linux/fs/read_write.c
Greg Kroah-Hartman b24413180f License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.

By default all files without license information are under the default
license of the kernel, which is GPL version 2.

Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier.  The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.

This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.

How this work was done:

Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
 - file had no licensing information it it.
 - file was a */uapi/* one with no licensing information in it,
 - file was a */uapi/* one with existing licensing information,

Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.

The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne.  Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.

The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed.  Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.

Criteria used to select files for SPDX license identifier tagging was:
 - Files considered eligible had to be source code files.
 - Make and config files were included as candidates if they contained >5
   lines of source
 - File already had some variant of a license header in it (even if <5
   lines).

All documentation files were explicitly excluded.

The following heuristics were used to determine which SPDX license
identifiers to apply.

 - when both scanners couldn't find any license traces, file was
   considered to have no license information in it, and the top level
   COPYING file license applied.

   For non */uapi/* files that summary was:

   SPDX license identifier                            # files
   ---------------------------------------------------|-------
   GPL-2.0                                              11139

   and resulted in the first patch in this series.

   If that file was a */uapi/* path one, it was "GPL-2.0 WITH
   Linux-syscall-note" otherwise it was "GPL-2.0".  Results of that was:

   SPDX license identifier                            # files
   ---------------------------------------------------|-------
   GPL-2.0 WITH Linux-syscall-note                        930

   and resulted in the second patch in this series.

 - if a file had some form of licensing information in it, and was one
   of the */uapi/* ones, it was denoted with the Linux-syscall-note if
   any GPL family license was found in the file or had no licensing in
   it (per prior point).  Results summary:

   SPDX license identifier                            # files
   ---------------------------------------------------|------
   GPL-2.0 WITH Linux-syscall-note                       270
   GPL-2.0+ WITH Linux-syscall-note                      169
   ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause)    21
   ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)    17
   LGPL-2.1+ WITH Linux-syscall-note                      15
   GPL-1.0+ WITH Linux-syscall-note                       14
   ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause)    5
   LGPL-2.0+ WITH Linux-syscall-note                       4
   LGPL-2.1 WITH Linux-syscall-note                        3
   ((GPL-2.0 WITH Linux-syscall-note) OR MIT)              3
   ((GPL-2.0 WITH Linux-syscall-note) AND MIT)             1

   and that resulted in the third patch in this series.

 - when the two scanners agreed on the detected license(s), that became
   the concluded license(s).

 - when there was disagreement between the two scanners (one detected a
   license but the other didn't, or they both detected different
   licenses) a manual inspection of the file occurred.

 - In most cases a manual inspection of the information in the file
   resulted in a clear resolution of the license that should apply (and
   which scanner probably needed to revisit its heuristics).

 - When it was not immediately clear, the license identifier was
   confirmed with lawyers working with the Linux Foundation.

 - If there was any question as to the appropriate license identifier,
   the file was flagged for further research and to be revisited later
   in time.

In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.

Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights.  The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.

Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.

In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.

Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
 - a full scancode scan run, collecting the matched texts, detected
   license ids and scores
 - reviewing anything where there was a license detected (about 500+
   files) to ensure that the applied SPDX license was correct
 - reviewing anything where there was no detection but the patch license
   was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
   SPDX license was correct

This produced a worksheet with 20 files needing minor correction.  This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.

These .csv files were then reviewed by Greg.  Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected.  This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.)  Finally Greg ran the script using the .csv files to
generate the patches.

Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-02 11:10:55 +01:00

2066 lines
47 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/read_write.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/slab.h>
#include <linux/stat.h>
#include <linux/sched/xacct.h>
#include <linux/fcntl.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/fsnotify.h>
#include <linux/security.h>
#include <linux/export.h>
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/fs.h>
#include "internal.h"
#include <linux/uaccess.h>
#include <asm/unistd.h>
const struct file_operations generic_ro_fops = {
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
.mmap = generic_file_readonly_mmap,
.splice_read = generic_file_splice_read,
};
EXPORT_SYMBOL(generic_ro_fops);
static inline bool unsigned_offsets(struct file *file)
{
return file->f_mode & FMODE_UNSIGNED_OFFSET;
}
/**
* vfs_setpos - update the file offset for lseek
* @file: file structure in question
* @offset: file offset to seek to
* @maxsize: maximum file size
*
* This is a low-level filesystem helper for updating the file offset to
* the value specified by @offset if the given offset is valid and it is
* not equal to the current file offset.
*
* Return the specified offset on success and -EINVAL on invalid offset.
*/
loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
{
if (offset < 0 && !unsigned_offsets(file))
return -EINVAL;
if (offset > maxsize)
return -EINVAL;
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
return offset;
}
EXPORT_SYMBOL(vfs_setpos);
/**
* generic_file_llseek_size - generic llseek implementation for regular files
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
* @size: max size of this file in file system
* @eof: offset used for SEEK_END position
*
* This is a variant of generic_file_llseek that allows passing in a custom
* maximum file size and a custom EOF position, for e.g. hashed directories
*
* Synchronization:
* SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms)
* SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes.
* read/writes behave like SEEK_SET against seeks.
*/
loff_t
generic_file_llseek_size(struct file *file, loff_t offset, int whence,
loff_t maxsize, loff_t eof)
{
switch (whence) {
case SEEK_END:
offset += eof;
break;
case SEEK_CUR:
/*
* Here we special-case the lseek(fd, 0, SEEK_CUR)
* position-querying operation. Avoid rewriting the "same"
* f_pos value back to the file because a concurrent read(),
* write() or lseek() might have altered it
*/
if (offset == 0)
return file->f_pos;
/*
* f_lock protects against read/modify/write race with other
* SEEK_CURs. Note that parallel writes and reads behave
* like SEEK_SET.
*/
spin_lock(&file->f_lock);
offset = vfs_setpos(file, file->f_pos + offset, maxsize);
spin_unlock(&file->f_lock);
return offset;
case SEEK_DATA:
/*
* In the generic case the entire file is data, so as long as
* offset isn't at the end of the file then the offset is data.
*/
if ((unsigned long long)offset >= eof)
return -ENXIO;
break;
case SEEK_HOLE:
/*
* There is a virtual hole at the end of the file, so as long as
* offset isn't i_size or larger, return i_size.
*/
if ((unsigned long long)offset >= eof)
return -ENXIO;
offset = eof;
break;
}
return vfs_setpos(file, offset, maxsize);
}
EXPORT_SYMBOL(generic_file_llseek_size);
/**
* generic_file_llseek - generic llseek implementation for regular files
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
*
* This is a generic implemenation of ->llseek useable for all normal local
* filesystems. It just updates the file offset to the value specified by
* @offset and @whence.
*/
loff_t generic_file_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
return generic_file_llseek_size(file, offset, whence,
inode->i_sb->s_maxbytes,
i_size_read(inode));
}
EXPORT_SYMBOL(generic_file_llseek);
/**
* fixed_size_llseek - llseek implementation for fixed-sized devices
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
* @size: size of the file
*
*/
loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size)
{
switch (whence) {
case SEEK_SET: case SEEK_CUR: case SEEK_END:
return generic_file_llseek_size(file, offset, whence,
size, size);
default:
return -EINVAL;
}
}
EXPORT_SYMBOL(fixed_size_llseek);
/**
* no_seek_end_llseek - llseek implementation for fixed-sized devices
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
*
*/
loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence)
{
switch (whence) {
case SEEK_SET: case SEEK_CUR:
return generic_file_llseek_size(file, offset, whence,
OFFSET_MAX, 0);
default:
return -EINVAL;
}
}
EXPORT_SYMBOL(no_seek_end_llseek);
/**
* no_seek_end_llseek_size - llseek implementation for fixed-sized devices
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
* @size: maximal offset allowed
*
*/
loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size)
{
switch (whence) {
case SEEK_SET: case SEEK_CUR:
return generic_file_llseek_size(file, offset, whence,
size, 0);
default:
return -EINVAL;
}
}
EXPORT_SYMBOL(no_seek_end_llseek_size);
/**
* noop_llseek - No Operation Performed llseek implementation
* @file: file structure to seek on
* @offset: file offset to seek to
* @whence: type of seek
*
* This is an implementation of ->llseek useable for the rare special case when
* userspace expects the seek to succeed but the (device) file is actually not
* able to perform the seek. In this case you use noop_llseek() instead of
* falling back to the default implementation of ->llseek.
*/
loff_t noop_llseek(struct file *file, loff_t offset, int whence)
{
return file->f_pos;
}
EXPORT_SYMBOL(noop_llseek);
loff_t no_llseek(struct file *file, loff_t offset, int whence)
{
return -ESPIPE;
}
EXPORT_SYMBOL(no_llseek);
loff_t default_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file_inode(file);
loff_t retval;
inode_lock(inode);
switch (whence) {
case SEEK_END:
offset += i_size_read(inode);
break;
case SEEK_CUR:
if (offset == 0) {
retval = file->f_pos;
goto out;
}
offset += file->f_pos;
break;
case SEEK_DATA:
/*
* In the generic case the entire file is data, so as
* long as offset isn't at the end of the file then the
* offset is data.
*/
if (offset >= inode->i_size) {
retval = -ENXIO;
goto out;
}
break;
case SEEK_HOLE:
/*
* There is a virtual hole at the end of the file, so
* as long as offset isn't i_size or larger, return
* i_size.
*/
if (offset >= inode->i_size) {
retval = -ENXIO;
goto out;
}
offset = inode->i_size;
break;
}
retval = -EINVAL;
if (offset >= 0 || unsigned_offsets(file)) {
if (offset != file->f_pos) {
file->f_pos = offset;
file->f_version = 0;
}
retval = offset;
}
out:
inode_unlock(inode);
return retval;
}
EXPORT_SYMBOL(default_llseek);
loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
{
loff_t (*fn)(struct file *, loff_t, int);
fn = no_llseek;
if (file->f_mode & FMODE_LSEEK) {
if (file->f_op->llseek)
fn = file->f_op->llseek;
}
return fn(file, offset, whence);
}
EXPORT_SYMBOL(vfs_llseek);
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
struct fd f = fdget_pos(fd);
if (!f.file)
return -EBADF;
retval = -EINVAL;
if (whence <= SEEK_MAX) {
loff_t res = vfs_llseek(f.file, offset, whence);
retval = res;
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
fdput_pos(f);
return retval;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence)
{
return sys_lseek(fd, offset, whence);
}
#endif
#ifdef __ARCH_WANT_SYS_LLSEEK
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
unsigned long, offset_low, loff_t __user *, result,
unsigned int, whence)
{
int retval;
struct fd f = fdget_pos(fd);
loff_t offset;
if (!f.file)
return -EBADF;
retval = -EINVAL;
if (whence > SEEK_MAX)
goto out_putf;
offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
whence);
retval = (int)offset;
if (offset >= 0) {
retval = -EFAULT;
if (!copy_to_user(result, &offset, sizeof(offset)))
retval = 0;
}
out_putf:
fdput_pos(f);
return retval;
}
#endif
int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
{
struct inode *inode;
loff_t pos;
int retval = -EINVAL;
inode = file_inode(file);
if (unlikely((ssize_t) count < 0))
return retval;
pos = *ppos;
if (unlikely(pos < 0)) {
if (!unsigned_offsets(file))
return retval;
if (count >= -pos) /* both values are in 0..LLONG_MAX */
return -EOVERFLOW;
} else if (unlikely((loff_t) (pos + count) < 0)) {
if (!unsigned_offsets(file))
return retval;
}
if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
retval = locks_mandatory_area(inode, file, pos, pos + count - 1,
read_write == READ ? F_RDLCK : F_WRLCK);
if (retval < 0)
return retval;
}
return security_file_permission(file,
read_write == READ ? MAY_READ : MAY_WRITE);
}
static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = buf, .iov_len = len };
struct kiocb kiocb;
struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
iov_iter_init(&iter, READ, &iov, 1, len);
ret = call_read_iter(filp, &kiocb, &iter);
BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
}
ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
loff_t *pos)
{
if (file->f_op->read)
return file->f_op->read(file, buf, count, pos);
else if (file->f_op->read_iter)
return new_sync_read(file, buf, count, pos);
else
return -EINVAL;
}
ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
{
mm_segment_t old_fs;
ssize_t result;
old_fs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
result = vfs_read(file, (void __user *)buf, count, pos);
set_fs(old_fs);
return result;
}
EXPORT_SYMBOL(kernel_read);
ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
if (!(file->f_mode & FMODE_READ))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_WRITE, buf, count)))
return -EFAULT;
ret = rw_verify_area(READ, file, pos, count);
if (!ret) {
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
ret = __vfs_read(file, buf, count, pos);
if (ret > 0) {
fsnotify_access(file);
add_rchar(current, ret);
}
inc_syscr(current);
}
return ret;
}
static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
struct kiocb kiocb;
struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
iov_iter_init(&iter, WRITE, &iov, 1, len);
ret = call_write_iter(filp, &kiocb, &iter);
BUG_ON(ret == -EIOCBQUEUED);
if (ret > 0)
*ppos = kiocb.ki_pos;
return ret;
}
ssize_t __vfs_write(struct file *file, const char __user *p, size_t count,
loff_t *pos)
{
if (file->f_op->write)
return file->f_op->write(file, p, count, pos);
else if (file->f_op->write_iter)
return new_sync_write(file, p, count, pos);
else
return -EINVAL;
}
ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
{
mm_segment_t old_fs;
const char __user *p;
ssize_t ret;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
old_fs = get_fs();
set_fs(get_ds());
p = (__force const char __user *)buf;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
ret = __vfs_write(file, p, count, pos);
set_fs(old_fs);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
return ret;
}
EXPORT_SYMBOL(__kernel_write);
ssize_t kernel_write(struct file *file, const void *buf, size_t count,
loff_t *pos)
{
mm_segment_t old_fs;
ssize_t res;
old_fs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
res = vfs_write(file, (__force const char __user *)buf, count, pos);
set_fs(old_fs);
return res;
}
EXPORT_SYMBOL(kernel_write);
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
if (!ret) {
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
file_start_write(file);
ret = __vfs_write(file, buf, count, pos);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
file_end_write(file);
}
return ret;
}
static inline loff_t file_pos_read(struct file *file)
{
return file->f_pos;
}
static inline void file_pos_write(struct file *file, loff_t pos)
{
file->f_pos = pos;
}
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_read(f.file, buf, count, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
}
return ret;
}
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_write(f.file, buf, count, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
}
return ret;
}
SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf,
size_t, count, loff_t, pos)
{
struct fd f;
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
ret = vfs_read(f.file, buf, count, &pos);
fdput(f);
}
return ret;
}
SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
size_t, count, loff_t, pos)
{
struct fd f;
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
ret = vfs_write(f.file, buf, count, &pos);
fdput(f);
}
return ret;
}
/*
* Reduce an iovec's length in-place. Return the resulting number of segments
*/
unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
{
unsigned long seg = 0;
size_t len = 0;
while (seg < nr_segs) {
seg++;
if (len + iov->iov_len >= to) {
iov->iov_len = to - len;
break;
}
len += iov->iov_len;
iov++;
}
return seg;
}
EXPORT_SYMBOL(iov_shorten);
static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
loff_t *ppos, int type, rwf_t flags)
{
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
ret = kiocb_set_rw_flags(&kiocb, flags);
if (ret)
return ret;
kiocb.ki_pos = *ppos;
if (type == READ)
ret = call_read_iter(filp, &kiocb, iter);
else
ret = call_write_iter(filp, &kiocb, iter);
BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
}
/* Do it by hand, with file-ops */
static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
loff_t *ppos, int type, rwf_t flags)
{
ssize_t ret = 0;
if (flags & ~RWF_HIPRI)
return -EOPNOTSUPP;
while (iov_iter_count(iter)) {
struct iovec iovec = iov_iter_iovec(iter);
ssize_t nr;
if (type == READ) {
nr = filp->f_op->read(filp, iovec.iov_base,
iovec.iov_len, ppos);
} else {
nr = filp->f_op->write(filp, iovec.iov_base,
iovec.iov_len, ppos);
}
if (nr < 0) {
if (!ret)
ret = nr;
break;
}
ret += nr;
if (nr != iovec.iov_len)
break;
iov_iter_advance(iter, nr);
}
return ret;
}
/* A write operation does a read from user space and vice versa */
#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
/**
* rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
* into the kernel and check that it is valid.
*
* @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
* @uvector: Pointer to the userspace array.
* @nr_segs: Number of elements in userspace array.
* @fast_segs: Number of elements in @fast_pointer.
* @fast_pointer: Pointer to (usually small on-stack) kernel array.
* @ret_pointer: (output parameter) Pointer to a variable that will point to
* either @fast_pointer, a newly allocated kernel array, or NULL,
* depending on which array was used.
*
* This function copies an array of &struct iovec of @nr_segs from
* userspace into the kernel and checks that each element is valid (e.g.
* it does not point to a kernel address or cause overflow by being too
* large, etc.).
*
* As an optimization, the caller may provide a pointer to a small
* on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
* (the size of this array, or 0 if unused, should be given in @fast_segs).
*
* @ret_pointer will always point to the array that was used, so the
* caller must take care not to call kfree() on it e.g. in case the
* @fast_pointer array was used and it was allocated on the stack.
*
* Return: The total number of bytes covered by the iovec array on success
* or a negative error code on error.
*/
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
unsigned long nr_segs, unsigned long fast_segs,
struct iovec *fast_pointer,
struct iovec **ret_pointer)
{
unsigned long seg;
ssize_t ret;
struct iovec *iov = fast_pointer;
/*
* SuS says "The readv() function *may* fail if the iovcnt argument
* was less than or equal to 0, or greater than {IOV_MAX}. Linux has
* traditionally returned zero for zero segments, so...
*/
if (nr_segs == 0) {
ret = 0;
goto out;
}
/*
* First get the "struct iovec" from user memory and
* verify all the pointers
*/
if (nr_segs > UIO_MAXIOV) {
ret = -EINVAL;
goto out;
}
if (nr_segs > fast_segs) {
iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
if (iov == NULL) {
ret = -ENOMEM;
goto out;
}
}
if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
ret = -EFAULT;
goto out;
}
/*
* According to the Single Unix Specification we should return EINVAL
* if an element length is < 0 when cast to ssize_t or if the
* total length would overflow the ssize_t return value of the
* system call.
*
* Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
* overflow case.
*/
ret = 0;
for (seg = 0; seg < nr_segs; seg++) {
void __user *buf = iov[seg].iov_base;
ssize_t len = (ssize_t)iov[seg].iov_len;
/* see if we we're about to use an invalid len or if
* it's about to overflow ssize_t */
if (len < 0) {
ret = -EINVAL;
goto out;
}
if (type >= 0
&& unlikely(!access_ok(vrfy_dir(type), buf, len))) {
ret = -EFAULT;
goto out;
}
if (len > MAX_RW_COUNT - ret) {
len = MAX_RW_COUNT - ret;
iov[seg].iov_len = len;
}
ret += len;
}
out:
*ret_pointer = iov;
return ret;
}
#ifdef CONFIG_COMPAT
ssize_t compat_rw_copy_check_uvector(int type,
const struct compat_iovec __user *uvector, unsigned long nr_segs,
unsigned long fast_segs, struct iovec *fast_pointer,
struct iovec **ret_pointer)
{
compat_ssize_t tot_len;
struct iovec *iov = *ret_pointer = fast_pointer;
ssize_t ret = 0;
int seg;
/*
* SuS says "The readv() function *may* fail if the iovcnt argument
* was less than or equal to 0, or greater than {IOV_MAX}. Linux has
* traditionally returned zero for zero segments, so...
*/
if (nr_segs == 0)
goto out;
ret = -EINVAL;
if (nr_segs > UIO_MAXIOV)
goto out;
if (nr_segs > fast_segs) {
ret = -ENOMEM;
iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
if (iov == NULL)
goto out;
}
*ret_pointer = iov;
ret = -EFAULT;
if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
goto out;
/*
* Single unix specification:
* We should -EINVAL if an element length is not >= 0 and fitting an
* ssize_t.
*
* In Linux, the total length is limited to MAX_RW_COUNT, there is
* no overflow possibility.
*/
tot_len = 0;
ret = -EINVAL;
for (seg = 0; seg < nr_segs; seg++) {
compat_uptr_t buf;
compat_ssize_t len;
if (__get_user(len, &uvector->iov_len) ||
__get_user(buf, &uvector->iov_base)) {
ret = -EFAULT;
goto out;
}
if (len < 0) /* size_t not fitting in compat_ssize_t .. */
goto out;
if (type >= 0 &&
!access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
ret = -EFAULT;
goto out;
}
if (len > MAX_RW_COUNT - tot_len)
len = MAX_RW_COUNT - tot_len;
tot_len += len;
iov->iov_base = compat_ptr(buf);
iov->iov_len = (compat_size_t) len;
uvector++;
iov++;
}
ret = tot_len;
out:
return ret;
}
#endif
static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
loff_t *pos, rwf_t flags)
{
size_t tot_len;
ssize_t ret = 0;
if (!(file->f_mode & FMODE_READ))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
tot_len = iov_iter_count(iter);
if (!tot_len)
goto out;
ret = rw_verify_area(READ, file, pos, tot_len);
if (ret < 0)
return ret;
if (file->f_op->read_iter)
ret = do_iter_readv_writev(file, iter, pos, READ, flags);
else
ret = do_loop_readv_writev(file, iter, pos, READ, flags);
out:
if (ret >= 0)
fsnotify_access(file);
return ret;
}
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags)
{
if (!file->f_op->read_iter)
return -EINVAL;
return do_iter_read(file, iter, ppos, flags);
}
EXPORT_SYMBOL(vfs_iter_read);
static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
loff_t *pos, rwf_t flags)
{
size_t tot_len;
ssize_t ret = 0;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
tot_len = iov_iter_count(iter);
if (!tot_len)
return 0;
ret = rw_verify_area(WRITE, file, pos, tot_len);
if (ret < 0)
return ret;
if (file->f_op->write_iter)
ret = do_iter_readv_writev(file, iter, pos, WRITE, flags);
else
ret = do_loop_readv_writev(file, iter, pos, WRITE, flags);
if (ret > 0)
fsnotify_modify(file);
return ret;
}
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags)
{
if (!file->f_op->write_iter)
return -EINVAL;
return do_iter_write(file, iter, ppos, flags);
}
EXPORT_SYMBOL(vfs_iter_write);
ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
if (ret >= 0) {
ret = do_iter_read(file, &iter, pos, flags);
kfree(iov);
}
return ret;
}
static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
if (ret >= 0) {
file_start_write(file);
ret = do_iter_write(file, &iter, pos, flags);
file_end_write(file);
kfree(iov);
}
return ret;
}
static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, rwf_t flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_readv(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
}
if (ret > 0)
add_rchar(current, ret);
inc_syscr(current);
return ret;
}
static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, rwf_t flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_writev(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
}
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
{
#define HALF_LONG_BITS (BITS_PER_LONG / 2)
return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
}
static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, loff_t pos, rwf_t flags)
{
struct fd f;
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
ret = vfs_readv(f.file, vec, vlen, &pos, flags);
fdput(f);
}
if (ret > 0)
add_rchar(current, ret);
inc_syscr(current);
return ret;
}
static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, loff_t pos, rwf_t flags)
{
struct fd f;
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
ret = vfs_writev(f.file, vec, vlen, &pos, flags);
fdput(f);
}
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
return do_readv(fd, vec, vlen, 0);
}
SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
return do_writev(fd, vec, vlen, 0);
}
SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
{
loff_t pos = pos_from_hilo(pos_h, pos_l);
return do_preadv(fd, vec, vlen, pos, 0);
}
SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
rwf_t, flags)
{
loff_t pos = pos_from_hilo(pos_h, pos_l);
if (pos == -1)
return do_readv(fd, vec, vlen, flags);
return do_preadv(fd, vec, vlen, pos, flags);
}
SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
{
loff_t pos = pos_from_hilo(pos_h, pos_l);
return do_pwritev(fd, vec, vlen, pos, 0);
}
SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
rwf_t, flags)
{
loff_t pos = pos_from_hilo(pos_h, pos_l);
if (pos == -1)
return do_writev(fd, vec, vlen, flags);
return do_pwritev(fd, vec, vlen, pos, flags);
}
#ifdef CONFIG_COMPAT
static size_t compat_readv(struct file *file,
const struct compat_iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter);
if (ret >= 0) {
ret = do_iter_read(file, &iter, pos, flags);
kfree(iov);
}
if (ret > 0)
add_rchar(current, ret);
inc_syscr(current);
return ret;
}
static size_t do_compat_readv(compat_ulong_t fd,
const struct compat_iovec __user *vec,
compat_ulong_t vlen, rwf_t flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
ret = compat_readv(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
f.file->f_pos = pos;
fdput_pos(f);
return ret;
}
COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen)
{
return do_compat_readv(fd, vec, vlen, 0);
}
static long do_compat_preadv64(unsigned long fd,
const struct compat_iovec __user *vec,
unsigned long vlen, loff_t pos, rwf_t flags)
{
struct fd f;
ssize_t ret;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (!f.file)
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
ret = compat_readv(f.file, vec, vlen, &pos, flags);
fdput(f);
return ret;
}
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos)
{
return do_compat_preadv64(fd, vec, vlen, pos, 0);
}
#endif
COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
return do_compat_preadv64(fd, vec, vlen, pos, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos, rwf_t, flags)
{
return do_compat_preadv64(fd, vec, vlen, pos, flags);
}
#endif
COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
rwf_t, flags)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
if (pos == -1)
return do_compat_readv(fd, vec, vlen, flags);
return do_compat_preadv64(fd, vec, vlen, pos, flags);
}
static size_t compat_writev(struct file *file,
const struct compat_iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter);
if (ret >= 0) {
file_start_write(file);
ret = do_iter_write(file, &iter, pos, flags);
file_end_write(file);
kfree(iov);
}
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
static size_t do_compat_writev(compat_ulong_t fd,
const struct compat_iovec __user* vec,
compat_ulong_t vlen, rwf_t flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
ret = compat_writev(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
f.file->f_pos = pos;
fdput_pos(f);
return ret;
}
COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
const struct compat_iovec __user *, vec,
compat_ulong_t, vlen)
{
return do_compat_writev(fd, vec, vlen, 0);
}
static long do_compat_pwritev64(unsigned long fd,
const struct compat_iovec __user *vec,
unsigned long vlen, loff_t pos, rwf_t flags)
{
struct fd f;
ssize_t ret;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (!f.file)
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
ret = compat_writev(f.file, vec, vlen, &pos, flags);
fdput(f);
return ret;
}
#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos)
{
return do_compat_pwritev64(fd, vec, vlen, pos, 0);
}
#endif
COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
return do_compat_pwritev64(fd, vec, vlen, pos, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos, rwf_t, flags)
{
return do_compat_pwritev64(fd, vec, vlen, pos, flags);
}
#endif
COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
if (pos == -1)
return do_compat_writev(fd, vec, vlen, flags);
return do_compat_pwritev64(fd, vec, vlen, pos, flags);
}
#endif
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
size_t count, loff_t max)
{
struct fd in, out;
struct inode *in_inode, *out_inode;
loff_t pos;
loff_t out_pos;
ssize_t retval;
int fl;
/*
* Get input file, and verify that it is ok..
*/
retval = -EBADF;
in = fdget(in_fd);
if (!in.file)
goto out;
if (!(in.file->f_mode & FMODE_READ))
goto fput_in;
retval = -ESPIPE;
if (!ppos) {
pos = in.file->f_pos;
} else {
pos = *ppos;
if (!(in.file->f_mode & FMODE_PREAD))
goto fput_in;
}
retval = rw_verify_area(READ, in.file, &pos, count);
if (retval < 0)
goto fput_in;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
/*
* Get output file, and verify that it is ok..
*/
retval = -EBADF;
out = fdget(out_fd);
if (!out.file)
goto fput_in;
if (!(out.file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
in_inode = file_inode(in.file);
out_inode = file_inode(out.file);
out_pos = out.file->f_pos;
retval = rw_verify_area(WRITE, out.file, &out_pos, count);
if (retval < 0)
goto fput_out;
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
if (unlikely(pos + count > max)) {
retval = -EOVERFLOW;
if (pos >= max)
goto fput_out;
count = max - pos;
}
fl = 0;
#if 0
/*
* We need to debate whether we can enable this or not. The
* man page documents EAGAIN return for the output at least,
* and the application is arguably buggy if it doesn't expect
* EAGAIN on a non-blocking file descriptor.
*/
if (in.file->f_flags & O_NONBLOCK)
fl = SPLICE_F_NONBLOCK;
#endif
file_start_write(out.file);
retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl);
file_end_write(out.file);
if (retval > 0) {
add_rchar(current, retval);
add_wchar(current, retval);
fsnotify_access(in.file);
fsnotify_modify(out.file);
out.file->f_pos = out_pos;
if (ppos)
*ppos = pos;
else
in.file->f_pos = pos;
}
inc_syscr(current);
inc_syscw(current);
if (pos > max)
retval = -EOVERFLOW;
fput_out:
fdput(out);
fput_in:
fdput(in);
out:
return retval;
}
SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count)
{
loff_t pos;
off_t off;
ssize_t ret;
if (offset) {
if (unlikely(get_user(off, offset)))
return -EFAULT;
pos = off;
ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS);
if (unlikely(put_user(pos, offset)))
return -EFAULT;
return ret;
}
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count)
{
loff_t pos;
ssize_t ret;
if (offset) {
if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t))))
return -EFAULT;
ret = do_sendfile(out_fd, in_fd, &pos, count, 0);
if (unlikely(put_user(pos, offset)))
return -EFAULT;
return ret;
}
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd,
compat_off_t __user *, offset, compat_size_t, count)
{
loff_t pos;
off_t off;
ssize_t ret;
if (offset) {
if (unlikely(get_user(off, offset)))
return -EFAULT;
pos = off;
ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS);
if (unlikely(put_user(pos, offset)))
return -EFAULT;
return ret;
}
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
compat_loff_t __user *, offset, compat_size_t, count)
{
loff_t pos;
ssize_t ret;
if (offset) {
if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t))))
return -EFAULT;
ret = do_sendfile(out_fd, in_fd, &pos, count, 0);
if (unlikely(put_user(pos, offset)))
return -EFAULT;
return ret;
}
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
#endif
/*
* copy_file_range() differs from regular file read and write in that it
* specifically allows return partial success. When it does so is up to
* the copy_file_range method.
*/
ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t len, unsigned int flags)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
ssize_t ret;
if (flags != 0)
return -EINVAL;
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
ret = rw_verify_area(READ, file_in, &pos_in, len);
if (unlikely(ret))
return ret;
ret = rw_verify_area(WRITE, file_out, &pos_out, len);
if (unlikely(ret))
return ret;
if (!(file_in->f_mode & FMODE_READ) ||
!(file_out->f_mode & FMODE_WRITE) ||
(file_out->f_flags & O_APPEND))
return -EBADF;
/* this could be relaxed once a method supports cross-fs copies */
if (inode_in->i_sb != inode_out->i_sb)
return -EXDEV;
if (len == 0)
return 0;
file_start_write(file_out);
/*
* Try cloning first, this is supported by more file systems, and
* more efficient if both clone and copy are supported (e.g. NFS).
*/
if (file_in->f_op->clone_file_range) {
ret = file_in->f_op->clone_file_range(file_in, pos_in,
file_out, pos_out, len);
if (ret == 0) {
ret = len;
goto done;
}
}
if (file_out->f_op->copy_file_range) {
ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
pos_out, len, flags);
if (ret != -EOPNOTSUPP)
goto done;
}
ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
done:
if (ret > 0) {
fsnotify_access(file_in);
add_rchar(current, ret);
fsnotify_modify(file_out);
add_wchar(current, ret);
}
inc_syscr(current);
inc_syscw(current);
file_end_write(file_out);
return ret;
}
EXPORT_SYMBOL(vfs_copy_file_range);
SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
int, fd_out, loff_t __user *, off_out,
size_t, len, unsigned int, flags)
{
loff_t pos_in;
loff_t pos_out;
struct fd f_in;
struct fd f_out;
ssize_t ret = -EBADF;
f_in = fdget(fd_in);
if (!f_in.file)
goto out2;
f_out = fdget(fd_out);
if (!f_out.file)
goto out1;
ret = -EFAULT;
if (off_in) {
if (copy_from_user(&pos_in, off_in, sizeof(loff_t)))
goto out;
} else {
pos_in = f_in.file->f_pos;
}
if (off_out) {
if (copy_from_user(&pos_out, off_out, sizeof(loff_t)))
goto out;
} else {
pos_out = f_out.file->f_pos;
}
ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len,
flags);
if (ret > 0) {
pos_in += ret;
pos_out += ret;
if (off_in) {
if (copy_to_user(off_in, &pos_in, sizeof(loff_t)))
ret = -EFAULT;
} else {
f_in.file->f_pos = pos_in;
}
if (off_out) {
if (copy_to_user(off_out, &pos_out, sizeof(loff_t)))
ret = -EFAULT;
} else {
f_out.file->f_pos = pos_out;
}
}
out:
fdput(f_out);
out1:
fdput(f_in);
out2:
return ret;
}
static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
{
struct inode *inode = file_inode(file);
if (unlikely(pos < 0))
return -EINVAL;
if (unlikely((loff_t) (pos + len) < 0))
return -EINVAL;
if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
loff_t end = len ? pos + len - 1 : OFFSET_MAX;
int retval;
retval = locks_mandatory_area(inode, file, pos, end,
write ? F_WRLCK : F_RDLCK);
if (retval < 0)
return retval;
}
return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
}
/*
* Check that the two inodes are eligible for cloning, the ranges make
* sense, and then flush all dirty data. Caller must ensure that the
* inodes have been locked against any other modifications.
*
* Returns: 0 for "nothing to clone", 1 for "something to clone", or
* the usual negative error code.
*/
int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
struct inode *inode_out, loff_t pos_out,
u64 *len, bool is_dedupe)
{
loff_t bs = inode_out->i_sb->s_blocksize;
loff_t blen;
loff_t isize;
bool same_inode = (inode_in == inode_out);
int ret;
/* Don't touch certain kinds of inodes */
if (IS_IMMUTABLE(inode_out))
return -EPERM;
if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
return -ETXTBSY;
/* Don't reflink dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/* Are we going all the way to the end? */
isize = i_size_read(inode_in);
if (isize == 0)
return 0;
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (*len == 0) {
if (is_dedupe || pos_in == isize)
return 0;
if (pos_in > isize)
return -EINVAL;
*len = isize - pos_in;
}
/* Ensure offsets don't wrap and the input is inside i_size */
if (pos_in + *len < pos_in || pos_out + *len < pos_out ||
pos_in + *len > isize)
return -EINVAL;
/* Don't allow dedupe past EOF in the dest file */
if (is_dedupe) {
loff_t disize;
disize = i_size_read(inode_out);
if (pos_out >= disize || pos_out + *len > disize)
return -EINVAL;
}
/* If we're linking to EOF, continue to the block boundary. */
if (pos_in + *len == isize)
blen = ALIGN(isize, bs) - pos_in;
else
blen = *len;
/* Only reflink if we're aligned to block boundaries */
if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
!IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
return -EINVAL;
/* Don't allow overlapped reflink within the same file */
if (same_inode) {
if (pos_out + blen > pos_in && pos_out < pos_in + blen)
return -EINVAL;
}
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
ret = filemap_write_and_wait_range(inode_in->i_mapping,
pos_in, pos_in + *len - 1);
if (ret)
return ret;
ret = filemap_write_and_wait_range(inode_out->i_mapping,
pos_out, pos_out + *len - 1);
if (ret)
return ret;
/*
* Check that the extents are the same.
*/
if (is_dedupe) {
bool is_same = false;
ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
inode_out, pos_out, *len, &is_same);
if (ret)
return ret;
if (!is_same)
return -EBADE;
}
return 1;
}
EXPORT_SYMBOL(vfs_clone_file_prep_inodes);
int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out, u64 len)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
int ret;
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/*
* FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
* the same mount. Practically, they only need to be on the same file
* system.
*/
if (inode_in->i_sb != inode_out->i_sb)
return -EXDEV;
if (!(file_in->f_mode & FMODE_READ) ||
!(file_out->f_mode & FMODE_WRITE) ||
(file_out->f_flags & O_APPEND))
return -EBADF;
if (!file_in->f_op->clone_file_range)
return -EOPNOTSUPP;
ret = clone_verify_area(file_in, pos_in, len, false);
if (ret)
return ret;
ret = clone_verify_area(file_out, pos_out, len, true);
if (ret)
return ret;
if (pos_in + len > i_size_read(inode_in))
return -EINVAL;
ret = file_in->f_op->clone_file_range(file_in, pos_in,
file_out, pos_out, len);
if (!ret) {
fsnotify_access(file_in);
fsnotify_modify(file_out);
}
return ret;
}
EXPORT_SYMBOL(vfs_clone_file_range);
/*
* Read a page's worth of file data into the page cache. Return the page
* locked.
*/
static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
{
struct address_space *mapping;
struct page *page;
pgoff_t n;
n = offset >> PAGE_SHIFT;
mapping = inode->i_mapping;
page = read_mapping_page(mapping, n, NULL);
if (IS_ERR(page))
return page;
if (!PageUptodate(page)) {
put_page(page);
return ERR_PTR(-EIO);
}
lock_page(page);
return page;
}
/*
* Compare extents of two files to see if they are the same.
* Caller must have locked both inodes to prevent write races.
*/
int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
struct inode *dest, loff_t destoff,
loff_t len, bool *is_same)
{
loff_t src_poff;
loff_t dest_poff;
void *src_addr;
void *dest_addr;
struct page *src_page;
struct page *dest_page;
loff_t cmp_len;
bool same;
int error;
error = -EINVAL;
same = true;
while (len) {
src_poff = srcoff & (PAGE_SIZE - 1);
dest_poff = destoff & (PAGE_SIZE - 1);
cmp_len = min(PAGE_SIZE - src_poff,
PAGE_SIZE - dest_poff);
cmp_len = min(cmp_len, len);
if (cmp_len <= 0)
goto out_error;
src_page = vfs_dedupe_get_page(src, srcoff);
if (IS_ERR(src_page)) {
error = PTR_ERR(src_page);
goto out_error;
}
dest_page = vfs_dedupe_get_page(dest, destoff);
if (IS_ERR(dest_page)) {
error = PTR_ERR(dest_page);
unlock_page(src_page);
put_page(src_page);
goto out_error;
}
src_addr = kmap_atomic(src_page);
dest_addr = kmap_atomic(dest_page);
flush_dcache_page(src_page);
flush_dcache_page(dest_page);
if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
same = false;
kunmap_atomic(dest_addr);
kunmap_atomic(src_addr);
unlock_page(dest_page);
unlock_page(src_page);
put_page(dest_page);
put_page(src_page);
if (!same)
break;
srcoff += cmp_len;
destoff += cmp_len;
len -= cmp_len;
}
*is_same = same;
return 0;
out_error:
return error;
}
EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
{
struct file_dedupe_range_info *info;
struct inode *src = file_inode(file);
u64 off;
u64 len;
int i;
int ret;
bool is_admin = capable(CAP_SYS_ADMIN);
u16 count = same->dest_count;
struct file *dst_file;
loff_t dst_off;
ssize_t deduped;
if (!(file->f_mode & FMODE_READ))
return -EINVAL;
if (same->reserved1 || same->reserved2)
return -EINVAL;
off = same->src_offset;
len = same->src_length;
ret = -EISDIR;
if (S_ISDIR(src->i_mode))
goto out;
ret = -EINVAL;
if (!S_ISREG(src->i_mode))
goto out;
ret = clone_verify_area(file, off, len, false);
if (ret < 0)
goto out;
ret = 0;
if (off + len > i_size_read(src))
return -EINVAL;
/* pre-format output fields to sane values */
for (i = 0; i < count; i++) {
same->info[i].bytes_deduped = 0ULL;
same->info[i].status = FILE_DEDUPE_RANGE_SAME;
}
for (i = 0, info = same->info; i < count; i++, info++) {
struct inode *dst;
struct fd dst_fd = fdget(info->dest_fd);
dst_file = dst_fd.file;
if (!dst_file) {
info->status = -EBADF;
goto next_loop;
}
dst = file_inode(dst_file);
ret = mnt_want_write_file(dst_file);
if (ret) {
info->status = ret;
goto next_loop;
}
dst_off = info->dest_offset;
ret = clone_verify_area(dst_file, dst_off, len, true);
if (ret < 0) {
info->status = ret;
goto next_file;
}
ret = 0;
if (info->reserved) {
info->status = -EINVAL;
} else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
info->status = -EINVAL;
} else if (file->f_path.mnt != dst_file->f_path.mnt) {
info->status = -EXDEV;
} else if (S_ISDIR(dst->i_mode)) {
info->status = -EISDIR;
} else if (dst_file->f_op->dedupe_file_range == NULL) {
info->status = -EINVAL;
} else {
deduped = dst_file->f_op->dedupe_file_range(file, off,
len, dst_file,
info->dest_offset);
if (deduped == -EBADE)
info->status = FILE_DEDUPE_RANGE_DIFFERS;
else if (deduped < 0)
info->status = deduped;
else
info->bytes_deduped += deduped;
}
next_file:
mnt_drop_write_file(dst_file);
next_loop:
fdput(dst_fd);
if (fatal_signal_pending(current))
goto out;
}
out:
return ret;
}
EXPORT_SYMBOL(vfs_dedupe_file_range);