diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 52b8893f26f1..1286c1ac1940 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -105,6 +105,9 @@ void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
 	/* Make sure we're already in task context. */
 	ASSERT(in_task());
 
+	if (bbio->async_csum)
+		wait_for_completion(&bbio->csum_done);
+
 	bbio->bio.bi_status = status;
 	if (bbio->bio.bi_pool == &btrfs_clone_bioset) {
 		struct btrfs_bio *orig_bbio = bbio->private;
@@ -538,7 +541,11 @@ static int btrfs_bio_csum(struct btrfs_bio *bbio)
 {
 	if (bbio->bio.bi_opf & REQ_META)
 		return btree_csum_one_bio(bbio);
-	return btrfs_csum_one_bio(bbio);
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+	return btrfs_csum_one_bio(bbio, true);
+#else
+	return btrfs_csum_one_bio(bbio, false);
+#endif
 }
 
 /*
@@ -617,10 +624,14 @@ static bool should_async_write(struct btrfs_bio *bbio)
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	enum btrfs_offload_csum_mode csum_mode = READ_ONCE(fs_devices->offload_csum_mode);
 
-	if (csum_mode == BTRFS_OFFLOAD_CSUM_FORCE_OFF)
-		return false;
-
-	auto_csum_mode = (csum_mode == BTRFS_OFFLOAD_CSUM_AUTO);
+	if (csum_mode == BTRFS_OFFLOAD_CSUM_FORCE_ON)
+		return true;
+	/*
+	 * Write bios will calculate checksum and submit bio at the same time.
+	 * Unless explicitly required don't offload serial csum calculate and bio
+	 * submit into a workqueue.
+	 */
+	return false;
 #endif
 
 	/* Submit synchronously if the checksum implementation is fast. */
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index 5d20f959e12d..deaeea3becf4 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -56,6 +56,9 @@ struct btrfs_bio {
 		struct {
 			struct btrfs_ordered_extent *ordered;
 			struct btrfs_ordered_sum *sums;
+			struct work_struct csum_work;
+			struct completion csum_done;
+			struct bvec_iter csum_saved_iter;
 			u64 orig_physical;
 		};
 
@@ -83,6 +86,10 @@ struct btrfs_bio {
 	 * scrub bios.
 	 */
 	bool is_scrub;
+
+	/* Whether the csum generation for data write is async. */
+	bool async_csum;
+
 	/*
 	 * This member must come last, bio_alloc_bioset will allocate enough
 	 * bytes for entire btrfs_bio but relies on bio being last.
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a42e6d54e7cd..4b7c40f05e8f 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -18,6 +18,7 @@
 #include "fs.h"
 #include "accessors.h"
 #include "file-item.h"
+#include "volumes.h"
 
 #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \
 				   sizeof(struct btrfs_item) * 2) / \
@@ -764,21 +765,46 @@ int btrfs_lookup_csums_bitmap(struct btrfs_root *root, struct btrfs_path *path,
 	return ret;
 }
 
-/*
- * Calculate checksums of the data contained inside a bio.
- */
-int btrfs_csum_one_bio(struct btrfs_bio *bbio)
+static void csum_one_bio(struct btrfs_bio *bbio, struct bvec_iter *src)
 {
-	struct btrfs_ordered_extent *ordered = bbio->ordered;
 	struct btrfs_inode *inode = bbio->inode;
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	struct bio *bio = &bbio->bio;
-	struct btrfs_ordered_sum *sums;
-	struct bvec_iter iter = bio->bi_iter;
+	struct btrfs_ordered_sum *sums = bbio->sums;
+	struct bvec_iter iter = *src;
 	phys_addr_t paddr;
 	const u32 blocksize = fs_info->sectorsize;
-	int index;
+	int index = 0;
+
+	shash->tfm = fs_info->csum_shash;
+
+	btrfs_bio_for_each_block(paddr, bio, &iter, blocksize) {
+		btrfs_calculate_block_csum(fs_info, paddr, sums->sums + index);
+		index += fs_info->csum_size;
+	}
+}
+
+static void csum_one_bio_work(struct work_struct *work)
+{
+	struct btrfs_bio *bbio = container_of(work, struct btrfs_bio, csum_work);
+
+	ASSERT(btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE);
+	ASSERT(bbio->async_csum == true);
+	csum_one_bio(bbio, &bbio->csum_saved_iter);
+	complete(&bbio->csum_done);
+}
+
+/*
+ * Calculate checksums of the data contained inside a bio.
+ */
+int btrfs_csum_one_bio(struct btrfs_bio *bbio, bool async)
+{
+	struct btrfs_ordered_extent *ordered = bbio->ordered;
+	struct btrfs_inode *inode = bbio->inode;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct bio *bio = &bbio->bio;
+	struct btrfs_ordered_sum *sums;
 	unsigned nofs_flag;
 
 	nofs_flag = memalloc_nofs_save();
@@ -789,21 +815,21 @@ int btrfs_csum_one_bio(struct btrfs_bio *bbio)
 	if (!sums)
 		return -ENOMEM;
 
+	sums->logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 	sums->len = bio->bi_iter.bi_size;
 	INIT_LIST_HEAD(&sums->list);
-
-	sums->logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
-	index = 0;
-
-	shash->tfm = fs_info->csum_shash;
-
-	btrfs_bio_for_each_block(paddr, bio, &iter, blocksize) {
-		btrfs_calculate_block_csum(fs_info, paddr, sums->sums + index);
-		index += fs_info->csum_size;
-	}
-
 	bbio->sums = sums;
 	btrfs_add_ordered_sum(ordered, sums);
+
+	if (!async) {
+		csum_one_bio(bbio, &bbio->bio.bi_iter);
+		return 0;
+	}
+	init_completion(&bbio->csum_done);
+	bbio->async_csum = true;
+	bbio->csum_saved_iter = bbio->bio.bi_iter;
+	INIT_WORK(&bbio->csum_work, csum_one_bio_work);
+	schedule_work(&bbio->csum_work);
 	return 0;
 }
 
diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h
index 0d59e830018a..5645c5e3abdb 100644
--- a/fs/btrfs/file-item.h
+++ b/fs/btrfs/file-item.h
@@ -64,7 +64,7 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
 int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct btrfs_ordered_sum *sums);
-int btrfs_csum_one_bio(struct btrfs_bio *bbio);
+int btrfs_csum_one_bio(struct btrfs_bio *bbio, bool async);
 int btrfs_alloc_dummy_sum(struct btrfs_bio *bbio);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit,