*/
static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
static atomic_t md_event_count;
-static void md_new_event(mddev_t *mddev)
+void md_new_event(mddev_t *mddev)
{
atomic_inc(&md_event_count);
wake_up(&md_event_waiters);
}
+EXPORT_SYMBOL_GPL(md_new_event);
/*
* Enables to iterate over all existing md arrays
return;
if (!mddev->raid_disks && list_empty(&mddev->disks)) {
list_del(&mddev->all_mddevs);
- blk_put_queue(mddev->queue);
+ /* that blocks */
+ blk_cleanup_queue(mddev->queue);
+ /* that also blocks */
kobject_unregister(&mddev->kobj);
+ /* result blows... */
}
spin_unlock(&all_mddevs_lock);
}
kfree(new);
return NULL;
}
+ set_bit(QUEUE_FLAG_CLUSTER, &new->queue->queue_flags);
blk_queue_make_request(new->queue, md_fail_request);
}
if (sb->major_version != 0 ||
- sb->minor_version != 90) {
+ sb->minor_version < 90 ||
+ sb->minor_version > 91) {
printk(KERN_WARNING "Bad version number %d.%d on %s\n",
sb->major_version, sb->minor_version,
b);
mddev->bitmap_offset = 0;
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
+ if (mddev->minor_version >= 91) {
+ mddev->reshape_position = sb->reshape_position;
+ mddev->delta_disks = sb->delta_disks;
+ mddev->new_level = sb->new_level;
+ mddev->new_layout = sb->new_layout;
+ mddev->new_chunk = sb->new_chunk;
+ } else {
+ mddev->reshape_position = MaxSector;
+ mddev->delta_disks = 0;
+ mddev->new_level = mddev->level;
+ mddev->new_layout = mddev->layout;
+ mddev->new_chunk = mddev->chunk_size;
+ }
+
if (sb->state & (1<<MD_SB_CLEAN))
mddev->recovery_cp = MaxSector;
else {
if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
mddev->bitmap_file == NULL) {
- if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6
+ if (mddev->level != 1 && mddev->level != 4
+ && mddev->level != 5 && mddev->level != 6
&& mddev->level != 10) {
/* FIXME use a better test */
printk(KERN_WARNING "md: bitmaps not supported for this level.\n");
sb->md_magic = MD_SB_MAGIC;
sb->major_version = mddev->major_version;
- sb->minor_version = mddev->minor_version;
sb->patch_version = mddev->patch_version;
sb->gvalid_words = 0; /* ignored */
memcpy(&sb->set_uuid0, mddev->uuid+0, 4);
sb->events_hi = (mddev->events>>32);
sb->events_lo = (u32)mddev->events;
+ if (mddev->reshape_position == MaxSector)
+ sb->minor_version = 90;
+ else {
+ sb->minor_version = 91;
+ sb->reshape_position = mddev->reshape_position;
+ sb->new_level = mddev->new_level;
+ sb->delta_disks = mddev->delta_disks;
+ sb->new_layout = mddev->new_layout;
+ sb->new_chunk = mddev->new_chunk;
+ }
+ mddev->minor_version = sb->minor_version;
if (mddev->in_sync)
{
sb->recovery_cp = mddev->recovery_cp;
d->raid_disk = rdev2->raid_disk;
else
d->raid_disk = rdev2->desc_nr; /* compatibility */
- if (test_bit(Faulty, &rdev2->flags)) {
+ if (test_bit(Faulty, &rdev2->flags))
d->state = (1<<MD_DISK_FAULTY);
- failed++;
- } else if (test_bit(In_sync, &rdev2->flags)) {
+ else if (test_bit(In_sync, &rdev2->flags)) {
d->state = (1<<MD_DISK_ACTIVE);
d->state |= (1<<MD_DISK_SYNC);
active++;
rdev-> sb_size = (rdev->sb_size | bmask)+1;
if (refdev == 0)
- return 1;
+ ret = 1;
else {
__u64 ev1, ev2;
struct mdp_superblock_1 *refsb =
ev2 = le64_to_cpu(refsb->events);
if (ev1 > ev2)
- return 1;
+ ret = 1;
+ else
+ ret = 0;
}
if (minor_version)
rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
if (le32_to_cpu(sb->size) > rdev->size*2)
return -EINVAL;
- return 0;
+ return ret;
}
static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->size = le64_to_cpu(sb->size)/2;
mddev->events = le64_to_cpu(sb->events);
mddev->bitmap_offset = 0;
- mddev->default_bitmap_offset = 1024;
+ mddev->default_bitmap_offset = 1024 >> 9;
mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
memcpy(mddev->uuid, sb->set_uuid, 16);
}
mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);
}
+ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
+ mddev->reshape_position = le64_to_cpu(sb->reshape_position);
+ mddev->delta_disks = le32_to_cpu(sb->delta_disks);
+ mddev->new_level = le32_to_cpu(sb->new_level);
+ mddev->new_layout = le32_to_cpu(sb->new_layout);
+ mddev->new_chunk = le32_to_cpu(sb->new_chunk)<<9;
+ } else {
+ mddev->reshape_position = MaxSector;
+ mddev->delta_disks = 0;
+ mddev->new_level = mddev->level;
+ mddev->new_layout = mddev->layout;
+ mddev->new_chunk = mddev->chunk_size;
+ }
+
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling */
__u64 ev1 = le64_to_cpu(sb->events);
sb->cnt_corrected_read = atomic_read(&rdev->corrected_errors);
sb->raid_disks = cpu_to_le32(mddev->raid_disks);
- sb->size = cpu_to_le64(mddev->size);
+ sb->size = cpu_to_le64(mddev->size<<1);
if (mddev->bitmap && mddev->bitmap_file == NULL) {
sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
}
+ if (mddev->reshape_position != MaxSector) {
+ sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
+ sb->reshape_position = cpu_to_le64(mddev->reshape_position);
+ sb->new_layout = cpu_to_le32(mddev->new_layout);
+ sb->delta_disks = cpu_to_le32(mddev->delta_disks);
+ sb->new_level = cpu_to_le32(mddev->new_level);
+ sb->new_chunk = cpu_to_le32(mddev->new_chunk>>9);
+ }
max_dev = 0;
ITERATE_RDEV(mddev,rdev2,tmp)
else
ko = &rdev->bdev->bd_disk->kobj;
sysfs_create_link(&rdev->kobj, ko, "block");
+ bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk);
return 0;
}
MD_BUG();
return;
}
+ bd_release_from_disk(rdev->bdev, rdev->mddev->gendisk);
list_del_init(&rdev->same_set);
printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
rdev->mddev = NULL;
}
}
-static void md_update_sb(mddev_t * mddev)
+void md_update_sb(mddev_t * mddev)
{
int err;
struct list_head *tmp;
wake_up(&mddev->sb_wait);
}
+EXPORT_SYMBOL_GPL(md_update_sb);
/* words written to sysfs files may, or my not, be \n terminated.
* We want to accept with case. For this we use cmd_match.
char *type = "idle";
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) {
- if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ type = "reshape";
+ else if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
type = "resync";
else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
mddev->level = pers->level;
strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+ if (mddev->reshape_position != MaxSector &&
+ pers->start_reshape == NULL) {
+ /* This personality cannot handle reshaping... */
+ mddev->pers = NULL;
+ module_put(pers->owner);
+ return -EINVAL;
+ }
+
mddev->recovery = 0;
mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */
mddev->barriers_work = 1;
*/
static void autorun_devices(int part)
{
- struct list_head candidates;
struct list_head *tmp;
mdk_rdev_t *rdev0, *rdev;
mddev_t *mddev;
printk(KERN_INFO "md: autorun ...\n");
while (!list_empty(&pending_raid_disks)) {
dev_t dev;
+ LIST_HEAD(candidates);
rdev0 = list_entry(pending_raid_disks.next,
mdk_rdev_t, same_set);
info.ctime = mddev->ctime;
info.level = mddev->level;
info.size = mddev->size;
+ if (info.size != mddev->size) /* overflow */
+ info.size = -1;
info.nr_disks = nr;
info.raid_disks = mddev->raid_disks;
info.md_minor = mddev->md_minor;
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
mddev->bitmap_offset = 0;
+ mddev->reshape_position = MaxSector;
+
/*
* Generate a 128 bit UUID
*/
get_random_bytes(mddev->uuid, 16);
+ mddev->new_level = mddev->level;
+ mddev->new_chunk = mddev->chunk_size;
+ mddev->new_layout = mddev->layout;
+ mddev->delta_disks = 0;
+
return 0;
}
{
int rv;
/* change the number of raid disks */
- if (mddev->pers->reshape == NULL)
+ if (mddev->pers->check_reshape == NULL)
return -EINVAL;
if (raid_disks <= 0 ||
raid_disks >= mddev->max_disks)
return -EINVAL;
- if (mddev->sync_thread)
+ if (mddev->sync_thread || mddev->reshape_position != MaxSector)
return -EBUSY;
- rv = mddev->pers->reshape(mddev, raid_disks);
+ mddev->delta_disks = raid_disks - mddev->raid_disks;
+
+ rv = mddev->pers->check_reshape(mddev);
return rv;
}
)
return -EINVAL;
/* Check there is only one change */
- if (mddev->size != info->size) cnt++;
+ if (info->size >= 0 && mddev->size != info->size) cnt++;
if (mddev->raid_disks != info->raid_disks) cnt++;
if (mddev->layout != info->layout) cnt++;
if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) cnt++;
else
return mddev->pers->reconfig(mddev, info->layout, -1);
}
- if (mddev->size != info->size)
+ if (info->size >= 0 && mddev->size != info->size)
rv = update_size(mddev, info->size);
if (mddev->raid_disks != info->raid_disks)
static void status_resync(struct seq_file *seq, mddev_t * mddev)
{
- unsigned long max_blocks, resync, res, dt, db, rt;
+ sector_t max_blocks, resync, res;
+ unsigned long dt, db, rt;
+ int scale;
+ unsigned int per_milli;
resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active))/2;
MD_BUG();
return;
}
- res = (resync/1024)*1000/(max_blocks/1024 + 1);
+ /* Pick 'scale' such that (resync>>scale)*1000 will fit
+ * in a sector_t, and (max_blocks>>scale) will fit in a
+ * u32, as those are the requirements for sector_div.
+ * Thus 'scale' must be at least 10
+ */
+ scale = 10;
+ if (sizeof(sector_t) > sizeof(unsigned long)) {
+ while ( max_blocks/2 > (1ULL<<(scale+32)))
+ scale++;
+ }
+ res = (resync>>scale)*1000;
+ sector_div(res, (u32)((max_blocks>>scale)+1));
+
+ per_milli = res;
{
- int i, x = res/50, y = 20-x;
+ int i, x = per_milli/50, y = 20-x;
seq_printf(seq, "[");
for (i = 0; i < x; i++)
seq_printf(seq, "=");
seq_printf(seq, ".");
seq_printf(seq, "] ");
}
- seq_printf(seq, " %s =%3lu.%lu%% (%lu/%lu)",
+ seq_printf(seq, " %s =%3u.%u%% (%llu/%llu)",
+ (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)?
+ "reshape" :
(test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?
- "resync" : "recovery"),
- res/10, res % 10, resync, max_blocks);
+ "resync" : "recovery")),
+ per_milli/10, per_milli % 10,
+ (unsigned long long) resync,
+ (unsigned long long) max_blocks);
/*
* We do not want to overflow, so the order of operands and
dt = ((jiffies - mddev->resync_mark) / HZ);
if (!dt) dt++;
db = resync - (mddev->resync_mark_cnt/2);
- rt = (dt * ((max_blocks-resync) / (db/100+1)))/100;
+ rt = (dt * ((unsigned long)(max_blocks-resync) / (db/100+1)))/100;
seq_printf(seq, " finish=%lu.%lumin", rt / 60, (rt % 60)/6);
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
-static void md_do_sync(mddev_t *mddev)
+void md_do_sync(mddev_t *mddev)
{
mddev_t *mddev2;
unsigned int currspeed = 0,
*/
max_sectors = mddev->resync_max_sectors;
mddev->resync_mismatches = 0;
- } else
+ } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ max_sectors = mddev->size << 1;
+ else
/* recovery follows the physical size of devices */
max_sectors = mddev->size << 1;
mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
+ test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
+ !test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 2 &&
mddev->curr_resync >= mddev->recovery_cp) {
if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
md_wakeup_thread(mddev->thread);
}
+EXPORT_SYMBOL_GPL(md_do_sync);
/*
projects / mirror_ubuntu-bionic-kernel.git / blobdiff