with the slab_mutex held. The problem was amplified by commits |
| 801faf0db894 ("mm/slab: lockless decision to grow cache") in case of |
| SLAB and 81ae6d03952c ("mm/slub.c: replace kick_all_cpus_sync() with |
| synchronize_sched() in kmem_cache_shrink()") in case of SLUB, which |
| increased the maximal time the slab_mutex can be held. |
| |
| To prevent that from happening, let's use a special ordered single |
| threaded workqueue for kmem cache creation. This shouldn't introduce |
| any functional changes regarding how kmem caches are created, as the |
| work function holds the global slab_mutex during its whole runtime |
| anyway, making it impossible to run more than one work at a time. By |
| using a single threaded workqueue, we just avoid creating a thread per |
| each work. Ordering is required to avoid a situation when a cgroup's |
| work is put off indefinitely because there are other cgroups to serve, |
| in other words to guarantee fairness. |
| |
| Link: https://bugzilla.kernel.org/show_bug.cgi?id=172981 |
| Link: http://lkml.kernel.org/r/20161004131417.GC1862@esperanza |
| Signed-off-by: Vladimir Davydov <vdavydov.dev@gmail.com> |
| Reported-by: Doug Smythies <dsmythies@telus.net> |
| Acked-by: Michal Hocko <mhocko@suse.com> |
| Cc: Christoph Lameter <cl@linux.com> |
| Cc: David Rientjes <rientjes@google.com> |
| Cc: Johannes Weiner <hannes@cmpxchg.org> |
| Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> |
| Cc: Pekka Enberg <penberg@kernel.org> |
| Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
| Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
| Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> |
| |
| diff --git a/mm/memcontrol.c b/mm/memcontrol.c |
| index face124e24e9..a6da3f1aca60 100644 |
| --- a/mm/memcontrol.c |
| +++ b/mm/memcontrol.c |
| @@ -2182,6 +2182,8 @@ struct memcg_kmem_cache_create_work { |
| struct work_struct work; |
| }; |
| |
| +static struct workqueue_struct *memcg_kmem_cache_create_wq; |
| + |
| static void memcg_kmem_cache_create_func(struct work_struct *w) |
| { |
| struct memcg_kmem_cache_create_work *cw = |
| @@ -2213,7 +2215,7 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, |
| cw->cachep = cachep; |
| INIT_WORK(&cw->work, memcg_kmem_cache_create_func); |
| |
| - schedule_work(&cw->work); |
| + queue_work(memcg_kmem_cache_create_wq, &cw->work); |
| } |
| |
| static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, |
| @@ -5806,6 +5808,17 @@ static int __init mem_cgroup_init(void) |
| { |
| int cpu, node; |
| |
| +#ifndef CONFIG_SLOB |
| + /* |
| + * Kmem cache creation is mostly done with the slab_mutex held, |
| + * so use a special workqueue to avoid stalling all worker |
| + * threads in case lots of cgroups are created simultaneously. |
| + */ |
| + memcg_kmem_cache_create_wq = |
| + alloc_ordered_workqueue("memcg_kmem_cache_create", 0); |
| + BUG_ON(!memcg_kmem_cache_create_wq); |
| +#endif |
| + |
| hotcpu_notifier(memcg_cpu_hotplug_callback, 0); |
| |
| for_each_possible_cpu(cpu) |
| -- |
| 2.12.0 |
| |