Merge branch 'md-next' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.17/driversfor-5.17/drivers-2022-01-11

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

1 files changed, 56 insertions, 27 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7dc8026cf6ee..02db187090fa 100644
--- a/drivers/md/raid1.c
+++ b/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);