diff options
author | Christoph Lameter <cl@linux.com> | 2013-09-21 21:56:34 +0000 |
---|---|---|
committer | Pekka Enberg <penberg@kernel.org> | 2013-09-28 09:47:41 +0300 |
commit | 3e374919b314f20e2a04f641ebc1093d758f66a4 (patch) | |
tree | c0d542012f379d503b17baa796586d23ef457a9b | |
parent | 4a10c2ac2f368583138b774ca41fac4207911983 (diff) | |
download | op-kernel-dev-3e374919b314f20e2a04f641ebc1093d758f66a4.zip op-kernel-dev-3e374919b314f20e2a04f641ebc1093d758f66a4.tar.gz |
slab_common: Do not check for duplicate slab names
SLUB can alias multiple slab kmem_create_requests to one slab cache to save
memory and increase the cache hotness. As a result the name of the slab can be
stale. Only check the name for duplicates if we are in debug mode where we do
not merge multiple caches.
This fixes the following problem reported by Jonathan Brassow:
The problem with kmem_cache* is this:
*) Assume CONFIG_SLUB is set
1) kmem_cache_create(name="foo-a")
- creates new kmem_cache structure
2) kmem_cache_create(name="foo-b")
- If identical cache characteristics, it will be merged with the previously
created cache associated with "foo-a". The cache's refcount will be
incremented and an alias will be created via sysfs_slab_alias().
3) kmem_cache_destroy(<ptr>)
- Attempting to destroy cache associated with "foo-a", but instead the
refcount is simply decremented. I don't even think the sysfs aliases are
ever removed...
4) kmem_cache_create(name="foo-a")
- This FAILS because kmem_cache_sanity_check colides with the existing
name ("foo-a") associated with the non-removed cache.
This is a problem for RAID (specifically dm-raid) because the name used
for the kmem_cache_create is ("raid%d-%p", level, mddev). If the cache
persists for long enough, the memory address of an old mddev will be
reused for a new mddev - causing an identical formulation of the cache
name. Even though kmem_cache_destory had long ago been used to delete
the old cache, the merging of caches has cause the name and cache of that
old instance to be preserved and causes a colision (and thus failure) in
kmem_cache_create(). I see this regularly in my testing.
Reported-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
-rw-r--r-- | mm/slab_common.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/mm/slab_common.c b/mm/slab_common.c index a344327..e2e98af 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -56,6 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, continue; } +#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) /* * For simplicity, we won't check this in the list of memcg * caches. We have control over memcg naming, and if there @@ -69,6 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, s = NULL; return -EINVAL; } +#endif } WARN_ON(strchr(name, ' ')); /* It confuses parsers */ |