Commit
a1d767191096 ("md: use mddev->external to select holder in
export_rdev()") fix the problem that 'claim_rdev' is used for
blkdev_get_by_dev() while 'rdev' is used for blkdev_put().
However, if mddev->external is changed from 0 to 1, then 'rdev' is used
for blkdev_get_by_dev() while 'claim_rdev' is used for blkdev_put(). And
this problem can be reporduced reliably by following:
New file: mdadm/tests/23rdev-lifetime
devname=${dev0##*/}
devt=`cat /sys/block/$devname/dev`
pid=""
runtime=2
clean_up_test() {
pill -9 $pid
echo clear > /sys/block/md0/md/array_state
}
trap 'clean_up_test' EXIT
add_by_sysfs() {
while true; do
echo $devt > /sys/block/md0/md/new_dev
done
}
remove_by_sysfs(){
while true; do
echo remove > /sys/block/md0/md/dev-${devname}/state
done
}
echo md0 > /sys/module/md_mod/parameters/new_array || die "create md0 failed"
add_by_sysfs &
pid="$pid $!"
remove_by_sysfs &
pid="$pid $!"
sleep $runtime
exit 0
Test cmd:
./test --save-logs --logdir=/tmp/ --keep-going --dev=loop --tests=23rdev-lifetime
Test result:
------------[ cut here ]------------
WARNING: CPU: 0 PID: 960 at block/bdev.c:618 blkdev_put+0x27c/0x330
Modules linked in: multipath md_mod loop
CPU: 0 PID: 960 Comm: test Not tainted
6.5.0-rc2-00121-g01e55c376936-dirty #50
RIP: 0010:blkdev_put+0x27c/0x330
Call Trace:
<TASK>
export_rdev.isra.23+0x50/0xa0 [md_mod]
mddev_unlock+0x19d/0x300 [md_mod]
rdev_attr_store+0xec/0x190 [md_mod]
sysfs_kf_write+0x52/0x70
kernfs_fop_write_iter+0x19a/0x2a0
vfs_write+0x3b5/0x770
ksys_write+0x74/0x150
__x64_sys_write+0x22/0x30
do_syscall_64+0x40/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
Fix the problem by recording if 'rdev' is used as holder.
Fixes: a1d767191096 ("md: use mddev->external to select holder in export_rdev()")
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230825025532.1523008-3-yukuai1@huaweicloud.com
if (test_bit(AutoDetected, &rdev->flags))
md_autodetect_dev(rdev->bdev->bd_dev);
#endif
- blkdev_put(rdev->bdev, mddev->external ? &claim_rdev : rdev);
+ blkdev_put(rdev->bdev,
+ test_bit(Holder, &rdev->flags) ? rdev : &claim_rdev);
rdev->bdev = NULL;
kobject_put(&rdev->kobj);
}
static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
{
struct md_rdev *rdev;
+ struct md_rdev *holder;
sector_t size;
int err;
if (err)
goto out_clear_rdev;
+ if (super_format == -2) {
+ holder = &claim_rdev;
+ } else {
+ holder = rdev;
+ set_bit(Holder, &rdev->flags);
+ }
+
rdev->bdev = blkdev_get_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE,
- super_format == -2 ? &claim_rdev : rdev, NULL);
+ holder, NULL);
if (IS_ERR(rdev->bdev)) {
pr_warn("md: could not open device unknown-block(%u,%u).\n",
MAJOR(newdev), MINOR(newdev));
return rdev;
out_blkdev_put:
- blkdev_put(rdev->bdev, super_format == -2 ? &claim_rdev : rdev);
+ blkdev_put(rdev->bdev, holder);
out_clear_rdev:
md_rdev_clear(rdev);
out_free_rdev:
* check if there is collision between raid1
* serial bios.
*/
+ Holder, /* rdev is used as holder while opening
+ * underlying disk exclusively.
+ */
};
static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,