dm raid: add support for the MD RAID0 personality

Add dm-raid access to the MD RAID0 personality to enable single zone
striping.

The following changes enable that access:
- add type definition to raid_types array
- make bitmap creation conditonal in super_validate(), because
bitmaps are not allowed in raid0
- set rdev->sectors to the data image size in super_validate()
to allow the raid0 personality to calculate the MD array
size properly
- use mdddev(un)lock() functions instead of direct mutex_(un)lock()
(wrapped in here because it's a trivial change)
- enhance raid_status() to always report full sync for raid0
so that userspace checks for 100% sync will succeed and allow
for resize (and takeover/reshape once added in future paches)
- enhance raid_resume() to not load bitmap in case of raid0
- add merge function to avoid data corruption (seen with readahead)
that resulted from bio payloads that grew too large. This problem
did not occur with the other raid levels because it either did not
apply without striping (raid1) or was avoided via stripe caching.
- raise version to 1.7.0 because of the raid0 API change

Signed-off-by: Heinz Mauelshagen <[e-mail]>
Reviewed-by: Jonathan Brassow <[e-mail]>
Signed-off-by: Mike Snitzer <[e-mail]>

Documentation/device-mapper/dm-raid.txt

···
 1.5.1   Add ability to restore transiently failed devices on resume.
 1.5.2   'mismatch_cnt' is zero unless [last_]sync_action is "check".
 1.6.0   Add discard support (and devices_handle_discard_safely module param).
+1.7.0   Add support for MD RAID0 mappings.

drivers/md/dm-raid.c

···
 /*
  * Copyright (C) 2010-2011 Neil Brown
- * Copyright (C) 2010-2014 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2010-2015 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
···
 	const unsigned level;		/* RAID level. */
 	const unsigned algorithm;	/* RAID algorithm. */
 } raid_types[] = {
+	{"raid0",    "RAID0 (striping)",                0, 2, 0, 0 /* NONE */},
 	{"raid1",    "RAID1 (mirroring)",               0, 2, 1, 0 /* NONE */},
 	{"raid10",   "RAID10 (striped mirrors)",        0, 2, 10, UINT_MAX /* Varies */},
 	{"raid4",    "RAID4 (dedicated parity disk)",	1, 2, 5, ALGORITHM_PARITY_0},
···
 		rs->md.layout = raid10_format_to_md_layout(raid10_format,
 							   raid10_copies);
 		rs->md.new_layout = rs->md.layout;
-	} else if ((rs->raid_type->level > 1) &&
+	} else if ((!rs->raid_type->level || rs->raid_type->level > 1) &&
 		   sector_div(sectors_per_dev,
 			      (rs->md.raid_disks - rs->raid_type->parity_devs))) {
 		rs->ti->error = "Target length not divisible by number of data devices";
···
 	return 0;
 }
 
-static int super_validate(struct mddev *mddev, struct md_rdev *rdev)
+static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
 {
+	struct mddev *mddev = &rs->md;
 	struct dm_raid_superblock *sb = page_address(rdev->sb_page);
 
 	/*
···
 	if (!mddev->events && super_init_validation(mddev, rdev))
 		return -EINVAL;
 
-	mddev->bitmap_info.offset = 4096 >> 9; /* Enable bitmap creation */
-	rdev->mddev->bitmap_info.default_offset = 4096 >> 9;
+	/* Enable bitmap creation for RAID levels != 0 */
+	mddev->bitmap_info.offset = (rs->raid_type->level) ? to_sector(4096) : 0;
+	rdev->mddev->bitmap_info.default_offset = mddev->bitmap_info.offset;
+
 	if (!test_bit(FirstUse, &rdev->flags)) {
 		rdev->recovery_offset = le64_to_cpu(sb->disk_recovery_offset);
 		if (rdev->recovery_offset != MaxSector)
···
 		 * that the "sync" directive is disallowed during the
 		 * reshape.
 		 */
+		rdev->sectors = to_sector(i_size_read(rdev->bdev->bd_inode));
+
 		if (rs->ctr_flags & CTR_FLAG_SYNC)
 			continue;
 
···
 	 * validation for the remaining devices.
 	 */
 	ti->error = "Unable to assemble array: Invalid superblocks";
-	if (super_validate(mddev, freshest))
+	if (super_validate(rs, freshest))
 		return -EINVAL;
 
 	rdev_for_each(rdev, mddev)
-		if ((rdev != freshest) && super_validate(mddev, rdev))
+		if ((rdev != freshest) && super_validate(rs, rdev))
 			return -EINVAL;
 
 	return 0;
···
 	 */
 	configure_discard_support(ti, rs);
 
-	mutex_lock(&rs->md.reconfig_mutex);
+	/* Has to be held on running the array */
+	mddev_lock_nointr(&rs->md);
 	ret = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
-	mutex_unlock(&rs->md.reconfig_mutex);
+	mddev_unlock(&rs->md);
 
 	if (ret) {
 		ti->error = "Fail to run raid array";
···
 	case STATUSTYPE_INFO:
 		DMEMIT("%s %d ", rs->raid_type->name, rs->md.raid_disks);
 
-		if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery))
-			sync = rs->md.curr_resync_completed;
-		else
-			sync = rs->md.recovery_cp;
+		if (rs->raid_type->level) {
+			if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery))
+				sync = rs->md.curr_resync_completed;
+			else
+				sync = rs->md.recovery_cp;
 
-		if (sync >= rs->md.resync_max_sectors) {
-			/*
-			 * Sync complete.
-			 */
+			if (sync >= rs->md.resync_max_sectors) {
+				/*
+				 * Sync complete.
+				 */
+				array_in_sync = 1;
+				sync = rs->md.resync_max_sectors;
+			} else if (test_bit(MD_RECOVERY_REQUESTED, &rs->md.recovery)) {
+				/*
+				 * If "check" or "repair" is occurring, the array has
+				 * undergone and initial sync and the health characters
+				 * should not be 'a' anymore.
+				 */
+				array_in_sync = 1;
+			} else {
+				/*
+				 * The array may be doing an initial sync, or it may
+				 * be rebuilding individual components.  If all the
+				 * devices are In_sync, then it is the array that is
+				 * being initialized.
+				 */
+				for (i = 0; i < rs->md.raid_disks; i++)
+					if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
+						array_in_sync = 1;
+			}
+		} else {
+			/* RAID0 */
 			array_in_sync = 1;
 			sync = rs->md.resync_max_sectors;
-		} else if (test_bit(MD_RECOVERY_REQUESTED, &rs->md.recovery)) {
-			/*
-			 * If "check" or "repair" is occurring, the array has
-			 * undergone and initial sync and the health characters
-			 * should not be 'a' anymore.
-			 */
-			array_in_sync = 1;
-		} else {
-			/*
-			 * The array may be doing an initial sync, or it may
-			 * be rebuilding individual components.  If all the
-			 * devices are In_sync, then it is the array that is
-			 * being initialized.
-			 */
-			for (i = 0; i < rs->md.raid_disks; i++)
-				if (!test_bit(In_sync, &rs->dev[i].rdev.flags))
-					array_in_sync = 1;
 		}
 
 		/*
···
 {
 	struct raid_set *rs = ti->private;
 
-	set_bit(MD_CHANGE_DEVS, &rs->md.flags);
-	if (!rs->bitmap_loaded) {
-		bitmap_load(&rs->md);
-		rs->bitmap_loaded = 1;
-	} else {
-		/*
-		 * A secondary resume while the device is active.
-		 * Take this opportunity to check whether any failed
-		 * devices are reachable again.
-		 */
-		attempt_restore_of_faulty_devices(rs);
+	if (rs->raid_type->level) {
+		set_bit(MD_CHANGE_DEVS, &rs->md.flags);
+
+		if (!rs->bitmap_loaded) {
+			bitmap_load(&rs->md);
+			rs->bitmap_loaded = 1;
+		} else {
+			/*
+			 * A secondary resume while the device is active.
+			 * Take this opportunity to check whether any failed
+			 * devices are reachable again.
+			 */
+			attempt_restore_of_faulty_devices(rs);
+		}
+
+		clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
 	}
 
-	clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
 	mddev_resume(&rs->md);
+}
+
+static int raid_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
+		      struct bio_vec *biovec, int max_size)
+{
+	struct raid_set *rs = ti->private;
+	struct md_personality *pers = rs->md.pers;
+
+	if (pers && pers->mergeable_bvec)
+		return min(max_size, pers->mergeable_bvec(&rs->md, bvm, biovec));
+
+	/*
+	 * In case we can't request the personality because
+	 * the raid set is not running yet
+	 *
+	 * -> return safe minimum
+	 */
+	return rs->md.chunk_sectors;
 }
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 6, 0},
+	.version = {1, 7, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
···
 	.presuspend = raid_presuspend,
 	.postsuspend = raid_postsuspend,
 	.resume = raid_resume,
+	.merge = raid_merge,
 };
 
 static int __init dm_raid_init(void)