summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
authorYu Kuai <yukuai3@huawei.com>2024-03-05 15:23:02 +0800
committerSong Liu <song@kernel.org>2024-03-05 12:53:32 -0800
commit16c4770c75b1223998adbeb7286f9a15c65fba73 (patch)
tree56bf3e69d3aa32dc67ccb57e6300cb1818f312e0 /drivers/md
parent503f9d43790fdd0c6e6ae2f4dd3f70b146ac4159 (diff)
dm-raid: really frozen sync_thread during suspend
1) commit f52f5c71f3d4 ("md: fix stopping sync thread") remove MD_RECOVERY_FROZEN from __md_stop_writes() and doesn't realize that dm-raid relies on __md_stop_writes() to frozen sync_thread indirectly. Fix this problem by adding MD_RECOVERY_FROZEN in md_stop_writes(), and since stop_sync_thread() is only used for dm-raid in this case, also move stop_sync_thread() to md_stop_writes(). 2) The flag MD_RECOVERY_FROZEN doesn't mean that sync thread is frozen, it only prevent new sync_thread to start, and it can't stop the running sync thread; In order to frozen sync_thread, after seting the flag, stop_sync_thread() should be used. 3) The flag MD_RECOVERY_FROZEN doesn't mean that writes are stopped, use it as condition for md_stop_writes() in raid_postsuspend() doesn't look correct. Consider that reentrant stop_sync_thread() do nothing, always call md_stop_writes() in raid_postsuspend(). 4) raid_message can set/clear the flag MD_RECOVERY_FROZEN at anytime, and if MD_RECOVERY_FROZEN is cleared while the array is suspended, new sync_thread can start unexpected. Fix this by disallow raid_message() to change sync_thread status during suspend. Note that after commit f52f5c71f3d4 ("md: fix stopping sync thread"), the test shell/lvconvert-raid-reshape.sh start to hang in stop_sync_thread(), and with previous fixes, the test won't hang there anymore, however, the test will still fail and complain that ext4 is corrupted. And with this patch, the test won't hang due to stop_sync_thread() or fail due to ext4 is corrupted anymore. However, there is still a deadlock related to dm-raid456 that will be fixed in following patches. Reported-by: Mikulas Patocka <mpatocka@redhat.com> Closes: https://lore.kernel.org/all/e5e8afe2-e9a8-49a2-5ab0-958d4065c55e@redhat.com/ Fixes: 1af2048a3e87 ("dm raid: fix deadlock caused by premature md_stop_writes()") Fixes: 9dbd1aa3a81c ("dm raid: add reshaping support to the target") Fixes: f52f5c71f3d4 ("md: fix stopping sync thread") 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/20240305072306.2562024-6-yukuai1@huaweicloud.com
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-raid.c25
-rw-r--r--drivers/md/md.c3
2 files changed, 17 insertions, 11 deletions
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index eb009d6bb03a..e2d7a73c0f87 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3240,11 +3240,12 @@ size_check:
rs->md.ro = 1;
rs->md.in_sync = 1;
- /* Keep array frozen until resume. */
- set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
-
/* Has to be held on running the array */
mddev_suspend_and_lock_nointr(&rs->md);
+
+ /* Keep array frozen until resume. */
+ md_frozen_sync_thread(&rs->md);
+
r = md_run(&rs->md);
rs->md.in_sync = 0; /* Assume already marked dirty */
if (r) {
@@ -3722,6 +3723,9 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
if (!mddev->pers || !mddev->pers->sync_request)
return -EINVAL;
+ 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
@@ -3796,10 +3800,11 @@ static void raid_postsuspend(struct dm_target *ti)
struct raid_set *rs = ti->private;
if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
- /* Writes have to be stopped before suspending to avoid deadlocks. */
- if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
- md_stop_writes(&rs->md);
-
+ /*
+ * sync_thread must be stopped during suspend, and writes have
+ * to be stopped before suspending to avoid deadlocks.
+ */
+ md_stop_writes(&rs->md);
mddev_suspend(&rs->md, false);
}
}
@@ -4012,8 +4017,6 @@ static int raid_preresume(struct dm_target *ti)
}
/* Check for any resize/reshape on @rs and adjust/initiate */
- /* Be prepared for mddev_resume() in raid_resume() */
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
if (mddev->recovery_cp && mddev->recovery_cp < MaxSector) {
set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
mddev->resync_min = mddev->recovery_cp;
@@ -4055,10 +4058,12 @@ static void raid_resume(struct dm_target *ti)
if (mddev->delta_disks < 0)
rs_set_capacity(rs);
+ WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery));
+ WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
mddev_lock_nointr(mddev);
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
mddev->ro = 0;
mddev->in_sync = 0;
+ md_unfrozen_sync_thread(mddev);
mddev_unlock_and_resume(mddev);
}
}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 55ecc05c17c6..167db7744239 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -6364,7 +6364,6 @@ static void md_clean(struct mddev *mddev)
static void __md_stop_writes(struct mddev *mddev)
{
- stop_sync_thread(mddev, true, false);
del_timer_sync(&mddev->safemode_timer);
if (mddev->pers && mddev->pers->quiesce) {
@@ -6389,6 +6388,8 @@ static void __md_stop_writes(struct mddev *mddev)
void md_stop_writes(struct mddev *mddev)
{
mddev_lock_nointr(mddev);
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ stop_sync_thread(mddev, true, false);
__md_stop_writes(mddev);
mddev_unlock(mddev);
}