Re: [PATCH v2] md: use READ_ONCE() for lockless reads of sb_flags

Hi,

在 2026/6/23 19:16, Chen Cheng 写道:
> 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
>
> Signed-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(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 096bb64e87bd..c5c50640b684 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -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))

Since this line is involved, please also fix checkpatch warning as well, like what
you did below.

>   		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.
> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index 29b58583e381..bd6808656edb 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -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);
>   }
>   
> diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
> index adaf9e432e25..3ffa5a19964d 100644
> --- a/drivers/md/raid10.c
> +++ b/drivers/md/raid10.c
> @@ -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;
>   		}
> diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> index ded6a69f7795..cb58b4353995 100644
> --- a/drivers/md/raid5.c
> +++ b/drivers/md/raid5.c
> @@ -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);
>   		}
>   	}

-- 
Thanks,
Kuai