dax,ext2: replace XIP read and write with DAX I/O

Use the generic AIO infrastructure instead of custom read and write
methods.  In addition to giving us support for AIO, this adds the missing
locking between read() and truncate().

Signed-off-by: Matthew Wilcox <[email protected]>
Reviewed-by: Ross Zwisler <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Cc: Andreas Dilger <[email protected]>
Cc: Boaz Harrosh <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Dave Chinner <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Kirill A. Shutemov <[email protected]>
Cc: Mathieu Desnoyers <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Theodore Ts'o <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

MAINTAINERS

@@ -3151,6 +3151,12 @@ L:	[email protected]
 S:	Maintained
 F:	drivers/i2c/busses/i2c-diolan-u2c.c
 
+DIRECT ACCESS (DAX)
+M:	Matthew Wilcox <[email protected]>
+L:	[email protected]
+S:	Supported
+F:	fs/dax.c
+
 DIRECTORY NOTIFICATION (DNOTIFY)
 M:	Eric Paris <[email protected]>
 S:	Maintained

fs/Makefile

@@ -28,6 +28,7 @@ obj-$(CONFIG_SIGNALFD)		+= signalfd.o
 obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_AIO)               += aio.o
+obj-$(CONFIG_FS_XIP)		+= dax.o
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o

fs/dax.c

@@ -0,0 +1,186 @@
+/*
+ * fs/dax.c - Direct Access filesystem code
+ * Copyright (c) 2013-2014 Intel Corporation
+ * Author: Matthew Wilcox <[email protected]>
+ * Author: Ross Zwisler <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/atomic.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/mutex.h>
+#include <linux/uio.h>
+
+static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
+{
+	unsigned long pfn;
+	sector_t sector = bh->b_blocknr << (blkbits - 9);
+	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
+}
+
+static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
+			loff_t end)
+{
+	loff_t final = end - pos + first; /* The final byte of the buffer */
+
+	if (first > 0)
+		memset(addr, 0, first);
+	if (final < size)
+		memset(addr + final, 0, size - final);
+}
+
+static bool buffer_written(struct buffer_head *bh)
+{
+	return buffer_mapped(bh) && !buffer_unwritten(bh);
+}
+
+/*
+ * When ext4 encounters a hole, it returns without modifying the buffer_head
+ * which means that we can't trust b_size.  To cope with this, we set b_state
+ * to 0 before calling get_block and, if any bit is set, we know we can trust
+ * b_size.  Unfortunate, really, since ext4 knows precisely how long a hole is
+ * and would save us time calling get_block repeatedly.
+ */
+static bool buffer_size_valid(struct buffer_head *bh)
+{
+	return bh->b_state != 0;
+}
+
+static ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
+			loff_t start, loff_t end, get_block_t get_block,
+			struct buffer_head *bh)
+{
+	ssize_t retval = 0;
+	loff_t pos = start;
+	loff_t max = start;
+	loff_t bh_max = start;
+	void *addr;
+	bool hole = false;
+
+	if (rw != WRITE)
+		end = min(end, i_size_read(inode));
+
+	while (pos < end) {
+		unsigned len;
+		if (pos == max) {
+			unsigned blkbits = inode->i_blkbits;
+			sector_t block = pos >> blkbits;
+			unsigned first = pos - (block << blkbits);
+			long size;
+
+			if (pos == bh_max) {
+				bh->b_size = PAGE_ALIGN(end - pos);
+				bh->b_state = 0;
+				retval = get_block(inode, block, bh,
+								rw == WRITE);
+				if (retval)
+					break;
+				if (!buffer_size_valid(bh))
+					bh->b_size = 1 << blkbits;
+				bh_max = pos - first + bh->b_size;
+			} else {
+				unsigned done = bh->b_size -
+						(bh_max - (pos - first));
+				bh->b_blocknr += done >> blkbits;
+				bh->b_size -= done;
+			}
+
+			hole = (rw != WRITE) && !buffer_written(bh);
+			if (hole) {
+				addr = NULL;
+				size = bh->b_size - first;
+			} else {
+				retval = dax_get_addr(bh, &addr, blkbits);
+				if (retval < 0)
+					break;
+				if (buffer_unwritten(bh) || buffer_new(bh))
+					dax_new_buf(addr, retval, first, pos,
+									end);
+				addr += first;
+				size = retval - first;
+			}
+			max = min(pos + size, end);
+		}
+
+		if (rw == WRITE)
+			len = copy_from_iter(addr, max - pos, iter);
+		else if (!hole)
+			len = copy_to_iter(addr, max - pos, iter);
+		else
+			len = iov_iter_zero(max - pos, iter);
+
+		if (!len)
+			break;
+
+		pos += len;
+		addr += len;
+	}
+
+	return (pos == start) ? retval : pos - start;
+}
+
+/**
+ * dax_do_io - Perform I/O to a DAX file
+ * @rw: READ to read or WRITE to write
+ * @iocb: The control block for this I/O
+ * @inode: The file which the I/O is directed at
+ * @iter: The addresses to do I/O from or to
+ * @pos: The file offset where the I/O starts
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ * @end_io: A filesystem callback for I/O completion
+ * @flags: See below
+ *
+ * This function uses the same locking scheme as do_blockdev_direct_IO:
+ * If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the
+ * caller for writes.  For reads, we take and release the i_mutex ourselves.
+ * If DIO_LOCKING is not set, the filesystem takes care of its own locking.
+ * As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O
+ * is in progress.
+ */
+ssize_t dax_do_io(int rw, struct kiocb *iocb, struct inode *inode,
+			struct iov_iter *iter, loff_t pos,
+			get_block_t get_block, dio_iodone_t end_io, int flags)
+{
+	struct buffer_head bh;
+	ssize_t retval = -EINVAL;
+	loff_t end = pos + iov_iter_count(iter);
+
+	memset(&bh, 0, sizeof(bh));
+
+	if ((flags & DIO_LOCKING) && (rw == READ)) {
+		struct address_space *mapping = inode->i_mapping;
+		mutex_lock(&inode->i_mutex);
+		retval = filemap_write_and_wait_range(mapping, pos, end - 1);
+		if (retval) {
+			mutex_unlock(&inode->i_mutex);
+			goto out;
+		}
+	}
+
+	/* Protects against truncate */
+	atomic_inc(&inode->i_dio_count);
+
+	retval = dax_io(rw, inode, iter, pos, end, get_block, &bh);
+
+	if ((flags & DIO_LOCKING) && (rw == READ))
+		mutex_unlock(&inode->i_mutex);
+
+	if ((retval > 0) && end_io)
+		end_io(iocb, pos, retval, bh.b_private);
+
+	inode_dio_done(inode);
+ out:
+	return retval;
+}
+EXPORT_SYMBOL_GPL(dax_do_io);

fs/ext2/file.c

@@ -81,8 +81,10 @@ const struct file_operations ext2_file_operations = {
 #ifdef CONFIG_EXT2_FS_XIP
 const struct file_operations ext2_xip_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= xip_file_read,
-	.write		= xip_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.unlocked_ioctl = ext2_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,

fs/ext2/inode.c

@@ -859,7 +859,12 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block);
+	if (IS_DAX(inode))
+		ret = dax_do_io(rw, iocb, inode, iter, offset, ext2_get_block,
+				NULL, DIO_LOCKING);
+	else
+		ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+					 ext2_get_block);
 	if (ret < 0 && (rw & WRITE))
 		ext2_write_failed(mapping, offset + count);
 	return ret;
@@ -888,6 +893,7 @@ const struct address_space_operations ext2_aops = {
 const struct address_space_operations ext2_aops_xip = {
 	.bmap			= ext2_bmap,
 	.get_xip_mem		= ext2_get_xip_mem,
+	.direct_IO		= ext2_direct_IO,
 };
 
 const struct address_space_operations ext2_nobh_aops = {

include/linux/fs.h

@@ -2587,12 +2587,11 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
+ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
+		loff_t, get_block_t, dio_iodone_t, int flags);
+
 #ifdef CONFIG_FS_XIP
-extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
-			     loff_t *ppos);
 extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
-extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
-			      size_t len, loff_t *ppos);
 extern int xip_truncate_page(struct address_space *mapping, loff_t from);
 #else
 static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
@@ -2756,6 +2755,11 @@ extern int generic_show_options(struct seq_file *m, struct dentry *root);
 extern void save_mount_options(struct super_block *sb, char *options);
 extern void replace_mount_options(struct super_block *sb, char *options);
 
+static inline bool io_is_direct(struct file *filp)
+{
+	return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
 	ino_t res;

mm/filemap.c

@@ -1695,8 +1695,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	loff_t *ppos = &iocb->ki_pos;
 	loff_t pos = *ppos;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (file->f_flags & O_DIRECT) {
+	if (io_is_direct(file)) {
 		struct address_space *mapping = file->f_mapping;
 		struct inode *inode = mapping->host;
 		size_t count = iov_iter_count(iter);
@@ -2584,8 +2583,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (err)
 		goto out;
 
-	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (unlikely(file->f_flags & O_DIRECT)) {
+	if (io_is_direct(file)) {
 		loff_t endbyte;
 
 		written = generic_file_direct_write(iocb, from, pos);