while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
bio->bi_next = NULL;
- generic_make_request(bio);
+ if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+ !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+ /* Just ignore it */
+ bio_endio(bio, 0);
+ else
+ generic_make_request(bio);
bio = next;
}
} else
return rdev->new_data_offset;
}
+struct raid10_plug_cb {
+ struct blk_plug_cb cb;
+ struct bio_list pending;
+ int pending_cnt;
+};
+
+static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+ struct raid10_plug_cb *plug = container_of(cb, struct raid10_plug_cb,
+ cb);
+ struct mddev *mddev = plug->cb.data;
+ struct r10conf *conf = mddev->private;
+ struct bio *bio;
+
+ if (from_schedule) {
+ spin_lock_irq(&conf->device_lock);
+ bio_list_merge(&conf->pending_bio_list, &plug->pending);
+ conf->pending_count += plug->pending_cnt;
+ spin_unlock_irq(&conf->device_lock);
+ md_wakeup_thread(mddev->thread);
+ kfree(plug);
+ return;
+ }
+
+ /* we aren't scheduling, so we can do the write-out directly. */
+ bio = bio_list_get(&plug->pending);
+ bitmap_unplug(mddev->bitmap);
+ wake_up(&conf->wait_barrier);
+
+ while (bio) { /* submit pending writes */
+ struct bio *next = bio->bi_next;
+ bio->bi_next = NULL;
+ generic_make_request(bio);
+ bio = next;
+ }
+ kfree(plug);
+}
+
static void make_request(struct mddev *mddev, struct bio * bio)
{
struct r10conf *conf = mddev->private;
const int rw = bio_data_dir(bio);
const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
+ const unsigned long do_discard = (bio->bi_rw
+ & (REQ_DISCARD | REQ_SECURE));
unsigned long flags;
struct md_rdev *blocked_rdev;
+ struct blk_plug_cb *cb;
+ struct raid10_plug_cb *plug = NULL;
int sectors_handled;
int max_sectors;
int sectors;
|| conf->prev.near_copies < conf->prev.raid_disks))) {
struct bio_pair *bp;
/* Sanity check -- queue functions should prevent this happening */
- if (bio->bi_vcnt != 1 ||
+ if ((bio->bi_vcnt != 1 && bio->bi_vcnt != 0) ||
bio->bi_idx != 0)
goto bad_map;
/* This is a one page bio that upper layers
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;
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);
for (i = 0; i < conf->copies; i++) {
struct bio *mbio;
int d = r10_bio->devs[i].devnum;
- if (!r10_bio->devs[i].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].bio = mbio;
-
- mbio->bi_sector = (r10_bio->devs[i].addr+
- choose_data_offset(r10_bio,
- conf->mirrors[d].rdev));
- 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 (!mddev_check_plugged(mddev))
- md_wakeup_thread(mddev->thread);
+ 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+
+ choose_data_offset(r10_bio,
+ rdev));
+ mbio->bi_bdev = rdev->bdev;
+ mbio->bi_end_io = raid10_end_write_request;
+ mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+ mbio->bi_private = r10_bio;
- if (!r10_bio->devs[i].repl_bio)
- continue;
+ atomic_inc(&r10_bio->remaining);
- 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;
+ cb = blk_check_plugged(raid10_unplug, mddev,
+ sizeof(*plug));
+ if (cb)
+ plug = container_of(cb, struct raid10_plug_cb,
+ cb);
+ else
+ plug = NULL;
+ spin_lock_irqsave(&conf->device_lock, flags);
+ if (plug) {
+ bio_list_add(&plug->pending, mbio);
+ plug->pending_cnt++;
+ } else {
+ bio_list_add(&conf->pending_bio_list, mbio);
+ conf->pending_count++;
+ }
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ if (!plug)
+ md_wakeup_thread(mddev->thread);
+ }
- /* 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 +
- choose_data_offset(
- r10_bio,
- conf->mirrors[d].replacement));
- 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 +
+ choose_data_offset(
+ r10_bio, rdev));
+ mbio->bi_bdev = rdev->bdev;
+ mbio->bi_end_io = raid10_end_write_request;
+ mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+ 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 (!mddev_check_plugged(mddev))
- md_wakeup_thread(mddev->thread);
+ 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 (!mddev_check_plugged(mddev))
+ md_wakeup_thread(mddev->thread);
+ }
}
/* Don't remove the bias on 'remaining' (one_write_done) until
&& !test_bit(Faulty, &tmp->rdev->flags)
&& !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
count++;
- sysfs_notify_dirent(tmp->rdev->sysfs_state);
+ sysfs_notify_dirent_safe(tmp->rdev->sysfs_state);
}
}
spin_lock_irqsave(&conf->device_lock, flags);
clear_bit(Unmerged, &rdev->flags);
}
md_integrity_add_rdev(rdev, mddev);
+ if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
print_conf(conf);
return err;
}
break;
if (j == vcnt)
continue;
- mddev->resync_mismatches += r10_bio->sectors;
+ atomic64_add(r10_bio->sectors, &mddev->resync_mismatches);
if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
/* Don't fix anything. */
continue;
}
}
-static void raid10d(struct mddev *mddev)
+static void raid10d(struct md_thread *thread)
{
+ struct mddev *mddev = thread->mddev;
struct r10bio *r10_bio;
unsigned long flags;
struct r10conf *conf = mddev->private;
else {
bad_sectors -= (sector - first_bad);
if (max_sync > bad_sectors)
- max_sync = max_sync;
+ max_sync = bad_sectors;
continue;
}
}
sector_t size;
sector_t min_offset_diff = 0;
int first = 1;
+ bool discard_supported = false;
if (mddev->private == NULL) {
conf = setup_conf(mddev);
chunk_size = mddev->chunk_sectors << 9;
if (mddev->queue) {
+ blk_queue_max_discard_sectors(mddev->queue,
+ mddev->chunk_sectors);
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);
rdev->data_offset << 9);
disk->head_position = 0;
+
+ if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ discard_supported = true;
}
+ if (mddev->queue) {
+ if (discard_supported)
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
+ mddev->queue);
+ else
+ queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD,
+ mddev->queue);
+ }
/* need to check that every block has at least one working mirror */
if (!enough(conf, -1)) {
printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",