block: loop: don't hold lo_ctl_mutex in lo_open
The lo_ctl_mutex is held for running all ioctl handlers, and
in some ioctl handlers, ioctl_by_bdev(BLKRRPART) is called for
rereading partitions, which requires bd_mutex.
So it is easy to cause failure because trylock(bd_mutex) may
fail inside blkdev_reread_part(), and follows the lock context:
blkid or other application:
->open()
->mutex_lock(bd_mutex)
->lo_open()
->mutex_lock(lo_ctl_mutex)
losetup(set fd ioctl):
->mutex_lock(lo_ctl_mutex)
->ioctl_by_bdev(BLKRRPART)
->trylock(bd_mutex)
This patch trys to eliminate the ABBA lock dependency by removing
lo_ctl_mutext in lo_open() with the following approach:
1) make lo_refcnt as atomic_t and avoid acquiring lo_ctl_mutex in lo_open():
- for open vs. add/del loop, no any problem because of loop_index_mutex
- freeze request queue during clr_fd, so I/O can't come until
clearing fd is completed, like the effect of holding lo_ctl_mutex
in lo_open
- both open() and release() have been serialized by bd_mutex already
2) don't hold lo_ctl_mutex for decreasing/checking lo_refcnt in
lo_release(), then lo_ctl_mutex is only required for the last release.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1bee523..b3e294e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -831,7 +831,7 @@
* <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
* command to fail with EBUSY.
*/
- if (lo->lo_refcnt > 1) {
+ if (atomic_read(&lo->lo_refcnt) > 1) {
lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
mutex_unlock(&lo->lo_ctl_mutex);
return 0;
@@ -840,6 +840,9 @@
if (filp == NULL)
return -EINVAL;
+ /* freeze request queue during the transition */
+ blk_mq_freeze_queue(lo->lo_queue);
+
spin_lock_irq(&lo->lo_lock);
lo->lo_state = Lo_rundown;
lo->lo_backing_file = NULL;
@@ -871,6 +874,8 @@
lo->lo_state = Lo_unbound;
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
+ blk_mq_unfreeze_queue(lo->lo_queue);
+
if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
ioctl_by_bdev(bdev, BLKRRPART, 0);
lo->lo_flags = 0;
@@ -1330,9 +1335,7 @@
goto out;
}
- mutex_lock(&lo->lo_ctl_mutex);
- lo->lo_refcnt++;
- mutex_unlock(&lo->lo_ctl_mutex);
+ atomic_inc(&lo->lo_refcnt);
out:
mutex_unlock(&loop_index_mutex);
return err;
@@ -1343,11 +1346,10 @@
struct loop_device *lo = disk->private_data;
int err;
+ if (atomic_dec_return(&lo->lo_refcnt))
+ return;
+
mutex_lock(&lo->lo_ctl_mutex);
-
- if (--lo->lo_refcnt)
- goto out;
-
if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) {
/*
* In autoclear mode, stop the loop thread
@@ -1601,6 +1603,7 @@
disk->flags |= GENHD_FL_NO_PART_SCAN;
disk->flags |= GENHD_FL_EXT_DEVT;
mutex_init(&lo->lo_ctl_mutex);
+ atomic_set(&lo->lo_refcnt, 0);
lo->lo_number = i;
spin_lock_init(&lo->lo_lock);
disk->major = LOOP_MAJOR;
@@ -1718,7 +1721,7 @@
mutex_unlock(&lo->lo_ctl_mutex);
break;
}
- if (lo->lo_refcnt > 0) {
+ if (atomic_read(&lo->lo_refcnt) > 0) {
ret = -EBUSY;
mutex_unlock(&lo->lo_ctl_mutex);
break;