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)
#define IMSM_RESERVED_SECTORS 4096
#define NUM_BLOCKS_DIRTY_STRIPE_REGION 2056
#define SECT_PER_MB_SHIFT 11
+#define MAX_SECTOR_SIZE 4096
/* Disk configuration info. */
#define IMSM_MAX_DEVICES 255
#define SPARE_DISK __cpu_to_le32(0x01) /* Spare */
#define CONFIGURED_DISK __cpu_to_le32(0x02) /* Member of some RaidDev */
#define FAILED_DISK __cpu_to_le32(0x04) /* Permanent failure */
+#define JOURNAL_DISK __cpu_to_le32(0x2000000) /* Device marked as Journaling Drive */
__u32 status; /* 0xF0 - 0xF3 */
__u32 owner_cfg_num; /* which config 0,1,2... owns this disk */
__u32 total_blocks_hi; /* 0xF4 - 0xF5 total blocks hi */
#define MIGR_STATE_CHANGE 4
#define MIGR_REPAIR 5
__u8 migr_type; /* Initializing, Rebuilding, ... */
+#define RAIDVOL_CLEAN 0
+#define RAIDVOL_DIRTY 1
+#define RAIDVOL_DSRECORD_VALID 2
__u8 dirty;
__u8 fs_state; /* fast-sync state for CnG (0xff == disabled) */
__u16 verify_errors; /* number of mismatches */
__u16 cache_policy;
__u8 cng_state;
__u8 cng_sub_state;
-#define IMSM_DEV_FILLERS 10
+ __u16 my_vol_raid_dev_num; /* Used in Unique volume Id for this RaidDev */
+
+ /* NVM_EN */
+ __u8 nv_cache_mode;
+ __u8 nv_cache_flags;
+
+ /* Unique Volume Id of the NvCache Volume associated with this volume */
+ __u32 nvc_vol_orig_family_num;
+ __u16 nvc_vol_raid_dev_num;
+
+#define RWH_OFF 0
+#define RWH_DISTRIBUTED 1
+#define RWH_JOURNALING_DRIVE 2
+ __u8 rwh_policy; /* Raid Write Hole Policy */
+ __u8 jd_serial[MAX_RAID_SERIAL_LEN]; /* Journal Drive serial number */
+ __u8 filler1;
+
+#define IMSM_DEV_FILLERS 3
__u32 filler[IMSM_DEV_FILLERS];
struct imsm_vol vol;
} __attribute__ ((packed));
} __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
static char *map_state_str[] = { "normal", "uninitialized", "degraded", "failed" };
-#endif
+
+#define BLOCKS_PER_KB (1024/512)
#define RAID_DISK_RESERVED_BLOCKS_IMSM_HI 2209
#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
#define UNIT_SRC_IN_CP_AREA 1 /* Source data for curr_migr_unit has
* already been migrated and must
* be recovered from checkpoint area */
+
+#define PPL_ENTRY_SPACE (128 * 1024) /* Size of the PPL, without the header */
+
struct migr_record {
__u32 rec_status; /* Status used to determine how to restart
* migration in case it aborts
}
}
-static unsigned int sector_count(__u32 bytes)
+static unsigned int sector_count(__u32 bytes, unsigned int sector_size)
{
- return ROUND_UP(bytes, 512) / 512;
+ return ROUND_UP(bytes, sector_size) / sector_size;
}
-static unsigned int mpb_sectors(struct imsm_super *mpb)
+static unsigned int mpb_sectors(struct imsm_super *mpb,
+ unsigned int sector_size)
{
- return sector_count(__le32_to_cpu(mpb->mpb_size));
+ return sector_count(__le32_to_cpu(mpb->mpb_size), sector_size);
}
struct intel_dev {
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 */
unsigned long long create_offset; /* common start for 'current_vol' */
__u32 random; /* random data for seeding new family numbers */
struct intel_dev *devlist;
+ unsigned int sector_size; /* sector size of used member drives */
struct dl {
struct dl *next;
int index;
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,
+ update_rwh_policy,
};
struct imsm_update_activate_spare {
enum imsm_update_type type;
};
+struct imsm_update_prealloc_bb_mem {
+ enum imsm_update_type type;
+};
+
+struct imsm_update_rwh_policy {
+ enum imsm_update_type type;
+ int new_policy;
+ int dev_idx;
+};
+
static const char *_sys_dev_type[] = {
[SYS_DEV_UNKNOWN] = "Unknown",
[SYS_DEV_SAS] = "SAS",
if (device->type != hba->type)
return 2;
- /* Always forbid spanning between VMD domains (seen as different controllers by mdadm) */
- if (device->type == SYS_DEV_VMD && !path_attached_to_hba(device->path, hba->path))
- return 2;
-
/* Multiple same type HBAs can be used if they share the same OROM */
const struct imsm_orom *device_orom = get_orom_by_device_id(device->dev_id);
return st;
}
-#ifndef MDASSEMBLE
static __u8 *get_imsm_version(struct imsm_super *mpb)
{
return &mpb->sig[MPB_SIG_LEN];
}
-#endif
/* retrieve a disk directly from the anchor when the anchor is known to be
* up-to-date, currently only at load time
return size;
}
-#ifndef MDASSEMBLE
/* retrieve disk serial number list from a metadata update */
static struct disk_info *get_disk_info(struct imsm_update_create_array *update)
{
return inf;
}
-#endif
static struct imsm_dev *__get_imsm_dev(struct imsm_super *mpb, __u8 index)
{
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;
+}
+
+/* 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;
+}
+
+/* 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)
{
split_ull(n, &disk->total_blocks_lo, &disk->total_blocks_hi);
}
-#endif
static void set_pba_of_lba0(struct imsm_map *map, unsigned long long n)
{
return (disk->status & FAILED_DISK) == FAILED_DISK;
}
+static int is_journal(struct imsm_disk *disk)
+{
+ return (disk->status & JOURNAL_DISK) == JOURNAL_DISK;
+}
+
+/* round array size down to closest MB and ensure it splits evenly
+ * between members
+ */
+static unsigned long long round_size_to_mb(unsigned long long size, unsigned int
+ disk_count)
+{
+ size /= disk_count;
+ size = (size >> SECT_PER_MB_SHIFT) << SECT_PER_MB_SHIFT;
+ size *= disk_count;
+
+ return size;
+}
+
/* try to determine how much space is reserved for metadata from
* the last get_extents() entry on the smallest active disk,
* otherwise fallback to the default
static int is_gen_migration(struct imsm_dev *dev);
-#ifndef MDASSEMBLE
+#define IMSM_4K_DIV 8
+
static __u64 blocks_per_migr_unit(struct intel_super *super,
struct imsm_dev *dev);
printf(" <-- %s", map_state_str[map->map_state]);
printf("\n Checkpoint : %u ",
__le32_to_cpu(dev->vol.curr_migr_unit));
- if ((is_gen_migration(dev)) && ((slot > 1) || (slot < 0)))
+ if (is_gen_migration(dev) && (slot > 1 || slot < 0))
printf("(N/A)");
else
printf("(%llu)", (unsigned long long)
blocks_per_migr_unit(super, dev));
}
printf("\n");
- printf(" Dirty State : %s\n", dev->vol.dirty ? "dirty" : "clean");
+ printf(" Dirty State : %s\n", (dev->vol.dirty & RAIDVOL_DIRTY) ?
+ "dirty" : "clean");
+ printf(" RWH Policy : ");
+ if (dev->rwh_policy == RWH_OFF)
+ printf("off\n");
+ else if (dev->rwh_policy == RWH_DISTRIBUTED)
+ printf("PPL distributed\n");
+ else if (dev->rwh_policy == RWH_JOURNALING_DRIVE)
+ printf("PPL journaling drive\n");
+ else
+ printf("<unknown:%d>\n", dev->rwh_policy);
}
-static void print_imsm_disk(struct imsm_disk *disk, int index, __u32 reserved)
-{
+static void print_imsm_disk(struct imsm_disk *disk,
+ int index,
+ __u32 reserved,
+ unsigned int sector_size) {
char str[MAX_RAID_SERIAL_LEN + 1];
__u64 sz;
printf(" Disk%02d Serial : %s\n", index, str);
else
printf(" Disk Serial : %s\n", str);
- printf(" State :%s%s%s\n", is_spare(disk) ? " spare" : "",
- is_configured(disk) ? " active" : "",
- is_failed(disk) ? " failed" : "");
+ printf(" State :%s%s%s%s\n", is_spare(disk) ? " spare" : "",
+ is_configured(disk) ? " active" : "",
+ is_failed(disk) ? " failed" : "",
+ is_journal(disk) ? " journal" : "");
printf(" Id : %08x\n", __le32_to_cpu(disk->scsi_id));
sz = total_blocks(disk) - reserved;
- printf(" Usable Size : %llu%s\n", (unsigned long long)sz,
+ printf(" Usable Size : %llu%s\n",
+ (unsigned long long)sz * 512 / sector_size,
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));
+}
+
+void convert_to_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);
+ /* disk */
+ convert_to_4k_imsm_disk(disk);
+ }
+ for (i = 0; i < mpb->num_raid_devs; i++) {
+ struct imsm_dev *dev = __get_imsm_dev(mpb, i);
+ struct imsm_map *map = get_imsm_map(dev, MAP_0);
+ /* dev */
+ split_ull((join_u32(dev->size_low, dev->size_high)/IMSM_4K_DIV),
+ &dev->size_low, &dev->size_high);
+ dev->vol.curr_migr_unit /= IMSM_4K_DIV;
+
+ /* map0 */
+ set_blocks_per_member(map, blocks_per_member(map)/IMSM_4K_DIV);
+ map->blocks_per_strip /= IMSM_4K_DIV;
+ set_pba_of_lba0(map, pba_of_lba0(map)/IMSM_4K_DIV);
+
+ if (dev->vol.migr_state) {
+ /* map1 */
+ map = get_imsm_map(dev, MAP_1);
+ set_blocks_per_member(map,
+ blocks_per_member(map)/IMSM_4K_DIV);
+ map->blocks_per_strip /= IMSM_4K_DIV;
+ 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);
+}
+
void examine_migr_rec_imsm(struct intel_super *super)
{
struct migr_record *migr_rec = super->migr_rec;
map = get_imsm_map(dev, MAP_0);
if (map)
slot = get_imsm_disk_slot(map, super->disks->index);
- if ((map == NULL) || (slot > 1) || (slot < 0)) {
+ if (map == NULL || slot > 1 || slot < 0) {
printf(" Empty\n ");
printf("Examine one of first two disks in array\n");
break;
break;
}
}
-#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);
+ /* disk */
+ set_total_blocks(disk, (total_blocks(disk)*IMSM_4K_DIV));
+ }
+
+ for (i = 0; i < mpb->num_raid_devs; i++) {
+ struct imsm_dev *dev = __get_imsm_dev(mpb, i);
+ struct imsm_map *map = get_imsm_map(dev, MAP_0);
+ /* dev */
+ split_ull((join_u32(dev->size_low, dev->size_high)*IMSM_4K_DIV),
+ &dev->size_low, &dev->size_high);
+ dev->vol.curr_migr_unit *= IMSM_4K_DIV;
+
+ /* map0 */
+ set_blocks_per_member(map, blocks_per_member(map)*IMSM_4K_DIV);
+ map->blocks_per_strip *= IMSM_4K_DIV;
+ set_pba_of_lba0(map, pba_of_lba0(map)*IMSM_4K_DIV);
+
+ if (dev->vol.migr_state) {
+ /* map1 */
+ map = get_imsm_map(dev, MAP_1);
+ set_blocks_per_member(map,
+ blocks_per_member(map)*IMSM_4K_DIV);
+ map->blocks_per_strip *= IMSM_4K_DIV;
+ 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);
+}
+
/*******************************************************************************
* function: imsm_check_attributes
* Description: Function checks if features represented by attributes flags
return ret_val;
}
-#ifndef MDASSEMBLE
static void getinfo_super_imsm(struct supertype *st, struct mdinfo *info, char *map);
static void examine_super_imsm(struct supertype *st, char *homehost)
__u32 reserved = imsm_reserved_sectors(super, super->disks);
struct dl *dl;
- snprintf(str, MPB_SIG_LEN, "%s", mpb->sig);
+ strncpy(str, (char *)mpb->sig, MPB_SIG_LEN);
+ str[MPB_SIG_LEN-1] = '\0';
printf(" Magic : %s\n", str);
snprintf(str, strlen(MPB_VERSION_RAID0), "%s", get_imsm_version(mpb));
printf(" Version : %s\n", get_imsm_version(mpb));
sum = __le32_to_cpu(mpb->check_sum);
printf(" Checksum : %08x %s\n", sum,
__gen_imsm_checksum(mpb) == sum ? "correct" : "incorrect");
- printf(" MPB Sectors : %d\n", mpb_sectors(mpb));
+ printf(" MPB Sectors : %d\n", mpb_sectors(mpb, super->sector_size));
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) {
+ print_imsm_disk(__get_imsm_disk(mpb, super->disks->index),
+ super->disks->index, reserved, super->sector_size);
+ 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;
for (i = 0; i < mpb->num_disks; i++) {
if (i == super->disks->index)
continue;
- print_imsm_disk(__get_imsm_disk(mpb, i), i, reserved);
+ print_imsm_disk(__get_imsm_disk(mpb, i), i, reserved,
+ super->sector_size);
}
for (dl = super->disks; dl; dl = dl->next)
if (dl->index == -1)
- print_imsm_disk(&dl->disk, -1, reserved);
+ print_imsm_disk(&dl->disk, -1, reserved,
+ super->sector_size);
examine_migr_rec_imsm(super);
}
static int copy_metadata_imsm(struct supertype *st, int from, int to)
{
- /* The second last 512byte sector of the device contains
+ /* The second last sector of the device contains
* the "struct imsm_super" metadata.
* This contains mpb_size which is the size in bytes of the
* extended metadata. This is located immediately before
unsigned long long dsize, offset;
int sectors;
struct imsm_super *sb;
- int written = 0;
+ struct intel_super *super = st->sb;
+ 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))
goto err;
- if (lseek64(from, dsize-1024, 0) < 0)
+ if (lseek64(from, dsize-(2*sector_size), 0) < 0)
goto err;
- if (read(from, buf, 512) != 512)
+ if ((unsigned int)read(from, buf, sector_size) != sector_size)
goto err;
sb = buf;
if (strncmp((char*)sb->sig, MPB_SIGNATURE, MPB_SIG_LEN) != 0)
goto err;
- sectors = mpb_sectors(sb) + 2;
- offset = dsize - sectors * 512;
+ sectors = mpb_sectors(sb, sector_size) + 2;
+ offset = dsize - sectors * sector_size;
if (lseek64(from, offset, 0) < 0 ||
lseek64(to, offset, 0) < 0)
goto err;
- while (written < sectors * 512) {
- int n = sectors*512 - written;
+ while (written < sectors * sector_size) {
+ int n = sectors*sector_size - written;
if (n > 4096)
n = 4096;
if (read(from, buf, n) != n)
getinfo_super_imsm(st, &info, NULL);
fname_from_uuid(st, &info, nbuf, ':');
- printf("\n UUID : %s\n", nbuf + 5);
+ printf("\n UUID : %s\n", nbuf + 5);
}
static void brief_detail_super_imsm(struct supertype *st)
continue;
sprintf(path, "/sys/bus/pci/drivers/nvme/%s", ent->d_name);
- /* if not a intel NVMe - skip it*/
- if (devpath_to_vendor(path) != 0x8086)
- continue;
rp = realpath(path, NULL);
if (!rp)
for (entry = orom_entries; entry; entry = entry->next) {
if (entry->type == SYS_DEV_VMD) {
+ print_imsm_capability(&entry->orom);
+ printf(" 3rd party NVMe :%s supported\n",
+ imsm_orom_has_tpv_support(&entry->orom)?"":" not");
for (hba = list; hba; hba = hba->next) {
if (hba->type == SYS_DEV_VMD) {
char buf[PATH_MAX];
- print_imsm_capability(&entry->orom);
printf(" I/O Controller : %s (%s)\n",
vmd_domain_to_controller(hba, buf), get_sys_dev_type(hba->type));
if (print_vmd_attached_devs(hba)) {
pr_err("failed to get devices attached to VMD domain.\n");
result |= 2;
}
- printf("\n");
}
}
+ printf("\n");
continue;
}
return result;
}
-#endif
-
static int match_home_imsm(struct supertype *st, char *homehost)
{
/* the imsm metadata format does not specify any host
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 ((unsigned int)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;
*/
if (dev == NULL)
return -2;
- map = get_imsm_map(dev, MAP_0);
if (info) {
for (sd = info->devs ; sd ; sd = sd->next) {
- /* skip spare and failed disks
- */
- if (sd->disk.raid_disk < 0)
- continue;
/* read only from one of the first two slots */
- if (map)
- slot = get_imsm_disk_slot(map,
- sd->disk.raid_disk);
- if ((map == NULL) || (slot > 1) || (slot < 0))
+ if ((sd->disk.raid_disk < 0) ||
+ (sd->disk.raid_disk > 1))
continue;
sprintf(nm, "%d:%d", sd->disk.major, sd->disk.minor);
}
}
if (fd < 0) {
+ map = get_imsm_map(dev, MAP_0);
for (dl = super->disks; dl; dl = dl->next) {
/* skip spare and failed disks
*/
/* read only from one of the first two slots */
if (map)
slot = get_imsm_disk_slot(map, dl->index);
- if ((map == NULL) || (slot > 1) || (slot < 0))
+ if (map == NULL || slot > 1 || slot < 0)
continue;
sprintf(nm, "%d:%d", dl->major, dl->minor);
fd = dev_open(nm, O_RDONLY);
return retval;
}
-#ifndef MDASSEMBLE
/*******************************************************************************
* function: imsm_create_metadata_checkpoint_update
* Description: It creates update for checkpoint change.
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;
/* write to 2 first slots only */
if (map)
slot = get_imsm_disk_slot(map, sd->index);
- if ((map == NULL) || (slot > 1) || (slot < 0))
+ if (map == NULL || slot > 1 || slot < 0)
continue;
sprintf(nm, "%d:%d", sd->major, sd->minor);
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 ((unsigned int)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;
close(fd);
return retval;
}
-#endif /* MDASSEMBLE */
/* spare/missing disks activations are not allowe when
* array/container performs reshape operation, because
}
static unsigned long long imsm_component_size_aligment_check(int level,
int chunk_size,
+ unsigned int sector_size,
unsigned long long component_size)
{
unsigned int component_size_alligment;
/* check component size aligment
*/
- component_size_alligment = component_size % (chunk_size/512);
+ component_size_alligment = component_size % (chunk_size/sector_size);
dprintf("(Level: %i, chunk_size = %i, component_size = %llu), component_size_alligment = %u\n",
level, chunk_size, component_size,
return component_size;
}
+static unsigned long long get_ppl_sector(struct intel_super *super, int dev_idx)
+{
+ struct imsm_dev *dev = get_imsm_dev(super, dev_idx);
+ struct imsm_map *map = get_imsm_map(dev, MAP_0);
+
+ return pba_of_lba0(map) +
+ (num_data_stripes(map) * map->blocks_per_strip);
+}
+
static void getinfo_super_imsm_volume(struct supertype *st, struct mdinfo *info, char *dmap)
{
struct intel_super *super = st->sb;
info->array.utime = 0;
info->array.chunk_size =
__le16_to_cpu(map_to_analyse->blocks_per_strip) << 9;
- info->array.state = !dev->vol.dirty;
+ info->array.state = !(dev->vol.dirty & RAIDVOL_DIRTY);
info->custom_array_size = __le32_to_cpu(dev->size_high);
info->custom_array_size <<= 32;
info->custom_array_size |= __le32_to_cpu(dev->size_low);
}
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 = 1;
memset(info->uuid, 0, sizeof(info->uuid));
info->recovery_start = MaxSector;
+ if (info->array.level == 5 && dev->rwh_policy == RWH_DISTRIBUTED) {
+ info->consistency_policy = CONSISTENCY_POLICY_PPL;
+ info->ppl_sector = get_ppl_sector(super, super->current_vol);
+ info->ppl_size = (PPL_HEADER_SIZE + PPL_ENTRY_SPACE) >> 9;
+ } else if (info->array.level <= 0) {
+ info->consistency_policy = CONSISTENCY_POLICY_NONE;
+ } else {
+ info->consistency_policy = CONSISTENCY_POLICY_RESYNC;
+ }
+
info->reshape_progress = 0;
info->resync_start = MaxSector;
if ((map_to_analyse->map_state == IMSM_T_STATE_UNINITIALIZED ||
- dev->vol.dirty) &&
+ !(info->array.state & 1)) &&
imsm_reshape_blocks_arrays_changes(super) == 0) {
info->resync_start = 0;
}
if (used_disks > 0) {
array_blocks = blocks_per_member(map) *
used_disks;
- /* round array size down to closest MB
- */
- info->custom_array_size = (array_blocks
- >> SECT_PER_MB_SHIFT)
- << SECT_PER_MB_SHIFT;
+ info->custom_array_size =
+ round_size_to_mb(array_blocks,
+ used_disks);
+
}
}
case MIGR_VERIFY:
static int imsm_count_failed(struct intel_super *super, struct imsm_dev *dev,
int look_in_map);
-#ifndef MDASSEMBLE
static void manage_second_map(struct intel_super *super, struct imsm_dev *dev)
{
if (is_gen_migration(dev)) {
}
}
}
-#endif
static struct imsm_disk *get_imsm_missing(struct intel_super *super, __u8 index)
{
info->name[0] = 0;
info->recovery_start = MaxSector;
info->recovery_blocked = imsm_reshape_blocks_arrays_changes(st->sb);
+ info->bb.supported = 1;
/* do we have the all the insync disks that we expect? */
mpb = super->anchor;
+ info->events = __le32_to_cpu(mpb->generation_num);
for (i = 0; i < mpb->num_raid_devs; i++) {
struct imsm_dev *dev = get_imsm_dev(super, i);
* found the 'most fresh' version of the metadata
*/
info->disk.state |= is_failed(disk) ? (1 << MD_DISK_FAULTY) : 0;
- info->disk.state |= is_spare(disk) ? 0 : (1 << MD_DISK_SYNC);
+ info->disk.state |= (is_spare(disk) || is_journal(disk)) ?
+ 0 : (1 << MD_DISK_SYNC);
}
/* only call uuid_from_super_imsm when this disk is part of a populated container,
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;
}
}
}
+static int nvme_get_serial(int fd, void *buf, size_t buf_len)
+{
+ char path[60];
+ char *name = fd2kname(fd);
+
+ if (!name)
+ return 1;
+
+ if (strncmp(name, "nvme", 4) != 0)
+ return 1;
+
+ snprintf(path, sizeof(path) - 1, "/sys/block/%s/device/serial", name);
+
+ return load_sys(path, buf, buf_len);
+}
+
extern int scsi_get_serial(int fd, void *buf, size_t buf_len);
static int imsm_read_serial(int fd, char *devname,
__u8 serial[MAX_RAID_SERIAL_LEN])
{
- unsigned char scsi_serial[255];
+ char buf[50];
int rv;
- int rsp_len;
int len;
char *dest;
char *src;
- char *rsp_buf;
- int i;
+ unsigned int i;
+
+ memset(buf, 0, sizeof(buf));
- memset(scsi_serial, 0, sizeof(scsi_serial));
+ rv = nvme_get_serial(fd, buf, sizeof(buf));
- rv = scsi_get_serial(fd, scsi_serial, sizeof(scsi_serial));
+ if (rv)
+ rv = scsi_get_serial(fd, buf, sizeof(buf));
if (rv && check_env("IMSM_DEVNAME_AS_SERIAL")) {
memset(serial, 0, MAX_RAID_SERIAL_LEN);
return rv;
}
- rsp_len = scsi_serial[3];
- if (!rsp_len) {
- if (devname)
- pr_err("Failed to retrieve serial for %s\n",
- devname);
- return 2;
- }
- rsp_buf = (char *) &scsi_serial[4];
-
/* trim all whitespace and non-printable characters and convert
* ':' to ';'
*/
- for (i = 0, dest = rsp_buf; i < rsp_len; i++) {
- src = &rsp_buf[i];
+ for (i = 0, dest = buf; i < sizeof(buf) && buf[i]; i++) {
+ src = &buf[i];
if (*src > 0x20) {
/* ':' is reserved for use in placeholder serial
* numbers for missing disks
*dest++ = *src;
}
}
- len = dest - rsp_buf;
- dest = rsp_buf;
+ len = dest - buf;
+ dest = buf;
/* truncate leading characters */
if (len > MAX_RAID_SERIAL_LEN) {
*/
if (is_failed(&dl->disk))
dl->index = -2;
- else if (is_spare(&dl->disk))
+ else if (is_spare(&dl->disk) || is_journal(&dl->disk))
dl->index = -1;
}
return 0;
}
-#ifndef MDASSEMBLE
/* When migrating map0 contains the 'destination' state while map1
* contains the current state. When not migrating map0 contains the
* current state. This routine assumes that map[0].map_state is set to
/* duplicate and then set the target end state in map[0] */
memcpy(dest, src, sizeof_imsm_map(src));
- if ((migr_type == MIGR_REBUILD) ||
- (migr_type == MIGR_GEN_MIGR)) {
+ if (migr_type == MIGR_REBUILD || migr_type == MIGR_GEN_MIGR) {
__u32 ord;
int i;
*
* FIXME add support for raid-level-migration
*/
- if ((map_state != map->map_state) && (is_gen_migration(dev) == 0) &&
- (prev->map_state != IMSM_T_STATE_UNINITIALIZED)) {
+ if (map_state != map->map_state && (is_gen_migration(dev) == 0) &&
+ prev->map_state != IMSM_T_STATE_UNINITIALIZED) {
/* when final map state is other than expected
* merge maps (not for migration)
*/
dev->vol.curr_migr_unit = 0;
map->map_state = map_state;
}
-#endif
static int parse_raid_devices(struct intel_super *super)
{
if (__le32_to_cpu(mpb->mpb_size) + space_needed > super->len) {
void *buf;
- len = ROUND_UP(__le32_to_cpu(mpb->mpb_size) + space_needed, 512);
- if (posix_memalign(&buf, 512, len) != 0)
+ len = ROUND_UP(__le32_to_cpu(mpb->mpb_size) + space_needed,
+ super->sector_size);
+ if (posix_memalign(&buf, MAX_SECTOR_SIZE, len) != 0)
return 1;
memcpy(buf, super->buf, super->len);
super->len = len;
}
- return 0;
-}
-
-/* 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);
- }
+ super->extra_space += space_needed;
- return ptr;
+ return 0;
}
/*******************************************************************************
{
unsigned long long dsize;
unsigned long long sectors;
+ unsigned int sector_size = super->sector_size;
struct stat;
struct imsm_super *anchor;
__u32 check_sum;
get_dev_size(fd, NULL, &dsize);
- if (dsize < 1024) {
+ if (dsize < 2*sector_size) {
if (devname)
pr_err("%s: device to small for imsm\n",
devname);
return 1;
}
- if (lseek64(fd, dsize - (512 * 2), SEEK_SET) < 0) {
+ if (lseek64(fd, dsize - (sector_size * 2), SEEK_SET) < 0) {
if (devname)
pr_err("Cannot seek to anchor block on %s: %s\n",
devname, strerror(errno));
return 1;
}
- if (posix_memalign((void**)&anchor, 512, 512) != 0) {
+ if (posix_memalign((void **)&anchor, sector_size, sector_size) != 0) {
if (devname)
pr_err("Failed to allocate imsm anchor buffer on %s\n", devname);
return 1;
}
- if (read(fd, anchor, 512) != 512) {
+ if ((unsigned int)read(fd, anchor, sector_size) != sector_size) {
if (devname)
pr_err("Cannot read anchor block on %s: %s\n",
devname, strerror(errno));
/* capability and hba must be updated with new super allocation */
find_intel_hba_capability(fd, super, devname);
- super->len = ROUND_UP(anchor->mpb_size, 512);
- if (posix_memalign(&super->buf, 512, super->len) != 0) {
+ super->len = ROUND_UP(anchor->mpb_size, sector_size);
+ if (posix_memalign(&super->buf, MAX_SECTOR_SIZE, super->len) != 0) {
if (devname)
pr_err("unable to allocate %zu byte mpb buffer\n",
super->len);
free(anchor);
return 2;
}
- memcpy(super->buf, anchor, 512);
+ memcpy(super->buf, anchor, sector_size);
- sectors = mpb_sectors(anchor) - 1;
+ 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;
}
/* read the extended mpb */
- if (lseek64(fd, dsize - (512 * (2 + sectors)), SEEK_SET) < 0) {
+ if (lseek64(fd, dsize - (sector_size * (2 + sectors)), SEEK_SET) < 0) {
if (devname)
pr_err("Cannot seek to extended mpb on %s: %s\n",
devname, strerror(errno));
return 1;
}
- if ((unsigned)read(fd, super->buf + 512, super->len - 512) != super->len - 512) {
+ if ((unsigned int)read(fd, super->buf + sector_size,
+ super->len - sector_size) != super->len - sector_size) {
if (devname)
pr_err("Cannot read extended mpb on %s: %s\n",
devname, strerror(errno));
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;
}
err = load_imsm_mpb(fd, super, devname);
if (err)
return err;
+ if (super->sector_size == 4096)
+ convert_from_4k(super);
err = load_imsm_disk(fd, super, devname, keep_fd);
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;
}
struct sys_dev *hba_name;
int rv = 0;
- if ((fd < 0) || check_env("IMSM_NO_PLATFORM")) {
+ if (fd < 0 || check_env("IMSM_NO_PLATFORM")) {
super->orom = NULL;
super->hba = NULL;
return 0;
return 0;
}
-#ifndef MDASSEMBLE
static struct intel_disk *disk_list_get(__u8 *serial, struct intel_disk *disk_list)
{
struct intel_disk *idisk = disk_list;
}
/* Check migration compatibility */
- if ((err == 0) && (check_mpb_migr_compatibility(super) != 0)) {
+ if (err == 0 && check_mpb_migr_compatibility(super) != 0) {
pr_err("Unsupported migration detected");
if (devname)
fprintf(stderr, " on %s\n", devname);
goto error;
}
+ get_dev_sector_size(dfd, NULL, &s->sector_size);
find_intel_hba_capability(dfd, s, devname);
err = load_and_parse_mpb(dfd, s, NULL, keep_fd);
*super_list = s;
} else {
if (s)
- free(s);
+ free_imsm(s);
if (dfd >= 0)
close(dfd);
}
- if ((dfd >= 0) && (!keep_fd))
+ if (dfd >= 0 && !keep_fd)
close(dfd);
return err;
{
return load_super_imsm_all(st, fd, &st->sb, devname, NULL, 1);
}
-#endif
static int load_super_imsm(struct supertype *st, int fd, char *devname)
{
free_super_imsm(st);
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.
*/
rv = find_intel_hba_capability(fd, super, devname);
/* no orom/efi or non-intel hba of the disk */
- if ((rv != 0) && (st->ignore_hw_compat == 0)) {
+ if (rv != 0 && st->ignore_hw_compat == 0) {
if (devname)
pr_err("No OROM/EFI properties for %s\n", devname);
free_imsm(super);
}
static int init_super_imsm_volume(struct supertype *st, mdu_array_info_t *info,
- unsigned long long size, char *name,
+ struct shape *s, char *name,
char *homehost, int *uuid,
long long data_offset)
{
* so st->sb is already set.
*/
struct intel_super *super = st->sb;
+ unsigned int sector_size = super->sector_size;
struct imsm_super *mpb = super->anchor;
struct intel_dev *dv;
struct imsm_dev *dev;
unsigned long long array_blocks;
size_t size_old, size_new;
unsigned long long num_data_stripes;
+ unsigned int data_disks;
+ unsigned long long size_per_member;
if (super->orom && mpb->num_raid_devs >= super->orom->vpa) {
pr_err("This imsm-container already has the maximum of %d volumes\n", super->orom->vpa);
size_new = disks_to_mpb_size(info->nr_disks);
if (size_new > size_old) {
void *mpb_new;
- size_t size_round = ROUND_UP(size_new, 512);
+ size_t size_round = ROUND_UP(size_new, sector_size);
- if (posix_memalign(&mpb_new, 512, size_round) != 0) {
+ if (posix_memalign(&mpb_new, sector_size, size_round) != 0) {
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;
disk->status = CONFIGURED_DISK | FAILED_DISK;
disk->scsi_id = __cpu_to_le32(~(__u32)0);
snprintf((char *) disk->serial, MAX_RAID_SERIAL_LEN,
- "missing:%d", i);
+ "missing:%d", (__u8)i);
}
find_missing(super);
} else {
strncpy((char *) dev->volume, name, MAX_RAID_SERIAL_LEN);
array_blocks = calc_array_size(info->level, info->raid_disks,
info->layout, info->chunk_size,
- size * 2);
- /* round array size down to closest MB */
- array_blocks = (array_blocks >> SECT_PER_MB_SHIFT) << SECT_PER_MB_SHIFT;
+ s->size * BLOCKS_PER_KB);
+ data_disks = get_data_disks(info->level, info->layout,
+ info->raid_disks);
+ array_blocks = round_size_to_mb(array_blocks, data_disks);
+ size_per_member = array_blocks / data_disks;
dev->size_low = __cpu_to_le32((__u32) array_blocks);
dev->size_high = __cpu_to_le32((__u32) (array_blocks >> 32));
vol->curr_migr_unit = 0;
map = get_imsm_map(dev, MAP_0);
set_pba_of_lba0(map, super->create_offset);
- set_blocks_per_member(map, info_to_blocks_per_member(info, size));
+ set_blocks_per_member(map, info_to_blocks_per_member(info,
+ size_per_member /
+ BLOCKS_PER_KB));
map->blocks_per_strip = __cpu_to_le16(info_to_blocks_per_strip(info));
map->failed_disk_num = ~0;
if (info->level > 0)
map->num_domains = 1;
/* info->size is only int so use the 'size' parameter instead */
- num_data_stripes = (size * 2) / info_to_blocks_per_strip(info);
+ num_data_stripes = size_per_member / info_to_blocks_per_strip(info);
num_data_stripes /= map->num_domains;
set_num_data_stripes(map, num_data_stripes);
}
mpb->num_raid_devs++;
+ if (s->consistency_policy == UnSet ||
+ s->consistency_policy == CONSISTENCY_POLICY_RESYNC ||
+ s->consistency_policy == CONSISTENCY_POLICY_NONE) {
+ dev->rwh_policy = RWH_OFF;
+ } else if (s->consistency_policy == CONSISTENCY_POLICY_PPL) {
+ dev->rwh_policy = RWH_DISTRIBUTED;
+ } else {
+ free(dev);
+ free(dv);
+ pr_err("imsm does not support consistency policy %s\n",
+ map_num(consistency_policies, s->consistency_policy));
+ return 0;
+ }
+
dv->dev = dev;
dv->index = super->current_vol;
dv->next = super->devlist;
}
static int init_super_imsm(struct supertype *st, mdu_array_info_t *info,
- unsigned long long size, char *name,
+ struct shape *s, char *name,
char *homehost, int *uuid,
unsigned long long data_offset)
{
}
if (st->sb)
- return init_super_imsm_volume(st, info, size, name, homehost, uuid,
+ return init_super_imsm_volume(st, info, s, name, homehost, uuid,
data_offset);
if (info)
mpb_size = disks_to_mpb_size(info->nr_disks);
else
- mpb_size = 512;
+ mpb_size = MAX_SECTOR_SIZE;
super = alloc_super();
- if (super && posix_memalign(&super->buf, 512, mpb_size) != 0) {
- free(super);
+ if (super &&
+ posix_memalign(&super->buf, MAX_SECTOR_SIZE, mpb_size) != 0) {
+ 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);
return 1;
}
-#ifndef MDASSEMBLE
static int add_to_super_imsm_volume(struct supertype *st, mdu_disk_info_t *dk,
int fd, char *devname)
{
struct imsm_map *map2 = get_imsm_map(dev,
MAP_1);
int slot2 = get_imsm_disk_slot(map2, df->index);
- if ((slot2 < map2->num_members) &&
- (slot2 >= 0)) {
+ if (slot2 < map2->num_members && slot2 >= 0) {
__u32 ord2 = get_imsm_ord_tbl_ent(dev,
slot2,
MAP_1);
struct intel_super *super = st->sb;
struct dl *dd;
unsigned long long size;
+ unsigned int member_sector_size;
__u32 id;
int rv;
struct stat stb;
rv = imsm_read_serial(fd, devname, dd->serial);
if (rv) {
pr_err("failed to retrieve scsi serial, aborting\n");
+ if (dd->devname)
+ free(dd->devname);
free(dd);
abort();
}
+ if (super->hba && ((super->hba->type == SYS_DEV_NVME) ||
+ (super->hba->type == SYS_DEV_VMD))) {
+ int i;
+ char *devpath = diskfd_to_devpath(fd);
+ char controller_path[PATH_MAX];
+
+ if (!devpath) {
+ pr_err("failed to get devpath, aborting\n");
+ if (dd->devname)
+ free(dd->devname);
+ free(dd);
+ return 1;
+ }
+
+ snprintf(controller_path, PATH_MAX-1, "%s/device", devpath);
+ free(devpath);
+
+ if (devpath_to_vendor(controller_path) == 0x8086) {
+ /*
+ * If Intel's NVMe drive has serial ended with
+ * "-A","-B","-1" or "-2" it means that this is "x8"
+ * device (double drive on single PCIe card).
+ * User should be warned about potential data loss.
+ */
+ for (i = MAX_RAID_SERIAL_LEN-1; i > 0; i--) {
+ /* Skip empty character at the end */
+ if (dd->serial[i] == 0)
+ continue;
+
+ if (((dd->serial[i] == 'A') ||
+ (dd->serial[i] == 'B') ||
+ (dd->serial[i] == '1') ||
+ (dd->serial[i] == '2')) &&
+ (dd->serial[i-1] == '-'))
+ pr_err("\tThe action you are about to take may put your data at risk.\n"
+ "\tPlease note that x8 devices may consist of two separate x4 devices "
+ "located on a single PCIe port.\n"
+ "\tRAID 0 is the only supported configuration for this type of x8 device.\n");
+ break;
+ }
+ } else if (super->hba->type == SYS_DEV_VMD && super->orom &&
+ !imsm_orom_has_tpv_support(super->orom)) {
+ pr_err("\tPlatform configuration does not support non-Intel NVMe drives.\n"
+ "\tPlease refer to Intel(R) RSTe user guide.\n");
+ free(dd->devname);
+ free(dd);
+ return 1;
+ }
+ }
get_dev_size(fd, NULL, &size);
+ get_dev_sector_size(fd, NULL, &member_sector_size);
+
+ if (super->sector_size == 0) {
+ /* this a first device, so sector_size is not set yet */
+ super->sector_size = member_sector_size;
+ } else if (member_sector_size != super->sector_size) {
+ pr_err("Mixing between different sector size is forbidden, aborting...\n");
+ if (dd->devname)
+ free(dd->devname);
+ free(dd);
+ return 1;
+ }
+
/* 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) {
- if (write(fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ 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 ((unsigned int)write(fd, super->migr_rec_buf,
+ MIGR_REC_BUF_SECTORS*super->sector_size) !=
+ MIGR_REC_BUF_SECTORS*super->sector_size)
perror("Write migr_rec failed");
}
static int store_imsm_mpb(int fd, struct imsm_super *mpb);
static union {
- char buf[512];
+ char buf[MAX_SECTOR_SIZE];
struct imsm_super anchor;
-} spare_record __attribute__ ((aligned(512)));
+} spare_record __attribute__ ((aligned(MAX_SECTOR_SIZE)));
/* spare records have their own family number and do not have any defined raid
* devices
if (__le32_to_cpu(d->disk.total_blocks_hi) > 0)
spare->attributes |= MPB_ATTRIB_2TB_DISK;
+ if (super->sector_size == 4096)
+ convert_to_4k_imsm_disk(&spare->disk[0]);
+
sum = __gen_imsm_checksum(spare);
spare->family_num = __cpu_to_le32(sum);
spare->orig_family_num = 0;
static int write_super_imsm(struct supertype *st, int doclose)
{
struct intel_super *super = st->sb;
+ unsigned int sector_size = super->sector_size;
struct imsm_super *mpb = super->anchor;
struct dl *d;
__u32 generation;
__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);
/* write the mpb for disks that compose raid devices */
for (d = super->disks; d ; d = d->next) {
unsigned long long dsize;
get_dev_size(d->fd, NULL, &dsize);
- if (lseek64(d->fd, dsize - 512, SEEK_SET) >= 0) {
- if (write(d->fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ if (lseek64(d->fd, dsize - sector_size,
+ SEEK_SET) >= 0) {
+ if ((unsigned int)write(d->fd,
+ super->migr_rec_buf,
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size)
perror("Write migr_rec failed");
}
}
- if (store_imsm_mpb(d->fd, mpb))
- fprintf(stderr,
- "failed for device %d:%d (fd: %d)%s\n",
- d->major, d->minor,
- d->fd, strerror(errno));
+ if (store_imsm_mpb(d->fd, mpb))
+ fprintf(stderr,
+ "failed for device %d:%d (fd: %d)%s\n",
+ d->major, d->minor,
+ d->fd, strerror(errno));
+
+ if (doclose) {
+ close(d->fd);
+ d->fd = -1;
+ }
+ }
+
+ if (spares)
+ return write_super_imsm_spares(super, doclose);
+
+ return 0;
+}
+
+static int create_array(struct supertype *st, int dev_idx)
+{
+ size_t len;
+ struct imsm_update_create_array *u;
+ struct intel_super *super = st->sb;
+ struct imsm_dev *dev = get_imsm_dev(super, dev_idx);
+ struct imsm_map *map = get_imsm_map(dev, MAP_0);
+ struct disk_info *inf;
+ struct imsm_disk *disk;
+ int i;
+
+ len = sizeof(*u) - sizeof(*dev) + sizeof_imsm_dev(dev, 0) +
+ sizeof(*inf) * map->num_members;
+ u = xmalloc(len);
+ u->type = update_create_array;
+ u->dev_idx = dev_idx;
+ imsm_copy_dev(&u->dev, dev);
+ inf = get_disk_info(u);
+ for (i = 0; i < map->num_members; i++) {
+ int idx = get_imsm_disk_idx(dev, i, MAP_X);
+
+ disk = get_imsm_disk(super, idx);
+ if (!disk)
+ disk = get_imsm_missing(super, idx);
+ serialcpy(inf[i].serial, disk->serial);
+ }
+ append_metadata_update(st, u, len);
+
+ return 0;
+}
+
+static int mgmt_disk(struct supertype *st)
+{
+ struct intel_super *super = st->sb;
+ size_t len;
+ struct imsm_update_add_remove_disk *u;
+
+ if (!super->disk_mgmt_list)
+ return 0;
+
+ len = sizeof(*u);
+ u = xmalloc(len);
+ u->type = update_add_remove_disk;
+ append_metadata_update(st, u, len);
+
+ return 0;
+}
+
+__u32 crc32c_le(__u32 crc, unsigned char const *p, size_t len);
+
+static int write_init_ppl_imsm(struct supertype *st, struct mdinfo *info, int fd)
+{
+ struct intel_super *super = st->sb;
+ void *buf;
+ struct ppl_header *ppl_hdr;
+ int ret;
+
+ ret = posix_memalign(&buf, 4096, PPL_HEADER_SIZE);
+ if (ret) {
+ pr_err("Failed to allocate PPL header buffer\n");
+ return ret;
+ }
+
+ memset(buf, 0, PPL_HEADER_SIZE);
+ ppl_hdr = buf;
+ memset(ppl_hdr->reserved, 0xff, PPL_HDR_RESERVED);
+ ppl_hdr->signature = __cpu_to_le32(super->anchor->orig_family_num);
+ ppl_hdr->checksum = __cpu_to_le32(~crc32c_le(~0, buf, PPL_HEADER_SIZE));
+
+ if (lseek64(fd, info->ppl_sector * 512, SEEK_SET) < 0) {
+ ret = errno;
+ perror("Failed to seek to PPL header location");
+ }
+
+ if (!ret && write(fd, buf, PPL_HEADER_SIZE) != PPL_HEADER_SIZE) {
+ ret = errno;
+ perror("Write PPL header failed");
+ }
+
+ if (!ret)
+ fsync(fd);
+
+ free(buf);
+ return ret;
+}
+
+static int validate_ppl_imsm(struct supertype *st, struct mdinfo *info,
+ struct mdinfo *disk)
+{
+ struct intel_super *super = st->sb;
+ struct dl *d;
+ void *buf;
+ int ret = 0;
+ struct ppl_header *ppl_hdr;
+ __u32 crc;
+ struct imsm_dev *dev;
+ struct imsm_map *map;
+ __u32 idx;
+
+ if (disk->disk.raid_disk < 0)
+ return 0;
+
+ if (posix_memalign(&buf, 4096, PPL_HEADER_SIZE)) {
+ pr_err("Failed to allocate PPL header buffer\n");
+ return -1;
+ }
+
+ dev = get_imsm_dev(super, info->container_member);
+ map = get_imsm_map(dev, MAP_X);
+ idx = get_imsm_disk_idx(dev, disk->disk.raid_disk, MAP_X);
+ d = get_imsm_dl_disk(super, idx);
- if (doclose) {
- close(d->fd);
- d->fd = -1;
- }
+ if (!d || d->index < 0 || is_failed(&d->disk))
+ goto out;
+
+ if (lseek64(d->fd, info->ppl_sector * 512, SEEK_SET) < 0) {
+ perror("Failed to seek to PPL header location");
+ ret = -1;
+ goto out;
}
- if (spares)
- return write_super_imsm_spares(super, doclose);
+ if (read(d->fd, buf, PPL_HEADER_SIZE) != PPL_HEADER_SIZE) {
+ perror("Read PPL header failed");
+ ret = -1;
+ goto out;
+ }
- return 0;
-}
+ ppl_hdr = buf;
-static int create_array(struct supertype *st, int dev_idx)
-{
- size_t len;
- struct imsm_update_create_array *u;
- struct intel_super *super = st->sb;
- struct imsm_dev *dev = get_imsm_dev(super, dev_idx);
- struct imsm_map *map = get_imsm_map(dev, MAP_0);
- struct disk_info *inf;
- struct imsm_disk *disk;
- int i;
+ crc = __le32_to_cpu(ppl_hdr->checksum);
+ ppl_hdr->checksum = 0;
- len = sizeof(*u) - sizeof(*dev) + sizeof_imsm_dev(dev, 0) +
- sizeof(*inf) * map->num_members;
- u = xmalloc(len);
- u->type = update_create_array;
- u->dev_idx = dev_idx;
- imsm_copy_dev(&u->dev, dev);
- inf = get_disk_info(u);
- for (i = 0; i < map->num_members; i++) {
- int idx = get_imsm_disk_idx(dev, i, MAP_X);
+ if (crc != ~crc32c_le(~0, buf, PPL_HEADER_SIZE)) {
+ dprintf("Wrong PPL header checksum on %s\n",
+ d->devname);
+ ret = 1;
+ }
- disk = get_imsm_disk(super, idx);
- if (!disk)
- disk = get_imsm_missing(super, idx);
- serialcpy(inf[i].serial, disk->serial);
+ if (!ret && (__le32_to_cpu(ppl_hdr->signature) !=
+ super->anchor->orig_family_num)) {
+ dprintf("Wrong PPL header signature on %s\n",
+ d->devname);
+ ret = 1;
}
- append_metadata_update(st, u, len);
- return 0;
+out:
+ free(buf);
+
+ if (ret == 1 && map->map_state == IMSM_T_STATE_UNINITIALIZED)
+ return st->ss->write_init_ppl(st, info, d->fd);
+
+ return ret;
}
-static int mgmt_disk(struct supertype *st)
+static int write_init_ppl_imsm_all(struct supertype *st, struct mdinfo *info)
{
struct intel_super *super = st->sb;
- size_t len;
- struct imsm_update_add_remove_disk *u;
+ struct dl *d;
+ int ret = 0;
- if (!super->disk_mgmt_list)
+ if (info->consistency_policy != CONSISTENCY_POLICY_PPL ||
+ info->array.level != 5)
return 0;
- len = sizeof(*u);
- u = xmalloc(len);
- u->type = update_add_remove_disk;
- append_metadata_update(st, u, len);
+ for (d = super->disks; d ; d = d->next) {
+ if (d->index < 0 || is_failed(&d->disk))
+ continue;
- return 0;
+ ret = st->ss->write_init_ppl(st, info, d->fd);
+ if (ret)
+ break;
+ }
+
+ return ret;
}
static int write_init_super_imsm(struct supertype *st)
{
struct intel_super *super = st->sb;
int current_vol = super->current_vol;
+ int rv = 0;
+ struct mdinfo info;
+
+ getinfo_super_imsm(st, &info, NULL);
/* we are done with current_vol reset it to point st at the container */
super->current_vol = -1;
if (st->update_tail) {
/* queue the recently created array / added disk
* as a metadata update */
- int rv;
/* determine if we are creating a volume or adding a disk */
if (current_vol < 0) {
/* in the mgmt (add/remove) disk case we are running
* in mdmon context, so don't close fd's
*/
- return mgmt_disk(st);
- } else
- rv = create_array(st, current_vol);
-
- return rv;
+ rv = mgmt_disk(st);
+ } else {
+ rv = write_init_ppl_imsm_all(st, &info);
+ if (!rv)
+ rv = create_array(st, current_vol);
+ }
} else {
struct dl *d;
for (d = super->disks; d; d = d->next)
Kill(d->devname, NULL, 0, -1, 1);
- return write_super_imsm(st, 1);
+ if (current_vol >= 0)
+ rv = write_init_ppl_imsm_all(st, &info);
+ if (!rv)
+ rv = write_super_imsm(st, 1);
}
+
+ return rv;
}
-#endif
static int store_super_imsm(struct supertype *st, int fd)
{
if (!mpb)
return 1;
-#ifndef MDASSEMBLE
+ if (super->sector_size == 4096)
+ convert_to_4k(super);
return store_imsm_mpb(fd, mpb);
-#else
- return 1;
-#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,
unsigned long long size,
* 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);
+ return 0;
+ }
+
rv = find_intel_hba_capability(fd, super, verbose > 0 ? dev : NULL);
if (rv != 0) {
#if DEBUG
num = sprintf(path, "%s%s", "/dev/", dev->name);
if (num > 0)
fd = open(path, O_RDONLY, 0);
- if ((num <= 0) || (fd < 0)) {
- pr_vrb(": Cannot open %s: %s\n",
+ if (num <= 0 || fd < 0) {
+ pr_vrb("Cannot open %s: %s\n",
dev->name, strerror(errno));
}
free(path);
dev = dev->next;
}
found = 0;
- if ((fd >= 0) && disk_attached_to_hba(fd, hba)) {
+ if (fd >= 0 && disk_attached_to_hba(fd, hba)) {
struct mdstat_ent *vol;
for (vol = mdstat ; vol ; vol = vol->next) {
- if ((vol->active > 0) &&
+ if (vol->active > 0 &&
vol->metadata_version &&
is_container_member(vol, memb->devnm)) {
found++;
*found = 0;
st = match_metadata_desc_imsm("imsm");
if (st == NULL) {
- pr_vrb(": cannot allocate memory for imsm supertype\n");
+ pr_vrb("cannot allocate memory for imsm supertype\n");
return 0;
}
continue;
tst = dup_super(st);
if (tst == NULL) {
- pr_vrb(": cannot allocate memory for imsm supertype\n");
+ pr_vrb("cannot allocate memory for imsm supertype\n");
goto err_1;
}
tmpdev->container = 0;
}
for (tmpdev = devlist; tmpdev; tmpdev = tmpdev->next) {
- if ((tmpdev->used == 1) && (tmpdev->found)) {
+ if (tmpdev->used == 1 && tmpdev->found) {
if (count) {
if (count < tmpdev->found)
count = 0;
return count;
}
-static int
-count_volumes(struct intel_hba *hba, int dpa, int verbose)
+static int __count_volumes(char *hba_path, int dpa, int verbose,
+ int cmp_hba_path)
{
struct sys_dev *idev, *intel_devices = find_intel_devices();
int count = 0;
const struct orom_entry *entry;
struct devid_list *dv, *devid_list;
- if (!hba || !hba->path)
+ if (!hba_path)
return 0;
for (idev = intel_devices; idev; idev = idev->next) {
- if (strstr(idev->path, hba->path))
- break;
+ if (strstr(idev->path, hba_path))
+ break;
}
if (!idev || !idev->dev_id)
devid_list = entry->devid_list;
for (dv = devid_list; dv; dv = dv->next) {
struct md_list *devlist;
- struct sys_dev *device = device_by_id(dv->devid);
- char *hba_path;
+ struct sys_dev *device = NULL;
+ char *hpath;
int found = 0;
+ if (cmp_hba_path)
+ device = device_by_id_and_path(dv->devid, hba_path);
+ else
+ device = device_by_id(dv->devid);
+
if (device)
- hba_path = device->path;
+ hpath = device->path;
else
return 0;
- /* VMD has one orom entry for all domain, but spanning is not allowed.
- * VMD arrays should be counted per domain (controller), so skip
- * domains that are not the given one.
- */
- if ((hba->type == SYS_DEV_VMD) &&
- (strncmp(device->path, hba->path, strlen(device->path)) != 0))
- continue;
-
- devlist = get_devices(hba_path);
+ devlist = get_devices(hpath);
/* if no intel devices return zero volumes */
if (devlist == NULL)
return 0;
- count += active_arrays_by_format("imsm", hba_path, &devlist, dpa, verbose);
- dprintf("path: %s active arrays: %d\n", hba_path, count);
+ count += active_arrays_by_format("imsm", hpath, &devlist, dpa,
+ verbose);
+ dprintf("path: %s active arrays: %d\n", hpath, count);
if (devlist == NULL)
return 0;
do {
dprintf("found %d count: %d\n", found, count);
} while (found);
- dprintf("path: %s total number of volumes: %d\n", hba_path, count);
+ dprintf("path: %s total number of volumes: %d\n", hpath, count);
while (devlist) {
struct md_list *dv = devlist;
return count;
}
+static int count_volumes(struct intel_hba *hba, int dpa, int verbose)
+{
+ if (!hba)
+ return 0;
+ if (hba->type == SYS_DEV_VMD) {
+ struct sys_dev *dev;
+ int count = 0;
+
+ for (dev = find_intel_devices(); dev; dev = dev->next) {
+ if (dev->type == SYS_DEV_VMD)
+ count += __count_volumes(dev->path, dpa,
+ verbose, 1);
+ }
+ return count;
+ }
+ return __count_volumes(hba->path, dpa, verbose, 0);
+}
+
static int imsm_default_chunk(const struct imsm_orom *orom)
{
/* up to 512 if the plaform supports it, otherwise the platform max.
{
/* check/set platform and metadata limits/defaults */
if (super->orom && raiddisks > super->orom->dpa) {
- pr_vrb(": platform supports a maximum of %d disks per array\n",
+ pr_vrb("platform supports a maximum of %d disks per array\n",
super->orom->dpa);
return 0;
}
/* capabilities of OROM tested - copied from validate_geometry_imsm_volume */
if (!is_raid_level_supported(super->orom, level, raiddisks)) {
- pr_vrb(": platform does not support raid%d with %d disk%s\n",
+ pr_vrb("platform does not support raid%d with %d disk%s\n",
level, raiddisks, raiddisks > 1 ? "s" : "");
return 0;
}
*chunk = imsm_default_chunk(super->orom);
if (super->orom && !imsm_orom_has_chunk(super->orom, *chunk)) {
- pr_vrb(": platform does not support a chunk size of: %d\n", *chunk);
+ pr_vrb("platform does not support a chunk size of: %d\n", *chunk);
return 0;
}
if (layout != imsm_level_to_layout(level)) {
if (level == 5)
- pr_vrb(": imsm raid 5 only supports the left-asymmetric layout\n");
+ pr_vrb("imsm raid 5 only supports the left-asymmetric layout\n");
else if (level == 10)
- pr_vrb(": imsm raid 10 only supports the n2 layout\n");
+ pr_vrb("imsm raid 10 only supports the n2 layout\n");
else
- pr_vrb(": imsm unknown layout %#x for this raid level %d\n",
+ pr_vrb("imsm unknown layout %#x for this raid level %d\n",
layout, level);
return 0;
}
if (super->orom && (super->orom->attr & IMSM_OROM_ATTR_2TB) == 0 &&
(calc_array_size(level, raiddisks, layout, *chunk, size) >> 32) > 0) {
- pr_vrb(": platform does not support a volume size over 2TB\n");
+ pr_vrb("platform does not support a volume size over 2TB\n");
return 0;
}
int count = count_volumes(super->hba,
super->orom->dpa, verbose);
if (super->orom->vphba <= count) {
- pr_vrb(": platform does not support more than %d raid volumes.\n",
+ pr_vrb("platform does not support more than %d raid volumes.\n",
super->orom->vphba);
return 0;
}
int raiddisks, int *chunk, unsigned long long size,
unsigned long long data_offset,
char *dev, unsigned long long *freesize,
- int verbose)
+ int consistency_policy, int verbose)
{
int fd, cfd;
struct mdinfo *sra;
count = count_volumes(super->hba,
super->orom->dpa, verbose);
if (super->orom->vphba <= count) {
- pr_vrb(": platform does not support more than %d raid volumes.\n",
+ pr_vrb("platform does not support more than %d raid volumes.\n",
super->orom->vphba);
return 0;
}
u->type = update_rename_array;
u->dev_idx = vol;
- snprintf((char *) u->name, MAX_RAID_SERIAL_LEN, "%s", name);
+ strncpy((char *) u->name, name, MAX_RAID_SERIAL_LEN);
+ u->name[MAX_RAID_SERIAL_LEN-1] = '\0';
append_metadata_update(st, u, sizeof(*u));
} else {
struct imsm_dev *dev;
int i;
dev = get_imsm_dev(super, vol);
- snprintf((char *) dev->volume, MAX_RAID_SERIAL_LEN, "%s", name);
+ strncpy((char *) dev->volume, name, MAX_RAID_SERIAL_LEN);
+ dev->volume[MAX_RAID_SERIAL_LEN-1] = '\0';
for (i = 0; i < mpb->num_raid_devs; i++) {
dev = get_imsm_dev(super, i);
handle_missing(super, dev);
}
super->updates_pending++;
}
+ } else if (strcmp(update, "ppl") == 0 ||
+ strcmp(update, "no-ppl") == 0) {
+ int new_policy;
+ char *ep;
+ int vol = strtoul(subarray, &ep, 10);
+
+ if (*ep != '\0' || vol >= super->anchor->num_raid_devs)
+ return 2;
+
+ if (strcmp(update, "ppl") == 0)
+ new_policy = RWH_DISTRIBUTED;
+ else
+ new_policy = RWH_OFF;
+
+ if (st->update_tail) {
+ struct imsm_update_rwh_policy *u = xmalloc(sizeof(*u));
+
+ u->type = update_rwh_policy;
+ u->dev_idx = vol;
+ u->new_policy = new_policy;
+ append_metadata_update(st, u, sizeof(*u));
+ } else {
+ struct imsm_dev *dev;
+
+ dev = get_imsm_dev(super, vol);
+ dev->rwh_policy = new_policy;
+ super->updates_pending++;
+ }
} else
return 2;
return 0;
}
-#endif /* MDASSEMBLE */
static int is_gen_migration(struct imsm_dev *dev)
{
return 0;
}
-#ifndef MDASSEMBLE
static int is_initializing(struct imsm_dev *dev)
{
struct imsm_map *migr_map;
return 0;
}
-#endif
static void update_recovery_start(struct intel_super *super,
struct imsm_dev *dev,
rebuild->recovery_start = units * blocks_per_migr_unit(super, dev);
}
-#ifndef MDASSEMBLE
static int recover_backup_imsm(struct supertype *st, struct mdinfo *info);
-#endif
static struct mdinfo *container_content_imsm(struct supertype *st, char *subarray)
{
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)
struct imsm_map *map2;
struct mdinfo *this;
int slot;
-#ifndef MDASSEMBLE
int chunk;
-#endif
char *ep;
if (subarray &&
super->current_vol = i;
getinfo_super_imsm_volume(st, this, NULL);
this->next = rest;
-#ifndef MDASSEMBLE
chunk = __le16_to_cpu(map->blocks_per_strip) >> 1;
/* mdadm does not support all metadata features- set the bit in all arrays state */
if (!validate_geometry_imsm_orom(super,
(1<<MD_SB_BLOCK_CONTAINER_RESHAPE) |
(1<<MD_SB_BLOCK_VOLUME);
}
-#endif
/* if array has bad blocks, set suitable bit in all arrays state */
if (sb_errors)
*
* FIXME handle dirty degraded
*/
- if ((skip || recovery_start == 0) && !dev->vol.dirty)
+ if ((skip || recovery_start == 0) &&
+ !(dev->vol.dirty & RAIDVOL_DIRTY))
this->resync_start = MaxSector;
if (skip)
continue;
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;
+ info_d->ppl_sector = this->ppl_sector;
+ info_d->ppl_size = this->ppl_size;
+ } else {
+ info_d->component_size = blocks_per_member(map);
+ }
+ info_d->consistency_policy = this->consistency_policy;
+
+ info_d->bb.supported = 1;
+ 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);
this->array.spare_disks += spare_disks;
-#ifndef MDASSEMBLE
/* check for reshape */
if (this->reshape_active == 1)
recover_backup_imsm(st, this);
-#endif
rest = this;
}
/* when MAP_X is passed both maps failures are counted
*/
if (prev &&
- ((look_in_map == MAP_1) || (look_in_map == MAP_X)) &&
- (i < prev->num_members)) {
+ (look_in_map == MAP_1 || look_in_map == MAP_X) &&
+ i < prev->num_members) {
ord = __le32_to_cpu(prev->disk_ord_tbl[i]);
idx_1 = ord_to_idx(ord);
if (!disk || is_failed(disk) || ord & IMSM_ORD_REBUILD)
failed++;
}
- if (((look_in_map == MAP_0) || (look_in_map == MAP_X)) &&
- (i < map->num_members)) {
+ if ((look_in_map == MAP_0 || look_in_map == MAP_X) &&
+ i < map->num_members) {
ord = __le32_to_cpu(map->disk_ord_tbl[i]);
idx = ord_to_idx(ord);
return failed;
}
-#ifndef MDASSEMBLE
static int imsm_open_new(struct supertype *c, struct active_array *a,
char *inst)
{
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;
}
migr_map = get_imsm_map(dev, MAP_1);
- if ((migr_map->map_state == IMSM_T_STATE_NORMAL) &&
- (dev->vol.migr_type != MIGR_GEN_MIGR))
+ if (migr_map->map_state == IMSM_T_STATE_NORMAL &&
+ dev->vol.migr_type != MIGR_GEN_MIGR)
return 1;
else
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;
struct imsm_map *map2 = get_imsm_map(dev, MAP_1);
int slot2 = get_imsm_disk_slot(map2, idx);
- if ((slot2 < map2->num_members) &&
- (slot2 >= 0))
+ if (slot2 < map2->num_members && slot2 >= 0)
set_imsm_ord_tbl_ent(map2, slot2,
idx | IMSM_ORD_REBUILD);
}
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++;
}
array_blocks = new_size;
}
- /* round array size down to closest MB
- */
- array_blocks = (array_blocks >> SECT_PER_MB_SHIFT) << SECT_PER_MB_SHIFT;
+ array_blocks = round_size_to_mb(array_blocks, used_disks);
dev->size_low = __cpu_to_le32((__u32)array_blocks);
dev->size_high = __cpu_to_le32((__u32)(array_blocks >> 32));
array_blocks =
blocks_per_member(map) *
used_disks;
- /* round array size down to closest MB
- */
- array_blocks = (array_blocks
- >> SECT_PER_MB_SHIFT)
- << SECT_PER_MB_SHIFT;
+ array_blocks =
+ round_size_to_mb(array_blocks,
+ used_disks);
a->info.custom_array_size = array_blocks;
/* encourage manager to update array
* size
skip_mark_checkpoint:
/* mark dirty / clean */
- if (dev->vol.dirty != !consistent) {
+ if (((dev->vol.dirty & RAIDVOL_DIRTY) && consistent) ||
+ (!(dev->vol.dirty & RAIDVOL_DIRTY) && !consistent)) {
dprintf("imsm: mark '%s'\n", consistent ? "clean" : "dirty");
- if (consistent)
- dev->vol.dirty = 0;
- else
- dev->vol.dirty = 1;
+ if (consistent) {
+ dev->vol.dirty = RAIDVOL_CLEAN;
+ } else {
+ dev->vol.dirty = RAIDVOL_DIRTY;
+ if (dev->rwh_policy == RWH_DISTRIBUTED)
+ dev->vol.dirty |= RAIDVOL_DSRECORD_VALID;
+ }
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++;
}
break;
case IMSM_T_STATE_DEGRADED: /* transition to degraded state */
dprintf_cont("degraded: ");
- if ((map->map_state != map_state) &&
- !dev->vol.migr_state) {
+ if (map->map_state != map_state && !dev->vol.migr_state) {
dprintf_cont("mark degraded");
map->map_state = map_state;
super->updates_pending++;
__u32 mpb_size = __le32_to_cpu(mpb->mpb_size);
unsigned long long dsize;
unsigned long long sectors;
+ unsigned int sector_size;
+ get_dev_sector_size(fd, NULL, §or_size);
get_dev_size(fd, NULL, &dsize);
- if (mpb_size > 512) {
+ if (mpb_size > sector_size) {
/* -1 to account for anchor */
- sectors = mpb_sectors(mpb) - 1;
+ sectors = mpb_sectors(mpb, sector_size) - 1;
/* write the extended mpb to the sectors preceeding the anchor */
- if (lseek64(fd, dsize - (512 * (2 + sectors)), SEEK_SET) < 0)
+ if (lseek64(fd, dsize - (sector_size * (2 + sectors)),
+ SEEK_SET) < 0)
return 1;
- if ((unsigned long long)write(fd, buf + 512, 512 * sectors)
- != 512 * sectors)
+ if ((unsigned long long)write(fd, buf + sector_size,
+ sector_size * sectors) != sector_size * sectors)
return 1;
}
/* first block is stored on second to last sector of the disk */
- if (lseek64(fd, dsize - (512 * 2), SEEK_SET) < 0)
+ if (lseek64(fd, dsize - (sector_size * 2), SEEK_SET) < 0)
return 1;
- if (write(fd, buf, 512) != 512)
+ if ((unsigned int)write(fd, buf, sector_size) != sector_size)
return 1;
return 0;
di->data_offset = pba_of_lba0(map);
di->component_size = a->info.component_size;
di->container_member = inst;
+ di->bb.supported = 1;
+ if (dev->rwh_policy == RWH_DISTRIBUTED) {
+ di->consistency_policy = CONSISTENCY_POLICY_PPL;
+ di->ppl_sector = get_ppl_sector(super, inst);
+ di->ppl_size = (PPL_HEADER_SIZE + PPL_ENTRY_SPACE) >> 9;
+ }
super->random = random32();
di->next = rv;
rv = di;
struct dl *dl;
for (dl = super->disks; dl; dl = dl->next)
- if ((dl->major == major) && (dl->minor == minor))
+ if (dl->major == major && dl->minor == minor)
return dl;
return NULL;
}
prev = NULL;
for (dl = super->disks; dl; dl = dl->next) {
- if ((dl->major == major) && (dl->minor == minor)) {
+ if (dl->major == major && dl->minor == minor) {
/* remove */
if (prev)
prev->next = dl->next;
int ret_val = 0;
dprintf("(enter)\n");
- if ((u->subdev < 0) ||
- (u->subdev > 1)) {
+ if (u->subdev < 0 || u->subdev > 1) {
dprintf("imsm: Error: Wrong subdev: %i\n", u->subdev);
return ret_val;
}
- if ((space_list == NULL) || (*space_list == NULL)) {
+ if (space_list == NULL || *space_list == NULL) {
dprintf("imsm: Error: Memory is not allocated\n");
return ret_val;
}
/* 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
*/
- if ((u->new_level != 5) ||
- (migr_map->raid_level != 0) ||
- (migr_map->raid_level == map->raid_level))
+ if (u->new_level != 5 || migr_map->raid_level != 0 ||
+ migr_map->raid_level == map->raid_level)
goto skip_disk_add;
if (u->new_disks[0] >= 0) {
int ret_val = 0;
dprintf("(enter)\n");
- if ((u->subdev < 0) ||
- (u->subdev > 1)) {
+ if (u->subdev < 0 || u->subdev > 1) {
dprintf("imsm: Error: Wrong subdev: %i\n", u->subdev);
return ret_val;
}
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;
dprintf("imsm: new disk for reshape is: %i:%i (%p, index = %i)\n",
major(u->new_disks[i]), minor(u->new_disks[i]),
new_disk, new_disk->index);
- if ((new_disk == NULL) ||
- ((new_disk->index >= 0) &&
- (new_disk->index < u->old_raid_disks)))
+ if (new_disk == NULL ||
+ (new_disk->index >= 0 &&
+ new_disk->index < u->old_raid_disks))
goto update_reshape_exit;
new_disk->index = disk_count++;
/* slot to fill in autolayout
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;
+ case update_rwh_policy: {
+ struct imsm_update_rwh_policy *u = (void *)update->buf;
+ int target = u->dev_idx;
+ struct imsm_dev *dev = get_imsm_dev(super, target);
+ if (!dev) {
+ dprintf("could not find subarray-%d\n", target);
+ break;
+ }
+
+ if (dev->rwh_policy != u->new_policy) {
+ dev->rwh_policy = u->new_policy;
+ super->updates_pending++;
+ }
+ break;
+ }
default:
pr_err("error: unsuported process update type:(type: %d)\n", type);
}
*/
enum imsm_update_type type;
struct intel_super *super = st->sb;
+ unsigned int sector_size = super->sector_size;
struct imsm_super *mpb = super->anchor;
size_t buf_len;
size_t len = 0;
current_level = map->raid_level;
break;
}
- if ((u->new_level == 5) && (u->new_level != current_level)) {
+ if (u->new_level == 5 && u->new_level != current_level) {
struct mdinfo *spares;
spares = get_spares_for_grow(st);
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;
+ case update_rwh_policy: {
+ if (update->len < (int)sizeof(struct imsm_update_rwh_policy))
+ return 0;
+ 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, 512);
+ buf_len = ROUND_UP(__le32_to_cpu(mpb->mpb_size) +
+ super->extra_space + len, sector_size);
if (super->next_buf)
free(super->next_buf);
super->next_len = buf_len;
- if (posix_memalign(&super->next_buf, 512, buf_len) == 0)
+ if (posix_memalign(&super->next_buf, sector_size, buf_len) == 0)
memset(super->next_buf, 0, buf_len);
else
super->next_buf = NULL;
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) {
__free_imsm_disk(dl);
}
}
-#endif /* MDASSEMBLE */
static void close_targets(int *targets, int new_disks)
{
continue;
}
- if ((sd->disk.raid_disk >= raid_disks) ||
- (sd->disk.raid_disk < 0))
+ if (sd->disk.raid_disk >= raid_disks || sd->disk.raid_disk < 0)
continue;
dn = map_dev(sd->disk.major,
/* check if maximum array degradation level is not exceeded
*/
if ((raid_disks - opened) >
- imsm_get_allowed_degradation(info->new_level,
- raid_disks,
- super, dev)) {
+ imsm_get_allowed_degradation(info->new_level, raid_disks,
+ super, dev)) {
pr_err("Not enough disks can be opened.\n");
close_targets(raid_fds, raid_disks);
return -2;
return 1;
}
- if ((orom != orom2) || ((hba->type == SYS_DEV_VMD) && (hba != hba2))) {
+ if (orom != orom2) {
pr_err("WARNING - IMSM container assembled with disks under different HBAs!\n"
" This operation is not supported and can lead to data loss.\n");
return 1;
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
int new_disks, i, err;
char *buf = NULL;
int retval = 1;
+ unsigned int sector_size = super->sector_size;
unsigned long curr_migr_unit = __le32_to_cpu(migr_rec->curr_migr_unit);
unsigned long num_migr_units = __le32_to_cpu(migr_rec->num_migr_units);
char buffer[20];
pba_of_lba0(map_dest)) * 512;
unit_len = __le32_to_cpu(migr_rec->dest_depth_per_unit) * 512;
- if (posix_memalign((void **)&buf, 512, unit_len) != 0)
+ if (posix_memalign((void **)&buf, sector_size, unit_len) != 0)
goto abort;
targets = xcalloc(new_disks, sizeof(int));
break;
}
- if ((info->array.level != 0) &&
- (info->array.level != 5)) {
+ if (info->array.level != 0 && info->array.level != 5) {
/* we cannot use this container with other raid level
*/
dprintf("imsm: for container operation wrong raid level (%i) detected\n",
previous_level = map->raid_level;
}
}
- if ((geo->level == 5) && (previous_level == 0)) {
+ if (geo->level == 5 && previous_level == 0) {
struct mdinfo *spares = NULL;
u->new_raid_disks++;
spares = get_spares_for_grow(st);
- if ((spares == NULL) || (spares->array.spare_disks < 1)) {
+ if (spares == NULL || spares->array.spare_disks < 1) {
free(u);
sysfs_free(spares);
update_memory_size = 0;
- dprintf("error: cannot get spare device for requested migration");
+ pr_err("cannot get spare device for requested migration\n");
return 0;
}
sysfs_free(spares);
int rv;
getinfo_super_imsm_volume(st, &info, NULL);
- if ((geo->level != info.array.level) &&
- (geo->level >= 0) &&
- (geo->level != UnSet)) {
+ if (geo->level != info.array.level && geo->level >= 0 &&
+ geo->level != UnSet) {
switch (info.array.level) {
case 0:
if (geo->level == 5) {
} else
geo->level = info.array.level;
- if ((geo->layout != info.array.layout)
- && ((geo->layout != UnSet) && (geo->layout != -1))) {
+ if (geo->layout != info.array.layout &&
+ (geo->layout != UnSet && geo->layout != -1)) {
change = CH_MIGRATION;
- if ((info.array.layout == 0)
- && (info.array.level == 5)
- && (geo->layout == 5)) {
+ if (info.array.layout == 0 && info.array.level == 5 &&
+ geo->layout == 5) {
/* reshape 5 -> 4 */
- } else if ((info.array.layout == 5)
- && (info.array.level == 5)
- && (geo->layout == 0)) {
+ } else if (info.array.layout == 5 && info.array.level == 5 &&
+ geo->layout == 0) {
/* reshape 4 -> 5 */
geo->layout = 0;
geo->level = 5;
imsm_layout = info.array.layout;
}
- if ((geo->chunksize > 0) && (geo->chunksize != UnSet)
- && (geo->chunksize != info.array.chunk_size))
+ if (geo->chunksize > 0 && geo->chunksize != UnSet &&
+ geo->chunksize != info.array.chunk_size) {
+ if (info.array.level == 10) {
+ pr_err("Error. Chunk size change for RAID 10 is not supported.\n");
+ change = -1;
+ goto analyse_change_exit;
+ } else if (info.component_size % (geo->chunksize/512)) {
+ pr_err("New chunk size (%dK) does not evenly divide device size (%lluk). Aborting...\n",
+ geo->chunksize/1024, info.component_size/2);
+ change = -1;
+ goto analyse_change_exit;
+ }
change = CH_MIGRATION;
- else
+ } else {
geo->chunksize = info.array.chunk_size;
+ }
chunk = geo->chunksize / 1024;
*/
current_size = info.custom_array_size / data_disks;
- if ((geo->size > 0) && (geo->size != MAX_SIZE)) {
+ if (geo->size > 0 && geo->size != MAX_SIZE) {
/* align component size
*/
geo->size = imsm_component_size_aligment_check(
get_imsm_raid_level(dev->vol.map),
- chunk * 1024,
+ chunk * 1024, super->sector_size,
geo->size * 2);
if (geo->size == 0) {
pr_err("Error. Size expansion is supported only (current size is %llu, requested size /rounded/ is 0).\n",
}
}
- if ((current_size != geo->size) && (geo->size > 0)) {
+ if (current_size != geo->size && geo->size > 0) {
if (change != -1) {
pr_err("Error. Size change should be the only one at a time.\n");
change = -1;
*/
max_size = imsm_component_size_aligment_check(
get_imsm_raid_level(dev->vol.map),
- chunk * 1024,
+ chunk * 1024, super->sector_size,
max_size);
}
if (geo->size == MAX_SIZE) {
geo->size = max_size;
}
- if ((direction == ROLLBACK_METADATA_CHANGES)) {
+ if (direction == ROLLBACK_METADATA_CHANGES) {
/* accept size for rollback only
*/
} else {
geo->raid_disks + devNumChange,
&chunk,
geo->size, INVALID_SECTORS,
- 0, 0, 1))
+ 0, 0, info.consistency_policy, 1))
change = -1;
if (check_devs) {
}
analyse_change_exit:
- if ((direction == ROLLBACK_METADATA_CHANGES) &&
- ((change == CH_MIGRATION) || (change == CH_TAKEOVER))) {
+ if (direction == ROLLBACK_METADATA_CHANGES &&
+ (change == CH_MIGRATION || change == CH_TAKEOVER)) {
dprintf("imsm: Metadata changes rollback is not supported for migration and takeover operations.\n");
change = -1;
}
int rv;
rv = sysfs_get_ll(info, NULL, "degraded", &new_degraded);
- if ((rv == -1) || (new_degraded != (unsigned long long)degraded)) {
+ if (rv == -1 || (new_degraded != (unsigned long long)degraded)) {
/* check each device to ensure it is still working */
struct mdinfo *sd;
new_degraded = 0;
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;
}
/* Only one volume can migrate at the same time */
if (migr_vol_qan != 1) {
- pr_err(": %s", migr_vol_qan ?
+ pr_err("%s", migr_vol_qan ?
"Number of migrating volumes greater than 1\n" :
"There is no volume during migrationg\n");
goto abort;
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)
+ if ((unsigned int)write(d->fd, super->migr_rec_buf,
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size)
perror("Write migr_rec failed");
}
}
return ret_val;
}
-#endif /* MDASSEMBLE */
-
struct superswitch super_imsm = {
-#ifndef MDASSEMBLE
.examine_super = examine_super_imsm,
.brief_examine_super = brief_examine_super_imsm,
.brief_examine_subarrays = brief_examine_subarrays_imsm,
.manage_reshape = imsm_manage_reshape,
.recover_backup = recover_backup_imsm,
.copy_metadata = copy_metadata_imsm,
-#endif
+ .examine_badblocks = examine_badblocks_imsm,
.match_home = match_home_imsm,
.uuid_from_super= uuid_from_super_imsm,
.getinfo_super = getinfo_super_imsm,
.container_content = container_content_imsm,
.validate_container = validate_container_imsm,
+ .write_init_ppl = write_init_ppl_imsm,
+ .validate_ppl = validate_ppl_imsm,
+
.external = 1,
.name = "imsm",
-#ifndef MDASSEMBLE
/* for mdmon */
.open_new = imsm_open_new,
.set_array_state= imsm_set_array_state,
.activate_spare = imsm_activate_spare,
.process_update = imsm_process_update,
.prepare_update = imsm_prepare_update,
-#endif /* MDASSEMBLE */
+ .record_bad_block = imsm_record_badblock,
+ .clear_bad_block = imsm_clear_badblock,
+ .get_bad_blocks = imsm_get_badblocks,
};
projects / thirdparty / mdadm.git / blobdiff