1 files changed, 70 insertions, 77 deletions

diff --git a/block/bio.c b/block/bio.c
index e07bea077db8..39c6acdd777d 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -942,9 +942,8 @@ static inline bool bio_full(struct bio *bio, unsigned len)
 	return false;
 }
 
-static inline bool page_is_mergeable(const struct bio_vec *bv,
-		struct page *page, unsigned int len, unsigned int off,
-		bool *same_page)
+static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
+		unsigned int len, unsigned int off, bool *same_page)
 {
 	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;
@@ -958,49 +957,15 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		return false;
 
 	*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
-	if (*same_page)
-		return true;
-	else if (IS_ENABLED(CONFIG_KMSAN))
-		return false;
-	return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
-}
-
-/**
- * __bio_try_merge_page - try appending data to an existing bvec.
- * @bio: destination bio
- * @page: start page to add
- * @len: length of the data to add
- * @off: offset of the data relative to @page
- * @same_page: return if the segment has been merged inside the same page
- *
- * Try to add the data at @page + @off to the last bvec of @bio.  This is a
- * useful optimisation for file systems with a block size smaller than the
- * page size.
- *
- * Warn if (@len, @off) crosses pages in case that @same_page is true.
- *
- * Return %true on success or %false on failure.
- */
-static bool __bio_try_merge_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int off, bool *same_page)
-{
-	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
-		return false;
-
-	if (bio->bi_vcnt > 0) {
-		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
-		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len) {
-				*same_page = false;
-				return false;
-			}
-			bv->bv_len += len;
-			bio->bi_iter.bi_size += len;
-			return true;
-		}
+	if (!*same_page) {
+		if (IS_ENABLED(CONFIG_KMSAN))
+			return false;
+		if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE)
+			return false;
 	}
-	return false;
+
+	bv->bv_len += len;
+	return true;
 }
 
 /*
@@ -1008,11 +973,10 @@ static bool __bio_try_merge_page(struct bio *bio, struct page *page,
  * size limit.  This is not for normal read/write bios, but for passthrough
  * or Zone Append operations that we can't split.
  */
-static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
-				 struct page *page, unsigned len,
-				 unsigned offset, bool *same_page)
+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 bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 	unsigned long mask = queue_segment_boundary(q);
 	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
 	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
@@ -1021,7 +985,7 @@ static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
 		return false;
 	if (bv->bv_len + len > queue_max_segment_size(q))
 		return false;
-	return __bio_try_merge_page(bio, page, len, offset, same_page);
+	return bvec_try_merge_page(bv, page, len, offset, same_page);
 }
 
 /**
@@ -1041,8 +1005,6 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page)
 {
-	struct bio_vec *bvec;
-
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 
@@ -1050,15 +1012,19 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		return 0;
 
 	if (bio->bi_vcnt > 0) {
-		if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page))
+		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+		if (bvec_try_merge_hw_page(q, bv, page, len, offset,
+				same_page)) {
+			bio->bi_iter.bi_size += len;
 			return len;
+		}
 
 		/*
 		 * If the queue doesn't support SG gaps and adding this segment
 		 * would create a gap, disallow it.
 		 */
-		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
-		if (bvec_gap_to_prev(&q->limits, bvec, offset))
+		if (bvec_gap_to_prev(&q->limits, bv, offset))
 			return 0;
 	}
 
@@ -1168,15 +1134,33 @@ int bio_add_page(struct bio *bio, struct page *page,
 {
 	bool same_page = false;
 
-	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
-		if (bio_full(bio, len))
-			return 0;
-		__bio_add_page(bio, page, len, offset);
+	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+		return 0;
+	if (bio->bi_iter.bi_size > UINT_MAX - len)
+		return 0;
+
+	if (bio->bi_vcnt > 0 &&
+	    bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
+				page, len, offset, &same_page)) {
+		bio->bi_iter.bi_size += len;
+		return len;
 	}
+
+	if (bio_full(bio, len))
+		return 0;
+	__bio_add_page(bio, page, len, offset);
 	return len;
 }
 EXPORT_SYMBOL(bio_add_page);
 
+void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
+			  size_t off)
+{
+	WARN_ON_ONCE(len > UINT_MAX);
+	WARN_ON_ONCE(off > UINT_MAX);
+	__bio_add_page(bio, &folio->page, len, off);
+}
+
 /**
  * bio_add_folio - Attempt to add part of a folio to a bio.
  * @bio: BIO to add to.
@@ -1208,7 +1192,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 	bio_for_each_segment_all(bvec, bio, iter_all) {
 		if (mark_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
-		put_page(bvec->bv_page);
+		bio_release_page(bio, bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1230,7 +1214,6 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio->bi_io_vec = (struct bio_vec *)iter->bvec;
 	bio->bi_iter.bi_bvec_done = iter->iov_offset;
 	bio->bi_iter.bi_size = size;
-	bio_set_flag(bio, BIO_NO_PAGE_REF);
 	bio_set_flag(bio, BIO_CLONED);
 }
 
@@ -1239,13 +1222,18 @@ static int bio_iov_add_page(struct bio *bio, struct page *page,
 {
 	bool same_page = false;
 
-	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
-		__bio_add_page(bio, page, len, offset);
+	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],
+				page, len, offset, &same_page)) {
+		bio->bi_iter.bi_size += len;
+		if (same_page)
+			bio_release_page(bio, page);
 		return 0;
 	}
-
-	if (same_page)
-		put_page(page);
+	__bio_add_page(bio, page, len, offset);
 	return 0;
 }
 
@@ -1259,7 +1247,7 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
 			queue_max_zone_append_sectors(q), &same_page) != len)
 		return -EINVAL;
 	if (same_page)
-		put_page(page);
+		bio_release_page(bio, page);
 	return 0;
 }
 
@@ -1270,10 +1258,10 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins pages from *iter and appends them to @bio's bvec array. The
- * pages will have to be released using put_page() when done.
- * For multi-segment *iter, this function only adds pages from the
- * next non-empty segment of the iov iterator.
+ * 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)
 {
@@ -1305,9 +1293,9 @@ 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,
-				  UINT_MAX - bio->bi_iter.bi_size,
-				  nr_pages, &offset, extraction_flags);
+	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;
 
@@ -1340,7 +1328,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	iov_iter_revert(iter, left);
 out:
 	while (i < nr_pages)
-		put_page(pages[i++]);
+		bio_release_page(bio, pages[i++]);
 
 	return ret;
 }
@@ -1369,12 +1357,17 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
 	int ret = 0;
 
+	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
+		return -EIO;
+
 	if (iov_iter_is_bvec(iter)) {
 		bio_iov_bvec_set(bio, iter);
 		iov_iter_advance(iter, bio->bi_iter.bi_size);
 		return 0;
 	}
 
+	if (iov_iter_extract_will_pin(iter))
+		bio_set_flag(bio, BIO_PAGE_PINNED);
 	do {
 		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
@@ -1528,8 +1521,8 @@ void bio_set_pages_dirty(struct bio *bio)
  * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
- * here on.  It will run one put_page() against each page and will run one
- * bio_put() against the BIO.
+ * here on.  It will unpin each page and will run one bio_put() against the
+ * BIO.
  */
 
 static void bio_dirty_fn(struct work_struct *work);