mddev->pers->prepare_suspend(mddev);
wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io));
- mddev->pers->quiesce(mddev, 1);
clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags);
wait_event(mddev->sb_wait, !test_bit(MD_UPDATING_SB, &mddev->flags));
void mddev_resume(struct mddev *mddev)
{
- /* entred the memalloc scope from mddev_suspend() */
- memalloc_noio_restore(mddev->noio_flag);
lockdep_assert_held(&mddev->reconfig_mutex);
if (--mddev->suspended)
return;
+
+ /* entred the memalloc scope from mddev_suspend() */
+ memalloc_noio_restore(mddev->noio_flag);
+
percpu_ref_resurrect(&mddev->active_io);
wake_up(&mddev->sb_wait);
- mddev->pers->quiesce(mddev, 0);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
{
mutex_init(&mddev->open_mutex);
mutex_init(&mddev->reconfig_mutex);
+ mutex_init(&mddev->sync_mutex);
mutex_init(&mddev->bitmap_info.mutex);
INIT_LIST_HEAD(&mddev->disks);
INIT_LIST_HEAD(&mddev->all_mddevs);
timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0);
atomic_set(&mddev->active, 1);
atomic_set(&mddev->openers, 0);
+ atomic_set(&mddev->sync_seq, 0);
spin_lock_init(&mddev->lock);
atomic_set(&mddev->flush_pending, 0);
init_waitqueue_head(&mddev->sb_wait);
pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
(mddev->level != 1 && mddev->level != 10 &&
- bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE))) {
+ bioset_integrity_create(&mddev->io_clone_set, BIO_POOL_SIZE))) {
/*
* No need to handle the failure of bioset_integrity_create,
* because the function is called by md_run() -> pers->run(),
return sprintf(page, "%s\n", type);
}
+static void stop_sync_thread(struct mddev *mddev)
+{
+ if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ return;
+
+ if (mddev_lock(mddev))
+ return;
+
+ /*
+ * Check again in case MD_RECOVERY_RUNNING is cleared before lock is
+ * held.
+ */
+ if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+ mddev_unlock(mddev);
+ return;
+ }
+
+ if (work_pending(&mddev->del_work))
+ flush_workqueue(md_misc_wq);
+
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ /*
+ * Thread might be blocked waiting for metadata update which will now
+ * never happen
+ */
+ md_wakeup_thread_directly(mddev->sync_thread);
+
+ mddev_unlock(mddev);
+}
+
+static void idle_sync_thread(struct mddev *mddev)
+{
+ int sync_seq = atomic_read(&mddev->sync_seq);
+
+ mutex_lock(&mddev->sync_mutex);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ stop_sync_thread(mddev);
+
+ wait_event(resync_wait, sync_seq != atomic_read(&mddev->sync_seq) ||
+ !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+
+ mutex_unlock(&mddev->sync_mutex);
+}
+
+static void frozen_sync_thread(struct mddev *mddev)
+{
+ mutex_lock(&mddev->sync_mutex);
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ stop_sync_thread(mddev);
+
+ wait_event(resync_wait, mddev->sync_thread == NULL &&
+ !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+
+ mutex_unlock(&mddev->sync_mutex);
+}
+
static ssize_t
action_store(struct mddev *mddev, const char *page, size_t len)
{
return -EINVAL;
- if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
- if (cmd_match(page, "frozen"))
- set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- else
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
- mddev_lock(mddev) == 0) {
- if (work_pending(&mddev->del_work))
- flush_workqueue(md_misc_wq);
- if (mddev->sync_thread) {
- sector_t save_rp = mddev->reshape_position;
-
- mddev_unlock(mddev);
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_unregister_thread(&mddev->sync_thread);
- mddev_lock_nointr(mddev);
- /*
- * set RECOVERY_INTR again and restore reshape
- * position in case others changed them after
- * got lock, eg, reshape_position_store and
- * md_check_recovery.
- */
- mddev->reshape_position = save_rp;
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev);
- }
- mddev_unlock(mddev);
- }
- } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ if (cmd_match(page, "idle"))
+ idle_sync_thread(mddev);
+ else if (cmd_match(page, "frozen"))
+ frozen_sync_thread(mddev);
+ else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
else if (cmd_match(page, "resync"))
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
goto exit_bio_set;
}
+ if (!bioset_initialized(&mddev->io_clone_set)) {
+ err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
+ offsetof(struct md_io_clone, bio_clone), 0);
+ if (err)
+ goto exit_sync_set;
+ }
+
spin_lock(&pers_lock);
pers = find_pers(mddev->level, mddev->clevel);
if (!pers || !try_module_get(pers->owner)) {
module_put(pers->owner);
md_bitmap_destroy(mddev);
abort:
+ bioset_exit(&mddev->io_clone_set);
+exit_sync_set:
bioset_exit(&mddev->sync_set);
exit_bio_set:
bioset_exit(&mddev->bio_set);
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_unregister_thread(&mddev->sync_thread);
md_reap_sync_thread(mddev);
}
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
}
- md_unregister_thread(&mddev->thread);
+ md_unregister_thread(mddev, &mddev->thread);
if (mddev->queue)
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
}
percpu_ref_exit(&mddev->active_io);
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
+ bioset_exit(&mddev->io_clone_set);
}
void md_stop(struct mddev *mddev)
if (mddev->bitmap || mddev->bitmap_info.file)
return -EEXIST; /* cannot add when bitmap is present */
+
+ if (!IS_ENABLED(CONFIG_MD_BITMAP_FILE)) {
+ pr_warn("%s: bitmap files not supported by this kernel\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ pr_warn("%s: using deprecated bitmap file support\n",
+ mdname(mddev));
+
f = fget(fd);
if (f == NULL) {
}
EXPORT_SYMBOL(md_register_thread);
-void md_unregister_thread(struct md_thread __rcu **threadp)
+void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **threadp)
{
- struct md_thread *thread = rcu_dereference_protected(*threadp, true);
+ struct md_thread *thread = rcu_dereference_protected(*threadp,
+ lockdep_is_held(&mddev->reconfig_mutex));
if (!thread)
return;
}
EXPORT_SYMBOL_GPL(md_submit_discard_bio);
-int acct_bioset_init(struct mddev *mddev)
+static void md_end_clone_io(struct bio *bio)
{
- int err = 0;
-
- if (!bioset_initialized(&mddev->io_acct_set))
- err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
- offsetof(struct md_io_acct, bio_clone), 0);
- return err;
-}
-EXPORT_SYMBOL_GPL(acct_bioset_init);
-
-void acct_bioset_exit(struct mddev *mddev)
-{
- bioset_exit(&mddev->io_acct_set);
-}
-EXPORT_SYMBOL_GPL(acct_bioset_exit);
-
-static void md_end_io_acct(struct bio *bio)
-{
- struct md_io_acct *md_io_acct = bio->bi_private;
- struct bio *orig_bio = md_io_acct->orig_bio;
- struct mddev *mddev = md_io_acct->mddev;
+ struct md_io_clone *md_io_clone = bio->bi_private;
+ struct bio *orig_bio = md_io_clone->orig_bio;
+ struct mddev *mddev = md_io_clone->mddev;
orig_bio->bi_status = bio->bi_status;
- bio_end_io_acct(orig_bio, md_io_acct->start_time);
+ if (md_io_clone->start_time)
+ bio_end_io_acct(orig_bio, md_io_clone->start_time);
+
bio_put(bio);
bio_endio(orig_bio);
-
percpu_ref_put(&mddev->active_io);
}
-/*
- * Used by personalities that don't already clone the bio and thus can't
- * easily add the timestamp to their extended bio structure.
- */
-void md_account_bio(struct mddev *mddev, struct bio **bio)
+static void md_clone_bio(struct mddev *mddev, struct bio **bio)
{
struct block_device *bdev = (*bio)->bi_bdev;
- struct md_io_acct *md_io_acct;
- struct bio *clone;
-
- if (!blk_queue_io_stat(bdev->bd_disk->queue))
- return;
+ struct md_io_clone *md_io_clone;
+ struct bio *clone =
+ bio_alloc_clone(bdev, *bio, GFP_NOIO, &mddev->io_clone_set);
+
+ md_io_clone = container_of(clone, struct md_io_clone, bio_clone);
+ md_io_clone->orig_bio = *bio;
+ md_io_clone->mddev = mddev;
+ if (blk_queue_io_stat(bdev->bd_disk->queue))
+ md_io_clone->start_time = bio_start_io_acct(*bio);
+
+ clone->bi_end_io = md_end_clone_io;
+ clone->bi_private = md_io_clone;
+ *bio = clone;
+}
+void md_account_bio(struct mddev *mddev, struct bio **bio)
+{
percpu_ref_get(&mddev->active_io);
-
- clone = bio_alloc_clone(bdev, *bio, GFP_NOIO, &mddev->io_acct_set);
- md_io_acct = container_of(clone, struct md_io_acct, bio_clone);
- md_io_acct->orig_bio = *bio;
- md_io_acct->start_time = bio_start_io_acct(*bio);
- md_io_acct->mddev = mddev;
-
- clone->bi_end_io = md_end_io_acct;
- clone->bi_private = md_io_acct;
- *bio = clone;
+ md_clone_bio(mddev, bio);
}
EXPORT_SYMBOL_GPL(md_account_bio);
* ->spare_active and clear saved_raid_disk
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_unregister_thread(&mddev->sync_thread);
md_reap_sync_thread(mddev);
clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
if (mddev->sb_flags)
md_update_sb(mddev, 0);
- if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
- !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
- /* resync/recovery still happening */
- clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- goto unlock;
- }
- if (mddev->sync_thread) {
- md_unregister_thread(&mddev->sync_thread);
+ /*
+ * Never start a new sync thread if MD_RECOVERY_RUNNING is
+ * still set.
+ */
+ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
+ if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
+ /* resync/recovery still happening */
+ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ goto unlock;
+ }
+
+ if (WARN_ON_ONCE(!mddev->sync_thread))
+ goto unlock;
+
md_reap_sync_thread(mddev);
goto unlock;
}
+
/* Set RUNNING before clearing NEEDED to avoid
* any transients in the value of "sync_action".
*/
sector_t old_dev_sectors = mddev->dev_sectors;
bool is_reshaped = false;
- /* sync_thread should be unregistered, collect result */
+ /* resync has finished, collect result */
+ md_unregister_thread(mddev, &mddev->sync_thread);
+ atomic_inc(&mddev->sync_seq);
+
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
mddev->degraded != mddev->raid_disks) {
if (mddev_is_clustered(mddev) && is_reshaped
&& !test_bit(MD_CLOSING, &mddev->flags))
md_cluster_ops->update_size(mddev, old_dev_sectors);
- wake_up(&resync_wait);
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
sysfs_notify_dirent_safe(mddev->sysfs_completed);
md_new_event();
if (mddev->event_work.func)
queue_work(md_misc_wq, &mddev->event_work);
+ wake_up(&resync_wait);
}
EXPORT_SYMBOL(md_reap_sync_thread);
projects / linux-2.6-microblaze.git / blobdiff