block: introduce folio awareness and add a bigger size from folio

Add a bigger size from folio to bio and skip merge processing for pages.

Fetch the offset of page within a folio. Depending on the size of folio
and folio_offset, fetch a larger length. This length may consist of
multiple contiguous pages if folio is multiorder.

Using the length calculate number of pages which will be added to bio and
increment the loop counter to skip those pages.

This technique helps to avoid overhead of merging pages which belong to
same large order folio.

Also folio-ize the functions bio_iov_add_page() and
bio_iov_add_zone_append_page()

Signed-off-by: Kundan Kumar <[email protected]>
Tested-by: Luis Chamberlain <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Reviewed-by: Matthew Wilcox (Oracle) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

Author: Kundan Kumar

block/bio.c

@@ -931,7 +931,8 @@ 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);
+	*same_page = ((vec_end_addr & PAGE_MASK) == ((page_addr + off) &
+		     PAGE_MASK));
 	if (!*same_page) {
 		if (IS_ENABLED(CONFIG_KMSAN))
 			return false;
@@ -1227,8 +1228,8 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio_set_flag(bio, BIO_CLONED);
 }
 
-static int bio_iov_add_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int offset)
+static int bio_iov_add_folio(struct bio *bio, struct folio *folio, size_t len,
+			     size_t offset)
 {
 	bool same_page = false;
 
@@ -1237,30 +1238,61 @@ static int bio_iov_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)) {
+				folio_page(folio, 0), len, offset,
+				&same_page)) {
 		bio->bi_iter.bi_size += len;
 		if (same_page)
-			bio_release_page(bio, page);
+			bio_release_page(bio, folio_page(folio, 0));
 		return 0;
 	}
-	__bio_add_page(bio, page, len, offset);
+	bio_add_folio_nofail(bio, folio, len, offset);
 	return 0;
 }
 
-static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int offset)
+static int bio_iov_add_zone_append_folio(struct bio *bio, struct folio *folio,
+					 size_t len, size_t offset)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	bool same_page = false;
 
-	if (bio_add_hw_page(q, bio, page, len, offset,
+	if (bio_add_hw_folio(q, bio, folio, len, offset,
 			queue_max_zone_append_sectors(q), &same_page) != len)
 		return -EINVAL;
 	if (same_page)
-		bio_release_page(bio, page);
+		bio_release_page(bio, folio_page(folio, 0));
 	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,
+					 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 *))
 
 /**
@@ -1280,9 +1312,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	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, left;
-	unsigned len, i = 0;
-	size_t offset;
+	ssize_t size;
+	unsigned int num_pages, i = 0;
+	size_t offset, folio_offset, left, len;
 	int ret = 0;
 
 	/*
@@ -1322,17 +1354,28 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		goto out;
 	}
 
-	for (left = size, i = 0; left > 0; left -= len, i++) {
+	for (left = size, i = 0; left > 0; left -= len, i += num_pages) {
 		struct page *page = pages[i];
+		struct folio *folio = page_folio(page);
+
+		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);
 
-		len = min_t(size_t, PAGE_SIZE - offset, left);
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
-			ret = bio_iov_add_zone_append_page(bio, page, len,
-					offset);
+			ret = bio_iov_add_zone_append_folio(bio, folio, len,
+					folio_offset);
 			if (ret)
 				break;
 		} else
-			bio_iov_add_page(bio, page, len, offset);
+			bio_iov_add_folio(bio, folio, len, folio_offset);
 
 		offset = 0;
 	}