1 files changed, 88 insertions, 40 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6c9d24203f39..519c56f0ee3d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1322,7 +1322,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	const enum req_op op = bio_op(bio);
 	const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC;
 	int max_sectors;
-	int rdisk;
+	int rdisk, error;
 	bool r1bio_existed = !!r1_bio;
 
 	/*
@@ -1383,6 +1383,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      gfp, &conf->bio_split);
+
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		submit_bio_noacct(bio);
 		bio = split;
@@ -1410,6 +1415,47 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_private = r1_bio;
 	mddev_trace_remap(mddev, read_bio, r1_bio->sector);
 	submit_bio_noacct(read_bio);
+	return;
+
+err_handle:
+	atomic_dec(&mirror->rdev->nr_pending);
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R1BIO_Uptodate, &r1_bio->state);
+	raid_end_bio_io(r1_bio);
+}
+
+static bool wait_blocked_rdev(struct mddev *mddev, struct bio *bio)
+{
+	struct r1conf *conf = mddev->private;
+	int disks = conf->raid_disks * 2;
+	int i;
+
+retry:
+	for (i = 0; i < disks; i++) {
+		struct md_rdev *rdev = conf->mirrors[i].rdev;
+
+		if (!rdev)
+			continue;
+
+		/* don't write here until the bad block is acknowledged */
+		if (test_bit(WriteErrorSeen, &rdev->flags) &&
+		    rdev_has_badblock(rdev, bio->bi_iter.bi_sector,
+				      bio_sectors(bio)) < 0)
+			set_bit(BlockedBadBlocks, &rdev->flags);
+
+		if (rdev_blocked(rdev)) {
+			if (bio->bi_opf & REQ_NOWAIT)
+				return false;
+
+			mddev_add_trace_msg(rdev->mddev, "raid1 wait rdev %d blocked",
+					    rdev->raid_disk);
+			atomic_inc(&rdev->nr_pending);
+			md_wait_for_blocked_rdev(rdev, rdev->mddev);
+			goto retry;
+		}
+	}
+
+	return true;
 }
 
 static void raid1_write_request(struct mddev *mddev, struct bio *bio,
@@ -1417,9 +1463,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
-	int i, disks;
+	int i, disks, k, error;
 	unsigned long flags;
-	struct md_rdev *blocked_rdev;
 	int first_clone;
 	int max_sectors;
 	bool write_behind = false;
@@ -1457,7 +1502,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		return;
 	}
 
- retry_write:
+	if (!wait_blocked_rdev(mddev, bio)) {
+		bio_wouldblock_error(bio);
+		return;
+	}
+
 	r1_bio = alloc_r1bio(mddev, bio);
 	r1_bio->sectors = max_write_sectors;
 
@@ -1473,7 +1522,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	 */
 
 	disks = conf->raid_disks * 2;
-	blocked_rdev = NULL;
 	max_sectors = r1_bio->sectors;
 	for (i = 0;  i < disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
@@ -1486,11 +1534,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		if (!is_discard && rdev && test_bit(WriteMostly, &rdev->flags))
 			write_behind = true;
 
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
 		r1_bio->bios[i] = NULL;
 		if (!rdev || test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
@@ -1506,13 +1549,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 			is_bad = is_badblock(rdev, r1_bio->sector, max_sectors,
 					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
-				/* mustn't write here until the bad block is
-				 * acknowledged*/
-				set_bit(BlockedBadBlocks, &rdev->flags);
-				blocked_rdev = rdev;
-				break;
-			}
 			if (is_bad && first_bad <= r1_bio->sector) {
 				/* Cannot write here at all */
 				bad_sectors -= (r1_bio->sector - first_bad);
@@ -1535,7 +1571,21 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				continue;
 			}
 			if (is_bad) {
-				int good_sectors = first_bad - r1_bio->sector;
+				int good_sectors;
+
+				/*
+				 * We cannot atomically write this, so just
+				 * error in that case. It could be possible to
+				 * atomically write other mirrors, but the
+				 * complexity of supporting that is not worth
+				 * the benefit.
+				 */
+				if (bio->bi_opf & REQ_ATOMIC) {
+					error = -EIO;
+					goto err_handle;
+				}
+
+				good_sectors = first_bad - r1_bio->sector;
 				if (good_sectors < max_sectors)
 					max_sectors = good_sectors;
 			}
@@ -1543,27 +1593,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		r1_bio->bios[i] = bio;
 	}
 
-	if (unlikely(blocked_rdev)) {
-		/* Wait for this device to become unblocked */
-		int j;
-
-		for (j = 0; j < i; j++)
-			if (r1_bio->bios[j])
-				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
-		mempool_free(r1_bio, &conf->r1bio_pool);
-		allow_barrier(conf, bio->bi_iter.bi_sector);
-
-		if (bio->bi_opf & REQ_NOWAIT) {
-			bio_wouldblock_error(bio);
-			return;
-		}
-		mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked",
-				blocked_rdev->raid_disk);
-		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		wait_barrier(conf, bio->bi_iter.bi_sector, false);
-		goto retry_write;
-	}
-
 	/*
 	 * When using a bitmap, we may call alloc_behind_master_bio below.
 	 * alloc_behind_master_bio allocates a copy of the data payload a page
@@ -1576,6 +1605,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	if (max_sectors < bio_sectors(bio)) {
 		struct bio *split = bio_split(bio, max_sectors,
 					      GFP_NOIO, &conf->bio_split);
+
+		if (IS_ERR(split)) {
+			error = PTR_ERR(split);
+			goto err_handle;
+		}
 		bio_chain(split, bio);
 		submit_bio_noacct(bio);
 		bio = split;
@@ -1637,7 +1671,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 		mbio->bi_iter.bi_sector	= (r1_bio->sector + rdev->data_offset);
 		mbio->bi_end_io	= raid1_end_write_request;
-		mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA));
+		mbio->bi_opf = bio_op(bio) |
+			(bio->bi_opf & (REQ_SYNC | REQ_FUA | REQ_ATOMIC));
 		if (test_bit(FailFast, &rdev->flags) &&
 		    !test_bit(WriteMostly, &rdev->flags) &&
 		    conf->raid_disks - mddev->degraded > 1)
@@ -1660,6 +1695,18 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	/* In case raid1d snuck in to freeze_array */
 	wake_up_barrier(conf);
+	return;
+err_handle:
+	for (k = 0; k < i; k++) {
+		if (r1_bio->bios[k]) {
+			rdev_dec_pending(conf->mirrors[k].rdev, mddev);
+			r1_bio->bios[k] = NULL;
+		}
+	}
+
+	bio->bi_status = errno_to_blk_status(error);
+	set_bit(R1BIO_Uptodate, &r1_bio->state);
+	raid_end_bio_io(r1_bio);
 }
 
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
@@ -3192,6 +3239,7 @@ static int raid1_set_limits(struct mddev *mddev)
 
 	md_init_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES_STACKED;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
 	if (err) {
 		queue_limits_cancel_update(mddev->gendisk->queue);