X-Git-Url: http://git.ipfire.org/?a=blobdiff_plain;f=super1.c;h=882cd61a0f3285ad244363bfa9fb92c5811045d3;hb=72b616aff26e64079727ea908073027c08f99c07;hp=a95c8d0cce9656658a097ce45e391dde00a77567;hpb=06bd679317a2a514aa7d51b54b5ad2a01742e42e;p=thirdparty%2Fmdadm.git

diff --git a/super1.c b/super1.c
index a95c8d0c..882cd61a 100644
--- a/super1.c
+++ b/super1.c
@@ -1,7 +1,7 @@
 /*
  * mdadm - manage Linux "md" devices aka RAID arrays.
  *
- * Copyright (C) 2001-2009 Neil Brown <neilb@suse.de>
+ * Copyright (C) 2001-2016 Neil Brown <neilb@suse.com>
  *
  *
  *    This program is free software; you can redistribute it and/or modify
@@ -68,12 +68,16 @@ struct mdp_superblock_1 {
 	__u64	data_offset;	/* sector start of data, often 0 */
 	__u64	data_size;	/* sectors in this device that can be used for data */
 	__u64	super_offset;	/* sector start of this superblock */
-	__u64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+	union {
+		__u64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+		__u64	journal_tail;/* journal tail of journal device (from data_offset) */
+	};
 	__u32	dev_number;	/* permanent identifier of this  device - not role in raid */
 	__u32	cnt_corrected_read; /* number of read errors that were corrected by re-writing */
 	__u8	device_uuid[16]; /* user-space setable, ignored by kernel */
 	__u8    devflags;        /* per-device flags.  Only one defined...*/
 #define WriteMostly1    1        /* mask for writemostly flag in above */
+#define FailFast1	2        /* Device should get FailFast requests */
 	/* bad block log.  If there are any bad blocks the feature flag is set.
 	 * if offset and size are non-zero, that space is reserved and available.
 	 */
@@ -125,6 +129,8 @@ struct misc_dev_info {
 					    * backwards anyway.
 					    */
 #define	MD_FEATURE_NEW_OFFSET		64 /* new_offset must be honoured */
+#define	MD_FEATURE_BITMAP_VERSIONED	256 /* bitmap version number checked properly */
+#define	MD_FEATURE_JOURNAL		512 /* support write journal */
 #define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
 					|MD_FEATURE_RECOVERY_OFFSET	\
 					|MD_FEATURE_RESHAPE_ACTIVE	\
@@ -132,8 +138,40 @@ struct misc_dev_info {
 					|MD_FEATURE_REPLACEMENT		\
 					|MD_FEATURE_RESHAPE_BACKWARDS	\
 					|MD_FEATURE_NEW_OFFSET		\
+					|MD_FEATURE_BITMAP_VERSIONED	\
+					|MD_FEATURE_JOURNAL		\
 					)
 
+#ifndef MDASSEMBLE
+static int role_from_sb(struct mdp_superblock_1 *sb)
+{
+	unsigned int d;
+	int role;
+
+	d = __le32_to_cpu(sb->dev_number);
+	if (d < __le32_to_cpu(sb->max_dev))
+		role = __le16_to_cpu(sb->dev_roles[d]);
+	else
+		role = MD_DISK_ROLE_SPARE;
+	return role;
+}
+#endif
+
+/* return how many bytes are needed for bitmap, for cluster-md each node
+ * should have it's own bitmap */
+static unsigned int calc_bitmap_size(bitmap_super_t *bms, unsigned int boundary)
+{
+	unsigned long long bits, bytes;
+
+	bits = bitmap_bits(__le64_to_cpu(bms->sync_size),
+			   __le32_to_cpu(bms->chunksize));
+	bytes = (bits+7) >> 3;
+	bytes += sizeof(bitmap_super_t);
+	bytes = ROUND_UP(bytes, boundary);
+
+	return bytes;
+}
+
 static unsigned int calc_sb_1_csum(struct mdp_superblock_1 * sb)
 {
 	unsigned int disk_csum, csum;
@@ -176,8 +214,7 @@ struct align_fd {
 static void init_afd(struct align_fd *afd, int fd)
 {
 	afd->fd = fd;
-
-	if (ioctl(afd->fd, BLKSSZGET, &afd->blk_sz) != 0)
+	if (!get_dev_sector_size(afd->fd, NULL, (unsigned int *)&afd->blk_sz))
 		afd->blk_sz = 512;
 }
 
@@ -256,6 +293,7 @@ static int awrite(struct align_fd *afd, void *buf, int len)
 static void examine_super1(struct supertype *st, char *homehost)
 {
 	struct mdp_superblock_1 *sb = st->sb;
+	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb)+MAX_SB_SIZE);
 	time_t atime;
 	unsigned int d;
 	int role;
@@ -289,6 +327,8 @@ static void examine_super1(struct supertype *st, char *homehost)
 	    strncmp(sb->set_name, homehost, l) == 0)
 		printf("  (local to host %s)", homehost);
 	printf("\n");
+	if (bms->nodes > 0 && (__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET))
+		printf("   Cluster Name : %-64s\n", bms->cluster_name);
 	atime = __le64_to_cpu(sb->ctime) & 0xFFFFFFFFFFULL;
 	printf("  Creation Time : %.24s\n", ctime(&atime));
 	c=map_num(pers, __le32_to_cpu(sb->level));
@@ -391,6 +431,8 @@ static void examine_super1(struct supertype *st, char *homehost)
 		printf("          Flags :");
 		if (sb->devflags & WriteMostly1)
 			printf(" write-mostly");
+		if (sb->devflags & FailFast1)
+			printf(" failfast");
 		printf("\n");
 	}
 
@@ -446,25 +488,23 @@ static void examine_super1(struct supertype *st, char *homehost)
 	/* This turns out to just be confusing */
 	printf("    Array Slot : %d (", __le32_to_cpu(sb->dev_number));
 	for (i= __le32_to_cpu(sb->max_dev); i> 0 ; i--)
-		if (__le16_to_cpu(sb->dev_roles[i-1]) != 0xffff)
+		if (__le16_to_cpu(sb->dev_roles[i-1]) != MD_DISK_ROLE_SPARE)
 			break;
 	for (d=0; d < i; d++) {
 		int role = __le16_to_cpu(sb->dev_roles[d]);
 		if (d) printf(", ");
-		if (role == 0xffff) printf("empty");
-		else if(role == 0xfffe) printf("failed");
+		if (role == MD_DISK_ROLE_SPARE) printf("empty");
+		else if(role == MD_DISK_ROLE_FAULTY) printf("failed");
 		else printf("%d", role);
 	}
 	printf(")\n");
 #endif
 	printf("   Device Role : ");
-	d = __le32_to_cpu(sb->dev_number);
-	if (d < __le32_to_cpu(sb->max_dev))
-		role = __le16_to_cpu(sb->dev_roles[d]);
-	else
-		role = 0xFFFF;
-	if (role >= 0xFFFE)
+	role = role_from_sb(sb);
+	if (role >= MD_DISK_ROLE_FAULTY)
 		printf("spare\n");
+	else if (role == MD_DISK_ROLE_JOURNAL)
+		printf("Journal\n");
 	else if (sb->feature_map & __cpu_to_le32(MD_FEATURE_REPLACEMENT))
 		printf("Replacement device %d\n", role);
 	else
@@ -493,7 +533,7 @@ static void examine_super1(struct supertype *st, char *homehost)
 	faulty = 0;
 	for (i=0; i< __le32_to_cpu(sb->max_dev); i++) {
 		int role = __le16_to_cpu(sb->dev_roles[i]);
-		if (role == 0xFFFE)
+		if (role == MD_DISK_ROLE_FAULTY)
 			faulty++;
 	}
 	if (faulty) printf(" %d failed", faulty);
@@ -681,12 +721,8 @@ static int copy_metadata1(struct supertype *st, int from, int to)
 				/* have the header, can calculate
 				 * correct bitmap bytes */
 				bitmap_super_t *bms;
-				int bits;
 				bms = (void*)buf;
-				bits = __le64_to_cpu(bms->sync_size) / (__le32_to_cpu(bms->chunksize)>>9);
-				bytes = (bits+7) >> 3;
-				bytes += sizeof(bitmap_super_t);
-				bytes = ROUND_UP(bytes, 512);
+				bytes = calc_bitmap_size(bms, 512);
 				if (n > bytes)
 					n =  bytes;
 			}
@@ -697,12 +733,12 @@ static int copy_metadata1(struct supertype *st, int from, int to)
 	}
 
 	if (super.bblog_size != 0 &&
-	    __le32_to_cpu(super.bblog_size) <= 100 &&
+	    __le16_to_cpu(super.bblog_size) <= 100 &&
 	    super.bblog_offset != 0 &&
 	    (super.feature_map & __le32_to_cpu(MD_FEATURE_BAD_BLOCKS))) {
 		/* There is a bad block log */
 		unsigned long long bb_offset = sb_offset;
-		int bytes = __le32_to_cpu(super.bblog_size) * 512;
+		int bytes = __le16_to_cpu(super.bblog_size) * 512;
 		int written = 0;
 		struct align_fd afrom, ato;
 
@@ -740,6 +776,7 @@ err:
 static void detail_super1(struct supertype *st, char *homehost)
 {
 	struct mdp_superblock_1 *sb = st->sb;
+	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
 	int i;
 	int l = homehost ? strlen(homehost) : 0;
 
@@ -748,6 +785,8 @@ static void detail_super1(struct supertype *st, char *homehost)
 	    sb->set_name[l] == ':' &&
 	    strncmp(sb->set_name, homehost, l) == 0)
 		printf("  (local to host %s)", homehost);
+	if (bms->nodes > 0 && (__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET))
+	    printf("\n   Cluster Name : %-64s", bms->cluster_name);
 	printf("\n           UUID : ");
 	for (i=0; i<16; i++) {
 		if ((i&3)==0 && i != 0) printf(":");
@@ -796,7 +835,7 @@ static int examine_badblocks_super1(struct supertype *st, int fd, char *devname)
 	__u64 *bbl, *bbp;
 	int i;
 
-	if  (!sb->bblog_size || __le32_to_cpu(sb->bblog_size) > 100
+	if  (!sb->bblog_size || __le16_to_cpu(sb->bblog_size) > 100
 	     || !sb->bblog_offset){
 		printf("No bad-blocks list configured on %s\n", devname);
 		return 0;
@@ -807,7 +846,7 @@ static int examine_badblocks_super1(struct supertype *st, int fd, char *devname)
 		return 0;
 	}
 
-	size = __le32_to_cpu(sb->bblog_size)* 512;
+	size = __le16_to_cpu(sb->bblog_size)* 512;
 	if (posix_memalign((void**)&bbl, 4096, size) != 0) {
 		pr_err("could not allocate badblocks list\n");
 		return 0;
@@ -904,7 +943,7 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 	info->disk.number = __le32_to_cpu(sb->dev_number);
 	if (__le32_to_cpu(sb->dev_number) >= __le32_to_cpu(sb->max_dev) ||
 	    __le32_to_cpu(sb->dev_number) >= MAX_DEVS)
-		role = 0xfffe;
+		role = MD_DISK_ROLE_FAULTY;
 	else
 		role = __le16_to_cpu(sb->dev_roles[__le32_to_cpu(sb->dev_number)]);
 
@@ -937,20 +976,16 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 		earliest = super_offset + (32+4)*2; /* match kernel */
 		if (info->bitmap_offset > 0) {
 			unsigned long long bmend = info->bitmap_offset;
-			unsigned long long size = __le64_to_cpu(bsb->sync_size);
-			size /= __le32_to_cpu(bsb->chunksize) >> 9;
-			size = (size + 7) >> 3;
-			size += sizeof(bitmap_super_t);
-			size = ROUND_UP(size, 4096);
+			unsigned long long size = calc_bitmap_size(bsb, 4096);
 			size /= 512;
 			bmend += size;
 			if (bmend > earliest)
-				bmend = earliest;
+				earliest = bmend;
 		}
 		if (sb->bblog_offset && sb->bblog_size) {
 			unsigned long long bbend = super_offset;
 			bbend += (int32_t)__le32_to_cpu(sb->bblog_offset);
-			bbend += __le32_to_cpu(sb->bblog_size);
+			bbend += __le16_to_cpu(sb->bblog_size);
 			if (bbend > earliest)
 				earliest = bbend;
 		}
@@ -971,18 +1006,25 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 
 	info->disk.raid_disk = -1;
 	switch(role) {
-	case 0xFFFF:
+	case MD_DISK_ROLE_SPARE:
 		info->disk.state = 0; /* spare: not active, not sync, not faulty */
 		break;
-	case 0xFFFE:
+	case MD_DISK_ROLE_FAULTY:
 		info->disk.state = 1; /* faulty */
 		break;
+	case MD_DISK_ROLE_JOURNAL:
+		info->disk.state = (1 << MD_DISK_JOURNAL);
+		info->disk.raid_disk = role;
+		info->space_after = (misc->device_size - info->data_offset) % 8; /* journal uses all 4kB blocks*/
+		break;
 	default:
 		info->disk.state = 6; /* active and in sync */
 		info->disk.raid_disk = role;
 	}
 	if (sb->devflags & WriteMostly1)
 		info->disk.state |= (1 << MD_DISK_WRITEMOSTLY);
+	if (sb->devflags & FailFast1)
+		info->disk.state |= (1 << MD_DISK_FAILFAST);
 	info->events = __le64_to_cpu(sb->events);
 	sprintf(info->text_version, "1.%d", st->minor_version);
 	info->safe_mode_delay = 200;
@@ -1024,7 +1066,7 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 			map[i] = 0;
 	for (i = 0; i < __le32_to_cpu(sb->max_dev); i++) {
 		role = __le16_to_cpu(sb->dev_roles[i]);
-		if (/*role == 0xFFFF || */role < (unsigned) info->array.raid_disks) {
+		if (/*role == MD_DISK_ROLE_SPARE || */role < (unsigned) info->array.raid_disks) {
 			working++;
 			if (map && role < map_disks)
 				map[role] = 1;
@@ -1032,6 +1074,9 @@ static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
 	}
 
 	info->array.working_disks = working;
+	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_JOURNAL))
+		info->journal_device_required = 1;
+	info->journal_clean = 0;
 }
 
 static struct mdinfo *container_content1(struct supertype *st, char *subarray)
@@ -1056,7 +1101,18 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 	 * ignored.
 	 */
 	int rv = 0;
+	int lockid;
 	struct mdp_superblock_1 *sb = st->sb;
+	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
+
+	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready()) {
+		rv = cluster_get_dlmlock(&lockid);
+		if (rv) {
+			pr_err("Cannot get dlmlock in %s return %d\n", __func__, rv);
+			cluster_release_dlmlock(lockid);
+			return rv;
+		}
+	}
 
 	if (strcmp(update, "homehost") == 0 &&
 	    homehost) {
@@ -1096,8 +1152,10 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 		int want;
 		if (info->disk.state & (1<<MD_DISK_ACTIVE))
 			want = info->disk.raid_disk;
+		else if (info->disk.state & (1<<MD_DISK_JOURNAL))
+			want = MD_DISK_ROLE_JOURNAL;
 		else
-			want = 0xFFFF;
+			want = MD_DISK_ROLE_SPARE;
 		if (sb->dev_roles[d] != __cpu_to_le16(want)) {
 			sb->dev_roles[d] = __cpu_to_le16(want);
 			rv = 1;
@@ -1118,24 +1176,18 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 		}
 	} else if (strcmp(update, "linear-grow-new") == 0) {
 		unsigned int i;
-		int rfd, fd;
+		int fd;
 		unsigned int max = __le32_to_cpu(sb->max_dev);
 
 		for (i=0 ; i < max ; i++)
-			if (__le16_to_cpu(sb->dev_roles[i]) >= 0xfffe)
+			if (__le16_to_cpu(sb->dev_roles[i]) >= MD_DISK_ROLE_FAULTY)
 				break;
 		sb->dev_number = __cpu_to_le32(i);
 		info->disk.number = i;
 		if (max >= __le32_to_cpu(sb->max_dev))
 			sb->max_dev = __cpu_to_le32(max+1);
 
-		if ((rfd = open("/dev/urandom", O_RDONLY)) < 0 ||
-		    read(rfd, sb->device_uuid, 16) != 16) {
-			__u32 r[4] = {random(), random(), random(), random()};
-			memcpy(sb->device_uuid, r, 16);
-		}
-		if (rfd >= 0)
-			close(rfd);
+		random_uuid(sb->device_uuid);
 
 		sb->dev_roles[i] =
 			__cpu_to_le16(info->disk.raid_disk);
@@ -1168,11 +1220,8 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 	} else if (strcmp(update, "uuid") == 0) {
 		copy_uuid(sb->set_uuid, info->uuid, super1.swapuuid);
 
-		if (__le32_to_cpu(sb->feature_map)&MD_FEATURE_BITMAP_OFFSET) {
-			struct bitmap_super_s *bm;
-			bm = (struct bitmap_super_s*)(st->sb+MAX_SB_SIZE);
-			memcpy(bm->uuid, sb->set_uuid, 16);
-		}
+		if (__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)
+			memcpy(bms->uuid, sb->set_uuid, 16);
 	} else if (strcmp(update, "no-bitmap") == 0) {
 		sb->feature_map &= ~__cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
 	} else if (strcmp(update, "bbl") == 0) {
@@ -1181,15 +1230,14 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 		 */
 		unsigned long long sb_offset = __le64_to_cpu(sb->super_offset);
 		unsigned long long data_offset = __le64_to_cpu(sb->data_offset);
-		long bitmap_offset = (long)(int32_t)__le32_to_cpu(sb->bitmap_offset);
+		long bitmap_offset = 0;
 		long bm_sectors = 0;
 		long space;
 
 #ifndef MDASSEMBLE
 		if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
-			struct bitmap_super_s *bsb;
-			bsb = (struct bitmap_super_s *)(((char*)sb)+MAX_SB_SIZE);
-			bm_sectors = bitmap_sectors(bsb);
+			bitmap_offset = (long)__le32_to_cpu(sb->bitmap_offset);
+			bm_sectors = calc_bitmap_size(bms, 4096) >> 9;
 		}
 #endif
 		if (sb_offset < data_offset) {
@@ -1227,6 +1275,11 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 			sb->bblog_shift = 0;
 			sb->bblog_offset = 0;
 		}
+	} else if (strcmp(update, "force-no-bbl") == 0) {
+		sb->feature_map &= ~ __cpu_to_le32(MD_FEATURE_BAD_BLOCKS);
+		sb->bblog_size = 0;
+		sb->bblog_shift = 0;
+		sb->bblog_offset = 0;
 	} else if (strcmp(update, "name") == 0) {
 		if (info->name[0] == 0)
 			sprintf(info->name, "%d", info->array.md_minor);
@@ -1238,7 +1291,7 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 			strcat(sb->set_name, ":");
 			strcat(sb->set_name, info->name);
 		} else
-			strcpy(sb->set_name, info->name);
+			strncpy(sb->set_name, info->name, sizeof(sb->set_name));
 	} else if (strcmp(update, "devicesize") == 0 &&
 	    __le64_to_cpu(sb->super_offset) <
 	    __le64_to_cpu(sb->data_offset)) {
@@ -1247,7 +1300,7 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 			(st->sb + MAX_SB_SIZE + BM_SUPER_SIZE);
 		sb->data_size = __cpu_to_le64(
 			misc->device_size - __le64_to_cpu(sb->data_offset));
-	} else if (strcmp(update, "revert-reshape") == 0) {
+	} else if (strncmp(update, "revert-reshape", 14) == 0) {
 		rv = -2;
 		if (!(sb->feature_map & __cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE)))
 			pr_err("No active reshape to revert on %s\n",
@@ -1257,6 +1310,24 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 			unsigned long long reshape_sectors;
 			long reshape_chunk;
 			rv = 0;
+			/* If the reshape hasn't started, just stop it.
+			 * It is conceivable that a stripe was modified but
+			 * the metadata not updated.  In that case the backup
+			 * should have been used to get passed the critical stage.
+			 * If that couldn't happen, the "-nobackup" version
+			 * will be used.
+			 */
+			if (strcmp(update, "revert-reshape-nobackup") == 0 &&
+			    sb->reshape_position == 0 &&
+			    (__le32_to_cpu(sb->delta_disks) > 0 ||
+			     (__le32_to_cpu(sb->delta_disks) == 0 &&
+			      !(sb->feature_map & __cpu_to_le32(MD_FEATURE_RESHAPE_BACKWARDS))))) {
+				sb->feature_map &= ~__cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
+				sb->raid_disks = __cpu_to_le32(__le32_to_cpu(sb->raid_disks) -
+							       __le32_to_cpu(sb->delta_disks));
+				sb->delta_disks = 0;
+				goto done;
+			}
 			/* reshape_position is a little messy.
 			 * Its value must be a multiple of the larger
 			 * chunk size, and of the "after" data disks.
@@ -1303,6 +1374,7 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 				sb->new_offset = __cpu_to_le32(-offset_delta);
 				sb->data_size = __cpu_to_le64(__le64_to_cpu(sb->data_size) - offset_delta);
 			}
+		done:;
 		}
 	} else if (strcmp(update, "_reshape_progress")==0)
 		sb->reshape_position = __cpu_to_le64(info->reshape_progress);
@@ -1310,10 +1382,17 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
 		sb->devflags |= WriteMostly1;
 	else if (strcmp(update, "readwrite")==0)
 		sb->devflags &= ~WriteMostly1;
+	else if (strcmp(update, "failfast") == 0)
+		sb->devflags |= FailFast1;
+	else if (strcmp(update, "nofailfast") == 0)
+		sb->devflags &= ~FailFast1;
 	else
 		rv = -1;
 
 	sb->sb_csum = calc_sb_1_csum(sb);
+	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready())
+		cluster_release_dlmlock(lockid);
+
 	return rv;
 }
 
@@ -1323,7 +1402,6 @@ static int init_super1(struct supertype *st, mdu_array_info_t *info,
 {
 	struct mdp_superblock_1 *sb;
 	int spares;
-	int rfd;
 	char defname[10];
 	int sbsize;
 
@@ -1353,14 +1431,8 @@ static int init_super1(struct supertype *st, mdu_array_info_t *info,
 
 	if (uuid)
 		copy_uuid(sb->set_uuid, uuid, super1.swapuuid);
-	else {
-		if ((rfd = open("/dev/urandom", O_RDONLY)) < 0 ||
-		    read(rfd, sb->set_uuid, 16) != 16) {
-			__u32 r[4] = {random(), random(), random(), random()};
-			memcpy(sb->set_uuid, r, 16);
-		}
-		if (rfd >= 0) close(rfd);
-	}
+	else
+		random_uuid(sb->set_uuid);;
 
 	if (name == NULL || *name == 0) {
 		sprintf(defname, "%d", info->md_minor);
@@ -1373,7 +1445,7 @@ static int init_super1(struct supertype *st, mdu_array_info_t *info,
 		strcat(sb->set_name, ":");
 		strcat(sb->set_name, name);
 	} else
-		strcpy(sb->set_name, name);
+		strncpy(sb->set_name, name, sizeof(sb->set_name));
 
 	sb->ctime = __cpu_to_le64((unsigned long long)time(0));
 	sb->level = __cpu_to_le32(info->level);
@@ -1417,13 +1489,26 @@ static int add_to_super1(struct supertype *st, mdu_disk_info_t *dk,
 	struct mdp_superblock_1 *sb = st->sb;
 	__u16 *rp = sb->dev_roles + dk->number;
 	struct devinfo *di, **dip;
+	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
+	int rv, lockid;
+
+	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready()) {
+		rv = cluster_get_dlmlock(&lockid);
+		if (rv) {
+			pr_err("Cannot get dlmlock in %s return %d\n", __func__, rv);
+			cluster_release_dlmlock(lockid);
+			return rv;
+		}
+	}
 
 	if ((dk->state & 6) == 6) /* active, sync */
 		*rp = __cpu_to_le16(dk->raid_disk);
+	else if (dk->state & (1<<MD_DISK_JOURNAL))
+                *rp = MD_DISK_ROLE_JOURNAL;
 	else if ((dk->state & ~2) == 0) /* active or idle -> spare */
-		*rp = 0xffff;
+		*rp = MD_DISK_ROLE_SPARE;
 	else
-		*rp = 0xfffe;
+		*rp = MD_DISK_ROLE_FAULTY;
 
 	if (dk->number >= (int)__le32_to_cpu(sb->max_dev) &&
 	    __le32_to_cpu(sb->max_dev) < MAX_DEVS)
@@ -1444,11 +1529,14 @@ static int add_to_super1(struct supertype *st, mdu_disk_info_t *dk,
 	di->next = NULL;
 	*dip = di;
 
+	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready())
+		cluster_release_dlmlock(lockid);
+
 	return 0;
 }
 #endif
 
-static void locate_bitmap1(struct supertype *st, int fd);
+static int locate_bitmap1(struct supertype *st, int fd, int node_num);
 
 static int store_super1(struct supertype *st, int fd)
 {
@@ -1457,6 +1545,17 @@ static int store_super1(struct supertype *st, int fd)
 	struct align_fd afd;
 	int sbsize;
 	unsigned long long dsize;
+	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
+	int rv, lockid;
+
+	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready()) {
+		rv = cluster_get_dlmlock(&lockid);
+		if (rv) {
+			pr_err("Cannot get dlmlock in %s return %d\n", __func__, rv);
+			cluster_release_dlmlock(lockid);
+			return rv;
+		}
+	}
 
 	if (!get_dev_size(fd, NULL, &dsize))
 		return 1;
@@ -1511,12 +1610,15 @@ static int store_super1(struct supertype *st, int fd)
 		struct bitmap_super_s *bm = (struct bitmap_super_s*)
 			(((char*)sb)+MAX_SB_SIZE);
 		if (__le32_to_cpu(bm->magic) == BITMAP_MAGIC) {
-			locate_bitmap1(st, fd);
+			locate_bitmap1(st, fd, 0);
 			if (awrite(&afd, bm, sizeof(*bm)) != sizeof(*bm))
 				return 5;
 		}
 	}
 	fsync(fd);
+	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready())
+		cluster_release_dlmlock(lockid);
+
 	return 0;
 }
 
@@ -1529,7 +1631,8 @@ static unsigned long choose_bm_space(unsigned long devsize)
 	 * NOTE: result must be multiple of 4K else bad things happen
 	 * on 4K-sector devices.
 	 */
-	if (devsize < 64*2) return 0;
+	if (devsize < 64*2)
+		return 0;
 	if (devsize - 64*2 >= 200*1024*1024*2)
 		return 128*2;
 	if (devsize - 4*2 > 8*1024*1024*2)
@@ -1539,18 +1642,71 @@ static unsigned long choose_bm_space(unsigned long devsize)
 
 static void free_super1(struct supertype *st);
 
+#define META_BLOCK_SIZE 4096
+__u32 crc32c_le(__u32 crc, unsigned char const *p, size_t len);
+
 #ifndef MDASSEMBLE
+static int write_empty_r5l_meta_block(struct supertype *st, int fd)
+{
+	struct r5l_meta_block *mb;
+	struct mdp_superblock_1 *sb = st->sb;
+	struct align_fd afd;
+	__u32 crc;
+
+	init_afd(&afd, fd);
+
+	if (posix_memalign((void**)&mb, 4096, META_BLOCK_SIZE) != 0) {
+		pr_err("Could not allocate memory for the meta block.\n");
+		return 1;
+	}
+
+	memset(mb, 0, META_BLOCK_SIZE);
+
+	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(random32());
+	mb->position = __cpu_to_le64(0);
+
+	crc = crc32c_le(0xffffffff, sb->set_uuid, sizeof(sb->set_uuid));
+	crc = crc32c_le(crc, (void *)mb, META_BLOCK_SIZE);
+	mb->checksum = crc;
+
+	if (lseek64(fd, (sb->data_offset) * 512, 0) < 0LL) {
+		pr_err("cannot seek to offset of the meta block\n");
+		goto fail_to_write;
+	}
+
+	if (awrite(&afd, mb, META_BLOCK_SIZE) != META_BLOCK_SIZE) {
+		pr_err("failed to store write the meta block \n");
+		goto fail_to_write;
+	}
+	fsync(fd);
+
+	free(mb);
+	return 0;
+
+fail_to_write:
+	free(mb);
+	return 1;
+}
+
 static int write_init_super1(struct supertype *st)
 {
 	struct mdp_superblock_1 *sb = st->sb;
 	struct supertype *refst;
-	int rfd;
 	int rv = 0;
 	unsigned long long bm_space;
 	struct devinfo *di;
 	unsigned long long dsize, array_size;
 	unsigned long long sb_offset;
 	unsigned long long data_offset;
+	long bm_offset;
+
+	for (di = st->info; di; di = di->next) {
+		if (di->disk.state & (1 << MD_DISK_JOURNAL))
+			sb->feature_map |= MD_FEATURE_JOURNAL;
+	}
 
 	for (di = st->info; di; di = di->next) {
 		if (di->disk.state & (1 << MD_DISK_FAULTY))
@@ -1566,16 +1722,15 @@ static int write_init_super1(struct supertype *st)
 			sb->devflags |= WriteMostly1;
 		else
 			sb->devflags &= ~WriteMostly1;
+		if (di->disk.state & (1<<MD_DISK_FAILFAST))
+			sb->devflags |= FailFast1;
+		else
+			sb->devflags &= ~FailFast1;
 
-		if ((rfd = open("/dev/urandom", O_RDONLY)) < 0 ||
-		    read(rfd, sb->device_uuid, 16) != 16) {
-			__u32 r[4] = {random(), random(), random(), random()};
-			memcpy(sb->device_uuid, r, 16);
-		}
-		if (rfd >= 0)
-			close(rfd);
+		random_uuid(sb->device_uuid);
 
-		sb->events = 0;
+		if (!(di->disk.state & (1<<MD_DISK_JOURNAL)))
+			sb->events = 0;
 
 		refst = dup_super(st);
 		if (load_super1(refst, di->fd, NULL)==0) {
@@ -1618,15 +1773,25 @@ static int write_init_super1(struct supertype *st)
 		 * data_offset has already been set.
 		 */
 		array_size = __le64_to_cpu(sb->size);
-		/* work out how much space we left for a bitmap,
-		 * Add 8 sectors for bad block log */
-		bm_space = choose_bm_space(array_size) + 8;
+
+		/* work out how much space we left for a bitmap */
+		if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
+			bitmap_super_t *bms = (bitmap_super_t *)
+					(((char *)sb) + MAX_SB_SIZE);
+			bm_space = calc_bitmap_size(bms, 4096) >> 9;
+			bm_offset = (long)__le32_to_cpu(sb->bitmap_offset);
+		} else {
+			bm_space = choose_bm_space(array_size);
+			bm_offset = 8;
+		}
 
 		data_offset = di->data_offset;
 		if (data_offset == INVALID_SECTORS)
 			data_offset = st->data_offset;
 		switch(st->minor_version) {
 		case 0:
+			/* Add 8 sectors for bad block log */
+			bm_space += 8;
 			if (data_offset == INVALID_SECTORS)
 				data_offset = 0;
 			sb_offset = dsize;
@@ -1643,38 +1808,26 @@ static int write_init_super1(struct supertype *st)
 			}
 			break;
 		case 1:
-			sb->super_offset = __cpu_to_le64(0);
-			if (data_offset == INVALID_SECTORS)
-				data_offset = 16;
-
-			sb->data_offset = __cpu_to_le64(data_offset);
-			sb->data_size = __cpu_to_le64(dsize - data_offset);
-			if (data_offset >= 8 + 32*2 + 8) {
-				sb->bblog_size = __cpu_to_le16(8);
-				sb->bblog_offset = __cpu_to_le32(8 + 32*2);
-			} else if (data_offset >= 16) {
-				sb->bblog_size = __cpu_to_le16(8);
-				sb->bblog_offset = __cpu_to_le32(data_offset-8);
-			}
-			break;
 		case 2:
-			sb_offset = 4*2;
+			sb_offset = st->minor_version == 2 ? 8 : 0;
 			sb->super_offset = __cpu_to_le64(sb_offset);
 			if (data_offset == INVALID_SECTORS)
-				data_offset = 24;
+				data_offset = sb_offset + 16;
 
 			sb->data_offset = __cpu_to_le64(data_offset);
 			sb->data_size = __cpu_to_le64(dsize - data_offset);
-			if (data_offset >= 16 + 32*2 + 8) {
+			if (data_offset >= sb_offset+bm_offset+bm_space+8) {
 				sb->bblog_size = __cpu_to_le16(8);
-				sb->bblog_offset = __cpu_to_le32(8 + 32*2);
-			} else if (data_offset >= 16+16) {
+				sb->bblog_offset = __cpu_to_le32(bm_offset +
+								 bm_space);
+			} else if (data_offset >= sb_offset + 16) {
 				sb->bblog_size = __cpu_to_le16(8);
-				/* '8' sectors for the bblog, and another '8'
+				/* '8' sectors for the bblog, and 'sb_offset'
 				 * because we want offset from superblock, not
 				 * start of device.
 				 */
-				sb->bblog_offset = __cpu_to_le32(data_offset-8-8);
+				sb->bblog_offset = __cpu_to_le32(data_offset -
+								 8 - sb_offset);
 			}
 			break;
 		default:
@@ -1683,15 +1836,23 @@ static int write_init_super1(struct supertype *st)
 			rv = -EINVAL;
 			goto out;
 		}
-		if (conf_get_create_info()->bblist == 0) {
+		/* Disable badblock log on clusters, or when explicitly requested */
+		if (st->nodes > 0 || conf_get_create_info()->bblist == 0) {
 			sb->bblog_size = 0;
 			sb->bblog_offset = 0;
 		}
 
 		sb->sb_csum = calc_sb_1_csum(sb);
 		rv = store_super1(st, di->fd);
+
+		if (rv == 0 && (di->disk.state & (1 << MD_DISK_JOURNAL))) {
+			rv = write_empty_r5l_meta_block(st, di->fd);
+			if (rv)
+				goto error_out;
+		}
+
 		if (rv == 0 && (__le32_to_cpu(sb->feature_map) & 1))
-			rv = st->ss->write_bitmap(st, di->fd);
+			rv = st->ss->write_bitmap(st, di->fd, NodeNumUpdate);
 		close(di->fd);
 		di->fd = -1;
 		if (rv)
@@ -1840,6 +2001,8 @@ static int load_super1(struct supertype *st, int fd, char *devname)
 		return 1;
 	}
 
+	memset(super, 0, SUPER1_SIZE);
+
 	if (aread(&afd, super, MAX_SB_SIZE) != MAX_SB_SIZE) {
 		if (devname)
 			pr_err("Cannot read superblock on %s\n",
@@ -1886,7 +2049,7 @@ static int load_super1(struct supertype *st, int fd, char *devname)
 	 * valid.  If it doesn't clear the bit.  An --assemble --force
 	 * should get that written out.
 	 */
-	locate_bitmap1(st, fd);
+	locate_bitmap1(st, fd, 0);
 	if (aread(&afd, bsb, 512) != 512)
 		goto no_bitmap;
 
@@ -1961,7 +2124,7 @@ static __u64 avail_size1(struct supertype *st, __u64 devsize,
 		/* hot-add. allow for actual size of bitmap */
 		struct bitmap_super_s *bsb;
 		bsb = (struct bitmap_super_s *)(((char*)super)+MAX_SB_SIZE);
-		bmspace = bitmap_sectors(bsb);
+		bmspace = calc_bitmap_size(bsb, 4096) >> 9;
 	}
 #endif
 	/* Allow space for bad block log */
@@ -2025,6 +2188,7 @@ add_internal_bitmap1(struct supertype *st,
 	unsigned long long chunk = *chunkp;
 	int room = 0;
 	int creating = 0;
+	int len;
 	struct mdp_superblock_1 *sb = st->sb;
 	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
 	int uuid[4];
@@ -2091,7 +2255,7 @@ add_internal_bitmap1(struct supertype *st,
 		}
 		break;
 	default:
-		return 0;
+		return -ENOSPC;
 	}
 
 	room -= bbl_size;
@@ -2101,7 +2265,7 @@ add_internal_bitmap1(struct supertype *st,
 
 	if (room <= 1)
 		/* No room for a bitmap */
-		return 0;
+		return -ENOSPC;
 
 	max_bits = (room * 512 - sizeof(bitmap_super_t)) * 8;
 
@@ -2119,9 +2283,9 @@ add_internal_bitmap1(struct supertype *st,
 		if (chunk < 64*1024*1024)
 			chunk = 64*1024*1024;
 	} else if (chunk < min_chunk)
-		return 0; /* chunk size too small */
+		return -EINVAL; /* chunk size too small */
 	if (chunk == 0) /* rounding problem */
-		return 0;
+		return -EINVAL;
 
 	if (offset == 0) {
 		/* start bitmap on a 4K boundary with enough space for
@@ -2147,47 +2311,111 @@ add_internal_bitmap1(struct supertype *st,
 	bms->sync_size = __cpu_to_le64(size);
 	bms->write_behind = __cpu_to_le32(write_behind);
 	bms->nodes = __cpu_to_le32(st->nodes);
-	if (st->cluster_name)
-		strncpy((char *)bms->cluster_name,
-			st->cluster_name, strlen(st->cluster_name));
+	if (st->nodes)
+		sb->feature_map = __cpu_to_le32(__le32_to_cpu(sb->feature_map)
+						| MD_FEATURE_BITMAP_VERSIONED);
+	if (st->cluster_name) {
+		len = sizeof(bms->cluster_name);
+		strncpy((char *)bms->cluster_name, st->cluster_name, len);
+		bms->cluster_name[len - 1] = '\0';
+	}
 
 	*chunkp = chunk;
-	return 1;
+	return 0;
 }
 
-static void locate_bitmap1(struct supertype *st, int fd)
+static int locate_bitmap1(struct supertype *st, int fd, int node_num)
 {
 	unsigned long long offset;
 	struct mdp_superblock_1 *sb;
 	int mustfree = 0;
+	int ret;
 
 	if (!st->sb) {
 		if (st->ss->load_super(st, fd, NULL))
-			return; /* no error I hope... */
+			return -1; /* no error I hope... */
 		mustfree = 1;
 	}
 	sb = st->sb;
 
+	if ((__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET))
+		ret = 0;
+	else
+		ret = -1;
 	offset = __le64_to_cpu(sb->super_offset);
-	offset += (int32_t) __le32_to_cpu(sb->bitmap_offset);
+	offset += (int32_t) __le32_to_cpu(sb->bitmap_offset) * (node_num + 1);
 	if (mustfree)
 		free(sb);
 	lseek64(fd, offset<<9, 0);
+	return ret;
 }
 
-static int write_bitmap1(struct supertype *st, int fd)
+static int write_bitmap1(struct supertype *st, int fd, enum bitmap_update update)
 {
 	struct mdp_superblock_1 *sb = st->sb;
 	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb)+MAX_SB_SIZE);
 	int rv = 0;
 	void *buf;
-	int towrite, n;
+	int towrite, n, len;
 	struct align_fd afd;
 	unsigned int i = 0;
+	unsigned long long total_bm_space, bm_space_per_node;
+
+	switch (update) {
+	case NameUpdate:
+		/* update cluster name */
+		if (st->cluster_name) {
+			len = sizeof(bms->cluster_name);
+			memset((char *)bms->cluster_name, 0, len);
+			strncpy((char *)bms->cluster_name,
+				st->cluster_name, len);
+			bms->cluster_name[len - 1] = '\0';
+		}
+		break;
+	case NodeNumUpdate:
+		/* cluster md only supports superblock 1.2 now */
+		if (st->minor_version != 2 && bms->version == BITMAP_MAJOR_CLUSTERED) {
+			pr_err("Warning: cluster md only works with superblock 1.2\n");
+			return -EINVAL;
+		}
+
+		if (bms->version == BITMAP_MAJOR_CLUSTERED) {
+			if (__cpu_to_le32(st->nodes) < bms->nodes) {
+				/* Since the nodes num is not increased, no need to check the space
+				 * is enough or not, just update bms->nodes */
+				bms->nodes = __cpu_to_le32(st->nodes);
+				break;
+			}
+		} else {
+			/* no need to change bms->nodes for other bitmap types */
+			if (st->nodes)
+				pr_err("Warning: --nodes option is only suitable for clustered bitmap\n");
+			break;
+		}
+
+		/* Each node has an independent bitmap, it is necessary to calculate the
+		 * space is enough or not, first get how many bytes for the total bitmap */
+		bm_space_per_node = calc_bitmap_size(bms, 4096);
+
+		total_bm_space = 512 * (__le64_to_cpu(sb->data_offset) - __le64_to_cpu(sb->super_offset));
+		total_bm_space = total_bm_space - 4096; /* leave another 4k for superblock */
+
+		if (bm_space_per_node * st->nodes > total_bm_space) {
+			pr_err("Warning: The max num of nodes can't exceed %llu\n",
+				total_bm_space / bm_space_per_node);
+			return -ENOMEM;
+		}
+
+		bms->nodes = __cpu_to_le32(st->nodes);
+		break;
+	case NoUpdate:
+	default:
+		break;
+	}
 
 	init_afd(&afd, fd);
 
-	locate_bitmap1(st, fd);
+	locate_bitmap1(st, fd, 0);
 
 	if (posix_memalign(&buf, 4096, 4096))
 		return -ENOMEM;
@@ -2202,11 +2430,15 @@ static int write_bitmap1(struct supertype *st, int fd)
 			memset(buf, 0xff, 4096);
 		memcpy(buf, (char *)bms, sizeof(bitmap_super_t));
 
-		towrite = __le64_to_cpu(bms->sync_size) / (__le32_to_cpu(bms->chunksize)>>9);
-		towrite = (towrite+7) >> 3; /* bits to bytes */
-		towrite += sizeof(bitmap_super_t);
-		/* we need the bitmaps to be at 4k boundary */
-		towrite = ROUND_UP(towrite, 4096);
+		/*
+		 * use 4096 boundary if bitmap_offset is aligned
+		 * with 8 sectors, then it should compatible with
+		 * older mdadm.
+		 */
+		if (__le32_to_cpu(sb->bitmap_offset) & 7)
+			towrite = calc_bitmap_size(bms, 512);
+		else
+			towrite = calc_bitmap_size(bms, 4096);
 		while (towrite > 0) {
 			n = towrite;
 			if (n > 4096)
@@ -2234,6 +2466,7 @@ static int write_bitmap1(struct supertype *st, int fd)
 
 static void free_super1(struct supertype *st)
 {
+
 	if (st->sb)
 		free(st->sb);
 	while (st->info) {
@@ -2349,7 +2582,6 @@ void *super1_make_v0(struct supertype *st, struct mdinfo *info, mdp_super_t *sb0
 	void *ret;
 	struct mdp_superblock_1 *sb;
 	int i;
-	int rfd;
 	unsigned long long offset;
 
 	if (posix_memalign(&ret, 4096, 1024) != 0)
@@ -2381,17 +2613,11 @@ void *super1_make_v0(struct supertype *st, struct mdinfo *info, mdp_super_t *sb0
 	sb->super_offset = __cpu_to_le64(offset);
 	//*(__u64*)(st->other + 128 + 8 + 8) = __cpu_to_le64(offset);
 
-	if ((rfd = open("/dev/urandom", O_RDONLY)) < 0 ||
-	    read(rfd, sb->device_uuid, 16) != 16) {
-		__u32 r[4] = {random(), random(), random(), random()};
-		memcpy(sb->device_uuid, r, 16);
-	}
-	if (rfd >= 0)
-		close(rfd);
+	random_uuid(sb->device_uuid);
 
 	for (i = 0; i < MD_SB_DISKS; i++) {
 		int state = sb0->disks[i].state;
-		sb->dev_roles[i] = 0xFFFF;
+		sb->dev_roles[i] = MD_DISK_ROLE_SPARE;
 		if ((state & (1<<MD_DISK_SYNC)) &&
 		    !(state & (1<<MD_DISK_FAULTY)))
 			sb->dev_roles[i] = __cpu_to_le16(sb0->disks[i].raid_disk);