The patch titled Subject: memcg: destroy kmem caches when last slab is freed has been removed from the -mm tree. Its filename was memcg-destroy-kmem-caches-when-last-slab-is-freed.patch This patch was dropped because it was withdrawn ------------------------------------------------------ From: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx> Subject: memcg: destroy kmem caches when last slab is freed When the memcg_cache_params->refcnt goes to 0, schedule the worker that will unregister the cache. To prevent this from happening when the owner memcg is alive, keep the refcnt incremented during memcg lifetime. Note, this doesn't guarantee that the cache that belongs to a dead memcg will go away as soon as the last object is freed, because SL[AU]B implementation can cache empty slabs for performance reasons. Hence the cache may be hanging around indefinitely after memcg offline. This is to be resolved by the next patches. Signed-off-by: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx> Acked-by: Christoph Lameter <cl@xxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Pekka Enberg <penberg@xxxxxxxxxx> Cc: David Rientjes <rientjes@xxxxxxxxxx> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/slab.h | 2 ++ mm/memcontrol.c | 22 ++++++++++++++++++++-- 2 files changed, 22 insertions(+), 2 deletions(-) diff -puN include/linux/slab.h~memcg-destroy-kmem-caches-when-last-slab-is-freed include/linux/slab.h --- a/include/linux/slab.h~memcg-destroy-kmem-caches-when-last-slab-is-freed +++ a/include/linux/slab.h @@ -527,6 +527,7 @@ static __always_inline void *kmalloc_nod * @list: list_head for the list of all caches in this memcg * @root_cache: pointer to the global, root cache, this cache was derived from * @refcnt: reference counter + * @unregister_work: worker to destroy the cache */ struct memcg_cache_params { bool is_root_cache; @@ -540,6 +541,7 @@ struct memcg_cache_params { struct list_head list; struct kmem_cache *root_cache; atomic_long_t refcnt; + struct work_struct unregister_work; }; }; }; diff -puN mm/memcontrol.c~memcg-destroy-kmem-caches-when-last-slab-is-freed mm/memcontrol.c --- a/mm/memcontrol.c~memcg-destroy-kmem-caches-when-last-slab-is-freed +++ a/mm/memcontrol.c @@ -3076,6 +3076,8 @@ int memcg_update_cache_size(struct kmem_ return 0; } +static void memcg_unregister_cache_func(struct work_struct *work); + int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s, struct kmem_cache *root_cache) { @@ -3097,6 +3099,9 @@ int memcg_alloc_cache_params(struct mem_ if (memcg) { s->memcg_params->memcg = memcg; s->memcg_params->root_cache = root_cache; + atomic_long_set(&s->memcg_params->refcnt, 1); + INIT_WORK(&s->memcg_params->unregister_work, + memcg_unregister_cache_func); css_get(&memcg->css); } else s->memcg_params->is_root_cache = true; @@ -3178,6 +3183,17 @@ static void memcg_unregister_cache(struc kmem_cache_destroy(cachep); } +static void memcg_unregister_cache_func(struct work_struct *work) +{ + struct memcg_cache_params *params = + container_of(work, struct memcg_cache_params, unregister_work); + struct kmem_cache *cachep = memcg_params_to_cache(params); + + mutex_lock(&memcg_slab_mutex); + memcg_unregister_cache(cachep); + mutex_unlock(&memcg_slab_mutex); +} + /* * During the creation a new cache, we need to disable our accounting mechanism * altogether. This is true even if we are not creating, but rather just @@ -3241,7 +3257,7 @@ static void memcg_unregister_all_caches( list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { cachep = memcg_params_to_cache(params); kmem_cache_shrink(cachep); - if (atomic_long_read(&cachep->memcg_params->refcnt) == 0) + if (atomic_long_dec_and_test(&cachep->memcg_params->refcnt)) memcg_unregister_cache(cachep); } mutex_unlock(&memcg_slab_mutex); @@ -3322,7 +3338,9 @@ int __memcg_charge_slab(struct kmem_cach void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) { memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order); - atomic_long_dec(&cachep->memcg_params->refcnt); + + if (unlikely(atomic_long_dec_and_test(&cachep->memcg_params->refcnt))) + schedule_work(&cachep->memcg_params->unregister_work); } /* _ Patches currently in -mm which might be from vdavydov@xxxxxxxxxxxxx are mm-slabh-wrap-the-whole-file-with-guarding-macro.patch memcg-cleanup-memcg_cache_params-refcnt-usage.patch mm-memcontrol-fold-mem_cgroup_do_charge.patch mm-memcontrol-rearrange-charging-fast-path.patch mm-memcontrol-reclaim-at-least-once-for-__gfp_noretry.patch mm-huge_memory-use-gfp_transhuge-when-charging-huge-pages.patch mm-memcontrol-retry-reclaim-for-oom-disabled-and-__gfp_nofail-charges.patch mm-memcontrol-remove-explicit-oom-parameter-in-charge-path.patch mm-memcontrol-simplify-move-precharge-function.patch mm-memcontrol-catch-root-bypass-in-move-precharge.patch mm-memcontrol-use-root_mem_cgroup-res_counter.patch mm-memcontrol-remove-ordering-between-pc-mem_cgroup-and-pagecgroupused.patch mm-memcontrol-do-not-acquire-page_cgroup-lock-for-kmem-pages.patch mm-memcontrol-rewrite-charge-api.patch mm-memcontrol-rewrite-uncharge-api.patch mm-memcontrol-rewrite-uncharge-api-fix-5.patch mm-memcontrol-use-page-lists-for-uncharge-batching.patch page-cgroup-trivial-cleanup.patch page-cgroup-get-rid-of-nr_pcg_flags.patch fork-exec-cleanup-mm-initialization.patch fork-reset-mm-pinned_vm.patch fork-copy-mms-vm-usage-counters-under-mmap_sem.patch fork-make-mm_init_owner-static.patch linux-next.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