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.c102
1 files changed, 57 insertions, 45 deletions
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6c66357f92f5..4fcfcb350d2b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -952,7 +952,9 @@ static void flush_pending_writes(struct r10conf *conf)
static void raise_barrier(struct r10conf *conf, int force)
{
write_seqlock_irq(&conf->resync_lock);
- BUG_ON(force && !conf->barrier);
+
+ if (WARN_ON_ONCE(force && !conf->barrier))
+ force = false;
/* Wait until no block IO is waiting (unless 'force') */
wait_event_barrier(conf, force || !conf->nr_waiting);
@@ -995,11 +997,15 @@ static bool stop_waiting_barrier(struct r10conf *conf)
(!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1])))
return true;
- /* move on if recovery thread is blocked by us */
- if (conf->mddev->thread->tsk == current &&
- test_bit(MD_RECOVERY_RUNNING, &conf->mddev->recovery) &&
- conf->nr_queued > 0)
+ /*
+ * move on if io is issued from raid10d(), nr_pending is not released
+ * from original io(see handle_read_error()). All raise barrier is
+ * blocked until this io is done.
+ */
+ if (conf->mddev->thread->tsk == current) {
+ WARN_ON_ONCE(atomic_read(&conf->nr_pending) == 0);
return true;
+ }
return false;
}
@@ -1244,7 +1250,8 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
}
slot = r10_bio->read_slot;
- if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+ if (!r10_bio->start_time &&
+ blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
r10_bio->start_time = bio_start_io_acct(bio);
read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set);
@@ -1574,6 +1581,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
r10_bio->sector = bio->bi_iter.bi_sector;
r10_bio->state = 0;
r10_bio->read_slot = -1;
+ r10_bio->start_time = 0;
memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) *
conf->geo.raid_disks);
@@ -1626,7 +1634,7 @@ static void raid10_end_discard_request(struct bio *bio)
/*
* raid10_remove_disk uses smp_mb to make sure rdev is set to
* replacement before setting replacement to NULL. It can read
- * rdev first without barrier protect even replacment is NULL
+ * rdev first without barrier protect even replacement is NULL
*/
smp_rmb();
rdev = conf->mirrors[dev].rdev;
@@ -2609,11 +2617,22 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
{
struct r10conf *conf = mddev->private;
int d;
- struct bio *wbio, *wbio2;
+ struct bio *wbio = r10_bio->devs[1].bio;
+ struct bio *wbio2 = r10_bio->devs[1].repl_bio;
+
+ /* Need to test wbio2->bi_end_io before we call
+ * submit_bio_noacct as if the former is NULL,
+ * the latter is free to free wbio2.
+ */
+ if (wbio2 && !wbio2->bi_end_io)
+ wbio2 = NULL;
if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) {
fix_recovery_read_error(r10_bio);
- end_sync_request(r10_bio);
+ if (wbio->bi_end_io)
+ end_sync_request(r10_bio);
+ if (wbio2)
+ end_sync_request(r10_bio);
return;
}
@@ -2622,14 +2641,6 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
* and submit the write request
*/
d = r10_bio->devs[1].devnum;
- wbio = r10_bio->devs[1].bio;
- wbio2 = r10_bio->devs[1].repl_bio;
- /* Need to test wbio2->bi_end_io before we call
- * submit_bio_noacct as if the former is NULL,
- * the latter is free to free wbio2.
- */
- if (wbio2 && !wbio2->bi_end_io)
- wbio2 = NULL;
if (wbio->bi_end_io) {
atomic_inc(&conf->mirrors[d].rdev->nr_pending);
md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
@@ -2978,9 +2989,13 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
md_error(mddev, rdev);
rdev_dec_pending(rdev, mddev);
- allow_barrier(conf);
r10_bio->state = 0;
raid10_read_request(mddev, r10_bio->master_bio, r10_bio);
+ /*
+ * allow_barrier after re-submit to ensure no sync io
+ * can be issued while regular io pending.
+ */
+ allow_barrier(conf);
}
static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio)
@@ -3289,10 +3304,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
sector_t chunk_mask = conf->geo.chunk_mask;
int page_idx = 0;
- if (!mempool_initialized(&conf->r10buf_pool))
- if (init_resync(conf))
- return 0;
-
/*
* Allow skipping a full rebuild for incremental assembly
* of a clean array, like RAID1 does.
@@ -3308,6 +3319,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
return mddev->dev_sectors - sector_nr;
}
+ if (!mempool_initialized(&conf->r10buf_pool))
+ if (init_resync(conf))
+ return 0;
+
skipped:
max_sector = mddev->dev_sectors;
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
@@ -4004,6 +4019,20 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new)
return nc*fc;
}
+static void raid10_free_conf(struct r10conf *conf)
+{
+ if (!conf)
+ return;
+
+ mempool_exit(&conf->r10bio_pool);
+ kfree(conf->mirrors);
+ kfree(conf->mirrors_old);
+ kfree(conf->mirrors_new);
+ safe_put_page(conf->tmppage);
+ bioset_exit(&conf->bio_split);
+ kfree(conf);
+}
+
static struct r10conf *setup_conf(struct mddev *mddev)
{
struct r10conf *conf = NULL;
@@ -4086,13 +4115,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
return conf;
out:
- if (conf) {
- mempool_exit(&conf->r10bio_pool);
- kfree(conf->mirrors);
- safe_put_page(conf->tmppage);
- bioset_exit(&conf->bio_split);
- kfree(conf);
- }
+ raid10_free_conf(conf);
return ERR_PTR(err);
}
@@ -4129,6 +4152,9 @@ static int raid10_run(struct mddev *mddev)
if (!conf)
goto out;
+ mddev->thread = conf->thread;
+ conf->thread = NULL;
+
if (mddev_is_clustered(conf->mddev)) {
int fc, fo;
@@ -4141,9 +4167,6 @@ static int raid10_run(struct mddev *mddev)
}
}
- mddev->thread = conf->thread;
- conf->thread = NULL;
-
if (mddev->queue) {
blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
@@ -4283,10 +4306,7 @@ static int raid10_run(struct mddev *mddev)
out_free_conf:
md_unregister_thread(&mddev->thread);
- mempool_exit(&conf->r10bio_pool);
- safe_put_page(conf->tmppage);
- kfree(conf->mirrors);
- kfree(conf);
+ raid10_free_conf(conf);
mddev->private = NULL;
out:
return -EIO;
@@ -4294,15 +4314,7 @@ out:
static void raid10_free(struct mddev *mddev, void *priv)
{
- struct r10conf *conf = priv;
-
- mempool_exit(&conf->r10bio_pool);
- safe_put_page(conf->tmppage);
- kfree(conf->mirrors);
- kfree(conf->mirrors_old);
- kfree(conf->mirrors_new);
- bioset_exit(&conf->bio_split);
- kfree(conf);
+ raid10_free_conf(priv);
}
static void raid10_quiesce(struct mddev *mddev, int quiesce)
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2025-01-12 07:09:54 +0000