cgroup: delay the clearing of cgrp->kn->priv

Run these two scripts concurrently:

    for ((; ;))
    {
        mkdir /cgroup/sub
        rmdir /cgroup/sub
    }

    for ((; ;))
    {
        echo $$ > /cgroup/sub/cgroup.procs
        echo $$ > /cgroup/cgroup.procs
    }

A kernel bug will be triggered:

BUG: unable to handle kernel NULL pointer dereference at 00000038
IP: [<c10bbd69>] cgroup_put+0x9/0x80
...
Call Trace:
 [<c10bbe19>] cgroup_kn_unlock+0x39/0x50
 [<c10bbe91>] cgroup_kn_lock_live+0x61/0x70
 [<c10be3c1>] __cgroup_procs_write.isra.26+0x51/0x230
 [<c10be5b2>] cgroup_tasks_write+0x12/0x20
 [<c10bb7b0>] cgroup_file_write+0x40/0x130
 [<c11aee71>] kernfs_fop_write+0xd1/0x160
 [<c1148e58>] vfs_write+0x98/0x1e0
 [<c114934d>] SyS_write+0x4d/0xa0
 [<c16f656b>] sysenter_do_call+0x12/0x12

We clear cgrp->kn->priv in the end of cgroup_rmdir(), but another
concurrent thread can access kn->priv after the clearing.

We should move the clearing to css_release_work_fn(). At that time
no one is holding reference to the cgroup and no one can gain a new
reference to access it.

v2:
- move RCU_INIT_POINTER() into the else block. (Tejun)
- remove the cgroup_parent() check. (Tejun)
- update the comment in css_tryget_online_from_dir().

Cc: <stable@vger.kernel.org> # 3.15+
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Zefan Li <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 50b94113f4f7a69f8c3be4b8297beffde67254e4..bf30076664ca4a281af97873b8b5f172cdb7bcbb 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4396,6 +4396,15 @@ static void css_release_work_fn(struct work_struct *work)
                /* cgroup release path */
                cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
                cgrp->id = -1;
+
+               /*
+                * There are two control paths which try to determine
+                * cgroup from dentry without going through kernfs -
+                * cgroupstats_build() and css_tryget_online_from_dir().
+                * Those are supported by RCU protecting clearing of
+                * cgrp->kn->priv backpointer.
+                */
+               RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
        }
 
        mutex_unlock(&cgroup_mutex);
@@ -4834,16 +4843,6 @@ static int cgroup_rmdir(struct kernfs_node *kn)
 
        cgroup_kn_unlock(kn);
 
-       /*
-        * There are two control paths which try to determine cgroup from
-        * dentry without going through kernfs - cgroupstats_build() and
-        * css_tryget_online_from_dir().  Those are supported by RCU
-        * protecting clearing of cgrp->kn->priv backpointer, which should
-        * happen after all files under it have been removed.
-        */
-       if (!ret)
-               RCU_INIT_POINTER(*(void __rcu __force **)&kn->priv, NULL);
-
        cgroup_put(cgrp);
        return ret;
 }
@@ -5430,7 +5429,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
        /*
         * This path doesn't originate from kernfs and @kn could already
         * have been or be removed at any point.  @kn->priv is RCU
-        * protected for this access.  See cgroup_rmdir() for details.
+        * protected for this access.  See css_release_work_fn() for details.
         */
        cgrp = rcu_dereference(kn->priv);
        if (cgrp)