Merge tag 'for-6.4/block-2023-05-06' of git://git.kernel.dk/linux

Pull more block updates from Jens Axboe:

 - MD pull request via Song:
      - Improve raid5 sequential IO performance on spinning disks, which
        fixes a regression since v6.0 (Jan Kara)
      - Fix bitmap offset types, which fixes an issue introduced in this
        merge window (Jonathan Derrick)

 - Cleanup of hweight type used for cgroup writeback (Maxim)

 - Fix a regression with the "has_submit_bio" changes across partitions
   (Ming)

 - Cleanup of QUEUE_FLAG_ADD_RANDOM clearing.

   We used to set this flag on queues non blk-mq queues, and hence some
   drivers clear it unconditionally. Since all of these have since been
   converted to true blk-mq drivers, drop the useless clear as the bit
   is not set (Chaitanya)

 - Fix the flags being set in a bio for a flush for drbd (Christoph)

 - Cleanup and deduplication of the code handling setting block device
   capacity (Damien)

 - Fix for ublk handling IO timeouts (Ming)

 - Fix for a regression in blk-cgroup teardown (Tao)

 - NBD documentation and code fixes (Eric)

 - Convert blk-integrity to using device_attributes rather than a second
   kobject to manage lifetimes (Thomas)

* tag 'for-6.4/block-2023-05-06' of git://git.kernel.dk/linux:
  ublk: add timeout handler
  drbd: correctly submit flush bio on barrier
  mailmap: add mailmap entries for Jens Axboe
  block: Skip destroyed blkg when restart in blkg_destroy_all()
  writeback: fix call of incorrect macro
  md: Fix bitmap offset type in sb writer
  md/raid5: Improve performance for sequential IO
  docs nbd: userspace NBD now favors github over sourceforge
  block nbd: use req.cookie instead of req.handle
  uapi nbd: add cookie alias to handle
  uapi nbd: improve doc links to userspace spec
  blk-integrity: register sysfs attributes on struct device
  blk-integrity: convert to struct device_attribute
  blk-integrity: use sysfs_emit
  block/drivers: remove dead clear of random flag
  block: sync part's ->bd_has_submit_bio with disk's
  block: Cleanup set_capacity()/bdev_set_nr_sectors()

3 files changed, 47 insertions, 5 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index ba3909bb6bea..7e9d19fd21dd 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -971,7 +971,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	}
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, d->disk->queue);
 
 	blk_queue_write_cache(q, true, true);
 
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 920bb68156d2..bc8d7565171d 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -219,7 +219,7 @@ static unsigned int optimal_io_size(struct block_device *bdev,
 }
 
 static unsigned int bitmap_io_size(unsigned int io_size, unsigned int opt_size,
-				   sector_t start, sector_t boundary)
+				   loff_t start, loff_t boundary)
 {
 	if (io_size != opt_size &&
 	    start + opt_size / SECTOR_SIZE <= boundary)
@@ -237,8 +237,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 	struct block_device *bdev;
 	struct mddev *mddev = bitmap->mddev;
 	struct bitmap_storage *store = &bitmap->storage;
-	sector_t offset = mddev->bitmap_info.offset;
-	sector_t ps, sboff, doff;
+	loff_t sboff, offset = mddev->bitmap_info.offset;
+	sector_t ps, doff;
 	unsigned int size = PAGE_SIZE;
 	unsigned int opt_size = PAGE_SIZE;
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 812a12e3e41a..4739ed891e75 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6079,6 +6079,38 @@ out_release:
 	return ret;
 }
 
+/*
+ * If the bio covers multiple data disks, find sector within the bio that has
+ * the lowest chunk offset in the first chunk.
+ */
+static sector_t raid5_bio_lowest_chunk_sector(struct r5conf *conf,
+					      struct bio *bi)
+{
+	int sectors_per_chunk = conf->chunk_sectors;
+	int raid_disks = conf->raid_disks;
+	int dd_idx;
+	struct stripe_head sh;
+	unsigned int chunk_offset;
+	sector_t r_sector = bi->bi_iter.bi_sector & ~((sector_t)RAID5_STRIPE_SECTORS(conf)-1);
+	sector_t sector;
+
+	/* We pass in fake stripe_head to get back parity disk numbers */
+	sector = raid5_compute_sector(conf, r_sector, 0, &dd_idx, &sh);
+	chunk_offset = sector_div(sector, sectors_per_chunk);
+	if (sectors_per_chunk - chunk_offset >= bio_sectors(bi))
+		return r_sector;
+	/*
+	 * Bio crosses to the next data disk. Check whether it's in the same
+	 * chunk.
+	 */
+	dd_idx++;
+	while (dd_idx == sh.pd_idx || dd_idx == sh.qd_idx)
+		dd_idx++;
+	if (dd_idx >= raid_disks)
+		return r_sector;
+	return r_sector + sectors_per_chunk - chunk_offset;
+}
+
 static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -6150,6 +6182,17 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 	}
 	md_account_bio(mddev, &bi);
 
+	/*
+	 * Lets start with the stripe with the lowest chunk offset in the first
+	 * chunk. That has the best chances of creating IOs adjacent to
+	 * previous IOs in case of sequential IO and thus creates the most
+	 * sequential IO pattern. We don't bother with the optimization when
+	 * reshaping as the performance benefit is not worth the complexity.
+	 */
+	if (likely(conf->reshape_progress == MaxSector))
+		logical_sector = raid5_bio_lowest_chunk_sector(conf, bi);
+	s = (logical_sector - ctx.first_sector) >> RAID5_STRIPE_SHIFT(conf);
+
 	add_wait_queue(&conf->wait_for_overlap, &wait);
 	while (1) {
 		res = make_stripe_request(mddev, conf, &ctx, logical_sector,
@@ -6178,7 +6221,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 			continue;
 		}
 
-		s = find_first_bit(ctx.sectors_to_do, stripe_cnt);
+		s = find_next_bit_wrap(ctx.sectors_to_do, stripe_cnt, s);
 		if (s == stripe_cnt)
 			break;