Merge tag 'md-3.10-fixes' of git://neil.brown.name/md

Pull md bugfixes from Neil Brown:
 "A few bugfixes for md

  Some tagged for -stable"

* tag 'md-3.10-fixes' of git://neil.brown.name/md:
  md/raid1,5,10: Disable WRITE SAME until a recovery strategy is in place
  md/raid1,raid10: use freeze_array in place of raise_barrier in various places.
  md/raid1: consider WRITE as successful only if at least one non-Faulty and non-rebuilding drive completed it.
  md: md_stop_writes() should always freeze recovery.

4 files changed, 47 insertions, 26 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 681d109..9b82377 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 5595118..6e17f81 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 59d4daa..6ddae25 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 753f318..05e4a10 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5466,7 +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,
@@ -5589,6 +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);