block: pass a block_device and opf to bio_alloc_bioset

Pass the block_device and operation that we plan to use this bio for to
bio_alloc_bioset to optimize the assigment. NULL/0 can be passed, both
for the passthrough case on a raw request_queue and to temporarily avoid
refactoring some nasty code.

Also move the gfp_mask argument after the nr_vecs argument for a much
more logical calling convention matching what most of the kernel does.

Signed-off-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Chaitanya Kulkarni <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jens Axboe <[e-mail]>

block/bio.c

···
 
 /**
  * bio_alloc_bioset - allocate a bio for I/O
+ * @bdev:	block device to allocate the bio for (can be %NULL)
+ * @nr_vecs:	number of bvecs to pre-allocate
+ * @opf:	operation and flags for bio
  * @gfp_mask:   the GFP_* mask given to the slab allocator
- * @nr_iovecs:	number of iovecs to pre-allocate
  * @bs:		the bio_set to allocate from.
  *
  * Allocate a bio from the mempools in @bs.
···
  *
  * Returns: Pointer to new bio on success, NULL on failure.
  */
-struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned short nr_iovecs,
+struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
+			     unsigned int opf, gfp_t gfp_mask,
 			     struct bio_set *bs)
 {
 	gfp_t saved_gfp = gfp_mask;
 	struct bio *bio;
 	void *p;
 
-	/* should not use nobvec bioset for nr_iovecs > 0 */
-	if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_iovecs > 0))
+	/* should not use nobvec bioset for nr_vecs > 0 */
+	if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0))
 		return NULL;
 
 	/*
···
 		return NULL;
 
 	bio = p + bs->front_pad;
-	if (nr_iovecs > BIO_INLINE_VECS) {
+	if (nr_vecs > BIO_INLINE_VECS) {
 		struct bio_vec *bvl = NULL;
 
-		bvl = bvec_alloc(&bs->bvec_pool, &nr_iovecs, gfp_mask);
+		bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
 		if (!bvl && gfp_mask != saved_gfp) {
 			punt_bios_to_rescuer(bs);
 			gfp_mask = saved_gfp;
-			bvl = bvec_alloc(&bs->bvec_pool, &nr_iovecs, gfp_mask);
+			bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
 		}
 		if (unlikely(!bvl))
 			goto err_free;
 
-		bio_init(bio, bvl, nr_iovecs);
-	} else if (nr_iovecs) {
+		bio_init(bio, bvl, nr_vecs);
+	} else if (nr_vecs) {
 		bio_init(bio, bio->bi_inline_vecs, BIO_INLINE_VECS);
 	} else {
 		bio_init(bio, NULL, 0);
 	}
 
 	bio->bi_pool = bs;
+	if (bdev)
+		bio_set_dev(bio, bdev);
+	bio->bi_opf = opf;
 	return bio;
 
 err_free:
···
 {
 	struct bio *b;
 
-	b = bio_alloc_bioset(gfp_mask, 0, bs);
+	b = bio_alloc_bioset(NULL, 0, 0, gfp_mask, bs);
 	if (!b)
 		return NULL;
 
···
 	struct bio *bio;
 
 	if (!(kiocb->ki_flags & IOCB_ALLOC_CACHE) || nr_vecs > BIO_INLINE_VECS)
-		return bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs);
+		return bio_alloc_bioset(NULL, nr_vecs, 0, GFP_KERNEL, bs);
 
 	cache = per_cpu_ptr(bs->cache, get_cpu());
 	if (cache->free_list) {
···
 		return bio;
 	}
 	put_cpu();
-	bio = bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs);
+	bio = bio_alloc_bioset(NULL, nr_vecs, 0, GFP_KERNEL, bs);
 	bio_set_flag(bio, BIO_PERCPU_CACHE);
 	return bio;
 }

block/bounce.c

···
 	 *    asking for trouble and would force extra work on
 	 *    __bio_clone_fast() anyways.
 	 */
-	bio = bio_alloc_bioset(GFP_NOIO, bio_segments(bio_src),
-			       &bounce_bio_set);
-	bio->bi_bdev		= bio_src->bi_bdev;
+	bio = bio_alloc_bioset(bio_src->bi_bdev, bio_segments(bio_src),
+			       bio_src->bi_opf, GFP_NOIO, &bounce_bio_set);
 	if (bio_flagged(bio_src, BIO_REMAPPED))
 		bio_set_flag(bio, BIO_REMAPPED);
-	bio->bi_opf		= bio_src->bi_opf;
 	bio->bi_ioprio		= bio_src->bi_ioprio;
 	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;

drivers/block/drbd/drbd_actlog.c

···
 		op_flags |= REQ_FUA | REQ_PREFLUSH;
 	op_flags |= REQ_SYNC;
 
-	bio = bio_alloc_bioset(GFP_NOIO, 1, &drbd_md_io_bio_set);
-	bio_set_dev(bio, bdev->md_bdev);
+	bio = bio_alloc_bioset(bdev->md_bdev, 1, op | op_flags, GFP_NOIO,
+			       &drbd_md_io_bio_set);
 	bio->bi_iter.bi_sector = sector;
 	err = -EIO;
 	if (bio_add_page(bio, device->md_io.page, size, 0) != size)
 		goto out;
 	bio->bi_private = device;
 	bio->bi_end_io = drbd_md_endio;
-	bio_set_op_attrs(bio, op, op_flags);
 
 	if (op != REQ_OP_WRITE && device->state.disk == D_DISKLESS && device->ldev == NULL)
 		/* special case, drbd_md_read() during drbd_adm_attach(): no get_ldev */

drivers/block/drbd/drbd_bitmap.c

···
 
 static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_hold(local)
 {
-	struct bio *bio = bio_alloc_bioset(GFP_NOIO, 1, &drbd_md_io_bio_set);
 	struct drbd_device *device = ctx->device;
+	unsigned int op = (ctx->flags & BM_AIO_READ) ? REQ_OP_READ : REQ_OP_WRITE;
+	struct bio *bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op,
+					   GFP_NOIO, &drbd_md_io_bio_set);
 	struct drbd_bitmap *b = device->bitmap;
 	struct page *page;
 	unsigned int len;
-	unsigned int op = (ctx->flags & BM_AIO_READ) ? REQ_OP_READ : REQ_OP_WRITE;
 
 	sector_t on_disk_sector =
 		device->ldev->md.md_offset + device->ldev->md.bm_offset;
···
 		bm_store_page_idx(page, page_nr);
 	} else
 		page = b->bm_pages[page_nr];
-	bio_set_dev(bio, device->ldev->md_bdev);
 	bio->bi_iter.bi_sector = on_disk_sector;
 	/* bio_add_page of a single page to an empty bio will always succeed,
 	 * according to api.  Do we want to assert that? */
 	bio_add_page(bio, page, len, 0);
 	bio->bi_private = ctx;
 	bio->bi_end_io = drbd_bm_endio;
-	bio_set_op_attrs(bio, op, 0);
 
 	if (drbd_insert_fault(device, (op == REQ_OP_WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) {
 		bio_io_error(bio);

drivers/md/bcache/request.c

···
 	/* btree_search_recurse()'s btree iterator is no good anymore */
 	ret = miss == bio ? MAP_DONE : -EINTR;
 
-	cache_bio = bio_alloc_bioset(GFP_NOWAIT,
+	cache_bio = bio_alloc_bioset(miss->bi_bdev,
 			DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS),
-			&dc->disk.bio_split);
+			0, GFP_NOWAIT, &dc->disk.bio_split);
 	if (!cache_bio)
 		goto out_submit;
 
 	cache_bio->bi_iter.bi_sector	= miss->bi_iter.bi_sector;
-	bio_copy_dev(cache_bio, miss);
 	cache_bio->bi_iter.bi_size	= s->insert_bio_sectors << 9;
 
 	cache_bio->bi_end_io	= backing_request_endio;
···
 			 */
 			struct bio *flush;
 
-			flush = bio_alloc_bioset(GFP_NOIO, 0,
-						 &dc->disk.bio_split);
+			flush = bio_alloc_bioset(bio->bi_bdev, 0,
+						 REQ_OP_WRITE | REQ_PREFLUSH,
+						 GFP_NOIO, &dc->disk.bio_split);
 			if (!flush) {
 				s->iop.status = BLK_STS_RESOURCE;
 				goto insert_data;
 			}
-			bio_copy_dev(flush, bio);
 			flush->bi_end_io = backing_request_endio;
 			flush->bi_private = cl;
-			flush->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 			/* I/O request sent to backing device */
 			closure_bio_submit(s->iop.c, flush, cl);
 		}

drivers/md/dm-crypt.c

···
 	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
 		mutex_lock(&cc->bio_alloc_lock);
 
-	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, &cc->bs);
+	clone = bio_alloc_bioset(cc->dev->bdev, nr_iovecs, io->base_bio->bi_opf,
+				 GFP_NOIO, &cc->bs);
 	clone->bi_private = io;
 	clone->bi_end_io = crypt_endio;
-	bio_set_dev(clone, cc->dev->bdev);
-	clone->bi_opf = io->base_bio->bi_opf;
 
 	remaining_size = size;
 

drivers/md/dm-io.c

···
 						(PAGE_SIZE >> SECTOR_SHIFT)));
 		}
 
-		bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, &io->client->bios);
+		bio = bio_alloc_bioset(where->bdev, num_bvecs, op | op_flags,
+				       GFP_NOIO, &io->client->bios);
 		bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
-		bio_set_dev(bio, where->bdev);
 		bio->bi_end_io = endio;
-		bio_set_op_attrs(bio, op, op_flags);
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) {

drivers/md/dm-writecache.c

···
 
 		max_pages = e->wc_list_contiguous;
 
-		bio = bio_alloc_bioset(GFP_NOIO, max_pages, &wc->bio_set);
+		bio = bio_alloc_bioset(wc->dev->bdev, max_pages, REQ_OP_WRITE,
+				       GFP_NOIO, &wc->bio_set);
 		wb = container_of(bio, struct writeback_struct, bio);
 		wb->wc = wc;
 		bio->bi_end_io = writecache_writeback_endio;
-		bio_set_dev(bio, wc->dev->bdev);
 		bio->bi_iter.bi_sector = read_original_sector(wc, e);
 		if (max_pages <= WB_LIST_INLINE ||
 		    unlikely(!(wb->wc_list = kmalloc_array(max_pages, sizeof(struct wc_entry *),
···
 			wb->wc_list[wb->wc_list_n++] = f;
 			e = f;
 		}
-		bio_set_op_attrs(bio, REQ_OP_WRITE, WC_MODE_FUA(wc) * REQ_FUA);
+		if (WC_MODE_FUA(wc))
+			bio->bi_opf |= REQ_FUA;
 		if (writecache_has_error(wc)) {
 			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);

drivers/md/dm.c

···
 	struct dm_target_io *tio;
 	struct bio *clone;
 
-	clone = bio_alloc_bioset(GFP_NOIO, 0, &md->io_bs);
+	clone = bio_alloc_bioset(NULL, 0, 0, GFP_NOIO, &md->io_bs);
 
 	tio = container_of(clone, struct dm_target_io, clone);
 	tio->inside_dm_io = true;
···
 		/* the dm_target_io embedded in ci->io is available */
 		tio = &ci->io->tio;
 	} else {
-		struct bio *clone = bio_alloc_bioset(gfp_mask, 0, &ci->io->md->bs);
+		struct bio *clone = bio_alloc_bioset(NULL, 0, 0, gfp_mask,
+						     &ci->io->md->bs);
 		if (!clone)
 			return NULL;
 

drivers/md/md.c

···
 			atomic_inc(&rdev->nr_pending);
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
-			bi = bio_alloc_bioset(GFP_NOIO, 0, &mddev->bio_set);
+			bi = bio_alloc_bioset(rdev->bdev, 0,
+					      REQ_OP_WRITE | REQ_PREFLUSH,
+					      GFP_NOIO, &mddev->bio_set);
 			bi->bi_end_io = md_end_flush;
 			bi->bi_private = rdev;
-			bio_set_dev(bi, rdev->bdev);
-			bi->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 			atomic_inc(&mddev->flush_pending);
 			submit_bio(bi);
 			rcu_read_lock();
···
 	 * If an error occurred, call md_error
 	 */
 	struct bio *bio;
-	int ff = 0;
 
 	if (!page)
 		return;
···
 	if (test_bit(Faulty, &rdev->flags))
 		return;
 
-	bio = bio_alloc_bioset(GFP_NOIO, 1, &mddev->sync_set);
+	bio = bio_alloc_bioset(rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev,
+			       1,
+			       REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA,
+			       GFP_NOIO, &mddev->sync_set);
 
 	atomic_inc(&rdev->nr_pending);
 
-	bio_set_dev(bio, rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev);
 	bio->bi_iter.bi_sector = sector;
 	bio_add_page(bio, page, size, 0);
 	bio->bi_private = rdev;
···
 	if (test_bit(MD_FAILFAST_SUPPORTED, &mddev->flags) &&
 	    test_bit(FailFast, &rdev->flags) &&
 	    !test_bit(LastDev, &rdev->flags))
-		ff = MD_FAILFAST;
-	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA | ff;
+		bio->bi_opf |= MD_FAILFAST;
 
 	atomic_inc(&mddev->pending_writes);
 	submit_bio(bio);

drivers/md/raid1.c

···
 	int i = 0;
 	struct bio *behind_bio = NULL;
 
-	behind_bio = bio_alloc_bioset(GFP_NOIO, vcnt, &r1_bio->mddev->bio_set);
+	behind_bio = bio_alloc_bioset(NULL, vcnt, 0, GFP_NOIO,
+				      &r1_bio->mddev->bio_set);
 	if (!behind_bio)
 		return;
 

drivers/md/raid10.c

···
 		return sectors_done;
 	}
 
-	read_bio = bio_alloc_bioset(GFP_KERNEL, RESYNC_PAGES, &mddev->bio_set);
-
-	bio_set_dev(read_bio, rdev->bdev);
+	read_bio = bio_alloc_bioset(rdev->bdev, RESYNC_PAGES, REQ_OP_READ,
+				    GFP_KERNEL, &mddev->bio_set);
 	read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
 			       + rdev->data_offset);
 	read_bio->bi_private = r10_bio;
 	read_bio->bi_end_io = end_reshape_read;
-	bio_set_op_attrs(read_bio, REQ_OP_READ, 0);
 	r10_bio->master_bio = read_bio;
 	r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum;
 

drivers/md/raid5-cache.c

···
 
 static struct bio *r5l_bio_alloc(struct r5l_log *log)
 {
-	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, &log->bs);
+	struct bio *bio = bio_alloc_bioset(log->rdev->bdev, BIO_MAX_VECS,
+					   REQ_OP_WRITE, GFP_NOIO, &log->bs);
 
-	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-	bio_set_dev(bio, log->rdev->bdev);
 	bio->bi_iter.bi_sector = log->rdev->data_offset + log->log_start;
 
 	return bio;
···
 {
 	struct page *page;
 
-	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_VECS, &log->bs);
+	ctx->ra_bio = bio_alloc_bioset(NULL, BIO_MAX_VECS, 0, GFP_KERNEL,
+				       &log->bs);
 	if (!ctx->ra_bio)
 		return -ENOMEM;
 

drivers/md/raid5-ppl.c

···
 		if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) {
 			struct bio *prev = bio;
 
-			bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS,
+			bio = bio_alloc_bioset(prev->bi_bdev, BIO_MAX_VECS,
+					       prev->bi_opf, GFP_NOIO,
 					       &ppl_conf->bs);
-			bio->bi_opf = prev->bi_opf;
 			bio->bi_write_hint = prev->bi_write_hint;
-			bio_copy_dev(bio, prev);
 			bio->bi_iter.bi_sector = bio_end_sector(prev);
 			bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0);
 
···
 			struct bio *bio;
 			char b[BDEVNAME_SIZE];
 
-			bio = bio_alloc_bioset(GFP_NOIO, 0, &ppl_conf->flush_bs);
-			bio_set_dev(bio, bdev);
+			bio = bio_alloc_bioset(bdev, 0, GFP_NOIO,
+					       REQ_OP_WRITE | REQ_PREFLUSH,
+					       &ppl_conf->flush_bs);
 			bio->bi_private = io;
-			bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 			bio->bi_end_io = ppl_flush_endio;
 
 			pr_debug("%s: dev: %s\n", __func__,

drivers/target/target_core_iblock.c

···
 	 * Only allocate as many vector entries as the bio code allows us to,
 	 * we'll loop later on until we have handled the whole request.
 	 */
-	bio = bio_alloc_bioset(GFP_NOIO, bio_max_segs(sg_num),
-				&ib_dev->ibd_bio_set);
+	bio = bio_alloc_bioset(ib_dev->ibd_bd, bio_max_segs(sg_num), opf,
+			       GFP_NOIO, &ib_dev->ibd_bio_set);
 	if (!bio) {
 		pr_err("Unable to allocate memory for bio\n");
 		return NULL;
 	}
 
-	bio_set_dev(bio, ib_dev->ibd_bd);
 	bio->bi_private = cmd;
 	bio->bi_end_io = &iblock_bio_done;
 	bio->bi_iter.bi_sector = lba;
-	bio->bi_opf = opf;
 
 	return bio;
 }

fs/btrfs/extent_io.c

···
 	struct bio *bio;
 
 	ASSERT(0 < nr_iovecs && nr_iovecs <= BIO_MAX_VECS);
-	bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, &btrfs_bioset);
+	bio = bio_alloc_bioset(NULL, nr_iovecs, 0, GFP_NOFS, &btrfs_bioset);
 	btrfs_bio_init(btrfs_bio(bio));
 	return bio;
 }

fs/f2fs/data.c

···
 	struct f2fs_sb_info *sbi = fio->sbi;
 	struct bio *bio;
 
-	bio = bio_alloc_bioset(GFP_NOIO, npages, &f2fs_bioset);
+	bio = bio_alloc_bioset(NULL, npages, 0, GFP_NOIO, &f2fs_bioset);
 
 	f2fs_target_device(sbi, fio->new_blkaddr, bio);
 	if (is_read_io(fio->op)) {
···
 	struct bio_post_read_ctx *ctx = NULL;
 	unsigned int post_read_steps = 0;
 
-	bio = bio_alloc_bioset(for_write ? GFP_NOIO : GFP_KERNEL,
-			       bio_max_segs(nr_pages), &f2fs_bioset);
+	bio = bio_alloc_bioset(NULL, bio_max_segs(nr_pages), REQ_OP_READ,
+			       for_write ? GFP_NOIO : GFP_KERNEL, &f2fs_bioset);
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
 
···
 
 	f2fs_target_device(sbi, blkaddr, bio);
 	bio->bi_end_io = f2fs_read_end_io;
-	bio_set_op_attrs(bio, REQ_OP_READ, op_flag);
 
 	if (fscrypt_inode_uses_fs_layer_crypto(inode))
 		post_read_steps |= STEP_DECRYPT;

fs/iomap/buffered-io.c

···
 	struct iomap_ioend *ioend;
 	struct bio *bio;
 
-	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &iomap_ioend_bioset);
-	bio_set_dev(bio, wpc->iomap.bdev);
+	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
+			       REQ_OP_WRITE | wbc_to_write_flags(wbc),
+			       GFP_NOFS, &iomap_ioend_bioset);
 	bio->bi_iter.bi_sector = sector;
-	bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
 	bio->bi_write_hint = inode->i_write_hint;
 	wbc_init_bio(wbc, bio);
 

include/linux/bio.h

···
 extern int biovec_init_pool(mempool_t *pool, int pool_entries);
 extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src);
 
-struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs,
-		struct bio_set *bs);
+struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
+			     unsigned int opf, gfp_t gfp_mask,
+			     struct bio_set *bs);
 struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs,
 		struct bio_set *bs);
 struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs);
···
 
 static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs)
 {
-	return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set);
+	return bio_alloc_bioset(NULL, nr_iovecs, 0, gfp_mask, &fs_bio_set);
 }
 
 void submit_bio(struct bio *bio);