struct list_head *list = &temp_inactive_list[size - 1];
/*
- * We don't hold any lock here yet, get_active_stripe() might
+ * We don't hold any lock here yet, raid5_get_active_stripe() might
* remove stripes from the list
*/
if (!list_empty_careful(list)) {
return count;
}
-static void release_stripe(struct stripe_head *sh)
+void raid5_release_stripe(struct stripe_head *sh)
{
struct r5conf *conf = sh->raid_conf;
unsigned long flags;
return 0;
}
-static struct stripe_head *
-get_active_stripe(struct r5conf *conf, sector_t sector,
- int previous, int noblock, int noquiesce)
+struct stripe_head *
+raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
+ int previous, int noblock, int noquiesce)
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(sector);
/* Only freshly new full stripe normal write stripe can be added to a batch list */
static bool stripe_can_batch(struct stripe_head *sh)
{
+ struct r5conf *conf = sh->raid_conf;
+
+ if (conf->log)
+ return false;
return test_bit(STRIPE_BATCH_READY, &sh->state) &&
!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
is_full_stripe_write(sh);
unlock_out:
unlock_two_stripes(head, sh);
out:
- release_stripe(head);
+ raid5_release_stripe(head);
}
/* Determine if 'data_offset' or 'new_data_offset' should be used
might_sleep();
+ if (r5l_write_stripe(conf->log, sh) == 0)
+ return;
for (i = disks; i--; ) {
int rw;
int replace_only = 0;
return_io(&return_bi);
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
static void ops_run_biofill(struct stripe_head *sh)
if (sh->check_state == check_state_compute_run)
sh->check_state = check_state_compute_result;
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
/* return a pointer to the address conversion region of the scribble buffer */
}
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
static void
sh->check_state = check_state_check_result;
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
/* we just created an active stripe so... */
atomic_inc(&conf->active_stripes);
- release_stripe(sh);
+ raid5_release_stripe(sh);
conf->max_nr_stripes++;
return 1;
}
if (!p)
err = -ENOMEM;
}
- release_stripe(nsh);
+ raid5_release_stripe(nsh);
}
/* critical section pass, GFP_NOIO no longer needed */
rdev_dec_pending(rdev, conf->mddev);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
static void raid5_end_write_request(struct bio *bi)
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
if (sh->batch_head && sh != sh->batch_head)
- release_stripe(sh->batch_head);
+ raid5_release_stripe(sh->batch_head);
}
-static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
-
static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
struct r5dev *dev = &sh->dev[i];
dev->rreq.bi_private = sh;
dev->flags = 0;
- dev->sector = compute_blocknr(sh, i, previous);
+ dev->sector = raid5_compute_blocknr(sh, i, previous);
}
static void error(struct mddev *mddev, struct md_rdev *rdev)
* Input: a 'big' sector number,
* Output: index of the data and parity disk, and the sector # in them.
*/
-static sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
- int previous, int *dd_idx,
- struct stripe_head *sh)
+sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
+ int previous, int *dd_idx,
+ struct stripe_head *sh)
{
sector_t stripe, stripe2;
sector_t chunk_number;
return new_sector;
}
-static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
+sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous)
{
struct r5conf *conf = sh->raid_conf;
int raid_disks = sh->disks;
if (bi)
bitmap_end = 1;
+ r5l_stripe_write_finished(sh);
+
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
* the data has not reached the cache yet.
*/
if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
+ s->failed > conf->max_degraded &&
(!test_bit(R5_Insync, &sh->dev[i].flags) ||
test_bit(R5_ReadError, &sh->dev[i].flags))) {
spin_lock_irq(&sh->stripe_lock);
WARN_ON(test_bit(R5_SkipCopy, &dev->flags));
WARN_ON(dev->page != dev->orig_page);
}
+
+ r5l_stripe_write_finished(sh);
+
if (!discard_pending &&
test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
int hash;
struct stripe_head *sh2;
struct async_submit_ctl submit;
- sector_t bn = compute_blocknr(sh, i, 1);
+ sector_t bn = raid5_compute_blocknr(sh, i, 1);
sector_t s = raid5_compute_sector(conf, bn, 0,
&dd_idx, NULL);
- sh2 = get_active_stripe(conf, s, 0, 1, 1);
+ sh2 = raid5_get_active_stripe(conf, s, 0, 1, 1);
if (sh2 == NULL)
/* so far only the early blocks of this stripe
* have been requested. When later blocks
if (!test_bit(STRIPE_EXPANDING, &sh2->state) ||
test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) {
/* must have already done this block */
- release_stripe(sh2);
+ raid5_release_stripe(sh2);
continue;
}
set_bit(STRIPE_EXPAND_READY, &sh2->state);
set_bit(STRIPE_HANDLE, &sh2->state);
}
- release_stripe(sh2);
+ raid5_release_stripe(sh2);
}
/* done submitting copies, wait for them to complete */
s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state) && !sh->batch_head;
s->failed_num[0] = -1;
s->failed_num[1] = -1;
+ s->log_failed = r5l_log_disk_error(conf);
/* Now to look around and see what can be done */
rcu_read_lock();
if (handle_flags == 0 ||
sh->state & handle_flags)
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
spin_lock_irq(&head_sh->stripe_lock);
head_sh->batch_head = NULL;
analyse_stripe(sh, &s);
+ if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
+ goto finish;
+
if (s.handle_bad_blocks) {
set_bit(STRIPE_HANDLE, &sh->state);
goto finish;
/* check if the array has lost more than max_degraded devices and,
* if so, some requests might need to be failed.
*/
- if (s.failed > conf->max_degraded) {
+ if (s.failed > conf->max_degraded || s.log_failed) {
sh->check_state = 0;
sh->reconstruct_state = 0;
break_stripe_batch_list(sh, 0);
/* Finish reconstruct operations initiated by the expansion process */
if (sh->reconstruct_state == reconstruct_state_result) {
struct stripe_head *sh_src
- = get_active_stripe(conf, sh->sector, 1, 1, 1);
+ = raid5_get_active_stripe(conf, sh->sector, 1, 1, 1);
if (sh_src && test_bit(STRIPE_EXPAND_SOURCE, &sh_src->state)) {
/* sh cannot be written until sh_src has been read.
* so arrange for sh to be delayed a little
if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
&sh_src->state))
atomic_inc(&conf->preread_active_stripes);
- release_stripe(sh_src);
+ raid5_release_stripe(sh_src);
goto finish;
}
if (sh_src)
- release_stripe(sh_src);
+ raid5_release_stripe(sh_src);
sh->reconstruct_state = reconstruct_state_idle;
clear_bit(STRIPE_EXPANDING, &sh->state);
struct raid5_plug_cb *cb;
if (!blk_cb) {
- release_stripe(sh);
+ raid5_release_stripe(sh);
return;
}
if (!test_and_set_bit(STRIPE_ON_UNPLUG_LIST, &sh->state))
list_add_tail(&sh->lru, &cb->list);
else
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
static void make_discard_request(struct mddev *mddev, struct bio *bi)
DEFINE_WAIT(w);
int d;
again:
- sh = get_active_stripe(conf, logical_sector, 0, 0, 0);
+ sh = raid5_get_active_stripe(conf, logical_sector, 0, 0, 0);
prepare_to_wait(&conf->wait_for_overlap, &w,
TASK_UNINTERRUPTIBLE);
set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
if (test_bit(STRIPE_SYNCING, &sh->state)) {
- release_stripe(sh);
+ raid5_release_stripe(sh);
schedule();
goto again;
}
if (sh->dev[d].towrite || sh->dev[d].toread) {
set_bit(R5_Overlap, &sh->dev[d].flags);
spin_unlock_irq(&sh->stripe_lock);
- release_stripe(sh);
+ raid5_release_stripe(sh);
schedule();
goto again;
}
bool do_prepare;
if (unlikely(bi->bi_rw & REQ_FLUSH)) {
- md_flush_request(mddev, bi);
- return;
+ int ret = r5l_handle_flush_request(conf->log, bi);
+
+ if (ret == 0)
+ return;
+ if (ret == -ENODEV) {
+ md_flush_request(mddev, bi);
+ return;
+ }
+ /* ret == -EAGAIN, fallback */
}
md_write_start(mddev, bi);
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
- sh = get_active_stripe(conf, new_sector, previous,
+ sh = raid5_get_active_stripe(conf, new_sector, previous,
(bi->bi_rw&RWA_MASK), 0);
if (sh) {
if (unlikely(previous)) {
must_retry = 1;
spin_unlock_irq(&conf->device_lock);
if (must_retry) {
- release_stripe(sh);
+ raid5_release_stripe(sh);
schedule();
do_prepare = true;
goto retry;
/* Might have got the wrong stripe_head
* by accident
*/
- release_stripe(sh);
+ raid5_release_stripe(sh);
goto retry;
}
if (rw == WRITE &&
logical_sector >= mddev->suspend_lo &&
logical_sector < mddev->suspend_hi) {
- release_stripe(sh);
+ raid5_release_stripe(sh);
/* As the suspend_* range is controlled by
* userspace, we want an interruptible
* wait.
* and wait a while
*/
md_wakeup_thread(mddev->thread);
- release_stripe(sh);
+ raid5_release_stripe(sh);
schedule();
do_prepare = true;
goto retry;
for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
int j;
int skipped_disk = 0;
- sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
+ sh = raid5_get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
set_bit(STRIPE_EXPANDING, &sh->state);
atomic_inc(&conf->reshape_stripes);
/* If any of this stripe is beyond the end of the old
if (conf->level == 6 &&
j == sh->qd_idx)
continue;
- s = compute_blocknr(sh, j, 0);
+ s = raid5_compute_blocknr(sh, j, 0);
if (s < raid5_size(mddev, 0, 0)) {
skipped_disk = 1;
continue;
if (last_sector >= mddev->dev_sectors)
last_sector = mddev->dev_sectors - 1;
while (first_sector <= last_sector) {
- sh = get_active_stripe(conf, first_sector, 1, 0, 1);
+ sh = raid5_get_active_stripe(conf, first_sector, 1, 0, 1);
set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
first_sector += STRIPE_SECTORS;
}
/* Now that the sources are clearly marked, we can release
while (!list_empty(&stripes)) {
sh = list_entry(stripes.next, struct stripe_head, lru);
list_del_init(&sh->lru);
- release_stripe(sh);
+ raid5_release_stripe(sh);
}
/* If this takes us to the resync_max point where we have to pause,
* then we need to write out the superblock.
return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
}
- bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr, false);
- sh = get_active_stripe(conf, sector_nr, 0, 1, 0);
+ sh = raid5_get_active_stripe(conf, sector_nr, 0, 1, 0);
if (sh == NULL) {
- sh = get_active_stripe(conf, sector_nr, 0, 0, 0);
+ sh = raid5_get_active_stripe(conf, sector_nr, 0, 0, 0);
/* make sure we don't swamp the stripe cache if someone else
* is trying to get access
*/
set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
+ raid5_release_stripe(sh);
return STRIPE_SECTORS;
}
/* already done this stripe */
continue;
- sh = get_active_stripe(conf, sector, 0, 1, 1);
+ sh = raid5_get_active_stripe(conf, sector, 0, 1, 1);
if (!sh) {
/* failed to get a stripe - must wait */
}
if (!add_stripe_bio(sh, raid_bio, dd_idx, 0, 0)) {
- release_stripe(sh);
+ raid5_release_stripe(sh);
raid5_set_bi_processed_stripes(raid_bio, scnt);
conf->retry_read_aligned = raid_bio;
return handled;
set_bit(R5_ReadNoMerge, &sh->dev[dd_idx].flags);
handle_stripe(sh);
- release_stripe(sh);
+ raid5_release_stripe(sh);
handled++;
}
remaining = raid5_dec_bi_active_stripes(raid_bio);
for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++)
if (!list_empty(temp_inactive_list + i))
break;
- if (i == NR_STRIPE_HASH_LOCKS)
+ if (i == NR_STRIPE_HASH_LOCKS) {
+ spin_unlock_irq(&conf->device_lock);
+ r5l_flush_stripe_to_raid(conf->log);
+ spin_lock_irq(&conf->device_lock);
return batch_size;
+ }
release_inactive = true;
}
spin_unlock_irq(&conf->device_lock);
release_inactive_stripe_list(conf, temp_inactive_list,
NR_STRIPE_HASH_LOCKS);
+ r5l_flush_stripe_to_raid(conf->log);
if (release_inactive) {
spin_lock_irq(&conf->device_lock);
return 0;
for (i = 0; i < batch_size; i++)
handle_stripe(batch[i]);
+ r5l_write_stripe_run(conf->log);
cond_resched();
mutex_unlock(&conf->cache_size_mutex);
}
+ r5l_flush_stripe_to_raid(conf->log);
+
async_tx_issue_pending_all();
blk_finish_plug(&plug);
static void free_conf(struct r5conf *conf)
{
+ if (conf->log)
+ r5l_exit_log(conf->log);
if (conf->shrinker.seeks)
unregister_shrinker(&conf->shrinker);
+
free_thread_groups(conf);
shrink_stripes(conf);
raid5_free_percpu(conf);
rdev_for_each(rdev, mddev) {
raid_disk = rdev->raid_disk;
if (raid_disk >= max_disks
- || raid_disk < 0)
+ || raid_disk < 0 || test_bit(Journal, &rdev->flags))
continue;
disk = conf->disks + raid_disk;
int working_disks = 0;
int dirty_parity_disks = 0;
struct md_rdev *rdev;
+ struct md_rdev *journal_dev = NULL;
sector_t reshape_offset = 0;
int i;
long long min_offset_diff = 0;
rdev_for_each(rdev, mddev) {
long long diff;
+
+ if (test_bit(Journal, &rdev->flags)) {
+ journal_dev = rdev;
+ continue;
+ }
if (rdev->raid_disk < 0)
continue;
diff = (rdev->new_data_offset - rdev->data_offset);
int chunk_sectors;
int new_data_disks;
+ if (journal_dev) {
+ printk(KERN_ERR "md/raid:%s: don't support reshape with journal - aborting.\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+
if (mddev->new_level != mddev->level) {
printk(KERN_ERR "md/raid:%s: unsupported reshape "
"required - aborting.\n",
if (IS_ERR(conf))
return PTR_ERR(conf);
+ if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
+ printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
+ mdname(mddev));
+ mddev->ro = 1;
+ set_disk_ro(mddev->gendisk, 1);
+ }
+
conf->min_offset_diff = min_offset_diff;
mddev->thread = conf->thread;
conf->thread = NULL;
mddev->queue);
}
+ if (journal_dev) {
+ char b[BDEVNAME_SIZE];
+
+ printk(KERN_INFO"md/raid:%s: using device %s as journal\n",
+ mdname(mddev), bdevname(journal_dev->bdev, b));
+ r5l_init_log(conf, journal_dev);
+ }
+
return 0;
abort:
md_unregister_thread(&mddev->thread);
struct disk_info *p = conf->disks + number;
print_raid5_conf(conf);
+ if (test_bit(Journal, &rdev->flags)) {
+ /*
+ * journal disk is not removable, but we need give a chance to
+ * update superblock of other disks. Otherwise journal disk
+ * will be considered as 'fresh'
+ */
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ return -EINVAL;
+ }
if (rdev == p->rdev)
rdevp = &p->rdev;
else if (rdev == p->replacement)
int first = 0;
int last = conf->raid_disks - 1;
+ if (test_bit(Journal, &rdev->flags))
+ return -EINVAL;
if (mddev->recovery_disabled == conf->recovery_disabled)
return -EBUSY;
sector_t newsize;
struct r5conf *conf = mddev->private;
+ if (conf->log)
+ return -EINVAL;
sectors &= ~((sector_t)conf->chunk_sectors - 1);
newsize = raid5_size(mddev, sectors, mddev->raid_disks);
if (mddev->external_size &&
{
struct r5conf *conf = mddev->private;
+ if (conf->log)
+ return -EINVAL;
if (mddev->delta_disks == 0 &&
mddev->new_layout == mddev->layout &&
mddev->new_chunk_sectors == mddev->chunk_sectors)
unlock_all_device_hash_locks_irq(conf);
break;
}
+ r5l_quiesce(conf->log, state);
}
static void *raid45_takeover_raid0(struct mddev *mddev, int level)
projects / karo-tx-linux.git / blobdiff