[PATCH 6.18.y 1/6] iov_iter: extract a iov_iter_extract_bvecs helper from bio code

[Sasha Levin <sashal@kernel.org>]

From: Christoph Hellwig <hch@lst.de>

[ Upstream commit 91b73c458182801a8c9cf6135335e064567d1013 ]

Massage __bio_iov_iter_get_pages so that it doesn't need the bio, and
move it to lib/iov_iter.c so that it can be used by block code for
other things than filling a bio and by other subsystems like netfs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Stable-dep-of: 14b007e17881 ("block: validate user space vectors during extraction")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 block/bio.c         | 141 ++++++--------------------------------------
 include/linux/uio.h |   3 +
 lib/iov_iter.c      |  98 ++++++++++++++++++++++++++++++
 3 files changed, 120 insertions(+), 122 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index b184f0a3fcb2b..63594139efe05 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1166,122 +1166,6 @@ void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter)
 	bio_set_flag(bio, BIO_CLONED);
 }
 
-static unsigned int get_contig_folio_len(unsigned int *num_pages,
-					 struct page **pages, unsigned int i,
-					 struct folio *folio, size_t left,
-					 size_t offset)
-{
-	size_t bytes = left;
-	size_t contig_sz = min_t(size_t, PAGE_SIZE - offset, bytes);
-	unsigned int j;
-
-	/*
-	 * We might COW a single page in the middle of
-	 * a large folio, so we have to check that all
-	 * pages belong to the same folio.
-	 */
-	bytes -= contig_sz;
-	for (j = i + 1; j < i + *num_pages; j++) {
-		size_t next = min_t(size_t, PAGE_SIZE, bytes);
-
-		if (page_folio(pages[j]) != folio ||
-		    pages[j] != pages[j - 1] + 1) {
-			break;
-		}
-		contig_sz += next;
-		bytes -= next;
-	}
-	*num_pages = j - i;
-
-	return contig_sz;
-}
-
-#define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
-
-/**
- * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
- * @bio: bio to add pages to
- * @iter: iov iterator describing the region to be mapped
- *
- * Extracts pages from *iter and appends them to @bio's bvec array.  The pages
- * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag.
- * For a multi-segment *iter, this function only adds pages from the next
- * non-empty segment of the iov iterator.
- */
-static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
-{
-	iov_iter_extraction_t extraction_flags = 0;
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
-	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
-	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
-	struct page **pages = (struct page **)bv;
-	ssize_t size;
-	unsigned int num_pages, i = 0;
-	size_t offset, folio_offset, left, len;
-	int ret = 0;
-
-	/*
-	 * Move page array up in the allocated memory for the bio vecs as far as
-	 * possible so that we can start filling biovecs from the beginning
-	 * without overwriting the temporary page array.
-	 */
-	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
-	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
-
-	if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue))
-		extraction_flags |= ITER_ALLOW_P2PDMA;
-
-	size = iov_iter_extract_pages(iter, &pages,
-				      UINT_MAX - bio->bi_iter.bi_size,
-				      nr_pages, extraction_flags, &offset);
-	if (unlikely(size <= 0))
-		return size ? size : -EFAULT;
-
-	nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
-	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;
-
-		len = min(folio_size(folio) - folio_offset, left);
-
-		num_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
-
-		if (num_pages > 1)
-			len = get_contig_folio_len(&num_pages, pages, i,
-						   folio, left, 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;
-	}
-
-	iov_iter_revert(iter, left);
-out:
-	while (i < nr_pages)
-		bio_release_page(bio, pages[i++]);
-
-	return ret;
-}
-
 /*
  * Aligns the bio size to the len_align_mask, releasing excessive bio vecs that
  * __bio_iov_iter_get_pages may have inserted, and reverts the trimmed length
@@ -1339,7 +1223,7 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 			   unsigned len_align_mask)
 {
-	int ret = 0;
+	iov_iter_extraction_t flags = 0;
 
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return -EIO;
@@ -1352,13 +1236,26 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 
 	if (iov_iter_extract_will_pin(iter))
 		bio_set_flag(bio, BIO_PAGE_PINNED);
+	if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue))
+		flags |= ITER_ALLOW_P2PDMA;
+
 	do {
-		ret = __bio_iov_iter_get_pages(bio, iter);
-	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
+		ssize_t ret;
+
+		ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec,
+				UINT_MAX - bio->bi_iter.bi_size,
+				&bio->bi_vcnt, bio->bi_max_vecs, flags);
+		if (ret <= 0) {
+			if (!bio->bi_vcnt)
+				return ret;
+			break;
+		}
+		bio->bi_iter.bi_size += ret;
+	} while (iov_iter_count(iter) && !bio_full(bio, 0));
 
-	if (bio->bi_vcnt)
-		return bio_iov_iter_align_down(bio, iter, len_align_mask);
-	return ret;
+	if (is_pci_p2pdma_page(bio->bi_io_vec->bv_page))
+		bio->bi_opf |= REQ_NOMERGE;
+	return bio_iov_iter_align_down(bio, iter, len_align_mask);
 }
 
 static void submit_bio_wait_endio(struct bio *bio)
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 5b127043a1519..a9bc5b3067e32 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -389,6 +389,9 @@ ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages,
 			       size_t maxsize, unsigned int maxpages,
 			       iov_iter_extraction_t extraction_flags,
 			       size_t *offset0);
+ssize_t iov_iter_extract_bvecs(struct iov_iter *iter, struct bio_vec *bv,
+		size_t max_size, unsigned short *nr_vecs,
+		unsigned short max_vecs, iov_iter_extraction_t extraction_flags);
 
 /**
  * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 4bc7c19337558..53dcd9649d59a 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1833,3 +1833,101 @@ ssize_t iov_iter_extract_pages(struct iov_iter *i,
 	return -EFAULT;
 }
 EXPORT_SYMBOL_GPL(iov_iter_extract_pages);
+
+static unsigned int get_contig_folio_len(struct page **pages,
+		unsigned int *num_pages, size_t left, size_t offset)
+{
+	struct folio *folio = page_folio(pages[0]);
+	size_t contig_sz = min_t(size_t, PAGE_SIZE - offset, left);
+	unsigned int max_pages, i;
+	size_t folio_offset, len;
+
+	folio_offset = PAGE_SIZE * folio_page_idx(folio, pages[0]) + offset;
+	len = min(folio_size(folio) - folio_offset, left);
+
+	/*
+	 * We might COW a single page in the middle of a large folio, so we have
+	 * to check that all pages belong to the same folio.
+	 */
+	left -= contig_sz;
+	max_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+	for (i = 1; i < max_pages; i++) {
+		size_t next = min_t(size_t, PAGE_SIZE, left);
+
+		if (page_folio(pages[i]) != folio ||
+		    pages[i] != pages[i - 1] + 1)
+			break;
+		contig_sz += next;
+		left -= next;
+	}
+
+	*num_pages = i;
+	return contig_sz;
+}
+
+#define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
+
+/**
+ * iov_iter_extract_bvecs - Extract bvecs from an iterator
+ * @iter:	the iterator to extract from
+ * @bv:		bvec return array
+ * @max_size:	maximum size to extract from @iter
+ * @nr_vecs:	number of vectors in @bv (on in and output)
+ * @max_vecs:	maximum vectors in @bv, including those filled before calling
+ * @extraction_flags: flags to qualify request
+ *
+ * Like iov_iter_extract_pages(), but returns physically contiguous ranges
+ * contained in a single folio as a single bvec instead of multiple entries.
+ *
+ * Returns the number of bytes extracted when successful, or a negative errno.
+ * If @nr_vecs was non-zero on entry, the number of successfully extracted bytes
+ * can be 0.
+ */
+ssize_t iov_iter_extract_bvecs(struct iov_iter *iter, struct bio_vec *bv,
+		size_t max_size, unsigned short *nr_vecs,
+		unsigned short max_vecs, iov_iter_extraction_t extraction_flags)
+{
+	unsigned short entries_left = max_vecs - *nr_vecs;
+	unsigned short nr_pages, i = 0;
+	size_t left, offset, len;
+	struct page **pages;
+	ssize_t size;
+
+	/*
+	 * Move page array up in the allocated memory for the bio vecs as far as
+	 * possible so that we can start filling biovecs from the beginning
+	 * without overwriting the temporary page array.
+	 */
+	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
+	pages = (struct page **)(bv + *nr_vecs) +
+		entries_left * (PAGE_PTRS_PER_BVEC - 1);
+
+	size = iov_iter_extract_pages(iter, &pages, max_size, entries_left,
+			extraction_flags, &offset);
+	if (unlikely(size <= 0))
+		return size ? size : -EFAULT;
+
+	nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
+	for (left = size; left > 0; left -= len) {
+		unsigned int nr_to_add;
+
+		if (*nr_vecs > 0 &&
+		    !zone_device_pages_have_same_pgmap(bv[*nr_vecs - 1].bv_page,
+				pages[i]))
+			break;
+
+		len = get_contig_folio_len(&pages[i], &nr_to_add, left, offset);
+		bvec_set_page(&bv[*nr_vecs], pages[i], len, offset);
+		i += nr_to_add;
+		(*nr_vecs)++;
+		offset = 0;
+	}
+
+	iov_iter_revert(iter, left);
+	if (iov_iter_extract_will_pin(iter)) {
+		while (i < nr_pages)
+			unpin_user_page(pages[i++]);
+	}
+	return size - left;
+}
+EXPORT_SYMBOL_GPL(iov_iter_extract_bvecs);
-- 
2.53.0