Commit 542f85f9 authored by Michal Hocko's avatar Michal Hocko Committed by Linus Torvalds

memcg: rework mem_cgroup_iter to use cgroup iterators

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

Commit 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 initialized sufficiently for iteration in mem_cgroup_css_alloc
already 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).

Per node-zone-prio iter_lock has been introduced to ensure that
css_tryget and iter->last_visited is set atomically.  Otherwise two
racing walkers could both take a references and only one release it
leading to a css leak (which pins cgroup dentry).
Signed-off-by: default avatarMichal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Ying Han <yinghan@google.com>
Cc: Tejun Heo <htejun@gmail.com>
Cc: Glauber Costa <glommer@parallels.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent c40046f3
...@@ -152,10 +152,12 @@ struct mem_cgroup_stat_cpu { ...@@ -152,10 +152,12 @@ struct mem_cgroup_stat_cpu {
}; };
struct mem_cgroup_reclaim_iter { struct mem_cgroup_reclaim_iter {
/* css_id of the last scanned hierarchy member */ /* last scanned hierarchy member with elevated css ref count */
int position; struct mem_cgroup *last_visited;
/* scan generation, increased every round-trip */ /* scan generation, increased every round-trip */
unsigned int generation; unsigned int generation;
/* lock to protect the position and generation */
spinlock_t iter_lock;
}; };
/* /*
...@@ -1089,7 +1091,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, ...@@ -1089,7 +1091,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
struct mem_cgroup_reclaim_cookie *reclaim) struct mem_cgroup_reclaim_cookie *reclaim)
{ {
struct mem_cgroup *memcg = NULL; struct mem_cgroup *memcg = NULL;
int id = 0; struct mem_cgroup *last_visited = NULL;
if (mem_cgroup_disabled()) if (mem_cgroup_disabled())
return NULL; return NULL;
...@@ -1098,7 +1100,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, ...@@ -1098,7 +1100,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
root = root_mem_cgroup; root = root_mem_cgroup;
if (prev && !reclaim) if (prev && !reclaim)
id = css_id(&prev->css); last_visited = prev;
if (!root->use_hierarchy && root != root_mem_cgroup) { if (!root->use_hierarchy && root != root_mem_cgroup) {
if (prev) if (prev)
...@@ -1106,9 +1108,10 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, ...@@ -1106,9 +1108,10 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
return root; return root;
} }
rcu_read_lock();
while (!memcg) { while (!memcg) {
struct mem_cgroup_reclaim_iter *uninitialized_var(iter); struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
struct cgroup_subsys_state *css; struct cgroup_subsys_state *css = NULL;
if (reclaim) { if (reclaim) {
int nid = zone_to_nid(reclaim->zone); int nid = zone_to_nid(reclaim->zone);
...@@ -1117,31 +1120,74 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, ...@@ -1117,31 +1120,74 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
mz = mem_cgroup_zoneinfo(root, nid, zid); mz = mem_cgroup_zoneinfo(root, nid, zid);
iter = &mz->reclaim_iter[reclaim->priority]; iter = &mz->reclaim_iter[reclaim->priority];
if (prev && reclaim->generation != iter->generation) spin_lock(&iter->iter_lock);
goto out_css_put; last_visited = iter->last_visited;
id = iter->position; 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_unlock;
}
} }
rcu_read_lock(); /*
css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id); * Root is not visited by cgroup iterators so it needs an
if (css) { * explicit visit.
if (css == &root->css || css_tryget(css)) */
memcg = mem_cgroup_from_css(css); if (!last_visited) {
} else css = &root->css;
id = 0; } else {
rcu_read_unlock(); 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) { 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;
if (!css) if (!css)
iter->generation++; iter->generation++;
else if (!prev && memcg) else if (!prev && memcg)
reclaim->generation = iter->generation; reclaim->generation = iter->generation;
spin_unlock(&iter->iter_lock);
} else if (css && !memcg) {
last_visited = mem_cgroup_from_css(css);
} }
if (prev && !css) if (prev && !css)
goto out_css_put; goto out_unlock;
} }
out_unlock:
rcu_read_unlock();
out_css_put: out_css_put:
if (prev && prev != root) if (prev && prev != root)
css_put(&prev->css); css_put(&prev->css);
...@@ -5929,8 +5975,12 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) ...@@ -5929,8 +5975,12 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
return 1; return 1;
for (zone = 0; zone < MAX_NR_ZONES; zone++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) {
int prio;
mz = &pn->zoneinfo[zone]; mz = &pn->zoneinfo[zone];
lruvec_init(&mz->lruvec); lruvec_init(&mz->lruvec);
for (prio = 0; prio < DEF_PRIORITY + 1; prio++)
spin_lock_init(&mz->reclaim_iter[prio].iter_lock);
mz->usage_in_excess = 0; mz->usage_in_excess = 0;
mz->on_tree = false; mz->on_tree = false;
mz->memcg = memcg; mz->memcg = memcg;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment