1 files changed, 125 insertions, 1 deletions

diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index d1ae0f0a3726..0b4c91c62e1f 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -25,9 +25,11 @@
 #include <linux/quotaops.h>
 #include <linux/iomap.h>
 #include <linux/uio.h>
+#include <linux/buffer_head.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
+#include "trace.h"
 
 #ifdef CONFIG_FS_DAX
 static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -153,7 +155,7 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct super_block *sb = file->f_mapping->host->i_sb;
 
-	ret = generic_file_fsync(file, start, end, datasync);
+	ret = generic_buffers_fsync(file, start, end, datasync);
 	if (ret == -EIO)
 		/* We don't really know where the IO error happened... */
 		ext2_error(sb, __func__,
@@ -161,12 +163,131 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	return ret;
 }
 
+static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+
+	trace_ext2_dio_read_begin(iocb, to, 0);
+	inode_lock_shared(inode);
+	ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0);
+	inode_unlock_shared(inode);
+	trace_ext2_dio_read_end(iocb, to, ret);
+
+	return ret;
+}
+
+static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+				 int error, unsigned int flags)
+{
+	loff_t pos = iocb->ki_pos;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (error)
+		goto out;
+
+	/*
+	 * If we are extending the file, we have to update i_size here before
+	 * page cache gets invalidated in iomap_dio_rw(). This prevents racing
+	 * buffered reads from zeroing out too much from page cache pages.
+	 * Note that all extending writes always happens synchronously with
+	 * inode lock held by ext2_dio_write_iter(). So it is safe to update
+	 * inode size here for extending file writes.
+	 */
+	pos += size;
+	if (pos > i_size_read(inode)) {
+		i_size_write(inode, pos);
+		mark_inode_dirty(inode);
+	}
+out:
+	trace_ext2_dio_write_endio(iocb, size, error);
+	return error;
+}
+
+static const struct iomap_dio_ops ext2_dio_write_ops = {
+	.end_io = ext2_dio_write_end_io,
+};
+
+static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	ssize_t ret;
+	unsigned int flags = 0;
+	unsigned long blocksize = inode->i_sb->s_blocksize;
+	loff_t offset = iocb->ki_pos;
+	loff_t count = iov_iter_count(from);
+	ssize_t status = 0;
+
+	trace_ext2_dio_write_begin(iocb, from, 0);
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out_unlock;
+
+	ret = kiocb_modified(iocb);
+	if (ret)
+		goto out_unlock;
+
+	/* use IOMAP_DIO_FORCE_WAIT for unaligned or extending writes */
+	if (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode) ||
+	   (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(from), blocksize)))
+		flags |= IOMAP_DIO_FORCE_WAIT;
+
+	ret = iomap_dio_rw(iocb, from, &ext2_iomap_ops, &ext2_dio_write_ops,
+			   flags, NULL, 0);
+
+	/* ENOTBLK is magic return value for fallback to buffered-io */
+	if (ret == -ENOTBLK)
+		ret = 0;
+
+	if (ret < 0 && ret != -EIOCBQUEUED)
+		ext2_write_failed(inode->i_mapping, offset + count);
+
+	/* handle case for partial write and for fallback to buffered write */
+	if (ret >= 0 && iov_iter_count(from)) {
+		loff_t pos, endbyte;
+		int ret2;
+
+		iocb->ki_flags &= ~IOCB_DIRECT;
+		pos = iocb->ki_pos;
+		status = generic_perform_write(iocb, from);
+		if (unlikely(status < 0)) {
+			ret = status;
+			goto out_unlock;
+		}
+
+		iocb->ki_pos += status;
+		ret += status;
+		endbyte = pos + status - 1;
+		ret2 = filemap_write_and_wait_range(inode->i_mapping, pos,
+						    endbyte);
+		if (!ret2)
+			invalidate_mapping_pages(inode->i_mapping,
+						 pos >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+		if (ret > 0)
+			generic_write_sync(iocb, ret);
+	}
+
+out_unlock:
+	inode_unlock(inode);
+	if (status)
+		trace_ext2_dio_write_buff_end(iocb, from, status);
+	trace_ext2_dio_write_end(iocb, from, ret);
+	return ret;
+}
+
 static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 #ifdef CONFIG_FS_DAX
 	if (IS_DAX(iocb->ki_filp->f_mapping->host))
 		return ext2_dax_read_iter(iocb, to);
 #endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext2_dio_read_iter(iocb, to);
+
 	return generic_file_read_iter(iocb, to);
 }
 
@@ -176,6 +297,9 @@ static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (IS_DAX(iocb->ki_filp->f_mapping->host))
 		return ext2_dax_write_iter(iocb, from);
 #endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext2_dio_write_iter(iocb, from);
+
 	return generic_file_write_iter(iocb, from);
 }