summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMing Lei <ming.lei@redhat.com>2019-09-23 23:12:09 +0800
committerJens Axboe <axboe@kernel.dk>2019-09-26 00:45:51 -0600
commitb89f625e28d44552083f43752f62d8621ded0a04 (patch)
tree473504d2f44f9ec2ff427649a8434b2faccec793
parent284b94be1925dbe035ce5218d8b5c197321262c7 (diff)
block: don't release queue's sysfs lock during switching elevator
cecf5d87ff20 ("block: split .sysfs_lock into two locks") starts to release & acquire sysfs_lock before registering/un-registering elevator queue during switching elevator for avoiding potential deadlock from showing & storing 'queue/iosched' attributes and removing elevator's kobject. Turns out there isn't such deadlock because 'q->sysfs_lock' isn't required in .show & .store of queue/iosched's attributes, and just elevator's sysfs lock is acquired in elv_iosched_store() and elv_iosched_show(). So it is safe to hold queue's sysfs lock when registering/un-registering elevator queue. The biggest issue is that commit cecf5d87ff20 assumes that concurrent write on 'queue/scheduler' can't happen. However, this assumption isn't true, because kernfs_fop_write() only guarantees that concurrent write aren't called on the same open file, but the write could be from different open on the file. So we can't release & re-acquire queue's sysfs lock during switching elevator, otherwise use-after-free on elevator could be triggered. Fixes the issue by not releasing queue's sysfs lock during switching elevator. Fixes: cecf5d87ff20 ("block: split .sysfs_lock into two locks") Cc: Christoph Hellwig <hch@infradead.org> Cc: Hannes Reinecke <hare@suse.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--block/blk-sysfs.c13
-rw-r--r--block/elevator.c31
2 files changed, 5 insertions, 39 deletions
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index b82736c781c5..962fc0c44381 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -989,13 +989,11 @@ int blk_register_queue(struct gendisk *disk)
blk_mq_debugfs_register(q);
}
- /*
- * The flag of QUEUE_FLAG_REGISTERED isn't set yet, so elevator
- * switch won't happen at all.
- */
+ mutex_lock(&q->sysfs_lock);
if (q->elevator) {
ret = elv_register_queue(q, false);
if (ret) {
+ mutex_unlock(&q->sysfs_lock);
mutex_unlock(&q->sysfs_dir_lock);
kobject_del(&q->kobj);
blk_trace_remove_sysfs(dev);
@@ -1005,7 +1003,6 @@ int blk_register_queue(struct gendisk *disk)
has_elevator = true;
}
- mutex_lock(&q->sysfs_lock);
blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
wbt_enable_default(q);
blk_throtl_register_queue(q);
@@ -1062,12 +1059,10 @@ void blk_unregister_queue(struct gendisk *disk)
kobject_del(&q->kobj);
blk_trace_remove_sysfs(disk_to_dev(disk));
- /*
- * q->kobj has been removed, so it is safe to check if elevator
- * exists without holding q->sysfs_lock.
- */
+ mutex_lock(&q->sysfs_lock);
if (q->elevator)
elv_unregister_queue(q);
+ mutex_unlock(&q->sysfs_lock);
mutex_unlock(&q->sysfs_dir_lock);
kobject_put(&disk_to_dev(disk)->kobj);
diff --git a/block/elevator.c b/block/elevator.c
index bba10e83478a..5437059c9261 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -503,9 +503,7 @@ int elv_register_queue(struct request_queue *q, bool uevent)
if (uevent)
kobject_uevent(&e->kobj, KOBJ_ADD);
- mutex_lock(&q->sysfs_lock);
e->registered = 1;
- mutex_unlock(&q->sysfs_lock);
}
return error;
}
@@ -523,11 +521,9 @@ void elv_unregister_queue(struct request_queue *q)
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
- mutex_lock(&q->sysfs_lock);
e->registered = 0;
/* Re-enable throttling in case elevator disabled it */
wbt_enable_default(q);
- mutex_unlock(&q->sysfs_lock);
}
}
@@ -590,32 +586,11 @@ int elevator_switch_mq(struct request_queue *q,
lockdep_assert_held(&q->sysfs_lock);
if (q->elevator) {
- if (q->elevator->registered) {
- mutex_unlock(&q->sysfs_lock);
-
- /*
- * Concurrent elevator switch can't happen becasue
- * sysfs write is always exclusively on same file.
- *
- * Also the elevator queue won't be freed after
- * sysfs_lock is released becasue kobject_del() in
- * blk_unregister_queue() waits for completion of
- * .store & .show on its attributes.
- */
+ if (q->elevator->registered)
elv_unregister_queue(q);
- mutex_lock(&q->sysfs_lock);
- }
ioc_clear_queue(q);
elevator_exit(q, q->elevator);
-
- /*
- * sysfs_lock may be dropped, so re-check if queue is
- * unregistered. If yes, don't switch to new elevator
- * any more
- */
- if (!blk_queue_registered(q))
- return 0;
}
ret = blk_mq_init_sched(q, new_e);
@@ -623,11 +598,7 @@ int elevator_switch_mq(struct request_queue *q,
goto out;
if (new_e) {
- mutex_unlock(&q->sysfs_lock);
-
ret = elv_register_queue(q, true);
-
- mutex_lock(&q->sysfs_lock);
if (ret) {
elevator_exit(q, q->elevator);
goto out;