Offering: HULK hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBKHTZ ------------------------ When writing to a RAID1 array where all member disks have bad sectors at the target location, the bitmap update is skipped because all bios[] are NULL, leading to bitmap counter inconsistency. This can cause subsequent I/O operations to hang while waiting for bitmap counter to reach the expected value. Fix this by updating the bitmap when all member disks have bad sectors. Fixes: 1f68f0c4b677 ("md/raid1: avoid writing to known-bad blocks on known-bad drives.") Signed-off-by: Zheng Qixing <zhengqixing@huawei.com> --- drivers/md/raid1.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ee3826db193d..62e73ac32a3b 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1551,6 +1551,13 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, } } + /* + * Corresponding to md_bitmap_endwrite() from close_write(), in the case + * io range from all member disks are badblocks. + */ + if (first_clone) + md_bitmap_startwrite(bitmap, r1_bio->sector, r1_bio->sectors, 0); + r1_bio_write_done(r1_bio); /* In case raid1d snuck in to freeze_array */ -- 2.39.2