Hi,
在 2024/10/28 23:27, 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 panding count and NULLify the r1_bio->bios[] pointers.
Signed-off-by: John Garry <john.g.garry@xxxxxxxxxx>
---
drivers/md/raid1.c | 32 ++++++++++++++++++++++++++++++--
1 file changed, 30 insertions(+), 2 deletions(-)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6c9d24203f39..a10018282629 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 +1415,12 @@ 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:
+ 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 +1428,7 @@ 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 +1587,11 @@ 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 +1676,18 @@ 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);
Looks good that error code is passed to orig bio. However,
I really think badblocks should be handled somehow, it just doesn't make
sense to return IO error to filesystems or user if one underlying disk
contain BB, while others are good.
Or is it guaranteed that IO error by atomic write won't hurt anyone,
user will handle this error and retry with non atomic write?
Thanks,
Kuai
}
static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
