#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 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
}
}
-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 {
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;
[SYS_DEV_UNKNOWN] = "Unknown",
[SYS_DEV_SAS] = "SAS",
[SYS_DEV_SATA] = "SATA",
- [SYS_DEV_NVME] = "NVMe"
+ [SYS_DEV_NVME] = "NVMe",
+ [SYS_DEV_VMD] = "VMD"
};
const char *get_sys_dev_type(enum sys_dev_type type)
static struct intel_hba * find_intel_hba(struct intel_hba *hba, struct sys_dev *device)
{
- struct intel_hba *result=NULL;
+ struct intel_hba *result;
+
for (result = hba; result; result = result->next) {
if (result->type == device->type && strcmp(result->path, device->path) == 0)
break;
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)
{
static int is_gen_migration(struct imsm_dev *dev);
+#define IMSM_4K_DIV 8
+
#ifndef MDASSEMBLE
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)
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;
+
+ 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);
+ }
+ }
+
+ 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;
}
}
#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;
+
+ 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);
+ }
+ }
+
+ mpb->check_sum = __gen_imsm_checksum(mpb);
+}
+
/*******************************************************************************
* function: imsm_check_attributes
* Description: Function checks if features represented by attributes flags
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);
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 (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)
* this hba
*/
dir = opendir("/sys/dev/block");
- for (ent = dir ? readdir(dir) : NULL; ent; ent = readdir(dir)) {
+ if (!dir)
+ return 1;
+
+ for (ent = readdir(dir); ent; ent = readdir(dir)) {
int fd;
char model[64];
char vendor[64];
break;
}
sprintf(device, "/sys/dev/block/%d:%d/device/type", major, minor);
- if (load_sys(device, buf) != 0) {
+ if (load_sys(device, buf, sizeof(buf)) != 0) {
if (verbose > 0)
pr_err("failed to read device type for %s\n",
path);
vendor[0] = '\0';
model[0] = '\0';
sprintf(device, "/sys/dev/block/%d:%d/device/vendor", major, minor);
- if (load_sys(device, buf) == 0) {
+ if (load_sys(device, buf, sizeof(buf)) == 0) {
strncpy(vendor, buf, sizeof(vendor));
vendor[sizeof(vendor) - 1] = '\0';
c = (char *) &vendor[sizeof(vendor) - 1];
}
sprintf(device, "/sys/dev/block/%d:%d/device/model", major, minor);
- if (load_sys(device, buf) == 0) {
+ if (load_sys(device, buf, sizeof(buf)) == 0) {
strncpy(model, buf, sizeof(model));
model[sizeof(model) - 1] = '\0';
c = (char *) &model[sizeof(model) - 1];
return err;
}
+static int print_vmd_attached_devs(struct sys_dev *hba)
+{
+ struct dirent *ent;
+ DIR *dir;
+ char path[292];
+ char link[256];
+ char *c, *rp;
+
+ if (hba->type != SYS_DEV_VMD)
+ return 1;
+
+ /* scroll through /sys/dev/block looking for devices attached to
+ * this hba
+ */
+ dir = opendir("/sys/bus/pci/drivers/nvme");
+ if (!dir)
+ return 1;
+
+ for (ent = readdir(dir); ent; ent = readdir(dir)) {
+ int n;
+
+ /* is 'ent' a device? check that the 'subsystem' link exists and
+ * that its target matches 'bus'
+ */
+ sprintf(path, "/sys/bus/pci/drivers/nvme/%s/subsystem",
+ ent->d_name);
+ n = readlink(path, link, sizeof(link));
+ if (n < 0 || n >= (int)sizeof(link))
+ continue;
+ link[n] = '\0';
+ c = strrchr(link, '/');
+ if (!c)
+ continue;
+ if (strncmp("pci", c+1, strlen("pci")) != 0)
+ 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)
+ continue;
+
+ if (path_attached_to_hba(rp, hba->path)) {
+ printf(" NVMe under VMD : %s\n", rp);
+ }
+ free(rp);
+ }
+
+ closedir(dir);
+ return 0;
+}
+
static void print_found_intel_controllers(struct sys_dev *elem)
{
for (; elem; elem = elem->next) {
fprintf(stderr, "SAS ");
else if (elem->type == SYS_DEV_NVME)
fprintf(stderr, "NVMe ");
- fprintf(stderr, "RAID controller");
+
+ if (elem->type == SYS_DEV_VMD)
+ fprintf(stderr, "VMD domain");
+ else
+ fprintf(stderr, "RAID controller");
+
if (elem->pci_id)
fprintf(stderr, " at %s", elem->pci_id);
fprintf(stderr, ".\n");
if (controller_path && (compare_paths(hba->path, controller_path) != 0))
continue;
if (!find_imsm_capability(hba)) {
+ char buf[PATH_MAX];
pr_err("imsm capabilities not found for controller: %s (type %s)\n",
- hba->path, get_sys_dev_type(hba->type));
+ hba->type == SYS_DEV_VMD ? vmd_domain_to_controller(hba, buf) : hba->path,
+ get_sys_dev_type(hba->type));
continue;
}
result = 0;
const struct orom_entry *entry;
for (entry = orom_entries; entry; entry = entry->next) {
- print_imsm_capability(&entry->orom);
+ if (entry->type == SYS_DEV_VMD) {
+ print_imsm_capability(&entry->orom);
+ for (hba = list; hba; hba = hba->next) {
+ if (hba->type == SYS_DEV_VMD) {
+ char buf[PATH_MAX];
+ 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)) {
+ if (verbose > 0)
+ pr_err("failed to get devices attached to VMD domain.\n");
+ result |= 2;
+ }
+ }
+ }
+ printf("\n");
+ continue;
+ }
- if (imsm_orom_is_nvme(&entry->orom)) {
+ print_imsm_capability(&entry->orom);
+ if (entry->type == SYS_DEV_NVME) {
for (hba = list; hba; hba = hba->next) {
if (hba->type == SYS_DEV_NVME)
printf(" NVMe Device : %s\n", hba->path);
}
+ printf("\n");
continue;
}
for (hba = list; hba; hba = hba->next) {
if (controller_path && (compare_paths(hba->path,controller_path) != 0))
continue;
- if (!find_imsm_capability(hba) && verbose > 0)
- pr_err("IMSM_DETAIL_PLATFORM_ERROR=NO_IMSM_CAPABLE_DEVICE_UNDER_%s\n", hba->path);
+ if (!find_imsm_capability(hba) && verbose > 0) {
+ char buf[PATH_MAX];
+ pr_err("IMSM_DETAIL_PLATFORM_ERROR=NO_IMSM_CAPABLE_DEVICE_UNDER_%s\n",
+ hba->type == SYS_DEV_VMD ? vmd_domain_to_controller(hba, buf) : hba->path);
+ }
else
result = 0;
}
const struct orom_entry *entry;
- for (entry = orom_entries; entry; entry = entry->next)
+ for (entry = orom_entries; entry; entry = entry->next) {
+ if (entry->type == SYS_DEV_VMD) {
+ for (hba = list; hba; hba = hba->next)
+ print_imsm_capability_export(&entry->orom);
+ continue;
+ }
print_imsm_capability_export(&entry->orom);
+ }
return result;
}
static int read_imsm_migr_rec(int fd, struct intel_super *super)
{
int ret_val = -1;
+ unsigned int sector_size = super->sector_size;
unsigned long long dsize;
get_dev_size(fd, NULL, &dsize);
- if (lseek64(fd, dsize - MIGR_REC_POSITION, SEEK_SET) < 0) {
+ if (lseek64(fd, dsize - (sector_size*MIGR_REC_SECTOR_POSITION),
+ SEEK_SET) < 0) {
pr_err("Cannot seek to anchor block: %s\n",
strerror(errno));
goto out;
}
- if (read(fd, super->migr_rec_buf, MIGR_REC_BUF_SIZE) !=
- MIGR_REC_BUF_SIZE) {
+ if (read(fd, super->migr_rec_buf,
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size) {
pr_err("Cannot read migr record block: %s\n",
strerror(errno));
goto out;
}
ret_val = 0;
+ if (sector_size == 4096)
+ convert_from_4k_imsm_migr_rec(super);
out:
return ret_val;
static int load_imsm_migr_rec(struct intel_super *super, struct mdinfo *info)
{
struct mdinfo *sd;
- struct dl *dl = NULL;
+ struct dl *dl;
char nm[30];
int retval = -1;
int fd = -1;
struct imsm_dev *dev;
- struct imsm_map *map = NULL;
+ struct imsm_map *map;
int slot = -1;
/* find map under migration */
*/
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);
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;
int len;
struct imsm_update_general_migration_checkpoint *u;
struct imsm_dev *dev;
- struct imsm_map *map = NULL;
+ struct imsm_map *map;
/* find map under migration */
dev = imsm_get_device_during_migration(super);
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 (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;
}
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,
}
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);
memset(info->uuid, 0, sizeof(info->uuid));
* for each disk in array */
struct mdinfo *getinfo_super_disks_imsm(struct supertype *st)
{
- struct mdinfo *mddev = NULL;
+ struct mdinfo *mddev;
struct intel_super *super = st->sb;
struct imsm_disk *disk;
int count = 0;
}
}
+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(scsi_serial, 0, sizeof(scsi_serial));
+ memset(buf, 0, sizeof(buf));
- rv = scsi_get_serial(fd, scsi_serial, sizeof(scsi_serial));
+ rv = nvme_get_serial(fd, buf, sizeof(buf));
+
+ 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) {
/* 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)
*/
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);
{
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 (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));
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;
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;
if (devname) {
struct intel_hba *hba = super->hba;
- pr_err("%s is attached to Intel(R) %s RAID controller (%s),\n"
- " but the container is assigned to Intel(R) %s RAID controller (",
+ pr_err("%s is attached to Intel(R) %s %s (%s),\n"
+ " but the container is assigned to Intel(R) %s %s (",
devname,
get_sys_dev_type(hba_name->type),
+ hba_name->type == SYS_DEV_VMD ? "domain" : "RAID controller",
hba_name->pci_id ? : "Err!",
- get_sys_dev_type(super->hba->type));
+ get_sys_dev_type(super->hba->type),
+ hba->type == SYS_DEV_VMD ? "domain" : "RAID controller");
while (hba) {
fprintf(stderr, "%s", hba->pci_id ? : "Err!");
hba = hba->next;
}
fprintf(stderr, ").\n"
- " Mixing devices attached to different controllers is not allowed.\n");
+ " Mixing devices attached to different %s is not allowed.\n",
+ hba_name->type == SYS_DEV_VMD ? "VMD domains" : "controllers");
}
return 2;
}
}
/* 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);
static int get_super_block(struct intel_super **super_list, char *devnm, char *devname,
int major, int minor, int keep_fd)
{
- struct intel_super*s = NULL;
+ struct intel_super *s;
char nm[32];
int dfd = -1;
int err = 0;
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);
if (dfd >= 0)
close(dfd);
}
- if ((dfd >= 0) && (!keep_fd))
+ if (dfd >= 0 && !keep_fd)
close(dfd);
return err;
free_super_imsm(st);
super = alloc_super();
+ get_dev_sector_size(fd, NULL, &super->sector_size);
/* 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);
/* retry the load if we might have raced against mdmon */
if (rv == 3) {
- struct mdstat_ent *mdstat = mdstat_by_component(fd2devnm(fd));
+ struct mdstat_ent *mdstat = NULL;
+ char *name = fd2kname(fd);
+
+ if (name)
+ mdstat = mdstat_by_component(name);
if (mdstat && mdmon_running(mdstat->devnm) && getpid() != mdmon_pid(mdstat->devnm)) {
for (retry = 0; retry < 3; retry++) {
* 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;
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);
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) {
+ if (super &&
+ posix_memalign(&super->buf, MAX_SECTOR_SIZE, mpb_size) != 0) {
free(super);
super = NULL;
}
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);
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;
+ }
+ }
+ }
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) {
+ memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SECTORS*super->sector_size);
+ if (lseek64(fd, size - MIGR_REC_SECTOR_POSITION*super->sector_size,
+ SEEK_SET) >= 0) {
if (write(fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ MIGR_REC_BUF_SECTORS*super->sector_size) !=
+ MIGR_REC_BUF_SECTORS*super->sector_size)
perror("Write migr_rec failed");
}
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;
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 (lseek64(d->fd, dsize - sector_size,
+ SEEK_SET) >= 0) {
if (write(d->fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size)
perror("Write migr_rec failed");
}
}
return 1;
#ifndef MDASSEMBLE
+ if (super->sector_size == 4096)
+ convert_to_4k(super);
return store_imsm_mpb(fd, mpb);
#else
return 1;
{
int fd;
unsigned long long ldsize;
- struct intel_super *super=NULL;
+ struct intel_super *super;
int rv = 0;
if (level != LEVEL_CONTAINER)
* note that there is no fd for the disks in array.
*/
super = alloc_super();
+ 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
int dpa, int verbose)
{
struct mdstat_ent *mdstat = mdstat_read(0, 0);
- struct mdstat_ent *memb = NULL;
+ struct mdstat_ent *memb;
int count = 0;
int num = 0;
- struct md_list *dv = NULL;
+ struct md_list *dv;
int found;
for (memb = mdstat ; memb ; memb = memb->next) {
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++;
{
int i;
struct md_list *devlist = NULL;
- struct md_list *dv = NULL;
+ struct md_list *dv;
for(i = 0; i < 12; i++) {
dv = xcalloc(1, sizeof(*dv));
get_devices(const char *hba_path)
{
struct md_list *devlist = NULL;
- struct md_list *dv = NULL;
+ struct md_list *dv;
struct dirent *ent;
DIR *dir;
int err = 0;
{
struct md_list *tmpdev;
int count = 0;
- struct supertype *st = NULL;
+ struct supertype *st;
/* first walk the list of devices to find a consistent set
* that match the criterea, if that is possible.
*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;
devid_list = entry->devid_list;
for (dv = devid_list; dv; dv = dv->next) {
-
- struct md_list *devlist = NULL;
+ struct md_list *devlist;
struct sys_dev *device = device_by_id(dv->devid);
char *hba_path;
int found = 0;
{
/* 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;
}
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;
}
info_d->events = __le32_to_cpu(mpb->generation_num);
info_d->data_offset = pba_of_lba0(map);
- info_d->component_size = blocks_per_member(map);
+
+ if (map->raid_level == 5) {
+ info_d->component_size =
+ num_data_stripes(map) *
+ map->blocks_per_strip;
+ } else {
+ info_d->component_size = blocks_per_member(map);
+ }
}
/* now that the disk list is up-to-date fixup recovery_start */
update_recovery_start(super, dev, 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);
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;
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);
}
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 (write(fd, buf, sector_size) != sector_size)
return 1;
return 0;
IMSM_T_STATE_DEGRADED)
return NULL;
+ if (get_imsm_map(dev, MAP_0)->map_state == IMSM_T_STATE_UNINITIALIZED) {
+ dprintf("imsm: No spare activation allowed. Volume is not initialized.\n");
+ return NULL;
+ }
+
/*
* If there are any failed disks check state of the other volume.
* Block rebuild if the another one is failed until failed disks
static struct dl *get_disk_super(struct intel_super *super, int major, int minor)
{
- struct dl *dl = NULL;
+ 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;
}
static int remove_disk_super(struct intel_super *super, int major, int minor)
{
- struct dl *prev = NULL;
+ struct dl *prev;
struct dl *dl;
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;
static int add_remove_disk_update(struct intel_super *super)
{
int check_degraded = 0;
- struct dl *disk = NULL;
+ struct dl *disk;
+
/* add/remove some spares to/from the metadata/contrainer */
while (super->disk_mgmt_list) {
struct dl *disk_cfg;
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))
*/
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);
* 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) + 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;
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;
{
int rv = -1;
struct intel_super *super = st->sb;
- unsigned long long *target_offsets = NULL;
- int *targets = NULL;
+ unsigned long long *target_offsets;
+ int *targets;
int i;
struct imsm_map *map_dest = get_imsm_map(dev, MAP_0);
int new_disks = map_dest->num_members;
{
struct intel_super *super = st->sb;
struct migr_record *migr_rec = super->migr_rec;
- struct imsm_map *map_dest = NULL;
+ struct imsm_map *map_dest;
struct intel_dev *id = NULL;
unsigned long long read_offset;
unsigned long long write_offset;
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));
strncat(disk_path, path, PATH_MAX - strlen(disk_path) - 1);
if (stat(disk_path, &st) == 0) {
struct sys_dev* hba;
- char *path=NULL;
+ char *path;
path = devt_to_devpath(st.st_rdev);
if (path == NULL)
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",
{
struct intel_super *super = st->sb;
struct imsm_super *mpb = super->anchor;
- int update_memory_size = 0;
- struct imsm_update_reshape *u = NULL;
- struct mdinfo *spares = NULL;
+ int update_memory_size;
+ struct imsm_update_reshape *u;
+ struct mdinfo *spares;
int i;
- int delta_disks = 0;
+ int delta_disks;
struct mdinfo *dev;
dprintf("(enter) raid_disks = %i\n", geo->raid_disks);
struct imsm_update_size_change **updatep)
{
struct intel_super *super = st->sb;
- int update_memory_size = 0;
- struct imsm_update_size_change *u = NULL;
+ int update_memory_size;
+ struct imsm_update_size_change *u;
dprintf("(enter) New size = %llu\n", geo->size);
struct imsm_update_reshape_migration **updatep)
{
struct intel_super *super = st->sb;
- int update_memory_size = 0;
- struct imsm_update_reshape_migration *u = NULL;
+ int update_memory_size;
+ struct imsm_update_reshape_migration *u;
struct imsm_dev *dev;
int previous_level = -1;
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;
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;
+ }
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 {
}
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;
}
return ret_val;
}
+#define COMPLETED_OK 0
+#define COMPLETED_NONE 1
+#define COMPLETED_DELAYED 2
+
+static int read_completed(int fd, unsigned long long *val)
+{
+ int ret;
+ char buf[50];
+
+ ret = sysfs_fd_get_str(fd, buf, 50);
+ if (ret < 0)
+ return ret;
+
+ ret = COMPLETED_OK;
+ if (strncmp(buf, "none", 4) == 0) {
+ ret = COMPLETED_NONE;
+ } else if (strncmp(buf, "delayed", 7) == 0) {
+ ret = COMPLETED_DELAYED;
+ } else {
+ char *ep;
+ *val = strtoull(buf, &ep, 0);
+ if (ep == buf || (*ep != 0 && *ep != '\n' && *ep != ' '))
+ ret = -1;
+ }
+ return ret;
+}
+
/*******************************************************************************
* Function: wait_for_reshape_imsm
* Description: Function writes new sync_max value and waits until
int wait_for_reshape_imsm(struct mdinfo *sra, int ndata)
{
int fd = sysfs_get_fd(sra, NULL, "sync_completed");
+ int retry = 3;
unsigned long long completed;
/* to_complete : new sync_max position */
unsigned long long to_complete = sra->reshape_progress;
return 1;
}
- if (sysfs_fd_get_ll(fd, &completed) < 0) {
- dprintf("cannot read reshape_position (no reshape in progres)\n");
- close(fd);
- return 0;
- }
+ do {
+ if (sysfs_fd_get_ll(fd, &completed) < 0) {
+ if (!retry) {
+ dprintf("cannot read reshape_position (no reshape in progres)\n");
+ close(fd);
+ return 1;
+ }
+ usleep(30000);
+ } else
+ break;
+ } while (retry--);
if (completed > position_to_set) {
dprintf("wrong next position to set %llu (%llu)\n",
}
do {
+ int rc;
char action[20];
- sysfs_wait(fd, NULL);
+ int timeout = 3000;
+
+ sysfs_wait(fd, &timeout);
if (sysfs_get_str(sra, NULL, "sync_action",
action, 20) > 0 &&
- strncmp(action, "reshape", 7) != 0)
- break;
- if (sysfs_fd_get_ll(fd, &completed) < 0) {
+ strncmp(action, "reshape", 7) != 0) {
+ if (strncmp(action, "idle", 4) == 0)
+ break;
+ close(fd);
+ return -1;
+ }
+
+ rc = read_completed(fd, &completed);
+ if (rc < 0) {
dprintf("cannot read reshape_position (in loop)\n");
close(fd);
return 1;
- }
+ } else if (rc == COMPLETED_NONE)
+ break;
} while (completed < position_to_set);
+
close(fd);
return 0;
-
}
/*******************************************************************************
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 */
* Function: imsm_manage_reshape
* Description: Function finds array under reshape and it manages reshape
* process. It creates stripes backups (if required) and sets
- * checheckpoits.
+ * checkpoints.
* Parameters:
* afd : Backup handle (nattive) - not used
* sra : general array info
{
int ret_val = 0;
struct intel_super *super = st->sb;
- struct intel_dev *dv = NULL;
+ 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;
int degraded = 0;
int source_layout = 0;
- if (!fds || !offsets || !sra)
+ if (!sra)
+ return ret_val;
+
+ if (!fds || !offsets)
goto abort;
/* Find volume during the reshape */
}
/* 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;
}
start = current_position * 512;
- /* allign reading start to old geometry */
+ /* align reading start to old geometry */
start_buf_shift = start % old_data_stripe_length;
start_src = start - start_buf_shift;
* to backup alligned to source array
* [bytes]
*/
- unsigned long long next_step_filler = 0;
+ unsigned long long next_step_filler;
unsigned long long copy_length = next_step * 512;
/* allign copy area length to stripe in old geometry */
sra->reshape_progress = next_step;
/* wait until reshape finish */
- if (wait_for_reshape_imsm(sra, ndata) < 0) {
+ if (wait_for_reshape_imsm(sra, ndata)) {
dprintf("wait_for_reshape_imsm returned error!\n");
goto abort;
}
/* clear migr_rec on disks after successful migration */
struct dl *d;
- memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SIZE);
+ memset(super->migr_rec_buf, 0, MIGR_REC_BUF_SECTORS*sector_size);
for (d = super->disks; d; d = d->next) {
if (d->index < 0 || is_failed(&d->disk))
continue;
unsigned long long dsize;
get_dev_size(d->fd, NULL, &dsize);
- if (lseek64(d->fd, dsize - MIGR_REC_POSITION,
+ if (lseek64(d->fd, dsize - MIGR_REC_SECTOR_POSITION*sector_size,
SEEK_SET) >= 0) {
if (write(d->fd, super->migr_rec_buf,
- MIGR_REC_BUF_SIZE) != MIGR_REC_BUF_SIZE)
+ MIGR_REC_BUF_SECTORS*sector_size) !=
+ MIGR_REC_BUF_SECTORS*sector_size)
perror("Write migr_rec failed");
}
}
ret_val = 1;
abort:
free(buf);
- abort_reshape(sra);
+ /* See Grow.c: abort_reshape() for further explanation */
+ sysfs_set_num(sra, NULL, "suspend_lo", 0x7FFFFFFFFFFFFFFFULL);
+ sysfs_set_num(sra, NULL, "suspend_hi", 0);
+ sysfs_set_num(sra, NULL, "suspend_lo", 0);
return ret_val;
}
projects / thirdparty / mdadm.git / blobdiff