Merge tag 'for-5.17/drivers-2022-01-11' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - mtip32xx pci cleanups (Bjorn)

 - mtip32xx conversion to generic power management (Vaibhav)

 - rsxx pci powermanagement cleanups (Bjorn)

 - Remove the rsxx driver. This hardware never saw much adoption, and
   it's been end of lifed for a while. (Christoph)

 - MD pull request from Song:
      - REQ_NOWAIT support (Vishal Verma)
      - raid6 benchmark optimization (Dirk Müller)
      - Fix for acct bioset (Xiao Ni)
      - Clean up max_queued_requests (Mariusz Tkaczyk)
      - PREEMPT_RT optimization (Davidlohr Bueso)
      - Use default_groups in kobj_type (Greg Kroah-Hartman)

 - Use attribute groups in pktcdvd and rnbd (Greg)

 - NVMe pull request from Christoph:
      - increment request genctr on completion (Keith Busch, Geliang
        Tang)
      - add a 'iopolicy' module parameter (Hannes Reinecke)
      - print out valid arguments when reading from /dev/nvme-fabrics
        (Hannes Reinecke)

 - Use struct_group() in drbd (Kees)

 - null_blk fixes (Ming)

 - Get rid of congestion logic in pktcdvd (Neil)

 - Floppy ejection hang fix (Tasos)

 - Floppy max user request size fix (Xiongwei)

 - Loop locking fix (Tetsuo)

* tag 'for-5.17/drivers-2022-01-11' of git://git.kernel.dk/linux-block: (32 commits)
  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
  block/rnbd-clt-sysfs: use default_groups in kobj_type
  pktcdvd: convert to use attribute groups
  block: null_blk: only set set->nr_maps as 3 if active poll_queues is > 0
  nvme: add 'iopolicy' module parameter
  nvme: drop unused variable ctrl in nvme_setup_cmd
  nvme: increment request genctr on completion
  nvme-fabrics: print out valid arguments when reading from /dev/nvme-fabrics
  block: remove the rsxx driver
  rsxx: Drop PCI legacy power management
  ...

1 files changed, 67 insertions, 40 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index dde98f65bd04..2b969f70a31f 100644
--- a/drivers/md/raid10.c
+++ b/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 @@ retry_wait:
 		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 @@ retry_discard:
 		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);