1 files changed, 77 insertions, 71 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d1295aff4173..64d48249c03b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -499,7 +499,7 @@ 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);
 }
 
 /*
@@ -952,7 +952,7 @@ static void raise_barrier(struct r10conf *conf, int force)
 
         /* Wait until no block IO is waiting (unless 'force') */
         wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
-                            conf->resync_lock, );
+                            conf->resync_lock);
 
         /* block any new IO from starting */
         conf->barrier++;
@@ -960,7 +960,7 @@ static void raise_barrier(struct r10conf *conf, int force)
         /* Now wait for all pending IO to complete */
         wait_event_lock_irq(conf->wait_barrier,
                             !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
-                            conf->resync_lock, );
+                            conf->resync_lock);
 
         spin_unlock_irq(&conf->resync_lock);
 }
@@ -993,8 +993,7 @@ static void wait_barrier(struct r10conf *conf)
                                     (conf->nr_pending &&
                                      current->bio_list &&
                                      !bio_list_empty(current->bio_list)),
-                                    conf->resync_lock,
-                        );
+                                    conf->resync_lock);
                 conf->nr_waiting--;
         }
         conf->nr_pending++;
@@ -1027,10 +1026,10 @@ static void freeze_array(struct r10conf *conf)
         spin_lock_irq(&conf->resync_lock);
         conf->barrier++;
         conf->nr_waiting++;
-        wait_event_lock_irq(conf->wait_barrier,
-                            conf->nr_pending == conf->nr_queued+1,
-                            conf->resync_lock,
-                            flush_pending_writes(conf));
+        wait_event_lock_irq_cmd(conf->wait_barrier,
+                                conf->nr_pending == conf->nr_queued+1,
+                                conf->resync_lock,
+                                flush_pending_writes(conf));
 
         spin_unlock_irq(&conf->resync_lock);
 }
@@ -1069,7 +1068,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
         struct r10conf *conf = mddev->private;
         struct bio *bio;
 
-        if (from_schedule) {
+        if (from_schedule || current->bio_list) {
                 spin_lock_irq(&conf->device_lock);
                 bio_list_merge(&conf->pending_bio_list, &plug->pending);
                 conf->pending_count += plug->pending_cnt;
@@ -1334,18 +1333,21 @@ 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;
@@ -1387,8 +1389,10 @@ 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);
@@ -1444,69 +1448,71 @@ 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+
+                                           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;
 
-                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;
+                        atomic_inc(&r10_bio->remaining);
 
-                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 | do_discard;
-                mbio->bi_private = r10_bio;
+                        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);
+                }
 
-                atomic_inc(&r10_bio->remaining);
+                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;
 
-                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 {
+                        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);
                 }
-                spin_unlock_irqrestore(&conf->device_lock, flags);
-                if (!plug)
-                        md_wakeup_thread(mddev->thread);
-
-                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;
-
-                /* 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 | 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);
         }
 
         /* Don't remove the bias on 'remaining' (one_write_done) until