Merge branch 'md-next' of...

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

drivers/md/raid10.c

@@ -952,8 +952,10 @@ static void lower_barrier(struct r10conf *conf)
 	wake_up(&conf->wait_barrier);
 }
 
-static void wait_barrier(struct r10conf *conf)
+static bool wait_barrier(struct r10conf *conf, bool nowait)
 {
+	bool ret = true;
+
 	spin_lock_irq(&conf->resync_lock);
 	if (conf->barrier) {
 		struct bio_list *bio_list = current->bio_list;
@@ -967,27 +969,35 @@ static void wait_barrier(struct r10conf *conf)
 		 * that queue to get the nr_pending
 		 * count down.
 		 */
-		raid10_log(conf->mddev, "wait barrier");
-		wait_event_lock_irq(conf->wait_barrier,
-				    !conf->barrier ||
-				    (atomic_read(&conf->nr_pending) &&
-				     bio_list &&
-				     (!bio_list_empty(&bio_list[0]) ||
-				      !bio_list_empty(&bio_list[1]))) ||
-				     /* move on if recovery thread is
-				      * blocked by us
-				      */
-				     (conf->mddev->thread->tsk == current &&
-				      test_bit(MD_RECOVERY_RUNNING,
-					       &conf->mddev->recovery) &&
-				      conf->nr_queued > 0),
-				    conf->resync_lock);
+		/* Return false when nowait flag is set */
+		if (nowait) {
+			ret = false;
+		} else {
+			raid10_log(conf->mddev, "wait barrier");
+			wait_event_lock_irq(conf->wait_barrier,
+					    !conf->barrier ||
+					    (atomic_read(&conf->nr_pending) &&
+					     bio_list &&
+					     (!bio_list_empty(&bio_list[0]) ||
+					      !bio_list_empty(&bio_list[1]))) ||
+					     /* move on if recovery thread is
+					      * blocked by us
+					      */
+					     (conf->mddev->thread->tsk == current &&
+					      test_bit(MD_RECOVERY_RUNNING,
+						       &conf->mddev->recovery) &&
+					      conf->nr_queued > 0),
+					    conf->resync_lock);
+		}
 		conf->nr_waiting--;
 		if (!conf->nr_waiting)
 			wake_up(&conf->wait_barrier);
 	}
-	atomic_inc(&conf->nr_pending);
+	/* Only increment nr_pending when we wait */
+	if (ret)
+		atomic_inc(&conf->nr_pending);
 	spin_unlock_irq(&conf->resync_lock);
+	return ret;
 }
 
 static void allow_barrier(struct r10conf *conf)
@@ -1098,21 +1108,30 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
  * currently.
  * 2. If IO spans the reshape position.  Need to wait for reshape to pass.
  */
-static void regular_request_wait(struct mddev *mddev, struct r10conf *conf,
+static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 				 struct bio *bio, sector_t sectors)
 {
-	wait_barrier(conf);
+	/* Bail out if REQ_NOWAIT is set for the bio */
+	if (!wait_barrier(conf, bio->bi_opf & REQ_NOWAIT)) {
+		bio_wouldblock_error(bio);
+		return false;
+	}
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio->bi_iter.bi_sector < conf->reshape_progress &&
 	    bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
-		raid10_log(conf->mddev, "wait reshape");
 		allow_barrier(conf);
+		if (bio->bi_opf & REQ_NOWAIT) {
+			bio_wouldblock_error(bio);
+			return false;
+		}
+		raid10_log(conf->mddev, "wait reshape");
 		wait_event(conf->wait_barrier,
 			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
 			   conf->reshape_progress >= bio->bi_iter.bi_sector +
 			   sectors);
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 	}
+	return true;
 }
 
 static void raid10_read_request(struct mddev *mddev, struct bio *bio,
@@ -1157,7 +1176,8 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		rcu_read_unlock();
 	}
 
-	regular_request_wait(mddev, conf, bio, r10_bio->sectors);
+	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors))
+		return;
 	rdev = read_balance(conf, r10_bio, &max_sectors);
 	if (!rdev) {
 		if (err_rdev) {
@@ -1179,7 +1199,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		submit_bio_noacct(bio);
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 		bio = split;
 		r10_bio->master_bio = bio;
 		r10_bio->sectors = max_sectors;
@@ -1338,7 +1358,7 @@ static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 		raid10_log(conf->mddev, "%s wait rdev %d blocked",
 				__func__, blocked_rdev->raid_disk);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 		goto retry_wait;
 	}
 }
@@ -1356,6 +1376,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 					    bio->bi_iter.bi_sector,
 					    bio_end_sector(bio)))) {
 		DEFINE_WAIT(w);
+		/* Bail out if REQ_NOWAIT is set for the bio */
+		if (bio->bi_opf & REQ_NOWAIT) {
+			bio_wouldblock_error(bio);
+			return;
+		}
 		for (;;) {
 			prepare_to_wait(&conf->wait_barrier,
 					&w, TASK_IDLE);
@@ -1368,7 +1393,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	sectors = r10_bio->sectors;
-	regular_request_wait(mddev, conf, bio, sectors);
+	if (!regular_request_wait(mddev, conf, bio, sectors))
+		return;
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    (mddev->reshape_backwards
 	     ? (bio->bi_iter.bi_sector < conf->reshape_safe &&
@@ -1380,6 +1406,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		set_mask_bits(&mddev->sb_flags, 0,
 			      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
 		md_wakeup_thread(mddev->thread);
+		if (bio->bi_opf & REQ_NOWAIT) {
+			allow_barrier(conf);
+			bio_wouldblock_error(bio);
+			return;
+		}
 		raid10_log(conf->mddev, "wait reshape metadata");
 		wait_event(mddev->sb_wait,
 			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
@@ -1387,12 +1418,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		conf->reshape_safe = mddev->reshape_position;
 	}
 
-	if (conf->pending_count >= max_queued_requests) {
-		md_wakeup_thread(mddev->thread);
-		raid10_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
@@ -1482,7 +1507,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 		bio_chain(split, bio);
 		allow_barrier(conf);
 		submit_bio_noacct(bio);
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 		bio = split;
 		r10_bio->master_bio = bio;
 	}
@@ -1607,7 +1632,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		return -EAGAIN;
 
-	wait_barrier(conf);
+	if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) {
+		bio_wouldblock_error(bio);
+		return 0;
+	}
+	wait_barrier(conf, false);
 
 	/*
 	 * Check reshape again to avoid reshape happens after checking
@@ -1649,7 +1678,7 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 		allow_barrier(conf);
 		/* Resend the fist split part */
 		submit_bio_noacct(split);
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 	}
 	div_u64_rem(bio_end, stripe_size, &remainder);
 	if (remainder) {
@@ -1660,7 +1689,7 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 		/* Resend the second split part */
 		submit_bio_noacct(bio);
 		bio = split;
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 	}
 
 	bio_start = bio->bi_iter.bi_sector;
@@ -1816,7 +1845,7 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
 		end_disk_offset += geo->stride;
 		atomic_inc(&first_r10bio->remaining);
 		raid_end_discard_bio(r10_bio);
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 		goto retry_discard;
 	}
 
@@ -2011,7 +2040,7 @@ static void print_conf(struct r10conf *conf)
 
 static void close_sync(struct r10conf *conf)
 {
-	wait_barrier(conf);
+	wait_barrier(conf, false);
 	allow_barrier(conf);
 
 	mempool_exit(&conf->r10buf_pool);
@@ -4819,7 +4848,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 	if (need_flush ||
 	    time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) {
 		/* Need to update reshape_position in metadata */
-		wait_barrier(conf);
+		wait_barrier(conf, false);
 		mddev->reshape_position = conf->reshape_progress;
 		if (mddev->reshape_backwards)
 			mddev->curr_resync_completed = raid10_size(mddev, 0, 0)
@@ -5242,5 +5271,3 @@ MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD");
 MODULE_ALIAS("md-personality-9"); /* RAID10 */
 MODULE_ALIAS("md-raid10");
 MODULE_ALIAS("md-level-10");
-
-module_param(max_queued_requests, int, S_IRUGO|S_IWUSR);

drivers/md/raid5.c

@@ -2215,10 +2215,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	struct r5conf *conf = sh->raid_conf;
 	int level = conf->level;
 	struct raid5_percpu *percpu;
-	unsigned long cpu;
 
-	cpu = get_cpu();
-	percpu = per_cpu_ptr(conf->percpu, cpu);
+	local_lock(&conf->percpu->lock);
+	percpu = this_cpu_ptr(conf->percpu);
 	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
@@ -2271,13 +2270,14 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 			BUG();
 	}
 
-	if (overlap_clear && !sh->batch_head)
+	if (overlap_clear && !sh->batch_head) {
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (test_and_clear_bit(R5_Overlap, &dev->flags))
 				wake_up(&sh->raid_conf->wait_for_overlap);
 		}
-	put_cpu();
+	}
+	local_unlock(&conf->percpu->lock);
 }
 
 static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
@@ -5686,6 +5686,10 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 	struct stripe_head *sh;
 	int stripe_sectors;
 
+	/* We need to handle this when io_uring supports discard/trim */
+	if (WARN_ON_ONCE(bi->bi_opf & REQ_NOWAIT))
+		return;
+
 	if (mddev->reshape_position != MaxSector)
 		/* Skip discard while reshape is happening */
 		return;
@@ -5819,6 +5823,17 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 
+	/* Bail out if conflicts with reshape and REQ_NOWAIT is set */
+	if ((bi->bi_opf & REQ_NOWAIT) &&
+	    (conf->reshape_progress != MaxSector) &&
+	    (mddev->reshape_backwards
+	    ? (logical_sector > conf->reshape_progress && logical_sector <= conf->reshape_safe)
+	    : (logical_sector >= conf->reshape_safe && logical_sector < conf->reshape_progress))) {
+		bio_wouldblock_error(bi);
+		if (rw == WRITE)
+			md_write_end(mddev);
+		return true;
+	}
 	md_account_bio(mddev, &bi);
 	prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
 	for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) {
@@ -7052,6 +7067,7 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu
 		return -ENOMEM;
 	}
 
+	local_lock_init(&percpu->lock);
 	return 0;
 }
 
@@ -7446,12 +7462,19 @@ static int raid5_run(struct mddev *mddev)
 	struct md_rdev *rdev;
 	struct md_rdev *journal_dev = NULL;
 	sector_t reshape_offset = 0;
-	int i;
+	int i, ret = 0;
 	long long min_offset_diff = 0;
 	int first = 1;
 
-	if (mddev_init_writes_pending(mddev) < 0)
+	if (acct_bioset_init(mddev)) {
+		pr_err("md/raid456:%s: alloc acct bioset failed.\n", mdname(mddev));
 		return -ENOMEM;
+	}
+
+	if (mddev_init_writes_pending(mddev) < 0) {
+		ret = -ENOMEM;
+		goto exit_acct_set;
+	}
 
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
@@ -7482,7 +7505,8 @@ static int raid5_run(struct mddev *mddev)
 	    (mddev->bitmap_info.offset || mddev->bitmap_info.file)) {
 		pr_notice("md/raid:%s: array cannot have both journal and bitmap\n",
 			  mdname(mddev));
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit_acct_set;
 	}
 
 	if (mddev->reshape_position != MaxSector) {
@@ -7507,13 +7531,15 @@ static int raid5_run(struct mddev *mddev)
 		if (journal_dev) {
 			pr_warn("md/raid:%s: don't support reshape with journal - aborting.\n",
 				mdname(mddev));
-			return -EINVAL;
+			ret = -EINVAL;
+			goto exit_acct_set;
 		}
 
 		if (mddev->new_level != mddev->level) {
 			pr_warn("md/raid:%s: unsupported reshape required - aborting.\n",
 				mdname(mddev));
-			return -EINVAL;
+			ret = -EINVAL;
+			goto exit_acct_set;
 		}
 		old_disks = mddev->raid_disks - mddev->delta_disks;
 		/* reshape_position must be on a new-stripe boundary, and one
@@ -7529,7 +7555,8 @@ static int raid5_run(struct mddev *mddev)
 		if (sector_div(here_new, chunk_sectors * new_data_disks)) {
 			pr_warn("md/raid:%s: reshape_position not on a stripe boundary\n",
 				mdname(mddev));
-			return -EINVAL;
+			ret = -EINVAL;
+			goto exit_acct_set;
 		}
 		reshape_offset = here_new * chunk_sectors;
 		/* here_new is the stripe we will write to */
@@ -7551,7 +7578,8 @@ static int raid5_run(struct mddev *mddev)
 			else if (mddev->ro == 0) {
 				pr_warn("md/raid:%s: in-place reshape must be started in read-only mode - aborting\n",
 					mdname(mddev));
-				return -EINVAL;
+				ret = -EINVAL;
+				goto exit_acct_set;
 			}
 		} else if (mddev->reshape_backwards
 		    ? (here_new * chunk_sectors + min_offset_diff <=
@@ -7561,7 +7589,8 @@ static int raid5_run(struct mddev *mddev)
 			/* Reading from the same stripe as writing to - bad */
 			pr_warn("md/raid:%s: reshape_position too early for auto-recovery - aborting.\n",
 				mdname(mddev));
-			return -EINVAL;
+			ret = -EINVAL;
+			goto exit_acct_set;
 		}
 		pr_debug("md/raid:%s: reshape will continue\n", mdname(mddev));
 		/* OK, we should be able to continue; */
@@ -7585,8 +7614,10 @@ static int raid5_run(struct mddev *mddev)
 	else
 		conf = mddev->private;
 
-	if (IS_ERR(conf))
-		return PTR_ERR(conf);
+	if (IS_ERR(conf)) {
+		ret = PTR_ERR(conf);
+		goto exit_acct_set;
+	}
 
 	if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
 		if (!journal_dev) {
@@ -7783,7 +7814,10 @@ static int raid5_run(struct mddev *mddev)
 	free_conf(conf);
 	mddev->private = NULL;
 	pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
-	return -EIO;
+	ret = -EIO;
+exit_acct_set:
+	acct_bioset_exit(mddev);
+	return ret;
 }
 
 static void raid5_free(struct mddev *mddev, void *priv)
@@ -7791,6 +7825,7 @@ static void raid5_free(struct mddev *mddev, void *priv)
 	struct r5conf *conf = priv;
 
 	free_conf(conf);
+	acct_bioset_exit(mddev);
 	mddev->to_remove = &raid5_attrs_group;
 }
 

drivers/md/raid5.h

@@ -4,6 +4,7 @@
 
 #include <linux/raid/xor.h>
 #include <linux/dmaengine.h>
+#include <linux/local_lock.h>
 
 /*
  *
@@ -640,7 +641,8 @@ struct r5conf {
 					     * lists and performing address
 					     * conversions
 					     */
-		int scribble_obj_size;
+		int             scribble_obj_size;
+		local_lock_t    lock;
 	} __percpu *percpu;
 	int scribble_disks;
 	int scribble_sectors;

include/linux/raid/pq.h

@@ -81,7 +81,7 @@ struct raid6_calls {
 	void (*xor_syndrome)(int, int, int, size_t, void **);
 	int  (*valid)(void);	/* Returns 1 if this routine set is usable */
 	const char *name;	/* Name of this routine set */
-	int prefer;		/* Has special performance attribute */
+	int priority;		/* Relative priority ranking if non-zero */
 };
 
 /* Selected algorithm */

lib/raid6/algos.c

@@ -145,13 +145,13 @@ static inline const struct raid6_recov_calls *raid6_choose_recov(void)
 static inline const struct raid6_calls *raid6_choose_gen(
 	void *(*const dptrs)[RAID6_TEST_DISKS], const int disks)
 {
-	unsigned long perf, bestgenperf, bestxorperf, j0, j1;
+	unsigned long perf, bestgenperf, j0, j1;
 	int start = (disks>>1)-1, stop = disks-3;	/* work on the second half of the disks */
 	const struct raid6_calls *const *algo;
 	const struct raid6_calls *best;
 
-	for (bestgenperf = 0, bestxorperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
-		if (!best || (*algo)->prefer >= best->prefer) {
+	for (bestgenperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
+		if (!best || (*algo)->priority >= best->priority) {
 			if ((*algo)->valid && !(*algo)->valid())
 				continue;
 
@@ -180,50 +180,48 @@ static inline const struct raid6_calls *raid6_choose_gen(
 			pr_info("raid6: %-8s gen() %5ld MB/s\n", (*algo)->name,
 				(perf * HZ * (disks-2)) >>
 				(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2));
+		}
+	}
 
-			if (!(*algo)->xor_syndrome)
-				continue;
+	if (!best) {
+		pr_err("raid6: Yikes! No algorithm found!\n");
+		goto out;
+	}
 
-			perf = 0;
+	raid6_call = *best;
 
-			preempt_disable();
-			j0 = jiffies;
-			while ((j1 = jiffies) == j0)
-				cpu_relax();
-			while (time_before(jiffies,
-					    j1 + (1<<RAID6_TIME_JIFFIES_LG2))) {
-				(*algo)->xor_syndrome(disks, start, stop,
-						      PAGE_SIZE, *dptrs);
-				perf++;
-			}
-			preempt_enable();
-
-			if (best == *algo)
-				bestxorperf = perf;
+	if (!IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK)) {
+		pr_info("raid6: skipped pq benchmark and selected %s\n",
+			best->name);
+		goto out;
+	}
 
-			pr_info("raid6: %-8s xor() %5ld MB/s\n", (*algo)->name,
-				(perf * HZ * (disks-2)) >>
-				(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2 + 1));
+	pr_info("raid6: using algorithm %s gen() %ld MB/s\n",
+		best->name,
+		(bestgenperf * HZ * (disks - 2)) >>
+		(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2));
+
+	if (best->xor_syndrome) {
+		perf = 0;
+
+		preempt_disable();
+		j0 = jiffies;
+		while ((j1 = jiffies) == j0)
+			cpu_relax();
+		while (time_before(jiffies,
+				   j1 + (1 << RAID6_TIME_JIFFIES_LG2))) {
+			best->xor_syndrome(disks, start, stop,
+					   PAGE_SIZE, *dptrs);
+			perf++;
 		}
-	}
+		preempt_enable();
 
-	if (best) {
-		if (IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK)) {
-			pr_info("raid6: using algorithm %s gen() %ld MB/s\n",
-				best->name,
-				(bestgenperf * HZ * (disks-2)) >>
-				(20 - PAGE_SHIFT+RAID6_TIME_JIFFIES_LG2));
-			if (best->xor_syndrome)
-				pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n",
-					(bestxorperf * HZ * (disks-2)) >>
-					(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2 + 1));
-		} else
-			pr_info("raid6: skip pq benchmark and using algorithm %s\n",
-				best->name);
-		raid6_call = *best;
-	} else
-		pr_err("raid6: Yikes!  No algorithm found!\n");
+		pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n",
+			(perf * HZ * (disks - 2)) >>
+			(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2 + 1));
+	}
 
+out:
 	return best;
 }
 

lib/raid6/avx2.c

@@ -132,7 +132,7 @@ const struct raid6_calls raid6_avx2x1 = {
 	raid6_avx21_xor_syndrome,
 	raid6_have_avx2,
 	"avx2x1",
-	1			/* Has cache hints */
+	.priority = 2		/* Prefer AVX2 over priority 1 (SSE2 and others) */
 };
 
 /*
@@ -262,7 +262,7 @@ const struct raid6_calls raid6_avx2x2 = {
 	raid6_avx22_xor_syndrome,
 	raid6_have_avx2,
 	"avx2x2",
-	1			/* Has cache hints */
+	.priority = 2		/* Prefer AVX2 over priority 1 (SSE2 and others) */
 };
 
 #ifdef CONFIG_X86_64
@@ -465,6 +465,6 @@ const struct raid6_calls raid6_avx2x4 = {
 	raid6_avx24_xor_syndrome,
 	raid6_have_avx2,
 	"avx2x4",
-	1			/* Has cache hints */
+	.priority = 2		/* Prefer AVX2 over priority 1 (SSE2 and others) */
 };
-#endif
+#endif /* CONFIG_X86_64 */

lib/raid6/avx512.c

@@ -162,7 +162,7 @@ const struct raid6_calls raid6_avx512x1 = {
 	raid6_avx5121_xor_syndrome,
 	raid6_have_avx512,
 	"avx512x1",
-	1                       /* Has cache hints */
+	.priority = 2		/* Prefer AVX512 over priority 1 (SSE2 and others) */
 };
 
 /*
@@ -319,7 +319,7 @@ const struct raid6_calls raid6_avx512x2 = {
 	raid6_avx5122_xor_syndrome,
 	raid6_have_avx512,
 	"avx512x2",
-	1                       /* Has cache hints */
+	.priority = 2		/* Prefer AVX512 over priority 1 (SSE2 and others) */
 };
 
 #ifdef CONFIG_X86_64
@@ -557,7 +557,7 @@ const struct raid6_calls raid6_avx512x4 = {
 	raid6_avx5124_xor_syndrome,
 	raid6_have_avx512,
 	"avx512x4",
-	1                       /* Has cache hints */
+	.priority = 2		/* Prefer AVX512 over priority 1 (SSE2 and others) */
 };
 #endif