| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CALWz4ixPmvguxQO8s9mqH+OLEXC5LDfzEVFx_qqe2hBaRcsXiA@mail.gmail.com>
Date: Sun, 9 Dec 2012 11:39:50 -0800
From: Ying Han <yinghan@...gle.com>
To: Michal Hocko <mhocko@...e.cz>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
Johannes Weiner <hannes@...xchg.org>,
Tejun Heo <htejun@...il.com>,
Glauber Costa <glommer@...allels.com>,
Li Zefan <lizefan@...wei.com>
Subject: Re: [patch v2 3/6] memcg: rework mem_cgroup_iter to use cgroup iterators
On Mon, Nov 26, 2012 at 10:47 AM, Michal Hocko <mhocko@...e.cz> wrote:
> mem_cgroup_iter curently relies on css->id when walking down a group
> hierarchy tree. This is really awkward because the tree walk depends on
> the groups creation ordering. The only guarantee is that a parent node
> is visited before its children.
> Example
> 1) mkdir -p a a/d a/b/c
> 2) mkdir -a a/b/c a/d
> Will create the same trees but the tree walks will be different:
> 1) a, d, b, c
> 2) a, b, c, d
>
> 574bd9f7 (cgroup: implement generic child / descendant walk macros) has
> introduced generic cgroup tree walkers which provide either pre-order
> or post-order tree walk. This patch converts css->id based iteration
> to pre-order tree walk to keep the semantic with the original iterator
> where parent is always visited before its subtree.
>
> cgroup_for_each_descendant_pre suggests using post_create and
> pre_destroy for proper synchronization with groups addidition resp.
> removal. This implementation doesn't use those because a new memory
> cgroup is fully initialized in mem_cgroup_create and css reference
> counting enforces that the group is alive for both the last seen cgroup
> and the found one resp. it signals that the group is dead and it should
> be skipped.
>
> If the reclaim cookie is used we need to store the last visited group
> into the iterator so we have to be careful that it doesn't disappear in
> the mean time. Elevated reference count on the css keeps it alive even
> though the group have been removed (parked waiting for the last dput so
> that it can be freed).
>
> V2
> - use css_{get,put} for iter->last_visited rather than
> mem_cgroup_{get,put} because it is stronger wrt. cgroup life cycle
> - cgroup_next_descendant_pre expects NULL pos for the first iterartion
> otherwise it might loop endlessly for intermediate node without any
> children.
>
> Signed-off-by: Michal Hocko <mhocko@...e.cz>
> ---
> mm/memcontrol.c | 74 ++++++++++++++++++++++++++++++++++++++++++-------------
> 1 file changed, 57 insertions(+), 17 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 1f5528d..6bcc97b 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -144,8 +144,8 @@ struct mem_cgroup_stat_cpu {
> };
>
> struct mem_cgroup_reclaim_iter {
> - /* css_id of the last scanned hierarchy member */
> - int position;
> + /* last scanned hierarchy member with elevated css ref count */
> + struct mem_cgroup *last_visited;
> /* scan generation, increased every round-trip */
> unsigned int generation;
> /* lock to protect the position and generation */
> @@ -1066,7 +1066,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
> struct mem_cgroup_reclaim_cookie *reclaim)
> {
> struct mem_cgroup *memcg = NULL;
> - int id = 0;
> + struct mem_cgroup *last_visited = NULL;
>
> if (mem_cgroup_disabled())
> return NULL;
> @@ -1075,7 +1075,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
> root = root_mem_cgroup;
>
> if (prev && !reclaim)
> - id = css_id(&prev->css);
> + last_visited = prev;
>
> if (!root->use_hierarchy && root != root_mem_cgroup) {
> if (prev)
> @@ -1083,9 +1083,10 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
> return root;
> }
>
> + rcu_read_lock();
> while (!memcg) {
> struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
> - struct cgroup_subsys_state *css;
> + struct cgroup_subsys_state *css = NULL;
>
> if (reclaim) {
> int nid = zone_to_nid(reclaim->zone);
> @@ -1095,34 +1096,73 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
> mz = mem_cgroup_zoneinfo(root, nid, zid);
> iter = &mz->reclaim_iter[reclaim->priority];
> spin_lock(&iter->iter_lock);
> + last_visited = iter->last_visited;
> if (prev && reclaim->generation != iter->generation) {
> + if (last_visited) {
> + css_put(&last_visited->css);
> + iter->last_visited = NULL;
> + }
> spin_unlock(&iter->iter_lock);
> - goto out_css_put;
> + goto out_unlock;
> }
> - id = iter->position;
> }
>
> - rcu_read_lock();
> - css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id);
> - if (css) {
> - if (css == &root->css || css_tryget(css))
> - memcg = mem_cgroup_from_css(css);
> - } else
> - id = 0;
> - rcu_read_unlock();
> + /*
> + * Root is not visited by cgroup iterators so it needs an
> + * explicit visit.
> + */
> + if (!last_visited) {
> + css = &root->css;
> + } else {
> + struct cgroup *prev_cgroup, *next_cgroup;
> +
> + prev_cgroup = (last_visited == root) ? NULL
> + : last_visited->css.cgroup;
> + next_cgroup = cgroup_next_descendant_pre(prev_cgroup,
> + root->css.cgroup);
> + if (next_cgroup)
> + css = cgroup_subsys_state(next_cgroup,
> + mem_cgroup_subsys_id);
> + }
> +
> + /*
> + * Even if we found a group we have to make sure it is alive.
> + * css && !memcg means that the groups should be skipped and
> + * we should continue the tree walk.
> + * last_visited css is safe to use because it is protected by
> + * css_get and the tree walk is rcu safe.
> + */
> + if (css == &root->css || (css && css_tryget(css)))
> + memcg = mem_cgroup_from_css(css);
>
> if (reclaim) {
> - iter->position = id;
> + struct mem_cgroup *curr = memcg;
> +
> + if (last_visited)
> + css_put(&last_visited->css);
> +
> + if (css && !memcg)
> + curr = mem_cgroup_from_css(css);
> +
> + /* make sure that the cached memcg is not removed */
> + if (curr)
> + css_get(&curr->css);
> + iter->last_visited = curr;
Here we take extra refcnt for last_visited, and assume it is under
target reclaim which then calls mem_cgroup_iter_break() and we leaked
a refcnt of the
target memcg css. Sorry if i missed the change in iter_break(),
otherwise we might need something like this:
void mem_cgroup_iter_break(struct mem_cgroup *root,
- struct mem_cgroup *prev)
+ struct mem_cgroup *prev,
+ struct mem_cgroup_reclaim_cookie *reclaim)
{
if (!root)
root = root_mem_cgroup;
if (prev && prev != root)
css_put(&prev->css);
+
+ if (reclaim) {
+ int nid = zone_to_nid(reclaim->zone);
+ int zid = zone_idx(reclaim->zone);
+ struct mem_cgroup *last_visited = NULL;
+ struct mem_cgroup_per_zone *mz;
+ struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
+
+ mz = mem_cgroup_zoneinfo(root, nid, zid);
+ iter = &mz->reclaim_iter[reclaim->priority];
+ spin_lock(&iter->iter_lock);
+ last_visited = iter->last_visited;
+ if (last_visited) {
+ css_put(&last_visited->css);
+ iter->last_visited = NULL;
+ }
+ spin_unlock(&iter->iter_lock);
+ }
}
--Ying
> if (!css)
> iter->generation++;
> else if (!prev && memcg)
> reclaim->generation = iter->generation;
> spin_unlock(&iter->iter_lock);
> + } else if (css && !memcg) {
> + last_visited = mem_cgroup_from_css(css);
> }
>
> if (prev && !css)
> - goto out_css_put;
> + goto out_unlock;
> }
> +out_unlock:
> + rcu_read_unlock();
> out_css_put:
> if (prev && prev != root)
> css_put(&prev->css);
> --
> 1.7.10.4
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists