diff mbox series

[3/3] md/raid10: fix io loss while replacement replace rdev

Message ID 20230522115449.2203939-4-linan666@huaweicloud.com
State New
Headers
Series raid10 bugfix |

Commit Message

Li Nan May 22, 2023, 11:54 a.m. UTC 
  From: Li Nan <linan122@huawei.com>

When we remove a disk which has replacement, first set rdev to NULL
and then set replacement to rdev, finally set replacement to NULL (see
raid10_remove_disk()). If io is submitted during the same time, it might
read both rdev and replacement as NULL, and io will not be submitted.

  rdev -> NULL
			read rdev
  replacement -> NULL
			read replacement

Fix it by reading replacement first and rdev later, meanwhile, use smp_mb()
to prevent memory reordering.

Fixes: 475b0321a4df ("md/raid10: writes should get directed to replacement as well as original.")
Signed-off-by: Li Nan <linan122@huawei.com>
---
 drivers/md/raid10.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

Comments

Yu Kuai May 22, 2023, 1:03 p.m. UTC | #1 
Hi,

在 2023/05/22 19:54, linan666@huaweicloud.com 写道:
> From: Li Nan <linan122@huawei.com>
> 
> When we remove a disk which has replacement, first set rdev to NULL
> and then set replacement to rdev, finally set replacement to NULL (see
> raid10_remove_disk()). If io is submitted during the same time, it might
> read both rdev and replacement as NULL, and io will not be submitted.
> 
>    rdev -> NULL
> 			read rdev
>    replacement -> NULL
> 			read replacement
> 
> Fix it by reading replacement first and rdev later, meanwhile, use smp_mb()
> to prevent memory reordering.

Looks good, feel free to add:

Reviewed-by: Yu Kuai <yukuai3@huawei.com>
> 
> Fixes: 475b0321a4df ("md/raid10: writes should get directed to replacement as well as original.")
> Signed-off-by: Li Nan <linan122@huawei.com>
> ---
>   drivers/md/raid10.c | 22 ++++++++++++++++++----
>   1 file changed, 18 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
> index 70cc87c7ee57..25a5a7b1e95c 100644
> --- a/drivers/md/raid10.c
> +++ b/drivers/md/raid10.c
> @@ -779,8 +779,16 @@ static struct md_rdev *read_balance(struct r10conf *conf,
>   		disk = r10_bio->devs[slot].devnum;
>   		rdev = rcu_dereference(conf->mirrors[disk].replacement);
>   		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
> -		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
> +		    r10_bio->devs[slot].addr + sectors >
> +		    rdev->recovery_offset) {
> +			/*
> +			 * Read replacement first to prevent reading both rdev
> +			 * and replacement as NULL during replacement replace
> +			 * rdev.
> +			 */
> +			smp_mb();
>   			rdev = rcu_dereference(conf->mirrors[disk].rdev);
> +		    }
>   		if (rdev == NULL ||
>   		    test_bit(Faulty, &rdev->flags))
>   			continue;
> @@ -1479,9 +1487,15 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
>   
>   	for (i = 0;  i < conf->copies; i++) {
>   		int d = r10_bio->devs[i].devnum;
> -		struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
> -		struct md_rdev *rrdev = rcu_dereference(
> -			conf->mirrors[d].replacement);
> +		struct md_rdev *rdev, *rrdev;
> +
> +		rrdev = rcu_dereference(conf->mirrors[d].replacement);
> +		/*
> +		 * Read replacement first to Prevent reading both rdev and
> +		 * replacement as NULL during replacement replace rdev.
> +		 */
> +		smp_mb();
> +		rdev = rcu_dereference(conf->mirrors[d].rdev);
>   		if (rdev == rrdev)
>   			rrdev = NULL;
>   		if (rdev && (test_bit(Faulty, &rdev->flags)))
>
diff mbox series

Patch

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 70cc87c7ee57..25a5a7b1e95c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -779,8 +779,16 @@  static struct md_rdev *read_balance(struct r10conf *conf,
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
-		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
+		    r10_bio->devs[slot].addr + sectors >
+		    rdev->recovery_offset) {
+			/*
+			 * Read replacement first to prevent reading both rdev
+			 * and replacement as NULL during replacement replace
+			 * rdev.
+			 */
+			smp_mb();
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
+		    }
 		if (rdev == NULL ||
 		    test_bit(Faulty, &rdev->flags))
 			continue;
@@ -1479,9 +1487,15 @@  static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 
 	for (i = 0;  i < conf->copies; i++) {
 		int d = r10_bio->devs[i].devnum;
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev);
-		struct md_rdev *rrdev = rcu_dereference(
-			conf->mirrors[d].replacement);
+		struct md_rdev *rdev, *rrdev;
+
+		rrdev = rcu_dereference(conf->mirrors[d].replacement);
+		/*
+		 * Read replacement first to Prevent reading both rdev and
+		 * replacement as NULL during replacement replace rdev.
+		 */
+		smp_mb();
+		rdev = rcu_dereference(conf->mirrors[d].rdev);
 		if (rdev == rrdev)
 			rrdev = NULL;
 		if (rdev && (test_bit(Faulty, &rdev->flags)))