Merge tag 'md/4.4' of git://neil.brown.name/md

Pull md updates from Neil Brown:
"Two major components to this update.

1) The clustered-raid1 support from SUSE is nearly complete. There
are a few outstanding issues being worked on. Maybe half a dozen
patches will bring this to a usable state.

2) The first stage of journalled-raid5 support from Facebook makes an
appearance. With a journal device configured (typically NVRAM or
SSD), the "RAID5 write hole" should be closed - a crash during
degraded operations cannot result in data corruption.

The next stage will be to use the journal as a write-behind cache
so that latency can be reduced and in some cases throughput
increased by performing more full-stripe writes.

* tag 'md/4.4' of git://neil.brown.name/md: (66 commits)
MD: when RAID journal is missing/faulty, block RESTART_ARRAY_RW
MD: set journal disk ->raid_disk
MD: kick out journal disk if it's not fresh
raid5-cache: start raid5 readonly if journal is missing
MD: add new bit to indicate raid array with journal
raid5-cache: IO error handling
raid5: journal disk can't be removed
raid5-cache: add trim support for log
MD: fix info output for journal disk
raid5-cache: use bio chaining
raid5-cache: small log->seq cleanup
raid5-cache: new helper: r5_reserve_log_entry
raid5-cache: inline r5l_alloc_io_unit into r5l_new_meta
raid5-cache: take rdev->data_offset into account early on
raid5-cache: refactor bio allocation
raid5-cache: clean up r5l_get_meta
raid5-cache: simplify state machine when caches flushes are not needed
raid5-cache: factor out a helper to run all stripes for an I/O unit
raid5-cache: rename flushed_ios to finished_ios
raid5-cache: free I/O units earlier
...

drivers/md/Makefile

···
 dm-cache-cleaner-y += dm-cache-policy-cleaner.o
 dm-era-y	+= dm-era-target.o
 md-mod-y	+= md.o bitmap.o
-raid456-y	+= raid5.o
+raid456-y	+= raid5.o raid5-cache.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 

drivers/md/bitmap.c

···
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
-	/* XXX: This is a hack to ensure that we don't use clustering
-	 *  in case:
-	 *	- dm-raid is in use and
-	 *	- the nodes written in bitmap_sb is erroneous.
+	/* Setup nodes/clustername only if bitmap version is
+	 * cluster-compatible
 	 */
-	if (!bitmap->mddev->sync_super) {
+	if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) {
 		nodes = le32_to_cpu(sb->nodes);
 		strlcpy(bitmap->mddev->bitmap_info.cluster_name,
 				sb->cluster_name, 64);
···
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
 		reason = "bad magic";
 	else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
-		 le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
+		 le32_to_cpu(sb->version) > BITMAP_MAJOR_CLUSTERED)
 		reason = "unrecognized superblock version";
 	else if (chunksize < 512)
 		reason = "bitmap chunksize too small";
···
 }
 EXPORT_SYMBOL(bitmap_close_sync);
 
-void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
+void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)
 {
 	sector_t s = 0;
 	sector_t blocks;
···
 		bitmap->last_end_sync = jiffies;
 		return;
 	}
-	if (time_before(jiffies, (bitmap->last_end_sync
+	if (!force && time_before(jiffies, (bitmap->last_end_sync
 				  + bitmap->mddev->bitmap_info.daemon_sleep)))
 		return;
 	wait_event(bitmap->mddev->recovery_wait,

drivers/md/bitmap.h

···
 #define BITMAP_MAJOR_LO 3
 /* version 4 insists the bitmap is in little-endian order
  * with version 3, it is host-endian which is non-portable
+ * Version 5 is currently set only for clustered devices
  */
 #define BITMAP_MAJOR_HI 4
+#define BITMAP_MAJOR_CLUSTERED 5
 #define	BITMAP_MAJOR_HOSTENDIAN 3
 
 /*
···
 int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int degraded);
 void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted);
 void bitmap_close_sync(struct bitmap *bitmap);
-void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
+void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force);
 
 void bitmap_unplug(struct bitmap *bitmap);
 void bitmap_daemon_work(struct mddev *mddev);

drivers/md/md-cluster.c

···
 	struct completion completion; /* completion for synchronized locking */
 	void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
 	struct mddev *mddev; /* pointing back to mddev. */
+	int mode;
 };
 
 struct suspend_info {
···
 	dlm_lockspace_t *lockspace;
 	int slot_number;
 	struct completion completion;
-	struct mutex sb_mutex;
 	struct dlm_lock_resource *bitmap_lockres;
+	struct dlm_lock_resource *resync_lockres;
 	struct list_head suspend_list;
 	spinlock_t suspend_lock;
 	struct md_thread *recovery_thread;
···
 };
 
 struct cluster_msg {
-	int type;
-	int slot;
+	__le32 type;
+	__le32 slot;
 	/* TODO: Unionize this for smaller footprint */
-	sector_t low;
-	sector_t high;
+	__le64 low;
+	__le64 high;
 	char uuid[16];
-	int raid_slot;
+	__le32 raid_slot;
 };
 
 static void sync_ast(void *arg)
 {
 	struct dlm_lock_resource *res;
 
-	res = (struct dlm_lock_resource *) arg;
+	res = arg;
 	complete(&res->completion);
 }
 
···
 	if (ret)
 		return ret;
 	wait_for_completion(&res->completion);
+	if (res->lksb.sb_status == 0)
+		res->mode = mode;
 	return res->lksb.sb_status;
 }
 
···
 	init_completion(&res->completion);
 	res->ls = cinfo->lockspace;
 	res->mddev = mddev;
+	res->mode = DLM_LOCK_IV;
 	namelen = strlen(name);
 	res->name = kzalloc(namelen + 1, GFP_KERNEL);
 	if (!res->name) {
···
 	kfree(res);
 }
 
-static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres,
-		sector_t lo, sector_t hi)
+static void add_resync_info(struct dlm_lock_resource *lockres,
+			    sector_t lo, sector_t hi)
 {
 	struct resync_info *ri;
 
···
 	dlm_lock_sync(lockres, DLM_LOCK_CR);
 	memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info));
 	hi = le64_to_cpu(ri.hi);
-	if (ri.hi > 0) {
+	if (hi > 0) {
 		s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
 		if (!s)
 			goto out;
···
  */
 static void ack_bast(void *arg, int mode)
 {
-	struct dlm_lock_resource *res = (struct dlm_lock_resource *)arg;
+	struct dlm_lock_resource *res = arg;
 	struct md_cluster_info *cinfo = res->mddev->cluster_info;
 
 	if (mode == DLM_LOCK_EX)
···
 
 	list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
 		if (slot == s->slot) {
-			pr_info("%s:%d Deleting suspend_info: %d\n",
-					__func__, __LINE__, slot);
 			list_del(&s->list);
 			kfree(s);
 			break;
 		}
 }
 
-static void remove_suspend_info(struct md_cluster_info *cinfo, int slot)
+static void remove_suspend_info(struct mddev *mddev, int slot)
 {
+	struct md_cluster_info *cinfo = mddev->cluster_info;
 	spin_lock_irq(&cinfo->suspend_lock);
 	__remove_suspend_info(cinfo, slot);
 	spin_unlock_irq(&cinfo->suspend_lock);
+	mddev->pers->quiesce(mddev, 2);
 }
 
 
-static void process_suspend_info(struct md_cluster_info *cinfo,
+static void process_suspend_info(struct mddev *mddev,
 		int slot, sector_t lo, sector_t hi)
 {
+	struct md_cluster_info *cinfo = mddev->cluster_info;
 	struct suspend_info *s;
 
 	if (!hi) {
-		remove_suspend_info(cinfo, slot);
+		remove_suspend_info(mddev, slot);
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		md_wakeup_thread(mddev->thread);
 		return;
 	}
 	s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL);
···
 	s->slot = slot;
 	s->lo = lo;
 	s->hi = hi;
+	mddev->pers->quiesce(mddev, 1);
+	mddev->pers->quiesce(mddev, 0);
 	spin_lock_irq(&cinfo->suspend_lock);
 	/* Remove existing entry (if exists) before adding */
 	__remove_suspend_info(cinfo, slot);
 	list_add(&s->list, &cinfo->suspend_list);
 	spin_unlock_irq(&cinfo->suspend_lock);
+	mddev->pers->quiesce(mddev, 2);
 }
 
 static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
···
 
 	len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
 	sprintf(disk_uuid + len, "%pU", cmsg->uuid);
-	snprintf(raid_slot, 16, "RAID_DISK=%d", cmsg->raid_slot);
+	snprintf(raid_slot, 16, "RAID_DISK=%d", le32_to_cpu(cmsg->raid_slot));
 	pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot);
 	init_completion(&cinfo->newdisk_completion);
 	set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
···
 static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-
-	md_reload_sb(mddev);
+	md_reload_sb(mddev, le32_to_cpu(msg->raid_slot));
 	dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
 }
 
 static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
 {
-	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
+	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
+						   le32_to_cpu(msg->raid_slot));
 
 	if (rdev)
 		md_kick_rdev_from_array(rdev);
 	else
-		pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, msg->raid_slot);
+		pr_warn("%s: %d Could not find disk(%d) to REMOVE\n",
+			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
 }
 
 static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg)
 {
-	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
+	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
+						   le32_to_cpu(msg->raid_slot));
 
 	if (rdev && test_bit(Faulty, &rdev->flags))
 		clear_bit(Faulty, &rdev->flags);
 	else
-		pr_warn("%s: %d Could not find disk(%d) which is faulty", __func__, __LINE__, msg->raid_slot);
+		pr_warn("%s: %d Could not find disk(%d) which is faulty",
+			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
 }
 
 static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 {
-	switch (msg->type) {
+	if (WARN(mddev->cluster_info->slot_number - 1 == le32_to_cpu(msg->slot),
+		"node %d received it's own msg\n", le32_to_cpu(msg->slot)))
+		return;
+	switch (le32_to_cpu(msg->type)) {
 	case METADATA_UPDATED:
-		pr_info("%s: %d Received message: METADATA_UPDATE from %d\n",
-			__func__, __LINE__, msg->slot);
 		process_metadata_update(mddev, msg);
 		break;
 	case RESYNCING:
-		pr_info("%s: %d Received message: RESYNCING from %d\n",
-			__func__, __LINE__, msg->slot);
-		process_suspend_info(mddev->cluster_info, msg->slot,
-				msg->low, msg->high);
+		process_suspend_info(mddev, le32_to_cpu(msg->slot),
+				     le64_to_cpu(msg->low),
+				     le64_to_cpu(msg->high));
 		break;
 	case NEWDISK:
-		pr_info("%s: %d Received message: NEWDISK from %d\n",
-			__func__, __LINE__, msg->slot);
 		process_add_new_disk(mddev, msg);
 		break;
 	case REMOVE:
-		pr_info("%s: %d Received REMOVE from %d\n",
-			__func__, __LINE__, msg->slot);
 		process_remove_disk(mddev, msg);
 		break;
 	case RE_ADD:
-		pr_info("%s: %d Received RE_ADD from %d\n",
-			__func__, __LINE__, msg->slot);
 		process_readd_disk(mddev, msg);
 		break;
 	case BITMAP_NEEDS_SYNC:
-		pr_info("%s: %d Received BITMAP_NEEDS_SYNC from %d\n",
-			__func__, __LINE__, msg->slot);
-		__recover_slot(mddev, msg->slot);
+		__recover_slot(mddev, le32_to_cpu(msg->slot));
 		break;
 	default:
 		pr_warn("%s:%d Received unknown message from %d\n",
···
 /* lock_comm()
  * Takes the lock on the TOKEN lock resource so no other
  * node can communicate while the operation is underway.
+ * If called again, and the TOKEN lock is alread in EX mode
+ * return success. However, care must be taken that unlock_comm()
+ * is called only once.
  */
 static int lock_comm(struct md_cluster_info *cinfo)
 {
 	int error;
+
+	if (cinfo->token_lockres->mode == DLM_LOCK_EX)
+		return 0;
 
 	error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX);
 	if (error)
···
 
 static void unlock_comm(struct md_cluster_info *cinfo)
 {
+	WARN_ON(cinfo->token_lockres->mode != DLM_LOCK_EX);
 	dlm_unlock_sync(cinfo->token_lockres);
 }
 
···
 	init_completion(&cinfo->completion);
 	set_bit(MD_CLUSTER_BEGIN_JOIN_CLUSTER, &cinfo->state);
 
-	mutex_init(&cinfo->sb_mutex);
 	mddev->cluster_info = cinfo;
 
 	memset(str, 0, 64);
···
 		goto err;
 	}
 
+	cinfo->resync_lockres = lockres_init(mddev, "resync", NULL, 0);
+	if (!cinfo->resync_lockres)
+		goto err;
+
 	ret = gather_all_resync_info(mddev, nodes);
 	if (ret)
 		goto err;
···
 	lockres_free(cinfo->token_lockres);
 	lockres_free(cinfo->ack_lockres);
 	lockres_free(cinfo->no_new_dev_lockres);
+	lockres_free(cinfo->resync_lockres);
 	lockres_free(cinfo->bitmap_lockres);
 	if (cinfo->lockspace)
 		dlm_release_lockspace(cinfo->lockspace, 2);
···
 	return ret;
 }
 
+static void resync_bitmap(struct mddev *mddev)
+{
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+	struct cluster_msg cmsg = {0};
+	int err;
+
+	cmsg.type = cpu_to_le32(BITMAP_NEEDS_SYNC);
+	err = sendmsg(cinfo, &cmsg);
+	if (err)
+		pr_err("%s:%d: failed to send BITMAP_NEEDS_SYNC message (%d)\n",
+			__func__, __LINE__, err);
+}
+
 static int leave(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 
 	if (!cinfo)
 		return 0;
+
+	/* BITMAP_NEEDS_SYNC message should be sent when node
+	 * is leaving the cluster with dirty bitmap, also we
+	 * can only deliver it when dlm connection is available */
+	if (cinfo->slot_number > 0 && mddev->recovery_cp != MaxSector)
+		resync_bitmap(mddev);
+
 	md_unregister_thread(&cinfo->recovery_thread);
 	md_unregister_thread(&cinfo->recv_thread);
 	lockres_free(cinfo->message_lockres);
···
 	return cinfo->slot_number - 1;
 }
 
-static void resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
-{
-	struct md_cluster_info *cinfo = mddev->cluster_info;
-
-	add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi);
-	/* Re-acquire the lock to refresh LVB */
-	dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
-}
-
 static int metadata_update_start(struct mddev *mddev)
 {
 	return lock_comm(mddev->cluster_info);
···
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	struct cluster_msg cmsg;
-	int ret;
+	struct md_rdev *rdev;
+	int ret = 0;
+	int raid_slot = -1;
 
 	memset(&cmsg, 0, sizeof(cmsg));
 	cmsg.type = cpu_to_le32(METADATA_UPDATED);
-	ret = __sendmsg(cinfo, &cmsg);
+	/* Pick up a good active device number to send.
+	 */
+	rdev_for_each(rdev, mddev)
+		if (rdev->raid_disk > -1 && !test_bit(Faulty, &rdev->flags)) {
+			raid_slot = rdev->desc_nr;
+			break;
+		}
+	if (raid_slot >= 0) {
+		cmsg.raid_slot = cpu_to_le32(raid_slot);
+		ret = __sendmsg(cinfo, &cmsg);
+	} else
+		pr_warn("md-cluster: No good device id found to send\n");
 	unlock_comm(cinfo);
 	return ret;
 }
 
-static int metadata_update_cancel(struct mddev *mddev)
+static void metadata_update_cancel(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-
-	return dlm_unlock_sync(cinfo->token_lockres);
+	unlock_comm(cinfo);
 }
 
-static int resync_send(struct mddev *mddev, enum msg_type type,
-		sector_t lo, sector_t hi)
+static int resync_start(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-	struct cluster_msg cmsg;
-	int slot = cinfo->slot_number - 1;
+	cinfo->resync_lockres->flags |= DLM_LKF_NOQUEUE;
+	return dlm_lock_sync(cinfo->resync_lockres, DLM_LOCK_EX);
+}
 
-	pr_info("%s:%d lo: %llu hi: %llu\n", __func__, __LINE__,
-			(unsigned long long)lo,
-			(unsigned long long)hi);
-	resync_info_update(mddev, lo, hi);
-	cmsg.type = cpu_to_le32(type);
-	cmsg.slot = cpu_to_le32(slot);
+static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
+{
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+	struct cluster_msg cmsg = {0};
+
+	add_resync_info(cinfo->bitmap_lockres, lo, hi);
+	/* Re-acquire the lock to refresh LVB */
+	dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);
+	cmsg.type = cpu_to_le32(RESYNCING);
 	cmsg.low = cpu_to_le64(lo);
 	cmsg.high = cpu_to_le64(hi);
+
 	return sendmsg(cinfo, &cmsg);
 }
 
-static int resync_start(struct mddev *mddev, sector_t lo, sector_t hi)
-{
-	pr_info("%s:%d\n", __func__, __LINE__);
-	return resync_send(mddev, RESYNCING, lo, hi);
-}
-
-static void resync_finish(struct mddev *mddev)
+static int resync_finish(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-	struct cluster_msg cmsg;
-	int slot = cinfo->slot_number - 1;
-
-	pr_info("%s:%d\n", __func__, __LINE__);
-	resync_send(mddev, RESYNCING, 0, 0);
-	if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
-		cmsg.type = cpu_to_le32(BITMAP_NEEDS_SYNC);
-		cmsg.slot = cpu_to_le32(slot);
-		sendmsg(cinfo, &cmsg);
-	}
+	cinfo->resync_lockres->flags &= ~DLM_LKF_NOQUEUE;
+	dlm_unlock_sync(cinfo->resync_lockres);
+	return resync_info_update(mddev, 0, 0);
 }
 
 static int area_resyncing(struct mddev *mddev, int direction,
···
 	return ret;
 }
 
-static int add_new_disk_start(struct mddev *mddev, struct md_rdev *rdev)
+/* add_new_disk() - initiates a disk add
+ * However, if this fails before writing md_update_sb(),
+ * add_new_disk_cancel() must be called to release token lock
+ */
+static int add_new_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	struct cluster_msg cmsg;
···
 	memset(&cmsg, 0, sizeof(cmsg));
 	cmsg.type = cpu_to_le32(NEWDISK);
 	memcpy(cmsg.uuid, uuid, 16);
-	cmsg.raid_slot = rdev->desc_nr;
+	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
 	lock_comm(cinfo);
 	ret = __sendmsg(cinfo, &cmsg);
 	if (ret)
···
 	/* Some node does not "see" the device */
 	if (ret == -EAGAIN)
 		ret = -ENOENT;
+	if (ret)
+		unlock_comm(cinfo);
 	else
 		dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
 	return ret;
 }
 
-static int add_new_disk_finish(struct mddev *mddev)
+static void add_new_disk_cancel(struct mddev *mddev)
 {
-	struct cluster_msg cmsg;
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-	int ret;
-	/* Write sb and inform others */
-	md_update_sb(mddev, 1);
-	cmsg.type = METADATA_UPDATED;
-	ret = __sendmsg(cinfo, &cmsg);
 	unlock_comm(cinfo);
-	return ret;
 }
 
 static int new_disk_ack(struct mddev *mddev, bool ack)
···
 
 static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
-	struct cluster_msg cmsg;
+	struct cluster_msg cmsg = {0};
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-	cmsg.type = REMOVE;
-	cmsg.raid_slot = rdev->desc_nr;
+	cmsg.type = cpu_to_le32(REMOVE);
+	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
 	return __sendmsg(cinfo, &cmsg);
 }
 
···
 {
 	int sn, err;
 	sector_t lo, hi;
-	struct cluster_msg cmsg;
+	struct cluster_msg cmsg = {0};
 	struct mddev *mddev = rdev->mddev;
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 
-	cmsg.type = RE_ADD;
-	cmsg.raid_slot = rdev->desc_nr;
+	cmsg.type = cpu_to_le32(RE_ADD);
+	cmsg.raid_slot = cpu_to_le32(rdev->desc_nr);
 	err = sendmsg(cinfo, &cmsg);
 	if (err)
 		goto out;
···
 	.join   = join,
 	.leave  = leave,
 	.slot_number = slot_number,
-	.resync_info_update = resync_info_update,
 	.resync_start = resync_start,
 	.resync_finish = resync_finish,
+	.resync_info_update = resync_info_update,
 	.metadata_update_start = metadata_update_start,
 	.metadata_update_finish = metadata_update_finish,
 	.metadata_update_cancel = metadata_update_cancel,
 	.area_resyncing = area_resyncing,
-	.add_new_disk_start = add_new_disk_start,
-	.add_new_disk_finish = add_new_disk_finish,
+	.add_new_disk = add_new_disk,
+	.add_new_disk_cancel = add_new_disk_cancel,
 	.new_disk_ack = new_disk_ack,
 	.remove_disk = remove_disk,
 	.gather_bitmaps = gather_bitmaps,
···
 
 module_init(cluster_init);
 module_exit(cluster_exit);
+MODULE_AUTHOR("SUSE");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Clustering support for MD");

drivers/md/md-cluster.h

···
 	int (*join)(struct mddev *mddev, int nodes);
 	int (*leave)(struct mddev *mddev);
 	int (*slot_number)(struct mddev *mddev);
-	void (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi);
-	int (*resync_start)(struct mddev *mddev, sector_t lo, sector_t hi);
-	void (*resync_finish)(struct mddev *mddev);
+	int (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi);
 	int (*metadata_update_start)(struct mddev *mddev);
 	int (*metadata_update_finish)(struct mddev *mddev);
-	int (*metadata_update_cancel)(struct mddev *mddev);
+	void (*metadata_update_cancel)(struct mddev *mddev);
+	int (*resync_start)(struct mddev *mddev);
+	int (*resync_finish)(struct mddev *mddev);
 	int (*area_resyncing)(struct mddev *mddev, int direction, sector_t lo, sector_t hi);
-	int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev);
-	int (*add_new_disk_finish)(struct mddev *mddev);
+	int (*add_new_disk)(struct mddev *mddev, struct md_rdev *rdev);
+	void (*add_new_disk_cancel)(struct mddev *mddev);
 	int (*new_disk_ack)(struct mddev *mddev, bool ack);
 	int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
 	int (*gather_bitmaps)(struct md_rdev *rdev);

drivers/md/md.c

···
 		++ev1;
 		if (rdev->desc_nr >= 0 &&
 		    rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
-		    le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < 0xfffe)
+		    (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
+		     le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))
 			if (ev1 < mddev->events)
 				return -EINVAL;
 	} else if (mddev->bitmap) {
···
 		int role;
 		if (rdev->desc_nr < 0 ||
 		    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
-			role = 0xffff;
+			role = MD_DISK_ROLE_SPARE;
 			rdev->desc_nr = -1;
 		} else
 			role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
 		switch(role) {
-		case 0xffff: /* spare */
+		case MD_DISK_ROLE_SPARE: /* spare */
 			break;
-		case 0xfffe: /* faulty */
+		case MD_DISK_ROLE_FAULTY: /* faulty */
 			set_bit(Faulty, &rdev->flags);
+			break;
+		case MD_DISK_ROLE_JOURNAL: /* journal device */
+			if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) {
+				/* journal device without journal feature */
+				printk(KERN_WARNING
+				  "md: journal device provided without journal feature, ignoring the device\n");
+				return -EINVAL;
+			}
+			set_bit(Journal, &rdev->flags);
+			rdev->journal_tail = le64_to_cpu(sb->journal_tail);
+			if (mddev->recovery_cp == MaxSector)
+				set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
+			rdev->raid_disk = mddev->raid_disks;
 			break;
 		default:
 			rdev->saved_raid_disk = role;
···
 			set_bit(WriteMostly, &rdev->flags);
 		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
 			set_bit(Replacement, &rdev->flags);
+		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
+			set_bit(MD_HAS_JOURNAL, &mddev->flags);
 	} else /* MULTIPATH are always insync */
 		set_bit(In_sync, &rdev->flags);
 
···
 	sb->events = cpu_to_le64(mddev->events);
 	if (mddev->in_sync)
 		sb->resync_offset = cpu_to_le64(mddev->recovery_cp);
+	else if (test_bit(MD_JOURNAL_CLEAN, &mddev->flags))
+		sb->resync_offset = cpu_to_le64(MaxSector);
 	else
 		sb->resync_offset = cpu_to_le64(0);
 
···
 		sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
 	}
 
-	if (rdev->raid_disk >= 0 &&
+	if (rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags) &&
 	    !test_bit(In_sync, &rdev->flags)) {
 		sb->feature_map |=
 			cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
···
 			sb->feature_map |=
 				cpu_to_le32(MD_FEATURE_RECOVERY_BITMAP);
 	}
+	/* Note: recovery_offset and journal_tail share space  */
+	if (test_bit(Journal, &rdev->flags))
+		sb->journal_tail = cpu_to_le64(rdev->journal_tail);
 	if (test_bit(Replacement, &rdev->flags))
 		sb->feature_map |=
 			cpu_to_le32(MD_FEATURE_REPLACEMENT);
···
 							     - rdev->data_offset));
 		}
 	}
+
+	if (mddev_is_clustered(mddev))
+		sb->feature_map |= cpu_to_le32(MD_FEATURE_CLUSTERED);
 
 	if (rdev->badblocks.count == 0)
 		/* Nothing to do for bad blocks*/ ;
···
 		max_dev = le32_to_cpu(sb->max_dev);
 
 	for (i=0; i<max_dev;i++)
-		sb->dev_roles[i] = cpu_to_le16(0xfffe);
+		sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY);
+
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags))
+		sb->feature_map |= cpu_to_le32(MD_FEATURE_JOURNAL);
 
 	rdev_for_each(rdev2, mddev) {
 		i = rdev2->desc_nr;
 		if (test_bit(Faulty, &rdev2->flags))
-			sb->dev_roles[i] = cpu_to_le16(0xfffe);
+			sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY);
 		else if (test_bit(In_sync, &rdev2->flags))
 			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
+		else if (test_bit(Journal, &rdev2->flags))
+			sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_JOURNAL);
 		else if (rdev2->raid_disk >= 0)
 			sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
 		else
-			sb->dev_roles[i] = cpu_to_le16(0xffff);
+			sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE);
 	}
 
 	sb->sb_csum = calc_sb_1_csum(sb);
···
 	struct md_rdev *rdev, *rdev2;
 
 	rcu_read_lock();
-	rdev_for_each_rcu(rdev, mddev1)
-		rdev_for_each_rcu(rdev2, mddev2)
+	rdev_for_each_rcu(rdev, mddev1) {
+		if (test_bit(Faulty, &rdev->flags) ||
+		    test_bit(Journal, &rdev->flags) ||
+		    rdev->raid_disk == -1)
+			continue;
+		rdev_for_each_rcu(rdev2, mddev2) {
+			if (test_bit(Faulty, &rdev2->flags) ||
+			    test_bit(Journal, &rdev2->flags) ||
+			    rdev2->raid_disk == -1)
+				continue;
 			if (rdev->bdev->bd_contains ==
 			    rdev2->bdev->bd_contains) {
 				rcu_read_unlock();
 				return 1;
 			}
+		}
+	}
 	rcu_read_unlock();
 	return 0;
 }
···
 	}
 }
 
+static bool does_sb_need_changing(struct mddev *mddev)
+{
+	struct md_rdev *rdev;
+	struct mdp_superblock_1 *sb;
+	int role;
+
+	/* Find a good rdev */
+	rdev_for_each(rdev, mddev)
+		if ((rdev->raid_disk >= 0) && !test_bit(Faulty, &rdev->flags))
+			break;
+
+	/* No good device found. */
+	if (!rdev)
+		return false;
+
+	sb = page_address(rdev->sb_page);
+	/* Check if a device has become faulty or a spare become active */
+	rdev_for_each(rdev, mddev) {
+		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+		/* Device activated? */
+		if (role == 0xffff && rdev->raid_disk >=0 &&
+		    !test_bit(Faulty, &rdev->flags))
+			return true;
+		/* Device turned faulty? */
+		if (test_bit(Faulty, &rdev->flags) && (role < 0xfffd))
+			return true;
+	}
+
+	/* Check if any mddev parameters have changed */
+	if ((mddev->dev_sectors != le64_to_cpu(sb->size)) ||
+	    (mddev->reshape_position != le64_to_cpu(sb->reshape_position)) ||
+	    (mddev->layout != le64_to_cpu(sb->layout)) ||
+	    (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) ||
+	    (mddev->chunk_sectors != le32_to_cpu(sb->chunksize)))
+		return true;
+
+	return false;
+}
+
 void md_update_sb(struct mddev *mddev, int force_change)
 {
 	struct md_rdev *rdev;
 	int sync_req;
 	int nospares = 0;
 	int any_badblocks_changed = 0;
+	int ret = -1;
 
 	if (mddev->ro) {
 		if (force_change)
 			set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		return;
 	}
+
+	if (mddev_is_clustered(mddev)) {
+		if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
+			force_change = 1;
+		ret = md_cluster_ops->metadata_update_start(mddev);
+		/* Has someone else has updated the sb */
+		if (!does_sb_need_changing(mddev)) {
+			if (ret == 0)
+				md_cluster_ops->metadata_update_cancel(mddev);
+			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+			return;
+		}
+	}
 repeat:
 	/* First make sure individual recovery_offsets are correct */
 	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    mddev->delta_disks >= 0 &&
+		    !test_bit(Journal, &rdev->flags) &&
 		    !test_bit(In_sync, &rdev->flags) &&
 		    mddev->curr_resync_completed > rdev->recovery_offset)
 				rdev->recovery_offset = mddev->curr_resync_completed;
···
 		clear_bit(BlockedBadBlocks, &rdev->flags);
 		wake_up(&rdev->blocked_wait);
 	}
+
+	if (mddev_is_clustered(mddev) && ret == 0)
+		md_cluster_ops->metadata_update_finish(mddev);
 }
 EXPORT_SYMBOL(md_update_sb);
 
···
 		len += sprintf(page+len, "%sin_sync",sep);
 		sep = ",";
 	}
+	if (test_bit(Journal, &flags)) {
+		len += sprintf(page+len, "%sjournal",sep);
+		sep = ",";
+	}
 	if (test_bit(WriteMostly, &flags)) {
 		len += sprintf(page+len, "%swrite_mostly",sep);
 		sep = ",";
···
 		sep = ",";
 	}
 	if (!test_bit(Faulty, &flags) &&
+	    !test_bit(Journal, &flags) &&
 	    !test_bit(In_sync, &flags)) {
 		len += sprintf(page+len, "%sspare", sep);
 		sep = ",";
···
 			err = -EBUSY;
 		else {
 			struct mddev *mddev = rdev->mddev;
-			if (mddev_is_clustered(mddev))
-				md_cluster_ops->remove_disk(mddev, rdev);
-			md_kick_rdev_from_array(rdev);
-			if (mddev_is_clustered(mddev))
-				md_cluster_ops->metadata_update_start(mddev);
-			if (mddev->pers)
-				md_update_sb(mddev, 1);
-			md_new_event(mddev);
-			if (mddev_is_clustered(mddev))
-				md_cluster_ops->metadata_update_finish(mddev);
 			err = 0;
+			if (mddev_is_clustered(mddev))
+				err = md_cluster_ops->remove_disk(mddev, rdev);
+
+			if (err == 0) {
+				md_kick_rdev_from_array(rdev);
+				if (mddev->pers)
+					md_update_sb(mddev, 1);
+				md_new_event(mddev);
+			}
 		}
 	} else if (cmd_match(buf, "writemostly")) {
 		set_bit(WriteMostly, &rdev->flags);
···
 	} else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) {
 		set_bit(In_sync, &rdev->flags);
 		err = 0;
-	} else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0) {
+	} else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0 &&
+		   !test_bit(Journal, &rdev->flags)) {
 		if (rdev->mddev->pers == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			rdev->saved_raid_disk = rdev->raid_disk;
···
 		 * check if recovery is needed.
 		 */
 		if (rdev->raid_disk >= 0 &&
+		    !test_bit(Journal, &rdev->flags) &&
 		    !test_bit(Replacement, &rdev->flags))
 			set_bit(WantReplacement, &rdev->flags);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
···
 static ssize_t
 slot_show(struct md_rdev *rdev, char *page)
 {
-	if (rdev->raid_disk < 0)
+	if (test_bit(Journal, &rdev->flags))
+		return sprintf(page, "journal\n");
+	else if (rdev->raid_disk < 0)
 		return sprintf(page, "none\n");
 	else
 		return sprintf(page, "%d\n", rdev->raid_disk);
···
 	int slot;
 	int err;
 
+	if (test_bit(Journal, &rdev->flags))
+		return -EBUSY;
 	if (strncmp(buf, "none", 4)==0)
 		slot = -1;
 	else {
···
 			rdev->saved_raid_disk = -1;
 		clear_bit(In_sync, &rdev->flags);
 		clear_bit(Bitmap_sync, &rdev->flags);
-		err = rdev->mddev->pers->
-			hot_add_disk(rdev->mddev, rdev);
-		if (err) {
-			rdev->raid_disk = -1;
-			return err;
-		} else
-			sysfs_notify_dirent_safe(rdev->sysfs_state);
-		if (sysfs_link_rdev(rdev->mddev, rdev))
-			/* failure here is OK */;
+		remove_and_add_spares(rdev->mddev, rdev);
+		if (rdev->raid_disk == -1)
+			return -EBUSY;
 		/* don't wakeup anyone, leave that to userspace. */
 	} else {
 		if (slot >= rdev->mddev->raid_disks &&
···
 	sector_t oldsectors = rdev->sectors;
 	sector_t sectors;
 
+	if (test_bit(Journal, &rdev->flags))
+		return -EBUSY;
 	if (strict_blocks_to_sectors(buf, &sectors) < 0)
 		return -EINVAL;
 	if (rdev->data_offset != rdev->new_data_offset)
···
 				md_kick_rdev_from_array(rdev);
 				continue;
 			}
-			/* No device should have a Candidate flag
-			 * when reading devices
-			 */
-			if (test_bit(Candidate, &rdev->flags)) {
-				pr_info("md: kicking Cluster Candidate %s from array!\n",
-					bdevname(rdev->bdev, b));
-				md_kick_rdev_from_array(rdev);
-			}
 		}
 		if (mddev->level == LEVEL_MULTIPATH) {
 			rdev->desc_nr = i++;
 			rdev->raid_disk = rdev->desc_nr;
 			set_bit(In_sync, &rdev->flags);
-		} else if (rdev->raid_disk >= (mddev->raid_disks - min(0, mddev->delta_disks))) {
+		} else if (rdev->raid_disk >=
+			    (mddev->raid_disks - min(0, mddev->delta_disks)) &&
+			   !test_bit(Journal, &rdev->flags)) {
 			rdev->raid_disk = -1;
 			clear_bit(In_sync, &rdev->flags);
 		}
···
 safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len)
 {
 	unsigned long msec;
+
+	if (mddev_is_clustered(mddev)) {
+		pr_info("md: Safemode is disabled for clustered mode\n");
+		return -EINVAL;
+	}
 
 	if (strict_strtoul_scaled(cbuf, &msec, 3) < 0)
 		return -EINVAL;
···
 		break;
 	case clean:
 		if (mddev->pers) {
-			restart_array(mddev);
+			err = restart_array(mddev);
+			if (err)
+				break;
 			spin_lock(&mddev->lock);
 			if (atomic_read(&mddev->writes_pending) == 0) {
 				if (mddev->in_sync == 0) {
···
 		break;
 	case active:
 		if (mddev->pers) {
-			restart_array(mddev);
+			err = restart_array(mddev);
+			if (err)
+				break;
 			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
 			wake_up(&mddev->sb_wait);
 			err = 0;
···
 	if (err)
 		return err;
 	if (mddev->pers) {
-		if (mddev_is_clustered(mddev))
-			md_cluster_ops->metadata_update_start(mddev);
 		err = update_size(mddev, sectors);
 		md_update_sb(mddev, 1);
-		if (mddev_is_clustered(mddev))
-			md_cluster_ops->metadata_update_finish(mddev);
 	} else {
 		if (mddev->dev_sectors == 0 ||
 		    mddev->dev_sectors > sectors)
···
 	atomic_set(&mddev->max_corr_read_errors,
 		   MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
 	mddev->safemode = 0;
-	mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
+	if (mddev_is_clustered(mddev))
+		mddev->safemode_delay = 0;
+	else
+		mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
 	mddev->in_sync = 1;
 	smp_wmb();
 	spin_lock(&mddev->lock);
···
 		goto out;
 	}
 
+	if (mddev_is_clustered(mddev))
+		md_allow_write(mddev);
+
 	md_wakeup_thread(mddev->thread);
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
···
 		return -EINVAL;
 	if (!mddev->ro)
 		return -EBUSY;
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+		struct md_rdev *rdev;
+		bool has_journal = false;
+
+		rcu_read_lock();
+		rdev_for_each_rcu(rdev, mddev) {
+			if (test_bit(Journal, &rdev->flags) &&
+			    !test_bit(Faulty, &rdev->flags)) {
+				has_journal = true;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		/* Don't restart rw with journal missing/faulty */
+		if (!has_journal)
+			return -EINVAL;
+	}
+
 	mddev->safemode = 0;
 	mddev->ro = 0;
 	set_disk_ro(disk, 0);
···
 
 static void __md_stop_writes(struct mddev *mddev)
 {
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_start(mddev);
 	set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	flush_workqueue(md_misc_wq);
 	if (mddev->sync_thread) {
···
 	md_super_wait(mddev);
 
 	if (mddev->ro == 0 &&
-	    (!mddev->in_sync || (mddev->flags & MD_UPDATE_SB_FLAGS))) {
+	    ((!mddev->in_sync && !mddev_is_clustered(mddev)) ||
+	     (mddev->flags & MD_UPDATE_SB_FLAGS))) {
 		/* mark array as shutdown cleanly */
-		mddev->in_sync = 1;
+		if (!mddev_is_clustered(mddev))
+			mddev->in_sync = 1;
 		md_update_sb(mddev, 1);
 	}
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_finish(mddev);
 }
 
 void md_stop_writes(struct mddev *mddev)
···
 			info.state |= (1<<MD_DISK_ACTIVE);
 			info.state |= (1<<MD_DISK_SYNC);
 		}
+		if (test_bit(Journal, &rdev->flags))
+			info.state |= (1<<MD_DISK_JOURNAL);
 		if (test_bit(WriteMostly, &rdev->flags))
 			info.state |= (1<<MD_DISK_WRITEMOSTLY);
 	} else {
···
 		else
 			clear_bit(WriteMostly, &rdev->flags);
 
+		if (info->state & (1<<MD_DISK_JOURNAL))
+			set_bit(Journal, &rdev->flags);
 		/*
 		 * check whether the device shows up in other nodes
 		 */
 		if (mddev_is_clustered(mddev)) {
-			if (info->state & (1 << MD_DISK_CANDIDATE)) {
-				/* Through --cluster-confirm */
+			if (info->state & (1 << MD_DISK_CANDIDATE))
 				set_bit(Candidate, &rdev->flags);
-				err = md_cluster_ops->new_disk_ack(mddev, true);
-				if (err) {
-					export_rdev(rdev);
-					return err;
-				}
-			} else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) {
+			else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) {
 				/* --add initiated by this node */
-				err = md_cluster_ops->add_new_disk_start(mddev, rdev);
+				err = md_cluster_ops->add_new_disk(mddev, rdev);
 				if (err) {
-					md_cluster_ops->add_new_disk_finish(mddev);
 					export_rdev(rdev);
 					return err;
 				}
···
 
 		rdev->raid_disk = -1;
 		err = bind_rdev_to_array(rdev, mddev);
+
 		if (err)
 			export_rdev(rdev);
-		else
+
+		if (mddev_is_clustered(mddev)) {
+			if (info->state & (1 << MD_DISK_CANDIDATE))
+				md_cluster_ops->new_disk_ack(mddev, (err == 0));
+			else {
+				if (err)
+					md_cluster_ops->add_new_disk_cancel(mddev);
+				else
+					err = add_bound_rdev(rdev);
+			}
+
+		} else if (!err)
 			err = add_bound_rdev(rdev);
-		if (mddev_is_clustered(mddev) &&
-				(info->state & (1 << MD_DISK_CLUSTER_ADD)))
-			md_cluster_ops->add_new_disk_finish(mddev);
+
 		return err;
 	}
 
···
 {
 	char b[BDEVNAME_SIZE];
 	struct md_rdev *rdev;
+	int ret = -1;
 
 	rdev = find_rdev(mddev, dev);
 	if (!rdev)
 		return -ENXIO;
 
 	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_start(mddev);
+		ret = md_cluster_ops->metadata_update_start(mddev);
+
+	if (rdev->raid_disk < 0)
+		goto kick_rdev;
 
 	clear_bit(Blocked, &rdev->flags);
 	remove_and_add_spares(mddev, rdev);
···
 	if (rdev->raid_disk >= 0)
 		goto busy;
 
-	if (mddev_is_clustered(mddev))
+kick_rdev:
+	if (mddev_is_clustered(mddev) && ret == 0)
 		md_cluster_ops->remove_disk(mddev, rdev);
 
 	md_kick_rdev_from_array(rdev);
 	md_update_sb(mddev, 1);
 	md_new_event(mddev);
 
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_finish(mddev);
-
 	return 0;
 busy:
-	if (mddev_is_clustered(mddev))
+	if (mddev_is_clustered(mddev) && ret == 0)
 		md_cluster_ops->metadata_update_cancel(mddev);
+
 	printk(KERN_WARNING "md: cannot remove active disk %s from %s ...\n",
 		bdevname(rdev->bdev,b), mdname(mddev));
 	return -EBUSY;
···
 		goto abort_export;
 	}
 
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_start(mddev);
 	clear_bit(In_sync, &rdev->flags);
 	rdev->desc_nr = -1;
 	rdev->saved_raid_disk = -1;
 	err = bind_rdev_to_array(rdev, mddev);
 	if (err)
-		goto abort_clustered;
+		goto abort_export;
 
 	/*
 	 * The rest should better be atomic, we can have disk failures
···
 	rdev->raid_disk = -1;
 
 	md_update_sb(mddev, 1);
-
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_finish(mddev);
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
 	 * array immediately.
···
 	md_new_event(mddev);
 	return 0;
 
-abort_clustered:
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_cancel(mddev);
 abort_export:
 	export_rdev(rdev);
 	return err;
···
 			return rv;
 		}
 	}
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_start(mddev);
 	if (info->size >= 0 && mddev->dev_sectors / 2 != info->size)
 		rv = update_size(mddev, (sector_t)info->size * 2);
 
···
 		}
 	}
 	md_update_sb(mddev, 1);
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_finish(mddev);
 	return rv;
 err:
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_cancel(mddev);
 	return rv;
 }
 
···
 				bdevname(rdev->bdev,b), rdev->desc_nr);
 			if (test_bit(WriteMostly, &rdev->flags))
 				seq_printf(seq, "(W)");
+			if (test_bit(Journal, &rdev->flags))
+				seq_printf(seq, "(J)");
 			if (test_bit(Faulty, &rdev->flags)) {
 				seq_printf(seq, "(F)");
 				continue;
···
 		    mddev->safemode == 0)
 			mddev->safemode = 1;
 		spin_unlock(&mddev->lock);
-		if (mddev_is_clustered(mddev))
-			md_cluster_ops->metadata_update_start(mddev);
 		md_update_sb(mddev, 0);
-		if (mddev_is_clustered(mddev))
-			md_cluster_ops->metadata_update_finish(mddev);
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	} else
 		spin_unlock(&mddev->lock);
···
 	struct md_rdev *rdev;
 	char *desc, *action = NULL;
 	struct blk_plug plug;
+	bool cluster_resync_finished = false;
 
 	/* just incase thread restarts... */
 	if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
···
 		rcu_read_lock();
 		rdev_for_each_rcu(rdev, mddev)
 			if (rdev->raid_disk >= 0 &&
+			    !test_bit(Journal, &rdev->flags) &&
 			    !test_bit(Faulty, &rdev->flags) &&
 			    !test_bit(In_sync, &rdev->flags) &&
 			    rdev->recovery_offset < j)
···
 	sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 	md_new_event(mddev);
 	update_time = jiffies;
-
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->resync_start(mddev, j, max_sectors);
 
 	blk_start_plug(&plug);
 	while (j < max_sectors) {
···
 			j = max_sectors;
 		if (j > 2)
 			mddev->curr_resync = j;
-		if (mddev_is_clustered(mddev))
-			md_cluster_ops->resync_info_update(mddev, j, max_sectors);
 		mddev->curr_mark_cnt = io_sectors;
 		if (last_check == 0)
 			/* this is the earliest that rebuild will be
···
 		mddev->curr_resync_completed = mddev->curr_resync;
 		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 	}
-	/* tell personality that we are finished */
+	/* tell personality and other nodes that we are finished */
+	if (mddev_is_clustered(mddev)) {
+		md_cluster_ops->resync_finish(mddev);
+		cluster_resync_finished = true;
+	}
 	mddev->pers->sync_request(mddev, max_sectors, &skipped);
 
 	if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
···
 			rdev_for_each_rcu(rdev, mddev)
 				if (rdev->raid_disk >= 0 &&
 				    mddev->delta_disks >= 0 &&
+				    !test_bit(Journal, &rdev->flags) &&
 				    !test_bit(Faulty, &rdev->flags) &&
 				    !test_bit(In_sync, &rdev->flags) &&
 				    rdev->recovery_offset < mddev->curr_resync)
···
 		}
 	}
  skip:
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->resync_finish(mddev);
-
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+
+	if (mddev_is_clustered(mddev) &&
+	    test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+	    !cluster_resync_finished)
+		md_cluster_ops->resync_finish(mddev);
 
 	spin_lock(&mddev->lock);
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
···
 		    rdev->raid_disk >= 0 &&
 		    !test_bit(Blocked, &rdev->flags) &&
 		    (test_bit(Faulty, &rdev->flags) ||
-		     ! test_bit(In_sync, &rdev->flags)) &&
+		     (!test_bit(In_sync, &rdev->flags) &&
+		      !test_bit(Journal, &rdev->flags))) &&
 		    atomic_read(&rdev->nr_pending)==0) {
 			if (mddev->pers->hot_remove_disk(
 				    mddev, rdev) == 0) {
···
 	if (removed && mddev->kobj.sd)
 		sysfs_notify(&mddev->kobj, NULL, "degraded");
 
-	if (this)
+	if (this && removed)
 		goto no_add;
 
 	rdev_for_each(rdev, mddev) {
+		if (this && this != rdev)
+			continue;
+		if (test_bit(Candidate, &rdev->flags))
+			continue;
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
+		    !test_bit(Journal, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags))
 			spares++;
 		if (rdev->raid_disk >= 0)
 			continue;
 		if (test_bit(Faulty, &rdev->flags))
+			continue;
+		if (test_bit(Journal, &rdev->flags))
 			continue;
 		if (mddev->ro &&
 		    ! (rdev->saved_raid_disk >= 0 &&
···
 static void md_start_sync(struct work_struct *ws)
 {
 	struct mddev *mddev = container_of(ws, struct mddev, del_work);
+	int ret = 0;
+
+	if (mddev_is_clustered(mddev)) {
+		ret = md_cluster_ops->resync_start(mddev);
+		if (ret) {
+			mddev->sync_thread = NULL;
+			goto out;
+		}
+	}
 
 	mddev->sync_thread = md_register_thread(md_do_sync,
 						mddev,
 						"resync");
+out:
 	if (!mddev->sync_thread) {
-		printk(KERN_ERR "%s: could not start resync"
-		       " thread...\n",
-		       mdname(mddev));
+		if (!(mddev_is_clustered(mddev) && ret == -EAGAIN))
+			printk(KERN_ERR "%s: could not start resync"
+			       " thread...\n",
+			       mdname(mddev));
 		/* leave the spares where they are, it shouldn't hurt */
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
···
 				sysfs_notify_dirent_safe(mddev->sysfs_state);
 		}
 
-		if (mddev->flags & MD_UPDATE_SB_FLAGS) {
-			if (mddev_is_clustered(mddev))
-				md_cluster_ops->metadata_update_start(mddev);
+		if (mddev->flags & MD_UPDATE_SB_FLAGS)
 			md_update_sb(mddev, 0);
-			if (mddev_is_clustered(mddev))
-				md_cluster_ops->metadata_update_finish(mddev);
-		}
 
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
 		    !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
···
 			set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		}
 	}
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_start(mddev);
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    mddev->pers->finish_reshape)
 		mddev->pers->finish_reshape(mddev);
···
 			rdev->saved_raid_disk = -1;
 
 	md_update_sb(mddev, 1);
-	if (mddev_is_clustered(mddev))
-		md_cluster_ops->metadata_update_finish(mddev);
 	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
···
 	return ret;
 }
 
-void md_reload_sb(struct mddev *mddev)
+static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 {
-	struct md_rdev *rdev, *tmp;
+	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
+	struct md_rdev *rdev2;
+	int role, ret;
+	char b[BDEVNAME_SIZE];
 
-	rdev_for_each_safe(rdev, tmp, mddev) {
-		rdev->sb_loaded = 0;
-		ClearPageUptodate(rdev->sb_page);
-	}
-	mddev->raid_disks = 0;
-	analyze_sbs(mddev);
-	rdev_for_each_safe(rdev, tmp, mddev) {
-		struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
-		/* since we don't write to faulty devices, we figure out if the
-		 *  disk is faulty by comparing events
-		 */
-		if (mddev->events > sb->events)
-			set_bit(Faulty, &rdev->flags);
+	/* Check for change of roles in the active devices */
+	rdev_for_each(rdev2, mddev) {
+		if (test_bit(Faulty, &rdev2->flags))
+			continue;
+
+		/* Check if the roles changed */
+		role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]);
+
+		if (test_bit(Candidate, &rdev2->flags)) {
+			if (role == 0xfffe) {
+				pr_info("md: Removing Candidate device %s because add failed\n", bdevname(rdev2->bdev,b));
+				md_kick_rdev_from_array(rdev2);
+				continue;
+			}
+			else
+				clear_bit(Candidate, &rdev2->flags);
+		}
+
+		if (role != rdev2->raid_disk) {
+			/* got activated */
+			if (rdev2->raid_disk == -1 && role != 0xffff) {
+				rdev2->saved_raid_disk = role;
+				ret = remove_and_add_spares(mddev, rdev2);
+				pr_info("Activated spare: %s\n",
+						bdevname(rdev2->bdev,b));
+				continue;
+			}
+			/* device faulty
+			 * We just want to do the minimum to mark the disk
+			 * as faulty. The recovery is performed by the
+			 * one who initiated the error.
+			 */
+			if ((role == 0xfffe) || (role == 0xfffd)) {
+				md_error(mddev, rdev2);
+				clear_bit(Blocked, &rdev2->flags);
+			}
+		}
 	}
 
+	if (mddev->raid_disks != le32_to_cpu(sb->raid_disks))
+		update_raid_disks(mddev, le32_to_cpu(sb->raid_disks));
+
+	/* Finally set the event to be up to date */
+	mddev->events = le64_to_cpu(sb->events);
+}
+
+static int read_rdev(struct mddev *mddev, struct md_rdev *rdev)
+{
+	int err;
+	struct page *swapout = rdev->sb_page;
+	struct mdp_superblock_1 *sb;
+
+	/* Store the sb page of the rdev in the swapout temporary
+	 * variable in case we err in the future
+	 */
+	rdev->sb_page = NULL;
+	alloc_disk_sb(rdev);
+	ClearPageUptodate(rdev->sb_page);
+	rdev->sb_loaded = 0;
+	err = super_types[mddev->major_version].load_super(rdev, NULL, mddev->minor_version);
+
+	if (err < 0) {
+		pr_warn("%s: %d Could not reload rdev(%d) err: %d. Restoring old values\n",
+				__func__, __LINE__, rdev->desc_nr, err);
+		put_page(rdev->sb_page);
+		rdev->sb_page = swapout;
+		rdev->sb_loaded = 1;
+		return err;
+	}
+
+	sb = page_address(rdev->sb_page);
+	/* Read the offset unconditionally, even if MD_FEATURE_RECOVERY_OFFSET
+	 * is not set
+	 */
+
+	if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RECOVERY_OFFSET))
+		rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
+
+	/* The other node finished recovery, call spare_active to set
+	 * device In_sync and mddev->degraded
+	 */
+	if (rdev->recovery_offset == MaxSector &&
+	    !test_bit(In_sync, &rdev->flags) &&
+	    mddev->pers->spare_active(mddev))
+		sysfs_notify(&mddev->kobj, NULL, "degraded");
+
+	put_page(swapout);
+	return 0;
+}
+
+void md_reload_sb(struct mddev *mddev, int nr)
+{
+	struct md_rdev *rdev;
+	int err;
+
+	/* Find the rdev */
+	rdev_for_each_rcu(rdev, mddev) {
+		if (rdev->desc_nr == nr)
+			break;
+	}
+
+	if (!rdev || rdev->desc_nr != nr) {
+		pr_warn("%s: %d Could not find rdev with nr %d\n", __func__, __LINE__, nr);
+		return;
+	}
+
+	err = read_rdev(mddev, rdev);
+	if (err < 0)
+		return;
+
+	check_sb_changes(mddev, rdev);
+
+	/* Read all rdev's to update recovery_offset */
+	rdev_for_each_rcu(rdev, mddev)
+		read_rdev(mddev, rdev);
 }
 EXPORT_SYMBOL(md_reload_sb);
 

drivers/md/md.h

···
 					 * array and could again if we did a partial
 					 * resync from the bitmap
 					 */
-	sector_t	recovery_offset;/* If this device has been partially
+	union {
+		sector_t recovery_offset;/* If this device has been partially
 					 * recovered, this is where we were
 					 * up to.
 					 */
+		sector_t journal_tail;	/* If this device is a journal device,
+					 * this is the journal tail (journal
+					 * recovery start point)
+					 */
+	};
 
 	atomic_t	nr_pending;	/* number of pending requests.
 					 * only maintained for arrays that
···
 				 * This device is seen locally but not
 				 * by the whole cluster
 				 */
+	Journal,		/* This device is used as journal for
+				 * raid-5/6.
+				 * Usually, this device should be faster
+				 * than other devices in the array
+				 */
 };
 
 #define BB_LEN_MASK	(0x00000000000001FFULL)
···
 #define MD_STILL_CLOSED	4	/* If set, then array has not been opened since
 				 * md_ioctl checked on it.
 				 */
+#define MD_JOURNAL_CLEAN 5	/* A raid with journal is already clean */
+#define MD_HAS_JOURNAL	6	/* The raid array has journal feature set */
 
 	int				suspended;
 	atomic_t			active_io;
···
 				   struct mddev *mddev);
 
 extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
-extern void md_reload_sb(struct mddev *mddev);
+extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
 extern void md_kick_rdev_from_array(struct md_rdev * rdev);
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);

drivers/md/raid1.c

···
 #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
 #define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH)
 #define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9)
+#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW)
+#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9)
 #define NEXT_NORMALIO_DISTANCE (3 * RESYNC_WINDOW_SECTORS)
 
 static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
···
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
+	/*
+	 * find the disk ... but prefer rdev->saved_raid_disk
+	 * if possible.
+	 */
+	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
+	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
+		first = last = rdev->saved_raid_disk;
+
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors+mirror;
 		if (!p->rdev) {
···
 
 		bitmap_close_sync(mddev->bitmap);
 		close_sync(conf);
+
+		if (mddev_is_clustered(mddev)) {
+			conf->cluster_sync_low = 0;
+			conf->cluster_sync_high = 0;
+		}
 		return 0;
 	}
 
···
 		return sync_blocks;
 	}
 
-	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+	/* we are incrementing sector_nr below. To be safe, we check against
+	 * sector_nr + two times RESYNC_SECTORS
+	 */
+
+	bitmap_cond_end_sync(mddev->bitmap, sector_nr,
+		mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
 	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
 
 	raise_barrier(conf, sector_nr);
···
 	} while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES);
  bio_full:
 	r1_bio->sectors = nr_sectors;
+
+	if (mddev_is_clustered(mddev) &&
+			conf->cluster_sync_high < sector_nr + nr_sectors) {
+		conf->cluster_sync_low = mddev->curr_resync_completed;
+		conf->cluster_sync_high = conf->cluster_sync_low + CLUSTER_RESYNC_WINDOW_SECTORS;
+		/* Send resync message */
+		md_cluster_ops->resync_info_update(mddev,
+				conf->cluster_sync_low,
+				conf->cluster_sync_high);
+	}
 
 	/* For a user-requested sync, we read all readable devices and do a
 	 * compare
···
 		return -EINVAL;
 	}
 
-	err = md_allow_write(mddev);
-	if (err)
-		return err;
+	if (!mddev_is_clustered(mddev)) {
+		err = md_allow_write(mddev);
+		if (err)
+			return err;
+	}
 
 	raid_disks = mddev->raid_disks + mddev->delta_disks;
 

drivers/md/raid1.h

···
 	 * the new thread here until we fully activate the array.
 	 */
 	struct md_thread	*thread;
+
+	/* Keep track of cluster resync window to send to other
+	 * nodes.
+	 */
+	sector_t		cluster_sync_low;
+	sector_t		cluster_sync_high;
+
 };
 
 /*

drivers/md/raid10.c

···
 		/* resync. Schedule a read for every block at this virt offset */
 		int count = 0;
 
-		bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+		bitmap_cond_end_sync(mddev->bitmap, sector_nr, 0);
 
 		if (!bitmap_start_sync(mddev->bitmap, sector_nr,
 				       &sync_blocks, mddev->degraded) &&

drivers/md/raid5-cache.c

···
+/*
+ * Copyright (C) 2015 Shaohua Li <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/wait.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/raid/md_p.h>
+#include <linux/crc32c.h>
+#include <linux/random.h>
+#include "md.h"
+#include "raid5.h"
+
+/*
+ * metadata/data stored in disk with 4k size unit (a block) regardless
+ * underneath hardware sector size. only works with PAGE_SIZE == 4096
+ */
+#define BLOCK_SECTORS (8)
+
+/*
+ * reclaim runs every 1/4 disk size or 10G reclaimable space. This can prevent
+ * recovery scans a very long log
+ */
+#define RECLAIM_MAX_FREE_SPACE (10 * 1024 * 1024 * 2) /* sector */
+#define RECLAIM_MAX_FREE_SPACE_SHIFT (2)
+
+struct r5l_log {
+	struct md_rdev *rdev;
+
+	u32 uuid_checksum;
+
+	sector_t device_size;		/* log device size, round to
+					 * BLOCK_SECTORS */
+	sector_t max_free_space;	/* reclaim run if free space is at
+					 * this size */
+
+	sector_t last_checkpoint;	/* log tail. where recovery scan
+					 * starts from */
+	u64 last_cp_seq;		/* log tail sequence */
+
+	sector_t log_start;		/* log head. where new data appends */
+	u64 seq;			/* log head sequence */
+
+	sector_t next_checkpoint;
+	u64 next_cp_seq;
+
+	struct mutex io_mutex;
+	struct r5l_io_unit *current_io;	/* current io_unit accepting new data */
+
+	spinlock_t io_list_lock;
+	struct list_head running_ios;	/* io_units which are still running,
+					 * and have not yet been completely
+					 * written to the log */
+	struct list_head io_end_ios;	/* io_units which have been completely
+					 * written to the log but not yet written
+					 * to the RAID */
+	struct list_head flushing_ios;	/* io_units which are waiting for log
+					 * cache flush */
+	struct list_head finished_ios;	/* io_units which settle down in log disk */
+	struct bio flush_bio;
+
+	struct kmem_cache *io_kc;
+
+	struct md_thread *reclaim_thread;
+	unsigned long reclaim_target;	/* number of space that need to be
+					 * reclaimed.  if it's 0, reclaim spaces
+					 * used by io_units which are in
+					 * IO_UNIT_STRIPE_END state (eg, reclaim
+					 * dones't wait for specific io_unit
+					 * switching to IO_UNIT_STRIPE_END
+					 * state) */
+	wait_queue_head_t iounit_wait;
+
+	struct list_head no_space_stripes; /* pending stripes, log has no space */
+	spinlock_t no_space_stripes_lock;
+
+	bool need_cache_flush;
+	bool in_teardown;
+};
+
+/*
+ * an IO range starts from a meta data block and end at the next meta data
+ * block. The io unit's the meta data block tracks data/parity followed it. io
+ * unit is written to log disk with normal write, as we always flush log disk
+ * first and then start move data to raid disks, there is no requirement to
+ * write io unit with FLUSH/FUA
+ */
+struct r5l_io_unit {
+	struct r5l_log *log;
+
+	struct page *meta_page;	/* store meta block */
+	int meta_offset;	/* current offset in meta_page */
+
+	struct bio *current_bio;/* current_bio accepting new data */
+
+	atomic_t pending_stripe;/* how many stripes not flushed to raid */
+	u64 seq;		/* seq number of the metablock */
+	sector_t log_start;	/* where the io_unit starts */
+	sector_t log_end;	/* where the io_unit ends */
+	struct list_head log_sibling; /* log->running_ios */
+	struct list_head stripe_list; /* stripes added to the io_unit */
+
+	int state;
+	bool need_split_bio;
+};
+
+/* r5l_io_unit state */
+enum r5l_io_unit_state {
+	IO_UNIT_RUNNING = 0,	/* accepting new IO */
+	IO_UNIT_IO_START = 1,	/* io_unit bio start writing to log,
+				 * don't accepting new bio */
+	IO_UNIT_IO_END = 2,	/* io_unit bio finish writing to log */
+	IO_UNIT_STRIPE_END = 3,	/* stripes data finished writing to raid */
+};
+
+static sector_t r5l_ring_add(struct r5l_log *log, sector_t start, sector_t inc)
+{
+	start += inc;
+	if (start >= log->device_size)
+		start = start - log->device_size;
+	return start;
+}
+
+static sector_t r5l_ring_distance(struct r5l_log *log, sector_t start,
+				  sector_t end)
+{
+	if (end >= start)
+		return end - start;
+	else
+		return end + log->device_size - start;
+}
+
+static bool r5l_has_free_space(struct r5l_log *log, sector_t size)
+{
+	sector_t used_size;
+
+	used_size = r5l_ring_distance(log, log->last_checkpoint,
+					log->log_start);
+
+	return log->device_size > used_size + size;
+}
+
+static void r5l_free_io_unit(struct r5l_log *log, struct r5l_io_unit *io)
+{
+	__free_page(io->meta_page);
+	kmem_cache_free(log->io_kc, io);
+}
+
+static void r5l_move_io_unit_list(struct list_head *from, struct list_head *to,
+				  enum r5l_io_unit_state state)
+{
+	struct r5l_io_unit *io;
+
+	while (!list_empty(from)) {
+		io = list_first_entry(from, struct r5l_io_unit, log_sibling);
+		/* don't change list order */
+		if (io->state >= state)
+			list_move_tail(&io->log_sibling, to);
+		else
+			break;
+	}
+}
+
+static void __r5l_set_io_unit_state(struct r5l_io_unit *io,
+				    enum r5l_io_unit_state state)
+{
+	if (WARN_ON(io->state >= state))
+		return;
+	io->state = state;
+}
+
+static void r5l_io_run_stripes(struct r5l_io_unit *io)
+{
+	struct stripe_head *sh, *next;
+
+	list_for_each_entry_safe(sh, next, &io->stripe_list, log_list) {
+		list_del_init(&sh->log_list);
+		set_bit(STRIPE_HANDLE, &sh->state);
+		raid5_release_stripe(sh);
+	}
+}
+
+static void r5l_log_run_stripes(struct r5l_log *log)
+{
+	struct r5l_io_unit *io, *next;
+
+	assert_spin_locked(&log->io_list_lock);
+
+	list_for_each_entry_safe(io, next, &log->running_ios, log_sibling) {
+		/* don't change list order */
+		if (io->state < IO_UNIT_IO_END)
+			break;
+
+		list_move_tail(&io->log_sibling, &log->finished_ios);
+		r5l_io_run_stripes(io);
+	}
+}
+
+static void r5l_log_endio(struct bio *bio)
+{
+	struct r5l_io_unit *io = bio->bi_private;
+	struct r5l_log *log = io->log;
+	unsigned long flags;
+
+	if (bio->bi_error)
+		md_error(log->rdev->mddev, log->rdev);
+
+	bio_put(bio);
+
+	spin_lock_irqsave(&log->io_list_lock, flags);
+	__r5l_set_io_unit_state(io, IO_UNIT_IO_END);
+	if (log->need_cache_flush)
+		r5l_move_io_unit_list(&log->running_ios, &log->io_end_ios,
+				      IO_UNIT_IO_END);
+	else
+		r5l_log_run_stripes(log);
+	spin_unlock_irqrestore(&log->io_list_lock, flags);
+
+	if (log->need_cache_flush)
+		md_wakeup_thread(log->rdev->mddev->thread);
+}
+
+static void r5l_submit_current_io(struct r5l_log *log)
+{
+	struct r5l_io_unit *io = log->current_io;
+	struct r5l_meta_block *block;
+	unsigned long flags;
+	u32 crc;
+
+	if (!io)
+		return;
+
+	block = page_address(io->meta_page);
+	block->meta_size = cpu_to_le32(io->meta_offset);
+	crc = crc32c_le(log->uuid_checksum, block, PAGE_SIZE);
+	block->checksum = cpu_to_le32(crc);
+
+	log->current_io = NULL;
+	spin_lock_irqsave(&log->io_list_lock, flags);
+	__r5l_set_io_unit_state(io, IO_UNIT_IO_START);
+	spin_unlock_irqrestore(&log->io_list_lock, flags);
+
+	submit_bio(WRITE, io->current_bio);
+}
+
+static struct bio *r5l_bio_alloc(struct r5l_log *log)
+{
+	struct bio *bio = bio_kmalloc(GFP_NOIO | __GFP_NOFAIL, BIO_MAX_PAGES);
+
+	bio->bi_rw = WRITE;
+	bio->bi_bdev = log->rdev->bdev;
+	bio->bi_iter.bi_sector = log->rdev->data_offset + log->log_start;
+
+	return bio;
+}
+
+static void r5_reserve_log_entry(struct r5l_log *log, struct r5l_io_unit *io)
+{
+	log->log_start = r5l_ring_add(log, log->log_start, BLOCK_SECTORS);
+
+	/*
+	 * If we filled up the log device start from the beginning again,
+	 * which will require a new bio.
+	 *
+	 * Note: for this to work properly the log size needs to me a multiple
+	 * of BLOCK_SECTORS.
+	 */
+	if (log->log_start == 0)
+		io->need_split_bio = true;
+
+	io->log_end = log->log_start;
+}
+
+static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log)
+{
+	struct r5l_io_unit *io;
+	struct r5l_meta_block *block;
+
+	/* We can't handle memory allocate failure so far */
+	io = kmem_cache_zalloc(log->io_kc, GFP_NOIO | __GFP_NOFAIL);
+	io->log = log;
+	INIT_LIST_HEAD(&io->log_sibling);
+	INIT_LIST_HEAD(&io->stripe_list);
+	io->state = IO_UNIT_RUNNING;
+
+	io->meta_page = alloc_page(GFP_NOIO | __GFP_NOFAIL | __GFP_ZERO);
+	block = page_address(io->meta_page);
+	block->magic = cpu_to_le32(R5LOG_MAGIC);
+	block->version = R5LOG_VERSION;
+	block->seq = cpu_to_le64(log->seq);
+	block->position = cpu_to_le64(log->log_start);
+
+	io->log_start = log->log_start;
+	io->meta_offset = sizeof(struct r5l_meta_block);
+	io->seq = log->seq++;
+
+	io->current_bio = r5l_bio_alloc(log);
+	io->current_bio->bi_end_io = r5l_log_endio;
+	io->current_bio->bi_private = io;
+	bio_add_page(io->current_bio, io->meta_page, PAGE_SIZE, 0);
+
+	r5_reserve_log_entry(log, io);
+
+	spin_lock_irq(&log->io_list_lock);
+	list_add_tail(&io->log_sibling, &log->running_ios);
+	spin_unlock_irq(&log->io_list_lock);
+
+	return io;
+}
+
+static int r5l_get_meta(struct r5l_log *log, unsigned int payload_size)
+{
+	if (log->current_io &&
+	    log->current_io->meta_offset + payload_size > PAGE_SIZE)
+		r5l_submit_current_io(log);
+
+	if (!log->current_io)
+		log->current_io = r5l_new_meta(log);
+	return 0;
+}
+
+static void r5l_append_payload_meta(struct r5l_log *log, u16 type,
+				    sector_t location,
+				    u32 checksum1, u32 checksum2,
+				    bool checksum2_valid)
+{
+	struct r5l_io_unit *io = log->current_io;
+	struct r5l_payload_data_parity *payload;
+
+	payload = page_address(io->meta_page) + io->meta_offset;
+	payload->header.type = cpu_to_le16(type);
+	payload->header.flags = cpu_to_le16(0);
+	payload->size = cpu_to_le32((1 + !!checksum2_valid) <<
+				    (PAGE_SHIFT - 9));
+	payload->location = cpu_to_le64(location);
+	payload->checksum[0] = cpu_to_le32(checksum1);
+	if (checksum2_valid)
+		payload->checksum[1] = cpu_to_le32(checksum2);
+
+	io->meta_offset += sizeof(struct r5l_payload_data_parity) +
+		sizeof(__le32) * (1 + !!checksum2_valid);
+}
+
+static void r5l_append_payload_page(struct r5l_log *log, struct page *page)
+{
+	struct r5l_io_unit *io = log->current_io;
+
+	if (io->need_split_bio) {
+		struct bio *prev = io->current_bio;
+
+		io->current_bio = r5l_bio_alloc(log);
+		bio_chain(io->current_bio, prev);
+
+		submit_bio(WRITE, prev);
+	}
+
+	if (!bio_add_page(io->current_bio, page, PAGE_SIZE, 0))
+		BUG();
+
+	r5_reserve_log_entry(log, io);
+}
+
+static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh,
+			   int data_pages, int parity_pages)
+{
+	int i;
+	int meta_size;
+	struct r5l_io_unit *io;
+
+	meta_size =
+		((sizeof(struct r5l_payload_data_parity) + sizeof(__le32))
+		 * data_pages) +
+		sizeof(struct r5l_payload_data_parity) +
+		sizeof(__le32) * parity_pages;
+
+	r5l_get_meta(log, meta_size);
+	io = log->current_io;
+
+	for (i = 0; i < sh->disks; i++) {
+		if (!test_bit(R5_Wantwrite, &sh->dev[i].flags))
+			continue;
+		if (i == sh->pd_idx || i == sh->qd_idx)
+			continue;
+		r5l_append_payload_meta(log, R5LOG_PAYLOAD_DATA,
+					raid5_compute_blocknr(sh, i, 0),
+					sh->dev[i].log_checksum, 0, false);
+		r5l_append_payload_page(log, sh->dev[i].page);
+	}
+
+	if (sh->qd_idx >= 0) {
+		r5l_append_payload_meta(log, R5LOG_PAYLOAD_PARITY,
+					sh->sector, sh->dev[sh->pd_idx].log_checksum,
+					sh->dev[sh->qd_idx].log_checksum, true);
+		r5l_append_payload_page(log, sh->dev[sh->pd_idx].page);
+		r5l_append_payload_page(log, sh->dev[sh->qd_idx].page);
+	} else {
+		r5l_append_payload_meta(log, R5LOG_PAYLOAD_PARITY,
+					sh->sector, sh->dev[sh->pd_idx].log_checksum,
+					0, false);
+		r5l_append_payload_page(log, sh->dev[sh->pd_idx].page);
+	}
+
+	list_add_tail(&sh->log_list, &io->stripe_list);
+	atomic_inc(&io->pending_stripe);
+	sh->log_io = io;
+}
+
+static void r5l_wake_reclaim(struct r5l_log *log, sector_t space);
+/*
+ * running in raid5d, where reclaim could wait for raid5d too (when it flushes
+ * data from log to raid disks), so we shouldn't wait for reclaim here
+ */
+int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh)
+{
+	int write_disks = 0;
+	int data_pages, parity_pages;
+	int meta_size;
+	int reserve;
+	int i;
+
+	if (!log)
+		return -EAGAIN;
+	/* Don't support stripe batch */
+	if (sh->log_io || !test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags) ||
+	    test_bit(STRIPE_SYNCING, &sh->state)) {
+		/* the stripe is written to log, we start writing it to raid */
+		clear_bit(STRIPE_LOG_TRAPPED, &sh->state);
+		return -EAGAIN;
+	}
+
+	for (i = 0; i < sh->disks; i++) {
+		void *addr;
+
+		if (!test_bit(R5_Wantwrite, &sh->dev[i].flags))
+			continue;
+		write_disks++;
+		/* checksum is already calculated in last run */
+		if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
+			continue;
+		addr = kmap_atomic(sh->dev[i].page);
+		sh->dev[i].log_checksum = crc32c_le(log->uuid_checksum,
+						    addr, PAGE_SIZE);
+		kunmap_atomic(addr);
+	}
+	parity_pages = 1 + !!(sh->qd_idx >= 0);
+	data_pages = write_disks - parity_pages;
+
+	meta_size =
+		((sizeof(struct r5l_payload_data_parity) + sizeof(__le32))
+		 * data_pages) +
+		sizeof(struct r5l_payload_data_parity) +
+		sizeof(__le32) * parity_pages;
+	/* Doesn't work with very big raid array */
+	if (meta_size + sizeof(struct r5l_meta_block) > PAGE_SIZE)
+		return -EINVAL;
+
+	set_bit(STRIPE_LOG_TRAPPED, &sh->state);
+	/*
+	 * The stripe must enter state machine again to finish the write, so
+	 * don't delay.
+	 */
+	clear_bit(STRIPE_DELAYED, &sh->state);
+	atomic_inc(&sh->count);
+
+	mutex_lock(&log->io_mutex);
+	/* meta + data */
+	reserve = (1 + write_disks) << (PAGE_SHIFT - 9);
+	if (r5l_has_free_space(log, reserve))
+		r5l_log_stripe(log, sh, data_pages, parity_pages);
+	else {
+		spin_lock(&log->no_space_stripes_lock);
+		list_add_tail(&sh->log_list, &log->no_space_stripes);
+		spin_unlock(&log->no_space_stripes_lock);
+
+		r5l_wake_reclaim(log, reserve);
+	}
+	mutex_unlock(&log->io_mutex);
+
+	return 0;
+}
+
+void r5l_write_stripe_run(struct r5l_log *log)
+{
+	if (!log)
+		return;
+	mutex_lock(&log->io_mutex);
+	r5l_submit_current_io(log);
+	mutex_unlock(&log->io_mutex);
+}
+
+int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio)
+{
+	if (!log)
+		return -ENODEV;
+	/*
+	 * we flush log disk cache first, then write stripe data to raid disks.
+	 * So if bio is finished, the log disk cache is flushed already. The
+	 * recovery guarantees we can recovery the bio from log disk, so we
+	 * don't need to flush again
+	 */
+	if (bio->bi_iter.bi_size == 0) {
+		bio_endio(bio);
+		return 0;
+	}
+	bio->bi_rw &= ~REQ_FLUSH;
+	return -EAGAIN;
+}
+
+/* This will run after log space is reclaimed */
+static void r5l_run_no_space_stripes(struct r5l_log *log)
+{
+	struct stripe_head *sh;
+
+	spin_lock(&log->no_space_stripes_lock);
+	while (!list_empty(&log->no_space_stripes)) {
+		sh = list_first_entry(&log->no_space_stripes,
+				      struct stripe_head, log_list);
+		list_del_init(&sh->log_list);
+		set_bit(STRIPE_HANDLE, &sh->state);
+		raid5_release_stripe(sh);
+	}
+	spin_unlock(&log->no_space_stripes_lock);
+}
+
+static sector_t r5l_reclaimable_space(struct r5l_log *log)
+{
+	return r5l_ring_distance(log, log->last_checkpoint,
+				 log->next_checkpoint);
+}
+
+static bool r5l_complete_finished_ios(struct r5l_log *log)
+{
+	struct r5l_io_unit *io, *next;
+	bool found = false;
+
+	assert_spin_locked(&log->io_list_lock);
+
+	list_for_each_entry_safe(io, next, &log->finished_ios, log_sibling) {
+		/* don't change list order */
+		if (io->state < IO_UNIT_STRIPE_END)
+			break;
+
+		log->next_checkpoint = io->log_start;
+		log->next_cp_seq = io->seq;
+
+		list_del(&io->log_sibling);
+		r5l_free_io_unit(log, io);
+
+		found = true;
+	}
+
+	return found;
+}
+
+static void __r5l_stripe_write_finished(struct r5l_io_unit *io)
+{
+	struct r5l_log *log = io->log;
+	unsigned long flags;
+
+	spin_lock_irqsave(&log->io_list_lock, flags);
+	__r5l_set_io_unit_state(io, IO_UNIT_STRIPE_END);
+
+	if (!r5l_complete_finished_ios(log)) {
+		spin_unlock_irqrestore(&log->io_list_lock, flags);
+		return;
+	}
+
+	if (r5l_reclaimable_space(log) > log->max_free_space)
+		r5l_wake_reclaim(log, 0);
+
+	spin_unlock_irqrestore(&log->io_list_lock, flags);
+	wake_up(&log->iounit_wait);
+}
+
+void r5l_stripe_write_finished(struct stripe_head *sh)
+{
+	struct r5l_io_unit *io;
+
+	io = sh->log_io;
+	sh->log_io = NULL;
+
+	if (io && atomic_dec_and_test(&io->pending_stripe))
+		__r5l_stripe_write_finished(io);
+}
+
+static void r5l_log_flush_endio(struct bio *bio)
+{
+	struct r5l_log *log = container_of(bio, struct r5l_log,
+		flush_bio);
+	unsigned long flags;
+	struct r5l_io_unit *io;
+
+	if (bio->bi_error)
+		md_error(log->rdev->mddev, log->rdev);
+
+	spin_lock_irqsave(&log->io_list_lock, flags);
+	list_for_each_entry(io, &log->flushing_ios, log_sibling)
+		r5l_io_run_stripes(io);
+	list_splice_tail_init(&log->flushing_ios, &log->finished_ios);
+	spin_unlock_irqrestore(&log->io_list_lock, flags);
+}
+
+/*
+ * Starting dispatch IO to raid.
+ * io_unit(meta) consists of a log. There is one situation we want to avoid. A
+ * broken meta in the middle of a log causes recovery can't find meta at the
+ * head of log. If operations require meta at the head persistent in log, we
+ * must make sure meta before it persistent in log too. A case is:
+ *
+ * stripe data/parity is in log, we start write stripe to raid disks. stripe
+ * data/parity must be persistent in log before we do the write to raid disks.
+ *
+ * The solution is we restrictly maintain io_unit list order. In this case, we
+ * only write stripes of an io_unit to raid disks till the io_unit is the first
+ * one whose data/parity is in log.
+ */
+void r5l_flush_stripe_to_raid(struct r5l_log *log)
+{
+	bool do_flush;
+
+	if (!log || !log->need_cache_flush)
+		return;
+
+	spin_lock_irq(&log->io_list_lock);
+	/* flush bio is running */
+	if (!list_empty(&log->flushing_ios)) {
+		spin_unlock_irq(&log->io_list_lock);
+		return;
+	}
+	list_splice_tail_init(&log->io_end_ios, &log->flushing_ios);
+	do_flush = !list_empty(&log->flushing_ios);
+	spin_unlock_irq(&log->io_list_lock);
+
+	if (!do_flush)
+		return;
+	bio_reset(&log->flush_bio);
+	log->flush_bio.bi_bdev = log->rdev->bdev;
+	log->flush_bio.bi_end_io = r5l_log_flush_endio;
+	submit_bio(WRITE_FLUSH, &log->flush_bio);
+}
+
+static void r5l_write_super(struct r5l_log *log, sector_t cp);
+static void r5l_write_super_and_discard_space(struct r5l_log *log,
+	sector_t end)
+{
+	struct block_device *bdev = log->rdev->bdev;
+	struct mddev *mddev;
+
+	r5l_write_super(log, end);
+
+	if (!blk_queue_discard(bdev_get_queue(bdev)))
+		return;
+
+	mddev = log->rdev->mddev;
+	/*
+	 * This is to avoid a deadlock. r5l_quiesce holds reconfig_mutex and
+	 * wait for this thread to finish. This thread waits for
+	 * MD_CHANGE_PENDING clear, which is supposed to be done in
+	 * md_check_recovery(). md_check_recovery() tries to get
+	 * reconfig_mutex. Since r5l_quiesce already holds the mutex,
+	 * md_check_recovery() fails, so the PENDING never get cleared. The
+	 * in_teardown check workaround this issue.
+	 */
+	if (!log->in_teardown) {
+		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_CHANGE_PENDING, &mddev->flags);
+		md_wakeup_thread(mddev->thread);
+		wait_event(mddev->sb_wait,
+			!test_bit(MD_CHANGE_PENDING, &mddev->flags) ||
+			log->in_teardown);
+		/*
+		 * r5l_quiesce could run after in_teardown check and hold
+		 * mutex first. Superblock might get updated twice.
+		 */
+		if (log->in_teardown)
+			md_update_sb(mddev, 1);
+	} else {
+		WARN_ON(!mddev_is_locked(mddev));
+		md_update_sb(mddev, 1);
+	}
+
+	/* discard IO error really doesn't matter, ignore it */
+	if (log->last_checkpoint < end) {
+		blkdev_issue_discard(bdev,
+				log->last_checkpoint + log->rdev->data_offset,
+				end - log->last_checkpoint, GFP_NOIO, 0);
+	} else {
+		blkdev_issue_discard(bdev,
+				log->last_checkpoint + log->rdev->data_offset,
+				log->device_size - log->last_checkpoint,
+				GFP_NOIO, 0);
+		blkdev_issue_discard(bdev, log->rdev->data_offset, end,
+				GFP_NOIO, 0);
+	}
+}
+
+
+static void r5l_do_reclaim(struct r5l_log *log)
+{
+	sector_t reclaim_target = xchg(&log->reclaim_target, 0);
+	sector_t reclaimable;
+	sector_t next_checkpoint;
+	u64 next_cp_seq;
+
+	spin_lock_irq(&log->io_list_lock);
+	/*
+	 * move proper io_unit to reclaim list. We should not change the order.
+	 * reclaimable/unreclaimable io_unit can be mixed in the list, we
+	 * shouldn't reuse space of an unreclaimable io_unit
+	 */
+	while (1) {
+		reclaimable = r5l_reclaimable_space(log);
+		if (reclaimable >= reclaim_target ||
+		    (list_empty(&log->running_ios) &&
+		     list_empty(&log->io_end_ios) &&
+		     list_empty(&log->flushing_ios) &&
+		     list_empty(&log->finished_ios)))
+			break;
+
+		md_wakeup_thread(log->rdev->mddev->thread);
+		wait_event_lock_irq(log->iounit_wait,
+				    r5l_reclaimable_space(log) > reclaimable,
+				    log->io_list_lock);
+	}
+
+	next_checkpoint = log->next_checkpoint;
+	next_cp_seq = log->next_cp_seq;
+	spin_unlock_irq(&log->io_list_lock);
+
+	BUG_ON(reclaimable < 0);
+	if (reclaimable == 0)
+		return;
+
+	/*
+	 * write_super will flush cache of each raid disk. We must write super
+	 * here, because the log area might be reused soon and we don't want to
+	 * confuse recovery
+	 */
+	r5l_write_super_and_discard_space(log, next_checkpoint);
+
+	mutex_lock(&log->io_mutex);
+	log->last_checkpoint = next_checkpoint;
+	log->last_cp_seq = next_cp_seq;
+	mutex_unlock(&log->io_mutex);
+
+	r5l_run_no_space_stripes(log);
+}
+
+static void r5l_reclaim_thread(struct md_thread *thread)
+{
+	struct mddev *mddev = thread->mddev;
+	struct r5conf *conf = mddev->private;
+	struct r5l_log *log = conf->log;
+
+	if (!log)
+		return;
+	r5l_do_reclaim(log);
+}
+
+static void r5l_wake_reclaim(struct r5l_log *log, sector_t space)
+{
+	unsigned long target;
+	unsigned long new = (unsigned long)space; /* overflow in theory */
+
+	do {
+		target = log->reclaim_target;
+		if (new < target)
+			return;
+	} while (cmpxchg(&log->reclaim_target, target, new) != target);
+	md_wakeup_thread(log->reclaim_thread);
+}
+
+void r5l_quiesce(struct r5l_log *log, int state)
+{
+	struct mddev *mddev;
+	if (!log || state == 2)
+		return;
+	if (state == 0) {
+		log->in_teardown = 0;
+		log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
+					log->rdev->mddev, "reclaim");
+	} else if (state == 1) {
+		/*
+		 * at this point all stripes are finished, so io_unit is at
+		 * least in STRIPE_END state
+		 */
+		log->in_teardown = 1;
+		/* make sure r5l_write_super_and_discard_space exits */
+		mddev = log->rdev->mddev;
+		wake_up(&mddev->sb_wait);
+		r5l_wake_reclaim(log, -1L);
+		md_unregister_thread(&log->reclaim_thread);
+		r5l_do_reclaim(log);
+	}
+}
+
+bool r5l_log_disk_error(struct r5conf *conf)
+{
+	/* don't allow write if journal disk is missing */
+	if (!conf->log)
+		return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags);
+	return test_bit(Faulty, &conf->log->rdev->flags);
+}
+
+struct r5l_recovery_ctx {
+	struct page *meta_page;		/* current meta */
+	sector_t meta_total_blocks;	/* total size of current meta and data */
+	sector_t pos;			/* recovery position */
+	u64 seq;			/* recovery position seq */
+};
+
+static int r5l_read_meta_block(struct r5l_log *log,
+			       struct r5l_recovery_ctx *ctx)
+{
+	struct page *page = ctx->meta_page;
+	struct r5l_meta_block *mb;
+	u32 crc, stored_crc;
+
+	if (!sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page, READ, false))
+		return -EIO;
+
+	mb = page_address(page);
+	stored_crc = le32_to_cpu(mb->checksum);
+	mb->checksum = 0;
+
+	if (le32_to_cpu(mb->magic) != R5LOG_MAGIC ||
+	    le64_to_cpu(mb->seq) != ctx->seq ||
+	    mb->version != R5LOG_VERSION ||
+	    le64_to_cpu(mb->position) != ctx->pos)
+		return -EINVAL;
+
+	crc = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
+	if (stored_crc != crc)
+		return -EINVAL;
+
+	if (le32_to_cpu(mb->meta_size) > PAGE_SIZE)
+		return -EINVAL;
+
+	ctx->meta_total_blocks = BLOCK_SECTORS;
+
+	return 0;
+}
+
+static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
+					 struct r5l_recovery_ctx *ctx,
+					 sector_t stripe_sect,
+					 int *offset, sector_t *log_offset)
+{
+	struct r5conf *conf = log->rdev->mddev->private;
+	struct stripe_head *sh;
+	struct r5l_payload_data_parity *payload;
+	int disk_index;
+
+	sh = raid5_get_active_stripe(conf, stripe_sect, 0, 0, 0);
+	while (1) {
+		payload = page_address(ctx->meta_page) + *offset;
+
+		if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_DATA) {
+			raid5_compute_sector(conf,
+					     le64_to_cpu(payload->location), 0,
+					     &disk_index, sh);
+
+			sync_page_io(log->rdev, *log_offset, PAGE_SIZE,
+				     sh->dev[disk_index].page, READ, false);
+			sh->dev[disk_index].log_checksum =
+				le32_to_cpu(payload->checksum[0]);
+			set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
+			ctx->meta_total_blocks += BLOCK_SECTORS;
+		} else {
+			disk_index = sh->pd_idx;
+			sync_page_io(log->rdev, *log_offset, PAGE_SIZE,
+				     sh->dev[disk_index].page, READ, false);
+			sh->dev[disk_index].log_checksum =
+				le32_to_cpu(payload->checksum[0]);
+			set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
+
+			if (sh->qd_idx >= 0) {
+				disk_index = sh->qd_idx;
+				sync_page_io(log->rdev,
+					     r5l_ring_add(log, *log_offset, BLOCK_SECTORS),
+					     PAGE_SIZE, sh->dev[disk_index].page,
+					     READ, false);
+				sh->dev[disk_index].log_checksum =
+					le32_to_cpu(payload->checksum[1]);
+				set_bit(R5_Wantwrite,
+					&sh->dev[disk_index].flags);
+			}
+			ctx->meta_total_blocks += BLOCK_SECTORS * conf->max_degraded;
+		}
+
+		*log_offset = r5l_ring_add(log, *log_offset,
+					   le32_to_cpu(payload->size));
+		*offset += sizeof(struct r5l_payload_data_parity) +
+			sizeof(__le32) *
+			(le32_to_cpu(payload->size) >> (PAGE_SHIFT - 9));
+		if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_PARITY)
+			break;
+	}
+
+	for (disk_index = 0; disk_index < sh->disks; disk_index++) {
+		void *addr;
+		u32 checksum;
+
+		if (!test_bit(R5_Wantwrite, &sh->dev[disk_index].flags))
+			continue;
+		addr = kmap_atomic(sh->dev[disk_index].page);
+		checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE);
+		kunmap_atomic(addr);
+		if (checksum != sh->dev[disk_index].log_checksum)
+			goto error;
+	}
+
+	for (disk_index = 0; disk_index < sh->disks; disk_index++) {
+		struct md_rdev *rdev, *rrdev;
+
+		if (!test_and_clear_bit(R5_Wantwrite,
+					&sh->dev[disk_index].flags))
+			continue;
+
+		/* in case device is broken */
+		rdev = rcu_dereference(conf->disks[disk_index].rdev);
+		if (rdev)
+			sync_page_io(rdev, stripe_sect, PAGE_SIZE,
+				     sh->dev[disk_index].page, WRITE, false);
+		rrdev = rcu_dereference(conf->disks[disk_index].replacement);
+		if (rrdev)
+			sync_page_io(rrdev, stripe_sect, PAGE_SIZE,
+				     sh->dev[disk_index].page, WRITE, false);
+	}
+	raid5_release_stripe(sh);
+	return 0;
+
+error:
+	for (disk_index = 0; disk_index < sh->disks; disk_index++)
+		sh->dev[disk_index].flags = 0;
+	raid5_release_stripe(sh);
+	return -EINVAL;
+}
+
+static int r5l_recovery_flush_one_meta(struct r5l_log *log,
+				       struct r5l_recovery_ctx *ctx)
+{
+	struct r5conf *conf = log->rdev->mddev->private;
+	struct r5l_payload_data_parity *payload;
+	struct r5l_meta_block *mb;
+	int offset;
+	sector_t log_offset;
+	sector_t stripe_sector;
+
+	mb = page_address(ctx->meta_page);
+	offset = sizeof(struct r5l_meta_block);
+	log_offset = r5l_ring_add(log, ctx->pos, BLOCK_SECTORS);
+
+	while (offset < le32_to_cpu(mb->meta_size)) {
+		int dd;
+
+		payload = (void *)mb + offset;
+		stripe_sector = raid5_compute_sector(conf,
+						     le64_to_cpu(payload->location), 0, &dd, NULL);
+		if (r5l_recovery_flush_one_stripe(log, ctx, stripe_sector,
+						  &offset, &log_offset))
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/* copy data/parity from log to raid disks */
+static void r5l_recovery_flush_log(struct r5l_log *log,
+				   struct r5l_recovery_ctx *ctx)
+{
+	while (1) {
+		if (r5l_read_meta_block(log, ctx))
+			return;
+		if (r5l_recovery_flush_one_meta(log, ctx))
+			return;
+		ctx->seq++;
+		ctx->pos = r5l_ring_add(log, ctx->pos, ctx->meta_total_blocks);
+	}
+}
+
+static int r5l_log_write_empty_meta_block(struct r5l_log *log, sector_t pos,
+					  u64 seq)
+{
+	struct page *page;
+	struct r5l_meta_block *mb;
+	u32 crc;
+
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page)
+		return -ENOMEM;
+	mb = page_address(page);
+	mb->magic = cpu_to_le32(R5LOG_MAGIC);
+	mb->version = R5LOG_VERSION;
+	mb->meta_size = cpu_to_le32(sizeof(struct r5l_meta_block));
+	mb->seq = cpu_to_le64(seq);
+	mb->position = cpu_to_le64(pos);
+	crc = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
+	mb->checksum = cpu_to_le32(crc);
+
+	if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, WRITE_FUA, false)) {
+		__free_page(page);
+		return -EIO;
+	}
+	__free_page(page);
+	return 0;
+}
+
+static int r5l_recovery_log(struct r5l_log *log)
+{
+	struct r5l_recovery_ctx ctx;
+
+	ctx.pos = log->last_checkpoint;
+	ctx.seq = log->last_cp_seq;
+	ctx.meta_page = alloc_page(GFP_KERNEL);
+	if (!ctx.meta_page)
+		return -ENOMEM;
+
+	r5l_recovery_flush_log(log, &ctx);
+	__free_page(ctx.meta_page);
+
+	/*
+	 * we did a recovery. Now ctx.pos points to an invalid meta block. New
+	 * log will start here. but we can't let superblock point to last valid
+	 * meta block. The log might looks like:
+	 * | meta 1| meta 2| meta 3|
+	 * meta 1 is valid, meta 2 is invalid. meta 3 could be valid. If
+	 * superblock points to meta 1, we write a new valid meta 2n.  if crash
+	 * happens again, new recovery will start from meta 1. Since meta 2n is
+	 * valid now, recovery will think meta 3 is valid, which is wrong.
+	 * The solution is we create a new meta in meta2 with its seq == meta
+	 * 1's seq + 10 and let superblock points to meta2. The same recovery will
+	 * not think meta 3 is a valid meta, because its seq doesn't match
+	 */
+	if (ctx.seq > log->last_cp_seq + 1) {
+		int ret;
+
+		ret = r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq + 10);
+		if (ret)
+			return ret;
+		log->seq = ctx.seq + 11;
+		log->log_start = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
+		r5l_write_super(log, ctx.pos);
+	} else {
+		log->log_start = ctx.pos;
+		log->seq = ctx.seq;
+	}
+	return 0;
+}
+
+static void r5l_write_super(struct r5l_log *log, sector_t cp)
+{
+	struct mddev *mddev = log->rdev->mddev;
+
+	log->rdev->journal_tail = cp;
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+}
+
+static int r5l_load_log(struct r5l_log *log)
+{
+	struct md_rdev *rdev = log->rdev;
+	struct page *page;
+	struct r5l_meta_block *mb;
+	sector_t cp = log->rdev->journal_tail;
+	u32 stored_crc, expected_crc;
+	bool create_super = false;
+	int ret;
+
+	/* Make sure it's valid */
+	if (cp >= rdev->sectors || round_down(cp, BLOCK_SECTORS) != cp)
+		cp = 0;
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	if (!sync_page_io(rdev, cp, PAGE_SIZE, page, READ, false)) {
+		ret = -EIO;
+		goto ioerr;
+	}
+	mb = page_address(page);
+
+	if (le32_to_cpu(mb->magic) != R5LOG_MAGIC ||
+	    mb->version != R5LOG_VERSION) {
+		create_super = true;
+		goto create;
+	}
+	stored_crc = le32_to_cpu(mb->checksum);
+	mb->checksum = 0;
+	expected_crc = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
+	if (stored_crc != expected_crc) {
+		create_super = true;
+		goto create;
+	}
+	if (le64_to_cpu(mb->position) != cp) {
+		create_super = true;
+		goto create;
+	}
+create:
+	if (create_super) {
+		log->last_cp_seq = prandom_u32();
+		cp = 0;
+		/*
+		 * Make sure super points to correct address. Log might have
+		 * data very soon. If super hasn't correct log tail address,
+		 * recovery can't find the log
+		 */
+		r5l_write_super(log, cp);
+	} else
+		log->last_cp_seq = le64_to_cpu(mb->seq);
+
+	log->device_size = round_down(rdev->sectors, BLOCK_SECTORS);
+	log->max_free_space = log->device_size >> RECLAIM_MAX_FREE_SPACE_SHIFT;
+	if (log->max_free_space > RECLAIM_MAX_FREE_SPACE)
+		log->max_free_space = RECLAIM_MAX_FREE_SPACE;
+	log->last_checkpoint = cp;
+
+	__free_page(page);
+
+	return r5l_recovery_log(log);
+ioerr:
+	__free_page(page);
+	return ret;
+}
+
+int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
+{
+	struct r5l_log *log;
+
+	if (PAGE_SIZE != 4096)
+		return -EINVAL;
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		return -ENOMEM;
+	log->rdev = rdev;
+
+	log->need_cache_flush = (rdev->bdev->bd_disk->queue->flush_flags != 0);
+
+	log->uuid_checksum = crc32c_le(~0, rdev->mddev->uuid,
+				       sizeof(rdev->mddev->uuid));
+
+	mutex_init(&log->io_mutex);
+
+	spin_lock_init(&log->io_list_lock);
+	INIT_LIST_HEAD(&log->running_ios);
+	INIT_LIST_HEAD(&log->io_end_ios);
+	INIT_LIST_HEAD(&log->flushing_ios);
+	INIT_LIST_HEAD(&log->finished_ios);
+	bio_init(&log->flush_bio);
+
+	log->io_kc = KMEM_CACHE(r5l_io_unit, 0);
+	if (!log->io_kc)
+		goto io_kc;
+
+	log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
+						 log->rdev->mddev, "reclaim");
+	if (!log->reclaim_thread)
+		goto reclaim_thread;
+	init_waitqueue_head(&log->iounit_wait);
+
+	INIT_LIST_HEAD(&log->no_space_stripes);
+	spin_lock_init(&log->no_space_stripes_lock);
+
+	if (r5l_load_log(log))
+		goto error;
+
+	conf->log = log;
+	return 0;
+error:
+	md_unregister_thread(&log->reclaim_thread);
+reclaim_thread:
+	kmem_cache_destroy(log->io_kc);
+io_kc:
+	kfree(log);
+	return -EINVAL;
+}
+
+void r5l_exit_log(struct r5l_log *log)
+{
+	md_unregister_thread(&log->reclaim_thread);
+	kmem_cache_destroy(log->io_kc);
+	kfree(log);
+}

drivers/md/raid5.c

···
 		struct list_head *list = &temp_inactive_list[size - 1];
 
 		/*
-		 * We don't hold any lock here yet, get_active_stripe() might
+		 * We don't hold any lock here yet, raid5_get_active_stripe() might
 		 * remove stripes from the list
 		 */
 		if (!list_empty_careful(list)) {
···
 	return count;
 }
 
-static void release_stripe(struct stripe_head *sh)
+void raid5_release_stripe(struct stripe_head *sh)
 {
 	struct r5conf *conf = sh->raid_conf;
 	unsigned long flags;
···
 	return 0;
 }
 
-static struct stripe_head *
-get_active_stripe(struct r5conf *conf, sector_t sector,
-		  int previous, int noblock, int noquiesce)
+struct stripe_head *
+raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
+			int previous, int noblock, int noquiesce)
 {
 	struct stripe_head *sh;
 	int hash = stripe_hash_locks_hash(sector);
···
 /* Only freshly new full stripe normal write stripe can be added to a batch list */
 static bool stripe_can_batch(struct stripe_head *sh)
 {
+	struct r5conf *conf = sh->raid_conf;
+
+	if (conf->log)
+		return false;
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
 		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
 		is_full_stripe_write(sh);
···
 unlock_out:
 	unlock_two_stripes(head, sh);
 out:
-	release_stripe(head);
+	raid5_release_stripe(head);
 }
 
 /* Determine if 'data_offset' or 'new_data_offset' should be used
···
 
 	might_sleep();
 
+	if (r5l_write_stripe(conf->log, sh) == 0)
+		return;
 	for (i = disks; i--; ) {
 		int rw;
 		int replace_only = 0;
···
 	return_io(&return_bi);
 
 	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 }
 
 static void ops_run_biofill(struct stripe_head *sh)
···
 	if (sh->check_state == check_state_compute_run)
 		sh->check_state = check_state_compute_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 }
 
 /* return a pointer to the address conversion region of the scribble buffer */
···
 	}
 
 	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 }
 
 static void
···
 
 	sh->check_state = check_state_check_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 }
 
 static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
···
 	/* we just created an active stripe so... */
 	atomic_inc(&conf->active_stripes);
 
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 	conf->max_nr_stripes++;
 	return 1;
 }
···
 				if (!p)
 					err = -ENOMEM;
 			}
-		release_stripe(nsh);
+		raid5_release_stripe(nsh);
 	}
 	/* critical section pass, GFP_NOIO no longer needed */
 
···
 	rdev_dec_pending(rdev, conf->mddev);
 	clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 }
 
 static void raid5_end_write_request(struct bio *bi)
···
 	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
 		clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 
 	if (sh->batch_head && sh != sh->batch_head)
-		release_stripe(sh->batch_head);
+		raid5_release_stripe(sh->batch_head);
 }
-
-static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
 
 static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 {
···
 	dev->rreq.bi_private = sh;
 
 	dev->flags = 0;
-	dev->sector = compute_blocknr(sh, i, previous);
+	dev->sector = raid5_compute_blocknr(sh, i, previous);
 }
 
 static void error(struct mddev *mddev, struct md_rdev *rdev)
···
  * Input: a 'big' sector number,
  * Output: index of the data and parity disk, and the sector # in them.
  */
-static sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
-				     int previous, int *dd_idx,
-				     struct stripe_head *sh)
+sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
+			      int previous, int *dd_idx,
+			      struct stripe_head *sh)
 {
 	sector_t stripe, stripe2;
 	sector_t chunk_number;
···
 	return new_sector;
 }
 
-static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
+sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous)
 {
 	struct r5conf *conf = sh->raid_conf;
 	int raid_disks = sh->disks;
···
 		if (bi)
 			bitmap_end = 1;
 
+		r5l_stripe_write_finished(sh);
+
 		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 			wake_up(&conf->wait_for_overlap);
 
···
 		 * the data has not reached the cache yet.
 		 */
 		if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
+		    s->failed > conf->max_degraded &&
 		    (!test_bit(R5_Insync, &sh->dev[i].flags) ||
 		      test_bit(R5_ReadError, &sh->dev[i].flags))) {
 			spin_lock_irq(&sh->stripe_lock);
···
 			WARN_ON(test_bit(R5_SkipCopy, &dev->flags));
 			WARN_ON(dev->page != dev->orig_page);
 		}
+
+	r5l_stripe_write_finished(sh);
+
 	if (!discard_pending &&
 	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
 		int hash;
···
 			struct stripe_head *sh2;
 			struct async_submit_ctl submit;
 
-			sector_t bn = compute_blocknr(sh, i, 1);
+			sector_t bn = raid5_compute_blocknr(sh, i, 1);
 			sector_t s = raid5_compute_sector(conf, bn, 0,
 							  &dd_idx, NULL);
-			sh2 = get_active_stripe(conf, s, 0, 1, 1);
+			sh2 = raid5_get_active_stripe(conf, s, 0, 1, 1);
 			if (sh2 == NULL)
 				/* so far only the early blocks of this stripe
 				 * have been requested.  When later blocks
···
 			if (!test_bit(STRIPE_EXPANDING, &sh2->state) ||
 			   test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) {
 				/* must have already done this block */
-				release_stripe(sh2);
+				raid5_release_stripe(sh2);
 				continue;
 			}
 
···
 				set_bit(STRIPE_EXPAND_READY, &sh2->state);
 				set_bit(STRIPE_HANDLE, &sh2->state);
 			}
-			release_stripe(sh2);
+			raid5_release_stripe(sh2);
 
 		}
 	/* done submitting copies, wait for them to complete */
···
 	s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state) && !sh->batch_head;
 	s->failed_num[0] = -1;
 	s->failed_num[1] = -1;
+	s->log_failed = r5l_log_disk_error(conf);
 
 	/* Now to look around and see what can be done */
 	rcu_read_lock();
···
 		if (handle_flags == 0 ||
 		    sh->state & handle_flags)
 			set_bit(STRIPE_HANDLE, &sh->state);
-		release_stripe(sh);
+		raid5_release_stripe(sh);
 	}
 	spin_lock_irq(&head_sh->stripe_lock);
 	head_sh->batch_head = NULL;
···
 
 	analyse_stripe(sh, &s);
 
+	if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
+		goto finish;
+
 	if (s.handle_bad_blocks) {
 		set_bit(STRIPE_HANDLE, &sh->state);
 		goto finish;
···
 	/* check if the array has lost more than max_degraded devices and,
 	 * if so, some requests might need to be failed.
 	 */
-	if (s.failed > conf->max_degraded) {
+	if (s.failed > conf->max_degraded || s.log_failed) {
 		sh->check_state = 0;
 		sh->reconstruct_state = 0;
 		break_stripe_batch_list(sh, 0);
···
 	/* Finish reconstruct operations initiated by the expansion process */
 	if (sh->reconstruct_state == reconstruct_state_result) {
 		struct stripe_head *sh_src
-			= get_active_stripe(conf, sh->sector, 1, 1, 1);
+			= raid5_get_active_stripe(conf, sh->sector, 1, 1, 1);
 		if (sh_src && test_bit(STRIPE_EXPAND_SOURCE, &sh_src->state)) {
 			/* sh cannot be written until sh_src has been read.
 			 * so arrange for sh to be delayed a little
···
 			if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
 					      &sh_src->state))
 				atomic_inc(&conf->preread_active_stripes);
-			release_stripe(sh_src);
+			raid5_release_stripe(sh_src);
 			goto finish;
 		}
 		if (sh_src)
-			release_stripe(sh_src);
+			raid5_release_stripe(sh_src);
 
 		sh->reconstruct_state = reconstruct_state_idle;
 		clear_bit(STRIPE_EXPANDING, &sh->state);
···
 	struct raid5_plug_cb *cb;
 
 	if (!blk_cb) {
-		release_stripe(sh);
+		raid5_release_stripe(sh);
 		return;
 	}
 
···
 	if (!test_and_set_bit(STRIPE_ON_UNPLUG_LIST, &sh->state))
 		list_add_tail(&sh->lru, &cb->list);
 	else
-		release_stripe(sh);
+		raid5_release_stripe(sh);
 }
 
 static void make_discard_request(struct mddev *mddev, struct bio *bi)
···
 		DEFINE_WAIT(w);
 		int d;
 	again:
-		sh = get_active_stripe(conf, logical_sector, 0, 0, 0);
+		sh = raid5_get_active_stripe(conf, logical_sector, 0, 0, 0);
 		prepare_to_wait(&conf->wait_for_overlap, &w,
 				TASK_UNINTERRUPTIBLE);
 		set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
 		if (test_bit(STRIPE_SYNCING, &sh->state)) {
-			release_stripe(sh);
+			raid5_release_stripe(sh);
 			schedule();
 			goto again;
 		}
···
 			if (sh->dev[d].towrite || sh->dev[d].toread) {
 				set_bit(R5_Overlap, &sh->dev[d].flags);
 				spin_unlock_irq(&sh->stripe_lock);
-				release_stripe(sh);
+				raid5_release_stripe(sh);
 				schedule();
 				goto again;
 			}
···
 	bool do_prepare;
 
 	if (unlikely(bi->bi_rw & REQ_FLUSH)) {
-		md_flush_request(mddev, bi);
-		return;
+		int ret = r5l_handle_flush_request(conf->log, bi);
+
+		if (ret == 0)
+			return;
+		if (ret == -ENODEV) {
+			md_flush_request(mddev, bi);
+			return;
+		}
+		/* ret == -EAGAIN, fallback */
 	}
 
 	md_write_start(mddev, bi);
···
 			(unsigned long long)new_sector,
 			(unsigned long long)logical_sector);
 
-		sh = get_active_stripe(conf, new_sector, previous,
+		sh = raid5_get_active_stripe(conf, new_sector, previous,
 				       (bi->bi_rw&RWA_MASK), 0);
 		if (sh) {
 			if (unlikely(previous)) {
···
 					must_retry = 1;
 				spin_unlock_irq(&conf->device_lock);
 				if (must_retry) {
-					release_stripe(sh);
+					raid5_release_stripe(sh);
 					schedule();
 					do_prepare = true;
 					goto retry;
···
 				/* Might have got the wrong stripe_head
 				 * by accident
 				 */
-				release_stripe(sh);
+				raid5_release_stripe(sh);
 				goto retry;
 			}
 
 			if (rw == WRITE &&
 			    logical_sector >= mddev->suspend_lo &&
 			    logical_sector < mddev->suspend_hi) {
-				release_stripe(sh);
+				raid5_release_stripe(sh);
 				/* As the suspend_* range is controlled by
 				 * userspace, we want an interruptible
 				 * wait.
···
 				 * and wait a while
 				 */
 				md_wakeup_thread(mddev->thread);
-				release_stripe(sh);
+				raid5_release_stripe(sh);
 				schedule();
 				do_prepare = true;
 				goto retry;
···
 	for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
 		int j;
 		int skipped_disk = 0;
-		sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
+		sh = raid5_get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
 		set_bit(STRIPE_EXPANDING, &sh->state);
 		atomic_inc(&conf->reshape_stripes);
 		/* If any of this stripe is beyond the end of the old
···
 			if (conf->level == 6 &&
 			    j == sh->qd_idx)
 				continue;
-			s = compute_blocknr(sh, j, 0);
+			s = raid5_compute_blocknr(sh, j, 0);
 			if (s < raid5_size(mddev, 0, 0)) {
 				skipped_disk = 1;
 				continue;
···
 	if (last_sector >= mddev->dev_sectors)
 		last_sector = mddev->dev_sectors - 1;
 	while (first_sector <= last_sector) {
-		sh = get_active_stripe(conf, first_sector, 1, 0, 1);
+		sh = raid5_get_active_stripe(conf, first_sector, 1, 0, 1);
 		set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 		set_bit(STRIPE_HANDLE, &sh->state);
-		release_stripe(sh);
+		raid5_release_stripe(sh);
 		first_sector += STRIPE_SECTORS;
 	}
 	/* Now that the sources are clearly marked, we can release
···
 	while (!list_empty(&stripes)) {
 		sh = list_entry(stripes.next, struct stripe_head, lru);
 		list_del_init(&sh->lru);
-		release_stripe(sh);
+		raid5_release_stripe(sh);
 	}
 	/* If this takes us to the resync_max point where we have to pause,
 	 * then we need to write out the superblock.
···
 		return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
 	}
 
-	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+	bitmap_cond_end_sync(mddev->bitmap, sector_nr, false);
 
-	sh = get_active_stripe(conf, sector_nr, 0, 1, 0);
+	sh = raid5_get_active_stripe(conf, sector_nr, 0, 1, 0);
 	if (sh == NULL) {
-		sh = get_active_stripe(conf, sector_nr, 0, 0, 0);
+		sh = raid5_get_active_stripe(conf, sector_nr, 0, 0, 0);
 		/* make sure we don't swamp the stripe cache if someone else
 		 * is trying to get access
 		 */
···
 	set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
 	set_bit(STRIPE_HANDLE, &sh->state);
 
-	release_stripe(sh);
+	raid5_release_stripe(sh);
 
 	return STRIPE_SECTORS;
 }
···
 			/* already done this stripe */
 			continue;
 
-		sh = get_active_stripe(conf, sector, 0, 1, 1);
+		sh = raid5_get_active_stripe(conf, sector, 0, 1, 1);
 
 		if (!sh) {
 			/* failed to get a stripe - must wait */
···
 		}
 
 		if (!add_stripe_bio(sh, raid_bio, dd_idx, 0, 0)) {
-			release_stripe(sh);
+			raid5_release_stripe(sh);
 			raid5_set_bi_processed_stripes(raid_bio, scnt);
 			conf->retry_read_aligned = raid_bio;
 			return handled;
···
 
 		set_bit(R5_ReadNoMerge, &sh->dev[dd_idx].flags);
 		handle_stripe(sh);
-		release_stripe(sh);
+		raid5_release_stripe(sh);
 		handled++;
 	}
 	remaining = raid5_dec_bi_active_stripes(raid_bio);
···
 		for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++)
 			if (!list_empty(temp_inactive_list + i))
 				break;
-		if (i == NR_STRIPE_HASH_LOCKS)
+		if (i == NR_STRIPE_HASH_LOCKS) {
+			spin_unlock_irq(&conf->device_lock);
+			r5l_flush_stripe_to_raid(conf->log);
+			spin_lock_irq(&conf->device_lock);
 			return batch_size;
+		}
 		release_inactive = true;
 	}
 	spin_unlock_irq(&conf->device_lock);
···
 	release_inactive_stripe_list(conf, temp_inactive_list,
 				     NR_STRIPE_HASH_LOCKS);
 
+	r5l_flush_stripe_to_raid(conf->log);
 	if (release_inactive) {
 		spin_lock_irq(&conf->device_lock);
 		return 0;
···
 
 	for (i = 0; i < batch_size; i++)
 		handle_stripe(batch[i]);
+	r5l_write_stripe_run(conf->log);
 
 	cond_resched();
 
···
 		set_bit(R5_DID_ALLOC, &conf->cache_state);
 		mutex_unlock(&conf->cache_size_mutex);
 	}
+
+	r5l_flush_stripe_to_raid(conf->log);
 
 	async_tx_issue_pending_all();
 	blk_finish_plug(&plug);
···
 
 static void free_conf(struct r5conf *conf)
 {
+	if (conf->log)
+		r5l_exit_log(conf->log);
 	if (conf->shrinker.seeks)
 		unregister_shrinker(&conf->shrinker);
+
 	free_thread_groups(conf);
 	shrink_stripes(conf);
 	raid5_free_percpu(conf);
···
 	rdev_for_each(rdev, mddev) {
 		raid_disk = rdev->raid_disk;
 		if (raid_disk >= max_disks
-		    || raid_disk < 0)
+		    || raid_disk < 0 || test_bit(Journal, &rdev->flags))
 			continue;
 		disk = conf->disks + raid_disk;
 
···
 	int working_disks = 0;
 	int dirty_parity_disks = 0;
 	struct md_rdev *rdev;
+	struct md_rdev *journal_dev = NULL;
 	sector_t reshape_offset = 0;
 	int i;
 	long long min_offset_diff = 0;
···
 
 	rdev_for_each(rdev, mddev) {
 		long long diff;
+
+		if (test_bit(Journal, &rdev->flags)) {
+			journal_dev = rdev;
+			continue;
+		}
 		if (rdev->raid_disk < 0)
 			continue;
 		diff = (rdev->new_data_offset - rdev->data_offset);
···
 		int max_degraded = (mddev->level == 6 ? 2 : 1);
 		int chunk_sectors;
 		int new_data_disks;
+
+		if (journal_dev) {
+			printk(KERN_ERR "md/raid:%s: don't support reshape with journal - aborting.\n",
+			       mdname(mddev));
+			return -EINVAL;
+		}
 
 		if (mddev->new_level != mddev->level) {
 			printk(KERN_ERR "md/raid:%s: unsupported reshape "
···
 
 	if (IS_ERR(conf))
 		return PTR_ERR(conf);
+
+	if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
+		printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
+		       mdname(mddev));
+		mddev->ro = 1;
+		set_disk_ro(mddev->gendisk, 1);
+	}
 
 	conf->min_offset_diff = min_offset_diff;
 	mddev->thread = conf->thread;
···
 						mddev->queue);
 	}
 
+	if (journal_dev) {
+		char b[BDEVNAME_SIZE];
+
+		printk(KERN_INFO"md/raid:%s: using device %s as journal\n",
+		       mdname(mddev), bdevname(journal_dev->bdev, b));
+		r5l_init_log(conf, journal_dev);
+	}
+
 	return 0;
 abort:
 	md_unregister_thread(&mddev->thread);
···
 	struct disk_info *p = conf->disks + number;
 
 	print_raid5_conf(conf);
+	if (test_bit(Journal, &rdev->flags)) {
+		/*
+		 * journal disk is not removable, but we need give a chance to
+		 * update superblock of other disks. Otherwise journal disk
+		 * will be considered as 'fresh'
+		 */
+		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		return -EINVAL;
+	}
 	if (rdev == p->rdev)
 		rdevp = &p->rdev;
 	else if (rdev == p->replacement)
···
 	int first = 0;
 	int last = conf->raid_disks - 1;
 
+	if (test_bit(Journal, &rdev->flags))
+		return -EINVAL;
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
 
···
 	sector_t newsize;
 	struct r5conf *conf = mddev->private;
 
+	if (conf->log)
+		return -EINVAL;
 	sectors &= ~((sector_t)conf->chunk_sectors - 1);
 	newsize = raid5_size(mddev, sectors, mddev->raid_disks);
 	if (mddev->external_size &&
···
 {
 	struct r5conf *conf = mddev->private;
 
+	if (conf->log)
+		return -EINVAL;
 	if (mddev->delta_disks == 0 &&
 	    mddev->new_layout == mddev->layout &&
 	    mddev->new_chunk_sectors == mddev->chunk_sectors)
···
 		unlock_all_device_hash_locks_irq(conf);
 		break;
 	}
+	r5l_quiesce(conf->log, state);
 }
 
 static void *raid45_takeover_raid0(struct mddev *mddev, int level)

drivers/md/raid5.h

···
 	struct stripe_head	*batch_head; /* protected by stripe lock */
 	spinlock_t		batch_lock; /* only header's lock is useful */
 	struct list_head	batch_list; /* protected by head's batch lock*/
+
+	struct r5l_io_unit	*log_io;
+	struct list_head	log_list;
 	/**
 	 * struct stripe_operations
 	 * @target - STRIPE_OP_COMPUTE_BLK target
···
 		struct bio	*toread, *read, *towrite, *written;
 		sector_t	sector;			/* sector of this page */
 		unsigned long	flags;
+		u32		log_checksum;
 	} dev[1]; /* allocated with extra space depending of RAID geometry */
 };
 
···
 	struct bio_list return_bi;
 	struct md_rdev *blocked_rdev;
 	int handle_bad_blocks;
+	int log_failed;
 };
 
 /* Flags for struct r5dev.flags */
···
 	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
 				 * to batch yet.
 				 */
+	STRIPE_LOG_TRAPPED, /* trapped into log */
 };
 
 #define STRIPE_EXPAND_SYNC_FLAGS \
···
 	struct r5worker_group	*worker_groups;
 	int			group_cnt;
 	int			worker_cnt_per_group;
+	struct r5l_log		*log;
 };
 
 
···
 
 extern void md_raid5_kick_device(struct r5conf *conf);
 extern int raid5_set_cache_size(struct mddev *mddev, int size);
+extern sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous);
+extern void raid5_release_stripe(struct stripe_head *sh);
+extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
+				     int previous, int *dd_idx,
+				     struct stripe_head *sh);
+extern struct stripe_head *
+raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
+			int previous, int noblock, int noquiesce);
+extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev);
+extern void r5l_exit_log(struct r5l_log *log);
+extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh);
+extern void r5l_write_stripe_run(struct r5l_log *log);
+extern void r5l_flush_stripe_to_raid(struct r5l_log *log);
+extern void r5l_stripe_write_finished(struct stripe_head *sh);
+extern int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio);
+extern void r5l_quiesce(struct r5l_log *log, int state);
+extern bool r5l_log_disk_error(struct r5conf *conf);
 #endif

include/uapi/linux/raid/md_p.h

···
 				   * read requests will only be sent here in
 				   * dire need
 				   */
+#define MD_DISK_JOURNAL		18 /* disk is used as the write journal in RAID-5/6 */
+
+#define MD_DISK_ROLE_SPARE	0xffff
+#define MD_DISK_ROLE_FAULTY	0xfffe
+#define MD_DISK_ROLE_JOURNAL	0xfffd
+#define MD_DISK_ROLE_MAX	0xff00 /* max value of regular disk role */
 
 typedef struct mdp_device_descriptor_s {
 	__u32 number;		/* 0 Device number in the entire set	      */
···
 	__le64	data_offset;	/* sector start of data, often 0 */
 	__le64	data_size;	/* sectors in this device that can be used for data */
 	__le64	super_offset;	/* sector start of this superblock */
-	__le64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+	union {
+		__le64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+		__le64	journal_tail;/* journal tail of journal device (from data_offset) */
+	};
 	__le32	dev_number;	/* permanent identifier of this  device - not role in raid */
 	__le32	cnt_corrected_read; /* number of read errors that were corrected by re-writing */
 	__u8	device_uuid[16]; /* user-space setable, ignored by kernel */
···
 #define	MD_FEATURE_RECOVERY_BITMAP	128 /* recovery that is happening
 					     * is guided by bitmap.
 					     */
+#define MD_FEATURE_CLUSTERED		256 /* clustered MD */
+#define	MD_FEATURE_JOURNAL		512 /* support write cache */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
···
 					|MD_FEATURE_RESHAPE_BACKWARDS	\
 					|MD_FEATURE_NEW_OFFSET		\
 					|MD_FEATURE_RECOVERY_BITMAP	\
+					|MD_FEATURE_CLUSTERED		\
+					|MD_FEATURE_JOURNAL		\
 					)
 
+struct r5l_payload_header {
+	__le16 type;
+	__le16 flags;
+} __attribute__ ((__packed__));
+
+enum r5l_payload_type {
+	R5LOG_PAYLOAD_DATA = 0,
+	R5LOG_PAYLOAD_PARITY = 1,
+	R5LOG_PAYLOAD_FLUSH = 2,
+};
+
+struct r5l_payload_data_parity {
+	struct r5l_payload_header header;
+	__le32 size;		/* sector. data/parity size. each 4k
+				 * has a checksum */
+	__le64 location;	/* sector. For data, it's raid sector. For
+				 * parity, it's stripe sector */
+	__le32 checksum[];
+} __attribute__ ((__packed__));
+
+enum r5l_payload_data_parity_flag {
+	R5LOG_PAYLOAD_FLAG_DISCARD = 1, /* payload is discard */
+	/*
+	 * RESHAPED/RESHAPING is only set when there is reshape activity. Note,
+	 * both data/parity of a stripe should have the same flag set
+	 *
+	 * RESHAPED: reshape is running, and this stripe finished reshape
+	 * RESHAPING: reshape is running, and this stripe isn't reshaped
+	 */
+	R5LOG_PAYLOAD_FLAG_RESHAPED = 2,
+	R5LOG_PAYLOAD_FLAG_RESHAPING = 3,
+};
+
+struct r5l_payload_flush {
+	struct r5l_payload_header header;
+	__le32 size; /* flush_stripes size, bytes */
+	__le64 flush_stripes[];
+} __attribute__ ((__packed__));
+
+enum r5l_payload_flush_flag {
+	R5LOG_PAYLOAD_FLAG_FLUSH_STRIPE = 1, /* data represents whole stripe */
+};
+
+struct r5l_meta_block {
+	__le32 magic;
+	__le32 checksum;
+	__u8 version;
+	__u8 __zero_pading_1;
+	__le16 __zero_pading_2;
+	__le32 meta_size; /* whole size of the block */
+
+	__le64 seq;
+	__le64 position; /* sector, start from rdev->data_offset, current position */
+	struct r5l_payload_header payloads[];
+} __attribute__ ((__packed__));
+
+#define R5LOG_VERSION 0x1
+#define R5LOG_MAGIC 0x6433c509
 #endif