diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8e35a82db606369e5b154564ea7bd014d24fe337..3074e35cb4b118acb5dfbdc32a6f677b13dc39eb 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -163,19 +163,25 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
  * threads are at work on the same unwritten block, they must be synchronized
  * or one thread will zero the other's data, causing corruption.
  */
-static int
-ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
+static bool
+ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos)
 {
 	struct super_block *sb = inode->i_sb;
-	int blockmask = sb->s_blocksize - 1;
-
-	if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
-		return 0;
+	unsigned long blockmask = sb->s_blocksize - 1;
 
 	if ((pos | iov_iter_alignment(from)) & blockmask)
-		return 1;
+		return true;
 
-	return 0;
+	return false;
+}
+
+static bool
+ext4_extending_io(struct inode *inode, loff_t offset, size_t len)
+{
+	if (offset + len > i_size_read(inode) ||
+	    offset + len > EXT4_I(inode)->i_disksize)
+		return true;
+	return false;
 }
 
 /* Is IO overwriting allocated and initialized blocks? */
@@ -201,10 +207,10 @@ static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
 	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
 }
 
-static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_generic_write_checks(struct kiocb *iocb,
+					 struct iov_iter *from)
 {
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file);
+	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
 	ret = generic_write_checks(iocb, from);
@@ -226,6 +232,18 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
 	}
 
+	return iov_iter_count(from);
+}
+
+static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t ret, count;
+
+	count = ext4_generic_write_checks(iocb, from);
+	if (count <= 0)
+		return count;
+
 	ret = file_remove_privs(file);
 	if (ret)
 		return ret;
@@ -236,7 +254,7 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 			return ret;
 	}
 
-	return iov_iter_count(from);
+	return count;
 }
 
 static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
@@ -368,62 +386,145 @@ static const struct iomap_dio_ops ext4_dio_write_ops = {
 	.end_io = ext4_dio_write_end_io,
 };
 
+/*
+ * The intention here is to start with shared lock acquired then see if any
+ * condition requires an exclusive inode lock. If yes, then we restart the
+ * whole operation by releasing the shared lock and acquiring exclusive lock.
+ *
+ * - For unaligned_io we never take shared lock as it may cause data corruption
+ *   when two unaligned IO tries to modify the same block e.g. while zeroing.
+ *
+ * - For extending writes case we don't take the shared lock, since it requires
+ *   updating inode i_disksize and/or orphan handling with exclusive lock.
+ *
+ * - shared locking will only be true mostly with overwrites in dioread_nolock
+ *   mode. Otherwise we will switch to exclusive i_rwsem lock.
+ */
+static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
+				     bool *ilock_shared, bool *extend)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	loff_t offset;
+	size_t count;
+	ssize_t ret;
+
+restart:
+	ret = ext4_generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	offset = iocb->ki_pos;
+	count = iov_iter_count(from);
+	if (ext4_extending_io(inode, offset, count))
+		*extend = true;
+	/*
+	 * Determine whether the IO operation will overwrite allocated
+	 * and initialized blocks. If so, check to see whether it is
+	 * possible to take the dioread_nolock path.
+	 *
+	 * We need exclusive i_rwsem for changing security info
+	 * in file_modified().
+	 */
+	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
+	     !ext4_should_dioread_nolock(inode) ||
+	     !ext4_overwrite_io(inode, offset, count))) {
+		inode_unlock_shared(inode);
+		*ilock_shared = false;
+		inode_lock(inode);
+		goto restart;
+	}
+
+	ret = file_remove_privs(file);
+	if (ret < 0)
+		goto out;
+
+	if (!(file->f_mode & FMODE_NOCMTIME)) {
+		ret = file_update_time(file);
+		if (ret < 0)
+			goto out;
+	}
+
+	return count;
+out:
+	if (*ilock_shared)
+		inode_unlock_shared(inode);
+	else
+		inode_unlock(inode);
+	return ret;
+}
+
 static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	ssize_t ret;
-	size_t count;
-	loff_t offset;
 	handle_t *handle;
 	struct inode *inode = file_inode(iocb->ki_filp);
-	bool extend = false, overwrite = false, unaligned_aio = false;
+	loff_t offset = iocb->ki_pos;
+	size_t count = iov_iter_count(from);
+	bool extend = false, unaligned_io = false;
+	bool ilock_shared = true;
+
+	/*
+	 * We initially start with shared inode lock unless it is
+	 * unaligned IO which needs exclusive lock anyways.
+	 */
+	if (ext4_unaligned_io(inode, from, offset)) {
+		unaligned_io = true;
+		ilock_shared = false;
+	}
+	/*
+	 * Quick check here without any i_rwsem lock to see if it is extending
+	 * IO. A more reliable check is done in ext4_dio_write_checks() with
+	 * proper locking in place.
+	 */
+	if (offset + count > i_size_read(inode))
+		ilock_shared = false;
 
 	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (!inode_trylock(inode))
-			return -EAGAIN;
+		if (ilock_shared) {
+			if (!inode_trylock_shared(inode))
+				return -EAGAIN;
+		} else {
+			if (!inode_trylock(inode))
+				return -EAGAIN;
+		}
 	} else {
-		inode_lock(inode);
+		if (ilock_shared)
+			inode_lock_shared(inode);
+		else
+			inode_lock(inode);
 	}
 
+	/* Fallback to buffered I/O if the inode does not support direct I/O. */
 	if (!ext4_dio_supported(inode)) {
-		inode_unlock(inode);
-		/*
-		 * Fallback to buffered I/O if the inode does not support
-		 * direct I/O.
-		 */
+		if (ilock_shared)
+			inode_unlock_shared(inode);
+		else
+			inode_unlock(inode);
 		return ext4_buffered_write_iter(iocb, from);
 	}
 
-	ret = ext4_write_checks(iocb, from);
-	if (ret <= 0) {
-		inode_unlock(inode);
+	ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend);
+	if (ret <= 0)
 		return ret;
-	}
 
-	/*
-	 * Unaligned asynchronous direct I/O must be serialized among each
-	 * other as the zeroing of partial blocks of two competing unaligned
-	 * asynchronous direct I/O writes can result in data corruption.
-	 */
 	offset = iocb->ki_pos;
 	count = iov_iter_count(from);
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
-	    !is_sync_kiocb(iocb) && ext4_unaligned_aio(inode, from, offset)) {
-		unaligned_aio = true;
-		inode_dio_wait(inode);
-	}
 
 	/*
-	 * Determine whether the I/O will overwrite allocated and initialized
-	 * blocks. If so, check to see whether it is possible to take the
-	 * dioread_nolock path.
+	 * Unaligned direct IO must be serialized among each other as zeroing
+	 * of partial blocks of two competing unaligned IOs can result in data
+	 * corruption.
+	 *
+	 * So we make sure we don't allow any unaligned IO in flight.
+	 * For IOs where we need not wait (like unaligned non-AIO DIO),
+	 * below inode_dio_wait() may anyway become a no-op, since we start
+	 * with exclusive lock.
 	 */
-	if (!unaligned_aio && ext4_overwrite_io(inode, offset, count) &&
-	    ext4_should_dioread_nolock(inode)) {
-		overwrite = true;
-		downgrade_write(&inode->i_rwsem);
-	}
+	if (unaligned_io)
+		inode_dio_wait(inode);
 
-	if (offset + count > EXT4_I(inode)->i_disksize) {
+	if (extend) {
 		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
@@ -446,7 +547,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		ret = ext4_handle_inode_extension(inode, offset, ret, count);
 
 out:
-	if (overwrite)
+	if (ilock_shared)
 		inode_unlock_shared(inode);
 	else
 		inode_unlock(inode);