From d9c10ddddc98db0a316243cd266c466875975a94 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 28 Mar 2013 08:48:14 +0100 Subject: memcg: fix memcg_cache_name() to use cgroup_name() As cgroup supports rename, it's unsafe to dereference dentry->d_name without proper vfs locks. Fix this by using cgroup_name() rather than dentry directly. Also open code memcg_cache_name because it is called only from kmem_cache_dup which frees the returned name right after kmem_cache_create_memcg makes a copy of it. Such a short-lived allocation doesn't make too much sense. So replace it by a static buffer as kmem_cache_dup is called with memcg_cache_mutex. Signed-off-by: Li Zefan Signed-off-by: Michal Hocko Acked-by: Glauber Costa Signed-off-by: Tejun Heo --- mm/memcontrol.c | 63 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 32 insertions(+), 31 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53b8201b31eb..9715c0c491b0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3214,52 +3214,53 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep) schedule_work(&cachep->memcg_params->destroy); } -static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s) -{ - char *name; - struct dentry *dentry; - - rcu_read_lock(); - dentry = rcu_dereference(memcg->css.cgroup->dentry); - rcu_read_unlock(); - - BUG_ON(dentry == NULL); - - name = kasprintf(GFP_KERNEL, "%s(%d:%s)", s->name, - memcg_cache_id(memcg), dentry->d_name.name); - - return name; -} +/* + * This lock protects updaters, not readers. We want readers to be as fast as + * they can, and they will either see NULL or a valid cache value. Our model + * allow them to see NULL, in which case the root memcg will be selected. + * + * We need this lock because multiple allocations to the same cache from a non + * will span more than one worker. Only one of them can create the cache. + */ +static DEFINE_MUTEX(memcg_cache_mutex); +/* + * Called with memcg_cache_mutex held + */ static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg, struct kmem_cache *s) { - char *name; struct kmem_cache *new; + static char *tmp_name = NULL; - name = memcg_cache_name(memcg, s); - if (!name) - return NULL; + lockdep_assert_held(&memcg_cache_mutex); + + /* + * kmem_cache_create_memcg duplicates the given name and + * cgroup_name for this name requires RCU context. + * This static temporary buffer is used to prevent from + * pointless shortliving allocation. + */ + if (!tmp_name) { + tmp_name = kmalloc(PATH_MAX, GFP_KERNEL); + if (!tmp_name) + return NULL; + } + + rcu_read_lock(); + snprintf(tmp_name, PATH_MAX, "%s(%d:%s)", s->name, + memcg_cache_id(memcg), cgroup_name(memcg->css.cgroup)); + rcu_read_unlock(); - new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align, + new = kmem_cache_create_memcg(memcg, tmp_name, s->object_size, s->align, (s->flags & ~SLAB_PANIC), s->ctor, s); if (new) new->allocflags |= __GFP_KMEMCG; - kfree(name); return new; } -/* - * This lock protects updaters, not readers. We want readers to be as fast as - * they can, and they will either see NULL or a valid cache value. Our model - * allow them to see NULL, in which case the root memcg will be selected. - * - * We need this lock because multiple allocations to the same cache from a non - * will span more than one worker. Only one of them can create the cache. - */ -static DEFINE_MUTEX(memcg_cache_mutex); static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, struct kmem_cache *cachep) { -- cgit v1.2.3-58-ga151 From f00baae7ad6c5f1503528efa852f0be8e9513f0e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 Apr 2013 13:41:15 -0700 Subject: memcg: force use_hierarchy if sane_behavior Turn on use_hierarchy by default if sane_behavior is specified and don't create .use_hierarchy file. It is debatable whether to remove .use_hierarchy file or make it ro as the former could make transition easier in certain cases; however, the behavior changes which will be gated by sane_behavior are intensive including changing basic meaning of certain control knobs in a few controllers and I don't really think keeping this piece would make things easier in any noticeable way, so let's remove it. v2: Explain that mem_cgroup_bind() doesn't have to worry about children as suggested by Michal Hocko. Signed-off-by: Tejun Heo Acked-by: Serge E. Hallyn Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: KAMEZAWA Hiroyuki --- include/linux/cgroup.h | 3 +++ mm/memcontrol.c | 17 +++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'mm') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 64047ae7fde1..cda7eb2239e1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -268,6 +268,9 @@ enum { * * - Remount is disallowed. * + * - memcg: use_hierarchy is on by default and the cgroup file for + * the flag is not created. + * * The followings are planned changes. * * - release_agent will be disallowed once replacement notification diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9715c0c491b0..df87bdd4d692 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5814,6 +5814,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "use_hierarchy", + .flags = CFTYPE_INSANE, .write_u64 = mem_cgroup_hierarchy_write, .read_u64 = mem_cgroup_hierarchy_read, }, @@ -6784,6 +6785,21 @@ static void mem_cgroup_move_task(struct cgroup *cont, } #endif +/* + * Cgroup retains root cgroups across [un]mount cycles making it necessary + * to verify sane_behavior flag on each mount attempt. + */ +static void mem_cgroup_bind(struct cgroup *root) +{ + /* + * use_hierarchy is forced with sane_behavior. cgroup core + * guarantees that @root doesn't have any children, so turning it + * on for the root memcg is enough. + */ + if (cgroup_sane_behavior(root)) + mem_cgroup_from_cont(root)->use_hierarchy = true; +} + struct cgroup_subsys mem_cgroup_subsys = { .name = "memory", .subsys_id = mem_cgroup_subsys_id, @@ -6794,6 +6810,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, + .bind = mem_cgroup_bind, .base_cftypes = mem_cgroup_files, .early_init = 0, .use_id = 1, -- cgit v1.2.3-58-ga151