summaryrefslogtreecommitdiff
path: root/block/blk-sysfs.c
diff options
context:
space:
mode:
authorBart Van Assche <bvanassche@acm.org>2014-12-09 18:57:48 +0300
committerJens Axboe <axboe@fb.com>2014-12-09 19:07:13 +0300
commit45a9c9d909b24c6ad0e28a7946e7486e73010319 (patch)
tree7317f2beee89119a5e2906dea3c6601e11ae1d61 /block/blk-sysfs.c
parent19c66e59ce57e7b181625cbb408d48eb10837763 (diff)
downloadlinux-45a9c9d909b24c6ad0e28a7946e7486e73010319.tar.xz
blk-mq: Fix a use-after-free
blk-mq users are allowed to free the memory request_queue.tag_set points at after blk_cleanup_queue() has finished but before blk_release_queue() has started. This can happen e.g. in the SCSI core. The SCSI core namely embeds the tag_set structure in a SCSI host structure. The SCSI host structure is freed by scsi_host_dev_release(). This function is called after blk_cleanup_queue() finished but can be called before blk_release_queue(). This means that it is not safe to access request_queue.tag_set from inside blk_release_queue(). Hence remove the blk_sync_queue() call from blk_release_queue(). This call is not necessary - outstanding requests must have finished before blk_release_queue() is called. Additionally, move the blk_mq_free_queue() call from blk_release_queue() to blk_cleanup_queue() to avoid that struct request_queue.tag_set gets accessed after it has been freed. This patch avoids that the following kernel oops can be triggered when deleting a SCSI host for which scsi-mq was enabled: Call Trace: [<ffffffff8109a7c4>] lock_acquire+0xc4/0x270 [<ffffffff814ce111>] mutex_lock_nested+0x61/0x380 [<ffffffff812575f0>] blk_mq_free_queue+0x30/0x180 [<ffffffff8124d654>] blk_release_queue+0x84/0xd0 [<ffffffff8126c29b>] kobject_cleanup+0x7b/0x1a0 [<ffffffff8126c140>] kobject_put+0x30/0x70 [<ffffffff81245895>] blk_put_queue+0x15/0x20 [<ffffffff8125c409>] disk_release+0x99/0xd0 [<ffffffff8133d056>] device_release+0x36/0xb0 [<ffffffff8126c29b>] kobject_cleanup+0x7b/0x1a0 [<ffffffff8126c140>] kobject_put+0x30/0x70 [<ffffffff8125a78a>] put_disk+0x1a/0x20 [<ffffffff811d4cb5>] __blkdev_put+0x135/0x1b0 [<ffffffff811d56a0>] blkdev_put+0x50/0x160 [<ffffffff81199eb4>] kill_block_super+0x44/0x70 [<ffffffff8119a2a4>] deactivate_locked_super+0x44/0x60 [<ffffffff8119a87e>] deactivate_super+0x4e/0x70 [<ffffffff811b9833>] cleanup_mnt+0x43/0x90 [<ffffffff811b98d2>] __cleanup_mnt+0x12/0x20 [<ffffffff8107252c>] task_work_run+0xac/0xe0 [<ffffffff81002c01>] do_notify_resume+0x61/0xa0 [<ffffffff814d2c58>] int_signal+0x12/0x17 Signed-off-by: Bart Van Assche <bvanassche@acm.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Robert Elliott <elliott@hp.com> Cc: Ming Lei <ming.lei@canonical.com> Cc: Alexander Gordeev <agordeev@redhat.com> Cc: <stable@vger.kernel.org> # v3.13+ Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'block/blk-sysfs.c')
-rw-r--r--block/blk-sysfs.c12
1 files changed, 4 insertions, 8 deletions
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 1fac43408911..935ea2aa0730 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -492,17 +492,15 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head)
* Currently, its primary task it to free all the &struct request
* structures that were allocated to the queue and the queue itself.
*
- * Caveat:
- * Hopefully the low level driver will have finished any
- * outstanding requests first...
+ * Note:
+ * The low level driver must have finished any outstanding requests first
+ * via blk_cleanup_queue().
**/
static void blk_release_queue(struct kobject *kobj)
{
struct request_queue *q =
container_of(kobj, struct request_queue, kobj);
- blk_sync_queue(q);
-
blkcg_exit_queue(q);
if (q->elevator) {
@@ -517,9 +515,7 @@ static void blk_release_queue(struct kobject *kobj)
if (q->queue_tags)
__blk_queue_free_tags(q);
- if (q->mq_ops)
- blk_mq_free_queue(q);
- else
+ if (!q->mq_ops)
blk_free_flush_queue(q->fq);
blk_trace_shutdown(q);