diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c
index 3e227292b0ac..b80dc45c3ff9 100644
--- a/fs/btrfs/direct-io.c
+++ b/fs/btrfs/direct-io.c
@@ -817,13 +817,41 @@ static ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter,
 			    IOMAP_DIO_PARTIAL | IOMAP_DIO_FSBLOCK_ALIGNED, &data, done_before);
 }
 
+static bool need_stable_write(struct btrfs_inode *inode)
+{
+	const u64 data_profile = btrfs_data_alloc_profile(inode->root->fs_info) &
+				 BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+	/* Data checksum requires stable buffer. */
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		return true;
+	/*
+	 * Any profile with mirror/parity will require stable buffer.
+	 * Otherwise the mirror may differ from each other.
+	 *
+	 * Thus only SINGLE and RAID0 doesn't require stable buffer.
+	 */
+	if (data_profile != 0 && data_profile != BTRFS_BLOCK_GROUP_RAID0)
+		return true;
+	return false;
+}
+
 static struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
 					 size_t done_before)
 {
 	struct btrfs_dio_data data = { 0 };
+	unsigned int dio_flags = IOMAP_DIO_PARTIAL | IOMAP_DIO_FSBLOCK_ALIGNED;
+
+	if (need_stable_write(BTRFS_I(file_inode(iocb->ki_filp)))) {
+		/* For now no support for BOUNCE and NOWAIT direct write. */
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return ERR_PTR(-EAGAIN);
+
+		dio_flags |= IOMAP_DIO_BOUNCE;
+	}
 
 	return __iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			    IOMAP_DIO_PARTIAL | IOMAP_DIO_FSBLOCK_ALIGNED, &data, done_before);
+			      dio_flags, &data, done_before);
 }
 
 static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
@@ -852,8 +880,6 @@ ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t ret;
 	unsigned int ilock_flags = 0;
 	struct iomap_dio *dio;
-	const u64 data_profile = btrfs_data_alloc_profile(fs_info) &
-				 BTRFS_BLOCK_GROUP_PROFILE_MASK;
 
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		ilock_flags |= BTRFS_ILOCK_TRY;
@@ -867,16 +893,6 @@ ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode) && IS_NOSEC(inode))
 		ilock_flags |= BTRFS_ILOCK_SHARED;
 
-	/*
-	 * If our data profile has duplication (either extra mirrors or RAID56),
-	 * we can not trust the direct IO buffer, the content may change during
-	 * writeback and cause different contents written to different mirrors.
-	 *
-	 * Thus only RAID0 and SINGLE can go true zero-copy direct IO.
-	 */
-	if (data_profile != BTRFS_BLOCK_GROUP_RAID0 && data_profile != 0)
-		goto buffered;
-
 relock:
 	ret = btrfs_inode_lock(BTRFS_I(inode), ilock_flags);
 	if (ret < 0)
@@ -917,22 +933,6 @@ ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 		btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
 		goto buffered;
 	}
-	/*
-	 * We can't control the folios being passed in, applications can write
-	 * to them while a direct IO write is in progress.  This means the
-	 * content might change after we calculated the data checksum.
-	 * Therefore we can end up storing a checksum that doesn't match the
-	 * persisted data.
-	 *
-	 * To be extra safe and avoid false data checksum mismatch, if the
-	 * inode requires data checksum, just fallback to buffered IO.
-	 * For buffered IO we have full control of page cache and can ensure
-	 * no one is modifying the content during writeback.
-	 */
-	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
-		btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
-		goto buffered;
-	}
 
 	/*
 	 * The iov_iter can be mapped to the same file range we are writing to.