summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorYu Kuai <yukuai3@huawei.com>2023-05-29 16:20:37 +0300
committerSong Liu <song@kernel.org>2023-07-27 10:13:29 +0300
commitf71209b1f21c838a973d858d9f6f76cd39227733 (patch)
tree1a10f042ff871ffc2ff52774cd289b3f223ab51b /drivers
parent753260ed0b46d2ba0d3d6f68a6a49187bff443e4 (diff)
downloadlinux-f71209b1f21c838a973d858d9f6f76cd39227733.tar.xz
md: enhance checking in md_check_recovery()
For md_check_recovery(): 1) if 'MD_RECOVERY_RUNING' is not set, register new sync_thread. 2) if 'MD_RECOVERY_RUNING' is set: a) if 'MD_RECOVERY_DONE' is not set, don't do anything, wait for md_do_sync() to be done. b) if 'MD_RECOVERY_DONE' is set, unregister sync_thread. Current code expects that sync_thread is not NULL, otherwise new sync_thread will be registered, which will corrupt the array. Make sure md_check_recovery() won't register new sync_thread if 'MD_RECOVERY_RUNING' is still set, and a new WARN_ON_ONCE() is added for the above corruption, Signed-off-by: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Xiao Ni <xni@redhat.com> Signed-off-by: Song Liu <song@kernel.org> Link: https://lore.kernel.org/r/20230529132037.2124527-7-yukuai1@huaweicloud.com
Diffstat (limited to 'drivers')
-rw-r--r--drivers/md/md.c22
1 files changed, 15 insertions, 7 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index e0d8e751a782..320d71537359 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -9388,16 +9388,24 @@ void md_check_recovery(struct mddev *mddev)
if (mddev->sb_flags)
md_update_sb(mddev, 0);
- if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
- !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
- /* resync/recovery still happening */
- clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- goto unlock;
- }
- if (mddev->sync_thread) {
+ /*
+ * Never start a new sync thread if MD_RECOVERY_RUNNING is
+ * still set.
+ */
+ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+ if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
+ /* resync/recovery still happening */
+ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ goto unlock;
+ }
+
+ if (WARN_ON_ONCE(!mddev->sync_thread))
+ goto unlock;
+
md_reap_sync_thread(mddev);
goto unlock;
}
+
/* Set RUNNING before clearing NEEDED to avoid
* any transients in the value of "sync_action".
*/