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()

9 files changed, 82 insertions, 13 deletions

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 34177f1bd97d..bcad9b926b0c 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -404,7 +404,6 @@ static int brd_alloc(int i)
 	/* Tell the block layer that this is not a rotational device */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, disk->queue);
 	err = add_disk(disk);
 	if (err)
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 719a7260c22b..8c2bc47de473 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1283,7 +1283,7 @@ static void one_flush_endio(struct bio *bio)
 static void submit_one_flush(struct drbd_device *device, struct issue_flush_context *ctx)
 {
 	struct bio *bio = bio_alloc(device->ldev->backing_bdev, 0,
-				    REQ_OP_FLUSH | REQ_PREFLUSH, GFP_NOIO);
+				    REQ_OP_WRITE | REQ_PREFLUSH, GFP_NOIO);
 	struct one_flush_context *octx = kmalloc(sizeof(*octx), GFP_NOIO);
 
 	if (!octx) {
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index d445fd0934bd..9c35c958f2c8 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -609,7 +609,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		request.len = htonl(size);
 	}
 	handle = nbd_cmd_handle(cmd);
-	memcpy(request.handle, &handle, sizeof(handle));
+	request.cookie = cpu_to_be64(handle);
 
 	trace_nbd_send_request(&request, nbd->index, blk_mq_rq_from_pdu(cmd));
 
@@ -621,7 +621,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	trace_nbd_header_sent(req, handle);
 	if (result < 0) {
 		if (was_interrupted(result)) {
-			/* If we havne't sent anything we can just return BUSY,
+			/* If we haven't sent anything we can just return BUSY,
 			 * however if we have sent something we need to make
 			 * sure we only allow this req to be sent until we are
 			 * completely done.
@@ -735,7 +735,7 @@ static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index,
 	u32 tag;
 	int ret = 0;
 
-	memcpy(&handle, reply->handle, sizeof(handle));
+	handle = be64_to_cpu(reply->cookie);
 	tag = nbd_handle_to_tag(handle);
 	hwq = blk_mq_unique_tag_to_hwq(tag);
 	if (hwq < nbd->tag_set.nr_hw_queues)
@@ -1805,7 +1805,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
 	 * Tell the block layer that we are not a rotational device
 	 */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 	disk->queue->limits.discard_granularity = 0;
 	blk_queue_max_discard_sectors(disk->queue, 0);
 	blk_queue_max_segment_size(disk->queue, UINT_MAX);
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index b195b8b9fe32..b3fedafe301e 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -2144,7 +2144,6 @@ static int null_add_dev(struct nullb_device *dev)
 
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
 	mutex_lock(&lock);
 	rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 6b8aa0d030f7..72a5cde9a5af 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -129,6 +129,7 @@ struct ublk_queue {
 	unsigned long io_addr;	/* mapped vm address */
 	unsigned int max_io_sz;
 	bool force_abort;
+	bool timeout;
 	unsigned short nr_io_ready;	/* how many ios setup */
 	struct ublk_device *dev;
 	struct ublk_io ios[];
@@ -898,6 +899,22 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
 	}
 }
 
+static enum blk_eh_timer_return ublk_timeout(struct request *rq)
+{
+	struct ublk_queue *ubq = rq->mq_hctx->driver_data;
+
+	if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) {
+		if (!ubq->timeout) {
+			send_sig(SIGKILL, ubq->ubq_daemon, 0);
+			ubq->timeout = true;
+		}
+
+		return BLK_EH_DONE;
+	}
+
+	return BLK_EH_RESET_TIMER;
+}
+
 static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
@@ -957,6 +974,7 @@ static const struct blk_mq_ops ublk_mq_ops = {
 	.queue_rq       = ublk_queue_rq,
 	.init_hctx	= ublk_init_hctx,
 	.init_request   = ublk_init_rq,
+	.timeout	= ublk_timeout,
 };
 
 static int ublk_ch_open(struct inode *inode, struct file *filp)
@@ -1737,6 +1755,18 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
 	else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))
 		return -EPERM;
 
+	/*
+	 * unprivileged device can't be trusted, but RECOVERY and
+	 * RECOVERY_REISSUE still may hang error handling, so can't
+	 * support recovery features for unprivileged ublk now
+	 *
+	 * TODO: provide forward progress for RECOVERY handler, so that
+	 * unprivileged device can benefit from it
+	 */
+	if (info.flags & UBLK_F_UNPRIVILEGED_DEV)
+		info.flags &= ~(UBLK_F_USER_RECOVERY_REISSUE |
+				UBLK_F_USER_RECOVERY);
+
 	/* the created device is always owned by current user */
 	ublk_store_owner_uid_gid(&info.owner_uid, &info.owner_gid);
 
@@ -2007,6 +2037,7 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq)
 	put_task_struct(ubq->ubq_daemon);
 	/* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */
 	ubq->ubq_daemon = NULL;
+	ubq->timeout = false;
 
 	for (i = 0; i < ubq->q_depth; i++) {
 		struct ublk_io *io = &ubq->ios[i];
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index a84c4268257a..f6d90f1ba5cf 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -2215,7 +2215,6 @@ static int zram_add(void)
 	/* zram devices sort of resembles non-rotational disks */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);
 
 	/*
 	 * To ensure that we always get PAGE_SIZE aligned
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;