4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ming Lei <ming....@redhat.com>


[ Upstream commit fb350e0ad99359768e1e80b4784692031ec340e4 ]

In both elevator_switch_mq() and blk_mq_update_nr_hw_queues(), sched tags
can be allocated, and q->nr_hw_queue is used, and race is inevitable, for
example: blk_mq_init_sched() may trigger use-after-free on hctx, which is
freed in blk_mq_realloc_hw_ctxs() when nr_hw_queues is decreased.

This patch fixes the race be holding q->sysfs_lock.

Reviewed-by: Christoph Hellwig <h...@lst.de>
Reported-by: Yi Zhang <yi.zh...@redhat.com>
Tested-by: Yi Zhang <yi.zh...@redhat.com>
Signed-off-by: Ming Lei <ming....@redhat.com>
Signed-off-by: Jens Axboe <ax...@kernel.dk>
Signed-off-by: Sasha Levin <alexander.le...@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
 block/blk-mq.c |    4 ++++
 1 file changed, 4 insertions(+)

--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2314,6 +2314,9 @@ static void blk_mq_realloc_hw_ctxs(struc
        struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
        blk_mq_sysfs_unregister(q);
+
+       /* protect against switching io scheduler  */
+       mutex_lock(&q->sysfs_lock);
        for (i = 0; i < set->nr_hw_queues; i++) {
                int node;
 
@@ -2358,6 +2361,7 @@ static void blk_mq_realloc_hw_ctxs(struc
                }
        }
        q->nr_hw_queues = i;
+       mutex_unlock(&q->sysfs_lock);
        blk_mq_sysfs_register(q);
 }
 


Reply via email to