Skip to contentSkip to conversation

block: Rework bio_for_each_segment_all()

PATCH In review Kent Overstreet 4 participants 10 messages Jun 5, 2023 – Jun 9, 2023

Subsystems (20)
VFS SCSI PowerPC Block layer +16 more subsystems
lore
Share & tools
lore

Kent Overstreet

author maintainer
#0 lore raw

PATCH v2 1/5 block: Rework bio_for_each_segment_all()

This patch reworks bio_for_each_segment_all() to be more inline with how the other bio iterators work:

- bio_iter_all_peek() now returns a synthesized bio_vec; we don't stash one in the iterator and pass a pointer to it - bad. This way makes it clearer what's a constructed value vs. a reference to something pre-existing, and it also will help with cleaning up and consolidating code with bio_for_each_folio_all().

- We now provide bio_for_each_segment_all_continue(), for squashfs:
this makes their code clearer.

---
 block/bio.c                | 38 ++++++++++++------------
 block/blk-map.c            | 38 ++++++++++++------------
 block/bounce.c             | 12 ++++----
 drivers/md/bcache/btree.c  |  8 ++---
 drivers/md/dm-crypt.c      | 10 +++----
 drivers/md/raid1.c         |  4 +--
 fs/btrfs/disk-io.c         |  4 +--
 fs/btrfs/extent_io.c       | 50 +++++++++++++++----------------
 fs/btrfs/raid56.c          | 14 ++++-----
 fs/erofs/zdata.c           |  4 +--
 fs/f2fs/data.c             | 20 ++++++-------
 fs/gfs2/lops.c             | 10 +++----
 fs/gfs2/meta_io.c          |  8 ++---
 fs/squashfs/block.c        | 48 +++++++++++++++++-------------
 fs/squashfs/lz4_wrapper.c  | 17 ++++++-----
 fs/squashfs/lzo_wrapper.c  | 17 ++++++-----
 fs/squashfs/xz_wrapper.c   | 19 ++++++------
 fs/squashfs/zlib_wrapper.c | 18 ++++++-----
 fs/squashfs/zstd_wrapper.c | 19 ++++++------
 include/linux/bio.h        | 28 ++++++++++++-----
 include/linux/bvec.h       | 61 ++++++++++++++++++++++----------------
 21 files changed, 242 insertions(+), 205 deletions(-)
block/bio.c +19 -19
index 798cc4cf3b..2af9f50643 100644
@@ -1163,13 +1163,13 @@ EXPORT_SYMBOL(bio_add_folio);
 
 void __bio_release_pages(struct bio *bio, bool mark_dirty)
 {
-	struct bvec_iter_all iter_all;
-	struct bio_vec *bvec;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (mark_dirty && !PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
-		bio_release_page(bio, bvec->bv_page);
+	bio_for_each_segment_all(bvec, bio, iter) {
+		if (mark_dirty && !PageCompound(bvec.bv_page))
+			set_page_dirty_lock(bvec.bv_page);
+		bio_release_page(bio, bvec.bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1435,11 +1435,11 @@ EXPORT_SYMBOL(bio_copy_data);
 
 void bio_free_pages(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all)
-		__free_page(bvec->bv_page);
+	bio_for_each_segment_all(bvec, bio, iter)
+		__free_page(bvec.bv_page);
 }
 EXPORT_SYMBOL(bio_free_pages);
 
@@ -1474,12 +1474,12 @@ EXPORT_SYMBOL(bio_free_pages);
  */
 void bio_set_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
+	bio_for_each_segment_all(bvec, bio, iter) {
+		if (!PageCompound(bvec.bv_page))
+			set_page_dirty_lock(bvec.bv_page);
 	}
 }
 
@@ -1522,12 +1522,12 @@ static void bio_dirty_fn(struct work_struct *work)
 
 void bio_check_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 	unsigned long flags;
-	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+	bio_for_each_segment_all(bvec, bio, iter) {
+		if (!PageDirty(bvec.bv_page) && !PageCompound(bvec.bv_page))
 			goto defer;
 	}
 
block/blk-map.c +19 -19
index 3551c3ff17..524d84011f 100644
@@ -47,21 +47,21 @@ static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
  */
 static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all bv_iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_segment_all(bvec, bio, bv_iter) {
 		ssize_t ret;
 
-		ret = copy_page_from_iter(bvec->bv_page,
-					  bvec->bv_offset,
-					  bvec->bv_len,
+		ret = copy_page_from_iter(bvec.bv_page,
+					  bvec.bv_offset,
+					  bvec.bv_len,
 					  iter);
 
 		if (!iov_iter_count(iter))
 			break;
 
-		if (ret < bvec->bv_len)
+		if (ret < bvec.bv_len)
 			return -EFAULT;
 	}
 
@@ -78,21 +78,21 @@ static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
  */
 static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all bv_iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_segment_all(bvec, bio, bv_iter) {
 		ssize_t ret;
 
-		ret = copy_page_to_iter(bvec->bv_page,
-					bvec->bv_offset,
-					bvec->bv_len,
+		ret = copy_page_to_iter(bvec.bv_page,
+					bvec.bv_offset,
+					bvec.bv_len,
 					&iter);
 
 		if (!iov_iter_count(&iter))
 			break;
 
-		if (ret < bvec->bv_len)
+		if (ret < bvec.bv_len)
 			return -EFAULT;
 	}
 
@@ -443,12 +443,12 @@ static void bio_copy_kern_endio(struct bio *bio)
 static void bio_copy_kern_endio_read(struct bio *bio)
 {
 	char *p = bio->bi_private;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		memcpy_from_bvec(p, bvec);
-		p += bvec->bv_len;
+	bio_for_each_segment_all(bvec, bio, iter) {
+		memcpy_from_bvec(p, &bvec);
+		p += bvec.bv_len;
 	}
 
 	bio_copy_kern_endio(bio);
block/bounce.c +6 -6
index 7cfcb242f9..e701832d76 100644
@@ -102,18 +102,18 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 static void bounce_end_io(struct bio *bio)
 {
 	struct bio *bio_orig = bio->bi_private;
-	struct bio_vec *bvec, orig_vec;
+	struct bio_vec bvec, orig_vec;
 	struct bvec_iter orig_iter = bio_orig->bi_iter;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
 
 	/*
 	 * free up bounce indirect pages used
 	 */
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter) {
 		orig_vec = bio_iter_iovec(bio_orig, orig_iter);
-		if (bvec->bv_page != orig_vec.bv_page) {
-			dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
-			mempool_free(bvec->bv_page, &page_pool);
+		if (bvec.bv_page != orig_vec.bv_page) {
+			dec_zone_page_state(bvec.bv_page, NR_BOUNCE);
+			mempool_free(bvec.bv_page, &page_pool);
 		}
 		bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len);
 	}
drivers/md/bcache/btree.c +4 -4
index 147c493a98..98ce12b239 100644
@@ -373,12 +373,12 @@ static void do_btree_node_write(struct btree *b)
 		       bset_sector_offset(&b->keys, i));
 
 	if (!bch_bio_alloc_pages(b->bio, __GFP_NOWARN|GFP_NOWAIT)) {
-		struct bio_vec *bv;
+		struct bio_vec bv;
 		void *addr = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
-		struct bvec_iter_all iter_all;
+		struct bvec_iter_all iter;
 
-		bio_for_each_segment_all(bv, b->bio, iter_all) {
-			memcpy(page_address(bv->bv_page), addr, PAGE_SIZE);
+		bio_for_each_segment_all(bv, b->bio, iter) {
+			memcpy(page_address(bv.bv_page), addr, PAGE_SIZE);
 			addr += PAGE_SIZE;
 		}
 
drivers/md/dm-crypt.c +5 -5
index 8b47b913ee..8ffc225f7b 100644
@@ -1713,12 +1713,12 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 
 static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
 {
-	struct bio_vec *bv;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bv;
 
-	bio_for_each_segment_all(bv, clone, iter_all) {
-		BUG_ON(!bv->bv_page);
-		mempool_free(bv->bv_page, &cc->page_pool);
+	bio_for_each_segment_all(bv, clone, iter) {
+		BUG_ON(!bv.bv_page);
+		mempool_free(bv.bv_page, &cc->page_pool);
 	}
 }
 
drivers/md/raid1.c +2 -2
index 68a9e2d998..4f58cae37e 100644
@@ -2188,7 +2188,7 @@ static void process_checks(struct r1bio *r1_bio)
 		blk_status_t status = sbio->bi_status;
 		struct page **ppages = get_resync_pages(pbio)->pages;
 		struct page **spages = get_resync_pages(sbio)->pages;
-		struct bio_vec *bi;
+		struct bio_vec bi;
 		int page_len[RESYNC_PAGES] = { 0 };
 		struct bvec_iter_all iter_all;
 
@@ -2198,7 +2198,7 @@ static void process_checks(struct r1bio *r1_bio)
 		sbio->bi_status = 0;
 
 		bio_for_each_segment_all(bi, sbio, iter_all)
-			page_len[j++] = bi->bv_len;
+			page_len[j++] = bi.bv_len;
 
 		if (!status) {
 			for (j = vcnt; j-- ; ) {
fs/btrfs/disk-io.c +2 -2
index fbf9006c62..10326f978a 100644
@@ -3807,12 +3807,12 @@ ALLOW_ERROR_INJECTION(open_ctree, ERRNO);
 static void btrfs_end_super_write(struct bio *bio)
 {
 	struct btrfs_device *device = bio->bi_private;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 	struct page *page;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
+		page = bvec.bv_page;
 
 		if (bio->bi_status) {
 			btrfs_warn_rl_in_rcu(device->fs_info,
fs/btrfs/extent_io.c +25 -25

125 lines not on this page · raw message

fs/btrfs/raid56.c +7 -7
index 2fab37f062..8da6097c42 100644
@@ -1393,7 +1393,7 @@ static struct sector_ptr *find_stripe_sector(struct btrfs_raid_bio *rbio,
 static void set_bio_pages_uptodate(struct btrfs_raid_bio *rbio, struct bio *bio)
 {
 	const u32 sectorsize = rbio->bioc->fs_info->sectorsize;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
@@ -1402,9 +1402,9 @@ static void set_bio_pages_uptodate(struct btrfs_raid_bio *rbio, struct bio *bio)
 		struct sector_ptr *sector;
 		int pgoff;
 
-		for (pgoff = bvec->bv_offset; pgoff - bvec->bv_offset < bvec->bv_len;
+		for (pgoff = bvec.bv_offset; pgoff - bvec.bv_offset < bvec.bv_len;
 		     pgoff += sectorsize) {
-			sector = find_stripe_sector(rbio, bvec->bv_page, pgoff);
+			sector = find_stripe_sector(rbio, bvec.bv_page, pgoff);
 			ASSERT(sector);
 			if (sector)
 				sector->uptodate = 1;
@@ -1458,7 +1458,7 @@ static void verify_bio_data_sectors(struct btrfs_raid_bio *rbio,
 {
 	struct btrfs_fs_info *fs_info = rbio->bioc->fs_info;
 	int total_sector_nr = get_bio_sector_nr(rbio, bio);
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	/* No data csum for the whole stripe, no need to verify. */
@@ -1472,8 +1472,8 @@ static void verify_bio_data_sectors(struct btrfs_raid_bio *rbio,
 	bio_for_each_segment_all(bvec, bio, iter_all) {
 		int bv_offset;
 
-		for (bv_offset = bvec->bv_offset;
-		     bv_offset < bvec->bv_offset + bvec->bv_len;
+		for (bv_offset = bvec.bv_offset;
+		     bv_offset < bvec.bv_offset + bvec.bv_len;
 		     bv_offset += fs_info->sectorsize, total_sector_nr++) {
 			u8 csum_buf[BTRFS_CSUM_SIZE];
 			u8 *expected_csum = rbio->csum_buf +
@@ -1484,7 +1484,7 @@ static void verify_bio_data_sectors(struct btrfs_raid_bio *rbio,
 			if (!test_bit(total_sector_nr, rbio->csum_bitmap))
 				continue;
 
-			ret = btrfs_check_sector_csum(fs_info, bvec->bv_page,
+			ret = btrfs_check_sector_csum(fs_info, bvec.bv_page,
 				bv_offset, csum_buf, expected_csum);
 			if (ret < 0)
 				set_bit(total_sector_nr, rbio->error_bitmap);
fs/erofs/zdata.c +2 -2
index 45f21db230..fc0ce6d685 100644
@@ -1648,11 +1648,11 @@ static void z_erofs_decompressqueue_endio(struct bio *bio)
 {
 	struct z_erofs_decompressqueue *q = bio->bi_private;
 	blk_status_t err = bio->bi_status;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 
 		DBG_BUGON(PageUptodate(page));
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
fs/f2fs/data.c +10 -10
index 7165b1202f..d687e11bdf 100644
@@ -139,12 +139,12 @@ struct bio_post_read_ctx {
  */
 static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	struct bvec_iter_all iter_all;
 	struct bio_post_read_ctx *ctx = bio->bi_private;
 
 	bio_for_each_segment_all(bv, bio, iter_all) {
-		struct page *page = bv->bv_page;
+		struct page *page = bv.bv_page;
 
 		if (f2fs_is_compressed_page(page)) {
 			if (ctx && !ctx->decompression_attempted)
@@ -189,11 +189,11 @@ static void f2fs_verify_bio(struct work_struct *work)
 	 * as those were handled separately by f2fs_end_read_compressed_page().
 	 */
 	if (may_have_compressed_pages) {
-		struct bio_vec *bv;
+		struct bio_vec bv;
 		struct bvec_iter_all iter_all;
 
 		bio_for_each_segment_all(bv, bio, iter_all) {
-			struct page *page = bv->bv_page;
+			struct page *page = bv.bv_page;
 
 			if (!f2fs_is_compressed_page(page) &&
 			    !fsverity_verify_page(page)) {
@@ -241,13 +241,13 @@ static void f2fs_verify_and_finish_bio(struct bio *bio, bool in_task)
 static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx,
 		bool in_task)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	struct bvec_iter_all iter_all;
 	bool all_compressed = true;
 	block_t blkaddr = ctx->fs_blkaddr;
 
 	bio_for_each_segment_all(bv, ctx->bio, iter_all) {
-		struct page *page = bv->bv_page;
+		struct page *page = bv.bv_page;
 
 		if (f2fs_is_compressed_page(page))
 			f2fs_end_read_compressed_page(page, false, blkaddr,
@@ -327,7 +327,7 @@ static void f2fs_read_end_io(struct bio *bio)
 static void f2fs_write_end_io(struct bio *bio)
 {
 	struct f2fs_sb_info *sbi;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	iostat_update_and_unbind_ctx(bio);
@@ -337,7 +337,7 @@ static void f2fs_write_end_io(struct bio *bio)
 		bio->bi_status = BLK_STS_IOERR;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 		enum count_type type = WB_DATA_TYPE(page);
 
 		if (page_private_dummy(page)) {
@@ -583,7 +583,7 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 static bool __has_merged_page(struct bio *bio, struct inode *inode,
 						struct page *page, nid_t ino)
 {
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	if (!bio)
@@ -593,7 +593,7 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode,
 		return true;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *target = bvec->bv_page;
+		struct page *target = bvec.bv_page;
 
 		if (fscrypt_is_bounce_page(target)) {
 			target = fscrypt_pagecache_page(target);
fs/gfs2/lops.c +5 -5
index 1902413d5d..7f62fe8eb7 100644
@@ -202,7 +202,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp,
 static void gfs2_end_log_write(struct bio *bio)
 {
 	struct gfs2_sbd *sdp = bio->bi_private;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct page *page;
 	struct bvec_iter_all iter_all;
 
@@ -217,9 +217,9 @@ static void gfs2_end_log_write(struct bio *bio)
 	}
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
+		page = bvec.bv_page;
 		if (page_has_buffers(page))
-			gfs2_end_log_write_bh(sdp, bvec, bio->bi_status);
+			gfs2_end_log_write_bh(sdp, &bvec, bio->bi_status);
 		else
 			mempool_free(page, gfs2_page_pool);
 	}
@@ -395,11 +395,11 @@ static void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
 static void gfs2_end_log_read(struct bio *bio)
 {
 	struct page *page;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
+		page = bvec.bv_page;
 		if (bio->bi_status) {
 			int err = blk_status_to_errno(bio->bi_status);
 
fs/gfs2/meta_io.c +4 -4
index 924361fa51..832572784e 100644
@@ -193,15 +193,15 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 
 static void gfs2_meta_read_endio(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 		struct buffer_head *bh = page_buffers(page);
-		unsigned int len = bvec->bv_len;
+		unsigned int len = bvec.bv_len;
 
-		while (bh_offset(bh) < bvec->bv_offset)
+		while (bh_offset(bh) < bvec.bv_offset)
 			bh = bh->b_this_page;
 		do {
 			struct buffer_head *next = bh->b_this_page;
fs/squashfs/block.c +27 -21

97 lines not on this page · raw message

fs/squashfs/lz4_wrapper.c +10 -7
index 49797729f1..bd0dd787d2 100644
@@ -92,20 +92,23 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 	struct squashfs_lz4 *stream = strm;
 	void *buff = stream->input, *data;
 	int bytes = length, res;
 
-	while (bio_next_segment(bio, &iter_all)) {
-		int avail = min(bytes, ((int)bvec->bv_len) - offset);
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
 
-		data = bvec_virt(bvec);
-		memcpy(buff, data + offset, avail);
+	bio_for_each_segment_all_continue(bvec, bio, iter) {
+		unsigned avail = min_t(unsigned, bytes, bvec.bv_len);
+
+		memcpy(buff, bvec_virt(&bvec), avail);
 		buff += avail;
 		bytes -= avail;
-		offset = 0;
+		if (!bytes)
+			break;
 	}
 
 	res = LZ4_decompress_safe(stream->input, stream->output,
fs/squashfs/lzo_wrapper.c +10 -7
index d216aeefa8..bccfcfa12e 100644
@@ -66,21 +66,24 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 	struct squashfs_lzo *stream = strm;
 	void *buff = stream->input, *data;
 	int bytes = length, res;
 	size_t out_len = output->length;
 
-	while (bio_next_segment(bio, &iter_all)) {
-		int avail = min(bytes, ((int)bvec->bv_len) - offset);
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
 
-		data = bvec_virt(bvec);
-		memcpy(buff, data + offset, avail);
+	bio_for_each_segment_all_continue(bvec, bio, iter) {
+		unsigned avail = min_t(unsigned, bytes, bvec.bv_len);
+
+		memcpy(buff, bvec_virt(&bvec), avail);
 		buff += avail;
 		bytes -= avail;
-		offset = 0;
+		if (!bytes)
+			break;
 	}
 
 	res = lzo1x_decompress_safe(stream->input, (size_t)length,
fs/squashfs/xz_wrapper.c +10 -9
index 6c49481a2f..6cf0e11e3b 100644
@@ -120,8 +120,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
 	int total = 0, error = 0;
 	struct squashfs_xz *stream = strm;
 
@@ -136,26 +135,28 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		goto finish;
 	}
 
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
+
 	for (;;) {
 		enum xz_ret xz_err;
 
 		if (stream->buf.in_pos == stream->buf.in_size) {
-			const void *data;
-			int avail;
+			struct bio_vec bvec = bio_iter_all_peek(bio, &iter);
+			unsigned avail = min_t(unsigned, length, bvec.bv_len);
 
-			if (!bio_next_segment(bio, &iter_all)) {
+			if (iter.idx >= bio->bi_vcnt) {
 				/* XZ_STREAM_END must be reached. */
 				error = -EIO;
 				break;
 			}
 
-			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = bvec_virt(bvec);
 			length -= avail;
-			stream->buf.in = data + offset;
+			stream->buf.in = bvec_virt(&bvec);
 			stream->buf.in_size = avail;
 			stream->buf.in_pos = 0;
-			offset = 0;
+
+			bio_iter_all_advance(bio, &iter, avail);
 		}
 
 		if (stream->buf.out_pos == stream->buf.out_size) {
fs/squashfs/zlib_wrapper.c +10 -8
index cbb7afe7bc..981ca5e410 100644
@@ -53,8 +53,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
 	int zlib_init = 0, error = 0;
 	z_stream *stream = strm;
 
@@ -67,25 +66,28 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		goto finish;
 	}
 
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
+
 	for (;;) {
 		int zlib_err;
 
 		if (stream->avail_in == 0) {
-			const void *data;
+			struct bio_vec bvec = bio_iter_all_peek(bio, &iter);
 			int avail;
 
-			if (!bio_next_segment(bio, &iter_all)) {
+			if (iter.idx >= bio->bi_vcnt) {
 				/* Z_STREAM_END must be reached. */
 				error = -EIO;
 				break;
 			}
 
-			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = bvec_virt(bvec);
+			avail = min_t(unsigned, length, bvec.bv_len);
 			length -= avail;
-			stream->next_in = data + offset;
+			stream->next_in = bvec_virt(&bvec);
 			stream->avail_in = avail;
-			offset = 0;
+
+			bio_iter_all_advance(bio, &iter, avail);
 		}
 
 		if (stream->avail_out == 0) {
fs/squashfs/zstd_wrapper.c +10 -9
index 0e407c4d8b..658e5d462a 100644
@@ -68,8 +68,7 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	int error = 0;
 	zstd_in_buffer in_buf = { NULL, 0, 0 };
 	zstd_out_buffer out_buf = { NULL, 0, 0 };
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
 
 	stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size);
 
@@ -85,25 +84,27 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		goto finish;
 	}
 
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
+
 	for (;;) {
 		size_t zstd_err;
 
 		if (in_buf.pos == in_buf.size) {
-			const void *data;
-			int avail;
+			struct bio_vec bvec = bio_iter_all_peek(bio, &iter);
+			unsigned avail = min_t(unsigned, length, bvec.bv_len);
 
-			if (!bio_next_segment(bio, &iter_all)) {
+			if (iter.idx >= bio->bi_vcnt) {
 				error = -EIO;
 				break;
 			}
 
-			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = bvec_virt(bvec);
 			length -= avail;
-			in_buf.src = data + offset;
+			in_buf.src = bvec_virt(&bvec);
 			in_buf.size = avail;
 			in_buf.pos = 0;
-			offset = 0;
+
+			bio_iter_all_advance(bio, &iter, avail);
 		}
 
 		if (out_buf.pos == out_buf.size) {
include/linux/bio.h +20 -8
index 8588bcfbc6..39d8a1cc6e 100644
@@ -78,22 +78,34 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
-static inline bool bio_next_segment(const struct bio *bio,
-				    struct bvec_iter_all *iter)
+static inline struct bio_vec bio_iter_all_peek(const struct bio *bio,
+					       struct bvec_iter_all *iter)
 {
-	if (iter->idx >= bio->bi_vcnt)
-		return false;
+	return bvec_iter_all_peek(bio->bi_io_vec, iter);
+}
 
-	bvec_advance(&bio->bi_io_vec[iter->idx], iter);
-	return true;
+static inline void bio_iter_all_advance(const struct bio *bio,
+					struct bvec_iter_all *iter,
+					unsigned bytes)
+{
+	bvec_iter_all_advance(bio->bi_io_vec, iter, bytes);
 }
 
+#define bio_for_each_segment_all_continue(bvl, bio, iter)		\
+	for (;								\
+	     iter.idx < bio->bi_vcnt &&					\
+		((bvl = bio_iter_all_peek(bio, &iter)), true);		\
+	     bio_iter_all_advance((bio), &iter, bvl.bv_len))
+
 /*
  * drivers should _never_ use the all version - the bio may have been split
  * before it got to the driver and the driver won't own all of it
  */
-#define bio_for_each_segment_all(bvl, bio, iter) \
-	for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); )
+#define bio_for_each_segment_all(bvl, bio, iter)			\
+	for (bvec_iter_all_init(&iter);					\
+	     iter.idx < (bio)->bi_vcnt &&				\
+		((bvl = bio_iter_all_peek((bio), &iter)), true);		\
+	     bio_iter_all_advance((bio), &iter, bvl.bv_len))
 
 static inline void bio_advance_iter(const struct bio *bio,
 				    struct bvec_iter *iter, unsigned int bytes)
include/linux/bvec.h +35 -26

87 lines not on this page · raw message

Signature · 1 line
2.40.1
author maintainer
#1 lore raw

PATCH v2 2/5 block: Rework bio_for_each_folio_all()

This reimplements bio_for_each_folio_all() on top of the newly-reworked bvec_iter_all, and since it's now trivial we also provide bio_for_each_folio.

---
 fs/crypto/bio.c        |  9 ++--
 fs/ext4/page-io.c      | 11 ++---
 fs/ext4/readpage.c     |  7 ++--
 fs/iomap/buffered-io.c | 14 ++++---
 fs/mpage.c             | 22 +++++-----
 fs/verity/verify.c     |  9 ++--
 include/linux/bio.h    | 95 ++++++++++++++++++++++--------------------
 include/linux/bvec.h   | 13 ++++--
 8 files changed, 99 insertions(+), 81 deletions(-)
fs/crypto/bio.c +5 -4
index 62e1a3dd83..4fed8d175c 100644
@@ -30,11 +30,12 @@
  */
 bool fscrypt_decrypt_bio(struct bio *bio)
 {
-	struct folio_iter fi;
+	struct bvec_iter_all iter;
+	struct folio_seg fs;
 
-	bio_for_each_folio_all(fi, bio) {
-		int err = fscrypt_decrypt_pagecache_blocks(fi.folio, fi.length,
-							   fi.offset);
+	bio_for_each_folio_all(fs, bio, iter) {
+		int err = fscrypt_decrypt_pagecache_blocks(fs.fs_folio, fs.fs_len,
+							   fs.fs_offset);
 
 		if (err) {
 			bio->bi_status = errno_to_blk_status(err);
fs/ext4/page-io.c +6 -5
index 3621f29ec6..4c2fa805b3 100644
@@ -99,14 +99,15 @@ static void buffer_io_error(struct buffer_head *bh)
 
 static void ext4_finish_bio(struct bio *bio)
 {
-	struct folio_iter fi;
+	struct bvec_iter_all iter;
+	struct folio_seg fs;
 
-	bio_for_each_folio_all(fi, bio) {
-		struct folio *folio = fi.folio;
+	bio_for_each_folio_all(fs, bio, iter) {
+		struct folio *folio = fs.fs_folio;
 		struct folio *io_folio = NULL;
 		struct buffer_head *bh, *head;
-		size_t bio_start = fi.offset;
-		size_t bio_end = bio_start + fi.length;
+		size_t bio_start = fs.fs_offset;
+		size_t bio_end = bio_start + fs.fs_len;
 		unsigned under_io = 0;
 		unsigned long flags;
 
fs/ext4/readpage.c +4 -3
index 6f46823fba..8aa560d61c 100644
@@ -68,10 +68,11 @@ struct bio_post_read_ctx {
 
 static void __read_end_io(struct bio *bio)
 {
-	struct folio_iter fi;
+	struct bvec_iter_all iter;
+	struct folio_seg fs;
 
-	bio_for_each_folio_all(fi, bio) {
-		struct folio *folio = fi.folio;
+	bio_for_each_folio_all(fs, bio, iter) {
+		struct folio *folio = fs.fs_folio;
 
 		if (bio->bi_status)
 			folio_clear_uptodate(folio);
fs/iomap/buffered-io.c +8 -6
index 063133ec77..43956529cb 100644
@@ -187,10 +187,11 @@ static void iomap_finish_folio_read(struct folio *folio, size_t offset,
 static void iomap_read_end_io(struct bio *bio)
 {
 	int error = blk_status_to_errno(bio->bi_status);
-	struct folio_iter fi;
+	struct bvec_iter_all iter;
+	struct folio_seg fs;
 
-	bio_for_each_folio_all(fi, bio)
-		iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error);
+	bio_for_each_folio_all(fs, bio, iter)
+		iomap_finish_folio_read(fs.fs_folio, fs.fs_offset, fs.fs_len, error);
 	bio_put(bio);
 }
 
@@ -1321,7 +1322,8 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 	u32 folio_count = 0;
 
 	for (bio = &ioend->io_inline_bio; bio; bio = next) {
-		struct folio_iter fi;
+		struct bvec_iter_all iter;
+		struct folio_seg fs;
 
 		/*
 		 * For the last bio, bi_private points to the ioend, so we
@@ -1333,8 +1335,8 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 			next = bio->bi_private;
 
 		/* walk all folios in bio, ending page IO on them */
-		bio_for_each_folio_all(fi, bio) {
-			iomap_finish_folio_write(inode, fi.folio, fi.length,
+		bio_for_each_folio_all(fs, bio, iter) {
+			iomap_finish_folio_write(inode, fs.fs_folio, fs.fs_len,
 					error);
 			folio_count++;
 		}
fs/mpage.c +12 -10
index 242e213ee0..7da2c80f71 100644
@@ -45,15 +45,16 @@
  */
 static void mpage_read_end_io(struct bio *bio)
 {
-	struct folio_iter fi;
+	struct bvec_iter_all iter;
+	struct folio_seg fs;
 	int err = blk_status_to_errno(bio->bi_status);
 
-	bio_for_each_folio_all(fi, bio) {
+	bio_for_each_folio_all(fs, bio, iter) {
 		if (err)
-			folio_set_error(fi.folio);
+			folio_set_error(fs.fs_folio);
 		else
-			folio_mark_uptodate(fi.folio);
-		folio_unlock(fi.folio);
+			folio_mark_uptodate(fs.fs_folio);
+		folio_unlock(fs.fs_folio);
 	}
 
 	bio_put(bio);
@@ -61,15 +62,16 @@ static void mpage_read_end_io(struct bio *bio)
 
 static void mpage_write_end_io(struct bio *bio)
 {
-	struct folio_iter fi;
+	struct bvec_iter_all iter;
+	struct folio_seg fs;
 	int err = blk_status_to_errno(bio->bi_status);
 
-	bio_for_each_folio_all(fi, bio) {
+	bio_for_each_folio_all(fs, bio, iter) {
 		if (err) {
-			folio_set_error(fi.folio);
-			mapping_set_error(fi.folio->mapping, err);
+			folio_set_error(fs.fs_folio);
+			mapping_set_error(fs.fs_folio->mapping, err);
 		}
-		folio_end_writeback(fi.folio);
+		folio_end_writeback(fs.fs_folio);
 	}
 
 	bio_put(bio);
fs/verity/verify.c +5 -4
index e250822275..29ebca1006 100644
@@ -340,7 +340,8 @@ void fsverity_verify_bio(struct bio *bio)
 	struct inode *inode = bio_first_page_all(bio)->mapping->host;
 	struct fsverity_info *vi = inode->i_verity_info;
 	struct ahash_request *req;
-	struct folio_iter fi;
+	struct bvec_iter_all iter;
+	struct folio_seg fs;
 	unsigned long max_ra_pages = 0;
 
 	/* This allocation never fails, since it's mempool-backed. */
@@ -359,9 +360,9 @@ void fsverity_verify_bio(struct bio *bio)
 		max_ra_pages = bio->bi_iter.bi_size >> (PAGE_SHIFT + 2);
 	}
 
-	bio_for_each_folio_all(fi, bio) {
-		if (!verify_data_blocks(inode, vi, req, fi.folio, fi.length,
-					fi.offset, max_ra_pages)) {
+	bio_for_each_folio_all(fs, bio, iter) {
+		if (!verify_data_blocks(inode, vi, req, fs.fs_folio, fs.fs_len,
+					fs.fs_offset, max_ra_pages)) {
 			bio->bi_status = BLK_STS_IOERR;
 			break;
 		}
include/linux/bio.h +49 -46

114 lines not on this page · raw message

include/linux/bvec.h +10 -3
index 635fb54143..ebf8b612ba 100644
@@ -205,8 +205,8 @@ static inline void bvec_iter_all_init(struct bvec_iter_all *iter_all)
 	iter_all->idx = 0;
 }
 
-static inline struct bio_vec bvec_iter_all_peek(const struct bio_vec *bvec,
-						struct bvec_iter_all *iter)
+static inline struct bio_vec __bvec_iter_all_peek(const struct bio_vec *bvec,
+						  const struct bvec_iter_all *iter)
 {
 	struct bio_vec bv = bvec[iter->idx];
 
@@ -215,8 +215,15 @@ static inline struct bio_vec bvec_iter_all_peek(const struct bio_vec *bvec,
 
 	bv.bv_page	+= bv.bv_offset >> PAGE_SHIFT;
 	bv.bv_offset	&= ~PAGE_MASK;
-	bv.bv_len	= min_t(unsigned, PAGE_SIZE - bv.bv_offset, bv.bv_len);
+	return bv;
+}
+
+static inline struct bio_vec bvec_iter_all_peek(const struct bio_vec *bvec,
+						const struct bvec_iter_all *iter)
+{
+	struct bio_vec bv = __bvec_iter_all_peek(bvec, iter);
 
+	bv.bv_len = min_t(unsigned, PAGE_SIZE - bv.bv_offset, bv.bv_len);
 	return bv;
 }
 
Signature · 1 line
2.40.1
author maintainer
#2 lore raw

PATCH v2 3/5 block: Add documentation for bio iterator macros

In reply to Kent Overstreet

We've now got 3x2 interfaces for iterating over bios: by page, by bvec, or by folio, and variants that iterate over what bi_iter points to, or the entire bio as created by the filesystem/originator.

This adds more detailed kerneldoc comments for each variant.

---
 include/linux/bio.h | 54 ++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 48 insertions(+), 6 deletions(-)
include/linux/bio.h +48 -6
index 4b197ea83c..f599bcf15e 100644
@@ -97,9 +97,14 @@ static inline void bio_iter_all_advance(const struct bio *bio,
 		((bvl = bio_iter_all_peek(bio, &iter)), true);		\
 	     bio_iter_all_advance((bio), &iter, bvl.bv_len))
 
-/*
- * drivers should _never_ use the all version - the bio may have been split
- * before it got to the driver and the driver won't own all of it
+/**
+ * bio_for_each_segment_all - iterate over single pages in a bio
+ *
+ * Like other _all versions, this is for the filesystem, or the owner/creator of
+ * a bio; it iterates over the original contents of a bio.
+ *
+ * Drivers that are working with bios that were submitted to them should not use
+ * the _all version.
  */
 #define bio_for_each_segment_all(bvl, bio, iter)			\
 	for (bvec_iter_all_init(&iter);					\
@@ -160,6 +165,13 @@ static inline void bio_advance(struct bio *bio, unsigned int nbytes)
 		((bvl = bio_iter_iovec((bio), (iter))), 1);		\
 	     bio_advance_iter_single((bio), &(iter), (bvl).bv_len))
 
+/**
+ * bio_for_each_segment - iterate over single pages in a bio
+ *
+ * Like other non-_all versions, this iterates over what bio->bi_iter currently
+ * points to. This version is for drivers, where the bio may have previously
+ * been split or cloned.
+ */
 #define bio_for_each_segment(bvl, bio, iter)				\
 	__bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter)
 
@@ -200,6 +212,13 @@ static inline struct folio_seg bio_iter_iovec_folio(struct bio *bio,
 		((fs = bio_iter_iovec_folio((bio), (iter))), 1);	\
 	     bio_advance_iter_single((bio), &(iter), (fs).fs_len))
 
+/**
+ * bio_for_each_folio - iterate over folios within a bio
+ *
+ * Like other non-_all versions, this iterates over what bio->bi_iter currently
+ * points to. This version is for drivers, where the bio may have previously
+ * been split or cloned.
+ */
 #define bio_for_each_folio(fs, bio, iter)				\
 	__bio_for_each_folio(fs, bio, iter, (bio)->bi_iter)
 
@@ -209,13 +228,30 @@ static inline struct folio_seg bio_iter_iovec_folio(struct bio *bio,
 		((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \
 	     bio_advance_iter_single((bio), &(iter), (bvl).bv_len))
 
-/* iterate over multi-page bvec */
+/**
+ * bio_for_each_bvec - iterate over bvecs within a bio
+ *
+ * This version iterates over entire bio_vecs, which will be a range of
+ * contiguous pages.
+ *
+ * Like other non-_all versions, this iterates over what bio->bi_iter currently
+ * points to. This version is for drivers, where the bio may have previously
+ * been split or cloned.
+ */
 #define bio_for_each_bvec(bvl, bio, iter)			\
 	__bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter)
 
 /*
- * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the
- * same reasons as bio_for_each_segment_all().
+ * bio_for_each_bvec_all - iterate over bvecs within a bio
+ *
+ * This version iterates over entire bio_vecs, which will be a range of
+ * contiguous pages.
+ *
+ * Like other _all versions, this is for the filesystem, or the owner/creator of
+ * a bio; it iterates over the original contents of a bio.
+ *
+ * Drivers that are working with bios that were submitted to them should not use
+ * the _all version.
  */
 #define bio_for_each_bvec_all(bvl, bio, i)		\
 	for (i = 0, bvl = bio_first_bvec_all(bio);	\
@@ -321,6 +357,12 @@ static inline struct folio_seg bio_folio_iter_all_peek(const struct bio *bio,
  * bio_for_each_folio_all - Iterate over each folio in a bio.
  * @fi: struct bio_folio_iter_all which is updated for each folio.
  * @bio: struct bio to iterate over.
+ *
+ * Like other _all versions, this is for the filesystem, or the owner/creator of
+ * a bio; it iterates over the original contents of a bio.
+ *
+ * Drivers that are working with bios that were submitted to them should not use
+ * the _all version.
  */
 #define bio_for_each_folio_all(fs, bio, iter)				\
 	for (bvec_iter_all_init(&iter);					\
Signature · 1 line
2.40.1
author maintainer
#3 lore raw

PATCH v2 4/5 block: Change memcpy_(to|from)_bvec to pass bvec by value

In reply to Kent Overstreet

This is a small code size decrease; memcpy_from_bvec() is inlined so there's no benefit to passing the bvec by referene, but taking a pointer to it may inhibit optimization in the caller.

---
 block/blk-map.c               | 2 +-
 block/bounce.c                | 4 ++--
 drivers/block/floppy.c        | 4 ++--
 drivers/block/ps3disk.c       | 2 +-
 drivers/block/zram/zram_drv.c | 4 ++--
 drivers/md/dm-log-writes.c    | 2 +-
 drivers/scsi/aha1542.c        | 2 +-
 include/linux/bvec.h          | 8 ++++----
 8 files changed, 14 insertions(+), 14 deletions(-)
block/blk-map.c +1 -1
index 524d84011f..50540d0a22 100644
@@ -447,7 +447,7 @@ static void bio_copy_kern_endio_read(struct bio *bio)
 	struct bio_vec bvec;
 
 	bio_for_each_segment_all(bvec, bio, iter) {
-		memcpy_from_bvec(p, &bvec);
+		memcpy_from_bvec(p, bvec);
 		p += bvec.bv_len;
 	}
 
block/bounce.c +2 -2
index e701832d76..1dc6716084 100644
@@ -92,7 +92,7 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 			 * been modified by the block layer, so use the original
 			 * copy, bounce_copy_vec already uses tovec->bv_len
 			 */
-			memcpy_to_bvec(&tovec, page_address(fromvec.bv_page) +
+			memcpy_to_bvec(tovec, page_address(fromvec.bv_page) +
 				       tovec.bv_offset);
 		}
 		bio_advance_iter(from, &from_iter, tovec.bv_len);
@@ -249,7 +249,7 @@ struct bio *__blk_queue_bounce(struct bio *bio_orig, struct request_queue *q)
 
 		if (rw == WRITE) {
 			flush_dcache_page(to->bv_page);
-			memcpy_from_bvec(page_address(bounce_page), to);
+			memcpy_from_bvec(page_address(bounce_page), *to);
 		}
 		to->bv_page = bounce_page;
 	}
drivers/block/floppy.c +2 -2
index cec2c20f5e..039e4ebfad 100644
@@ -2483,9 +2483,9 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 		}
 
 		if (CT(raw_cmd->cmd[COMMAND]) == FD_READ)
-			memcpy_to_bvec(&bv, dma_buffer);
+			memcpy_to_bvec(bv, dma_buffer);
 		else
-			memcpy_from_bvec(dma_buffer, &bv);
+			memcpy_from_bvec(dma_buffer, bv);
 
 		remaining -= size;
 		dma_buffer += size;
drivers/block/ps3disk.c +1 -1
index 36d7b36c60..73db9ca530 100644
@@ -86,7 +86,7 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev,
 
 	rq_for_each_segment(bvec, req, iter) {
 		if (gather)
-			memcpy_from_bvec(dev->bounce_buf + offset, &bvec);
+			memcpy_from_bvec(dev->bounce_buf + offset, bvec);
 		else
 			memcpy_to_bvec(&bvec, dev->bounce_buf + offset);
 	}
drivers/block/zram/zram_drv.c +2 -2
index f6d90f1ba5..b68ae64a99 100644
@@ -1396,7 +1396,7 @@ static int zram_bvec_read_partial(struct zram *zram, struct bio_vec *bvec,
 		return -ENOMEM;
 	ret = zram_read_page(zram, page, index, NULL);
 	if (likely(!ret))
-		memcpy_to_bvec(bvec, page_address(page) + offset);
+		memcpy_to_bvec(*bvec, page_address(page) + offset);
 	__free_page(page);
 	return ret;
 }
@@ -1548,7 +1548,7 @@ static int zram_bvec_write_partial(struct zram *zram, struct bio_vec *bvec,
 
 	ret = zram_read_page(zram, page, index, bio);
 	if (!ret) {
-		memcpy_from_bvec(page_address(page) + offset, bvec);
+		memcpy_from_bvec(page_address(page) + offset, *bvec);
 		ret = zram_write_page(zram, page, index);
 	}
 	__free_page(page);
drivers/md/dm-log-writes.c +1 -1
index f17a6cf228..7772466d0a 100644
@@ -744,7 +744,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 		}
 
 		dst = kmap_local_page(page);
-		memcpy_from_bvec(dst, &bv);
+		memcpy_from_bvec(dst, bv);
 		kunmap_local(dst);
 		block->vecs[i].bv_page = page;
 		block->vecs[i].bv_len = bv.bv_len;
drivers/scsi/aha1542.c +1 -1
index 9503996c63..5db9e31352 100644
@@ -450,7 +450,7 @@ static int aha1542_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *cmd)
 		struct bio_vec bv;
 
 		rq_for_each_segment(bv, rq, iter) {
-			memcpy_from_bvec(buf, &bv);
+			memcpy_from_bvec(buf, bv);
 			buf += bv.bv_len;
 		}
 	}
include/linux/bvec.h +4 -4
index ebf8b612ba..ee5965fedf 100644
@@ -257,9 +257,9 @@ static inline void *bvec_kmap_local(struct bio_vec *bvec)
  *
  * Must be called on single-page bvecs only.
  */
-static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec)
+static inline void memcpy_from_bvec(char *to, struct bio_vec bvec)
 {
-	memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, bvec->bv_len);
+	memcpy_from_page(to, bvec.bv_page, bvec.bv_offset, bvec.bv_len);
 }
 
 /**
@@ -268,9 +268,9 @@ static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec)
  *
  * Must be called on single-page bvecs only.
  */
-static inline void memcpy_to_bvec(struct bio_vec *bvec, const char *from)
+static inline void memcpy_to_bvec(struct bio_vec bvec, const char *from)
 {
-	memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, bvec->bv_len);
+	memcpy_to_page(bvec.bv_page, bvec.bv_offset, from, bvec.bv_len);
 }
 
 /**
Signature · 1 line
2.40.1
#4 lore raw

Re: [PATCH v2 4/5] block: Change memcpy_(to|from)_bvec to pass bvec by value

kernel test robot noticed the following build errors:

Hi Kent,

kernel test robot noticed the following build errors:

[auto build test ERROR on axboe-block/for-next]
[cannot apply to kdave/for-next device-mapper-dm/for-next gfs2/for-next tytso-ext4/dev linus/master v6.4-rc5 next-20230606] [If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Kent-Overstreet/block-Rework-bio_for_each_folio_all/20230606-052850
base:   https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git for-next
patch link:    https://lore.kernel.org/r/20230605212717.2570570-4-kent.overstreet%40linux.dev
patch subject: [PATCH v2 4/5] block: Change memcpy_(to|from)_bvec to pass bvec by value
config: alpha-allyesconfig (https://download.01.org/0day-ci/archive/20230606/[email protected]/config)
compiler: alpha-linux-gcc (GCC) 12.3.0

reproduce (this is a W=1 build):
mkdir -p ~/bin
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
git remote add axboe-block https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
git fetch axboe-block for-next
git checkout axboe-block/for-next
b4 shazam https://lore.kernel.org/r/[email protected]
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.3.0 ~/bin/make.cross W=1 O=build_dir ARCH=alpha olddefconfig COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.3.0 ~/bin/make.cross W=1 O=build_dir ARCH=alpha SHELL=/bin/bash drivers/scsi/

If you fix the issue, kindly add following tag where applicable
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/

All errors (new ones prefixed by >>):

drivers/scsi/aha1542.c: In function 'aha1542_free_cmd':

>> drivers/scsi/aha1542.c:270:40: error: incompatible type for argument 1 of 'memcpy_to_bvec'
     270 |                         memcpy_to_bvec(&bv, buf);
         |                                        ^~~
         |                                        |
         |                                        struct bio_vec *
   In file included from include/linux/blk_types.h:10,
                    from include/linux/blkdev.h:9,
                    from include/scsi/scsi_cmnd.h:6,
                    from drivers/scsi/aha1542.c:23:

include/linux/bvec.h:271:50: note: expected 'struct bio_vec' but argument is of type 'struct bio_vec *'
271 | static inline void memcpy_to_bvec(struct bio_vec bvec, const char *from)
| ~~~~~~~~~~~~~~~^~~~

vim +/memcpy_to_bvec +270 drivers/scsi/aha1542.c

^1da177e4c3f41 Linus Torvalds    2005-04-16  258  
1794ef2b150dd5 Christoph Hellwig 2018-11-10  259  static void aha1542_free_cmd(struct scsi_cmnd *cmd)
1794ef2b150dd5 Christoph Hellwig 2018-11-10  260  {
1794ef2b150dd5 Christoph Hellwig 2018-11-10  261  	struct aha1542_cmd *acmd = scsi_cmd_priv(cmd);
1794ef2b150dd5 Christoph Hellwig 2018-11-10  262  
2f2fef022c3e7a Christoph Hellwig 2021-03-31  263  	if (cmd->sc_data_direction == DMA_FROM_DEVICE) {
11bf4ec580737c Bart Van Assche   2021-08-09  264  		struct request *rq = scsi_cmd_to_rq(cmd);
2f2fef022c3e7a Christoph Hellwig 2021-03-31  265  		void *buf = acmd->data_buffer;
2f2fef022c3e7a Christoph Hellwig 2021-03-31  266  		struct req_iterator iter;
2f2fef022c3e7a Christoph Hellwig 2021-03-31  267  		struct bio_vec bv;
2f2fef022c3e7a Christoph Hellwig 2021-03-31  268  
11bf4ec580737c Bart Van Assche   2021-08-09  269  		rq_for_each_segment(bv, rq, iter) {
e6ab6113526aa4 Christoph Hellwig 2021-10-18 @270  			memcpy_to_bvec(&bv, buf);
2f2fef022c3e7a Christoph Hellwig 2021-03-31  271  			buf += bv.bv_len;
2f2fef022c3e7a Christoph Hellwig 2021-03-31  272  		}
1794ef2b150dd5 Christoph Hellwig 2018-11-10  273  	}
1794ef2b150dd5 Christoph Hellwig 2018-11-10  274  
1794ef2b150dd5 Christoph Hellwig 2018-11-10  275  	scsi_dma_unmap(cmd);
1794ef2b150dd5 Christoph Hellwig 2018-11-10  276  }
1794ef2b150dd5 Christoph Hellwig 2018-11-10  277  
Signature · 2 lines
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
author maintainer
#5 lore raw

PATCH v2 5/5 block: CONFIG_BLK_DEBUG

In reply to Kent Overstreet

This adds a new kconfig option to enable some extra debug mode assertions. Currently this is just used for some bio iterator assertions, but hopefully more will be added in the future.

---
 block/Kconfig        | 7 +++++++
 include/linux/bio.h  | 5 +++++
 include/linux/bvec.h | 8 ++++++++
 3 files changed, 20 insertions(+)
block/Kconfig +7 -0
index 86122e459f..611dddb59c 100644
@@ -165,6 +165,13 @@ config BLK_CGROUP_IOPRIO
 	scheduler and block devices process requests. Only some I/O schedulers
 	and some block devices support I/O priorities.
 
+config BLK_DEBUG
+	bool "Extra block layer assertions"
+	depends on DEBUG_KERNEL
+	help
+	Enable extra assertions in the block layer. Currently this is just the
+	bio iterator code, but may be expanded.
+
 config BLK_DEBUG_FS
 	bool "Block layer debugging information in debugfs"
 	default y
include/linux/bio.h +5 -0
index f599bcf15e..cece57c54d 100644
@@ -81,6 +81,8 @@ static inline void *bio_data(struct bio *bio)
 static inline struct bio_vec bio_iter_all_peek(const struct bio *bio,
 					       struct bvec_iter_all *iter)
 {
+	BLK_BUG_ON(iter->idx >= bio->bi_vcnt);
+
 	return bvec_iter_all_peek(bio->bi_io_vec, iter);
 }
 
@@ -89,6 +91,9 @@ static inline void bio_iter_all_advance(const struct bio *bio,
 					unsigned bytes)
 {
 	bvec_iter_all_advance(bio->bi_io_vec, iter, bytes);
+
+	BLK_BUG_ON(iter->idx > bio->bi_vcnt ||
+		   (iter->idx == bio->bi_vcnt && iter->done));
 }
 
 #define bio_for_each_segment_all_continue(bvl, bio, iter)		\
include/linux/bvec.h +8 -0
index ee5965fedf..2467245da2 100644
@@ -16,6 +16,12 @@
 
 struct page;
 
+#ifdef CONFIG_BLK_DEBUG
+#define BLK_BUG_ON(cond) BUG_ON(cond)
+#else
+#define BLK_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
+#endif
+
 /**
  * struct bio_vec - a contiguous range of physical memory addresses
  * @bv_page:   First page associated with the address range.
@@ -210,6 +216,8 @@ static inline struct bio_vec __bvec_iter_all_peek(const struct bio_vec *bvec,
 {
 	struct bio_vec bv = bvec[iter->idx];
 
+	BLK_BUG_ON(iter->done >= bv.bv_len);
+
 	bv.bv_offset	+= iter->done;
 	bv.bv_len	-= iter->done;
 
Signature · 1 line
2.40.1
#6 lore raw

Re: [PATCH v2 5/5] block: CONFIG_BLK_DEBUG

Hi,

Quoted 5 lines · Kent Overstreet
block/Kconfig +0 -0
index 86122e459f..611dddb59c 100644

block/Kconfig config BLK_CGROUP_IOPRIO · line 173

Quoted 9 lines
block/Kconfig +6 -0
@@ -165,6 +165,13 @@ config BLK_CGROUP_IOPRIO
 	scheduler and block devices process requests. Only some I/O schedulers
 	and some block devices support I/O priorities.
 
+config BLK_DEBUG
+	bool "Extra block layer assertions"
+	depends on DEBUG_KERNEL
+	help
+	Enable extra assertions in the block layer. Currently this is just the
+	bio iterator code, but may be expanded.

I see that block/Kconfig isn't consistent about indenting help text, but Documentation/process/coding-style.rst says:

10) Kconfig configuration files
-------------------------------

For all of the Kconfig* configuration files throughout the source tree, the indentation is somewhat different. Lines under a ``config`` definition are indented with one tab, while help text is indented an additional two spaces.

so please add 2 spaces after the tab at the beginning of the help text lines (but not the "help" line itself).

Signature · 1 line
~Randy
#7 lore raw
In reply to Kent Overstreet
Quoted 8 lines · Kent Overstreet

This patch reworks bio_for_each_segment_all() to be more inline with how the other bio iterators work:

- bio_iter_all_peek() now returns a synthesized bio_vec; we don't stash one in the iterator and pass a pointer to it - bad. This way makes it clearer what's a constructed value vs. a reference to something pre-existing, and it also will help with cleaning up and consolidating code with bio_for_each_folio_all().

by-value is more readable & clean, the current by-reference is just for aligning with original interface.

Quoted 3 lines

- We now provide bio_for_each_segment_all_continue(), for squashfs:
this makes their code clearer.

Probably it is better to move the new helper into new patch, but I guess it could be hard for this patch.

Quoted 901 lines
---
 block/bio.c                | 38 ++++++++++++------------
 block/blk-map.c            | 38 ++++++++++++------------
 block/bounce.c             | 12 ++++----
 drivers/md/bcache/btree.c  |  8 ++---
 drivers/md/dm-crypt.c      | 10 +++----
 drivers/md/raid1.c         |  4 +--
 fs/btrfs/disk-io.c         |  4 +--
 fs/btrfs/extent_io.c       | 50 +++++++++++++++----------------
 fs/btrfs/raid56.c          | 14 ++++-----
 fs/erofs/zdata.c           |  4 +--
 fs/f2fs/data.c             | 20 ++++++-------
 fs/gfs2/lops.c             | 10 +++----
 fs/gfs2/meta_io.c          |  8 ++---
 fs/squashfs/block.c        | 48 +++++++++++++++++-------------
 fs/squashfs/lz4_wrapper.c  | 17 ++++++-----
 fs/squashfs/lzo_wrapper.c  | 17 ++++++-----
 fs/squashfs/xz_wrapper.c   | 19 ++++++------
 fs/squashfs/zlib_wrapper.c | 18 ++++++-----
 fs/squashfs/zstd_wrapper.c | 19 ++++++------
 include/linux/bio.h        | 28 ++++++++++++-----
 include/linux/bvec.h       | 61 ++++++++++++++++++++++----------------
 21 files changed, 242 insertions(+), 205 deletions(-)
block/bio.c +19 -19
index 798cc4cf3b..2af9f50643 100644
@@ -1163,13 +1163,13 @@ EXPORT_SYMBOL(bio_add_folio);
 
 void __bio_release_pages(struct bio *bio, bool mark_dirty)
 {
-	struct bvec_iter_all iter_all;
-	struct bio_vec *bvec;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (mark_dirty && !PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
-		bio_release_page(bio, bvec->bv_page);
+	bio_for_each_segment_all(bvec, bio, iter) {
+		if (mark_dirty && !PageCompound(bvec.bv_page))
+			set_page_dirty_lock(bvec.bv_page);
+		bio_release_page(bio, bvec.bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1435,11 +1435,11 @@ EXPORT_SYMBOL(bio_copy_data);
 
 void bio_free_pages(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all)
-		__free_page(bvec->bv_page);
+	bio_for_each_segment_all(bvec, bio, iter)
+		__free_page(bvec.bv_page);
 }
 EXPORT_SYMBOL(bio_free_pages);
 
@@ -1474,12 +1474,12 @@ EXPORT_SYMBOL(bio_free_pages);
  */
 void bio_set_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
+	bio_for_each_segment_all(bvec, bio, iter) {
+		if (!PageCompound(bvec.bv_page))
+			set_page_dirty_lock(bvec.bv_page);
 	}
 }
 
@@ -1522,12 +1522,12 @@ static void bio_dirty_fn(struct work_struct *work)
 
 void bio_check_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 	unsigned long flags;
-	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+	bio_for_each_segment_all(bvec, bio, iter) {
+		if (!PageDirty(bvec.bv_page) && !PageCompound(bvec.bv_page))
 			goto defer;
 	}
 
block/blk-map.c +19 -19
index 3551c3ff17..524d84011f 100644
@@ -47,21 +47,21 @@ static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
  */
 static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all bv_iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_segment_all(bvec, bio, bv_iter) {
 		ssize_t ret;
 
-		ret = copy_page_from_iter(bvec->bv_page,
-					  bvec->bv_offset,
-					  bvec->bv_len,
+		ret = copy_page_from_iter(bvec.bv_page,
+					  bvec.bv_offset,
+					  bvec.bv_len,
 					  iter);
 
 		if (!iov_iter_count(iter))
 			break;
 
-		if (ret < bvec->bv_len)
+		if (ret < bvec.bv_len)
 			return -EFAULT;
 	}
 
@@ -78,21 +78,21 @@ static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
  */
 static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all bv_iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_segment_all(bvec, bio, bv_iter) {
 		ssize_t ret;
 
-		ret = copy_page_to_iter(bvec->bv_page,
-					bvec->bv_offset,
-					bvec->bv_len,
+		ret = copy_page_to_iter(bvec.bv_page,
+					bvec.bv_offset,
+					bvec.bv_len,
 					&iter);
 
 		if (!iov_iter_count(&iter))
 			break;
 
-		if (ret < bvec->bv_len)
+		if (ret < bvec.bv_len)
 			return -EFAULT;
 	}
 
@@ -443,12 +443,12 @@ static void bio_copy_kern_endio(struct bio *bio)
 static void bio_copy_kern_endio_read(struct bio *bio)
 {
 	char *p = bio->bi_private;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		memcpy_from_bvec(p, bvec);
-		p += bvec->bv_len;
+	bio_for_each_segment_all(bvec, bio, iter) {
+		memcpy_from_bvec(p, &bvec);
+		p += bvec.bv_len;
 	}
 
 	bio_copy_kern_endio(bio);
block/bounce.c +6 -6
index 7cfcb242f9..e701832d76 100644
@@ -102,18 +102,18 @@ static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
 static void bounce_end_io(struct bio *bio)
 {
 	struct bio *bio_orig = bio->bi_private;
-	struct bio_vec *bvec, orig_vec;
+	struct bio_vec bvec, orig_vec;
 	struct bvec_iter orig_iter = bio_orig->bi_iter;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
 
 	/*
 	 * free up bounce indirect pages used
 	 */
-	bio_for_each_segment_all(bvec, bio, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter) {
 		orig_vec = bio_iter_iovec(bio_orig, orig_iter);
-		if (bvec->bv_page != orig_vec.bv_page) {
-			dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
-			mempool_free(bvec->bv_page, &page_pool);
+		if (bvec.bv_page != orig_vec.bv_page) {
+			dec_zone_page_state(bvec.bv_page, NR_BOUNCE);
+			mempool_free(bvec.bv_page, &page_pool);
 		}
 		bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len);
 	}
drivers/md/bcache/btree.c +4 -4
index 147c493a98..98ce12b239 100644
@@ -373,12 +373,12 @@ static void do_btree_node_write(struct btree *b)
 		       bset_sector_offset(&b->keys, i));
 
 	if (!bch_bio_alloc_pages(b->bio, __GFP_NOWARN|GFP_NOWAIT)) {
-		struct bio_vec *bv;
+		struct bio_vec bv;
 		void *addr = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
-		struct bvec_iter_all iter_all;
+		struct bvec_iter_all iter;
 
-		bio_for_each_segment_all(bv, b->bio, iter_all) {
-			memcpy(page_address(bv->bv_page), addr, PAGE_SIZE);
+		bio_for_each_segment_all(bv, b->bio, iter) {
+			memcpy(page_address(bv.bv_page), addr, PAGE_SIZE);
 			addr += PAGE_SIZE;
 		}
 
drivers/md/dm-crypt.c +5 -5
index 8b47b913ee..8ffc225f7b 100644
@@ -1713,12 +1713,12 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 
 static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
 {
-	struct bio_vec *bv;
-	struct bvec_iter_all iter_all;
+	struct bvec_iter_all iter;
+	struct bio_vec bv;
 
-	bio_for_each_segment_all(bv, clone, iter_all) {
-		BUG_ON(!bv->bv_page);
-		mempool_free(bv->bv_page, &cc->page_pool);
+	bio_for_each_segment_all(bv, clone, iter) {
+		BUG_ON(!bv.bv_page);
+		mempool_free(bv.bv_page, &cc->page_pool);
 	}
 }
 
drivers/md/raid1.c +2 -2
index 68a9e2d998..4f58cae37e 100644
@@ -2188,7 +2188,7 @@ static void process_checks(struct r1bio *r1_bio)
 		blk_status_t status = sbio->bi_status;
 		struct page **ppages = get_resync_pages(pbio)->pages;
 		struct page **spages = get_resync_pages(sbio)->pages;
-		struct bio_vec *bi;
+		struct bio_vec bi;
 		int page_len[RESYNC_PAGES] = { 0 };
 		struct bvec_iter_all iter_all;
 
@@ -2198,7 +2198,7 @@ static void process_checks(struct r1bio *r1_bio)
 		sbio->bi_status = 0;
 
 		bio_for_each_segment_all(bi, sbio, iter_all)
-			page_len[j++] = bi->bv_len;
+			page_len[j++] = bi.bv_len;
 
 		if (!status) {
 			for (j = vcnt; j-- ; ) {
fs/btrfs/disk-io.c +2 -2
index fbf9006c62..10326f978a 100644
@@ -3807,12 +3807,12 @@ ALLOW_ERROR_INJECTION(open_ctree, ERRNO);
 static void btrfs_end_super_write(struct bio *bio)
 {
 	struct btrfs_device *device = bio->bi_private;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 	struct page *page;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
+		page = bvec.bv_page;
 
 		if (bio->bi_status) {
 			btrfs_warn_rl_in_rcu(device->fs_info,
fs/btrfs/extent_io.c +25 -25
index a1adadd5d2..e3b7fbbad7 100644
@@ -573,34 +573,34 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio)
 {
 	struct bio *bio = &bbio->bio;
 	int error = blk_status_to_errno(bio->bi_status);
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	u64 start;
 	u64 end;
 	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 		struct inode *inode = page->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 		const u32 sectorsize = fs_info->sectorsize;
 
 		/* Our read/write should always be sector aligned. */
-		if (!IS_ALIGNED(bvec->bv_offset, sectorsize))
+		if (!IS_ALIGNED(bvec.bv_offset, sectorsize))
 			btrfs_err(fs_info,
 		"partial page write in btrfs with offset %u and length %u",
-				  bvec->bv_offset, bvec->bv_len);
-		else if (!IS_ALIGNED(bvec->bv_len, sectorsize))
+				  bvec.bv_offset, bvec.bv_len);
+		else if (!IS_ALIGNED(bvec.bv_len, sectorsize))
 			btrfs_info(fs_info,
 		"incomplete page write with offset %u and length %u",
-				   bvec->bv_offset, bvec->bv_len);
+				   bvec.bv_offset, bvec.bv_len);
 
-		start = page_offset(page) + bvec->bv_offset;
-		end = start + bvec->bv_len - 1;
+		start = page_offset(page) + bvec.bv_offset;
+		end = start + bvec.bv_len - 1;
 
 		end_extent_writepage(page, error, start, end);
 
-		btrfs_page_clear_writeback(fs_info, page, start, bvec->bv_len);
+		btrfs_page_clear_writeback(fs_info, page, start, bvec.bv_len);
 	}
 
 	bio_put(bio);
@@ -728,7 +728,7 @@ static struct extent_buffer *find_extent_buffer_readpage(
 static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 {
 	struct bio *bio = &bbio->bio;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct processed_extent processed = { 0 };
 	/*
 	 * The offset to the beginning of a bio, since one bio can never be
@@ -741,7 +741,7 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, iter_all) {
 		bool uptodate = !bio->bi_status;
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 		struct inode *inode = page->mapping->host;
 		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 		const u32 sectorsize = fs_info->sectorsize;
@@ -761,19 +761,19 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
 		 * for unaligned offsets, and an error if they don't add up to
 		 * a full sector.
 		 */
-		if (!IS_ALIGNED(bvec->bv_offset, sectorsize))
+		if (!IS_ALIGNED(bvec.bv_offset, sectorsize))
 			btrfs_err(fs_info,
 		"partial page read in btrfs with offset %u and length %u",
-				  bvec->bv_offset, bvec->bv_len);
-		else if (!IS_ALIGNED(bvec->bv_offset + bvec->bv_len,
+				  bvec.bv_offset, bvec.bv_len);
+		else if (!IS_ALIGNED(bvec.bv_offset + bvec.bv_len,
 				     sectorsize))
 			btrfs_info(fs_info,
 		"incomplete page read with offset %u and length %u",
-				   bvec->bv_offset, bvec->bv_len);
+				   bvec.bv_offset, bvec.bv_len);
 
-		start = page_offset(page) + bvec->bv_offset;
-		end = start + bvec->bv_len - 1;
-		len = bvec->bv_len;
+		start = page_offset(page) + bvec.bv_offset;
+		end = start + bvec.bv_len - 1;
+		len = bvec.bv_len;
 
 		mirror = bbio->mirror_num;
 		if (uptodate && !is_data_inode(inode) &&
@@ -1879,7 +1879,7 @@ static void end_bio_subpage_eb_writepage(struct btrfs_bio *bbio)
 {
 	struct bio *bio = &bbio->bio;
 	struct btrfs_fs_info *fs_info;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	fs_info = btrfs_sb(bio_first_page_all(bio)->mapping->host->i_sb);
@@ -1887,12 +1887,12 @@ static void end_bio_subpage_eb_writepage(struct btrfs_bio *bbio)
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
-		u64 bvec_start = page_offset(page) + bvec->bv_offset;
-		u64 bvec_end = bvec_start + bvec->bv_len - 1;
+		struct page *page = bvec.bv_page;
+		u64 bvec_start = page_offset(page) + bvec.bv_offset;
+		u64 bvec_end = bvec_start + bvec.bv_len - 1;
 		u64 cur_bytenr = bvec_start;
 
-		ASSERT(IS_ALIGNED(bvec->bv_len, fs_info->nodesize));
+		ASSERT(IS_ALIGNED(bvec.bv_len, fs_info->nodesize));
 
 		/* Iterate through all extent buffers in the range */
 		while (cur_bytenr <= bvec_end) {
@@ -1936,14 +1936,14 @@ static void end_bio_subpage_eb_writepage(struct btrfs_bio *bbio)
 static void end_bio_extent_buffer_writepage(struct btrfs_bio *bbio)
 {
 	struct bio *bio = &bbio->bio;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct extent_buffer *eb;
 	int done;
 	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 
 		eb = (struct extent_buffer *)page->private;
 		BUG_ON(!eb);
fs/btrfs/raid56.c +7 -7
index 2fab37f062..8da6097c42 100644
@@ -1393,7 +1393,7 @@ static struct sector_ptr *find_stripe_sector(struct btrfs_raid_bio *rbio,
 static void set_bio_pages_uptodate(struct btrfs_raid_bio *rbio, struct bio *bio)
 {
 	const u32 sectorsize = rbio->bioc->fs_info->sectorsize;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	ASSERT(!bio_flagged(bio, BIO_CLONED));
@@ -1402,9 +1402,9 @@ static void set_bio_pages_uptodate(struct btrfs_raid_bio *rbio, struct bio *bio)
 		struct sector_ptr *sector;
 		int pgoff;
 
-		for (pgoff = bvec->bv_offset; pgoff - bvec->bv_offset < bvec->bv_len;
+		for (pgoff = bvec.bv_offset; pgoff - bvec.bv_offset < bvec.bv_len;
 		     pgoff += sectorsize) {
-			sector = find_stripe_sector(rbio, bvec->bv_page, pgoff);
+			sector = find_stripe_sector(rbio, bvec.bv_page, pgoff);
 			ASSERT(sector);
 			if (sector)
 				sector->uptodate = 1;
@@ -1458,7 +1458,7 @@ static void verify_bio_data_sectors(struct btrfs_raid_bio *rbio,
 {
 	struct btrfs_fs_info *fs_info = rbio->bioc->fs_info;
 	int total_sector_nr = get_bio_sector_nr(rbio, bio);
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	/* No data csum for the whole stripe, no need to verify. */
@@ -1472,8 +1472,8 @@ static void verify_bio_data_sectors(struct btrfs_raid_bio *rbio,
 	bio_for_each_segment_all(bvec, bio, iter_all) {
 		int bv_offset;
 
-		for (bv_offset = bvec->bv_offset;
-		     bv_offset < bvec->bv_offset + bvec->bv_len;
+		for (bv_offset = bvec.bv_offset;
+		     bv_offset < bvec.bv_offset + bvec.bv_len;
 		     bv_offset += fs_info->sectorsize, total_sector_nr++) {
 			u8 csum_buf[BTRFS_CSUM_SIZE];
 			u8 *expected_csum = rbio->csum_buf +
@@ -1484,7 +1484,7 @@ static void verify_bio_data_sectors(struct btrfs_raid_bio *rbio,
 			if (!test_bit(total_sector_nr, rbio->csum_bitmap))
 				continue;
 
-			ret = btrfs_check_sector_csum(fs_info, bvec->bv_page,
+			ret = btrfs_check_sector_csum(fs_info, bvec.bv_page,
 				bv_offset, csum_buf, expected_csum);
 			if (ret < 0)
 				set_bit(total_sector_nr, rbio->error_bitmap);
fs/erofs/zdata.c +2 -2
index 45f21db230..fc0ce6d685 100644
@@ -1648,11 +1648,11 @@ static void z_erofs_decompressqueue_endio(struct bio *bio)
 {
 	struct z_erofs_decompressqueue *q = bio->bi_private;
 	blk_status_t err = bio->bi_status;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 
 		DBG_BUGON(PageUptodate(page));
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
fs/f2fs/data.c +10 -10
index 7165b1202f..d687e11bdf 100644
@@ -139,12 +139,12 @@ struct bio_post_read_ctx {
  */
 static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	struct bvec_iter_all iter_all;
 	struct bio_post_read_ctx *ctx = bio->bi_private;
 
 	bio_for_each_segment_all(bv, bio, iter_all) {
-		struct page *page = bv->bv_page;
+		struct page *page = bv.bv_page;
 
 		if (f2fs_is_compressed_page(page)) {
 			if (ctx && !ctx->decompression_attempted)
@@ -189,11 +189,11 @@ static void f2fs_verify_bio(struct work_struct *work)
 	 * as those were handled separately by f2fs_end_read_compressed_page().
 	 */
 	if (may_have_compressed_pages) {
-		struct bio_vec *bv;
+		struct bio_vec bv;
 		struct bvec_iter_all iter_all;
 
 		bio_for_each_segment_all(bv, bio, iter_all) {
-			struct page *page = bv->bv_page;
+			struct page *page = bv.bv_page;
 
 			if (!f2fs_is_compressed_page(page) &&
 			    !fsverity_verify_page(page)) {
@@ -241,13 +241,13 @@ static void f2fs_verify_and_finish_bio(struct bio *bio, bool in_task)
 static void f2fs_handle_step_decompress(struct bio_post_read_ctx *ctx,
 		bool in_task)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	struct bvec_iter_all iter_all;
 	bool all_compressed = true;
 	block_t blkaddr = ctx->fs_blkaddr;
 
 	bio_for_each_segment_all(bv, ctx->bio, iter_all) {
-		struct page *page = bv->bv_page;
+		struct page *page = bv.bv_page;
 
 		if (f2fs_is_compressed_page(page))
 			f2fs_end_read_compressed_page(page, false, blkaddr,
@@ -327,7 +327,7 @@ static void f2fs_read_end_io(struct bio *bio)
 static void f2fs_write_end_io(struct bio *bio)
 {
 	struct f2fs_sb_info *sbi;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	iostat_update_and_unbind_ctx(bio);
@@ -337,7 +337,7 @@ static void f2fs_write_end_io(struct bio *bio)
 		bio->bi_status = BLK_STS_IOERR;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 		enum count_type type = WB_DATA_TYPE(page);
 
 		if (page_private_dummy(page)) {
@@ -583,7 +583,7 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 static bool __has_merged_page(struct bio *bio, struct inode *inode,
 						struct page *page, nid_t ino)
 {
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	if (!bio)
@@ -593,7 +593,7 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode,
 		return true;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *target = bvec->bv_page;
+		struct page *target = bvec.bv_page;
 
 		if (fscrypt_is_bounce_page(target)) {
 			target = fscrypt_pagecache_page(target);
fs/gfs2/lops.c +5 -5
index 1902413d5d..7f62fe8eb7 100644
@@ -202,7 +202,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp,
 static void gfs2_end_log_write(struct bio *bio)
 {
 	struct gfs2_sbd *sdp = bio->bi_private;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct page *page;
 	struct bvec_iter_all iter_all;
 
@@ -217,9 +217,9 @@ static void gfs2_end_log_write(struct bio *bio)
 	}
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
+		page = bvec.bv_page;
 		if (page_has_buffers(page))
-			gfs2_end_log_write_bh(sdp, bvec, bio->bi_status);
+			gfs2_end_log_write_bh(sdp, &bvec, bio->bi_status);
 		else
 			mempool_free(page, gfs2_page_pool);
 	}
@@ -395,11 +395,11 @@ static void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
 static void gfs2_end_log_read(struct bio *bio)
 {
 	struct page *page;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		page = bvec->bv_page;
+		page = bvec.bv_page;
 		if (bio->bi_status) {
 			int err = blk_status_to_errno(bio->bi_status);
 
fs/gfs2/meta_io.c +4 -4
index 924361fa51..832572784e 100644
@@ -193,15 +193,15 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 
 static void gfs2_meta_read_endio(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	struct bvec_iter_all iter_all;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
+		struct page *page = bvec.bv_page;
 		struct buffer_head *bh = page_buffers(page);
-		unsigned int len = bvec->bv_len;
+		unsigned int len = bvec.bv_len;
 
-		while (bh_offset(bh) < bvec->bv_offset)
+		while (bh_offset(bh) < bvec.bv_offset)
 			bh = bh->b_this_page;
 		do {
 			struct buffer_head *next = bh->b_this_page;
fs/squashfs/block.c +27 -21
index bed3bb8b27..83e8b44518 100644
@@ -35,30 +35,33 @@ static int copy_bio_to_actor(struct bio *bio,
 			     int offset, int req_length)
 {
 	void *actor_addr;
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 	int copied_bytes = 0;
 	int actor_offset = 0;
+	int bytes_to_copy;
 
 	squashfs_actor_nobuff(actor);
 	actor_addr = squashfs_first_page(actor);
 
-	if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all)))
-		return 0;
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
 
-	while (copied_bytes < req_length) {
-		int bytes_to_copy = min_t(int, bvec->bv_len - offset,
+	while (copied_bytes < req_length &&
+	       iter.idx < bio->bi_vcnt) {
+		bvec = bio_iter_all_peek(bio, &iter);
+
+		bytes_to_copy = min_t(int, bvec.bv_len,
 					  PAGE_SIZE - actor_offset);
 
 		bytes_to_copy = min_t(int, bytes_to_copy,
 				      req_length - copied_bytes);
 		if (!IS_ERR(actor_addr))
-			memcpy(actor_addr + actor_offset, bvec_virt(bvec) +
-					offset, bytes_to_copy);
+			memcpy(actor_addr + actor_offset, bvec_virt(&bvec),
+			       bytes_to_copy);
 
 		actor_offset += bytes_to_copy;
 		copied_bytes += bytes_to_copy;
-		offset += bytes_to_copy;
 
 		if (actor_offset >= PAGE_SIZE) {
 			actor_addr = squashfs_next_page(actor);
@@ -66,11 +69,8 @@ static int copy_bio_to_actor(struct bio *bio,
 				break;
 			actor_offset = 0;
 		}
-		if (offset >= bvec->bv_len) {
-			if (!bio_next_segment(bio, &iter_all))
-				break;
-			offset = 0;
-		}
+
+		bio_iter_all_advance(bio, &iter, bytes_to_copy);
 	}
 	squashfs_finish_page(actor);
 	return copied_bytes;
@@ -159,8 +159,10 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 		 * Metadata block.
 		 */
 		const u8 *data;
-		struct bvec_iter_all iter_all = {};
-		struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+		struct bvec_iter_all iter;
+		struct bio_vec bvec;
+
+		bvec_iter_all_init(&iter);
 
 		if (index + 2 > msblk->bytes_used) {
 			res = -EIO;
@@ -170,21 +172,25 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length,
 		if (res)
 			goto out;
 
-		if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) {
+		bvec = bio_iter_all_peek(bio, &iter);
+
+		if (WARN_ON_ONCE(!bvec.bv_len)) {
 			res = -EIO;
 			goto out_free_bio;
 		}
 		/* Extract the length of the metadata block */
-		data = bvec_virt(bvec);
+		data = bvec_virt(&bvec);
 		length = data[offset];
-		if (offset < bvec->bv_len - 1) {
+		if (offset < bvec.bv_len - 1) {
 			length |= data[offset + 1] << 8;
 		} else {
-			if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) {
+			bio_iter_all_advance(bio, &iter, bvec.bv_len);
+
+			if (WARN_ON_ONCE(!bvec.bv_len)) {
 				res = -EIO;
 				goto out_free_bio;
 			}
-			data = bvec_virt(bvec);
+			data = bvec_virt(&bvec);
 			length |= data[0] << 8;
 		}
 		bio_free_pages(bio);
fs/squashfs/lz4_wrapper.c +10 -7
index 49797729f1..bd0dd787d2 100644
@@ -92,20 +92,23 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 	struct squashfs_lz4 *stream = strm;
 	void *buff = stream->input, *data;
 	int bytes = length, res;
 
-	while (bio_next_segment(bio, &iter_all)) {
-		int avail = min(bytes, ((int)bvec->bv_len) - offset);
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
 
-		data = bvec_virt(bvec);
-		memcpy(buff, data + offset, avail);
+	bio_for_each_segment_all_continue(bvec, bio, iter) {
+		unsigned avail = min_t(unsigned, bytes, bvec.bv_len);
+
+		memcpy(buff, bvec_virt(&bvec), avail);
 		buff += avail;
 		bytes -= avail;
-		offset = 0;
+		if (!bytes)
+			break;
 	}
 
 	res = LZ4_decompress_safe(stream->input, stream->output,
fs/squashfs/lzo_wrapper.c +10 -7
index d216aeefa8..bccfcfa12e 100644
@@ -66,21 +66,24 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
+	struct bio_vec bvec;
 	struct squashfs_lzo *stream = strm;
 	void *buff = stream->input, *data;
 	int bytes = length, res;
 	size_t out_len = output->length;
 
-	while (bio_next_segment(bio, &iter_all)) {
-		int avail = min(bytes, ((int)bvec->bv_len) - offset);
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
 
-		data = bvec_virt(bvec);
-		memcpy(buff, data + offset, avail);
+	bio_for_each_segment_all_continue(bvec, bio, iter) {
+		unsigned avail = min_t(unsigned, bytes, bvec.bv_len);
+
+		memcpy(buff, bvec_virt(&bvec), avail);
 		buff += avail;
 		bytes -= avail;
-		offset = 0;
+		if (!bytes)
+			break;
 	}
 
 	res = lzo1x_decompress_safe(stream->input, (size_t)length,
fs/squashfs/xz_wrapper.c +10 -9
index 6c49481a2f..6cf0e11e3b 100644
@@ -120,8 +120,7 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
 	int total = 0, error = 0;
 	struct squashfs_xz *stream = strm;
 
@@ -136,26 +135,28 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		goto finish;
 	}
 
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
+
 	for (;;) {
 		enum xz_ret xz_err;
 
 		if (stream->buf.in_pos == stream->buf.in_size) {
-			const void *data;
-			int avail;
+			struct bio_vec bvec = bio_iter_all_peek(bio, &iter);
+			unsigned avail = min_t(unsigned, length, bvec.bv_len);
 
-			if (!bio_next_segment(bio, &iter_all)) {
+			if (iter.idx >= bio->bi_vcnt) {
 				/* XZ_STREAM_END must be reached. */
 				error = -EIO;
 				break;
 			}
 
-			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = bvec_virt(bvec);
 			length -= avail;
-			stream->buf.in = data + offset;
+			stream->buf.in = bvec_virt(&bvec);
 			stream->buf.in_size = avail;
 			stream->buf.in_pos = 0;
-			offset = 0;
+
+			bio_iter_all_advance(bio, &iter, avail);
 		}
 
 		if (stream->buf.out_pos == stream->buf.out_size) {
fs/squashfs/zlib_wrapper.c +4 -2
index cbb7afe7bc..981ca5e410 100644
@@ -53,8 +53,7 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct bio *bio, int offset, int length,
 	struct squashfs_page_actor *output)
 {
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
 	int zlib_init = 0, error = 0;
 	z_stream *stream = strm;
 
@@ -67,25 +66,28 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		goto finish;
 	}
 
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
+

fs/squashfs/zlib_wrapper.c static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, · line 79

Quoted 10 lines
fs/squashfs/zlib_wrapper.c +2 -2
 	for (;;) {
 		int zlib_err;
 
 		if (stream->avail_in == 0) {
-			const void *data;
+			struct bio_vec bvec = bio_iter_all_peek(bio, &iter);
 			int avail;
 
-			if (!bio_next_segment(bio, &iter_all)) {
+			if (iter.idx >= bio->bi_vcnt) {

It is bad to expose iterator/bio internal here, probably you can return bool from bio_iter_all_peek() by moveing the check into helper, meantime passing bvec reference to bio_iter_all_peek().

Quoted 40 lines
fs/squashfs/zlib_wrapper.c +4 -4
 				/* Z_STREAM_END must be reached. */
 				error = -EIO;
 				break;
 			}
 
-			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = bvec_virt(bvec);
+			avail = min_t(unsigned, length, bvec.bv_len);
 			length -= avail;
-			stream->next_in = data + offset;
+			stream->next_in = bvec_virt(&bvec);
 			stream->avail_in = avail;
-			offset = 0;
+
+			bio_iter_all_advance(bio, &iter, avail);
 		}
 
 		if (stream->avail_out == 0) {
fs/squashfs/zstd_wrapper.c +4 -2
index 0e407c4d8b..658e5d462a 100644
@@ -68,8 +68,7 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	int error = 0;
 	zstd_in_buffer in_buf = { NULL, 0, 0 };
 	zstd_out_buffer out_buf = { NULL, 0, 0 };
-	struct bvec_iter_all iter_all = {};
-	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+	struct bvec_iter_all iter;
 
 	stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size);
 
@@ -85,25 +84,27 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		goto finish;
 	}
 
+	bvec_iter_all_init(&iter);
+	bio_iter_all_advance(bio, &iter, offset);
+
 	for (;;) {

fs/squashfs/zstd_wrapper.c static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, · line 97

Quoted 10 lines
fs/squashfs/zstd_wrapper.c +3 -3
 		size_t zstd_err;
 
 		if (in_buf.pos == in_buf.size) {
-			const void *data;
-			int avail;
+			struct bio_vec bvec = bio_iter_all_peek(bio, &iter);
+			unsigned avail = min_t(unsigned, length, bvec.bv_len);
 
-			if (!bio_next_segment(bio, &iter_all)) {
+			if (iter.idx >= bio->bi_vcnt) {

Same with above.

Quoted 50 lines
fs/squashfs/zstd_wrapper.c +3 -4
 				error = -EIO;
 				break;
 			}
 
-			avail = min(length, ((int)bvec->bv_len) - offset);
-			data = bvec_virt(bvec);
 			length -= avail;
-			in_buf.src = data + offset;
+			in_buf.src = bvec_virt(&bvec);
 			in_buf.size = avail;
 			in_buf.pos = 0;
-			offset = 0;
+
+			bio_iter_all_advance(bio, &iter, avail);
 		}
 
 		if (out_buf.pos == out_buf.size) {
include/linux/bio.h +15 -6
index 8588bcfbc6..39d8a1cc6e 100644
@@ -78,22 +78,34 @@ static inline void *bio_data(struct bio *bio)
 	return NULL;
 }
 
-static inline bool bio_next_segment(const struct bio *bio,
-				    struct bvec_iter_all *iter)
+static inline struct bio_vec bio_iter_all_peek(const struct bio *bio,
+					       struct bvec_iter_all *iter)
 {
-	if (iter->idx >= bio->bi_vcnt)
-		return false;
+	return bvec_iter_all_peek(bio->bi_io_vec, iter);
+}
 
-	bvec_advance(&bio->bi_io_vec[iter->idx], iter);
-	return true;
+static inline void bio_iter_all_advance(const struct bio *bio,
+					struct bvec_iter_all *iter,
+					unsigned bytes)
+{
+	bvec_iter_all_advance(bio->bi_io_vec, iter, bytes);
 }
 
+#define bio_for_each_segment_all_continue(bvl, bio, iter)		\
+	for (;								\
+	     iter.idx < bio->bi_vcnt &&					\
+		((bvl = bio_iter_all_peek(bio, &iter)), true);		\
+	     bio_iter_all_advance((bio), &iter, bvl.bv_len))
+

include/linux/bio.h static inline void *bio_data(struct bio *bio) · line 107

Quoted 10 lines
include/linux/bio.h +4 -2
 /*
  * drivers should _never_ use the all version - the bio may have been split
  * before it got to the driver and the driver won't own all of it
  */
-#define bio_for_each_segment_all(bvl, bio, iter) \
-	for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); )
+#define bio_for_each_segment_all(bvl, bio, iter)			\
+	for (bvec_iter_all_init(&iter);					\
+	     iter.idx < (bio)->bi_vcnt &&				\
+		((bvl = bio_iter_all_peek((bio), &iter)), true);		\

The check of 'iter.idx < (bio)->bi_vcnt' could be moved to bio_iter_all_peek(), meantime passing &bvl to bio_iter_all_peek().

Quoted 58 lines
include/linux/bio.h +1 -0
+	     bio_iter_all_advance((bio), &iter, bvl.bv_len))
 
 static inline void bio_advance_iter(const struct bio *bio,
 				    struct bvec_iter *iter, unsigned int bytes)
include/linux/bvec.h +19 -9
index 555aae5448..635fb54143 100644
@@ -85,12 +85,6 @@ struct bvec_iter {
 						   current bvec */
 } __packed;
 
-struct bvec_iter_all {
-	struct bio_vec	bv;
-	int		idx;
-	unsigned	done;
-};
-
 /*
  * various member access, note that bio_data should of course not be used
  * on highmem page vectors
@@ -184,7 +178,10 @@ static inline void bvec_iter_advance_single(const struct bio_vec *bv,
 		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
 	     bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len))
 
-/* for iterating one bio from start to end */
+/*
+ * bvec_iter_all: for advancing over a bio as it was originally created, but
+ * with the usual bio_for_each_segment interface - nonstandard, do not use:
+ */
 #define BVEC_ITER_ALL_INIT (struct bvec_iter)				\
 {									\
 	.bi_sector	= 0,						\
@@ -193,33 +190,45 @@ static inline void bvec_iter_advance_single(const struct bio_vec *bv,
 	.bi_bvec_done	= 0,						\
 }
 
-static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all)
+/*
+ * bvec_iter_all: for advancing over individual pages in a bio, as it was when
+ * it was first created:
+ */
+struct bvec_iter_all {
+	int		idx;
+	unsigned	done;
+};
+
+static inline void bvec_iter_all_init(struct bvec_iter_all *iter_all)
 {
 	iter_all->done = 0;
 	iter_all->idx = 0;
+}
 
-	return &iter_all->bv;
+static inline struct bio_vec bvec_iter_all_peek(const struct bio_vec *bvec,
+						struct bvec_iter_all *iter)
+{
+	struct bio_vec bv = bvec[iter->idx];

include/linux/bvec.h static inline void bvec_iter_advance_single(const struct bio_vec *bv, · line 221

Quoted 10 lines
include/linux/bvec.h +9 -0
+
+	bv.bv_offset	+= iter->done;
+	bv.bv_len	-= iter->done;
+
+	bv.bv_page	+= bv.bv_offset >> PAGE_SHIFT;
+	bv.bv_offset	&= ~PAGE_MASK;
+	bv.bv_len	= min_t(unsigned, PAGE_SIZE - bv.bv_offset, bv.bv_len);
+
+	return bv;
 }

Here I think compiler optimizes the last bvec copy by using external bvec directly, and I run fio/t/io_uring and not find IOPS degrade.

As mentioned above, it can be done explicitly by passing &bvl to bvec_iter_all_peek(), then user of bvec_iter_all_peek() can know if one real bvec is peeked, and check of 'if (iter.idx >= bio->bi_vcnt)' can be avoided in external callers.

Otherwise, this patch looks fine for me.

thanks,
Ming

author maintainer
#8 lore raw
Quoted 4 lines · Ming Lei
Quoted 3 lines · Kent Overstreet

This patch reworks bio_for_each_segment_all() to be more inline with how the other bio iterators work:

Quoted 8 lines
Quoted 5 lines

- bio_iter_all_peek() now returns a synthesized bio_vec; we don't stash one in the iterator and pass a pointer to it - bad. This way makes it clearer what's a constructed value vs. a reference to something pre-existing, and it also will help with cleaning up and consolidating code with bio_for_each_folio_all().

by-value is more readable & clean, the current by-reference is just for aligning with original interface.

This is the fourth or fifth time this patch set has been out on the list, and I specifically asked you to review it awhile back, and you're just now looking at it?