Merge branch 'md-next' of ssh://gitolite.kernel.org/pub/scm/linux/ker…

…nel/git/song/md into for-5.17/drivers

Pull MD updates from Song:

"The major changes are:

- REQ_NOWAIT support, by Vishal Verma
- raid6 benchmark optimization, by Dirk Müller
- Fix for acct bioset, by Xiao Ni
- Clean up max_queued_requests, by Mariusz Tkaczyk
- PREEMPT_RT optimization, by Davidlohr Bueso
- Use default_groups in kobj_type, by Greg Kroah-Hartman"

* 'md-next' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/song/md:
  md: use default_groups in kobj_type
  md: Move alloc/free acct bioset in to personality
  lib/raid6: Use strict priority ranking for pq gen() benchmarking
  lib/raid6: skip benchmark of non-chosen xor_syndrome functions
  md: fix spelling of "its"
  md: raid456 add nowait support
  md: raid10 add nowait support
  md: raid1 add nowait support
  md: add support for REQ_NOWAIT
  md: drop queue limitation for RAID1 and RAID10
  md/raid5: play nice with PREEMPT_RT

drivers/md/md-cluster.c

@@ -574,7 +574,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 	int ret = 0;
 
 	if (WARN(mddev->cluster_info->slot_number - 1 == le32_to_cpu(msg->slot),
-		"node %d received it's own msg\n", le32_to_cpu(msg->slot)))
+		"node %d received its own msg\n", le32_to_cpu(msg->slot)))
 		return -1;
 	switch (le32_to_cpu(msg->type)) {
 	case METADATA_UPDATED:

drivers/md/md.c

@@ -418,6 +418,12 @@ void md_handle_request(struct mddev *mddev, struct bio *bio)
 	rcu_read_lock();
 	if (is_suspended(mddev, bio)) {
 		DEFINE_WAIT(__wait);
+		/* Bail out if REQ_NOWAIT is set for the bio */
+		if (bio->bi_opf & REQ_NOWAIT) {
+			rcu_read_unlock();
+			bio_wouldblock_error(bio);
+			return;
+		}
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
@@ -3602,6 +3608,7 @@ static struct attribute *rdev_default_attrs[] = {
 	&rdev_ppl_size.attr,
 	NULL,
 };
+ATTRIBUTE_GROUPS(rdev_default);
 static ssize_t
 rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
@@ -3651,7 +3658,7 @@ static const struct sysfs_ops rdev_sysfs_ops = {
 static struct kobj_type rdev_ktype = {
 	.release	= rdev_free,
 	.sysfs_ops	= &rdev_sysfs_ops,
-	.default_attrs	= rdev_default_attrs,
+	.default_groups	= rdev_default_groups,
 };
 
 int md_rdev_init(struct md_rdev *rdev)
@@ -5787,6 +5794,7 @@ int md_run(struct mddev *mddev)
 	int err;
 	struct md_rdev *rdev;
 	struct md_personality *pers;
+	bool nowait = true;
 
 	if (list_empty(&mddev->disks))
 		/* cannot run an array with no devices.. */
@@ -5857,8 +5865,13 @@ int md_run(struct mddev *mddev)
 			}
 		}
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
+		nowait = nowait && blk_queue_nowait(bdev_get_queue(rdev->bdev));
 	}
 
+	/* Set the NOWAIT flags if all underlying devices support it */
+	if (nowait)
+		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue);
+
 	if (!bioset_initialized(&mddev->bio_set)) {
 		err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 		if (err)
@@ -5869,13 +5882,6 @@ int md_run(struct mddev *mddev)
 		if (err)
 			goto exit_bio_set;
 	}
-	if (mddev->level != 1 && mddev->level != 10 &&
-	    !bioset_initialized(&mddev->io_acct_set)) {
-		err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
-				  offsetof(struct md_io_acct, bio_clone), 0);
-		if (err)
-			goto exit_sync_set;
-	}
 
 	spin_lock(&pers_lock);
 	pers = find_pers(mddev->level, mddev->clevel);
@@ -6052,9 +6058,6 @@ int md_run(struct mddev *mddev)
 	module_put(pers->owner);
 	md_bitmap_destroy(mddev);
 abort:
-	if (mddev->level != 1 && mddev->level != 10)
-		bioset_exit(&mddev->io_acct_set);
-exit_sync_set:
 	bioset_exit(&mddev->sync_set);
 exit_bio_set:
 	bioset_exit(&mddev->bio_set);
@@ -7002,6 +7005,15 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	if (!mddev->thread)
 		md_update_sb(mddev, 1);
+	/*
+	 * If the new disk does not support REQ_NOWAIT,
+	 * disable on the whole MD.
+	 */
+	if (!blk_queue_nowait(bdev_get_queue(rdev->bdev))) {
+		pr_info("%s: Disabling nowait because %s does not support nowait\n",
+			mdname(mddev), bdevname(rdev->bdev, b));
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue);
+	}
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
 	 * array immediately.
@@ -8400,7 +8412,7 @@ int md_setup_cluster(struct mddev *mddev, int nodes)
 	spin_lock(&pers_lock);
 	/* ensure module won't be unloaded */
 	if (!md_cluster_ops || !try_module_get(md_cluster_mod)) {
-		pr_warn("can't find md-cluster module or get it's reference.\n");
+		pr_warn("can't find md-cluster module or get its reference.\n");
 		spin_unlock(&pers_lock);
 		return -ENOENT;
 	}
@@ -8587,6 +8599,23 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 
+int acct_bioset_init(struct mddev *mddev)
+{
+	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;

drivers/md/md.h

@@ -721,6 +721,8 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
+int acct_bioset_init(struct mddev *mddev);
+void acct_bioset_exit(struct mddev *mddev);
 void md_account_bio(struct mddev *mddev, struct bio **bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);

drivers/md/raid0.c

@@ -356,7 +356,21 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	return array_sectors;
 }
 
-static void raid0_free(struct mddev *mddev, void *priv);
+static void free_conf(struct mddev *mddev, struct r0conf *conf)
+{
+	kfree(conf->strip_zone);
+	kfree(conf->devlist);
+	kfree(conf);
+	mddev->private = NULL;
+}
+
+static void raid0_free(struct mddev *mddev, void *priv)
+{
+	struct r0conf *conf = priv;
+
+	free_conf(mddev, conf);
+	acct_bioset_exit(mddev);
+}
 
 static int raid0_run(struct mddev *mddev)
 {
@@ -370,11 +384,16 @@ static int raid0_run(struct mddev *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 
+	if (acct_bioset_init(mddev)) {
+		pr_err("md/raid0:%s: alloc acct bioset failed.\n", mdname(mddev));
+		return -ENOMEM;
+	}
+
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
 		ret = create_strip_zones(mddev, &conf);
 		if (ret < 0)
-			return ret;
+			goto exit_acct_set;
 		mddev->private = conf;
 	}
 	conf = mddev->private;
@@ -413,17 +432,16 @@ static int raid0_run(struct mddev *mddev)
 	dump_zones(mddev);
 
 	ret = md_integrity_register(mddev);
+	if (ret)
+		goto free;
 
 	return ret;
-}
 
-static void raid0_free(struct mddev *mddev, void *priv)
-{
-	struct r0conf *conf = priv;
-
-	kfree(conf->strip_zone);
-	kfree(conf->devlist);
-	kfree(conf);
+free:
+	free_conf(mddev, conf);
+exit_acct_set:
+	acct_bioset_exit(mddev);
+	return ret;
 }
 
 static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)

drivers/md/raid1-10.c

@@ -22,12 +22,6 @@
 
 #define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
 
-/* When there are this many requests queue to be written by
- * the raid thread, we become 'congested' to provide back-pressure
- * for writeback.
- */
-static int max_queued_requests = 1024;
-
 /* for managing resync I/O pages */
 struct resync_pages {
 	void		*raid_bio;

drivers/md/raid1.c

@@ -929,8 +929,10 @@ static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
 	wake_up(&conf->wait_barrier);
 }
 
-static void _wait_barrier(struct r1conf *conf, int idx)
+static bool _wait_barrier(struct r1conf *conf, int idx, bool nowait)
 {
+	bool ret = true;
+
 	/*
 	 * We need to increase conf->nr_pending[idx] very early here,
 	 * then raise_barrier() can be blocked when it waits for
@@ -961,7 +963,7 @@ static void _wait_barrier(struct r1conf *conf, int idx)
 	 */
 	if (!READ_ONCE(conf->array_frozen) &&
 	    !atomic_read(&conf->barrier[idx]))
-		return;
+		return ret;
 
 	/*
 	 * After holding conf->resync_lock, conf->nr_pending[idx]
@@ -979,18 +981,27 @@ static void _wait_barrier(struct r1conf *conf, int idx)
 	 */
 	wake_up(&conf->wait_barrier);
 	/* Wait for the barrier in same barrier unit bucket to drop. */
-	wait_event_lock_irq(conf->wait_barrier,
-			    !conf->array_frozen &&
-			     !atomic_read(&conf->barrier[idx]),
-			    conf->resync_lock);
-	atomic_inc(&conf->nr_pending[idx]);
+
+	/* Return false when nowait flag is set */
+	if (nowait) {
+		ret = false;
+	} else {
+		wait_event_lock_irq(conf->wait_barrier,
+				!conf->array_frozen &&
+				!atomic_read(&conf->barrier[idx]),
+				conf->resync_lock);
+		atomic_inc(&conf->nr_pending[idx]);
+	}
+
 	atomic_dec(&conf->nr_waiting[idx]);
 	spin_unlock_irq(&conf->resync_lock);
+	return ret;
 }
 
-static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr)
+static bool wait_read_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait)
 {
 	int idx = sector_to_idx(sector_nr);
+	bool ret = true;
 
 	/*
 	 * Very similar to _wait_barrier(). The difference is, for read
@@ -1002,7 +1013,7 @@ static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr)
 	atomic_inc(&conf->nr_pending[idx]);
 
 	if (!READ_ONCE(conf->array_frozen))
-		return;
+		return ret;
 
 	spin_lock_irq(&conf->resync_lock);
 	atomic_inc(&conf->nr_waiting[idx]);
@@ -1013,19 +1024,28 @@ static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr)
 	 */
 	wake_up(&conf->wait_barrier);
 	/* Wait for array to be unfrozen */
-	wait_event_lock_irq(conf->wait_barrier,
-			    !conf->array_frozen,
-			    conf->resync_lock);
-	atomic_inc(&conf->nr_pending[idx]);
+
+	/* Return false when nowait flag is set */
+	if (nowait) {
+		/* Return false when nowait flag is set */
+		ret = false;
+	} else {
+		wait_event_lock_irq(conf->wait_barrier,
+				!conf->array_frozen,
+				conf->resync_lock);
+		atomic_inc(&conf->nr_pending[idx]);
+	}
+
 	atomic_dec(&conf->nr_waiting[idx]);
 	spin_unlock_irq(&conf->resync_lock);
+	return ret;
 }
 
-static void wait_barrier(struct r1conf *conf, sector_t sector_nr)
+static bool wait_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait)
 {
 	int idx = sector_to_idx(sector_nr);
 
-	_wait_barrier(conf, idx);
+	return _wait_barrier(conf, idx, nowait);
 }
 
 static void _allow_barrier(struct r1conf *conf, int idx)
@@ -1236,7 +1256,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	 * Still need barrier for READ in case that whole
 	 * array is frozen.
 	 */
-	wait_read_barrier(conf, bio->bi_iter.bi_sector);
+	if (!wait_read_barrier(conf, bio->bi_iter.bi_sector,
+				bio->bi_opf & REQ_NOWAIT)) {
+		bio_wouldblock_error(bio);
+		return;
+	}
 
 	if (!r1_bio)
 		r1_bio = alloc_r1bio(mddev, bio);
@@ -1336,6 +1360,10 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		     bio->bi_iter.bi_sector, bio_end_sector(bio))) {
 
 		DEFINE_WAIT(w);
+		if (bio->bi_opf & REQ_NOWAIT) {
+			bio_wouldblock_error(bio);
+			return;
+		}
 		for (;;) {
 			prepare_to_wait(&conf->wait_barrier,
 					&w, TASK_IDLE);
@@ -1353,17 +1381,15 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	 * thread has put up a bar for new requests.
 	 * Continue immediately if no resync is active currently.
 	 */
-	wait_barrier(conf, bio->bi_iter.bi_sector);
+	if (!wait_barrier(conf, bio->bi_iter.bi_sector,
+				bio->bi_opf & REQ_NOWAIT)) {
+		bio_wouldblock_error(bio);
+		return;
+	}
 
 	r1_bio = alloc_r1bio(mddev, bio);
 	r1_bio->sectors = max_write_sectors;
 
-	if (conf->pending_count >= max_queued_requests) {
-		md_wakeup_thread(mddev->thread);
-		raid1_log(mddev, "wait queued");
-		wait_event(conf->wait_barrier,
-			   conf->pending_count < max_queued_requests);
-	}
 	/* first select target devices under rcu_lock and
 	 * inc refcount on their rdev.  Record them by setting
 	 * bios[x] to bio
@@ -1458,9 +1484,14 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
 		r1_bio->state = 0;
 		allow_barrier(conf, bio->bi_iter.bi_sector);
+
+		if (bio->bi_opf & REQ_NOWAIT) {
+			bio_wouldblock_error(bio);
+			return;
+		}
 		raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		wait_barrier(conf, bio->bi_iter.bi_sector);
+		wait_barrier(conf, bio->bi_iter.bi_sector, false);
 		goto retry_write;
 	}
 
@@ -1687,7 +1718,7 @@ static void close_sync(struct r1conf *conf)
 	int idx;
 
 	for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++) {
-		_wait_barrier(conf, idx);
+		_wait_barrier(conf, idx, false);
 		_allow_barrier(conf, idx);
 	}
 
@@ -3409,5 +3440,3 @@ MODULE_DESCRIPTION("RAID1 (mirroring) personality for MD");
 MODULE_ALIAS("md-personality-3"); /* RAID1 */
 MODULE_ALIAS("md-raid1");
 MODULE_ALIAS("md-level-1");
-
-module_param(max_queued_requests, int, S_IRUGO|S_IWUSR);