md/dm-raid: don't call md_reap_sync_thread() directly

Currently md_reap_sync_thread() is called from raid_message() directly
without holding 'reconfig_mutex', this is definitely unsafe because
md_reap_sync_thread() can change many fields that is protected by
'reconfig_mutex'.

However, hold 'reconfig_mutex' here is still problematic because this
will cause deadlock, for example, commit 130443d60b1b ("md: refactor
idle/frozen_sync_thread() to fix deadlock").

Fix this problem by using stop_sync_thread() to unregister sync_thread,
like md/raid did.

Fixes: be83651f0050 ("DM RAID: Add message/status support for changing sync action")
Cc: stable@vger.kernel.org # v6.7+
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Xiao Ni <xni@redhat.com>
Acked-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240305072306.2562024-7-yukuai1@huaweicloud.com

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index e2d7a73c0f87446544f6a6c81b45141ae0fc2fd9..47c4b1b6e532a6e8c049eabbed6c930cdc013949 100644 (file)
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3719,6 +3719,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 {
        struct raid_set *rs = ti->private;
        struct mddev *mddev = &rs->md;
+       int ret = 0;
 
        if (!mddev->pers || !mddev->pers->sync_request)
                return -EINVAL;
@@ -3726,17 +3727,24 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
        if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags))
                return -EBUSY;
 
-       if (!strcasecmp(argv[0], "frozen"))
-               set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-       else
-               clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+       if (!strcasecmp(argv[0], "frozen")) {
+               ret = mddev_lock(mddev);
+               if (ret)
+                       return ret;
 
-       if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
-               if (mddev->sync_thread) {
-                       set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-                       md_reap_sync_thread(mddev);
-               }
-       } else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
+               md_frozen_sync_thread(mddev);
+               mddev_unlock(mddev);
+       } else if (!strcasecmp(argv[0], "idle")) {
+               ret = mddev_lock(mddev);
+               if (ret)
+                       return ret;
+
+               md_idle_sync_thread(mddev);
+               mddev_unlock(mddev);
+       }
+
+       clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+       if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
                return -EBUSY;
        else if (!strcasecmp(argv[0], "resync"))
                ; /* MD_RECOVERY_NEEDED set below */