Merge tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - ublk updates:
      - Add support for updating the size of a ublk instance
      - Zero-copy improvements
      - Auto-registering of buffers for zero-copy
      - Series simplifying and improving GET_DATA and request lookup
      - Series adding quiesce support
      - Lots of selftests additions
      - Various cleanups

 - NVMe updates via Christoph:
      - add per-node DMA pools and use them for PRP/SGL allocations
        (Caleb Sander Mateos, Keith Busch)
      - nvme-fcloop refcounting fixes (Daniel Wagner)
      - support delayed removal of the multipath node and optionally
        support the multipath node for private namespaces (Nilay Shroff)
      - support shared CQs in the PCI endpoint target code (Wilfred
        Mallawa)
      - support admin-queue only authentication (Hannes Reinecke)
      - use the crc32c library instead of the crypto API (Eric Biggers)
      - misc cleanups (Christoph Hellwig, Marcelo Moreira, Hannes
        Reinecke, Leon Romanovsky, Gustavo A. R. Silva)

 - MD updates via Yu:
      - Fix that normal IO can be starved by sync IO, found by mkfs on
        newly created large raid5, with some clean up patches for bdev
        inflight counters

 - Clean up brd, getting rid of atomic kmaps and bvec poking

 - Add loop driver specifically for zoned IO testing

 - Eliminate blk-rq-qos calls with a static key, if not enabled

 - Improve hctx locking for when a plug has IO for multiple queues
   pending

 - Remove block layer bouncing support, which in turn means we can
   remove the per-node bounce stat as well

 - Improve blk-throttle support

 - Improve delay support for blk-throttle

 - Improve brd discard support

 - Unify IO scheduler switching. This should also fix a bunch of lockdep
   warnings we've been seeing, after enabling lockdep support for queue
   freezing/unfreezeing

 - Add support for block write streams via FDP (flexible data placement)
   on NVMe

 - Add a bunch of block helpers, facilitating the removal of a bunch of
   duplicated boilerplate code

 - Remove obsolete BLK_MQ pci and virtio Kconfig options

 - Add atomic/untorn write support to blktrace

 - Various little cleanups and fixes

* tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux: (186 commits)
  selftests: ublk: add test for UBLK_F_QUIESCE
  ublk: add feature UBLK_F_QUIESCE
  selftests: ublk: add test case for UBLK_U_CMD_UPDATE_SIZE
  traceevent/block: Add REQ_ATOMIC flag to block trace events
  ublk: run auto buf unregisgering in same io_ring_ctx with registering
  io_uring: add helper io_uring_cmd_ctx_handle()
  ublk: remove io argument from ublk_auto_buf_reg_fallback()
  ublk: handle ublk_set_auto_buf_reg() failure correctly in ublk_fetch()
  selftests: ublk: add test for covering UBLK_AUTO_BUF_REG_FALLBACK
  selftests: ublk: support UBLK_F_AUTO_BUF_REG
  ublk: support UBLK_AUTO_BUF_REG_FALLBACK
  ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG
  ublk: prepare for supporting to register request buffer automatically
  ublk: convert to refcount_t
  selftests: ublk: make IO & device removal test more stressful
  nvme: rename nvme_mpath_shutdown_disk to nvme_mpath_remove_disk
  nvme: introduce multipath_always_on module param
  nvme-multipath: introduce delayed removal of the multipath head node
  nvme-pci: derive and better document max segments limits
  nvme-pci: use struct_size for allocation struct nvme_dev
  ...

1 files changed, 126 insertions, 32 deletions

diff --git a/block/bio.c b/block/bio.c
index 4be592d37fb6..3c0a558c90f5 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -251,6 +251,7 @@ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
 	bio->bi_flags = 0;
 	bio->bi_ioprio = 0;
 	bio->bi_write_hint = 0;
+	bio->bi_write_stream = 0;
 	bio->bi_status = 0;
 	bio->bi_iter.bi_sector = 0;
 	bio->bi_iter.bi_size = 0;
@@ -827,6 +828,7 @@ static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
 	bio_set_flag(bio, BIO_CLONED);
 	bio->bi_ioprio = bio_src->bi_ioprio;
 	bio->bi_write_hint = bio_src->bi_write_hint;
+	bio->bi_write_stream = bio_src->bi_write_stream;
 	bio->bi_iter = bio_src->bi_iter;
 
 	if (bio->bi_bdev) {
@@ -918,7 +920,7 @@ static inline bool bio_full(struct bio *bio, unsigned len)
 }
 
 static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
-		unsigned int len, unsigned int off, bool *same_page)
+		unsigned int len, unsigned int off)
 {
 	size_t bv_end = bv->bv_offset + bv->bv_len;
 	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
@@ -931,9 +933,7 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
 	if (!zone_device_pages_have_same_pgmap(bv->bv_page, page))
 		return false;
 
-	*same_page = ((vec_end_addr & PAGE_MASK) == ((page_addr + off) &
-		     PAGE_MASK));
-	if (!*same_page) {
+	if ((vec_end_addr & PAGE_MASK) != ((page_addr + off) & PAGE_MASK)) {
 		if (IS_ENABLED(CONFIG_KMSAN))
 			return false;
 		if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE)
@@ -953,8 +953,7 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
  * helpers to split.  Hopefully this will go away soon.
  */
 bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
-		struct page *page, unsigned len, unsigned offset,
-		bool *same_page)
+		struct page *page, unsigned len, unsigned offset)
 {
 	unsigned long mask = queue_segment_boundary(q);
 	phys_addr_t addr1 = bvec_phys(bv);
@@ -964,7 +963,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
 		return false;
 	if (len > queue_max_segment_size(q) - bv->bv_len)
 		return false;
-	return bvec_try_merge_page(bv, page, len, offset, same_page);
+	return bvec_try_merge_page(bv, page, len, offset);
 }
 
 /**
@@ -990,6 +989,22 @@ void __bio_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL_GPL(__bio_add_page);
 
 /**
+ * bio_add_virt_nofail - add data in the direct kernel mapping to a bio
+ * @bio: destination bio
+ * @vaddr: data to add
+ * @len: length of the data to add, may cross pages
+ *
+ * Add the data at @vaddr to @bio.  The caller must have ensure a segment
+ * is available for the added data.  No merging into an existing segment
+ * will be performed.
+ */
+void bio_add_virt_nofail(struct bio *bio, void *vaddr, unsigned len)
+{
+	__bio_add_page(bio, virt_to_page(vaddr), len, offset_in_page(vaddr));
+}
+EXPORT_SYMBOL_GPL(bio_add_virt_nofail);
+
+/**
  *	bio_add_page	-	attempt to add page(s) to bio
  *	@bio: destination bio
  *	@page: start page to add
@@ -1002,8 +1017,6 @@ EXPORT_SYMBOL_GPL(__bio_add_page);
 int bio_add_page(struct bio *bio, struct page *page,
 		 unsigned int len, unsigned int offset)
 {
-	bool same_page = false;
-
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 	if (bio->bi_iter.bi_size > UINT_MAX - len)
@@ -1011,7 +1024,7 @@ int bio_add_page(struct bio *bio, struct page *page,
 
 	if (bio->bi_vcnt > 0 &&
 	    bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
-				page, len, offset, &same_page)) {
+				page, len, offset)) {
 		bio->bi_iter.bi_size += len;
 		return len;
 	}
@@ -1058,6 +1071,61 @@ bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len,
 }
 EXPORT_SYMBOL(bio_add_folio);
 
+/**
+ * bio_add_vmalloc_chunk - add a vmalloc chunk to a bio
+ * @bio: destination bio
+ * @vaddr: vmalloc address to add
+ * @len: total length in bytes of the data to add
+ *
+ * Add data starting at @vaddr to @bio and return how many bytes were added.
+ * This may be less than the amount originally asked.  Returns 0 if no data
+ * could be added to @bio.
+ *
+ * This helper calls flush_kernel_vmap_range() for the range added.  For reads
+ * the caller still needs to manually call invalidate_kernel_vmap_range() in
+ * the completion handler.
+ */
+unsigned int bio_add_vmalloc_chunk(struct bio *bio, void *vaddr, unsigned len)
+{
+	unsigned int offset = offset_in_page(vaddr);
+
+	len = min(len, PAGE_SIZE - offset);
+	if (bio_add_page(bio, vmalloc_to_page(vaddr), len, offset) < len)
+		return 0;
+	if (op_is_write(bio_op(bio)))
+		flush_kernel_vmap_range(vaddr, len);
+	return len;
+}
+EXPORT_SYMBOL_GPL(bio_add_vmalloc_chunk);
+
+/**
+ * bio_add_vmalloc - add a vmalloc region to a bio
+ * @bio: destination bio
+ * @vaddr: vmalloc address to add
+ * @len: total length in bytes of the data to add
+ *
+ * Add data starting at @vaddr to @bio.  Return %true on success or %false if
+ * @bio does not have enough space for the payload.
+ *
+ * This helper calls flush_kernel_vmap_range() for the range added.  For reads
+ * the caller still needs to manually call invalidate_kernel_vmap_range() in
+ * the completion handler.
+ */
+bool bio_add_vmalloc(struct bio *bio, void *vaddr, unsigned int len)
+{
+	do {
+		unsigned int added = bio_add_vmalloc_chunk(bio, vaddr, len);
+
+		if (!added)
+			return false;
+		vaddr += added;
+		len -= added;
+	} while (len);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(bio_add_vmalloc);
+
 void __bio_release_pages(struct bio *bio, bool mark_dirty)
 {
 	struct folio_iter fi;
@@ -1088,27 +1156,6 @@ void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter)
 	bio_set_flag(bio, BIO_CLONED);
 }
 
-static int bio_iov_add_folio(struct bio *bio, struct folio *folio, size_t len,
-			     size_t offset)
-{
-	bool same_page = false;
-
-	if (WARN_ON_ONCE(bio->bi_iter.bi_size > UINT_MAX - len))
-		return -EIO;
-
-	if (bio->bi_vcnt > 0 &&
-	    bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
-				folio_page(folio, 0), len, offset,
-				&same_page)) {
-		bio->bi_iter.bi_size += len;
-		if (same_page && bio_flagged(bio, BIO_PAGE_PINNED))
-			unpin_user_folio(folio, 1);
-		return 0;
-	}
-	bio_add_folio_nofail(bio, folio, len, offset);
-	return 0;
-}
-
 static unsigned int get_contig_folio_len(unsigned int *num_pages,
 					 struct page **pages, unsigned int i,
 					 struct folio *folio, size_t left,
@@ -1203,6 +1250,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	for (left = size, i = 0; left > 0; left -= len, i += num_pages) {
 		struct page *page = pages[i];
 		struct folio *folio = page_folio(page);
+		unsigned int old_vcnt = bio->bi_vcnt;
 
 		folio_offset = ((size_t)folio_page_idx(folio, page) <<
 			       PAGE_SHIFT) + offset;
@@ -1215,7 +1263,23 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 			len = get_contig_folio_len(&num_pages, pages, i,
 						   folio, left, offset);
 
-		bio_iov_add_folio(bio, folio, len, folio_offset);
+		if (!bio_add_folio(bio, folio, len, folio_offset)) {
+			WARN_ON_ONCE(1);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if (bio_flagged(bio, BIO_PAGE_PINNED)) {
+			/*
+			 * We're adding another fragment of a page that already
+			 * was part of the last segment.  Undo our pin as the
+			 * page was pinned when an earlier fragment of it was
+			 * added to the bio and __bio_release_pages expects a
+			 * single pin per page.
+			 */
+			if (offset && bio->bi_vcnt == old_vcnt)
+				unpin_user_folio(folio, 1);
+		}
 		offset = 0;
 	}
 
@@ -1301,6 +1365,36 @@ int submit_bio_wait(struct bio *bio)
 }
 EXPORT_SYMBOL(submit_bio_wait);
 
+/**
+ * bdev_rw_virt - synchronously read into / write from kernel mapping
+ * @bdev:	block device to access
+ * @sector:	sector to access
+ * @data:	data to read/write
+ * @len:	length in byte to read/write
+ * @op:		operation (e.g. REQ_OP_READ/REQ_OP_WRITE)
+ *
+ * Performs synchronous I/O to @bdev for @data/@len.  @data must be in
+ * the kernel direct mapping and not a vmalloc address.
+ */
+int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data,
+		size_t len, enum req_op op)
+{
+	struct bio_vec bv;
+	struct bio bio;
+	int error;
+
+	if (WARN_ON_ONCE(is_vmalloc_addr(data)))
+		return -EIO;
+
+	bio_init(&bio, bdev, &bv, 1, op);
+	bio.bi_iter.bi_sector = sector;
+	bio_add_virt_nofail(&bio, data, len);
+	error = submit_bio_wait(&bio);
+	bio_uninit(&bio);
+	return error;
+}
+EXPORT_SYMBOL_GPL(bdev_rw_virt);
+
 static void bio_wait_end_io(struct bio *bio)
 {
 	complete(bio->bi_private);