md: add ->takeover method to support changing the personality managing an array

Implement this for RAID6 to be able to 'takeover' a RAID5 array.  The
new RAID6 will use a layout which places Q on the last device, and
that device will be missing.
If there are any available spares, one will immediately have Q
recovered onto it.

Signed-off-by: NeilBrown <neilb@suse.de>

3 files changed, 161 insertions, 14 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6cb31f8da14c..05b613b5e4b2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2649,18 +2649,101 @@ level_show(mddev_t *mddev, char *page)
 static ssize_t
 level_store(mddev_t *mddev, const char *buf, size_t len)
 {
+	char level[16];
 	ssize_t rv = len;
-	if (mddev->pers)
+	struct mdk_personality *pers;
+	void *priv;
+
+	if (mddev->pers == NULL) {
+		if (len == 0)
+			return 0;
+		if (len >= sizeof(mddev->clevel))
+			return -ENOSPC;
+		strncpy(mddev->clevel, buf, len);
+		if (mddev->clevel[len-1] == '\n')
+			len--;
+		mddev->clevel[len] = 0;
+		mddev->level = LEVEL_NONE;
+		return rv;
+	}
+
+	/* request to change the personality.  Need to ensure:
+	 *  - array is not engaged in resync/recovery/reshape
+	 *  - old personality can be suspended
+	 *  - new personality will access other array.
+	 */
+
+	if (mddev->sync_thread || mddev->reshape_position != MaxSector)
 		return -EBUSY;
-	if (len == 0)
-		return 0;
-	if (len >= sizeof(mddev->clevel))
-		return -ENOSPC;
-	strncpy(mddev->clevel, buf, len);
-	if (mddev->clevel[len-1] == '\n')
+
+	if (!mddev->pers->quiesce) {
+		printk(KERN_WARNING "md: %s: %s does not support online personality change\n",
+		       mdname(mddev), mddev->pers->name);
+		return -EINVAL;
+	}
+
+	/* Now find the new personality */
+	if (len == 0 || len >= sizeof(level))
+		return -EINVAL;
+	strncpy(level, buf, len);
+	if (level[len-1] == '\n')
 		len--;
-	mddev->clevel[len] = 0;
-	mddev->level = LEVEL_NONE;
+	level[len] = 0;
+
+	request_module("md-%s", level);
+	spin_lock(&pers_lock);
+	pers = find_pers(LEVEL_NONE, level);
+	if (!pers || !try_module_get(pers->owner)) {
+		spin_unlock(&pers_lock);
+		printk(KERN_WARNING "md: personality %s not loaded\n", level);
+		return -EINVAL;
+	}
+	spin_unlock(&pers_lock);
+
+	if (pers == mddev->pers) {
+		/* Nothing to do! */
+		module_put(pers->owner);
+		return rv;
+	}
+	if (!pers->takeover) {
+		module_put(pers->owner);
+		printk(KERN_WARNING "md: %s: %s does not support personality takeover\n",
+		       mdname(mddev), level);
+		return -EINVAL;
+	}
+
+	/* ->takeover must set new_* and/or delta_disks
+	 * if it succeeds, and may set them when it fails.
+	 */
+	priv = pers->takeover(mddev);
+	if (IS_ERR(priv)) {
+		mddev->new_level = mddev->level;
+		mddev->new_layout = mddev->layout;
+		mddev->new_chunk = mddev->chunk_size;
+		mddev->raid_disks -= mddev->delta_disks;
+		mddev->delta_disks = 0;
+		module_put(pers->owner);
+		printk(KERN_WARNING "md: %s: %s would not accept array\n",
+		       mdname(mddev), level);
+		return PTR_ERR(priv);
+	}
+
+	/* Looks like we have a winner */
+	mddev_suspend(mddev);
+	mddev->pers->stop(mddev);
+	module_put(mddev->pers->owner);
+	mddev->pers = pers;
+	mddev->private = priv;
+	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+	mddev->level = mddev->new_level;
+	mddev->layout = mddev->new_layout;
+	mddev->chunk_size = mddev->new_chunk;
+	mddev->delta_disks = 0;
+	pers->run(mddev);
+	mddev_resume(mddev);
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
 	return rv;
 }
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 84b22d67ba14..8034f62a9d28 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -321,6 +321,16 @@ struct mdk_personality
 	 * others - reserved
 	 */
 	void (*quiesce) (mddev_t *mddev, int state);
+	/* takeover is used to transition an array from one
+	 * personality to another.  The new personality must be able
+	 * to handle the data in the current layout.
+	 * e.g. 2drive raid1 -> 2drive raid5
+	 *      ndrive raid5 -> degraded n+1drive raid6 with special layout
+	 * If the takeover succeeds, a new 'private' structure is returned.
+	 * This needs to be installed and then ->run used to activate the
+	 * array.
+	 */
+	void *(*takeover) (mddev_t *mddev);
 };
 
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 81789fa7a023..5b346b41e515 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -933,8 +933,10 @@ static int grow_stripes(raid5_conf_t *conf, int num)
 	struct kmem_cache *sc;
 	int devs = conf->raid_disks;
 
-	sprintf(conf->cache_name[0], "raid5-%s", mdname(conf->mddev));
-	sprintf(conf->cache_name[1], "raid5-%s-alt", mdname(conf->mddev));
+	sprintf(conf->cache_name[0],
+		"raid%d-%s", conf->level, mdname(conf->mddev));
+	sprintf(conf->cache_name[1],
+		"raid%d-%s-alt", conf->level, mdname(conf->mddev));
 	conf->active_name = 0;
 	sc = kmem_cache_create(conf->cache_name[conf->active_name],
 			       sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
@@ -4361,10 +4363,12 @@ static int run(mddev_t *mddev)
 		BUG_ON(mddev->chunk_size != mddev->new_chunk);
 		BUG_ON(mddev->delta_disks != 0);
 	}
-	conf = setup_conf(mddev);
 
-	if (conf == NULL)
-		return -EIO;
+	if (mddev->private == NULL)
+		conf = setup_conf(mddev);
+	else
+		conf = mddev->private;
+
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
 
@@ -4880,6 +4884,55 @@ static void raid5_quiesce(mddev_t *mddev, int state)
 	}
 }
 
+static struct mdk_personality raid5_personality;
+
+static void *raid6_takeover(mddev_t *mddev)
+{
+	/* Currently can only take over a raid5.  We map the
+	 * personality to an equivalent raid6 personality
+	 * with the Q block at the end.
+	 */
+	int new_layout;
+
+	if (mddev->pers != &raid5_personality)
+		return ERR_PTR(-EINVAL);
+	if (mddev->degraded > 1)
+		return ERR_PTR(-EINVAL);
+	if (mddev->raid_disks > 253)
+		return ERR_PTR(-EINVAL);
+	if (mddev->raid_disks < 3)
+		return ERR_PTR(-EINVAL);
+
+	switch (mddev->layout) {
+	case ALGORITHM_LEFT_ASYMMETRIC:
+		new_layout = ALGORITHM_LEFT_ASYMMETRIC_6;
+		break;
+	case ALGORITHM_RIGHT_ASYMMETRIC:
+		new_layout = ALGORITHM_RIGHT_ASYMMETRIC_6;
+		break;
+	case ALGORITHM_LEFT_SYMMETRIC:
+		new_layout = ALGORITHM_LEFT_SYMMETRIC_6;
+		break;
+	case ALGORITHM_RIGHT_SYMMETRIC:
+		new_layout = ALGORITHM_RIGHT_SYMMETRIC_6;
+		break;
+	case ALGORITHM_PARITY_0:
+		new_layout = ALGORITHM_PARITY_0_6;
+		break;
+	case ALGORITHM_PARITY_N:
+		new_layout = ALGORITHM_PARITY_N;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+	mddev->new_level = 6;
+	mddev->new_layout = new_layout;
+	mddev->delta_disks = 1;
+	mddev->raid_disks += 1;
+	return setup_conf(mddev);
+}
+
+
 static struct mdk_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -4900,6 +4953,7 @@ static struct mdk_personality raid6_personality =
 	.start_reshape  = raid5_start_reshape,
 #endif
 	.quiesce	= raid5_quiesce,
+	.takeover	= raid6_takeover,
 };
 static struct mdk_personality raid5_personality =
 {