diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 89e1bcb21341..b84aa1ca480a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2527,8 +2527,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
 int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
 			     struct buffer_head *bh_result, int create);
-int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
-			    struct buffer_head *bh_result, int create);
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
 		   struct buffer_head *bh_result, int create);
 int ext4_dio_get_block(struct inode *inode, sector_t iblock,
@@ -3334,6 +3334,13 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
 	}
 }
 
+static inline bool ext4_aligned_io(struct inode *inode, loff_t off, loff_t len)
+{
+	int blksize = 1 << inode->i_blkbits;
+
+	return IS_ALIGNED(off, blksize) && IS_ALIGNED(len, blksize);
+}
+
 #endif	/* __KERNEL__ */
 
 #define EFSBADCRC	EBADMSG		/* Bad CRC detected */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 3e850b988923..37e28082885a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -207,7 +207,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
+		result = __dax_fault(vma, vmf, ext4_dax_get_block, NULL);
 
 	if (write) {
 		if (!IS_ERR(handle))
@@ -243,7 +243,7 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 		result = VM_FAULT_SIGBUS;
 	else
 		result = __dax_pmd_fault(vma, addr, pmd, flags,
-				ext4_dax_mmap_get_block, NULL);
+					 ext4_dax_get_block, NULL);
 
 	if (write) {
 		if (!IS_ERR(handle))
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4879e93c91d3..f9ab1e8cc416 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3229,13 +3229,17 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 }
 
 #ifdef CONFIG_FS_DAX
-int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
-			    struct buffer_head *bh_result, int create)
+/*
+ * Get block function for DAX IO and mmap faults. It takes care of converting
+ * unwritten extents to written ones and initializes new / converted blocks
+ * to zeros.
+ */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh_result, int create)
 {
 	int ret;
 
-	ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n",
-		   inode->i_ino, create);
+	ext4_debug("inode %lu, create flag %d\n", inode->i_ino, create);
 	if (!create)
 		return _ext4_get_block(inode, iblock, bh_result, 0);
 
@@ -3247,9 +3251,9 @@ int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
 
 	if (buffer_unwritten(bh_result)) {
 		/*
-		 * We are protected by i_mmap_sem so we know block cannot go
-		 * away from under us even though we dropped i_data_sem.
-		 * Convert extent to written and write zeros there.
+		 * We are protected by i_mmap_sem or i_mutex so we know block
+		 * cannot go away from under us even though we dropped
+		 * i_data_sem. Convert extent to written and write zeros there.
 		 */
 		ret = ext4_get_block_trans(inode, iblock, bh_result,
 					   EXT4_GET_BLOCKS_CONVERT |
@@ -3264,6 +3268,14 @@ int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
 	clear_buffer_new(bh_result);
 	return 0;
 }
+#else
+/* Just define empty function, it will never get called. */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+		       struct buffer_head *bh_result, int create)
+{
+	BUG();
+	return 0;
+}
 #endif
 
 static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
@@ -3385,8 +3397,20 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter,
 	iocb->private = NULL;
 	if (overwrite)
 		get_block_func = ext4_dio_get_block_overwrite;
-	else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
-		 round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+	else if (IS_DAX(inode)) {
+		/*
+		 * We can avoid zeroing for aligned DAX writes beyond EOF. Other
+		 * writes need zeroing either because they can race with page
+		 * faults or because they use partial blocks.
+		 */
+		if (round_down(offset, 1<<inode->i_blkbits) >= inode->i_size &&
+		    ext4_aligned_io(inode, offset, count))
+			get_block_func = ext4_dio_get_block;
+		else
+			get_block_func = ext4_dax_get_block;
+		dio_flags = DIO_LOCKING;
+	} else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
+		   round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
 		get_block_func = ext4_dio_get_block;
 		dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
 	} else if (is_sync_kiocb(iocb)) {
@@ -3400,7 +3424,6 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter,
 	BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
 #endif
 	if (IS_DAX(inode)) {
-		dio_flags &= ~DIO_SKIP_HOLES;
 		ret = dax_do_io(iocb, inode, iter, offset, get_block_func,
 				ext4_end_io_dio, dio_flags);
 	} else