md: use READ_ONCE() for lockless reads of sb_flags
PATCH v2 1/1 md: use READ_ONCE() for lockless reads of sb_flags
From: Chen Cheng <[email protected]>
sb_flags is checked without a lock in md, raid1, raid5, and raid10. KCSAN reports these reads as data races.
The write side uses atomic bit ops.
The read side still has plain loads in a few places.
Use READ_ONCE() for the lockless reads of sb_flags.
v1 -> v2:
- Add lock-free read paths for other array levels.
KCSAN reports #1:
======================================
BUG: KCSAN: data-race in md_check_recovery / md_write_start
write (marked) to 0xffff8e39f897f030 of 8 bytes by task 248146 on cpu 8:
md_write_start+0x5dd/0x910 raid10_make_request+0x9b/0x1080 md_handle_request+0x4a2/0xa40 [........]
read to 0xffff8e39f897f030 of 8 bytes by task 250445 on cpu 11:
md_check_recovery+0x574/0x900 raid10d+0xb7/0x2950 [........]
KCSAN reports #2:
======================================
BUG: KCSAN: data-race in md_check_recovery / md_write_start
write (marked) to 0xffff8e39e953f030 of 8 bytes by task 540091 on cpu 11:
md_write_start+0x5dd/0x910 raid1_make_request+0x141/0x1990 [........]
read to 0xffff8e39e953f030 of 8 bytes by task 580822 on cpu 0:
md_check_recovery+0x574/0x900 raid1d+0xcc/0x3840 [........]
value changed: 0x0000000000000002 -> 0x0000000000000006
KCSAN reports #3:
======================================
BUG: KCSAN: data-race in md_check_recovery / md_do_sync.cold
write (marked) to 0xffff8e39e9404030 of 8 bytes by task 492473 on cpu 6:
md_do_sync.cold+0x3f6/0x1686 [........]
read to 0xffff8e39e9404030 of 8 bytes by task 492402 on cpu 3:
md_check_recovery+0x16d/0x900 raid1d+0xcc/0x3840 [........]
value changed: 0x0000000000000000 -> 0x0000000000000002
KCSAN reports #4:
======================================
BUG: KCSAN: data-race in md_do_sync.cold / raid5d
write (marked) to 0xffff8e39c35cb030 of 8 bytes by task 192196 on cpu 10:
md_do_sync.cold+0x3f6/0x1686 md_thread+0x15a/0x2d0 [........]
read to 0xffff8e39c35cb030 of 8 bytes by task 190759 on cpu 5:
raid5d+0x7f9/0xba0 md_thread+0x15a/0x2d0 [........]
value changed: 0x0000000000000000 -> 0x0000000000000002
--- drivers/md/md.c | 8 ++++---- drivers/md/raid1.c | 2 +- drivers/md/raid10.c | 4 ++-- drivers/md/raid5.c | 7 ++++--- 4 files changed, 11 insertions(+), 10 deletions(-)
drivers/md/md.c +4 -4
@@ -6830,11 +6830,11 @@ int md_run(struct mddev *mddev)* via sysfs - until a lack of spares is confirmed. */ set_bit (MD_RECOVERY_RECOVER , &mddev->recovery);set_bit (MD_RECOVERY_NEEDED , &mddev->recovery); -if (mddev->sb_flags) +if (READ_ONCE (mddev->sb_flags))md_update_sb (mddev,0 );if (IS_ENABLED (CONFIG_MD_BITMAP ) && !mddev->bitmap_info.file && !mddev->bitmap_info.offset)md_bitmap_set_none (mddev);
@@ -7024,11 +7024,11 @@ static void __md_stop_writes(struct mddev *mddev) mddev->bitmap_ops->flush (mddev); }if (md_is_rdwr (mddev) && ((!mddev->in_sync && !mddev_is_clustered (mddev)) || - mddev->sb_flags)) { +READ_ONCE (mddev->sb_flags))) {/* mark array as shutdown cleanly */ if (!mddev_is_clustered (mddev)) mddev->in_sync =1 ;md_update_sb (mddev,1 ); }
@@ -10294,11 +10294,11 @@ static bool md_should_do_recovery(struct mddev *mddev)/* * MD_SB_CHANGE_PENDING indicates that the array is switching from clean to * active, and no action is needed for now. * All other MD_SB_* flags require to update the superblock. */ -if (mddev->sb_flags & ~ (1 <<MD_SB_CHANGE_PENDING )) +if (READ_ONCE (mddev->sb_flags) & ~ (1 <<MD_SB_CHANGE_PENDING ))return true;/* * If the array is not using external metadata and there has been no data * written for some time, then the array's status needs to be set to
@@ -10423,11 +10423,11 @@ void md_check_recovery(struct mddev *mddev)spin_lock (&mddev->lock);set_in_sync (mddev);spin_unlock (&mddev->lock); } -if (mddev->sb_flags) +if (READ_ONCE (mddev->sb_flags))md_update_sb (mddev,0 );/* * Never start a new sync thread if MD_RECOVERY_RUNNING is * still set.
drivers/md/raid1.c +1 -1
@@ -2738,11 +2738,11 @@ static void raid1d(struct md_thread *thread)handle_read_error (conf, r1_bio); else WARN_ON_ONCE(1);cond_resched (); -if (mddev->sb_flags & ~(1 <<MD_SB_CHANGE_PENDING )) +if (READ_ONCE (mddev->sb_flags) & ~(1 <<MD_SB_CHANGE_PENDING ))md_check_recovery (mddev); }blk_finish_plug (&plug); }
drivers/md/raid10.c +2 -2
@@ -3030,11 +3030,11 @@ static void raid10d(struct md_thread *thread)handle_read_error (mddev, r10_bio); else WARN_ON_ONCE(1);cond_resched (); -if (mddev->sb_flags & ~(1 <<MD_SB_CHANGE_PENDING )) +if (READ_ONCE (mddev->sb_flags) & ~(1 <<MD_SB_CHANGE_PENDING ))md_check_recovery (mddev); }blk_finish_plug (&plug); }
@@ -4698,11 +4698,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,else mddev->curr_resync_completed = conf->reshape_progress; conf->reshape_checkpoint = jiffies;set_bit (MD_SB_CHANGE_DEVS , &mddev->sb_flags);md_wakeup_thread (mddev->thread); -wait_event (mddev->sb_wait, mddev->sb_flags ==0 || +wait_event (mddev->sb_wait,READ_ONCE (mddev->sb_flags) ==0 ||test_bit (MD_RECOVERY_INTR , &mddev->recovery));if (test_bit (MD_RECOVERY_INTR , &mddev->recovery)) {allow_barrier (conf);return sectors_done; }
drivers/md/raid5.c +4 -3
@@ -1219,11 +1219,11 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)break ;if (bad <0 ) {set_bit (BlockedBadBlocks, &rdev->flags);if (!conf->mddev->external && - conf->mddev->sb_flags) { +READ_ONCE (conf->mddev->sb_flags)) {/* It is very unlikely, but we might * still need to write out the * bad block log - better give it * a chance*/ md_check_recovery (conf->mddev);
@@ -6469,11 +6469,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk rdev->recovery_offset = sector_nr; conf->reshape_checkpoint = jiffies;set_bit (MD_SB_CHANGE_DEVS , &mddev->sb_flags);md_wakeup_thread (mddev->thread); -wait_event (mddev->sb_wait, mddev->sb_flags ==0 || +wait_event (mddev->sb_wait,READ_ONCE (mddev->sb_flags) ==0 ||test_bit (MD_RECOVERY_INTR , &mddev->recovery));if (test_bit (MD_RECOVERY_INTR , &mddev->recovery))return 0 ;spin_lock_irq (&conf->device_lock); conf->reshape_safe = mddev->reshape_position;
@@ -6913,11 +6913,12 @@ static void raid5d(struct md_thread *thread) conf->temp_inactive_list);if (!batch_size && !released)break ; handled += batch_size; -if (mddev->sb_flags & ~(1 <<MD_SB_CHANGE_PENDING )) { +if (READ_ONCE (mddev->sb_flags) & + ~(1 <<MD_SB_CHANGE_PENDING )) {spin_unlock_irq (&conf->device_lock);md_check_recovery (mddev);spin_lock_irq (&conf->device_lock); } }
Signature · 1 line
2.54.0
[email protected]
AI reviewThank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [Low] Lockless plain reads of mddev->recovery will cause KCSAN data race warnings, similar to the ones fixed for sb_flags. --
commit f286787fa23a14cb6ec022eb99574f7a85f9957d
Author: Chen Cheng <[email protected]>
md: use READ_ONCE() for lockless reads of sb_flags
This patch adds READ_ONCE() annotations to lockless reads of mddev->sb_flags across md, raid1, raid5, and raid10. It aims to fix KCSAN data race warnings caused by concurrent set_bit() operations on sb_flags.
drivers/md/md.c int md_run(struct mddev *mddev) · line 6833
Quoted 7 lines
drivers/md/md.c +0
-0@@ -6832,7 +6832,7 @@ int md_run(struct mddev *mddev)set_bit (MD_RECOVERY_RECOVER , &mddev->recovery);set_bit (MD_RECOVERY_NEEDED , &mddev->recovery);
[Severity: Low]
This is a pre-existing issue, but since this patch targets KCSAN warnings for atomic bitmasks, could plain lockless reads of mddev->recovery trigger similar data races?
There are places where mddev->recovery is read without locks and without READ_ONCE(), potentially causing KCSAN noise against set_bit() updates:
drivers/md/md.c:md_sync_action() {
...
unsigned long recovery = mddev->recovery;
...
}drivers/md/md.c:set_bitmap_file() {
...
if (mddev->recovery || mddev->sync_thread)
...
}drivers/md/md.c:update_array_info() {
...
if (mddev->recovery || mddev->sync_thread) {
...
}Should READ_ONCE() also be applied to these reads of mddev->recovery to provide a more complete fix?
Quoted 3 lines
drivers/md/md.c +1
-1-if (mddev->sb_flags) +if (READ_ONCE (mddev->sb_flags))md_update_sb (mddev,0 );
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
Quoted 49 lines · 在 2026/6/23 19:25, [email protected] 写道:
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [Low] Lockless plain reads ofmddev->recoverywill cause KCSAN data race warnings, similar to the ones fixed forsb_flags. --commit
f286787fa23a14cb6ec022eb99574f7a85f9957d
Author: Chen Cheng <[email protected]>md: use
READ_ONCE()for lockless reads ofsb_flagsThis patch adds
READ_ONCE()annotations to lockless reads ofmddev->sb_flagsacross md, raid1, raid5, and raid10. It aims to fix KCSAN data race warnings caused by concurrentset_bit()operations onsb_flags.drivers/md/md.c int md_run(struct mddev *mddev) · line 6833
Quoted 7 lines
drivers/md/md.c +0
-0@@ -6832,7 +6832,7 @@ int md_run(struct mddev *mddev)set_bit (MD_RECOVERY_RECOVER , &mddev->recovery);set_bit (MD_RECOVERY_NEEDED , &mddev->recovery);[Severity: Low]
This is a pre-existing issue, but since this patch targets KCSAN warnings for atomic bitmasks, could plain lockless reads ofmddev->recoverytrigger similar data races?There are places where
mddev->recoveryis read without locks and withoutREAD_ONCE(), potentially causing KCSAN noise againstset_bit()updates:drivers/md/md.c:md_sync_action() { ... unsigned long recovery = mddev->recovery; ... }drivers/md/md.c:set_bitmap_file() { ... if (mddev->recovery || mddev->sync_thread) ... }drivers/md/md.c:update_array_info() { ... if (mddev->recovery || mddev->sync_thread) { ... }
Quoted 7 lines
Should
READ_ONCE()also be applied to these reads ofmddev->recoveryto provide a more complete fix?drivers/md/md.c int md_run(struct mddev *mddev) · line 6836
Quoted 3 lines
drivers/md/md.c +1
-1-if (mddev->sb_flags) +if (READ_ONCE (mddev->sb_flags))md_update_sb (mddev,0 );
Only md_sync_action() do lockless u64 plain read, READ_ONCE could be safer in here ..
yu kuai
maintainerHi,
Quoted 116 lines · Chen Cheng
From: Chen Cheng <[email protected]>
sb_flagsis checked without a lock in md, raid1, raid5, and raid10. KCSAN reports these reads as data races.The write side uses atomic bit ops.
The read side still has plain loads in a few places.Use
READ_ONCE()for the lockless reads ofsb_flags.v1 -> v2:
- Add lock-free read paths for other array levels.KCSAN reports #1:
======================================BUG: KCSAN: data-race in md_check_recovery / md_write_startwrite (marked) to
0xffff8e39f897f030of 8 bytes by task 248146 on cpu 8:md_write_start+0x5dd/0x910 raid10_make_request+0x9b/0x1080 md_handle_request+0x4a2/0xa40 [........]read to
0xffff8e39f897f030of 8 bytes by task 250445 on cpu 11:md_check_recovery+0x574/0x900 raid10d+0xb7/0x2950 [........]KCSAN reports #2:
======================================BUG: KCSAN: data-race in md_check_recovery / md_write_startwrite (marked) to
0xffff8e39e953f030of 8 bytes by task 540091 on cpu 11:md_write_start+0x5dd/0x910 raid1_make_request+0x141/0x1990 [........]read to
0xffff8e39e953f030of 8 bytes by task 580822 on cpu 0:md_check_recovery+0x574/0x900 raid1d+0xcc/0x3840 [........]value changed:
0x0000000000000002->0x0000000000000006KCSAN reports #3:
======================================BUG: KCSAN: data-race in md_check_recovery / md_do_sync.coldwrite (marked) to
0xffff8e39e9404030of 8 bytes by task 492473 on cpu 6:md_do_sync.cold+0x3f6/0x1686 [........]read to
0xffff8e39e9404030of 8 bytes by task 492402 on cpu 3:md_check_recovery+0x16d/0x900 raid1d+0xcc/0x3840 [........]value changed:
0x0000000000000000->0x0000000000000002KCSAN reports #4:
======================================BUG: KCSAN: data-race in md_do_sync.cold / raid5dwrite (marked) to
0xffff8e39c35cb030of 8 bytes by task 192196 on cpu 10:md_do_sync.cold+0x3f6/0x1686 md_thread+0x15a/0x2d0 [........]read to
0xffff8e39c35cb030of 8 bytes by task 190759 on cpu 5:raid5d+0x7f9/0xba0 md_thread+0x15a/0x2d0 [........]value changed:
0x0000000000000000->0x0000000000000002Signed-off-by Chen Cheng <[email protected]>--- drivers/md/md.c | 8 ++++---- drivers/md/raid1.c | 2 +- drivers/md/raid10.c | 4 ++-- drivers/md/raid5.c | 7 ++++--- 4 files changed, 11 insertions(+), 10 deletions(-)drivers/md/md.c +2
-2@@ -6830,11 +6830,11 @@ int md_run(struct mddev *mddev)* via sysfs - until a lack of spares is confirmed. */ set_bit (MD_RECOVERY_RECOVER , &mddev->recovery);set_bit (MD_RECOVERY_NEEDED , &mddev->recovery); -if (mddev->sb_flags) +if (READ_ONCE (mddev->sb_flags))md_update_sb (mddev,0 );if (IS_ENABLED (CONFIG_MD_BITMAP ) && !mddev->bitmap_info.file && !mddev->bitmap_info.offset)md_bitmap_set_none (mddev);@@ -7024,11 +7024,11 @@ static void __md_stop_writes(struct mddev *mddev) mddev->bitmap_ops->flush (mddev); }if (md_is_rdwr (mddev) && ((!mddev->in_sync && !mddev_is_clustered (mddev)) || - mddev->sb_flags)) { +READ_ONCE (mddev->sb_flags))) {/* mark array as shutdown cleanly */ if (!mddev_is_clustered (mddev)) mddev->in_sync =1 ;md_update_sb (mddev,1 ); }
drivers/md/md.c static bool md_should_do_recovery(struct mddev *mddev) · line 10299
Quoted 7 lines
drivers/md/md.c +1
-1@@ -10294,11 +10294,11 @@ static bool md_should_do_recovery(struct mddev *mddev)/* * MD_SB_CHANGE_PENDING indicates that the array is switching from clean to * active, and no action is needed for now. * All other MD_SB_* flags require to update the superblock. */ -if (mddev->sb_flags & ~ (1 <<MD_SB_CHANGE_PENDING )) +if (READ_ONCE (mddev->sb_flags) & ~ (1 <<MD_SB_CHANGE_PENDING ))
Since this line is involved, please also fix checkpatch warning as well, like what you did below.
Quoted 109 lines
drivers/md/md.c +1
-1return true;/* * If the array is not using external metadata and there has been no data * written for some time, then the array's status needs to be set to @@ -10423,11 +10423,11 @@ void md_check_recovery(struct mddev *mddev)spin_lock (&mddev->lock);set_in_sync (mddev);spin_unlock (&mddev->lock); } -if (mddev->sb_flags) +if (READ_ONCE (mddev->sb_flags))md_update_sb (mddev,0 );/* * Never start a new sync thread if MD_RECOVERY_RUNNING is * still set. drivers/md/raid1.c +1
-1@@ -2738,11 +2738,11 @@ static void raid1d(struct md_thread *thread)handle_read_error (conf, r1_bio); else WARN_ON_ONCE(1);cond_resched (); -if (mddev->sb_flags & ~(1 <<MD_SB_CHANGE_PENDING )) +if (READ_ONCE (mddev->sb_flags) & ~(1 <<MD_SB_CHANGE_PENDING ))md_check_recovery (mddev); }blk_finish_plug (&plug); }drivers/md/raid10.c +2
-2@@ -3030,11 +3030,11 @@ static void raid10d(struct md_thread *thread)handle_read_error (mddev, r10_bio); else WARN_ON_ONCE(1);cond_resched (); -if (mddev->sb_flags & ~(1 <<MD_SB_CHANGE_PENDING )) +if (READ_ONCE (mddev->sb_flags) & ~(1 <<MD_SB_CHANGE_PENDING ))md_check_recovery (mddev); }blk_finish_plug (&plug); }@@ -4698,11 +4698,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,else mddev->curr_resync_completed = conf->reshape_progress; conf->reshape_checkpoint = jiffies;set_bit (MD_SB_CHANGE_DEVS , &mddev->sb_flags);md_wakeup_thread (mddev->thread); -wait_event (mddev->sb_wait, mddev->sb_flags ==0 || +wait_event (mddev->sb_wait,READ_ONCE (mddev->sb_flags) ==0 ||test_bit (MD_RECOVERY_INTR , &mddev->recovery));if (test_bit (MD_RECOVERY_INTR , &mddev->recovery)) {allow_barrier (conf);return sectors_done; }drivers/md/raid5.c +4
-3@@ -1219,11 +1219,11 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)break ;if (bad <0 ) {set_bit (BlockedBadBlocks, &rdev->flags);if (!conf->mddev->external && - conf->mddev->sb_flags) { +READ_ONCE (conf->mddev->sb_flags)) {/* It is very unlikely, but we might * still need to write out the * bad block log - better give it * a chance*/ md_check_recovery (conf->mddev);@@ -6469,11 +6469,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk rdev->recovery_offset = sector_nr; conf->reshape_checkpoint = jiffies;set_bit (MD_SB_CHANGE_DEVS , &mddev->sb_flags);md_wakeup_thread (mddev->thread); -wait_event (mddev->sb_wait, mddev->sb_flags ==0 || +wait_event (mddev->sb_wait,READ_ONCE (mddev->sb_flags) ==0 ||test_bit (MD_RECOVERY_INTR , &mddev->recovery));if (test_bit (MD_RECOVERY_INTR , &mddev->recovery))return 0 ;spin_lock_irq (&conf->device_lock); conf->reshape_safe = mddev->reshape_position;@@ -6913,11 +6913,12 @@ static void raid5d(struct md_thread *thread) conf->temp_inactive_list);if (!batch_size && !released)break ; handled += batch_size; -if (mddev->sb_flags & ~(1 <<MD_SB_CHANGE_PENDING )) { +if (READ_ONCE (mddev->sb_flags) & + ~(1 <<MD_SB_CHANGE_PENDING )) {spin_unlock_irq (&conf->device_lock);md_check_recovery (mddev);spin_lock_irq (&conf->device_lock); } }
Signature · 2 lines
Thanks, Kuai