summaryrefslogtreecommitdiff
path: root/drivers/md/raid10.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid10.c')
-rw-r--r--drivers/md/raid10.c120
1 files changed, 65 insertions, 55 deletions
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a954c95d7c92..6137d0041d4d 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -476,7 +476,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
*/
one_write_done(r10_bio);
if (dec_rdev)
- rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
+ rdev_dec_pending(rdev, conf->mddev);
}
/*
@@ -612,20 +612,24 @@ static int raid10_mergeable_bvec(struct request_queue *q,
max = biovec->bv_len;
if (mddev->merge_check_needed) {
- struct r10bio r10_bio;
+ struct {
+ struct r10bio r10_bio;
+ struct r10dev devs[conf->copies];
+ } on_stack;
+ struct r10bio *r10_bio = &on_stack.r10_bio;
int s;
- r10_bio.sector = sector;
- raid10_find_phys(conf, &r10_bio);
+ r10_bio->sector = sector;
+ raid10_find_phys(conf, r10_bio);
rcu_read_lock();
for (s = 0; s < conf->copies; s++) {
- int disk = r10_bio.devs[s].devnum;
+ int disk = r10_bio->devs[s].devnum;
struct md_rdev *rdev = rcu_dereference(
conf->mirrors[disk].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q =
bdev_get_queue(rdev->bdev);
if (q->merge_bvec_fn) {
- bvm->bi_sector = r10_bio.devs[s].addr
+ bvm->bi_sector = r10_bio->devs[s].addr
+ rdev->data_offset;
bvm->bi_bdev = rdev->bdev;
max = min(max, q->merge_bvec_fn(
@@ -637,7 +641,7 @@ static int raid10_mergeable_bvec(struct request_queue *q,
struct request_queue *q =
bdev_get_queue(rdev->bdev);
if (q->merge_bvec_fn) {
- bvm->bi_sector = r10_bio.devs[s].addr
+ bvm->bi_sector = r10_bio->devs[s].addr
+ rdev->data_offset;
bvm->bi_bdev = rdev->bdev;
max = min(max, q->merge_bvec_fn(
@@ -1178,18 +1182,21 @@ retry_write:
blocked_rdev = rrdev;
break;
}
+ if (rdev && (test_bit(Faulty, &rdev->flags)
+ || test_bit(Unmerged, &rdev->flags)))
+ rdev = NULL;
if (rrdev && (test_bit(Faulty, &rrdev->flags)
|| test_bit(Unmerged, &rrdev->flags)))
rrdev = NULL;
r10_bio->devs[i].bio = NULL;
r10_bio->devs[i].repl_bio = NULL;
- if (!rdev || test_bit(Faulty, &rdev->flags) ||
- test_bit(Unmerged, &rdev->flags)) {
+
+ if (!rdev && !rrdev) {
set_bit(R10BIO_Degraded, &r10_bio->state);
continue;
}
- if (test_bit(WriteErrorSeen, &rdev->flags)) {
+ if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
sector_t dev_sector = r10_bio->devs[i].addr;
int bad_sectors;
@@ -1231,8 +1238,10 @@ retry_write:
max_sectors = good_sectors;
}
}
- r10_bio->devs[i].bio = bio;
- atomic_inc(&rdev->nr_pending);
+ if (rdev) {
+ r10_bio->devs[i].bio = bio;
+ atomic_inc(&rdev->nr_pending);
+ }
if (rrdev) {
r10_bio->devs[i].repl_bio = bio;
atomic_inc(&rrdev->nr_pending);
@@ -1288,51 +1297,52 @@ retry_write:
for (i = 0; i < conf->copies; i++) {
struct bio *mbio;
int d = r10_bio->devs[i].devnum;
- if (!r10_bio->devs[i].bio)
- continue;
+ if (r10_bio->devs[i].bio) {
+ struct md_rdev *rdev = conf->mirrors[d].rdev;
+ mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+ md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+ max_sectors);
+ r10_bio->devs[i].bio = mbio;
+
+ mbio->bi_sector = (r10_bio->devs[i].addr+
+ rdev->data_offset);
+ mbio->bi_bdev = rdev->bdev;
+ mbio->bi_end_io = raid10_end_write_request;
+ mbio->bi_rw = WRITE | do_sync | do_fua;
+ mbio->bi_private = r10_bio;
- mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
- max_sectors);
- r10_bio->devs[i].bio = mbio;
-
- mbio->bi_sector = (r10_bio->devs[i].addr+
- conf->mirrors[d].rdev->data_offset);
- mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
- mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua;
- mbio->bi_private = r10_bio;
-
- atomic_inc(&r10_bio->remaining);
- spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_add(&conf->pending_bio_list, mbio);
- conf->pending_count++;
- spin_unlock_irqrestore(&conf->device_lock, flags);
-
- if (!r10_bio->devs[i].repl_bio)
- continue;
-
- mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
- md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
- max_sectors);
- r10_bio->devs[i].repl_bio = mbio;
+ atomic_inc(&r10_bio->remaining);
+ spin_lock_irqsave(&conf->device_lock, flags);
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ }
- /* We are actively writing to the original device
- * so it cannot disappear, so the replacement cannot
- * become NULL here
- */
- mbio->bi_sector = (r10_bio->devs[i].addr+
- conf->mirrors[d].replacement->data_offset);
- mbio->bi_bdev = conf->mirrors[d].replacement->bdev;
- mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua;
- mbio->bi_private = r10_bio;
+ if (r10_bio->devs[i].repl_bio) {
+ struct md_rdev *rdev = conf->mirrors[d].replacement;
+ if (rdev == NULL) {
+ /* Replacement just got moved to main 'rdev' */
+ smp_mb();
+ rdev = conf->mirrors[d].rdev;
+ }
+ mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+ md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+ max_sectors);
+ r10_bio->devs[i].repl_bio = mbio;
+
+ mbio->bi_sector = (r10_bio->devs[i].addr+
+ rdev->data_offset);
+ mbio->bi_bdev = rdev->bdev;
+ mbio->bi_end_io = raid10_end_write_request;
+ mbio->bi_rw = WRITE | do_sync | do_fua;
+ mbio->bi_private = r10_bio;
- atomic_inc(&r10_bio->remaining);
- spin_lock_irqsave(&conf->device_lock, flags);
- bio_list_add(&conf->pending_bio_list, mbio);
- conf->pending_count++;
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ atomic_inc(&r10_bio->remaining);
+ spin_lock_irqsave(&conf->device_lock, flags);
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ }
}
/* Don't remove the bias on 'remaining' (one_write_done) until
@@ -3015,7 +3025,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
else {
bad_sectors -= (sector - first_bad);
if (max_sync > bad_sectors)
- max_sync = max_sync;
+ max_sync = bad_sectors;
continue;
}
}