The patch titled Subject: memcg/sl[au]b: track all the memcg children of a kmem_cache has been added to the -mm tree. Its filename is memcg-slb-track-all-the-memcg-children-of-a-kmem_cache.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Glauber Costa <glommer@xxxxxxxxxxxxx> Subject: memcg/sl[au]b: track all the memcg children of a kmem_cache This enables us to remove all the children of a kmem_cache being destroyed, if for example the kernel module it's being used in gets unloaded. Otherwise, the children will still point to the destroyed parent. Signed-off-by: Suleiman Souhlal <suleiman@xxxxxxxxxx> Signed-off-by: Glauber Costa <glommer@xxxxxxxxxxxxx> Cc: Christoph Lameter <cl@xxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Frederic Weisbecker <fweisbec@xxxxxxxxxx> Cc: Greg Thelen <gthelen@xxxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: JoonSoo Kim <js1304@xxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Mel Gorman <mel@xxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxx> Cc: Pekka Enberg <penberg@xxxxxxxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Tejun Heo <tj@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/memcontrol.h | 5 +++ mm/memcontrol.c | 49 +++++++++++++++++++++++++++++++++-- mm/slab_common.c | 3 ++ 3 files changed, 55 insertions(+), 2 deletions(-) diff -puN include/linux/memcontrol.h~memcg-slb-track-all-the-memcg-children-of-a-kmem_cache include/linux/memcontrol.h --- a/include/linux/memcontrol.h~memcg-slb-track-all-the-memcg-children-of-a-kmem_cache +++ a/include/linux/memcontrol.h @@ -447,6 +447,7 @@ struct kmem_cache * __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); void mem_cgroup_destroy_cache(struct kmem_cache *cachep); +void kmem_cache_destroy_memcg_children(struct kmem_cache *s); /** * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. @@ -594,6 +595,10 @@ memcg_kmem_get_cache(struct kmem_cache * { return cachep; } + +static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s) +{ +} #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ diff -puN mm/memcontrol.c~memcg-slb-track-all-the-memcg-children-of-a-kmem_cache mm/memcontrol.c --- a/mm/memcontrol.c~memcg-slb-track-all-the-memcg-children-of-a-kmem_cache +++ a/mm/memcontrol.c @@ -2741,6 +2741,8 @@ static void __mem_cgroup_commit_charge(s memcg_check_events(memcg, page); } +static DEFINE_MUTEX(set_limit_mutex); + #ifdef CONFIG_MEMCG_KMEM static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg) { @@ -3153,6 +3155,51 @@ out: return new_cachep; } +void kmem_cache_destroy_memcg_children(struct kmem_cache *s) +{ + struct kmem_cache *c; + int i; + + if (!s->memcg_params) + return; + if (!s->memcg_params->is_root_cache) + return; + + /* + * If the cache is being destroyed, we trust that there is no one else + * requesting objects from it. Even if there are, the sanity checks in + * kmem_cache_destroy should caught this ill-case. + * + * Still, we don't want anyone else freeing memcg_caches under our + * noses, which can happen if a new memcg comes to life. As usual, + * we'll take the set_limit_mutex to protect ourselves against this. + */ + mutex_lock(&set_limit_mutex); + for (i = 0; i < memcg_limited_groups_array_size; i++) { + c = s->memcg_params->memcg_caches[i]; + if (!c) + continue; + + /* + * We will now manually delete the caches, so to avoid races + * we need to cancel all pending destruction workers and + * proceed with destruction ourselves. + * + * kmem_cache_destroy() will call kmem_cache_shrink internally, + * and that could spawn the workers again: it is likely that + * the cache still have active pages until this very moment. + * This would lead us back to mem_cgroup_destroy_cache. + * + * But that will not execute at all if the "dead" flag is not + * set, so flip it down to guarantee we are in control. + */ + c->memcg_params->dead = false; + cancel_delayed_work_sync(&c->memcg_params->destroy); + kmem_cache_destroy(c); + } + mutex_unlock(&set_limit_mutex); +} + struct create_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; @@ -4280,8 +4327,6 @@ void mem_cgroup_print_bad_page(struct pa } #endif -static DEFINE_MUTEX(set_limit_mutex); - static int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) { diff -puN mm/slab_common.c~memcg-slb-track-all-the-memcg-children-of-a-kmem_cache mm/slab_common.c --- a/mm/slab_common.c~memcg-slb-track-all-the-memcg-children-of-a-kmem_cache +++ a/mm/slab_common.c @@ -221,6 +221,9 @@ EXPORT_SYMBOL(kmem_cache_create); void kmem_cache_destroy(struct kmem_cache *s) { + /* Destroy all the children caches if we aren't a memcg cache */ + kmem_cache_destroy_memcg_children(s); + get_online_cpus(); mutex_lock(&slab_mutex); s->refcount--; _ Patches currently in -mm which might be from glommer@xxxxxxxxxxxxx are linux-next.patch memcg-make-it-possible-to-use-the-stock-for-more-than-one-page.patch memcg-reclaim-when-more-than-one-page-needed.patch memcg-change-defines-to-an-enum.patch memcg-kmem-accounting-basic-infrastructure.patch mm-add-a-__gfp_kmemcg-flag.patch memcg-kmem-controller-infrastructure.patch mm-allocate-kernel-pages-to-the-right-memcg.patch res_counter-return-amount-of-charges-after-res_counter_uncharge.patch memcg-kmem-accounting-lifecycle-management.patch memcg-use-static-branches-when-code-not-in-use.patch memcg-allow-a-memcg-with-kmem-charges-to-be-destructed.patch memcg-execute-the-whole-memcg-freeing-in-free_worker.patch fork-protect-architectures-where-thread_size-=-page_size-against-fork-bombs.patch memcg-add-documentation-about-the-kmem-controller.patch slab-slub-struct-memcg_params.patch slab-annotate-on-slab-caches-nodelist-locks.patch slab-slub-consider-a-memcg-parameter-in-kmem_create_cache.patch memcg-allocate-memory-for-memcg-caches-whenever-a-new-memcg-appears.patch memcg-infrastructure-to-match-an-allocation-to-the-right-cache.patch memcg-skip-memcg-kmem-allocations-in-specified-code-regions.patch slb-always-get-the-cache-from-its-page-in-kmem_cache_free.patch slb-allocate-objects-from-memcg-cache.patch memcg-destroy-memcg-caches.patch memcg-slb-track-all-the-memcg-children-of-a-kmem_cache.patch memcg-slb-shrink-dead-caches.patch memcg-aggregate-memcg-cache-values-in-slabinfo.patch slab-propagate-tunable-values.patch slub-slub-specific-propagation-changes.patch kmem-add-slab-specific-documentation-about-the-kmem-controller.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html