aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/drivers/md/raid10.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--drivers/md/raid10.c107
1 files changed, 82 insertions, 25 deletions
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 862b1fb71d86..7d7a8a2524dc 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1159,6 +1159,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
int slot = r10_bio->read_slot;
struct md_rdev *err_rdev = NULL;
gfp_t gfp = GFP_NOIO;
+ int error;
if (slot >= 0 && r10_bio->devs[slot].rdev) {
/*
@@ -1206,6 +1207,10 @@ static void raid10_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);
allow_barrier(conf);
submit_bio_noacct(bio);
@@ -1236,6 +1241,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
mddev_trace_remap(mddev, read_bio, r10_bio->sector);
submit_bio_noacct(read_bio);
return;
+err_handle:
+ atomic_dec(&rdev->nr_pending);
+ bio->bi_status = errno_to_blk_status(error);
+ set_bit(R10BIO_Uptodate, &r10_bio->state);
+ raid_end_bio_io(r10_bio);
}
static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
@@ -1245,6 +1255,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
const enum req_op op = bio_op(bio);
const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
const blk_opf_t do_fua = bio->bi_opf & REQ_FUA;
+ const blk_opf_t do_atomic = bio->bi_opf & REQ_ATOMIC;
unsigned long flags;
struct r10conf *conf = mddev->private;
struct md_rdev *rdev;
@@ -1263,7 +1274,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
mbio->bi_iter.bi_sector = (r10_bio->devs[n_copy].addr +
choose_data_offset(r10_bio, rdev));
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_opf = op | do_sync | do_fua;
+ mbio->bi_opf = op | do_sync | do_fua | do_atomic;
if (!replacement && test_bit(FailFast,
&conf->mirrors[devnum].rdev->flags)
&& enough(conf, devnum))
@@ -1285,9 +1296,9 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
{
- int i;
struct r10conf *conf = mddev->private;
struct md_rdev *blocked_rdev;
+ int i;
retry_wait:
blocked_rdev = NULL;
@@ -1295,40 +1306,36 @@ retry_wait:
struct md_rdev *rdev, *rrdev;
rdev = conf->mirrors[i].rdev;
- rrdev = conf->mirrors[i].replacement;
- if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
- atomic_inc(&rdev->nr_pending);
- blocked_rdev = rdev;
- break;
- }
- if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
- atomic_inc(&rrdev->nr_pending);
- blocked_rdev = rrdev;
- break;
- }
-
- if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
+ if (rdev) {
sector_t dev_sector = r10_bio->devs[i].addr;
/*
* Discard request doesn't care the write result
* so it doesn't need to wait blocked disk here.
*/
- if (!r10_bio->sectors)
- continue;
-
- if (rdev_has_badblock(rdev, dev_sector,
- r10_bio->sectors) < 0) {
+ if (test_bit(WriteErrorSeen, &rdev->flags) &&
+ r10_bio->sectors &&
+ rdev_has_badblock(rdev, dev_sector,
+ r10_bio->sectors) < 0)
/*
- * Mustn't write here until the bad block
- * is acknowledged
+ * Mustn't write here until the bad
+ * block is acknowledged
*/
- atomic_inc(&rdev->nr_pending);
set_bit(BlockedBadBlocks, &rdev->flags);
+
+ if (rdev_blocked(rdev)) {
blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
break;
}
}
+
+ rrdev = conf->mirrors[i].replacement;
+ if (rrdev && rdev_blocked(rrdev)) {
+ atomic_inc(&rrdev->nr_pending);
+ blocked_rdev = rrdev;
+ break;
+ }
}
if (unlikely(blocked_rdev)) {
@@ -1347,9 +1354,10 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
struct r10bio *r10_bio)
{
struct r10conf *conf = mddev->private;
- int i;
+ int i, k;
sector_t sectors;
int max_sectors;
+ int error;
if ((mddev_is_clustered(mddev) &&
md_cluster_ops->area_resyncing(mddev, WRITE,
@@ -1461,7 +1469,21 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
continue;
}
if (is_bad) {
- int good_sectors = first_bad - dev_sector;
+ int good_sectors;
+
+ /*
+ * We cannot atomically write this, so just
+ * error in that case. It could be possible to
+ * atomically write other mirrors, but the
+ * complexity of supporting that is not worth
+ * the benefit.
+ */
+ if (bio->bi_opf & REQ_ATOMIC) {
+ error = -EIO;
+ goto err_handle;
+ }
+
+ good_sectors = first_bad - dev_sector;
if (good_sectors < max_sectors)
max_sectors = good_sectors;
}
@@ -1482,6 +1504,10 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
if (r10_bio->sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, r10_bio->sectors,
GFP_NOIO, &conf->bio_split);
+ if (IS_ERR(split)) {
+ error = PTR_ERR(split);
+ goto err_handle;
+ }
bio_chain(split, bio);
allow_barrier(conf);
submit_bio_noacct(bio);
@@ -1503,6 +1529,26 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
raid10_write_one_disk(mddev, r10_bio, bio, true, i);
}
one_write_done(r10_bio);
+ return;
+err_handle:
+ for (k = 0; k < i; k++) {
+ int d = r10_bio->devs[k].devnum;
+ struct md_rdev *rdev = conf->mirrors[d].rdev;
+ struct md_rdev *rrdev = conf->mirrors[d].replacement;
+
+ if (r10_bio->devs[k].bio) {
+ rdev_dec_pending(rdev, mddev);
+ r10_bio->devs[k].bio = NULL;
+ }
+ if (r10_bio->devs[k].repl_bio) {
+ rdev_dec_pending(rrdev, mddev);
+ r10_bio->devs[k].repl_bio = NULL;
+ }
+ }
+
+ bio->bi_status = errno_to_blk_status(error);
+ set_bit(R10BIO_Uptodate, &r10_bio->state);
+ raid_end_bio_io(r10_bio);
}
static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
@@ -1644,6 +1690,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
if (remainder) {
split_size = stripe_size - remainder;
split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+ if (IS_ERR(split)) {
+ bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+ bio_endio(bio);
+ return 0;
+ }
bio_chain(split, bio);
allow_barrier(conf);
/* Resend the fist split part */
@@ -1654,6 +1705,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
if (remainder) {
split_size = bio_sectors(bio) - remainder;
split = bio_split(bio, split_size, GFP_NOIO, &conf->bio_split);
+ if (IS_ERR(split)) {
+ bio->bi_status = errno_to_blk_status(PTR_ERR(split));
+ bio_endio(bio);
+ return 0;
+ }
bio_chain(split, bio);
allow_barrier(conf);
/* Resend the second split part */
@@ -3984,6 +4040,7 @@ static int raid10_set_queue_limits(struct mddev *mddev)
lim.max_write_zeroes_sectors = 0;
lim.io_min = mddev->chunk_sectors << 9;
lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
+ lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED;
err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
if (err) {
queue_limits_cancel_update(mddev->gendisk->queue);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.