Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round for this release. This contains:

   - Add support for zoned storage to ublk (Andreas, Ming)

   - Series improving performance for drivers that mark themselves as
     needing a blocking context for issue (Bart)

   - Cleanup the flush logic (Chengming)

   - sed opal keyring support (Greg)

   - Fixes and improvements to the integrity support (Jinyoung)

   - Add some exports for bcachefs that we can hopefully delete again in
     the future (Kent)

   - deadline throttling fix (Zhiguo)

   - Series allowing building the kernel without buffer_head support
     (Christoph)

   - Sanitize the bio page adding flow (Christoph)

   - Write back cache fixes (Christoph)

   - MD updates via Song:
      - Fix perf regression for raid0 large sequential writes (Jan)
      - Fix split bio iostat for raid0 (David)
      - Various raid1 fixes (Heinz, Xueshi)
      - raid6test build fixes (WANG)
      - Deprecate bitmap file support (Christoph)
      - Fix deadlock with md sync thread (Yu)
      - Refactor md io accounting (Yu)
      - Various non-urgent fixes (Li, Yu, Jack)

   - Various fixes and cleanups (Arnd, Azeem, Chengming, Damien, Li,
     Ming, Nitesh, Ruan, Tejun, Thomas, Xu)"

* tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux: (113 commits)
  block: use strscpy() to instead of strncpy()
  block: sed-opal: keyring support for SED keys
  block: sed-opal: Implement IOC_OPAL_REVERT_LSP
  block: sed-opal: Implement IOC_OPAL_DISCOVERY
  blk-mq: prealloc tags when increase tagset nr_hw_queues
  blk-mq: delete redundant tagset map update when fallback
  blk-mq: fix tags leak when shrink nr_hw_queues
  ublk: zoned: support REQ_OP_ZONE_RESET_ALL
  md: raid0: account for split bio in iostat accounting
  md/raid0: Fix performance regression for large sequential writes
  md/raid0: Factor out helper for mapping and submitting a bio
  md raid1: allow writebehind to work on any leg device set WriteMostly
  md/raid1: hold the barrier until handle_read_error() finishes
  md/raid1: free the r1bio before waiting for blocked rdev
  md/raid1: call free_r1bio() before allow_barrier() in raid_end_bio_io()
  blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init
  drivers/rnbd: restore sysfs interface to rnbd-client
  md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid()
  raid6: test: only check for Altivec if building on powerpc hosts
  raid6: test: make sure all intermediate and artifact files are .gitignored
  ...

1 files changed, 50 insertions, 36 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index dd25832eb045..4b30a1742162 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -304,8 +304,6 @@ static void call_bio_endio(struct r1bio *r1_bio)
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
 		bio->bi_status = BLK_STS_IOERR;
 
-	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		bio_end_io_acct(bio, r1_bio->start_time);
 	bio_endio(bio);
 }
 
@@ -313,6 +311,7 @@ static void raid_end_bio_io(struct r1bio *r1_bio)
 {
 	struct bio *bio = r1_bio->master_bio;
 	struct r1conf *conf = r1_bio->mddev->private;
+	sector_t sector = r1_bio->sector;
 
 	/* if nobody has done the final endio yet, do it now */
 	if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
@@ -323,13 +322,13 @@ static void raid_end_bio_io(struct r1bio *r1_bio)
 
 		call_bio_endio(r1_bio);
 	}
+
+	free_r1bio(r1_bio);
 	/*
 	 * Wake up any possible resync thread that waits for the device
 	 * to go idle.  All I/Os, even write-behind writes, are done.
 	 */
-	allow_barrier(conf, r1_bio->sector);
-
-	free_r1bio(r1_bio);
+	allow_barrier(conf, sector);
 }
 
 /*
@@ -791,11 +790,17 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
+static void wake_up_barrier(struct r1conf *conf)
+{
+	if (wq_has_sleeper(&conf->wait_barrier))
+		wake_up(&conf->wait_barrier);
+}
+
 static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 {
 	/* flush any pending bitmap writes to disk before proceeding w/ I/O */
 	raid1_prepare_flush_writes(conf->mddev->bitmap);
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
@@ -972,7 +977,7 @@ static bool _wait_barrier(struct r1conf *conf, int idx, bool nowait)
 	 * In case freeze_array() is waiting for
 	 * get_unqueued_pending() == extra
 	 */
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 	/* Wait for the barrier in same barrier unit bucket to drop. */
 
 	/* Return false when nowait flag is set */
@@ -1015,7 +1020,7 @@ static bool wait_read_barrier(struct r1conf *conf, sector_t sector_nr, bool nowa
 	 * In case freeze_array() is waiting for
 	 * get_unqueued_pending() == extra
 	 */
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 	/* Wait for array to be unfrozen */
 
 	/* Return false when nowait flag is set */
@@ -1044,7 +1049,7 @@ static bool wait_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait)
 static void _allow_barrier(struct r1conf *conf, int idx)
 {
 	atomic_dec(&conf->nr_pending[idx]);
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 }
 
 static void allow_barrier(struct r1conf *conf, sector_t sector_nr)
@@ -1173,7 +1178,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
 		spin_lock_irq(&conf->device_lock);
 		bio_list_merge(&conf->pending_bio_list, &plug->pending);
 		spin_unlock_irq(&conf->device_lock);
-		wake_up(&conf->wait_barrier);
+		wake_up_barrier(conf);
 		md_wakeup_thread(mddev->thread);
 		kfree(plug);
 		return;
@@ -1303,10 +1308,10 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	r1_bio->read_disk = rdisk;
-
-	if (!r1bio_existed && blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		r1_bio->start_time = bio_start_io_acct(bio);
-
+	if (!r1bio_existed) {
+		md_account_bio(mddev, &bio);
+		r1_bio->master_bio = bio;
+	}
 	read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp,
 				   &mddev->bio_set);
 
@@ -1373,6 +1378,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		return;
 	}
 
+ retry_write:
 	r1_bio = alloc_r1bio(mddev, bio);
 	r1_bio->sectors = max_write_sectors;
 
@@ -1388,7 +1394,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	 */
 
 	disks = conf->raid_disks * 2;
- retry_write:
 	blocked_rdev = NULL;
 	rcu_read_lock();
 	max_sectors = r1_bio->sectors;
@@ -1468,7 +1473,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		for (j = 0; j < i; j++)
 			if (r1_bio->bios[j])
 				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
-		r1_bio->state = 0;
+		free_r1bio(r1_bio);
 		allow_barrier(conf, bio->bi_iter.bi_sector);
 
 		if (bio->bi_opf & REQ_NOWAIT) {
@@ -1500,8 +1505,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		r1_bio->sectors = max_sectors;
 	}
 
-	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
-		r1_bio->start_time = bio_start_io_acct(bio);
+	md_account_bio(mddev, &bio);
+	r1_bio->master_bio = bio;
 	atomic_set(&r1_bio->remaining, 1);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
@@ -1518,8 +1523,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 			 * Not if there are too many, or cannot
 			 * allocate memory, or a reader on WriteMostly
 			 * is waiting for behind writes to flush */
-			if (bitmap &&
-			    test_bit(WriteMostly, &rdev->flags) &&
+			if (bitmap && write_behind &&
 			    (atomic_read(&bitmap->behind_writes)
 			     < mddev->bitmap_info.max_write_behind) &&
 			    !waitqueue_active(&bitmap->behind_wait)) {
@@ -1576,7 +1580,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	r1_bio_write_done(r1_bio);
 
 	/* In case raid1d snuck in to freeze_array */
-	wake_up(&conf->wait_barrier);
+	wake_up_barrier(conf);
 }
 
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
@@ -1766,7 +1770,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
 	int err = -EEXIST;
-	int mirror = 0;
+	int mirror = 0, repl_slot = -1;
 	struct raid1_info *p;
 	int first = 0;
 	int last = conf->raid_disks - 1;
@@ -1809,17 +1813,21 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			break;
 		}
 		if (test_bit(WantReplacement, &p->rdev->flags) &&
-		    p[conf->raid_disks].rdev == NULL) {
-			/* Add this device as a replacement */
-			clear_bit(In_sync, &rdev->flags);
-			set_bit(Replacement, &rdev->flags);
-			rdev->raid_disk = mirror;
-			err = 0;
-			conf->fullsync = 1;
-			rcu_assign_pointer(p[conf->raid_disks].rdev, rdev);
-			break;
-		}
+		    p[conf->raid_disks].rdev == NULL && repl_slot < 0)
+			repl_slot = mirror;
 	}
+
+	if (err && repl_slot >= 0) {
+		/* Add this device as a replacement */
+		p = conf->mirrors + repl_slot;
+		clear_bit(In_sync, &rdev->flags);
+		set_bit(Replacement, &rdev->flags);
+		rdev->raid_disk = repl_slot;
+		err = 0;
+		conf->fullsync = 1;
+		rcu_assign_pointer(p[conf->raid_disks].rdev, rdev);
+	}
+
 	print_conf(conf);
 	return err;
 }
@@ -1829,6 +1837,10 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct r1conf *conf = mddev->private;
 	int err = 0;
 	int number = rdev->raid_disk;
+
+	if (unlikely(number >= conf->raid_disks))
+		goto abort;
+
 	struct raid1_info *p = conf->mirrors + number;
 
 	if (rdev != p->rdev)
@@ -2299,7 +2311,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d++;
 			if (d == conf->raid_disks * 2)
 				d = 0;
-		} while (!success && d != read_disk);
+		} while (d != read_disk);
 
 		if (!success) {
 			/* Cannot read from anywhere - mark it bad */
@@ -2498,6 +2510,7 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	struct mddev *mddev = conf->mddev;
 	struct bio *bio;
 	struct md_rdev *rdev;
+	sector_t sector;
 
 	clear_bit(R1BIO_ReadError, &r1_bio->state);
 	/* we got a read error. Maybe the drive is bad.  Maybe just
@@ -2527,12 +2540,13 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	}
 
 	rdev_dec_pending(rdev, conf->mddev);
-	allow_barrier(conf, r1_bio->sector);
+	sector = r1_bio->sector;
 	bio = r1_bio->master_bio;
 
 	/* Reuse the old r1_bio so that the IO_BLOCKED settings are preserved */
 	r1_bio->state = 0;
 	raid1_read_request(mddev, bio, r1_bio->sectors, r1_bio);
+	allow_barrier(conf, sector);
 }
 
 static void raid1d(struct md_thread *thread)
@@ -3144,7 +3158,7 @@ static int raid1_run(struct mddev *mddev)
 	 * RAID1 needs at least one disk in active
 	 */
 	if (conf->raid_disks - mddev->degraded < 1) {
-		md_unregister_thread(&conf->thread);
+		md_unregister_thread(mddev, &conf->thread);
 		ret = -EINVAL;
 		goto abort;
 	}
@@ -3171,7 +3185,7 @@ static int raid1_run(struct mddev *mddev)
 
 	ret = md_integrity_register(mddev);
 	if (ret) {
-		md_unregister_thread(&mddev->thread);
+		md_unregister_thread(mddev, &mddev->thread);
 		goto abort;
 	}
 	return 0;