Merge branch 'for-7.4/lazy-bounce-buffering' into for-next

* for-7.4/lazy-bounce-buffering:
  block,iomap: remove the old read side bounce buffering support
  xfs: log a message at mount time when using integrity protection
  xfs: add error injection for lazy bounce buffering
  xfs: add support for lazy direct read bounce buffering
  iomap,xfs: move integrity verification to the file system
  xfs: use BIO_COMPLETE_IN_TASK for bounce buffered read I/Os
  iomap: better read bounce buffering support
  block,iomap: fix protection information verification with initial bvec offset
  xfs: move PI generation into xfs_submit_zoned_bio
  iomap,xfs: move T10 PI handling for direct I/O into ->submit_io
  iomap: add a IOMAP_IOEND_INTEGRITY flag
  iomap: add a iomap_ioend_flags helper
  iomap: respect maximum I/O size in iomap_dio_bio_iter_one
  block: warn on too larger integrity allocations
  block: pass a maxlen argument to bio_iov_iter_get_pages
  block: add a bio_prepare_reissue helper
  block: export fs_bio_integrity_{alloc,free}
  block: split bio_iov_iter_bounce_write

22 files changed, 498 insertions, 225 deletions

diff --git a/block/bio-integrity-fs.c b/block/bio-integrity-fs.c
index 692403dfa047..c8e91ada8ca6 100644
--- a/block/bio-integrity-fs.c
+++ b/block/bio-integrity-fs.c
@@ -31,6 +31,7 @@ unsigned int fs_bio_integrity_alloc(struct bio *bio)
 		bio_integrity_setup_default(bio);
 	return action;
 }
+EXPORT_SYMBOL_GPL(fs_bio_integrity_alloc);
 
 void fs_bio_integrity_free(struct bio *bio)
 {
@@ -43,6 +44,7 @@ void fs_bio_integrity_free(struct bio *bio)
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
 }
+EXPORT_SYMBOL_GPL(fs_bio_integrity_free);
 
 void fs_bio_integrity_generate(struct bio *bio)
 {
@@ -52,14 +54,10 @@ void fs_bio_integrity_generate(struct bio *bio)
 }
 EXPORT_SYMBOL_GPL(fs_bio_integrity_generate);
 
-int fs_bio_integrity_verify(struct bio *bio, sector_t sector, unsigned int size)
+int fs_bio_integrity_verify(struct bio *bio, struct bvec_iter *data_iter)
 {
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct bvec_iter data_iter = {
-		.bi_sector	= sector,
-		.bi_size	= size,
-	};
 
 	if (!bip || !(bip->bip_flags & BIP_CHECK_FLAGS))
 		return 0;
@@ -71,9 +69,10 @@ int fs_bio_integrity_verify(struct bio *bio, sector_t sector, unsigned int size)
 	 * bio.  Requires the submitter to remember the sector and the size.
 	 */
 	memset(&bip->bip_iter, 0, sizeof(bip->bip_iter));
-	bip->bip_iter.bi_sector = sector;
-	bip->bip_iter.bi_size = bio_integrity_bytes(bi, size >> SECTOR_SHIFT);
-	return blk_status_to_errno(bio_integrity_verify(bio, &data_iter));
+	bip->bip_iter.bi_sector = data_iter->bi_sector;
+	bip->bip_iter.bi_size =
+		bio_integrity_bytes(bi, data_iter->bi_size >> SECTOR_SHIFT);
+	return blk_status_to_errno(bio_integrity_verify(bio, data_iter));
 }
 
 static int __init fs_bio_integrity_init(void)
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index b23e2434d80c..d3df726e0f08 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -72,6 +72,7 @@ void bio_integrity_alloc_buf(struct bio *bio, gfp_t gfp, bool zero_buffer)
 	unsigned int len = bio_integrity_bytes(bi, bio_sectors(bio));
 	void *buf;
 
+	WARN_ON_ONCE(len > BLK_INTEGRITY_MAX_SIZE);
 	buf = kmalloc(len, gfp | __GFP_NOWARN | (zero_buffer ? __GFP_ZERO : 0));
 	if (unlikely(!buf)) {
 		struct page *page;
diff --git a/block/bio.c b/block/bio.c
index 57ee335899f3..b48091c7663f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -320,6 +320,26 @@ void bio_reuse(struct bio *bio, blk_opf_t opf)
 }
 EXPORT_SYMBOL_GPL(bio_reuse);
 
+/**
+ * bio_prepare_reissue - prepare a bio for reuissing the original I/O
+ * @bio:	bio to reuse
+ * @bdev:	block device to use the bio for
+ *
+ * Prepare @bio to be resubmitted to retry the original operation.
+ * The caller must reset bio->bi_iter to the original state.
+ */
+void bio_prepare_reissue(struct bio *bio, struct block_device *bdev)
+{
+	bio->bi_bdev = bdev;
+	bio_associate_blkg(bio);
+	bio->bi_flags &=
+		(BIO_PAGE_PINNED | BIO_CLONED | BIO_QUIET | BIO_REFFED);
+	bio->bi_status = BLK_STS_OK;
+	bio->bi_bvec_gap_bit = 0;
+	atomic_set(&bio->__bi_remaining, 1);
+}
+EXPORT_SYMBOL_GPL(bio_prepare_reissue);
+
 static struct bio *__bio_chain_endio(struct bio *bio)
 {
 	struct bio *parent = bio->bi_private;
@@ -1203,8 +1223,9 @@ bool bio_iov_iter_set(struct bio *bio, const struct iov_iter *iter)
  * for the next iteration.
  */
 static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
-				   struct bio_vec *bv, unsigned len_align_mask)
+				   unsigned len_align_mask)
 {
+	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 	size_t nbytes = bio->bi_iter.bi_size & len_align_mask;
 
 	if (!nbytes)
@@ -1262,6 +1283,7 @@ static inline bool bio_iov_bvec_aligned(const struct bio *bio,
  * bio_iov_iter_get_pages - add user or kernel pages to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be added
+ * @maxlen: maximum size to consume from @iter
  * @mem_align_mask: the mask the source address and length must be aligned to,
  *	0 for no requirement
  * @len_align_mask: the mask to align the total size to, 0 for any length
@@ -1282,7 +1304,8 @@ static inline bool bio_iov_bvec_aligned(const struct bio *bio,
  * is returned only if 0 pages could be pinned.
  */
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
-			   unsigned mem_align_mask, unsigned len_align_mask)
+			   unsigned maxlen, unsigned mem_align_mask,
+			   unsigned len_align_mask)
 {
 	iov_iter_extraction_t flags = 0;
 
@@ -1294,6 +1317,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 		    !bio_iov_bvec_aligned(bio, mem_align_mask))
 			return -EINVAL;
 
+		/* Truncate to the maximum size that the caller can handle */
+		bio->bi_iter.bi_size = min(bio->bi_iter.bi_size, maxlen);
 		iov_iter_advance(iter, bio->bi_iter.bi_size);
 		return 0;
 	}
@@ -1307,7 +1332,7 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 		ssize_t ret;
 
 		ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec,
-				BIO_MAX_SIZE - bio->bi_iter.bi_size,
+				maxlen - bio->bi_iter.bi_size,
 				&bio->bi_vcnt, bio->bi_max_vecs,
 				mem_align_mask, flags);
 		if (ret <= 0) {
@@ -1330,8 +1355,7 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 
 	if (is_pci_p2pdma_page(bio->bi_io_vec->bv_page))
 		bio->bi_opf |= REQ_NOMERGE;
-	return bio_iov_iter_align_down(bio, iter,
-			&bio->bi_io_vec[bio->bi_vcnt - 1], len_align_mask);
+	return bio_iov_iter_align_down(bio, iter, len_align_mask);
 }
 
 static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size,
@@ -1350,7 +1374,7 @@ static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size,
 	return folio_alloc(gfp, get_order(*size));
 }
 
-static void bio_free_folios(struct bio *bio)
+void bio_free_folios(struct bio *bio)
 {
 	struct bio_vec *bv;
 	int i;
@@ -1363,11 +1387,8 @@ static void bio_free_folios(struct bio *bio)
 	}
 }
 
-static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
-		size_t maxlen, size_t minsize)
+int bio_alloc_bounce_folios(struct bio *bio, size_t total_len, size_t minsize)
 {
-	size_t total_len = min(maxlen, iov_iter_count(iter));
-
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return -EINVAL;
 	if (WARN_ON_ONCE(bio->bi_iter.bi_size))
@@ -1377,7 +1398,6 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
 
 	do {
 		size_t this_len = min(total_len, SZ_1M);
-		size_t copied;
 		struct folio *folio;
 
 		if (this_len > minsize * 2)
@@ -1398,27 +1418,6 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
 		 */
 		this_len &= ~(minsize - 1);
 		bio_add_folio_nofail(bio, folio, this_len, 0);
-
-		if (iter->nofault)
-			copied = copy_folio_from_iter_atomic(folio, 0, this_len,
-							     iter);
-		else
-			copied = copy_folio_from_iter(folio, 0, this_len, iter);
-		if (copied < this_len) {
-			/*
-			 * Need to revert the iov iter for all bytes we have
-			 * copied.
-			 *
-			 * However the bio size differs from the real copied
-			 * bytes as @this_len is queued but only advanced
-			 * less than that.
-			 * Need to compensate that for the revert.
-			 */
-			iov_iter_revert(iter, bio->bi_iter.bi_size - this_len +
-					copied);
-			bio_free_folios(bio);
-			return -EFAULT;
-		}
 		total_len -= this_len;
 	} while (total_len && bio->bi_vcnt < bio->bi_max_vecs);
 
@@ -1427,133 +1426,52 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
 	return 0;
 }
 
-static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter,
-		size_t maxlen, size_t minsize)
-{
-	size_t len = min3(iov_iter_count(iter), maxlen, SZ_1M);
-	struct folio *folio;
-	ssize_t ret;
-
-	folio = folio_alloc_greedy(GFP_KERNEL, &len, minsize);
-	if (!folio)
-		return -ENOMEM;
-
-	do {
-		ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec + 1, len,
-				&bio->bi_vcnt, bio->bi_max_vecs - 1, 0, 0);
-		if (ret <= 0) {
-			if (!bio->bi_vcnt)
-				goto out_folio_put;
-			break;
-		}
-		len -= ret;
-		bio->bi_iter.bi_size += ret;
-	} while (len && bio->bi_vcnt < bio->bi_max_vecs - 1);
-
-	/*
-	 * Set the folio directly here.  The above loop has already calculated
-	 * the correct bi_size, and we use bi_vcnt for the user buffers.  That
-	 * is safe as bi_vcnt is only used by the submitter and not the actual
-	 * I/O path.
-	 */
-	bvec_set_folio(&bio->bi_io_vec[0], folio, bio->bi_iter.bi_size, 0);
-	if (iov_iter_extract_will_pin(iter))
-		bio_set_flag(bio, BIO_PAGE_PINNED);
-
-	/* The first vec stores the bounce buffer, so do not subtract 1 here. */
-	ret = bio_iov_iter_align_down(bio, iter,
-			&bio->bi_io_vec[bio->bi_vcnt], minsize - 1);
-	if (ret)
-		goto out_folio_put;
-
-	/* Update the bounc buffer bv_len to the aligned down size. */
-	bio->bi_io_vec[0].bv_len = bio->bi_iter.bi_size;
-	return 0;
-
-out_folio_put:
-	folio_put(folio);
-	return ret;
-}
-
 /**
- * bio_iov_iter_bounce - bounce buffer data from an iter into a bio
+ * bio_iov_iter_bounce_write - bounce buffer data from an iter into a bio
  * @bio:	bio to send
- * @iter:	iter to read from / write into
+ * @iter:	iter to read from
  * @maxlen:	maximum size to bounce
  * @minsize:	minimum folio allocation size
  *
- * Helper for direct I/O implementations that need to bounce buffer because
- * we need to checksum the data or perform other operations that require
- * consistency.  Allocates folios to back the bounce buffer, and for writes
- * copies the data into it.  Needs to be paired with bio_iov_iter_unbounce()
- * called on completion.
+ * Helper for direct I/O write implementations that need to bounce buffer
+ * because they need need to checksum the data or perform other operations that
+ * require consistency.  Allocates folios to back the bounce buffer, and copies
+ * the data into it.  Needs to be paired with bio_free_folios() called on
+ * completion.
  */
-int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen,
-			size_t minsize)
-{
-	if (op_is_write(bio_op(bio)))
-		return bio_iov_iter_bounce_write(bio, iter, maxlen, minsize);
-	return bio_iov_iter_bounce_read(bio, iter, maxlen, minsize);
-}
-
-static void bvec_unpin(struct bio_vec *bv, bool mark_dirty)
-{
-	struct folio *folio = bvec_folio(bv);
-	size_t nr_pages = (bv->bv_offset + bv->bv_len - 1) / PAGE_SIZE -
-			bv->bv_offset / PAGE_SIZE + 1;
-
-	if (mark_dirty)
-		folio_mark_dirty_lock(folio);
-	unpin_user_folio(folio, nr_pages);
-}
-
-static void bio_iov_iter_unbounce_read(struct bio *bio, bool is_error,
-		bool mark_dirty)
+int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
+		size_t maxlen, size_t minsize)
 {
-	unsigned int len = bio->bi_io_vec[0].bv_len;
-
-	if (likely(!is_error)) {
-		void *buf = bvec_virt(&bio->bi_io_vec[0]);
-		struct iov_iter to;
+	size_t total_len = min(maxlen, iov_iter_count(iter));
+	size_t total_copied = 0;
+	struct bio_vec *bv;
+	int i, error;
 
-		iov_iter_bvec(&to, ITER_DEST, bio->bi_io_vec + 1, bio->bi_vcnt,
-				len);
-		/* copying to pinned pages should always work */
-		WARN_ON_ONCE(copy_to_iter(buf, len, &to) != len);
-	} else {
-		/* No need to mark folios dirty if never copied to them */
-		mark_dirty = false;
-	}
+	error = bio_alloc_bounce_folios(bio, total_len, minsize);
+	if (error)
+		return error;
 
-	if (bio_flagged(bio, BIO_PAGE_PINNED)) {
-		int i;
+	bio_for_each_bvec_all(bv, bio, i) {
+		struct folio *folio = page_folio(bv->bv_page);
+		size_t copied;
 
-		for (i = 0; i < bio->bi_vcnt; i++)
-			bvec_unpin(&bio->bi_io_vec[1 + i], mark_dirty);
+		if (iter->nofault)
+			copied = copy_folio_from_iter_atomic(folio, 0,
+					bv->bv_len, iter);
+		else
+			copied = copy_folio_from_iter(folio, 0, bv->bv_len,
+					iter);
+		total_copied += copied;
+		if (copied < bv->bv_len) {
+			iov_iter_revert(iter, total_copied);
+			bio_free_folios(bio);
+			return -EFAULT;
+		}
 	}
 
-	folio_put(bvec_folio(&bio->bi_io_vec[0]));
-}
-
-/**
- * bio_iov_iter_unbounce - finish a bounce buffer operation
- * @bio:	completed bio
- * @is_error:	%true if an I/O error occurred and data should not be copied
- * @mark_dirty:	If %true, folios will be marked dirty.
- *
- * Helper for direct I/O implementations that need to bounce buffer because
- * we need to checksum the data or perform other operations that require
- * consistency.  Called to complete a bio set up by bio_iov_iter_bounce().
- * Copies data back for reads, and marks the original folios dirty if
- * requested and then frees the bounce buffer.
- */
-void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty)
-{
-	if (op_is_write(bio_op(bio)))
-		bio_free_folios(bio);
-	else
-		bio_iov_iter_unbounce_read(bio, is_error, mark_dirty);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(bio_iov_iter_bounce_write);
 
 static void bio_wait_end_io(struct bio *bio)
 {
diff --git a/block/blk-map.c b/block/blk-map.c
index 9cb9605d1f62..81cba3af4e9c 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -274,7 +274,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	 * No alignment requirements on our part to support arbitrary
 	 * passthrough commands.
 	 */
-	ret = bio_iov_iter_get_pages(bio, iter, 0, 0);
+	ret = bio_iov_iter_get_pages(bio, iter, BIO_MAX_SIZE, 0, 0);
 	if (ret)
 		goto out_put;
 	ret = blk_rq_append_bio(rq, bio);
diff --git a/block/fops.c b/block/fops.c
index b917bc0f6b44..b182d0b30748 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -60,7 +60,8 @@ static bool blkdev_dio_invalid(struct block_device *bdev, struct kiocb *iocb,
 static inline int blkdev_iov_iter_get_pages(struct bio *bio,
 		struct iov_iter *iter, struct block_device *bdev)
 {
-	return bio_iov_iter_get_pages(bio, iter, bdev_dma_alignment(bdev),
+	return bio_iov_iter_get_pages(bio, iter, BIO_MAX_SIZE,
+			bdev_dma_alignment(bdev),
 			bdev_logical_block_size(bdev) - 1);
 }
 
diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c
index 48100c614431..d46c2f8ea18c 100644
--- a/fs/iomap/bio.c
+++ b/fs/iomap/bio.c
@@ -169,6 +169,7 @@ int iomap_bio_read_folio_range_sync(const struct iomap_iter *iter,
 {
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	sector_t sector = iomap_sector(srcmap, pos);
+	struct bvec_iter saved_iter;
 	struct bio_vec bvec;
 	struct bio bio;
 	int error;
@@ -178,10 +179,11 @@ int iomap_bio_read_folio_range_sync(const struct iomap_iter *iter,
 	bio_add_folio_nofail(&bio, folio, len, offset_in_folio(folio, pos));
 	if (srcmap->flags & IOMAP_F_INTEGRITY)
 		fs_bio_integrity_alloc(&bio);
+	saved_iter = bio.bi_iter;
 	error = submit_bio_wait(&bio);
 	if (bio_integrity(&bio)) {
 		if (!error)
-			error = fs_bio_integrity_verify(&bio, sector, len);
+			error = fs_bio_integrity_verify(&bio, &saved_iter);
 		fs_bio_integrity_free(&bio);
 	}
 	bio_uninit(&bio);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 8b4039d16ce8..41fdc90a9094 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -76,10 +76,19 @@ static void iomap_dio_submit_bio(const struct iomap_iter *iter,
 
 	if (dio->dops && dio->dops->submit_io) {
 		dio->dops->submit_io(iter, bio, pos);
-	} else {
-		WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_ANON_WRITE);
-		blk_crypto_submit_bio(bio);
+		return;
+	}
+
+	WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_ANON_WRITE);
+
+	if (iter->iomap.flags & IOMAP_F_INTEGRITY) {
+		if (dio->flags & IOMAP_DIO_WRITE)
+			fs_bio_integrity_generate(bio);
+		else
+			fs_bio_integrity_alloc(bio);
 	}
+
+	blk_crypto_submit_bio(bio);
 }
 
 static inline enum fserror_type iomap_dio_err_type(const struct iomap_dio *dio)
@@ -246,8 +255,7 @@ static void __iomap_dio_bio_end_io(struct bio *bio, bool inline_completion)
 		fs_bio_integrity_free(bio);
 
 	if (dio->flags & IOMAP_DIO_BOUNCE) {
-		bio_iov_iter_unbounce(bio, !!dio->error,
-				dio->flags & IOMAP_DIO_USER_BACKED);
+		bio_free_folios(bio);
 		bio_put(bio);
 	} else if (dio->flags & IOMAP_DIO_USER_BACKED) {
 		bio_check_pages_dirty(bio);
@@ -336,6 +344,7 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
 		struct iomap_dio *dio, loff_t pos, unsigned int alignment,
 		blk_opf_t op)
 {
+	unsigned int maxsize = iomap_max_bio_size(&iter->iomap);
 	unsigned int nr_vecs;
 	struct bio *bio;
 	ssize_t ret;
@@ -353,14 +362,12 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
 	bio->bi_private = dio;
 	bio->bi_end_io = iomap_dio_bio_end_io;
 
-
 	if (dio->flags & IOMAP_DIO_BOUNCE)
-		ret = bio_iov_iter_bounce(bio, dio->submit.iter,
-				iomap_max_bio_size(&iter->iomap), alignment);
+		ret = bio_iov_iter_bounce_write(bio, dio->submit.iter, maxsize,
+				alignment);
 	else
-		ret = bio_iov_iter_get_pages(bio, dio->submit.iter,
-					     bdev_dma_alignment(bio->bi_bdev),
-					     alignment - 1);
+		ret = bio_iov_iter_get_pages(bio, dio->submit.iter, maxsize,
+				bdev_dma_alignment(bio->bi_bdev), alignment - 1);
 	if (unlikely(ret))
 		goto out_put_bio;
 	ret = bio->bi_iter.bi_size;
@@ -374,13 +381,6 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
 		goto out_bio_release_pages;
 	}
 
-	if (iter->iomap.flags & IOMAP_F_INTEGRITY) {
-		if (dio->flags & IOMAP_DIO_WRITE)
-			fs_bio_integrity_generate(bio);
-		else
-			fs_bio_integrity_alloc(bio);
-	}
-
 	if (dio->flags & IOMAP_DIO_WRITE)
 		task_io_account_write(ret);
 	else if ((dio->flags & IOMAP_DIO_USER_BACKED) &&
@@ -397,7 +397,7 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
 
 out_bio_release_pages:
 	if (dio->flags & IOMAP_DIO_BOUNCE)
-		bio_iov_iter_unbounce(bio, true, false);
+		bio_free_folios(bio);
 	else
 		bio_release_pages(bio, false);
 out_put_bio:
@@ -1034,9 +1034,9 @@ ssize_t __iomap_dio_read_simple(struct kiocb *iocb, struct iov_iter *iter,
 	bio->bi_iter.bi_sector = iomap_sector(&iomi->iomap, iomi->pos);
 	bio->bi_ioprio = iocb->ki_ioprio;
 
-	ret = bio_iov_iter_get_pages(bio, iter,
-				bdev_dma_alignment(bio->bi_bdev),
-				alignment - 1);
+	ret = bio_iov_iter_get_pages(bio, iter, BIO_MAX_SIZE,
+			bdev_dma_alignment(bio->bi_bdev),
+			alignment - 1);
 	if (unlikely(ret))
 		goto out_bio_put;
 
diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index 7bbbb417f915..bbebecc31670 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -25,6 +25,7 @@ struct iomap_ioend *iomap_init_ioend(struct inode *inode,
 	ioend->io_parent = NULL;
 	INIT_LIST_HEAD(&ioend->io_list);
 	ioend->io_flags = ioend_flags;
+	ioend->io_bvec_offset = bio->bi_iter.bi_offset;
 	ioend->io_inode = inode;
 	ioend->io_offset = file_offset;
 	ioend->io_size = bio->bi_iter.bi_size;
@@ -149,7 +150,7 @@ int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error)
 		return error;
 	}
 
-	if (wpc->iomap.flags & IOMAP_F_INTEGRITY)
+	if (ioend->io_flags & IOMAP_IOEND_INTEGRITY)
 		fs_bio_integrity_generate(&ioend->io_bio);
 	submit_bio(&ioend->io_bio);
 	return 0;
@@ -215,7 +216,7 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 {
 	struct iomap_ioend *ioend = wpc->wb_ctx;
 	size_t poff = offset_in_folio(folio, pos);
-	unsigned int ioend_flags = 0;
+	unsigned int ioend_flags = iomap_ioend_flags(&wpc->iomap);
 	unsigned int map_len = min_t(u64, dirty_len,
 		wpc->iomap.offset + wpc->iomap.length - pos);
 	int error;
@@ -225,20 +226,16 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 	WARN_ON_ONCE(!folio->private && map_len < dirty_len);
 
 	switch (wpc->iomap.type) {
+	case IOMAP_HOLE:
+		return map_len;
 	case IOMAP_UNWRITTEN:
-		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
-		break;
 	case IOMAP_MAPPED:
 		break;
-	case IOMAP_HOLE:
-		return map_len;
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
 	}
 
-	if (wpc->iomap.flags & IOMAP_F_SHARED)
-		ioend_flags |= IOMAP_IOEND_SHARED;
 	if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
 		ioend_flags |= IOMAP_IOEND_BOUNDARY;
 
@@ -312,6 +309,16 @@ new_ioend:
 }
 EXPORT_SYMBOL_GPL(iomap_add_to_ioend);
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+int iomap_ioend_integrity_verify(struct iomap_ioend *ioend)
+{
+	struct bvec_iter data_iter = BVEC_ITER_IOEND(ioend);
+
+	return fs_bio_integrity_verify(&ioend->io_bio, &data_iter);
+}
+EXPORT_SYMBOL_GPL(iomap_ioend_integrity_verify);
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
 static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 {
 	if (ioend->io_parent) {
@@ -327,13 +334,6 @@ static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 	if (!atomic_dec_and_test(&ioend->io_remaining))
 		return 0;
 
-	if (!ioend->io_error &&
-	    bio_integrity(&ioend->io_bio) &&
-	    bio_op(&ioend->io_bio) == REQ_OP_READ) {
-		ioend->io_error = fs_bio_integrity_verify(&ioend->io_bio,
-			ioend->io_sector, ioend->io_size);
-	}
-
 	if (ioend->io_flags & IOMAP_IOEND_DIRECT)
 		return iomap_finish_ioend_direct(ioend);
 	if (bio_op(&ioend->io_bio) == REQ_OP_READ)
@@ -512,6 +512,96 @@ struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
 }
 EXPORT_SYMBOL_GPL(iomap_split_ioend);
 
+void iomap_bounce_read(struct iomap_ioend *orig_ioend, unsigned int minsize,
+		void (*submit_ioend)(struct iomap_ioend *ioend))
+{
+	struct inode *inode = orig_ioend->io_inode;
+	struct bio *orig_bio = &orig_ioend->io_bio;
+	loff_t file_offset = orig_ioend->io_offset;
+	sector_t sector = orig_ioend->io_sector;
+	size_t total_len = round_up(orig_ioend->io_size, minsize);
+
+	WARN_ON_ONCE(!(orig_ioend->io_flags & IOMAP_IOEND_DIRECT));
+
+	/* We can't poll a bio that is not passed on to hardware */
+	orig_bio->bi_opf &= ~REQ_POLLED;
+
+	do {
+		struct iomap_ioend *ioend;
+		struct bio *bio;
+		int error;
+
+		bio = bio_alloc_bioset(orig_bio->bi_bdev,
+				min(total_len / minsize, BIO_MAX_VECS),
+				orig_bio->bi_opf, GFP_KERNEL,
+				&iomap_ioend_split_bioset);
+		error = bio_alloc_bounce_folios(bio, total_len, minsize);
+		if (error) {
+			bio_put(bio);
+			orig_bio->bi_status = errno_to_blk_status(error);
+			break;
+		}
+		bio->bi_ioprio = orig_bio->bi_ioprio;
+		bio->bi_write_hint = orig_bio->bi_write_hint;
+		bio->bi_write_stream = orig_bio->bi_write_stream;
+		bio->bi_iter.bi_sector = sector;
+
+		ioend = iomap_init_ioend(inode, bio, file_offset,
+				orig_ioend->io_flags);
+
+		total_len -= bio->bi_iter.bi_size;
+		file_offset += bio->bi_iter.bi_size;
+		sector += (bio->bi_iter.bi_size >> SECTOR_SHIFT);
+
+		bio->bi_private = orig_bio;
+		bio_inc_remaining(orig_bio);
+		submit_ioend(ioend);
+	} while (total_len > 0);
+
+	bio_endio(&orig_ioend->io_bio);
+}
+EXPORT_SYMBOL_GPL(iomap_bounce_read);
+
+static void iomap_ioend_unbounce(struct iomap_ioend *orig_ioend,
+		struct iomap_ioend *ioend)
+{
+	struct bio *orig_bio = &orig_ioend->io_bio;
+	struct iov_iter to;
+	struct bio_vec *bv;
+	int i;
+
+	iov_iter_bvec(&to, ITER_DEST, orig_bio->bi_io_vec, orig_bio->bi_vcnt,
+			orig_ioend->io_size);
+	to.iov_offset = orig_ioend->io_bvec_offset;
+
+	if (ioend->io_offset != orig_ioend->io_offset) {
+		WARN_ON_ONCE(ioend->io_offset < orig_ioend->io_offset);
+		iov_iter_advance(&to, ioend->io_offset - orig_ioend->io_offset);
+	}
+
+	/* copying to pinned pages should always work */
+	bio_for_each_bvec_all(bv, &ioend->io_bio, i)
+		WARN_ON_ONCE(copy_to_iter(bvec_virt(bv), bv->bv_len, &to) !=
+				bv->bv_len);
+}
+
+void iomap_bounce_read_end_io(struct iomap_ioend *ioend, struct bio *orig_bio,
+		int error)
+{
+	if (error)
+		orig_bio->bi_status = errno_to_blk_status(error);
+	else
+		iomap_ioend_unbounce(iomap_ioend_from_bio(orig_bio), ioend);
+
+	bio_free_folios(&ioend->io_bio);
+	if (bio_integrity(&ioend->io_bio))
+		fs_bio_integrity_free(&ioend->io_bio);
+	bio_put(&ioend->io_bio);
+
+	bio_endio(orig_bio);
+}
+EXPORT_SYMBOL_GPL(iomap_bounce_read_end_io);
+
 static int __init iomap_ioend_init(void)
 {
 	const unsigned int nr_mempool_entries = 4 * (PAGE_SIZE / SECTOR_SIZE);
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index 6de207fed2d8..2dc441da0333 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -75,7 +75,8 @@
 #define XFS_ERRTAG_METAFILE_RESV_CRITICAL		45
 #define XFS_ERRTAG_FORCE_ZERO_RANGE			46
 #define XFS_ERRTAG_ZONE_RESET				47
-#define XFS_ERRTAG_MAX					48
+#define XFS_ERRTAG_BOUNCE_REREAD			48
+#define XFS_ERRTAG_MAX					49
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -137,7 +138,8 @@ XFS_ERRTAG(WRITE_DELAY_MS,	write_delay_ms,		3000) \
 XFS_ERRTAG(EXCHMAPS_FINISH_ONE,	exchmaps_finish_one,	1) \
 XFS_ERRTAG(METAFILE_RESV_CRITICAL, metafile_resv_crit,	4) \
 XFS_ERRTAG(FORCE_ZERO_RANGE,	force_zero_range,	4) \
-XFS_ERRTAG(ZONE_RESET,		zone_reset,		1)
+XFS_ERRTAG(ZONE_RESET,		zone_reset,		1)  \
+XFS_ERRTAG(BOUNCE_REREAD,	bounce_reread,		XFS_RANDOM_DEFAULT)
 #endif /* XFS_ERRTAG */
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8b6119776fb3..c30e688cfc9f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -23,7 +23,6 @@
 #include "xfs_ioend.h"
 #include "xfs_zone_alloc.h"
 #include "xfs_rtgroup.h"
-#include <linux/bio-integrity.h>
 
 struct xfs_writepage_ctx {
 	struct iomap_writepage_ctx ctx;
@@ -498,8 +497,7 @@ xfs_zoned_writeback_submit(
 		bio_endio(&ioend->io_bio);
 		return error;
 	}
-	if (wpc->iomap.flags & IOMAP_F_INTEGRITY)
-		fs_bio_integrity_generate(&ioend->io_bio);
+
 	xfs_zone_alloc_and_submit(ioend, &XFS_ZWPC(wpc)->open_zone);
 	return 0;
 }
@@ -585,11 +583,10 @@ xfs_bio_submit_read(
 	const struct iomap_iter		*iter,
 	struct iomap_read_folio_ctx	*ctx)
 {
-	struct bio			*bio = ctx->read_ctx;
-
-	/* defer read completions to the ioend workqueue */
-	iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset, 0);
-	iomap_bio_submit_read_endio(iter, ctx, xfs_end_bio);
+	xfs_ioend_submit_read(iter->inode, ctx->read_ctx,
+			ctx->read_ctx_file_offset,
+			iomap_ioend_flags(&iter->iomap));
+	ctx->read_ctx = NULL;
 }
 
 static const struct iomap_read_ops xfs_iomap_read_ops = {
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8256c1d13ce2..6c93b4f5629c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -5,6 +5,7 @@
  */
 #include "xfs_platform.h"
 #include <linux/backing-dev.h>
+#include <linux/blk-integrity.h>
 #include <linux/dax.h>
 
 #include "xfs_shared.h"
@@ -1694,6 +1695,7 @@ xfs_configure_buftarg(
 	struct xfs_mount	*mp = btp->bt_mount;
 
 	if (btp->bt_bdev) {
+		struct blk_integrity *bi = bdev_get_integrity(btp->bt_bdev);
 		int		error;
 
 		error = bdev_validate_blocksize(btp->bt_bdev, sectorsize);
@@ -1706,6 +1708,15 @@ xfs_configure_buftarg(
 
 		if (bdev_can_atomic_write(btp->bt_bdev))
 			xfs_configure_buftarg_atomic_writes(btp);
+
+		if (!bi)
+			;
+		else if (btp->bt_bdev == btp->bt_mount->m_super->s_bdev)
+			xfs_info(mp, "using %s integrity profile",
+				blk_integrity_profile_name(bi));
+		else
+			xfs_info(mp, "using %s integrity profile for %pg",
+				blk_integrity_profile_name(bi), btp->bt_bdev);
 	}
 
 	btp->bt_meta_sectorsize = sectorsize;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index d8202da15aca..dd3782e9af93 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -37,6 +37,7 @@
 #include <linux/fadvise.h>
 #include <linux/mount.h>
 #include <linux/filelock.h>
+#include <linux/bio-integrity.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;
 
@@ -222,9 +223,8 @@ xfs_dio_read_bounce_submit_io(
 	struct bio		*bio,
 	loff_t			file_offset)
 {
-	iomap_init_ioend(iter->inode, bio, file_offset, IOMAP_IOEND_DIRECT);
-	bio->bi_end_io = xfs_end_bio;
-	submit_bio(bio);
+	xfs_ioend_submit_read(iter->inode, bio, file_offset,
+			iomap_ioend_flags(&iter->iomap) | IOMAP_IOEND_DIRECT);
 }
 
 static const struct iomap_dio_ops xfs_dio_read_bounce_ops = {
@@ -252,8 +252,7 @@ xfs_file_dio_read(
 		return ret;
 	if (mapping_stable_writes(iocb->ki_filp->f_mapping)) {
 		ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops,
-				&xfs_dio_read_bounce_ops, IOMAP_DIO_BOUNCE,
-				NULL, 0);
+				&xfs_dio_read_bounce_ops, 0, NULL, 0);
 	} else {
 		ret = iomap_dio_read_simple(iocb, to, xfs_read_iomap_begin);
 		if (ret == -ENOTBLK)
@@ -713,7 +712,7 @@ xfs_dio_zoned_submit_io(
 
 	bio->bi_end_io = xfs_end_bio;
 	ioend = iomap_init_ioend(iter->inode, bio, file_offset,
-			IOMAP_IOEND_DIRECT);
+			iomap_ioend_flags(&iter->iomap) | IOMAP_IOEND_DIRECT);
 	xfs_zone_alloc_and_submit(ioend, &ac->open_zone);
 }
 
diff --git a/fs/xfs/xfs_ioend.c b/fs/xfs/xfs_ioend.c
index 40695d18dac0..e70be5b86f0b 100644
--- a/fs/xfs/xfs_ioend.c
+++ b/fs/xfs/xfs_ioend.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2016-2025 Christoph Hellwig.
+ * Copyright (c) 2016-2026 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include "xfs_platform.h"
@@ -16,6 +16,135 @@
 #include "xfs_reflink.h"
 #include "xfs_zone_alloc.h"
 #include "xfs_ioend.h"
+#include "xfs_error.h"
+#include "xfs_errortag.h"
+#include <linux/bio-integrity.h>
+
+static void
+xfs_dio_bounce_end_io(
+	struct bio		*bio)
+{
+	struct iomap_ioend	*ioend = iomap_ioend_from_bio(bio);
+	int			error = blk_status_to_errno(bio->bi_status);
+	struct bio		*orig_bio = bio->bi_private;
+
+	if ((ioend->io_flags & IOMAP_IOEND_INTEGRITY) && !bio->bi_status)
+		error = iomap_ioend_integrity_verify(ioend);
+	iomap_bounce_read_end_io(ioend, orig_bio, error);
+}
+
+static void
+xfs_bounce_submit_ioend(
+	struct iomap_ioend	*ioend)
+{
+	if (ioend->io_flags & IOMAP_IOEND_INTEGRITY)
+		fs_bio_integrity_alloc(&ioend->io_bio);
+	ioend->io_bio.bi_end_io = xfs_dio_bounce_end_io;
+	bio_set_flag(&ioend->io_bio, BIO_COMPLETE_IN_TASK);
+	submit_bio(&ioend->io_bio);
+}
+
+static void
+xfs_end_bio_bounced(
+	struct bio		*bio)
+{
+	/*
+	 * Just complete the original ioends as all verification is done by the
+	 * end_io handlers for the clone bio(s).
+	 */
+	iomap_finish_ioends(iomap_ioend_from_bio(bio),
+			blk_status_to_errno(bio->bi_status));
+}
+
+static void
+xfs_read_bounce_and_resubmit(
+	struct iomap_ioend	*ioend)
+{
+	struct bio		*bio = &ioend->io_bio;
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	unsigned int		nofs_flag = memalloc_nofs_save();
+
+	trace_xfs_bounce_reread(ip, ioend->io_offset, ioend->io_size);
+
+	/*
+	 * Free the bio integrity data for the original bio, as we'll allocate
+	 * a new one for each sub-I/O, which could deadlock if we keep the
+	 * integrity data for the original bio around.
+	 */
+	if (bio_integrity(bio))
+		fs_bio_integrity_free(bio);
+
+	/*
+	 * Resubmit the bio through the iomap bounce machinery.  The original
+	 * bio itself is not resubmitted to the block layer, but just used to
+	 * track I/O completion of the cloned bios.
+	 */
+	bio_prepare_reissue(bio, xfs_inode_buftarg(ip)->bt_bdev);
+	bio->bi_iter = (struct bvec_iter) {
+		.bi_sector	= ioend->io_sector,
+		.bi_size	= ioend->io_size,
+		.bi_offset	= ioend->io_bvec_offset,
+	};
+	bio->bi_end_io = xfs_end_bio_bounced;
+	iomap_bounce_read(ioend, bdev_logical_block_size(bio->bi_bdev),
+			xfs_bounce_submit_ioend);
+	memalloc_nofs_restore(nofs_flag);
+}
+
+static void
+xfs_end_io_read(
+	struct bio		*bio)
+{
+	struct iomap_ioend	*ioend = iomap_ioend_from_bio(bio);
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	int			error = blk_status_to_errno(bio->bi_status);
+
+	if (!error && (ioend->io_flags & IOMAP_IOEND_INTEGRITY)) {
+		error = iomap_ioend_integrity_verify(ioend);
+		if ((ioend->io_flags & IOMAP_IOEND_DIRECT) &&
+		    READ_ONCE(mp->m_read_bounce) == XFS_READ_BOUNCE_LAZY) {
+			/*
+			 * We only really need to retry for guard tag errors,
+			 * but right now we can't distinguish them from other
+			 * (i.e, reftag) errors.
+			 */
+			if (error ||
+			    XFS_TEST_ERROR(mp, XFS_ERRTAG_BOUNCE_REREAD)) {
+				xfs_read_bounce_and_resubmit(ioend);
+				return;
+			}
+		}
+	}
+
+	iomap_finish_ioends(ioend, error);
+}
+
+void
+xfs_ioend_submit_read(
+	struct inode		*inode,
+	struct bio		*bio,
+	loff_t			file_offset,
+	u16			ioend_flags)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct iomap_ioend	*ioend;
+
+	ioend = iomap_init_ioend(inode, bio, file_offset, ioend_flags);
+	if ((ioend_flags & IOMAP_IOEND_DIRECT) &&
+	    READ_ONCE(mp->m_read_bounce) == XFS_READ_BOUNCE_ALWAYS) {
+		iomap_bounce_read(ioend, bdev_logical_block_size(bio->bi_bdev),
+				xfs_bounce_submit_ioend);
+		return;
+	}
+
+	if (ioend_flags & IOMAP_IOEND_INTEGRITY)
+		fs_bio_integrity_alloc(bio);
+	bio->bi_end_io = xfs_end_io_read;
+	bio_set_flag(bio, BIO_COMPLETE_IN_TASK);
+	submit_bio(bio);
+}
 
 static void
 xfs_ioend_put_open_zones(
@@ -148,11 +277,7 @@ xfs_end_io(
 			io_list))) {
 		list_del_init(&ioend->io_list);
 		iomap_ioend_try_merge(ioend, &tmp);
-		if (bio_op(&ioend->io_bio) == REQ_OP_READ)
-			iomap_finish_ioends(ioend,
-				blk_status_to_errno(ioend->io_bio.bi_status));
-		else
-			xfs_end_ioend_write(ioend);
+		xfs_end_ioend_write(ioend);
 		cond_resched();
 	}
 }
diff --git a/fs/xfs/xfs_ioend.h b/fs/xfs/xfs_ioend.h
index 525865767fca..7c2a1ea3e6ed 100644
--- a/fs/xfs/xfs_ioend.h
+++ b/fs/xfs/xfs_ioend.h
@@ -12,5 +12,7 @@ static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend)
 }
 
 void xfs_end_bio(struct bio *bio);
+void xfs_ioend_submit_read(struct inode *inode, struct bio *bio,
+		loff_t file_offset, u16 ioend_flags);
 
 #endif /* __XFS_IOEND_H */
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 216a38a354e7..894ff2f4ecbd 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -142,6 +142,12 @@ struct xfs_freecounter {
 	uint64_t		res_saved;
 };
 
+enum xfs_read_bounce {
+	XFS_READ_BOUNCE_NEVER,
+	XFS_READ_BOUNCE_ALWAYS,
+	XFS_READ_BOUNCE_LAZY,
+};
+
 /*
  * The struct xfsmount layout is optimised to separate read-mostly variables
  * from variables that are frequently modified. We put the read-mostly variables
@@ -177,6 +183,7 @@ typedef struct xfs_mount {
 	struct workqueue_struct	*m_sync_workqueue;
 	struct workqueue_struct *m_blockgc_wq;
 	struct workqueue_struct *m_inodegc_wq;
+	enum xfs_read_bounce	m_read_bounce;
 
 	int			m_bsize;	/* fs logical block size */
 	uint8_t			m_blkbit_log;	/* blocklog + NBBY */
@@ -291,6 +298,7 @@ typedef struct xfs_mount {
 	struct xfs_zone_info	*m_zone_info;	/* zone allocator information */
 	struct dentry		*m_debugfs;	/* debugfs parent */
 	struct xfs_kobj		m_kobj;
+	struct xfs_kobj		m_csum_kobj;
 	struct xfs_kobj		m_error_kobj;
 	struct xfs_kobj		m_error_meta_kobj;
 	struct xfs_error_cfg	m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX];
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index b24db75eaedc..fce1d2905c94 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2317,6 +2317,7 @@ xfs_init_fs_context(
 	mp->m_logbufs = -1;
 	mp->m_logbsize = -1;
 	mp->m_allocsize_log = 16; /* 64k */
+	mp->m_read_bounce = XFS_READ_BOUNCE_LAZY;
 
 	xfs_hooks_init(&mp->m_dir_update_hooks);
 
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index b62712187324..e77917ac179d 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -392,6 +392,71 @@ const struct kobj_type xfs_stats_ktype = {
 	.default_groups = xfs_stats_groups,
 };
 
+static inline struct xfs_mount *csum_to_mp(struct kobject *kobj)
+{
+	return container_of(to_kobj(kobj), struct xfs_mount, m_csum_kobj);
+}
+
+static bool
+xfs_has_read_bounce(
+	struct xfs_mount	*mp)
+{
+	if (bdev_has_integrity_csum(mp->m_ddev_targp->bt_bdev))
+		return true;
+	if (mp->m_rtdev_targp &&
+	    bdev_has_integrity_csum(mp->m_rtdev_targp->bt_bdev))
+		return true;
+	return false;
+}
+
+static const char * const bounce_modes[] = {
+	[XFS_READ_BOUNCE_NEVER]		= "never",
+	[XFS_READ_BOUNCE_ALWAYS]	= "always",
+	[XFS_READ_BOUNCE_LAZY]		= "lazy",
+};
+
+static ssize_t
+read_bounce_show(
+	struct kobject		*kobj,
+	char			*buf)
+{
+	struct xfs_mount	*mp = csum_to_mp(kobj);
+
+	return sysfs_emit(buf, "%s\n",
+			bounce_modes[READ_ONCE(mp->m_read_bounce)]);
+}
+
+static ssize_t
+read_bounce_store(
+	struct kobject		*kobj,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_mount	*mp = csum_to_mp(kobj);
+	int			ret;
+
+	if (!xfs_has_read_bounce(mp))
+		return -EINVAL;
+	ret = sysfs_match_string(bounce_modes, buf);
+	if (ret < 0)
+		return ret;
+	WRITE_ONCE(mp->m_read_bounce, ret);
+	return count;
+}
+XFS_SYSFS_ATTR_RW(read_bounce);
+
+static struct attribute *xfs_csum_attrs[] = {
+	ATTR_LIST(read_bounce),
+	NULL,
+};
+ATTRIBUTE_GROUPS(xfs_csum);
+
+static const struct kobj_type xfs_csum_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_sysfs_ops,
+	.default_groups = xfs_csum_groups,
+};
+
 /* xlog */
 
 static inline struct xlog *
@@ -817,11 +882,17 @@ xfs_mount_sysfs_init(
 	if (error)
 		goto out_remove_fsdir;
 
+	/* .../xfs/<dev>/csum/ */
+	error = xfs_sysfs_init(&mp->m_csum_kobj, &xfs_csum_ktype, &mp->m_kobj,
+			"csum");
+	if (error)
+		goto out_remove_stats_dir;
+
 	/* .../xfs/<dev>/error/ */
 	error = xfs_sysfs_init(&mp->m_error_kobj, &xfs_error_ktype,
 				&mp->m_kobj, "error");
 	if (error)
-		goto out_remove_stats_dir;
+		goto out_remove_csum_dir;
 
 	/* .../xfs/<dev>/error/fail_at_unmount */
 	error = sysfs_create_file(&mp->m_error_kobj.kobject,
@@ -835,12 +906,14 @@ xfs_mount_sysfs_init(
 				"metadata", &mp->m_error_meta_kobj,
 				xfs_error_meta_init);
 	if (error)
-		goto out_remove_error_dir;
+		goto out_remove_csum_dir;
 
 	return 0;
 
 out_remove_error_dir:
 	xfs_sysfs_del(&mp->m_error_kobj);
+out_remove_csum_dir:
+	xfs_sysfs_del(&mp->m_csum_kobj);
 out_remove_stats_dir:
 	xfs_sysfs_del(&mp->m_stats.xs_kobj);
 out_remove_fsdir:
@@ -864,6 +937,7 @@ xfs_mount_sysfs_del(
 	}
 	xfs_sysfs_del(&mp->m_error_meta_kobj);
 	xfs_sysfs_del(&mp->m_error_kobj);
+	xfs_sysfs_del(&mp->m_csum_kobj);
 	xfs_sysfs_del(&mp->m_stats.xs_kobj);
 	xfs_sysfs_del(&mp->m_kobj);
 }
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 6aa379c2cf0c..eed9b241aec6 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1896,6 +1896,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
 DEFINE_SIMPLE_IO_EVENT(xfs_file_splice_read);
 DEFINE_SIMPLE_IO_EVENT(xfs_zoned_map_blocks);
+DEFINE_SIMPLE_IO_EVENT(xfs_bounce_reread);
 
 DECLARE_EVENT_CLASS(xfs_itrunc_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 28c1e48909fa..6516361a3f38 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -26,6 +26,7 @@
 #include "xfs_zones.h"
 #include "xfs_trace.h"
 #include "xfs_mru_cache.h"
+#include <linux/bio-integrity.h>
 
 static void
 xfs_open_zone_free_rcu(
@@ -911,6 +912,9 @@ xfs_zone_alloc_and_submit(
 	if (xfs_is_shutdown(mp))
 		goto out_error;
 
+	if (ioend->io_flags & IOMAP_IOEND_INTEGRITY)
+		fs_bio_integrity_generate(&ioend->io_bio);
+
 	/*
 	 * If we don't have a locally cached zone in this write context, see if
 	 * the inode is still associated with a zone and use that if so.
diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h
index 0ea2a8bf7efb..a954c97be0b3 100644
--- a/include/linux/bio-integrity.h
+++ b/include/linux/bio-integrity.h
@@ -151,7 +151,6 @@ void bio_integrity_setup_default(struct bio *bio);
 unsigned int fs_bio_integrity_alloc(struct bio *bio);
 void fs_bio_integrity_free(struct bio *bio);
 void fs_bio_integrity_generate(struct bio *bio);
-int fs_bio_integrity_verify(struct bio *bio, sector_t sector,
-		unsigned int size);
+int fs_bio_integrity_verify(struct bio *bio, struct bvec_iter *data_iter);
 
 #endif /* _LINUX_BIO_INTEGRITY_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index bb3235497e67..17944e44b584 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -479,6 +479,7 @@ static inline void bio_init_inline(struct bio *bio, struct block_device *bdev,
 extern void bio_uninit(struct bio *);
 void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf);
 void bio_reuse(struct bio *bio, blk_opf_t opf);
+void bio_prepare_reissue(struct bio *bio, struct block_device *bdev);
 void bio_chain(struct bio *, struct bio *);
 void bio_await(struct bio *bio, void *priv,
 	       void (*submit)(struct bio *bio, void *priv));
@@ -516,16 +517,18 @@ int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data,
 		size_t len, enum req_op op);
 
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
-		unsigned mem_align_mask, unsigned len_align_mask);
+		unsigned maxlen, unsigned mem_align_mask,
+		unsigned len_align_mask);
 
 bool bio_iov_iter_set(struct bio *bio, const struct iov_iter *iter);
 void __bio_release_pages(struct bio *bio, bool mark_dirty);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen,
-		size_t minsize);
-void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty);
+int bio_alloc_bounce_folios(struct bio *bio, size_t total_len, size_t minsize);
+void bio_free_folios(struct bio *bio);
+int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
+		size_t maxlen, size_t minsize);
 
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index bc7ae6327dbf..59718f73c15a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -483,13 +483,35 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 #define IOMAP_IOEND_BOUNDARY		(1U << 2)
 /* is direct I/O */
 #define IOMAP_IOEND_DIRECT		(1U << 3)
+/* generate integrity (PI) information */
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+#define IOMAP_IOEND_INTEGRITY		(1U << 4)
+#else
+#define IOMAP_IOEND_INTEGRITY		0
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 /*
  * Flags that if set on either ioend prevent the merge of two ioends.
  * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way)
  */
 #define IOMAP_IOEND_NOMERGE_FLAGS \
-	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT)
+	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT | \
+	 IOMAP_IOEND_INTEGRITY)
+
+/* ioend flags directly implied by iomap flags */
+static inline u16 iomap_ioend_flags(const struct iomap *iomap)
+{
+	unsigned int flags = 0;
+
+	if (iomap->type == IOMAP_UNWRITTEN)
+		flags |= IOMAP_IOEND_UNWRITTEN;
+	if (iomap->flags & IOMAP_F_SHARED)
+		flags |= IOMAP_IOEND_SHARED;
+	if (iomap->flags & IOMAP_F_INTEGRITY)
+		flags |= IOMAP_IOEND_INTEGRITY;
+
+	return flags;
+}
 
 /*
  * Structure for writeback I/O completions.
@@ -500,6 +522,7 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
 	u16			io_flags;	/* IOMAP_IOEND_* */
+	u32			io_bvec_offset;	/* offset into first bvec */
 	struct inode		*io_inode;	/* file being written to */
 	size_t			io_size;	/* size of the extent */
 	atomic_t		io_remaining;	/* completetion defer count */
@@ -517,6 +540,13 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
 	return container_of(bio, struct iomap_ioend, io_bio);
 }
 
+#define BVEC_ITER_IOEND(_ioend)				\
+{							\
+	.bi_sector	= (_ioend)->io_sector,		\
+	.bi_size	= (_ioend)->io_size,		\
+	.bi_offset	= (_ioend)->io_bvec_offset,	\
+}
+
 struct iomap_writeback_ops {
 	/*
 	 * Performs writeback on the passed in range
@@ -565,6 +595,7 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 		struct list_head *more_ioends);
 void iomap_sort_ioends(struct list_head *ioend_list);
+int iomap_ioend_integrity_verify(struct iomap_ioend *ioend);
 ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 		loff_t pos, loff_t end_pos, unsigned int dirty_len);
 int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error);
@@ -577,6 +608,11 @@ void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
 int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
 int iomap_writepages(struct iomap_writepage_ctx *wpc);
 
+void iomap_bounce_read(struct iomap_ioend *orig_ioend, unsigned int minsize,
+		void (*submit_ioend)(struct iomap_ioend *ioend));
+void iomap_bounce_read_end_io(struct iomap_ioend *ioend, struct bio *orig_bio,
+		int error);
+
 struct iomap_read_folio_ctx {
 	const struct iomap_read_ops *ops;
 	struct folio		*cur_folio;