Btrfs: use bio_clone_bioset_partial to simplify DIO submit

Currently when mapping bio to limit bio to a single stripe length, we
split bio by adding page to bio one by one, but later we don't modify
the vector of bio at all, thus we can use bio_clone_fast to use the
original bio vector directly.
Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/inode.c

@@ -8380,16 +8380,6 @@ static void btrfs_end_dio_bio(struct bio *bio)
 	bio_put(bio);
 }
 
-static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
-				       u64 first_sector, gfp_t gfp_flags)
-{
-	struct bio *bio;
-	bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags);
-	if (bio)
-		bio_associate_current(bio);
-	return bio;
-}
-
 static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode,
 						 struct btrfs_dio_private *dip,
 						 struct bio *bio,
@@ -8479,24 +8469,23 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct bio *bio;
 	struct bio *orig_bio = dip->orig_bio;
-	struct bio_vec *bvec;
 	u64 start_sector = orig_bio->bi_iter.bi_sector;
 	u64 file_offset = dip->logical_offset;
-	u64 submit_len = 0;
 	u64 map_length;
-	u32 blocksize = fs_info->sectorsize;
 	int async_submit = 0;
-	int nr_sectors;
+	u64 submit_len;
+	int clone_offset = 0;
+	int clone_len;
 	int ret;
-	int i, j;
 
 	map_length = orig_bio->bi_iter.bi_size;
+	submit_len = map_length;
 	ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), start_sector << 9,
 			      &map_length, NULL, 0);
 	if (ret)
 		return -EIO;
 
-	if (map_length >= orig_bio->bi_iter.bi_size) {
+	if (map_length >= submit_len) {
 		bio = orig_bio;
 		dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED;
 		goto submit;
@@ -8508,32 +8497,36 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	else
 		async_submit = 1;
 
-	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
-	if (!bio)
-		return -ENOMEM;
+	/* bio split */
+	ASSERT(map_length <= INT_MAX);
+	atomic_inc(&dip->pending_bios);
+	while (submit_len > 0) {
+		clone_len = min_t(int, submit_len, map_length);
 
-	bio->bi_opf = orig_bio->bi_opf;
+		/*
+		 * This will never fail as it's passing GPF_NOFS and
+		 * the allocation is backed by btrfs_bioset.
+		 */
+		bio = btrfs_bio_clone_partial(orig_bio, GFP_NOFS, clone_offset,
+					      clone_len);
 		bio->bi_private = dip;
 		bio->bi_end_io = btrfs_end_dio_bio;
 		btrfs_io_bio(bio)->logical = file_offset;
-	atomic_inc(&dip->pending_bios);
 
-	bio_for_each_segment_all(bvec, orig_bio, j) {
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-		i = 0;
-next_block:
-		if (unlikely(map_length < submit_len + blocksize ||
-		    bio_add_page(bio, bvec->bv_page, blocksize,
-			    bvec->bv_offset + (i * blocksize)) < blocksize)) {
+		ASSERT(submit_len >= clone_len);
+		submit_len -= clone_len;
+		if (submit_len == 0)
+			break;
+
 		/*
-			 * inc the count before we submit the bio so
-			 * we know the end IO handler won't happen before
-			 * we inc the count. Otherwise, the dip might get freed
-			 * before we're done setting it up
+		 * Increase the count before we submit the bio so we know
+		 * the end IO handler won't happen before we increase the
+		 * count. Otherwise, the dip might get freed before we're
+		 * done setting it up.
 		 */
 		atomic_inc(&dip->pending_bios);
-			ret = __btrfs_submit_dio_bio(bio, inode,
-						     file_offset, skip_sum,
+
+		ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
 					     async_submit);
 		if (ret) {
 			bio_put(bio);
@@ -8541,39 +8534,17 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 			goto out_err;
 		}
 
-			start_sector += submit_len >> 9;
-			file_offset += submit_len;
-
-			submit_len = 0;
+		clone_offset += clone_len;
+		start_sector += clone_len >> 9;
+		file_offset += clone_len;
 
-			bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
-						  start_sector, GFP_NOFS);
-			if (!bio)
-				goto out_err;
-			bio->bi_opf = orig_bio->bi_opf;
-			bio->bi_private = dip;
-			bio->bi_end_io = btrfs_end_dio_bio;
-			btrfs_io_bio(bio)->logical = file_offset;
-
-			map_length = orig_bio->bi_iter.bi_size;
+		map_length = submit_len;
 		ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
-					      start_sector << 9,
-					      &map_length, NULL, 0);
-			if (ret) {
-				bio_put(bio);
+				      start_sector << 9, &map_length, NULL, 0);
+		if (ret)
 			goto out_err;
 	}
 
-			goto next_block;
-		} else {
-			submit_len += blocksize;
-			if (--nr_sectors) {
-				i++;
-				goto next_block;
-			}
-		}
-	}
-
 submit:
 	ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
 				     async_submit);