Pls hold on, I will verify it with latest kernel. Thanks, Guoqing On 6/7/22 10:03 AM, Guoqing Jiang wrote:
Since the bug which commit 8b48ec23cc51a ("md: don't unregister sync_thread with reconfig_mutex held") fixed is related with action_store path, other callers which reap sync_thread didn't need to be changed. Let's pull md_unregister_thread from md_reap_sync_thread, then fix previous bug with belows. 1. unlock mddev before md_reap_sync_thread in action_store. 2. save reshape_position before unlock, then restore it to ensure position not changed accidentally by others. Signed-off-by: Guoqing Jiang <guoqing.jiang@xxxxxxxxx> --- drivers/md/dm-raid.c | 1 + drivers/md/md.c | 12 ++++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 9526ccbedafb..d43b8075c055 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3725,6 +3725,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) { if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); } } else if (decipher_sync_action(mddev, mddev->recovery) != st_idle) diff --git a/drivers/md/md.c b/drivers/md/md.c index 2e83a19e3aba..4d70672f8ea8 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4830,6 +4830,12 @@ action_store(struct mddev *mddev, const char *page, size_t len) if (work_pending(&mddev->del_work)) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { + sector_t save_rp = mddev->reshape_position; + + mddev_unlock(mddev); + md_unregister_thread(&mddev->sync_thread); + mddev_lock_nointr(mddev); + mddev->reshape_position = save_rp; set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_reap_sync_thread(mddev); } @@ -6197,6 +6203,7 @@ static void __md_stop_writes(struct mddev *mddev) flush_workqueue(md_misc_wq); if (mddev->sync_thread) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); }@@ -9303,6 +9310,7 @@ void md_check_recovery(struct mddev *mddev)* ->spare_active and clear saved_raid_disk */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); @@ -9338,6 +9346,7 @@ void md_check_recovery(struct mddev *mddev) goto unlock; } if (mddev->sync_thread) { + md_unregister_thread(&mddev->sync_thread); md_reap_sync_thread(mddev); goto unlock; } @@ -9417,8 +9426,7 @@ void md_reap_sync_thread(struct mddev *mddev) sector_t old_dev_sectors = mddev->dev_sectors; bool is_reshaped = false;- /* resync has finished, collect result */- md_unregister_thread(&mddev->sync_thread); + /* sync_thread should be unregistered, collect result */ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && mddev->degraded != mddev->raid_disks) {
