MPB_ATTRIB_RAID1 | \
MPB_ATTRIB_RAID10 | \
MPB_ATTRIB_RAID5 | \
- MPB_ATTRIB_EXP_STRIPE_SIZE)
+ MPB_ATTRIB_EXP_STRIPE_SIZE | \
+ MPB_ATTRIB_BBM)
/* Define attributes that are unused but not harmful */
#define MPB_ATTRIB_IGNORED (MPB_ATTRIB_NEVER_USE)
} __attribute__ ((packed));
#define BBM_LOG_MAX_ENTRIES 254
+#define BBM_LOG_MAX_LBA_ENTRY_VAL 256 /* Represents 256 LBAs */
+#define BBM_LOG_SIGNATURE 0xabadb10c
+
+struct bbm_log_block_addr {
+ __u16 w1;
+ __u32 dw1;
+} __attribute__ ((__packed__));
struct bbm_log_entry {
- __u64 defective_block_start;
-#define UNREADABLE 0xFFFFFFFF
- __u32 spare_block_offset;
- __u16 remapped_marked_count;
- __u16 disk_ordinal;
+ __u8 marked_count; /* Number of blocks marked - 1 */
+ __u8 disk_ordinal; /* Disk entry within the imsm_super */
+ struct bbm_log_block_addr defective_block_start;
} __attribute__ ((__packed__));
struct bbm_log {
__u32 signature; /* 0xABADB10C */
__u32 entry_count;
- __u32 reserved_spare_block_count; /* 0 */
- __u32 reserved; /* 0xFFFF */
- __u64 first_spare_lba;
- struct bbm_log_entry mapped_block_entries[BBM_LOG_MAX_ENTRIES];
+ struct bbm_log_entry marked_block_entries[BBM_LOG_MAX_ENTRIES];
} __attribute__ ((__packed__));
#ifndef MDASSEMBLE
#define GEN_MIGR_AREA_SIZE 2048 /* General Migration Copy Area size in blocks */
-#define MIGR_REC_BUF_SIZE 512 /* size of migr_record i/o buffer */
-#define MIGR_REC_POSITION 512 /* migr_record position offset on disk,
- * MIGR_REC_BUF_SIZE <= MIGR_REC_POSITION
+#define MIGR_REC_BUF_SECTORS 1 /* size of migr_record i/o buffer in sectors */
+#define MIGR_REC_SECTOR_POSITION 1 /* migr_record position offset on disk,
+ * MIGR_REC_BUF_SECTORS <= MIGR_REC_SECTOR_POS
*/
#define UNIT_SRC_NORMAL 0 /* Source data for curr_migr_unit must
array, it indicates that mdmon is allowed to clean migration
record */
size_t len; /* size of the 'buf' allocation */
+ size_t extra_space; /* extra space in 'buf' that is not used yet */
void *next_buf; /* for realloc'ing buf from the manager */
size_t next_len;
int updates_pending; /* count of pending updates for mdmon */
struct intel_hba *hba; /* device path of the raid controller for this metadata */
const struct imsm_orom *orom; /* platform firmware support */
struct intel_super *next; /* (temp) list for disambiguating family_num */
+ struct md_bb bb; /* memory for get_bad_blocks call */
};
struct intel_disk {
update_takeover,
update_general_migration_checkpoint,
update_size_change,
+ update_prealloc_badblocks_mem,
};
struct imsm_update_activate_spare {
enum imsm_update_type type;
};
+struct imsm_update_prealloc_bb_mem {
+ enum imsm_update_type type;
+};
+
static const char *_sys_dev_type[] = {
[SYS_DEV_UNKNOWN] = "Unknown",
[SYS_DEV_SAS] = "SAS",
return NULL;
}
+static inline unsigned long long __le48_to_cpu(const struct bbm_log_block_addr
+ *addr)
+{
+ return ((((__u64)__le32_to_cpu(addr->dw1)) << 16) |
+ __le16_to_cpu(addr->w1));
+}
+
+static inline struct bbm_log_block_addr __cpu_to_le48(unsigned long long sec)
+{
+ struct bbm_log_block_addr addr;
+
+ addr.w1 = __cpu_to_le16((__u16)(sec & 0xffff));
+ addr.dw1 = __cpu_to_le32((__u32)(sec >> 16) & 0xffffffff);
+ return addr;
+}
+
+#ifndef MDASSEMBLE
+/* get size of the bbm log */
+static __u32 get_imsm_bbm_log_size(struct bbm_log *log)
+{
+ if (!log || log->entry_count == 0)
+ return 0;
+
+ return sizeof(log->signature) +
+ sizeof(log->entry_count) +
+ log->entry_count * sizeof(struct bbm_log_entry);
+}
+
+/* check if bad block is not partially stored in bbm log */
+static int is_stored_in_bbm(struct bbm_log *log, const __u8 idx, const unsigned
+ long long sector, const int length, __u32 *pos)
+{
+ __u32 i;
+
+ for (i = *pos; i < log->entry_count; i++) {
+ struct bbm_log_entry *entry = &log->marked_block_entries[i];
+ unsigned long long bb_start;
+ unsigned long long bb_end;
+
+ bb_start = __le48_to_cpu(&entry->defective_block_start);
+ bb_end = bb_start + (entry->marked_count + 1);
+
+ if ((entry->disk_ordinal == idx) && (bb_start >= sector) &&
+ (bb_end <= sector + length)) {
+ *pos = i;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+/* record new bad block in bbm log */
+static int record_new_badblock(struct bbm_log *log, const __u8 idx, unsigned
+ long long sector, int length)
+{
+ int new_bb = 0;
+ __u32 pos = 0;
+ struct bbm_log_entry *entry = NULL;
+
+ while (is_stored_in_bbm(log, idx, sector, length, &pos)) {
+ struct bbm_log_entry *e = &log->marked_block_entries[pos];
+
+ if ((e->marked_count + 1 == BBM_LOG_MAX_LBA_ENTRY_VAL) &&
+ (__le48_to_cpu(&e->defective_block_start) == sector)) {
+ sector += BBM_LOG_MAX_LBA_ENTRY_VAL;
+ length -= BBM_LOG_MAX_LBA_ENTRY_VAL;
+ pos = pos + 1;
+ continue;
+ }
+ entry = e;
+ break;
+ }
+
+ if (entry) {
+ int cnt = (length <= BBM_LOG_MAX_LBA_ENTRY_VAL) ? length :
+ BBM_LOG_MAX_LBA_ENTRY_VAL;
+ entry->defective_block_start = __cpu_to_le48(sector);
+ entry->marked_count = cnt - 1;
+ if (cnt == length)
+ return 1;
+ sector += cnt;
+ length -= cnt;
+ }
+
+ new_bb = ROUND_UP(length, BBM_LOG_MAX_LBA_ENTRY_VAL) /
+ BBM_LOG_MAX_LBA_ENTRY_VAL;
+ if (log->entry_count + new_bb > BBM_LOG_MAX_ENTRIES)
+ return 0;
+
+ while (length > 0) {
+ int cnt = (length <= BBM_LOG_MAX_LBA_ENTRY_VAL) ? length :
+ BBM_LOG_MAX_LBA_ENTRY_VAL;
+ struct bbm_log_entry *entry =
+ &log->marked_block_entries[log->entry_count];
+
+ entry->defective_block_start = __cpu_to_le48(sector);
+ entry->marked_count = cnt - 1;
+ entry->disk_ordinal = idx;
+
+ sector += cnt;
+ length -= cnt;
+
+ log->entry_count++;
+ }
+
+ return new_bb;
+}
+
+/* clear all bad blocks for given disk */
+static void clear_disk_badblocks(struct bbm_log *log, const __u8 idx)
+{
+ __u32 i = 0;
+
+ while (i < log->entry_count) {
+ struct bbm_log_entry *entries = log->marked_block_entries;
+
+ if (entries[i].disk_ordinal == idx) {
+ if (i < log->entry_count - 1)
+ entries[i] = entries[log->entry_count - 1];
+ log->entry_count--;
+ } else {
+ i++;
+ }
+ }
+}
+
+/* clear given bad block */
+static int clear_badblock(struct bbm_log *log, const __u8 idx, const unsigned
+ long long sector, const int length) {
+ __u32 i = 0;
+
+ while (i < log->entry_count) {
+ struct bbm_log_entry *entries = log->marked_block_entries;
+
+ if ((entries[i].disk_ordinal == idx) &&
+ (__le48_to_cpu(&entries[i].defective_block_start) ==
+ sector) && (entries[i].marked_count + 1 == length)) {
+ if (i < log->entry_count - 1)
+ entries[i] = entries[log->entry_count - 1];
+ log->entry_count--;
+ break;
+ }
+ i++;
+ }
+
+ return 1;
+}
+#endif /* MDASSEMBLE */
+
+/* allocate and load BBM log from metadata */
+static int load_bbm_log(struct intel_super *super)
+{
+ struct imsm_super *mpb = super->anchor;
+ __u32 bbm_log_size = __le32_to_cpu(mpb->bbm_log_size);
+
+ super->bbm_log = xcalloc(1, sizeof(struct bbm_log));
+ if (!super->bbm_log)
+ return 1;
+
+ if (bbm_log_size) {
+ struct bbm_log *log = (void *)mpb +
+ __le32_to_cpu(mpb->mpb_size) - bbm_log_size;
+
+ __u32 entry_count;
+
+ if (bbm_log_size < sizeof(log->signature) +
+ sizeof(log->entry_count))
+ return 2;
+
+ entry_count = __le32_to_cpu(log->entry_count);
+ if ((__le32_to_cpu(log->signature) != BBM_LOG_SIGNATURE) ||
+ (entry_count > BBM_LOG_MAX_ENTRIES))
+ return 3;
+
+ if (bbm_log_size !=
+ sizeof(log->signature) + sizeof(log->entry_count) +
+ entry_count * sizeof(struct bbm_log_entry))
+ return 4;
+
+ memcpy(super->bbm_log, log, bbm_log_size);
+ } else {
+ super->bbm_log->signature = __cpu_to_le32(BBM_LOG_SIGNATURE);
+ super->bbm_log->entry_count = 0;
+ }
+
+ return 0;
+}
+
+/* checks if bad block is within volume boundaries */
+static int is_bad_block_in_volume(const struct bbm_log_entry *entry,
+ const unsigned long long start_sector,
+ const unsigned long long size)
+{
+ unsigned long long bb_start;
+ unsigned long long bb_end;
+
+ bb_start = __le48_to_cpu(&entry->defective_block_start);
+ bb_end = bb_start + (entry->marked_count + 1);
+
+ if (((bb_start >= start_sector) && (bb_start < start_sector + size)) ||
+ ((bb_end >= start_sector) && (bb_end <= start_sector + size)))
+ return 1;
+
+ return 0;
+}
+
+/* get list of bad blocks on a drive for a volume */
+static void get_volume_badblocks(const struct bbm_log *log, const __u8 idx,
+ const unsigned long long start_sector,
+ const unsigned long long size,
+ struct md_bb *bbs)
+{
+ __u32 count = 0;
+ __u32 i;
+
+ for (i = 0; i < log->entry_count; i++) {
+ const struct bbm_log_entry *ent =
+ &log->marked_block_entries[i];
+ struct md_bb_entry *bb;
+
+ if ((ent->disk_ordinal == idx) &&
+ is_bad_block_in_volume(ent, start_sector, size)) {
+
+ if (!bbs->entries) {
+ bbs->entries = xmalloc(BBM_LOG_MAX_ENTRIES *
+ sizeof(*bb));
+ if (!bbs->entries)
+ break;
+ }
+
+ bb = &bbs->entries[count++];
+ bb->sector = __le48_to_cpu(&ent->defective_block_start);
+ bb->length = ent->marked_count + 1;
+ }
+ }
+ bbs->count = count;
+}
+
/*
* for second_map:
* == MAP_0 get first map
return join_u32(map->blocks_per_member_lo, map->blocks_per_member_hi);
}
-#ifndef MDASSEMBLE
static unsigned long long num_data_stripes(struct imsm_map *map)
{
if (map == NULL)
return 0;
return join_u32(map->num_data_stripes_lo, map->num_data_stripes_hi);
}
-#endif
static void set_total_blocks(struct imsm_disk *disk, unsigned long long n)
{
human_size(sz * 512));
}
+void convert_to_4k_imsm_migr_rec(struct intel_super *super)
+{
+ struct migr_record *migr_rec = super->migr_rec;
+
+ migr_rec->blocks_per_unit /= IMSM_4K_DIV;
+ migr_rec->ckpt_area_pba /= IMSM_4K_DIV;
+ migr_rec->dest_1st_member_lba /= IMSM_4K_DIV;
+ migr_rec->dest_depth_per_unit /= IMSM_4K_DIV;
+ split_ull((join_u32(migr_rec->post_migr_vol_cap,
+ migr_rec->post_migr_vol_cap_hi) / IMSM_4K_DIV),
+ &migr_rec->post_migr_vol_cap, &migr_rec->post_migr_vol_cap_hi);
+}
+
void convert_to_4k_imsm_disk(struct imsm_disk *disk)
{
set_total_blocks(disk, (total_blocks(disk)/IMSM_4K_DIV));
struct imsm_super *mpb = super->anchor;
struct imsm_disk *disk;
int i;
+ __u32 bbm_log_size = __le32_to_cpu(mpb->bbm_log_size);
for (i = 0; i < mpb->num_disks ; i++) {
disk = __get_imsm_disk(mpb, i);
set_pba_of_lba0(map, pba_of_lba0(map)/IMSM_4K_DIV);
}
}
+ if (bbm_log_size) {
+ struct bbm_log *log = (void *)mpb +
+ __le32_to_cpu(mpb->mpb_size) - bbm_log_size;
+ __u32 i;
+
+ for (i = 0; i < log->entry_count; i++) {
+ struct bbm_log_entry *entry =
+ &log->marked_block_entries[i];
+
+ __u8 count = entry->marked_count + 1;
+ unsigned long long sector =
+ __le48_to_cpu(&entry->defective_block_start);
+
+ entry->defective_block_start =
+ __cpu_to_le48(sector/IMSM_4K_DIV);
+ entry->marked_count = max(count/IMSM_4K_DIV, 1) - 1;
+ }
+ }
mpb->check_sum = __gen_imsm_checksum(mpb);
}
}
#endif /* MDASSEMBLE */
+void convert_from_4k_imsm_migr_rec(struct intel_super *super)
+{
+ struct migr_record *migr_rec = super->migr_rec;
+
+ migr_rec->blocks_per_unit *= IMSM_4K_DIV;
+ migr_rec->ckpt_area_pba *= IMSM_4K_DIV;
+ migr_rec->dest_1st_member_lba *= IMSM_4K_DIV;
+ migr_rec->dest_depth_per_unit *= IMSM_4K_DIV;
+ split_ull((join_u32(migr_rec->post_migr_vol_cap,
+ migr_rec->post_migr_vol_cap_hi) * IMSM_4K_DIV),
+ &migr_rec->post_migr_vol_cap,
+ &migr_rec->post_migr_vol_cap_hi);
+}
+
void convert_from_4k(struct intel_super *super)
{
struct imsm_super *mpb = super->anchor;
struct imsm_disk *disk;
int i;
+ __u32 bbm_log_size = __le32_to_cpu(mpb->bbm_log_size);
for (i = 0; i < mpb->num_disks ; i++) {
disk = __get_imsm_disk(mpb, i);
set_pba_of_lba0(map, pba_of_lba0(map)*IMSM_4K_DIV);
}
}
+ if (bbm_log_size) {
+ struct bbm_log *log = (void *)mpb +
+ __le32_to_cpu(mpb->mpb_size) - bbm_log_size;
+ __u32 i;
+
+ for (i = 0; i < log->entry_count; i++) {
+ struct bbm_log_entry *entry =
+ &log->marked_block_entries[i];
+
+ __u8 count = entry->marked_count + 1;
+ unsigned long long sector =
+ __le48_to_cpu(&entry->defective_block_start);
+
+ entry->defective_block_start =
+ __cpu_to_le48(sector*IMSM_4K_DIV);
+ entry->marked_count = count*IMSM_4K_DIV - 1;
+ }
+ }
mpb->check_sum = __gen_imsm_checksum(mpb);
}
printf(" Disks : %d\n", mpb->num_disks);
printf(" RAID Devices : %d\n", mpb->num_raid_devs);
print_imsm_disk(__get_imsm_disk(mpb, super->disks->index), super->disks->index, reserved);
- if (super->bbm_log) {
+ if (get_imsm_bbm_log_size(super->bbm_log)) {
struct bbm_log *log = super->bbm_log;
printf("\n");
printf(" Log Size : %d\n", __le32_to_cpu(mpb->bbm_log_size));
printf(" Signature : %x\n", __le32_to_cpu(log->signature));
printf(" Entry Count : %d\n", __le32_to_cpu(log->entry_count));
- printf(" Spare Blocks : %d\n", __le32_to_cpu(log->reserved_spare_block_count));
- printf(" First Spare : %llx\n",
- (unsigned long long) __le64_to_cpu(log->first_spare_lba));
}
for (i = 0; i < mpb->num_raid_devs; i++) {
struct mdinfo info;
unsigned int sector_size = super->sector_size;
unsigned int written = 0;
- if (posix_memalign(&buf, 4096, 4096) != 0)
+ if (posix_memalign(&buf, MAX_SECTOR_SIZE, MAX_SECTOR_SIZE) != 0)
return 1;
if (!get_dev_size(from, NULL, &dsize))
static int read_imsm_migr_rec(int fd, struct intel_super *super)
{
int ret_val = -1;
+ unsigned int sector_size = super->sector_size;
unsigned long long dsize;
get_dev_size(fd, NULL, &dsize);
- if (lseek64(fd, dsize - MIGR_REC_POSITION, SEEK_SET) < 0) {
+ if (lseek64(fd, dsize - (sector_size*MIGR_REC_SECTOR_POSITION),
+ SEEK_SET) < 0) {
pr_err("Cannot seek to anchor block: %s\n",
strerror(errno));
goto out;
}
- if (read(fd, super->migr_rec_buf, MIGR_REC_BUF_SIZE) !=
- MIGR_REC_BUF_SIZE) {
+ if (read(fd, super->migr_rec_buf,
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size) {
pr_err("Cannot read migr record block: %s\n",
strerror(errno));
goto out;
}
ret_val = 0;
+ if (sector_size == 4096)
+ convert_from_4k_imsm_migr_rec(super);
out:
return ret_val;
static int write_imsm_migr_rec(struct supertype *st)
{
struct intel_super *super = st->sb;
+ unsigned int sector_size = super->sector_size;
unsigned long long dsize;
char nm[30];
int fd = -1;
map = get_imsm_map(dev, MAP_0);
+ if (sector_size == 4096)
+ convert_to_4k_imsm_migr_rec(super);
for (sd = super->disks ; sd ; sd = sd->next) {
int slot = -1;
if (fd < 0)
continue;
get_dev_size(fd, NULL, &dsize);
- if (lseek64(fd, dsize - MIGR_REC_POSITION, SEEK_SET) < 0) {
+ if (lseek64(fd, dsize - (MIGR_REC_SECTOR_POSITION*sector_size),
+ SEEK_SET) < 0) {
pr_err("Cannot seek to anchor block: %s\n",
strerror(errno));
goto out;
}
- if (write(fd, super->migr_rec_buf, MIGR_REC_BUF_SIZE) !=
- MIGR_REC_BUF_SIZE) {
+ if (write(fd, super->migr_rec_buf,
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size) {
pr_err("Cannot write migr record block: %s\n",
strerror(errno));
goto out;
close(fd);
fd = -1;
}
+ if (sector_size == 4096)
+ convert_from_4k_imsm_migr_rec(super);
/* update checkpoint information in metadata */
len = imsm_create_metadata_checkpoint_update(super, &u);
-
if (len <= 0) {
dprintf("imsm: Cannot prepare update\n");
goto out;
}
info->data_offset = pba_of_lba0(map_to_analyse);
- info->component_size = blocks_per_member(map_to_analyse);
+
+ if (info->array.level == 5) {
+ info->component_size = num_data_stripes(map_to_analyse) *
+ map_to_analyse->blocks_per_strip;
+ } else {
+ info->component_size = blocks_per_member(map_to_analyse);
+ }
info->component_size = imsm_component_size_aligment_check(
info->array.level,
info->array.chunk_size,
super->sector_size,
info->component_size);
+ info->bb.supported = 0;
memset(info->uuid, 0, sizeof(info->uuid));
info->recovery_start = MaxSector;
info->name[0] = 0;
info->recovery_start = MaxSector;
info->recovery_blocked = imsm_reshape_blocks_arrays_changes(st->sb);
+ info->bb.supported = 0;
/* do we have the all the insync disks that we expect? */
mpb = super->anchor;
size += (4 - 2) * sizeof(struct imsm_map);
/* 4 possible disk_ord_tbl's */
size += 4 * (disks - 1) * sizeof(__u32);
+ /* maximum bbm log */
+ size += sizeof(struct bbm_log);
return size;
}
super->len = len;
}
- return 0;
-}
+ super->extra_space += space_needed;
-/* retrieve a pointer to the bbm log which starts after all raid devices */
-struct bbm_log *__get_imsm_bbm_log(struct imsm_super *mpb)
-{
- void *ptr = NULL;
-
- if (__le32_to_cpu(mpb->bbm_log_size)) {
- ptr = mpb;
- ptr += mpb->mpb_size - __le32_to_cpu(mpb->bbm_log_size);
- }
-
- return ptr;
+ return 0;
}
/*******************************************************************************
sectors = mpb_sectors(anchor, sector_size) - 1;
free(anchor);
- if (posix_memalign(&super->migr_rec_buf, 512, MIGR_REC_BUF_SIZE) != 0) {
+ if (posix_memalign(&super->migr_rec_buf, sector_size,
+ MIGR_REC_BUF_SECTORS*sector_size) != 0) {
pr_err("could not allocate migr_rec buffer\n");
free(super->buf);
return 2;
return 3;
}
- /* FIXME the BBM log is disk specific so we cannot use this global
- * buffer for all disks. Ok for now since we only look at the global
- * bbm_log_size parameter to gate assembly
- */
- super->bbm_log = __get_imsm_bbm_log(super->anchor);
-
return 0;
}
if (err)
return err;
err = parse_raid_devices(super);
+ if (err)
+ return err;
+ err = load_bbm_log(super);
clear_hi(super);
return err;
}
free(elem);
elem = next;
}
+ if (super->bbm_log)
+ free(super->bbm_log);
super->hba = NULL;
}
static void free_imsm(struct intel_super *super)
{
__free_imsm(super, 1);
+ free(super->bb.entries);
free(super);
}
super->current_vol = -1;
super->create_offset = ~((unsigned long long) 0);
+
+ super->bb.entries = xmalloc(BBM_LOG_MAX_ENTRIES *
+ sizeof(struct md_bb_entry));
+ if (!super->bb.entries) {
+ free(super);
+ return NULL;
+ }
+
return super;
}
*super_list = s;
} else {
if (s)
- free(s);
+ free_imsm(s);
if (dfd >= 0)
close(dfd);
}
super = alloc_super();
get_dev_sector_size(fd, NULL, &super->sector_size);
+ if (!super)
+ return 1;
/* Load hba and capabilities if they exist.
* But do not preclude loading metadata in case capabilities or hba are
* non-compliant and ignore_hw_compat is set.
pr_err("could not allocate new mpb\n");
return 0;
}
- if (posix_memalign(&super->migr_rec_buf, 512,
- MIGR_REC_BUF_SIZE) != 0) {
+ if (posix_memalign(&super->migr_rec_buf, sector_size,
+ MIGR_REC_BUF_SECTORS*sector_size) != 0) {
pr_err("could not allocate migr_rec buffer\n");
free(super->buf);
free(super);
super->anchor = mpb_new;
mpb->mpb_size = __cpu_to_le32(size_new);
memset(mpb_new + size_old, 0, size_round - size_old);
+ super->len = size_round;
}
super->current_vol = idx;
super = alloc_super();
if (super &&
posix_memalign(&super->buf, MAX_SECTOR_SIZE, mpb_size) != 0) {
- free(super);
+ free_imsm(super);
super = NULL;
}
if (!super) {
pr_err("could not allocate superblock\n");
return 0;
}
- if (posix_memalign(&super->migr_rec_buf, 512, MIGR_REC_BUF_SIZE) != 0) {
+ if (posix_memalign(&super->migr_rec_buf, MAX_SECTOR_SIZE,
+ MIGR_REC_BUF_SECTORS*MAX_SECTOR_SIZE) != 0) {
pr_err("could not allocate migr_rec buffer\n");
free(super->buf);
- free(super);
+ free_imsm(super);
return 0;
}
memset(super->buf, 0, mpb_size);
}
/* clear migr_rec when adding disk to container */
- memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SIZE);
- if (lseek64(fd, size - MIGR_REC_POSITION, SEEK_SET) >= 0) {
+ memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SECTORS*super->sector_size);
+ if (lseek64(fd, size - MIGR_REC_SECTOR_POSITION*super->sector_size,
+ SEEK_SET) >= 0) {
if (write(fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ MIGR_REC_BUF_SECTORS*super->sector_size) !=
+ MIGR_REC_BUF_SECTORS*super->sector_size)
perror("Write migr_rec failed");
}
__u32 mpb_size = sizeof(struct imsm_super) - sizeof(struct imsm_disk);
int num_disks = 0;
int clear_migration_record = 1;
+ __u32 bbm_log_size;
/* 'generation' is incremented everytime the metadata is written */
generation = __le32_to_cpu(mpb->generation_num);
if (is_gen_migration(dev2))
clear_migration_record = 0;
}
- mpb_size += __le32_to_cpu(mpb->bbm_log_size);
+
+ bbm_log_size = get_imsm_bbm_log_size(super->bbm_log);
+
+ if (bbm_log_size) {
+ memcpy((void *)mpb + mpb_size, super->bbm_log, bbm_log_size);
+ mpb->attributes |= MPB_ATTRIB_BBM;
+ } else
+ mpb->attributes &= ~MPB_ATTRIB_BBM;
+
+ super->anchor->bbm_log_size = __cpu_to_le32(bbm_log_size);
+ mpb_size += bbm_log_size;
mpb->mpb_size = __cpu_to_le32(mpb_size);
+#ifdef DEBUG
+ assert(super->len == 0 || mpb_size <= super->len);
+#endif
+
/* recalculate checksum */
sum = __gen_imsm_checksum(mpb);
mpb->check_sum = __cpu_to_le32(sum);
super->clean_migration_record_by_mdmon = 0;
}
if (clear_migration_record)
- memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SIZE);
+ memset(super->migr_rec_buf, 0,
+ MIGR_REC_BUF_SECTORS*sector_size);
if (sector_size == 4096)
convert_to_4k(super);
unsigned long long dsize;
get_dev_size(d->fd, NULL, &dsize);
- if (lseek64(d->fd, dsize - 512, SEEK_SET) >= 0) {
+ if (lseek64(d->fd, dsize - sector_size,
+ SEEK_SET) >= 0) {
if (write(d->fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size)
perror("Write migr_rec failed");
}
}
#endif
}
-static int imsm_bbm_log_size(struct imsm_super *mpb)
-{
- return __le32_to_cpu(mpb->bbm_log_size);
-}
-
#ifndef MDASSEMBLE
static int validate_geometry_imsm_container(struct supertype *st, int level,
int layout, int raiddisks, int chunk,
* note that there is no fd for the disks in array.
*/
super = alloc_super();
+ if (!super) {
+ close(fd);
+ return 0;
+ }
if (!get_dev_sector_size(fd, NULL, &super->sector_size)) {
close(fd);
free_imsm(super);
pr_err("Unsupported attributes in IMSM metadata.Arrays activation is blocked.\n");
}
- /* check for bad blocks */
- if (imsm_bbm_log_size(super->anchor)) {
- pr_err("BBM log found in IMSM metadata.Arrays activation is blocked.\n");
- sb_errors = 1;
- }
-
/* count spare devices, not used in maps
*/
for (d = super->disks; d; d = d->next)
info_d->events = __le32_to_cpu(mpb->generation_num);
info_d->data_offset = pba_of_lba0(map);
- info_d->component_size = blocks_per_member(map);
+
+ if (map->raid_level == 5) {
+ info_d->component_size =
+ num_data_stripes(map) *
+ map->blocks_per_strip;
+ } else {
+ info_d->component_size = blocks_per_member(map);
+ }
+
+ info_d->bb.supported = 0;
+ get_volume_badblocks(super->bbm_log, ord_to_idx(ord),
+ info_d->data_offset,
+ info_d->component_size,
+ &info_d->bb);
}
/* now that the disk list is up-to-date fixup recovery_start */
update_recovery_start(super, dev, this);
{
struct intel_super *super = c->sb;
struct imsm_super *mpb = super->anchor;
+ struct imsm_update_prealloc_bb_mem u;
if (atoi(inst) >= mpb->num_raid_devs) {
pr_err("subarry index %d, out of range\n", atoi(inst));
dprintf("imsm: open_new %s\n", inst);
a->info.container_member = atoi(inst);
+
+ u.type = update_prealloc_badblocks_mem;
+ imsm_update_metadata_locally(c, &u, sizeof(u));
+
return 0;
}
}
/* return true if we recorded new information */
-static int mark_failure(struct imsm_dev *dev, struct imsm_disk *disk, int idx)
+static int mark_failure(struct intel_super *super,
+ struct imsm_dev *dev, struct imsm_disk *disk, int idx)
{
__u32 ord;
int slot;
}
if (map->failed_disk_num == 0xff)
map->failed_disk_num = slot;
+
+ clear_disk_badblocks(super->bbm_log, ord_to_idx(ord));
+
return 1;
}
-static void mark_missing(struct imsm_dev *dev, struct imsm_disk *disk, int idx)
+static void mark_missing(struct intel_super *super,
+ struct imsm_dev *dev, struct imsm_disk *disk, int idx)
{
- mark_failure(dev, disk, idx);
+ mark_failure(super, dev, disk, idx);
if (disk->scsi_id == __cpu_to_le32(~(__u32)0))
return;
end_migration(dev, super, map_state);
}
for (dl = super->missing; dl; dl = dl->next)
- mark_missing(dev, &dl->disk, dl->index);
+ mark_missing(super, dev, &dl->disk, dl->index);
super->updates_pending++;
}
return consistent;
}
+static int imsm_disk_slot_to_ord(struct active_array *a, int slot)
+{
+ int inst = a->info.container_member;
+ struct intel_super *super = a->container->sb;
+ struct imsm_dev *dev = get_imsm_dev(super, inst);
+ struct imsm_map *map = get_imsm_map(dev, MAP_0);
+
+ if (slot > map->num_members) {
+ pr_err("imsm: imsm_disk_slot_to_ord %d out of range 0..%d\n",
+ slot, map->num_members - 1);
+ return -1;
+ }
+
+ if (slot < 0)
+ return -1;
+
+ return get_imsm_ord_tbl_ent(dev, slot, MAP_0);
+}
+
static void imsm_set_disk(struct active_array *a, int n, int state)
{
int inst = a->info.container_member;
struct mdinfo *mdi;
int recovery_not_finished = 0;
int failed;
- __u32 ord;
+ int ord;
__u8 map_state;
- if (n > map->num_members)
- pr_err("imsm: set_disk %d out of range 0..%d\n",
- n, map->num_members - 1);
-
- if (n < 0)
+ ord = imsm_disk_slot_to_ord(a, n);
+ if (ord < 0)
return;
dprintf("imsm: set_disk %d:%x\n", n, state);
-
- ord = get_imsm_ord_tbl_ent(dev, n, MAP_0);
disk = get_imsm_disk(super, ord_to_idx(ord));
/* check for new failures */
if (state & DS_FAULTY) {
- if (mark_failure(dev, disk, ord_to_idx(ord)))
+ if (mark_failure(super, dev, disk, ord_to_idx(ord)))
super->updates_pending++;
}
di->data_offset = pba_of_lba0(map);
di->component_size = a->info.component_size;
di->container_member = inst;
+ di->bb.supported = 0;
super->random = random32();
di->next = rv;
rv = di;
/* update chunk size
*/
- if (u->new_chunksize > 0)
+ if (u->new_chunksize > 0) {
+ unsigned long long num_data_stripes;
+ int used_disks =
+ imsm_num_data_members(dev, MAP_0);
+
+ if (used_disks == 0)
+ return ret_val;
+
map->blocks_per_strip =
__cpu_to_le16(u->new_chunksize * 2);
+ num_data_stripes =
+ (join_u32(dev->size_low, dev->size_high)
+ / used_disks);
+ num_data_stripes /= map->blocks_per_strip;
+ num_data_stripes /= map->num_domains;
+ set_num_data_stripes(map, num_data_stripes);
+ }
/* add disk
*/
struct imsm_map *map = get_imsm_map(dev, MAP_0);
int used_disks = imsm_num_data_members(dev, MAP_0);
unsigned long long blocks_per_member;
+ unsigned long long num_data_stripes;
/* calculate new size
*/
blocks_per_member = u->new_size / used_disks;
- dprintf("(size: %llu, blocks per member: %llu)\n",
- u->new_size, blocks_per_member);
+ num_data_stripes = blocks_per_member /
+ map->blocks_per_strip;
+ num_data_stripes /= map->num_domains;
+ dprintf("(size: %llu, blocks per member: %llu, num_data_stipes: %llu)\n",
+ u->new_size, blocks_per_member,
+ num_data_stripes);
set_blocks_per_member(map, blocks_per_member);
+ set_num_data_stripes(map, num_data_stripes);
imsm_set_array_size(dev, u->new_size);
ret_val = 1;
map = get_imsm_map(dev, MAP_0);
if (u->direction == R10_TO_R0) {
+ unsigned long long num_data_stripes;
+
+ map->num_domains = 1;
+ num_data_stripes = blocks_per_member(map);
+ num_data_stripes /= map->blocks_per_strip;
+ num_data_stripes /= map->num_domains;
+ set_num_data_stripes(map, num_data_stripes);
+
/* Number of failed disks must be half of initial disk number */
if (imsm_count_failed(super, dev, MAP_0) !=
(map->num_members / 2))
for (du = super->missing; du; du = du->next)
if (du->index >= 0) {
set_imsm_ord_tbl_ent(map, du->index, du->index);
- mark_missing(dv->dev, &du->disk, du->index);
+ mark_missing(super, dv->dev, &du->disk, du->index);
}
return 1;
}
break;
}
+ case update_prealloc_badblocks_mem:
+ break;
default:
pr_err("error: unsuported process update type:(type: %d)\n", type);
}
case update_add_remove_disk:
/* no update->len needed */
break;
+ case update_prealloc_badblocks_mem:
+ super->extra_space += sizeof(struct bbm_log) -
+ get_imsm_bbm_log_size(super->bbm_log);
+ break;
default:
return 0;
}
else
buf_len = super->len;
- if (__le32_to_cpu(mpb->mpb_size) + len > buf_len) {
+ if (__le32_to_cpu(mpb->mpb_size) + super->extra_space + len > buf_len) {
/* ok we need a larger buf than what is currently allocated
* if this allocation fails process_update will notice that
* ->next_len is set and ->next_buf is NULL
*/
- buf_len = ROUND_UP(__le32_to_cpu(mpb->mpb_size) + len,
- sector_size);
+ buf_len = ROUND_UP(__le32_to_cpu(mpb->mpb_size) +
+ super->extra_space + len, sector_size);
if (super->next_buf)
free(super->next_buf);
struct dl *iter;
struct imsm_dev *dev;
struct imsm_map *map;
- int i, j, num_members;
+ unsigned int i, j, num_members;
__u32 ord;
+ struct bbm_log *log = super->bbm_log;
dprintf("deleting device[%d] from imsm_super\n", index);
}
}
+ for (i = 0; i < log->entry_count; i++) {
+ struct bbm_log_entry *entry = &log->marked_block_entries[i];
+
+ if (entry->disk_ordinal <= index)
+ continue;
+ entry->disk_ordinal--;
+ }
+
mpb->num_disks--;
super->updates_pending++;
if (*dlp) {
return 0;
}
#ifndef MDASSEMBLE
+/*******************************************************************************
+* Function: imsm_record_badblock
+* Description: This routine stores new bad block record in BBM log
+*
+* Parameters:
+* a : array containing a bad block
+* slot : disk number containing a bad block
+* sector : bad block sector
+* length : bad block sectors range
+* Returns:
+* 1 : Success
+* 0 : Error
+******************************************************************************/
+static int imsm_record_badblock(struct active_array *a, int slot,
+ unsigned long long sector, int length)
+{
+ struct intel_super *super = a->container->sb;
+ int ord;
+ int ret;
+
+ ord = imsm_disk_slot_to_ord(a, slot);
+ if (ord < 0)
+ return 0;
+
+ ret = record_new_badblock(super->bbm_log, ord_to_idx(ord), sector,
+ length);
+ if (ret)
+ super->updates_pending++;
+
+ return ret;
+}
+/*******************************************************************************
+* Function: imsm_clear_badblock
+* Description: This routine clears bad block record from BBM log
+*
+* Parameters:
+* a : array containing a bad block
+* slot : disk number containing a bad block
+* sector : bad block sector
+* length : bad block sectors range
+* Returns:
+* 1 : Success
+* 0 : Error
+******************************************************************************/
+static int imsm_clear_badblock(struct active_array *a, int slot,
+ unsigned long long sector, int length)
+{
+ struct intel_super *super = a->container->sb;
+ int ord;
+ int ret;
+
+ ord = imsm_disk_slot_to_ord(a, slot);
+ if (ord < 0)
+ return 0;
+
+ ret = clear_badblock(super->bbm_log, ord_to_idx(ord), sector, length);
+ if (ret)
+ super->updates_pending++;
+
+ return ret;
+}
+/*******************************************************************************
+* Function: imsm_get_badblocks
+* Description: This routine get list of bad blocks for an array
+*
+* Parameters:
+* a : array
+* slot : disk number
+* Returns:
+* bb : structure containing bad blocks
+* NULL : error
+******************************************************************************/
+static struct md_bb *imsm_get_badblocks(struct active_array *a, int slot)
+{
+ int inst = a->info.container_member;
+ struct intel_super *super = a->container->sb;
+ struct imsm_dev *dev = get_imsm_dev(super, inst);
+ struct imsm_map *map = get_imsm_map(dev, MAP_0);
+ int ord;
+
+ ord = imsm_disk_slot_to_ord(a, slot);
+ if (ord < 0)
+ return NULL;
+
+ get_volume_badblocks(super->bbm_log, ord_to_idx(ord), pba_of_lba0(map),
+ blocks_per_member(map), &super->bb);
+
+ return &super->bb;
+}
+/*******************************************************************************
+* Function: examine_badblocks_imsm
+* Description: Prints list of bad blocks on a disk to the standard output
+*
+* Parameters:
+* st : metadata handler
+* fd : open file descriptor for device
+* devname : device name
+* Returns:
+* 0 : Success
+* 1 : Error
+******************************************************************************/
+static int examine_badblocks_imsm(struct supertype *st, int fd, char *devname)
+{
+ struct intel_super *super = st->sb;
+ struct bbm_log *log = super->bbm_log;
+ struct dl *d = NULL;
+ int any = 0;
+
+ for (d = super->disks; d ; d = d->next) {
+ if (strcmp(d->devname, devname) == 0)
+ break;
+ }
+
+ if ((d == NULL) || (d->index < 0)) { /* serial mismatch probably */
+ pr_err("%s doesn't appear to be part of a raid array\n",
+ devname);
+ return 1;
+ }
+
+ if (log != NULL) {
+ unsigned int i;
+ struct bbm_log_entry *entry = &log->marked_block_entries[0];
+
+ for (i = 0; i < log->entry_count; i++) {
+ if (entry[i].disk_ordinal == d->index) {
+ unsigned long long sector = __le48_to_cpu(
+ &entry[i].defective_block_start);
+ int cnt = entry[i].marked_count + 1;
+
+ if (!any) {
+ printf("Bad-blocks on %s:\n", devname);
+ any = 1;
+ }
+
+ printf("%20llu for %d sectors\n", sector, cnt);
+ }
+ }
+ }
+
+ if (!any)
+ printf("No bad-blocks list configured on %s\n", devname);
+
+ return 0;
+}
/*******************************************************************************
* Function: init_migr_record_imsm
* Description: Function inits imsm migration record
if (sd->disk.state & (1<<MD_DISK_FAULTY))
continue;
if (sd->disk.state & (1<<MD_DISK_SYNC)) {
- char sbuf[20];
+ char sbuf[100];
+
if (sysfs_get_str(info,
- sd, "state", sbuf, 20) < 0 ||
+ sd, "state", sbuf, sizeof(sbuf)) < 0 ||
strstr(sbuf, "faulty") ||
strstr(sbuf, "in_sync") == NULL) {
/* this device is dead */
int ret_val = 0;
struct intel_super *super = st->sb;
struct intel_dev *dv;
+ unsigned int sector_size = super->sector_size;
struct imsm_dev *dev = NULL;
struct imsm_map *map_src;
int migr_vol_qan = 0;
buf_size += __le32_to_cpu(migr_rec->dest_depth_per_unit) * 512;
/* add space for stripe aligment */
buf_size += old_data_stripe_length;
- if (posix_memalign((void **)&buf, 4096, buf_size)) {
- dprintf("imsm: Cannot allocate checpoint buffer\n");
+ if (posix_memalign((void **)&buf, MAX_SECTOR_SIZE, buf_size)) {
+ dprintf("imsm: Cannot allocate checkpoint buffer\n");
goto abort;
}
/* clear migr_rec on disks after successful migration */
struct dl *d;
- memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SIZE);
+ memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SECTORS*sector_size);
for (d = super->disks; d; d = d->next) {
if (d->index < 0 || is_failed(&d->disk))
continue;
unsigned long long dsize;
get_dev_size(d->fd, NULL, &dsize);
- if (lseek64(d->fd, dsize - MIGR_REC_POSITION,
+ if (lseek64(d->fd, dsize - MIGR_REC_SECTOR_POSITION*sector_size,
SEEK_SET) >= 0) {
if (write(d->fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size)
perror("Write migr_rec failed");
}
}
.manage_reshape = imsm_manage_reshape,
.recover_backup = recover_backup_imsm,
.copy_metadata = copy_metadata_imsm,
+ .examine_badblocks = examine_badblocks_imsm,
#endif
.match_home = match_home_imsm,
.uuid_from_super= uuid_from_super_imsm,
.activate_spare = imsm_activate_spare,
.process_update = imsm_process_update,
.prepare_update = imsm_prepare_update,
+ .record_bad_block = imsm_record_badblock,
+ .clear_bad_block = imsm_clear_badblock,
+ .get_bad_blocks = imsm_get_badblocks,
#endif /* MDASSEMBLE */
};