summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/bcache/Kconfig1
-rw-r--r--drivers/md/bcache/bcache.h2
-rw-r--r--drivers/md/bcache/stats.c34
-rw-r--r--drivers/md/bcache/super.c185
-rw-r--r--drivers/md/bcache/writeback.c2
-rw-r--r--drivers/md/dm-thin.c4
-rw-r--r--drivers/md/md.c2
-rw-r--r--drivers/md/raid1.c38
-rw-r--r--drivers/md/raid10.c29
-rw-r--r--drivers/md/raid5.c6
10 files changed, 151 insertions, 152 deletions
diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index 05c220d05e23..f950c9d29f3e 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -1,7 +1,6 @@
config BCACHE
tristate "Block device as cache"
- select CLOSURES
---help---
Allows a block device to be used as cache for other devices; uses
a btree for indexing and the layout is optimized for SSDs.
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 340146d7c17f..d3e15b42a4ab 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -1241,7 +1241,7 @@ void bch_cache_set_stop(struct cache_set *);
struct cache_set *bch_cache_set_alloc(struct cache_sb *);
void bch_btree_cache_free(struct cache_set *);
int bch_btree_cache_alloc(struct cache_set *);
-void bch_writeback_init_cached_dev(struct cached_dev *);
+void bch_cached_dev_writeback_init(struct cached_dev *);
void bch_moving_init_cache_set(struct cache_set *);
void bch_cache_allocator_exit(struct cache *ca);
diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c
index 64e679449c2a..b8730e714d69 100644
--- a/drivers/md/bcache/stats.c
+++ b/drivers/md/bcache/stats.c
@@ -93,24 +93,6 @@ static struct attribute *bch_stats_files[] = {
};
static KTYPE(bch_stats);
-static void scale_accounting(unsigned long data);
-
-void bch_cache_accounting_init(struct cache_accounting *acc,
- struct closure *parent)
-{
- kobject_init(&acc->total.kobj, &bch_stats_ktype);
- kobject_init(&acc->five_minute.kobj, &bch_stats_ktype);
- kobject_init(&acc->hour.kobj, &bch_stats_ktype);
- kobject_init(&acc->day.kobj, &bch_stats_ktype);
-
- closure_init(&acc->cl, parent);
- init_timer(&acc->timer);
- acc->timer.expires = jiffies + accounting_delay;
- acc->timer.data = (unsigned long) acc;
- acc->timer.function = scale_accounting;
- add_timer(&acc->timer);
-}
-
int bch_cache_accounting_add_kobjs(struct cache_accounting *acc,
struct kobject *parent)
{
@@ -244,3 +226,19 @@ void bch_mark_sectors_bypassed(struct search *s, int sectors)
atomic_add(sectors, &dc->accounting.collector.sectors_bypassed);
atomic_add(sectors, &s->op.c->accounting.collector.sectors_bypassed);
}
+
+void bch_cache_accounting_init(struct cache_accounting *acc,
+ struct closure *parent)
+{
+ kobject_init(&acc->total.kobj, &bch_stats_ktype);
+ kobject_init(&acc->five_minute.kobj, &bch_stats_ktype);
+ kobject_init(&acc->hour.kobj, &bch_stats_ktype);
+ kobject_init(&acc->day.kobj, &bch_stats_ktype);
+
+ closure_init(&acc->cl, parent);
+ init_timer(&acc->timer);
+ acc->timer.expires = jiffies + accounting_delay;
+ acc->timer.data = (unsigned long) acc;
+ acc->timer.function = scale_accounting;
+ add_timer(&acc->timer);
+}
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index c8046bc4aa57..f88e2b653a3f 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -634,11 +634,10 @@ static int open_dev(struct block_device *b, fmode_t mode)
return 0;
}
-static int release_dev(struct gendisk *b, fmode_t mode)
+static void release_dev(struct gendisk *b, fmode_t mode)
{
struct bcache_device *d = b->private_data;
closure_put(&d->cl);
- return 0;
}
static int ioctl_dev(struct block_device *b, fmode_t mode,
@@ -732,8 +731,7 @@ static void bcache_device_free(struct bcache_device *d)
if (d->c)
bcache_device_detach(d);
-
- if (d->disk)
+ if (d->disk && d->disk->flags & GENHD_FL_UP)
del_gendisk(d->disk);
if (d->disk && d->disk->queue)
blk_cleanup_queue(d->disk->queue);
@@ -756,12 +754,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size)
if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
!(d->unaligned_bvec = mempool_create_kmalloc_pool(1,
sizeof(struct bio_vec) * BIO_MAX_PAGES)) ||
- bio_split_pool_init(&d->bio_split_hook))
-
- return -ENOMEM;
-
- d->disk = alloc_disk(1);
- if (!d->disk)
+ bio_split_pool_init(&d->bio_split_hook) ||
+ !(d->disk = alloc_disk(1)) ||
+ !(q = blk_alloc_queue(GFP_KERNEL)))
return -ENOMEM;
snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", bcache_minor);
@@ -771,10 +766,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size)
d->disk->fops = &bcache_ops;
d->disk->private_data = d;
- q = blk_alloc_queue(GFP_KERNEL);
- if (!q)
- return -ENOMEM;
-
blk_queue_make_request(q, NULL);
d->disk->queue = q;
q->queuedata = d;
@@ -999,14 +990,17 @@ static void cached_dev_free(struct closure *cl)
mutex_lock(&bch_register_lock);
- bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
+ if (atomic_read(&dc->running))
+ bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
bcache_device_free(&dc->disk);
list_del(&dc->list);
mutex_unlock(&bch_register_lock);
if (!IS_ERR_OR_NULL(dc->bdev)) {
- blk_sync_queue(bdev_get_queue(dc->bdev));
+ if (dc->bdev->bd_disk)
+ blk_sync_queue(bdev_get_queue(dc->bdev));
+
blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
@@ -1028,73 +1022,67 @@ static void cached_dev_flush(struct closure *cl)
static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
{
- int err;
+ int ret;
struct io *io;
-
- closure_init(&dc->disk.cl, NULL);
- set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq);
+ struct request_queue *q = bdev_get_queue(dc->bdev);
__module_get(THIS_MODULE);
INIT_LIST_HEAD(&dc->list);
+ closure_init(&dc->disk.cl, NULL);
+ set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq);
kobject_init(&dc->disk.kobj, &bch_cached_dev_ktype);
-
- bch_cache_accounting_init(&dc->accounting, &dc->disk.cl);
-
- err = bcache_device_init(&dc->disk, block_size);
- if (err)
- goto err;
-
- spin_lock_init(&dc->io_lock);
- closure_init_unlocked(&dc->sb_write);
INIT_WORK(&dc->detach, cached_dev_detach_finish);
+ closure_init_unlocked(&dc->sb_write);
+ INIT_LIST_HEAD(&dc->io_lru);
+ spin_lock_init(&dc->io_lock);
+ bch_cache_accounting_init(&dc->accounting, &dc->disk.cl);
dc->sequential_merge = true;
dc->sequential_cutoff = 4 << 20;
- INIT_LIST_HEAD(&dc->io_lru);
- dc->sb_bio.bi_max_vecs = 1;
- dc->sb_bio.bi_io_vec = dc->sb_bio.bi_inline_vecs;
-
for (io = dc->io; io < dc->io + RECENT_IO; io++) {
list_add(&io->lru, &dc->io_lru);
hlist_add_head(&io->hash, dc->io_hash + RECENT_IO);
}
- bch_writeback_init_cached_dev(dc);
+ ret = bcache_device_init(&dc->disk, block_size);
+ if (ret)
+ return ret;
+
+ set_capacity(dc->disk.disk,
+ dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
+
+ dc->disk.disk->queue->backing_dev_info.ra_pages =
+ max(dc->disk.disk->queue->backing_dev_info.ra_pages,
+ q->backing_dev_info.ra_pages);
+
+ bch_cached_dev_request_init(dc);
+ bch_cached_dev_writeback_init(dc);
return 0;
-err:
- bcache_device_stop(&dc->disk);
- return err;
}
/* Cached device - bcache superblock */
-static const char *register_bdev(struct cache_sb *sb, struct page *sb_page,
+static void register_bdev(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev,
struct cached_dev *dc)
{
char name[BDEVNAME_SIZE];
const char *err = "cannot allocate memory";
- struct gendisk *g;
struct cache_set *c;
- if (!dc || cached_dev_init(dc, sb->block_size << 9) != 0)
- return err;
-
memcpy(&dc->sb, sb, sizeof(struct cache_sb));
- dc->sb_bio.bi_io_vec[0].bv_page = sb_page;
dc->bdev = bdev;
dc->bdev->bd_holder = dc;
- g = dc->disk.disk;
-
- set_capacity(g, dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
-
- g->queue->backing_dev_info.ra_pages =
- max(g->queue->backing_dev_info.ra_pages,
- bdev->bd_queue->backing_dev_info.ra_pages);
+ bio_init(&dc->sb_bio);
+ dc->sb_bio.bi_max_vecs = 1;
+ dc->sb_bio.bi_io_vec = dc->sb_bio.bi_inline_vecs;
+ dc->sb_bio.bi_io_vec[0].bv_page = sb_page;
+ get_page(sb_page);
- bch_cached_dev_request_init(dc);
+ if (cached_dev_init(dc, sb->block_size << 9))
+ goto err;
err = "error creating kobject";
if (kobject_add(&dc->disk.kobj, &part_to_dev(bdev->bd_part)->kobj,
@@ -1103,6 +1091,8 @@ static const char *register_bdev(struct cache_sb *sb, struct page *sb_page,
if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
goto err;
+ pr_info("registered backing device %s", bdevname(bdev, name));
+
list_add(&dc->list, &uncached_devices);
list_for_each_entry(c, &bch_cache_sets, list)
bch_cached_dev_attach(dc, c);
@@ -1111,15 +1101,10 @@ static const char *register_bdev(struct cache_sb *sb, struct page *sb_page,
BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
bch_cached_dev_run(dc);
- return NULL;
+ return;
err:
- kobject_put(&dc->disk.kobj);
pr_notice("error opening %s: %s", bdevname(bdev, name), err);
- /*
- * Return NULL instead of an error because kobject_put() cleans
- * everything up
- */
- return NULL;
+ bcache_device_stop(&dc->disk);
}
/* Flash only volumes */
@@ -1717,20 +1702,11 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
size_t free;
struct bucket *b;
- if (!ca)
- return -ENOMEM;
-
__module_get(THIS_MODULE);
kobject_init(&ca->kobj, &bch_cache_ktype);
- memcpy(&ca->sb, sb, sizeof(struct cache_sb));
-
INIT_LIST_HEAD(&ca->discards);
- bio_init(&ca->sb_bio);
- ca->sb_bio.bi_max_vecs = 1;
- ca->sb_bio.bi_io_vec = ca->sb_bio.bi_inline_vecs;
-
bio_init(&ca->journal.bio);
ca->journal.bio.bi_max_vecs = 8;
ca->journal.bio.bi_io_vec = ca->journal.bio.bi_inline_vecs;
@@ -1742,18 +1718,17 @@ static int cache_alloc(struct cache_sb *sb, struct cache *ca)
!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) ||
!init_fifo(&ca->unused, free << 2, GFP_KERNEL) ||
!init_heap(&ca->heap, free << 3, GFP_KERNEL) ||
- !(ca->buckets = vmalloc(sizeof(struct bucket) *
+ !(ca->buckets = vzalloc(sizeof(struct bucket) *
ca->sb.nbuckets)) ||
!(ca->prio_buckets = kzalloc(sizeof(uint64_t) * prio_buckets(ca) *
2, GFP_KERNEL)) ||
!(ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca)) ||
!(ca->alloc_workqueue = alloc_workqueue("bch_allocator", 0, 1)) ||
bio_split_pool_init(&ca->bio_split_hook))
- goto err;
+ return -ENOMEM;
ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca);
- memset(ca->buckets, 0, ca->sb.nbuckets * sizeof(struct bucket));
for_each_bucket(b, ca)
atomic_set(&b->pin, 0);
@@ -1766,22 +1741,28 @@ err:
return -ENOMEM;
}
-static const char *register_cache(struct cache_sb *sb, struct page *sb_page,
+static void register_cache(struct cache_sb *sb, struct page *sb_page,
struct block_device *bdev, struct cache *ca)
{
char name[BDEVNAME_SIZE];
const char *err = "cannot allocate memory";
- if (cache_alloc(sb, ca) != 0)
- return err;
-
- ca->sb_bio.bi_io_vec[0].bv_page = sb_page;
+ memcpy(&ca->sb, sb, sizeof(struct cache_sb));
ca->bdev = bdev;
ca->bdev->bd_holder = ca;
+ bio_init(&ca->sb_bio);
+ ca->sb_bio.bi_max_vecs = 1;
+ ca->sb_bio.bi_io_vec = ca->sb_bio.bi_inline_vecs;
+ ca->sb_bio.bi_io_vec[0].bv_page = sb_page;
+ get_page(sb_page);
+
if (blk_queue_discard(bdev_get_queue(ca->bdev)))
ca->discard = CACHE_DISCARD(&ca->sb);
+ if (cache_alloc(sb, ca) != 0)
+ goto err;
+
err = "error creating kobject";
if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache"))
goto err;
@@ -1791,15 +1772,10 @@ static const char *register_cache(struct cache_sb *sb, struct page *sb_page,
goto err;
pr_info("registered cache device %s", bdevname(bdev, name));
-
- return NULL;
+ return;
err:
+ pr_notice("error opening %s: %s", bdevname(bdev, name), err);
kobject_put(&ca->kobj);
- pr_info("error opening %s: %s", bdevname(bdev, name), err);
- /* Return NULL instead of an error because kobject_put() cleans
- * everything up
- */
- return NULL;
}
/* Global interfaces/init */
@@ -1833,12 +1809,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
bdev = blkdev_get_by_path(strim(path),
FMODE_READ|FMODE_WRITE|FMODE_EXCL,
sb);
- if (bdev == ERR_PTR(-EBUSY))
- err = "device busy";
-
- if (IS_ERR(bdev) ||
- set_blocksize(bdev, 4096))
+ if (IS_ERR(bdev)) {
+ if (bdev == ERR_PTR(-EBUSY))
+ err = "device busy";
goto err;
+ }
+
+ err = "failed to set blocksize";
+ if (set_blocksize(bdev, 4096))
+ goto err_close;
err = read_super(sb, bdev, &sb_page);
if (err)
@@ -1846,33 +1825,33 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
if (SB_IS_BDEV(sb)) {
struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
+ if (!dc)
+ goto err_close;
- err = register_bdev(sb, sb_page, bdev, dc);
+ register_bdev(sb, sb_page, bdev, dc);
} else {
struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+ if (!ca)
+ goto err_close;
- err = register_cache(sb, sb_page, bdev, ca);
+ register_cache(sb, sb_page, bdev, ca);
}
-
- if (err) {
- /* register_(bdev|cache) will only return an error if they
- * didn't get far enough to create the kobject - if they did,
- * the kobject destructor will do this cleanup.
- */
+out:
+ if (sb_page)
put_page(sb_page);
-err_close:
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
-err:
- if (attr != &ksysfs_register_quiet)
- pr_info("error opening %s: %s", path, err);
- ret = -EINVAL;
- }
-
kfree(sb);
kfree(path);
mutex_unlock(&bch_register_lock);
module_put(THIS_MODULE);
return ret;
+
+err_close:
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+err:
+ if (attr != &ksysfs_register_quiet)
+ pr_info("error opening %s: %s", path, err);
+ ret = -EINVAL;
+ goto out;
}
static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 93e7e31a4bd3..2714ed3991d1 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -375,7 +375,7 @@ err:
refill_dirty(cl);
}
-void bch_writeback_init_cached_dev(struct cached_dev *dc)
+void bch_cached_dev_writeback_init(struct cached_dev *dc)
{
closure_init_unlocked(&dc->writeback);
init_rwsem(&dc->writeback_lock);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 759cffc45cab..88f2f802d528 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2188,7 +2188,7 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit)
*need_commit = false;
- metadata_dev_size = get_metadata_dev_size(pool->md_dev);
+ metadata_dev_size = get_metadata_dev_size_in_blocks(pool->md_dev);
r = dm_pool_get_metadata_dev_size(pool->pmd, &sb_metadata_dev_size);
if (r) {
@@ -2197,7 +2197,7 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit)
}
if (metadata_dev_size < sb_metadata_dev_size) {
- DMERR("metadata device (%llu sectors) too small: expected %llu",
+ DMERR("metadata device (%llu blocks) too small: expected %llu",
metadata_dev_size, sb_metadata_dev_size);
return -EINVAL;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 681d1099a2d5..9b82377a833b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5268,8 +5268,8 @@ static void md_clean(struct mddev *mddev)
static void __md_stop_writes(struct mddev *mddev)
{
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
if (mddev->sync_thread) {
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_reap_sync_thread(mddev);
}
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 55951182af73..6e17f8181c4b 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -417,7 +417,17 @@ static void raid1_end_write_request(struct bio *bio, int error)
r1_bio->bios[mirror] = NULL;
to_put = bio;
- set_bit(R1BIO_Uptodate, &r1_bio->state);
+ /*
+ * Do not set R1BIO_Uptodate if the current device is
+ * rebuilding or Faulty. This is because we cannot use
+ * such device for properly reading the data back (we could
+ * potentially use it, if the current write would have felt
+ * before rdev->recovery_offset, but for simplicity we don't
+ * check this here.
+ */
+ if (test_bit(In_sync, &conf->mirrors[mirror].rdev->flags) &&
+ !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags))
+ set_bit(R1BIO_Uptodate, &r1_bio->state);
/* Maybe we can clear some bad blocks. */
if (is_badblock(conf->mirrors[mirror].rdev,
@@ -870,17 +880,17 @@ static void allow_barrier(struct r1conf *conf)
wake_up(&conf->wait_barrier);
}
-static void freeze_array(struct r1conf *conf)
+static void freeze_array(struct r1conf *conf, int extra)
{
/* stop syncio and normal IO and wait for everything to
* go quite.
* We increment barrier and nr_waiting, and then
- * wait until nr_pending match nr_queued+1
+ * wait until nr_pending match nr_queued+extra
* This is called in the context of one normal IO request
* that has failed. Thus any sync request that might be pending
* will be blocked by nr_pending, and we need to wait for
* pending IO requests to complete or be queued for re-try.
- * Thus the number queued (nr_queued) plus this request (1)
+ * Thus the number queued (nr_queued) plus this request (extra)
* must match the number of pending IOs (nr_pending) before
* we continue.
*/
@@ -888,7 +898,7 @@ static void freeze_array(struct r1conf *conf)
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq_cmd(conf->wait_barrier,
- conf->nr_pending == conf->nr_queued+1,
+ conf->nr_pending == conf->nr_queued+extra,
conf->resync_lock,
flush_pending_writes(conf));
spin_unlock_irq(&conf->resync_lock);
@@ -1544,8 +1554,8 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
* we wait for all outstanding requests to complete.
*/
synchronize_sched();
- raise_barrier(conf);
- lower_barrier(conf);
+ freeze_array(conf, 0);
+ unfreeze_array(conf);
clear_bit(Unmerged, &rdev->flags);
}
md_integrity_add_rdev(rdev, mddev);
@@ -1595,11 +1605,11 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
*/
struct md_rdev *repl =
conf->mirrors[conf->raid_disks + number].rdev;
- raise_barrier(conf);
+ freeze_array(conf, 0);
clear_bit(Replacement, &repl->flags);
p->rdev = repl;
conf->mirrors[conf->raid_disks + number].rdev = NULL;
- lower_barrier(conf);
+ unfreeze_array(conf);
clear_bit(WantReplacement, &rdev->flags);
} else
clear_bit(WantReplacement, &rdev->flags);
@@ -2195,7 +2205,7 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
* frozen
*/
if (mddev->ro == 0) {
- freeze_array(conf);
+ freeze_array(conf, 1);
fix_read_error(conf, r1_bio->read_disk,
r1_bio->sector, r1_bio->sectors);
unfreeze_array(conf);
@@ -2780,8 +2790,8 @@ static int run(struct mddev *mddev)
return PTR_ERR(conf);
if (mddev->queue)
- blk_queue_max_write_same_sectors(mddev->queue,
- mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue, 0);
+
rdev_for_each(rdev, mddev) {
if (!mddev->gendisk)
continue;
@@ -2963,7 +2973,7 @@ static int raid1_reshape(struct mddev *mddev)
return -ENOMEM;
}
- raise_barrier(conf);
+ freeze_array(conf, 0);
/* ok, everything is stopped */
oldpool = conf->r1bio_pool;
@@ -2994,7 +3004,7 @@ static int raid1_reshape(struct mddev *mddev)
conf->raid_disks = mddev->raid_disks = raid_disks;
mddev->delta_disks = 0;
- lower_barrier(conf);
+ unfreeze_array(conf);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 59d4daa5f4c7..6ddae2501b9a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -490,7 +490,17 @@ static void raid10_end_write_request(struct bio *bio, int error)
sector_t first_bad;
int bad_sectors;
- set_bit(R10BIO_Uptodate, &r10_bio->state);
+ /*
+ * Do not set R10BIO_Uptodate if the current device is
+ * rebuilding or Faulty. This is because we cannot use
+ * such device for properly reading the data back (we could
+ * potentially use it, if the current write would have felt
+ * before rdev->recovery_offset, but for simplicity we don't
+ * check this here.
+ */
+ if (test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags))
+ set_bit(R10BIO_Uptodate, &r10_bio->state);
/* Maybe we can clear some bad blocks. */
if (is_badblock(rdev,
@@ -1055,17 +1065,17 @@ static void allow_barrier(struct r10conf *conf)
wake_up(&conf->wait_barrier);
}
-static void freeze_array(struct r10conf *conf)
+static void freeze_array(struct r10conf *conf, int extra)
{
/* stop syncio and normal IO and wait for everything to
* go quiet.
* We increment barrier and nr_waiting, and then
- * wait until nr_pending match nr_queued+1
+ * wait until nr_pending match nr_queued+extra
* This is called in the context of one normal IO request
* that has failed. Thus any sync request that might be pending
* will be blocked by nr_pending, and we need to wait for
* pending IO requests to complete or be queued for re-try.
- * Thus the number queued (nr_queued) plus this request (1)
+ * Thus the number queued (nr_queued) plus this request (extra)
* must match the number of pending IOs (nr_pending) before
* we continue.
*/
@@ -1073,7 +1083,7 @@ static void freeze_array(struct r10conf *conf)
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq_cmd(conf->wait_barrier,
- conf->nr_pending == conf->nr_queued+1,
+ conf->nr_pending == conf->nr_queued+extra,
conf->resync_lock,
flush_pending_writes(conf));
@@ -1837,8 +1847,8 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
* we wait for all outstanding requests to complete.
*/
synchronize_sched();
- raise_barrier(conf, 0);
- lower_barrier(conf);
+ freeze_array(conf, 0);
+ unfreeze_array(conf);
clear_bit(Unmerged, &rdev->flags);
}
md_integrity_add_rdev(rdev, mddev);
@@ -2612,7 +2622,7 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
r10_bio->devs[slot].bio = NULL;
if (mddev->ro == 0) {
- freeze_array(conf);
+ freeze_array(conf, 1);
fix_read_error(conf, mddev, r10_bio);
unfreeze_array(conf);
} else
@@ -3609,8 +3619,7 @@ static int run(struct mddev *mddev)
if (mddev->queue) {
blk_queue_max_discard_sectors(mddev->queue,
mddev->chunk_sectors);
- blk_queue_max_write_same_sectors(mddev->queue,
- mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue, 0);
blk_queue_io_min(mddev->queue, chunk_size);
if (conf->geo.raid_disks % conf->geo.near_copies)
blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9359828ffe26..05e4a105b9c7 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -664,6 +664,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
bi->bi_rw |= REQ_FLUSH;
+ bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
@@ -701,6 +702,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
else
rbi->bi_sector = (sh->sector
+ rrdev->data_offset);
+ rbi->bi_vcnt = 1;
rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
rbi->bi_io_vec[0].bv_offset = 0;
rbi->bi_size = STRIPE_SIZE;
@@ -5464,7 +5466,7 @@ static int run(struct mddev *mddev)
if (mddev->major_version == 0 &&
mddev->minor_version > 90)
rdev->recovery_offset = reshape_offset;
-
+
if (rdev->recovery_offset < reshape_offset) {
/* We need to check old and new layout */
if (!only_parity(rdev->raid_disk,
@@ -5587,6 +5589,8 @@ static int run(struct mddev *mddev)
*/
mddev->queue->limits.discard_zeroes_data = 0;
+ blk_queue_max_write_same_sectors(mddev->queue, 0);
+
rdev_for_each(rdev, mddev) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);