1 files changed, 194 insertions, 137 deletions

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 62c8b6adac70..985c377356eb 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -37,7 +37,6 @@ static void dump_zones(struct mddev *mddev)
 	int j, k;
 	sector_t zone_size = 0;
 	sector_t zone_start = 0;
-	char b[BDEVNAME_SIZE];
 	struct r0conf *conf = mddev->private;
 	int raid_disks = conf->strip_zone[0].nb_dev;
 	pr_debug("md: RAID0 configuration for %s - %d zone%s\n",
@@ -48,9 +47,8 @@ static void dump_zones(struct mddev *mddev)
 		int len = 0;
 
 		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
-			len += snprintf(line+len, 200-len, "%s%s", k?"/":"",
-					bdevname(conf->devlist[j*raid_disks
-							       + k]->bdev, b));
+			len += scnprintf(line+len, 200-len, "%s%pg", k?"/":"",
+				conf->devlist[j * raid_disks + k]->bdev);
 		pr_debug("md: zone%d=[%s]\n", j, line);
 
 		zone_size  = conf->strip_zone[j].zone_end - zone_start;
@@ -69,18 +67,19 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	struct md_rdev *smallest, *rdev1, *rdev2, *rdev, **dev;
 	struct strip_zone *zone;
 	int cnt;
-	char b[BDEVNAME_SIZE];
-	char b2[BDEVNAME_SIZE];
 	struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-	unsigned blksize = 512;
+	unsigned int blksize = 512;
+
+	if (!mddev_is_dm(mddev))
+		blksize = queue_logical_block_size(mddev->gendisk->queue);
 
 	*private_conf = ERR_PTR(-ENOMEM);
 	if (!conf)
 		return -ENOMEM;
 	rdev_for_each(rdev1, mddev) {
-		pr_debug("md/raid0:%s: looking at %s\n",
+		pr_debug("md/raid0:%s: looking at %pg\n",
 			 mdname(mddev),
-			 bdevname(rdev1->bdev, b));
+			 rdev1->bdev);
 		c = 0;
 
 		/* round size to chunk_size */
@@ -88,16 +87,17 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		sector_div(sectors, mddev->chunk_sectors);
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
-		blksize = max(blksize, queue_logical_block_size(
+		if (mddev_is_dm(mddev))
+			blksize = max(blksize, queue_logical_block_size(
 				      rdev1->bdev->bd_disk->queue));
 
 		rdev_for_each(rdev2, mddev) {
-			pr_debug("md/raid0:%s:   comparing %s(%llu)"
-				 " with %s(%llu)\n",
+			pr_debug("md/raid0:%s:   comparing %pg(%llu)"
+				 " with %pg(%llu)\n",
 				 mdname(mddev),
-				 bdevname(rdev1->bdev,b),
+				 rdev1->bdev,
 				 (unsigned long long)rdev1->sectors,
-				 bdevname(rdev2->bdev,b2),
+				 rdev2->bdev,
 				 (unsigned long long)rdev2->sectors);
 			if (rdev2 == rdev1) {
 				pr_debug("md/raid0:%s:   END\n",
@@ -128,21 +128,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	pr_debug("md/raid0:%s: FINAL %d zones\n",
 		 mdname(mddev), conf->nr_strip_zones);
 
-	if (conf->nr_strip_zones == 1) {
-		conf->layout = RAID0_ORIG_LAYOUT;
-	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
-		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
-		conf->layout = mddev->layout;
-	} else if (default_layout == RAID0_ORIG_LAYOUT ||
-		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
-		conf->layout = default_layout;
-	} else {
-		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
-		       mdname(mddev));
-		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
-		err = -ENOTSUPP;
-		goto abort;
-	}
 	/*
 	 * now since we have the hard sector sizes, we can make sure
 	 * chunk size is a multiple of that sector size
@@ -240,15 +225,15 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		for (j=0; j<cnt; j++) {
 			rdev = conf->devlist[j];
 			if (rdev->sectors <= zone->dev_start) {
-				pr_debug("md/raid0:%s: checking %s ... nope\n",
+				pr_debug("md/raid0:%s: checking %pg ... nope\n",
 					 mdname(mddev),
-					 bdevname(rdev->bdev, b));
+					 rdev->bdev);
 				continue;
 			}
-			pr_debug("md/raid0:%s: checking %s ..."
+			pr_debug("md/raid0:%s: checking %pg ..."
 				 " contained as device %d\n",
 				 mdname(mddev),
-				 bdevname(rdev->bdev, b), c);
+				 rdev->bdev, c);
 			dev[c] = rdev;
 			c++;
 			if (!smallest || rdev->sectors < smallest->sectors) {
@@ -273,6 +258,34 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 			 (unsigned long long)smallest->sectors);
 	}
 
+	if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) {
+		conf->layout = RAID0_ORIG_LAYOUT;
+	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = mddev->layout;
+	} else if (default_layout == RAID0_ORIG_LAYOUT ||
+		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = default_layout;
+	} else {
+		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
+		       mdname(mddev));
+		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
+		err = -EOPNOTSUPP;
+		goto abort;
+	}
+
+	if (conf->layout == RAID0_ORIG_LAYOUT) {
+		for (i = 1; i < conf->nr_strip_zones; i++) {
+			sector_t first_sector = conf->strip_zone[i-1].zone_end;
+
+			sector_div(first_sector, mddev->chunk_sectors);
+			zone = conf->strip_zone + i;
+			/* disk_shift is first disk index used in the zone */
+			zone->disk_shift = sector_div(first_sector,
+						      zone->nb_dev);
+		}
+	}
+
 	pr_debug("md/raid0:%s: done.\n", mdname(mddev));
 	*private_conf = conf;
 
@@ -356,7 +369,34 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	return array_sectors;
 }
 
-static void raid0_free(struct mddev *mddev, void *priv);
+static void raid0_free(struct mddev *mddev, void *priv)
+{
+	struct r0conf *conf = priv;
+
+	kfree(conf->strip_zone);
+	kfree(conf->devlist);
+	kfree(conf);
+}
+
+static int raid0_set_limits(struct mddev *mddev)
+{
+	struct queue_limits lim;
+	int err;
+
+	md_init_stacking_limits(&lim);
+	lim.max_hw_sectors = mddev->chunk_sectors;
+	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
+	lim.max_hw_wzeroes_unmap_sectors = mddev->chunk_sectors;
+	lim.logical_block_size = mddev->logical_block_size;
+	lim.io_min = mddev->chunk_sectors << 9;
+	lim.io_opt = lim.io_min * mddev->raid_disks;
+	lim.chunk_sectors = mddev->chunk_sectors;
+	lim.features |= BLK_FEAT_ATOMIC_WRITES;
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err)
+		return err;
+	return queue_limits_set(mddev->gendisk->queue, &lim);
+}
 
 static int raid0_run(struct mddev *mddev)
 {
@@ -370,6 +410,12 @@ static int raid0_run(struct mddev *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 
+	if (!mddev_is_dm(mddev)) {
+		ret = raid0_set_limits(mddev);
+		if (ret)
+			return ret;
+	}
+
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
 		ret = create_strip_zones(mddev, &conf);
@@ -378,30 +424,6 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
-	if (mddev->queue) {
-		struct md_rdev *rdev;
-		bool discard_supported = false;
-
-		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_discard_sectors(mddev->queue, UINT_MAX);
-
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		blk_queue_io_opt(mddev->queue,
-				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-			if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
-				discard_supported = true;
-		}
-		if (!discard_supported)
-			blk_queue_flag_clear(QUEUE_FLAG_DISCARD, mddev->queue);
-		else
-			blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
-	}
 
 	/* calculate array device size */
 	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
@@ -412,18 +434,21 @@ static int raid0_run(struct mddev *mddev)
 
 	dump_zones(mddev);
 
-	ret = md_integrity_register(mddev);
-
-	return ret;
+	return md_integrity_register(mddev);
 }
 
-static void raid0_free(struct mddev *mddev, void *priv)
+/*
+ * Convert disk_index to the disk order in which it is read/written.
+ *  For example, if we have 4 disks, they are numbered 0,1,2,3. If we
+ *  write the disks starting at disk 3, then the read/write order would
+ *  be disk 3, then 0, then 1, and then disk 2 and we want map_disk_shift()
+ *  to map the disks as follows 0,1,2,3 => 1,2,3,0. So disk 0 would map
+ *  to 1, 1 to 2, 2 to 3, and 3 to 0. That way we can compare disks in
+ *  that 'output' space to understand the read/write disk ordering.
+ */
+static int map_disk_shift(int disk_index, int num_disks, int disk_shift)
 {
-	struct r0conf *conf = priv;
-
-	kfree(conf->strip_zone);
-	kfree(conf->devlist);
-	kfree(conf);
+	return ((disk_index + num_disks - disk_shift) % num_disks);
 }
 
 static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
@@ -439,20 +464,24 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 	sector_t end_disk_offset;
 	unsigned int end_disk_index;
 	unsigned int disk;
+	sector_t orig_start, orig_end;
 
+	orig_start = start;
 	zone = find_zone(conf, &start);
 
 	if (bio_end_sector(bio) > zone->zone_end) {
-		struct bio *split = bio_split(bio,
-			zone->zone_end - bio->bi_iter.bi_sector, GFP_NOIO,
-			&mddev->bio_set);
-		bio_chain(split, bio);
-		submit_bio_noacct(bio);
-		bio = split;
+		bio = bio_submit_split_bioset(bio,
+				zone->zone_end - bio->bi_iter.bi_sector,
+				&mddev->bio_set);
+		if (!bio)
+			return;
+
 		end = zone->zone_end;
-	} else
+	} else {
 		end = bio_end_sector(bio);
+	}
 
+	orig_end = end;
 	if (zone != conf->strip_zone)
 		end = end - zone[-1].zone_end;
 
@@ -464,13 +493,26 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 	last_stripe_index = end;
 	sector_div(last_stripe_index, stripe_size);
 
-	start_disk_index = (int)(start - first_stripe_index * stripe_size) /
-		mddev->chunk_sectors;
+	/* In the first zone the original and alternate layouts are the same */
+	if ((conf->layout == RAID0_ORIG_LAYOUT) && (zone != conf->strip_zone)) {
+		sector_div(orig_start, mddev->chunk_sectors);
+		start_disk_index = sector_div(orig_start, zone->nb_dev);
+		start_disk_index = map_disk_shift(start_disk_index,
+						  zone->nb_dev,
+						  zone->disk_shift);
+		sector_div(orig_end, mddev->chunk_sectors);
+		end_disk_index = sector_div(orig_end, zone->nb_dev);
+		end_disk_index = map_disk_shift(end_disk_index,
+						zone->nb_dev, zone->disk_shift);
+	} else {
+		start_disk_index = (int)(start - first_stripe_index * stripe_size) /
+			mddev->chunk_sectors;
+		end_disk_index = (int)(end - last_stripe_index * stripe_size) /
+			mddev->chunk_sectors;
+	}
 	start_disk_offset = ((int)(start - first_stripe_index * stripe_size) %
 		mddev->chunk_sectors) +
 		first_stripe_index * mddev->chunk_sectors;
-	end_disk_index = (int)(end - last_stripe_index * stripe_size) /
-		mddev->chunk_sectors;
 	end_disk_offset = ((int)(end - last_stripe_index * stripe_size) %
 		mddev->chunk_sectors) +
 		last_stripe_index * mddev->chunk_sectors;
@@ -478,18 +520,22 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 	for (disk = 0; disk < zone->nb_dev; disk++) {
 		sector_t dev_start, dev_end;
 		struct md_rdev *rdev;
+		int compare_disk;
 
-		if (disk < start_disk_index)
+		compare_disk = map_disk_shift(disk, zone->nb_dev,
+					      zone->disk_shift);
+
+		if (compare_disk < start_disk_index)
 			dev_start = (first_stripe_index + 1) *
 				mddev->chunk_sectors;
-		else if (disk > start_disk_index)
+		else if (compare_disk > start_disk_index)
 			dev_start = first_stripe_index * mddev->chunk_sectors;
 		else
 			dev_start = start_disk_offset;
 
-		if (disk < end_disk_index)
+		if (compare_disk < end_disk_index)
 			dev_end = (last_stripe_index + 1) * mddev->chunk_sectors;
-		else if (disk > end_disk_index)
+		else if (compare_disk > end_disk_index)
 			dev_end = last_stripe_index * mddev->chunk_sectors;
 		else
 			dev_end = end_disk_offset;
@@ -506,14 +552,47 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 	bio_endio(bio);
 }
 
-static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
+static void raid0_map_submit_bio(struct mddev *mddev, struct bio *bio)
 {
 	struct r0conf *conf = mddev->private;
 	struct strip_zone *zone;
 	struct md_rdev *tmp_dev;
-	sector_t bio_sector;
+	sector_t bio_sector = bio->bi_iter.bi_sector;
+	sector_t sector = bio_sector;
+
+	md_account_bio(mddev, &bio);
+
+	zone = find_zone(mddev->private, &sector);
+	switch (conf->layout) {
+	case RAID0_ORIG_LAYOUT:
+		tmp_dev = map_sector(mddev, zone, bio_sector, &sector);
+		break;
+	case RAID0_ALT_MULTIZONE_LAYOUT:
+		tmp_dev = map_sector(mddev, zone, sector, &sector);
+		break;
+	default:
+		WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev));
+		bio_io_error(bio);
+		return;
+	}
+
+	if (unlikely(is_rdev_broken(tmp_dev))) {
+		bio_io_error(bio);
+		md_error(mddev, tmp_dev);
+		return;
+	}
+
+	bio_set_dev(bio, tmp_dev->bdev);
+	bio->bi_iter.bi_sector = sector + zone->dev_start +
+		tmp_dev->data_offset;
+	mddev_trace_remap(mddev, bio, bio_sector);
+	mddev_check_write_zeroes(mddev, bio);
+	submit_bio_noacct(bio);
+}
+
+static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
+{
 	sector_t sector;
-	sector_t orig_sector;
 	unsigned chunk_sects;
 	unsigned sectors;
 
@@ -526,8 +605,7 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		return true;
 	}
 
-	bio_sector = bio->bi_iter.bi_sector;
-	sector = bio_sector;
+	sector = bio->bi_iter.bi_sector;
 	chunk_sects = mddev->chunk_sectors;
 
 	sectors = chunk_sects -
@@ -535,50 +613,14 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio)
 		 ? (sector & (chunk_sects-1))
 		 : sector_div(sector, chunk_sects));
 
-	/* Restore due to sector_div */
-	sector = bio_sector;
-
 	if (sectors < bio_sectors(bio)) {
-		struct bio *split = bio_split(bio, sectors, GFP_NOIO,
+		bio = bio_submit_split_bioset(bio, sectors,
 					      &mddev->bio_set);
-		bio_chain(split, bio);
-		submit_bio_noacct(bio);
-		bio = split;
+		if (!bio)
+			return true;
 	}
 
-	if (bio->bi_pool != &mddev->bio_set)
-		md_account_bio(mddev, &bio);
-
-	orig_sector = sector;
-	zone = find_zone(mddev->private, &sector);
-	switch (conf->layout) {
-	case RAID0_ORIG_LAYOUT:
-		tmp_dev = map_sector(mddev, zone, orig_sector, &sector);
-		break;
-	case RAID0_ALT_MULTIZONE_LAYOUT:
-		tmp_dev = map_sector(mddev, zone, sector, &sector);
-		break;
-	default:
-		WARN(1, "md/raid0:%s: Invalid layout\n", mdname(mddev));
-		bio_io_error(bio);
-		return true;
-	}
-
-	if (unlikely(is_mddev_broken(tmp_dev, "raid0"))) {
-		bio_io_error(bio);
-		return true;
-	}
-
-	bio_set_dev(bio, tmp_dev->bdev);
-	bio->bi_iter.bi_sector = sector + zone->dev_start +
-		tmp_dev->data_offset;
-
-	if (mddev->gendisk)
-		trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
-				      bio_sector);
-	mddev_check_writesame(mddev, bio);
-	mddev_check_write_zeroes(mddev, bio);
-	submit_bio_noacct(bio);
+	raid0_map_submit_bio(mddev, bio);
 	return true;
 }
 
@@ -588,6 +630,16 @@ static void raid0_status(struct seq_file *seq, struct mddev *mddev)
 	return;
 }
 
+static void raid0_error(struct mddev *mddev, struct md_rdev *rdev)
+{
+	if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
+		char *md_name = mdname(mddev);
+
+		pr_crit("md/raid0%s: Disk failure on %pg detected, failing array.\n",
+			md_name, rdev->bdev);
+	}
+}
+
 static void *raid0_takeover_raid45(struct mddev *mddev)
 {
 	struct md_rdev *rdev;
@@ -617,7 +669,7 @@ static void *raid0_takeover_raid45(struct mddev *mddev)
 	mddev->raid_disks--;
 	mddev->delta_disks = -1;
 	/* make sure it will be not marked as dirty */
-	mddev->recovery_cp = MaxSector;
+	mddev->resync_offset = MaxSector;
 	mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
 
 	create_strip_zones(mddev, &priv_conf);
@@ -660,7 +712,7 @@ static void *raid0_takeover_raid10(struct mddev *mddev)
 	mddev->raid_disks += mddev->delta_disks;
 	mddev->degraded = 0;
 	/* make sure it will be not marked as dirty */
-	mddev->recovery_cp = MaxSector;
+	mddev->resync_offset = MaxSector;
 	mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
 
 	create_strip_zones(mddev, &priv_conf);
@@ -703,7 +755,7 @@ static void *raid0_takeover_raid1(struct mddev *mddev)
 	mddev->delta_disks = 1 - mddev->raid_disks;
 	mddev->raid_disks = 1;
 	/* make sure it will be not marked as dirty */
-	mddev->recovery_cp = MaxSector;
+	mddev->resync_offset = MaxSector;
 	mddev_clear_unsupported_flags(mddev, UNSUPPORTED_MDDEV_FLAGS);
 
 	create_strip_zones(mddev, &priv_conf);
@@ -753,9 +805,13 @@ static void raid0_quiesce(struct mddev *mddev, int quiesce)
 
 static struct md_personality raid0_personality=
 {
-	.name		= "raid0",
-	.level		= 0,
-	.owner		= THIS_MODULE,
+	.head = {
+		.type	= MD_PERSONALITY,
+		.id	= ID_RAID0,
+		.name	= "raid0",
+		.owner	= THIS_MODULE,
+	},
+
 	.make_request	= raid0_make_request,
 	.run		= raid0_run,
 	.free		= raid0_free,
@@ -763,16 +819,17 @@ static struct md_personality raid0_personality=
 	.size		= raid0_size,
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
+	.error_handler	= raid0_error,
 };
 
-static int __init raid0_init (void)
+static int __init raid0_init(void)
 {
-	return register_md_personality (&raid0_personality);
+	return register_md_submodule(&raid0_personality.head);
 }
 
-static void raid0_exit (void)
+static void __exit raid0_exit(void)
 {
-	unregister_md_personality (&raid0_personality);
+	unregister_md_submodule(&raid0_personality.head);
 }
 
 module_init(raid0_init);