blk-cgroup: Fix potential deadlock in blk-cgroup

I triggered a lockdep warning as following.

=======================================================
[ INFO: possible circular locking dependency detected ]
2.6.33-rc2 #1
-------------------------------------------------------
test_io_control/7357 is trying to acquire lock:
 (blkio_list_lock){+.+...}, at: [<c053a990>] blkiocg_weight_write+0x82/0x9e

but task is already holding lock:
 (&(&blkcg->lock)->rlock){......}, at: [<c053a949>] blkiocg_weight_write+0x3b/0x9e

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (&(&blkcg->lock)->rlock){......}:
       [<c04583b7>] validate_chain+0x8bc/0xb9c
       [<c0458dba>] __lock_acquire+0x723/0x789
       [<c0458eb0>] lock_acquire+0x90/0xa7
       [<c0692b0a>] _raw_spin_lock_irqsave+0x27/0x5a
       [<c053a4e1>] blkiocg_add_blkio_group+0x1a/0x6d
       [<c053cac7>] cfq_get_queue+0x225/0x3de
       [<c053eec2>] cfq_set_request+0x217/0x42d
       [<c052c8a6>] elv_set_request+0x17/0x26
       [<c0532a0f>] get_request+0x203/0x2c5
       [<c0532ae9>] get_request_wait+0x18/0x10e
       [<c0533470>] __make_request+0x2ba/0x375
       [<c0531985>] generic_make_request+0x28d/0x30f
       [<c0532da7>] submit_bio+0x8a/0x8f
       [<c04d827a>] submit_bh+0xf0/0x10f
       [<c04d91d2>] ll_rw_block+0xc0/0xf9
       [<f86e9705>] ext3_find_entry+0x319/0x544 [ext3]
       [<f86eae58>] ext3_lookup+0x2c/0xb9 [ext3]
       [<c04c3e1b>] do_lookup+0xd3/0x172
       [<c04c56c8>] link_path_walk+0x5fb/0x95c
       [<c04c5a65>] path_walk+0x3c/0x81
       [<c04c5b63>] do_path_lookup+0x21/0x8a
       [<c04c66cc>] do_filp_open+0xf0/0x978
       [<c04c0c7e>] open_exec+0x1b/0xb7
       [<c04c1436>] do_execve+0xbb/0x266
       [<c04081a9>] sys_execve+0x24/0x4a
       [<c04028a2>] ptregs_execve+0x12/0x18

-> #1 (&(&q->__queue_lock)->rlock){..-.-.}:
       [<c04583b7>] validate_chain+0x8bc/0xb9c
       [<c0458dba>] __lock_acquire+0x723/0x789
       [<c0458eb0>] lock_acquire+0x90/0xa7
       [<c0692b0a>] _raw_spin_lock_irqsave+0x27/0x5a
       [<c053dd2a>] cfq_unlink_blkio_group+0x17/0x41
       [<c053a6eb>] blkiocg_destroy+0x72/0xc7
       [<c0467df0>] cgroup_diput+0x4a/0xb2
       [<c04ca473>] dentry_iput+0x93/0xb7
       [<c04ca4b3>] d_kill+0x1c/0x36
       [<c04cb5c5>] dput+0xf5/0xfe
       [<c04c6084>] do_rmdir+0x95/0xbe
       [<c04c60ec>] sys_rmdir+0x10/0x12
       [<c04027cc>] sysenter_do_call+0x12/0x32

-> #0 (blkio_list_lock){+.+...}:
       [<c0458117>] validate_chain+0x61c/0xb9c
       [<c0458dba>] __lock_acquire+0x723/0x789
       [<c0458eb0>] lock_acquire+0x90/0xa7
       [<c06929fd>] _raw_spin_lock+0x1e/0x4e
       [<c053a990>] blkiocg_weight_write+0x82/0x9e
       [<c0467f1e>] cgroup_file_write+0xc6/0x1c0
       [<c04bd2f3>] vfs_write+0x8c/0x116
       [<c04bd7c6>] sys_write+0x3b/0x60
       [<c04027cc>] sysenter_do_call+0x12/0x32

other info that might help us debug this:

1 lock held by test_io_control/7357:
 #0:  (&(&blkcg->lock)->rlock){......}, at: [<c053a949>] blkiocg_weight_write+0x3b/0x9e
stack backtrace:
Pid: 7357, comm: test_io_control Not tainted 2.6.33-rc2 #1
Call Trace:
 [<c045754f>] print_circular_bug+0x91/0x9d
 [<c0458117>] validate_chain+0x61c/0xb9c
 [<c0458dba>] __lock_acquire+0x723/0x789
 [<c0458eb0>] lock_acquire+0x90/0xa7
 [<c053a990>] ? blkiocg_weight_write+0x82/0x9e
 [<c06929fd>] _raw_spin_lock+0x1e/0x4e
 [<c053a990>] ? blkiocg_weight_write+0x82/0x9e
 [<c053a990>] blkiocg_weight_write+0x82/0x9e
 [<c0467f1e>] cgroup_file_write+0xc6/0x1c0
 [<c0454df5>] ? trace_hardirqs_off+0xb/0xd
 [<c044d93a>] ? cpu_clock+0x2e/0x44
 [<c050e6ec>] ? security_file_permission+0xf/0x11
 [<c04bcdda>] ? rw_verify_area+0x8a/0xad
 [<c0467e58>] ? cgroup_file_write+0x0/0x1c0
 [<c04bd2f3>] vfs_write+0x8c/0x116
 [<c04bd7c6>] sys_write+0x3b/0x60
 [<c04027cc>] sysenter_do_call+0x12/0x32

To prevent deadlock, we should take locks as following sequence:

blkio_list_lock -> queue_lock ->  blkcg_lock.

The following patch should fix this bug.

Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1fa2654db0a62c1c3f07b92fb8b33eff473d1b41..e7dbbaf5fb3ee58698b1692508b991da8d38accd 100644 (file)
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -147,16 +147,16 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
                return -EINVAL;
 
        blkcg = cgroup_to_blkio_cgroup(cgroup);
+       spin_lock(&blkio_list_lock);
        spin_lock_irq(&blkcg->lock);
        blkcg->weight = (unsigned int)val;
        hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
-               spin_lock(&blkio_list_lock);
                list_for_each_entry(blkiop, &blkio_list, list)
                        blkiop->ops.blkio_update_group_weight_fn(blkg,
                                        blkcg->weight);
-               spin_unlock(&blkio_list_lock);
        }
        spin_unlock_irq(&blkcg->lock);
+       spin_unlock(&blkio_list_lock);
        return 0;
 }