From: Guoqing Jiang <guoqing.jiang@linux.dev>
To: song@kernel.org
Cc: buczek@molgen.mpg.de, logang@deltatee.com, linux-raid@vger.kernel.org
Subject: [PATCH 1/2] Revert "md: don't unregister sync_thread with reconfig_mutex held"
Date: Tue, 7 Jun 2022 10:03:56 +0800 [thread overview]
Message-ID: <20220607020357.14831-2-guoqing.jiang@linux.dev> (raw)
In-Reply-To: <20220607020357.14831-1-guoqing.jiang@linux.dev>
The 07reshape5intr test is broke because of below path.
md_reap_sync_thread
-> mddev_unlock
-> md_unregister_thread(&mddev->sync_thread)
And md_check_recovery is triggered by,
mddev_unlock -> md_wakeup_thread(mddev->thread)
then mddev->reshape_position is set to MaxSector in raid5_finish_reshape
since MD_RECOVERY_INTR is cleared in md_check_recovery, which means
feature_map is not set with MD_FEATURE_RESHAPE_ACTIVE and superblock's
reshape_position can't be updated accordingly.
Fixes: 8b48ec23cc51a ("md: don't unregister sync_thread with reconfig_mutex held")
Reported-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
---
drivers/md/dm-raid.c | 2 +-
drivers/md/md.c | 14 +++++---------
drivers/md/md.h | 2 +-
3 files changed, 7 insertions(+), 11 deletions(-)
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 5e41fbae3f6b..9526ccbedafb 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3725,7 +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_reap_sync_thread(mddev, false);
+ md_reap_sync_thread(mddev);
}
} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
return -EBUSY;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5c8efef13881..2e83a19e3aba 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4831,7 +4831,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
}
mddev_unlock(mddev);
}
@@ -6197,7 +6197,7 @@ 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_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
}
del_timer_sync(&mddev->safemode_timer);
@@ -9303,7 +9303,7 @@ void md_check_recovery(struct mddev *mddev)
* ->spare_active and clear saved_raid_disk
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
@@ -9338,7 +9338,7 @@ void md_check_recovery(struct mddev *mddev)
goto unlock;
}
if (mddev->sync_thread) {
- md_reap_sync_thread(mddev, true);
+ md_reap_sync_thread(mddev);
goto unlock;
}
/* Set RUNNING before clearing NEEDED to avoid
@@ -9411,18 +9411,14 @@ void md_check_recovery(struct mddev *mddev)
}
EXPORT_SYMBOL(md_check_recovery);
-void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held)
+void md_reap_sync_thread(struct mddev *mddev)
{
struct md_rdev *rdev;
sector_t old_dev_sectors = mddev->dev_sectors;
bool is_reshaped = false;
- if (reconfig_mutex_held)
- mddev_unlock(mddev);
/* resync has finished, collect result */
md_unregister_thread(&mddev->sync_thread);
- if (reconfig_mutex_held)
- mddev_lock_nointr(mddev);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
mddev->degraded != mddev->raid_disks) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 82465a4b1588..ba8224fd68e9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -719,7 +719,7 @@ extern struct md_thread *md_register_thread(
extern void md_unregister_thread(struct md_thread **threadp);
extern void md_wakeup_thread(struct md_thread *thread);
extern void md_check_recovery(struct mddev *mddev);
-extern void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held);
+extern void md_reap_sync_thread(struct mddev *mddev);
extern int mddev_init_writes_pending(struct mddev *mddev);
extern bool md_write_start(struct mddev *mddev, struct bio *bi);
extern void md_write_inc(struct mddev *mddev, struct bio *bi);
--
2.31.1
next prev parent reply other threads:[~2022-06-07 2:04 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-07 2:03 [PATCH 0/2] md: regression fix Guoqing Jiang
2022-06-07 2:03 ` Guoqing Jiang [this message]
2022-06-07 2:03 ` [PATCH 2/2] md: unlock mddev before reap sync_thread in action_store Guoqing Jiang
2022-06-07 9:46 ` Guoqing Jiang
2022-06-07 22:59 ` Song Liu
2022-06-07 23:45 ` Guoqing Jiang
2022-06-08 17:23 ` Logan Gunthorpe
2022-06-09 7:20 ` Guoqing Jiang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220607020357.14831-2-guoqing.jiang@linux.dev \
--to=guoqing.jiang@linux.dev \
--cc=buczek@molgen.mpg.de \
--cc=linux-raid@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=song@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).