The patch titled
Subject: memcg: release memcg_cache_id on css offline
has been removed from the -mm tree. Its filename was
memcg-release-memcg_cache_id-on-css-offline.patch
This patch was dropped because it was withdrawn
------------------------------------------------------
From: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Subject: memcg: release memcg_cache_id on css offline
The memcg_cache_id (mem_cgroup->kmemcg_id) is used as the index in root
cache's memcg_cache_params->memcg_caches array. Whenever a new kmem
active cgroup is created we must allocate an id for it. As a result, the
array size must always be greater than or equal to the number of memory
cgroups that have memcg_cache_id assigned to them.
Currently we release the id only on css free. This is bad, because css
can be zombieing around for quite a long time after css offline, occupying
an array slot and making the arrays grow larger and larger. Although the
number of arrays is limited - only root kmem caches have them - we can
still experience problems while creating new kmem active cgroups, because
they might require arrays relocation and each array relocation will
require costly high-order page allocations if there are a lot of ids
allocated. The situation will become even worse when per-memcg list_lru's
are introduced, because each super block has a list_lru, and the number of
super blocks is practically unlimited.
So let's release memcg_cache_id on css offline - there's nothing that
prevents us from doing so.
Signed-off-by: Vladimir Davydov <vdavydov@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 42 ++++++++++++++++++++++++++++++++++++------
1 file changed, 36 insertions(+), 6 deletions(-)
diff -puN mm/memcontrol.c~memcg-release-memcg_cache_id-on-css-offline mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-release-memcg_cache_id-on-css-offline
+++ a/mm/memcontrol.c
@@ -648,10 +648,8 @@ EXPORT_SYMBOL(memcg_kmem_enabled_key);
static void disarm_kmem_keys(struct mem_cgroup *memcg)
{
- if (memcg_kmem_is_active(memcg)) {
+ if (memcg_kmem_is_active(memcg))
static_key_slow_dec(&memcg_kmem_enabled_key);
- ida_simple_remove(&kmem_limited_groups, memcg->kmemcg_id);
- }
/*
* This check can't live in kmem destruction function,
* since the charges will outlive the cgroup
@@ -3017,6 +3015,12 @@ static void memcg_register_cache(struct
lockdep_assert_held(&memcg_slab_mutex);
id = memcg_cache_id(memcg);
+ /*
+ * The cgroup was taken offline while the create work was pending,
+ * nothing to do then.
+ */
+ if (id < 0)
+ return;
/*
* Since per-memcg caches are created asynchronously on first
@@ -3071,8 +3075,17 @@ static void memcg_unregister_cache(struc
memcg = cachep->memcg_params->memcg;
id = memcg_cache_id(memcg);
- BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep);
- root_cache->memcg_params->memcg_caches[id] = NULL;
+ /*
+ * This function can be called both after and before css offline. If
+ * it's called before css offline, which happens on the root cache
+ * destruction, we should clear the slot corresponding to the cache in
+ * memcg_caches array. Otherwise the slot must have already been
+ * cleared in memcg_unregister_all_caches.
+ */
+ if (id >= 0) {
+ BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep);
+ root_cache->memcg_params->memcg_caches[id] = NULL;
+ }
list_del(&cachep->memcg_params->list);
@@ -3124,19 +3137,27 @@ void __memcg_cleanup_cache_params(struct
static void memcg_unregister_all_caches(struct mem_cgroup *memcg)
{
struct memcg_cache_params *params, *tmp;
+ int id = memcg_cache_id(memcg);
if (!memcg_kmem_is_active(memcg))
return;
mutex_lock(&memcg_slab_mutex);
+ memcg->kmemcg_id = -1;
list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) {
struct kmem_cache *cachep = params->cachep;
+ struct kmem_cache *root_cache = params->root_cache;
+
+ BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep);
+ root_cache->memcg_params->memcg_caches[id] = NULL;
kmem_cache_shrink(cachep);
if (atomic_read(&cachep->memcg_params->nr_pages) == 0)
memcg_unregister_cache(cachep);
}
mutex_unlock(&memcg_slab_mutex);
+
+ ida_simple_remove(&kmem_limited_groups, id);
}
struct memcg_register_cache_work {
@@ -3235,6 +3256,7 @@ struct kmem_cache *__memcg_kmem_get_cach
{
struct mem_cgroup *memcg;
struct kmem_cache *memcg_cachep;
+ int id;
VM_BUG_ON(!cachep->memcg_params);
VM_BUG_ON(!cachep->memcg_params->is_root_cache);
@@ -3248,7 +3270,15 @@ struct kmem_cache *__memcg_kmem_get_cach
if (!memcg_can_account_kmem(memcg))
goto out;
- memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg));
+ id = memcg_cache_id(memcg);
+ /*
+ * This can happen if current was migrated to another cgroup and this
+ * cgroup was taken offline after we issued mem_cgroup_from_task above.
+ */
+ if (unlikely(id < 0))
+ goto out;
+
+ memcg_cachep = cache_from_memcg_idx(cachep, id);
if (likely(memcg_cachep)) {
cachep = memcg_cachep;
goto out;
_
Patches currently in -mm which might be from vdavydov@xxxxxxxxxxxxx are
mm-slabh-wrap-the-whole-file-with-guarding-macro.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
mm-memcontrol-use-page-lists-for-uncharge-batching-fix-hugetlb-page-lru.patch
page-cgroup-trivial-cleanup.patch
page-cgroup-get-rid-of-nr_pcg_flags.patch
slub-remove-kmemcg-id-from-create_unique_id.patch
slab-use-mem_cgroup_id-for-per-memcg-cache-naming.patch
memcg-make-memcg_cache_id-static.patch
memcg-add-pointer-to-owner-cache-to-memcg_cache_params.patch
memcg-keep-all-children-of-each-root-cache-on-a-list.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
