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

@@ -17,7 +17,7 @@ dm-cache-smq-y   += dm-cache-policy-smq.o
 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

@@ -613,12 +613,10 @@ re_read:
 	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);
@@ -628,7 +626,7 @@ re_read:
 	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";
@@ -1572,7 +1570,7 @@ void bitmap_close_sync(struct bitmap *bitmap)
 }
 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;
@@ -1583,7 +1581,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 		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

@@ -9,8 +9,10 @@
 #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
 
 /*
@@ -255,7 +257,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
 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.h

@@ -12,15 +12,15 @@ struct md_cluster_operations {
 	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.h

@@ -87,10 +87,16 @@ struct md_rdev {
 					 * 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
@@ -172,6 +178,11 @@ enum flag_bits {
 				 * 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)
@@ -221,6 +232,8 @@ struct mddev {
 #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;
@@ -658,7 +671,7 @@ extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 				   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

@@ -90,6 +90,8 @@ static void r1bio_pool_free(void *r1_bio, void *data)
 #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)
@@ -1590,6 +1592,15 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	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) {
@@ -2495,6 +2506,11 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 
 		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;
 	}
 
@@ -2515,7 +2531,12 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 		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);
@@ -2706,6 +2727,16 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
  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
 	 */
@@ -3020,9 +3051,11 @@ static int raid1_reshape(struct mddev *mddev)
 		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

@@ -111,6 +111,13 @@ struct r1conf {
 	 * 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

@@ -3149,7 +3149,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		/* 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.h

@@ -223,6 +223,9 @@ struct stripe_head {
 	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
@@ -244,6 +247,7 @@ struct stripe_head {
 		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 */
 };
 
@@ -268,6 +272,7 @@ struct stripe_head_state {
 	struct bio_list return_bi;
 	struct md_rdev *blocked_rdev;
 	int handle_bad_blocks;
+	int log_failed;
 };
 
 /* Flags for struct r5dev.flags */
@@ -340,6 +345,7 @@ enum {
 	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
 				 * to batch yet.
 				 */
+	STRIPE_LOG_TRAPPED, /* trapped into log */
 };
 
 #define STRIPE_EXPAND_SYNC_FLAGS \
@@ -543,6 +549,7 @@ struct r5conf {
 	struct r5worker_group	*worker_groups;
 	int			group_cnt;
 	int			worker_cnt_per_group;
+	struct r5l_log		*log;
 };
 
 
@@ -609,4 +616,21 @@ static inline int algorithm_is_DDF(int layout)
 
 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

@@ -89,6 +89,12 @@
 				   * 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	      */
@@ -252,7 +258,10 @@ struct mdp_superblock_1 {
 	__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 */
@@ -302,6 +311,8 @@ struct mdp_superblock_1 {
 #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	\
@@ -310,6 +321,66 @@ struct mdp_superblock_1 {
 					|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