summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLi Zefan <lizefan@huawei.com>2014-06-30 11:50:59 +0800
committerTejun Heo <tj@kernel.org>2014-06-30 10:16:26 -0400
commit3a32bd72d77058d768dbb38183ad517f720dd1bc (patch)
treedc67b70a50e1dc649b059113bb8303f420192eca
parent4e26445faad366d67d7723622bf6a60a6f0f5993 (diff)
downloadop-kernel-dev-3a32bd72d77058d768dbb38183ad517f720dd1bc.zip
op-kernel-dev-3a32bd72d77058d768dbb38183ad517f720dd1bc.tar.gz
cgroup: fix a race between cgroup_mount() and cgroup_kill_sb()
We've converted cgroup to kernfs so cgroup won't be intertwined with vfs objects and locking, but there are dark areas. Run two instances of this script concurrently: for ((; ;)) { mount -t cgroup -o cpuacct xxx /cgroup umount /cgroup } After a while, I saw two mount processes were stuck at retrying, because they were waiting for a subsystem to become free, but the root associated with this subsystem never got freed. This can happen, if thread A is in the process of killing superblock but hasn't called percpu_ref_kill(), and at this time thread B is mounting the same cgroup root and finds the root in the root list and performs percpu_ref_try_get(). To fix this, we try to increase both the refcnt of the superblock and the percpu refcnt of cgroup root. v2: - we should try to get both the superblock refcnt and cgroup_root refcnt, because cgroup_root may have no superblock assosiated with it. - adjust/add comments. tj: Updated comments. Renamed @sb to @pinned_sb. Cc: <stable@vger.kernel.org> # 3.15 Signed-off-by: Li Zefan <lizefan@huawei.com> Signed-off-by: Tejun Heo <tj@kernel.org>
-rw-r--r--kernel/cgroup.c33
1 files changed, 26 insertions, 7 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 6406866..70776ae 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1648,6 +1648,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data)
{
+ struct super_block *pinned_sb = NULL;
struct cgroup_subsys *ss;
struct cgroup_root *root;
struct cgroup_sb_opts opts;
@@ -1740,15 +1741,23 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
}
/*
- * A root's lifetime is governed by its root cgroup.
- * tryget_live failure indicate that the root is being
- * destroyed. Wait for destruction to complete so that the
- * subsystems are free. We can use wait_queue for the wait
- * but this path is super cold. Let's just sleep for a bit
- * and retry.
+ * We want to reuse @root whose lifetime is governed by its
+ * ->cgrp. Let's check whether @root is alive and keep it
+ * that way. As cgroup_kill_sb() can happen anytime, we
+ * want to block it by pinning the sb so that @root doesn't
+ * get killed before mount is complete.
+ *
+ * With the sb pinned, tryget_live can reliably indicate
+ * whether @root can be reused. If it's being killed,
+ * drain it. We can use wait_queue for the wait but this
+ * path is super cold. Let's just sleep a bit and retry.
*/
- if (!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
+ pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
+ if (IS_ERR(pinned_sb) ||
+ !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
mutex_unlock(&cgroup_mutex);
+ if (!IS_ERR_OR_NULL(pinned_sb))
+ deactivate_super(pinned_sb);
msleep(10);
ret = restart_syscall();
goto out_free;
@@ -1793,6 +1802,16 @@ out_free:
CGROUP_SUPER_MAGIC, &new_sb);
if (IS_ERR(dentry) || !new_sb)
cgroup_put(&root->cgrp);
+
+ /*
+ * If @pinned_sb, we're reusing an existing root and holding an
+ * extra ref on its sb. Mount is complete. Put the extra ref.
+ */
+ if (pinned_sb) {
+ WARN_ON(new_sb);
+ deactivate_super(pinned_sb);
+ }
+
return dentry;
}
OpenPOWER on IntegriCloud