md: unlock mddev before reap sync_thread in action_store
Subsystems (2)
PATCH v2 1/1 md: unlock mddev before reap sync_thread in action_store
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.
---
V2 changes:
1. add set_bit(MD_RECOVERY_INTR, &mddev->recovery) before unregister sync thread
And I didn't find regression with this version after run mdadm tests.
drivers/md/dm-raid.c | 1 + drivers/md/md.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-)
drivers/md/dm-raid.c +1 -0
@@ -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)
drivers/md/md.c +17 -2
@@ -4830,6 +4830,19 @@ 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); +set_bit (MD_RECOVERY_INTR , &mddev->recovery); +md_unregister_thread (&mddev->sync_thread); +mddev_lock_nointr (mddev); +/* +* set RECOVERY_INTR again and restore reshape +* position in case others changed them after +* got lock, eg, reshape_position_store and +* md_check_recovery. +*/ + mddev->reshape_position = save_rp;set_bit (MD_RECOVERY_INTR , &mddev->recovery);md_reap_sync_thread (mddev); }
@@ -6197,6 +6210,7 @@ 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 +9317,7 @@ 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 +9353,7 @@ 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 +9433,7 @@ 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) {
Signature · 1 line
2.31.1
Song Liu
maintainerQuoted 45 lines · Guoqing Jiang
Since the bug which commit
8b48ec23cc51a("md: don't unregistersync_threadwithreconfig_mutexheld") fixed is related withaction_storepath, other callers which reapsync_threaddidn't need to be changed.Let's pull
md_unregister_threadfrommd_reap_sync_thread, then fix previous bug with belows.1. unlock mddev before
md_reap_sync_threadinaction_store.
2. savereshape_positionbefore unlock, then restore it to ensure position not changed accidentally by others.Signed-off-by Guoqing Jiang <[email protected]>---
V2 changes:
1. addset_bit(MD_RECOVERY_INTR, &mddev->recovery)before unregister sync threadAnd I didn't find regression with this version after run mdadm tests.
drivers/md/dm-raid.c | 1 + drivers/md/md.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-)drivers/md/dm-raid.c +1
-0@@ -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)drivers/md/md.c +2
-0@@ -4830,6 +4830,19 @@ 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; +
drivers/md/md.c action_store(struct mddev *mddev, const char *page, size_t len) · line 4844
Quoted 10 lines
drivers/md/md.c +10
-0+mddev_unlock (mddev); +set_bit (MD_RECOVERY_INTR , &mddev->recovery); +md_unregister_thread (&mddev->sync_thread); +mddev_lock_nointr (mddev); +/* +* set RECOVERY_INTR again and restore reshape +* position in case others changed them after +* got lock, eg, reshape_position_store and +* md_check_recovery. +*/
Hmm.. do we really need to handle reshape_position changed case? What would break if we don't?
Thanks,
Song
Quoted 41 lines
drivers/md/md.c +5
-3+ mddev->reshape_position = save_rp;set_bit (MD_RECOVERY_INTR , &mddev->recovery);md_reap_sync_thread (mddev); }@@ -6197,6 +6210,7 @@ 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 +9317,7 @@ 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 +9353,7 @@ 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 +9433,7 @@ 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) { --2.31.1
Quoted 49 lines · Song Liu
Quoted 48 lines · Guoqing Jiang
Since the bug which commit
8b48ec23cc51a("md: don't unregistersync_threadwithreconfig_mutexheld") fixed is related withaction_storepath, other callers which reapsync_threaddidn't need to be changed.Let's pull
md_unregister_threadfrommd_reap_sync_thread, then fix previous bug with belows.1. unlock mddev before
md_reap_sync_threadinaction_store.
2. savereshape_positionbefore unlock, then restore it to ensure position not changed accidentally by others.Signed-off-by Guoqing Jiang <[email protected]>---
V2 changes:
1. addset_bit(MD_RECOVERY_INTR, &mddev->recovery)before unregister sync threadAnd I didn't find regression with this version after run mdadm tests.
drivers/md/dm-raid.c | 1 + drivers/md/md.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-)drivers/md/dm-raid.c +1
-0@@ -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)drivers/md/md.c +6
-0@@ -4830,6 +4830,19 @@ 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); +set_bit (MD_RECOVERY_INTR , &mddev->recovery); +md_unregister_thread (&mddev->sync_thread); +mddev_lock_nointr (mddev);
Quoted 8 lines
drivers/md/md.c action_store(struct mddev *mddev, const char *page, size_t len) · line 4844
Quoted 6 lines
drivers/md/md.c +6
-0+/* +* set RECOVERY_INTR again and restore reshape +* position in case others changed them after +* got lock, eg, reshape_position_store and +* md_check_recovery. +*/ Hmm.. do we really need to handle
reshape_positionchanged case? What would break if we don't?
I want to make the behavior consistent with previous code, and reshape_position_store can change it as said in comment.
Anyway, I didn't see regression with mdadm test with or without setting reshape_position, so it is a more conservative way to avoid potential issue. I will remove it if you think it is not necessary.
Thanks,
Guoqing
Song Liu
maintainerQuoted 62 lines · Guoqing Jiang
Quoted 49 lines · Song Liu
Quoted 48 lines · Guoqing Jiang
Since the bug which commit
8b48ec23cc51a("md: don't unregistersync_threadwithreconfig_mutexheld") fixed is related withaction_storepath, other callers which reapsync_threaddidn't need to be changed.Let's pull
md_unregister_threadfrommd_reap_sync_thread, then fix previous bug with belows.1. unlock mddev before
md_reap_sync_threadinaction_store.
2. savereshape_positionbefore unlock, then restore it to ensure position not changed accidentally by others.Signed-off-by Guoqing Jiang <[email protected]>---
V2 changes:
1. addset_bit(MD_RECOVERY_INTR, &mddev->recovery)before unregister sync threadAnd I didn't find regression with this version after run mdadm tests.
drivers/md/dm-raid.c | 1 + drivers/md/md.c | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-)drivers/md/dm-raid.c +1
-0@@ -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)drivers/md/md.c +6
-0@@ -4830,6 +4830,19 @@ 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); +set_bit (MD_RECOVERY_INTR , &mddev->recovery); +md_unregister_thread (&mddev->sync_thread); +mddev_lock_nointr (mddev);Quoted 8 lines
drivers/md/md.c action_store(struct mddev *mddev, const char *page, size_t len) · line 4844
Quoted 6 lines
drivers/md/md.c +6
-0+/* +* set RECOVERY_INTR again and restore reshape +* position in case others changed them after +* got lock, eg, reshape_position_store and +* md_check_recovery. +*/ Hmm.. do we really need to handle
reshape_positionchanged case? What would break if we don't?
Quoted 3 lines
I want to make the behavior consistent with previous code, and
reshape_position_store
can change it as said in comment.
I see. I will apply the patch as-is.
Thanks,
Song
Quoted 6 lines
Anyway, I didn't see regression with mdadm test with or without setting
reshape_position,
so it is a more conservative way to avoid potential issue. I will remove it if you think it is
not necessary.