Merge tag 'for-5.14/drivers-2021-06-29' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Pretty calm round, mostly just NVMe and a bit of MD:

   - NVMe updates (via Christoph)
        - improve the APST configuration algorithm (Alexey Bogoslavsky)
        - look for StorageD3Enable on companion ACPI device
          (Mario Limonciello)
        - allow selecting the network interface for TCP connections
          (Martin Belanger)
        - misc cleanups (Amit Engel, Chaitanya Kulkarni, Colin Ian King,
          Christoph)
        - move the ACPI StorageD3 code to drivers/acpi/ and add quirks
          for certain AMD CPUs (Mario Limonciello)
        - zoned device support for nvmet (Chaitanya Kulkarni)
        - fix the rules for changing the serial number in nvmet
          (Noam Gottlieb)
        - various small fixes and cleanups (Dan Carpenter, JK Kim,
          Chaitanya Kulkarni, Hannes Reinecke, Wesley Sheng, Geert
          Uytterhoeven, Daniel Wagner)

   - MD updates (Via Song)
        - iostats rewrite (Guoqing Jiang)
        - raid5 lock contention optimization (Gal Ofri)

   - Fall through warning fix (Gustavo)

   - Misc fixes (Gustavo, Jiapeng)"

* tag 'for-5.14/drivers-2021-06-29' of git://git.kernel.dk/linux-block: (78 commits)
  nvmet: use NVMET_MAX_NAMESPACES to set nn value
  loop: Fix missing discard support when using LOOP_CONFIGURE
  nvme.h: add missing nvme_lba_range_type endianness annotations
  nvme: remove zeroout memset call for struct
  nvme-pci: remove zeroout memset call for struct
  nvmet: remove zeroout memset call for struct
  nvmet: add ZBD over ZNS backend support
  nvmet: add Command Set Identifier support
  nvmet: add nvmet_req_bio put helper for backends
  nvmet: add req cns error complete helper
  block: export blk_next_bio()
  nvmet: remove local variable
  nvmet: use nvme status value directly
  nvmet: use u32 type for the local variable nsid
  nvmet: use u32 for nvmet_subsys max_nsid
  nvmet: use req->cmd directly in file-ns fast path
  nvmet: use req->cmd directly in bdev-ns fast path
  nvmet: make ver stable once connection established
  nvmet: allow mn change if subsys not discovered
  nvmet: make sn stable once connection was established
  ...

1 files changed, 45 insertions, 18 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7d4ff8a5c55e..b8436e4930ed 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5362,11 +5362,13 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf,
  */
 static void raid5_align_endio(struct bio *bi)
 {
-	struct bio* raid_bi  = bi->bi_private;
+	struct md_io_acct *md_io_acct = bi->bi_private;
+	struct bio *raid_bi = md_io_acct->orig_bio;
 	struct mddev *mddev;
 	struct r5conf *conf;
 	struct md_rdev *rdev;
 	blk_status_t error = bi->bi_status;
+	unsigned long start_time = md_io_acct->start_time;
 
 	bio_put(bi);
 
@@ -5378,6 +5380,8 @@ static void raid5_align_endio(struct bio *bi)
 	rdev_dec_pending(rdev, conf->mddev);
 
 	if (!error) {
+		if (blk_queue_io_stat(raid_bi->bi_bdev->bd_disk->queue))
+			bio_end_io_acct(raid_bi, start_time);
 		bio_endio(raid_bi);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_quiescent);
@@ -5396,6 +5400,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	struct md_rdev *rdev;
 	sector_t sector, end_sector, first_bad;
 	int bad_sectors, dd_idx;
+	struct md_io_acct *md_io_acct;
+	bool did_inc;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
 		pr_debug("%s: non aligned\n", __func__);
@@ -5425,29 +5431,46 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio)
 	atomic_inc(&rdev->nr_pending);
 	rcu_read_unlock();
 
-	align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
-	bio_set_dev(align_bio, rdev->bdev);
-	align_bio->bi_end_io = raid5_align_endio;
-	align_bio->bi_private = raid_bio;
-	align_bio->bi_iter.bi_sector = sector;
-
-	raid_bio->bi_next = (void *)rdev;
-
-	if (is_badblock(rdev, sector, bio_sectors(align_bio), &first_bad,
+	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
 			&bad_sectors)) {
-		bio_put(align_bio);
+		bio_put(raid_bio);
 		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
 
+	align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->io_acct_set);
+	md_io_acct = container_of(align_bio, struct md_io_acct, bio_clone);
+	raid_bio->bi_next = (void *)rdev;
+	if (blk_queue_io_stat(raid_bio->bi_bdev->bd_disk->queue))
+		md_io_acct->start_time = bio_start_io_acct(raid_bio);
+	md_io_acct->orig_bio = raid_bio;
+
+	bio_set_dev(align_bio, rdev->bdev);
+	align_bio->bi_end_io = raid5_align_endio;
+	align_bio->bi_private = md_io_acct;
+	align_bio->bi_iter.bi_sector = sector;
+
 	/* No reshape active, so we can trust rdev->data_offset */
 	align_bio->bi_iter.bi_sector += rdev->data_offset;
 
-	spin_lock_irq(&conf->device_lock);
-	wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0,
-			    conf->device_lock);
-	atomic_inc(&conf->active_aligned_reads);
-	spin_unlock_irq(&conf->device_lock);
+	did_inc = false;
+	if (conf->quiesce == 0) {
+		atomic_inc(&conf->active_aligned_reads);
+		did_inc = true;
+	}
+	/* need a memory barrier to detect the race with raid5_quiesce() */
+	if (!did_inc || smp_load_acquire(&conf->quiesce) != 0) {
+		/* quiesce is in progress, so we need to undo io activation and wait
+		 * for it to finish
+		 */
+		if (did_inc && atomic_dec_and_test(&conf->active_aligned_reads))
+			wake_up(&conf->wait_for_quiescent);
+		spin_lock_irq(&conf->device_lock);
+		wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0,
+				    conf->device_lock);
+		atomic_inc(&conf->active_aligned_reads);
+		spin_unlock_irq(&conf->device_lock);
+	}
 
 	if (mddev->gendisk)
 		trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
@@ -5796,6 +5819,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 
+	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)) {
 		int previous;
@@ -6928,7 +6952,7 @@ static struct attribute *raid5_attrs[] =  {
 	&ppl_write_hint.attr,
 	NULL,
 };
-static struct attribute_group raid5_attrs_group = {
+static const struct attribute_group raid5_attrs_group = {
 	.name = NULL,
 	.attrs = raid5_attrs,
 };
@@ -8334,7 +8358,10 @@ static void raid5_quiesce(struct mddev *mddev, int quiesce)
 		 * active stripes can drain
 		 */
 		r5c_flush_cache(conf, INT_MAX);
-		conf->quiesce = 2;
+		/* need a memory barrier to make sure read_one_chunk() sees
+		 * quiesce started and reverts to slow (locked) path.
+		 */
+		smp_store_release(&conf->quiesce, 2);
 		wait_event_cmd(conf->wait_for_quiescent,
 				    atomic_read(&conf->active_stripes) == 0 &&
 				    atomic_read(&conf->active_aligned_reads) == 0,