cgroup: protect modifications to cgroup_idr with cgroup_mutex

commit 0ab02ca8f887908152d1a96db5130fc661d36a1e upstream.

Setup cgroupfs like this:
  # mount -t cgroup -o cpuacct xxx /cgroup
  # mkdir /cgroup/sub1
  # mkdir /cgroup/sub2

Then run these two commands:
  # for ((; ;)) { mkdir /cgroup/sub1/tmp && rmdir /mnt/sub1/tmp; } &
  # for ((; ;)) { mkdir /cgroup/sub2/tmp && rmdir /mnt/sub2/tmp; } &

After seconds you may see this warning:

------------[ cut here ]------------
WARNING: CPU: 1 PID: 25243 at lib/idr.c:527 sub_remove+0x87/0x1b0()
idr_remove called for id=6 which is not allocated.
...
Call Trace:
 [<ffffffff8156063c>] dump_stack+0x7a/0x96
 [<ffffffff810591ac>] warn_slowpath_common+0x8c/0xc0
 [<ffffffff81059296>] warn_slowpath_fmt+0x46/0x50
 [<ffffffff81300aa7>] sub_remove+0x87/0x1b0
 [<ffffffff810f3f02>] ? css_killed_work_fn+0x32/0x1b0
 [<ffffffff81300bf5>] idr_remove+0x25/0xd0
 [<ffffffff810f2bab>] cgroup_destroy_css_killed+0x5b/0xc0
 [<ffffffff810f4000>] css_killed_work_fn+0x130/0x1b0
 [<ffffffff8107cdbc>] process_one_work+0x26c/0x550
 [<ffffffff8107eefe>] worker_thread+0x12e/0x3b0
 [<ffffffff81085f96>] kthread+0xe6/0xf0
 [<ffffffff81570bac>] ret_from_fork+0x7c/0xb0
---[ end trace 2d1577ec10cf80d0 ]---

It's because allocating/removing cgroup ID is not properly synchronized.

The bug was introduced when we converted cgroup_ida to cgroup_idr.
While synchronization is already done inside ida_simple_{get,remove}(),
users are responsible for concurrent calls to idr_{alloc,remove}().

[mhocko@suse.cz: ported to 3.12]
Fixes: 4e96ee8e981b ("cgroup: convert cgroup_ida to cgroup_idr")
Cc: <stable@vger.kernel.org> #3.12+
Reported-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3561d30..7b3a119 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -169,6 +169,8 @@ struct cgroup {
         *
         * The ID of the root cgroup is always 0, and a new cgroup
         * will be assigned with a smallest available ID.
+        *
+        * Allocating/Removing ID must be protected by cgroup_mutex.
         */
        int id;
 

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c4f8bc7..1c204fd 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4410,16 +4410,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
        rcu_assign_pointer(cgrp->name, name);
 
        /*
-        * Temporarily set the pointer to NULL, so idr_find() won't return
-        * a half-baked cgroup.
-        */
-       cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
-       if (cgrp->id < 0) {
-               err = -ENOMEM;
-               goto err_free_name;
-       }
-
-       /*
         * Only live parents can have children.  Note that the liveliness
         * check isn't strictly necessary because cgroup_mkdir() and
         * cgroup_rmdir() are fully synchronized by i_mutex; however, do it
@@ -4428,7 +4418,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
         */
        if (!cgroup_lock_live_group(parent)) {
                err = -ENODEV;
-               goto err_free_id;
+               goto err_free_name;
        }
 
        /* Grab a reference on the superblock so the hierarchy doesn't
@@ -4438,6 +4428,16 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
         * fs */
        atomic_inc(&sb->s_active);
 
+       /*
+        * Temporarily set the pointer to NULL, so idr_find() won't return
+        * a half-baked cgroup.
+        */
+       cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+       if (cgrp->id < 0) {
+               err = -ENOMEM;
+               goto err_unlock;
+       }
+
        init_cgroup_housekeeping(cgrp);
 
        dentry->d_fsdata = cgrp;
@@ -4544,11 +4544,11 @@ err_free_all:
                        ss->css_free(css);
                }
        }
+       idr_remove(&root->cgroup_idr, cgrp->id);
+err_unlock:
        mutex_unlock(&cgroup_mutex);
        /* Release the reference count that we took on the superblock */
        deactivate_super(sb);
-err_free_id:
-       idr_remove(&root->cgroup_idr, cgrp->id);
 err_free_name:
        kfree(rcu_dereference_raw(cgrp->name));
 err_free_cgrp: