block: enable bio caching use for passthru IO

bdev based polled O_DIRECT is currently quite a bit faster than
passthru on the same device, and one of the reaons is that we're not
able to use the bio caching for passthru IO.

If REQ_POLLED is set on the request, use the fs bio set for grabbing a
bio from the caches, if available. This saves 5-6% of CPU over head
for polled passthru IO.
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-map.c

@@ -231,6 +231,16 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data,
 	return ret;
 }
 
+static void bio_map_put(struct bio *bio)
+{
+	if (bio->bi_opf & REQ_ALLOC_CACHE) {
+		bio_put(bio);
+	} else {
+		bio_uninit(bio);
+		kfree(bio);
+	}
+}
+
 static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 		gfp_t gfp_mask)
 {
@@ -243,10 +253,19 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 	if (!iov_iter_count(iter))
 		return -EINVAL;
 
+	if (rq->cmd_flags & REQ_POLLED) {
+		blk_opf_t opf = rq->cmd_flags | REQ_ALLOC_CACHE;
+
+		bio = bio_alloc_bioset(NULL, nr_vecs, opf, gfp_mask,
+					&fs_bio_set);
+		if (!bio)
+			return -ENOMEM;
+	} else {
 		bio = bio_kmalloc(nr_vecs, gfp_mask);
 		if (!bio)
 			return -ENOMEM;
 		bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq));
+	}
 
 	while (iov_iter_count(iter)) {
 		struct page **pages;
@@ -305,8 +324,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 
  out_unmap:
 	bio_release_pages(bio, false);
-	bio_uninit(bio);
-	kfree(bio);
+	bio_map_put(bio);
 	return ret;
 }
 
@@ -611,8 +629,7 @@ int blk_rq_unmap_user(struct bio *bio)
 
 		next_bio = bio;
 		bio = bio->bi_next;
-		bio_uninit(next_bio);
-		kfree(next_bio);
+		bio_map_put(next_bio);
 	}
 
 	return ret;