Merge tag 'for-5.20/block-2022-08-04' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - add support for In-Band authentication (Hannes Reinecke)
      - handle the persistent internal error AER (Michael Kelley)
      - use in-capsule data for TCP I/O queue connect (Caleb Sander)
      - remove timeout for getting RDMA-CM established event (Israel
        Rukshin)
      - misc cleanups (Joel Granados, Sagi Grimberg, Chaitanya Kulkarni,
        Guixin Liu, Xiang wangx)
      - use command_id instead of req->tag in trace_nvme_complete_rq()
        (Bean Huo)
      - various fixes for the new authentication code (Lukas Bulwahn,
        Dan Carpenter, Colin Ian King, Chaitanya Kulkarni, Hannes
        Reinecke)
      - small cleanups (Liu Song, Christoph Hellwig)
      - restore compat_ioctl support (Nick Bowler)
      - make a nvmet-tcp workqueue lockdep-safe (Sagi Grimberg)
      - enable generic interface (/dev/ngXnY) for unknown command sets
        (Joel Granados, Christoph Hellwig)
      - don't always build constants.o (Christoph Hellwig)
      - print the command name of aborted commands (Christoph Hellwig)

 - MD pull requests via Song:
      - Improve raid5 lock contention, by Logan Gunthorpe.
      - Misc fixes to raid5, by Logan Gunthorpe.
      - Fix race condition with md_reap_sync_thread(), by Guoqing Jiang.
      - Fix potential deadlock with raid5_quiesce and
        raid5_get_active_stripe, by Logan Gunthorpe.
      - Refactoring md_alloc(), by Christoph"
      - Fix md disk_name lifetime problems, by Christoph Hellwig
      - Convert prepare_to_wait() to wait_woken() api, by Logan
        Gunthorpe;
      - Fix sectors_to_do bitmap issue, by Logan Gunthorpe.

 - Work on unifying the null_blk module parameters and configfs API
   (Vincent)

 - drbd bitmap IO error fix (Lars)

 - Set of rnbd fixes (Guoqing, Md Haris)

 - Remove experimental marker on bcache async device registration (Coly)

 - Series from cleaning up the bio splitting (Christoph)

 - Removal of the sx8 block driver. This hardware never really
   widespread, and it didn't receive a lot of attention after the
   initial merge of it back in 2005 (Christoph)

 - A few fixes for s390 dasd (Eric, Jiang)

 - Followup set of fixes for ublk (Ming)

 - Support for UBLK_IO_NEED_GET_DATA for ublk (ZiyangZhang)

 - Fixes for the dio dma alignment (Keith)

 - Misc fixes and cleanups (Ming, Yu, Dan, Christophe

* tag 'for-5.20/block-2022-08-04' of git://git.kernel.dk/linux-block: (136 commits)
  s390/dasd: Establish DMA alignment
  s390/dasd: drop unexpected word 'for' in comments
  ublk_drv: add support for UBLK_IO_NEED_GET_DATA
  ublk_cmd.h: add one new ublk command: UBLK_IO_NEED_GET_DATA
  ublk_drv: cleanup ublksrv_ctrl_dev_info
  ublk_drv: add SET_PARAMS/GET_PARAMS control command
  ublk_drv: fix ublk device leak in case that add_disk fails
  ublk_drv: cancel device even though disk isn't up
  block: fix leaking page ref on truncated direct io
  block: ensure bio_iov_add_page can't fail
  block: ensure iov_iter advances for added pages
  drivers:md:fix a potential use-after-free bug
  md/raid5: Ensure batch_last is released before sleeping for quiesce
  md/raid5: Move stripe_request_ctx up
  md/raid5: Drop unnecessary call to r5c_check_stripe_cache_usage()
  md/raid5: Make is_inactive_blocked() helper
  md/raid5: Refactor raid5_get_active_stripe()
  block: pass struct queue_limits to the bio splitting helpers
  block: move bio_allowed_max_sectors to blk-merge.c
  block: move the call to get_max_io_size out of blk_bio_segment_split
  ...

Author: torvalds

Documentation/block/null_blk.rst

@@ -72,6 +72,28 @@ submit_queues=[1..nr_cpus]: Default: 1
 hw_queue_depth=[0..qdepth]: Default: 64
   The hardware queue depth of the device.
 
+memory_backed=[0/1]: Default: 0
+  Whether or not to use a memory buffer to respond to IO requests
+
+  =  =============================================
+  0  Transfer no data in response to IO requests
+  1  Use a memory buffer to respond to IO requests
+  =  =============================================
+
+discard=[0/1]: Default: 0
+  Support discard operations (requires memory-backed null_blk device).
+
+  =  =====================================
+  0  Do not support discard operations
+  1  Enable support for discard operations
+  =  =====================================
+
+cache_size=[Size in MB]: Default: 0
+  Cache size in MB for memory-backed device.
+
+mbps=[Maximum bandwidth in MB/s]: Default: 0 (no limit)
+  Bandwidth limit for device performance.
+
 Multi-queue specific parameters
 -------------------------------
 

MAINTAINERS

@@ -14507,7 +14507,8 @@ S:	Supported
 W:	http://git.infradead.org/nvme.git
 T:	git://git.infradead.org/nvme.git
 F:	drivers/nvme/host/
-F:	include/linux/nvme.h
+F:	drivers/nvme/common/
+F:	include/linux/nvme*
 F:	include/uapi/linux/nvme_ioctl.h
 
 NVM EXPRESS FC TRANSPORT DRIVERS
@@ -18838,6 +18839,7 @@ SOFTWARE RAID (Multiple Disks) SUPPORT
 M:	Song Liu <[email protected]>
 L:	[email protected]
 S:	Supported
+Q:	https://patchwork.kernel.org/project/linux-raid/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/song/md.git
 F:	drivers/md/Kconfig
 F:	drivers/md/Makefile

block/bio-integrity.c

@@ -134,7 +134,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 	iv = bip->bip_vec + bip->bip_vcnt;
 
 	if (bip->bip_vcnt &&
-	    bvec_gap_to_prev(bdev_get_queue(bio->bi_bdev),
+	    bvec_gap_to_prev(&bdev_get_queue(bio->bi_bdev)->limits,
 			     &bip->bip_vec[bip->bip_vcnt - 1], offset))
 		return 0;
 

block/bio.c

@@ -965,7 +965,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		 * would create a gap, disallow it.
 		 */
 		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
-		if (bvec_gap_to_prev(q, bvec, offset))
+		if (bvec_gap_to_prev(&q->limits, bvec, offset))
 			return 0;
 	}
 
@@ -1151,22 +1151,12 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio_set_flag(bio, BIO_CLONED);
 }
 
-static void bio_put_pages(struct page **pages, size_t size, size_t off)
-{
-	size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE);
-
-	for (i = 0; i < nr; i++)
-		put_page(pages[i]);
-}
-
 static int bio_iov_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int offset)
 {
 	bool same_page = false;
 
 	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
-		if (WARN_ON_ONCE(bio_full(bio, len)))
-			return -EINVAL;
 		__bio_add_page(bio, page, len, offset);
 		return 0;
 	}
@@ -1209,8 +1199,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
 	ssize_t size, left;
-	unsigned len, i;
+	unsigned len, i = 0;
 	size_t offset;
+	int ret = 0;
 
 	/*
 	 * Move page array up in the allocated memory for the bio vecs as far as
@@ -1227,32 +1218,40 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	 * result to ensure the bio's total size is correct. The remainder of
 	 * the iov data will be picked up in the next bio iteration.
 	 */
-	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
-	if (size > 0)
+	size = iov_iter_get_pages(iter, pages, UINT_MAX - bio->bi_iter.bi_size,
+				  nr_pages, &offset);
+	if (size > 0) {
+		nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
 		size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev));
-	if (unlikely(size <= 0))
-		return size ? size : -EFAULT;
+	} else
+		nr_pages = 0;
+
+	if (unlikely(size <= 0)) {
+		ret = size ? size : -EFAULT;
+		goto out;
+	}
 
 	for (left = size, i = 0; left > 0; left -= len, i++) {
 		struct page *page = pages[i];
-		int ret;
 
 		len = min_t(size_t, PAGE_SIZE - offset, left);
-		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 			ret = bio_iov_add_zone_append_page(bio, page, len,
 					offset);
-		else
-			ret = bio_iov_add_page(bio, page, len, offset);
+			if (ret)
+				break;
+		} else
+			bio_iov_add_page(bio, page, len, offset);
 
-		if (ret) {
-			bio_put_pages(pages + i, left, offset);
-			return ret;
-		}
 		offset = 0;
 	}
 
-	iov_iter_advance(iter, size);
-	return 0;
+	iov_iter_advance(iter, size - left);
+out:
+	while (i < nr_pages)
+		put_page(pages[i++]);
+
+	return ret;
 }
 
 /**

block/blk-core.c

@@ -377,7 +377,6 @@ static void blk_timeout_work(struct work_struct *work)
 struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 {
 	struct request_queue *q;
-	int ret;
 
 	q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu),
 			GFP_KERNEL | __GFP_ZERO, node_id);
@@ -396,13 +395,9 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 	if (q->id < 0)
 		goto fail_srcu;
 
-	ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0);
-	if (ret)
-		goto fail_id;
-
 	q->stats = blk_alloc_queue_stats();
 	if (!q->stats)
-		goto fail_split;
+		goto fail_id;
 
 	q->node = node_id;
 
@@ -439,8 +434,6 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu)
 
 fail_stats:
 	blk_free_queue_stats(q->stats);
-fail_split:
-	bioset_exit(&q->bio_split);
 fail_id:
 	ida_free(&blk_queue_ida, q->id);
 fail_srcu: