[PATCH v3 5/6] md/raid1: Handle bio_split() errors

John Garry posted 6 patches 1 month ago
There is a newer version of this series
[PATCH v3 5/6] md/raid1: Handle bio_split() errors
Posted by John Garry 1 month ago
Add proper bio_split() error handling. For any error, call
raid_end_bio_io() and return.

For the case of an in the write path, we need to undo the increment in
the rdev pending count and NULLify the r1_bio->bios[] pointers.

For read path failure, we need to undo rdev pending count increment from
the earlier read_balance() call.

Signed-off-by: John Garry <john.g.garry@oracle.com>
---
 drivers/md/raid1.c | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6c9d24203f39..7e023e9303c8 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1322,7 +1322,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	const enum req_op op = bio_op(bio);
 	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
-	int rdisk;
+	int rdisk, error;
 	bool r1bio_existed = !!r1_bio;
 
 	/*
@@ -1383,6 +1383,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      gfp, &conf->bio_split);
+
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		submit_bio_noacct(bio);
 		bio = split;
@@ -1410,6 +1415,13 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_private = r1_bio;
 	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
 	submit_bio_noacct(read_bio);
+	return;
+
+err_handle:
+	atomic_dec(&mirror->rdev->nr_pending);
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R1BIO_Uptodate, &r1_bio->state);
+	raid_end_bio_io(r1_bio);
 }
 
 static void raid1_write_request(struct mddev *mddev, struct bio *bio,
@@ -1417,7 +1429,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
-	int i, disks;
+	int i, disks, k, error;
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
 	int first_clone;
@@ -1576,6 +1588,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      GFP_NOIO, &conf->bio_split);
+
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		submit_bio_noacct(bio);
 		bio = split;
@@ -1660,6 +1677,18 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	/* In case raid1d snuck in to freeze_array */
 	wake_up_barrier(conf);
+	return;
+err_handle:
+	for (k = 0; k < i; k++) {
+		if (r1_bio->bios[k]) {
+			rdev_dec_pending(conf->mirrors[k].rdev, mddev);
+			r1_bio->bios[k] = NULL;
+		}
+	}
+
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R1BIO_Uptodate, &r1_bio->state);
+	raid_end_bio_io(r1_bio);
 }
 
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
-- 
2.31.1
Re: [PATCH v3 5/6] md/raid1: Handle bio_split() errors
Posted by Hannes Reinecke 3 weeks, 6 days ago
On 10/31/24 10:59, John Garry wrote:
> Add proper bio_split() error handling. For any error, call
> raid_end_bio_io() and return.
> 
> For the case of an in the write path, we need to undo the increment in
> the rdev pending count and NULLify the r1_bio->bios[] pointers.
> 
> For read path failure, we need to undo rdev pending count increment from
> the earlier read_balance() call.
> 
> Signed-off-by: John Garry <john.g.garry@oracle.com>
> ---
>   drivers/md/raid1.c | 33 +++++++++++++++++++++++++++++++--
>   1 file changed, 31 insertions(+), 2 deletions(-)
> 
Reviewed-by: Hannes Reinecke <hare@suse.de>

Cheers,

Hannes
-- 
Dr. Hannes Reinecke                  Kernel Storage Architect
hare@suse.de                                +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich
Re: [PATCH v3 5/6] md/raid1: Handle bio_split() errors
Posted by Yu Kuai 1 month ago
在 2024/10/31 17:59, John Garry 写道:
> Add proper bio_split() error handling. For any error, call
> raid_end_bio_io() and return.
> 
> For the case of an in the write path, we need to undo the increment in
> the rdev pending count and NULLify the r1_bio->bios[] pointers.
> 
> For read path failure, we need to undo rdev pending count increment from
> the earlier read_balance() call.
> 
> Signed-off-by: John Garry <john.g.garry@oracle.com>
> ---
>   drivers/md/raid1.c | 33 +++++++++++++++++++++++++++++++--
>   1 file changed, 31 insertions(+), 2 deletions(-)
> 
LGTM
Reviewed-by: Yu Kuai <yukuai3@huawei.com>

> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index 6c9d24203f39..7e023e9303c8 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -1322,7 +1322,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
>   	const enum req_op op = bio_op(bio);
>   	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
>   	int max_sectors;
> -	int rdisk;
> +	int rdisk, error;
>   	bool r1bio_existed = !!r1_bio;
>   
>   	/*
> @@ -1383,6 +1383,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
>   	if (max_sectors < bio_sectors(bio)) {
>   		struct bio *split = bio_split(bio, max_sectors,
>   					      gfp, &conf->bio_split);
> +
> +		if (IS_ERR(split)) {
> +			error = PTR_ERR(split);
> +			goto err_handle;
> +		}
>   		bio_chain(split, bio);
>   		submit_bio_noacct(bio);
>   		bio = split;
> @@ -1410,6 +1415,13 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
>   	read_bio->bi_private = r1_bio;
>   	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
>   	submit_bio_noacct(read_bio);
> +	return;
> +
> +err_handle:
> +	atomic_dec(&mirror->rdev->nr_pending);
> +	bio->bi_status = errno_to_blk_status(error);
> +	set_bit(R1BIO_Uptodate, &r1_bio->state);
> +	raid_end_bio_io(r1_bio);
>   }
>   
>   static void raid1_write_request(struct mddev *mddev, struct bio *bio,
> @@ -1417,7 +1429,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
>   {
>   	struct r1conf *conf = mddev->private;
>   	struct r1bio *r1_bio;
> -	int i, disks;
> +	int i, disks, k, error;
>   	unsigned long flags;
>   	struct md_rdev *blocked_rdev;
>   	int first_clone;
> @@ -1576,6 +1588,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
>   	if (max_sectors < bio_sectors(bio)) {
>   		struct bio *split = bio_split(bio, max_sectors,
>   					      GFP_NOIO, &conf->bio_split);
> +
> +		if (IS_ERR(split)) {
> +			error = PTR_ERR(split);
> +			goto err_handle;
> +		}
>   		bio_chain(split, bio);
>   		submit_bio_noacct(bio);
>   		bio = split;
> @@ -1660,6 +1677,18 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
>   
>   	/* In case raid1d snuck in to freeze_array */
>   	wake_up_barrier(conf);
> +	return;
> +err_handle:
> +	for (k = 0; k < i; k++) {
> +		if (r1_bio->bios[k]) {
> +			rdev_dec_pending(conf->mirrors[k].rdev, mddev);
> +			r1_bio->bios[k] = NULL;
> +		}
> +	}
> +
> +	bio->bi_status = errno_to_blk_status(error);
> +	set_bit(R1BIO_Uptodate, &r1_bio->state);
> +	raid_end_bio_io(r1_bio);
>   }
>   
>   static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
>