[RFC PATCH v2 09/21] dio: Convert direct_IO to use iov_iter

From: Dave Kleikamp
Date: Fri Mar 30 2012 - 11:45:24 EST

Change the direct_IO aop to take an iov_iter argument rather than an iovec.
This will get passed down through most filesystems so that only the
__blockdev_direct_IO helper need be aware of whether user or kernel memory
is being passed to the function.

Signed-off-by: Dave Kleikamp <dave.kleikamp@xxxxxxxxxx>
Cc: Zach Brown <zab@xxxxxxxxx>
Cc: v9fs-developer@xxxxxxxxxxxxxxxxxxxxx
Cc: linux-btrfs@xxxxxxxxxxxxxxx
Cc: ceph-devel@xxxxxxxxxxxxxxx
Cc: linux-ext4@xxxxxxxxxxxxxxx
Cc: OGAWA Hirofumi <hirofumi@xxxxxxxxxxxxxxxxxx>
Cc: jfs-discussion@xxxxxxxxxxxxxxxxxxxxx
Cc: linux-nfs@xxxxxxxxxxxxxxx
Cc: linux-nilfs@xxxxxxxxxxxxxxx
Cc: ocfs2-devel@xxxxxxxxxxxxxx
Cc: reiserfs-devel@xxxxxxxxxxxxxxx
Cc: xfs@xxxxxxxxxxx
---
Documentation/filesystems/Locking | 4 +--
Documentation/filesystems/vfs.txt | 4 +--
fs/9p/vfs_addr.c | 8 ++---
fs/block_dev.c | 8 ++---
fs/btrfs/inode.c | 70 ++++++++++++++++++++++---------------
fs/ceph/addr.c | 3 +-
fs/direct-io.c | 19 +++++-----
fs/ext2/inode.c | 8 ++---
fs/ext3/inode.c | 15 ++++----
fs/ext4/ext4.h | 3 +-
fs/ext4/indirect.c | 16 ++++-----
fs/ext4/inode.c | 23 ++++++------
fs/fat/inode.c | 10 +++---
fs/gfs2/aops.c | 7 ++--
fs/hfs/inode.c | 7 ++--
fs/hfsplus/inode.c | 6 ++--
fs/jfs/inode.c | 7 ++--
fs/nfs/direct.c | 8 ++---
fs/nilfs2/inode.c | 8 ++---
fs/ocfs2/aops.c | 8 ++---
fs/reiserfs/inode.c | 7 ++--
fs/xfs/xfs_aops.c | 11 +++---
include/linux/fs.h | 18 +++++-----
include/linux/nfs_fs.h | 3 +-
mm/filemap.c | 13 +++++--
25 files changed, 144 insertions(+), 150 deletions(-)

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 4fca82e..1e725f7 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -194,8 +194,8 @@ prototypes:
int (*invalidatepage) (struct page *, unsigned long);
int (*releasepage) (struct page *, int);
void (*freepage)(struct page *);
- int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs);
+ int (*direct_IO)(int, struct kiocb *, struct iov_iter *iter,
+ loff_t offset);
int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
unsigned long *);
int (*migratepage)(struct address_space *, struct page *, struct page *);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 3d9393b..0029302 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -573,8 +573,8 @@ struct address_space_operations {
int (*invalidatepage) (struct page *, unsigned long);
int (*releasepage) (struct page *, int);
void (*freepage)(struct page *);
- ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs);
+ ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter,
+ loff_t offset);
struct page* (*get_xip_page)(struct address_space *, sector_t,
int);
/* migrate the contents of a page to the specified target */
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 0ad61c6..e70f239 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -239,9 +239,8 @@ static int v9fs_launder_page(struct page *page)
* v9fs_direct_IO - 9P address space operation for direct I/O
* @rw: direction (read or write)
* @iocb: target I/O control block
- * @iov: array of vectors that define I/O buffer
+ * @iter: array of vectors that define I/O buffer
* @pos: offset in file to begin the operation
- * @nr_segs: size of iovec array
*
* The presence of v9fs_direct_IO() in the address space ops vector
* allowes open() O_DIRECT flags which would have failed otherwise.
@@ -255,8 +254,7 @@ static int v9fs_launder_page(struct page *page)
*
*/
static ssize_t
-v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t pos, unsigned long nr_segs)
+v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
{
/*
* FIXME
@@ -265,7 +263,7 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
*/
p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n",
iocb->ki_filp->f_path.dentry->d_name.name,
- (long long)pos, nr_segs);
+ (long long)pos, iter->nr_segs);

return -EINVAL;
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 5e9f198..da889ae 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -209,14 +209,14 @@ blkdev_get_blocks(struct inode *inode, sector_t iblock,
}

static ssize_t
-blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;

- return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset,
- nr_segs, blkdev_get_blocks, NULL, NULL, 0);
+ return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter,
+ offset, blkdev_get_blocks, NULL, NULL, 0);
}

int __sync_blockdev(struct block_device *bdev, int wait)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 892b347..2d2bb2a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6139,8 +6139,7 @@ free_ordered:
}

static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
int seg;
int i;
@@ -6154,34 +6153,49 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
goto out;

/* Check the memory alignment. Blocks cannot straddle pages */
- for (seg = 0; seg < nr_segs; seg++) {
- addr = (unsigned long)iov[seg].iov_base;
- size = iov[seg].iov_len;
- end += size;
- if ((addr & blocksize_mask) || (size & blocksize_mask))
- goto out;
+ if (iov_iter_has_iovec(iter)) {
+ const struct iovec *iov = iov_iter_iovec(iter);
+
+ for (seg = 0; seg < iter->nr_segs; seg++) {
+ addr = (unsigned long)iov[seg].iov_base;
+ size = iov[seg].iov_len;
+ end += size;
+ if ((addr & blocksize_mask) || (size & blocksize_mask))
+ goto out;

- /* If this is a write we don't need to check anymore */
- if (rw & WRITE)
- continue;
+ /* If this is a write we don't need to check anymore */
+ if (rw & WRITE)
+ continue;

- /*
- * Check to make sure we don't have duplicate iov_base's in this
- * iovec, if so return EINVAL, otherwise we'll get csum errors
- * when reading back.
- */
- for (i = seg + 1; i < nr_segs; i++) {
- if (iov[seg].iov_base == iov[i].iov_base)
+ /*
+ * Check to make sure we don't have duplicate iov_base's
+ * in this iovec, if so return EINVAL, otherwise we'll
+ * get csum errors when reading back.
+ */
+ for (i = seg + 1; i < iter->nr_segs; i++) {
+ if (iov[seg].iov_base == iov[i].iov_base)
+ goto out;
+ }
+ }
+ } else if (iov_iter_has_bvec(iter)) {
+ struct bio_vec *bvec = iov_iter_bvec(iter);
+
+ for (seg = 0; seg < iter->nr_segs; seg++) {
+ addr = (unsigned long)bvec[seg].bv_offset;
+ size = bvec[seg].bv_len;
+ end += size;
+ if ((addr & blocksize_mask) || (size & blocksize_mask))
goto out;
}
- }
+ } else
+ BUG();
+
retval = 0;
out:
return retval;
}
static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -6191,12 +6205,10 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
ssize_t ret;
int writing = rw & WRITE;
int write_bits = 0;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);

- if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov,
- offset, nr_segs)) {
+ if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset))
return 0;
- }

lockstart = offset;
lockend = offset + count - 1;
@@ -6248,21 +6260,21 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,

ret = __blockdev_direct_IO(rw, iocb, inode,
BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
+ iter, offset, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, 0);

if (ret < 0 && ret != -EIOCBQUEUED) {
clear_extent_bit(&BTRFS_I(inode)->io_tree, offset,
- offset + iov_length(iov, nr_segs) - 1,
+ offset + iov_iter_count(iter) - 1,
EXTENT_LOCKED | write_bits, 1, 0,
&cached_state, GFP_NOFS);
- } else if (ret >= 0 && ret < iov_length(iov, nr_segs)) {
+ } else if (ret >= 0 && ret < iov_iter_count(iter)) {
/*
* We're falling back to buffered, unlock the section we didn't
* do IO on.
*/
clear_extent_bit(&BTRFS_I(inode)->io_tree, offset + ret,
- offset + iov_length(iov, nr_segs) - 1,
+ offset + iov_iter_count(iter) - 1,
EXTENT_LOCKED | write_bits, 1, 0,
&cached_state, GFP_NOFS);
}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 173b1d2..fce6738 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1144,8 +1144,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
* never get called.
*/
static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
- const struct iovec *iov,
- loff_t pos, unsigned long nr_segs)
+ struct iov_iter *iter, loff_t pos)
{
WARN_ON(1);
return -EINVAL;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index d1ee42b..b8bdfba 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1123,9 +1123,9 @@ static int dio_aligned(unsigned long offset, unsigned *blkbits,
*/
static inline ssize_t
do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
- struct block_device *bdev, const struct iovec *iov, loff_t offset,
- unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- dio_submit_t submit_io, int flags)
+ struct block_device *bdev, struct iov_iter *iter, loff_t offset,
+ get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io,
+ int flags)
{
int seg;
size_t size;
@@ -1138,6 +1138,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
unsigned long user_addr;
size_t bytes;
struct buffer_head map_bh = { 0, };
+ const struct iovec *iov = iov_iter_iovec(iter);
+ unsigned long nr_segs = iter->nr_segs;

if (rw & WRITE)
rw = WRITE_ODIRECT;
@@ -1335,9 +1337,9 @@ out:

ssize_t
__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
- struct block_device *bdev, const struct iovec *iov, loff_t offset,
- unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- dio_submit_t submit_io, int flags)
+ struct block_device *bdev, struct iov_iter *iter, loff_t offset,
+ get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io,
+ int flags)
{
/*
* The block device state is needed in the end to finally
@@ -1351,9 +1353,8 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
prefetch(bdev->bd_queue);
prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);

- return do_blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io,
- submit_io, flags);
+ return do_blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset,
+ get_block, end_io, submit_io, flags);
}

EXPORT_SYMBOL(__blockdev_direct_IO);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 740cad8..3c44aab 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -830,18 +830,16 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
}

static ssize_t
-ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
ssize_t ret;

- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- ext2_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block);
if (ret < 0 && (rw & WRITE))
- ext2_write_failed(mapping, offset + iov_length(iov, nr_segs));
+ ext2_write_failed(mapping, offset + iov_iter_count(iter));
return ret;
}

diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2d0afec..c2b49b5 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1863,8 +1863,7 @@ static int ext3_releasepage(struct page *page, gfp_t wait)
* VFS code falls back into buffered path in that case so we are safe.
*/
static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -1872,10 +1871,10 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
handle_t *handle;
ssize_t ret;
int orphan = 0;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
int retries = 0;

- trace_ext3_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+ trace_ext3_direct_IO_enter(inode, offset, count, rw);

if (rw == WRITE) {
loff_t final_size = offset + count;
@@ -1899,15 +1898,14 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
}

retry:
- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- ext3_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block);
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again.
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + count;

if (end > isize)
ext3_truncate_failed_direct_write(inode);
@@ -1950,8 +1948,7 @@ retry:
ret = err;
}
out:
- trace_ext3_direct_IO_exit(inode, offset,
- iov_length(iov, nr_segs), rw, ret);
+ trace_ext3_direct_IO_exit(inode, offset, count, rw, ret);
return ret;
}

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 513004f..b680581 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1903,8 +1903,7 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs);
+ struct iov_iter *iter, loff_t offset);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
extern void ext4_ind_truncate(struct inode *inode);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 830e1b2..d6ee840 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -772,8 +772,7 @@ out:
* VFS code falls back into buffered path in that case so we are safe.
*/
ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -781,7 +780,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
handle_t *handle;
ssize_t ret;
int orphan = 0;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
int retries = 0;

if (rw == WRITE) {
@@ -813,16 +812,15 @@ retry:
mutex_unlock(&inode->i_mutex);
}
ret = __blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iov,
- offset, nr_segs,
- ext4_get_block, NULL, NULL, 0);
+ inode->i_sb->s_bdev, iter,
+ offset, ext4_get_block, NULL, NULL, 0);
} else {
- ret = blockdev_direct_IO(rw, iocb, inode, iov,
- offset, nr_segs, ext4_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter,
+ offset, ext4_get_block);

if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + iov_iter_count(iter);

if (end > isize)
ext4_truncate_failed_write(inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index feaa82f..db86d11 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2888,13 +2888,12 @@ retry:
*
*/
static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);

loff_t final_size = offset + count;
if (rw == WRITE && final_size <= inode->i_size) {
@@ -2935,8 +2934,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
}

ret = __blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iov,
- offset, nr_segs,
+ inode->i_sb->s_bdev, iter,
+ offset,
ext4_get_block_write,
ext4_end_io_dio,
NULL,
@@ -2977,12 +2976,11 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
}

/* for write the the end of file case, we fall back to old way */
- return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+ return ext4_ind_direct_IO(rw, iocb, iter, offset);
}

static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -2994,13 +2992,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
if (ext4_should_journal_data(inode))
return 0;

- trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+ trace_ext4_direct_IO_enter(inode, offset, iov_iter_count(iter), rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
+ ret = ext4_ext_direct_IO(rw, iocb, iter, offset);
else
- ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
- trace_ext4_direct_IO_exit(inode, offset,
- iov_length(iov, nr_segs), rw, ret);
+ ret = ext4_ind_direct_IO(rw, iocb, iter, offset);
+ trace_ext4_direct_IO_exit(inode, offset, iov_iter_count(iter), rw, ret);
return ret;
}

diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 3ab8410..22cfb80 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -184,8 +184,7 @@ static int fat_write_end(struct file *file, struct address_space *mapping,
}

static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -202,7 +201,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
*
* Return 0, and fallback to normal buffered write.
*/
- loff_t size = offset + iov_length(iov, nr_segs);
+ loff_t size = offset + iov_iter_count(iter);
if (MSDOS_I(inode)->mmu_private < size)
return 0;
}
@@ -211,10 +210,9 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
* FAT need to use the DIO_LOCKING for avoiding the race
* condition of fat_get_block() and ->truncate().
*/
- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- fat_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, fat_get_block);
if (ret < 0 && (rw & WRITE))
- fat_write_failed(mapping, offset + iov_length(iov, nr_segs));
+ fat_write_failed(mapping, offset + iov_iter_count(iter));

return ret;
}
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 501e5cb..cb0c19f 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -1007,8 +1007,7 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)


static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -1032,8 +1031,8 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */

- rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
- offset, nr_segs, gfs2_get_block_direct,
+ rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
+ offset, gfs2_get_block_direct,
NULL, NULL, 0);
out:
gfs2_glock_dq_m(1, &gh);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 737dbeb..96650e7 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -117,14 +117,13 @@ static int hfs_releasepage(struct page *page, gfp_t mask)
}

static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
ssize_t ret;

- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- hfs_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, hfs_get_block);

/*
* In case of error extending write may have instantiated a few
@@ -132,7 +131,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + iov_iter_count(iter);

if (end > isize)
vmtruncate(inode, isize);
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 6643b24..76e3f8e 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -113,13 +113,13 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
}

static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
ssize_t ret;

- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
hfsplus_get_block);

/*
@@ -128,7 +128,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + iov_iter_count(iter);

if (end > isize)
vmtruncate(inode, isize);
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 77b69b2..3dabfc9 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -323,14 +323,13 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block)
}

static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;

- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- jfs_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, jfs_get_block);

/*
* In case of error extending write may have instantiated a few
@@ -338,7 +337,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + iov_iter_count(iter);

if (end > isize)
vmtruncate(inode, isize);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 1940f1a..9d0f3c2 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -107,20 +107,20 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
* nfs_direct_IO - NFS address space operation for direct I/O
* @rw: direction (read or write)
* @iocb: target I/O control block
- * @iov: array of vectors that define I/O buffer
+ * @iter: array of vectors that define I/O buffer
* @pos: offset in file to begin the operation
- * @nr_segs: size of iovec array
*
* The presence of this routine in the address space ops vector means
* the NFS client supports direct I/O. However, we shunt off direct
* read and write requests before the VFS gets them, so this method
* should never be called.
*/
-ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
+ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t pos)
{
dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
iocb->ki_filp->f_path.dentry->d_name.name,
- (long long) pos, nr_segs);
+ (long long) pos, iter->nr_segs);

return -EINVAL;
}
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 8f7b95a..882159f 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -248,8 +248,8 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
}

static ssize_t
-nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -259,7 +259,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
return 0;

/* Needs synchronization with the cleaner */
- size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+ size = blockdev_direct_IO(rw, iocb, inode, iter, offset,
nilfs_get_block);

/*
@@ -268,7 +268,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
*/
if (unlikely((rw & WRITE) && size < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + iov_iter_count(iter);

if (end > isize)
vmtruncate(inode, isize);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 78b68af..f4f2c1e 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -621,9 +621,8 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)

static ssize_t ocfs2_direct_IO(int rw,
struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
@@ -640,8 +639,7 @@ static ssize_t ocfs2_direct_IO(int rw,
return 0;

return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
- iov, offset, nr_segs,
- ocfs2_direct_IO_get_blocks,
+ iter, offset, ocfs2_direct_IO_get_blocks,
ocfs2_dio_end_io, NULL, 0);
}

diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 9e8cd5a..3142d40 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3066,14 +3066,13 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags)
/* We thank Mingming Cao for helping us understand in great detail what
to do in this section of the code. */
static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;

- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
reiserfs_get_blocks_direct_io);

/*
@@ -3082,7 +3081,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + iov_iter_count(iter);

if (end > isize)
vmtruncate(inode, isize);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 74b9baf..053a213 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1308,9 +1308,8 @@ STATIC ssize_t
xfs_vm_direct_IO(
int rw,
struct kiocb *iocb,
- const struct iovec *iov,
- loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter,
+ loff_t offset)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
struct block_device *bdev = xfs_find_bdev_for_inode(inode);
@@ -1319,15 +1318,13 @@ xfs_vm_direct_IO(
if (rw & WRITE) {
iocb->private = xfs_alloc_ioend(inode, IO_DIRECT);

- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset,
xfs_get_blocks_direct,
xfs_end_io_direct_write, NULL, 0);
if (ret != -EIOCBQUEUED && iocb->private)
xfs_destroy_ioend(iocb->private);
} else {
- ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
- offset, nr_segs,
+ ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset,
xfs_get_blocks_direct,
NULL, NULL, 0);
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5b69020..86ac246 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -690,8 +690,8 @@ struct address_space_operations {
void (*invalidatepage) (struct page *, unsigned long);
int (*releasepage) (struct page *, gfp_t);
void (*freepage)(struct page *);
- ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs);
+ ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter,
+ loff_t offset);
int (*get_xip_mem)(struct address_space *, pgoff_t, int,
void **, unsigned long *);
/*
@@ -2518,16 +2518,16 @@ void inode_dio_wait(struct inode *inode);
void inode_dio_done(struct inode *inode);

ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
- struct block_device *bdev, const struct iovec *iov, loff_t offset,
- unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- dio_submit_t submit_io, int flags);
+ struct block_device *bdev, struct iov_iter *iter, loff_t offset,
+ get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io,
+ int flags);

static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
- struct inode *inode, const struct iovec *iov, loff_t offset,
- unsigned long nr_segs, get_block_t get_block)
+ struct inode *inode, struct iov_iter *iter, loff_t offset,
+ get_block_t get_block)
{
- return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
- offset, nr_segs, get_block, NULL, NULL,
+ return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
+ offset, get_block, NULL, NULL,
DIO_LOCKING | DIO_SKIP_HOLES);
}
#else
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 8c29950..50fd8ca 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -451,8 +451,7 @@ extern int nfs3_removexattr (struct dentry *, const char *name);
/*
* linux/fs/nfs/direct.c
*/
-extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
- unsigned long);
+extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t);
extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
const struct iovec *iov, unsigned long nr_segs,
loff_t pos);
diff --git a/mm/filemap.c b/mm/filemap.c
index 0533a71..b6f45b4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1418,14 +1418,18 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
goto out; /* skip atime */
size = i_size_read(inode);
if (pos < size) {
+ size_t bytes = iov_length(iov, nr_segs);
retval = filemap_write_and_wait_range(mapping, pos,
- pos + iov_length(iov, nr_segs) - 1);
+ pos + bytes - 1);
if (!retval) {
struct blk_plug plug;
+ struct iov_iter iter;
+
+ iov_iter_init(&iter, iov, nr_segs, bytes, 0);

blk_start_plug(&plug);
retval = mapping->a_ops->direct_IO(READ, iocb,
- iov, pos, nr_segs);
+ &iter, pos);
blk_finish_plug(&plug);
}
if (retval > 0) {
@@ -2126,6 +2130,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
ssize_t written;
size_t write_len;
pgoff_t end;
+ struct iov_iter iter;

if (count != ocount)
*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
@@ -2157,7 +2162,9 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
}
}

- written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs);
+ iov_iter_init(&iter, iov, *nr_segs, write_len, 0);
+
+ written = mapping->a_ops->direct_IO(WRITE, iocb, &iter, pos);

/*
* Finally, try again to invalidate clean pages which might have been
--
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/